1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 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, 2018 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
13 ;;; This file is part of GNU Guix.
15 ;;; GNU Guix is free software; you can redistribute it and/or modify it
16 ;;; under the terms of the GNU General Public License as published by
17 ;;; the Free Software Foundation; either version 3 of the License, or (at
18 ;;; your option) any later version.
20 ;;; GNU Guix is distributed in the hope that it will be useful, but
21 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
22 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23 ;;; GNU General Public License for more details.
25 ;;; You should have received a copy of the GNU General Public License
26 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
28 (define-module (gnu packages bioinformatics)
29 #:use-module ((guix licenses) #:prefix license:)
30 #:use-module (guix packages)
31 #:use-module (guix utils)
32 #:use-module (guix download)
33 #:use-module (guix git-download)
34 #:use-module (guix hg-download)
35 #:use-module (guix build-system ant)
36 #:use-module (guix build-system gnu)
37 #:use-module (guix build-system cmake)
38 #:use-module (guix build-system ocaml)
39 #:use-module (guix build-system perl)
40 #:use-module (guix build-system python)
41 #:use-module (guix build-system r)
42 #:use-module (guix build-system ruby)
43 #:use-module (guix build-system scons)
44 #:use-module (guix build-system trivial)
45 #:use-module (gnu packages)
46 #:use-module (gnu packages autotools)
47 #:use-module (gnu packages algebra)
48 #:use-module (gnu packages base)
49 #:use-module (gnu packages bash)
50 #:use-module (gnu packages bison)
51 #:use-module (gnu packages boost)
52 #:use-module (gnu packages check)
53 #:use-module (gnu packages compression)
54 #:use-module (gnu packages cpio)
55 #:use-module (gnu packages cran)
56 #:use-module (gnu packages curl)
57 #:use-module (gnu packages documentation)
58 #:use-module (gnu packages databases)
59 #:use-module (gnu packages datastructures)
60 #:use-module (gnu packages file)
61 #:use-module (gnu packages flex)
62 #:use-module (gnu packages gawk)
63 #:use-module (gnu packages gcc)
64 #:use-module (gnu packages gd)
65 #:use-module (gnu packages gtk)
66 #:use-module (gnu packages glib)
67 #:use-module (gnu packages graph)
68 #:use-module (gnu packages groff)
69 #:use-module (gnu packages guile)
70 #:use-module (gnu packages haskell)
71 #:use-module (gnu packages image)
72 #:use-module (gnu packages imagemagick)
73 #:use-module (gnu packages java)
74 #:use-module (gnu packages jemalloc)
75 #:use-module (gnu packages ldc)
76 #:use-module (gnu packages linux)
77 #:use-module (gnu packages logging)
78 #:use-module (gnu packages machine-learning)
79 #:use-module (gnu packages man)
80 #:use-module (gnu packages maths)
81 #:use-module (gnu packages mpi)
82 #:use-module (gnu packages ncurses)
83 #:use-module (gnu packages ocaml)
84 #:use-module (gnu packages pcre)
85 #:use-module (gnu packages parallel)
86 #:use-module (gnu packages pdf)
87 #:use-module (gnu packages perl)
88 #:use-module (gnu packages perl-check)
89 #:use-module (gnu packages pkg-config)
90 #:use-module (gnu packages popt)
91 #:use-module (gnu packages protobuf)
92 #:use-module (gnu packages python)
93 #:use-module (gnu packages python-web)
94 #:use-module (gnu packages readline)
95 #:use-module (gnu packages ruby)
96 #:use-module (gnu packages serialization)
97 #:use-module (gnu packages shells)
98 #:use-module (gnu packages statistics)
99 #:use-module (gnu packages swig)
100 #:use-module (gnu packages tbb)
101 #:use-module (gnu packages tex)
102 #:use-module (gnu packages texinfo)
103 #:use-module (gnu packages textutils)
104 #:use-module (gnu packages time)
105 #:use-module (gnu packages tls)
106 #:use-module (gnu packages vim)
107 #:use-module (gnu packages web)
108 #:use-module (gnu packages xml)
109 #:use-module (gnu packages xorg)
110 #:use-module (srfi srfi-1)
111 #:use-module (ice-9 match))
120 (uri (cran-uri "ape" version))
123 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
124 (build-system r-build-system)
126 `(("r-lattice" ,r-lattice)
129 (home-page "http://ape-package.ird.fr/")
130 (synopsis "Analyses of phylogenetics and evolution")
132 "This package provides functions for reading, writing, plotting, and
133 manipulating phylogenetic trees, analyses of comparative data in a
134 phylogenetic framework, ancestral character analyses, analyses of
135 diversification and macroevolution, computing distances from DNA sequences,
136 and several other tools.")
137 (license license:gpl2+)))
139 (define-public aragorn
146 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
150 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
151 (build-system gnu-build-system)
153 `(#:tests? #f ; there are no tests
155 (modify-phases %standard-phases
159 (zero? (system* "gcc"
165 (string-append "aragorn" ,version ".c")))))
167 (lambda* (#:key outputs #:allow-other-keys)
168 (let* ((out (assoc-ref outputs "out"))
169 (bin (string-append out "/bin"))
170 (man (string-append out "/share/man/man1")))
172 (install-file "aragorn" bin)
174 (install-file "aragorn.1" man))
176 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
177 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
179 "Aragorn identifies transfer RNA, mitochondrial RNA and
180 transfer-messenger RNA from nucleotide sequences, based on homology to known
181 tRNA consensus sequences and RNA structure. It also outputs the secondary
182 structure of the predicted RNA.")
183 (license license:gpl2)))
191 ;; BamM is not available on pypi.
193 "https://github.com/Ecogenomics/BamM/archive/"
195 (file-name (string-append name "-" version ".tar.gz"))
198 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
199 (modules '((guix build utils)))
202 ;; Delete bundled htslib.
203 (delete-file-recursively "c/htslib-1.3.1")
205 (build-system python-build-system)
207 `(#:python ,python-2 ; BamM is Python 2 only.
208 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
209 ;; been modified from its original form.
211 (let ((htslib (assoc-ref %build-inputs "htslib")))
212 (list "--with-libhts-lib" (string-append htslib "/lib")
213 "--with-libhts-inc" (string-append htslib "/include/htslib")))
215 (modify-phases %standard-phases
216 (add-after 'unpack 'autogen
218 (with-directory-excursion "c"
219 (let ((sh (which "sh")))
220 ;; Use autogen so that 'configure' works.
221 (substitute* "autogen.sh" (("/bin/sh") sh))
222 (setenv "CONFIG_SHELL" sh)
223 (substitute* "configure" (("/bin/sh") sh))
224 (zero? (system* "./autogen.sh"))))))
226 ;; Run tests after installation so compilation only happens once.
228 (add-after 'install 'wrap-executable
229 (lambda* (#:key outputs #:allow-other-keys)
230 (let* ((out (assoc-ref outputs "out"))
231 (path (getenv "PATH")))
232 (wrap-program (string-append out "/bin/bamm")
233 `("PATH" ":" prefix (,path))))
235 (add-after 'wrap-executable 'post-install-check
236 (lambda* (#:key inputs outputs #:allow-other-keys)
238 (string-append (assoc-ref outputs "out")
243 (assoc-ref outputs "out")
245 (string-take (string-take-right
246 (assoc-ref inputs "python") 5) 3)
248 (getenv "PYTHONPATH")))
249 ;; There are 2 errors printed, but they are safe to ignore:
250 ;; 1) [E::hts_open_format] fail to open file ...
251 ;; 2) samtools view: failed to open ...
252 (zero? (system* "nosetests")))))))
254 `(("autoconf" ,autoconf)
255 ("automake" ,automake)
258 ("python-nose" ,python2-nose)
259 ("python-pysam" ,python2-pysam)))
261 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
262 ("samtools" ,samtools)
266 ("coreutils" ,coreutils)))
268 `(("python-numpy" ,python2-numpy)))
269 (home-page "http://ecogenomics.github.io/BamM/")
270 (synopsis "Metagenomics-focused BAM file manipulator")
272 "BamM is a C library, wrapped in python, to efficiently generate and
273 parse BAM files, specifically for the analysis of metagenomic data. For
274 instance, it implements several methods to assess contig-wise read coverage.")
275 (license license:lgpl3+)))
277 (define-public bamtools
284 "https://github.com/pezmaster31/bamtools/archive/v"
286 (file-name (string-append name "-" version ".tar.gz"))
289 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
290 (build-system cmake-build-system)
292 `(#:tests? #f ;no "check" target
294 (modify-phases %standard-phases
296 'configure 'set-ldflags
297 (lambda* (#:key outputs #:allow-other-keys)
301 (assoc-ref outputs "out") "/lib/bamtools")))))))
302 (inputs `(("zlib" ,zlib)))
303 (home-page "https://github.com/pezmaster31/bamtools")
304 (synopsis "C++ API and command-line toolkit for working with BAM data")
306 "BamTools provides both a C++ API and a command-line toolkit for handling
308 (license license:expat)))
310 (define-public bcftools
317 "https://github.com/samtools/bcftools/releases/download/"
318 version "/bcftools-" version ".tar.bz2"))
321 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
322 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
323 (modules '((guix build utils)))
325 ;; Delete bundled htslib.
326 '(delete-file-recursively "htslib-1.5"))))
327 (build-system gnu-build-system)
329 `(#:test-target "test"
330 #:configure-flags (list "--with-htslib=system")
334 "LIBS=-lgsl -lgslcblas"
335 (string-append "prefix=" (assoc-ref %outputs "out"))
336 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
337 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
338 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
339 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
340 (string-append "PACKAGE_VERSION=" ,version))
342 (modify-phases %standard-phases
343 (add-before 'check 'patch-tests
345 (substitute* "test/test.pl"
346 (("/bin/bash") (which "bash")))
354 (home-page "https://samtools.github.io/bcftools/")
355 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
357 "BCFtools is a set of utilities that manipulate variant calls in the
358 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
359 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
360 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
361 (license (list license:gpl3+ license:expat))))
363 (define-public bedops
369 (uri (string-append "https://github.com/bedops/bedops/archive/v"
371 (file-name (string-append name "-" version ".tar.gz"))
374 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
375 (build-system gnu-build-system)
378 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
380 (modify-phases %standard-phases
381 (add-after 'unpack 'unpack-tarballs
383 ;; FIXME: Bedops includes tarballs of minimally patched upstream
384 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
385 ;; libraries because at least one of the libraries (zlib) is
386 ;; patched to add a C++ function definition (deflateInit2cpp).
387 ;; Until the Bedops developers offer a way to link against system
388 ;; libraries we have to build the in-tree copies of these three
391 ;; See upstream discussion:
392 ;; https://github.com/bedops/bedops/issues/124
394 ;; Unpack the tarballs to benefit from shebang patching.
395 (with-directory-excursion "third-party"
396 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
397 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
398 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
399 ;; Disable unpacking of tarballs in Makefile.
400 (substitute* "system.mk/Makefile.linux"
401 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
402 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
403 (substitute* "third-party/zlib-1.2.7/Makefile.in"
404 (("^SHELL=.*$") "SHELL=bash\n"))
406 (delete 'configure))))
407 (home-page "https://github.com/bedops/bedops")
408 (synopsis "Tools for high-performance genomic feature operations")
410 "BEDOPS is a suite of tools to address common questions raised in genomic
411 studies---mostly with regard to overlap and proximity relationships between
412 data sets. It aims to be scalable and flexible, facilitating the efficient
413 and accurate analysis and management of large-scale genomic data.
415 BEDOPS provides tools that perform highly efficient and scalable Boolean and
416 other set operations, statistical calculations, archiving, conversion and
417 other management of genomic data of arbitrary scale. Tasks can be easily
418 split by chromosome for distributing whole-genome analyses across a
419 computational cluster.")
420 (license license:gpl2+)))
422 (define-public bedtools
428 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
429 "download/v" version "/"
430 "bedtools-" version ".tar.gz"))
433 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
434 (build-system gnu-build-system)
436 '(#:test-target "test"
438 (list (string-append "prefix=" (assoc-ref %outputs "out")))
440 (modify-phases %standard-phases
441 (delete 'configure))))
442 (native-inputs `(("python" ,python-2)))
444 `(("samtools" ,samtools)
446 (home-page "https://github.com/arq5x/bedtools2")
447 (synopsis "Tools for genome analysis and arithmetic")
449 "Collectively, the bedtools utilities are a swiss-army knife of tools for
450 a wide-range of genomics analysis tasks. The most widely-used tools enable
451 genome arithmetic: that is, set theory on the genome. For example, bedtools
452 allows one to intersect, merge, count, complement, and shuffle genomic
453 intervals from multiple files in widely-used genomic file formats such as BAM,
455 (license license:gpl2)))
457 ;; Later releases of bedtools produce files with more columns than
458 ;; what Ribotaper expects.
459 (define-public bedtools-2.18
460 (package (inherit bedtools)
465 (uri (string-append "https://github.com/arq5x/bedtools2/"
466 "archive/v" version ".tar.gz"))
467 (file-name (string-append name "-" version ".tar.gz"))
470 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
472 '(#:test-target "test"
474 (modify-phases %standard-phases
477 (lambda* (#:key outputs #:allow-other-keys)
478 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
479 (for-each (lambda (file)
480 (install-file file bin))
481 (find-files "bin" ".*")))
484 (define-public ribotaper
490 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
491 "files/RiboTaper/RiboTaper_Version_"
495 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
496 (build-system gnu-build-system)
499 (modify-phases %standard-phases
500 (add-after 'install 'wrap-executables
501 (lambda* (#:key inputs outputs #:allow-other-keys)
502 (let* ((out (assoc-ref outputs "out")))
505 (wrap-program (string-append out "/bin/" script)
506 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
507 '("create_annotations_files.bash"
508 "create_metaplots.bash"
509 "Ribotaper_ORF_find.sh"
510 "Ribotaper.sh"))))))))
512 `(("bedtools" ,bedtools-2.18)
513 ("samtools" ,samtools-0.1)
514 ("r-minimal" ,r-minimal)
515 ("r-foreach" ,r-foreach)
516 ("r-xnomial" ,r-xnomial)
518 ("r-multitaper" ,r-multitaper)
519 ("r-seqinr" ,r-seqinr)))
520 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
521 (synopsis "Define translated ORFs using ribosome profiling data")
523 "Ribotaper is a method for defining translated @dfn{open reading
524 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
525 provides the Ribotaper pipeline.")
526 (license license:gpl3+)))
528 (define-public ribodiff
535 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
536 "archive/v" version ".tar.gz"))
537 (file-name (string-append name "-" version ".tar.gz"))
540 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
541 (build-system python-build-system)
545 (modify-phases %standard-phases
546 ;; Generate an installable executable script wrapper.
547 (add-after 'unpack 'patch-setup.py
549 (substitute* "setup.py"
550 (("^(.*)packages=.*" line prefix)
551 (string-append line "\n"
552 prefix "scripts=['scripts/TE.py'],\n")))
555 `(("python-numpy" ,python2-numpy)
556 ("python-matplotlib" ,python2-matplotlib)
557 ("python-scipy" ,python2-scipy)
558 ("python-statsmodels" ,python2-statsmodels)))
560 `(("python-mock" ,python2-mock)
561 ("python-nose" ,python2-nose)))
562 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
563 (synopsis "Detect translation efficiency changes from ribosome footprints")
564 (description "RiboDiff is a statistical tool that detects the protein
565 translational efficiency change from Ribo-Seq (ribosome footprinting) and
566 RNA-Seq data. It uses a generalized linear model to detect genes showing
567 difference in translational profile taking mRNA abundance into account. It
568 facilitates us to decipher the translational regulation that behave
569 independently with transcriptional regulation.")
570 (license license:gpl3+)))
572 (define-public bioawk
578 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
580 (file-name (string-append name "-" version ".tar.gz"))
582 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
583 (build-system gnu-build-system)
589 `(#:tests? #f ; There are no tests to run.
590 ;; Bison must generate files, before other targets can build.
593 (modify-phases %standard-phases
594 (delete 'configure) ; There is no configure phase.
596 (lambda* (#:key outputs #:allow-other-keys)
597 (let* ((out (assoc-ref outputs "out"))
598 (bin (string-append out "/bin"))
599 (man (string-append out "/share/man/man1")))
601 (copy-file "awk.1" (string-append man "/bioawk.1"))
602 (install-file "bioawk" bin)))))))
603 (home-page "https://github.com/lh3/bioawk")
604 (synopsis "AWK with bioinformatics extensions")
605 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
606 support of several common biological data formats, including optionally gzip'ed
607 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
608 also adds a few built-in functions and a command line option to use TAB as the
609 input/output delimiter. When the new functionality is not used, bioawk is
610 intended to behave exactly the same as the original BWK awk.")
611 (license license:x11)))
613 (define-public python2-pybedtools
615 (name "python2-pybedtools")
620 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
624 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
625 (build-system python-build-system)
626 (arguments `(#:python ,python-2)) ; no Python 3 support
628 `(("python-matplotlib" ,python2-matplotlib)))
630 `(("bedtools" ,bedtools)
631 ("samtools" ,samtools)))
633 `(("python-cython" ,python2-cython)
634 ("python-pyyaml" ,python2-pyyaml)
635 ("python-nose" ,python2-nose)))
636 (home-page "https://pythonhosted.org/pybedtools/")
637 (synopsis "Python wrapper for BEDtools programs")
639 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
640 which are widely used for genomic interval manipulation or \"genome algebra\".
641 pybedtools extends BEDTools by offering feature-level manipulations from with
643 (license license:gpl2+)))
645 (define-public python-biom-format
647 (name "python-biom-format")
652 ;; Use GitHub as source because PyPI distribution does not contain
653 ;; test data: https://github.com/biocore/biom-format/issues/693
654 (uri (string-append "https://github.com/biocore/biom-format/archive/"
656 (file-name (string-append name "-" version ".tar.gz"))
659 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
660 (build-system python-build-system)
662 `(("python-numpy" ,python-numpy)
663 ("python-scipy" ,python-scipy)
664 ("python-future" ,python-future)
665 ("python-click" ,python-click)
666 ("python-h5py" ,python-h5py)
667 ("python-pandas" ,python-pandas)))
669 `(("python-nose" ,python-nose)))
670 (home-page "http://www.biom-format.org")
671 (synopsis "Biological Observation Matrix (BIOM) format utilities")
673 "The BIOM file format is designed to be a general-use format for
674 representing counts of observations e.g. operational taxonomic units, KEGG
675 orthology groups or lipid types, in one or more biological samples
676 e.g. microbiome samples, genomes, metagenomes.")
677 (license license:bsd-3)
678 (properties `((python2-variant . ,(delay python2-biom-format))))))
680 (define-public python2-biom-format
681 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
686 (modify-phases %standard-phases
687 ;; Do not require the unmaintained pyqi library.
688 (add-after 'unpack 'remove-pyqi
690 (substitute* "setup.py"
691 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
693 ,@(package-arguments base))))))
695 (define-public bioperl-minimal
696 (let* ((inputs `(("perl-module-build" ,perl-module-build)
697 ("perl-data-stag" ,perl-data-stag)
698 ("perl-libwww" ,perl-libwww)
699 ("perl-uri" ,perl-uri)))
701 (map (compose package-name cadr)
704 (map (compose package-transitive-target-inputs cadr) inputs))))))
706 (name "bioperl-minimal")
711 (uri (string-append "https://github.com/bioperl/bioperl-live/"
713 (string-map (lambda (c)
719 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
720 (build-system perl-build-system)
723 (modify-phases %standard-phases
725 'install 'wrap-programs
726 (lambda* (#:key outputs #:allow-other-keys)
727 ;; Make sure all executables in "bin" find the required Perl
728 ;; modules at runtime. As the PERL5LIB variable contains also
729 ;; the paths of native inputs, we pick the transitive target
730 ;; inputs from %build-inputs.
731 (let* ((out (assoc-ref outputs "out"))
732 (bin (string-append out "/bin/"))
734 (cons (string-append out "/lib/perl5/site_perl")
736 (assoc-ref %build-inputs name))
737 ',transitive-inputs))
739 (for-each (lambda (file)
741 `("PERL5LIB" ":" prefix (,path))))
742 (find-files bin "\\.pl$"))
746 `(("perl-test-most" ,perl-test-most)))
747 (home-page "http://search.cpan.org/dist/BioPerl")
748 (synopsis "Bioinformatics toolkit")
750 "BioPerl is the product of a community effort to produce Perl code which
751 is useful in biology. Examples include Sequence objects, Alignment objects
752 and database searching objects. These objects not only do what they are
753 advertised to do in the documentation, but they also interact - Alignment
754 objects are made from the Sequence objects, Sequence objects have access to
755 Annotation and SeqFeature objects and databases, Blast objects can be
756 converted to Alignment objects, and so on. This means that the objects
757 provide a coordinated and extensible framework to do computational biology.")
758 (license license:perl-license))))
760 (define-public python-biopython
762 (name "python-biopython")
766 ;; use PyPi rather than biopython.org to ease updating
767 (uri (pypi-uri "biopython" version))
770 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
771 (build-system python-build-system)
774 (modify-phases %standard-phases
775 (add-before 'check 'set-home
776 ;; Some tests require a home directory to be set.
777 (lambda _ (setenv "HOME" "/tmp") #t)))))
779 `(("python-numpy" ,python-numpy)))
780 (home-page "http://biopython.org/")
781 (synopsis "Tools for biological computation in Python")
783 "Biopython is a set of tools for biological computation including parsers
784 for bioinformatics files into Python data structures; interfaces to common
785 bioinformatics programs; a standard sequence class and tools for performing
786 common operations on them; code to perform data classification; code for
787 dealing with alignments; code making it easy to split up parallelizable tasks
788 into separate processes; and more.")
789 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
791 (define-public python2-biopython
792 (package-with-python2 python-biopython))
794 (define-public bpp-core
795 ;; The last release was in 2014 and the recommended way to install from source
796 ;; is to clone the git repository, so we do this.
797 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
798 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
801 (version (string-append "2.2.0-1." (string-take commit 7)))
805 (url "http://biopp.univ-montp2.fr/git/bpp-core")
807 (file-name (string-append name "-" version "-checkout"))
810 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
811 (build-system cmake-build-system)
813 `(#:parallel-build? #f))
815 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
816 ; compile all of the bpp packages with GCC 5.
817 (home-page "http://biopp.univ-montp2.fr")
818 (synopsis "C++ libraries for Bioinformatics")
820 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
821 analysis, phylogenetics, molecular evolution and population genetics. It is
822 Object Oriented and is designed to be both easy to use and computer efficient.
823 Bio++ intends to help programmers to write computer expensive programs, by
824 providing them a set of re-usable tools.")
825 (license license:cecill-c))))
827 (define-public bpp-phyl
828 ;; The last release was in 2014 and the recommended way to install from source
829 ;; is to clone the git repository, so we do this.
830 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
831 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
834 (version (string-append "2.2.0-1." (string-take commit 7)))
838 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
840 (file-name (string-append name "-" version "-checkout"))
843 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
844 (build-system cmake-build-system)
846 `(#:parallel-build? #f
847 ;; If out-of-source, test data is not copied into the build directory
848 ;; so the tests fail.
849 #:out-of-source? #f))
851 `(("bpp-core" ,bpp-core)
853 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
856 (home-page "http://biopp.univ-montp2.fr")
857 (synopsis "Bio++ phylogenetic Library")
859 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
860 analysis, phylogenetics, molecular evolution and population genetics. This
861 library provides phylogenetics-related modules.")
862 (license license:cecill-c))))
864 (define-public bpp-popgen
865 ;; The last release was in 2014 and the recommended way to install from source
866 ;; is to clone the git repository, so we do this.
867 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
868 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
871 (version (string-append "2.2.0-1." (string-take commit 7)))
875 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
877 (file-name (string-append name "-" version "-checkout"))
880 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
881 (build-system cmake-build-system)
883 `(#:parallel-build? #f
884 #:tests? #f)) ; There are no tests.
886 `(("bpp-core" ,bpp-core)
889 (home-page "http://biopp.univ-montp2.fr")
890 (synopsis "Bio++ population genetics library")
892 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
893 analysis, phylogenetics, molecular evolution and population genetics. This
894 library provides population genetics-related modules.")
895 (license license:cecill-c))))
897 (define-public bpp-seq
898 ;; The last release was in 2014 and the recommended way to install from source
899 ;; is to clone the git repository, so we do this.
900 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
901 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
904 (version (string-append "2.2.0-1." (string-take commit 7)))
908 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
910 (file-name (string-append name "-" version "-checkout"))
913 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
914 (build-system cmake-build-system)
916 `(#:parallel-build? #f
917 ;; If out-of-source, test data is not copied into the build directory
918 ;; so the tests fail.
919 #:out-of-source? #f))
921 `(("bpp-core" ,bpp-core)
922 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
923 (home-page "http://biopp.univ-montp2.fr")
924 (synopsis "Bio++ sequence library")
926 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
927 analysis, phylogenetics, molecular evolution and population genetics. This
928 library provides sequence-related modules.")
929 (license license:cecill-c))))
931 (define-public bppsuite
932 ;; The last release was in 2014 and the recommended way to install from source
933 ;; is to clone the git repository, so we do this.
934 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
935 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
938 (version (string-append "2.2.0-1." (string-take commit 7)))
942 (url "http://biopp.univ-montp2.fr/git/bppsuite")
944 (file-name (string-append name "-" version "-checkout"))
947 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
948 (build-system cmake-build-system)
950 `(#:parallel-build? #f
951 #:tests? #f)) ; There are no tests.
955 ("texinfo" ,texinfo)))
957 `(("bpp-core" ,bpp-core)
959 ("bpp-phyl" ,bpp-phyl)
960 ("bpp-phyl" ,bpp-popgen)
962 (home-page "http://biopp.univ-montp2.fr")
963 (synopsis "Bioinformatics tools written with the Bio++ libraries")
965 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
966 analysis, phylogenetics, molecular evolution and population genetics. This
967 package provides command line tools using the Bio++ library.")
968 (license license:cecill-c))))
970 (define-public blast+
977 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
978 version "/ncbi-blast-" version "+-src.tar.gz"))
981 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
982 (patches (search-patches "blast+-fix-makefile.patch"))
983 (modules '((guix build utils)))
986 ;; Remove bundled bzip2, zlib and pcre.
987 (delete-file-recursively "c++/src/util/compress/bzip2")
988 (delete-file-recursively "c++/src/util/compress/zlib")
989 (delete-file-recursively "c++/src/util/regexp")
990 (substitute* "c++/src/util/compress/Makefile.in"
991 (("bzip2 zlib api") "api"))
992 ;; Remove useless msbuild directory
993 (delete-file-recursively
994 "c++/src/build-system/project_tree_builder/msbuild")
996 (build-system gnu-build-system)
998 `(;; There are two(!) tests for this massive library, and both fail with
999 ;; "unparsable timing stats".
1000 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1001 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1004 #:parallel-build? #f ; not supported
1006 (modify-phases %standard-phases
1008 'configure 'set-HOME
1009 ;; $HOME needs to be set at some point during the configure phase
1010 (lambda _ (setenv "HOME" "/tmp") #t))
1013 (lambda _ (chdir "c++") #t))
1015 'enter-dir 'fix-build-system
1017 (define (which* cmd)
1018 (cond ((string=? cmd "date")
1019 ;; make call to "date" deterministic
1024 (format (current-error-port)
1025 "WARNING: Unable to find absolute path for ~s~%"
1029 ;; Rewrite hardcoded paths to various tools
1030 (substitute* (append '("src/build-system/configure.ac"
1031 "src/build-system/configure"
1032 "src/build-system/helpers/run_with_lock.c"
1033 "scripts/common/impl/if_diff.sh"
1034 "scripts/common/impl/run_with_lock.sh"
1035 "src/build-system/Makefile.configurables.real"
1036 "src/build-system/Makefile.in.top"
1037 "src/build-system/Makefile.meta.gmake=no"
1038 "src/build-system/Makefile.meta.in"
1039 "src/build-system/Makefile.meta_l"
1040 "src/build-system/Makefile.meta_p"
1041 "src/build-system/Makefile.meta_r"
1042 "src/build-system/Makefile.mk.in"
1043 "src/build-system/Makefile.requirements"
1044 "src/build-system/Makefile.rules_with_autodep.in")
1045 (find-files "scripts/common/check" "\\.sh$"))
1046 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1047 (or (which* cmd) all)))
1049 (substitute* (find-files "src/build-system" "^config.*")
1050 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1053 ;; rewrite "/var/tmp" in check script
1054 (substitute* "scripts/common/check/check_make_unix.sh"
1055 (("/var/tmp") "/tmp"))
1057 ;; do not reset PATH
1058 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1060 (("action=/bin/") "action=")
1061 (("export PATH") ":"))
1065 (lambda* (#:key inputs outputs #:allow-other-keys)
1066 (let ((out (assoc-ref outputs "out"))
1067 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1068 (include (string-append (assoc-ref outputs "include")
1069 "/include/ncbi-tools++")))
1070 ;; The 'configure' script doesn't recognize things like
1071 ;; '--enable-fast-install'.
1072 (zero? (system* "./configure.orig"
1073 (string-append "--with-build-root=" (getcwd) "/build")
1074 (string-append "--prefix=" out)
1075 (string-append "--libdir=" lib)
1076 (string-append "--includedir=" include)
1077 (string-append "--with-bz2="
1078 (assoc-ref inputs "bzip2"))
1079 (string-append "--with-z="
1080 (assoc-ref inputs "zlib"))
1081 (string-append "--with-pcre="
1082 (assoc-ref inputs "pcre"))
1083 ;; Each library is built twice by default, once
1084 ;; with "-static" in its name, and again
1087 "--with-dll"))))))))
1088 (outputs '("out" ; 21 MB
1096 ("python" ,python-wrapper)))
1099 (home-page "http://blast.ncbi.nlm.nih.gov")
1100 (synopsis "Basic local alignment search tool")
1102 "BLAST is a popular method of performing a DNA or protein sequence
1103 similarity search, using heuristics to produce results quickly. It also
1104 calculates an “expect value” that estimates how many matches would have
1105 occurred at a given score by chance, which can aid a user in judging how much
1106 confidence to have in an alignment.")
1107 ;; Most of the sources are in the public domain, with the following
1110 ;; * ./c++/include/util/bitset/
1111 ;; * ./c++/src/html/ncbi_menu*.js
1113 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1115 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1117 ;; * ./c++/src/corelib/teamcity_*
1118 (license (list license:public-domain
1124 (define-public bless
1130 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1134 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1135 (modules '((guix build utils)))
1138 ;; Remove bundled boost, pigz, zlib, and .git directory
1139 ;; FIXME: also remove bundled sources for murmurhash3 and
1140 ;; kmc once packaged.
1141 (delete-file-recursively "boost")
1142 (delete-file-recursively "pigz")
1143 (delete-file-recursively "google-sparsehash")
1144 (delete-file-recursively "zlib")
1145 (delete-file-recursively ".git")
1147 (build-system gnu-build-system)
1149 '(#:tests? #f ;no "check" target
1151 (list (string-append "ZLIB="
1152 (assoc-ref %build-inputs "zlib")
1154 (string-append "LDFLAGS="
1155 (string-join '("-lboost_filesystem"
1162 (modify-phases %standard-phases
1163 (add-after 'unpack 'do-not-build-bundled-pigz
1164 (lambda* (#:key inputs outputs #:allow-other-keys)
1165 (substitute* "Makefile"
1166 (("cd pigz/pigz-2.3.3; make") ""))
1168 (add-after 'unpack 'patch-paths-to-executables
1169 (lambda* (#:key inputs outputs #:allow-other-keys)
1170 (substitute* "parse_args.cpp"
1171 (("kmc_binary = .*")
1172 (string-append "kmc_binary = \""
1173 (assoc-ref outputs "out")
1175 (("pigz_binary = .*")
1176 (string-append "pigz_binary = \""
1177 (assoc-ref inputs "pigz")
1181 (lambda* (#:key outputs #:allow-other-keys)
1182 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1183 (for-each (lambda (file)
1184 (install-file file bin))
1185 '("bless" "kmc/bin/kmc"))
1187 (delete 'configure))))
1191 `(("openmpi" ,openmpi)
1193 ("sparsehash" ,sparsehash)
1196 (supported-systems '("x86_64-linux"))
1197 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1198 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1200 "@dfn{Bloom-filter-based error correction solution for high-throughput
1201 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1202 correction tool for genomic reads produced by @dfn{Next-generation
1203 sequencing} (NGS). BLESS produces accurate correction results with much less
1204 memory compared with previous solutions and is also able to tolerate a higher
1205 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1206 errors at the end of reads.")
1207 (license license:gpl3+)))
1209 (define-public bowtie
1215 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1217 (file-name (string-append name "-" version ".tar.gz"))
1220 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1221 (modules '((guix build utils)))
1223 '(substitute* "Makefile"
1224 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1225 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1226 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1227 (build-system gnu-build-system)
1230 ("perl-clone" ,perl-clone)
1231 ("perl-test-deep" ,perl-test-deep)
1232 ("perl-test-simple" ,perl-test-simple)
1233 ("python" ,python-2)
1240 (string-append "prefix=" (assoc-ref %outputs "out")))
1242 (modify-phases %standard-phases
1245 (lambda* (#:key outputs #:allow-other-keys)
1246 (zero? (system* "perl"
1247 "scripts/test/simple_tests.pl"
1248 "--bowtie2=./bowtie2"
1249 "--bowtie2-build=./bowtie2-build")))))))
1250 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1251 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1253 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1254 reads to long reference sequences. It is particularly good at aligning reads
1255 of about 50 up to 100s or 1,000s of characters, and particularly good at
1256 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1257 genome with an FM Index to keep its memory footprint small: for the human
1258 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1259 gapped, local, and paired-end alignment modes.")
1260 (supported-systems '("x86_64-linux"))
1261 (license license:gpl3+)))
1263 (define-public tophat
1270 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1274 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1275 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1276 (modules '((guix build utils)))
1279 ;; Remove bundled SeqAn and samtools
1280 (delete-file-recursively "src/SeqAn-1.3")
1281 (delete-file-recursively "src/samtools-0.1.18")
1283 (build-system gnu-build-system)
1285 '(#:parallel-build? #f ; not supported
1287 (modify-phases %standard-phases
1288 (add-after 'unpack 'use-system-samtools
1289 (lambda* (#:key inputs #:allow-other-keys)
1290 (substitute* "src/Makefile.in"
1291 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1292 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1293 (("SAMPROG = samtools_0\\.1\\.18") "")
1294 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1295 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1296 (substitute* '("src/common.cpp"
1298 (("samtools_0.1.18") (which "samtools")))
1299 (substitute* '("src/common.h"
1300 "src/bam2fastx.cpp")
1301 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1302 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1303 (substitute* '("src/bwt_map.h"
1305 "src/align_status.h")
1306 (("#include <bam.h>") "#include <samtools/bam.h>")
1307 (("#include <sam.h>") "#include <samtools/sam.h>"))
1312 ("samtools" ,samtools-0.1)
1313 ("ncurses" ,ncurses)
1314 ("python" ,python-2)
1318 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1319 (synopsis "Spliced read mapper for RNA-Seq data")
1321 "TopHat is a fast splice junction mapper for nucleotide sequence
1322 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1323 mammalian-sized genomes using the ultra high-throughput short read
1324 aligner Bowtie, and then analyzes the mapping results to identify
1325 splice junctions between exons.")
1326 ;; TopHat is released under the Boost Software License, Version 1.0
1327 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1328 (license license:boost1.0)))
1337 "https://github.com/lh3/bwa/releases/download/v"
1338 version "/bwa-" version ".tar.bz2"))
1341 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1342 (build-system gnu-build-system)
1344 '(#:tests? #f ;no "check" target
1346 (modify-phases %standard-phases
1348 (lambda* (#:key outputs #:allow-other-keys)
1349 (let ((bin (string-append
1350 (assoc-ref outputs "out") "/bin"))
1352 (assoc-ref outputs "out") "/share/doc/bwa"))
1354 (assoc-ref outputs "out") "/share/man/man1")))
1355 (install-file "bwa" bin)
1356 (install-file "README.md" doc)
1357 (install-file "bwa.1" man))
1359 ;; no "configure" script
1360 (delete 'configure))))
1361 (inputs `(("zlib" ,zlib)))
1362 ;; Non-portable SSE instructions are used so building fails on platforms
1363 ;; other than x86_64.
1364 (supported-systems '("x86_64-linux"))
1365 (home-page "http://bio-bwa.sourceforge.net/")
1366 (synopsis "Burrows-Wheeler sequence aligner")
1368 "BWA is a software package for mapping low-divergent sequences against a
1369 large reference genome, such as the human genome. It consists of three
1370 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1371 designed for Illumina sequence reads up to 100bp, while the rest two for
1372 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1373 features such as long-read support and split alignment, but BWA-MEM, which is
1374 the latest, is generally recommended for high-quality queries as it is faster
1375 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1376 70-100bp Illumina reads.")
1377 (license license:gpl3+)))
1379 (define-public bwa-pssm
1380 (package (inherit bwa)
1385 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1386 "archive/" version ".tar.gz"))
1387 (file-name (string-append name "-" version ".tar.gz"))
1390 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1391 (build-system gnu-build-system)
1396 (home-page "http://bwa-pssm.binf.ku.dk/")
1397 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1399 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1400 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1401 existing aligners it is fast and sensitive. Unlike most other aligners,
1402 however, it is also adaptible in the sense that one can direct the alignment
1403 based on known biases within the data set. It is coded as a modification of
1404 the original BWA alignment program and shares the genome index structure as
1405 well as many of the command line options.")
1406 (license license:gpl3+)))
1408 (define-public python2-bx-python
1410 (name "python2-bx-python")
1414 (uri (pypi-uri "bx-python" version))
1417 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1418 (modules '((guix build utils)))
1420 '(substitute* "setup.py"
1421 ;; remove dependency on outdated "distribute" module
1422 (("^from distribute_setup import use_setuptools") "")
1423 (("^use_setuptools\\(\\)") "")))))
1424 (build-system python-build-system)
1426 `(#:tests? #f ;tests fail because test data are not included
1427 #:python ,python-2))
1429 `(("python-numpy" ,python2-numpy)
1432 `(("python-nose" ,python2-nose)))
1433 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1434 (synopsis "Tools for manipulating biological data")
1436 "bx-python provides tools for manipulating biological data, particularly
1437 multiple sequence alignments.")
1438 (license license:expat)))
1440 (define-public python-pysam
1442 (name "python-pysam")
1446 ;; Test data is missing on PyPi.
1448 "https://github.com/pysam-developers/pysam/archive/v"
1450 (file-name (string-append name "-" version ".tar.gz"))
1453 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1454 (modules '((guix build utils)))
1456 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1457 '(delete-file-recursively "htslib"))))
1458 (build-system python-build-system)
1460 `(#:modules ((ice-9 ftw)
1462 (guix build python-build-system)
1465 (modify-phases %standard-phases
1466 (add-before 'build 'set-flags
1467 (lambda* (#:key inputs #:allow-other-keys)
1468 (setenv "HTSLIB_MODE" "external")
1469 (setenv "HTSLIB_LIBRARY_DIR"
1470 (string-append (assoc-ref inputs "htslib") "/lib"))
1471 (setenv "HTSLIB_INCLUDE_DIR"
1472 (string-append (assoc-ref inputs "htslib") "/include"))
1473 (setenv "LDFLAGS" "-lncurses")
1474 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1477 (lambda* (#:key inputs outputs #:allow-other-keys)
1478 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1479 (setenv "PYTHONPATH"
1481 (getenv "PYTHONPATH")
1482 ":" (getcwd) "/build/"
1483 (car (scandir "build"
1484 (negate (cut string-prefix? "." <>))))))
1485 ;; Step out of source dir so python does not import from CWD.
1486 (with-directory-excursion "tests"
1487 (setenv "HOME" "/tmp")
1488 (and (zero? (system* "make" "-C" "pysam_data"))
1489 (zero? (system* "make" "-C" "cbcf_data"))
1490 ;; Running nosetests without explicitly asking for a
1491 ;; single process leads to a crash. Running with multiple
1492 ;; processes fails because the tests are not designed to
1495 ;; FIXME: tests keep timing out on some systems.
1496 ;; (zero? (system* "nosetests" "-v"
1497 ;; "--processes" "1"))
1500 `(("htslib" ,htslib))) ; Included from installed header files.
1502 `(("ncurses" ,ncurses)
1505 `(("python-cython" ,python-cython)
1506 ;; Dependencies below are are for tests only.
1507 ("samtools" ,samtools)
1508 ("bcftools" ,bcftools)
1509 ("python-nose" ,python-nose)))
1510 (home-page "https://github.com/pysam-developers/pysam")
1511 (synopsis "Python bindings to the SAMtools C API")
1513 "Pysam is a Python module for reading and manipulating files in the
1514 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1515 also includes an interface for tabix.")
1516 (license license:expat)))
1518 (define-public python2-pysam
1519 (package-with-python2 python-pysam))
1521 (define-public python-twobitreader
1523 (name "python-twobitreader")
1527 (uri (pypi-uri "twobitreader" version))
1530 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1531 (build-system python-build-system)
1533 '(;; Tests are not distributed in the PyPi release.
1534 ;; TODO Try building from the Git repo or asking the upstream maintainer
1535 ;; to distribute the tests on PyPi.
1538 `(("python-sphinx" ,python-sphinx)))
1539 (home-page "https://github.com/benjschiller/twobitreader")
1540 (synopsis "Python library for reading .2bit files")
1542 "twobitreader is a Python library for reading .2bit files as used by the
1543 UCSC genome browser.")
1544 (license license:artistic2.0)))
1546 (define-public python2-twobitreader
1547 (package-with-python2 python-twobitreader))
1549 (define-public python-plastid
1551 (name "python-plastid")
1555 (uri (pypi-uri "plastid" version))
1558 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1559 (build-system python-build-system)
1561 ;; Some test files are not included.
