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>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
14 ;;; This file is part of GNU Guix.
16 ;;; GNU Guix is free software; you can redistribute it and/or modify it
17 ;;; under the terms of the GNU General Public License as published by
18 ;;; the Free Software Foundation; either version 3 of the License, or (at
19 ;;; your option) any later version.
21 ;;; GNU Guix is distributed in the hope that it will be useful, but
22 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;;; GNU General Public License for more details.
26 ;;; You should have received a copy of the GNU General Public License
27 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
29 (define-module (gnu packages bioinformatics)
30 #:use-module ((guix licenses) #:prefix license:)
31 #:use-module (guix packages)
32 #:use-module (guix utils)
33 #:use-module (guix download)
34 #:use-module (guix git-download)
35 #:use-module (guix hg-download)
36 #:use-module (guix build-system ant)
37 #:use-module (guix build-system gnu)
38 #:use-module (guix build-system cmake)
39 #:use-module (guix build-system ocaml)
40 #:use-module (guix build-system perl)
41 #:use-module (guix build-system python)
42 #:use-module (guix build-system r)
43 #:use-module (guix build-system ruby)
44 #:use-module (guix build-system scons)
45 #:use-module (guix build-system trivial)
46 #:use-module (gnu packages)
47 #:use-module (gnu packages autotools)
48 #:use-module (gnu packages algebra)
49 #:use-module (gnu packages base)
50 #:use-module (gnu packages bash)
51 #:use-module (gnu packages bison)
52 #:use-module (gnu packages boost)
53 #:use-module (gnu packages check)
54 #:use-module (gnu packages compression)
55 #:use-module (gnu packages cpio)
56 #:use-module (gnu packages cran)
57 #:use-module (gnu packages curl)
58 #:use-module (gnu packages documentation)
59 #:use-module (gnu packages databases)
60 #:use-module (gnu packages datastructures)
61 #:use-module (gnu packages file)
62 #:use-module (gnu packages flex)
63 #:use-module (gnu packages gawk)
64 #:use-module (gnu packages gcc)
65 #:use-module (gnu packages gd)
66 #:use-module (gnu packages gtk)
67 #:use-module (gnu packages glib)
68 #:use-module (gnu packages graph)
69 #:use-module (gnu packages groff)
70 #:use-module (gnu packages guile)
71 #:use-module (gnu packages haskell)
72 #:use-module (gnu packages image)
73 #:use-module (gnu packages imagemagick)
74 #:use-module (gnu packages java)
75 #:use-module (gnu packages jemalloc)
76 #:use-module (gnu packages ldc)
77 #:use-module (gnu packages linux)
78 #:use-module (gnu packages logging)
79 #:use-module (gnu packages machine-learning)
80 #:use-module (gnu packages man)
81 #:use-module (gnu packages maths)
82 #:use-module (gnu packages mpi)
83 #:use-module (gnu packages ncurses)
84 #:use-module (gnu packages ocaml)
85 #:use-module (gnu packages pcre)
86 #:use-module (gnu packages parallel)
87 #:use-module (gnu packages pdf)
88 #:use-module (gnu packages perl)
89 #:use-module (gnu packages perl-check)
90 #:use-module (gnu packages pkg-config)
91 #:use-module (gnu packages popt)
92 #:use-module (gnu packages protobuf)
93 #:use-module (gnu packages python)
94 #:use-module (gnu packages python-web)
95 #:use-module (gnu packages readline)
96 #:use-module (gnu packages ruby)
97 #:use-module (gnu packages serialization)
98 #:use-module (gnu packages shells)
99 #:use-module (gnu packages statistics)
100 #:use-module (gnu packages swig)
101 #:use-module (gnu packages tbb)
102 #:use-module (gnu packages tex)
103 #:use-module (gnu packages texinfo)
104 #:use-module (gnu packages textutils)
105 #:use-module (gnu packages time)
106 #:use-module (gnu packages tls)
107 #:use-module (gnu packages vim)
108 #:use-module (gnu packages web)
109 #:use-module (gnu packages xml)
110 #:use-module (gnu packages xorg)
111 #:use-module (srfi srfi-1)
112 #:use-module (ice-9 match))
114 (define-public aragorn
121 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
125 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
126 (build-system gnu-build-system)
128 `(#:tests? #f ; there are no tests
130 (modify-phases %standard-phases
134 (zero? (system* "gcc"
140 (string-append "aragorn" ,version ".c")))))
142 (lambda* (#:key outputs #:allow-other-keys)
143 (let* ((out (assoc-ref outputs "out"))
144 (bin (string-append out "/bin"))
145 (man (string-append out "/share/man/man1")))
147 (install-file "aragorn" bin)
149 (install-file "aragorn.1" man))
151 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
152 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
154 "Aragorn identifies transfer RNA, mitochondrial RNA and
155 transfer-messenger RNA from nucleotide sequences, based on homology to known
156 tRNA consensus sequences and RNA structure. It also outputs the secondary
157 structure of the predicted RNA.")
158 (license license:gpl2)))
166 ;; BamM is not available on pypi.
168 "https://github.com/Ecogenomics/BamM/archive/"
170 (file-name (string-append name "-" version ".tar.gz"))
173 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
174 (modules '((guix build utils)))
177 ;; Delete bundled htslib.
178 (delete-file-recursively "c/htslib-1.3.1")
180 (build-system python-build-system)
182 `(#:python ,python-2 ; BamM is Python 2 only.
183 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
184 ;; been modified from its original form.
186 (let ((htslib (assoc-ref %build-inputs "htslib")))
187 (list "--with-libhts-lib" (string-append htslib "/lib")
188 "--with-libhts-inc" (string-append htslib "/include/htslib")))
190 (modify-phases %standard-phases
191 (add-after 'unpack 'autogen
193 (with-directory-excursion "c"
194 (let ((sh (which "sh")))
195 ;; Use autogen so that 'configure' works.
196 (substitute* "autogen.sh" (("/bin/sh") sh))
197 (setenv "CONFIG_SHELL" sh)
198 (substitute* "configure" (("/bin/sh") sh))
199 (zero? (system* "./autogen.sh"))))))
201 ;; Run tests after installation so compilation only happens once.
203 (add-after 'install 'wrap-executable
204 (lambda* (#:key outputs #:allow-other-keys)
205 (let* ((out (assoc-ref outputs "out"))
206 (path (getenv "PATH")))
207 (wrap-program (string-append out "/bin/bamm")
208 `("PATH" ":" prefix (,path))))
210 (add-after 'wrap-executable 'post-install-check
211 (lambda* (#:key inputs outputs #:allow-other-keys)
213 (string-append (assoc-ref outputs "out")
218 (assoc-ref outputs "out")
220 (string-take (string-take-right
221 (assoc-ref inputs "python") 5) 3)
223 (getenv "PYTHONPATH")))
224 ;; There are 2 errors printed, but they are safe to ignore:
225 ;; 1) [E::hts_open_format] fail to open file ...
226 ;; 2) samtools view: failed to open ...
227 (zero? (system* "nosetests")))))))
229 `(("autoconf" ,autoconf)
230 ("automake" ,automake)
233 ("python-nose" ,python2-nose)
234 ("python-pysam" ,python2-pysam)))
236 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
237 ("samtools" ,samtools)
241 ("coreutils" ,coreutils)))
243 `(("python-numpy" ,python2-numpy)))
244 (home-page "http://ecogenomics.github.io/BamM/")
245 (synopsis "Metagenomics-focused BAM file manipulator")
247 "BamM is a C library, wrapped in python, to efficiently generate and
248 parse BAM files, specifically for the analysis of metagenomic data. For
249 instance, it implements several methods to assess contig-wise read coverage.")
250 (license license:lgpl3+)))
252 (define-public bamtools
259 "https://github.com/pezmaster31/bamtools/archive/v"
261 (file-name (string-append name "-" version ".tar.gz"))
264 "1z3kg24qrwq13a88n9d86izngrar4fll7gr6phddb2faw75pdgaa"))))
265 (build-system cmake-build-system)
267 `(#:tests? #f ;no "check" target
269 (modify-phases %standard-phases
271 'configure 'set-ldflags
272 (lambda* (#:key outputs #:allow-other-keys)
276 (assoc-ref outputs "out") "/lib/bamtools")))))))
277 (inputs `(("zlib" ,zlib)))
278 (home-page "https://github.com/pezmaster31/bamtools")
279 (synopsis "C++ API and command-line toolkit for working with BAM data")
281 "BamTools provides both a C++ API and a command-line toolkit for handling
283 (license license:expat)))
285 (define-public bcftools
292 "https://github.com/samtools/bcftools/releases/download/"
293 version "/bcftools-" version ".tar.bz2"))
296 "1vgw2mwngq20c530zim52zvgmw1lci8rzl33pvh44xqk3xlzvjsa"))
297 (modules '((guix build utils)))
299 ;; Delete bundled htslib.
300 (delete-file-recursively "htslib-1.8")
302 (build-system gnu-build-system)
304 `(#:test-target "test"
305 #:configure-flags (list "--with-htslib=system")
309 "LIBS=-lgsl -lgslcblas"
310 (string-append "prefix=" (assoc-ref %outputs "out"))
311 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
312 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
313 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
314 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
315 (string-append "PACKAGE_VERSION=" ,version))
317 (modify-phases %standard-phases
318 (add-before 'check 'patch-tests
320 (substitute* "test/test.pl"
321 (("/bin/bash") (which "bash")))
329 (home-page "https://samtools.github.io/bcftools/")
330 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
332 "BCFtools is a set of utilities that manipulate variant calls in the
333 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
334 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
335 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
336 (license (list license:gpl3+ license:expat))))
338 (define-public bedops
344 (uri (string-append "https://github.com/bedops/bedops/archive/v"
346 (file-name (string-append name "-" version ".tar.gz"))
349 "0kx4awrwby8f33wqyx8w7ms7v25xhf0d421csgf96a3hfzn2mb0m"))))
350 (build-system gnu-build-system)
353 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
355 (modify-phases %standard-phases
356 (add-after 'unpack 'unpack-tarballs
358 ;; FIXME: Bedops includes tarballs of minimally patched upstream
359 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
360 ;; libraries because at least one of the libraries (zlib) is
361 ;; patched to add a C++ function definition (deflateInit2cpp).
362 ;; Until the Bedops developers offer a way to link against system
363 ;; libraries we have to build the in-tree copies of these three
366 ;; See upstream discussion:
367 ;; https://github.com/bedops/bedops/issues/124
369 ;; Unpack the tarballs to benefit from shebang patching.
370 (with-directory-excursion "third-party"
371 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
372 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
373 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
374 ;; Disable unpacking of tarballs in Makefile.
375 (substitute* "system.mk/Makefile.linux"
376 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
377 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
378 (substitute* "third-party/zlib-1.2.7/Makefile.in"
379 (("^SHELL=.*$") "SHELL=bash\n"))
381 (delete 'configure))))
382 (home-page "https://github.com/bedops/bedops")
383 (synopsis "Tools for high-performance genomic feature operations")
385 "BEDOPS is a suite of tools to address common questions raised in genomic
386 studies---mostly with regard to overlap and proximity relationships between
387 data sets. It aims to be scalable and flexible, facilitating the efficient
388 and accurate analysis and management of large-scale genomic data.
390 BEDOPS provides tools that perform highly efficient and scalable Boolean and
391 other set operations, statistical calculations, archiving, conversion and
392 other management of genomic data of arbitrary scale. Tasks can be easily
393 split by chromosome for distributing whole-genome analyses across a
394 computational cluster.")
395 (license license:gpl2+)))
397 (define-public bedtools
403 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
404 "download/v" version "/"
405 "bedtools-" version ".tar.gz"))
408 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
409 (build-system gnu-build-system)
411 '(#:test-target "test"
413 (list (string-append "prefix=" (assoc-ref %outputs "out")))
415 (modify-phases %standard-phases
416 (delete 'configure))))
417 (native-inputs `(("python" ,python-2)))
419 `(("samtools" ,samtools)
421 (home-page "https://github.com/arq5x/bedtools2")
422 (synopsis "Tools for genome analysis and arithmetic")
424 "Collectively, the bedtools utilities are a swiss-army knife of tools for
425 a wide-range of genomics analysis tasks. The most widely-used tools enable
426 genome arithmetic: that is, set theory on the genome. For example, bedtools
427 allows one to intersect, merge, count, complement, and shuffle genomic
428 intervals from multiple files in widely-used genomic file formats such as BAM,
430 (license license:gpl2)))
432 ;; Later releases of bedtools produce files with more columns than
433 ;; what Ribotaper expects.
434 (define-public bedtools-2.18
435 (package (inherit bedtools)
440 (uri (string-append "https://github.com/arq5x/bedtools2/"
441 "archive/v" version ".tar.gz"))
442 (file-name (string-append name "-" version ".tar.gz"))
445 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
447 '(#:test-target "test"
449 (modify-phases %standard-phases
452 (lambda* (#:key outputs #:allow-other-keys)
453 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
454 (for-each (lambda (file)
455 (install-file file bin))
456 (find-files "bin" ".*")))
459 (define-public ribotaper
465 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
466 "files/RiboTaper/RiboTaper_Version_"
470 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
471 (build-system gnu-build-system)
474 (modify-phases %standard-phases
475 (add-after 'install 'wrap-executables
476 (lambda* (#:key inputs outputs #:allow-other-keys)
477 (let* ((out (assoc-ref outputs "out")))
480 (wrap-program (string-append out "/bin/" script)
481 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
482 '("create_annotations_files.bash"
483 "create_metaplots.bash"
484 "Ribotaper_ORF_find.sh"
485 "Ribotaper.sh"))))))))
487 `(("bedtools" ,bedtools-2.18)
488 ("samtools" ,samtools-0.1)
489 ("r-minimal" ,r-minimal)
490 ("r-foreach" ,r-foreach)
491 ("r-xnomial" ,r-xnomial)
493 ("r-multitaper" ,r-multitaper)
494 ("r-seqinr" ,r-seqinr)))
495 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
496 (synopsis "Define translated ORFs using ribosome profiling data")
498 "Ribotaper is a method for defining translated @dfn{open reading
499 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
500 provides the Ribotaper pipeline.")
501 (license license:gpl3+)))
503 (define-public ribodiff
510 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
511 "archive/v" version ".tar.gz"))
512 (file-name (string-append name "-" version ".tar.gz"))
515 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
516 (build-system python-build-system)
520 (modify-phases %standard-phases
521 ;; Generate an installable executable script wrapper.
522 (add-after 'unpack 'patch-setup.py
524 (substitute* "setup.py"
525 (("^(.*)packages=.*" line prefix)
526 (string-append line "\n"
527 prefix "scripts=['scripts/TE.py'],\n")))
530 `(("python-numpy" ,python2-numpy)
531 ("python-matplotlib" ,python2-matplotlib)
532 ("python-scipy" ,python2-scipy)
533 ("python-statsmodels" ,python2-statsmodels)))
535 `(("python-mock" ,python2-mock)
536 ("python-nose" ,python2-nose)))
537 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
538 (synopsis "Detect translation efficiency changes from ribosome footprints")
539 (description "RiboDiff is a statistical tool that detects the protein
540 translational efficiency change from Ribo-Seq (ribosome footprinting) and
541 RNA-Seq data. It uses a generalized linear model to detect genes showing
542 difference in translational profile taking mRNA abundance into account. It
543 facilitates us to decipher the translational regulation that behave
544 independently with transcriptional regulation.")
545 (license license:gpl3+)))
547 (define-public bioawk
553 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
555 (file-name (string-append name "-" version ".tar.gz"))
557 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
558 (build-system gnu-build-system)
564 `(#:tests? #f ; There are no tests to run.
565 ;; Bison must generate files, before other targets can build.
568 (modify-phases %standard-phases
569 (delete 'configure) ; There is no configure phase.
571 (lambda* (#:key outputs #:allow-other-keys)
572 (let* ((out (assoc-ref outputs "out"))
573 (bin (string-append out "/bin"))
574 (man (string-append out "/share/man/man1")))
576 (copy-file "awk.1" (string-append man "/bioawk.1"))
577 (install-file "bioawk" bin)))))))
578 (home-page "https://github.com/lh3/bioawk")
579 (synopsis "AWK with bioinformatics extensions")
580 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
581 support of several common biological data formats, including optionally gzip'ed
582 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
583 also adds a few built-in functions and a command line option to use TAB as the
584 input/output delimiter. When the new functionality is not used, bioawk is
585 intended to behave exactly the same as the original BWK awk.")
586 (license license:x11)))
588 (define-public python2-pybedtools
590 (name "python2-pybedtools")
595 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
599 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
600 (build-system python-build-system)
601 (arguments `(#:python ,python-2)) ; no Python 3 support
603 `(("python-matplotlib" ,python2-matplotlib)))
605 `(("bedtools" ,bedtools)
606 ("samtools" ,samtools)))
608 `(("python-cython" ,python2-cython)
609 ("python-pyyaml" ,python2-pyyaml)
610 ("python-nose" ,python2-nose)))
611 (home-page "https://pythonhosted.org/pybedtools/")
612 (synopsis "Python wrapper for BEDtools programs")
614 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
615 which are widely used for genomic interval manipulation or \"genome algebra\".
616 pybedtools extends BEDTools by offering feature-level manipulations from with
618 (license license:gpl2+)))
620 (define-public python-biom-format
622 (name "python-biom-format")
627 ;; Use GitHub as source because PyPI distribution does not contain
628 ;; test data: https://github.com/biocore/biom-format/issues/693
629 (uri (string-append "https://github.com/biocore/biom-format/archive/"
631 (file-name (string-append name "-" version ".tar.gz"))
634 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
635 (build-system python-build-system)
637 `(("python-numpy" ,python-numpy)
638 ("python-scipy" ,python-scipy)
639 ("python-future" ,python-future)
640 ("python-click" ,python-click)
641 ("python-h5py" ,python-h5py)
642 ("python-pandas" ,python-pandas)))
644 `(("python-nose" ,python-nose)))
645 (home-page "http://www.biom-format.org")
646 (synopsis "Biological Observation Matrix (BIOM) format utilities")
648 "The BIOM file format is designed to be a general-use format for
649 representing counts of observations e.g. operational taxonomic units, KEGG
650 orthology groups or lipid types, in one or more biological samples
651 e.g. microbiome samples, genomes, metagenomes.")
652 (license license:bsd-3)
653 (properties `((python2-variant . ,(delay python2-biom-format))))))
655 (define-public python2-biom-format
656 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
661 (modify-phases %standard-phases
662 ;; Do not require the unmaintained pyqi library.
663 (add-after 'unpack 'remove-pyqi
665 (substitute* "setup.py"
666 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
668 ,@(package-arguments base))))))
670 (define-public bioperl-minimal
671 (let* ((inputs `(("perl-module-build" ,perl-module-build)
672 ("perl-data-stag" ,perl-data-stag)
673 ("perl-libwww" ,perl-libwww)
674 ("perl-uri" ,perl-uri)))
676 (map (compose package-name cadr)
679 (map (compose package-transitive-target-inputs cadr) inputs))))))
681 (name "bioperl-minimal")
686 (uri (string-append "https://github.com/bioperl/bioperl-live/"
688 (string-map (lambda (c)
694 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
695 (build-system perl-build-system)
698 (modify-phases %standard-phases
700 'install 'wrap-programs
701 (lambda* (#:key outputs #:allow-other-keys)
702 ;; Make sure all executables in "bin" find the required Perl
703 ;; modules at runtime. As the PERL5LIB variable contains also
704 ;; the paths of native inputs, we pick the transitive target
705 ;; inputs from %build-inputs.
706 (let* ((out (assoc-ref outputs "out"))
707 (bin (string-append out "/bin/"))
709 (cons (string-append out "/lib/perl5/site_perl")
711 (assoc-ref %build-inputs name))
712 ',transitive-inputs))
714 (for-each (lambda (file)
716 `("PERL5LIB" ":" prefix (,path))))
717 (find-files bin "\\.pl$"))
721 `(("perl-test-most" ,perl-test-most)))
722 (home-page "http://search.cpan.org/dist/BioPerl")
723 (synopsis "Bioinformatics toolkit")
725 "BioPerl is the product of a community effort to produce Perl code which
726 is useful in biology. Examples include Sequence objects, Alignment objects
727 and database searching objects. These objects not only do what they are
728 advertised to do in the documentation, but they also interact - Alignment
729 objects are made from the Sequence objects, Sequence objects have access to
730 Annotation and SeqFeature objects and databases, Blast objects can be
731 converted to Alignment objects, and so on. This means that the objects
732 provide a coordinated and extensible framework to do computational biology.")
733 (license license:perl-license))))
735 (define-public python-biopython
737 (name "python-biopython")
741 ;; use PyPi rather than biopython.org to ease updating
742 (uri (pypi-uri "biopython" version))
745 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
746 (build-system python-build-system)
749 (modify-phases %standard-phases
750 (add-before 'check 'set-home
751 ;; Some tests require a home directory to be set.
752 (lambda _ (setenv "HOME" "/tmp") #t)))))
754 `(("python-numpy" ,python-numpy)))
755 (home-page "http://biopython.org/")
756 (synopsis "Tools for biological computation in Python")
758 "Biopython is a set of tools for biological computation including parsers
759 for bioinformatics files into Python data structures; interfaces to common
760 bioinformatics programs; a standard sequence class and tools for performing
761 common operations on them; code to perform data classification; code for
762 dealing with alignments; code making it easy to split up parallelizable tasks
763 into separate processes; and more.")
764 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
766 (define-public python2-biopython
767 (package-with-python2 python-biopython))
769 (define-public bpp-core
770 ;; The last release was in 2014 and the recommended way to install from source
771 ;; is to clone the git repository, so we do this.
772 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
773 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
776 (version (string-append "2.2.0-1." (string-take commit 7)))
780 (url "http://biopp.univ-montp2.fr/git/bpp-core")
782 (file-name (string-append name "-" version "-checkout"))
785 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
786 (build-system cmake-build-system)
788 `(#:parallel-build? #f))
790 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
791 ; compile all of the bpp packages with GCC 5.
792 (home-page "http://biopp.univ-montp2.fr")
793 (synopsis "C++ libraries for Bioinformatics")
795 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
796 analysis, phylogenetics, molecular evolution and population genetics. It is
797 Object Oriented and is designed to be both easy to use and computer efficient.
798 Bio++ intends to help programmers to write computer expensive programs, by
799 providing them a set of re-usable tools.")
800 (license license:cecill-c))))
802 (define-public bpp-phyl
803 ;; The last release was in 2014 and the recommended way to install from source
804 ;; is to clone the git repository, so we do this.
805 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
806 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
809 (version (string-append "2.2.0-1." (string-take commit 7)))
813 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
815 (file-name (string-append name "-" version "-checkout"))
818 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
819 (build-system cmake-build-system)
821 `(#:parallel-build? #f
822 ;; If out-of-source, test data is not copied into the build directory
823 ;; so the tests fail.
824 #:out-of-source? #f))
826 `(("bpp-core" ,bpp-core)
828 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
831 (home-page "http://biopp.univ-montp2.fr")
832 (synopsis "Bio++ phylogenetic Library")
834 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
835 analysis, phylogenetics, molecular evolution and population genetics. This
836 library provides phylogenetics-related modules.")
837 (license license:cecill-c))))
839 (define-public bpp-popgen
840 ;; The last release was in 2014 and the recommended way to install from source
841 ;; is to clone the git repository, so we do this.
842 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
843 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
846 (version (string-append "2.2.0-1." (string-take commit 7)))
850 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
852 (file-name (string-append name "-" version "-checkout"))
855 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
856 (build-system cmake-build-system)
858 `(#:parallel-build? #f
859 #:tests? #f)) ; There are no tests.
861 `(("bpp-core" ,bpp-core)
864 (home-page "http://biopp.univ-montp2.fr")
865 (synopsis "Bio++ population genetics library")
867 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
868 analysis, phylogenetics, molecular evolution and population genetics. This
869 library provides population genetics-related modules.")
870 (license license:cecill-c))))
872 (define-public bpp-seq
873 ;; The last release was in 2014 and the recommended way to install from source
874 ;; is to clone the git repository, so we do this.
875 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
876 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
879 (version (string-append "2.2.0-1." (string-take commit 7)))
883 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
885 (file-name (string-append name "-" version "-checkout"))
888 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
889 (build-system cmake-build-system)
891 `(#:parallel-build? #f
892 ;; If out-of-source, test data is not copied into the build directory
893 ;; so the tests fail.
894 #:out-of-source? #f))
896 `(("bpp-core" ,bpp-core)
897 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
898 (home-page "http://biopp.univ-montp2.fr")
899 (synopsis "Bio++ sequence library")
901 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
902 analysis, phylogenetics, molecular evolution and population genetics. This
903 library provides sequence-related modules.")
904 (license license:cecill-c))))
906 (define-public bppsuite
907 ;; The last release was in 2014 and the recommended way to install from source
908 ;; is to clone the git repository, so we do this.
909 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
910 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
913 (version (string-append "2.2.0-1." (string-take commit 7)))
917 (url "http://biopp.univ-montp2.fr/git/bppsuite")
919 (file-name (string-append name "-" version "-checkout"))
922 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
923 (build-system cmake-build-system)
925 `(#:parallel-build? #f
926 #:tests? #f)) ; There are no tests.
930 ("texinfo" ,texinfo)))
932 `(("bpp-core" ,bpp-core)
934 ("bpp-phyl" ,bpp-phyl)
935 ("bpp-phyl" ,bpp-popgen)
937 (home-page "http://biopp.univ-montp2.fr")
938 (synopsis "Bioinformatics tools written with the Bio++ libraries")
940 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
941 analysis, phylogenetics, molecular evolution and population genetics. This
942 package provides command line tools using the Bio++ library.")
943 (license license:cecill-c))))
945 (define-public blast+
952 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
953 version "/ncbi-blast-" version "+-src.tar.gz"))
956 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
957 (patches (search-patches "blast+-fix-makefile.patch"))
958 (modules '((guix build utils)))
961 ;; Remove bundled bzip2, zlib and pcre.
962 (delete-file-recursively "c++/src/util/compress/bzip2")
963 (delete-file-recursively "c++/src/util/compress/zlib")
964 (delete-file-recursively "c++/src/util/regexp")
965 (substitute* "c++/src/util/compress/Makefile.in"
966 (("bzip2 zlib api") "api"))
967 ;; Remove useless msbuild directory
968 (delete-file-recursively
969 "c++/src/build-system/project_tree_builder/msbuild")
971 (build-system gnu-build-system)
973 `(;; There are two(!) tests for this massive library, and both fail with
974 ;; "unparsable timing stats".
975 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
976 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
979 #:parallel-build? #f ; not supported
981 (modify-phases %standard-phases
984 ;; $HOME needs to be set at some point during the configure phase
985 (lambda _ (setenv "HOME" "/tmp") #t))
988 (lambda _ (chdir "c++") #t))
990 'enter-dir 'fix-build-system
993 (cond ((string=? cmd "date")
994 ;; make call to "date" deterministic
999 (format (current-error-port)
1000 "WARNING: Unable to find absolute path for ~s~%"
1004 ;; Rewrite hardcoded paths to various tools
1005 (substitute* (append '("src/build-system/configure.ac"
1006 "src/build-system/configure"
1007 "src/build-system/helpers/run_with_lock.c"
1008 "scripts/common/impl/if_diff.sh"
1009 "scripts/common/impl/run_with_lock.sh"
1010 "src/build-system/Makefile.configurables.real"
1011 "src/build-system/Makefile.in.top"
1012 "src/build-system/Makefile.meta.gmake=no"
1013 "src/build-system/Makefile.meta.in"
1014 "src/build-system/Makefile.meta_l"
1015 "src/build-system/Makefile.meta_p"
1016 "src/build-system/Makefile.meta_r"
1017 "src/build-system/Makefile.mk.in"
1018 "src/build-system/Makefile.requirements"
1019 "src/build-system/Makefile.rules_with_autodep.in")
1020 (find-files "scripts/common/check" "\\.sh$"))
1021 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1022 (or (which* cmd) all)))
1024 (substitute* (find-files "src/build-system" "^config.*")
1025 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1028 ;; rewrite "/var/tmp" in check script
1029 (substitute* "scripts/common/check/check_make_unix.sh"
1030 (("/var/tmp") "/tmp"))
1032 ;; do not reset PATH
1033 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1035 (("action=/bin/") "action=")
1036 (("export PATH") ":"))
1040 (lambda* (#:key inputs outputs #:allow-other-keys)
1041 (let ((out (assoc-ref outputs "out"))
1042 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1043 (include (string-append (assoc-ref outputs "include")
1044 "/include/ncbi-tools++")))
1045 ;; The 'configure' script doesn't recognize things like
1046 ;; '--enable-fast-install'.
1047 (zero? (system* "./configure.orig"
1048 (string-append "--with-build-root=" (getcwd) "/build")
1049 (string-append "--prefix=" out)
1050 (string-append "--libdir=" lib)
1051 (string-append "--includedir=" include)
1052 (string-append "--with-bz2="
1053 (assoc-ref inputs "bzip2"))
1054 (string-append "--with-z="
1055 (assoc-ref inputs "zlib"))
1056 (string-append "--with-pcre="
1057 (assoc-ref inputs "pcre"))
1058 ;; Each library is built twice by default, once
1059 ;; with "-static" in its name, and again
1062 "--with-dll"))))))))
1063 (outputs '("out" ; 21 MB
1071 ("python" ,python-wrapper)))
1074 (home-page "http://blast.ncbi.nlm.nih.gov")
1075 (synopsis "Basic local alignment search tool")
1077 "BLAST is a popular method of performing a DNA or protein sequence
1078 similarity search, using heuristics to produce results quickly. It also
1079 calculates an “expect value” that estimates how many matches would have
1080 occurred at a given score by chance, which can aid a user in judging how much
1081 confidence to have in an alignment.")
1082 ;; Most of the sources are in the public domain, with the following
1085 ;; * ./c++/include/util/bitset/
1086 ;; * ./c++/src/html/ncbi_menu*.js
1088 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1090 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1092 ;; * ./c++/src/corelib/teamcity_*
1093 (license (list license:public-domain
1099 (define-public bless
1105 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1109 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1110 (modules '((guix build utils)))
1113 ;; Remove bundled boost, pigz, zlib, and .git directory
1114 ;; FIXME: also remove bundled sources for murmurhash3 and
1115 ;; kmc once packaged.
1116 (delete-file-recursively "boost")
1117 (delete-file-recursively "pigz")
1118 (delete-file-recursively "google-sparsehash")
1119 (delete-file-recursively "zlib")
1120 (delete-file-recursively ".git")
1122 (build-system gnu-build-system)
1124 '(#:tests? #f ;no "check" target
1126 (list (string-append "ZLIB="
1127 (assoc-ref %build-inputs "zlib")
1129 (string-append "LDFLAGS="
1130 (string-join '("-lboost_filesystem"
1137 (modify-phases %standard-phases
1138 (add-after 'unpack 'do-not-build-bundled-pigz
1139 (lambda* (#:key inputs outputs #:allow-other-keys)
1140 (substitute* "Makefile"
1141 (("cd pigz/pigz-2.3.3; make") ""))
1143 (add-after 'unpack 'patch-paths-to-executables
1144 (lambda* (#:key inputs outputs #:allow-other-keys)
1145 (substitute* "parse_args.cpp"
1146 (("kmc_binary = .*")
1147 (string-append "kmc_binary = \""
1148 (assoc-ref outputs "out")
1150 (("pigz_binary = .*")
1151 (string-append "pigz_binary = \""
1152 (assoc-ref inputs "pigz")
1156 (lambda* (#:key outputs #:allow-other-keys)
1157 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1158 (for-each (lambda (file)
1159 (install-file file bin))
1160 '("bless" "kmc/bin/kmc"))
1162 (delete 'configure))))
1166 `(("openmpi" ,openmpi)
1168 ("sparsehash" ,sparsehash)
1171 (supported-systems '("x86_64-linux"))
1172 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1173 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1175 "@dfn{Bloom-filter-based error correction solution for high-throughput
1176 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1177 correction tool for genomic reads produced by @dfn{Next-generation
1178 sequencing} (NGS). BLESS produces accurate correction results with much less
1179 memory compared with previous solutions and is also able to tolerate a higher
1180 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1181 errors at the end of reads.")
1182 (license license:gpl3+)))
1184 (define-public bowtie
1190 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1192 (file-name (string-append name "-" version ".tar.gz"))
1195 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1196 (modules '((guix build utils)))
1199 (substitute* "Makefile"
1200 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1201 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1202 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1204 (build-system gnu-build-system)
1207 ("perl-clone" ,perl-clone)
1208 ("perl-test-deep" ,perl-test-deep)
1209 ("perl-test-simple" ,perl-test-simple)
1210 ("python" ,python-2)
1217 (string-append "prefix=" (assoc-ref %outputs "out")))
1219 (modify-phases %standard-phases
1222 (lambda* (#:key outputs #:allow-other-keys)
1223 (zero? (system* "perl"
1224 "scripts/test/simple_tests.pl"
1225 "--bowtie2=./bowtie2"
1226 "--bowtie2-build=./bowtie2-build")))))))
1227 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1228 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1230 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1231 reads to long reference sequences. It is particularly good at aligning reads
1232 of about 50 up to 100s or 1,000s of characters, and particularly good at
1233 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1234 genome with an FM Index to keep its memory footprint small: for the human
1235 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1236 gapped, local, and paired-end alignment modes.")
1237 (supported-systems '("x86_64-linux"))
1238 (license license:gpl3+)))
1240 (define-public tophat
1247 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1251 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1252 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1253 (modules '((guix build utils)))
1256 ;; Remove bundled SeqAn and samtools
1257 (delete-file-recursively "src/SeqAn-1.3")
1258 (delete-file-recursively "src/samtools-0.1.18")
1260 (build-system gnu-build-system)
1262 '(#:parallel-build? #f ; not supported
1264 (modify-phases %standard-phases
1265 (add-after 'unpack 'use-system-samtools
1266 (lambda* (#:key inputs #:allow-other-keys)
1267 (substitute* "src/Makefile.in"
1268 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1269 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1270 (("SAMPROG = samtools_0\\.1\\.18") "")
1271 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1272 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1273 (substitute* '("src/common.cpp"
1275 (("samtools_0.1.18") (which "samtools")))
1276 (substitute* '("src/common.h"
1277 "src/bam2fastx.cpp")
1278 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1279 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1280 (substitute* '("src/bwt_map.h"
1282 "src/align_status.h")
1283 (("#include <bam.h>") "#include <samtools/bam.h>")
1284 (("#include <sam.h>") "#include <samtools/sam.h>"))
1289 ("samtools" ,samtools-0.1)
1290 ("ncurses" ,ncurses)
1291 ("python" ,python-2)
1295 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1296 (synopsis "Spliced read mapper for RNA-Seq data")
1298 "TopHat is a fast splice junction mapper for nucleotide sequence
1299 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1300 mammalian-sized genomes using the ultra high-throughput short read
1301 aligner Bowtie, and then analyzes the mapping results to identify
1302 splice junctions between exons.")
1303 ;; TopHat is released under the Boost Software License, Version 1.0
1304 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1305 (license license:boost1.0)))
1314 "https://github.com/lh3/bwa/releases/download/v"
1315 version "/bwa-" version ".tar.bz2"))
1318 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1319 (build-system gnu-build-system)
1321 '(#:tests? #f ;no "check" target
1323 (modify-phases %standard-phases
1325 (lambda* (#:key outputs #:allow-other-keys)
1326 (let ((bin (string-append
1327 (assoc-ref outputs "out") "/bin"))
1329 (assoc-ref outputs "out") "/share/doc/bwa"))
1331 (assoc-ref outputs "out") "/share/man/man1")))
1332 (install-file "bwa" bin)
1333 (install-file "README.md" doc)
1334 (install-file "bwa.1" man))
1336 ;; no "configure" script
1337 (delete 'configure))))
1338 (inputs `(("zlib" ,zlib)))
1339 ;; Non-portable SSE instructions are used so building fails on platforms
1340 ;; other than x86_64.
1341 (supported-systems '("x86_64-linux"))
1342 (home-page "http://bio-bwa.sourceforge.net/")
1343 (synopsis "Burrows-Wheeler sequence aligner")
1345 "BWA is a software package for mapping low-divergent sequences against a
1346 large reference genome, such as the human genome. It consists of three
1347 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1348 designed for Illumina sequence reads up to 100bp, while the rest two for
1349 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1350 features such as long-read support and split alignment, but BWA-MEM, which is
1351 the latest, is generally recommended for high-quality queries as it is faster
1352 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1353 70-100bp Illumina reads.")
1354 (license license:gpl3+)))
1356 (define-public bwa-pssm
1357 (package (inherit bwa)
1362 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1363 "archive/" version ".tar.gz"))
1364 (file-name (string-append name "-" version ".tar.gz"))
1367 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1368 (build-system gnu-build-system)
1373 (home-page "http://bwa-pssm.binf.ku.dk/")
1374 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1376 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1377 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1378 existing aligners it is fast and sensitive. Unlike most other aligners,
1379 however, it is also adaptible in the sense that one can direct the alignment
1380 based on known biases within the data set. It is coded as a modification of
1381 the original BWA alignment program and shares the genome index structure as
1382 well as many of the command line options.")
1383 (license license:gpl3+)))
1385 (define-public python2-bx-python
1387 (name "python2-bx-python")
1391 (uri (pypi-uri "bx-python" version))
1394 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1395 (modules '((guix build utils)))
1398 (substitute* "setup.py"
1399 ;; remove dependency on outdated "distribute" module
1400 (("^from distribute_setup import use_setuptools") "")
1401 (("^use_setuptools\\(\\)") ""))
1403 (build-system python-build-system)
1405 `(#:tests? #f ;tests fail because test data are not included
1406 #:python ,python-2))
1408 `(("python-numpy" ,python2-numpy)
1411 `(("python-nose" ,python2-nose)))
1412 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1413 (synopsis "Tools for manipulating biological data")
1415 "bx-python provides tools for manipulating biological data, particularly
1416 multiple sequence alignments.")
1417 (license license:expat)))
1419 (define-public python-pysam
1421 (name "python-pysam")
1425 ;; Test data is missing on PyPi.
1427 "https://github.com/pysam-developers/pysam/archive/v"
1429 (file-name (string-append name "-" version ".tar.gz"))
1432 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1433 (modules '((guix build utils)))
1435 ;; Drop bundled htslib. TODO: Also remove samtools
1437 (delete-file-recursively "htslib")
1439 (build-system python-build-system)
1441 `(#:modules ((ice-9 ftw)
1443 (guix build python-build-system)
1446 (modify-phases %standard-phases
1447 (add-before 'build 'set-flags
1448 (lambda* (#:key inputs #:allow-other-keys)
1449 (setenv "HTSLIB_MODE" "external")
1450 (setenv "HTSLIB_LIBRARY_DIR"
1451 (string-append (assoc-ref inputs "htslib") "/lib"))
1452 (setenv "HTSLIB_INCLUDE_DIR"
1453 (string-append (assoc-ref inputs "htslib") "/include"))
1454 (setenv "LDFLAGS" "-lncurses")
1455 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1458 (lambda* (#:key inputs outputs #:allow-other-keys)
1459 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1460 (setenv "PYTHONPATH"
1462 (getenv "PYTHONPATH")
1463 ":" (getcwd) "/build/"
1464 (car (scandir "build"
1465 (negate (cut string-prefix? "." <>))))))
1466 ;; Step out of source dir so python does not import from CWD.
1467 (with-directory-excursion "tests"
1468 (setenv "HOME" "/tmp")
1469 (and (zero? (system* "make" "-C" "pysam_data"))
1470 (zero? (system* "make" "-C" "cbcf_data"))
1471 ;; Running nosetests without explicitly asking for a
1472 ;; single process leads to a crash. Running with multiple
1473 ;; processes fails because the tests are not designed to
1476 ;; FIXME: tests keep timing out on some systems.
1477 ;; (zero? (system* "nosetests" "-v"
1478 ;; "--processes" "1"))
1481 `(("htslib" ,htslib))) ; Included from installed header files.
1483 `(("ncurses" ,ncurses)
1486 `(("python-cython" ,python-cython)
1487 ;; Dependencies below are are for tests only.
1488 ("samtools" ,samtools)
1489 ("bcftools" ,bcftools)
1490 ("python-nose" ,python-nose)))
1491 (home-page "https://github.com/pysam-developers/pysam")
1492 (synopsis "Python bindings to the SAMtools C API")
1494 "Pysam is a Python module for reading and manipulating files in the
1495 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1496 also includes an interface for tabix.")
1497 (license license:expat)))
1499 (define-public python2-pysam
1500 (package-with-python2 python-pysam))
1502 (define-public python-twobitreader
1504 (name "python-twobitreader")
1508 (uri (pypi-uri "twobitreader" version))
1511 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1512 (build-system python-build-system)
1514 '(;; Tests are not distributed in the PyPi release.
1515 ;; TODO Try building from the Git repo or asking the upstream maintainer
1516 ;; to distribute the tests on PyPi.
1519 `(("python-sphinx" ,python-sphinx)))
1520 (home-page "https://github.com/benjschiller/twobitreader")
1521 (synopsis "Python library for reading .2bit files")
1523 "twobitreader is a Python library for reading .2bit files as used by the
1524 UCSC genome browser.")
1525 (license license:artistic2.0)))
1527 (define-public python2-twobitreader
1528 (package-with-python2 python-twobitreader))
1530 (define-public python-plastid
1532 (name "python-plastid")
1536 (uri (pypi-uri "plastid" version))
1539 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1540 (build-system python-build-system)
1542 ;; Some test files are not included.
1545 `(("python-numpy" ,python-numpy)
1546 ("python-scipy" ,python-scipy)
1547 ("python-pandas" ,python-pandas)
1548 ("python-pysam" ,python-pysam)
1549 ("python-matplotlib" ,python-matplotlib)
1550 ("python-biopython" ,python-biopython)
1551 ("python-twobitreader" ,python-twobitreader)
1552 ("python-termcolor" ,python-termcolor)))
1554 `(("python-cython" ,python-cython)
1555 ("python-nose" ,python-nose)))
1556 (home-page "https://github.com/joshuagryphon/plastid")
1557 (synopsis "Python library for genomic analysis")
1559 "plastid is a Python library for genomic analysis – in particular,
1560 high-throughput sequencing data – with an emphasis on simplicity.")
1561 (license license:bsd-3)))
1563 (define-public python2-plastid
1564 (package-with-python2 python-plastid))
1566 (define-public cd-hit
1572 (uri (string-append "https://github.com/weizhongli/cdhit"
1573 "/releases/download/V" version
1575 "-2017-0621-source.tar.gz"))
1578 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1579 (build-system gnu-build-system)
1581 `(#:tests? #f ; there are no tests
1583 ;; Executables are copied directly to the PREFIX.
1584 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1586 (modify-phases %standard-phases
1587 ;; No "configure" script
1589 ;; Remove sources of non-determinism
1590 (add-after 'unpack 'be-timeless
1592 (substitute* "cdhit-utility.c++"
1593 ((" \\(built on \" __DATE__ \"\\)") ""))
1594 (substitute* "cdhit-common.c++"
1595 (("__DATE__") "\"0\"")
1596 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1598 ;; The "install" target does not create the target directory.
1599 (add-before 'install 'create-target-dir
1600 (lambda* (#:key outputs #:allow-other-keys)
1601 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1605 (home-page "http://weizhongli-lab.org/cd-hit/")
1606 (synopsis "Cluster and compare protein or nucleotide sequences")
1608 "CD-HIT is a program for clustering and comparing protein or nucleotide
1609 sequences. CD-HIT is designed to be fast and handle extremely large
1611 ;; The manual says: "It can be copied under the GNU General Public License
1612 ;; version 2 (GPLv2)."
1613 (license license:gpl2)))
1615 (define-public clipper
1622 "https://github.com/YeoLab/clipper/archive/"
1624 (file-name (string-append name "-" version ".tar.gz"))
1627 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1628 (modules '((guix build utils)))
1631 ;; remove unnecessary setup dependency
1632 (substitute* "setup.py"
1633 (("setup_requires = .*") ""))
1634 (for-each delete-file
1635 '("clipper/src/peaks.so"
1636 "clipper/src/readsToWiggle.so"))
1637 (delete-file-recursively "dist/")
1639 (build-system python-build-system)
1640 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1642 `(("htseq" ,python2-htseq)
1643 ("python-pybedtools" ,python2-pybedtools)
1644 ("python-cython" ,python2-cython)
1645 ("python-scikit-learn" ,python2-scikit-learn)
1646 ("python-matplotlib" ,python2-matplotlib)
1647 ("python-pandas" ,python2-pandas)
1648 ("python-pysam" ,python2-pysam)
1649 ("python-numpy" ,python2-numpy)
1650 ("python-scipy" ,python2-scipy)))
1652 `(("python-mock" ,python2-mock) ; for tests
1653 ("python-nose" ,python2-nose) ; for tests
1654 ("python-pytz" ,python2-pytz))) ; for tests
1655 (home-page "https://github.com/YeoLab/clipper")
1656 (synopsis "CLIP peak enrichment recognition")
1658 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1659 (license license:gpl2)))
1661 (define-public codingquarry
1663 (name "codingquarry")
1668 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1672 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1673 (build-system gnu-build-system)
1675 '(#:tests? #f ; no "check" target
1677 (modify-phases %standard-phases
1680 (lambda* (#:key outputs #:allow-other-keys)
1681 (let* ((out (assoc-ref outputs "out"))
1682 (bin (string-append out "/bin"))
1683 (doc (string-append out "/share/doc/codingquarry")))
1684 (install-file "INSTRUCTIONS.pdf" doc)
1685 (copy-recursively "QuarryFiles"
1686 (string-append out "/QuarryFiles"))
1687 (install-file "CodingQuarry" bin)
1688 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1689 (inputs `(("openmpi" ,openmpi)))
1690 (native-search-paths
1691 (list (search-path-specification
1692 (variable "QUARRY_PATH")
1693 (files '("QuarryFiles")))))
1694 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1695 (synopsis "Fungal gene predictor")
1696 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1697 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1698 (home-page "https://sourceforge.net/projects/codingquarry/")
1699 (license license:gpl3+)))
1701 (define-public couger
1708 "http://couger.oit.duke.edu/static/assets/COUGER"
1712 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1713 (build-system gnu-build-system)
1717 (modify-phases %standard-phases
1722 (lambda* (#:key outputs #:allow-other-keys)
1723 (let* ((out (assoc-ref outputs "out"))
1724 (bin (string-append out "/bin")))
1725 (copy-recursively "src" (string-append out "/src"))
1727 ;; Add "src" directory to module lookup path.
1728 (substitute* "couger"
1730 (string-append "import sys\nsys.path.append(\""
1731 out "\")\nfrom argparse")))
1732 (install-file "couger" bin))
1735 'install 'wrap-program
1736 (lambda* (#:key inputs outputs #:allow-other-keys)
1737 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1738 (let* ((out (assoc-ref outputs "out"))
1739 (path (getenv "PYTHONPATH")))
1740 (wrap-program (string-append out "/bin/couger")
1741 `("PYTHONPATH" ":" prefix (,path))))
1744 `(("python" ,python-2)
1745 ("python2-pillow" ,python2-pillow)
1746 ("python2-numpy" ,python2-numpy)
1747 ("python2-scipy" ,python2-scipy)
1748 ("python2-matplotlib" ,python2-matplotlib)))
1750 `(("r-minimal" ,r-minimal)
1752 ("randomjungle" ,randomjungle)))
1754 `(("unzip" ,unzip)))
1755 (home-page "http://couger.oit.duke.edu")
1756 (synopsis "Identify co-factors in sets of genomic regions")
1758 "COUGER can be applied to any two sets of genomic regions bound by
1759 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1760 putative co-factors that provide specificity to each TF. The framework
1761 determines the genomic targets uniquely-bound by each TF, and identifies a
1762 small set of co-factors that best explain the in vivo binding differences
1763 between the two TFs.
1765 COUGER uses classification algorithms (support vector machines and random
1766 forests) with features that reflect the DNA binding specificities of putative
1767 co-factors. The features are generated either from high-throughput TF-DNA
1768 binding data (from protein binding microarray experiments), or from large
1769 collections of DNA motifs.")
1770 (license license:gpl3+)))
1772 (define-public clustal-omega
1774 (name "clustal-omega")
1778 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1782 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1783 (build-system gnu-build-system)
1785 `(("argtable" ,argtable)))
1786 (home-page "http://www.clustal.org/omega/")
1787 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1789 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1790 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1791 of handling data-sets of hundreds of thousands of sequences in reasonable
1793 (license license:gpl2+)))
1795 (define-public crossmap
1801 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1805 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1806 ;; This patch has been sent upstream already and is available
1807 ;; for download from Sourceforge, but it has not been merged.
1808 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1809 (modules '((guix build utils)))
1811 ;; remove bundled copy of pysam
1812 (delete-file-recursively "lib/pysam")
1814 (build-system python-build-system)
1816 `(#:python ,python-2
1818 (modify-phases %standard-phases
1819 (add-after 'unpack 'set-env
1820 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1822 `(("python-numpy" ,python2-numpy)
1823 ("python-pysam" ,python2-pysam)
1826 `(("python-cython" ,python2-cython)
1827 ("python-nose" ,python2-nose)))
1828 (home-page "http://crossmap.sourceforge.net/")
1829 (synopsis "Convert genome coordinates between assemblies")
1831 "CrossMap is a program for conversion of genome coordinates or annotation
1832 files between different genome assemblies. It supports most commonly used
1833 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1834 (license license:gpl2+)))
1836 (define-public cutadapt
1843 (url "https://github.com/marcelm/cutadapt.git")
1844 (commit (string-append "v" version))))
1845 (file-name (string-append name "-" version "-checkout"))
1848 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1849 (build-system python-build-system)
1851 `(("python-xopen" ,python-xopen)))
1853 `(("python-cython" ,python-cython)
1854 ("python-pytest" ,python-pytest)))
1855 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1856 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1858 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1859 other types of unwanted sequence from high-throughput sequencing reads.")
1860 (license license:expat)))
1862 (define-public libbigwig
1868 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1869 "archive/" version ".tar.gz"))
1870 (file-name (string-append name "-" version ".tar.gz"))
1873 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1874 (build-system gnu-build-system)
1876 `(#:test-target "test"
1879 (string-append "prefix=" (assoc-ref %outputs "out")))
1881 (modify-phases %standard-phases
1883 (add-before 'check 'disable-curl-test
1885 (substitute* "Makefile"
1886 (("./test/testRemote.*") ""))
1888 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1889 ;; there has not yet been a release containing this change.
1890 (add-before 'install 'create-target-dirs
1891 (lambda* (#:key outputs #:allow-other-keys)
1892 (let ((out (assoc-ref outputs "out")))
1893 (mkdir-p (string-append out "/lib"))
1894 (mkdir-p (string-append out "/include"))
1900 `(("doxygen" ,doxygen)))
1901 (home-page "https://github.com/dpryan79/libBigWig")
1902 (synopsis "C library for handling bigWig files")
1904 "This package provides a C library for parsing local and remote BigWig
1906 (license license:expat)))
1908 (define-public python-pybigwig
1910 (name "python-pybigwig")
1914 (uri (pypi-uri "pyBigWig" version))
1917 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1918 (modules '((guix build utils)))
1921 ;; Delete bundled libBigWig sources
1922 (delete-file-recursively "libBigWig")
1924 (build-system python-build-system)
1927 (modify-phases %standard-phases
1928 (add-after 'unpack 'link-with-libBigWig
1929 (lambda* (#:key inputs #:allow-other-keys)
1930 (substitute* "setup.py"
1931 (("libs=\\[") "libs=[\"BigWig\", "))
1934 `(("libbigwig" ,libbigwig)
1937 (home-page "https://github.com/dpryan79/pyBigWig")
1938 (synopsis "Access bigWig files in Python using libBigWig")
1940 "This package provides Python bindings to the libBigWig library for
1941 accessing bigWig files.")
1942 (license license:expat)))
1944 (define-public python2-pybigwig
1945 (package-with-python2 python-pybigwig))
1947 (define-public python-dendropy
1949 (name "python-dendropy")
1954 (uri (pypi-uri "DendroPy" version))
1957 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1958 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1959 (build-system python-build-system)
1960 (home-page "http://packages.python.org/DendroPy/")
1961 (synopsis "Library for phylogenetics and phylogenetic computing")
1963 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1964 writing, simulation, processing and manipulation of phylogenetic
1965 trees (phylogenies) and characters.")
1966 (license license:bsd-3)
1967 (properties `((python2-variant . ,(delay python2-dendropy))))))
1969 (define-public python2-dendropy
1970 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1974 `(#:python ,python-2
1976 (modify-phases %standard-phases
1978 ;; There is currently a test failure that only happens on some
1979 ;; systems, and only using "setup.py test"
1980 (lambda _ (zero? (system* "nosetests")))))))
1981 (native-inputs `(("python2-nose" ,python2-nose)
1982 ,@(package-native-inputs base))))))
1984 (define-public python-py2bit
1986 (name "python-py2bit")
1991 (uri (pypi-uri "py2bit" version))
1994 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
1995 (build-system python-build-system)
1996 (home-page "https://github.com/dpryan79/py2bit")
1997 (synopsis "Access 2bit files using lib2bit")
1999 "This package provides Python bindings for lib2bit to access 2bit files
2001 (license license:expat)))
2003 (define-public deeptools
2009 (uri (string-append "https://github.com/deeptools/deepTools/"
2010 "archive/" version ".tar.gz"))
2011 (file-name (string-append name "-" version ".tar.gz"))
2014 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2015 (build-system python-build-system)
2017 `(("python-scipy" ,python-scipy)
2018 ("python-numpy" ,python-numpy)
2019 ("python-numpydoc" ,python-numpydoc)
2020 ("python-matplotlib" ,python-matplotlib)
2021 ("python-pysam" ,python-pysam)
2022 ("python-py2bit" ,python-py2bit)
2023 ("python-pybigwig" ,python-pybigwig)))
2025 `(("python-mock" ,python-mock) ;for tests
2026 ("python-nose" ,python-nose) ;for tests
2027 ("python-pytz" ,python-pytz))) ;for tests
2028 (home-page "https://github.com/deeptools/deepTools")
2029 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2031 "DeepTools addresses the challenge of handling the large amounts of data
2032 that are now routinely generated from DNA sequencing centers. To do so,
2033 deepTools contains useful modules to process the mapped reads data to create
2034 coverage files in standard bedGraph and bigWig file formats. By doing so,
2035 deepTools allows the creation of normalized coverage files or the comparison
2036 between two files (for example, treatment and control). Finally, using such
2037 normalized and standardized files, multiple visualizations can be created to
2038 identify enrichments with functional annotations of the genome.")
2039 (license license:gpl3+)))
2041 (define-public delly
2048 "https://github.com/tobiasrausch/delly/archive/v"
2050 (file-name (string-append name "-" version ".tar.gz"))
2052 (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj"))
2053 (patches (search-patches "delly-use-system-libraries.patch"))))
2054 (build-system gnu-build-system)
2056 `(#:tests? #f ; There are no tests to run.
2057 #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time.
2059 (modify-phases %standard-phases
2060 (delete 'configure) ; There is no configure phase.
2063 (let ((bin (string-append (assoc-ref %outputs "out") "/bin"))
2064 (templates (string-append (assoc-ref %outputs "out")
2065 "/share/delly/templates")))
2068 (copy-recursively "excludeTemplates" templates)
2069 (install-file "src/cov" bin)
2070 (install-file "src/delly" bin)
2071 (install-file "src/dpe" bin)))))))
2073 `(("python" ,python-2)))
2079 (home-page "https://github.com/tobiasrausch/delly")
2080 (synopsis "Integrated structural variant prediction method")
2081 (description "Delly is an integrated structural variant prediction method
2082 that can discover and genotype deletions, tandem duplications, inversions and
2083 translocations at single-nucleotide resolution in short-read massively parallel
2084 sequencing data. It uses paired-ends and split-reads to sensitively and
2085 accurately delineate genomic rearrangements throughout the genome.")
2086 (license license:gpl3+)))
2088 (define-public diamond
2095 "https://github.com/bbuchfink/diamond/archive/v"
2097 (file-name (string-append name "-" version ".tar.gz"))
2100 "0adp87r9ak63frdrdmrdfhsn6g0jnnyq1lr2wibvqbxcl37iir9m"))))
2101 (build-system cmake-build-system)
2103 '(#:tests? #f ; no "check" target
2105 (modify-phases %standard-phases
2106 (add-after 'unpack 'remove-native-compilation
2108 (substitute* "CMakeLists.txt" (("-march=native") ""))
2112 (home-page "https://github.com/bbuchfink/diamond")
2113 (synopsis "Accelerated BLAST compatible local sequence aligner")
2115 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2116 translated DNA query sequences against a protein reference database (BLASTP
2117 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2118 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2119 data and settings.")
2120 (license license:agpl3+)))
2122 (define-public discrover
2129 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2131 (file-name (string-append name "-" version ".tar.gz"))
2134 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2135 (build-system cmake-build-system)
2137 `(#:tests? #f ; there are no tests
2139 (modify-phases %standard-phases
2140 (add-after 'unpack 'add-missing-includes
2142 (substitute* "src/executioninformation.hpp"
2143 (("#define EXECUTIONINFORMATION_HPP" line)
2144 (string-append line "\n#include <random>")))
2145 (substitute* "src/plasma/fasta.hpp"
2146 (("#define FASTA_HPP" line)
2147 (string-append line "\n#include <random>")))
2153 `(("texlive" ,texlive)
2154 ("imagemagick" ,imagemagick)))
2155 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2156 (synopsis "Discover discriminative nucleotide sequence motifs")
2157 (description "Discrover is a motif discovery method to find binding sites
2158 of nucleic acid binding proteins.")
2159 (license license:gpl3+)))
2161 (define-public eigensoft
2162 (let ((revision "1")
2163 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2166 (version (string-append "6.1.2-"
2168 (string-take commit 9)))
2173 (url "https://github.com/DReichLab/EIG.git")
2175 (file-name (string-append "eigensoft-" commit "-checkout"))
2178 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2179 (modules '((guix build utils)))
2180 ;; Remove pre-built binaries.
2182 (delete-file-recursively "bin")
2185 (build-system gnu-build-system)
2187 `(#:tests? #f ; There are no tests.
2188 #:make-flags '("CC=gcc")
2190 (modify-phases %standard-phases
2191 ;; There is no configure phase, but the Makefile is in a
2196 ;; The link flags are incomplete.
2197 (substitute* "Makefile"
2198 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2200 ;; The provided install target only copies executables to
2201 ;; the "bin" directory in the build root.
2202 (add-after 'install 'actually-install
2203 (lambda* (#:key outputs #:allow-other-keys)
2204 (let* ((out (assoc-ref outputs "out"))
2205 (bin (string-append out "/bin")))
2206 (for-each (lambda (file)
2207 (install-file file bin))
2208 (find-files "../bin" ".*"))
2213 ("openblas" ,openblas)
2215 ("gfortran" ,gfortran "lib")))
2216 (home-page "https://github.com/DReichLab/EIG")
2217 (synopsis "Tools for population genetics")
2218 (description "The EIGENSOFT package provides tools for population
2219 genetics and stratification correction. EIGENSOFT implements methods commonly
2220 used in population genetics analyses such as PCA, computation of Tracy-Widom
2221 statistics, and finding related individuals in structured populations. It
2222 comes with a built-in plotting script and supports multiple file formats and
2223 quantitative phenotypes.")
2224 ;; The license of the eigensoft tools is Expat, but since it's
2225 ;; linking with the GNU Scientific Library (GSL) the effective
2226 ;; license is the GPL.
2227 (license license:gpl3+))))
2229 (define-public edirect
2235 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2236 "versions/2016-05-03/edirect.tar.gz"))
2239 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2240 (build-system perl-build-system)
2242 `(#:tests? #f ;no "check" target
2244 (modify-phases %standard-phases
2248 (lambda* (#:key outputs #:allow-other-keys)
2249 (let ((target (string-append (assoc-ref outputs "out")
2252 (install-file "edirect.pl" target)
2255 'install 'wrap-program
2256 (lambda* (#:key inputs outputs #:allow-other-keys)
2257 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2258 (let* ((out (assoc-ref outputs "out"))
2259 (path (getenv "PERL5LIB")))
2260 (wrap-program (string-append out "/bin/edirect.pl")
2261 `("PERL5LIB" ":" prefix (,path)))))))))
2263 `(("perl-html-parser" ,perl-html-parser)
2264 ("perl-encode-locale" ,perl-encode-locale)
2265 ("perl-file-listing" ,perl-file-listing)
2266 ("perl-html-tagset" ,perl-html-tagset)
2267 ("perl-html-tree" ,perl-html-tree)
2268 ("perl-http-cookies" ,perl-http-cookies)
2269 ("perl-http-date" ,perl-http-date)
2270 ("perl-http-message" ,perl-http-message)
2271 ("perl-http-negotiate" ,perl-http-negotiate)
2272 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2273 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2274 ("perl-net-http" ,perl-net-http)
2275 ("perl-uri" ,perl-uri)
2276 ("perl-www-robotrules" ,perl-www-robotrules)
2278 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2279 (synopsis "Tools for accessing the NCBI's set of databases")
2281 "Entrez Direct (EDirect) is a method for accessing the National Center
2282 for Biotechnology Information's (NCBI) set of interconnected
2283 databases (publication, sequence, structure, gene, variation, expression,
2284 etc.) from a terminal. Functions take search terms from command-line
2285 arguments. Individual operations are combined to build multi-step queries.
2286 Record retrieval and formatting normally complete the process.
2288 EDirect also provides an argument-driven function that simplifies the
2289 extraction of data from document summaries or other results that are returned
2290 in structured XML format. This can eliminate the need for writing custom
2291 software to answer ad hoc questions.")
2292 (license license:public-domain)))
2294 (define-public exonerate
2303 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2304 "exonerate-" version ".tar.gz"))
2307 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2308 (build-system gnu-build-system)
2310 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2312 `(("pkg-config" ,pkg-config)))
2316 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2317 (synopsis "Generic tool for biological sequence alignment")
2319 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2320 the alignment of sequences using a many alignment models, either exhaustive
2321 dynamic programming or a variety of heuristics.")
2322 (license license:gpl3)))
2324 (define-public express
2332 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2333 version "/express-" version "-src.tgz"))
2336 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2337 (build-system cmake-build-system)
2339 `(#:tests? #f ;no "check" target
2341 (modify-phases %standard-phases
2342 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2343 (lambda* (#:key inputs #:allow-other-keys)
2344 (substitute* "CMakeLists.txt"
2345 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2346 "set(Boost_USE_STATIC_LIBS OFF)")
2347 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2348 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2349 (substitute* "src/CMakeLists.txt"
2350 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2351 (string-append (assoc-ref inputs "bamtools") "/lib"))
2352 (("libprotobuf.a") "libprotobuf.so"))
2356 ("bamtools" ,bamtools)
2357 ("protobuf" ,protobuf)
2359 (home-page "http://bio.math.berkeley.edu/eXpress")
2360 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2362 "eXpress is a streaming tool for quantifying the abundances of a set of
2363 target sequences from sampled subsequences. Example applications include
2364 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2365 analysis (from RNA-Seq), transcription factor binding quantification in
2366 ChIP-Seq, and analysis of metagenomic data.")
2367 (license license:artistic2.0)))
2369 (define-public express-beta-diversity
2371 (name "express-beta-diversity")
2377 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2379 (file-name (string-append name "-" version ".tar.gz"))
2382 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2383 (build-system gnu-build-system)
2386 (modify-phases %standard-phases
2388 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2390 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2392 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2394 (lambda* (#:key outputs #:allow-other-keys)
2395 (let ((bin (string-append (assoc-ref outputs "out")
2398 (install-file "scripts/convertToEBD.py" bin)
2399 (install-file "bin/ExpressBetaDiversity" bin)
2402 `(("python" ,python-2)))
2403 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2404 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2406 "Express Beta Diversity (EBD) calculates ecological beta diversity
2407 (dissimilarity) measures between biological communities. EBD implements a
2408 variety of diversity measures including those that make use of phylogenetic
2409 similarity of community members.")
2410 (license license:gpl3+)))
2412 (define-public fasttree
2419 "http://www.microbesonline.org/fasttree/FastTree-"
2423 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2424 (build-system gnu-build-system)
2426 `(#:tests? #f ; no "check" target
2428 (modify-phases %standard-phases
2432 (lambda* (#:key source #:allow-other-keys)
2433 (and (zero? (system* "gcc"
2435 "-finline-functions"
2442 (zero? (system* "gcc"
2446 "-finline-functions"
2454 (lambda* (#:key outputs #:allow-other-keys)
2455 (let ((bin (string-append (assoc-ref outputs "out")
2458 (install-file "FastTree" bin)
2459 (install-file "FastTreeMP" bin)
2461 (home-page "http://www.microbesonline.org/fasttree")
2462 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2464 "FastTree can handle alignments with up to a million of sequences in a
2465 reasonable amount of time and memory. For large alignments, FastTree is
2466 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2467 (license license:gpl2+)))
2469 (define-public fastx-toolkit
2471 (name "fastx-toolkit")
2477 "https://github.com/agordon/fastx_toolkit/releases/download/"
2478 version "/fastx_toolkit-" version ".tar.bz2"))
2481 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2482 (build-system gnu-build-system)
2484 `(("libgtextutils" ,libgtextutils)))
2486 `(("pkg-config" ,pkg-config)))
2487 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2488 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2490 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2491 FASTA/FASTQ files preprocessing.
2493 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2494 containing multiple short-reads sequences. The main processing of such
2495 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2496 is sometimes more productive to preprocess the files before mapping the
2497 sequences to the genome---manipulating the sequences to produce better mapping
2498 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2499 (license license:agpl3+)))
2501 (define-public flexbar
2508 (string-append "mirror://sourceforge/flexbar/"
2509 version "/flexbar_v" version "_src.tgz"))
2512 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2513 (build-system cmake-build-system)
2515 `(#:configure-flags (list
2516 (string-append "-DFLEXBAR_BINARY_DIR="
2517 (assoc-ref %outputs "out")
2520 (modify-phases %standard-phases
2522 (lambda* (#:key outputs #:allow-other-keys)
2523 (setenv "PATH" (string-append
2524 (assoc-ref outputs "out") "/bin:"
2526 (chdir "../flexbar_v2.5_src/test")
2527 (zero? (system* "bash" "flexbar_validate.sh"))))
2528 (delete 'install))))
2533 `(("pkg-config" ,pkg-config)
2535 (home-page "http://flexbar.sourceforge.net")
2536 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2538 "Flexbar preprocesses high-throughput nucleotide sequencing data
2539 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2540 Moreover, trimming and filtering features are provided. Flexbar increases
2541 read mapping rates and improves genome and transcriptome assemblies. It
2542 supports next-generation sequencing data in fasta/q and csfasta/q format from
2543 Illumina, Roche 454, and the SOLiD platform.")
2544 (license license:gpl3)))
2546 (define-public fraggenescan
2548 (name "fraggenescan")
2554 (string-append "mirror://sourceforge/fraggenescan/"
2555 "FragGeneScan" version ".tar.gz"))
2557 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2558 (build-system gnu-build-system)
2561 (modify-phases %standard-phases
2563 (add-before 'build 'patch-paths
2564 (lambda* (#:key outputs #:allow-other-keys)
2565 (let* ((out (string-append (assoc-ref outputs "out")))
2566 (share (string-append out "/share/fraggenescan/")))
2567 (substitute* "run_FragGeneScan.pl"
2569 (string-append "system(\"" (which "rm")))
2571 (string-append "system(\"" (which "mv")))
2572 (("\\\"awk") (string-append "\"" (which "awk")))
2573 ;; This script and other programs expect the training files
2574 ;; to be in the non-standard location bin/train/XXX. Change
2575 ;; this to be share/fraggenescan/train/XXX instead.