1564 `(("python-numpy" ,python-numpy)
1565 ("python-scipy" ,python-scipy)
1566 ("python-pandas" ,python-pandas)
1567 ("python-pysam" ,python-pysam)
1568 ("python-matplotlib" ,python-matplotlib)
1569 ("python-biopython" ,python-biopython)
1570 ("python-twobitreader" ,python-twobitreader)
1571 ("python-termcolor" ,python-termcolor)))
1573 `(("python-cython" ,python-cython)
1574 ("python-nose" ,python-nose)))
1575 (home-page "https://github.com/joshuagryphon/plastid")
1576 (synopsis "Python library for genomic analysis")
1578 "plastid is a Python library for genomic analysis – in particular,
1579 high-throughput sequencing data – with an emphasis on simplicity.")
1580 (license license:bsd-3)))
1582 (define-public python2-plastid
1583 (package-with-python2 python-plastid))
1585 (define-public cd-hit
1591 (uri (string-append "https://github.com/weizhongli/cdhit"
1592 "/releases/download/V" version
1594 "-2017-0621-source.tar.gz"))
1597 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1598 (build-system gnu-build-system)
1600 `(#:tests? #f ; there are no tests
1602 ;; Executables are copied directly to the PREFIX.
1603 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1605 (modify-phases %standard-phases
1606 ;; No "configure" script
1608 ;; Remove sources of non-determinism
1609 (add-after 'unpack 'be-timeless
1611 (substitute* "cdhit-utility.c++"
1612 ((" \\(built on \" __DATE__ \"\\)") ""))
1613 (substitute* "cdhit-common.c++"
1614 (("__DATE__") "\"0\"")
1615 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1617 ;; The "install" target does not create the target directory.
1618 (add-before 'install 'create-target-dir
1619 (lambda* (#:key outputs #:allow-other-keys)
1620 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1624 (home-page "http://weizhongli-lab.org/cd-hit/")
1625 (synopsis "Cluster and compare protein or nucleotide sequences")
1627 "CD-HIT is a program for clustering and comparing protein or nucleotide
1628 sequences. CD-HIT is designed to be fast and handle extremely large
1630 ;; The manual says: "It can be copied under the GNU General Public License
1631 ;; version 2 (GPLv2)."
1632 (license license:gpl2)))
1634 (define-public clipper
1641 "https://github.com/YeoLab/clipper/archive/"
1643 (file-name (string-append name "-" version ".tar.gz"))
1646 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1647 (modules '((guix build utils)))
1650 ;; remove unnecessary setup dependency
1651 (substitute* "setup.py"
1652 (("setup_requires = .*") ""))
1653 (for-each delete-file
1654 '("clipper/src/peaks.so"
1655 "clipper/src/readsToWiggle.so"))
1656 (delete-file-recursively "dist/")
1658 (build-system python-build-system)
1659 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1661 `(("htseq" ,python2-htseq)
1662 ("python-pybedtools" ,python2-pybedtools)
1663 ("python-cython" ,python2-cython)
1664 ("python-scikit-learn" ,python2-scikit-learn)
1665 ("python-matplotlib" ,python2-matplotlib)
1666 ("python-pandas" ,python2-pandas)
1667 ("python-pysam" ,python2-pysam)
1668 ("python-numpy" ,python2-numpy)
1669 ("python-scipy" ,python2-scipy)))
1671 `(("python-mock" ,python2-mock) ; for tests
1672 ("python-nose" ,python2-nose) ; for tests
1673 ("python-pytz" ,python2-pytz))) ; for tests
1674 (home-page "https://github.com/YeoLab/clipper")
1675 (synopsis "CLIP peak enrichment recognition")
1677 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1678 (license license:gpl2)))
1680 (define-public codingquarry
1682 (name "codingquarry")
1687 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1691 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1692 (build-system gnu-build-system)
1694 '(#:tests? #f ; no "check" target
1696 (modify-phases %standard-phases
1699 (lambda* (#:key outputs #:allow-other-keys)
1700 (let* ((out (assoc-ref outputs "out"))
1701 (bin (string-append out "/bin"))
1702 (doc (string-append out "/share/doc/codingquarry")))
1703 (install-file "INSTRUCTIONS.pdf" doc)
1704 (copy-recursively "QuarryFiles"
1705 (string-append out "/QuarryFiles"))
1706 (install-file "CodingQuarry" bin)
1707 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1708 (inputs `(("openmpi" ,openmpi)))
1709 (native-search-paths
1710 (list (search-path-specification
1711 (variable "QUARRY_PATH")
1712 (files '("QuarryFiles")))))
1713 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1714 (synopsis "Fungal gene predictor")
1715 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1716 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1717 (home-page "https://sourceforge.net/projects/codingquarry/")
1718 (license license:gpl3+)))
1720 (define-public couger
1727 "http://couger.oit.duke.edu/static/assets/COUGER"
1731 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1732 (build-system gnu-build-system)
1736 (modify-phases %standard-phases
1741 (lambda* (#:key outputs #:allow-other-keys)
1742 (let* ((out (assoc-ref outputs "out"))
1743 (bin (string-append out "/bin")))
1744 (copy-recursively "src" (string-append out "/src"))
1746 ;; Add "src" directory to module lookup path.
1747 (substitute* "couger"
1749 (string-append "import sys\nsys.path.append(\""
1750 out "\")\nfrom argparse")))
1751 (install-file "couger" bin))
1754 'install 'wrap-program
1755 (lambda* (#:key inputs outputs #:allow-other-keys)
1756 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1757 (let* ((out (assoc-ref outputs "out"))
1758 (path (getenv "PYTHONPATH")))
1759 (wrap-program (string-append out "/bin/couger")
1760 `("PYTHONPATH" ":" prefix (,path))))
1763 `(("python" ,python-2)
1764 ("python2-pillow" ,python2-pillow)
1765 ("python2-numpy" ,python2-numpy)
1766 ("python2-scipy" ,python2-scipy)
1767 ("python2-matplotlib" ,python2-matplotlib)))
1769 `(("r-minimal" ,r-minimal)
1771 ("randomjungle" ,randomjungle)))
1773 `(("unzip" ,unzip)))
1774 (home-page "http://couger.oit.duke.edu")
1775 (synopsis "Identify co-factors in sets of genomic regions")
1777 "COUGER can be applied to any two sets of genomic regions bound by
1778 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1779 putative co-factors that provide specificity to each TF. The framework
1780 determines the genomic targets uniquely-bound by each TF, and identifies a
1781 small set of co-factors that best explain the in vivo binding differences
1782 between the two TFs.
1784 COUGER uses classification algorithms (support vector machines and random
1785 forests) with features that reflect the DNA binding specificities of putative
1786 co-factors. The features are generated either from high-throughput TF-DNA
1787 binding data (from protein binding microarray experiments), or from large
1788 collections of DNA motifs.")
1789 (license license:gpl3+)))
1791 (define-public clustal-omega
1793 (name "clustal-omega")
1797 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1801 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1802 (build-system gnu-build-system)
1804 `(("argtable" ,argtable)))
1805 (home-page "http://www.clustal.org/omega/")
1806 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1808 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1809 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1810 of handling data-sets of hundreds of thousands of sequences in reasonable
1812 (license license:gpl2+)))
1814 (define-public crossmap
1820 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1824 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1825 ;; This patch has been sent upstream already and is available
1826 ;; for download from Sourceforge, but it has not been merged.
1827 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1828 (modules '((guix build utils)))
1829 ;; remove bundled copy of pysam
1831 '(delete-file-recursively "lib/pysam"))))
1832 (build-system python-build-system)
1834 `(#:python ,python-2
1836 (modify-phases %standard-phases
1837 (add-after 'unpack 'set-env
1838 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1840 `(("python-numpy" ,python2-numpy)
1841 ("python-pysam" ,python2-pysam)
1844 `(("python-cython" ,python2-cython)
1845 ("python-nose" ,python2-nose)))
1846 (home-page "http://crossmap.sourceforge.net/")
1847 (synopsis "Convert genome coordinates between assemblies")
1849 "CrossMap is a program for conversion of genome coordinates or annotation
1850 files between different genome assemblies. It supports most commonly used
1851 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1852 (license license:gpl2+)))
1854 (define-public cutadapt
1861 "https://github.com/marcelm/cutadapt/archive/v"
1863 (file-name (string-append name "-" version ".tar.gz"))
1866 "16gbpiwy4m48vq2h5wqar3i8vr6vcj9gcl2qvqim19x6ya9dp8kd"))))
1867 (build-system python-build-system)
1870 (modify-phases %standard-phases
1871 ;; The tests must be run after installation.
1873 (add-after 'install 'check
1874 (lambda* (#:key inputs outputs #:allow-other-keys)
1875 (setenv "PYTHONPATH"
1877 (getenv "PYTHONPATH")
1878 ":" (assoc-ref outputs "out")
1880 (string-take (string-take-right
1881 (assoc-ref inputs "python") 5) 3)
1883 (zero? (system* "nosetests" "-P" "tests")))))))
1885 `(("python-xopen" ,python-xopen)))
1887 `(("python-cython" ,python-cython)
1888 ("python-nose" ,python-nose)))
1889 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1890 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1892 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1893 other types of unwanted sequence from high-throughput sequencing reads.")
1894 (license license:expat)))
1896 (define-public libbigwig
1902 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1903 "archive/" version ".tar.gz"))
1904 (file-name (string-append name "-" version ".tar.gz"))
1907 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1908 (build-system gnu-build-system)
1910 `(#:test-target "test"
1913 (string-append "prefix=" (assoc-ref %outputs "out")))
1915 (modify-phases %standard-phases
1917 (add-before 'check 'disable-curl-test
1919 (substitute* "Makefile"
1920 (("./test/testRemote.*") ""))
1922 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1923 ;; there has not yet been a release containing this change.
1924 (add-before 'install 'create-target-dirs
1925 (lambda* (#:key outputs #:allow-other-keys)
1926 (let ((out (assoc-ref outputs "out")))
1927 (mkdir-p (string-append out "/lib"))
1928 (mkdir-p (string-append out "/include"))
1934 `(("doxygen" ,doxygen)))
1935 (home-page "https://github.com/dpryan79/libBigWig")
1936 (synopsis "C library for handling bigWig files")
1938 "This package provides a C library for parsing local and remote BigWig
1940 (license license:expat)))
1942 (define-public python-pybigwig
1944 (name "python-pybigwig")
1948 (uri (pypi-uri "pyBigWig" version))
1951 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1952 (modules '((guix build utils)))
1955 ;; Delete bundled libBigWig sources
1956 (delete-file-recursively "libBigWig")))))
1957 (build-system python-build-system)
1960 (modify-phases %standard-phases
1961 (add-after 'unpack 'link-with-libBigWig
1962 (lambda* (#:key inputs #:allow-other-keys)
1963 (substitute* "setup.py"
1964 (("libs=\\[") "libs=[\"BigWig\", "))
1967 `(("libbigwig" ,libbigwig)
1970 (home-page "https://github.com/dpryan79/pyBigWig")
1971 (synopsis "Access bigWig files in Python using libBigWig")
1973 "This package provides Python bindings to the libBigWig library for
1974 accessing bigWig files.")
1975 (license license:expat)))
1977 (define-public python2-pybigwig
1978 (package-with-python2 python-pybigwig))
1980 (define-public python-dendropy
1982 (name "python-dendropy")
1987 (uri (pypi-uri "DendroPy" version))
1990 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1991 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1992 (build-system python-build-system)
1993 (home-page "http://packages.python.org/DendroPy/")
1994 (synopsis "Library for phylogenetics and phylogenetic computing")
1996 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1997 writing, simulation, processing and manipulation of phylogenetic
1998 trees (phylogenies) and characters.")
1999 (license license:bsd-3)
2000 (properties `((python2-variant . ,(delay python2-dendropy))))))
2002 (define-public python2-dendropy
2003 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2007 `(#:python ,python-2
2009 (modify-phases %standard-phases
2011 ;; There is currently a test failure that only happens on some
2012 ;; systems, and only using "setup.py test"
2013 (lambda _ (zero? (system* "nosetests")))))))
2014 (native-inputs `(("python2-nose" ,python2-nose)
2015 ,@(package-native-inputs base))))))
2017 (define-public python-py2bit
2019 (name "python-py2bit")
2024 (uri (pypi-uri "py2bit" version))
2027 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2028 (build-system python-build-system)
2029 (home-page "https://github.com/dpryan79/py2bit")
2030 (synopsis "Access 2bit files using lib2bit")
2032 "This package provides Python bindings for lib2bit to access 2bit files
2034 (license license:expat)))
2036 (define-public deeptools
2042 (uri (string-append "https://github.com/deeptools/deepTools/"
2043 "archive/" version ".tar.gz"))
2044 (file-name (string-append name "-" version ".tar.gz"))
2047 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2048 (build-system python-build-system)
2050 `(("python-scipy" ,python-scipy)
2051 ("python-numpy" ,python-numpy)
2052 ("python-numpydoc" ,python-numpydoc)
2053 ("python-matplotlib" ,python-matplotlib)
2054 ("python-pysam" ,python-pysam)
2055 ("python-py2bit" ,python-py2bit)
2056 ("python-pybigwig" ,python-pybigwig)))
2058 `(("python-mock" ,python-mock) ;for tests
2059 ("python-nose" ,python-nose) ;for tests
2060 ("python-pytz" ,python-pytz))) ;for tests
2061 (home-page "https://github.com/deeptools/deepTools")
2062 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2064 "DeepTools addresses the challenge of handling the large amounts of data
2065 that are now routinely generated from DNA sequencing centers. To do so,
2066 deepTools contains useful modules to process the mapped reads data to create
2067 coverage files in standard bedGraph and bigWig file formats. By doing so,
2068 deepTools allows the creation of normalized coverage files or the comparison
2069 between two files (for example, treatment and control). Finally, using such
2070 normalized and standardized files, multiple visualizations can be created to
2071 identify enrichments with functional annotations of the genome.")
2072 (license license:gpl3+)))
2074 (define-public diamond
2081 "https://github.com/bbuchfink/diamond/archive/v"
2083 (file-name (string-append name "-" version ".tar.gz"))
2086 "1p3fd1ad7hg2w09w3sjk4pxqx0p0gaqys8ipg3f4adg77mn9m9yd"))))
2087 (build-system cmake-build-system)
2089 '(#:tests? #f ; no "check" target
2091 (modify-phases %standard-phases
2092 (add-after 'unpack 'remove-native-compilation
2094 (substitute* "CMakeLists.txt" (("-march=native") ""))
2098 (home-page "https://github.com/bbuchfink/diamond")
2099 (synopsis "Accelerated BLAST compatible local sequence aligner")
2101 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2102 translated DNA query sequences against a protein reference database (BLASTP
2103 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2104 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2105 data and settings.")
2106 (license license:agpl3+)))
2108 (define-public discrover
2115 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2117 (file-name (string-append name "-" version ".tar.gz"))
2120 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2121 (build-system cmake-build-system)
2123 `(#:tests? #f ; there are no tests
2125 (modify-phases %standard-phases
2126 (add-after 'unpack 'add-missing-includes
2128 (substitute* "src/executioninformation.hpp"
2129 (("#define EXECUTIONINFORMATION_HPP" line)
2130 (string-append line "\n#include <random>")))
2131 (substitute* "src/plasma/fasta.hpp"
2132 (("#define FASTA_HPP" line)
2133 (string-append line "\n#include <random>")))
2139 `(("texlive" ,texlive)
2140 ("imagemagick" ,imagemagick)))
2141 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2142 (synopsis "Discover discriminative nucleotide sequence motifs")
2143 (description "Discrover is a motif discovery method to find binding sites
2144 of nucleic acid binding proteins.")
2145 (license license:gpl3+)))
2147 (define-public eigensoft
2148 (let ((revision "1")
2149 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2152 (version (string-append "6.1.2-"
2154 (string-take commit 9)))
2159 (url "https://github.com/DReichLab/EIG.git")
2161 (file-name (string-append "eigensoft-" commit "-checkout"))
2164 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2165 (modules '((guix build utils)))
2166 ;; Remove pre-built binaries.
2168 (delete-file-recursively "bin")
2171 (build-system gnu-build-system)
2173 `(#:tests? #f ; There are no tests.
2174 #:make-flags '("CC=gcc")
2176 (modify-phases %standard-phases
2177 ;; There is no configure phase, but the Makefile is in a
2182 ;; The link flags are incomplete.
2183 (substitute* "Makefile"
2184 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2186 ;; The provided install target only copies executables to
2187 ;; the "bin" directory in the build root.
2188 (add-after 'install 'actually-install
2189 (lambda* (#:key outputs #:allow-other-keys)
2190 (let* ((out (assoc-ref outputs "out"))
2191 (bin (string-append out "/bin")))
2192 (for-each (lambda (file)
2193 (install-file file bin))
2194 (find-files "../bin" ".*"))
2199 ("openblas" ,openblas)
2201 ("gfortran" ,gfortran "lib")))
2202 (home-page "https://github.com/DReichLab/EIG")
2203 (synopsis "Tools for population genetics")
2204 (description "The EIGENSOFT package provides tools for population
2205 genetics and stratification correction. EIGENSOFT implements methods commonly
2206 used in population genetics analyses such as PCA, computation of Tracy-Widom
2207 statistics, and finding related individuals in structured populations. It
2208 comes with a built-in plotting script and supports multiple file formats and
2209 quantitative phenotypes.")
2210 ;; The license of the eigensoft tools is Expat, but since it's
2211 ;; linking with the GNU Scientific Library (GSL) the effective
2212 ;; license is the GPL.
2213 (license license:gpl3+))))
2215 (define-public edirect
2221 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2222 "versions/2016-05-03/edirect.tar.gz"))
2225 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2226 (build-system perl-build-system)
2228 `(#:tests? #f ;no "check" target
2230 (modify-phases %standard-phases
2234 (lambda* (#:key outputs #:allow-other-keys)
2235 (let ((target (string-append (assoc-ref outputs "out")
2238 (install-file "edirect.pl" target)
2241 'install 'wrap-program
2242 (lambda* (#:key inputs outputs #:allow-other-keys)
2243 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2244 (let* ((out (assoc-ref outputs "out"))
2245 (path (getenv "PERL5LIB")))
2246 (wrap-program (string-append out "/bin/edirect.pl")
2247 `("PERL5LIB" ":" prefix (,path)))))))))
2249 `(("perl-html-parser" ,perl-html-parser)
2250 ("perl-encode-locale" ,perl-encode-locale)
2251 ("perl-file-listing" ,perl-file-listing)
2252 ("perl-html-tagset" ,perl-html-tagset)
2253 ("perl-html-tree" ,perl-html-tree)
2254 ("perl-http-cookies" ,perl-http-cookies)
2255 ("perl-http-date" ,perl-http-date)
2256 ("perl-http-message" ,perl-http-message)
2257 ("perl-http-negotiate" ,perl-http-negotiate)
2258 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2259 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2260 ("perl-net-http" ,perl-net-http)
2261 ("perl-uri" ,perl-uri)
2262 ("perl-www-robotrules" ,perl-www-robotrules)
2264 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2265 (synopsis "Tools for accessing the NCBI's set of databases")
2267 "Entrez Direct (EDirect) is a method for accessing the National Center
2268 for Biotechnology Information's (NCBI) set of interconnected
2269 databases (publication, sequence, structure, gene, variation, expression,
2270 etc.) from a terminal. Functions take search terms from command-line
2271 arguments. Individual operations are combined to build multi-step queries.
2272 Record retrieval and formatting normally complete the process.
2274 EDirect also provides an argument-driven function that simplifies the
2275 extraction of data from document summaries or other results that are returned
2276 in structured XML format. This can eliminate the need for writing custom
2277 software to answer ad hoc questions.")
2278 (license license:public-domain)))
2280 (define-public exonerate
2289 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2290 "exonerate-" version ".tar.gz"))
2293 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2294 (build-system gnu-build-system)
2296 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2298 `(("pkg-config" ,pkg-config)))
2302 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2303 (synopsis "Generic tool for biological sequence alignment")
2305 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2306 the alignment of sequences using a many alignment models, either exhaustive
2307 dynamic programming or a variety of heuristics.")
2308 (license license:gpl3)))
2310 (define-public express
2318 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2319 version "/express-" version "-src.tgz"))
2322 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2323 (build-system cmake-build-system)
2325 `(#:tests? #f ;no "check" target
2327 (modify-phases %standard-phases
2328 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2329 (lambda* (#:key inputs #:allow-other-keys)
2330 (substitute* "CMakeLists.txt"
2331 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2332 "set(Boost_USE_STATIC_LIBS OFF)")
2333 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2334 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2335 (substitute* "src/CMakeLists.txt"
2336 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2337 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2341 ("bamtools" ,bamtools)
2342 ("protobuf" ,protobuf)
2344 (home-page "http://bio.math.berkeley.edu/eXpress")
2345 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2347 "eXpress is a streaming tool for quantifying the abundances of a set of
2348 target sequences from sampled subsequences. Example applications include
2349 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2350 analysis (from RNA-Seq), transcription factor binding quantification in
2351 ChIP-Seq, and analysis of metagenomic data.")
2352 (license license:artistic2.0)))
2354 (define-public express-beta-diversity
2356 (name "express-beta-diversity")
2362 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2364 (file-name (string-append name "-" version ".tar.gz"))
2367 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2368 (build-system gnu-build-system)
2371 (modify-phases %standard-phases
2373 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2375 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2377 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2379 (lambda* (#:key outputs #:allow-other-keys)
2380 (let ((bin (string-append (assoc-ref outputs "out")
2383 (install-file "scripts/convertToEBD.py" bin)
2384 (install-file "bin/ExpressBetaDiversity" bin)
2387 `(("python" ,python-2)))
2388 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2389 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2391 "Express Beta Diversity (EBD) calculates ecological beta diversity
2392 (dissimilarity) measures between biological communities. EBD implements a
2393 variety of diversity measures including those that make use of phylogenetic
2394 similarity of community members.")
2395 (license license:gpl3+)))
2397 (define-public fasttree
2404 "http://www.microbesonline.org/fasttree/FastTree-"
2408 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2409 (build-system gnu-build-system)
2411 `(#:tests? #f ; no "check" target
2413 (modify-phases %standard-phases
2417 (lambda* (#:key source #:allow-other-keys)
2418 (and (zero? (system* "gcc"
2420 "-finline-functions"
2427 (zero? (system* "gcc"
2431 "-finline-functions"
2439 (lambda* (#:key outputs #:allow-other-keys)
2440 (let ((bin (string-append (assoc-ref outputs "out")
2443 (install-file "FastTree" bin)
2444 (install-file "FastTreeMP" bin)
2446 (home-page "http://www.microbesonline.org/fasttree")
2447 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2449 "FastTree can handle alignments with up to a million of sequences in a
2450 reasonable amount of time and memory. For large alignments, FastTree is
2451 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2452 (license license:gpl2+)))
2454 (define-public fastx-toolkit
2456 (name "fastx-toolkit")
2462 "https://github.com/agordon/fastx_toolkit/releases/download/"
2463 version "/fastx_toolkit-" version ".tar.bz2"))
2466 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2467 (build-system gnu-build-system)
2469 `(("libgtextutils" ,libgtextutils)))
2471 `(("pkg-config" ,pkg-config)))
2472 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2473 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2475 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2476 FASTA/FASTQ files preprocessing.
2478 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2479 containing multiple short-reads sequences. The main processing of such
2480 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2481 is sometimes more productive to preprocess the files before mapping the
2482 sequences to the genome---manipulating the sequences to produce better mapping
2483 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2484 (license license:agpl3+)))
2486 (define-public flexbar
2493 (string-append "mirror://sourceforge/flexbar/"
2494 version "/flexbar_v" version "_src.tgz"))
2497 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2498 (build-system cmake-build-system)
2500 `(#:configure-flags (list
2501 (string-append "-DFLEXBAR_BINARY_DIR="
2502 (assoc-ref %outputs "out")
2505 (modify-phases %standard-phases
2507 (lambda* (#:key outputs #:allow-other-keys)
2508 (setenv "PATH" (string-append
2509 (assoc-ref outputs "out") "/bin:"
2511 (chdir "../flexbar_v2.5_src/test")
2512 (zero? (system* "bash" "flexbar_validate.sh"))))
2513 (delete 'install))))
2518 `(("pkg-config" ,pkg-config)
2520 (home-page "http://flexbar.sourceforge.net")
2521 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2523 "Flexbar preprocesses high-throughput nucleotide sequencing data
2524 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2525 Moreover, trimming and filtering features are provided. Flexbar increases
2526 read mapping rates and improves genome and transcriptome assemblies. It
2527 supports next-generation sequencing data in fasta/q and csfasta/q format from
2528 Illumina, Roche 454, and the SOLiD platform.")
2529 (license license:gpl3)))
2531 (define-public fraggenescan
2533 (name "fraggenescan")
2539 (string-append "mirror://sourceforge/fraggenescan/"
2540 "FragGeneScan" version ".tar.gz"))
2542 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2543 (build-system gnu-build-system)
2546 (modify-phases %standard-phases
2548 (add-before 'build 'patch-paths
2549 (lambda* (#:key outputs #:allow-other-keys)
2550 (let* ((out (string-append (assoc-ref outputs "out")))
2551 (share (string-append out "/share/fraggenescan/")))
2552 (substitute* "run_FragGeneScan.pl"
2554 (string-append "system(\"" (which "rm")))
2556 (string-append "system(\"" (which "mv")))
2557 (("\\\"awk") (string-append "\"" (which "awk")))
2558 ;; This script and other programs expect the training files
2559 ;; to be in the non-standard location bin/train/XXX. Change
2560 ;; this to be share/fraggenescan/train/XXX instead.
2561 (("^\\$train.file = \\$dir.*")
2562 (string-append "$train_file = \""
2564 "train/\".$FGS_train_file;")))
2565 (substitute* "run_hmm.c"
2566 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2567 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2570 (lambda _ (and (zero? (system* "make" "clean"))
2571 (zero? (system* "make" "fgs")))))
2573 (lambda* (#:key outputs #:allow-other-keys)
2574 (let* ((out (string-append (assoc-ref outputs "out")))
2575 (bin (string-append out "/bin/"))
2576 (share (string-append out "/share/fraggenescan/train")))
2577 (install-file "run_FragGeneScan.pl" bin)
2578 (install-file "FragGeneScan" bin)
2579 (copy-recursively "train" share))))
2581 (add-after 'install 'post-install-check
2582 ;; In lieu of 'make check', run one of the examples and check the
2583 ;; output files gets created.
2584 (lambda* (#:key outputs #:allow-other-keys)
2585 (let* ((out (string-append (assoc-ref outputs "out")))
2586 (bin (string-append out "/bin/"))
2587 (frag (string-append bin "run_FragGeneScan.pl")))
2588 (and (zero? (system* frag ; Test complete genome.
2589 "-genome=./example/NC_000913.fna"
2593 (file-exists? "test2.faa")
2594 (file-exists? "test2.ffn")
2595 (file-exists? "test2.gff")
2596 (file-exists? "test2.out")
2597 (zero? (system* ; Test incomplete sequences.
2599 "-genome=./example/NC_000913-fgs.ffn"
2602 "-train=454_30")))))))))
2605 ("python" ,python-2))) ;not compatible with python 3.
2606 (home-page "https://sourceforge.net/projects/fraggenescan/")
2607 (synopsis "Finds potentially fragmented genes in short reads")
2609 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2610 short and error-prone DNA sequencing reads. It can also be applied to predict
2611 genes in incomplete assemblies or complete genomes.")
2612 ;; GPL3+ according to private correspondense with the authors.
2613 (license license:gpl3+)))
2615 (define-public fxtract
2616 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2624 "https://github.com/ctSkennerton/fxtract/archive/"
2626 (file-name (string-append "ctstennerton-util-"
2627 (string-take util-commit 7)
2631 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2632 (build-system gnu-build-system)
2634 `(#:make-flags (list
2635 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2637 #:test-target "fxtract_test"
2639 (modify-phases %standard-phases
2641 (add-before 'build 'copy-util
2642 (lambda* (#:key inputs #:allow-other-keys)
2644 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2646 ;; Do not use make install as this requires additional dependencies.
2648 (lambda* (#:key outputs #:allow-other-keys)
2649 (let* ((out (assoc-ref outputs "out"))
2650 (bin (string-append out"/bin")))
2651 (install-file "fxtract" bin)
2657 ;; ctskennerton-util is licensed under GPL2.
2658 `(("ctskennerton-util"
2662 (url "https://github.com/ctSkennerton/util.git")
2663 (commit util-commit)))
2664 (file-name (string-append
2665 "ctstennerton-util-" util-commit "-checkout"))
2668 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2669 (home-page "https://github.com/ctSkennerton/fxtract")
2670 (synopsis "Extract sequences from FASTA and FASTQ files")
2672 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2673 or FASTQ) file given a subsequence. It uses a simple substring search for
2674 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2675 lookups or multi-pattern searching as required. By default fxtract looks in
2676 the sequence of each record but can also be told to look in the header,
2677 comment or quality sections.")
2678 ;; 'util' requires SSE instructions.
2679 (supported-systems '("x86_64-linux"))
2680 (license license:expat))))
2682 (define-public gemma
2688 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2690 (file-name (string-append name "-" version ".tar.gz"))
2693 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2694 (patches (search-patches "gemma-intel-compat.patch"))))
2699 (build-system gnu-build-system)
2702 '(,@(match (%current-system)
2704 '("FORCE_DYNAMIC=1"))
2706 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2708 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2710 (modify-phases %standard-phases
2712 (add-before 'build 'bin-mkdir
2717 (lambda* (#:key outputs #:allow-other-keys)
2718 (let ((out (assoc-ref outputs "out")))
2719 (install-file "bin/gemma"
2723 #:tests? #f)) ; no tests included yet
2724 (home-page "https://github.com/xiangzhou/GEMMA")
2725 (synopsis "Tool for genome-wide efficient mixed model association")
2727 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2728 standard linear mixed model resolver with application in genome-wide
2729 association studies (GWAS).")
2730 (license license:gpl3)))
2739 "https://github.com/nboley/grit/archive/"
2741 (file-name (string-append name "-" version ".tar.gz"))
2744 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2745 (build-system python-build-system)
2747 `(#:python ,python-2
2749 (modify-phases %standard-phases
2750 (add-after 'unpack 'generate-from-cython-sources
2751 (lambda* (#:key inputs outputs #:allow-other-keys)
2752 ;; Delete these C files to force fresh generation from pyx sources.
2753 (delete-file "grit/sparsify_support_fns.c")
2754 (delete-file "grit/call_peaks_support_fns.c")
2755 (substitute* "setup.py"
2756 (("Cython.Setup") "Cython.Build")
2757 ;; Add numpy include path to fix compilation
2759 (string-append "pyx\", ], include_dirs = ['"
2760 (assoc-ref inputs "python-numpy")
2761 "/lib/python2.7/site-packages/numpy/core/include/"
2765 `(("python-scipy" ,python2-scipy)
2766 ("python-numpy" ,python2-numpy)
2767 ("python-pysam" ,python2-pysam)
2768 ("python-networkx" ,python2-networkx)))
2770 `(("python-cython" ,python2-cython)))
2771 (home-page "http://grit-bio.org")
2772 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2774 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2775 full length transcript models. When none of these data sources are available,
2776 GRIT can be run by providing a candidate set of TES or TSS sites. In
2777 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2778 also be run in quantification mode, where it uses a provided GTF file and just
2779 estimates transcript expression.")
2780 (license license:gpl3+)))
2782 (define-public hisat
2789 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2790 version "-beta-source.zip"))
2793 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2794 (build-system gnu-build-system)
2796 `(#:tests? #f ;no check target
2797 #:make-flags '("allall"
2798 ;; Disable unsupported `popcnt' instructions on
2799 ;; architectures other than x86_64
2800 ,@(if (string-prefix? "x86_64"
2801 (or (%current-target-system)
2804 '("POPCNT_CAPABILITY=0")))
2806 (modify-phases %standard-phases
2807 (add-after 'unpack 'patch-sources
2809 ;; XXX Cannot use snippet because zip files are not supported
2810 (substitute* "Makefile"
2811 (("^CC = .*$") "CC = gcc")
2812 (("^CPP = .*$") "CPP = g++")
2813 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2814 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2815 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2816 (substitute* '("hisat-build" "hisat-inspect")
2817 (("/usr/bin/env") (which "env")))
2820 (lambda* (#:key outputs #:allow-other-keys)
2821 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2822 (for-each (lambda (file)
2823 (install-file file bin))
2826 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2828 (delete 'configure))))
2830 `(("unzip" ,unzip)))
2835 ;; Non-portable SSE instructions are used so building fails on platforms
2836 ;; other than x86_64.
2837 (supported-systems '("x86_64-linux"))
2838 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2839 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2841 "HISAT is a fast and sensitive spliced alignment program for mapping
2842 RNA-seq reads. In addition to one global FM index that represents a whole
2843 genome, HISAT uses a large set of small FM indexes that collectively cover the
2844 whole genome. These small indexes (called local indexes) combined with
2845 several alignment strategies enable effective alignment of RNA-seq reads, in
2846 particular, reads spanning multiple exons.")
2847 (license license:gpl3+)))
2849 (define-public hisat2
2856 ;; FIXME: a better source URL is
2857 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2858 ;; "/downloads/hisat2-" version "-source.zip")
2859 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2860 ;; but it is currently unavailable.
2861 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2862 (file-name (string-append name "-" version ".tar.gz"))
2865 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2866 (build-system gnu-build-system)
2868 `(#:tests? #f ; no check target
2869 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2870 #:modules ((guix build gnu-build-system)
2874 (modify-phases %standard-phases
2875 (add-after 'unpack 'make-deterministic
2877 (substitute* "Makefile"
2882 (lambda* (#:key outputs #:allow-other-keys)
2883 (let* ((out (assoc-ref outputs "out"))
2884 (bin (string-append out "/bin/"))
2885 (doc (string-append out "/share/doc/hisat2/")))
2887 (cut install-file <> bin)
2889 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2891 (install-file "doc/manual.inc.html" doc))
2894 `(("unzip" ,unzip) ; needed for archive from ftp
2896 ("pandoc" ,ghc-pandoc))) ; for documentation
2897 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2898 (synopsis "Graph-based alignment of genomic sequencing reads")
2899 (description "HISAT2 is a fast and sensitive alignment program for mapping
2900 next-generation sequencing reads (both DNA and RNA) to a population of human
2901 genomes (as well as to a single reference genome). In addition to using one
2902 global @dfn{graph FM} (GFM) index that represents a population of human
2903 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2904 the whole genome. These small indexes, combined with several alignment
2905 strategies, enable rapid and accurate alignment of sequencing reads. This new
2906 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2907 ;; HISAT2 contains files from Bowtie2, which is released under
2908 ;; GPLv2 or later. The HISAT2 source files are released under
2910 (license license:gpl3+)))
2912 (define-public hmmer
2920 "http://eddylab.org/software/hmmer"
2921 (version-major version) "/"
2922 version "/hmmer-" version ".tar.gz"))
2925 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2926 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2927 (build-system gnu-build-system)
2928 (native-inputs `(("perl" ,perl)))
2929 (home-page "http://hmmer.org/")
2930 (synopsis "Biosequence analysis using profile hidden Markov models")
2932 "HMMER is used for searching sequence databases for homologs of protein
2933 sequences, and for making protein sequence alignments. It implements methods
2934 using probabilistic models called profile hidden Markov models (profile
2936 (license (list license:gpl3+
2937 ;; The bundled library 'easel' is distributed
2938 ;; under The Janelia Farm Software License.
2939 (license:non-copyleft
2940 "file://easel/LICENSE"
2941 "See easel/LICENSE in the distribution.")))))
2943 (define-public htseq
2949 (uri (pypi-uri "HTSeq" version))
2952 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2953 (build-system python-build-system)
2955 `(("python-cython" ,python-cython)))
2956 ;; Numpy needs to be propagated when htseq is used as a Python library.
2958 `(("python-numpy" ,python-numpy)))
2960 `(("python-pysam" ,python-pysam)
2961 ("python-matplotlib" ,python-matplotlib)))
2962 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2963 (synopsis "Analysing high-throughput sequencing data with Python")
2965 "HTSeq is a Python package that provides infrastructure to process data
2966 from high-throughput sequencing assays.")
2967 (license license:gpl3+)))
2969 (define-public python2-htseq
2970 (package-with-python2 htseq))
2972 (define-public java-htsjdk
2974 (name "java-htsjdk")
2975 (version "2.3.0") ; last version without build dependency on gradle
2979 "https://github.com/samtools/htsjdk/archive/"
2981 (file-name (string-append name "-" version ".tar.gz"))
2984 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2985 (modules '((guix build utils)))
2987 ;; Delete pre-built binaries
2989 (delete-file-recursively "lib")
2992 (build-system ant-build-system)
2994 `(#:tests? #f ; test require Internet access
2997 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2998 "/share/java/htsjdk/"))
2999 #:build-target "all"
3001 (modify-phases %standard-phases
3002 ;; The build phase also installs the jars
3003 (delete 'install))))
3005 `(("java-ngs" ,java-ngs)
3006 ("java-snappy-1" ,java-snappy-1)
3007 ("java-commons-compress" ,java-commons-compress)
3008 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3009 ("java-commons-jexl-2" ,java-commons-jexl-2)
3010 ("java-xz" ,java-xz)))
3012 `(("java-testng" ,java-testng)))
3013 (home-page "http://samtools.github.io/htsjdk/")
3014 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3016 "HTSJDK is an implementation of a unified Java library for accessing
3017 common file formats, such as SAM and VCF, used for high-throughput
3018 sequencing (HTS) data. There are also an number of useful utilities for
3019 manipulating HTS data.")
3020 (license license:expat)))
3022 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3023 ;; recent version of java-htsjdk, which depends on gradle.
3024 (define-public java-picard
3026 (name "java-picard")
3031 (url "https://github.com/broadinstitute/picard.git")
3033 (file-name (string-append "java-picard-" version "-checkout"))
3036 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3037 (modules '((guix build utils)))
3040 ;; Delete pre-built binaries.
3041 (delete-file-recursively "lib")
3043 (substitute* "build.xml"
3044 ;; Remove build-time dependency on git.
3045 (("failifexecutionfails=\"true\"")
3046 "failifexecutionfails=\"false\"")
3048 (("depends=\"compile-htsjdk, ")
3050 (("depends=\"compile-htsjdk-tests, ")
3052 ;; Build picard-lib.jar before building picard.jar
3053 (("name=\"picard-jar\" depends=\"" line)
3054 (string-append line "picard-lib-jar, ")))
3056 (build-system ant-build-system)
3058 `(#:build-target "picard-jar"
3059 #:test-target "test"
3060 ;; Tests require jacoco:coverage.
3063 (list (string-append "-Dhtsjdk_lib_dir="
3064 (assoc-ref %build-inputs "java-htsjdk")
3065 "/share/java/htsjdk/")
3066 "-Dhtsjdk-classes=dist/tmp"
3067 (string-append "-Dhtsjdk-version="
3068 ,(package-version java-htsjdk)))
3071 (modify-phases %standard-phases
3072 (add-after 'unpack 'use-our-htsjdk
3073 (lambda* (#:key inputs #:allow-other-keys)
3074 (substitute* "build.xml"
3075 (("\\$\\{htsjdk\\}/lib")
3076 (string-append (assoc-ref inputs "java-htsjdk")
3077 "/share/java/htsjdk/")))
3079 (add-after 'unpack 'make-test-target-independent
3080 (lambda* (#:key inputs #:allow-other-keys)
3081 (substitute* "build.xml"
3082 (("name=\"test\" depends=\"compile, ")
3083 "name=\"test\" depends=\""))
3085 (replace 'install (install-jars "dist")))))
3087 `(("java-htsjdk" ,java-htsjdk)
3088 ("java-guava" ,java-guava)))
3090 `(("java-testng" ,java-testng)))
3091 (home-page "http://broadinstitute.github.io/picard/")
3092 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3093 (description "Picard is a set of Java command line tools for manipulating
3094 high-throughput sequencing (HTS) data and formats. Picard is implemented
3095 using the HTSJDK Java library to support accessing file formats that are
3096 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3098 (license license:expat)))
3100 ;; This is the last version of Picard to provide net.sf.samtools
3101 (define-public java-picard-1.113
3102 (package (inherit java-picard)
3103 (name "java-picard")
3108 (url "https://github.com/broadinstitute/picard.git")
3110 (file-name (string-append "java-picard-" version "-checkout"))
3113 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3114 (modules '((guix build utils)))
3117 ;; Delete pre-built binaries.
3118 (delete-file-recursively "lib")
3121 (build-system ant-build-system)
3123 `(#:build-target "picard-jar"
3124 #:test-target "test"
3125 ;; FIXME: the class path at test time is wrong.
3126 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3127 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3130 ;; This is only used for tests.
3132 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3134 (modify-phases %standard-phases
3135 ;; Do not use bundled ant bzip2.
3136 (add-after 'unpack 'use-ant-bzip
3137 (lambda* (#:key inputs #:allow-other-keys)
3138 (substitute* "build.xml"
3139 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3140 (string-append (assoc-ref inputs "ant")
3143 (add-after 'unpack 'make-test-target-independent
3144 (lambda* (#:key inputs #:allow-other-keys)
3145 (substitute* "build.xml"
3146 (("name=\"test\" depends=\"compile, ")
3147 "name=\"test\" depends=\"compile-tests, ")
3148 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3149 "name=\"compile\" depends=\"compile-src\""))
3151 (add-after 'unpack 'fix-deflater-path
3152 (lambda* (#:key outputs #:allow-other-keys)
3153 (substitute* "src/java/net/sf/samtools/Defaults.java"
3154 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3155 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3156 (assoc-ref outputs "out")
3157 "/lib/jni/libIntelDeflater.so"
3160 ;; Build the deflater library, because we've previously deleted the
3161 ;; pre-built one. This can only be built with access to the JDK
3163 (add-after 'build 'build-jni
3164 (lambda* (#:key inputs #:allow-other-keys)
3167 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3168 "-xf" (assoc-ref inputs "jdk-src")))
3169 (zero? (system* "javah" "-jni"
3170 "-classpath" "classes"
3172 "net.sf.samtools.util.zip.IntelDeflater"))
3173 (with-directory-excursion "src/c/inteldeflater"
3174 (zero? (system* "gcc" "-I../../../lib" "-I."