2576 (("^\\$train.file = \\$dir.*")
2577 (string-append "$train_file = \""
2579 "train/\".$FGS_train_file;")))
2580 (substitute* "run_hmm.c"
2581 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2582 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2585 (lambda _ (and (zero? (system* "make" "clean"))
2586 (zero? (system* "make" "fgs")))))
2588 (lambda* (#:key outputs #:allow-other-keys)
2589 (let* ((out (string-append (assoc-ref outputs "out")))
2590 (bin (string-append out "/bin/"))
2591 (share (string-append out "/share/fraggenescan/train")))
2592 (install-file "run_FragGeneScan.pl" bin)
2593 (install-file "FragGeneScan" bin)
2594 (copy-recursively "train" share))))
2596 (add-after 'install 'post-install-check
2597 ;; In lieu of 'make check', run one of the examples and check the
2598 ;; output files gets created.
2599 (lambda* (#:key outputs #:allow-other-keys)
2600 (let* ((out (string-append (assoc-ref outputs "out")))
2601 (bin (string-append out "/bin/"))
2602 (frag (string-append bin "run_FragGeneScan.pl")))
2603 (and (zero? (system* frag ; Test complete genome.
2604 "-genome=./example/NC_000913.fna"
2608 (file-exists? "test2.faa")
2609 (file-exists? "test2.ffn")
2610 (file-exists? "test2.gff")
2611 (file-exists? "test2.out")
2612 (zero? (system* ; Test incomplete sequences.
2614 "-genome=./example/NC_000913-fgs.ffn"
2617 "-train=454_30")))))))))
2620 ("python" ,python-2))) ;not compatible with python 3.
2621 (home-page "https://sourceforge.net/projects/fraggenescan/")
2622 (synopsis "Finds potentially fragmented genes in short reads")
2624 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2625 short and error-prone DNA sequencing reads. It can also be applied to predict
2626 genes in incomplete assemblies or complete genomes.")
2627 ;; GPL3+ according to private correspondense with the authors.
2628 (license license:gpl3+)))
2630 (define-public fxtract
2631 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2639 "https://github.com/ctSkennerton/fxtract/archive/"
2641 (file-name (string-append "ctstennerton-util-"
2642 (string-take util-commit 7)
2646 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2647 (build-system gnu-build-system)
2649 `(#:make-flags (list
2650 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2652 #:test-target "fxtract_test"
2654 (modify-phases %standard-phases
2656 (add-before 'build 'copy-util
2657 (lambda* (#:key inputs #:allow-other-keys)
2659 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2661 ;; Do not use make install as this requires additional dependencies.
2663 (lambda* (#:key outputs #:allow-other-keys)
2664 (let* ((out (assoc-ref outputs "out"))
2665 (bin (string-append out"/bin")))
2666 (install-file "fxtract" bin)
2672 ;; ctskennerton-util is licensed under GPL2.
2673 `(("ctskennerton-util"
2677 (url "https://github.com/ctSkennerton/util.git")
2678 (commit util-commit)))
2679 (file-name (string-append
2680 "ctstennerton-util-" util-commit "-checkout"))
2683 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2684 (home-page "https://github.com/ctSkennerton/fxtract")
2685 (synopsis "Extract sequences from FASTA and FASTQ files")
2687 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2688 or FASTQ) file given a subsequence. It uses a simple substring search for
2689 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2690 lookups or multi-pattern searching as required. By default fxtract looks in
2691 the sequence of each record but can also be told to look in the header,
2692 comment or quality sections.")
2693 ;; 'util' requires SSE instructions.
2694 (supported-systems '("x86_64-linux"))
2695 (license license:expat))))
2697 (define-public gemma
2703 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2705 (file-name (string-append name "-" version ".tar.gz"))
2708 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2709 (patches (search-patches "gemma-intel-compat.patch"))))
2714 (build-system gnu-build-system)
2717 '(,@(match (%current-system)
2719 '("FORCE_DYNAMIC=1"))
2721 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2723 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2725 (modify-phases %standard-phases
2727 (add-before 'build 'bin-mkdir
2732 (lambda* (#:key outputs #:allow-other-keys)
2733 (let ((out (assoc-ref outputs "out")))
2734 (install-file "bin/gemma"
2738 #:tests? #f)) ; no tests included yet
2739 (home-page "https://github.com/xiangzhou/GEMMA")
2740 (synopsis "Tool for genome-wide efficient mixed model association")
2742 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2743 standard linear mixed model resolver with application in genome-wide
2744 association studies (GWAS).")
2745 (license license:gpl3)))
2754 "https://github.com/nboley/grit/archive/"
2756 (file-name (string-append name "-" version ".tar.gz"))
2759 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2760 (build-system python-build-system)
2762 `(#:python ,python-2
2764 (modify-phases %standard-phases
2765 (add-after 'unpack 'generate-from-cython-sources
2766 (lambda* (#:key inputs outputs #:allow-other-keys)
2767 ;; Delete these C files to force fresh generation from pyx sources.
2768 (delete-file "grit/sparsify_support_fns.c")
2769 (delete-file "grit/call_peaks_support_fns.c")
2770 (substitute* "setup.py"
2771 (("Cython.Setup") "Cython.Build")
2772 ;; Add numpy include path to fix compilation
2774 (string-append "pyx\", ], include_dirs = ['"
2775 (assoc-ref inputs "python-numpy")
2776 "/lib/python2.7/site-packages/numpy/core/include/"
2780 `(("python-scipy" ,python2-scipy)
2781 ("python-numpy" ,python2-numpy)
2782 ("python-pysam" ,python2-pysam)
2783 ("python-networkx" ,python2-networkx)))
2785 `(("python-cython" ,python2-cython)))
2786 (home-page "http://grit-bio.org")
2787 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2789 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2790 full length transcript models. When none of these data sources are available,
2791 GRIT can be run by providing a candidate set of TES or TSS sites. In
2792 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2793 also be run in quantification mode, where it uses a provided GTF file and just
2794 estimates transcript expression.")
2795 (license license:gpl3+)))
2797 (define-public hisat
2804 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2805 version "-beta-source.zip"))
2808 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2809 (build-system gnu-build-system)
2811 `(#:tests? #f ;no check target
2812 #:make-flags '("allall"
2813 ;; Disable unsupported `popcnt' instructions on
2814 ;; architectures other than x86_64
2815 ,@(if (string-prefix? "x86_64"
2816 (or (%current-target-system)
2819 '("POPCNT_CAPABILITY=0")))
2821 (modify-phases %standard-phases
2822 (add-after 'unpack 'patch-sources
2824 ;; XXX Cannot use snippet because zip files are not supported
2825 (substitute* "Makefile"
2826 (("^CC = .*$") "CC = gcc")
2827 (("^CPP = .*$") "CPP = g++")
2828 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2829 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2830 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2831 (substitute* '("hisat-build" "hisat-inspect")
2832 (("/usr/bin/env") (which "env")))
2835 (lambda* (#:key outputs #:allow-other-keys)
2836 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2837 (for-each (lambda (file)
2838 (install-file file bin))
2841 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2843 (delete 'configure))))
2845 `(("unzip" ,unzip)))
2850 ;; Non-portable SSE instructions are used so building fails on platforms
2851 ;; other than x86_64.
2852 (supported-systems '("x86_64-linux"))
2853 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2854 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2856 "HISAT is a fast and sensitive spliced alignment program for mapping
2857 RNA-seq reads. In addition to one global FM index that represents a whole
2858 genome, HISAT uses a large set of small FM indexes that collectively cover the
2859 whole genome. These small indexes (called local indexes) combined with
2860 several alignment strategies enable effective alignment of RNA-seq reads, in
2861 particular, reads spanning multiple exons.")
2862 (license license:gpl3+)))
2864 (define-public hisat2
2871 ;; FIXME: a better source URL is
2872 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2873 ;; "/downloads/hisat2-" version "-source.zip")
2874 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2875 ;; but it is currently unavailable.
2876 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2877 (file-name (string-append name "-" version ".tar.gz"))
2880 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2881 (build-system gnu-build-system)
2883 `(#:tests? #f ; no check target
2884 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2885 #:modules ((guix build gnu-build-system)
2889 (modify-phases %standard-phases
2890 (add-after 'unpack 'make-deterministic
2892 (substitute* "Makefile"
2897 (lambda* (#:key outputs #:allow-other-keys)
2898 (let* ((out (assoc-ref outputs "out"))
2899 (bin (string-append out "/bin/"))
2900 (doc (string-append out "/share/doc/hisat2/")))
2902 (cut install-file <> bin)
2904 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2906 (install-file "doc/manual.inc.html" doc))
2909 `(("unzip" ,unzip) ; needed for archive from ftp
2911 ("pandoc" ,ghc-pandoc))) ; for documentation
2912 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2913 (synopsis "Graph-based alignment of genomic sequencing reads")
2914 (description "HISAT2 is a fast and sensitive alignment program for mapping
2915 next-generation sequencing reads (both DNA and RNA) to a population of human
2916 genomes (as well as to a single reference genome). In addition to using one
2917 global @dfn{graph FM} (GFM) index that represents a population of human
2918 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2919 the whole genome. These small indexes, combined with several alignment
2920 strategies, enable rapid and accurate alignment of sequencing reads. This new
2921 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2922 ;; HISAT2 contains files from Bowtie2, which is released under
2923 ;; GPLv2 or later. The HISAT2 source files are released under
2925 (license license:gpl3+)))
2927 (define-public hmmer
2935 "http://eddylab.org/software/hmmer"
2936 (version-major version) "/"
2937 version "/hmmer-" version ".tar.gz"))
2940 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2941 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2942 (build-system gnu-build-system)
2943 (native-inputs `(("perl" ,perl)))
2944 (home-page "http://hmmer.org/")
2945 (synopsis "Biosequence analysis using profile hidden Markov models")
2947 "HMMER is used for searching sequence databases for homologs of protein
2948 sequences, and for making protein sequence alignments. It implements methods
2949 using probabilistic models called profile hidden Markov models (profile
2951 (license (list license:gpl3+
2952 ;; The bundled library 'easel' is distributed
2953 ;; under The Janelia Farm Software License.
2954 (license:non-copyleft
2955 "file://easel/LICENSE"
2956 "See easel/LICENSE in the distribution.")))))
2958 (define-public htseq
2964 (uri (pypi-uri "HTSeq" version))
2967 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2968 (build-system python-build-system)
2970 `(("python-cython" ,python-cython)))
2971 ;; Numpy needs to be propagated when htseq is used as a Python library.
2973 `(("python-numpy" ,python-numpy)))
2975 `(("python-pysam" ,python-pysam)
2976 ("python-matplotlib" ,python-matplotlib)))
2977 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2978 (synopsis "Analysing high-throughput sequencing data with Python")
2980 "HTSeq is a Python package that provides infrastructure to process data
2981 from high-throughput sequencing assays.")
2982 (license license:gpl3+)))
2984 (define-public python2-htseq
2985 (package-with-python2 htseq))
2987 (define-public java-htsjdk
2989 (name "java-htsjdk")
2990 (version "2.3.0") ; last version without build dependency on gradle
2994 "https://github.com/samtools/htsjdk/archive/"
2996 (file-name (string-append name "-" version ".tar.gz"))
2999 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
3000 (modules '((guix build utils)))
3002 ;; Delete pre-built binaries
3004 (delete-file-recursively "lib")
3007 (build-system ant-build-system)
3009 `(#:tests? #f ; test require Internet access
3012 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3013 "/share/java/htsjdk/"))
3014 #:build-target "all"
3016 (modify-phases %standard-phases
3017 ;; The build phase also installs the jars
3018 (delete 'install))))
3020 `(("java-ngs" ,java-ngs)
3021 ("java-snappy-1" ,java-snappy-1)
3022 ("java-commons-compress" ,java-commons-compress)
3023 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3024 ("java-commons-jexl-2" ,java-commons-jexl-2)
3025 ("java-xz" ,java-xz)))
3027 `(("java-testng" ,java-testng)))
3028 (home-page "http://samtools.github.io/htsjdk/")
3029 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3031 "HTSJDK is an implementation of a unified Java library for accessing
3032 common file formats, such as SAM and VCF, used for high-throughput
3033 sequencing (HTS) data. There are also an number of useful utilities for
3034 manipulating HTS data.")
3035 (license license:expat)))
3037 (define-public java-htsjdk-latest
3039 (name "java-htsjdk")
3044 (url "https://github.com/samtools/htsjdk.git")
3046 (file-name (string-append name "-" version "-checkout"))
3049 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3050 (build-system ant-build-system)
3052 `(#:tests? #f ; test require Scala
3054 #:jar-name "htsjdk.jar"
3056 (modify-phases %standard-phases
3057 (add-after 'unpack 'remove-useless-build.xml
3058 (lambda _ (delete-file "build.xml") #t))
3059 ;; The tests require the scalatest package.
3060 (add-after 'unpack 'remove-tests
3061 (lambda _ (delete-file-recursively "src/test") #t)))))
3063 `(("java-ngs" ,java-ngs)
3064 ("java-snappy-1" ,java-snappy-1)
3065 ("java-commons-compress" ,java-commons-compress)
3066 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3067 ("java-commons-jexl-2" ,java-commons-jexl-2)
3068 ("java-xz" ,java-xz)))
3070 `(("java-junit" ,java-junit)))
3071 (home-page "http://samtools.github.io/htsjdk/")
3072 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3074 "HTSJDK is an implementation of a unified Java library for accessing
3075 common file formats, such as SAM and VCF, used for high-throughput
3076 sequencing (HTS) data. There are also an number of useful utilities for
3077 manipulating HTS data.")
3078 (license license:expat)))
3080 ;; This is needed for picard 2.10.3
3081 (define-public java-htsjdk-2.10.1
3082 (package (inherit java-htsjdk-latest)
3083 (name "java-htsjdk")
3088 (url "https://github.com/samtools/htsjdk.git")
3090 (file-name (string-append name "-" version "-checkout"))
3093 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3094 (build-system ant-build-system)
3096 `(#:tests? #f ; tests require Scala
3098 #:jar-name "htsjdk.jar"
3100 (modify-phases %standard-phases
3101 (add-after 'unpack 'remove-useless-build.xml
3102 (lambda _ (delete-file "build.xml") #t))
3103 ;; The tests require the scalatest package.
3104 (add-after 'unpack 'remove-tests
3105 (lambda _ (delete-file-recursively "src/test") #t)))))))
3107 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3108 ;; recent version of java-htsjdk, which depends on gradle.
3109 (define-public java-picard
3111 (name "java-picard")
3116 (url "https://github.com/broadinstitute/picard.git")
3118 (file-name (string-append "java-picard-" version "-checkout"))
3121 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3122 (modules '((guix build utils)))
3125 ;; Delete pre-built binaries.
3126 (delete-file-recursively "lib")
3128 (substitute* "build.xml"
3129 ;; Remove build-time dependency on git.
3130 (("failifexecutionfails=\"true\"")
3131 "failifexecutionfails=\"false\"")
3133 (("depends=\"compile-htsjdk, ")
3135 (("depends=\"compile-htsjdk-tests, ")
3137 ;; Build picard-lib.jar before building picard.jar
3138 (("name=\"picard-jar\" depends=\"" line)
3139 (string-append line "picard-lib-jar, ")))
3141 (build-system ant-build-system)
3143 `(#:build-target "picard-jar"
3144 #:test-target "test"
3145 ;; Tests require jacoco:coverage.
3148 (list (string-append "-Dhtsjdk_lib_dir="
3149 (assoc-ref %build-inputs "java-htsjdk")
3150 "/share/java/htsjdk/")
3151 "-Dhtsjdk-classes=dist/tmp"
3152 (string-append "-Dhtsjdk-version="
3153 ,(package-version java-htsjdk)))
3156 (modify-phases %standard-phases
3157 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3158 (delete 'generate-jar-indices)
3159 (add-after 'unpack 'use-our-htsjdk
3160 (lambda* (#:key inputs #:allow-other-keys)
3161 (substitute* "build.xml"
3162 (("\\$\\{htsjdk\\}/lib")
3163 (string-append (assoc-ref inputs "java-htsjdk")
3164 "/share/java/htsjdk/")))
3166 (add-after 'unpack 'make-test-target-independent
3167 (lambda* (#:key inputs #:allow-other-keys)
3168 (substitute* "build.xml"
3169 (("name=\"test\" depends=\"compile, ")
3170 "name=\"test\" depends=\""))
3172 (replace 'install (install-jars "dist")))))
3174 `(("java-htsjdk" ,java-htsjdk)
3175 ("java-guava" ,java-guava)))
3177 `(("java-testng" ,java-testng)))
3178 (home-page "http://broadinstitute.github.io/picard/")
3179 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3180 (description "Picard is a set of Java command line tools for manipulating
3181 high-throughput sequencing (HTS) data and formats. Picard is implemented
3182 using the HTSJDK Java library to support accessing file formats that are
3183 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3185 (license license:expat)))
3187 ;; This is needed for dropseq-tools
3188 (define-public java-picard-2.10.3
3190 (name "java-picard")
3195 (url "https://github.com/broadinstitute/picard.git")
3197 (file-name (string-append "java-picard-" version "-checkout"))
3200 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3201 (build-system ant-build-system)
3203 `(#:jar-name "picard.jar"
3204 ;; Tests require jacoco:coverage.
3207 #:main-class "picard.cmdline.PicardCommandLine"
3208 #:modules ((guix build ant-build-system)
3210 (guix build java-utils)
3215 (modify-phases %standard-phases
3216 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3217 (delete 'generate-jar-indices)
3218 (add-after 'unpack 'remove-useless-build.xml
3219 (lambda _ (delete-file "build.xml") #t))
3220 ;; This is necessary to ensure that htsjdk is found when using
3221 ;; picard.jar as an executable.
3222 (add-before 'build 'edit-classpath-in-manifest
3223 (lambda* (#:key inputs #:allow-other-keys)
3224 (chmod "build.xml" #o664)
3225 (call-with-output-file "build.xml.new"
3229 (with-input-from-file "build.xml"
3230 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3231 `((target . ,(lambda (tag . kids)
3232 (let ((name ((sxpath '(name *text*))
3234 ;; FIXME: We're breaking the line
3235 ;; early with a dummy path to
3236 ;; ensure that the store reference
3237 ;; isn't broken apart and can still
3238 ;; be found by the reference
3243 ~a/share/java/htsjdk.jar${line.separator}"
3244 ;; maximum line length is 70
3245 (string-tabulate (const #\b) 57)
3246 (assoc-ref inputs "java-htsjdk"))))
3247 (if (member "manifest" name)
3251 (file "${manifest.file}")
3254 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3255 (*text* . ,(lambda (_ txt) txt))))
3257 (rename-file "build.xml.new" "build.xml")
3260 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3262 `(("java-testng" ,java-testng)
3263 ("java-guava" ,java-guava)))
3264 (home-page "http://broadinstitute.github.io/picard/")
3265 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3266 (description "Picard is a set of Java command line tools for manipulating
3267 high-throughput sequencing (HTS) data and formats. Picard is implemented
3268 using the HTSJDK Java library to support accessing file formats that are
3269 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3271 (license license:expat)))
3273 ;; This is the last version of Picard to provide net.sf.samtools
3274 (define-public java-picard-1.113
3275 (package (inherit java-picard)
3276 (name "java-picard")
3281 (url "https://github.com/broadinstitute/picard.git")
3283 (file-name (string-append "java-picard-" version "-checkout"))
3286 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3287 (modules '((guix build utils)))
3290 ;; Delete pre-built binaries.
3291 (delete-file-recursively "lib")
3294 (build-system ant-build-system)
3296 `(#:build-target "picard-jar"
3297 #:test-target "test"
3298 ;; FIXME: the class path at test time is wrong.
3299 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3300 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3303 ;; This is only used for tests.
3305 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3307 (modify-phases %standard-phases
3308 ;; FIXME: This phase fails.
3309 (delete 'generate-jar-indices)
3310 ;; Do not use bundled ant bzip2.
3311 (add-after 'unpack 'use-ant-bzip
3312 (lambda* (#:key inputs #:allow-other-keys)
3313 (substitute* "build.xml"
3314 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3315 (string-append (assoc-ref inputs "ant")
3318 (add-after 'unpack 'make-test-target-independent
3319 (lambda* (#:key inputs #:allow-other-keys)
3320 (substitute* "build.xml"
3321 (("name=\"test\" depends=\"compile, ")
3322 "name=\"test\" depends=\"compile-tests, ")
3323 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3324 "name=\"compile\" depends=\"compile-src\""))
3326 (add-after 'unpack 'fix-deflater-path
3327 (lambda* (#:key outputs #:allow-other-keys)
3328 (substitute* "src/java/net/sf/samtools/Defaults.java"
3329 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3330 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3331 (assoc-ref outputs "out")
3332 "/lib/jni/libIntelDeflater.so"
3335 ;; Build the deflater library, because we've previously deleted the
3336 ;; pre-built one. This can only be built with access to the JDK
3338 (add-after 'build 'build-jni
3339 (lambda* (#:key inputs #:allow-other-keys)
3342 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3343 "-xf" (assoc-ref inputs "jdk-src")))
3344 (zero? (system* "javah" "-jni"
3345 "-classpath" "classes"
3347 "net.sf.samtools.util.zip.IntelDeflater"))
3348 (with-directory-excursion "src/c/inteldeflater"
3349 (zero? (system* "gcc" "-I../../../lib" "-I."
3350 (string-append "-I" (assoc-ref inputs "jdk")
3352 "-I../../../jdk-src/src/share/native/common/"
3353 "-I../../../jdk-src/src/solaris/native/common/"
3354 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3355 (zero? (system* "gcc" "-shared"
3356 "-o" "../../../lib/jni/libIntelDeflater.so"
3357 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3358 ;; We can only build everything else after building the JNI library.
3359 (add-after 'build-jni 'build-rest
3360 (lambda* (#:key make-flags #:allow-other-keys)
3361 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3362 (add-before 'build 'set-JAVA6_HOME
3364 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3366 (replace 'install (install-jars "dist"))
3367 (add-after 'install 'install-jni-lib
3368 (lambda* (#:key outputs #:allow-other-keys)
3369 (let ((jni (string-append (assoc-ref outputs "out")
3372 (install-file "lib/jni/libIntelDeflater.so" jni)
3375 `(("java-snappy-1" ,java-snappy-1)
3376 ("java-commons-jexl-2" ,java-commons-jexl-2)
3377 ("java-cofoja" ,java-cofoja)
3378 ("ant" ,ant) ; for bzip2 support at runtime
3381 `(("ant-apache-bcel" ,ant-apache-bcel)
3382 ("ant-junit" ,ant-junit)
3383 ("java-testng" ,java-testng)
3384 ("java-commons-bcel" ,java-commons-bcel)
3385 ("java-jcommander" ,java-jcommander)
3386 ("jdk" ,icedtea-8 "jdk")
3387 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3389 (define-public fastqc
3396 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3397 "projects/fastqc/fastqc_v"
3398 version "_source.zip"))
3401 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3402 (build-system ant-build-system)
3404 `(#:tests? #f ; there are no tests
3405 #:build-target "build"
3407 (modify-phases %standard-phases
3408 (add-after 'unpack 'fix-dependencies
3409 (lambda* (#:key inputs #:allow-other-keys)
3410 (substitute* "build.xml"
3412 (string-append (assoc-ref inputs "java-jbzip2")
3413 "/share/java/jbzip2.jar"))
3415 (string-append (assoc-ref inputs "java-picard-1.113")
3416 "/share/java/sam-1.112.jar"))
3418 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3419 "/share/java/sis-jhdf5.jar")))
3421 ;; There is no installation target
3423 (lambda* (#:key inputs outputs #:allow-other-keys)
3424 (let* ((out (assoc-ref outputs "out"))
3425 (bin (string-append out "/bin"))
3426 (share (string-append out "/share/fastqc/"))
3427 (exe (string-append share "/fastqc")))
3428 (for-each mkdir-p (list bin share))
3429 (copy-recursively "bin" share)
3431 (("my \\$java_bin = 'java';")
3432 (string-append "my $java_bin = '"
3433 (assoc-ref inputs "java")
3436 (symlink exe (string-append bin "/fastqc"))
3440 ("perl" ,perl) ; needed for the wrapper script
3441 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3442 ("java-picard-1.113" ,java-picard-1.113)
3443 ("java-jbzip2" ,java-jbzip2)))
3445 `(("unzip" ,unzip)))
3446 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3447 (synopsis "Quality control tool for high throughput sequence data")
3449 "FastQC aims to provide a simple way to do some quality control
3450 checks on raw sequence data coming from high throughput sequencing
3451 pipelines. It provides a modular set of analyses which you can use to
3452 give a quick impression of whether your data has any problems of which
3453 you should be aware before doing any further analysis.
3455 The main functions of FastQC are:
3458 @item Import of data from BAM, SAM or FastQ files (any variant);
3459 @item Providing a quick overview to tell you in which areas there may
3461 @item Summary graphs and tables to quickly assess your data;
3462 @item Export of results to an HTML based permanent report;
3463 @item Offline operation to allow automated generation of reports
3464 without running the interactive application.
3466 (license license:gpl3+)))
3468 (define-public fastp
3476 (url "https://github.com/OpenGene/fastp.git")
3477 (commit (string-append "v" version))))
3478 (file-name (git-file-name name version))
3481 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3482 (build-system gnu-build-system)
3484 `(#:tests? #f ; there are none
3486 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3488 (modify-phases %standard-phases
3490 (add-before 'install 'create-target-dir
3491 (lambda* (#:key outputs #:allow-other-keys)
3492 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3496 (home-page "https://github.com/OpenGene/fastp/")
3497 (synopsis "All-in-one FastQ preprocessor")
3499 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3500 FastQ files. This tool has multi-threading support to afford high
3502 (license license:expat)))
3504 (define-public htslib
3511 "https://github.com/samtools/htslib/releases/download/"
3512 version "/htslib-" version ".tar.bz2"))
3515 "18bw0mn9pj5wgarnlaxmf1bb8pdqgl1zd6czirqcr62ajpn1xvy0"))))
3516 (build-system gnu-build-system)
3518 `(("openssl" ,openssl)
3523 (home-page "http://www.htslib.org")
3524 (synopsis "C library for reading/writing high-throughput sequencing data")
3526 "HTSlib is a C library for reading/writing high-throughput sequencing
3527 data. It also provides the @command{bgzip}, @command{htsfile}, and
3528 @command{tabix} utilities.")
3529 ;; Files under cram/ are released under the modified BSD license;
3530 ;; the rest is released under the Expat license
3531 (license (list license:expat license:bsd-3))))
3533 ;; This package should be removed once no packages rely upon it.
3541 "https://github.com/samtools/htslib/releases/download/"
3542 version "/htslib-" version ".tar.bz2"))
3545 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3554 "https://github.com/nboley/idr/archive/"
3556 (file-name (string-append name "-" version ".tar.gz"))
3559 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3560 ;; Delete generated C code.
3562 '(begin (delete-file "idr/inv_cdf.c") #t))))
3563 (build-system python-build-system)
3564 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3565 ;; are no longer part of this package. It also asserts False, which
3566 ;; causes the tests to always fail.
3567 (arguments `(#:tests? #f))
3569 `(("python-scipy" ,python-scipy)
3570 ("python-sympy" ,python-sympy)
3571 ("python-numpy" ,python-numpy)
3572 ("python-matplotlib" ,python-matplotlib)))
3574 `(("python-cython" ,python-cython)))
3575 (home-page "https://github.com/nboley/idr")
3576 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3578 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3579 to measure the reproducibility of findings identified from replicate
3580 experiments and provide highly stable thresholds based on reproducibility.")
3581 (license license:gpl2+)))
3583 (define-public jellyfish
3589 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3590 "releases/download/v" version
3591 "/jellyfish-" version ".tar.gz"))
3594 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3595 (build-system gnu-build-system)
3596 (outputs '("out" ;for library
3597 "ruby" ;for Ruby bindings
3598 "python")) ;for Python bindings
3601 (list (string-append "--enable-ruby-binding="
3602 (assoc-ref %outputs "ruby"))
3603 (string-append "--enable-python-binding="
3604 (assoc-ref %outputs "python")))
3606 (modify-phases %standard-phases
3607 (add-before 'check 'set-SHELL-variable
3609 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3611 (setenv "SHELL" (which "bash"))
3617 ("python" ,python-2)
3618 ("pkg-config" ,pkg-config)))
3620 `(("htslib" ,htslib)))
3621 (synopsis "Tool for fast counting of k-mers in DNA")
3623 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3624 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3625 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3626 is a command-line program that reads FASTA and multi-FASTA files containing
3627 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3628 translated into a human-readable text format using the @code{jellyfish dump}
3629 command, or queried for specific k-mers with @code{jellyfish query}.")
3630 (home-page "http://www.genome.umd.edu/jellyfish.html")
3631 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3632 (supported-systems '("x86_64-linux"))
3633 ;; The combined work is published under the GPLv3 or later. Individual
3634 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3635 (license (list license:gpl3+ license:expat))))
3637 (define-public khmer
3644 (uri (pypi-uri "khmer" version))
3647 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3648 (patches (search-patches "khmer-use-libraries.patch"))))
3649 (build-system python-build-system)
3652 (modify-phases %standard-phases
3653 (add-after 'unpack 'set-paths
3654 (lambda* (#:key inputs outputs #:allow-other-keys)
3655 ;; Delete bundled libraries.
3656 (delete-file-recursively "third-party/zlib")
3657 (delete-file-recursively "third-party/bzip2")
3658 ;; Replace bundled seqan.
3659 (let* ((seqan-all "third-party/seqan")
3660 (seqan-include (string-append
3661 seqan-all "/core/include")))
3662 (delete-file-recursively seqan-all)
3663 (copy-recursively (string-append (assoc-ref inputs "seqan")
3665 (string-append seqan-include "/seqan")))
3666 ;; We do not replace the bundled MurmurHash as the canonical
3667 ;; repository for this code 'SMHasher' is unsuitable for
3668 ;; providing a library. See
3669 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3671 (add-after 'unpack 'set-cc
3675 ;; It is simpler to test after installation.
3677 (add-after 'install 'post-install-check
3678 (lambda* (#:key inputs outputs #:allow-other-keys)
3679 (let ((out (assoc-ref outputs "out")))
3684 (assoc-ref outputs "out")
3686 (setenv "PYTHONPATH"
3688 (getenv "PYTHONPATH")
3692 (string-take (string-take-right
3693 (assoc-ref inputs "python") 5) 3)
3695 (with-directory-excursion "build"
3696 (zero? (system* "nosetests" "khmer" "--attr"
3697 "!known_failing")))))))))
3700 ("python-nose" ,python-nose)))
3704 ("python-screed" ,python-screed)
3705 ("python-bz2file" ,python-bz2file)
3706 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3707 ;; until the next version of khmer (likely 2.1) is released.
3709 (home-page "https://khmer.readthedocs.org/")
3710 (synopsis "K-mer counting, filtering and graph traversal library")
3711 (description "The khmer software is a set of command-line tools for
3712 working with DNA shotgun sequencing data from genomes, transcriptomes,
3713 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3714 sometimes better. Khmer can also identify and fix problems with shotgun
3716 ;; When building on i686, armhf and mips64el, we get the following error:
3717 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3718 (supported-systems '("x86_64-linux" "aarch64-linux"))
3719 (license license:bsd-3)))
3721 (define-public kaiju
3728 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3730 (file-name (string-append name "-" version ".tar.gz"))
3733 "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7"))))
3734 (build-system gnu-build-system)
3736 `(#:tests? #f ; There are no tests.
3738 (modify-phases %standard-phases
3740 (add-before 'build 'move-to-src-dir
3741 (lambda _ (chdir "src") #t))
3743 (lambda* (#:key inputs outputs #:allow-other-keys)
3744 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3747 (copy-recursively "bin" bin)
3748 (copy-recursively "util" bin))
3753 (home-page "http://kaiju.binf.ku.dk/")
3754 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3755 (description "Kaiju is a program for sensitive taxonomic classification
3756 of high-throughput sequencing reads from metagenomic whole genome sequencing
3758 (license license:gpl3+)))
3763 (version "2.1.0.20151222")
3766 (uri (pypi-uri "MACS2" version))
3769 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3770 (build-system python-build-system)
3772 `(#:python ,python-2 ; only compatible with Python 2.7
3773 #:tests? #f)) ; no test target
3775 `(("python-numpy" ,python2-numpy)))
3776 (home-page "https://github.com/taoliu/MACS/")
3777 (synopsis "Model based analysis for ChIP-Seq data")
3779 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3780 identifying transcript factor binding sites named Model-based Analysis of
3781 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3782 the significance of enriched ChIP regions and it improves the spatial
3783 resolution of binding sites through combining the information of both
3784 sequencing tag position and orientation.")
3785 (license license:bsd-3)))
3787 (define-public mafft
3794 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3795 "-without-extensions-src.tgz"))
3796 (file-name (string-append name "-" version ".tgz"))
3799 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3800 (build-system gnu-build-system)
3802 `(#:tests? #f ; no automated tests, though there are tests in the read me
3803 #:make-flags (let ((out (assoc-ref %outputs "out")))
3804 (list (string-append "PREFIX=" out)
3805 (string-append "BINDIR="
3806 (string-append out "/bin"))))
3808 (modify-phases %standard-phases
3809 (add-after 'unpack 'enter-dir
3810 (lambda _ (chdir "core") #t))
3811 (add-after 'enter-dir 'patch-makefile
3813 ;; on advice from the MAFFT authors, there is no need to
3814 ;; distribute mafft-profile, mafft-distance, or
3815 ;; mafft-homologs.rb as they are too "specialised".
3816 (substitute* "Makefile"
3817 ;; remove mafft-homologs.rb from SCRIPTS
3818 (("^SCRIPTS = mafft mafft-homologs.rb")
3820 ;; remove mafft-homologs from MANPAGES
3821 (("^MANPAGES = mafft.1 mafft-homologs.1")
3822 "MANPAGES = mafft.1")
3823 ;; remove mafft-distance from PROGS
3824 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3825 "PROGS = dvtditr dndfast7 dndblast sextet5")
3826 ;; remove mafft-profile from PROGS
3827 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3828 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3829 (("^rm -f mafft-profile mafft-profile.exe") "#")
3830 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3831 ;; do not install MAN pages in libexec folder
3832 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3833 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3835 (add-after 'enter-dir 'patch-paths
3836 (lambda* (#:key inputs #:allow-other-keys)
3837 (substitute* '("pairash.c"
3839 (("perl") (which "perl"))
3840 (("([\"`| ])awk" _ prefix)
3841 (string-append prefix (which "awk")))
3842 (("grep") (which "grep")))
3845 (add-after 'install 'wrap-programs
3846 (lambda* (#:key outputs #:allow-other-keys)
3847 (let* ((out (assoc-ref outputs "out"))
3848 (bin (string-append out "/bin"))
3849 (path (string-append
3850 (assoc-ref %build-inputs "coreutils") "/bin:")))
3851 (for-each (lambda (file)
3853 `("PATH" ":" prefix (,path))))
3861 ("coreutils" ,coreutils)))
3862 (home-page "http://mafft.cbrc.jp/alignment/software/")
3863 (synopsis "Multiple sequence alignment program")
3865 "MAFFT offers a range of multiple alignment methods for nucleotide and
3866 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3867 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3869 (license (license:non-copyleft
3870 "http://mafft.cbrc.jp/alignment/software/license.txt"
3871 "BSD-3 with different formatting"))))
3880 "https://github.com/marbl/mash/archive/v"
3882 (file-name (string-append name "-" version ".tar.gz"))
3885 "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv"))
3886 (modules '((guix build utils)))
3889 ;; Delete bundled kseq.
3890 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3891 (delete-file "src/mash/kseq.h")
3893 (build-system gnu-build-system)
3895 `(#:tests? #f ; No tests.
3898 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3899 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3900 #:make-flags (list "CC=gcc")
3902 (modify-phases %standard-phases
3903 (add-after 'unpack 'fix-includes
3905 (substitute* '("src/mash/Sketch.cpp"
3906 "src/mash/CommandFind.cpp"
3907 "src/mash/CommandScreen.cpp")
3908 (("^#include \"kseq\\.h\"")
3909 "#include \"htslib/kseq.h\""))
3911 (add-after 'fix-includes 'autoconf
3912 (lambda _ (zero? (system* "autoconf")))))))
3914 `(("autoconf" ,autoconf)
3915 ;; Capnproto and htslib are statically embedded in the final
3916 ;; application. Therefore we also list their licenses, below.
3917 ("capnproto" ,capnproto)
3918 ("htslib" ,htslib)))
3922 (supported-systems '("x86_64-linux"))
3923 (home-page "https://mash.readthedocs.io")
3924 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3925 (description "Mash is a fast sequence distance estimator that uses the
3926 MinHash algorithm and is designed to work with genomes and metagenomes in the
3927 form of assemblies or reads.")
3928 (license (list license:bsd-3 ; Mash
3929 license:expat ; HTSlib and capnproto
3930 license:public-domain ; MurmurHash 3
3931 license:cpl1.0)))) ; Open Bloom Filter
3933 (define-public metabat
3940 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3942 (file-name (string-append name "-" version ".tar.gz"))
3945 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3946 (patches (search-patches "metabat-fix-compilation.patch"))))
3947 (build-system scons-build-system)
3949 `(#:scons ,scons-python2
3951 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3952 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3953 #:tests? #f ;; Tests are run during the build phase.
3955 (modify-phases %standard-phases
3956 (add-after 'unpack 'fix-includes
3958 (substitute* "src/BamUtils.h"
3959 (("^#include \"bam/bam\\.h\"")
3960 "#include \"samtools/bam.h\"")
3961 (("^#include \"bam/sam\\.h\"")
3962 "#include \"samtools/sam.h\""))
3963 (substitute* "src/KseqReader.h"
3964 (("^#include \"bam/kseq\\.h\"")
3965 "#include \"htslib/kseq.h\""))
3967 (add-after 'unpack 'fix-scons
3968 (lambda* (#:key inputs #:allow-other-keys)
3969 (substitute* "SConstruct"
3970 (("^htslib_dir += 'samtools'")
3971 (string-append "htslib_dir = '"
3972 (assoc-ref inputs "htslib")
3974 (("^samtools_dir = 'samtools'")
3975 (string-append "samtools_dir = '"
3976 (assoc-ref inputs "samtools")
3978 (("^findStaticOrShared\\('bam', hts_lib")
3979 (string-append "findStaticOrShared('bam', '"
3980 (assoc-ref inputs "samtools")
3982 ;; Do not distribute README.
3983 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3988 ("samtools" ,samtools)
3991 (home-page "https://bitbucket.org/berkeleylab/metabat")
3993 "Reconstruction of single genomes from complex microbial communities")
3995 "Grouping large genomic fragments assembled from shotgun metagenomic
3996 sequences to deconvolute complex microbial communities, or metagenome binning,
3997 enables the study of individual organisms and their interactions. MetaBAT is
3998 an automated metagenome binning software, which integrates empirical
3999 probabilistic distances of genome abundance and tetranucleotide frequency.")
4000 ;; The source code contains inline assembly.
4001 (supported-systems '("x86_64-linux" "i686-linux"))
4002 (license (license:non-copyleft "file://license.txt"
4003 "See license.txt in the distribution."))))
4005 (define-public minced
4012 "https://github.com/ctSkennerton/minced/archive/"
4014 (file-name (string-append name "-" version ".tar.gz"))
4017 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
4018 (build-system gnu-build-system)
4020 `(#:test-target "test"
4022 (modify-phases %standard-phases
4024 (add-before 'check 'fix-test
4026 ;; Fix test for latest version.
4027 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4028 (("minced:0.1.6") "minced:0.2.0"))
4030 (replace 'install ; No install target.
4031 (lambda* (#:key inputs outputs #:allow-other-keys)
4032 (let* ((out (assoc-ref outputs "out"))
4033 (bin (string-append out "/bin"))
4034 (wrapper (string-append bin "/minced")))
4035 ;; Minced comes with a wrapper script that tries to figure out where
4036 ;; it is located before running the JAR. Since these paths are known
4037 ;; to us, we build our own wrapper to avoid coreutils dependency.
4038 (install-file "minced.jar" bin)
4039 (with-output-to-file wrapper
4043 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4044 (assoc-ref inputs "jre") "/bin/java -jar "
4045 bin "/minced.jar \"$@\"\n"))))
4046 (chmod wrapper #o555)))))))
4048 `(("jdk" ,icedtea "jdk")))
4051 ("jre" ,icedtea "out")))
4052 (home-page "https://github.com/ctSkennerton/minced")
4053 (synopsis "Mining CRISPRs in Environmental Datasets")
4055 "MinCED is a program to find Clustered Regularly Interspaced Short
4056 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4057 unassembled metagenomic reads, but is mainly designed for full genomes and
4058 assembled metagenomic sequence.")
4059 (license license:gpl3+)))
4067 (uri (pypi-uri "misopy" version))
4070 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4071 (modules '((guix build utils)))
4073 (substitute* "setup.py"
4074 ;; Use setuptools, or else the executables are not
4076 (("distutils.core") "setuptools")
4077 ;; use "gcc" instead of "cc" for compilation
4079 "cc.set_executables(
4083 linker_so='gcc -shared'); defines"))
4085 (build-system python-build-system)
4087 `(#:python ,python-2 ; only Python 2 is supported
4088 #:tests? #f)) ; no "test" target
4090 `(("samtools" ,samtools)
4091 ("python-numpy" ,python2-numpy)
4092 ("python-pysam" ,python2-pysam)
4093 ("python-scipy" ,python2-scipy)
4094 ("python-matplotlib" ,python2-matplotlib)))
4096 `(("python-mock" ,python2-mock) ;for tests
4097 ("python-pytz" ,python2-pytz))) ;for tests
4098 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4099 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4101 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4102 the expression level of alternatively spliced genes from RNA-Seq data, and
4103 identifies differentially regulated isoforms or exons across samples. By
4104 modeling the generative process by which reads are produced from isoforms in
4105 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4106 that a read originated from a particular isoform.")
4107 (license license:gpl2)))
4109 (define-public muscle
4112 (version "3.8.1551")
4114 (method url-fetch/tarbomb)
4116 "http://www.drive5.com/muscle/muscle_src_"
4120 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4121 (build-system gnu-build-system)
4123 `(#:make-flags (list "LDLIBS = -lm")
4125 (modify-phases %standard-phases
4128 ;; There are no tests, so just test if it runs.
4129 (lambda _ (zero? (system* "./muscle" "-version"))))
4131 (lambda* (#:key outputs #:allow-other-keys)
4132 (let* ((out (assoc-ref outputs "out"))
4133 (bin (string-append out "/bin")))
4134 (install-file "muscle" bin)))))))
4135 (home-page "http://www.drive5.com/muscle")
4136 (synopsis "Multiple sequence alignment program")
4138 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4139 program for nucleotide and protein sequences.")
4140 ;; License information found in 'muscle -h' and usage.cpp.
4141 (license license:public-domain)))
4143 (define-public newick-utils
4144 ;; There are no recent releases so we package from git.
4145 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4147 (name "newick-utils")
4148 (version (string-append "1.6-1." (string-take commit 8)))
4152 (url "https://github.com/tjunier/newick_utils.git")
4154 (file-name (string-append name "-" version "-checkout"))
4157 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4158 (build-system gnu-build-system)
4161 (modify-phases %standard-phases
4162 (add-after 'unpack 'autoconf
4163 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4165 ;; XXX: TODO: Enable Lua and Guile bindings.
4166 ;; https://github.com/tjunier/newick_utils/issues/13
4167 `(("libxml2" ,libxml2)
4171 `(("autoconf" ,autoconf)
4172 ("automake" ,automake)
4173 ("libtool" ,libtool)))
4174 (synopsis "Programs for working with newick format phylogenetic trees")
4176 "Newick-utils is a suite of utilities for processing phylogenetic trees
4177 in Newick format. Functions include re-rooting, extracting subtrees,
4178 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4179 (home-page "https://github.com/tjunier/newick_utils")
4180 (license license:bsd-3))))
4189 "https://github.com/wwood/OrfM/releases/download/v"
4190 version "/orfm-" version ".tar.gz"))
4193 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4194 (build-system gnu-build-system)
4195 (inputs `(("zlib" ,zlib)))
4197 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4198 ("ruby-rspec" ,ruby-rspec)
4200 (synopsis "Simple and not slow open reading frame (ORF) caller")
4202 "An ORF caller finds stretches of DNA that, when translated, are not
4203 interrupted by stop codons. OrfM finds and prints these ORFs.")
4204 (home-page "https://github.com/wwood/OrfM")
4205 (license license:lgpl3+)))
4207 (define-public pplacer
4208 (let ((commit "g807f6f3"))
4211 ;; The commit should be updated with each version change.
4212 (version "1.1.alpha19")
4216 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4218 (file-name (string-append name "-" version ".tar.gz"))
4220 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4221 (build-system ocaml-build-system)
4223 `(#:ocaml ,ocaml-4.01
4224 #:findlib ,ocaml4.01-findlib
4225 #:modules ((guix build ocaml-build-system)
4229 (modify-phases %standard-phases
4231 (add-after 'unpack 'replace-bundled-cddlib
4232 (lambda* (#:key inputs #:allow-other-keys)
4233 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4234 (local-dir "cddlib_guix"))
4236 (with-directory-excursion local-dir
4237 (system* "tar" "xvf" cddlib-src))
4238 (let ((cddlib-src-folder
4239 (string-append local-dir "/"
4240 (list-ref (scandir local-dir) 2)
4245 (string-append "cdd_src/" (basename file))))
4246 (find-files cddlib-src-folder ".*[ch]$")))
4248 (add-after 'unpack 'fix-makefile
4250 ;; Remove system calls to 'git'.
4251 (substitute* "Makefile"
4252 (("^DESCRIPT:=pplacer-.*")
4254 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4255 (substitute* "myocamlbuild.ml"
4256 (("git describe --tags --long .*\\\" with")
4258 "echo -n v" ,version "-" ,commit "\" with")))
4261 (lambda* (#:key outputs #:allow-other-keys)
4262 (let* ((out (assoc-ref outputs "out"))
4263 (bin (string-append out "/bin")))
4264 (copy-recursively "bin" bin))
4269 ("ocaml-ounit" ,ocaml4.01-ounit)
4270 ("ocaml-batteries" ,ocaml4.01-batteries)
4271 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4272 ("ocaml-csv" ,ocaml4.01-csv)
4273 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4274 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4275 ("ocaml-mcl" ,ocaml4.01-mcl)
4276 ("ocaml-gsl" ,ocaml4.01-gsl)
4277 ("cddlib-src" ,(package-source cddlib))))
4279 `(("pplacer-scripts" ,pplacer-scripts)))
4280 (synopsis "Phylogenetic placement of biological sequences")
4282 "Pplacer places query sequences on a fixed reference phylogenetic tree
4283 to maximize phylogenetic likelihood or posterior probability according to a
4284 reference alignment. Pplacer is designed to be fast, to give useful
4285 information about uncertainty, and to offer advanced visualization and
4286 downstream analysis.")
4287 (home-page "http://matsen.fhcrc.org/pplacer")
4288 (license license:gpl3))))
4290 ;; This package is installed alongside 'pplacer'. It is a separate package so
4291 ;; that it can use the python-build-system for the scripts that are
4292 ;; distributed alongside the main OCaml binaries.
4293 (define pplacer-scripts
4296 (name "pplacer-scripts")
4297 (build-system python-build-system)
4299 `(#:python ,python-2
4301 (modify-phases %standard-phases
4302 (add-after 'unpack 'enter-scripts-dir
4303 (lambda _ (chdir "scripts")))
4306 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4307 (add-after 'install 'wrap-executables
4308 (lambda* (#:key inputs outputs #:allow-other-keys)
4309 (let* ((out (assoc-ref outputs "out"))
4310 (bin (string-append out "/bin")))
4311 (let ((path (string-append
4312 (assoc-ref inputs "hmmer") "/bin:"
4313 (assoc-ref inputs "infernal") "/bin")))
4315 (wrap-program (string-append bin "/refpkg_align.py")
4316 `("PATH" ":" prefix (,path))))
4317 (let ((path (string-append
4318 (assoc-ref inputs "hmmer") "/bin")))
4319 (wrap-program (string-append bin "/hrefpkg_query.py")
4320 `("PATH" ":" prefix (,path)))))
4323 `(("infernal" ,infernal)
4326 `(("python-biopython" ,python2-biopython)
4327 ("taxtastic" ,taxtastic)))
4328 (synopsis "Pplacer Python scripts")))
4330 (define-public python2-pbcore
4332 (name "python2-pbcore")
4336 (uri (pypi-uri "pbcore" version))
4339 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4340 (build-system python-build-system)
4341 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4343 `(("python-cython" ,python2-cython)
4344 ("python-numpy" ,python2-numpy)
4345 ("python-pysam" ,python2-pysam)
4346 ("python-h5py" ,python2-h5py)))
4348 `(("python-nose" ,python2-nose)
4349 ("python-sphinx" ,python2-sphinx)
4350 ("python-pyxb" ,python2-pyxb)))
4351 (home-page "http://pacificbiosciences.github.io/pbcore/")
4352 (synopsis "Library for reading and writing PacBio data files")
4354 "The pbcore package provides Python APIs for interacting with PacBio data
4355 files and writing bioinformatics applications.")
4356 (license license:bsd-3)))
4358 (define-public python2-warpedlmm
4360 (name "python2-warpedlmm")
4366 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4370 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4371 (build-system python-build-system)
4373 `(#:python ,python-2)) ; requires Python 2.7
4375 `(("python-scipy" ,python2-scipy)
4376 ("python-numpy" ,python2-numpy)
4377 ("python-matplotlib" ,python2-matplotlib)
4378 ("python-fastlmm" ,python2-fastlmm)
4379 ("python-pandas" ,python2-pandas)
4380 ("python-pysnptools" ,python2-pysnptools)))
4382 `(("python-mock" ,python2-mock)
4383 ("python-nose" ,python2-nose)
4385 (home-page "https://github.com/PMBio/warpedLMM")
4386 (synopsis "Implementation of warped linear mixed models")
4388 "WarpedLMM is a Python implementation of the warped linear mixed model,
4389 which automatically learns an optimal warping function (or transformation) for
4390 the phenotype as it models the data.")
4391 (license license:asl2.0)))
4393 (define-public pbtranscript-tofu
4394 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4396 (name "pbtranscript-tofu")
4397 (version (string-append "2.2.3." (string-take commit 7)))
4401 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4403 (file-name (string-append name "-" version "-checkout"))
4406 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4407 (modules '((guix build utils)))
4410 ;; remove bundled Cython sources
4411 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4413 (build-system python-build-system)
4415 `(#:python ,python-2
4416 ;; FIXME: Tests fail with "No such file or directory:
4417 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4420 (modify-phases %standard-phases
4421 (add-after 'unpack 'enter-directory
4423 (chdir "pbtranscript-tofu/pbtranscript/")
4425 ;; With setuptools version 18.0 and later this setup.py hack causes
4426 ;; a build error, so we disable it.
4427 (add-after 'enter-directory 'patch-setuppy
4429 (substitute* "setup.py"
4430 (("if 'setuptools.extension' in sys.modules:")
4434 `(("python-numpy" ,python2-numpy)
4435 ("python-bx-python" ,python2-bx-python)
4436 ("python-networkx" ,python2-networkx)
4437 ("python-scipy" ,python2-scipy)
4438 ("python-pbcore" ,python2-pbcore)
4439 ("python-h5py" ,python2-h5py)))
4441 `(("python-cython" ,python2-cython)
4442 ("python-nose" ,python2-nose)))
4443 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4444 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4446 "pbtranscript-tofu contains scripts to analyze transcriptome data
4447 generated using the PacBio Iso-Seq protocol.")
4448 (license license:bsd-3))))
4450 (define-public prank
4457 "http://wasabiapp.org/download/prank/prank.source."
4461 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4462 (build-system gnu-build-system)
4465 (modify-phases %standard-phases
4466 (add-after 'unpack 'enter-src-dir
4470 (add-after 'unpack 'remove-m64-flag
4471 ;; Prank will build with the correct 'bit-ness' without this flag
4472 ;; and this allows building on 32-bit machines.
4473 (lambda _ (substitute* "src/Makefile"
4478 (lambda* (#:key outputs #:allow-other-keys)
4479 (let* ((out (assoc-ref outputs "out"))
4480 (bin (string-append out "/bin"))
4481 (man (string-append out "/share/man/man1"))
4482 (path (string-append
4483 (assoc-ref %build-inputs "mafft") "/bin:"
4484 (assoc-ref %build-inputs "exonerate") "/bin:"
4485 (assoc-ref %build-inputs "bppsuite") "/bin")))
4486 (install-file "prank" bin)
4487 (wrap-program (string-append bin "/prank")
4488 `("PATH" ":" prefix (,path)))
4489 (install-file "prank.1" man))
4493 ("exonerate" ,exonerate)
4494 ("bppsuite" ,bppsuite)))
4495 (home-page "http://wasabiapp.org/software/prank/")
4496 (synopsis "Probabilistic multiple sequence alignment program")
4498 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4499 codon and amino-acid sequences. It is based on a novel algorithm that treats
4500 insertions correctly and avoids over-estimation of the number of deletion
4501 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4502 in phylogenetics and correctly takes into account the evolutionary distances
4503 between sequences. Lastly, PRANK allows for defining a potential structure
4504 for sequences to be aligned and then, simultaneously with the alignment,
4505 predicts the locations of structural units in the sequences.")
4506 (license license:gpl2+)))
4508 (define-public proteinortho
4510 (name "proteinortho")
4517 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4518 version "_src.tar.gz"))
4521 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4522 (build-system gnu-build-system)
4524 `(#:test-target "test"
4526 (modify-phases %standard-phases
4528 ;; There is no configure script, so we modify the Makefile directly.
4529 (lambda* (#:key outputs #:allow-other-keys)
4530 (substitute* "Makefile"
4533 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4535 (add-before 'install 'make-install-directory
4536 ;; The install directory is not created during 'make install'.
4537 (lambda* (#:key outputs #:allow-other-keys)
4538 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4540 (add-after 'install 'wrap-programs
4541 (lambda* (#:key inputs outputs #:allow-other-keys)
4542 (let* ((path (getenv "PATH"))
4543 (out (assoc-ref outputs "out"))
4544 (binary (string-append out "/bin/proteinortho5.pl")))
4545 (wrap-program binary `("PATH" ":" prefix (,path))))
4549 ("python" ,python-2)
4550 ("blast+" ,blast+)))
4551 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4552 (synopsis "Detect orthologous genes across species")
4554 "Proteinortho is a tool to detect orthologous genes across different
4555 species. For doing so, it compares similarities of given gene sequences and
4556 clusters them to find significant groups. The algorithm was designed to handle
4557 large-scale data and can be applied to hundreds of species at once.")
4558 (license license:gpl2+)))
4560 (define-public pyicoteo
4567 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4568 "pyicoteo/get/v" version ".tar.bz2"))
4569 (file-name (string-append name "-" version ".tar.bz2"))
4572 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4573 (build-system python-build-system)
4575 `(#:python ,python-2 ; does not work with Python 3
4576 #:tests? #f)) ; there are no tests
4578 `(("python2-matplotlib" ,python2-matplotlib)))
4579 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4580 (synopsis "Analyze high-throughput genetic sequencing data")
4582 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4583 sequencing data. It works with genomic coordinates. There are currently six
4584 different command-line tools:
4587 @item pyicoregion: for generating exploratory regions automatically;
4588 @item pyicoenrich: for differential enrichment between two conditions;
4589 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4590 @item pyicos: for genomic coordinates manipulation;
4591 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4592 @item pyicount: to count how many reads from N experiment files overlap in a
4594 @item pyicotrocol: to combine operations from pyicoteo.
4596 (license license:gpl3+)))
4598 (define-public prodigal
4605 "https://github.com/hyattpd/Prodigal/archive/v"
4607 (file-name (string-append name "-" version ".tar.gz"))
4610 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4611 (build-system gnu-build-system)
4613 `(#:tests? #f ;no check target
4614 #:make-flags (list (string-append "INSTALLDIR="
4615 (assoc-ref %outputs "out")
4618 (modify-phases %standard-phases
4619 (delete 'configure))))
4620 (home-page "http://prodigal.ornl.gov")
4621 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4623 "Prodigal runs smoothly on finished genomes, draft genomes, and
4624 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4625 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4626 partial genes, and identifies translation initiation sites.")
4627 (license license:gpl3+)))
4629 (define-public roary
4637 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4641 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4642 (build-system perl-build-system)
4645 (modify-phases %standard-phases
4650 ;; The tests are not run by default, so we run each test file
4652 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4654 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4655 (getenv "PERL5LIB")))
4656 (zero? (length (filter (lambda (file)
4657 (display file)(display "\n")
4658 (not (zero? (system* "perl" file))))
4659 (find-files "t" ".*\\.t$"))))))
4661 ;; There is no 'install' target in the Makefile.
4662 (lambda* (#:key outputs #:allow-other-keys)
4663 (let* ((out (assoc-ref outputs "out"))
4664 (bin (string-append out "/bin"))
4665 (perl (string-append out "/lib/perl5/site_perl"))
4666 (roary-plots "contrib/roary_plots"))
4669 (copy-recursively "bin" bin)
4670 (copy-recursively "lib" perl)
4672 (add-after 'install 'wrap-programs
4673 (lambda* (#:key inputs outputs #:allow-other-keys)
4674 (let* ((out (assoc-ref outputs "out"))
4675 (perl5lib (getenv "PERL5LIB"))
4676 (path (getenv "PATH")))
4677 (for-each (lambda (prog)
4678 (let ((binary (string-append out "/" prog)))
4679 (wrap-program binary
4680 `("PERL5LIB" ":" prefix
4681 (,(string-append perl5lib ":" out
4682 "/lib/perl5/site_perl"))))
4683 (wrap-program binary
4685 (,(string-append path ":" out "/bin"))))))
4686 (find-files "bin" ".*[^R]$"))
4688 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4689 (r-site-lib (getenv "R_LIBS_SITE"))
4691 (string-append (assoc-ref inputs "coreutils") "/bin")))
4693 `("R_LIBS_SITE" ":" prefix
4694 (,(string-append r-site-lib ":" out "/site-library/"))))
4697 (,(string-append coreutils-path ":" out "/bin"))))))
4700 `(("perl-env-path" ,perl-env-path)
4701 ("perl-test-files" ,perl-test-files)
4702 ("perl-test-most" ,perl-test-most)
4703 ("perl-test-output" ,perl-test-output)))
4705 `(("perl-array-utils" ,perl-array-utils)
4706 ("bioperl" ,bioperl-minimal)
4707 ("perl-digest-md5-file" ,perl-digest-md5-file)
4708 ("perl-exception-class" ,perl-exception-class)
4709 ("perl-file-find-rule" ,perl-file-find-rule)
4710 ("perl-file-grep" ,perl-file-grep)
4711 ("perl-file-slurper" ,perl-file-slurper)
4712 ("perl-file-which" ,perl-file-which)
4713 ("perl-graph" ,perl-graph)
4714 ("perl-graph-readwrite" ,perl-graph-readwrite)
4715 ("perl-log-log4perl" ,perl-log-log4perl)
4716 ("perl-moose" ,perl-moose)
4717 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4718 ("perl-text-csv" ,perl-text-csv)
4719 ("bedtools" ,bedtools)
4723 ("parallel" ,parallel)
4726 ("fasttree" ,fasttree)
4730 ("r-minimal" ,r-minimal)
4731 ("r-ggplot2" ,r-ggplot2)
4732 ("coreutils" ,coreutils)))
4733 (home-page "http://sanger-pathogens.github.io/Roary")
4734 (synopsis "High speed stand-alone pan genome pipeline")
4736 "Roary is a high speed stand alone pan genome pipeline, which takes
4737 annotated assemblies in GFF3 format (produced by the Prokka program) and
4738 calculates the pan genome. Using a standard desktop PC, it can analyse
4739 datasets with thousands of samples, without compromising the quality of the
4740 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4741 single processor. Roary is not intended for metagenomics or for comparing
4742 extremely diverse sets of genomes.")
4743 (license license:gpl3)))
4745 (define-public raxml
4754 "https://github.com/stamatak/standard-RAxML/archive/v"
4756 (file-name (string-append name "-" version ".tar.gz"))
4759 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4760 (build-system gnu-build-system)
4762 `(#:tests? #f ; There are no tests.
4763 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4764 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4766 (modify-phases %standard-phases
4769 (lambda* (#:key outputs #:allow-other-keys)
4770 (let* ((out (assoc-ref outputs "out"))
4771 (bin (string-append out "/bin"))
4772 (executable "raxmlHPC-HYBRID"))
4773 (install-file executable bin)
4774 (symlink (string-append bin "/" executable) "raxml"))
4777 `(("openmpi" ,openmpi)))
4778 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4779 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4781 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4783 ;; The source includes x86 specific code
4784 (supported-systems '("x86_64-linux" "i686-linux"))
4785 (license license:gpl2+)))
4795 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4798 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4799 (patches (search-patches "rsem-makefile.patch"))
4800 (modules '((guix build utils)))
4803 ;; remove bundled copy of boost
4804 (delete-file-recursively "boost")
4806 (build-system gnu-build-system)
4808 `(#:tests? #f ;no "check" target
4810 (modify-phases %standard-phases
4811 ;; No "configure" script.
4812 ;; Do not build bundled samtools library.
4815 (substitute* "Makefile"
4816 (("^all : sam/libbam.a") "all : "))
4819 (lambda* (#:key outputs #:allow-other-keys)
4820 (let* ((out (string-append (assoc-ref outputs "out")))
4821 (bin (string-append out "/bin/"))
4822 (perl (string-append out "/lib/perl5/site_perl")))
4825 (for-each (lambda (file)
4826 (install-file file bin))
4827 (find-files "." "rsem-.*"))
4828 (install-file "rsem_perl_utils.pm" perl))
4831 'install 'wrap-program
4832 (lambda* (#:key outputs #:allow-other-keys)
4833 (let ((out (assoc-ref outputs "out")))
4834 (for-each (lambda (prog)
4835 (wrap-program (string-append out "/bin/" prog)
4836 `("PERL5LIB" ":" prefix
4837 (,(string-append out "/lib/perl5/site_perl")))))
4838 '("rsem-plot-transcript-wiggles"
4839 "rsem-calculate-expression"
4840 "rsem-generate-ngvector"
4842 "rsem-prepare-reference")))
4846 ("ncurses" ,ncurses)
4847 ("r-minimal" ,r-minimal)
4849 ("samtools" ,samtools-0.1)
4851 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4852 (synopsis "Estimate gene expression levels from RNA-Seq data")
4854 "RSEM is a software package for estimating gene and isoform expression
4855 levels from RNA-Seq data. The RSEM package provides a user-friendly
4856 interface, supports threads for parallel computation of the EM algorithm,
4857 single-end and paired-end read data, quality scores, variable-length reads and
4858 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4859 interval estimates for expression levels. For visualization, it can generate
4860 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4861 (license license:gpl3+)))
4863 (define-public rseqc
4871 (string-append "mirror://sourceforge/rseqc/"
4872 "RSeQC-" version ".tar.gz"))
4874 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4875 (modules '((guix build utils)))
4878 ;; remove bundled copy of pysam
4879 (delete-file-recursively "lib/pysam")
4880 (substitute* "setup.py"
4881 ;; remove dependency on outdated "distribute" module
4882 (("^from distribute_setup import use_setuptools") "")
4883 (("^use_setuptools\\(\\)") "")
4884 ;; do not use bundled copy of pysam
4885 (("^have_pysam = False") "have_pysam = True"))
4887 (build-system python-build-system)
4888 (arguments `(#:python ,python-2))
4890 `(("python-cython" ,python2-cython)
4891 ("python-pysam" ,python2-pysam)
4892 ("python-numpy" ,python2-numpy)
4895 `(("python-nose" ,python2-nose)))
4896 (home-page "http://rseqc.sourceforge.net/")
4897 (synopsis "RNA-seq quality control package")
4899 "RSeQC provides a number of modules that can comprehensively evaluate
4900 high throughput sequence data, especially RNA-seq data. Some basic modules
4901 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4902 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4903 distribution, coverage uniformity, strand specificity, etc.")
4904 (license license:gpl3+)))
4907 ;; There are no release tarballs. According to the installation
4908 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4909 ;; stable release is identified by this changeset ID.
4910 (let ((changeset "2329130")
4914 (version (string-append "0-" revision "." changeset))
4918 (url "https://bitbucket.org/libsleipnir/sleipnir")
4919 (changeset changeset)))
4920 (file-name (string-append name "-" version "-checkout"))
4923 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4924 (build-system gnu-build-system)
4926 `(#:modules ((srfi srfi-1)
4927 (guix build gnu-build-system)
4930 (let ((dirs '("SeekMiner"
4936 (modify-phases %standard-phases
4939 (invoke "bash" "gen_auto")))
4940 (add-after 'build 'build-additional-tools
4941 (lambda* (#:key make-flags #:allow-other-keys)
4942 (every (lambda (dir)
4943 (with-directory-excursion (string-append "tools/" dir)
4944 (zero? (apply system* "make" make-flags))))
4946 (add-after 'install 'install-additional-tools
4947 (lambda* (#:key make-flags #:allow-other-keys)
4948 (fold (lambda (dir result)
4949 (with-directory-excursion (string-append "tools/" dir)
4951 (zero? (apply system*
4952 `("make" ,@make-flags "install"))))))
4958 ("readline" ,readline)
4959 ("gengetopt" ,gengetopt)
4960 ("log4cpp" ,log4cpp)))
4962 `(("autoconf" ,autoconf)
4963 ("automake" ,automake)
4965 (home-page "http://seek.princeton.edu")
4966 (synopsis "Gene co-expression search engine")
4968 "SEEK is a computational gene co-expression search engine. SEEK provides
4969 biologists with a way to navigate the massive human expression compendium that
4970 now contains thousands of expression datasets. SEEK returns a robust ranking
4971 of co-expressed genes in the biological area of interest defined by the user's
4972 query genes. It also prioritizes thousands of expression datasets according
4973 to the user's query of interest.")
4974 (license license:cc-by3.0))))
4976 (define-public samtools
4984 (string-append "mirror://sourceforge/samtools/samtools/"
4985 version "/samtools-" version ".tar.bz2"))
4988 "05myg7bs90i68qbqab9cdg9rqj2xh39azibrx82ipzc5kcfvqhn9"))))
4989 (build-system gnu-build-system)
4991 `(#:modules ((ice-9 ftw)
4993 (guix build gnu-build-system)
4995 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4996 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4998 (modify-phases %standard-phases
4999 (add-after 'unpack 'patch-tests
5001 (substitute* "test/test.pl"
5002 ;; The test script calls out to /bin/bash
5003 (("/bin/bash") (which "bash")))
5005 (add-after 'install 'install-library
5006 (lambda* (#:key outputs #:allow-other-keys)
5007 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5008 (install-file "libbam.a" lib)
5010 (add-after 'install 'install-headers
5011 (lambda* (#:key outputs #:allow-other-keys)
5012 (let ((include (string-append (assoc-ref outputs "out")
5013 "/include/samtools/")))
5014 (for-each (lambda (file)
5015 (install-file file include))
5016 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5018 (native-inputs `(("pkg-config" ,pkg-config)))
5020 `(("htslib" ,htslib)
5021 ("ncurses" ,ncurses)
5025 (home-page "http://samtools.sourceforge.net")
5026 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5028 "Samtools implements various utilities for post-processing nucleotide
5029 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5030 variant calling (in conjunction with bcftools), and a simple alignment
5032 (license license:expat)))
5034 (define-public samtools-0.1
5035 ;; This is the most recent version of the 0.1 line of samtools. The input
5036 ;; and output formats differ greatly from that used and produced by samtools
5037 ;; 1.x and is still used in many bioinformatics pipelines.