3175 (string-append "-I" (assoc-ref inputs "jdk")
3177 "-I../../../jdk-src/src/share/native/common/"
3178 "-I../../../jdk-src/src/solaris/native/common/"
3179 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3180 (zero? (system* "gcc" "-shared"
3181 "-o" "../../../lib/jni/libIntelDeflater.so"
3182 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3183 ;; We can only build everything else after building the JNI library.
3184 (add-after 'build-jni 'build-rest
3185 (lambda* (#:key make-flags #:allow-other-keys)
3186 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3187 (add-before 'build 'set-JAVA6_HOME
3189 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3191 (replace 'install (install-jars "dist"))
3192 (add-after 'install 'install-jni-lib
3193 (lambda* (#:key outputs #:allow-other-keys)
3194 (let ((jni (string-append (assoc-ref outputs "out")
3197 (install-file "lib/jni/libIntelDeflater.so" jni)
3200 `(("java-snappy-1" ,java-snappy-1)
3201 ("java-commons-jexl-2" ,java-commons-jexl-2)
3202 ("java-cofoja" ,java-cofoja)
3203 ("ant" ,ant) ; for bzip2 support at runtime
3206 `(("ant-apache-bcel" ,ant-apache-bcel)
3207 ("ant-junit" ,ant-junit)
3208 ("java-testng" ,java-testng)
3209 ("java-commons-bcel" ,java-commons-bcel)
3210 ("java-jcommander" ,java-jcommander)
3211 ("jdk" ,icedtea-8 "jdk")
3212 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3214 (define-public htslib
3221 "https://github.com/samtools/htslib/releases/download/"
3222 version "/htslib-" version ".tar.bz2"))
3225 "1jsca3hg4rbr6iqq6imkj4lsvgl8g9768bcmny3hlff2w25vx24m"))))
3226 (build-system gnu-build-system)
3229 (modify-phases %standard-phases
3231 'unpack 'patch-tests
3233 (substitute* "test/test.pl"
3234 (("/bin/bash") (which "bash")))
3237 `(("openssl" ,openssl)
3242 (home-page "http://www.htslib.org")
3243 (synopsis "C library for reading/writing high-throughput sequencing data")
3245 "HTSlib is a C library for reading/writing high-throughput sequencing
3246 data. It also provides the @command{bgzip}, @command{htsfile}, and
3247 @command{tabix} utilities.")
3248 ;; Files under cram/ are released under the modified BSD license;
3249 ;; the rest is released under the Expat license
3250 (license (list license:expat license:bsd-3))))
3252 ;; This package should be removed once no packages rely upon it.
3260 "https://github.com/samtools/htslib/releases/download/"
3261 version "/htslib-" version ".tar.bz2"))
3264 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3273 "https://github.com/nboley/idr/archive/"
3275 (file-name (string-append name "-" version ".tar.gz"))
3278 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3279 ;; Delete generated C code.
3281 '(begin (delete-file "idr/inv_cdf.c") #t))))
3282 (build-system python-build-system)
3283 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3284 ;; are no longer part of this package. It also asserts False, which
3285 ;; causes the tests to always fail.
3286 (arguments `(#:tests? #f))
3288 `(("python-scipy" ,python-scipy)
3289 ("python-sympy" ,python-sympy)
3290 ("python-numpy" ,python-numpy)
3291 ("python-matplotlib" ,python-matplotlib)))
3293 `(("python-cython" ,python-cython)))
3294 (home-page "https://github.com/nboley/idr")
3295 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3297 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3298 to measure the reproducibility of findings identified from replicate
3299 experiments and provide highly stable thresholds based on reproducibility.")
3300 (license license:gpl2+)))
3302 (define-public jellyfish
3308 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3309 "releases/download/v" version
3310 "/jellyfish-" version ".tar.gz"))
3313 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3314 (build-system gnu-build-system)
3315 (outputs '("out" ;for library
3316 "ruby" ;for Ruby bindings
3317 "python")) ;for Python bindings
3320 (list (string-append "--enable-ruby-binding="
3321 (assoc-ref %outputs "ruby"))
3322 (string-append "--enable-python-binding="
3323 (assoc-ref %outputs "python")))
3325 (modify-phases %standard-phases
3326 (add-before 'check 'set-SHELL-variable
3328 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3330 (setenv "SHELL" (which "bash"))
3336 ("python" ,python-2)
3337 ("pkg-config" ,pkg-config)))
3339 `(("htslib" ,htslib)))
3340 (synopsis "Tool for fast counting of k-mers in DNA")
3342 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3343 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3344 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3345 is a command-line program that reads FASTA and multi-FASTA files containing
3346 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3347 translated into a human-readable text format using the @code{jellyfish dump}
3348 command, or queried for specific k-mers with @code{jellyfish query}.")
3349 (home-page "http://www.genome.umd.edu/jellyfish.html")
3350 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3351 (supported-systems '("x86_64-linux"))
3352 ;; The combined work is published under the GPLv3 or later. Individual
3353 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3354 (license (list license:gpl3+ license:expat))))
3356 (define-public khmer
3363 (uri (pypi-uri "khmer" version))
3366 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3367 (patches (search-patches "khmer-use-libraries.patch"))))
3368 (build-system python-build-system)
3371 (modify-phases %standard-phases
3372 (add-after 'unpack 'set-paths
3373 (lambda* (#:key inputs outputs #:allow-other-keys)
3374 ;; Delete bundled libraries.
3375 (delete-file-recursively "third-party/zlib")
3376 (delete-file-recursively "third-party/bzip2")
3377 ;; Replace bundled seqan.
3378 (let* ((seqan-all "third-party/seqan")
3379 (seqan-include (string-append
3380 seqan-all "/core/include")))
3381 (delete-file-recursively seqan-all)
3382 (copy-recursively (string-append (assoc-ref inputs "seqan")
3384 (string-append seqan-include "/seqan")))
3385 ;; We do not replace the bundled MurmurHash as the canonical
3386 ;; repository for this code 'SMHasher' is unsuitable for
3387 ;; providing a library. See
3388 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3390 (add-after 'unpack 'set-cc
3394 ;; It is simpler to test after installation.
3396 (add-after 'install 'post-install-check
3397 (lambda* (#:key inputs outputs #:allow-other-keys)
3398 (let ((out (assoc-ref outputs "out")))
3403 (assoc-ref outputs "out")
3405 (setenv "PYTHONPATH"
3407 (getenv "PYTHONPATH")
3411 (string-take (string-take-right
3412 (assoc-ref inputs "python") 5) 3)
3414 (with-directory-excursion "build"
3415 (zero? (system* "nosetests" "khmer" "--attr"
3416 "!known_failing")))))))))
3419 ("python-nose" ,python-nose)))
3423 ("python-screed" ,python-screed)
3424 ("python-bz2file" ,python-bz2file)
3425 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3426 ;; until the next version of khmer (likely 2.1) is released.
3428 (home-page "https://khmer.readthedocs.org/")
3429 (synopsis "K-mer counting, filtering and graph traversal library")
3430 (description "The khmer software is a set of command-line tools for
3431 working with DNA shotgun sequencing data from genomes, transcriptomes,
3432 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3433 sometimes better. Khmer can also identify and fix problems with shotgun
3435 ;; When building on i686, armhf and mips64el, we get the following error:
3436 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3437 (supported-systems '("x86_64-linux" "aarch64-linux"))
3438 (license license:bsd-3)))
3440 (define-public kaiju
3447 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3449 (file-name (string-append name "-" version ".tar.gz"))
3452 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3453 (build-system gnu-build-system)
3455 `(#:tests? #f ; There are no tests.
3457 (modify-phases %standard-phases
3459 (add-before 'build 'move-to-src-dir
3460 (lambda _ (chdir "src") #t))
3462 (lambda* (#:key inputs outputs #:allow-other-keys)
3463 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3466 (copy-recursively "bin" bin)
3467 (copy-recursively "util" bin))
3471 (home-page "http://kaiju.binf.ku.dk/")
3472 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3473 (description "Kaiju is a program for sensitive taxonomic classification
3474 of high-throughput sequencing reads from metagenomic whole genome sequencing
3476 (license license:gpl3+)))
3481 (version "2.1.0.20151222")
3484 (uri (pypi-uri "MACS2" version))
3487 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3488 (build-system python-build-system)
3490 `(#:python ,python-2 ; only compatible with Python 2.7
3491 #:tests? #f)) ; no test target
3493 `(("python-numpy" ,python2-numpy)))
3494 (home-page "https://github.com/taoliu/MACS/")
3495 (synopsis "Model based analysis for ChIP-Seq data")
3497 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3498 identifying transcript factor binding sites named Model-based Analysis of
3499 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3500 the significance of enriched ChIP regions and it improves the spatial
3501 resolution of binding sites through combining the information of both
3502 sequencing tag position and orientation.")
3503 (license license:bsd-3)))
3505 (define-public mafft
3512 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3513 "-without-extensions-src.tgz"))
3514 (file-name (string-append name "-" version ".tgz"))
3517 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3518 (build-system gnu-build-system)
3520 `(#:tests? #f ; no automated tests, though there are tests in the read me
3521 #:make-flags (let ((out (assoc-ref %outputs "out")))
3522 (list (string-append "PREFIX=" out)
3523 (string-append "BINDIR="
3524 (string-append out "/bin"))))
3526 (modify-phases %standard-phases
3527 (add-after 'unpack 'enter-dir
3528 (lambda _ (chdir "core") #t))
3529 (add-after 'enter-dir 'patch-makefile
3531 ;; on advice from the MAFFT authors, there is no need to
3532 ;; distribute mafft-profile, mafft-distance, or
3533 ;; mafft-homologs.rb as they are too "specialised".
3534 (substitute* "Makefile"
3535 ;; remove mafft-homologs.rb from SCRIPTS
3536 (("^SCRIPTS = mafft mafft-homologs.rb")
3538 ;; remove mafft-homologs from MANPAGES
3539 (("^MANPAGES = mafft.1 mafft-homologs.1")
3540 "MANPAGES = mafft.1")
3541 ;; remove mafft-distance from PROGS
3542 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3543 "PROGS = dvtditr dndfast7 dndblast sextet5")
3544 ;; remove mafft-profile from PROGS
3545 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3546 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3547 (("^rm -f mafft-profile mafft-profile.exe") "#")
3548 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3549 ;; do not install MAN pages in libexec folder
3550 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3551 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3553 (add-after 'enter-dir 'patch-paths
3554 (lambda* (#:key inputs #:allow-other-keys)
3555 (substitute* '("pairash.c"
3557 (("perl") (which "perl"))
3558 (("([\"`| ])awk" _ prefix)
3559 (string-append prefix (which "awk")))
3560 (("grep") (which "grep")))
3563 (add-after 'install 'wrap-programs
3564 (lambda* (#:key outputs #:allow-other-keys)
3565 (let* ((out (assoc-ref outputs "out"))
3566 (bin (string-append out "/bin"))
3567 (path (string-append
3568 (assoc-ref %build-inputs "coreutils") "/bin:")))
3569 (for-each (lambda (file)
3571 `("PATH" ":" prefix (,path))))
3579 ("coreutils" ,coreutils)))
3580 (home-page "http://mafft.cbrc.jp/alignment/software/")
3581 (synopsis "Multiple sequence alignment program")
3583 "MAFFT offers a range of multiple alignment methods for nucleotide and
3584 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3585 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3587 (license (license:non-copyleft
3588 "http://mafft.cbrc.jp/alignment/software/license.txt"
3589 "BSD-3 with different formatting"))))
3598 "https://github.com/marbl/mash/archive/v"
3600 (file-name (string-append name "-" version ".tar.gz"))
3603 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3604 (modules '((guix build utils)))
3606 ;; Delete bundled kseq.
3607 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3608 '(delete-file "src/mash/kseq.h"))))
3609 (build-system gnu-build-system)
3611 `(#:tests? #f ; No tests.
3614 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3615 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3616 #:make-flags (list "CC=gcc")
3618 (modify-phases %standard-phases
3619 (add-after 'unpack 'fix-includes
3621 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3622 (("^#include \"kseq\\.h\"")
3623 "#include \"htslib/kseq.h\""))
3625 (add-after 'fix-includes 'autoconf
3626 (lambda _ (zero? (system* "autoconf")))))))
3628 `(("autoconf" ,autoconf)
3629 ;; Capnproto and htslib are statically embedded in the final
3630 ;; application. Therefore we also list their licenses, below.
3631 ("capnproto" ,capnproto)
3632 ("htslib" ,htslib)))
3636 (supported-systems '("x86_64-linux"))
3637 (home-page "https://mash.readthedocs.io")
3638 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3639 (description "Mash is a fast sequence distance estimator that uses the
3640 MinHash algorithm and is designed to work with genomes and metagenomes in the
3641 form of assemblies or reads.")
3642 (license (list license:bsd-3 ; Mash
3643 license:expat ; HTSlib and capnproto
3644 license:public-domain ; MurmurHash 3
3645 license:cpl1.0)))) ; Open Bloom Filter
3647 (define-public metabat
3654 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3656 (file-name (string-append name "-" version ".tar.gz"))
3659 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3660 (patches (search-patches "metabat-fix-compilation.patch"))))
3661 (build-system scons-build-system)
3663 `(#:scons ,scons-python2
3665 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3666 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3667 #:tests? #f ;; Tests are run during the build phase.
3669 (modify-phases %standard-phases
3670 (add-after 'unpack 'fix-includes
3672 (substitute* "src/BamUtils.h"
3673 (("^#include \"bam/bam\\.h\"")
3674 "#include \"samtools/bam.h\"")
3675 (("^#include \"bam/sam\\.h\"")
3676 "#include \"samtools/sam.h\""))
3677 (substitute* "src/KseqReader.h"
3678 (("^#include \"bam/kseq\\.h\"")
3679 "#include \"htslib/kseq.h\""))
3681 (add-after 'unpack 'fix-scons
3682 (lambda* (#:key inputs #:allow-other-keys)
3683 (substitute* "SConstruct"
3684 (("^htslib_dir += 'samtools'")
3685 (string-append "htslib_dir = '"
3686 (assoc-ref inputs "htslib")
3688 (("^samtools_dir = 'samtools'")
3689 (string-append "samtools_dir = '"
3690 (assoc-ref inputs "samtools")
3692 (("^findStaticOrShared\\('bam', hts_lib")
3693 (string-append "findStaticOrShared('bam', '"
3694 (assoc-ref inputs "samtools")
3696 ;; Do not distribute README.
3697 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3702 ("samtools" ,samtools)
3705 (home-page "https://bitbucket.org/berkeleylab/metabat")
3707 "Reconstruction of single genomes from complex microbial communities")
3709 "Grouping large genomic fragments assembled from shotgun metagenomic
3710 sequences to deconvolute complex microbial communities, or metagenome binning,
3711 enables the study of individual organisms and their interactions. MetaBAT is
3712 an automated metagenome binning software, which integrates empirical
3713 probabilistic distances of genome abundance and tetranucleotide frequency.")
3714 ;; The source code contains inline assembly.
3715 (supported-systems '("x86_64-linux" "i686-linux"))
3716 (license (license:non-copyleft "file://license.txt"
3717 "See license.txt in the distribution."))))
3719 (define-public minced
3726 "https://github.com/ctSkennerton/minced/archive/"
3728 (file-name (string-append name "-" version ".tar.gz"))
3731 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3732 (build-system gnu-build-system)
3734 `(#:test-target "test"
3736 (modify-phases %standard-phases
3738 (add-before 'check 'fix-test
3740 ;; Fix test for latest version.
3741 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3742 (("minced:0.1.6") "minced:0.2.0"))
3744 (replace 'install ; No install target.
3745 (lambda* (#:key inputs outputs #:allow-other-keys)
3746 (let* ((out (assoc-ref outputs "out"))
3747 (bin (string-append out "/bin"))
3748 (wrapper (string-append bin "/minced")))
3749 ;; Minced comes with a wrapper script that tries to figure out where
3750 ;; it is located before running the JAR. Since these paths are known
3751 ;; to us, we build our own wrapper to avoid coreutils dependency.
3752 (install-file "minced.jar" bin)
3753 (with-output-to-file wrapper
3757 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3758 (assoc-ref inputs "jre") "/bin/java -jar "
3759 bin "/minced.jar \"$@\"\n"))))
3760 (chmod wrapper #o555)))))))
3762 `(("jdk" ,icedtea "jdk")))
3765 ("jre" ,icedtea "out")))
3766 (home-page "https://github.com/ctSkennerton/minced")
3767 (synopsis "Mining CRISPRs in Environmental Datasets")
3769 "MinCED is a program to find Clustered Regularly Interspaced Short
3770 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3771 unassembled metagenomic reads, but is mainly designed for full genomes and
3772 assembled metagenomic sequence.")
3773 (license license:gpl3+)))
3781 (uri (pypi-uri "misopy" version))
3784 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3785 (modules '((guix build utils)))
3787 '(substitute* "setup.py"
3788 ;; Use setuptools, or else the executables are not
3790 (("distutils.core") "setuptools")
3791 ;; use "gcc" instead of "cc" for compilation
3793 "cc.set_executables(
3797 linker_so='gcc -shared'); defines")))))
3798 (build-system python-build-system)
3800 `(#:python ,python-2 ; only Python 2 is supported
3801 #:tests? #f)) ; no "test" target
3803 `(("samtools" ,samtools)
3804 ("python-numpy" ,python2-numpy)
3805 ("python-pysam" ,python2-pysam)
3806 ("python-scipy" ,python2-scipy)
3807 ("python-matplotlib" ,python2-matplotlib)))
3809 `(("python-mock" ,python2-mock) ;for tests
3810 ("python-pytz" ,python2-pytz))) ;for tests
3811 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3812 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3814 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3815 the expression level of alternatively spliced genes from RNA-Seq data, and
3816 identifies differentially regulated isoforms or exons across samples. By
3817 modeling the generative process by which reads are produced from isoforms in
3818 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3819 that a read originated from a particular isoform.")
3820 (license license:gpl2)))
3822 (define-public muscle
3825 (version "3.8.1551")
3827 (method url-fetch/tarbomb)
3829 "http://www.drive5.com/muscle/muscle_src_"
3833 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3834 (build-system gnu-build-system)
3836 `(#:make-flags (list "LDLIBS = -lm")
3838 (modify-phases %standard-phases
3841 ;; There are no tests, so just test if it runs.
3842 (lambda _ (zero? (system* "./muscle" "-version"))))
3844 (lambda* (#:key outputs #:allow-other-keys)
3845 (let* ((out (assoc-ref outputs "out"))
3846 (bin (string-append out "/bin")))
3847 (install-file "muscle" bin)))))))
3848 (home-page "http://www.drive5.com/muscle")
3849 (synopsis "Multiple sequence alignment program")
3851 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3852 program for nucleotide and protein sequences.")
3853 ;; License information found in 'muscle -h' and usage.cpp.
3854 (license license:public-domain)))
3856 (define-public newick-utils
3857 ;; There are no recent releases so we package from git.
3858 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3860 (name "newick-utils")
3861 (version (string-append "1.6-1." (string-take commit 8)))
3865 (url "https://github.com/tjunier/newick_utils.git")
3867 (file-name (string-append name "-" version "-checkout"))
3870 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3871 (build-system gnu-build-system)
3874 (modify-phases %standard-phases
3875 (add-after 'unpack 'autoconf
3876 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3878 ;; XXX: TODO: Enable Lua and Guile bindings.
3879 ;; https://github.com/tjunier/newick_utils/issues/13
3880 `(("libxml2" ,libxml2)
3884 `(("autoconf" ,autoconf)
3885 ("automake" ,automake)
3886 ("libtool" ,libtool)))
3887 (synopsis "Programs for working with newick format phylogenetic trees")
3889 "Newick-utils is a suite of utilities for processing phylogenetic trees
3890 in Newick format. Functions include re-rooting, extracting subtrees,
3891 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3892 (home-page "https://github.com/tjunier/newick_utils")
3893 (license license:bsd-3))))
3902 "https://github.com/wwood/OrfM/releases/download/v"
3903 version "/orfm-" version ".tar.gz"))
3906 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3907 (build-system gnu-build-system)
3908 (inputs `(("zlib" ,zlib)))
3910 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3911 ("ruby-rspec" ,ruby-rspec)
3913 (synopsis "Simple and not slow open reading frame (ORF) caller")
3915 "An ORF caller finds stretches of DNA that, when translated, are not
3916 interrupted by stop codons. OrfM finds and prints these ORFs.")
3917 (home-page "https://github.com/wwood/OrfM")
3918 (license license:lgpl3+)))
3920 (define-public pplacer
3921 (let ((commit "g807f6f3"))
3924 ;; The commit should be updated with each version change.
3925 (version "1.1.alpha19")
3929 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3931 (file-name (string-append name "-" version ".tar.gz"))
3933 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3934 (build-system ocaml-build-system)
3936 `(#:ocaml ,ocaml-4.01
3937 #:findlib ,ocaml4.01-findlib
3938 #:modules ((guix build ocaml-build-system)
3942 (modify-phases %standard-phases
3944 (add-after 'unpack 'replace-bundled-cddlib
3945 (lambda* (#:key inputs #:allow-other-keys)
3946 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3947 (local-dir "cddlib_guix"))
3949 (with-directory-excursion local-dir
3950 (system* "tar" "xvf" cddlib-src))
3951 (let ((cddlib-src-folder
3952 (string-append local-dir "/"
3953 (list-ref (scandir local-dir) 2)
3958 (string-append "cdd_src/" (basename file))))
3959 (find-files cddlib-src-folder ".*[ch]$")))
3961 (add-after 'unpack 'fix-makefile
3963 ;; Remove system calls to 'git'.
3964 (substitute* "Makefile"
3965 (("^DESCRIPT:=pplacer-.*")
3967 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3968 (substitute* "myocamlbuild.ml"
3969 (("git describe --tags --long .*\\\" with")
3971 "echo -n v" ,version "-" ,commit "\" with")))
3974 (lambda* (#:key outputs #:allow-other-keys)
3975 (let* ((out (assoc-ref outputs "out"))
3976 (bin (string-append out "/bin")))
3977 (copy-recursively "bin" bin))
3982 ("ocaml-ounit" ,ocaml4.01-ounit)
3983 ("ocaml-batteries" ,ocaml4.01-batteries)
3984 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3985 ("ocaml-csv" ,ocaml4.01-csv)
3986 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3987 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3988 ("ocaml-mcl" ,ocaml4.01-mcl)
3989 ("ocaml-gsl" ,ocaml4.01-gsl)
3990 ("cddlib-src" ,(package-source cddlib))))
3992 `(("pplacer-scripts" ,pplacer-scripts)))
3993 (synopsis "Phylogenetic placement of biological sequences")
3995 "Pplacer places query sequences on a fixed reference phylogenetic tree
3996 to maximize phylogenetic likelihood or posterior probability according to a
3997 reference alignment. Pplacer is designed to be fast, to give useful
3998 information about uncertainty, and to offer advanced visualization and
3999 downstream analysis.")
4000 (home-page "http://matsen.fhcrc.org/pplacer")
4001 (license license:gpl3))))
4003 ;; This package is installed alongside 'pplacer'. It is a separate package so
4004 ;; that it can use the python-build-system for the scripts that are
4005 ;; distributed alongside the main OCaml binaries.
4006 (define pplacer-scripts
4009 (name "pplacer-scripts")
4010 (build-system python-build-system)
4012 `(#:python ,python-2
4014 (modify-phases %standard-phases
4015 (add-after 'unpack 'enter-scripts-dir
4016 (lambda _ (chdir "scripts")))
4019 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4020 (add-after 'install 'wrap-executables
4021 (lambda* (#:key inputs outputs #:allow-other-keys)
4022 (let* ((out (assoc-ref outputs "out"))
4023 (bin (string-append out "/bin")))
4024 (let ((path (string-append
4025 (assoc-ref inputs "hmmer") "/bin:"
4026 (assoc-ref inputs "infernal") "/bin")))
4028 (wrap-program (string-append bin "/refpkg_align.py")
4029 `("PATH" ":" prefix (,path))))
4030 (let ((path (string-append
4031 (assoc-ref inputs "hmmer") "/bin")))
4032 (wrap-program (string-append bin "/hrefpkg_query.py")
4033 `("PATH" ":" prefix (,path)))))
4036 `(("infernal" ,infernal)
4039 `(("python-biopython" ,python2-biopython)
4040 ("taxtastic" ,taxtastic)))
4041 (synopsis "Pplacer Python scripts")))
4043 (define-public python2-pbcore
4045 (name "python2-pbcore")
4049 (uri (pypi-uri "pbcore" version))
4052 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4053 (build-system python-build-system)
4054 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4056 `(("python-cython" ,python2-cython)
4057 ("python-numpy" ,python2-numpy)
4058 ("python-pysam" ,python2-pysam)
4059 ("python-h5py" ,python2-h5py)))
4061 `(("python-nose" ,python2-nose)
4062 ("python-sphinx" ,python2-sphinx)
4063 ("python-pyxb" ,python2-pyxb)))
4064 (home-page "http://pacificbiosciences.github.io/pbcore/")
4065 (synopsis "Library for reading and writing PacBio data files")
4067 "The pbcore package provides Python APIs for interacting with PacBio data
4068 files and writing bioinformatics applications.")
4069 (license license:bsd-3)))
4071 (define-public python2-warpedlmm
4073 (name "python2-warpedlmm")
4079 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4083 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4084 (build-system python-build-system)
4086 `(#:python ,python-2)) ; requires Python 2.7
4088 `(("python-scipy" ,python2-scipy)
4089 ("python-numpy" ,python2-numpy)
4090 ("python-matplotlib" ,python2-matplotlib)
4091 ("python-fastlmm" ,python2-fastlmm)
4092 ("python-pandas" ,python2-pandas)
4093 ("python-pysnptools" ,python2-pysnptools)))
4095 `(("python-mock" ,python2-mock)
4096 ("python-nose" ,python2-nose)
4098 (home-page "https://github.com/PMBio/warpedLMM")
4099 (synopsis "Implementation of warped linear mixed models")
4101 "WarpedLMM is a Python implementation of the warped linear mixed model,
4102 which automatically learns an optimal warping function (or transformation) for
4103 the phenotype as it models the data.")
4104 (license license:asl2.0)))
4106 (define-public pbtranscript-tofu
4107 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4109 (name "pbtranscript-tofu")
4110 (version (string-append "2.2.3." (string-take commit 7)))
4114 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4116 (file-name (string-append name "-" version "-checkout"))
4119 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4120 (modules '((guix build utils)))
4123 ;; remove bundled Cython sources
4124 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4126 (build-system python-build-system)
4128 `(#:python ,python-2
4129 ;; FIXME: Tests fail with "No such file or directory:
4130 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4133 (modify-phases %standard-phases
4134 (add-after 'unpack 'enter-directory
4136 (chdir "pbtranscript-tofu/pbtranscript/")
4138 ;; With setuptools version 18.0 and later this setup.py hack causes
4139 ;; a build error, so we disable it.
4140 (add-after 'enter-directory 'patch-setuppy
4142 (substitute* "setup.py"
4143 (("if 'setuptools.extension' in sys.modules:")
4147 `(("python-numpy" ,python2-numpy)
4148 ("python-bx-python" ,python2-bx-python)
4149 ("python-networkx" ,python2-networkx)
4150 ("python-scipy" ,python2-scipy)
4151 ("python-pbcore" ,python2-pbcore)
4152 ("python-h5py" ,python2-h5py)))
4154 `(("python-cython" ,python2-cython)
4155 ("python-nose" ,python2-nose)))
4156 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4157 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4159 "pbtranscript-tofu contains scripts to analyze transcriptome data
4160 generated using the PacBio Iso-Seq protocol.")
4161 (license license:bsd-3))))
4163 (define-public prank
4170 "http://wasabiapp.org/download/prank/prank.source."
4174 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4175 (build-system gnu-build-system)
4178 (modify-phases %standard-phases
4179 (add-after 'unpack 'enter-src-dir
4183 (add-after 'unpack 'remove-m64-flag
4184 ;; Prank will build with the correct 'bit-ness' without this flag
4185 ;; and this allows building on 32-bit machines.
4186 (lambda _ (substitute* "src/Makefile"
4191 (lambda* (#:key outputs #:allow-other-keys)
4192 (let* ((out (assoc-ref outputs "out"))
4193 (bin (string-append out "/bin"))
4194 (man (string-append out "/share/man/man1"))
4195 (path (string-append
4196 (assoc-ref %build-inputs "mafft") "/bin:"
4197 (assoc-ref %build-inputs "exonerate") "/bin:"
4198 (assoc-ref %build-inputs "bppsuite") "/bin")))
4199 (install-file "prank" bin)
4200 (wrap-program (string-append bin "/prank")
4201 `("PATH" ":" prefix (,path)))
4202 (install-file "prank.1" man))
4206 ("exonerate" ,exonerate)
4207 ("bppsuite" ,bppsuite)))
4208 (home-page "http://wasabiapp.org/software/prank/")
4209 (synopsis "Probabilistic multiple sequence alignment program")
4211 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4212 codon and amino-acid sequences. It is based on a novel algorithm that treats
4213 insertions correctly and avoids over-estimation of the number of deletion
4214 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4215 in phylogenetics and correctly takes into account the evolutionary distances
4216 between sequences. Lastly, PRANK allows for defining a potential structure
4217 for sequences to be aligned and then, simultaneously with the alignment,
4218 predicts the locations of structural units in the sequences.")
4219 (license license:gpl2+)))
4221 (define-public proteinortho
4223 (name "proteinortho")
4230 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4231 version "_src.tar.gz"))
4234 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4235 (build-system gnu-build-system)
4237 `(#:test-target "test"
4239 (modify-phases %standard-phases
4241 ;; There is no configure script, so we modify the Makefile directly.
4242 (lambda* (#:key outputs #:allow-other-keys)
4243 (substitute* "Makefile"
4246 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4248 (add-before 'install 'make-install-directory
4249 ;; The install directory is not created during 'make install'.
4250 (lambda* (#:key outputs #:allow-other-keys)
4251 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4253 (add-after 'install 'wrap-programs
4254 (lambda* (#:key inputs outputs #:allow-other-keys)
4255 (let* ((path (getenv "PATH"))
4256 (out (assoc-ref outputs "out"))
4257 (binary (string-append out "/bin/proteinortho5.pl")))
4258 (wrap-program binary `("PATH" ":" prefix (,path))))
4262 ("python" ,python-2)
4263 ("blast+" ,blast+)))
4264 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4265 (synopsis "Detect orthologous genes across species")
4267 "Proteinortho is a tool to detect orthologous genes across different
4268 species. For doing so, it compares similarities of given gene sequences and
4269 clusters them to find significant groups. The algorithm was designed to handle
4270 large-scale data and can be applied to hundreds of species at once.")
4271 (license license:gpl2+)))
4273 (define-public pyicoteo
4280 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4281 "pyicoteo/get/v" version ".tar.bz2"))
4282 (file-name (string-append name "-" version ".tar.bz2"))
4285 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4286 (build-system python-build-system)
4288 `(#:python ,python-2 ; does not work with Python 3
4289 #:tests? #f)) ; there are no tests
4291 `(("python2-matplotlib" ,python2-matplotlib)))
4292 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4293 (synopsis "Analyze high-throughput genetic sequencing data")
4295 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4296 sequencing data. It works with genomic coordinates. There are currently six
4297 different command-line tools:
4300 @item pyicoregion: for generating exploratory regions automatically;
4301 @item pyicoenrich: for differential enrichment between two conditions;
4302 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4303 @item pyicos: for genomic coordinates manipulation;
4304 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4305 @item pyicount: to count how many reads from N experiment files overlap in a
4307 @item pyicotrocol: to combine operations from pyicoteo.
4309 (license license:gpl3+)))
4311 (define-public prodigal
4318 "https://github.com/hyattpd/Prodigal/archive/v"
4320 (file-name (string-append name "-" version ".tar.gz"))
4323 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4324 (build-system gnu-build-system)
4326 `(#:tests? #f ;no check target
4327 #:make-flags (list (string-append "INSTALLDIR="
4328 (assoc-ref %outputs "out")
4331 (modify-phases %standard-phases
4332 (delete 'configure))))
4333 (home-page "http://prodigal.ornl.gov")
4334 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4336 "Prodigal runs smoothly on finished genomes, draft genomes, and
4337 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4338 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4339 partial genes, and identifies translation initiation sites.")
4340 (license license:gpl3+)))
4342 (define-public roary
4350 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4354 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4355 (build-system perl-build-system)
4358 (modify-phases %standard-phases
4363 ;; The tests are not run by default, so we run each test file
4365 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4367 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4368 (getenv "PERL5LIB")))
4369 (zero? (length (filter (lambda (file)
4370 (display file)(display "\n")
4371 (not (zero? (system* "perl" file))))
4372 (find-files "t" ".*\\.t$"))))))
4374 ;; There is no 'install' target in the Makefile.
4375 (lambda* (#:key outputs #:allow-other-keys)
4376 (let* ((out (assoc-ref outputs "out"))
4377 (bin (string-append out "/bin"))
4378 (perl (string-append out "/lib/perl5/site_perl"))
4379 (roary-plots "contrib/roary_plots"))
4382 (copy-recursively "bin" bin)
4383 (copy-recursively "lib" perl)
4385 (add-after 'install 'wrap-programs
4386 (lambda* (#:key inputs outputs #:allow-other-keys)
4387 (let* ((out (assoc-ref outputs "out"))
4388 (perl5lib (getenv "PERL5LIB"))
4389 (path (getenv "PATH")))
4390 (for-each (lambda (prog)
4391 (let ((binary (string-append out "/" prog)))
4392 (wrap-program binary
4393 `("PERL5LIB" ":" prefix
4394 (,(string-append perl5lib ":" out
4395 "/lib/perl5/site_perl"))))
4396 (wrap-program binary
4398 (,(string-append path ":" out "/bin"))))))
4399 (find-files "bin" ".*[^R]$"))
4401 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4402 (r-site-lib (getenv "R_LIBS_SITE"))
4404 (string-append (assoc-ref inputs "coreutils") "/bin")))
4406 `("R_LIBS_SITE" ":" prefix
4407 (,(string-append r-site-lib ":" out "/site-library/"))))
4410 (,(string-append coreutils-path ":" out "/bin"))))))
4413 `(("perl-env-path" ,perl-env-path)
4414 ("perl-test-files" ,perl-test-files)
4415 ("perl-test-most" ,perl-test-most)
4416 ("perl-test-output" ,perl-test-output)))
4418 `(("perl-array-utils" ,perl-array-utils)
4419 ("bioperl" ,bioperl-minimal)
4420 ("perl-digest-md5-file" ,perl-digest-md5-file)
4421 ("perl-exception-class" ,perl-exception-class)
4422 ("perl-file-find-rule" ,perl-file-find-rule)
4423 ("perl-file-grep" ,perl-file-grep)
4424 ("perl-file-slurper" ,perl-file-slurper)
4425 ("perl-file-which" ,perl-file-which)
4426 ("perl-graph" ,perl-graph)
4427 ("perl-graph-readwrite" ,perl-graph-readwrite)
4428 ("perl-log-log4perl" ,perl-log-log4perl)
4429 ("perl-moose" ,perl-moose)
4430 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4431 ("perl-text-csv" ,perl-text-csv)
4432 ("bedtools" ,bedtools)
4436 ("parallel" ,parallel)
4439 ("fasttree" ,fasttree)
4443 ("r-minimal" ,r-minimal)
4444 ("r-ggplot2" ,r-ggplot2)
4445 ("coreutils" ,coreutils)))
4446 (home-page "http://sanger-pathogens.github.io/Roary")
4447 (synopsis "High speed stand-alone pan genome pipeline")
4449 "Roary is a high speed stand alone pan genome pipeline, which takes
4450 annotated assemblies in GFF3 format (produced by the Prokka program) and
4451 calculates the pan genome. Using a standard desktop PC, it can analyse
4452 datasets with thousands of samples, without compromising the quality of the
4453 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4454 single processor. Roary is not intended for metagenomics or for comparing
4455 extremely diverse sets of genomes.")
4456 (license license:gpl3)))
4458 (define-public raxml
4467 "https://github.com/stamatak/standard-RAxML/archive/v"
4469 (file-name (string-append name "-" version ".tar.gz"))
4472 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4473 (build-system gnu-build-system)
4475 `(#:tests? #f ; There are no tests.
4476 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4477 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4479 (modify-phases %standard-phases
4482 (lambda* (#:key outputs #:allow-other-keys)
4483 (let* ((out (assoc-ref outputs "out"))
4484 (bin (string-append out "/bin"))
4485 (executable "raxmlHPC-HYBRID"))
4486 (install-file executable bin)
4487 (symlink (string-append bin "/" executable) "raxml"))
4490 `(("openmpi" ,openmpi)))
4491 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4492 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4494 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4496 ;; The source includes x86 specific code
4497 (supported-systems '("x86_64-linux" "i686-linux"))
4498 (license license:gpl2+)))
4508 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4511 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4512 (patches (search-patches "rsem-makefile.patch"))
4513 (modules '((guix build utils)))
4516 ;; remove bundled copy of boost
4517 (delete-file-recursively "boost")
4519 (build-system gnu-build-system)
4521 `(#:tests? #f ;no "check" target
4523 (modify-phases %standard-phases
4524 ;; No "configure" script.
4525 ;; Do not build bundled samtools library.
4528 (substitute* "Makefile"
4529 (("^all : sam/libbam.a") "all : "))
4532 (lambda* (#:key outputs #:allow-other-keys)
4533 (let* ((out (string-append (assoc-ref outputs "out")))
4534 (bin (string-append out "/bin/"))
4535 (perl (string-append out "/lib/perl5/site_perl")))
4538 (for-each (lambda (file)
4539 (install-file file bin))
4540 (find-files "." "rsem-.*"))
4541 (install-file "rsem_perl_utils.pm" perl))
4544 'install 'wrap-program
4545 (lambda* (#:key outputs #:allow-other-keys)
4546 (let ((out (assoc-ref outputs "out")))
4547 (for-each (lambda (prog)
4548 (wrap-program (string-append out "/bin/" prog)
4549 `("PERL5LIB" ":" prefix
4550 (,(string-append out "/lib/perl5/site_perl")))))
4551 '("rsem-plot-transcript-wiggles"
4552 "rsem-calculate-expression"
4553 "rsem-generate-ngvector"
4555 "rsem-prepare-reference")))
4559 ("ncurses" ,ncurses)
4560 ("r-minimal" ,r-minimal)
4562 ("samtools" ,samtools-0.1)
4564 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4565 (synopsis "Estimate gene expression levels from RNA-Seq data")
4567 "RSEM is a software package for estimating gene and isoform expression
4568 levels from RNA-Seq data. The RSEM package provides a user-friendly
4569 interface, supports threads for parallel computation of the EM algorithm,
4570 single-end and paired-end read data, quality scores, variable-length reads and
4571 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4572 interval estimates for expression levels. For visualization, it can generate
4573 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4574 (license license:gpl3+)))
4576 (define-public rseqc
4584 (string-append "mirror://sourceforge/rseqc/"
4585 "RSeQC-" version ".tar.gz"))
4587 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4588 (modules '((guix build utils)))
4591 ;; remove bundled copy of pysam
4592 (delete-file-recursively "lib/pysam")
4593 (substitute* "setup.py"
4594 ;; remove dependency on outdated "distribute" module
4595 (("^from distribute_setup import use_setuptools") "")
4596 (("^use_setuptools\\(\\)") "")
4597 ;; do not use bundled copy of pysam
4598 (("^have_pysam = False") "have_pysam = True"))))))
4599 (build-system python-build-system)
4600 (arguments `(#:python ,python-2))
4602 `(("python-cython" ,python2-cython)
4603 ("python-pysam" ,python2-pysam)
4604 ("python-numpy" ,python2-numpy)
4607 `(("python-nose" ,python2-nose)))
4608 (home-page "http://rseqc.sourceforge.net/")
4609 (synopsis "RNA-seq quality control package")
4611 "RSeQC provides a number of modules that can comprehensively evaluate
4612 high throughput sequence data, especially RNA-seq data. Some basic modules
4613 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4614 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4615 distribution, coverage uniformity, strand specificity, etc.")
4616 (license license:gpl3+)))
4619 ;; There are no release tarballs. According to the installation
4620 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4621 ;; stable release is identified by this changeset ID.