5038 (package (inherit samtools)
5044 (string-append "mirror://sourceforge/samtools/samtools/"
5045 version "/samtools-" version ".tar.bz2"))
5047 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5049 `(#:tests? #f ;no "check" target
5050 ,@(substitute-keyword-arguments (package-arguments samtools)
5051 ((#:make-flags flags)
5052 `(cons "LIBCURSES=-lncurses" ,flags))
5054 `(modify-phases ,phases
5056 (lambda* (#:key outputs #:allow-other-keys)
5057 (let ((bin (string-append
5058 (assoc-ref outputs "out") "/bin")))
5060 (install-file "samtools" bin)
5062 (delete 'patch-tests)
5063 (delete 'configure))))))))
5065 (define-public mosaik
5066 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5071 ;; There are no release tarballs nor tags.
5074 (url "https://github.com/wanpinglee/MOSAIK.git")
5076 (file-name (string-append name "-" version))
5079 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5080 (build-system gnu-build-system)
5082 `(#:tests? #f ; no tests
5083 #:make-flags (list "CC=gcc")
5085 (modify-phases %standard-phases
5087 (lambda _ (chdir "src") #t))
5089 (lambda* (#:key outputs #:allow-other-keys)
5090 (let ((bin (string-append (assoc-ref outputs "out")
5093 (copy-recursively "../bin" bin)
5098 (supported-systems '("x86_64-linux"))
5099 (home-page "https://github.com/wanpinglee/MOSAIK")
5100 (synopsis "Map nucleotide sequence reads to reference genomes")
5102 "MOSAIK is a program for mapping second and third-generation sequencing
5103 reads to a reference genome. MOSAIK can align reads generated by all the
5104 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5105 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5106 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5107 ;; code released into the public domain:
5108 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5109 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5110 (license (list license:gpl2+ license:public-domain)))))
5112 (define-public ngs-sdk
5120 (string-append "https://github.com/ncbi/ngs/archive/"
5122 (file-name (string-append name "-" version ".tar.gz"))
5125 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5126 (build-system gnu-build-system)
5128 `(#:parallel-build? #f ; not supported
5129 #:tests? #f ; no "check" target
5131 (modify-phases %standard-phases
5133 (lambda* (#:key outputs #:allow-other-keys)
5134 (let ((out (assoc-ref outputs "out")))
5135 ;; Allow 'konfigure.perl' to find 'package.prl'.
5137 (string-append ".:" (getenv "PERL5LIB")))
5139 ;; The 'configure' script doesn't recognize things like
5140 ;; '--enable-fast-install'.
5141 (zero? (system* "./configure"
5142 (string-append "--build-prefix=" (getcwd) "/build")
5143 (string-append "--prefix=" out))))))
5144 (add-after 'unpack 'enter-dir
5145 (lambda _ (chdir "ngs-sdk") #t)))))
5146 (native-inputs `(("perl" ,perl)))
5147 ;; According to the test
5148 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5149 ;; in ngs-sdk/setup/konfigure.perl
5150 (supported-systems '("i686-linux" "x86_64-linux"))
5151 (home-page "https://github.com/ncbi/ngs")
5152 (synopsis "API for accessing Next Generation Sequencing data")
5154 "NGS is a domain-specific API for accessing reads, alignments and pileups
5155 produced from Next Generation Sequencing. The API itself is independent from
5156 any particular back-end implementation, and supports use of multiple back-ends
5158 (license license:public-domain)))
5160 (define-public java-ngs
5161 (package (inherit ngs-sdk)
5164 `(,@(substitute-keyword-arguments
5165 `(#:modules ((guix build gnu-build-system)
5169 ,@(package-arguments ngs-sdk))
5171 `(modify-phases ,phases
5172 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5174 `(("jdk" ,icedtea "jdk")
5175 ("ngs-sdk" ,ngs-sdk)))
5176 (synopsis "Java bindings for NGS SDK")))
5178 (define-public ncbi-vdb
5186 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5188 (file-name (string-append name "-" version ".tar.gz"))
5191 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5192 (build-system gnu-build-system)
5194 `(#:parallel-build? #f ; not supported
5195 #:tests? #f ; no "check" target
5197 (modify-phases %standard-phases
5198 (add-before 'configure 'set-perl-search-path
5200 ;; Work around "dotless @INC" build failure.
5202 (string-append (getcwd) "/setup:"
5203 (getenv "PERL5LIB")))
5206 (lambda* (#:key inputs outputs #:allow-other-keys)
5207 (let ((out (assoc-ref outputs "out")))
5208 ;; Override include path for libmagic
5209 (substitute* "setup/package.prl"
5210 (("name => 'magic', Include => '/usr/include'")
5211 (string-append "name=> 'magic', Include => '"
5212 (assoc-ref inputs "libmagic")
5215 ;; Install kdf5 library (needed by sra-tools)
5216 (substitute* "build/Makefile.install"
5217 (("LIBRARIES_TO_INSTALL =")
5218 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5220 (substitute* "build/Makefile.env"
5221 (("CFLAGS =" prefix)
5222 (string-append prefix "-msse2 ")))
5224 ;; Override search path for ngs-java
5225 (substitute* "setup/package.prl"
5226 (("/usr/local/ngs/ngs-java")
5227 (assoc-ref inputs "java-ngs")))
5229 ;; The 'configure' script doesn't recognize things like
5230 ;; '--enable-fast-install'.
5233 (string-append "--build-prefix=" (getcwd) "/build")
5234 (string-append "--prefix=" (assoc-ref outputs "out"))
5235 (string-append "--debug")
5236 (string-append "--with-xml2-prefix="
5237 (assoc-ref inputs "libxml2"))
5238 (string-append "--with-ngs-sdk-prefix="
5239 (assoc-ref inputs "ngs-sdk"))
5240 (string-append "--with-hdf5-prefix="
5241 (assoc-ref inputs "hdf5")))))))
5242 (add-after 'install 'install-interfaces
5243 (lambda* (#:key outputs #:allow-other-keys)
5244 ;; Install interface libraries. On i686 the interface libraries
5245 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5246 ;; architecture name ("i386") instead of the target system prefix
5248 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5249 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5250 ,(system->linux-architecture
5251 (or (%current-target-system)
5254 (string-append (assoc-ref outputs "out")
5256 ;; Install interface headers
5257 (copy-recursively "interfaces"
5258 (string-append (assoc-ref outputs "out")
5261 ;; These files are needed by sra-tools.
5262 (add-after 'install 'install-configuration-files
5263 (lambda* (#:key outputs #:allow-other-keys)
5264 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5266 (install-file "libs/kfg/default.kfg" target)
5267 (install-file "libs/kfg/certs.kfg" target))
5270 `(("libxml2" ,libxml2)
5271 ("ngs-sdk" ,ngs-sdk)
5272 ("java-ngs" ,java-ngs)
5275 (native-inputs `(("perl" ,perl)))
5276 ;; NCBI-VDB requires SSE capability.
5277 (supported-systems '("i686-linux" "x86_64-linux"))
5278 (home-page "https://github.com/ncbi/ncbi-vdb")
5279 (synopsis "Database engine for genetic information")
5281 "The NCBI-VDB library implements a highly compressed columnar data
5282 warehousing engine that is most often used to store genetic information.
5283 Databases are stored in a portable image within the file system, and can be
5284 accessed/downloaded on demand across HTTP.")
5285 (license license:public-domain)))
5287 (define-public plink
5295 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5296 version "-src.zip"))
5298 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5299 (patches (search-patches "plink-1.07-unclobber-i.patch"
5300 "plink-endian-detection.patch"))))
5301 (build-system gnu-build-system)
5303 '(#:tests? #f ;no "check" target
5304 #:make-flags (list (string-append "LIB_LAPACK="
5305 (assoc-ref %build-inputs "lapack")
5306 "/lib/liblapack.so")
5309 ;; disable phoning home
5312 (modify-phases %standard-phases
5313 ;; no "configure" script
5316 (lambda* (#:key outputs #:allow-other-keys)
5317 (let ((bin (string-append (assoc-ref outputs "out")
5319 (install-file "plink" bin)
5323 ("lapack" ,lapack)))
5325 `(("unzip" ,unzip)))
5326 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5327 (synopsis "Whole genome association analysis toolset")
5329 "PLINK is a whole genome association analysis toolset, designed to
5330 perform a range of basic, large-scale analyses in a computationally efficient
5331 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5332 so there is no support for steps prior to this (e.g. study design and
5333 planning, generating genotype or CNV calls from raw data). Through
5334 integration with gPLINK and Haploview, there is some support for the
5335 subsequent visualization, annotation and storage of results.")
5336 ;; Code is released under GPLv2, except for fisher.h, which is under
5338 (license (list license:gpl2 license:lgpl2.1+))))
5340 (define-public plink-ng
5341 (package (inherit plink)
5347 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5349 (file-name (string-append name "-" version ".tar.gz"))
5351 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5352 (build-system gnu-build-system)
5354 '(#:tests? #f ;no "check" target
5355 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5356 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5358 "-f" "Makefile.std")
5360 (modify-phases %standard-phases
5361 (add-after 'unpack 'chdir
5362 (lambda _ (chdir "1.9") #t))
5363 (delete 'configure) ; no "configure" script
5365 (lambda* (#:key outputs #:allow-other-keys)
5366 (let ((bin (string-append (assoc-ref outputs "out")
5368 (install-file "plink" bin)
5373 ("openblas" ,openblas)))
5374 (home-page "https://www.cog-genomics.org/plink/")
5375 (license license:gpl3+)))
5377 (define-public smithlab-cpp
5378 (let ((revision "1")
5379 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5381 (name "smithlab-cpp")
5382 (version (string-append "0." revision "." (string-take commit 7)))
5386 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5388 (file-name (string-append name "-" version "-checkout"))
5391 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5392 (build-system gnu-build-system)
5394 `(#:modules ((guix build gnu-build-system)
5397 #:tests? #f ;no "check" target
5399 (modify-phases %standard-phases
5400 (add-after 'unpack 'use-samtools-headers
5402 (substitute* '("SAM.cpp"
5404 (("sam.h") "samtools/sam.h"))
5407 (lambda* (#:key outputs #:allow-other-keys)
5408 (let* ((out (assoc-ref outputs "out"))
5409 (lib (string-append out "/lib"))
5410 (include (string-append out "/include/smithlab-cpp")))
5413 (for-each (cut install-file <> lib)
5414 (find-files "." "\\.o$"))
5415 (for-each (cut install-file <> include)
5416 (find-files "." "\\.hpp$")))
5418 (delete 'configure))))
5420 `(("samtools" ,samtools-0.1)
5422 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5423 (synopsis "C++ helper library for functions used in Smith lab projects")
5425 "Smithlab CPP is a C++ library that includes functions used in many of
5426 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5427 structures, classes for genomic regions, mapped sequencing reads, etc.")
5428 (license license:gpl3+))))
5430 (define-public preseq
5436 (uri (string-append "https://github.com/smithlabcode/"
5437 "preseq/archive/v" version ".tar.gz"))
5438 (file-name (string-append name "-" version ".tar.gz"))
5440 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5441 (modules '((guix build utils)))
5443 ;; Remove bundled samtools.
5444 (delete-file-recursively "samtools")
5446 (build-system gnu-build-system)
5448 `(#:tests? #f ;no "check" target
5450 (modify-phases %standard-phases
5451 (delete 'configure))
5453 (list (string-append "PREFIX="
5454 (assoc-ref %outputs "out"))
5455 (string-append "LIBBAM="
5456 (assoc-ref %build-inputs "samtools")
5458 (string-append "SMITHLAB_CPP="
5459 (assoc-ref %build-inputs "smithlab-cpp")
5462 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5465 ("samtools" ,samtools-0.1)
5466 ("smithlab-cpp" ,smithlab-cpp)
5468 (home-page "http://smithlabresearch.org/software/preseq/")
5469 (synopsis "Program for analyzing library complexity")
5471 "The preseq package is aimed at predicting and estimating the complexity
5472 of a genomic sequencing library, equivalent to predicting and estimating the
5473 number of redundant reads from a given sequencing depth and how many will be
5474 expected from additional sequencing using an initial sequencing experiment.
5475 The estimates can then be used to examine the utility of further sequencing,
5476 optimize the sequencing depth, or to screen multiple libraries to avoid low
5477 complexity samples.")
5478 (license license:gpl3+)))
5480 (define-public python-screed
5482 (name "python-screed")
5487 (uri (pypi-uri "screed" version))
5490 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5491 (build-system python-build-system)
5494 (modify-phases %standard-phases
5497 (setenv "PYTHONPATH"
5498 (string-append (getenv "PYTHONPATH") ":."))
5499 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5501 `(("python-nose" ,python-nose)))
5503 `(("python-bz2file" ,python-bz2file)))
5504 (home-page "https://github.com/dib-lab/screed/")
5505 (synopsis "Short read sequence database utilities")
5506 (description "Screed parses FASTA and FASTQ files and generates databases.
5507 Values such as sequence name, sequence description, sequence quality and the
5508 sequence itself can be retrieved from these databases.")
5509 (license license:bsd-3)))
5511 (define-public python2-screed
5512 (package-with-python2 python-screed))
5514 (define-public sra-tools
5522 (string-append "https://github.com/ncbi/sra-tools/archive/"
5524 (file-name (string-append name "-" version ".tar.gz"))
5527 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5528 (build-system gnu-build-system)
5530 `(#:parallel-build? #f ; not supported
5531 #:tests? #f ; no "check" target
5533 (list (string-append "DEFAULT_CRT="
5534 (assoc-ref %build-inputs "ncbi-vdb")
5536 (string-append "DEFAULT_KFG="
5537 (assoc-ref %build-inputs "ncbi-vdb")
5539 (string-append "VDB_LIBDIR="
5540 (assoc-ref %build-inputs "ncbi-vdb")
5541 ,(if (string-prefix? "x86_64"
5542 (or (%current-target-system)
5547 (modify-phases %standard-phases
5548 (add-before 'configure 'set-perl-search-path
5550 ;; Work around "dotless @INC" build failure.
5552 (string-append (getcwd) "/setup:"
5553 (getenv "PERL5LIB")))
5556 (lambda* (#:key inputs outputs #:allow-other-keys)
5557 ;; The build system expects a directory containing the sources and
5558 ;; raw build output of ncbi-vdb, including files that are not
5559 ;; installed. Since we are building against an installed version of
5560 ;; ncbi-vdb, the following modifications are needed.
5561 (substitute* "setup/konfigure.perl"
5562 ;; Make the configure script look for the "ilib" directory of
5563 ;; "ncbi-vdb" without first checking for the existence of a
5564 ;; matching library in its "lib" directory.
5565 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5566 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5567 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5568 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5569 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5572 (substitute* "tools/copycat/Makefile"
5573 (("smagic-static") "lmagic"))
5575 ;; The 'configure' script doesn't recognize things like
5576 ;; '--enable-fast-install'.
5579 (string-append "--build-prefix=" (getcwd) "/build")
5580 (string-append "--prefix=" (assoc-ref outputs "out"))
5581 (string-append "--debug")
5582 (string-append "--with-fuse-prefix="
5583 (assoc-ref inputs "fuse"))
5584 (string-append "--with-magic-prefix="
5585 (assoc-ref inputs "libmagic"))
5586 ;; TODO: building with libxml2 fails with linker errors
5587 ;; (string-append "--with-xml2-prefix="
5588 ;; (assoc-ref inputs "libxml2"))
5589 (string-append "--with-ncbi-vdb-sources="
5590 (assoc-ref inputs "ncbi-vdb"))
5591 (string-append "--with-ncbi-vdb-build="
5592 (assoc-ref inputs "ncbi-vdb"))
5593 (string-append "--with-ngs-sdk-prefix="
5594 (assoc-ref inputs "ngs-sdk"))
5595 (string-append "--with-hdf5-prefix="
5596 (assoc-ref inputs "hdf5"))))))
5597 ;; This version of sra-tools fails to build with glibc because of a
5598 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5599 ;; contains a definition of "canonicalize", so we rename it.
5601 ;; See upstream bug report:
5602 ;; https://github.com/ncbi/sra-tools/issues/67
5603 (add-after 'unpack 'patch-away-glibc-conflict
5605 (substitute* "tools/bam-loader/bam.c"
5606 (("canonicalize\\(" line)
5607 (string-append "sra_tools_" line)))
5609 (native-inputs `(("perl" ,perl)))
5611 `(("ngs-sdk" ,ngs-sdk)
5612 ("ncbi-vdb" ,ncbi-vdb)
5617 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5618 (synopsis "Tools and libraries for reading and writing sequencing data")
5620 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5621 reading of sequencing files from the Sequence Read Archive (SRA) database and
5622 writing files into the .sra format.")
5623 (license license:public-domain)))
5625 (define-public seqan
5631 (uri (string-append "http://packages.seqan.de/seqan-library/"
5632 "seqan-library-" version ".tar.bz2"))
5635 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5636 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5637 ;; makes sense to split the outputs.
5638 (outputs '("out" "doc"))
5639 (build-system trivial-build-system)
5641 `(#:modules ((guix build utils))
5644 (use-modules (guix build utils))
5645 (let ((tar (assoc-ref %build-inputs "tar"))
5646 (bzip (assoc-ref %build-inputs "bzip2"))
5647 (out (assoc-ref %outputs "out"))
5648 (doc (assoc-ref %outputs "doc")))
5649 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5650 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5651 (chdir (string-append "seqan-library-" ,version))
5652 (copy-recursively "include" (string-append out "/include"))
5653 (copy-recursively "share" (string-append doc "/share"))
5656 `(("source" ,source)
5659 (home-page "http://www.seqan.de")
5660 (synopsis "Library for nucleotide sequence analysis")
5662 "SeqAn is a C++ library of efficient algorithms and data structures for
5663 the analysis of sequences with the focus on biological data. It contains
5664 algorithms and data structures for string representation and their
5665 manipulation, online and indexed string search, efficient I/O of
5666 bioinformatics file formats, sequence alignment, and more.")
5667 (license license:bsd-3)))
5669 (define-public seqmagick
5676 (uri (pypi-uri "seqmagick" version))
5679 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5680 (build-system python-build-system)
5682 `(("python-biopython" ,python-biopython)))
5684 `(("python-nose" ,python-nose)))
5685 (home-page "https://github.com/fhcrc/seqmagick")
5686 (synopsis "Tools for converting and modifying sequence files")
5688 "Bioinformaticians often have to convert sequence files between formats
5689 and do little manipulations on them, and it's not worth writing scripts for
5690 that. Seqmagick is a utility to expose the file format conversion in
5691 BioPython in a convenient way. Instead of having a big mess of scripts, there
5692 is one that takes arguments.")
5693 (license license:gpl3)))
5695 (define-public seqtk
5702 "https://github.com/lh3/seqtk/archive/v"
5704 (file-name (string-append name "-" version ".tar.gz"))
5707 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5708 (modules '((guix build utils)))
5711 ;; Remove extraneous header files, as is done in the seqtk
5713 (for-each (lambda (file) (delete-file file))
5714 (list "ksort.h" "kstring.h" "kvec.h"))
5716 (build-system gnu-build-system)
5719 (modify-phases %standard-phases
5722 ;; There are no tests, so we just run a sanity check.
5723 (lambda _ (zero? (system* "./seqtk" "seq"))))
5725 (lambda* (#:key outputs #:allow-other-keys)
5726 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5727 (install-file "seqtk" bin)))))))
5730 (home-page "https://github.com/lh3/seqtk")
5731 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5733 "Seqtk is a fast and lightweight tool for processing sequences in the
5734 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5735 optionally compressed by gzip.")
5736 (license license:expat)))
5738 (define-public snap-aligner
5740 (name "snap-aligner")
5741 (version "1.0beta.18")
5745 "https://github.com/amplab/snap/archive/v"
5747 (file-name (string-append name "-" version ".tar.gz"))
5750 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5751 (build-system gnu-build-system)
5754 (modify-phases %standard-phases
5756 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5758 (lambda* (#:key outputs #:allow-other-keys)
5759 (let* ((out (assoc-ref outputs "out"))
5760 (bin (string-append out "/bin")))
5761 (install-file "snap-aligner" bin)
5762 (install-file "SNAPCommand" bin)
5766 (home-page "http://snap.cs.berkeley.edu/")
5767 (synopsis "Short read DNA sequence aligner")
5769 "SNAP is a fast and accurate aligner for short DNA reads. It is
5770 optimized for modern read lengths of 100 bases or higher, and takes advantage
5771 of these reads to align data quickly through a hash-based indexing scheme.")
5772 ;; 32-bit systems are not supported by the unpatched code.
5773 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5774 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5775 ;; systems without a lot of memory cannot make good use of this program.
5776 (supported-systems '("x86_64-linux"))
5777 (license license:asl2.0)))
5779 (define-public sortmerna
5787 "https://github.com/biocore/sortmerna/archive/"
5789 (file-name (string-append name "-" version ".tar.gz"))
5792 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5793 (build-system gnu-build-system)
5794 (outputs '("out" ;for binaries
5795 "db")) ;for sequence databases
5798 (modify-phases %standard-phases
5800 (lambda* (#:key outputs #:allow-other-keys)
5801 (let* ((out (assoc-ref outputs "out"))
5802 (bin (string-append out "/bin"))
5803 (db (assoc-ref outputs "db"))
5805 (string-append db "/share/sortmerna/rRNA_databases")))
5806 (install-file "sortmerna" bin)
5807 (install-file "indexdb_rna" bin)
5808 (for-each (lambda (file)
5809 (install-file file share))
5810 (find-files "rRNA_databases" ".*fasta"))
5814 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5815 (synopsis "Biological sequence analysis tool for NGS reads")
5817 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5818 and operational taxonomic unit (OTU) picking of next generation
5819 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5820 allows for fast and sensitive analyses of nucleotide sequences. The main
5821 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5822 ;; The source includes x86 specific code
5823 (supported-systems '("x86_64-linux" "i686-linux"))
5824 (license license:lgpl3)))
5833 (url "https://github.com/alexdobin/STAR.git")
5835 (file-name (string-append name "-" version "-checkout"))
5838 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
5839 (modules '((guix build utils)))
5842 (substitute* "source/Makefile"
5844 ;; Remove pre-built binaries and bundled htslib sources.
5845 (delete-file-recursively "bin/MacOSX_x86_64")
5846 (delete-file-recursively "bin/Linux_x86_64")
5847 (delete-file-recursively "bin/Linux_x86_64_static")
5848 (delete-file-recursively "source/htslib")
5850 (build-system gnu-build-system)
5852 '(#:tests? #f ;no check target
5853 #:make-flags '("STAR")
5855 (modify-phases %standard-phases
5856 (add-after 'unpack 'enter-source-dir
5857 (lambda _ (chdir "source") #t))
5858 (add-after 'enter-source-dir 'make-reproducible
5860 (substitute* "Makefile"
5861 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5862 (string-append pre "Built with Guix" post)))))
5863 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5865 (substitute* "Makefile"
5866 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5868 (substitute* '("BAMfunctions.cpp"
5873 "bamRemoveDuplicates.cpp")
5874 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5875 (string-append "#include <" header ">")))
5876 (substitute* "IncludeDefine.h"
5877 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5878 (string-append "<" header ">")))
5881 (lambda* (#:key outputs #:allow-other-keys)
5882 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5883 (install-file "STAR" bin))
5885 (delete 'configure))))
5889 `(("htslib" ,htslib)
5891 (home-page "https://github.com/alexdobin/STAR")
5892 (synopsis "Universal RNA-seq aligner")
5894 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5895 based on a previously undescribed RNA-seq alignment algorithm that uses
5896 sequential maximum mappable seed search in uncompressed suffix arrays followed
5897 by seed clustering and stitching procedure. In addition to unbiased de novo
5898 detection of canonical junctions, STAR can discover non-canonical splices and
5899 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5901 ;; Only 64-bit systems are supported according to the README.
5902 (supported-systems '("x86_64-linux" "mips64el-linux"))
5903 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5904 (license license:gpl3+)))
5906 (define-public subread
5912 (uri (string-append "mirror://sourceforge/subread/subread-"
5913 version "/subread-" version "-source.tar.gz"))
5916 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5917 (build-system gnu-build-system)
5919 `(#:tests? #f ;no "check" target
5920 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5921 ;; optimizations by default, so we override these flags such that x86_64
5922 ;; flags are only added when the build target is an x86_64 system.
5924 (list (let ((system ,(or (%current-target-system)
5926 (flags '("-ggdb" "-fomit-frame-pointer"
5927 "-ffast-math" "-funroll-loops"
5928 "-fmessage-length=0"
5929 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5931 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5932 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5933 (if (string-prefix? "x86_64" system)
5934 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5935 (string-append "CCFLAGS=" (string-join flags))))
5936 "-f" "Makefile.Linux"
5937 "CC=gcc ${CCFLAGS}")
5939 (modify-phases %standard-phases
5940 (add-after 'unpack 'enter-dir
5941 (lambda _ (chdir "src") #t))
5943 (lambda* (#:key outputs #:allow-other-keys)
5944 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5946 (copy-recursively "../bin" bin))))
5947 ;; no "configure" script
5948 (delete 'configure))))
5949 (inputs `(("zlib" ,zlib)))
5950 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5951 (synopsis "Tool kit for processing next-gen sequencing data")
5953 "The subread package contains the following tools: subread aligner, a
5954 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5955 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5956 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5957 against local background noises.")
5958 (license license:gpl3+)))
5960 (define-public stringtie
5966 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5967 "stringtie-" version ".tar.gz"))
5970 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5971 (modules '((guix build utils)))
5974 (delete-file-recursively "samtools-0.1.18")
5976 (build-system gnu-build-system)
5978 `(#:tests? #f ;no test suite
5980 (modify-phases %standard-phases
5981 ;; no configure script
5983 (add-before 'build 'use-system-samtools
5985 (substitute* "Makefile"
5986 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5988 (substitute* '("gclib/GBam.h"
5990 (("#include \"(bam|sam|kstring).h\"" _ header)
5991 (string-append "#include <samtools/" header ".h>")))
5993 (add-after 'unpack 'remove-duplicate-typedef
5995 ;; This typedef conflicts with the typedef in
5996 ;; glibc-2.25/include/bits/types.h
5997 (substitute* "gclib/GThreads.h"
5998 (("typedef long long __intmax_t;") ""))
6001 (lambda* (#:key outputs #:allow-other-keys)
6002 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6003 (install-file "stringtie" bin)
6006 `(("samtools" ,samtools-0.1)
6008 (home-page "http://ccb.jhu.edu/software/stringtie/")
6009 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6011 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6012 alignments into potential transcripts. It uses a novel network flow algorithm
6013 as well as an optional de novo assembly step to assemble and quantitate
6014 full-length transcripts representing multiple splice variants for each gene
6015 locus. Its input can include not only the alignments of raw reads used by
6016 other transcript assemblers, but also alignments of longer sequences that have
6017 been assembled from those reads. To identify differentially expressed genes
6018 between experiments, StringTie's output can be processed either by the
6019 Cuffdiff or Ballgown programs.")
6020 (license license:artistic2.0)))
6022 (define-public taxtastic
6028 (uri (pypi-uri "taxtastic" version))
6031 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6032 (build-system python-build-system)
6034 `(#:python ,python-2
6036 (modify-phases %standard-phases
6039 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
6041 `(("python-sqlalchemy" ,python2-sqlalchemy)
6042 ("python-decorator" ,python2-decorator)
6043 ("python-biopython" ,python2-biopython)
6044 ("python-pandas" ,python2-pandas)))
6045 (home-page "https://github.com/fhcrc/taxtastic")
6046 (synopsis "Tools for taxonomic naming and annotation")
6048 "Taxtastic is software written in python used to build and maintain
6049 reference packages i.e. collections of reference trees, reference alignments,
6050 profiles, and associated taxonomic information.")
6051 (license license:gpl3+)))
6053 (define-public vcftools
6060 "https://github.com/vcftools/vcftools/releases/download/v"
6061 version "/vcftools-" version ".tar.gz"))
6064 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6065 (build-system gnu-build-system)
6067 `(#:tests? #f ; no "check" target
6069 "CFLAGS=-O2" ; override "-m64" flag
6070 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6071 (string-append "MANDIR=" (assoc-ref %outputs "out")
6072 "/share/man/man1"))))
6074 `(("pkg-config" ,pkg-config)))
6078 (home-page "https://vcftools.github.io/")
6079 (synopsis "Tools for working with VCF files")
6081 "VCFtools is a program package designed for working with VCF files, such
6082 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6083 provide easily accessible methods for working with complex genetic variation
6084 data in the form of VCF files.")
6085 ;; The license is declared as LGPLv3 in the README and
6086 ;; at https://vcftools.github.io/license.html
6087 (license license:lgpl3)))
6089 (define-public infernal
6095 (uri (string-append "http://eddylab.org/software/infernal/"
6096 "infernal-" version ".tar.gz"))
6099 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6100 (build-system gnu-build-system)
6102 `(("perl" ,perl))) ; for tests
6103 (home-page "http://eddylab.org/infernal/")
6104 (synopsis "Inference of RNA alignments")
6105 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6106 searching DNA sequence databases for RNA structure and sequence similarities.
6107 It is an implementation of a special case of profile stochastic context-free
6108 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6109 profile, but it scores a combination of sequence consensus and RNA secondary
6110 structure consensus, so in many cases, it is more capable of identifying RNA
6111 homologs that conserve their secondary structure more than their primary
6113 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6114 (supported-systems '("i686-linux" "x86_64-linux"))
6115 (license license:bsd-3)))
6117 (define-public r-centipede
6119 (name "r-centipede")
6123 (uri (string-append "http://download.r-forge.r-project.org/"
6124 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6127 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6128 (build-system r-build-system)
6129 (home-page "http://centipede.uchicago.edu/")
6130 (synopsis "Predict transcription factor binding sites")
6132 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6133 of the genome that are bound by particular transcription factors. It starts
6134 by identifying a set of candidate binding sites, and then aims to classify the
6135 sites according to whether each site is bound or not bound by a transcription
6136 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6137 between two different types of motif instances using as much relevant
6138 information as possible.")
6139 (license (list license:gpl2+ license:gpl3+))))
6141 (define-public r-vegan
6148 (uri (cran-uri "vegan" version))
6151 "13pyqvlpz64qibi8k5d109v7q09j06mbv6ndix3n4cn21mjx391c"))))
6152 (build-system r-build-system)
6154 `(("gfortran" ,gfortran)))
6156 `(("r-cluster" ,r-cluster)
6157 ("r-knitr" ,r-knitr) ; needed for vignettes
6158 ("r-lattice" ,r-lattice)
6161 ("r-permute" ,r-permute)))
6162 (home-page "https://cran.r-project.org/web/packages/vegan")
6163 (synopsis "Functions for community ecology")
6165 "The vegan package provides tools for descriptive community ecology. It
6166 has most basic functions of diversity analysis, community ordination and
6167 dissimilarity analysis. Most of its multivariate tools can be used for other
6168 data types as well.")
6169 (license license:gpl2+)))
6171 (define-public r-annotate
6178 (uri (bioconductor-uri "annotate" version))
6181 "1qmncyvy147a1ll3iri45p822kcs3s7583jfnq9jf6sz9ilk8cjf"))))
6182 (build-system r-build-system)
6184 `(("r-annotationdbi" ,r-annotationdbi)
6185 ("r-biobase" ,r-biobase)
6186 ("r-biocgenerics" ,r-biocgenerics)
6188 ("r-rcurl" ,r-rcurl)
6190 ("r-xtable" ,r-xtable)))
6192 "https://bioconductor.org/packages/annotate")
6193 (synopsis "Annotation for microarrays")
6194 (description "This package provides R environments for the annotation of
6196 (license license:artistic2.0)))
6198 (define-public r-copynumber
6200 (name "r-copynumber")
6204 (uri (bioconductor-uri "copynumber" version))
6207 "0y9nnwb0psphp3ix88wj2f8z5gr45r5znf55w892ysm27isdpmms"))))
6208 (build-system r-build-system)
6210 `(("r-s4vectors" ,r-s4vectors)
6211 ("r-iranges" ,r-iranges)
6212 ("r-genomicranges" ,r-genomicranges)
6213 ("r-biocgenerics" ,r-biocgenerics)))
6214 (home-page "https://bioconductor.org/packages/copynumber")
6215 (synopsis "Segmentation of single- and multi-track copy number data")
6217 "This package segments single- and multi-track copy number data by a
6218 penalized least squares regression method.")
6219 (license license:artistic2.0)))
6221 (define-public r-geneplotter
6223 (name "r-geneplotter")
6228 (uri (bioconductor-uri "geneplotter" version))
6231 "055g28xgiazl4l0gkg8xiamks64f5yckjjyvw1abd6d6qjavwx0g"))))
6232 (build-system r-build-system)
6234 `(("r-annotate" ,r-annotate)
6235 ("r-annotationdbi" ,r-annotationdbi)
6236 ("r-biobase" ,r-biobase)
6237 ("r-biocgenerics" ,r-biocgenerics)
6238 ("r-lattice" ,r-lattice)
6239 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6240 (home-page "https://bioconductor.org/packages/geneplotter")
6241 (synopsis "Graphics functions for genomic data")
6243 "This package provides functions for plotting genomic data.")