4622 (let ((changeset "2329130")
4626 (version (string-append "0-" revision "." changeset))
4630 (url "https://bitbucket.org/libsleipnir/sleipnir")
4631 (changeset changeset)))
4634 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4635 (build-system gnu-build-system)
4637 `(#:modules ((srfi srfi-1)
4638 (guix build gnu-build-system)
4641 (let ((dirs '("SeekMiner"
4647 (modify-phases %standard-phases
4648 (add-before 'configure 'bootstrap
4650 (zero? (system* "bash" "gen_auto"))))
4651 (add-after 'build 'build-additional-tools
4652 (lambda* (#:key make-flags #:allow-other-keys)
4653 (every (lambda (dir)
4654 (with-directory-excursion (string-append "tools/" dir)
4655 (zero? (apply system* "make" make-flags))))
4657 (add-after 'install 'install-additional-tools
4658 (lambda* (#:key make-flags #:allow-other-keys)
4659 (fold (lambda (dir result)
4660 (with-directory-excursion (string-append "tools/" dir)
4662 (zero? (apply system*
4663 `("make" ,@make-flags "install"))))))
4669 ("readline" ,readline)
4670 ("gengetopt" ,gengetopt)
4671 ("log4cpp" ,log4cpp)))
4673 `(("autoconf" ,autoconf)
4674 ("automake" ,automake)
4676 (home-page "http://seek.princeton.edu")
4677 (synopsis "Gene co-expression search engine")
4679 "SEEK is a computational gene co-expression search engine. SEEK provides
4680 biologists with a way to navigate the massive human expression compendium that
4681 now contains thousands of expression datasets. SEEK returns a robust ranking
4682 of co-expressed genes in the biological area of interest defined by the user's
4683 query genes. It also prioritizes thousands of expression datasets according
4684 to the user's query of interest.")
4685 (license license:cc-by3.0))))
4687 (define-public samtools
4695 (string-append "mirror://sourceforge/samtools/samtools/"
4696 version "/samtools-" version ".tar.bz2"))
4699 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4700 (build-system gnu-build-system)
4702 `(#:modules ((ice-9 ftw)
4704 (guix build gnu-build-system)
4706 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4707 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4709 (modify-phases %standard-phases
4710 (add-after 'unpack 'patch-tests
4712 (substitute* "test/test.pl"
4713 ;; The test script calls out to /bin/bash
4714 (("/bin/bash") (which "bash")))
4716 (add-after 'install 'install-library
4717 (lambda* (#:key outputs #:allow-other-keys)
4718 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4719 (install-file "libbam.a" lib)
4721 (add-after 'install 'install-headers
4722 (lambda* (#:key outputs #:allow-other-keys)
4723 (let ((include (string-append (assoc-ref outputs "out")
4724 "/include/samtools/")))
4725 (for-each (lambda (file)
4726 (install-file file include))
4727 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4729 (native-inputs `(("pkg-config" ,pkg-config)))
4731 `(("htslib" ,htslib)
4732 ("ncurses" ,ncurses)
4736 (home-page "http://samtools.sourceforge.net")
4737 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4739 "Samtools implements various utilities for post-processing nucleotide
4740 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4741 variant calling (in conjunction with bcftools), and a simple alignment
4743 (license license:expat)))
4745 (define-public samtools-0.1
4746 ;; This is the most recent version of the 0.1 line of samtools. The input
4747 ;; and output formats differ greatly from that used and produced by samtools
4748 ;; 1.x and is still used in many bioinformatics pipelines.
4749 (package (inherit samtools)
4755 (string-append "mirror://sourceforge/samtools/samtools/"
4756 version "/samtools-" version ".tar.bz2"))
4758 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4760 `(#:tests? #f ;no "check" target
4761 ,@(substitute-keyword-arguments (package-arguments samtools)
4762 ((#:make-flags flags)
4763 `(cons "LIBCURSES=-lncurses" ,flags))
4765 `(modify-phases ,phases
4767 (lambda* (#:key outputs #:allow-other-keys)
4768 (let ((bin (string-append
4769 (assoc-ref outputs "out") "/bin")))
4771 (install-file "samtools" bin)
4773 (delete 'patch-tests)
4774 (delete 'configure))))))))
4776 (define-public mosaik
4777 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4782 ;; There are no release tarballs nor tags.
4785 (url "https://github.com/wanpinglee/MOSAIK.git")
4787 (file-name (string-append name "-" version))
4790 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4791 (build-system gnu-build-system)
4793 `(#:tests? #f ; no tests
4794 #:make-flags (list "CC=gcc")
4796 (modify-phases %standard-phases
4798 (lambda _ (chdir "src") #t))
4800 (lambda* (#:key outputs #:allow-other-keys)
4801 (let ((bin (string-append (assoc-ref outputs "out")
4804 (copy-recursively "../bin" bin)
4809 (supported-systems '("x86_64-linux"))
4810 (home-page "https://github.com/wanpinglee/MOSAIK")
4811 (synopsis "Map nucleotide sequence reads to reference genomes")
4813 "MOSAIK is a program for mapping second and third-generation sequencing
4814 reads to a reference genome. MOSAIK can align reads generated by all the
4815 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4816 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4817 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4818 ;; code released into the public domain:
4819 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4820 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4821 (license (list license:gpl2+ license:public-domain)))))
4823 (define-public ngs-sdk
4831 (string-append "https://github.com/ncbi/ngs/archive/"
4833 (file-name (string-append name "-" version ".tar.gz"))
4836 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4837 (build-system gnu-build-system)
4839 `(#:parallel-build? #f ; not supported
4840 #:tests? #f ; no "check" target
4842 (modify-phases %standard-phases
4844 (lambda* (#:key outputs #:allow-other-keys)
4845 (let ((out (assoc-ref outputs "out")))
4846 ;; Allow 'konfigure.perl' to find 'package.prl'.
4848 (string-append ".:" (getenv "PERL5LIB")))
4850 ;; The 'configure' script doesn't recognize things like
4851 ;; '--enable-fast-install'.
4852 (zero? (system* "./configure"
4853 (string-append "--build-prefix=" (getcwd) "/build")
4854 (string-append "--prefix=" out))))))
4855 (add-after 'unpack 'enter-dir
4856 (lambda _ (chdir "ngs-sdk") #t)))))
4857 (native-inputs `(("perl" ,perl)))
4858 ;; According to the test
4859 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4860 ;; in ngs-sdk/setup/konfigure.perl
4861 (supported-systems '("i686-linux" "x86_64-linux"))
4862 (home-page "https://github.com/ncbi/ngs")
4863 (synopsis "API for accessing Next Generation Sequencing data")
4865 "NGS is a domain-specific API for accessing reads, alignments and pileups
4866 produced from Next Generation Sequencing. The API itself is independent from
4867 any particular back-end implementation, and supports use of multiple back-ends
4869 (license license:public-domain)))
4871 (define-public java-ngs
4872 (package (inherit ngs-sdk)
4875 `(,@(substitute-keyword-arguments
4876 `(#:modules ((guix build gnu-build-system)
4880 ,@(package-arguments ngs-sdk))
4882 `(modify-phases ,phases
4883 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4885 `(("jdk" ,icedtea "jdk")
4886 ("ngs-sdk" ,ngs-sdk)))
4887 (synopsis "Java bindings for NGS SDK")))
4889 (define-public ncbi-vdb
4897 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4899 (file-name (string-append name "-" version ".tar.gz"))
4902 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4903 (build-system gnu-build-system)
4905 `(#:parallel-build? #f ; not supported
4906 #:tests? #f ; no "check" target
4908 (modify-phases %standard-phases
4909 (add-before 'configure 'set-perl-search-path
4911 ;; Work around "dotless @INC" build failure.
4913 (string-append (getcwd) "/setup:"
4914 (getenv "PERL5LIB")))
4917 (lambda* (#:key inputs outputs #:allow-other-keys)
4918 (let ((out (assoc-ref outputs "out")))
4919 ;; Override include path for libmagic
4920 (substitute* "setup/package.prl"
4921 (("name => 'magic', Include => '/usr/include'")
4922 (string-append "name=> 'magic', Include => '"
4923 (assoc-ref inputs "libmagic")
4926 ;; Install kdf5 library (needed by sra-tools)
4927 (substitute* "build/Makefile.install"
4928 (("LIBRARIES_TO_INSTALL =")
4929 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4931 (substitute* "build/Makefile.env"
4932 (("CFLAGS =" prefix)
4933 (string-append prefix "-msse2 ")))
4935 ;; Override search path for ngs-java
4936 (substitute* "setup/package.prl"
4937 (("/usr/local/ngs/ngs-java")
4938 (assoc-ref inputs "java-ngs")))
4940 ;; The 'configure' script doesn't recognize things like
4941 ;; '--enable-fast-install'.
4944 (string-append "--build-prefix=" (getcwd) "/build")
4945 (string-append "--prefix=" (assoc-ref outputs "out"))
4946 (string-append "--debug")
4947 (string-append "--with-xml2-prefix="
4948 (assoc-ref inputs "libxml2"))
4949 (string-append "--with-ngs-sdk-prefix="
4950 (assoc-ref inputs "ngs-sdk"))
4951 (string-append "--with-hdf5-prefix="
4952 (assoc-ref inputs "hdf5")))))))
4953 (add-after 'install 'install-interfaces
4954 (lambda* (#:key outputs #:allow-other-keys)
4955 ;; Install interface libraries. On i686 the interface libraries
4956 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4957 ;; architecture name ("i386") instead of the target system prefix
4959 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4960 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4961 ,(system->linux-architecture
4962 (or (%current-target-system)
4965 (string-append (assoc-ref outputs "out")
4967 ;; Install interface headers
4968 (copy-recursively "interfaces"
4969 (string-append (assoc-ref outputs "out")
4972 ;; These files are needed by sra-tools.
4973 (add-after 'install 'install-configuration-files
4974 (lambda* (#:key outputs #:allow-other-keys)
4975 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4977 (install-file "libs/kfg/default.kfg" target)
4978 (install-file "libs/kfg/certs.kfg" target))
4981 `(("libxml2" ,libxml2)
4982 ("ngs-sdk" ,ngs-sdk)
4983 ("java-ngs" ,java-ngs)
4986 (native-inputs `(("perl" ,perl)))
4987 ;; NCBI-VDB requires SSE capability.
4988 (supported-systems '("i686-linux" "x86_64-linux"))
4989 (home-page "https://github.com/ncbi/ncbi-vdb")
4990 (synopsis "Database engine for genetic information")
4992 "The NCBI-VDB library implements a highly compressed columnar data
4993 warehousing engine that is most often used to store genetic information.
4994 Databases are stored in a portable image within the file system, and can be
4995 accessed/downloaded on demand across HTTP.")
4996 (license license:public-domain)))
4998 (define-public plink
5006 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5007 version "-src.zip"))
5009 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5010 (patches (search-patches "plink-1.07-unclobber-i.patch"
5011 "plink-endian-detection.patch"))))
5012 (build-system gnu-build-system)
5014 '(#:tests? #f ;no "check" target
5015 #:make-flags (list (string-append "LIB_LAPACK="
5016 (assoc-ref %build-inputs "lapack")
5017 "/lib/liblapack.so")
5020 ;; disable phoning home
5023 (modify-phases %standard-phases
5024 ;; no "configure" script
5027 (lambda* (#:key outputs #:allow-other-keys)
5028 (let ((bin (string-append (assoc-ref outputs "out")
5030 (install-file "plink" bin)
5034 ("lapack" ,lapack)))
5036 `(("unzip" ,unzip)))
5037 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5038 (synopsis "Whole genome association analysis toolset")
5040 "PLINK is a whole genome association analysis toolset, designed to
5041 perform a range of basic, large-scale analyses in a computationally efficient
5042 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5043 so there is no support for steps prior to this (e.g. study design and
5044 planning, generating genotype or CNV calls from raw data). Through
5045 integration with gPLINK and Haploview, there is some support for the
5046 subsequent visualization, annotation and storage of results.")
5047 ;; Code is released under GPLv2, except for fisher.h, which is under
5049 (license (list license:gpl2 license:lgpl2.1+))))
5051 (define-public plink-ng
5052 (package (inherit plink)
5058 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5060 (file-name (string-append name "-" version ".tar.gz"))
5062 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5063 (build-system gnu-build-system)
5065 '(#:tests? #f ;no "check" target
5066 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5067 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5069 "-f" "Makefile.std")
5071 (modify-phases %standard-phases
5072 (add-after 'unpack 'chdir
5073 (lambda _ (chdir "1.9") #t))
5074 (delete 'configure) ; no "configure" script
5076 (lambda* (#:key outputs #:allow-other-keys)
5077 (let ((bin (string-append (assoc-ref outputs "out")
5079 (install-file "plink" bin)
5084 ("openblas" ,openblas)))
5085 (home-page "https://www.cog-genomics.org/plink/")
5086 (license license:gpl3+)))
5088 (define-public smithlab-cpp
5089 (let ((revision "1")
5090 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5092 (name "smithlab-cpp")
5093 (version (string-append "0." revision "." (string-take commit 7)))
5097 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5099 (file-name (string-append name "-" version "-checkout"))
5102 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5103 (build-system gnu-build-system)
5105 `(#:modules ((guix build gnu-build-system)
5108 #:tests? #f ;no "check" target
5110 (modify-phases %standard-phases
5111 (add-after 'unpack 'use-samtools-headers
5113 (substitute* '("SAM.cpp"
5115 (("sam.h") "samtools/sam.h"))
5118 (lambda* (#:key outputs #:allow-other-keys)
5119 (let* ((out (assoc-ref outputs "out"))
5120 (lib (string-append out "/lib"))
5121 (include (string-append out "/include/smithlab-cpp")))
5124 (for-each (cut install-file <> lib)
5125 (find-files "." "\\.o$"))
5126 (for-each (cut install-file <> include)
5127 (find-files "." "\\.hpp$")))
5129 (delete 'configure))))
5131 `(("samtools" ,samtools-0.1)
5133 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5134 (synopsis "C++ helper library for functions used in Smith lab projects")
5136 "Smithlab CPP is a C++ library that includes functions used in many of
5137 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5138 structures, classes for genomic regions, mapped sequencing reads, etc.")
5139 (license license:gpl3+))))
5141 (define-public preseq
5147 (uri (string-append "https://github.com/smithlabcode/"
5148 "preseq/archive/v" version ".tar.gz"))
5149 (file-name (string-append name "-" version ".tar.gz"))
5151 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5152 (modules '((guix build utils)))
5154 ;; Remove bundled samtools.
5155 '(delete-file-recursively "samtools"))))
5156 (build-system gnu-build-system)
5158 `(#:tests? #f ;no "check" target
5160 (modify-phases %standard-phases
5161 (delete 'configure))
5163 (list (string-append "PREFIX="
5164 (assoc-ref %outputs "out"))
5165 (string-append "LIBBAM="
5166 (assoc-ref %build-inputs "samtools")
5168 (string-append "SMITHLAB_CPP="
5169 (assoc-ref %build-inputs "smithlab-cpp")
5172 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5175 ("samtools" ,samtools-0.1)
5176 ("smithlab-cpp" ,smithlab-cpp)
5178 (home-page "http://smithlabresearch.org/software/preseq/")
5179 (synopsis "Program for analyzing library complexity")
5181 "The preseq package is aimed at predicting and estimating the complexity
5182 of a genomic sequencing library, equivalent to predicting and estimating the
5183 number of redundant reads from a given sequencing depth and how many will be
5184 expected from additional sequencing using an initial sequencing experiment.
5185 The estimates can then be used to examine the utility of further sequencing,
5186 optimize the sequencing depth, or to screen multiple libraries to avoid low
5187 complexity samples.")
5188 (license license:gpl3+)))
5190 (define-public python-screed
5192 (name "python-screed")
5197 (uri (pypi-uri "screed" version))
5200 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5201 (build-system python-build-system)
5204 (modify-phases %standard-phases
5207 (setenv "PYTHONPATH"
5208 (string-append (getenv "PYTHONPATH") ":."))
5209 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5211 `(("python-nose" ,python-nose)))
5213 `(("python-bz2file" ,python-bz2file)))
5214 (home-page "https://github.com/dib-lab/screed/")
5215 (synopsis "Short read sequence database utilities")
5216 (description "Screed parses FASTA and FASTQ files and generates databases.
5217 Values such as sequence name, sequence description, sequence quality and the
5218 sequence itself can be retrieved from these databases.")
5219 (license license:bsd-3)))
5221 (define-public python2-screed
5222 (package-with-python2 python-screed))
5224 (define-public sra-tools
5232 (string-append "https://github.com/ncbi/sra-tools/archive/"
5234 (file-name (string-append name "-" version ".tar.gz"))
5237 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5238 (build-system gnu-build-system)
5240 `(#:parallel-build? #f ; not supported
5241 #:tests? #f ; no "check" target
5243 (list (string-append "DEFAULT_CRT="
5244 (assoc-ref %build-inputs "ncbi-vdb")
5246 (string-append "DEFAULT_KFG="
5247 (assoc-ref %build-inputs "ncbi-vdb")
5249 (string-append "VDB_LIBDIR="
5250 (assoc-ref %build-inputs "ncbi-vdb")
5251 ,(if (string-prefix? "x86_64"
5252 (or (%current-target-system)
5257 (modify-phases %standard-phases
5258 (add-before 'configure 'set-perl-search-path
5260 ;; Work around "dotless @INC" build failure.
5262 (string-append (getcwd) "/setup:"
5263 (getenv "PERL5LIB")))
5266 (lambda* (#:key inputs outputs #:allow-other-keys)
5267 ;; The build system expects a directory containing the sources and
5268 ;; raw build output of ncbi-vdb, including files that are not
5269 ;; installed. Since we are building against an installed version of
5270 ;; ncbi-vdb, the following modifications are needed.
5271 (substitute* "setup/konfigure.perl"
5272 ;; Make the configure script look for the "ilib" directory of
5273 ;; "ncbi-vdb" without first checking for the existence of a
5274 ;; matching library in its "lib" directory.
5275 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5276 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5277 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5278 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5279 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5282 (substitute* "tools/copycat/Makefile"
5283 (("smagic-static") "lmagic"))
5285 ;; The 'configure' script doesn't recognize things like
5286 ;; '--enable-fast-install'.
5289 (string-append "--build-prefix=" (getcwd) "/build")
5290 (string-append "--prefix=" (assoc-ref outputs "out"))
5291 (string-append "--debug")
5292 (string-append "--with-fuse-prefix="
5293 (assoc-ref inputs "fuse"))
5294 (string-append "--with-magic-prefix="
5295 (assoc-ref inputs "libmagic"))
5296 ;; TODO: building with libxml2 fails with linker errors
5297 ;; (string-append "--with-xml2-prefix="
5298 ;; (assoc-ref inputs "libxml2"))
5299 (string-append "--with-ncbi-vdb-sources="
5300 (assoc-ref inputs "ncbi-vdb"))
5301 (string-append "--with-ncbi-vdb-build="
5302 (assoc-ref inputs "ncbi-vdb"))
5303 (string-append "--with-ngs-sdk-prefix="
5304 (assoc-ref inputs "ngs-sdk"))
5305 (string-append "--with-hdf5-prefix="
5306 (assoc-ref inputs "hdf5"))))))
5307 ;; This version of sra-tools fails to build with glibc because of a
5308 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5309 ;; contains a definition of "canonicalize", so we rename it.
5311 ;; See upstream bug report:
5312 ;; https://github.com/ncbi/sra-tools/issues/67
5313 (add-after 'unpack 'patch-away-glibc-conflict
5315 (substitute* "tools/bam-loader/bam.c"
5316 (("canonicalize\\(" line)
5317 (string-append "sra_tools_" line)))
5319 (native-inputs `(("perl" ,perl)))
5321 `(("ngs-sdk" ,ngs-sdk)
5322 ("ncbi-vdb" ,ncbi-vdb)
5327 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5328 (synopsis "Tools and libraries for reading and writing sequencing data")
5330 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5331 reading of sequencing files from the Sequence Read Archive (SRA) database and
5332 writing files into the .sra format.")
5333 (license license:public-domain)))
5335 (define-public seqan
5341 (uri (string-append "http://packages.seqan.de/seqan-library/"
5342 "seqan-library-" version ".tar.bz2"))
5345 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5346 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5347 ;; makes sense to split the outputs.
5348 (outputs '("out" "doc"))
5349 (build-system trivial-build-system)
5351 `(#:modules ((guix build utils))
5354 (use-modules (guix build utils))
5355 (let ((tar (assoc-ref %build-inputs "tar"))
5356 (bzip (assoc-ref %build-inputs "bzip2"))
5357 (out (assoc-ref %outputs "out"))
5358 (doc (assoc-ref %outputs "doc")))
5359 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5360 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5361 (chdir (string-append "seqan-library-" ,version))
5362 (copy-recursively "include" (string-append out "/include"))
5363 (copy-recursively "share" (string-append doc "/share"))))))
5365 `(("source" ,source)
5368 (home-page "http://www.seqan.de")
5369 (synopsis "Library for nucleotide sequence analysis")
5371 "SeqAn is a C++ library of efficient algorithms and data structures for
5372 the analysis of sequences with the focus on biological data. It contains
5373 algorithms and data structures for string representation and their
5374 manipulation, online and indexed string search, efficient I/O of
5375 bioinformatics file formats, sequence alignment, and more.")
5376 (license license:bsd-3)))
5378 (define-public seqmagick
5385 (uri (pypi-uri "seqmagick" version))
5388 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5389 (build-system python-build-system)
5391 `(("python-biopython" ,python-biopython)))
5393 `(("python-nose" ,python-nose)))
5394 (home-page "https://github.com/fhcrc/seqmagick")
5395 (synopsis "Tools for converting and modifying sequence files")
5397 "Bioinformaticians often have to convert sequence files between formats
5398 and do little manipulations on them, and it's not worth writing scripts for
5399 that. Seqmagick is a utility to expose the file format conversion in
5400 BioPython in a convenient way. Instead of having a big mess of scripts, there
5401 is one that takes arguments.")
5402 (license license:gpl3)))
5404 (define-public seqtk
5411 "https://github.com/lh3/seqtk/archive/v"
5413 (file-name (string-append name "-" version ".tar.gz"))
5416 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5417 (modules '((guix build utils)))
5420 ;; Remove extraneous header files, as is done in the seqtk
5422 (for-each (lambda (file) (delete-file file))
5423 (list "ksort.h" "kstring.h" "kvec.h"))
5425 (build-system gnu-build-system)
5428 (modify-phases %standard-phases
5431 ;; There are no tests, so we just run a sanity check.
5432 (lambda _ (zero? (system* "./seqtk" "seq"))))
5434 (lambda* (#:key outputs #:allow-other-keys)
5435 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5436 (install-file "seqtk" bin)))))))
5439 (home-page "https://github.com/lh3/seqtk")
5440 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5442 "Seqtk is a fast and lightweight tool for processing sequences in the
5443 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5444 optionally compressed by gzip.")
5445 (license license:expat)))
5447 (define-public snap-aligner
5449 (name "snap-aligner")
5450 (version "1.0beta.18")
5454 "https://github.com/amplab/snap/archive/v"
5456 (file-name (string-append name "-" version ".tar.gz"))
5459 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5460 (build-system gnu-build-system)
5463 (modify-phases %standard-phases
5465 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5467 (lambda* (#:key outputs #:allow-other-keys)
5468 (let* ((out (assoc-ref outputs "out"))
5469 (bin (string-append out "/bin")))
5470 (install-file "snap-aligner" bin)
5471 (install-file "SNAPCommand" bin)
5475 (home-page "http://snap.cs.berkeley.edu/")
5476 (synopsis "Short read DNA sequence aligner")
5478 "SNAP is a fast and accurate aligner for short DNA reads. It is
5479 optimized for modern read lengths of 100 bases or higher, and takes advantage
5480 of these reads to align data quickly through a hash-based indexing scheme.")
5481 ;; 32-bit systems are not supported by the unpatched code.
5482 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5483 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5484 ;; systems without a lot of memory cannot make good use of this program.
5485 (supported-systems '("x86_64-linux"))
5486 (license license:asl2.0)))
5488 (define-public sortmerna
5496 "https://github.com/biocore/sortmerna/archive/"
5498 (file-name (string-append name "-" version ".tar.gz"))
5501 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5502 (build-system gnu-build-system)
5503 (outputs '("out" ;for binaries
5504 "db")) ;for sequence databases
5507 (modify-phases %standard-phases
5509 (lambda* (#:key outputs #:allow-other-keys)
5510 (let* ((out (assoc-ref outputs "out"))
5511 (bin (string-append out "/bin"))
5512 (db (assoc-ref outputs "db"))
5514 (string-append db "/share/sortmerna/rRNA_databases")))
5515 (install-file "sortmerna" bin)
5516 (install-file "indexdb_rna" bin)
5517 (for-each (lambda (file)
5518 (install-file file share))
5519 (find-files "rRNA_databases" ".*fasta"))
5523 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5524 (synopsis "Biological sequence analysis tool for NGS reads")
5526 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5527 and operational taxonomic unit (OTU) picking of next generation
5528 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5529 allows for fast and sensitive analyses of nucleotide sequences. The main
5530 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5531 ;; The source includes x86 specific code
5532 (supported-systems '("x86_64-linux" "i686-linux"))
5533 (license license:lgpl3)))
5541 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5543 (file-name (string-append name "-" version ".tar.gz"))
5546 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5547 (modules '((guix build utils)))
5550 (substitute* "source/Makefile"
5552 ;; Remove pre-built binaries and bundled htslib sources.
5553 (delete-file-recursively "bin/MacOSX_x86_64")
5554 (delete-file-recursively "bin/Linux_x86_64")
5555 (delete-file-recursively "bin/Linux_x86_64_static")
5556 (delete-file-recursively "source/htslib")
5558 (build-system gnu-build-system)
5560 '(#:tests? #f ;no check target
5561 #:make-flags '("STAR")
5563 (modify-phases %standard-phases
5564 (add-after 'unpack 'enter-source-dir
5565 (lambda _ (chdir "source") #t))
5566 (add-after 'enter-source-dir 'make-reproducible
5568 (substitute* "Makefile"
5569 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5570 (string-append pre "Built with Guix" post)))))
5571 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5573 (substitute* "Makefile"
5574 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5576 (substitute* '("BAMfunctions.cpp"
5581 "bamRemoveDuplicates.cpp")
5582 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5583 (string-append "#include <" header ">")))
5584 (substitute* "IncludeDefine.h"
5585 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5586 (string-append "<" header ">")))
5589 (lambda* (#:key outputs #:allow-other-keys)
5590 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5591 (install-file "STAR" bin))
5593 (delete 'configure))))
5597 `(("htslib" ,htslib)
5599 (home-page "https://github.com/alexdobin/STAR")
5600 (synopsis "Universal RNA-seq aligner")
5602 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5603 based on a previously undescribed RNA-seq alignment algorithm that uses
5604 sequential maximum mappable seed search in uncompressed suffix arrays followed
5605 by seed clustering and stitching procedure. In addition to unbiased de novo
5606 detection of canonical junctions, STAR can discover non-canonical splices and
5607 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5609 ;; Only 64-bit systems are supported according to the README.
5610 (supported-systems '("x86_64-linux" "mips64el-linux"))
5611 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5612 (license license:gpl3+)))
5614 (define-public subread
5620 (uri (string-append "mirror://sourceforge/subread/subread-"
5621 version "/subread-" version "-source.tar.gz"))
5624 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5625 (build-system gnu-build-system)
5627 `(#:tests? #f ;no "check" target
5628 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5629 ;; optimizations by default, so we override these flags such that x86_64
5630 ;; flags are only added when the build target is an x86_64 system.
5632 (list (let ((system ,(or (%current-target-system)
5634 (flags '("-ggdb" "-fomit-frame-pointer"
5635 "-ffast-math" "-funroll-loops"
5636 "-fmessage-length=0"
5637 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5639 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5640 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5641 (if (string-prefix? "x86_64" system)
5642 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5643 (string-append "CCFLAGS=" (string-join flags))))
5644 "-f" "Makefile.Linux"
5645 "CC=gcc ${CCFLAGS}")
5647 (modify-phases %standard-phases
5648 (add-after 'unpack 'enter-dir
5649 (lambda _ (chdir "src") #t))
5651 (lambda* (#:key outputs #:allow-other-keys)
5652 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5654 (copy-recursively "../bin" bin))))
5655 ;; no "configure" script
5656 (delete 'configure))))
5657 (inputs `(("zlib" ,zlib)))
5658 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5659 (synopsis "Tool kit for processing next-gen sequencing data")
5661 "The subread package contains the following tools: subread aligner, a
5662 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5663 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5664 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5665 against local background noises.")
5666 (license license:gpl3+)))
5668 (define-public stringtie
5674 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5675 "stringtie-" version ".tar.gz"))
5678 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5679 (modules '((guix build utils)))
5682 (delete-file-recursively "samtools-0.1.18")
5684 (build-system gnu-build-system)
5686 `(#:tests? #f ;no test suite
5688 (modify-phases %standard-phases
5689 ;; no configure script
5691 (add-before 'build 'use-system-samtools
5693 (substitute* "Makefile"
5694 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5696 (substitute* '("gclib/GBam.h"
5698 (("#include \"(bam|sam|kstring).h\"" _ header)
5699 (string-append "#include <samtools/" header ".h>")))
5701 (add-after 'unpack 'remove-duplicate-typedef
5703 ;; This typedef conflicts with the typedef in
5704 ;; glibc-2.25/include/bits/types.h
5705 (substitute* "gclib/GThreads.h"
5706 (("typedef long long __intmax_t;") ""))
5709 (lambda* (#:key outputs #:allow-other-keys)
5710 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5711 (install-file "stringtie" bin)
5714 `(("samtools" ,samtools-0.1)
5716 (home-page "http://ccb.jhu.edu/software/stringtie/")
5717 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5719 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5720 alignments into potential transcripts. It uses a novel network flow algorithm
5721 as well as an optional de novo assembly step to assemble and quantitate
5722 full-length transcripts representing multiple splice variants for each gene
5723 locus. Its input can include not only the alignments of raw reads used by
5724 other transcript assemblers, but also alignments of longer sequences that have
5725 been assembled from those reads. To identify differentially expressed genes
5726 between experiments, StringTie's output can be processed either by the
5727 Cuffdiff or Ballgown programs.")
5728 (license license:artistic2.0)))
5730 (define-public taxtastic
5736 (uri (pypi-uri "taxtastic" version))
5739 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5740 (build-system python-build-system)
5742 `(#:python ,python-2
5744 (modify-phases %standard-phases
5747 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5749 `(("python-sqlalchemy" ,python2-sqlalchemy)
5750 ("python-decorator" ,python2-decorator)
5751 ("python-biopython" ,python2-biopython)
5752 ("python-pandas" ,python2-pandas)))
5753 (home-page "https://github.com/fhcrc/taxtastic")
5754 (synopsis "Tools for taxonomic naming and annotation")
5756 "Taxtastic is software written in python used to build and maintain
5757 reference packages i.e. collections of reference trees, reference alignments,
5758 profiles, and associated taxonomic information.")
5759 (license license:gpl3+)))
5761 (define-public vcftools
5768 "https://github.com/vcftools/vcftools/releases/download/v"
5769 version "/vcftools-" version ".tar.gz"))
5772 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5773 (build-system gnu-build-system)
5775 `(#:tests? #f ; no "check" target
5777 "CFLAGS=-O2" ; override "-m64" flag
5778 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5779 (string-append "MANDIR=" (assoc-ref %outputs "out")
5780 "/share/man/man1"))))
5782 `(("pkg-config" ,pkg-config)))
5786 (home-page "https://vcftools.github.io/")
5787 (synopsis "Tools for working with VCF files")
5789 "VCFtools is a program package designed for working with VCF files, such
5790 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5791 provide easily accessible methods for working with complex genetic variation
5792 data in the form of VCF files.")
5793 ;; The license is declared as LGPLv3 in the README and
5794 ;; at https://vcftools.github.io/license.html
5795 (license license:lgpl3)))
5797 (define-public infernal
5803 (uri (string-append "http://eddylab.org/software/infernal/"
5804 "infernal-" version ".tar.gz"))
5807 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5808 (build-system gnu-build-system)
5810 `(("perl" ,perl))) ; for tests
5811 (home-page "http://eddylab.org/infernal/")
5812 (synopsis "Inference of RNA alignments")
5813 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5814 searching DNA sequence databases for RNA structure and sequence similarities.
5815 It is an implementation of a special case of profile stochastic context-free
5816 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5817 profile, but it scores a combination of sequence consensus and RNA secondary
5818 structure consensus, so in many cases, it is more capable of identifying RNA
5819 homologs that conserve their secondary structure more than their primary
5821 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5822 (supported-systems '("i686-linux" "x86_64-linux"))
5823 (license license:bsd-3)))
5825 (define-public r-centipede
5827 (name "r-centipede")
5831 (uri (string-append "http://download.r-forge.r-project.org/"
5832 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5835 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5836 (build-system r-build-system)
5837 (home-page "http://centipede.uchicago.edu/")
5838 (synopsis "Predict transcription factor binding sites")
5840 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5841 of the genome that are bound by particular transcription factors. It starts
5842 by identifying a set of candidate binding sites, and then aims to classify the
5843 sites according to whether each site is bound or not bound by a transcription
5844 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5845 between two different types of motif instances using as much relevant
5846 information as possible.")
5847 (license (list license:gpl2+ license:gpl3+))))
5849 (define-public r-vegan
5856 (uri (cran-uri "vegan" version))
5859 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
5860 (build-system r-build-system)
5862 `(("gfortran" ,gfortran)))
5864 `(("r-cluster" ,r-cluster)
5865 ("r-lattice" ,r-lattice)
5868 ("r-permute" ,r-permute)))
5869 (home-page "https://cran.r-project.org/web/packages/vegan")
5870 (synopsis "Functions for community ecology")
5872 "The vegan package provides tools for descriptive community ecology. It
5873 has most basic functions of diversity analysis, community ordination and
5874 dissimilarity analysis. Most of its multivariate tools can be used for other
5875 data types as well.")
5876 (license license:gpl2+)))
5878 (define-public r-annotate
5885 (uri (bioconductor-uri "annotate" version))
5888 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
5889 (build-system r-build-system)
5891 `(("r-annotationdbi" ,r-annotationdbi)
5892 ("r-biobase" ,r-biobase)
5893 ("r-biocgenerics" ,r-biocgenerics)
5895 ("r-rcurl" ,r-rcurl)
5897 ("r-xtable" ,r-xtable)))
5899 "https://bioconductor.org/packages/annotate")
5900 (synopsis "Annotation for microarrays")
5901 (description "This package provides R environments for the annotation of
5903 (license license:artistic2.0)))
5905 (define-public r-copynumber
5907 (name "r-copynumber")
5911 (uri (bioconductor-uri "copynumber" version))
5914 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
5915 (build-system r-build-system)
5917 `(("r-s4vectors" ,r-s4vectors)
5918 ("r-iranges" ,r-iranges)
5919 ("r-genomicranges" ,r-genomicranges)
5920 ("r-biocgenerics" ,r-biocgenerics)))
5921 (home-page "https://bioconductor.org/packages/copynumber")
5922 (synopsis "Segmentation of single- and multi-track copy number data")
5924 "This package segments single- and multi-track copy number data by a
5925 penalized least squares regression method.")
5926 (license license:artistic2.0)))
5928 (define-public r-geneplotter
5930 (name "r-geneplotter")
5935 (uri (bioconductor-uri "geneplotter" version))
5938 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
5939 (build-system r-build-system)
5941 `(("r-annotate" ,r-annotate)
5942 ("r-annotationdbi" ,r-annotationdbi)
5943 ("r-biobase" ,r-biobase)
5944 ("r-biocgenerics" ,r-biocgenerics)
5945 ("r-lattice" ,r-lattice)
5946 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5947 (home-page "https://bioconductor.org/packages/geneplotter")
5948 (synopsis "Graphics functions for genomic data")
5950 "This package provides functions for plotting genomic data.")
5951 (license license:artistic2.0)))
5953 (define-public r-genefilter
5955 (name "r-genefilter")
5960 (uri (bioconductor-uri "genefilter" version))
5963 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
5964 (build-system r-build-system)
5966 `(("gfortran" ,gfortran)))
5968 `(("r-annotate" ,r-annotate)
5969 ("r-annotationdbi" ,r-annotationdbi)
5970 ("r-biobase" ,r-biobase)
5971 ("r-s4vectors" ,r-s4vectors)
5972 ("r-survival" ,r-survival)))
5973 (home-page "https://bioconductor.org/packages/genefilter")
5974 (synopsis "Filter genes from high-throughput experiments")
5976 "This package provides basic functions for filtering genes from
5977 high-throughput sequencing experiments.")
5978 (license license:artistic2.0)))
5980 (define-public r-deseq2
5987 (uri (bioconductor-uri "DESeq2" version))
5990 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
5991 (properties `((upstream-name . "DESeq2")))
5992 (build-system r-build-system)
5994 `(("r-biobase" ,r-biobase)
5995 ("r-biocgenerics" ,r-biocgenerics)
5996 ("r-biocparallel" ,r-biocparallel)
5997 ("r-genefilter" ,r-genefilter)
5998 ("r-geneplotter" ,r-geneplotter)
5999 ("r-genomicranges" ,r-genomicranges)
6000 ("r-ggplot2" ,r-ggplot2)
6001 ("r-hmisc" ,r-hmisc)
6002 ("r-iranges" ,r-iranges)
6003 ("r-locfit" ,r-locfit)
6005 ("r-rcpparmadillo" ,r-rcpparmadillo)
6006 ("r-s4vectors" ,r-s4vectors)
6007 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6008 (home-page "https://bioconductor.org/packages/DESeq2")
6009 (synopsis "Differential gene expression analysis")
6011 "This package provides functions to estimate variance-mean dependence in
6012 count data from high-throughput nucleotide sequencing assays and test for
6013 differential expression based on a model using the negative binomial
6015 (license license:lgpl3+)))
6017 (define-public r-dexseq
6024 (uri (bioconductor-uri "DEXSeq" version))
6027 "18nh8ynxirfwkmc4sawdxgl7w1sl9ny5zpv8zbhv9vi5vgb8pxmj"))))
6028 (properties `((upstream-name . "DEXSeq")))
6029 (build-system r-build-system)
6031 `(("r-annotationdbi" ,r-annotationdbi)
6032 ("r-biobase" ,r-biobase)
6033 ("r-biocgenerics" ,r-biocgenerics)
6034 ("r-biocparallel" ,r-biocparallel)
6035 ("r-biomart" ,r-biomart)
6036 ("r-deseq2" ,r-deseq2)
6037 ("r-genefilter" ,r-genefilter)
6038 ("r-geneplotter" ,r-geneplotter)
6039 ("r-genomicranges" ,r-genomicranges)
6040 ("r-hwriter" ,r-hwriter)
6041 ("r-iranges" ,r-iranges)
6042 ("r-rcolorbrewer" ,r-rcolorbrewer)
6043 ("r-rsamtools" ,r-rsamtools)
6044 ("r-s4vectors" ,r-s4vectors)
6045 ("r-statmod" ,r-statmod)
6046 ("r-stringr" ,r-stringr)
6047 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6048 (home-page "https://bioconductor.org/packages/DEXSeq")
6049 (synopsis "Inference of differential exon usage in RNA-Seq")
6051 "This package is focused on finding differential exon usage using RNA-seq
6052 exon counts between samples with different experimental designs. It provides
6053 functions that allows the user to make the necessary statistical tests based
6054 on a model that uses the negative binomial distribution to estimate the
6055 variance between biological replicates and generalized linear models for
6056 testing. The package also provides functions for the visualization and
6057 exploration of the results.")
6058 (license license:gpl3+)))
6060 (define-public r-annotationforge
6062 (name "r-annotationforge")
6067 (uri (bioconductor-uri "AnnotationForge" version))
6070 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6072 `((upstream-name . "AnnotationForge")))
6073 (build-system r-build-system)
6075 `(("r-annotationdbi" ,r-annotationdbi)
6076 ("r-biobase" ,r-biobase)
6077 ("r-biocgenerics" ,r-biocgenerics)
6079 ("r-rcurl" ,r-rcurl)
6080 ("r-rsqlite" ,r-rsqlite)
6081 ("r-s4vectors" ,r-s4vectors)
6083 (home-page "https://bioconductor.org/packages/AnnotationForge")
6084 (synopsis "Code for building annotation database packages")
6086 "This package provides code for generating Annotation packages and their
6087 databases. Packages produced are intended to be used with AnnotationDbi.")
6088 (license license:artistic2.0)))
6090 (define-public r-rbgl
6097 (uri (bioconductor-uri "RBGL" version))
6100 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6101 (properties `((upstream-name . "RBGL")))
6102 (build-system r-build-system)
6103 (propagated-inputs `(("r-graph" ,r-graph)))
6104 (home-page "https://www.bioconductor.org/packages/RBGL")
6105 (synopsis "Interface to the Boost graph library")
6107 "This package provides a fairly extensive and comprehensive interface to
6108 the graph algorithms contained in the Boost library.")
6109 (license license:artistic2.0)))
6111 (define-public r-gseabase
6118 (uri (bioconductor-uri "GSEABase" version))
6121 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6122 (properties `((upstream-name . "GSEABase")))
6123 (build-system r-build-system)
6125 `(("r-annotate" ,r-annotate)
6126 ("r-annotationdbi" ,r-annotationdbi)
6127 ("r-biobase" ,r-biobase)
6128 ("r-biocgenerics" ,r-biocgenerics)
6129 ("r-graph" ,r-graph)
6131 (home-page "https://bioconductor.org/packages/GSEABase")
6132 (synopsis "Gene set enrichment data structures and methods")
6134 "This package provides classes and methods to support @dfn{Gene Set
6135 Enrichment Analysis} (GSEA).")
6136 (license license:artistic2.0)))
6138 (define-public r-category
6145 (uri (bioconductor-uri "Category" version))
6148 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6149 (properties `((upstream-name . "Category")))
6150 (build-system r-build-system)
6152 `(("r-annotate" ,r-annotate)
6153 ("r-annotationdbi" ,r-annotationdbi)
6154 ("r-biobase" ,r-biobase)
6155 ("r-biocgenerics" ,r-biocgenerics)
6156 ("r-genefilter" ,r-genefilter)
6157 ("r-graph" ,r-graph)
6158 ("r-gseabase" ,r-gseabase)
6159 ("r-matrix" ,r-matrix)
6162 (home-page "https://bioconductor.org/packages/Category")
6163 (synopsis "Category analysis")
6165 "This package provides a collection of tools for performing category
6167 (license license:artistic2.0)))
6169 (define-public r-gostats
6176 (uri (bioconductor-uri "GOstats" version))
6179 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6180 (properties `((upstream-name . "GOstats")))
6181 (build-system r-build-system)
6183 `(("r-annotate" ,r-annotate)
6184 ("r-annotationdbi" ,r-annotationdbi)
6185 ("r-annotationforge" ,r-annotationforge)
6186 ("r-biobase" ,r-biobase)
6187 ("r-category" ,r-category)
6188 ("r-go-db" ,r-go-db)
6189 ("r-graph" ,r-graph)
6190 ("r-rgraphviz" ,r-rgraphviz)
6191 ("r-rbgl" ,r-rbgl)))
6192 (home-page "https://bioconductor.org/packages/GOstats")
6193 (synopsis "Tools for manipulating GO and microarrays")
6195 "This package provides a set of tools for interacting with GO and
6196 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6197 testing and other simple calculations.")