6244 (license license:artistic2.0)))
6246 (define-public r-genefilter
6248 (name "r-genefilter")
6253 (uri (bioconductor-uri "genefilter" version))
6256 "14l0ff02spmjwxj0m1czhg5vlkgwcfi73cym8m2n9vn6i7bjdaqi"))))
6257 (build-system r-build-system)
6259 `(("gfortran" ,gfortran)))
6261 `(("r-annotate" ,r-annotate)
6262 ("r-annotationdbi" ,r-annotationdbi)
6263 ("r-biobase" ,r-biobase)
6264 ("r-s4vectors" ,r-s4vectors)
6265 ("r-survival" ,r-survival)))
6266 (home-page "https://bioconductor.org/packages/genefilter")
6267 (synopsis "Filter genes from high-throughput experiments")
6269 "This package provides basic functions for filtering genes from
6270 high-throughput sequencing experiments.")
6271 (license license:artistic2.0)))
6273 (define-public r-deseq2
6280 (uri (bioconductor-uri "DESeq2" version))
6283 "1wjnfpb41a9mmf9a22bz4zh7r1d4id50vpdc1mn5vfzrz7li9qik"))))
6284 (properties `((upstream-name . "DESeq2")))
6285 (build-system r-build-system)
6287 `(("r-biobase" ,r-biobase)
6288 ("r-biocgenerics" ,r-biocgenerics)
6289 ("r-biocparallel" ,r-biocparallel)
6290 ("r-genefilter" ,r-genefilter)
6291 ("r-geneplotter" ,r-geneplotter)
6292 ("r-genomicranges" ,r-genomicranges)
6293 ("r-ggplot2" ,r-ggplot2)
6294 ("r-hmisc" ,r-hmisc)
6295 ("r-iranges" ,r-iranges)
6296 ("r-locfit" ,r-locfit)
6298 ("r-rcpparmadillo" ,r-rcpparmadillo)
6299 ("r-s4vectors" ,r-s4vectors)
6300 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6301 (home-page "https://bioconductor.org/packages/DESeq2")
6302 (synopsis "Differential gene expression analysis")
6304 "This package provides functions to estimate variance-mean dependence in
6305 count data from high-throughput nucleotide sequencing assays and test for
6306 differential expression based on a model using the negative binomial
6308 (license license:lgpl3+)))
6310 (define-public r-dexseq
6317 (uri (bioconductor-uri "DEXSeq" version))
6320 "1mqb3mdxcsi3largsl7k27bvqrgps9ixv806xvmf29pw0xn05sg1"))))
6321 (properties `((upstream-name . "DEXSeq")))
6322 (build-system r-build-system)
6324 `(("r-annotationdbi" ,r-annotationdbi)
6325 ("r-biobase" ,r-biobase)
6326 ("r-biocgenerics" ,r-biocgenerics)
6327 ("r-biocparallel" ,r-biocparallel)
6328 ("r-biomart" ,r-biomart)
6329 ("r-deseq2" ,r-deseq2)
6330 ("r-genefilter" ,r-genefilter)
6331 ("r-geneplotter" ,r-geneplotter)
6332 ("r-genomicranges" ,r-genomicranges)
6333 ("r-hwriter" ,r-hwriter)
6334 ("r-iranges" ,r-iranges)
6335 ("r-rcolorbrewer" ,r-rcolorbrewer)
6336 ("r-rsamtools" ,r-rsamtools)
6337 ("r-s4vectors" ,r-s4vectors)
6338 ("r-statmod" ,r-statmod)
6339 ("r-stringr" ,r-stringr)
6340 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6341 (home-page "https://bioconductor.org/packages/DEXSeq")
6342 (synopsis "Inference of differential exon usage in RNA-Seq")
6344 "This package is focused on finding differential exon usage using RNA-seq
6345 exon counts between samples with different experimental designs. It provides
6346 functions that allows the user to make the necessary statistical tests based
6347 on a model that uses the negative binomial distribution to estimate the
6348 variance between biological replicates and generalized linear models for
6349 testing. The package also provides functions for the visualization and
6350 exploration of the results.")
6351 (license license:gpl3+)))
6353 (define-public r-annotationforge
6355 (name "r-annotationforge")
6360 (uri (bioconductor-uri "AnnotationForge" version))
6363 "12ffj7h95adiya5mzyjxazqn1qgr434ajpabfcyhrj5v83s4vk65"))))
6365 `((upstream-name . "AnnotationForge")))
6366 (build-system r-build-system)
6368 `(("r-annotationdbi" ,r-annotationdbi)
6369 ("r-biobase" ,r-biobase)
6370 ("r-biocgenerics" ,r-biocgenerics)
6372 ("r-rcurl" ,r-rcurl)
6373 ("r-rsqlite" ,r-rsqlite)
6374 ("r-s4vectors" ,r-s4vectors)
6376 (home-page "https://bioconductor.org/packages/AnnotationForge")
6377 (synopsis "Code for building annotation database packages")
6379 "This package provides code for generating Annotation packages and their
6380 databases. Packages produced are intended to be used with AnnotationDbi.")
6381 (license license:artistic2.0)))
6383 (define-public r-rbgl
6390 (uri (bioconductor-uri "RBGL" version))
6393 "0hj972mmqpyi5fx1rq33kysavdyz4nspi6gcffzi3rv339m0anhf"))))
6394 (properties `((upstream-name . "RBGL")))
6395 (build-system r-build-system)
6396 (propagated-inputs `(("r-graph" ,r-graph)))
6397 (home-page "https://www.bioconductor.org/packages/RBGL")
6398 (synopsis "Interface to the Boost graph library")
6400 "This package provides a fairly extensive and comprehensive interface to
6401 the graph algorithms contained in the Boost library.")
6402 (license license:artistic2.0)))
6404 (define-public r-gseabase
6411 (uri (bioconductor-uri "GSEABase" version))
6414 "11bv92svik399q677jv96b71i4bq68xxyxn1yijpdik2lq4hgl7a"))))
6415 (properties `((upstream-name . "GSEABase")))
6416 (build-system r-build-system)
6418 `(("r-annotate" ,r-annotate)
6419 ("r-annotationdbi" ,r-annotationdbi)
6420 ("r-biobase" ,r-biobase)
6421 ("r-biocgenerics" ,r-biocgenerics)
6422 ("r-graph" ,r-graph)
6424 (home-page "https://bioconductor.org/packages/GSEABase")
6425 (synopsis "Gene set enrichment data structures and methods")
6427 "This package provides classes and methods to support @dfn{Gene Set
6428 Enrichment Analysis} (GSEA).")
6429 (license license:artistic2.0)))
6431 (define-public r-category
6438 (uri (bioconductor-uri "Category" version))
6441 "03wfqa8d1dgwsm327zl2mpkq7dq3mzhq12598qz3ylfhrwplbgx0"))))
6442 (properties `((upstream-name . "Category")))
6443 (build-system r-build-system)
6445 `(("r-annotate" ,r-annotate)
6446 ("r-annotationdbi" ,r-annotationdbi)
6447 ("r-biobase" ,r-biobase)
6448 ("r-biocgenerics" ,r-biocgenerics)
6449 ("r-genefilter" ,r-genefilter)
6450 ("r-graph" ,r-graph)
6451 ("r-gseabase" ,r-gseabase)
6452 ("r-matrix" ,r-matrix)
6455 (home-page "https://bioconductor.org/packages/Category")
6456 (synopsis "Category analysis")
6458 "This package provides a collection of tools for performing category
6460 (license license:artistic2.0)))
6462 (define-public r-gostats
6469 (uri (bioconductor-uri "GOstats" version))
6472 "1i5mydz5d95w2k28qr9j01hmbnl2id55jq94jvcpcyp1pvinkdq0"))))
6473 (properties `((upstream-name . "GOstats")))
6474 (build-system r-build-system)
6476 `(("r-annotate" ,r-annotate)
6477 ("r-annotationdbi" ,r-annotationdbi)
6478 ("r-annotationforge" ,r-annotationforge)
6479 ("r-biobase" ,r-biobase)
6480 ("r-category" ,r-category)
6481 ("r-go-db" ,r-go-db)
6482 ("r-graph" ,r-graph)
6483 ("r-rgraphviz" ,r-rgraphviz)
6484 ("r-rbgl" ,r-rbgl)))
6485 (home-page "https://bioconductor.org/packages/GOstats")
6486 (synopsis "Tools for manipulating GO and microarrays")
6488 "This package provides a set of tools for interacting with GO and
6489 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6490 testing and other simple calculations.")
6491 (license license:artistic2.0)))
6493 (define-public r-shortread
6495 (name "r-shortread")
6500 (uri (bioconductor-uri "ShortRead" version))
6503 "038z3z7qaw5bpgjzy91sjkybsny6jwjjsrnnq4gdqdw9ss1qy1fb"))))
6504 (properties `((upstream-name . "ShortRead")))
6505 (build-system r-build-system)
6509 `(("r-biobase" ,r-biobase)
6510 ("r-biocgenerics" ,r-biocgenerics)
6511 ("r-biocparallel" ,r-biocparallel)
6512 ("r-biostrings" ,r-biostrings)
6513 ("r-genomeinfodb" ,r-genomeinfodb)
6514 ("r-genomicalignments" ,r-genomicalignments)
6515 ("r-genomicranges" ,r-genomicranges)
6516 ("r-hwriter" ,r-hwriter)
6517 ("r-iranges" ,r-iranges)
6518 ("r-lattice" ,r-lattice)
6519 ("r-latticeextra" ,r-latticeextra)
6520 ("r-rsamtools" ,r-rsamtools)
6521 ("r-s4vectors" ,r-s4vectors)
6522 ("r-xvector" ,r-xvector)
6523 ("r-zlibbioc" ,r-zlibbioc)))
6524 (home-page "https://bioconductor.org/packages/ShortRead")
6525 (synopsis "FASTQ input and manipulation tools")
6527 "This package implements sampling, iteration, and input of FASTQ files.
6528 It includes functions for filtering and trimming reads, and for generating a
6529 quality assessment report. Data are represented as
6530 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6531 purposes. The package also contains legacy support for early single-end,
6532 ungapped alignment formats.")
6533 (license license:artistic2.0)))
6535 (define-public r-systempiper
6537 (name "r-systempiper")
6542 (uri (bioconductor-uri "systemPipeR" version))
6545 "1550pd63mmky0vgkmpni7zf14kqz1741wv63nfaw29kcmhh3m5lm"))))
6546 (properties `((upstream-name . "systemPipeR")))
6547 (build-system r-build-system)
6549 `(("r-annotate" ,r-annotate)
6550 ("r-batchjobs" ,r-batchjobs)
6551 ("r-biocgenerics" ,r-biocgenerics)
6552 ("r-biostrings" ,r-biostrings)
6553 ("r-deseq2" ,r-deseq2)
6554 ("r-edger" ,r-edger)
6555 ("r-genomicfeatures" ,r-genomicfeatures)
6556 ("r-genomicranges" ,r-genomicranges)
6557 ("r-ggplot2" ,r-ggplot2)
6558 ("r-go-db" ,r-go-db)
6559 ("r-gostats" ,r-gostats)
6560 ("r-limma" ,r-limma)
6561 ("r-pheatmap" ,r-pheatmap)
6562 ("r-rjson" ,r-rjson)
6563 ("r-rsamtools" ,r-rsamtools)
6564 ("r-shortread" ,r-shortread)
6565 ("r-summarizedexperiment" ,r-summarizedexperiment)
6566 ("r-variantannotation" ,r-variantannotation)))
6567 (home-page "https://github.com/tgirke/systemPipeR")
6568 (synopsis "Next generation sequencing workflow and reporting environment")
6570 "This R package provides tools for building and running automated
6571 end-to-end analysis workflows for a wide range of @dfn{next generation
6572 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6573 Important features include a uniform workflow interface across different NGS
6574 applications, automated report generation, and support for running both R and
6575 command-line software, such as NGS aligners or peak/variant callers, on local
6576 computers or compute clusters. Efficient handling of complex sample sets and
6577 experimental designs is facilitated by a consistently implemented sample
6578 annotation infrastructure.")
6579 (license license:artistic2.0)))
6581 (define-public r-grohmm
6588 (uri (bioconductor-uri "groHMM" version))
6591 "1kjb14apyly44qdlx2ld6gr69wlazd4mbhs58l35hir12aphgrzp"))))
6592 (properties `((upstream-name . "groHMM")))
6593 (build-system r-build-system)
6595 `(("r-genomeinfodb" ,r-genomeinfodb)
6596 ("r-genomicalignments" ,r-genomicalignments)
6597 ("r-genomicranges" ,r-genomicranges)
6598 ("r-iranges" ,r-iranges)
6600 ("r-rtracklayer" ,r-rtracklayer)
6601 ("r-s4vectors" ,r-s4vectors)))
6602 (home-page "https://github.com/Kraus-Lab/groHMM")
6603 (synopsis "GRO-seq analysis pipeline")
6605 "This package provides a pipeline for the analysis of GRO-seq data.")
6606 (license license:gpl3+)))
6608 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6610 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6614 ;; We cannot use bioconductor-uri here because this tarball is
6615 ;; located under "data/annotation/" instead of "bioc/".
6616 (uri (string-append "https://bioconductor.org/packages/"
6617 "release/data/annotation/src/contrib"
6618 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6622 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6624 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6625 (build-system r-build-system)
6626 ;; As this package provides little more than a very large data file it
6627 ;; doesn't make sense to build substitutes.
6628 (arguments `(#:substitutable? #f))
6630 `(("r-genomicfeatures" ,r-genomicfeatures)))
6632 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6633 (synopsis "Annotation package for human genome in TxDb format")
6635 "This package provides an annotation database of Homo sapiens genome
6636 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6637 track. The database is exposed as a @code{TxDb} object.")
6638 (license license:artistic2.0)))
6640 (define-public r-sparql
6646 (uri (cran-uri "SPARQL" version))
6649 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6650 (properties `((upstream-name . "SPARQL")))
6651 (build-system r-build-system)
6653 `(("r-rcurl" ,r-rcurl)
6655 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6656 (synopsis "SPARQL client for R")
6657 (description "This package provides an interface to use SPARQL to pose
6658 SELECT or UPDATE queries to an end-point.")
6659 ;; The only license indication is found in the DESCRIPTION file,
6660 ;; which states GPL-3. So we cannot assume GPLv3+.
6661 (license license:gpl3)))
6663 (define-public vsearch
6671 "https://github.com/torognes/vsearch/archive/v"
6673 (file-name (string-append name "-" version ".tar.gz"))
6676 "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3"))
6677 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6680 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6681 ;; for this in the patch.
6682 (delete-file "src/city.h")
6683 (delete-file "src/citycrc.h")
6684 (delete-file "src/city.cc")
6686 (build-system gnu-build-system)
6689 (modify-phases %standard-phases
6690 (add-after 'unpack 'autogen
6691 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6695 ("cityhash" ,cityhash)))
6697 `(("autoconf" ,autoconf)
6698 ("automake" ,automake)))
6699 (synopsis "Sequence search tools for metagenomics")
6701 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6702 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6703 masking. The tool takes advantage of parallelism in the form of SIMD
6704 vectorization as well as multiple threads to perform accurate alignments at
6705 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6706 Needleman-Wunsch).")
6707 (home-page "https://github.com/torognes/vsearch")
6708 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6710 (supported-systems '("x86_64-linux"))
6711 ;; Dual licensed; also includes public domain source.
6712 (license (list license:gpl3 license:bsd-2))))
6714 (define-public pardre
6717 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6722 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6726 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6727 (build-system gnu-build-system)
6729 `(#:tests? #f ; no tests included
6731 (modify-phases %standard-phases
6734 (lambda* (#:key outputs #:allow-other-keys)
6735 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6736 (install-file "ParDRe" bin)
6739 `(("openmpi" ,openmpi)
6741 (synopsis "Parallel tool to remove duplicate DNA reads")
6743 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6744 Duplicate reads can be seen as identical or nearly identical sequences with
6745 some mismatches. This tool lets users avoid the analysis of unnecessary
6746 reads, reducing the time of subsequent procedures with the
6747 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6748 in order to exploit the parallel capabilities of multicore clusters. It is
6749 faster than multithreaded counterparts (end of 2015) for the same number of
6750 cores and, thanks to the message-passing technology, it can be executed on
6752 (home-page "https://sourceforge.net/projects/pardre/")
6753 (license license:gpl3+)))
6755 (define-public ruby-bio-kseq
6757 (name "ruby-bio-kseq")
6762 (uri (rubygems-uri "bio-kseq" version))
6765 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6766 (build-system ruby-build-system)
6768 `(#:test-target "spec"))
6770 `(("bundler" ,bundler)
6771 ("ruby-rspec" ,ruby-rspec)
6772 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6775 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6777 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6778 FASTQ parsing code. It provides a fast iterator over sequences and their
6780 (home-page "https://github.com/gusevfe/bio-kseq")
6781 (license license:expat)))
6783 (define-public bio-locus
6790 (uri (rubygems-uri "bio-locus" version))
6793 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6794 (build-system ruby-build-system)
6796 `(("ruby-rspec" ,ruby-rspec)))
6797 (synopsis "Tool for fast querying of genome locations")
6799 "Bio-locus is a tabix-like tool for fast querying of genome
6800 locations. Many file formats in bioinformatics contain records that
6801 start with a chromosome name and a position for a SNP, or a start-end
6802 position for indels. Bio-locus allows users to store this chr+pos or
6803 chr+pos+alt information in a database.")
6804 (home-page "https://github.com/pjotrp/bio-locus")
6805 (license license:expat)))
6807 (define-public bio-blastxmlparser
6809 (name "bio-blastxmlparser")
6813 (uri (rubygems-uri "bio-blastxmlparser" version))
6816 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6817 (build-system ruby-build-system)
6819 `(("ruby-bio-logger" ,ruby-bio-logger)
6820 ("ruby-nokogiri" ,ruby-nokogiri)))
6822 `(("ruby-rspec" ,ruby-rspec)))
6823 (synopsis "Fast big data BLAST XML parser and library")
6825 "Very fast parallel big-data BLAST XML file parser which can be used as
6826 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6827 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6828 (home-page "https://github.com/pjotrp/blastxmlparser")
6829 (license license:expat)))
6831 (define-public bioruby
6838 (uri (rubygems-uri "bio" version))
6841 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6842 (build-system ruby-build-system)
6844 `(("ruby-libxml" ,ruby-libxml)))
6846 `(("which" ,which))) ; required for test phase
6849 (modify-phases %standard-phases
6850 (add-before 'build 'patch-test-command
6852 (substitute* '("test/functional/bio/test_command.rb")
6853 (("/bin/sh") (which "sh")))
6854 (substitute* '("test/functional/bio/test_command.rb")
6855 (("/bin/ls") (which "ls")))
6856 (substitute* '("test/functional/bio/test_command.rb")
6857 (("which") (which "which")))
6858 (substitute* '("test/functional/bio/test_command.rb",
6859 "test/data/command/echoarg2.sh")
6860 (("/bin/echo") (which "echo")))
6862 (synopsis "Ruby library, shell and utilities for bioinformatics")
6863 (description "BioRuby comes with a comprehensive set of Ruby development
6864 tools and libraries for bioinformatics and molecular biology. BioRuby has
6865 components for sequence analysis, pathway analysis, protein modelling and
6866 phylogenetic analysis; it supports many widely used data formats and provides
6867 easy access to databases, external programs and public web services, including
6868 BLAST, KEGG, GenBank, MEDLINE and GO.")
6869 (home-page "http://bioruby.org/")
6870 ;; Code is released under Ruby license, except for setup
6871 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6872 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6874 (define-public r-acsnminer
6876 (name "r-acsnminer")
6877 (version "0.16.8.25")
6880 (uri (cran-uri "ACSNMineR" version))
6883 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6884 (properties `((upstream-name . "ACSNMineR")))
6885 (build-system r-build-system)
6887 `(("r-ggplot2" ,r-ggplot2)
6888 ("r-gridextra" ,r-gridextra)))
6889 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6890 (synopsis "Gene enrichment analysis")
6892 "This package provides tools to compute and represent gene set enrichment
6893 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6894 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6895 enrichment can be run with hypergeometric test or Fisher exact test, and can
6896 use multiple corrections. Visualization of data can be done either by
6897 barplots or heatmaps.")
6898 (license license:gpl2+)))
6900 (define-public r-biocgenerics
6902 (name "r-biocgenerics")
6906 (uri (bioconductor-uri "BiocGenerics" version))
6909 "19qxhy2cd3pykkhzbb5q3crgaxf65cpzf2mkfsz16gqhi8flj72p"))))
6911 `((upstream-name . "BiocGenerics")))
6912 (build-system r-build-system)
6913 (home-page "https://bioconductor.org/packages/BiocGenerics")
6914 (synopsis "S4 generic functions for Bioconductor")
6916 "This package provides S4 generic functions needed by many Bioconductor
6918 (license license:artistic2.0)))
6920 (define-public r-biocinstaller
6922 (name "r-biocinstaller")
6926 (uri (bioconductor-uri "BiocInstaller" version))
6929 "1xg1gi1hf5vflp71ji21gnmr4kcjpx8a6c47cllpc7yqnjv5nfg0"))))
6931 `((upstream-name . "BiocInstaller")))
6932 (build-system r-build-system)
6933 (home-page "https://bioconductor.org/packages/BiocInstaller")
6934 (synopsis "Install Bioconductor packages")
6935 (description "This package is used to install and update R packages from
6936 Bioconductor, CRAN, and Github.")
6937 (license license:artistic2.0)))
6939 (define-public r-biocviews
6941 (name "r-biocviews")
6945 (uri (bioconductor-uri "biocViews" version))
6948 "1yx2lir67ny0j150wyfqca0wsxp84byri8nscbs9qlndkh2jppq9"))))
6950 `((upstream-name . "biocViews")))
6951 (build-system r-build-system)
6953 `(("r-biobase" ,r-biobase)
6954 ("r-graph" ,r-graph)
6956 ("r-rcurl" ,r-rcurl)
6958 ("r-runit" ,r-runit)))
6959 (home-page "https://bioconductor.org/packages/biocViews")
6960 (synopsis "Bioconductor package categorization helper")
6961 (description "The purpose of biocViews is to create HTML pages that
6962 categorize packages in a Bioconductor package repository according to keywords,
6963 also known as views, in a controlled vocabulary.")
6964 (license license:artistic2.0)))
6966 (define-public r-bookdown
6972 (uri (cran-uri "bookdown" version))
6975 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6976 (build-system r-build-system)
6978 `(("r-htmltools" ,r-htmltools)
6979 ("r-knitr" ,r-knitr)
6980 ("r-rmarkdown" ,r-rmarkdown)
6981 ("r-tinytex" ,r-tinytex)
6983 ("r-xfun" ,r-xfun)))
6984 (home-page "https://github.com/rstudio/bookdown")
6985 (synopsis "Authoring books and technical documents with R markdown")
6986 (description "This package provides output formats and utilities for
6987 authoring books and technical documents with R Markdown.")
6988 (license license:gpl3)))
6990 (define-public r-biocstyle
6992 (name "r-biocstyle")
6996 (uri (bioconductor-uri "BiocStyle" version))
6999 "17m901ylz00w1a3nq5f910v55zixm1nr6rb3qrsbhqd94qzr0l2p"))))
7001 `((upstream-name . "BiocStyle")))
7002 (build-system r-build-system)
7004 `(("r-bookdown" ,r-bookdown)
7005 ("r-knitr" ,r-knitr)
7006 ("r-rmarkdown" ,r-rmarkdown)
7007 ("r-yaml" ,r-yaml)))
7008 (home-page "https://bioconductor.org/packages/BiocStyle")
7009 (synopsis "Bioconductor formatting styles")
7010 (description "This package provides standard formatting styles for
7011 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7013 (license license:artistic2.0)))
7015 (define-public r-bioccheck
7017 (name "r-bioccheck")
7021 (uri (bioconductor-uri "BiocCheck" version))
7024 "1srp1g809f1nn0fyqknr7r6dq89bw1xpjvmygr7cw6ffknbc671s"))))
7026 `((upstream-name . "BiocCheck")))
7027 (build-system r-build-system)
7030 (modify-phases %standard-phases
7031 ;; This package can be used by calling BiocCheck(<package>) from
7032 ;; within R, or by running R CMD BiocCheck <package>. This phase
7033 ;; makes sure the latter works. For this to work, the BiocCheck
7034 ;; script must be somewhere on the PATH (not the R bin directory).
7035 (add-after 'install 'install-bioccheck-subcommand
7036 (lambda* (#:key outputs #:allow-other-keys)
7037 (let* ((out (assoc-ref outputs "out"))
7038 (dest-dir (string-append out "/bin"))
7040 (string-append out "/site-library/BiocCheck/script/")))
7042 (symlink (string-append script-dir "/checkBadDeps.R")
7043 (string-append dest-dir "/checkBadDeps.R"))
7044 (symlink (string-append script-dir "/BiocCheck")
7045 (string-append dest-dir "/BiocCheck")))
7048 `(("r-codetools" ,r-codetools)
7049 ("r-graph" ,r-graph)
7051 ("r-optparse" ,r-optparse)
7052 ("r-biocinstaller" ,r-biocinstaller)
7053 ("r-biocviews" ,r-biocviews)
7054 ("r-stringdist" ,r-stringdist)))
7055 (home-page "https://bioconductor.org/packages/BiocCheck")
7056 (synopsis "Executes Bioconductor-specific package checks")
7057 (description "This package contains tools to perform additional quality
7058 checks on R packages that are to be submitted to the Bioconductor repository.")
7059 (license license:artistic2.0)))
7061 (define-public r-getopt
7068 (uri (cran-uri "getopt" version))
7071 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
7072 (build-system r-build-system)
7073 (home-page "https://github.com/trevorld/getopt")
7074 (synopsis "Command-line option processor for R")
7076 "This package is designed to be used with Rscript to write shebang
7077 scripts that accept short and long options. Many users will prefer to
7078 use the packages @code{optparse} or @code{argparse} which add extra
7079 features like automatically generated help options and usage texts,
7080 support for default values, positional argument support, etc.")
7081 (license license:gpl2+)))
7083 (define-public r-optparse
7090 (uri (cran-uri "optparse" version))
7093 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
7094 (build-system r-build-system)
7096 `(("r-getopt" ,r-getopt)))
7098 "https://github.com/trevorld/optparse")
7099 (synopsis "Command line option parser")
7101 "This package provides a command line parser inspired by Python's
7102 @code{optparse} library to be used with Rscript to write shebang scripts
7103 that accept short and long options.")
7104 (license license:gpl2+)))
7106 (define-public r-dnacopy
7112 (uri (bioconductor-uri "DNAcopy" version))
7115 "03hfhmmc5y60r2gcgm367w2fr7qj115l74m9bp3h9qpn5yci0d8n"))))
7117 `((upstream-name . "DNAcopy")))
7118 (build-system r-build-system)
7120 `(("gfortran" ,gfortran)))
7121 (home-page "https://bioconductor.org/packages/DNAcopy")
7122 (synopsis "Implementation of a circular binary segmentation algorithm")
7123 (description "This package implements the circular binary segmentation (CBS)
7124 algorithm to segment DNA copy number data and identify genomic regions with
7125 abnormal copy number.")
7126 (license license:gpl2+)))
7128 (define-public r-s4vectors
7130 (name "r-s4vectors")
7134 (uri (bioconductor-uri "S4Vectors" version))
7137 "0qvj2j0zl4djjl7vrwc6xak6h8dxr53iwypfbcvfb3sh7jwhdiz5"))))
7139 `((upstream-name . "S4Vectors")))
7140 (build-system r-build-system)
7142 `(("r-biocgenerics" ,r-biocgenerics)))
7143 (home-page "https://bioconductor.org/packages/S4Vectors")
7144 (synopsis "S4 implementation of vectors and lists")
7146 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7147 classes and a set of generic functions that extend the semantic of ordinary
7148 vectors and lists in R. Package developers can easily implement vector-like
7149 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7150 In addition, a few low-level concrete subclasses of general interest (e.g.
7151 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7152 S4Vectors package itself.")
7153 (license license:artistic2.0)))
7155 (define-public r-seqinr
7162 (uri (cran-uri "seqinr" version))
7165 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7166 (build-system r-build-system)
7168 `(("r-ade4" ,r-ade4)
7169 ("r-segmented" ,r-segmented)))
7172 (home-page "http://seqinr.r-forge.r-project.org/")
7173 (synopsis "Biological sequences retrieval and analysis")
7175 "This package provides tools for exploratory data analysis and data
7176 visualization of biological sequence (DNA and protein) data. It also includes
7177 utilities for sequence data management under the ACNUC system.")
7178 (license license:gpl2+)))
7180 (define-public r-iranges
7186 (uri (bioconductor-uri "IRanges" version))
7189 "10ccw930vfmkskkrzbps14xglqlkxf588623dr7f1a9ckx7yr2p6"))))
7191 `((upstream-name . "IRanges")))
7192 (build-system r-build-system)
7194 `(("r-biocgenerics" ,r-biocgenerics)
7195 ("r-s4vectors" ,r-s4vectors)))
7196 (home-page "https://bioconductor.org/packages/IRanges")
7197 (synopsis "Infrastructure for manipulating intervals on sequences")
7199 "This package provides efficient low-level and highly reusable S4 classes
7200 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7201 generally, data that can be organized sequentially (formally defined as
7202 @code{Vector} objects), as well as views on these @code{Vector} objects.
7203 Efficient list-like classes are also provided for storing big collections of
7204 instances of the basic classes. All classes in the package use consistent
7205 naming and share the same rich and consistent \"Vector API\" as much as
7207 (license license:artistic2.0)))
7209 (define-public r-genomeinfodbdata
7211 (name "r-genomeinfodbdata")
7215 ;; We cannot use bioconductor-uri here because this tarball is
7216 ;; located under "data/annotation/" instead of "bioc/".
7217 (uri (string-append "https://bioconductor.org/packages/release/"
7218 "data/annotation/src/contrib/GenomeInfoDbData_"
7222 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7224 `((upstream-name . "GenomeInfoDbData")))
7225 (build-system r-build-system)
7226 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7227 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7228 (description "This package contains data for mapping between NCBI taxonomy
7229 ID and species. It is used by functions in the GenomeInfoDb package.")
7230 (license license:artistic2.0)))
7232 (define-public r-genomeinfodb
7234 (name "r-genomeinfodb")
7238 (uri (bioconductor-uri "GenomeInfoDb" version))
7241 "0yhnqhaydmmq7ihmhj3rbal4afq5p993l2qqrd0n5wmbyg7glg2d"))))
7243 `((upstream-name . "GenomeInfoDb")))
7244 (build-system r-build-system)
7246 `(("r-biocgenerics" ,r-biocgenerics)
7247 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7248 ("r-iranges" ,r-iranges)
7249 ("r-rcurl" ,r-rcurl)
7250 ("r-s4vectors" ,r-s4vectors)))
7251 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7252 (synopsis "Utilities for manipulating chromosome identifiers")
7254 "This package contains data and functions that define and allow
7255 translation between different chromosome sequence naming conventions (e.g.,
7256 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7257 names in their natural, rather than lexicographic, order.")
7258 (license license:artistic2.0)))
7260 (define-public r-edger
7266 (uri (bioconductor-uri "edgeR" version))
7269 "07py2g6vg9jbflwhc1hnzr2silbinrjwxq3mkq30nzjgf0n0hrf3"))))
7270 (properties `((upstream-name . "edgeR")))
7271 (build-system r-build-system)
7273 `(("r-limma" ,r-limma)
7274 ("r-locfit" ,r-locfit)
7276 ("r-statmod" ,r-statmod))) ;for estimateDisp
7277 (home-page "http://bioinf.wehi.edu.au/edgeR")
7278 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7279 (description "This package can do differential expression analysis of
7280 RNA-seq expression profiles with biological replication. It implements a range
7281 of statistical methodology based on the negative binomial distributions,
7282 including empirical Bayes estimation, exact tests, generalized linear models
7283 and quasi-likelihood tests. It be applied to differential signal analysis of
7284 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7286 (license license:gpl2+)))
7288 (define-public r-variantannotation
7290 (name "r-variantannotation")
7294 (uri (bioconductor-uri "VariantAnnotation" version))
7297 "06bccdf57vja7m63chmgc4539lwng3q3b8zxn285fj8524l6mcn7"))))
7299 `((upstream-name . "VariantAnnotation")))
7303 `(("r-annotationdbi" ,r-annotationdbi)
7304 ("r-biobase" ,r-biobase)
7305 ("r-biocgenerics" ,r-biocgenerics)
7306 ("r-biostrings" ,r-biostrings)
7307 ("r-bsgenome" ,r-bsgenome)
7309 ("r-genomeinfodb" ,r-genomeinfodb)
7310 ("r-genomicfeatures" ,r-genomicfeatures)
7311 ("r-genomicranges" ,r-genomicranges)
7312 ("r-iranges" ,r-iranges)
7313 ("r-summarizedexperiment" ,r-summarizedexperiment)
7314 ("r-rsamtools" ,r-rsamtools)
7315 ("r-rtracklayer" ,r-rtracklayer)
7316 ("r-s4vectors" ,r-s4vectors)
7317 ("r-xvector" ,r-xvector)
7318 ("r-zlibbioc" ,r-zlibbioc)))
7319 (build-system r-build-system)
7320 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7321 (synopsis "Package for annotation of genetic variants")
7322 (description "This R package can annotate variants, compute amino acid
7323 coding changes and predict coding outcomes.")
7324 (license license:artistic2.0)))
7326 (define-public r-limma
7332 (uri (bioconductor-uri "limma" version))
7335 "1982g5v35ilfgxm2vkq1p3j1bbir795pjvfzx4nzam2rlqqymbqm"))))
7336 (build-system r-build-system)
7337 (home-page "http://bioinf.wehi.edu.au/limma")
7338 (synopsis "Package for linear models for microarray and RNA-seq data")
7339 (description "This package can be used for the analysis of gene expression
7340 studies, especially the use of linear models for analysing designed experiments
7341 and the assessment of differential expression. The analysis methods apply to
7342 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7343 (license license:gpl2+)))
7345 (define-public r-xvector
7351 (uri (bioconductor-uri "XVector" version))
7354 "1zjlhh9lsyhg0js1858csyw2389kbrzdqnqnha833wazkwxilp3f"))))
7356 `((upstream-name . "XVector")))
7357 (build-system r-build-system)
7360 (modify-phases %standard-phases
7361 (add-after 'unpack 'use-system-zlib
7363 (substitute* "DESCRIPTION"
7364 (("zlibbioc, ") ""))
7365 (substitute* "NAMESPACE"
7366 (("import\\(zlibbioc\\)") ""))
7371 `(("r-biocgenerics" ,r-biocgenerics)
7372 ("r-iranges" ,r-iranges)
7373 ("r-s4vectors" ,r-s4vectors)))
7374 (home-page "https://bioconductor.org/packages/XVector")
7375 (synopsis "Representation and manpulation of external sequences")
7377 "This package provides memory efficient S4 classes for storing sequences
7378 \"externally\" (behind an R external pointer, or on disk).")
7379 (license license:artistic2.0)))
7381 (define-public r-genomicranges
7383 (name "r-genomicranges")
7387 (uri (bioconductor-uri "GenomicRanges" version))
7390 "03gmka6rlz18vd4229796l5l3l6446v5cb90sn2nb5knjbp84hni"))))
7392 `((upstream-name . "GenomicRanges")))
7393 (build-system r-build-system)
7395 `(("r-biocgenerics" ,r-biocgenerics)
7396 ("r-genomeinfodb" ,r-genomeinfodb)
7397 ("r-iranges" ,r-iranges)
7398 ("r-s4vectors" ,r-s4vectors)
7399 ("r-xvector" ,r-xvector)))
7400 (home-page "https://bioconductor.org/packages/GenomicRanges")
7401 (synopsis "Representation and manipulation of genomic intervals")
7403 "This package provides tools to efficiently represent and manipulate
7404 genomic annotations and alignments is playing a central role when it comes to
7405 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7406 GenomicRanges package defines general purpose containers for storing and
7407 manipulating genomic intervals and variables defined along a genome.")
7408 (license license:artistic2.0)))
7410 (define-public r-biobase
7416 (uri (bioconductor-uri "Biobase" version))
7419 "1iwds2a5ir29k19dbpynlc7nn836cw2gamchhgpi2jf2xar9m9jz"))))
7421 `((upstream-name . "Biobase")))
7422 (build-system r-build-system)
7424 `(("r-biocgenerics" ,r-biocgenerics)))
7425 (home-page "https://bioconductor.org/packages/Biobase")
7426 (synopsis "Base functions for Bioconductor")
7428 "This package provides functions that are needed by many other packages
7429 on Bioconductor or which replace R functions.")
7430 (license license:artistic2.0)))
7432 (define-public r-annotationdbi
7434 (name "r-annotationdbi")
7438 (uri (bioconductor-uri "AnnotationDbi" version))
7441 "0afkbzli08vq02r2pr9phrz3rxd6ilp1w7yw8y99nbjiz14f8b1c"))))
7443 `((upstream-name . "AnnotationDbi")))
7444 (build-system r-build-system)
7446 `(("r-biobase" ,r-biobase)
7447 ("r-biocgenerics" ,r-biocgenerics)
7449 ("r-iranges" ,r-iranges)
7450 ("r-rsqlite" ,r-rsqlite)
7451 ("r-s4vectors" ,r-s4vectors)))
7452 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7453 (synopsis "Annotation database interface")
7455 "This package provides user interface and database connection code for
7456 annotation data packages using SQLite data storage.")
7457 (license license:artistic2.0)))
7459 (define-public r-biomart
7465 (uri (bioconductor-uri "biomaRt" version))
7468 "0b70s350ffc74v3xz5c3jpazr9zxdb7gjmjfj7aghlsrizrspill"))))
7470 `((upstream-name . "biomaRt")))
7471 (build-system r-build-system)
7473 `(("r-annotationdbi" ,r-annotationdbi)
7475 ("r-progress" ,r-progress)
7476 ("r-rcurl" ,r-rcurl)
7477 ("r-stringr" ,r-stringr)
7479 (home-page "https://bioconductor.org/packages/biomaRt")
7480 (synopsis "Interface to BioMart databases")
7482 "biomaRt provides an interface to a growing collection of databases
7483 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7484 package enables retrieval of large amounts of data in a uniform way without
7485 the need to know the underlying database schemas or write complex SQL queries.
7486 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7487 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7488 users direct access to a diverse set of data and enable a wide range of
7489 powerful online queries from gene annotation to database mining.")
7490 (license license:artistic2.0)))
7492 (define-public r-biocparallel
7494 (name "r-biocparallel")
7498 (uri (bioconductor-uri "BiocParallel" version))
7501 "00qg1kg2l9qqpyjaw5q910cmf84vwfiw1fhsx3ig784gwinwgj6n"))))
7503 `((upstream-name . "BiocParallel")))
7504 (build-system r-build-system)
7506 `(("r-futile-logger" ,r-futile-logger)
7509 (home-page "https://bioconductor.org/packages/BiocParallel")
7510 (synopsis "Bioconductor facilities for parallel evaluation")
7512 "This package provides modified versions and novel implementation of
7513 functions for parallel evaluation, tailored to use with Bioconductor
7515 (license (list license:gpl2+ license:gpl3+))))
7517 (define-public r-biostrings
7519 (name "r-biostrings")
7523 (uri (bioconductor-uri "Biostrings" version))
7526 "118b490jk87ydigm6ln25ms4kskzkw0akmh77clzznhzpqnxsi6j"))))
7528 `((upstream-name . "Biostrings")))
7529 (build-system r-build-system)
7531 `(("r-biocgenerics" ,r-biocgenerics)
7532 ("r-iranges" ,r-iranges)
7533 ("r-s4vectors" ,r-s4vectors)
7534 ("r-xvector" ,r-xvector)))
7535 (home-page "https://bioconductor.org/packages/Biostrings")
7536 (synopsis "String objects and algorithms for biological sequences")
7538 "This package provides memory efficient string containers, string
7539 matching algorithms, and other utilities, for fast manipulation of large
7540 biological sequences or sets of sequences.")
7541 (license license:artistic2.0)))
7543 (define-public r-rsamtools
7545 (name "r-rsamtools")
7549 (uri (bioconductor-uri "Rsamtools" version))
7552 "1s65y5wn4d0x8zsljg2kmhcl6r9884h95kr041j7hp49bmxg3an6"))))
7554 `((upstream-name . "Rsamtools")))
7555 (build-system r-build-system)
7558 (modify-phases %standard-phases
7559 (add-after 'unpack 'use-system-zlib
7561 (substitute* "DESCRIPTION"
7562 (("zlibbioc, ") ""))
7563 (substitute* "NAMESPACE"
7564 (("import\\(zlibbioc\\)") ""))
7569 `(("r-biocgenerics" ,r-biocgenerics)
7570 ("r-biocparallel" ,r-biocparallel)
7571 ("r-biostrings" ,r-biostrings)
7572 ("r-bitops" ,r-bitops)
7573 ("r-genomeinfodb" ,r-genomeinfodb)
7574 ("r-genomicranges" ,r-genomicranges)
7575 ("r-iranges" ,r-iranges)
7576 ("r-s4vectors" ,r-s4vectors)
7577 ("r-xvector" ,r-xvector)))
7578 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7579 (synopsis "Interface to samtools, bcftools, and tabix")
7581 "This package provides an interface to the 'samtools', 'bcftools', and
7582 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7583 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7585 (license license:expat)))
7587 (define-public r-delayedarray
7589 (name "r-delayedarray")
7593 (uri (bioconductor-uri "DelayedArray" version))
7596 "0n3w57cwy911q812wc8658y0v3xgpmg379sj98kfqdxa80z1mxdf"))))
7598 `((upstream-name . "DelayedArray")))
7599 (build-system r-build-system)
7601 `(("r-biocgenerics" ,r-biocgenerics)
7602 ("r-biocparallel" ,r-biocparallel)
7603 ("r-s4vectors" ,r-s4vectors)
7604 ("r-iranges" ,r-iranges)
7605 ("r-matrixstats" ,r-matrixstats)))
7606 (home-page "https://bioconductor.org/packages/DelayedArray")
7607 (synopsis "Delayed operations on array-like objects")
7609 "Wrapping an array-like object (typically an on-disk object) in a
7610 @code{DelayedArray} object allows one to perform common array operations on it
7611 without loading the object in memory. In order to reduce memory usage and
7612 optimize performance, operations on the object are either delayed or executed
7613 using a block processing mechanism. Note that this also works on in-memory
7614 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7615 @code{Matrix} objects, and ordinary arrays and data frames.")
7616 (license license:artistic2.0)))
7618 (define-public r-summarizedexperiment
7620 (name "r-summarizedexperiment")
7624 (uri (bioconductor-uri "SummarizedExperiment" version))
7627 "0v3zxl9cqsv79ag5cnvzlhvgaz5cr8f4rn7flmwnwpqd508cznl1"))))
7629 `((upstream-name . "SummarizedExperiment")))
7630 (build-system r-build-system)
7632 `(("r-biobase" ,r-biobase)
7633 ("r-biocgenerics" ,r-biocgenerics)
7634 ("r-delayedarray" ,r-delayedarray)
7635 ("r-genomeinfodb" ,r-genomeinfodb)
7636 ("r-genomicranges" ,r-genomicranges)
7637 ("r-iranges" ,r-iranges)
7638 ("r-matrix" ,r-matrix)
7639 ("r-s4vectors" ,r-s4vectors)))
7640 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7641 (synopsis "Container for representing genomic ranges by sample")
7643 "The SummarizedExperiment container contains one or more assays, each
7644 represented by a matrix-like object of numeric or other mode. The rows
7645 typically represent genomic ranges of interest and the columns represent
7647 (license license:artistic2.0)))
7649 (define-public r-genomicalignments
7651 (name "r-genomicalignments")
7655 (uri (bioconductor-uri "GenomicAlignments" version))
7658 "00pi2cnkkbj2023fg2x2cmglkdalwzy1vr3glsikwz7ix9yylcaw"))))
7660 `((upstream-name . "GenomicAlignments")))
7661 (build-system r-build-system)
7663 `(("r-biocgenerics" ,r-biocgenerics)
7664 ("r-biocparallel" ,r-biocparallel)
7665 ("r-biostrings" ,r-biostrings)
7666 ("r-genomeinfodb" ,r-genomeinfodb)
7667 ("r-genomicranges" ,r-genomicranges)
7668 ("r-iranges" ,r-iranges)
7669 ("r-rsamtools" ,r-rsamtools)
7670 ("r-s4vectors" ,r-s4vectors)
7671 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7672 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7673 (synopsis "Representation and manipulation of short genomic alignments")
7675 "This package provides efficient containers for storing and manipulating
7676 short genomic alignments (typically obtained by aligning short reads to a
7677 reference genome). This includes read counting, computing the coverage,
7678 junction detection, and working with the nucleotide content of the
7680 (license license:artistic2.0)))
7682 (define-public r-rtracklayer
7684 (name "r-rtracklayer")
7688 (uri (bioconductor-uri "rtracklayer" version))
7691 "0kvsjdaypn1jnxbnsxpycildwdyxwnjkigfq8qm8mlyfc4ahdgy3"))))
7692 (build-system r-build-system)
7695 (modify-phases %standard-phases
7696 (add-after 'unpack 'use-system-zlib
7698 (substitute* "DESCRIPTION"
7699 ((" zlibbioc,") ""))
7700 (substitute* "NAMESPACE"
7701 (("import\\(zlibbioc\\)") ""))
7704 `(("pkg-config" ,pkg-config)))
7708 `(("r-biocgenerics" ,r-biocgenerics)
7709 ("r-biostrings" ,r-biostrings)
7710 ("r-genomeinfodb" ,r-genomeinfodb)
7711 ("r-genomicalignments" ,r-genomicalignments)
7712 ("r-genomicranges" ,r-genomicranges)
7713 ("r-iranges" ,r-iranges)
7714 ("r-rcurl" ,r-rcurl)
7715 ("r-rsamtools" ,r-rsamtools)
7716 ("r-s4vectors" ,r-s4vectors)
7718 ("r-xvector" ,r-xvector)))
7719 (home-page "https://bioconductor.org/packages/rtracklayer")
7720 (synopsis "R interface to genome browsers and their annotation tracks")
7722 "rtracklayer is an extensible framework for interacting with multiple
7723 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7724 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7725 built-in). The user may export/import tracks to/from the supported browsers,
7726 as well as query and modify the browser state, such as the current viewport.")
7727 (license license:artistic2.0)))
7729 (define-public r-genomicfeatures
7731 (name "r-genomicfeatures")
7735 (uri (bioconductor-uri "GenomicFeatures" version))
7738 "1cqcl72q0k5wylw1brn4g4h7xzys1v06piry19cvp0gjcvm5sp7a"))))
7740 `((upstream-name . "GenomicFeatures")))
7741 (build-system r-build-system)
7743 `(("r-annotationdbi" ,r-annotationdbi)
7744 ("r-biobase" ,r-biobase)
7745 ("r-biocgenerics" ,r-biocgenerics)
7746 ("r-biomart" ,r-biomart)
7747 ("r-biostrings" ,r-biostrings)
7749 ("r-genomeinfodb" ,r-genomeinfodb)
7750 ("r-genomicranges" ,r-genomicranges)
7751 ("r-iranges" ,r-iranges)
7752 ("r-rcurl" ,r-rcurl)
7753 ("r-rsqlite" ,r-rsqlite)
7754 ("r-rtracklayer" ,r-rtracklayer)
7755 ("r-s4vectors" ,r-s4vectors)
7756 ("r-xvector" ,r-xvector)))
7757 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7758 (synopsis "Tools for working with transcript centric annotations")
7760 "This package provides a set of tools and methods for making and
7761 manipulating transcript centric annotations. With these tools the user can
7762 easily download the genomic locations of the transcripts, exons and cds of a
7763 given organism, from either the UCSC Genome Browser or a BioMart
7764 database (more sources will be supported in the future). This information is
7765 then stored in a local database that keeps track of the relationship between
7766 transcripts, exons, cds and genes. Flexible methods are provided for
7767 extracting the desired features in a convenient format.")
7768 (license license:artistic2.0)))
7770 (define-public r-go-db
7776 (uri (string-append "https://www.bioconductor.org/packages/"
7777 "release/data/annotation/src/contrib/GO.db_"
7781 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7783 `((upstream-name . "GO.db")))
7784 (build-system r-build-system)
7786 `(("r-annotationdbi" ,r-annotationdbi)))
7787 (home-page "https://bioconductor.org/packages/GO.db")
7788 (synopsis "Annotation maps describing the entire Gene Ontology")
7790 "The purpose of this GO.db annotation package is to provide detailed
7791 information about the latest version of the Gene Ontologies.")
7792 (license license:artistic2.0)))
7794 (define-public r-graph
7800 (uri (bioconductor-uri "graph" version))
7803 "1zx445lk36g1s6i5dbhhf00nzzazyklfjxxjfax6q8hnhvgm9759"))))
7804 (build-system r-build-system)
7806 `(("r-biocgenerics" ,r-biocgenerics)))
7807 (home-page "https://bioconductor.org/packages/graph")
7808 (synopsis "Handle graph data structures in R")
7810 "This package implements some simple graph handling capabilities for R.")
7811 (license license:artistic2.0)))
7813 (define-public r-topgo
7819 (uri (bioconductor-uri "topGO" version))
7822 "05yxnkid8bgw9lkm90if9fg63djhgvbailfa3qsfqa5c0zjmixw1"))))
7824 `((upstream-name . "topGO")))
7825 (build-system r-build-system)
7827 `(("r-annotationdbi" ,r-annotationdbi)
7829 ("r-biobase" ,r-biobase)
7830 ("r-biocgenerics" ,r-biocgenerics)
7831 ("r-go-db" ,r-go-db)
7832 ("r-graph" ,r-graph)
7833 ("r-lattice" ,r-lattice)
7834 ("r-matrixstats" ,r-matrixstats)
7835 ("r-sparsem" ,r-sparsem)))
7836 (home-page "https://bioconductor.org/packages/topGO")
7837 (synopsis "Enrichment analysis for gene ontology")
7839 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7840 terms while accounting for the topology of the GO graph. Different test
7841 statistics and different methods for eliminating local similarities and
7842 dependencies between GO terms can be implemented and applied.")
7843 ;; Any version of the LGPL applies.
7844 (license license:lgpl2.1+)))
7846 (define-public r-bsgenome
7852 (uri (bioconductor-uri "BSgenome" version))
7855 "1rk2piqq5dppkd51ln3r872d7ng3rvq98071mnd0xdv2xwnyn5g8"))))
7857 `((upstream-name . "BSgenome")))
7858 (build-system r-build-system)
7860 `(("r-biocgenerics" ,r-biocgenerics)
7861 ("r-biostrings" ,r-biostrings)
7862 ("r-genomeinfodb" ,r-genomeinfodb)
7863 ("r-genomicranges" ,r-genomicranges)
7864 ("r-iranges" ,r-iranges)
7865 ("r-rsamtools" ,r-rsamtools)
7866 ("r-rtracklayer" ,r-rtracklayer)
7867 ("r-s4vectors" ,r-s4vectors)
7868 ("r-xvector" ,r-xvector)))
7869 (home-page "https://bioconductor.org/packages/BSgenome")
7870 (synopsis "Infrastructure for Biostrings-based genome data packages")
7872 "This package provides infrastructure shared by all Biostrings-based
7873 genome data packages and support for efficient SNP representation.")
7874 (license license:artistic2.0)))
7876 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7878 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7882 ;; We cannot use bioconductor-uri here because this tarball is
7883 ;; located under "data/annotation/" instead of "bioc/".
7884 (uri (string-append "https://www.bioconductor.org/packages/"
7885 "release/data/annotation/src/contrib/"
7886 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7890 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7892 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7893 (build-system r-build-system)
7894 ;; As this package provides little more than a very large data file it
7895 ;; doesn't make sense to build substitutes.
7896 (arguments `(#:substitutable? #f))
7898 `(("r-bsgenome" ,r-bsgenome)))
7900 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7901 (synopsis "Full genome sequences for Homo sapiens")
7903 "This package provides full genome sequences for Homo sapiens from
7904 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7905 (license license:artistic2.0)))
7907 (define-public r-impute
7913 (uri (bioconductor-uri "impute" version))
7916 "1d3cpfaqlq2gnb3hsc2yhxwkrnbd7m6ifif32yp0ya0jr5brl4hr"))))
7918 `(("gfortran" ,gfortran)))
7919 (build-system r-build-system)
7920 (home-page "https://bioconductor.org/packages/impute")
7921 (synopsis "Imputation for microarray data")
7923 "This package provides a function to impute missing gene expression
7924 microarray data, using nearest neighbor averaging.")
7925 (license license:gpl2+)))
7927 (define-public r-seqpattern
7929 (name "r-seqpattern")
7933 (uri (bioconductor-uri "seqPattern" version))
7936 "0dw0yldfcf0ibvpqxlpx1ijnjf9lma47w9w22siszzhw09i0wp3w"))))
7938 `((upstream-name . "seqPattern")))
7939 (build-system r-build-system)
7941 `(("r-biostrings" ,r-biostrings)
7942 ("r-genomicranges" ,r-genomicranges)
7943 ("r-iranges" ,r-iranges)
7944 ("r-kernsmooth" ,r-kernsmooth)
7945 ("r-plotrix" ,r-plotrix)))
7946 (home-page "https://bioconductor.org/packages/seqPattern")
7947 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7949 "This package provides tools to visualize oligonucleotide patterns and
7950 sequence motif occurrences across a large set of sequences centred at a common
7951 reference point and sorted by a user defined feature.")
7952 (license license:gpl3+)))
7954 (define-public r-genomation
7956 (name "r-genomation")
7960 (uri (bioconductor-uri "genomation" version))
7963 "1vdmdyrq0n7pf8cvy2950v7hrcrcbd9zl4fg7dcmyly3iiwdyirp"))))
7964 (build-system r-build-system)
7966 `(("r-biostrings" ,r-biostrings)
7967 ("r-bsgenome" ,r-bsgenome)
7968 ("r-data-table" ,r-data-table)
7969 ("r-genomeinfodb" ,r-genomeinfodb)
7970 ("r-genomicalignments" ,r-genomicalignments)
7971 ("r-genomicranges" ,r-genomicranges)
7972 ("r-ggplot2" ,r-ggplot2)
7973 ("r-gridbase" ,r-gridbase)
7974 ("r-impute" ,r-impute)
7975 ("r-iranges" ,r-iranges)
7976 ("r-matrixstats" ,r-matrixstats)
7977 ("r-plotrix" ,r-plotrix)
7980 ("r-readr" ,r-readr)
7981 ("r-reshape2" ,r-reshape2)
7982 ("r-rsamtools" ,r-rsamtools)
7983 ("r-rtracklayer" ,r-rtracklayer)
7984 ("r-runit" ,r-runit)
7985 ("r-s4vectors" ,r-s4vectors)
7986 ("r-seqpattern" ,r-seqpattern)))
7987 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7988 (synopsis "Summary, annotation and visualization of genomic data")
7990 "This package provides a package for summary and annotation of genomic
7991 intervals. Users can visualize and quantify genomic intervals over
7992 pre-defined functional regions, such as promoters, exons, introns, etc. The
7993 genomic intervals represent regions with a defined chromosome position, which
7994 may be associated with a score, such as aligned reads from HT-seq experiments,
7995 TF binding sites, methylation scores, etc. The package can use any tabular
7996 genomic feature data as long as it has minimal information on the locations of
7997 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7998 (license license:artistic2.0)))
8000 (define-public r-genomationdata
8002 (name "r-genomationdata")
8006 ;; We cannot use bioconductor-uri here because this tarball is
8007 ;; located under "data/annotation/" instead of "bioc/".
8008 (uri (string-append "https://bioconductor.org/packages/"
8009 "release/data/experiment/src/contrib/"
8010 "genomationData_" version ".tar.gz"))
8013 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
8014 (build-system r-build-system)
8015 ;; As this package provides little more than large data files, it doesn't
8016 ;; make sense to build substitutes.
8017 (arguments `(#:substitutable? #f))
8019 `(("r-knitr" ,r-knitr)))
8020 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8021 (synopsis "Experimental data for use with the genomation package")
8023 "This package contains experimental genetic data for use with the
8024 genomation package. Included are Chip Seq, Methylation and Cage data,
8025 downloaded from Encode.")
8026 (license license:gpl3+)))
8028 (define-public r-org-hs-eg-db
8030 (name "r-org-hs-eg-db")
8034 ;; We cannot use bioconductor-uri here because this tarball is
8035 ;; located under "data/annotation/" instead of "bioc/".
8036 (uri (string-append "https://www.bioconductor.org/packages/"
8037 "release/data/annotation/src/contrib/"
8038 "org.Hs.eg.db_" version ".tar.gz"))
8041 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
8043 `((upstream-name . "org.Hs.eg.db")))
8044 (build-system r-build-system)
8046 `(("r-annotationdbi" ,r-annotationdbi)))
8047 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8048 (synopsis "Genome wide annotation for Human")
8050 "This package contains genome-wide annotations for Human, primarily based
8051 on mapping using Entrez Gene identifiers.")
8052 (license license:artistic2.0)))
8054 (define-public r-org-ce-eg-db
8056 (name "r-org-ce-eg-db")
8060 ;; We cannot use bioconductor-uri here because this tarball is
8061 ;; located under "data/annotation/" instead of "bioc/".
8062 (uri (string-append "https://www.bioconductor.org/packages/"
8063 "release/data/annotation/src/contrib/"
8064 "org.Ce.eg.db_" version ".tar.gz"))
8067 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8069 `((upstream-name . "org.Ce.eg.db")))
8070 (build-system r-build-system)
8072 `(("r-annotationdbi" ,r-annotationdbi)))
8073 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8074 (synopsis "Genome wide annotation for Worm")
8076 "This package provides mappings from Entrez gene identifiers to various
8077 annotations for the genome of the model worm Caenorhabditis elegans.")
8078 (license license:artistic2.0)))
8080 (define-public r-org-dm-eg-db
8082 (name "r-org-dm-eg-db")
8086 ;; We cannot use bioconductor-uri here because this tarball is
8087 ;; located under "data/annotation/" instead of "bioc/".
8088 (uri (string-append "https://www.bioconductor.org/packages/"
8089 "release/data/annotation/src/contrib/"
8090 "org.Dm.eg.db_" version ".tar.gz"))
8093 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8095 `((upstream-name . "org.Dm.eg.db")))
8096 (build-system r-build-system)
8098 `(("r-annotationdbi" ,r-annotationdbi)))
8099 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8100 (synopsis "Genome wide annotation for Fly")
8102 "This package provides mappings from Entrez gene identifiers to various
8103 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8104 (license license:artistic2.0)))
8106 (define-public r-org-mm-eg-db
8108 (name "r-org-mm-eg-db")
8112 ;; We cannot use bioconductor-uri here because this tarball is
8113 ;; located under "data/annotation/" instead of "bioc/".
8114 (uri (string-append "https://www.bioconductor.org/packages/"
8115 "release/data/annotation/src/contrib/"
8116 "org.Mm.eg.db_" version ".tar.gz"))
8119 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8121 `((upstream-name . "org.Mm.eg.db")))
8122 (build-system r-build-system)
8124 `(("r-annotationdbi" ,r-annotationdbi)))
8125 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8126 (synopsis "Genome wide annotation for Mouse")
8128 "This package provides mappings from Entrez gene identifiers to various
8129 annotations for the genome of the model mouse Mus musculus.")
8130 (license license:artistic2.0)))
8132 (define-public r-seqlogo
8139 (uri (bioconductor-uri "seqLogo" version))
8142 "16xvqcdknix9vjm8mrixi6nyfsr45jm844jh1x90m8044lwrsic1"))))
8143 (properties `((upstream-name . "seqLogo")))
8144 (build-system r-build-system)
8145 (home-page "https://bioconductor.org/packages/seqLogo")
8146 (synopsis "Sequence logos for DNA sequence alignments")
8148 "seqLogo takes the position weight matrix of a DNA sequence motif and
8149 plots the corresponding sequence logo as introduced by Schneider and
8151 (license license:lgpl2.0+)))
8153 (define-public r-bsgenome-hsapiens-ucsc-hg19
8155 (name "r-bsgenome-hsapiens-ucsc-hg19")
8159 ;; We cannot use bioconductor-uri here because this tarball is
8160 ;; located under "data/annotation/" instead of "bioc/".
8161 (uri (string-append "https://www.bioconductor.org/packages/"
8162 "release/data/annotation/src/contrib/"
8163 "BSgenome.Hsapiens.UCSC.hg19_"
8167 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8169 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8170 (build-system r-build-system)
8171 ;; As this package provides little more than a very large data file it
8172 ;; doesn't make sense to build substitutes.
8173 (arguments `(#:substitutable? #f))
8175 `(("r-bsgenome" ,r-bsgenome)))
8177 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8178 (synopsis "Full genome sequences for Homo sapiens")
8180 "This package provides full genome sequences for Homo sapiens as provided
8181 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8182 (license license:artistic2.0)))
8184 (define-public r-bsgenome-mmusculus-ucsc-mm9
8186 (name "r-bsgenome-mmusculus-ucsc-mm9")
8190 ;; We cannot use bioconductor-uri here because this tarball is
8191 ;; located under "data/annotation/" instead of "bioc/".
8192 (uri (string-append "https://www.bioconductor.org/packages/"
8193 "release/data/annotation/src/contrib/"
8194 "BSgenome.Mmusculus.UCSC.mm9_"
8198 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8200 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8201 (build-system r-build-system)
8202 ;; As this package provides little more than a very large data file it
8203 ;; doesn't make sense to build substitutes.
8204 (arguments `(#:substitutable? #f))
8206 `(("r-bsgenome" ,r-bsgenome)))
8208 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8209 (synopsis "Full genome sequences for Mouse")
8211 "This package provides full genome sequences for Mus musculus (Mouse) as
8212 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8213 (license license:artistic2.0)))
8215 (define-public r-bsgenome-mmusculus-ucsc-mm10
8217 (name "r-bsgenome-mmusculus-ucsc-mm10")
8221 ;; We cannot use bioconductor-uri here because this tarball is
8222 ;; located under "data/annotation/" instead of "bioc/".
8223 (uri (string-append "https://www.bioconductor.org/packages/"
8224 "release/data/annotation/src/contrib/"
8225 "BSgenome.Mmusculus.UCSC.mm10_"
8229 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8231 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8232 (build-system r-build-system)
8233 ;; As this package provides little more than a very large data file it
8234 ;; doesn't make sense to build substitutes.
8235 (arguments `(#:substitutable? #f))
8237 `(("r-bsgenome" ,r-bsgenome)))
8239 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8240 (synopsis "Full genome sequences for Mouse")
8242 "This package provides full genome sequences for Mus
8243 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8244 in Biostrings objects.")
8245 (license license:artistic2.0)))
8247 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8249 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8253 ;; We cannot use bioconductor-uri here because this tarball is
8254 ;; located under "data/annotation/" instead of "bioc/".
8255 (uri (string-append "https://www.bioconductor.org/packages/"
8256 "release/data/annotation/src/contrib/"
8257 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8261 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8263 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8264 (build-system r-build-system)
8265 ;; As this package provides little more than a very large data file it
8266 ;; doesn't make sense to build substitutes.
8267 (arguments `(#:substitutable? #f))
8269 `(("r-bsgenome" ,r-bsgenome)
8270 ("r-genomicfeatures" ,r-genomicfeatures)
8271 ("r-annotationdbi" ,r-annotationdbi)))
8273 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8274 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8276 "This package loads a TxDb object, which is an R interface to
8277 prefabricated databases contained in this package. This package provides
8278 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8279 based on the knownGene track.")
8280 (license license:artistic2.0)))
8282 (define-public r-bsgenome-celegans-ucsc-ce6
8284 (name "r-bsgenome-celegans-ucsc-ce6")
8288 ;; We cannot use bioconductor-uri here because this tarball is
8289 ;; located under "data/annotation/" instead of "bioc/".
8290 (uri (string-append "https://www.bioconductor.org/packages/"
8291 "release/data/annotation/src/contrib/"
8292 "BSgenome.Celegans.UCSC.ce6_"
8296 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8298 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8299 (build-system r-build-system)
8300 ;; As this package provides little more than a very large data file it
8301 ;; doesn't make sense to build substitutes.
8302 (arguments `(#:substitutable? #f))
8304 `(("r-bsgenome" ,r-bsgenome)))
8306 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8307 (synopsis "Full genome sequences for Worm")
8309 "This package provides full genome sequences for Caenorhabditis
8310 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8312 (license license:artistic2.0)))
8314 (define-public r-bsgenome-celegans-ucsc-ce10
8316 (name "r-bsgenome-celegans-ucsc-ce10")
8320 ;; We cannot use bioconductor-uri here because this tarball is
8321 ;; located under "data/annotation/" instead of "bioc/".
8322 (uri (string-append "https://www.bioconductor.org/packages/"
8323 "release/data/annotation/src/contrib/"
8324 "BSgenome.Celegans.UCSC.ce10_"
8328 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8330 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8331 (build-system r-build-system)
8332 ;; As this package provides little more than a very large data file it
8333 ;; doesn't make sense to build substitutes.
8334 (arguments `(#:substitutable? #f))
8336 `(("r-bsgenome" ,r-bsgenome)))
8338 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8339 (synopsis "Full genome sequences for Worm")
8341 "This package provides full genome sequences for Caenorhabditis
8342 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8344 (license license:artistic2.0)))
8346 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8348 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8352 ;; We cannot use bioconductor-uri here because this tarball is
8353 ;; located under "data/annotation/" instead of "bioc/".
8354 (uri (string-append "https://www.bioconductor.org/packages/"
8355 "release/data/annotation/src/contrib/"
8356 "BSgenome.Dmelanogaster.UCSC.dm3_"
8360 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8362 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8363 (build-system r-build-system)
8364 ;; As this package provides little more than a very large data file it
8365 ;; doesn't make sense to build substitutes.
8366 (arguments `(#:substitutable? #f))
8368 `(("r-bsgenome" ,r-bsgenome)))
8370 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8371 (synopsis "Full genome sequences for Fly")
8373 "This package provides full genome sequences for Drosophila
8374 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8375 Biostrings objects.")
8376 (license license:artistic2.0)))
8378 (define-public r-motifrg
8385 (uri (bioconductor-uri "motifRG" version))
8388 "0mxhyidkyd2zqahdbg69y20r550z78lvr1r3pbjymnwfg4hcfq1p"))))
8389 (properties `((upstream-name . "motifRG")))
8390 (build-system r-build-system)
8392 `(("r-biostrings" ,r-biostrings)
8393 ("r-bsgenome" ,r-bsgenome)
8394 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8395 ("r-iranges" ,r-iranges)
8396 ("r-seqlogo" ,r-seqlogo)
8397 ("r-xvector" ,r-xvector)))
8398 (home-page "https://bioconductor.org/packages/motifRG")
8399 (synopsis "Discover motifs in high throughput sequencing data")
8401 "This package provides tools for discriminative motif discovery in high
8402 throughput genetic sequencing data sets using regression methods.")