6198 (license license:artistic2.0)))
6200 (define-public r-shortread
6202 (name "r-shortread")
6207 (uri (bioconductor-uri "ShortRead" version))
6210 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
6211 (properties `((upstream-name . "ShortRead")))
6212 (build-system r-build-system)
6216 `(("r-biobase" ,r-biobase)
6217 ("r-biocgenerics" ,r-biocgenerics)
6218 ("r-biocparallel" ,r-biocparallel)
6219 ("r-biostrings" ,r-biostrings)
6220 ("r-genomeinfodb" ,r-genomeinfodb)
6221 ("r-genomicalignments" ,r-genomicalignments)
6222 ("r-genomicranges" ,r-genomicranges)
6223 ("r-hwriter" ,r-hwriter)
6224 ("r-iranges" ,r-iranges)
6225 ("r-lattice" ,r-lattice)
6226 ("r-latticeextra" ,r-latticeextra)
6227 ("r-rsamtools" ,r-rsamtools)
6228 ("r-s4vectors" ,r-s4vectors)
6229 ("r-xvector" ,r-xvector)
6230 ("r-zlibbioc" ,r-zlibbioc)))
6231 (home-page "https://bioconductor.org/packages/ShortRead")
6232 (synopsis "FASTQ input and manipulation tools")
6234 "This package implements sampling, iteration, and input of FASTQ files.
6235 It includes functions for filtering and trimming reads, and for generating a
6236 quality assessment report. Data are represented as
6237 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6238 purposes. The package also contains legacy support for early single-end,
6239 ungapped alignment formats.")
6240 (license license:artistic2.0)))
6242 (define-public r-systempiper
6244 (name "r-systempiper")
6249 (uri (bioconductor-uri "systemPipeR" version))
6252 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6253 (properties `((upstream-name . "systemPipeR")))
6254 (build-system r-build-system)
6256 `(("r-annotate" ,r-annotate)
6257 ("r-batchjobs" ,r-batchjobs)
6258 ("r-biocgenerics" ,r-biocgenerics)
6259 ("r-biostrings" ,r-biostrings)
6260 ("r-deseq2" ,r-deseq2)
6261 ("r-edger" ,r-edger)
6262 ("r-genomicfeatures" ,r-genomicfeatures)
6263 ("r-genomicranges" ,r-genomicranges)
6264 ("r-ggplot2" ,r-ggplot2)
6265 ("r-go-db" ,r-go-db)
6266 ("r-gostats" ,r-gostats)
6267 ("r-limma" ,r-limma)
6268 ("r-pheatmap" ,r-pheatmap)
6269 ("r-rjson" ,r-rjson)
6270 ("r-rsamtools" ,r-rsamtools)
6271 ("r-shortread" ,r-shortread)
6272 ("r-summarizedexperiment" ,r-summarizedexperiment)
6273 ("r-variantannotation" ,r-variantannotation)))
6274 (home-page "https://github.com/tgirke/systemPipeR")
6275 (synopsis "Next generation sequencing workflow and reporting environment")
6277 "This R package provides tools for building and running automated
6278 end-to-end analysis workflows for a wide range of @dfn{next generation
6279 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6280 Important features include a uniform workflow interface across different NGS
6281 applications, automated report generation, and support for running both R and
6282 command-line software, such as NGS aligners or peak/variant callers, on local
6283 computers or compute clusters. Efficient handling of complex sample sets and
6284 experimental designs is facilitated by a consistently implemented sample
6285 annotation infrastructure.")
6286 (license license:artistic2.0)))
6288 (define-public r-grohmm
6295 (uri (bioconductor-uri "groHMM" version))
6298 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6299 (properties `((upstream-name . "groHMM")))
6300 (build-system r-build-system)
6302 `(("r-genomeinfodb" ,r-genomeinfodb)
6303 ("r-genomicalignments" ,r-genomicalignments)
6304 ("r-genomicranges" ,r-genomicranges)
6305 ("r-iranges" ,r-iranges)
6307 ("r-rtracklayer" ,r-rtracklayer)
6308 ("r-s4vectors" ,r-s4vectors)))
6309 (home-page "https://github.com/Kraus-Lab/groHMM")
6310 (synopsis "GRO-seq analysis pipeline")
6312 "This package provides a pipeline for the analysis of GRO-seq data.")
6313 (license license:gpl3+)))
6315 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6317 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6321 ;; We cannot use bioconductor-uri here because this tarball is
6322 ;; located under "data/annotation/" instead of "bioc/".
6323 (uri (string-append "https://bioconductor.org/packages/"
6324 "release/data/annotation/src/contrib"
6325 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6329 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6331 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6332 (build-system r-build-system)
6333 ;; As this package provides little more than a very large data file it
6334 ;; doesn't make sense to build substitutes.
6335 (arguments `(#:substitutable? #f))
6337 `(("r-genomicfeatures" ,r-genomicfeatures)))
6339 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6340 (synopsis "Annotation package for human genome in TxDb format")
6342 "This package provides an annotation database of Homo sapiens genome
6343 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6344 track. The database is exposed as a @code{TxDb} object.")
6345 (license license:artistic2.0)))
6347 (define-public r-sparql
6353 (uri (cran-uri "SPARQL" version))
6356 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6357 (properties `((upstream-name . "SPARQL")))
6358 (build-system r-build-system)
6360 `(("r-rcurl" ,r-rcurl)
6362 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6363 (synopsis "SPARQL client for R")
6364 (description "This package provides an interface to use SPARQL to pose
6365 SELECT or UPDATE queries to an end-point.")
6366 ;; The only license indication is found in the DESCRIPTION file,
6367 ;; which states GPL-3. So we cannot assume GPLv3+.
6368 (license license:gpl3)))
6370 (define-public vsearch
6378 "https://github.com/torognes/vsearch/archive/v"
6380 (file-name (string-append name "-" version ".tar.gz"))
6383 "0523b8xq5fw60ayl0k5m1fm6yrh1932ljrsz1ys67xnki7p7f1d5"))
6384 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6387 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6388 ;; for this in the patch.
6389 (delete-file "src/city.h")
6390 (delete-file "src/citycrc.h")
6391 (delete-file "src/city.cc")
6393 (build-system gnu-build-system)
6396 (modify-phases %standard-phases
6397 (add-after 'unpack 'autogen
6398 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6402 ("cityhash" ,cityhash)))
6404 `(("autoconf" ,autoconf)
6405 ("automake" ,automake)))
6406 (synopsis "Sequence search tools for metagenomics")
6408 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6409 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6410 masking. The tool takes advantage of parallelism in the form of SIMD
6411 vectorization as well as multiple threads to perform accurate alignments at
6412 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6413 Needleman-Wunsch).")
6414 (home-page "https://github.com/torognes/vsearch")
6415 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6417 (supported-systems '("x86_64-linux"))
6418 ;; Dual licensed; also includes public domain source.
6419 (license (list license:gpl3 license:bsd-2))))
6421 (define-public pardre
6424 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6429 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6433 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6434 (build-system gnu-build-system)
6436 `(#:tests? #f ; no tests included
6438 (modify-phases %standard-phases
6441 (lambda* (#:key outputs #:allow-other-keys)
6442 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6443 (install-file "ParDRe" bin)
6446 `(("openmpi" ,openmpi)
6448 (synopsis "Parallel tool to remove duplicate DNA reads")
6450 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6451 Duplicate reads can be seen as identical or nearly identical sequences with
6452 some mismatches. This tool lets users avoid the analysis of unnecessary
6453 reads, reducing the time of subsequent procedures with the
6454 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6455 in order to exploit the parallel capabilities of multicore clusters. It is
6456 faster than multithreaded counterparts (end of 2015) for the same number of
6457 cores and, thanks to the message-passing technology, it can be executed on
6459 (home-page "https://sourceforge.net/projects/pardre/")
6460 (license license:gpl3+)))
6462 (define-public ruby-bio-kseq
6464 (name "ruby-bio-kseq")
6469 (uri (rubygems-uri "bio-kseq" version))
6472 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6473 (build-system ruby-build-system)
6475 `(#:test-target "spec"))
6477 `(("bundler" ,bundler)
6478 ("ruby-rspec" ,ruby-rspec)
6479 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6482 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6484 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6485 FASTQ parsing code. It provides a fast iterator over sequences and their
6487 (home-page "https://github.com/gusevfe/bio-kseq")
6488 (license license:expat)))
6490 (define-public bio-locus
6497 (uri (rubygems-uri "bio-locus" version))
6500 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6501 (build-system ruby-build-system)
6503 `(("ruby-rspec" ,ruby-rspec)))
6504 (synopsis "Tool for fast querying of genome locations")
6506 "Bio-locus is a tabix-like tool for fast querying of genome
6507 locations. Many file formats in bioinformatics contain records that
6508 start with a chromosome name and a position for a SNP, or a start-end
6509 position for indels. Bio-locus allows users to store this chr+pos or
6510 chr+pos+alt information in a database.")
6511 (home-page "https://github.com/pjotrp/bio-locus")
6512 (license license:expat)))
6514 (define-public bio-blastxmlparser
6516 (name "bio-blastxmlparser")
6520 (uri (rubygems-uri "bio-blastxmlparser" version))
6523 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6524 (build-system ruby-build-system)
6526 `(("ruby-bio-logger" ,ruby-bio-logger)
6527 ("ruby-nokogiri" ,ruby-nokogiri)))
6529 `(("ruby-rspec" ,ruby-rspec)))
6530 (synopsis "Fast big data BLAST XML parser and library")
6532 "Very fast parallel big-data BLAST XML file parser which can be used as
6533 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6534 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6535 (home-page "https://github.com/pjotrp/blastxmlparser")
6536 (license license:expat)))
6538 (define-public bioruby
6545 (uri (rubygems-uri "bio" version))
6548 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6549 (build-system ruby-build-system)
6551 `(("ruby-libxml" ,ruby-libxml)))
6553 `(("which" ,which))) ; required for test phase
6556 (modify-phases %standard-phases
6557 (add-before 'build 'patch-test-command
6559 (substitute* '("test/functional/bio/test_command.rb")
6560 (("/bin/sh") (which "sh")))
6561 (substitute* '("test/functional/bio/test_command.rb")
6562 (("/bin/ls") (which "ls")))
6563 (substitute* '("test/functional/bio/test_command.rb")
6564 (("which") (which "which")))
6565 (substitute* '("test/functional/bio/test_command.rb",
6566 "test/data/command/echoarg2.sh")
6567 (("/bin/echo") (which "echo")))
6569 (synopsis "Ruby library, shell and utilities for bioinformatics")
6570 (description "BioRuby comes with a comprehensive set of Ruby development
6571 tools and libraries for bioinformatics and molecular biology. BioRuby has
6572 components for sequence analysis, pathway analysis, protein modelling and
6573 phylogenetic analysis; it supports many widely used data formats and provides
6574 easy access to databases, external programs and public web services, including
6575 BLAST, KEGG, GenBank, MEDLINE and GO.")
6576 (home-page "http://bioruby.org/")
6577 ;; Code is released under Ruby license, except for setup
6578 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6579 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6581 (define-public r-acsnminer
6583 (name "r-acsnminer")
6584 (version "0.16.8.25")
6587 (uri (cran-uri "ACSNMineR" version))
6590 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6591 (properties `((upstream-name . "ACSNMineR")))
6592 (build-system r-build-system)
6594 `(("r-ggplot2" ,r-ggplot2)
6595 ("r-gridextra" ,r-gridextra)))
6596 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6597 (synopsis "Gene enrichment analysis")
6599 "This package provides tools to compute and represent gene set enrichment
6600 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6601 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6602 enrichment can be run with hypergeometric test or Fisher exact test, and can
6603 use multiple corrections. Visualization of data can be done either by
6604 barplots or heatmaps.")
6605 (license license:gpl2+)))
6607 (define-public r-biocgenerics
6609 (name "r-biocgenerics")
6613 (uri (bioconductor-uri "BiocGenerics" version))
6616 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6618 `((upstream-name . "BiocGenerics")))
6619 (build-system r-build-system)
6620 (home-page "https://bioconductor.org/packages/BiocGenerics")
6621 (synopsis "S4 generic functions for Bioconductor")
6623 "This package provides S4 generic functions needed by many Bioconductor
6625 (license license:artistic2.0)))
6627 (define-public r-biocinstaller
6629 (name "r-biocinstaller")
6633 (uri (bioconductor-uri "BiocInstaller" version))
6636 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6638 `((upstream-name . "BiocInstaller")))
6639 (build-system r-build-system)
6640 (home-page "https://bioconductor.org/packages/BiocInstaller")
6641 (synopsis "Install Bioconductor packages")
6642 (description "This package is used to install and update R packages from
6643 Bioconductor, CRAN, and Github.")
6644 (license license:artistic2.0)))
6646 (define-public r-biocviews
6648 (name "r-biocviews")
6652 (uri (bioconductor-uri "biocViews" version))
6655 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6657 `((upstream-name . "biocViews")))
6658 (build-system r-build-system)
6660 `(("r-biobase" ,r-biobase)
6661 ("r-graph" ,r-graph)
6663 ("r-rcurl" ,r-rcurl)
6665 ("r-runit" ,r-runit)))
6666 (home-page "https://bioconductor.org/packages/biocViews")
6667 (synopsis "Bioconductor package categorization helper")
6668 (description "The purpose of biocViews is to create HTML pages that
6669 categorize packages in a Bioconductor package repository according to keywords,
6670 also known as views, in a controlled vocabulary.")
6671 (license license:artistic2.0)))
6673 (define-public r-bookdown
6679 (uri (cran-uri "bookdown" version))
6682 "1pxxln42kvzl38fjprg6hcnyh1kij75fpj70vwp5hp5il813aszc"))))
6683 (build-system r-build-system)
6685 `(("r-htmltools" ,r-htmltools)
6686 ("r-knitr" ,r-knitr)
6687 ("r-rmarkdown" ,r-rmarkdown)
6690 ("ghc-pandoc" ,ghc-pandoc)))
6691 (home-page "https://github.com/rstudio/bookdown")
6692 (synopsis "Authoring books and technical documents with R markdown")
6693 (description "This package provides output formats and utilities for
6694 authoring books and technical documents with R Markdown.")
6695 (license license:gpl3)))
6697 (define-public r-biocstyle
6699 (name "r-biocstyle")
6703 (uri (bioconductor-uri "BiocStyle" version))
6706 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6708 `((upstream-name . "BiocStyle")))
6709 (build-system r-build-system)
6711 `(("r-bookdown" ,r-bookdown)
6712 ("r-knitr" ,r-knitr)
6713 ("r-rmarkdown" ,r-rmarkdown)
6714 ("r-yaml" ,r-yaml)))
6715 (home-page "https://bioconductor.org/packages/BiocStyle")
6716 (synopsis "Bioconductor formatting styles")
6717 (description "This package provides standard formatting styles for
6718 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6720 (license license:artistic2.0)))
6722 (define-public r-bioccheck
6724 (name "r-bioccheck")
6728 (uri (bioconductor-uri "BiocCheck" version))
6731 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6733 `((upstream-name . "BiocCheck")))
6734 (build-system r-build-system)
6737 (modify-phases %standard-phases
6738 ;; This package can be used by calling BiocCheck(<package>) from
6739 ;; within R, or by running R CMD BiocCheck <package>. This phase
6740 ;; makes sure the latter works. For this to work, the BiocCheck
6741 ;; script must be somewhere on the PATH (not the R bin directory).
6742 (add-after 'install 'install-bioccheck-subcommand
6743 (lambda* (#:key outputs #:allow-other-keys)
6744 (let* ((out (assoc-ref outputs "out"))
6745 (dest-dir (string-append out "/bin"))
6747 (string-append out "/site-library/BiocCheck/script/")))
6749 (symlink (string-append script-dir "/checkBadDeps.R")
6750 (string-append dest-dir "/checkBadDeps.R"))
6751 (symlink (string-append script-dir "/BiocCheck")
6752 (string-append dest-dir "/BiocCheck")))
6755 `(("r-codetools" ,r-codetools)
6756 ("r-graph" ,r-graph)
6758 ("r-optparse" ,r-optparse)
6759 ("r-biocinstaller" ,r-biocinstaller)
6760 ("r-biocviews" ,r-biocviews)
6761 ("r-stringdist" ,r-stringdist)))
6762 (home-page "https://bioconductor.org/packages/BiocCheck")
6763 (synopsis "Executes Bioconductor-specific package checks")
6764 (description "This package contains tools to perform additional quality
6765 checks on R packages that are to be submitted to the Bioconductor repository.")
6766 (license license:artistic2.0)))
6768 (define-public r-getopt
6775 (uri (cran-uri "getopt" version))
6778 "0m463mcvixh54i3ng42n0vxmdlf97dgbfs2sf9wnjm782ddw68hm"))))
6779 (build-system r-build-system)
6780 (home-page "https://github.com/trevorld/getopt")
6781 (synopsis "Command-line option processor for R")
6783 "This package is designed to be used with Rscript to write shebang
6784 scripts that accept short and long options. Many users will prefer to
6785 use the packages @code{optparse} or @code{argparse} which add extra
6786 features like automatically generated help options and usage texts,
6787 support for default values, positional argument support, etc.")
6788 (license license:gpl2+)))
6790 (define-public r-optparse
6797 (uri (cran-uri "optparse" version))
6800 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6801 (build-system r-build-system)
6803 `(("r-getopt" ,r-getopt)))
6805 "https://github.com/trevorld/optparse")
6806 (synopsis "Command line option parser")
6808 "This package provides a command line parser inspired by Python's
6809 @code{optparse} library to be used with Rscript to write shebang scripts
6810 that accept short and long options.")
6811 (license license:gpl2+)))
6813 (define-public r-dnacopy
6819 (uri (bioconductor-uri "DNAcopy" version))
6822 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6824 `((upstream-name . "DNAcopy")))
6825 (build-system r-build-system)
6827 `(("gfortran" ,gfortran)))
6828 (home-page "https://bioconductor.org/packages/DNAcopy")
6829 (synopsis "Implementation of a circular binary segmentation algorithm")
6830 (description "This package implements the circular binary segmentation (CBS)
6831 algorithm to segment DNA copy number data and identify genomic regions with
6832 abnormal copy number.")
6833 (license license:gpl2+)))
6835 (define-public r-s4vectors
6837 (name "r-s4vectors")
6841 (uri (bioconductor-uri "S4Vectors" version))
6844 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6846 `((upstream-name . "S4Vectors")))
6847 (build-system r-build-system)
6849 `(("r-biocgenerics" ,r-biocgenerics)))
6850 (home-page "https://bioconductor.org/packages/S4Vectors")
6851 (synopsis "S4 implementation of vectors and lists")
6853 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6854 classes and a set of generic functions that extend the semantic of ordinary
6855 vectors and lists in R. Package developers can easily implement vector-like
6856 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6857 In addition, a few low-level concrete subclasses of general interest (e.g.
6858 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6859 S4Vectors package itself.")
6860 (license license:artistic2.0)))
6862 (define-public r-seqinr
6869 (uri (cran-uri "seqinr" version))
6872 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6873 (build-system r-build-system)
6875 `(("r-ade4" ,r-ade4)
6876 ("r-segmented" ,r-segmented)))
6879 (home-page "http://seqinr.r-forge.r-project.org/")
6880 (synopsis "Biological sequences retrieval and analysis")
6882 "This package provides tools for exploratory data analysis and data
6883 visualization of biological sequence (DNA and protein) data. It also includes
6884 utilities for sequence data management under the ACNUC system.")
6885 (license license:gpl2+)))
6887 (define-public r-iranges
6893 (uri (bioconductor-uri "IRanges" version))
6896 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
6898 `((upstream-name . "IRanges")))
6899 (build-system r-build-system)
6901 `(("r-biocgenerics" ,r-biocgenerics)
6902 ("r-s4vectors" ,r-s4vectors)))
6903 (home-page "https://bioconductor.org/packages/IRanges")
6904 (synopsis "Infrastructure for manipulating intervals on sequences")
6906 "This package provides efficient low-level and highly reusable S4 classes
6907 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6908 generally, data that can be organized sequentially (formally defined as
6909 @code{Vector} objects), as well as views on these @code{Vector} objects.
6910 Efficient list-like classes are also provided for storing big collections of
6911 instances of the basic classes. All classes in the package use consistent
6912 naming and share the same rich and consistent \"Vector API\" as much as
6914 (license license:artistic2.0)))
6916 (define-public r-genomeinfodbdata
6918 (name "r-genomeinfodbdata")
6922 ;; We cannot use bioconductor-uri here because this tarball is
6923 ;; located under "data/annotation/" instead of "bioc/".
6924 (uri (string-append "https://bioconductor.org/packages/release/"
6925 "data/annotation/src/contrib/GenomeInfoDbData_"
6929 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
6931 `((upstream-name . "GenomeInfoDbData")))
6932 (build-system r-build-system)
6933 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
6934 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6935 (description "This package contains data for mapping between NCBI taxonomy
6936 ID and species. It is used by functions in the GenomeInfoDb package.")
6937 (license license:artistic2.0)))
6939 (define-public r-genomeinfodb
6941 (name "r-genomeinfodb")
6945 (uri (bioconductor-uri "GenomeInfoDb" version))
6948 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
6950 `((upstream-name . "GenomeInfoDb")))
6951 (build-system r-build-system)
6953 `(("r-biocgenerics" ,r-biocgenerics)
6954 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6955 ("r-iranges" ,r-iranges)
6956 ("r-rcurl" ,r-rcurl)
6957 ("r-s4vectors" ,r-s4vectors)))
6958 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
6959 (synopsis "Utilities for manipulating chromosome identifiers")
6961 "This package contains data and functions that define and allow
6962 translation between different chromosome sequence naming conventions (e.g.,
6963 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6964 names in their natural, rather than lexicographic, order.")
6965 (license license:artistic2.0)))
6967 (define-public r-edger
6973 (uri (bioconductor-uri "edgeR" version))
6976 "0g7bj6w61blw3m22hw9rc01n554k9qkjizh7njr3j4shmhads58d"))))
6977 (properties `((upstream-name . "edgeR")))
6978 (build-system r-build-system)
6980 `(("r-limma" ,r-limma)
6981 ("r-locfit" ,r-locfit)
6983 ("r-statmod" ,r-statmod))) ;for estimateDisp
6984 (home-page "http://bioinf.wehi.edu.au/edgeR")
6985 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6986 (description "This package can do differential expression analysis of
6987 RNA-seq expression profiles with biological replication. It implements a range
6988 of statistical methodology based on the negative binomial distributions,
6989 including empirical Bayes estimation, exact tests, generalized linear models
6990 and quasi-likelihood tests. It be applied to differential signal analysis of
6991 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6993 (license license:gpl2+)))
6995 (define-public r-variantannotation
6997 (name "r-variantannotation")
7001 (uri (bioconductor-uri "VariantAnnotation" version))
7004 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7006 `((upstream-name . "VariantAnnotation")))
7010 `(("r-annotationdbi" ,r-annotationdbi)
7011 ("r-biobase" ,r-biobase)
7012 ("r-biocgenerics" ,r-biocgenerics)
7013 ("r-biostrings" ,r-biostrings)
7014 ("r-bsgenome" ,r-bsgenome)
7016 ("r-genomeinfodb" ,r-genomeinfodb)
7017 ("r-genomicfeatures" ,r-genomicfeatures)
7018 ("r-genomicranges" ,r-genomicranges)
7019 ("r-iranges" ,r-iranges)
7020 ("r-summarizedexperiment" ,r-summarizedexperiment)
7021 ("r-rsamtools" ,r-rsamtools)
7022 ("r-rtracklayer" ,r-rtracklayer)
7023 ("r-s4vectors" ,r-s4vectors)
7024 ("r-xvector" ,r-xvector)
7025 ("r-zlibbioc" ,r-zlibbioc)))
7026 (build-system r-build-system)
7027 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7028 (synopsis "Package for annotation of genetic variants")
7029 (description "This R package can annotate variants, compute amino acid
7030 coding changes and predict coding outcomes.")
7031 (license license:artistic2.0)))
7033 (define-public r-limma
7039 (uri (bioconductor-uri "limma" version))
7042 "0bmxsgz2yll83sd3wbxsrsfd35468igb0d8lldym0d0lqfz906bw"))))
7043 (build-system r-build-system)
7044 (home-page "http://bioinf.wehi.edu.au/limma")
7045 (synopsis "Package for linear models for microarray and RNA-seq data")
7046 (description "This package can be used for the analysis of gene expression
7047 studies, especially the use of linear models for analysing designed experiments
7048 and the assessment of differential expression. The analysis methods apply to
7049 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7050 (license license:gpl2+)))
7052 (define-public r-xvector
7058 (uri (bioconductor-uri "XVector" version))
7061 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7063 `((upstream-name . "XVector")))
7064 (build-system r-build-system)
7067 (modify-phases %standard-phases
7068 (add-after 'unpack 'use-system-zlib
7070 (substitute* "DESCRIPTION"
7071 (("zlibbioc, ") ""))
7072 (substitute* "NAMESPACE"
7073 (("import\\(zlibbioc\\)") ""))
7078 `(("r-biocgenerics" ,r-biocgenerics)
7079 ("r-iranges" ,r-iranges)
7080 ("r-s4vectors" ,r-s4vectors)))
7081 (home-page "https://bioconductor.org/packages/XVector")
7082 (synopsis "Representation and manpulation of external sequences")
7084 "This package provides memory efficient S4 classes for storing sequences
7085 \"externally\" (behind an R external pointer, or on disk).")
7086 (license license:artistic2.0)))
7088 (define-public r-genomicranges
7090 (name "r-genomicranges")
7094 (uri (bioconductor-uri "GenomicRanges" version))
7097 "1wnvvhj8yjsx242y6kfr5vs8kzisa96rxl1rgnnychrrvnvnh3i1"))))
7099 `((upstream-name . "GenomicRanges")))
7100 (build-system r-build-system)
7102 `(("r-biocgenerics" ,r-biocgenerics)
7103 ("r-genomeinfodb" ,r-genomeinfodb)
7104 ("r-iranges" ,r-iranges)
7105 ("r-s4vectors" ,r-s4vectors)
7106 ("r-xvector" ,r-xvector)))
7107 (home-page "https://bioconductor.org/packages/GenomicRanges")
7108 (synopsis "Representation and manipulation of genomic intervals")
7110 "This package provides tools to efficiently represent and manipulate
7111 genomic annotations and alignments is playing a central role when it comes to
7112 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7113 GenomicRanges package defines general purpose containers for storing and
7114 manipulating genomic intervals and variables defined along a genome.")
7115 (license license:artistic2.0)))
7117 (define-public r-biobase
7123 (uri (bioconductor-uri "Biobase" version))
7126 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7128 `((upstream-name . "Biobase")))
7129 (build-system r-build-system)
7131 `(("r-biocgenerics" ,r-biocgenerics)))
7132 (home-page "https://bioconductor.org/packages/Biobase")
7133 (synopsis "Base functions for Bioconductor")
7135 "This package provides functions that are needed by many other packages
7136 on Bioconductor or which replace R functions.")
7137 (license license:artistic2.0)))
7139 (define-public r-annotationdbi
7141 (name "r-annotationdbi")
7145 (uri (bioconductor-uri "AnnotationDbi" version))
7148 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7150 `((upstream-name . "AnnotationDbi")))
7151 (build-system r-build-system)
7153 `(("r-biobase" ,r-biobase)
7154 ("r-biocgenerics" ,r-biocgenerics)
7156 ("r-iranges" ,r-iranges)
7157 ("r-rsqlite" ,r-rsqlite)
7158 ("r-s4vectors" ,r-s4vectors)))
7159 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7160 (synopsis "Annotation database interface")
7162 "This package provides user interface and database connection code for
7163 annotation data packages using SQLite data storage.")
7164 (license license:artistic2.0)))
7166 (define-public r-biomart
7172 (uri (bioconductor-uri "biomaRt" version))
7175 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7177 `((upstream-name . "biomaRt")))
7178 (build-system r-build-system)
7180 `(("r-annotationdbi" ,r-annotationdbi)
7182 ("r-progress" ,r-progress)
7183 ("r-rcurl" ,r-rcurl)
7184 ("r-stringr" ,r-stringr)
7186 (home-page "https://bioconductor.org/packages/biomaRt")
7187 (synopsis "Interface to BioMart databases")
7189 "biomaRt provides an interface to a growing collection of databases
7190 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7191 package enables retrieval of large amounts of data in a uniform way without
7192 the need to know the underlying database schemas or write complex SQL queries.
7193 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7194 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7195 users direct access to a diverse set of data and enable a wide range of
7196 powerful online queries from gene annotation to database mining.")
7197 (license license:artistic2.0)))
7199 (define-public r-biocparallel
7201 (name "r-biocparallel")
7205 (uri (bioconductor-uri "BiocParallel" version))
7208 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7210 `((upstream-name . "BiocParallel")))
7211 (build-system r-build-system)
7213 `(("r-futile-logger" ,r-futile-logger)
7216 (home-page "https://bioconductor.org/packages/BiocParallel")
7217 (synopsis "Bioconductor facilities for parallel evaluation")
7219 "This package provides modified versions and novel implementation of
7220 functions for parallel evaluation, tailored to use with Bioconductor
7222 (license (list license:gpl2+ license:gpl3+))))
7224 (define-public r-biostrings
7226 (name "r-biostrings")
7230 (uri (bioconductor-uri "Biostrings" version))
7233 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7235 `((upstream-name . "Biostrings")))
7236 (build-system r-build-system)
7238 `(("r-biocgenerics" ,r-biocgenerics)
7239 ("r-iranges" ,r-iranges)
7240 ("r-s4vectors" ,r-s4vectors)
7241 ("r-xvector" ,r-xvector)))
7242 (home-page "https://bioconductor.org/packages/Biostrings")
7243 (synopsis "String objects and algorithms for biological sequences")
7245 "This package provides memory efficient string containers, string
7246 matching algorithms, and other utilities, for fast manipulation of large
7247 biological sequences or sets of sequences.")
7248 (license license:artistic2.0)))
7250 (define-public r-rsamtools
7252 (name "r-rsamtools")
7256 (uri (bioconductor-uri "Rsamtools" version))
7259 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7261 `((upstream-name . "Rsamtools")))
7262 (build-system r-build-system)
7265 (modify-phases %standard-phases
7266 (add-after 'unpack 'use-system-zlib
7268 (substitute* "DESCRIPTION"
7269 (("zlibbioc, ") ""))
7270 (substitute* "NAMESPACE"
7271 (("import\\(zlibbioc\\)") ""))
7276 `(("r-biocgenerics" ,r-biocgenerics)
7277 ("r-biocparallel" ,r-biocparallel)
7278 ("r-biostrings" ,r-biostrings)
7279 ("r-bitops" ,r-bitops)
7280 ("r-genomeinfodb" ,r-genomeinfodb)
7281 ("r-genomicranges" ,r-genomicranges)
7282 ("r-iranges" ,r-iranges)
7283 ("r-s4vectors" ,r-s4vectors)
7284 ("r-xvector" ,r-xvector)))
7285 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7286 (synopsis "Interface to samtools, bcftools, and tabix")
7288 "This package provides an interface to the 'samtools', 'bcftools', and
7289 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7290 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7292 (license license:expat)))
7294 (define-public r-delayedarray
7296 (name "r-delayedarray")
7300 (uri (bioconductor-uri "DelayedArray" version))
7303 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7305 `((upstream-name . "DelayedArray")))
7306 (build-system r-build-system)
7308 `(("r-biocgenerics" ,r-biocgenerics)
7309 ("r-s4vectors" ,r-s4vectors)
7310 ("r-iranges" ,r-iranges)
7311 ("r-matrixstats" ,r-matrixstats)))
7312 (home-page "https://bioconductor.org/packages/DelayedArray")
7313 (synopsis "Delayed operations on array-like objects")
7315 "Wrapping an array-like object (typically an on-disk object) in a
7316 @code{DelayedArray} object allows one to perform common array operations on it
7317 without loading the object in memory. In order to reduce memory usage and
7318 optimize performance, operations on the object are either delayed or executed
7319 using a block processing mechanism. Note that this also works on in-memory
7320 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7321 @code{Matrix} objects, and ordinary arrays and data frames.")
7322 (license license:artistic2.0)))
7324 (define-public r-summarizedexperiment
7326 (name "r-summarizedexperiment")
7330 (uri (bioconductor-uri "SummarizedExperiment" version))
7333 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7335 `((upstream-name . "SummarizedExperiment")))
7336 (build-system r-build-system)
7338 `(("r-biobase" ,r-biobase)
7339 ("r-biocgenerics" ,r-biocgenerics)
7340 ("r-delayedarray" ,r-delayedarray)
7341 ("r-genomeinfodb" ,r-genomeinfodb)
7342 ("r-genomicranges" ,r-genomicranges)
7343 ("r-iranges" ,r-iranges)
7344 ("r-matrix" ,r-matrix)
7345 ("r-s4vectors" ,r-s4vectors)))
7346 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7347 (synopsis "Container for representing genomic ranges by sample")
7349 "The SummarizedExperiment container contains one or more assays, each
7350 represented by a matrix-like object of numeric or other mode. The rows
7351 typically represent genomic ranges of interest and the columns represent
7353 (license license:artistic2.0)))
7355 (define-public r-genomicalignments
7357 (name "r-genomicalignments")
7361 (uri (bioconductor-uri "GenomicAlignments" version))
7364 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7366 `((upstream-name . "GenomicAlignments")))
7367 (build-system r-build-system)
7369 `(("r-biocgenerics" ,r-biocgenerics)
7370 ("r-biocparallel" ,r-biocparallel)
7371 ("r-biostrings" ,r-biostrings)
7372 ("r-genomeinfodb" ,r-genomeinfodb)
7373 ("r-genomicranges" ,r-genomicranges)
7374 ("r-iranges" ,r-iranges)
7375 ("r-rsamtools" ,r-rsamtools)
7376 ("r-s4vectors" ,r-s4vectors)
7377 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7378 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7379 (synopsis "Representation and manipulation of short genomic alignments")
7381 "This package provides efficient containers for storing and manipulating
7382 short genomic alignments (typically obtained by aligning short reads to a
7383 reference genome). This includes read counting, computing the coverage,
7384 junction detection, and working with the nucleotide content of the
7386 (license license:artistic2.0)))
7388 (define-public r-rtracklayer
7390 (name "r-rtracklayer")
7394 (uri (bioconductor-uri "rtracklayer" version))
7397 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7398 (build-system r-build-system)
7401 (modify-phases %standard-phases
7402 (add-after 'unpack 'use-system-zlib
7404 (substitute* "DESCRIPTION"
7405 ((" zlibbioc,") ""))
7406 (substitute* "NAMESPACE"
7407 (("import\\(zlibbioc\\)") ""))
7412 `(("r-biocgenerics" ,r-biocgenerics)
7413 ("r-biostrings" ,r-biostrings)
7414 ("r-genomeinfodb" ,r-genomeinfodb)
7415 ("r-genomicalignments" ,r-genomicalignments)
7416 ("r-genomicranges" ,r-genomicranges)
7417 ("r-iranges" ,r-iranges)
7418 ("r-rcurl" ,r-rcurl)
7419 ("r-rsamtools" ,r-rsamtools)
7420 ("r-s4vectors" ,r-s4vectors)
7422 ("r-xvector" ,r-xvector)))
7423 (home-page "https://bioconductor.org/packages/rtracklayer")
7424 (synopsis "R interface to genome browsers and their annotation tracks")
7426 "rtracklayer is an extensible framework for interacting with multiple
7427 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7428 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7429 built-in). The user may export/import tracks to/from the supported browsers,
7430 as well as query and modify the browser state, such as the current viewport.")
7431 (license license:artistic2.0)))
7433 (define-public r-genomicfeatures
7435 (name "r-genomicfeatures")
7439 (uri (bioconductor-uri "GenomicFeatures" version))
7442 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7444 `((upstream-name . "GenomicFeatures")))
7445 (build-system r-build-system)
7447 `(("r-annotationdbi" ,r-annotationdbi)
7448 ("r-biobase" ,r-biobase)
7449 ("r-biocgenerics" ,r-biocgenerics)
7450 ("r-biomart" ,r-biomart)
7451 ("r-biostrings" ,r-biostrings)
7453 ("r-genomeinfodb" ,r-genomeinfodb)
7454 ("r-genomicranges" ,r-genomicranges)
7455 ("r-iranges" ,r-iranges)
7456 ("r-rcurl" ,r-rcurl)
7457 ("r-rsqlite" ,r-rsqlite)
7458 ("r-rmysql" ,r-rmysql)
7459 ("r-rtracklayer" ,r-rtracklayer)
7460 ("r-s4vectors" ,r-s4vectors)
7461 ("r-xvector" ,r-xvector)))
7462 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7463 (synopsis "Tools for working with transcript centric annotations")
7465 "This package provides a set of tools and methods for making and
7466 manipulating transcript centric annotations. With these tools the user can
7467 easily download the genomic locations of the transcripts, exons and cds of a
7468 given organism, from either the UCSC Genome Browser or a BioMart
7469 database (more sources will be supported in the future). This information is
7470 then stored in a local database that keeps track of the relationship between
7471 transcripts, exons, cds and genes. Flexible methods are provided for
7472 extracting the desired features in a convenient format.")
7473 (license license:artistic2.0)))
7475 (define-public r-go-db
7481 (uri (string-append "https://www.bioconductor.org/packages/"
7482 "release/data/annotation/src/contrib/GO.db_"
7486 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7488 `((upstream-name . "GO.db")))
7489 (build-system r-build-system)
7491 `(("r-annotationdbi" ,r-annotationdbi)))
7492 (home-page "https://bioconductor.org/packages/GO.db")
7493 (synopsis "Annotation maps describing the entire Gene Ontology")
7495 "The purpose of this GO.db annotation package is to provide detailed
7496 information about the latest version of the Gene Ontologies.")
7497 (license license:artistic2.0)))
7499 (define-public r-graph
7505 (uri (bioconductor-uri "graph" version))
7508 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7509 (build-system r-build-system)
7511 `(("r-biocgenerics" ,r-biocgenerics)))
7512 (home-page "https://bioconductor.org/packages/graph")
7513 (synopsis "Handle graph data structures in R")
7515 "This package implements some simple graph handling capabilities for R.")
7516 (license license:artistic2.0)))
7518 (define-public r-topgo
7524 (uri (bioconductor-uri "topGO" version))
7527 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
7529 `((upstream-name . "topGO")))
7530 (build-system r-build-system)
7532 `(("r-annotationdbi" ,r-annotationdbi)
7534 ("r-biobase" ,r-biobase)
7535 ("r-biocgenerics" ,r-biocgenerics)
7536 ("r-go-db" ,r-go-db)
7537 ("r-graph" ,r-graph)
7538 ("r-lattice" ,r-lattice)
7539 ("r-matrixstats" ,r-matrixstats)
7540 ("r-sparsem" ,r-sparsem)))
7541 (home-page "https://bioconductor.org/packages/topGO")
7542 (synopsis "Enrichment analysis for gene ontology")
7544 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7545 terms while accounting for the topology of the GO graph. Different test
7546 statistics and different methods for eliminating local similarities and
7547 dependencies between GO terms can be implemented and applied.")
7548 ;; Any version of the LGPL applies.
7549 (license license:lgpl2.1+)))
7551 (define-public r-bsgenome
7557 (uri (bioconductor-uri "BSgenome" version))
7560 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7562 `((upstream-name . "BSgenome")))
7563 (build-system r-build-system)
7565 `(("r-biocgenerics" ,r-biocgenerics)
7566 ("r-biostrings" ,r-biostrings)
7567 ("r-genomeinfodb" ,r-genomeinfodb)
7568 ("r-genomicranges" ,r-genomicranges)
7569 ("r-iranges" ,r-iranges)
7570 ("r-rsamtools" ,r-rsamtools)
7571 ("r-rtracklayer" ,r-rtracklayer)
7572 ("r-s4vectors" ,r-s4vectors)
7573 ("r-xvector" ,r-xvector)))
7574 (home-page "https://bioconductor.org/packages/BSgenome")
7575 (synopsis "Infrastructure for Biostrings-based genome data packages")
7577 "This package provides infrastructure shared by all Biostrings-based
7578 genome data packages and support for efficient SNP representation.")
7579 (license license:artistic2.0)))
7581 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7583 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7587 ;; We cannot use bioconductor-uri here because this tarball is
7588 ;; located under "data/annotation/" instead of "bioc/".
7589 (uri (string-append "https://www.bioconductor.org/packages/"
7590 "release/data/annotation/src/contrib/"
7591 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7595 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7597 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7598 (build-system r-build-system)
7599 ;; As this package provides little more than a very large data file it
7600 ;; doesn't make sense to build substitutes.
7601 (arguments `(#:substitutable? #f))
7603 `(("r-bsgenome" ,r-bsgenome)))
7605 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7606 (synopsis "Full genome sequences for Homo sapiens")
7608 "This package provides full genome sequences for Homo sapiens from
7609 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7610 (license license:artistic2.0)))
7612 (define-public r-impute
7618 (uri (bioconductor-uri "impute" version))
7621 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7623 `(("gfortran" ,gfortran)))
7624 (build-system r-build-system)
7625 (home-page "https://bioconductor.org/packages/impute")
7626 (synopsis "Imputation for microarray data")
7628 "This package provides a function to impute missing gene expression
7629 microarray data, using nearest neighbor averaging.")
7630 (license license:gpl2+)))
7632 (define-public r-seqpattern
7634 (name "r-seqpattern")
7638 (uri (bioconductor-uri "seqPattern" version))
7641 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7643 `((upstream-name . "seqPattern")))
7644 (build-system r-build-system)
7646 `(("r-biostrings" ,r-biostrings)
7647 ("r-genomicranges" ,r-genomicranges)
7648 ("r-iranges" ,r-iranges)
7649 ("r-kernsmooth" ,r-kernsmooth)
7650 ("r-plotrix" ,r-plotrix)))
7651 (home-page "https://bioconductor.org/packages/seqPattern")
7652 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7654 "This package provides tools to visualize oligonucleotide patterns and
7655 sequence motif occurrences across a large set of sequences centred at a common
7656 reference point and sorted by a user defined feature.")
7657 (license license:gpl3+)))
7659 (define-public r-genomation
7661 (name "r-genomation")
7665 (uri (bioconductor-uri "genomation" version))
7668 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7669 (build-system r-build-system)
7671 `(("r-biostrings" ,r-biostrings)
7672 ("r-bsgenome" ,r-bsgenome)
7673 ("r-data-table" ,r-data-table)
7674 ("r-genomeinfodb" ,r-genomeinfodb)
7675 ("r-genomicalignments" ,r-genomicalignments)
7676 ("r-genomicranges" ,r-genomicranges)
7677 ("r-ggplot2" ,r-ggplot2)
7678 ("r-gridbase" ,r-gridbase)
7679 ("r-impute" ,r-impute)
7680 ("r-iranges" ,r-iranges)
7681 ("r-matrixstats" ,r-matrixstats)
7682 ("r-plotrix" ,r-plotrix)
7685 ("r-readr" ,r-readr)
7686 ("r-reshape2" ,r-reshape2)
7687 ("r-rsamtools" ,r-rsamtools)
7688 ("r-rtracklayer" ,r-rtracklayer)
7689 ("r-runit" ,r-runit)
7690 ("r-s4vectors" ,r-s4vectors)
7691 ("r-seqpattern" ,r-seqpattern)))
7692 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7693 (synopsis "Summary, annotation and visualization of genomic data")
7695 "This package provides a package for summary and annotation of genomic
7696 intervals. Users can visualize and quantify genomic intervals over
7697 pre-defined functional regions, such as promoters, exons, introns, etc. The
7698 genomic intervals represent regions with a defined chromosome position, which
7699 may be associated with a score, such as aligned reads from HT-seq experiments,
7700 TF binding sites, methylation scores, etc. The package can use any tabular
7701 genomic feature data as long as it has minimal information on the locations of
7702 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7703 (license license:artistic2.0)))
7705 (define-public r-genomationdata
7707 (name "r-genomationdata")
7711 ;; We cannot use bioconductor-uri here because this tarball is
7712 ;; located under "data/annotation/" instead of "bioc/".
7713 (uri (string-append "https://bioconductor.org/packages/"
7714 "release/data/experiment/src/contrib/"
7715 "genomationData_" version ".tar.gz"))
7718 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7719 (build-system r-build-system)
7720 ;; As this package provides little more than large data files, it doesn't
7721 ;; make sense to build substitutes.
7722 (arguments `(#:substitutable? #f))
7724 `(("r-knitr" ,r-knitr)))
7725 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7726 (synopsis "Experimental data for use with the genomation package")
7728 "This package contains experimental genetic data for use with the
7729 genomation package. Included are Chip Seq, Methylation and Cage data,
7730 downloaded from Encode.")
7731 (license license:gpl3+)))
7733 (define-public r-org-hs-eg-db
7735 (name "r-org-hs-eg-db")
7739 ;; We cannot use bioconductor-uri here because this tarball is
7740 ;; located under "data/annotation/" instead of "bioc/".
7741 (uri (string-append "https://www.bioconductor.org/packages/"
7742 "release/data/annotation/src/contrib/"
7743 "org.Hs.eg.db_" version ".tar.gz"))
7746 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7748 `((upstream-name . "org.Hs.eg.db")))
7749 (build-system r-build-system)
7751 `(("r-annotationdbi" ,r-annotationdbi)))
7752 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7753 (synopsis "Genome wide annotation for Human")
7755 "This package contains genome-wide annotations for Human, primarily based
7756 on mapping using Entrez Gene identifiers.")
7757 (license license:artistic2.0)))
7759 (define-public r-org-ce-eg-db
7761 (name "r-org-ce-eg-db")
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 "org.Ce.eg.db_" version ".tar.gz"))
7772 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7774 `((upstream-name . "org.Ce.eg.db")))
7775 (build-system r-build-system)
7777 `(("r-annotationdbi" ,r-annotationdbi)))
7778 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7779 (synopsis "Genome wide annotation for Worm")
7781 "This package provides mappings from Entrez gene identifiers to various
7782 annotations for the genome of the model worm Caenorhabditis elegans.")
7783 (license license:artistic2.0)))
7785 (define-public r-org-dm-eg-db
7787 (name "r-org-dm-eg-db")
7791 ;; We cannot use bioconductor-uri here because this tarball is
7792 ;; located under "data/annotation/" instead of "bioc/".
7793 (uri (string-append "https://www.bioconductor.org/packages/"
7794 "release/data/annotation/src/contrib/"
7795 "org.Dm.eg.db_" version ".tar.gz"))
7798 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
7800 `((upstream-name . "org.Dm.eg.db")))
7801 (build-system r-build-system)
7803 `(("r-annotationdbi" ,r-annotationdbi)))
7804 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7805 (synopsis "Genome wide annotation for Fly")
7807 "This package provides mappings from Entrez gene identifiers to various
7808 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7809 (license license:artistic2.0)))
7811 (define-public r-org-mm-eg-db
7813 (name "r-org-mm-eg-db")
7817 ;; We cannot use bioconductor-uri here because this tarball is
7818 ;; located under "data/annotation/" instead of "bioc/".
7819 (uri (string-append "https://www.bioconductor.org/packages/"
7820 "release/data/annotation/src/contrib/"
7821 "org.Mm.eg.db_" version ".tar.gz"))
7824 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
7826 `((upstream-name . "org.Mm.eg.db")))
7827 (build-system r-build-system)
7829 `(("r-annotationdbi" ,r-annotationdbi)))
7830 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7831 (synopsis "Genome wide annotation for Mouse")
7833 "This package provides mappings from Entrez gene identifiers to various
7834 annotations for the genome of the model mouse Mus musculus.")
7835 (license license:artistic2.0)))
7837 (define-public r-seqlogo
7844 (uri (bioconductor-uri "seqLogo" version))
7847 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7848 (properties `((upstream-name . "seqLogo")))
7849 (build-system r-build-system)
7850 (home-page "https://bioconductor.org/packages/seqLogo")
7851 (synopsis "Sequence logos for DNA sequence alignments")
7853 "seqLogo takes the position weight matrix of a DNA sequence motif and
7854 plots the corresponding sequence logo as introduced by Schneider and
7856 (license license:lgpl2.0+)))
7858 (define-public r-bsgenome-hsapiens-ucsc-hg19
7860 (name "r-bsgenome-hsapiens-ucsc-hg19")
7864 ;; We cannot use bioconductor-uri here because this tarball is
7865 ;; located under "data/annotation/" instead of "bioc/".
7866 (uri (string-append "https://www.bioconductor.org/packages/"
7867 "release/data/annotation/src/contrib/"
7868 "BSgenome.Hsapiens.UCSC.hg19_"
7872 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7874 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7875 (build-system r-build-system)
7876 ;; As this package provides little more than a very large data file it
7877 ;; doesn't make sense to build substitutes.
7878 (arguments `(#:substitutable? #f))
7880 `(("r-bsgenome" ,r-bsgenome)))
7882 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7883 (synopsis "Full genome sequences for Homo sapiens")
7885 "This package provides full genome sequences for Homo sapiens as provided
7886 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7887 (license license:artistic2.0)))
7889 (define-public r-bsgenome-mmusculus-ucsc-mm9
7891 (name "r-bsgenome-mmusculus-ucsc-mm9")
7895 ;; We cannot use bioconductor-uri here because this tarball is
7896 ;; located under "data/annotation/" instead of "bioc/".
7897 (uri (string-append "https://www.bioconductor.org/packages/"
7898 "release/data/annotation/src/contrib/"
7899 "BSgenome.Mmusculus.UCSC.mm9_"
7903 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7905 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7906 (build-system r-build-system)
7907 ;; As this package provides little more than a very large data file it
7908 ;; doesn't make sense to build substitutes.
7909 (arguments `(#:substitutable? #f))
7911 `(("r-bsgenome" ,r-bsgenome)))
7913 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7914 (synopsis "Full genome sequences for Mouse")
7916 "This package provides full genome sequences for Mus musculus (Mouse) as
7917 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7918 (license license:artistic2.0)))
7920 (define-public r-bsgenome-mmusculus-ucsc-mm10
7922 (name "r-bsgenome-mmusculus-ucsc-mm10")
7926 ;; We cannot use bioconductor-uri here because this tarball is
7927 ;; located under "data/annotation/" instead of "bioc/".
7928 (uri (string-append "https://www.bioconductor.org/packages/"
7929 "release/data/annotation/src/contrib/"
7930 "BSgenome.Mmusculus.UCSC.mm10_"
7934 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7936 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7937 (build-system r-build-system)
7938 ;; As this package provides little more than a very large data file it
7939 ;; doesn't make sense to build substitutes.
7940 (arguments `(#:substitutable? #f))
7942 `(("r-bsgenome" ,r-bsgenome)))
7944 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7945 (synopsis "Full genome sequences for Mouse")
7947 "This package provides full genome sequences for Mus
7948 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7949 in Biostrings objects.")
7950 (license license:artistic2.0)))
7952 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7954 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7958 ;; We cannot use bioconductor-uri here because this tarball is
7959 ;; located under "data/annotation/" instead of "bioc/".
7960 (uri (string-append "https://www.bioconductor.org/packages/"
7961 "release/data/annotation/src/contrib/"
7962 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7966 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7968 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7969 (build-system r-build-system)
7970 ;; As this package provides little more than a very large data file it
7971 ;; doesn't make sense to build substitutes.
7972 (arguments `(#:substitutable? #f))
7974 `(("r-bsgenome" ,r-bsgenome)
7975 ("r-genomicfeatures" ,r-genomicfeatures)
7976 ("r-annotationdbi" ,r-annotationdbi)))
7978 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7979 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7981 "This package loads a TxDb object, which is an R interface to
7982 prefabricated databases contained in this package. This package provides
7983 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7984 based on the knownGene track.")
7985 (license license:artistic2.0)))
7987 (define-public r-bsgenome-celegans-ucsc-ce6
7989 (name "r-bsgenome-celegans-ucsc-ce6")
7993 ;; We cannot use bioconductor-uri here because this tarball is
7994 ;; located under "data/annotation/" instead of "bioc/".
7995 (uri (string-append "https://www.bioconductor.org/packages/"
7996 "release/data/annotation/src/contrib/"
7997 "BSgenome.Celegans.UCSC.ce6_"
8001 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8003 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8004 (build-system r-build-system)
8005 ;; As this package provides little more than a very large data file it
8006 ;; doesn't make sense to build substitutes.
8007 (arguments `(#:substitutable? #f))
8009 `(("r-bsgenome" ,r-bsgenome)))
8011 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8012 (synopsis "Full genome sequences for Worm")
8014 "This package provides full genome sequences for Caenorhabditis
8015 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8017 (license license:artistic2.0)))
8019 (define-public r-bsgenome-celegans-ucsc-ce10
8021 (name "r-bsgenome-celegans-ucsc-ce10")
8025 ;; We cannot use bioconductor-uri here because this tarball is
8026 ;; located under "data/annotation/" instead of "bioc/".
8027 (uri (string-append "https://www.bioconductor.org/packages/"
8028 "release/data/annotation/src/contrib/"
8029 "BSgenome.Celegans.UCSC.ce10_"
8033 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8035 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8036 (build-system r-build-system)
8037 ;; As this package provides little more than a very large data file it
8038 ;; doesn't make sense to build substitutes.
8039 (arguments `(#:substitutable? #f))
8041 `(("r-bsgenome" ,r-bsgenome)))
8043 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8044 (synopsis "Full genome sequences for Worm")
8046 "This package provides full genome sequences for Caenorhabditis
8047 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8049 (license license:artistic2.0)))
8051 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8053 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8057 ;; We cannot use bioconductor-uri here because this tarball is
8058 ;; located under "data/annotation/" instead of "bioc/".
8059 (uri (string-append "https://www.bioconductor.org/packages/"
8060 "release/data/annotation/src/contrib/"
8061 "BSgenome.Dmelanogaster.UCSC.dm3_"
8065 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8067 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8068 (build-system r-build-system)
8069 ;; As this package provides little more than a very large data file it
8070 ;; doesn't make sense to build substitutes.
8071 (arguments `(#:substitutable? #f))
8073 `(("r-bsgenome" ,r-bsgenome)))
8075 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8076 (synopsis "Full genome sequences for Fly")
8078 "This package provides full genome sequences for Drosophila
8079 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8080 Biostrings objects.")
8081 (license license:artistic2.0)))
8083 (define-public r-motifrg
8090 (uri (bioconductor-uri "motifRG" version))
8093 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8094 (properties `((upstream-name . "motifRG")))
8095 (build-system r-build-system)
8097 `(("r-biostrings" ,r-biostrings)
8098 ("r-bsgenome" ,r-bsgenome)
8099 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8100 ("r-iranges" ,r-iranges)
8101 ("r-seqlogo" ,r-seqlogo)
8102 ("r-xvector" ,r-xvector)))
8103 (home-page "https://bioconductor.org/packages/motifRG")
8104 (synopsis "Discover motifs in high throughput sequencing data")
8106 "This package provides tools for discriminative motif discovery in high
8107 throughput genetic sequencing data sets using regression methods.")
8108 (license license:artistic2.0)))
8110 (define-public r-qtl
8117 (uri (string-append "mirror://cran/src/contrib/qtl_"
8121 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
8122 (build-system r-build-system)
8123 (home-page "http://rqtl.org/")
8124 (synopsis "R package for analyzing QTL experiments in genetics")
8125 (description "R/qtl is an extension library for the R statistics
8126 system. It is used to analyze experimental crosses for identifying
8127 genes contributing to variation in quantitative traits (so-called
8128 quantitative trait loci, QTLs).
8130 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8131 identify genotyping errors, and to perform single-QTL and two-QTL,
8132 two-dimensional genome scans.")
8133 (license license:gpl3)))
8135 (define-public r-zlibbioc
8141 (uri (bioconductor-uri "zlibbioc" version))
8144 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8146 `((upstream-name . "zlibbioc")))
8147 (build-system r-build-system)
8148 (home-page "https://bioconductor.org/packages/zlibbioc")
8149 (synopsis "Provider for zlib-1.2.5 to R packages")
8150 (description "This package uses the source code of zlib-1.2.5 to create
8151 libraries for systems that do not have these available via other means.")
8152 (license license:artistic2.0)))
8154 (define-public r-r4rna
8161 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8165 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8166 (build-system r-build-system)
8168 `(("r-optparse" ,r-optparse)
8169 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8170 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8171 (synopsis "Analysis framework for RNA secondary structure")
8173 "The R4RNA package aims to be a general framework for the analysis of RNA
8174 secondary structure and comparative analysis in R.")
8175 (license license:gpl3+)))
8177 (define-public r-rhtslib
8184 (uri (bioconductor-uri "Rhtslib" version))
8187 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8188 (properties `((upstream-name . "Rhtslib")))
8189 (build-system r-build-system)
8191 `(("r-zlibbioc" ,r-zlibbioc)))
8195 `(("autoconf" ,autoconf)))
8196 (home-page "https://github.com/nhayden/Rhtslib")
8197 (synopsis "High-throughput sequencing library as an R package")
8199 "This package provides the HTSlib C library for high-throughput
8200 nucleotide sequence analysis. The package is primarily useful to developers
8201 of other R packages who wish to make use of HTSlib.")
8202 (license license:lgpl2.0+)))
8204 (define-public r-bamsignals
8206 (name "r-bamsignals")
8211 (uri (bioconductor-uri "bamsignals" version))
8214 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8215 (build-system r-build-system)
8217 `(("r-biocgenerics" ,r-biocgenerics)
8218 ("r-genomicranges" ,r-genomicranges)
8219 ("r-iranges" ,r-iranges)
8221 ("r-rhtslib" ,r-rhtslib)
8222 ("r-zlibbioc" ,r-zlibbioc)))
8225 (home-page "https://bioconductor.org/packages/bamsignals")
8226 (synopsis "Extract read count signals from bam files")
8228 "This package allows to efficiently obtain count vectors from indexed bam
8229 files. It counts the number of nucleotide sequence reads in given genomic
8230 ranges and it computes reads profiles and coverage profiles. It also handles
8232 (license license:gpl2+)))
8234 (define-public r-rcas
8240 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8242 (file-name (string-append name "-" version ".tar.gz"))
8245 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8246 (build-system r-build-system)
8248 `(("r-knitr" ,r-knitr)
8249 ("r-testthat" ,r-testthat)
8250 ;; During vignette building knitr checks that "pandoc-citeproc"
8252 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8254 `(("r-data-table" ,r-data-table)
8255 ("r-biomart" ,r-biomart)
8256 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8257 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8258 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8259 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8260 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8261 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8262 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8263 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8264 ("r-topgo" ,r-topgo)
8266 ("r-pbapply" ,r-pbapply)
8267 ("r-plotly" ,r-plotly)
8268 ("r-plotrix" ,r-plotrix)
8269 ("r-motifrg" ,r-motifrg)
8270 ("r-genomation" ,r-genomation)
8271 ("r-genomicfeatures" ,r-genomicfeatures)
8272 ("r-rtracklayer" ,r-rtracklayer)
8273 ("r-rmarkdown" ,r-rmarkdown)))
8274 (synopsis "RNA-centric annotation system")
8276 "RCAS aims to be a standalone RNA-centric annotation system that provides
8277 intuitive reports and publication-ready graphics. This package provides the R
8278 library implementing most of the pipeline's features.")
8279 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8280 (license license:artistic2.0)))
8282 (define-public rcas-web
8289 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8290 "releases/download/v" version
8291 "/rcas-web-" version ".tar.gz"))
8294 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8295 (build-system gnu-build-system)
8298 (modify-phases %standard-phases
8299 (add-after 'install 'wrap-executable
8300 (lambda* (#:key inputs outputs #:allow-other-keys)
8301 (let* ((out (assoc-ref outputs "out"))
8302 (json (assoc-ref inputs "guile-json"))
8303 (redis (assoc-ref inputs "guile-redis"))
8304 (path (string-append
8305 json "/share/guile/site/2.2:"
8306 redis "/share/guile/site/2.2")))
8307 (wrap-program (string-append out "/bin/rcas-web")
8308 `("GUILE_LOAD_PATH" ":" = (,path))
8309 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8310 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8313 `(("r-minimal" ,r-minimal)
8315 ("guile-next" ,guile-2.2)
8316 ("guile-json" ,guile-json)
8317 ("guile-redis" ,guile2.2-redis)))
8319 `(("pkg-config" ,pkg-config)))
8320 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8321 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8322 (description "This package provides a simple web interface for the
8323 @dfn{RNA-centric annotation system} (RCAS).")
8324 (license license:agpl3+)))
8326 (define-public r-mutationalpatterns
8328 (name "r-mutationalpatterns")
8333 (uri (bioconductor-uri "MutationalPatterns" version))
8336 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8337 (build-system r-build-system)
8339 `(("r-biocgenerics" ,r-biocgenerics)
8340 ("r-biostrings" ,r-biostrings)
8341 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8342 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8343 ("r-genomicranges" ,r-genomicranges)
8344 ("r-genomeinfodb" ,r-genomeinfodb)
8345 ("r-ggplot2" ,r-ggplot2)
8346 ("r-gridextra" ,r-gridextra)
8347 ("r-iranges" ,r-iranges)
8350 ("r-pracma" ,r-pracma)
8351 ("r-reshape2" ,r-reshape2)
8352 ("r-cowplot" ,r-cowplot)
8353 ("r-ggdendro" ,r-ggdendro)
8354 ("r-s4vectors" ,r-s4vectors)
8355 ("r-summarizedexperiment" ,r-summarizedexperiment)
8356 ("r-variantannotation" ,r-variantannotation)))
8357 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8358 (synopsis "Extract and visualize mutational patterns in genomic data")
8359 (description "This package provides an extensive toolset for the
8360 characterization and visualization of a wide range of mutational patterns
8361 in SNV base substitution data.")
8362 (license license:expat)))
8364 (define-public r-wgcna
8371 (uri (cran-uri "WGCNA" version))
8374 "0c52rp09gqphz6g5x9jzkdcsyvfrknq0dkq9saslgy8q8ap974vx"))))
8375 (properties `((upstream-name . "WGCNA")))
8376 (build-system r-build-system)
8378 `(("r-annotationdbi" ,r-annotationdbi)
8379 ("r-doparallel" ,r-doparallel)
8380 ("r-dynamictreecut" ,r-dynamictreecut)
8381 ("r-fastcluster" ,r-fastcluster)
8382 ("r-foreach" ,r-foreach)
8383 ("r-go-db" ,r-go-db)
8384 ("r-hmisc" ,r-hmisc)
8385 ("r-impute" ,r-impute)
8387 ("r-robust" ,r-robust)
8388 ("r-survival" ,r-survival)
8389 ("r-matrixstats" ,r-matrixstats)
8390 ("r-preprocesscore" ,r-preprocesscore)))
8392 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8393 (synopsis "Weighted correlation network analysis")
8395 "This package provides functions necessary to perform Weighted
8396 Correlation Network Analysis on high-dimensional data. It includes functions
8397 for rudimentary data cleaning, construction and summarization of correlation
8398 networks, module identification and functions for relating both variables and
8399 modules to sample traits. It also includes a number of utility functions for
8400 data manipulation and visualization.")
8401 (license license:gpl2+)))
8403 (define-public r-chipkernels
8404 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8407 (name "r-chipkernels")
8408 (version (string-append "1.1-" revision "." (string-take commit 9)))
8413 (url "https://github.com/ManuSetty/ChIPKernels.git")
8415 (file-name (string-append name "-" version))
8418 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8419 (build-system r-build-system)
8421 `(("r-iranges" ,r-iranges)
8422 ("r-xvector" ,r-xvector)
8423 ("r-biostrings" ,r-biostrings)
8424 ("r-bsgenome" ,r-bsgenome)
8425 ("r-gtools" ,r-gtools)
8426 ("r-genomicranges" ,r-genomicranges)
8427 ("r-sfsmisc" ,r-sfsmisc)
8428 ("r-kernlab" ,r-kernlab)
8429 ("r-s4vectors" ,r-s4vectors)
8430 ("r-biocgenerics" ,r-biocgenerics)))
8431 (home-page "https://github.com/ManuSetty/ChIPKernels")
8432 (synopsis "Build string kernels for DNA Sequence analysis")
8433 (description "ChIPKernels is an R package for building different string
8434 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8435 must be built and this dictionary can be used for determining kernels for DNA
8437 (license license:gpl2+))))
8439 (define-public r-seqgl
8446 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8447 "archive/" version ".tar.gz"))
8448 (file-name (string-append name "-" version ".tar.gz"))
8451 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8452 (build-system r-build-system)
8454 `(("r-biostrings" ,r-biostrings)
8455 ("r-chipkernels" ,r-chipkernels)
8456 ("r-genomicranges" ,r-genomicranges)
8457 ("r-spams" ,r-spams)
8458 ("r-wgcna" ,r-wgcna)
8459 ("r-fastcluster" ,r-fastcluster)))
8460 (home-page "https://github.com/ManuSetty/SeqGL")
8461 (synopsis "Group lasso for Dnase/ChIP-seq data")
8462 (description "SeqGL is a group lasso based algorithm to extract
8463 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8464 This package presents a method which uses group lasso to discriminate between
8465 bound and non bound genomic regions to accurately identify transcription
8466 factors bound at the specific regions.")
8467 (license license:gpl2+)))
8469 (define-public r-gkmsvm
8476 (uri (cran-uri "gkmSVM" version))
8479 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8480 (properties `((upstream-name . "gkmSVM")))
8481 (build-system r-build-system)
8483 `(("r-biocgenerics" ,r-biocgenerics)
8484 ("r-biostrings" ,r-biostrings)
8485 ("r-genomeinfodb" ,r-genomeinfodb)
8486 ("r-genomicranges" ,r-genomicranges)
8487 ("r-iranges" ,r-iranges)
8488 ("r-kernlab" ,r-kernlab)
8491 ("r-rtracklayer" ,r-rtracklayer)
8492 ("r-s4vectors" ,r-s4vectors)
8493 ("r-seqinr" ,r-seqinr)))
8494 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8495 (synopsis "Gapped-kmer support vector machine")
8497 "This R package provides tools for training gapped-kmer SVM classifiers
8498 for DNA and protein sequences. This package supports several sequence
8499 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8500 (license license:gpl2+)))
8502 (define-public r-tximport
8508 (uri (bioconductor-uri "tximport" version))
8511 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8512 (build-system r-build-system)
8513 (home-page "https://bioconductor.org/packages/tximport")
8514 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8516 "This package provides tools to import transcript-level abundance,
8517 estimated counts and transcript lengths, and to summarize them into matrices
8518 for use with downstream gene-level analysis packages. Average transcript
8519 length, weighted by sample-specific transcript abundance estimates, is
8520 provided as a matrix which can be used as an offset for different expression
8521 of gene-level counts.")
8522 (license license:gpl2+)))
8524 (define-public r-rhdf5
8530 (uri (bioconductor-uri "rhdf5" version))
8533 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8534 (build-system r-build-system)
8537 (modify-phases %standard-phases
8538 (add-after 'unpack 'unpack-smallhdf5
8539 (lambda* (#:key outputs #:allow-other-keys)
8540 (system* "tar" "-xzvf"
8541 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8542 (substitute* "src/hdf5/configure"
8546 `(("r-zlibbioc" ,r-zlibbioc)))
8550 (home-page "https://bioconductor.org/packages/rhdf5")
8551 (synopsis "HDF5 interface to R")
8553 "This R/Bioconductor package provides an interface between HDF5 and R.
8554 HDF5's main features are the ability to store and access very large and/or
8555 complex datasets and a wide variety of metadata on mass storage (disk) through
8556 a completely portable file format. The rhdf5 package is thus suited for the
8557 exchange of large and/or complex datasets between R and other software
8558 package, and for letting R applications work on datasets that are larger than
8559 the available RAM.")
8560 (license license:artistic2.0)))
8562 (define-public r-annotationfilter
8564 (name "r-annotationfilter")
8568 (uri (bioconductor-uri "AnnotationFilter" version))
8571 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8573 `((upstream-name . "AnnotationFilter")))
8574 (build-system r-build-system)
8576 `(("r-genomicranges" ,r-genomicranges)
8577 ("r-lazyeval" ,r-lazyeval)))
8578 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8579 (synopsis "Facilities for filtering Bioconductor annotation resources")
8581 "This package provides classes and other infrastructure to implement
8582 filters for manipulating Bioconductor annotation resources. The filters are
8583 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8584 (license license:artistic2.0)))
8586 (define-public emboss
8592 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8593 (version-major+minor version) ".0/"
8594 "EMBOSS-" version ".tar.gz"))
8597 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8598 (build-system gnu-build-system)
8601 (list (string-append "--with-hpdf="
8602 (assoc-ref %build-inputs "libharu")))
8604 (modify-phases %standard-phases
8605 (add-after 'unpack 'fix-checks
8607 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8608 ;; and zlib, but assume that they are all found at the same
8610 (substitute* "configure.in"
8611 (("CHECK_PNGDRIVER")
8612 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8613 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8614 AM_CONDITIONAL(AMPNG, true)"))
8616 (add-after 'fix-checks 'disable-update-check
8618 ;; At build time there is no connection to the Internet, so
8619 ;; looking for updates will not work.
8620 (substitute* "Makefile.am"
8621 (("\\$\\(bindir\\)/embossupdate") ""))
8623 (add-after 'disable-update-check 'autogen
8624 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8630 ("libharu" ,libharu)
8633 `(("autoconf" ,autoconf)
8634 ("automake" ,automake)
8635 ("libtool" ,libtool)
8636 ("pkg-config" ,pkg-config)))
8637 (home-page "http://emboss.sourceforge.net")
8638 (synopsis "Molecular biology analysis suite")
8639 (description "EMBOSS is the \"European Molecular Biology Open Software
8640 Suite\". EMBOSS is an analysis package specially developed for the needs of
8641 the molecular biology (e.g. EMBnet) user community. The software
8642 automatically copes with data in a variety of formats and even allows
8643 transparent retrieval of sequence data from the web. It also provides a
8644 number of libraries for the development of software in the field of molecular
8645 biology. EMBOSS also integrates a range of currently available packages and
8646 tools for sequence analysis into a seamless whole.")
8647 (license license:gpl2+)))
8650 (let ((revision "1")
8651 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8654 ;; The version is 2.13.0 even though no release archives have been
8655 ;; published as yet.
8656 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8660 (url "https://github.com/arq5x/bits.git")
8662 (file-name (string-append name "-" version "-checkout"))
8665 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8666 (build-system gnu-build-system)
8668 `(#:tests? #f ;no tests included
8670 (modify-phases %standard-phases
8672 (add-after 'unpack 'remove-cuda
8674 (substitute* "Makefile"
8676 (("(bits_test_intersections) \\\\" _ match) match))
8679 (lambda* (#:key outputs #:allow-other-keys)
8681 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8686 (home-page "https://github.com/arq5x/bits")
8687 (synopsis "Implementation of binary interval search algorithm")
8688 (description "This package provides an implementation of the
8689 BITS (Binary Interval Search) algorithm, an approach to interval set
8690 intersection. It is especially suited for the comparison of diverse genomic
8691 datasets and the exploration of large datasets of genome
8692 intervals (e.g. genes, sequence alignments).")
8693 (license license:gpl2))))
8695 (define-public piranha
8696 ;; There is no release tarball for the latest version. The latest commit is
8697 ;; older than one year at the time of this writing.
8698 (let ((revision "1")
8699 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8702 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8706 (url "https://github.com/smithlabcode/piranha.git")
8710 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8711 (build-system gnu-build-system)
8713 `(#:test-target "test"
8715 (modify-phases %standard-phases
8716 (add-after 'unpack 'copy-smithlab-cpp
8717 (lambda* (#:key inputs #:allow-other-keys)
8718 (for-each (lambda (file)
8719 (install-file file "./src/smithlab_cpp/"))
8720 (find-files (assoc-ref inputs "smithlab-cpp")))
8722 (add-after 'install 'install-to-store
8723 (lambda* (#:key outputs #:allow-other-keys)
8724 (let* ((out (assoc-ref outputs "out"))
8725 (bin (string-append out "/bin")))
8726 (for-each (lambda (file)
8727 (install-file file bin))
8728 (find-files "bin" ".*")))
8731 (list (string-append "--with-bam_tools_headers="
8732 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8733 (string-append "--with-bam_tools_library="
8734 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8736 `(("bamtools" ,bamtools)
8737 ("samtools" ,samtools-0.1)
8740 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8744 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8746 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8749 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8751 `(("python" ,python-2)))
8752 (home-page "https://github.com/smithlabcode/piranha")
8753 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8755 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8756 RIP-seq experiments. It takes input in BED or BAM format and identifies
8757 regions of statistically significant read enrichment. Additional covariates
8758 may optionally be provided to further inform the peak-calling process.")
8759 (license license:gpl3+))))
8767 (uri (string-append "https://pypi.python.org/packages/source/P"
8768 "/PePr/PePr-" version ".tar.gz"))
8771 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8772 (build-system python-build-system)
8774 `(#:python ,python-2 ; python2 only
8775 #:tests? #f)) ; no tests included
8777 `(("python2-numpy" ,python2-numpy)
8778 ("python2-scipy" ,python2-scipy)
8779 ("python2-pysam" ,python2-pysam)))
8780 (home-page "https://github.com/shawnzhangyx/PePr")
8781 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8783 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8784 that is primarily designed for data with biological replicates. It uses a
8785 negative binomial distribution to model the read counts among the samples in
8786 the same group, and look for consistent differences between ChIP and control
8787 group or two ChIP groups run under different conditions.")
8788 (license license:gpl3+)))
8790 (define-public filevercmp
8791 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8794 (version (string-append "0-1." (string-take commit 7)))
8797 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8799 (file-name (string-append name "-" version ".tar.gz"))
8801 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8802 (build-system gnu-build-system)
8804 `(#:tests? #f ; There are no tests to run.
8806 (modify-phases %standard-phases
8807 (delete 'configure) ; There is no configure phase.
8809 (lambda* (#:key outputs #:allow-other-keys)
8810 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8811 (install-file "filevercmp" bin)))))))
8812 (home-page "https://github.com/ekg/filevercmp")
8813 (synopsis "This program compares version strings")
8814 (description "This program compares version strings. It intends to be a
8815 replacement for strverscmp.")
8816 (license license:gpl3+))))
8818 (define-public multiqc
8825 (uri (pypi-uri "multiqc" version))
8828 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
8829 (build-system python-build-system)
8831 `(("python-jinja2" ,python-jinja2)
8832 ("python-simplejson" ,python-simplejson)
8833 ("python-pyyaml" ,python-pyyaml)
8834 ("python-click" ,python-click)
8835 ("python-spectra" ,python-spectra)
8836 ("python-requests" ,python-requests)
8837 ("python-markdown" ,python-markdown)
8838 ("python-lzstring" ,python-lzstring)
8839 ("python-matplotlib" ,python-matplotlib)
8840 ("python-numpy" ,python-numpy)
8841 ;; MultQC checks for the presence of nose at runtime.
8842 ("python-nose" ,python-nose)))
8843 (home-page "http://multiqc.info")
8844 (synopsis "Aggregate bioinformatics analysis reports")
8846 "MultiQC is a tool to aggregate bioinformatics results across many
8847 samples into a single report. It contains modules for a large number of
8848 common bioinformatics tools.")
8849 (license license:gpl3+)))
8851 (define-public r-chipseq
8858 (uri (bioconductor-uri "chipseq" version))
8861 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8862 (build-system r-build-system)
8864 `(("r-biocgenerics" ,r-biocgenerics)
8865 ("r-genomicranges" ,r-genomicranges)
8866 ("r-iranges" ,r-iranges)
8867 ("r-lattice" ,r-lattice)
8868 ("r-s4vectors" ,r-s4vectors)
8869 ("r-shortread" ,r-shortread)))
8870 (home-page "https://bioconductor.org/packages/chipseq")
8871 (synopsis "Package for analyzing ChIPseq data")
8873 "This package provides tools for processing short read data from ChIPseq
8875 (license license:artistic2.0)))
8877 (define-public r-copyhelper
8879 (name "r-copyhelper")
8884 (uri (string-append "https://bioconductor.org/packages/release/"
8885 "data/experiment/src/contrib/CopyhelpeR_"
8889 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8890 (properties `((upstream-name . "CopyhelpeR")))
8891 (build-system r-build-system)
8892 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8893 (synopsis "Helper files for CopywriteR")
8895 "This package contains the helper files that are required to run the
8896 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8897 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8898 mm10. In addition, it contains a blacklist filter to remove regions that
8899 display copy number variation. Files are stored as GRanges objects from the
8900 GenomicRanges Bioconductor package.")
8901 (license license:gpl2)))
8903 (define-public r-copywriter
8905 (name "r-copywriter")
8910 (uri (bioconductor-uri "CopywriteR" version))
8913 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
8914 (properties `((upstream-name . "CopywriteR")))
8915 (build-system r-build-system)
8917 `(("r-biocparallel" ,r-biocparallel)
8918 ("r-chipseq" ,r-chipseq)
8919 ("r-copyhelper" ,r-copyhelper)
8920 ("r-data-table" ,r-data-table)
8921 ("r-dnacopy" ,r-dnacopy)
8922 ("r-futile-logger" ,r-futile-logger)
8923 ("r-genomeinfodb" ,r-genomeinfodb)
8924 ("r-genomicalignments" ,r-genomicalignments)
8925 ("r-genomicranges" ,r-genomicranges)
8926 ("r-gtools" ,r-gtools)
8927 ("r-iranges" ,r-iranges)
8928 ("r-matrixstats" ,r-matrixstats)
8929 ("r-rsamtools" ,r-rsamtools)
8930 ("r-s4vectors" ,r-s4vectors)))
8931 (home-page "https://github.com/PeeperLab/CopywriteR")
8932 (synopsis "Copy number information from targeted sequencing")
8934 "CopywriteR extracts DNA copy number information from targeted sequencing
8935 by utilizing off-target reads. It allows for extracting uniformly distributed
8936 copy number information, can be used without reference, and can be applied to
8937 sequencing data obtained from various techniques including chromatin
8938 immunoprecipitation and target enrichment on small gene panels. Thereby,
8939 CopywriteR constitutes a widely applicable alternative to available copy
8940 number detection tools.")
8941 (license license:gpl2)))
8943 (define-public r-methylkit
8945 (name "r-methylkit")
8949 (uri (bioconductor-uri "methylKit" version))
8952 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
8953 (properties `((upstream-name . "methylKit")))
8954 (build-system r-build-system)
8956 `(("r-data-table" ,r-data-table)
8957 ("r-emdbook" ,r-emdbook)
8958 ("r-fastseg" ,r-fastseg)
8959 ("r-genomeinfodb" ,r-genomeinfodb)
8960 ("r-genomicranges" ,r-genomicranges)
8961 ("r-gtools" ,r-gtools)
8962 ("r-iranges" ,r-iranges)
8963 ("r-kernsmooth" ,r-kernsmooth)
8964 ("r-limma" ,r-limma)
8965 ("r-mclust" ,r-mclust)
8966 ("r-qvalue" ,r-qvalue)
8967 ("r-r-utils" ,r-r-utils)
8969 ("r-rhtslib" ,r-rhtslib)
8970 ("r-rsamtools" ,r-rsamtools)
8971 ("r-rtracklayer" ,r-rtracklayer)
8972 ("r-s4vectors" ,r-s4vectors)
8973 ("r-zlibbioc" ,r-zlibbioc)))
8976 (home-page "https://github.com/al2na/methylKit")
8978 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8980 "MethylKit is an R package for DNA methylation analysis and annotation
8981 from high-throughput bisulfite sequencing. The package is designed to deal
8982 with sequencing data from @dfn{Reduced representation bisulfite
8983 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8984 genome bisulfite sequencing. It also has functions to analyze base-pair
8985 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8987 (license license:artistic2.0)))
8989 (define-public r-sva
8996 (uri (bioconductor-uri "sva" version))
8999 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9000 (build-system r-build-system)
9002 `(("r-genefilter" ,r-genefilter)
9004 ("r-biocparallel" ,r-biocparallel)
9005 ("r-matrixstats" ,r-matrixstats)
9006 ("r-limma" ,r-limma)))
9007 (home-page "https://bioconductor.org/packages/sva")
9008 (synopsis "Surrogate variable analysis")
9010 "This package contains functions for removing batch effects and other
9011 unwanted variation in high-throughput experiment. It also contains functions
9012 for identifying and building surrogate variables for high-dimensional data
9013 sets. Surrogate variables are covariates constructed directly from
9014 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9015 imaging data that can be used in subsequent analyses to adjust for unknown,
9016 unmodeled, or latent sources of noise.")
9017 (license license:artistic2.0)))
9019 (define-public r-seqminer
9026 (uri (cran-uri "seqminer" version))
9029 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9030 (build-system r-build-system)
9033 (home-page "http://seqminer.genomic.codes")
9034 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9036 "This package provides tools to integrate nucleotide sequencing
9037 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9038 ;; Any version of the GPL is acceptable
9039 (license (list license:gpl2+ license:gpl3+))))
9041 (define-public r-raremetals2
9043 (name "r-raremetals2")
9048 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9049 "b/b7/RareMETALS2_" version ".tar.gz"))
9052 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9053 (properties `((upstream-name . "RareMETALS2")))
9054 (build-system r-build-system)
9056 `(("r-seqminer" ,r-seqminer)
9057 ("r-mvtnorm" ,r-mvtnorm)
9059 ("r-compquadform" ,r-compquadform)
9060 ("r-getopt" ,r-getopt)))
9061 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9062 (synopsis "Analyze gene-level association tests for binary trait")
9064 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9065 It was designed to meta-analyze gene-level association tests for binary trait.
9066 While rareMETALS offers a near-complete solution for meta-analysis of
9067 gene-level tests for quantitative trait, it does not offer the optimal
9068 solution for binary trait. The package rareMETALS2 offers improved features
9069 for analyzing gene-level association tests in meta-analyses for binary
9071 (license license:gpl3)))
9073 (define-public r-maldiquant
9075 (name "r-maldiquant")
9080 (uri (cran-uri "MALDIquant" version))
9083 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9084 (properties `((upstream-name . "MALDIquant")))
9085 (build-system r-build-system)
9086 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9087 (synopsis "Quantitative analysis of mass spectrometry data")
9089 "This package provides a complete analysis pipeline for matrix-assisted
9090 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9091 two-dimensional mass spectrometry data. In addition to commonly used plotting
9092 and processing methods it includes distinctive features, namely baseline
9093 subtraction methods such as morphological filters (TopHat) or the
9094 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9095 alignment using warping functions, handling of replicated measurements as well
9096 as allowing spectra with different resolutions.")
9097 (license license:gpl3+)))
9099 (define-public r-protgenerics
9101 (name "r-protgenerics")
9106 (uri (bioconductor-uri "ProtGenerics" version))
9109 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9110 (properties `((upstream-name . "ProtGenerics")))
9111 (build-system r-build-system)
9112 (home-page "https://github.com/lgatto/ProtGenerics")
9113 (synopsis "S4 generic functions for proteomics infrastructure")
9115 "This package provides S4 generic functions needed by Bioconductor
9116 proteomics packages.")
9117 (license license:artistic2.0)))
9119 (define-public r-mzr
9126 (uri (bioconductor-uri "mzR" version))
9129 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9130 (modules '((guix build utils)))
9133 (delete-file-recursively "src/boost")
9135 (properties `((upstream-name . "mzR")))
9136 (build-system r-build-system)
9139 (modify-phases %standard-phases
9140 (add-after 'unpack 'use-system-boost
9142 (substitute* "src/Makevars"
9143 (("\\./boost/libs.*") "")
9144 (("ARCH_OBJS=" line)
9146 "\nARCH_LIBS=-lboost_system -lboost_regex \
9147 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9150 `(("boost" ,boost) ; use this instead of the bundled boost sources
9151 ("netcdf" ,netcdf)))
9153 `(("r-biobase" ,r-biobase)
9154 ("r-biocgenerics" ,r-biocgenerics)
9155 ("r-protgenerics" ,r-protgenerics)
9157 ("r-zlibbioc" ,r-zlibbioc)))
9158 (home-page "https://github.com/sneumann/mzR/")
9159 (synopsis "Parser for mass spectrometry data files")
9161 "The mzR package provides a unified API to the common file formats and
9162 parsers available for mass spectrometry data. It comes with a wrapper for the
9163 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9164 The package contains the original code written by the ISB, and a subset of the
9165 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9166 previously been used in XCMS.")
9167 (license license:artistic2.0)))
9169 (define-public r-affyio
9176 (uri (bioconductor-uri "affyio" version))
9179 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9180 (build-system r-build-system)
9182 `(("r-zlibbioc" ,r-zlibbioc)))
9185 (home-page "https://github.com/bmbolstad/affyio")
9186 (synopsis "Tools for parsing Affymetrix data files")
9188 "This package provides routines for parsing Affymetrix data files based
9189 upon file format information. The primary focus is on accessing the CEL and
9191 (license license:lgpl2.0+)))
9193 (define-public r-affy
9200 (uri (bioconductor-uri "affy" version))
9203 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9204 (build-system r-build-system)
9206 `(("r-affyio" ,r-affyio)
9207 ("r-biobase" ,r-biobase)
9208 ("r-biocgenerics" ,r-biocgenerics)
9209 ("r-biocinstaller" ,r-biocinstaller)
9210 ("r-preprocesscore" ,r-preprocesscore)
9211 ("r-zlibbioc" ,r-zlibbioc)))
9212 (home-page "https://bioconductor.org/packages/affy")
9213 (synopsis "Methods for affymetrix oligonucleotide arrays")
9215 "This package contains functions for exploratory oligonucleotide array
9217 (license license:lgpl2.0+)))
9219 (define-public r-vsn
9226 (uri (bioconductor-uri "vsn" version))
9229 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9230 (build-system r-build-system)
9232 `(("r-affy" ,r-affy)
9233 ("r-biobase" ,r-biobase)
9234 ("r-ggplot2" ,r-ggplot2)
9235 ("r-lattice" ,r-lattice)
9236 ("r-limma" ,r-limma)))
9237 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9238 (synopsis "Variance stabilization and calibration for microarray data")
9240 "The package implements a method for normalising microarray intensities,
9241 and works for single- and multiple-color arrays. It can also be used for data
9242 from other technologies, as long as they have similar format. The method uses
9243 a robust variant of the maximum-likelihood estimator for an
9244 additive-multiplicative error model and affine calibration. The model
9245 incorporates data calibration step (a.k.a. normalization), a model for the
9246 dependence of the variance on the mean intensity and a variance stabilizing
9247 data transformation. Differences between transformed intensities are
9248 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9249 their variance is independent of the mean, and they are usually more sensitive
9250 and specific in detecting differential transcription.")
9251 (license license:artistic2.0)))
9253 (define-public r-mzid
9260 (uri (bioconductor-uri "mzID" version))
9263 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9264 (properties `((upstream-name . "mzID")))
9265 (build-system r-build-system)
9267 `(("r-doparallel" ,r-doparallel)
9268 ("r-foreach" ,r-foreach)
9269 ("r-iterators" ,r-iterators)
9271 ("r-protgenerics" ,r-protgenerics)
9274 (home-page "https://bioconductor.org/packages/mzID")
9275 (synopsis "Parser for mzIdentML files")
9277 "This package provides a parser for mzIdentML files implemented using the
9278 XML package. The parser tries to be general and able to handle all types of
9279 mzIdentML files with the drawback of having less pretty output than a vendor
9281 (license license:gpl2+)))
9283 (define-public r-pcamethods
9285 (name "r-pcamethods")
9290 (uri (bioconductor-uri "pcaMethods" version))
9293 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9294 (properties `((upstream-name . "pcaMethods")))
9295 (build-system r-build-system)
9297 `(("r-biobase" ,r-biobase)
9298 ("r-biocgenerics" ,r-biocgenerics)
9300 ("r-rcpp" ,r-rcpp)))
9301 (home-page "https://github.com/hredestig/pcamethods")
9302 (synopsis "Collection of PCA methods")
9304 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9305 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9306 for missing value estimation is included for comparison. BPCA, PPCA and
9307 NipalsPCA may be used to perform PCA on incomplete data as well as for
9308 accurate missing value estimation. A set of methods for printing and plotting
9309 the results is also provided. All PCA methods make use of the same data
9310 structure (pcaRes) to provide a common interface to the PCA results.")
9311 (license license:gpl3+)))
9313 (define-public r-msnbase
9320 (uri (bioconductor-uri "MSnbase" version))
9323 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9324 (properties `((upstream-name . "MSnbase")))
9325 (build-system r-build-system)
9327 `(("r-affy" ,r-affy)
9328 ("r-biobase" ,r-biobase)
9329 ("r-biocgenerics" ,r-biocgenerics)
9330 ("r-biocparallel" ,r-biocparallel)
9331 ("r-digest" ,r-digest)
9332 ("r-ggplot2" ,r-ggplot2)
9333 ("r-impute" ,r-impute)
9334 ("r-iranges" ,r-iranges)
9335 ("r-lattice" ,r-lattice)
9336 ("r-maldiquant" ,r-maldiquant)
9339 ("r-pcamethods" ,r-pcamethods)
9341 ("r-preprocesscore" ,r-preprocesscore)
9342 ("r-protgenerics" ,r-protgenerics)
9344 ("r-s4vectors" ,r-s4vectors)
9347 (home-page "https://github.com/lgatto/MSnbase")
9348 (synopsis "Base functions and classes for MS-based proteomics")
9350 "This package provides basic plotting, data manipulation and processing
9351 of mass spectrometry based proteomics data.")
9352 (license license:artistic2.0)))
9354 (define-public r-msnid
9361 (uri (bioconductor-uri "MSnID" version))
9364 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9365 (properties `((upstream-name . "MSnID")))
9366 (build-system r-build-system)
9368 `(("r-biobase" ,r-biobase)
9369 ("r-data-table" ,r-data-table)
9370 ("r-doparallel" ,r-doparallel)
9371 ("r-dplyr" ,r-dplyr)
9372 ("r-foreach" ,r-foreach)
9373 ("r-iterators" ,r-iterators)
9374 ("r-msnbase" ,r-msnbase)
9377 ("r-protgenerics" ,r-protgenerics)
9378 ("r-r-cache" ,r-r-cache)
9380 ("r-reshape2" ,r-reshape2)))
9381 (home-page "https://bioconductor.org/packages/MSnID")
9382 (synopsis "Utilities for LC-MSn proteomics identifications")
9384 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9385 from mzIdentML (leveraging the mzID package) or text files. After collating
9386 the search results from multiple datasets it assesses their identification
9387 quality and optimize filtering criteria to achieve the maximum number of
9388 identifications while not exceeding a specified false discovery rate. It also
9389 contains a number of utilities to explore the MS/MS results and assess missed
9390 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9391 (license license:artistic2.0)))
9393 (define-public r-seurat
9399 (uri (cran-uri "Seurat" version))
9402 "1yarzhbylkfk4vwp7f8710zpdglkfww2db3hmq69hjllgg80ykmw"))
9403 ;; Delete pre-built jar.
9405 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9407 (properties `((upstream-name . "Seurat")))
9408 (build-system r-build-system)
9411 (modify-phases %standard-phases
9412 (add-after 'unpack 'build-jar
9413 (lambda* (#:key inputs #:allow-other-keys)
9414 (let ((classesdir "tmp-classes"))
9415 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9417 (with-output-to-file "manifest"
9419 (display "Manifest-Version: 1.0
9420 Main-Class: ModularityOptimizer\n")))
9421 (and (zero? (apply system* `("javac" "-d" ,classesdir
9422 ,@(find-files "java" "\\.java$"))))
9423 (zero? (system* "jar"
9425 "inst/java/ModularityOptimizer.jar"
9426 "-C" classesdir ".")))))))))
9428 `(("jdk" ,icedtea "jdk")))
9431 ("r-caret" ,r-caret)
9432 ("r-cowplot" ,r-cowplot)
9433 ("r-diffusionmap" ,r-diffusionmap)
9434 ("r-dplyr" ,r-dplyr)
9438 ("r-gdata" ,r-gdata)
9439 ("r-ggplot2" ,r-ggplot2)
9440 ("r-ggridges" ,r-ggridges)
9441 ("r-gplots" ,r-gplots)
9442 ("r-gridextra" ,r-gridextra)
9443 ("r-hmisc" ,r-hmisc)
9445 ("r-igraph" ,r-igraph)
9446 ("r-irlba" ,r-irlba)
9449 ("r-matrix" ,r-matrix)
9450 ("r-mixtools" ,r-mixtools)
9452 ("r-pbapply" ,r-pbapply)
9453 ("r-plotly" ,r-plotly)
9454 ("r-ranger" ,r-ranger)
9455 ("r-rcolorbrewer" ,r-rcolorbrewer)
9457 ("r-rcppeigen" ,r-rcppeigen)
9458 ("r-rcppprogress" ,r-rcppprogress)
9459 ("r-reshape2" ,r-reshape2)
9461 ("r-rtsne" ,r-rtsne)
9462 ("r-sdmtools" ,r-sdmtools)
9463 ("r-stringr" ,r-stringr)
9464 ("r-tclust" ,r-tclust)
9465 ("r-tidyr" ,r-tidyr)
9467 ("r-vgam" ,r-vgam)))
9468 (home-page "http://www.satijalab.org/seurat")
9469 (synopsis "Seurat is an R toolkit for single cell genomics")
9471 "This package is an R package designed for QC, analysis, and
9472 exploration of single cell RNA-seq data. It easily enables widely-used
9473 analytical techniques, including the identification of highly variable genes,
9474 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9475 algorithms; density clustering, hierarchical clustering, k-means, and the
9476 discovery of differentially expressed genes and markers.")
9477 (license license:gpl3)))
9479 (define-public r-aroma-light
9481 (name "r-aroma-light")
9486 (uri (bioconductor-uri "aroma.light" version))
9489 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9490 (properties `((upstream-name . "aroma.light")))
9491 (build-system r-build-system)
9493 `(("r-matrixstats" ,r-matrixstats)
9494 ("r-r-methodss3" ,r-r-methodss3)
9496 ("r-r-utils" ,r-r-utils)))
9497 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9498 (synopsis "Methods for normalization and visualization of microarray data")
9500 "This package provides methods for microarray analysis that take basic
9501 data types such as matrices and lists of vectors. These methods can be used
9502 standalone, be utilized in other packages, or be wrapped up in higher-level
9504 (license license:gpl2+)))
9506 (define-public r-deseq
9513 (uri (bioconductor-uri "DESeq" version))
9516 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9517 (properties `((upstream-name . "DESeq")))
9518 (build-system r-build-system)
9520 `(("r-biobase" ,r-biobase)
9521 ("r-biocgenerics" ,r-biocgenerics)
9522 ("r-genefilter" ,r-genefilter)
9523 ("r-geneplotter" ,r-geneplotter)
9524 ("r-lattice" ,r-lattice)
9525 ("r-locfit" ,r-locfit)
9527 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9528 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9529 (synopsis "Differential gene expression analysis")
9531 "This package provides tools for estimating variance-mean dependence in
9532 count data from high-throughput genetic sequencing assays and for testing for
9533 differential expression based on a model using the negative binomial
9535 (license license:gpl3+)))
9537 (define-public r-edaseq
9544 (uri (bioconductor-uri "EDASeq" version))
9547 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9548 (properties `((upstream-name . "EDASeq")))
9549 (build-system r-build-system)
9551 `(("r-annotationdbi" ,r-annotationdbi)
9552 ("r-aroma-light" ,r-aroma-light)
9553 ("r-biobase" ,r-biobase)
9554 ("r-biocgenerics" ,r-biocgenerics)
9555 ("r-biomart" ,r-biomart)
9556 ("r-biostrings" ,r-biostrings)
9557 ("r-deseq" ,r-deseq)
9558 ("r-genomicfeatures" ,r-genomicfeatures)
9559 ("r-genomicranges" ,r-genomicranges)
9560 ("r-iranges" ,r-iranges)
9561 ("r-rsamtools" ,r-rsamtools)
9562 ("r-shortread" ,r-shortread)))
9563 (home-page "https://github.com/drisso/EDASeq")
9564 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9566 "This package provides support for numerical and graphical summaries of
9567 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9568 adjust for GC-content effect (or other gene-level effects) on read counts:
9569 loess robust local regression, global-scaling, and full-quantile
9570 normalization. Between-lane normalization procedures to adjust for
9571 distributional differences between lanes (e.g., sequencing depth):
9572 global-scaling and full-quantile normalization.")
9573 (license license:artistic2.0)))
9575 (define-public r-interactivedisplaybase
9577 (name "r-interactivedisplaybase")
9582 (uri (bioconductor-uri "interactiveDisplayBase" version))
9585 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9587 `((upstream-name . "interactiveDisplayBase")))
9588 (build-system r-build-system)
9590 `(("r-biocgenerics" ,r-biocgenerics)
9591 ("r-shiny" ,r-shiny)))
9592 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9593 (synopsis "Base package for web displays of Bioconductor objects")
9595 "This package contains the basic methods needed to generate interactive
9596 Shiny-based display methods for Bioconductor objects.")
9597 (license license:artistic2.0)))
9599 (define-public r-annotationhub
9601 (name "r-annotationhub")
9606 (uri (bioconductor-uri "AnnotationHub" version))
9609 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9610 (properties `((upstream-name . "AnnotationHub")))
9611 (build-system r-build-system)
9613 `(("r-annotationdbi" ,r-annotationdbi)
9614 ("r-biocgenerics" ,r-biocgenerics)
9615 ("r-biocinstaller" ,r-biocinstaller)
9618 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9619 ("r-rsqlite" ,r-rsqlite)
9620 ("r-s4vectors" ,r-s4vectors)
9621 ("r-yaml" ,r-yaml)))
9622 (home-page "https://bioconductor.org/packages/AnnotationHub")
9623 (synopsis "Client to access AnnotationHub resources")
9625 "This package provides a client for the Bioconductor AnnotationHub web
9626 resource. The AnnotationHub web resource provides a central location where
9627 genomic files (e.g. VCF, bed, wig) and other resources from standard
9628 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9629 metadata about each resource, e.g., a textual description, tags, and date of
9630 modification. The client creates and manages a local cache of files retrieved
9631 by the user, helping with quick and reproducible access.")
9632 (license license:artistic2.0)))
9634 (define-public r-fastseg
9641 (uri (bioconductor-uri "fastseg" version))
9644 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9645 (build-system r-build-system)
9647 `(("r-biobase" ,r-biobase)
9648 ("r-biocgenerics" ,r-biocgenerics)
9649 ("r-genomicranges" ,r-genomicranges)
9650 ("r-iranges" ,r-iranges)
9651 ("r-s4vectors" ,r-s4vectors)))
9652 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9653 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9655 "Fastseg implements a very fast and efficient segmentation algorithm.
9656 It can segment data from DNA microarrays and data from next generation
9657 sequencing for example to detect copy number segments. Further it can segment
9658 data from RNA microarrays like tiling arrays to identify transcripts. Most
9659 generally, it can segment data given as a matrix or as a vector. Various data
9660 formats can be used as input to fastseg like expression set objects for
9661 microarrays or GRanges for sequencing data.")
9662 (license license:lgpl2.0+)))
9664 (define-public r-keggrest
9671 (uri (bioconductor-uri "KEGGREST" version))
9674 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9675 (properties `((upstream-name . "KEGGREST")))
9676 (build-system r-build-system)
9678 `(("r-biostrings" ,r-biostrings)
9681 (home-page "https://bioconductor.org/packages/KEGGREST")
9682 (synopsis "Client-side REST access to KEGG")
9684 "This package provides a package that provides a client interface to the
9685 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9686 (license license:artistic2.0)))
9688 (define-public r-gage
9695 (uri (bioconductor-uri "gage" version))
9698 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9699 (build-system r-build-system)
9701 `(("r-annotationdbi" ,r-annotationdbi)
9702 ("r-graph" ,r-graph)
9703 ("r-keggrest" ,r-keggrest)))
9704 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9705 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9707 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9708 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9709 data attributes including sample sizes, experimental designs, assay platforms,
9710 and other types of heterogeneity. The gage package provides functions for
9711 basic GAGE analysis, result processing and presentation. In addition, it
9712 provides demo microarray data and commonly used gene set data based on KEGG
9713 pathways and GO terms. These funtions and data are also useful for gene set
9714 analysis using other methods.")
9715 (license license:gpl2+)))
9717 (define-public r-genomicfiles
9719 (name "r-genomicfiles")
9724 (uri (bioconductor-uri "GenomicFiles" version))
9727 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9728 (properties `((upstream-name . "GenomicFiles")))
9729 (build-system r-build-system)
9731 `(("r-biocgenerics" ,r-biocgenerics)
9732 ("r-biocparallel" ,r-biocparallel)
9733 ("r-genomeinfodb" ,r-genomeinfodb)
9734 ("r-genomicalignments" ,r-genomicalignments)
9735 ("r-genomicranges" ,r-genomicranges)
9736 ("r-iranges" ,r-iranges)
9737 ("r-rsamtools" ,r-rsamtools)
9738 ("r-rtracklayer" ,r-rtracklayer)
9739 ("r-s4vectors" ,r-s4vectors)
9740 ("r-summarizedexperiment" ,r-summarizedexperiment)
9741 ("r-variantannotation" ,r-variantannotation)))
9742 (home-page "https://bioconductor.org/packages/GenomicFiles")
9743 (synopsis "Distributed computing by file or by range")
9745 "This package provides infrastructure for parallel computations
9746 distributed by file or by range. User defined mapper and reducer functions
9747 provide added flexibility for data combination and manipulation.")
9748 (license license:artistic2.0)))
9750 (define-public r-complexheatmap
9752 (name "r-complexheatmap")
9757 (uri (bioconductor-uri "ComplexHeatmap" version))
9760 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9762 `((upstream-name . "ComplexHeatmap")))
9763 (build-system r-build-system)
9765 `(("r-circlize" ,r-circlize)
9766 ("r-colorspace" ,r-colorspace)
9767 ("r-getoptlong" ,r-getoptlong)
9768 ("r-globaloptions" ,r-globaloptions)
9769 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9771 "https://github.com/jokergoo/ComplexHeatmap")
9772 (synopsis "Making Complex Heatmaps")
9774 "Complex heatmaps are efficient to visualize associations between
9775 different sources of data sets and reveal potential structures. This package
9776 provides a highly flexible way to arrange multiple heatmaps and supports
9777 self-defined annotation graphics.")
9778 (license license:gpl2+)))
9780 (define-public r-dirichletmultinomial
9782 (name "r-dirichletmultinomial")
9787 (uri (bioconductor-uri "DirichletMultinomial" version))
9790 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9792 `((upstream-name . "DirichletMultinomial")))
9793 (build-system r-build-system)
9797 `(("r-biocgenerics" ,r-biocgenerics)
9798 ("r-iranges" ,r-iranges)
9799 ("r-s4vectors" ,r-s4vectors)))
9800 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9801 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9803 "Dirichlet-multinomial mixture models can be used to describe variability
9804 in microbial metagenomic data. This package is an interface to code
9805 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9807 (license license:lgpl3)))
9809 (define-public r-ensembldb
9811 (name "r-ensembldb")
9816 (uri (bioconductor-uri "ensembldb" version))
9819 "1vk6j0r5cczxmwbfzzkgayna66rxkfa3q2jikz649qvdiybhls40"))))
9820 (build-system r-build-system)
9822 `(("r-annotationdbi" ,r-annotationdbi)
9823 ("r-annotationfilter" ,r-annotationfilter)
9824 ("r-annotationhub" ,r-annotationhub)
9825 ("r-biobase" ,r-biobase)
9826 ("r-biocgenerics" ,r-biocgenerics)
9827 ("r-biostrings" ,r-biostrings)
9830 ("r-genomeinfodb" ,r-genomeinfodb)
9831 ("r-genomicfeatures" ,r-genomicfeatures)
9832 ("r-genomicranges" ,r-genomicranges)
9833 ("r-iranges" ,r-iranges)
9834 ("r-protgenerics" ,r-protgenerics)
9835 ("r-rsamtools" ,r-rsamtools)
9836 ("r-rsqlite" ,r-rsqlite)
9837 ("r-rtracklayer" ,r-rtracklayer)
9838 ("r-s4vectors" ,r-s4vectors)))
9839 (home-page "https://github.com/jotsetung/ensembldb")
9840 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9842 "The package provides functions to create and use transcript-centric
9843 annotation databases/packages. The annotation for the databases are directly
9844 fetched from Ensembl using their Perl API. The functionality and data is
9845 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9846 but, in addition to retrieve all gene/transcript models and annotations from
9847 the database, the @code{ensembldb} package also provides a filter framework
9848 allowing to retrieve annotations for specific entries like genes encoded on a
9849 chromosome region or transcript models of lincRNA genes.")
9850 ;; No version specified
9851 (license license:lgpl3+)))
9853 (define-public r-organismdbi
9855 (name "r-organismdbi")
9860 (uri (bioconductor-uri "OrganismDbi" version))
9863 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9864 (properties `((upstream-name . "OrganismDbi")))
9865 (build-system r-build-system)
9867 `(("r-annotationdbi" ,r-annotationdbi)
9868 ("r-biobase" ,r-biobase)
9869 ("r-biocgenerics" ,r-biocgenerics)
9870 ("r-biocinstaller" ,r-biocinstaller)
9872 ("r-genomicfeatures" ,r-genomicfeatures)
9873 ("r-genomicranges" ,r-genomicranges)
9874 ("r-graph" ,r-graph)
9875 ("r-iranges" ,r-iranges)
9877 ("r-s4vectors" ,r-s4vectors)))
9878 (home-page "https://bioconductor.org/packages/OrganismDbi")
9879 (synopsis "Software to enable the smooth interfacing of database packages")
9880 (description "The package enables a simple unified interface to several
9881 annotation packages each of which has its own schema by taking advantage of
9882 the fact that each of these packages implements a select methods.")
9883 (license license:artistic2.0)))
9885 (define-public r-biovizbase
9887 (name "r-biovizbase")
9892 (uri (bioconductor-uri "biovizBase" version))
9895 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
9896 (properties `((upstream-name . "biovizBase")))
9897 (build-system r-build-system)
9899 `(("r-annotationdbi" ,r-annotationdbi)
9900 ("r-annotationfilter" ,r-annotationfilter)
9901 ("r-biocgenerics" ,r-biocgenerics)
9902 ("r-biostrings" ,r-biostrings)
9903 ("r-dichromat" ,r-dichromat)
9904 ("r-ensembldb" ,r-ensembldb)
9905 ("r-genomeinfodb" ,r-genomeinfodb)
9906 ("r-genomicalignments" ,r-genomicalignments)
9907 ("r-genomicfeatures" ,r-genomicfeatures)
9908 ("r-genomicranges" ,r-genomicranges)
9909 ("r-hmisc" ,r-hmisc)
9910 ("r-iranges" ,r-iranges)
9911 ("r-rcolorbrewer" ,r-rcolorbrewer)
9912 ("r-rsamtools" ,r-rsamtools)
9913 ("r-s4vectors" ,r-s4vectors)
9914 ("r-scales" ,r-scales)
9915 ("r-summarizedexperiment" ,r-summarizedexperiment)
9916 ("r-variantannotation" ,r-variantannotation)))
9917 (home-page "https://bioconductor.org/packages/biovizBase")
9918 (synopsis "Basic graphic utilities for visualization of genomic data")
9920 "The biovizBase package is designed to provide a set of utilities, color
9921 schemes and conventions for genomic data. It serves as the base for various
9922 high-level packages for biological data visualization. This saves development
9923 effort and encourages consistency.")
9924 (license license:artistic2.0)))
9926 (define-public r-ggbio
9933 (uri (bioconductor-uri "ggbio" version))
9936 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
9937 (build-system r-build-system)
9939 `(("r-annotationdbi" ,r-annotationdbi)
9940 ("r-annotationfilter" ,r-annotationfilter)
9941 ("r-biobase" ,r-biobase)
9942 ("r-biocgenerics" ,r-biocgenerics)
9943 ("r-biostrings" ,r-biostrings)
9944 ("r-biovizbase" ,r-biovizbase)
9945 ("r-bsgenome" ,r-bsgenome)
9946 ("r-ensembldb" ,r-ensembldb)
9947 ("r-genomeinfodb" ,r-genomeinfodb)
9948 ("r-genomicalignments" ,r-genomicalignments)
9949 ("r-genomicfeatures" ,r-genomicfeatures)
9950 ("r-genomicranges" ,r-genomicranges)
9951 ("r-ggally" ,r-ggally)
9952 ("r-ggplot2" ,r-ggplot2)
9953 ("r-gridextra" ,r-gridextra)
9954 ("r-gtable" ,r-gtable)
9955 ("r-hmisc" ,r-hmisc)
9956 ("r-iranges" ,r-iranges)
9957 ("r-organismdbi" ,r-organismdbi)
9958 ("r-reshape2" ,r-reshape2)
9959 ("r-rsamtools" ,r-rsamtools)
9960 ("r-rtracklayer" ,r-rtracklayer)
9961 ("r-s4vectors" ,r-s4vectors)
9962 ("r-scales" ,r-scales)
9963 ("r-summarizedexperiment" ,r-summarizedexperiment)
9964 ("r-variantannotation" ,r-variantannotation)))
9965 (home-page "http://www.tengfei.name/ggbio/")
9966 (synopsis "Visualization tools for genomic data")
9968 "The ggbio package extends and specializes the grammar of graphics for
9969 biological data. The graphics are designed to answer common scientific
9970 questions, in particular those often asked of high throughput genomics data.
9971 All core Bioconductor data structures are supported, where appropriate. The
9972 package supports detailed views of particular genomic regions, as well as
9973 genome-wide overviews. Supported overviews include ideograms and grand linear
9974 views. High-level plots include sequence fragment length, edge-linked
9975 interval to data view, mismatch pileup, and several splicing summaries.")
9976 (license license:artistic2.0)))
9978 (define-public r-gprofiler
9980 (name "r-gprofiler")
9985 (uri (cran-uri "gProfileR" version))
9988 "08dsnja3g8qvqlgwhx9c9f8p8psn3qr5ddn84dhizkgglj30v2wj"))))
9989 (properties `((upstream-name . "gProfileR")))
9990 (build-system r-build-system)
9992 `(("r-plyr" ,r-plyr)
9993 ("r-rcurl" ,r-rcurl)))
9994 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
9995 (synopsis "Interface to the g:Profiler toolkit")
9997 "This package provides tools for functional enrichment analysis,
9998 gene identifier conversion and mapping homologous genes across related
9999 organisms via the @code{g:Profiler} toolkit.")
10000 (license license:gpl2+)))
10002 (define-public r-gqtlbase
10004 (name "r-gqtlbase")
10009 (uri (bioconductor-uri "gQTLBase" version))
10012 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10013 (properties `((upstream-name . "gQTLBase")))
10014 (build-system r-build-system)
10016 `(("r-batchjobs" ,r-batchjobs)
10017 ("r-bbmisc" ,r-bbmisc)
10018 ("r-biocgenerics" ,r-biocgenerics)
10020 ("r-doparallel" ,r-doparallel)
10022 ("r-ffbase" ,r-ffbase)
10023 ("r-foreach" ,r-foreach)
10024 ("r-genomicfiles" ,r-genomicfiles)
10025 ("r-genomicranges" ,r-genomicranges)
10026 ("r-rtracklayer" ,r-rtracklayer)
10027 ("r-s4vectors" ,r-s4vectors)
10028 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10029 (home-page "https://bioconductor.org/packages/gQTLBase")
10030 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10032 "The purpose of this package is to simplify the storage and interrogation
10033 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10035 (license license:artistic2.0)))
10037 (define-public r-snpstats
10039 (name "r-snpstats")
10044 (uri (bioconductor-uri "snpStats" version))
10047 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10048 (properties `((upstream-name . "snpStats")))
10049 (build-system r-build-system)
10050 (inputs `(("zlib" ,zlib)))
10052 `(("r-biocgenerics" ,r-biocgenerics)
10053 ("r-matrix" ,r-matrix)
10054 ("r-survival" ,r-survival)
10055 ("r-zlibbioc" ,r-zlibbioc)))
10056 (home-page "https://bioconductor.org/packages/snpStats")
10057 (synopsis "Methods for SNP association studies")
10059 "This package provides classes and statistical methods for large
10060 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10061 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10062 (license license:gpl3)))
10064 (define-public r-homo-sapiens
10066 (name "r-homo-sapiens")
10070 ;; We cannot use bioconductor-uri here because this tarball is
10071 ;; located under "data/annotation/" instead of "bioc/".
10072 (uri (string-append "http://www.bioconductor.org/packages/"
10073 "release/data/annotation/src/contrib/"
10075 version ".tar.gz"))
10078 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10080 `((upstream-name . "Homo.sapiens")))
10081 (build-system r-build-system)
10083 `(("r-genomicfeatures" ,r-genomicfeatures)
10084 ("r-go-db" ,r-go-db)
10085 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10086 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10087 ("r-organismdbi" ,r-organismdbi)
10088 ("r-annotationdbi" ,r-annotationdbi)))
10089 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10090 (synopsis "Annotation package for the Homo.sapiens object")
10092 "This package contains the Homo.sapiens object to access data from
10093 several related annotation packages.")
10094 (license license:artistic2.0)))
10096 (define-public r-erma
10103 (uri (bioconductor-uri "erma" version))
10106 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10107 (build-system r-build-system)
10109 `(("r-annotationdbi" ,r-annotationdbi)
10110 ("r-biobase" ,r-biobase)
10111 ("r-biocgenerics" ,r-biocgenerics)
10112 ("r-foreach" ,r-foreach)
10113 ("r-genomicfiles" ,r-genomicfiles)
10114 ("r-genomicranges" ,r-genomicranges)
10115 ("r-ggplot2" ,r-ggplot2)
10116 ("r-homo-sapiens" ,r-homo-sapiens)
10117 ("r-rtracklayer" ,r-rtracklayer)
10118 ("r-s4vectors" ,r-s4vectors)
10119 ("r-shiny" ,r-shiny)
10120 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10121 (home-page "https://bioconductor.org/packages/erma")
10122 (synopsis "Epigenomic road map adventures")
10124 "The epigenomics road map describes locations of epigenetic marks in DNA
10125 from a variety of cell types. Of interest are locations of histone
10126 modifications, sites of DNA methylation, and regions of accessible chromatin.
10127 This package presents a selection of elements of the road map including
10128 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10129 by Ernst and Kellis.")
10130 (license license:artistic2.0)))
10132 (define-public r-ldblock
10139 (uri (bioconductor-uri "ldblock" version))
10142 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10143 (build-system r-build-system)
10145 `(("r-erma" ,r-erma)
10146 ("r-genomeinfodb" ,r-genomeinfodb)
10147 ("r-genomicfiles" ,r-genomicfiles)
10148 ("r-go-db" ,r-go-db)
10149 ("r-homo-sapiens" ,r-homo-sapiens)
10150 ("r-matrix" ,r-matrix)
10151 ("r-rsamtools" ,r-rsamtools)
10152 ("r-snpstats" ,r-snpstats)
10153 ("r-variantannotation" ,r-variantannotation)))
10154 (home-page "https://bioconductor.org/packages/ldblock")
10155 (synopsis "Data structures for linkage disequilibrium measures in populations")
10157 "This package defines data structures for @dfn{linkage
10158 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10159 handling of existing population-level data for the purpose of flexibly
10160 defining LD blocks.")
10161 (license license:artistic2.0)))
10163 (define-public r-gqtlstats
10165 (name "r-gqtlstats")
10170 (uri (bioconductor-uri "gQTLstats" version))
10173 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10174 (properties `((upstream-name . "gQTLstats")))
10175 (build-system r-build-system)
10177 `(("r-annotationdbi" ,r-annotationdbi)
10178 ("r-batchjobs" ,r-batchjobs)
10179 ("r-bbmisc" ,r-bbmisc)
10180 ("r-beeswarm" ,r-beeswarm)
10181 ("r-biobase" ,r-biobase)
10182 ("r-biocgenerics" ,r-biocgenerics)
10183 ("r-doparallel" ,r-doparallel)
10184 ("r-dplyr" ,r-dplyr)
10186 ("r-ffbase" ,r-ffbase)
10187 ("r-foreach" ,r-foreach)
10188 ("r-genomeinfodb" ,r-genomeinfodb)
10189 ("r-genomicfeatures" ,r-genomicfeatures)
10190 ("r-genomicfiles" ,r-genomicfiles)
10191 ("r-genomicranges" ,r-genomicranges)
10192 ("r-ggbeeswarm" ,r-ggbeeswarm)
10193 ("r-ggplot2" ,r-ggplot2)
10194 ("r-gqtlbase" ,r-gqtlbase)
10195 ("r-hardyweinberg" ,r-hardyweinberg)
10196 ("r-iranges" ,r-iranges)
10197 ("r-ldblock" ,r-ldblock)
10198 ("r-limma" ,r-limma)
10200 ("r-plotly" ,r-plotly)
10201 ("r-reshape2" ,r-reshape2)
10202 ("r-s4vectors" ,r-s4vectors)
10203 ("r-shiny" ,r-shiny)
10204 ("r-snpstats" ,r-snpstats)
10205 ("r-summarizedexperiment" ,r-summarizedexperiment)
10206 ("r-variantannotation" ,r-variantannotation)))
10207 (home-page "https://bioconductor.org/packages/gQTLstats")
10208 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10210 "This package provides tools for the computationally efficient analysis
10211 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10212 The software in this package aims to support refinements and functional
10213 interpretation of members of a collection of association statistics on a
10214 family of feature/genome hypotheses.")
10215 (license license:artistic2.0)))
10217 (define-public r-gviz
10224 (uri (bioconductor-uri "Gviz" version))
10227 "173n99mc95sij2vb8n3xd016x7mxhjs961q3l29xkg1lrnnm2sva"))))
10228 (properties `((upstream-name . "Gviz")))
10229 (build-system r-build-system)
10231 `(("r-annotationdbi" ,r-annotationdbi)
10232 ("r-biobase" ,r-biobase)
10233 ("r-biocgenerics" ,r-biocgenerics)
10234 ("r-biomart" ,r-biomart)
10235 ("r-biostrings" ,r-biostrings)
10236 ("r-biovizbase" ,r-biovizbase)
10237 ("r-bsgenome" ,r-bsgenome)
10238 ("r-digest" ,r-digest)
10239 ("r-genomeinfodb" ,r-genomeinfodb)
10240 ("r-genomicalignments" ,r-genomicalignments)
10241 ("r-genomicfeatures" ,r-genomicfeatures)
10242 ("r-genomicranges" ,r-genomicranges)
10243 ("r-iranges" ,r-iranges)
10244 ("r-lattice" ,r-lattice)
10245 ("r-latticeextra" ,r-latticeextra)
10246 ("r-matrixstats" ,r-matrixstats)
10247 ("r-rcolorbrewer" ,r-rcolorbrewer)
10248 ("r-rsamtools" ,r-rsamtools)
10249 ("r-rtracklayer" ,r-rtracklayer)
10250 ("r-s4vectors" ,r-s4vectors)
10251 ("r-xvector" ,r-xvector)))
10252 (home-page "https://bioconductor.org/packages/Gviz")
10253 (synopsis "Plotting data and annotation information along genomic coordinates")
10255 "Genomic data analyses requires integrated visualization of known genomic
10256 information and new experimental data. Gviz uses the biomaRt and the
10257 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10258 and translates this to e.g. gene/transcript structures in viewports of the
10259 grid graphics package. This results in genomic information plotted together
10261 (license license:artistic2.0)))
10263 (define-public r-gwascat
10270 (uri (bioconductor-uri "gwascat" version))
10273 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10274 (build-system r-build-system)
10276 `(("r-annotationdbi" ,r-annotationdbi)
10277 ("r-annotationhub" ,r-annotationhub)
10278 ("r-biocgenerics" ,r-biocgenerics)
10279 ("r-biostrings" ,r-biostrings)
10280 ("r-genomeinfodb" ,r-genomeinfodb)
10281 ("r-genomicfeatures" ,r-genomicfeatures)
10282 ("r-genomicranges" ,r-genomicranges)
10283 ("r-ggbio" ,r-ggbio)
10284 ("r-ggplot2" ,r-ggplot2)
10285 ("r-gqtlstats" ,r-gqtlstats)
10286 ("r-graph" ,r-graph)
10288 ("r-homo-sapiens" ,r-homo-sapiens)
10289 ("r-iranges" ,r-iranges)
10290 ("r-rsamtools" ,r-rsamtools)
10291 ("r-rtracklayer" ,r-rtracklayer)
10292 ("r-s4vectors" ,r-s4vectors)
10293 ("r-snpstats" ,r-snpstats)
10294 ("r-summarizedexperiment" ,r-summarizedexperiment)
10295 ("r-variantannotation" ,r-variantannotation)))
10296 (home-page "https://bioconductor.org/packages/gwascat")
10297 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10299 "This package provides tools for representing and modeling data in the
10300 EMBL-EBI GWAS catalog.")
10301 (license license:artistic2.0)))
10303 (define-public r-sushi
10309 (uri (bioconductor-uri "Sushi" version))
10312 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10313 (properties `((upstream-name . "Sushi")))
10314 (build-system r-build-system)
10316 `(("r-biomart" ,r-biomart)
10318 (home-page "https://bioconductor.org/packages/Sushi")
10319 (synopsis "Tools for visualizing genomics data")
10321 "This package provides flexible, quantitative, and integrative genomic
10322 visualizations for publication-quality multi-panel figures.")
10323 (license license:gpl2+)))
10325 (define-public r-fithic
10331 (uri (bioconductor-uri "FitHiC" version))
10334 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10335 (properties `((upstream-name . "FitHiC")))
10336 (build-system r-build-system)
10338 `(("r-data-table" ,r-data-table)
10339 ("r-fdrtool" ,r-fdrtool)
10340 ("r-rcpp" ,r-rcpp)))
10341 (home-page "https://bioconductor.org/packages/FitHiC")
10342 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10344 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10345 intra-chromosomal contact maps produced by genome-wide genome architecture
10346 assays such as Hi-C.")
10347 (license license:gpl2+)))
10349 (define-public r-hitc
10355 (uri (bioconductor-uri "HiTC" version))
10358 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10359 (properties `((upstream-name . "HiTC")))
10360 (build-system r-build-system)
10362 `(("r-biostrings" ,r-biostrings)
10363 ("r-genomeinfodb" ,r-genomeinfodb)
10364 ("r-genomicranges" ,r-genomicranges)
10365 ("r-iranges" ,r-iranges)
10366 ("r-matrix" ,r-matrix)
10367 ("r-rcolorbrewer" ,r-rcolorbrewer)
10368 ("r-rtracklayer" ,r-rtracklayer)))
10369 (home-page "https://bioconductor.org/packages/HiTC")
10370 (synopsis "High throughput chromosome conformation capture analysis")
10372 "The HiTC package was developed to explore high-throughput \"C\" data
10373 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10374 quality controls, normalization, visualization, and further analysis are also
10376 (license license:artistic2.0)))
10378 (define-public r-qvalue
10385 (uri (bioconductor-uri "qvalue" version))
10388 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10389 (build-system r-build-system)
10391 `(("r-ggplot2" ,r-ggplot2)
10392 ("r-reshape2" ,r-reshape2)))
10393 (home-page "http://github.com/jdstorey/qvalue")
10394 (synopsis "Q-value estimation for false discovery rate control")
10396 "This package takes a list of p-values resulting from the simultaneous
10397 testing of many hypotheses and estimates their q-values and local @dfn{false
10398 discovery rate} (FDR) values. The q-value of a test measures the proportion
10399 of false positives incurred when that particular test is called significant.
10400 The local FDR measures the posterior probability the null hypothesis is true
10401 given the test's p-value. Various plots are automatically generated, allowing
10402 one to make sensible significance cut-offs. The software can be applied to
10403 problems in genomics, brain imaging, astrophysics, and data mining.")
10404 ;; Any version of the LGPL.
10405 (license license:lgpl3+)))
10407 (define-public r-hdf5array
10409 (name "r-hdf5array")
10414 (uri (bioconductor-uri "HDF5Array" version))
10417 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10418 (properties `((upstream-name . "HDF5Array")))
10419 (build-system r-build-system)
10421 `(("r-biocgenerics" ,r-biocgenerics)
10422 ("r-delayedarray" ,r-delayedarray)
10423 ("r-iranges" ,r-iranges)
10424 ("r-rhdf5" ,r-rhdf5)
10425 ("r-s4vectors" ,r-s4vectors)))
10426 (home-page "https://bioconductor.org/packages/HDF5Array")
10427 (synopsis "HDF5 back end for DelayedArray objects")
10428 (description "This package provides an array-like container for convenient
10429 access and manipulation of HDF5 datasets. It supports delayed operations and
10430 block processing.")
10431 (license license:artistic2.0)))
10433 (define-public r-rhdf5lib
10435 (name "r-rhdf5lib")
10440 (uri (bioconductor-uri "Rhdf5lib" version))
10443 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10444 (properties `((upstream-name . "Rhdf5lib")))
10445 (build-system r-build-system)
10448 (modify-phases %standard-phases
10449 (add-after 'unpack 'do-not-use-bundled-hdf5
10450 (lambda* (#:key inputs #:allow-other-keys)
10451 (for-each delete-file '("configure" "configure.ac"))
10452 ;; Do not make other packages link with the proprietary libsz.
10453 (substitute* "R/zzz.R"
10454 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10455 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10456 (("'%s/libhdf5.a %s/libsz.a'")
10457 "'%s/libhdf5.a %s/libhdf5.a'"))
10458 (with-directory-excursion "src"
10459 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10460 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10462 (rename-file "Makevars.in" "Makevars")
10463 (substitute* "Makevars"
10464 (("HDF5_CXX_LIB=.*")
10465 (string-append "HDF5_CXX_LIB="
10466 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10468 (string-append "HDF5_LIB="
10469 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10470 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10471 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10472 ;; szip is non-free software
10473 (("cp \\$\\{SZIP_LIB\\}.*") "")
10474 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10475 "PKG_LIBS = ${HDF5_LIB}\n")))
10482 `(("hdf5-source" ,(package-source hdf5))))
10483 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10484 (synopsis "HDF5 library as an R package")
10485 (description "This package provides C and C++ HDF5 libraries for use in R
10487 (license license:artistic2.0)))
10489 (define-public r-beachmat
10491 (name "r-beachmat")
10496 (uri (bioconductor-uri "beachmat" version))
10499 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10500 (build-system r-build-system)
10504 `(("r-delayedarray" ,r-delayedarray)
10505 ("r-hdf5array" ,r-hdf5array)
10507 ("r-rhdf5" ,r-rhdf5)
10508 ("r-rhdf5lib" ,r-rhdf5lib)))
10509 (home-page "https://bioconductor.org/packages/beachmat")
10510 (synopsis "Compiling Bioconductor to handle each matrix type")
10511 (description "This package provides a consistent C++ class interface for a
10512 variety of commonly used matrix types, including sparse and HDF5-backed
10514 (license license:gpl3)))
10516 (define-public r-singlecellexperiment
10518 (name "r-singlecellexperiment")
10523 (uri (bioconductor-uri "SingleCellExperiment" version))
10526 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10528 `((upstream-name . "SingleCellExperiment")))
10529 (build-system r-build-system)
10531 `(("r-biocgenerics" ,r-biocgenerics)
10532 ("r-s4vectors" ,r-s4vectors)
10533 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10534 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10535 (synopsis "S4 classes for single cell data")
10536 (description "This package defines an S4 class for storing data from
10537 single-cell experiments. This includes specialized methods to store and
10538 retrieve spike-in information, dimensionality reduction coordinates and size
10539 factors for each cell, along with the usual metadata for genes and
10541 (license license:gpl3)))
10543 (define-public r-scater
10549 (uri (bioconductor-uri "scater" version))
10552 "0fp68n0xnbf90wrprqawsbilg9x7v2scp0dxb3936g20025csrdd"))))
10553 (build-system r-build-system)
10555 `(("r-beachmat" ,r-beachmat)
10556 ("r-biobase" ,r-biobase)
10557 ("r-biocgenerics" ,r-biocgenerics)
10558 ("r-biomart" ,r-biomart)
10559 ("r-data-table" ,r-data-table)
10560 ("r-dplyr" ,r-dplyr)
10561 ("r-edger" ,r-edger)
10562 ("r-ggbeeswarm" ,r-ggbeeswarm)
10563 ("r-ggplot2" ,r-ggplot2)
10564 ("r-limma" ,r-limma)
10565 ("r-matrix" ,r-matrix)
10566 ("r-matrixstats" ,r-matrixstats)
10569 ("r-reshape2" ,r-reshape2)
10570 ("r-rhdf5" ,r-rhdf5)
10571 ("r-rhdf5lib" ,r-rhdf5lib)
10572 ("r-rjson" ,r-rjson)
10573 ("r-s4vectors" ,r-s4vectors)
10574 ("r-shiny" ,r-shiny)
10575 ("r-shinydashboard" ,r-shinydashboard)
10576 ("r-singlecellexperiment" ,r-singlecellexperiment)
10577 ("r-summarizedexperiment" ,r-summarizedexperiment)
10578 ("r-tximport" ,r-tximport)
10579 ("r-viridis" ,r-viridis)))
10580 (home-page "https://github.com/davismcc/scater")
10581 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10582 (description "This package provides a collection of tools for doing
10583 various analyses of single-cell RNA-seq gene expression data, with a focus on
10585 (license license:gpl2+)))
10587 (define-public r-scran
10594 (uri (bioconductor-uri "scran" version))
10597 "0zfm5i8xrnzb3894xygqd6zkbwaa2x3z74wbxw39fcjhyhxv2hmb"))))
10598 (build-system r-build-system)
10600 `(("r-beachmat" ,r-beachmat)
10601 ("r-biocgenerics" ,r-biocgenerics)
10602 ("r-biocparallel" ,r-biocparallel)
10604 ("r-dynamictreecut" ,r-dynamictreecut)
10605 ("r-edger" ,r-edger)
10607 ("r-ggplot2" ,r-ggplot2)
10608 ("r-igraph" ,r-igraph)
10609 ("r-limma" ,r-limma)
10610 ("r-matrix" ,r-matrix)
10612 ("r-rhdf5lib" ,r-rhdf5lib)
10613 ("r-s4vectors" ,r-s4vectors)
10614 ("r-scater" ,r-scater)
10615 ("r-shiny" ,r-shiny)
10616 ("r-singlecellexperiment" ,r-singlecellexperiment)
10617 ("r-statmod" ,r-statmod)
10618 ("r-summarizedexperiment" ,r-summarizedexperiment)
10619 ("r-viridis" ,r-viridis)
10621 (home-page "https://bioconductor.org/packages/scran")
10622 (synopsis "Methods for single-cell RNA-Seq data analysis")
10623 (description "This package implements a variety of low-level analyses of
10624 single-cell RNA-seq data. Methods are provided for normalization of
10625 cell-specific biases, assignment of cell cycle phase, and detection of highly
10626 variable and significantly correlated genes.")
10627 (license license:gpl3)))
10629 (define-public r-delayedmatrixstats
10631 (name "r-delayedmatrixstats")
10636 (uri (bioconductor-uri "DelayedMatrixStats" version))
10639 "1nfdan0k2z4mynxyblsil0cjclsy63b0w9r1hczfk27i8hmxx13h"))))
10641 `((upstream-name . "DelayedMatrixStats")))
10642 (build-system r-build-system)
10644 `(("r-delayedarray" ,r-delayedarray)
10645 ("r-iranges" ,r-iranges)
10646 ("r-matrix" ,r-matrix)
10647 ("r-matrixstats" ,r-matrixstats)
10648 ("r-s4vectors" ,r-s4vectors)))
10649 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10650 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10652 "This package provides a port of the @code{matrixStats} API for use with
10653 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10654 contains high-performing functions operating on rows and columns of
10655 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10656 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10657 are optimized per data type and for subsetted calculations such that both
10658 memory usage and processing time is minimized.")
10659 (license license:expat)))
10661 (define htslib-for-sambamba
10662 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10665 (name "htslib-for-sambamba")
10666 (version (string-append "1.3.1-1." (string-take commit 9)))
10670 (uri (git-reference
10671 (url "https://github.com/lomereiter/htslib.git")
10673 (file-name (string-append "htslib-" version "-checkout"))
10676 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10678 (substitute-keyword-arguments (package-arguments htslib)
10680 `(modify-phases ,phases
10681 (add-after 'unpack 'bootstrap
10683 (zero? (system* "autoreconf" "-vif"))))))))
10685 `(("autoconf" ,autoconf)
10686 ("automake" ,automake)
10687 ,@(package-native-inputs htslib))))))
10689 (define-public sambamba
10696 (uri (string-append "https://github.com/lomereiter/sambamba/"
10697 "archive/v" version ".tar.gz"))
10698 (file-name (string-append name "-" version ".tar.gz"))
10701 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10702 (build-system gnu-build-system)
10704 `(#:tests? #f ; there is no test target
10706 '("D_COMPILER=ldc2"
10707 ;; Override "--compiler" flag only.
10708 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10709 "sambamba-ldmd2-64")
10711 (modify-phases %standard-phases
10712 (delete 'configure)
10713 (add-after 'unpack 'place-biod
10714 (lambda* (#:key inputs #:allow-other-keys)
10715 (copy-recursively (assoc-ref inputs "biod") "BioD")
10717 (add-after 'unpack 'unbundle-prerequisites
10719 (substitute* "Makefile"
10720 ((" htslib-static lz4-static") ""))
10723 (lambda* (#:key outputs #:allow-other-keys)
10724 (let* ((out (assoc-ref outputs "out"))
10725 (bin (string-append out "/bin")))
10727 (install-file "build/sambamba" bin)
10733 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10736 (uri (git-reference
10737 (url "https://github.com/biod/BioD.git")
10739 (file-name (string-append "biod-"
10740 (string-take commit 9)
10744 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10747 ("htslib" ,htslib-for-sambamba)))
10748 (home-page "http://lomereiter.github.io/sambamba")
10749 (synopsis "Tools for working with SAM/BAM data")
10750 (description "Sambamba is a high performance modern robust and
10751 fast tool (and library), written in the D programming language, for
10752 working with SAM and BAM files. Current parallelised functionality is
10753 an important subset of samtools functionality, including view, index,
10754 sort, markdup, and depth.")
10755 (license license:gpl2+)))
10757 (define-public ritornello
10759 (name "ritornello")
10763 (uri (string-append "https://github.com/KlugerLab/"
10764 "Ritornello/archive/v"
10765 version ".tar.gz"))
10766 (file-name (string-append name "-" version ".tar.gz"))
10769 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10770 (build-system gnu-build-system)
10772 `(#:tests? #f ; there are no tests
10774 (modify-phases %standard-phases
10775 (add-after 'unpack 'patch-samtools-references
10776 (lambda* (#:key inputs #:allow-other-keys)
10777 (substitute* '("src/SamStream.h"
10778 "src/BufferedGenomeReader.h")
10779 (("<sam.h>") "<samtools/sam.h>"))
10781 (delete 'configure)
10783 (lambda* (#:key inputs outputs #:allow-other-keys)
10784 (let* ((out (assoc-ref outputs "out"))
10785 (bin (string-append out "/bin/")))
10787 (install-file "bin/Ritornello" bin)
10790 `(("samtools" ,samtools-0.1)
10794 (home-page "https://github.com/KlugerLab/Ritornello")
10795 (synopsis "Control-free peak caller for ChIP-seq data")
10796 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10797 signal processing that can accurately call binding events without the need to
10798 do a pair total DNA input or IgG control sample. It has been tested for use
10799 with narrow binding events such as transcription factor ChIP-seq.")
10800 (license license:gpl3+)))
10802 (define-public trim-galore
10804 (name "trim-galore")
10809 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10810 "projects/trim_galore/trim_galore_v"
10814 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10815 (build-system gnu-build-system)
10817 `(#:tests? #f ; no tests
10819 (modify-phases %standard-phases
10820 ;; The archive contains plain files.
10822 (lambda* (#:key source #:allow-other-keys)
10823 (zero? (system* "unzip" source))))
10824 (delete 'configure)
10826 (add-after 'unpack 'hardcode-tool-references
10827 (lambda* (#:key inputs #:allow-other-keys)
10828 (substitute* "trim_galore"
10829 (("\\$path_to_cutadapt = 'cutadapt'")
10830 (string-append "$path_to_cutadapt = '"
10831 (assoc-ref inputs "cutadapt")
10834 (string-append "| "
10835 (assoc-ref inputs "gzip")
10838 (string-append "\""
10839 (assoc-ref inputs "gzip")
10843 (lambda* (#:key outputs #:allow-other-keys)
10844 (let ((bin (string-append (assoc-ref outputs "out")
10847 (install-file "trim_galore" bin)
10852 ("cutadapt" ,cutadapt)))
10854 `(("unzip" ,unzip)))
10855 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10856 (synopsis "Wrapper around Cutadapt and FastQC")
10857 (description "Trim Galore! is a wrapper script to automate quality and
10858 adapter trimming as well as quality control, with some added functionality to
10859 remove biased methylation positions for RRBS sequence files.")
10860 (license license:gpl3+)))
10862 (define-public gess
10868 (uri (string-append "http://compbio.uthscsa.edu/"
10870 "gess-" version ".src.tar.gz"))
10873 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10874 (build-system gnu-build-system)
10876 `(#:tests? #f ; no tests
10878 (modify-phases %standard-phases
10879 (delete 'configure)
10882 (lambda* (#:key inputs outputs #:allow-other-keys)
10883 (let* ((python (assoc-ref inputs "python"))
10884 (out (assoc-ref outputs "out"))
10885 (bin (string-append out "/bin/"))
10886 (target (string-append
10887 out "/lib/python2.7/site-packages/gess/")))
10889 (copy-recursively "." target)
10890 ;; Make GESS.py executable
10891 (chmod (string-append target "GESS.py") #o555)
10892 ;; Add Python shebang to the top and make Matplotlib
10894 (substitute* (string-append target "GESS.py")
10895 (("\"\"\"Description:" line)
10896 (string-append "#!" (which "python") "
10898 matplotlib.use('Agg')
10900 ;; Make sure GESS has all modules in its path
10901 (wrap-program (string-append target "GESS.py")
10902 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10904 (symlink (string-append target "GESS.py")
10905 (string-append bin "GESS.py"))
10908 `(("python" ,python-2)
10909 ("python2-pysam" ,python2-pysam)
10910 ("python2-scipy" ,python2-scipy)
10911 ("python2-numpy" ,python2-numpy)
10912 ("python2-networkx" ,python2-networkx)
10913 ("python2-biopython" ,python2-biopython)))
10914 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10915 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10917 "GESS is an implementation of a novel computational method to detect de
10918 novo exon-skipping events directly from raw RNA-seq data without the prior
10919 knowledge of gene annotation information. GESS stands for the graph-based
10920 exon-skipping scanner detection scheme.")
10921 (license license:bsd-3)))
10923 (define-public phylip
10930 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10931 "download/phylip-" version ".tar.gz"))
10934 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10935 (build-system gnu-build-system)
10937 `(#:tests? #f ; no check target
10938 #:make-flags (list "-f" "Makefile.unx" "install")
10939 #:parallel-build? #f ; not supported
10941 (modify-phases %standard-phases
10942 (add-after 'unpack 'enter-dir
10943 (lambda _ (chdir "src") #t))
10944 (delete 'configure)
10946 (lambda* (#:key inputs outputs #:allow-other-keys)
10947 (let ((target (string-append (assoc-ref outputs "out")
10950 (for-each (lambda (file)
10951 (install-file file target))
10952 (find-files "../exe" ".*")))
10954 (home-page "http://evolution.genetics.washington.edu/phylip/")
10955 (synopsis "Tools for inferring phylogenies")
10956 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10957 programs for inferring phylogenies (evolutionary trees).")
10958 (license license:bsd-2)))
10967 (uri (string-append "https://integrativemodeling.org/"
10968 version "/download/imp-" version ".tar.gz"))
10971 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10972 (build-system cmake-build-system)
10974 `(;; FIXME: Some tests fail because they produce warnings, others fail
10975 ;; because the PYTHONPATH does not include the modeller's directory.
10983 ("python" ,python-2)))
10985 `(("python2-numpy" ,python2-numpy)
10986 ("python2-scipy" ,python2-scipy)
10987 ("python2-pandas" ,python2-pandas)
10988 ("python2-scikit-learn" ,python2-scikit-learn)
10989 ("python2-networkx" ,python2-networkx)))
10990 (home-page "https://integrativemodeling.org")
10991 (synopsis "Integrative modeling platform")
10992 (description "IMP's broad goal is to contribute to a comprehensive
10993 structural characterization of biomolecules ranging in size and complexity
10994 from small peptides to large macromolecular assemblies, by integrating data
10995 from diverse biochemical and biophysical experiments. IMP provides a C++ and
10996 Python toolbox for solving complex modeling problems, and a number of
10997 applications for tackling some common problems in a user-friendly way.")
10998 ;; IMP is largely available under the GNU Lesser GPL; see the file
10999 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11000 ;; available under the GNU GPL (see the file COPYING.GPL).
11001 (license (list license:lgpl2.1+
11004 (define-public tadbit
11010 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11011 "archive/v" version ".tar.gz"))
11012 (file-name (string-append name "-" version ".tar.gz"))
11015 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11016 (build-system python-build-system)
11018 `(;; Tests are included and must be run after installation, but
11019 ;; they are incomplete and thus cannot be run.
11023 (modify-phases %standard-phases
11024 (add-after 'unpack 'fix-problems-with-setup.py
11025 (lambda* (#:key outputs #:allow-other-keys)
11026 ;; setup.py opens these files for writing
11027 (chmod "_pytadbit/_version.py" #o664)
11028 (chmod "README.rst" #o664)
11030 ;; Don't attempt to install the bash completions to
11031 ;; the home directory.
11032 (rename-file "extras/.bash_completion"
11034 (substitute* "setup.py"
11035 (("\\(path.expanduser\\('~'\\)")
11036 (string-append "(\""
11037 (assoc-ref outputs "out")
11038 "/etc/bash_completion.d\""))
11039 (("extras/\\.bash_completion")
11043 ;; TODO: add Chimera for visualization
11046 ("python2-scipy" ,python2-scipy)
11047 ("python2-numpy" ,python2-numpy)
11048 ("python2-matplotlib" ,python2-matplotlib)
11049 ("python2-pysam" ,python2-pysam)))
11050 (home-page "http://3dgenomes.github.io/TADbit/")
11051 (synopsis "Analyze, model, and explore 3C-based data")
11053 "TADbit is a complete Python library to deal with all steps to analyze,
11054 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11055 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11056 correct interaction matrices, identify and compare the so-called
11057 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11058 interaction matrices, and finally, extract structural properties from the
11059 models. TADbit is complemented by TADkit for visualizing 3D models.")
11060 (license license:gpl3+)))
11062 (define-public kentutils
11065 ;; 302.1.0 is out, but the only difference is the inclusion of
11066 ;; pre-built binaries.
11067 (version "302.0.0")
11071 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11072 "archive/v" version ".tar.gz"))
11073 (file-name (string-append name "-" version ".tar.gz"))
11076 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11077 (modules '((guix build utils)
11082 ;; Only the contents of the specified directories are free
11083 ;; for all uses, so we remove the rest. "hg/autoSql" and
11084 ;; "hg/autoXml" are nominally free, but they depend on a
11085 ;; library that is built from the sources in "hg/lib",
11086 ;; which is nonfree.
11087 (let ((free (list "." ".."
11088 "utils" "lib" "inc" "tagStorm"
11089 "parasol" "htslib"))
11090 (directory? (lambda (file)
11091 (eq? 'directory (stat:type (stat file))))))
11092 (for-each (lambda (file)
11093 (and (directory? file)
11094 (delete-file-recursively file)))
11095 (map (cut string-append "src/" <>)
11098 (not (member file free)))))))
11099 ;; Only make the utils target, not the userApps target,
11100 ;; because that requires libraries we won't build.
11101 (substitute* "Makefile"
11102 ((" userApps") " utils"))
11103 ;; Only build libraries that are free.
11104 (substitute* "src/makefile"
11105 (("DIRS =.*") "DIRS =\n")
11106 (("cd jkOwnLib.*") "")
11109 (substitute* "src/utils/makefile"
11110 ;; These tools depend on "jkhgap.a", which is part of the
11111 ;; nonfree "src/hg/lib" directory.
11112 (("raSqlQuery") "")
11113 (("pslLiftSubrangeBlat") "")
11115 ;; Do not build UCSC tools, which may require nonfree
11117 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11119 (build-system gnu-build-system)
11121 `( ;; There is no global test target and the test target for
11122 ;; individual tools depends on input files that are not
11126 (modify-phases %standard-phases
11127 (add-after 'unpack 'fix-paths
11129 (substitute* "Makefile"
11130 (("/bin/echo") (which "echo")))
11132 (add-after 'unpack 'prepare-samtabix
11133 (lambda* (#:key inputs #:allow-other-keys)
11134 (copy-recursively (assoc-ref inputs "samtabix")
11137 (delete 'configure)
11139 (lambda* (#:key outputs #:allow-other-keys)
11140 (let ((bin (string-append (assoc-ref outputs "out")
11142 (copy-recursively "bin" bin))
11148 (uri (git-reference
11149 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11150 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11153 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11160 ("openssl" ,openssl)))
11161 (home-page "http://genome.cse.ucsc.edu/index.html")
11162 (synopsis "Assorted bioinformatics utilities")
11163 (description "This package provides the kentUtils, a selection of
11164 bioinformatics utilities used in combination with the UCSC genome
11166 ;; Only a subset of the sources are released under a non-copyleft
11167 ;; free software license. All other sources are removed in a
11168 ;; snippet. See this bug report for an explanation of how the
11169 ;; license statements apply:
11170 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11171 (license (license:non-copyleft
11172 "http://genome.ucsc.edu/license/"
11173 "The contents of this package are free for all uses."))))
11175 (define-public f-seq
11176 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11180 (version (string-append "1.1-" revision "." (string-take commit 7)))
11183 (uri (git-reference
11184 (url "https://github.com/aboyle/F-seq.git")
11186 (file-name (string-append name "-" version))
11189 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11190 (modules '((guix build utils)))
11191 ;; Remove bundled Java library archives.
11194 (for-each delete-file (find-files "lib" ".*"))
11196 (build-system ant-build-system)
11198 `(#:tests? #f ; no tests included
11200 (modify-phases %standard-phases
11202 (lambda* (#:key inputs outputs #:allow-other-keys)
11203 (let* ((target (assoc-ref outputs "out"))
11204 (doc (string-append target "/share/doc/f-seq/")))
11207 (substitute* "bin/linux/fseq"
11208 (("java") (which "java"))
11209 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11210 (string-append (assoc-ref inputs "java-commons-cli")
11211 "/share/java/commons-cli.jar"))
11213 (string-append "REALDIR=" target "/bin\n")))
11214 (install-file "README.txt" doc)
11215 (install-file "bin/linux/fseq" (string-append target "/bin"))
11216 (install-file "build~/fseq.jar" (string-append target "/lib"))
11217 (copy-recursively "lib" (string-append target "/lib"))
11221 ("java-commons-cli" ,java-commons-cli)))
11222 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11223 (synopsis "Feature density estimator for high-throughput sequence tags")
11225 "F-Seq is a software package that generates a continuous tag sequence
11226 density estimation allowing identification of biologically meaningful sites
11227 such as transcription factor binding sites (ChIP-seq) or regions of open
11228 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11230 (license license:gpl3+))))
11232 (define-public bismark
11239 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11240 "archive/" version ".tar.gz"))
11241 (file-name (string-append name "-" version ".tar.gz"))
11244 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11245 (build-system perl-build-system)
11247 `(#:tests? #f ; there are no tests
11249 (modify-phases %standard-phases
11250 (delete 'configure)
11253 (lambda* (#:key outputs #:allow-other-keys)
11254 (let ((bin (string-append (assoc-ref outputs "out")
11256 (docdir (string-append (assoc-ref outputs "out")
11257 "/share/doc/bismark"))
11258 (docs '("Bismark_User_Guide.pdf"
11259 "RELEASE_NOTES.txt"))
11260 (scripts '("bismark"
11261 "bismark_genome_preparation"
11262 "bismark_methylation_extractor"
11265 "coverage2cytosine"
11266 "deduplicate_bismark"
11267 "bismark_sitrep.tpl"
11269 "bismark2summary")))
11272 (for-each (lambda (file) (install-file file bin))
11274 (for-each (lambda (file) (install-file file docdir))
11277 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11278 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11279 (description "Bismark is a program to map bisulfite treated sequencing
11280 reads to a genome of interest and perform methylation calls in a single step.
11281 The output can be easily imported into a genome viewer, such as SeqMonk, and
11282 enables a researcher to analyse the methylation levels of their samples
11283 straight away. Its main features are:
11286 @item Bisulfite mapping and methylation calling in one single step
11287 @item Supports single-end and paired-end read alignments
11288 @item Supports ungapped and gapped alignments
11289 @item Alignment seed length, number of mismatches etc are adjustable
11290 @item Output discriminates between cytosine methylation in CpG, CHG
11293 (license license:gpl3+)))
11295 (define-public paml
11301 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11302 "paml" version ".tgz"))
11305 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11306 (modules '((guix build utils)))
11307 ;; Remove Windows binaries
11310 (for-each delete-file (find-files "." "\\.exe$"))
11312 (build-system gnu-build-system)
11314 `(#:tests? #f ; there are no tests
11315 #:make-flags '("CC=gcc")
11317 (modify-phases %standard-phases
11318 (replace 'configure
11320 (substitute* "src/BFdriver.c"
11321 (("/bin/bash") (which "bash")))
11325 (lambda* (#:key outputs #:allow-other-keys)
11326 (let ((tools '("baseml" "basemlg" "codeml"
11327 "pamp" "evolver" "yn00" "chi2"))
11328 (bin (string-append (assoc-ref outputs "out") "/bin"))
11329 (docdir (string-append (assoc-ref outputs "out")
11330 "/share/doc/paml")))
11332 (for-each (lambda (file) (install-file file bin)) tools)
11333 (copy-recursively "../doc" docdir)
11335 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11336 (synopsis "Phylogentic analysis by maximum likelihood")
11337 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11338 contains a few programs for model fitting and phylogenetic tree reconstruction
11339 using nucleotide or amino-acid sequence data.")
11341 (license license:gpl3)))
11343 (define-public kallisto
11349 (uri (string-append "https://github.com/pachterlab/"
11350 "kallisto/archive/v" version ".tar.gz"))
11351 (file-name (string-append name "-" version ".tar.gz"))
11354 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11355 (build-system cmake-build-system)
11356 (arguments `(#:tests? #f)) ; no "check" target
11360 (home-page "http://pachterlab.github.io/kallisto/")
11361 (synopsis "Near-optimal RNA-Seq quantification")
11363 "Kallisto is a program for quantifying abundances of transcripts from
11364 RNA-Seq data, or more generally of target sequences using high-throughput
11365 sequencing reads. It is based on the novel idea of pseudoalignment for
11366 rapidly determining the compatibility of reads with targets, without the need
11367 for alignment. Pseudoalignment of reads preserves the key information needed
11368 for quantification, and kallisto is therefore not only fast, but also as
11369 accurate as existing quantification tools.")
11370 (license license:bsd-2)))
11372 (define-public libgff
11378 (uri (string-append
11379 "https://github.com/Kingsford-Group/"
11380 "libgff/archive/v" version ".tar.gz"))
11381 (file-name (string-append name "-" version ".tar.gz"))
11384 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11385 (build-system cmake-build-system)
11386 (arguments `(#:tests? #f)) ; no tests included
11387 (home-page "https://github.com/Kingsford-Group/libgff")
11388 (synopsis "Parser library for reading/writing GFF files")
11389 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11390 code that is used in the Cufflinks codebase. The goal of this library is to
11391 provide this functionality without the necessity of drawing in a heavy-weight
11392 dependency like SeqAn.")
11393 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11395 (define-public libdivsufsort
11397 (name "libdivsufsort")
11401 (uri (git-reference
11402 (url "https://github.com/y-256/libdivsufsort.git")
11406 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11407 (build-system cmake-build-system)
11409 '(#:tests? #f ; there are no tests
11411 ;; Needed for rapmap and sailfish.
11412 '("-DBUILD_DIVSUFSORT64=ON")))
11413 (home-page "https://github.com/y-256/libdivsufsort")
11414 (synopsis "Lightweight suffix-sorting library")
11415 (description "libdivsufsort is a software library that implements a
11416 lightweight suffix array construction algorithm. This library provides a
11417 simple and an efficient C API to construct a suffix array and a
11418 Burrows-Wheeler transformed string from a given string over a constant-size
11419 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11420 bytes of memory space, where n is the length of the string.")
11421 (license license:expat)))
11423 (define-public sailfish
11430 (string-append "https://github.com/kingsfordgroup/"
11431 "sailfish/archive/v" version ".tar.gz"))
11432 (file-name (string-append name "-" version ".tar.gz"))
11435 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11436 (modules '((guix build utils)))
11439 ;; Delete bundled headers for eigen3.
11440 (delete-file-recursively "include/eigen3/")
11442 (build-system cmake-build-system)
11444 `(#:configure-flags
11445 (list (string-append "-DBOOST_INCLUDEDIR="
11446 (assoc-ref %build-inputs "boost")
11448 (string-append "-DBOOST_LIBRARYDIR="
11449 (assoc-ref %build-inputs "boost")
11451 (string-append "-DBoost_LIBRARIES="
11452 "-lboost_iostreams "
11453 "-lboost_filesystem "
11458 "-lboost_program_options")
11459 "-DBoost_FOUND=TRUE"
11460 ;; Don't download RapMap---we already have it!
11461 "-DFETCHED_RAPMAP=1")
11462 ;; Tests must be run after installation and the location of the test
11463 ;; data file must be overridden. But the tests fail. It looks like
11464 ;; they are not really meant to be run.
11467 (modify-phases %standard-phases
11468 ;; Boost cannot be found, even though it's right there.
11469 (add-after 'unpack 'do-not-look-for-boost
11470 (lambda* (#:key inputs #:allow-other-keys)
11471 (substitute* "CMakeLists.txt"
11472 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11473 (add-after 'unpack 'do-not-assign-to-macro
11475 (substitute* "include/spdlog/details/format.cc"
11476 (("const unsigned CHAR_WIDTH = 1;") ""))))
11477 (add-after 'unpack 'prepare-rapmap
11478 (lambda* (#:key inputs #:allow-other-keys)
11479 (let ((src "external/install/src/rapmap/")
11480 (include "external/install/include/rapmap/")
11481 (rapmap (assoc-ref inputs "rapmap")))
11482 (mkdir-p "/tmp/rapmap")
11483 (system* "tar" "xf"
11484 (assoc-ref inputs "rapmap")
11486 "--strip-components=1")
11489 (for-each (lambda (file)
11490 (install-file file src))
11491 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11492 (copy-recursively "/tmp/rapmap/include" include))))
11493 (add-after 'unpack 'use-system-libraries
11494 (lambda* (#:key inputs #:allow-other-keys)
11495 (substitute* '("src/SailfishIndexer.cpp"
11496 "src/SailfishUtils.cpp"
11497 "src/SailfishQuantify.cpp"
11498 "src/FASTAParser.cpp"
11500 "include/SailfishUtils.hpp"
11501 "include/SailfishIndex.hpp"
11502 "include/CollapsedEMOptimizer.hpp"
11503 "src/CollapsedEMOptimizer.cpp")
11504 (("#include \"jellyfish/config.h\"") ""))
11505 (substitute* "src/CMakeLists.txt"
11506 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11507 (string-append (assoc-ref inputs "jellyfish")
11508 "/include/jellyfish-" ,(package-version jellyfish)))
11509 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11510 (string-append (assoc-ref inputs "jellyfish")
11511 "/lib/libjellyfish-2.0.a"))
11512 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11513 (string-append (assoc-ref inputs "libdivsufsort")
11514 "/lib/libdivsufsort.so"))
11515 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11516 (string-append (assoc-ref inputs "libdivsufsort")
11517 "/lib/libdivsufsort64.so")))
11518 (substitute* "CMakeLists.txt"
11519 ;; Don't prefer static libs
11520 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11521 (("find_package\\(Jellyfish.*") "")
11522 (("ExternalProject_Add\\(libjellyfish") "message(")
11523 (("ExternalProject_Add\\(libgff") "message(")
11524 (("ExternalProject_Add\\(libsparsehash") "message(")
11525 (("ExternalProject_Add\\(libdivsufsort") "message("))
11527 ;; Ensure that Eigen headers can be found
11528 (setenv "CPLUS_INCLUDE_PATH"
11529 (string-append (getenv "CPLUS_INCLUDE_PATH")
11531 (assoc-ref inputs "eigen")
11532 "/include/eigen3")))))))
11536 ("jemalloc" ,jemalloc)
11537 ("jellyfish" ,jellyfish)
11538 ("sparsehash" ,sparsehash)
11541 (uri (git-reference
11542 (url "https://github.com/COMBINE-lab/RapMap.git")
11543 (commit (string-append "sf-v" version))))
11544 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11547 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11548 (modules '((guix build utils)))
11549 ;; These files are expected to be excluded.
11551 '(begin (delete-file-recursively "include/spdlog")
11552 (for-each delete-file '("include/xxhash.h"
11553 "src/xxhash.c"))))))
11554 ("libdivsufsort" ,libdivsufsort)
11559 `(("pkg-config" ,pkg-config)))
11560 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11561 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11562 (description "Sailfish is a tool for genomic transcript quantification
11563 from RNA-seq data. It requires a set of target transcripts (either from a
11564 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11565 fasta file containing your reference transcripts and a (set of) fasta/fastq
11566 file(s) containing your reads.")
11567 (license license:gpl3+)))
11569 (define libstadenio-for-salmon
11571 (name "libstadenio")
11575 (uri (git-reference
11576 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11577 (commit (string-append "v" version))))
11578 (file-name (string-append name "-" version "-checkout"))
11581 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11582 (build-system gnu-build-system)
11583 (arguments '(#:parallel-tests? #f)) ; not supported
11587 `(("perl" ,perl))) ; for tests
11588 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11589 (synopsis "General purpose trace and experiment file library")
11590 (description "This package provides a library of file reading and writing
11591 code to provide a general purpose Trace file (and Experiment File) reading
11594 The following file formats are supported:
11597 @item SCF trace files
11598 @item ABI trace files
11599 @item ALF trace files
11600 @item ZTR trace files
11601 @item SFF trace archives
11602 @item SRF trace archives
11603 @item Experiment files
11604 @item Plain text files
11605 @item SAM/BAM sequence files
11606 @item CRAM sequence files
11608 (license license:bsd-3)))
11610 (define spdlog-for-salmon
11616 (uri (git-reference
11617 (url "https://github.com/COMBINE-lab/spdlog.git")
11618 (commit (string-append "v" version))))
11619 (file-name (string-append name "-" version "-checkout"))
11622 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11623 (build-system cmake-build-system)
11624 (home-page "https://github.com/COMBINE-lab/spdlog")
11625 (synopsis "Very fast C++ logging library")
11626 (description "Spdlog is a very fast header-only C++ logging library with
11627 performance as its primary goal.")
11628 (license license:expat)))
11630 ;; This is a modified variant of bwa for use with Salmon. It installs a
11631 ;; library to avoid having to build this as part of Salmon.
11632 (define bwa-for-salmon
11633 (package (inherit bwa)
11635 (version "0.7.12.5")
11638 (uri (git-reference
11639 (url "https://github.com/COMBINE-lab/bwa.git")
11640 (commit (string-append "v" version))))
11641 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11644 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11645 (build-system gnu-build-system)
11647 '(#:tests? #f ;no "check" target
11649 (modify-phases %standard-phases
11651 (lambda* (#:key outputs #:allow-other-keys)
11652 (let* ((out (assoc-ref outputs "out"))
11653 (bin (string-append out "/bin"))
11654 (lib (string-append out "/lib"))
11655 (doc (string-append out "/share/doc/bwa"))
11656 (man (string-append out "/share/man/man1"))
11657 (inc (string-append out "/include/bwa")))
11658 (install-file "bwa" bin)
11659 (install-file "README.md" doc)
11660 (install-file "bwa.1" man)
11661 (install-file "libbwa.a" lib)
11664 (for-each (lambda (file)
11665 (install-file file inc))
11666 (find-files "." "\\.h$")))
11668 ;; no "configure" script
11669 (delete 'configure))))))
11671 (define-public salmon
11677 (uri (git-reference
11678 (url "https://github.com/COMBINE-lab/salmon.git")
11679 (commit (string-append "v" version))))
11680 (file-name (string-append name "-" version "-checkout"))
11683 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11684 (modules '((guix build utils)))
11687 ;; Delete bundled headers for eigen3.
11688 (delete-file-recursively "include/eigen3/")
11690 (build-system cmake-build-system)
11692 `(#:configure-flags
11693 (list (string-append "-DBOOST_INCLUDEDIR="
11694 (assoc-ref %build-inputs "boost")
11696 (string-append "-DBOOST_LIBRARYDIR="
11697 (assoc-ref %build-inputs "boost")
11699 (string-append "-DBoost_LIBRARIES="
11700 "-lboost_iostreams "
11701 "-lboost_filesystem "
11706 "-lboost_program_options")
11707 "-DBoost_FOUND=TRUE"
11708 "-DTBB_LIBRARIES=tbb tbbmalloc"
11709 ;; Don't download RapMap---we already have it!
11710 "-DFETCHED_RAPMAP=1")
11712 (modify-phases %standard-phases
11713 ;; Boost cannot be found, even though it's right there.
11714 (add-after 'unpack 'do-not-look-for-boost
11715 (lambda* (#:key inputs #:allow-other-keys)
11716 (substitute* "CMakeLists.txt"
11717 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11718 (add-after 'unpack 'do-not-phone-home
11720 (substitute* "src/Salmon.cpp"
11721 (("getVersionMessage\\(\\)") "\"\""))))
11722 (add-after 'unpack 'prepare-rapmap
11723 (lambda* (#:key inputs #:allow-other-keys)
11724 (let ((src "external/install/src/rapmap/")
11725 (include "external/install/include/rapmap/")
11726 (rapmap (assoc-ref inputs "rapmap")))
11729 (for-each (lambda (file)
11730 (install-file file src))
11731 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11732 (copy-recursively (string-append rapmap "/include") include)
11733 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11734 "external/install/include/rapmap/FastxParser.hpp"
11735 "external/install/include/rapmap/concurrentqueue.h"
11736 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11737 "external/install/src/rapmap/FastxParser.cpp"
11738 "external/install/src/rapmap/xxhash.c")))))
11739 (add-after 'unpack 'use-system-libraries
11740 (lambda* (#:key inputs #:allow-other-keys)
11741 (substitute* "src/CMakeLists.txt"
11742 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11743 (string-append (assoc-ref inputs "jellyfish")
11744 "/include/jellyfish-" ,(package-version jellyfish)))
11745 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11746 (string-append (assoc-ref inputs "jellyfish")
11747 "/lib/libjellyfish-2.0.a"))
11748 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11749 (string-append (assoc-ref inputs "libdivsufsort")
11750 "/lib/libdivsufsort.so"))
11751 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11752 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11753 "/lib/libstaden-read.a"))
11754 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
11755 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
11756 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11757 (string-append (assoc-ref inputs "libdivsufsort")
11758 "/lib/libdivsufsort64.so")))
11759 (substitute* "CMakeLists.txt"
11760 ;; Don't prefer static libs
11761 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11762 (("set\\(TBB_LIBRARIES") "message(")
11763 (("find_package\\(Jellyfish.*") "")
11764 (("ExternalProject_Add\\(libcereal") "message(")
11765 (("ExternalProject_Add\\(libbwa") "message(")
11766 (("ExternalProject_Add\\(libjellyfish") "message(")
11767 (("ExternalProject_Add\\(libgff") "message(")
11768 (("ExternalProject_Add\\(libtbb") "message(")
11769 (("ExternalProject_Add\\(libspdlog") "message(")
11770 (("ExternalProject_Add\\(libdivsufsort") "message(")
11771 (("ExternalProject_Add\\(libstadenio") "message(")
11772 (("ExternalProject_Add_Step\\(") "message("))
11774 ;; Ensure that all headers can be found
11775 (setenv "CPLUS_INCLUDE_PATH"
11776 (string-append (getenv "CPLUS_INCLUDE_PATH")
11778 (assoc-ref inputs "bwa")
11781 (assoc-ref inputs "eigen")
11782 "/include/eigen3"))
11784 (string-append (assoc-ref inputs "bwa")
11787 (assoc-ref inputs "eigen")
11788 "/include/eigen3"))
11790 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11791 ;; run. It only exists after the install phase.
11792 (add-after 'unpack 'fix-tests
11794 (substitute* "src/CMakeLists.txt"
11795 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11796 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11800 ("bwa" ,bwa-for-salmon)
11806 (uri (git-reference
11807 (url "https://github.com/COMBINE-lab/RapMap.git")
11808 (commit (string-append "salmon-v" version))))
11809 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11812 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
11813 ("jemalloc" ,jemalloc)
11814 ("jellyfish" ,jellyfish)
11817 ("libdivsufsort" ,libdivsufsort)
11818 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11819 ("spdlog-for-salmon" ,spdlog-for-salmon)
11822 (home-page "https://github.com/COMBINE-lab/salmon")
11823 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11824 (description "Salmon is a program to produce highly-accurate,
11825 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11826 its accuracy and speed via a number of different innovations, including the
11827 use of lightweight alignments (accurate but fast-to-compute proxies for
11828 traditional read alignments) and massively-parallel stochastic collapsed
11829 variational inference.")
11830 (license license:gpl3+)))