8403 (license license:artistic2.0)))
8405 (define-public r-qtl
8412 (uri (string-append "mirror://cran/src/contrib/qtl_"
8416 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8417 (build-system r-build-system)
8418 (home-page "http://rqtl.org/")
8419 (synopsis "R package for analyzing QTL experiments in genetics")
8420 (description "R/qtl is an extension library for the R statistics
8421 system. It is used to analyze experimental crosses for identifying
8422 genes contributing to variation in quantitative traits (so-called
8423 quantitative trait loci, QTLs).
8425 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8426 identify genotyping errors, and to perform single-QTL and two-QTL,
8427 two-dimensional genome scans.")
8428 (license license:gpl3)))
8430 (define-public r-zlibbioc
8436 (uri (bioconductor-uri "zlibbioc" version))
8439 "1rwr0mci8a712q0isavi4jmhm94gwivc4nr8j7r4kw05flp4g7gz"))))
8441 `((upstream-name . "zlibbioc")))
8442 (build-system r-build-system)
8443 (home-page "https://bioconductor.org/packages/zlibbioc")
8444 (synopsis "Provider for zlib-1.2.5 to R packages")
8445 (description "This package uses the source code of zlib-1.2.5 to create
8446 libraries for systems that do not have these available via other means.")
8447 (license license:artistic2.0)))
8449 (define-public r-r4rna
8456 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8460 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8461 (build-system r-build-system)
8463 `(("r-optparse" ,r-optparse)
8464 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8465 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8466 (synopsis "Analysis framework for RNA secondary structure")
8468 "The R4RNA package aims to be a general framework for the analysis of RNA
8469 secondary structure and comparative analysis in R.")
8470 (license license:gpl3+)))
8472 (define-public r-rhtslib
8479 (uri (bioconductor-uri "Rhtslib" version))
8482 "16ywnb8cmr2xabd1i21b92rfziw7xfbv25yv16ipw617p41wa39z"))))
8483 (properties `((upstream-name . "Rhtslib")))
8484 (build-system r-build-system)
8486 `(("r-zlibbioc" ,r-zlibbioc)))
8490 `(("pkg-config" ,pkg-config)))
8491 (home-page "https://github.com/nhayden/Rhtslib")
8492 (synopsis "High-throughput sequencing library as an R package")
8494 "This package provides the HTSlib C library for high-throughput
8495 nucleotide sequence analysis. The package is primarily useful to developers
8496 of other R packages who wish to make use of HTSlib.")
8497 (license license:lgpl2.0+)))
8499 (define-public r-bamsignals
8501 (name "r-bamsignals")
8506 (uri (bioconductor-uri "bamsignals" version))
8509 "141q3p4lzwiqk1mfxi8q1q84axjl0gyiqg59xd3sp4viny4jqmgv"))))
8510 (build-system r-build-system)
8512 `(("r-biocgenerics" ,r-biocgenerics)
8513 ("r-genomicranges" ,r-genomicranges)
8514 ("r-iranges" ,r-iranges)
8516 ("r-rhtslib" ,r-rhtslib)
8517 ("r-zlibbioc" ,r-zlibbioc)))
8520 (home-page "https://bioconductor.org/packages/bamsignals")
8521 (synopsis "Extract read count signals from bam files")
8523 "This package allows to efficiently obtain count vectors from indexed bam
8524 files. It counts the number of nucleotide sequence reads in given genomic
8525 ranges and it computes reads profiles and coverage profiles. It also handles
8527 (license license:gpl2+)))
8529 (define-public r-rcas
8535 (uri (bioconductor-uri "RCAS" version))
8538 "0vmn7a0rm2ban0kaxrf5danhss2r4hfhnwh5889fjcgqy300fdd5"))))
8539 (build-system r-build-system)
8541 `(("r-testthat" ,r-testthat)
8542 ;; During vignette building knitr checks that "pandoc-citeproc"
8544 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8546 `(("r-biocgenerics" ,r-biocgenerics)
8547 ("r-biomart" ,r-biomart)
8548 ("r-biostrings" ,r-biostrings)
8549 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8550 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8551 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8552 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8553 ("r-cowplot" ,r-cowplot)
8554 ("r-data-table" ,r-data-table)
8557 ("r-genomation" ,r-genomation)
8558 ("r-genomicfeatures" ,r-genomicfeatures)
8559 ("r-ggplot2" ,r-ggplot2)
8560 ("r-ggseqlogo" ,r-ggseqlogo)
8561 ("r-knitr" ,r-knitr)
8562 ("r-motifrg" ,r-motifrg)
8563 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8564 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8565 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8566 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8567 ("r-pbapply" ,r-pbapply)
8568 ("r-pheatmap" ,r-pheatmap)
8569 ("r-plotly" ,r-plotly)
8570 ("r-plotrix" ,r-plotrix)
8571 ("r-proxy" ,r-proxy)
8572 ("r-rsqlite" ,r-rsqlite)
8573 ("r-rtracklayer" ,r-rtracklayer)
8574 ("r-rmarkdown" ,r-rmarkdown)
8575 ("r-s4vectors" ,r-s4vectors)
8576 ("r-topgo" ,r-topgo)))
8577 (synopsis "RNA-centric annotation system")
8579 "RCAS aims to be a standalone RNA-centric annotation system that provides
8580 intuitive reports and publication-ready graphics. This package provides the R
8581 library implementing most of the pipeline's features.")
8582 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8583 (license license:artistic2.0)))
8585 (define-public rcas-web
8592 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8593 "releases/download/v" version
8594 "/rcas-web-" version ".tar.gz"))
8597 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8598 (build-system gnu-build-system)
8601 (modify-phases %standard-phases
8602 (add-after 'install 'wrap-executable
8603 (lambda* (#:key inputs outputs #:allow-other-keys)
8604 (let* ((out (assoc-ref outputs "out"))
8605 (json (assoc-ref inputs "guile-json"))
8606 (redis (assoc-ref inputs "guile-redis"))
8607 (path (string-append
8608 json "/share/guile/site/2.2:"
8609 redis "/share/guile/site/2.2")))
8610 (wrap-program (string-append out "/bin/rcas-web")
8611 `("GUILE_LOAD_PATH" ":" = (,path))
8612 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8613 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8616 `(("r-minimal" ,r-minimal)
8618 ("guile-next" ,guile-2.2)
8619 ("guile-json" ,guile-json)
8620 ("guile-redis" ,guile2.2-redis)))
8622 `(("pkg-config" ,pkg-config)))
8623 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8624 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8625 (description "This package provides a simple web interface for the
8626 @dfn{RNA-centric annotation system} (RCAS).")
8627 (license license:agpl3+)))
8629 (define-public r-mutationalpatterns
8631 (name "r-mutationalpatterns")
8636 (uri (bioconductor-uri "MutationalPatterns" version))
8639 "1yq7351j42mjxn8fd3c5bdxzb2l5s4lvqhjdvv4rwj4f600n6wj9"))))
8640 (build-system r-build-system)
8642 `(("r-biocgenerics" ,r-biocgenerics)
8643 ("r-biostrings" ,r-biostrings)
8644 ;; These two packages are suggested packages
8645 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8646 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8647 ("r-genomicranges" ,r-genomicranges)
8648 ("r-genomeinfodb" ,r-genomeinfodb)
8649 ("r-ggplot2" ,r-ggplot2)
8650 ("r-iranges" ,r-iranges)
8653 ("r-pracma" ,r-pracma)
8654 ("r-reshape2" ,r-reshape2)
8655 ("r-cowplot" ,r-cowplot)
8656 ("r-ggdendro" ,r-ggdendro)
8657 ("r-s4vectors" ,r-s4vectors)
8658 ("r-summarizedexperiment" ,r-summarizedexperiment)
8659 ("r-variantannotation" ,r-variantannotation)))
8660 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8661 (synopsis "Extract and visualize mutational patterns in genomic data")
8662 (description "This package provides an extensive toolset for the
8663 characterization and visualization of a wide range of mutational patterns
8664 in SNV base substitution data.")
8665 (license license:expat)))
8667 (define-public r-wgcna
8674 (uri (cran-uri "WGCNA" version))
8677 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8678 (properties `((upstream-name . "WGCNA")))
8679 (build-system r-build-system)
8681 `(("r-annotationdbi" ,r-annotationdbi)
8682 ("r-doparallel" ,r-doparallel)
8683 ("r-dynamictreecut" ,r-dynamictreecut)
8684 ("r-fastcluster" ,r-fastcluster)
8685 ("r-foreach" ,r-foreach)
8686 ("r-go-db" ,r-go-db)
8687 ("r-hmisc" ,r-hmisc)
8688 ("r-impute" ,r-impute)
8690 ("r-robust" ,r-robust)
8691 ("r-survival" ,r-survival)
8692 ("r-matrixstats" ,r-matrixstats)
8693 ("r-preprocesscore" ,r-preprocesscore)))
8695 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8696 (synopsis "Weighted correlation network analysis")
8698 "This package provides functions necessary to perform Weighted
8699 Correlation Network Analysis on high-dimensional data. It includes functions
8700 for rudimentary data cleaning, construction and summarization of correlation
8701 networks, module identification and functions for relating both variables and
8702 modules to sample traits. It also includes a number of utility functions for
8703 data manipulation and visualization.")
8704 (license license:gpl2+)))
8706 (define-public r-chipkernels
8707 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8710 (name "r-chipkernels")
8711 (version (string-append "1.1-" revision "." (string-take commit 9)))
8716 (url "https://github.com/ManuSetty/ChIPKernels.git")
8718 (file-name (string-append name "-" version))
8721 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8722 (build-system r-build-system)
8724 `(("r-iranges" ,r-iranges)
8725 ("r-xvector" ,r-xvector)
8726 ("r-biostrings" ,r-biostrings)
8727 ("r-bsgenome" ,r-bsgenome)
8728 ("r-gtools" ,r-gtools)
8729 ("r-genomicranges" ,r-genomicranges)
8730 ("r-sfsmisc" ,r-sfsmisc)
8731 ("r-kernlab" ,r-kernlab)
8732 ("r-s4vectors" ,r-s4vectors)
8733 ("r-biocgenerics" ,r-biocgenerics)))
8734 (home-page "https://github.com/ManuSetty/ChIPKernels")
8735 (synopsis "Build string kernels for DNA Sequence analysis")
8736 (description "ChIPKernels is an R package for building different string
8737 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8738 must be built and this dictionary can be used for determining kernels for DNA
8740 (license license:gpl2+))))
8742 (define-public r-seqgl
8749 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8750 "archive/" version ".tar.gz"))
8751 (file-name (string-append name "-" version ".tar.gz"))
8754 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8755 (build-system r-build-system)
8757 `(("r-biostrings" ,r-biostrings)
8758 ("r-chipkernels" ,r-chipkernels)
8759 ("r-genomicranges" ,r-genomicranges)
8760 ("r-spams" ,r-spams)
8761 ("r-wgcna" ,r-wgcna)
8762 ("r-fastcluster" ,r-fastcluster)))
8763 (home-page "https://github.com/ManuSetty/SeqGL")
8764 (synopsis "Group lasso for Dnase/ChIP-seq data")
8765 (description "SeqGL is a group lasso based algorithm to extract
8766 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8767 This package presents a method which uses group lasso to discriminate between
8768 bound and non bound genomic regions to accurately identify transcription
8769 factors bound at the specific regions.")
8770 (license license:gpl2+)))
8772 (define-public r-gkmsvm
8779 (uri (cran-uri "gkmSVM" version))
8782 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8783 (properties `((upstream-name . "gkmSVM")))
8784 (build-system r-build-system)
8786 `(("r-biocgenerics" ,r-biocgenerics)
8787 ("r-biostrings" ,r-biostrings)
8788 ("r-genomeinfodb" ,r-genomeinfodb)
8789 ("r-genomicranges" ,r-genomicranges)
8790 ("r-iranges" ,r-iranges)
8791 ("r-kernlab" ,r-kernlab)
8794 ("r-rtracklayer" ,r-rtracklayer)
8795 ("r-s4vectors" ,r-s4vectors)
8796 ("r-seqinr" ,r-seqinr)))
8797 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8798 (synopsis "Gapped-kmer support vector machine")
8800 "This R package provides tools for training gapped-kmer SVM classifiers
8801 for DNA and protein sequences. This package supports several sequence
8802 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8803 (license license:gpl2+)))
8805 (define-public r-tximport
8811 (uri (bioconductor-uri "tximport" version))
8814 "1qjc7ah9dzccpvcjrp9k4qnaz13x6kvy1c1xpdj503km6k528lip"))))
8815 (build-system r-build-system)
8816 (home-page "https://bioconductor.org/packages/tximport")
8817 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8819 "This package provides tools to import transcript-level abundance,
8820 estimated counts and transcript lengths, and to summarize them into matrices
8821 for use with downstream gene-level analysis packages. Average transcript
8822 length, weighted by sample-specific transcript abundance estimates, is
8823 provided as a matrix which can be used as an offset for different expression
8824 of gene-level counts.")
8825 (license license:gpl2+)))
8827 (define-public r-rhdf5
8833 (uri (bioconductor-uri "rhdf5" version))
8836 "15cmmchhk8bnp94gxg0zk9qyzdjx5kv16dzpbnb62mkq7ydmifx6"))))
8837 (build-system r-build-system)
8839 `(("r-rhdf5lib" ,r-rhdf5lib)))
8842 (home-page "https://bioconductor.org/packages/rhdf5")
8843 (synopsis "HDF5 interface to R")
8845 "This R/Bioconductor package provides an interface between HDF5 and R.
8846 HDF5's main features are the ability to store and access very large and/or
8847 complex datasets and a wide variety of metadata on mass storage (disk) through
8848 a completely portable file format. The rhdf5 package is thus suited for the
8849 exchange of large and/or complex datasets between R and other software
8850 package, and for letting R applications work on datasets that are larger than
8851 the available RAM.")
8852 (license license:artistic2.0)))
8854 (define-public r-annotationfilter
8856 (name "r-annotationfilter")
8860 (uri (bioconductor-uri "AnnotationFilter" version))
8863 "1w8ypfdz4g7vnwfrvnhjcpm8waciqyq2cn883ajdwg4vv7a5mj9a"))))
8865 `((upstream-name . "AnnotationFilter")))
8866 (build-system r-build-system)
8868 `(("r-genomicranges" ,r-genomicranges)
8869 ("r-lazyeval" ,r-lazyeval)))
8870 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8871 (synopsis "Facilities for filtering Bioconductor annotation resources")
8873 "This package provides classes and other infrastructure to implement
8874 filters for manipulating Bioconductor annotation resources. The filters are
8875 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8876 (license license:artistic2.0)))
8878 (define-public emboss
8884 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8885 (version-major+minor version) ".0/"
8886 "EMBOSS-" version ".tar.gz"))
8889 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8890 (build-system gnu-build-system)
8893 (list (string-append "--with-hpdf="
8894 (assoc-ref %build-inputs "libharu")))
8896 (modify-phases %standard-phases
8897 (add-after 'unpack 'fix-checks
8899 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8900 ;; and zlib, but assume that they are all found at the same
8902 (substitute* "configure.in"
8903 (("CHECK_PNGDRIVER")
8904 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8905 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8906 AM_CONDITIONAL(AMPNG, true)"))
8908 (add-after 'fix-checks 'disable-update-check
8910 ;; At build time there is no connection to the Internet, so
8911 ;; looking for updates will not work.
8912 (substitute* "Makefile.am"
8913 (("\\$\\(bindir\\)/embossupdate") ""))
8915 (add-after 'disable-update-check 'autogen
8916 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8922 ("libharu" ,libharu)
8925 `(("autoconf" ,autoconf)
8926 ("automake" ,automake)
8927 ("libtool" ,libtool)
8928 ("pkg-config" ,pkg-config)))
8929 (home-page "http://emboss.sourceforge.net")
8930 (synopsis "Molecular biology analysis suite")
8931 (description "EMBOSS is the \"European Molecular Biology Open Software
8932 Suite\". EMBOSS is an analysis package specially developed for the needs of
8933 the molecular biology (e.g. EMBnet) user community. The software
8934 automatically copes with data in a variety of formats and even allows
8935 transparent retrieval of sequence data from the web. It also provides a
8936 number of libraries for the development of software in the field of molecular
8937 biology. EMBOSS also integrates a range of currently available packages and
8938 tools for sequence analysis into a seamless whole.")
8939 (license license:gpl2+)))
8942 (let ((revision "1")
8943 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8946 ;; The version is 2.13.0 even though no release archives have been
8947 ;; published as yet.
8948 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8952 (url "https://github.com/arq5x/bits.git")
8954 (file-name (string-append name "-" version "-checkout"))
8957 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8958 (build-system gnu-build-system)
8960 `(#:tests? #f ;no tests included
8962 (modify-phases %standard-phases
8964 (add-after 'unpack 'remove-cuda
8966 (substitute* "Makefile"
8968 (("(bits_test_intersections) \\\\" _ match) match))
8971 (lambda* (#:key outputs #:allow-other-keys)
8973 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8978 (home-page "https://github.com/arq5x/bits")
8979 (synopsis "Implementation of binary interval search algorithm")
8980 (description "This package provides an implementation of the
8981 BITS (Binary Interval Search) algorithm, an approach to interval set
8982 intersection. It is especially suited for the comparison of diverse genomic
8983 datasets and the exploration of large datasets of genome
8984 intervals (e.g. genes, sequence alignments).")
8985 (license license:gpl2))))
8987 (define-public piranha
8988 ;; There is no release tarball for the latest version. The latest commit is
8989 ;; older than one year at the time of this writing.
8990 (let ((revision "1")
8991 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8994 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8998 (url "https://github.com/smithlabcode/piranha.git")
9000 (file-name (git-file-name name version))
9003 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9004 (build-system gnu-build-system)
9006 `(#:test-target "test"
9008 (modify-phases %standard-phases
9009 (add-after 'unpack 'copy-smithlab-cpp
9010 (lambda* (#:key inputs #:allow-other-keys)
9011 (for-each (lambda (file)
9012 (install-file file "./src/smithlab_cpp/"))
9013 (find-files (assoc-ref inputs "smithlab-cpp")))
9015 (add-after 'install 'install-to-store
9016 (lambda* (#:key outputs #:allow-other-keys)
9017 (let* ((out (assoc-ref outputs "out"))
9018 (bin (string-append out "/bin")))
9019 (for-each (lambda (file)
9020 (install-file file bin))
9021 (find-files "bin" ".*")))
9024 (list (string-append "--with-bam_tools_headers="
9025 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9026 (string-append "--with-bam_tools_library="
9027 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9029 `(("bamtools" ,bamtools)
9030 ("samtools" ,samtools-0.1)
9033 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9037 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9039 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9042 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9044 `(("python" ,python-2)))
9045 (home-page "https://github.com/smithlabcode/piranha")
9046 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9048 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9049 RIP-seq experiments. It takes input in BED or BAM format and identifies
9050 regions of statistically significant read enrichment. Additional covariates
9051 may optionally be provided to further inform the peak-calling process.")
9052 (license license:gpl3+))))
9060 (uri (string-append "https://pypi.python.org/packages/source/P"
9061 "/PePr/PePr-" version ".tar.gz"))
9064 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9065 (build-system python-build-system)
9067 `(#:python ,python-2 ; python2 only
9068 #:tests? #f)) ; no tests included
9070 `(("python2-numpy" ,python2-numpy)
9071 ("python2-scipy" ,python2-scipy)
9072 ("python2-pysam" ,python2-pysam)))
9073 (home-page "https://github.com/shawnzhangyx/PePr")
9074 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9076 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9077 that is primarily designed for data with biological replicates. It uses a
9078 negative binomial distribution to model the read counts among the samples in
9079 the same group, and look for consistent differences between ChIP and control
9080 group or two ChIP groups run under different conditions.")
9081 (license license:gpl3+)))
9083 (define-public filevercmp
9084 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9087 (version (string-append "0-1." (string-take commit 7)))
9090 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9092 (file-name (string-append name "-" version ".tar.gz"))
9094 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9095 (build-system gnu-build-system)
9097 `(#:tests? #f ; There are no tests to run.
9099 (modify-phases %standard-phases
9100 (delete 'configure) ; There is no configure phase.
9102 (lambda* (#:key outputs #:allow-other-keys)
9103 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9104 (install-file "filevercmp" bin)))))))
9105 (home-page "https://github.com/ekg/filevercmp")
9106 (synopsis "This program compares version strings")
9107 (description "This program compares version strings. It intends to be a
9108 replacement for strverscmp.")
9109 (license license:gpl3+))))
9111 (define-public multiqc
9118 (uri (pypi-uri "multiqc" version))
9121 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9122 (build-system python-build-system)
9124 `(("python-jinja2" ,python-jinja2)
9125 ("python-simplejson" ,python-simplejson)
9126 ("python-pyyaml" ,python-pyyaml)
9127 ("python-click" ,python-click)
9128 ("python-spectra" ,python-spectra)
9129 ("python-requests" ,python-requests)
9130 ("python-markdown" ,python-markdown)
9131 ("python-lzstring" ,python-lzstring)
9132 ("python-matplotlib" ,python-matplotlib)
9133 ("python-numpy" ,python-numpy)
9134 ;; MultQC checks for the presence of nose at runtime.
9135 ("python-nose" ,python-nose)))
9138 (modify-phases %standard-phases
9139 (add-after 'unpack 'relax-requirements
9141 (substitute* "setup.py"
9142 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9143 ;; than the one in Guix, but should work fine with 2.2.2.
9144 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9145 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9146 (("['\"]matplotlib.*?['\"]")
9149 (home-page "http://multiqc.info")
9150 (synopsis "Aggregate bioinformatics analysis reports")
9152 "MultiQC is a tool to aggregate bioinformatics results across many
9153 samples into a single report. It contains modules for a large number of
9154 common bioinformatics tools.")
9155 (license license:gpl3+)))
9157 (define-public r-chipseq
9164 (uri (bioconductor-uri "chipseq" version))
9167 "09f8dgl5ni75qkf7nvvppwr3irpplv4xb3ks59ld7l8i2mplcrx7"))))
9168 (build-system r-build-system)
9170 `(("r-biocgenerics" ,r-biocgenerics)
9171 ("r-genomicranges" ,r-genomicranges)
9172 ("r-iranges" ,r-iranges)
9173 ("r-lattice" ,r-lattice)
9174 ("r-s4vectors" ,r-s4vectors)
9175 ("r-shortread" ,r-shortread)))
9176 (home-page "https://bioconductor.org/packages/chipseq")
9177 (synopsis "Package for analyzing ChIPseq data")
9179 "This package provides tools for processing short read data from ChIPseq
9181 (license license:artistic2.0)))
9183 (define-public r-copyhelper
9185 (name "r-copyhelper")
9190 (uri (string-append "https://bioconductor.org/packages/release/"
9191 "data/experiment/src/contrib/CopyhelpeR_"
9195 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9196 (properties `((upstream-name . "CopyhelpeR")))
9197 (build-system r-build-system)
9198 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9199 (synopsis "Helper files for CopywriteR")
9201 "This package contains the helper files that are required to run the
9202 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9203 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9204 mm10. In addition, it contains a blacklist filter to remove regions that
9205 display copy number variation. Files are stored as GRanges objects from the
9206 GenomicRanges Bioconductor package.")
9207 (license license:gpl2)))
9209 (define-public r-copywriter
9211 (name "r-copywriter")
9216 (uri (bioconductor-uri "CopywriteR" version))
9219 "0b7xwq1va2zclb54f07c5ipmmq4iv2hrlph3j93jz5hmyayv50z3"))))
9220 (properties `((upstream-name . "CopywriteR")))
9221 (build-system r-build-system)
9223 `(("r-biocparallel" ,r-biocparallel)
9224 ("r-chipseq" ,r-chipseq)
9225 ("r-copyhelper" ,r-copyhelper)
9226 ("r-data-table" ,r-data-table)
9227 ("r-dnacopy" ,r-dnacopy)
9228 ("r-futile-logger" ,r-futile-logger)
9229 ("r-genomeinfodb" ,r-genomeinfodb)
9230 ("r-genomicalignments" ,r-genomicalignments)
9231 ("r-genomicranges" ,r-genomicranges)
9232 ("r-gtools" ,r-gtools)
9233 ("r-iranges" ,r-iranges)
9234 ("r-matrixstats" ,r-matrixstats)
9235 ("r-rsamtools" ,r-rsamtools)
9236 ("r-s4vectors" ,r-s4vectors)))
9237 (home-page "https://github.com/PeeperLab/CopywriteR")
9238 (synopsis "Copy number information from targeted sequencing")
9240 "CopywriteR extracts DNA copy number information from targeted sequencing
9241 by utilizing off-target reads. It allows for extracting uniformly distributed
9242 copy number information, can be used without reference, and can be applied to
9243 sequencing data obtained from various techniques including chromatin
9244 immunoprecipitation and target enrichment on small gene panels. Thereby,
9245 CopywriteR constitutes a widely applicable alternative to available copy
9246 number detection tools.")
9247 (license license:gpl2)))
9249 (define-public r-methylkit
9251 (name "r-methylkit")
9255 (uri (bioconductor-uri "methylKit" version))
9258 "1hr2czi5ybdf7hdmqsv39d17f3mvmw94wa38bc14zzm9mgy9gfy7"))))
9259 (properties `((upstream-name . "methylKit")))
9260 (build-system r-build-system)
9262 `(("r-data-table" ,r-data-table)
9263 ("r-emdbook" ,r-emdbook)
9264 ("r-fastseg" ,r-fastseg)
9265 ("r-genomeinfodb" ,r-genomeinfodb)
9266 ("r-genomicranges" ,r-genomicranges)
9267 ("r-gtools" ,r-gtools)
9268 ("r-iranges" ,r-iranges)
9269 ("r-kernsmooth" ,r-kernsmooth)
9270 ("r-limma" ,r-limma)
9271 ("r-mclust" ,r-mclust)
9272 ("r-qvalue" ,r-qvalue)
9273 ("r-r-utils" ,r-r-utils)
9275 ("r-rhtslib" ,r-rhtslib)
9276 ("r-rsamtools" ,r-rsamtools)
9277 ("r-rtracklayer" ,r-rtracklayer)
9278 ("r-s4vectors" ,r-s4vectors)
9279 ("r-zlibbioc" ,r-zlibbioc)))
9282 (home-page "https://github.com/al2na/methylKit")
9284 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9286 "MethylKit is an R package for DNA methylation analysis and annotation
9287 from high-throughput bisulfite sequencing. The package is designed to deal
9288 with sequencing data from @dfn{Reduced representation bisulfite
9289 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9290 genome bisulfite sequencing. It also has functions to analyze base-pair
9291 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9293 (license license:artistic2.0)))
9295 (define-public r-sva
9302 (uri (bioconductor-uri "sva" version))
9305 "0a3jqbz0jp1jxrnjkqfpmca840yqcdwxprdl608bzzx2zb4jl52s"))))
9306 (build-system r-build-system)
9308 `(("r-genefilter" ,r-genefilter)
9310 ("r-biocparallel" ,r-biocparallel)
9311 ("r-matrixstats" ,r-matrixstats)
9312 ("r-limma" ,r-limma)))
9313 (home-page "https://bioconductor.org/packages/sva")
9314 (synopsis "Surrogate variable analysis")
9316 "This package contains functions for removing batch effects and other
9317 unwanted variation in high-throughput experiment. It also contains functions
9318 for identifying and building surrogate variables for high-dimensional data
9319 sets. Surrogate variables are covariates constructed directly from
9320 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9321 imaging data that can be used in subsequent analyses to adjust for unknown,
9322 unmodeled, or latent sources of noise.")
9323 (license license:artistic2.0)))
9325 (define-public r-seqminer
9332 (uri (cran-uri "seqminer" version))
9335 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9336 (build-system r-build-system)
9339 (home-page "http://seqminer.genomic.codes")
9340 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9342 "This package provides tools to integrate nucleotide sequencing
9343 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9344 ;; Any version of the GPL is acceptable
9345 (license (list license:gpl2+ license:gpl3+))))
9347 (define-public r-raremetals2
9349 (name "r-raremetals2")
9354 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9355 "b/b7/RareMETALS2_" version ".tar.gz"))
9358 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9359 (properties `((upstream-name . "RareMETALS2")))
9360 (build-system r-build-system)
9362 `(("r-seqminer" ,r-seqminer)
9363 ("r-mvtnorm" ,r-mvtnorm)
9365 ("r-compquadform" ,r-compquadform)
9366 ("r-getopt" ,r-getopt)))
9367 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9368 (synopsis "Analyze gene-level association tests for binary trait")
9370 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9371 It was designed to meta-analyze gene-level association tests for binary trait.
9372 While rareMETALS offers a near-complete solution for meta-analysis of
9373 gene-level tests for quantitative trait, it does not offer the optimal
9374 solution for binary trait. The package rareMETALS2 offers improved features
9375 for analyzing gene-level association tests in meta-analyses for binary
9377 (license license:gpl3)))
9379 (define-public r-maldiquant
9381 (name "r-maldiquant")
9386 (uri (cran-uri "MALDIquant" version))
9389 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9390 (properties `((upstream-name . "MALDIquant")))
9391 (build-system r-build-system)
9392 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9393 (synopsis "Quantitative analysis of mass spectrometry data")
9395 "This package provides a complete analysis pipeline for matrix-assisted
9396 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9397 two-dimensional mass spectrometry data. In addition to commonly used plotting
9398 and processing methods it includes distinctive features, namely baseline
9399 subtraction methods such as morphological filters (TopHat) or the
9400 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9401 alignment using warping functions, handling of replicated measurements as well
9402 as allowing spectra with different resolutions.")
9403 (license license:gpl3+)))
9405 (define-public r-protgenerics
9407 (name "r-protgenerics")
9412 (uri (bioconductor-uri "ProtGenerics" version))
9415 "05jbadw2aiwy8vi2ia0jxg06cmwhly2cq4dy1ag7kdxf1c5i9ccn"))))
9416 (properties `((upstream-name . "ProtGenerics")))
9417 (build-system r-build-system)
9418 (home-page "https://github.com/lgatto/ProtGenerics")
9419 (synopsis "S4 generic functions for proteomics infrastructure")
9421 "This package provides S4 generic functions needed by Bioconductor
9422 proteomics packages.")
9423 (license license:artistic2.0)))
9425 (define-public r-mzr
9432 (uri (bioconductor-uri "mzR" version))
9435 "190m2bq5bqxhljaj4f7vz9wj5h5laaxd8zp5jampnql6xc4zmarg"))
9436 (modules '((guix build utils)))
9439 (delete-file-recursively "src/boost")
9441 (properties `((upstream-name . "mzR")))
9442 (build-system r-build-system)
9445 (modify-phases %standard-phases
9446 (add-after 'unpack 'use-system-boost
9448 (substitute* "src/Makevars"
9449 (("\\./boost/libs.*") "")
9450 (("ARCH_OBJS=" line)
9452 "\nARCH_LIBS=-lboost_system -lboost_regex \
9453 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9456 `(("boost" ,boost) ; use this instead of the bundled boost sources
9460 `(("r-biobase" ,r-biobase)
9461 ("r-biocgenerics" ,r-biocgenerics)
9462 ("r-protgenerics" ,r-protgenerics)
9464 ("r-rhdf5lib" ,r-rhdf5lib)
9465 ("r-zlibbioc" ,r-zlibbioc)))
9466 (home-page "https://github.com/sneumann/mzR/")
9467 (synopsis "Parser for mass spectrometry data files")
9469 "The mzR package provides a unified API to the common file formats and
9470 parsers available for mass spectrometry data. It comes with a wrapper for the
9471 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9472 The package contains the original code written by the ISB, and a subset of the
9473 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9474 previously been used in XCMS.")
9475 (license license:artistic2.0)))
9477 (define-public r-affyio
9484 (uri (bioconductor-uri "affyio" version))
9487 "0sh5wnnchyfpq5n6rchbqmb27byn7kdzn5rgran6i39c81i5z22n"))))
9488 (build-system r-build-system)
9490 `(("r-zlibbioc" ,r-zlibbioc)))
9493 (home-page "https://github.com/bmbolstad/affyio")
9494 (synopsis "Tools for parsing Affymetrix data files")
9496 "This package provides routines for parsing Affymetrix data files based
9497 upon file format information. The primary focus is on accessing the CEL and
9499 (license license:lgpl2.0+)))
9501 (define-public r-affy
9508 (uri (bioconductor-uri "affy" version))
9511 "0sxq875sigm21sf3qncrfrwfdz9nqw1vldxn3d3hj6aq64jg1ki6"))))
9512 (build-system r-build-system)
9514 `(("r-affyio" ,r-affyio)
9515 ("r-biobase" ,r-biobase)
9516 ("r-biocgenerics" ,r-biocgenerics)
9517 ("r-biocinstaller" ,r-biocinstaller)
9518 ("r-preprocesscore" ,r-preprocesscore)
9519 ("r-zlibbioc" ,r-zlibbioc)))
9522 (home-page "https://bioconductor.org/packages/affy")
9523 (synopsis "Methods for affymetrix oligonucleotide arrays")
9525 "This package contains functions for exploratory oligonucleotide array
9527 (license license:lgpl2.0+)))
9529 (define-public r-vsn
9536 (uri (bioconductor-uri "vsn" version))
9539 "0k6mah3g3zqbfap31xmvig4fn452a18xwwa5y0mfj5mj8588p57h"))))
9540 (build-system r-build-system)
9542 `(("r-affy" ,r-affy)
9543 ("r-biobase" ,r-biobase)
9544 ("r-ggplot2" ,r-ggplot2)
9545 ("r-lattice" ,r-lattice)
9546 ("r-limma" ,r-limma)))
9547 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9548 (synopsis "Variance stabilization and calibration for microarray data")
9550 "The package implements a method for normalising microarray intensities,
9551 and works for single- and multiple-color arrays. It can also be used for data
9552 from other technologies, as long as they have similar format. The method uses
9553 a robust variant of the maximum-likelihood estimator for an
9554 additive-multiplicative error model and affine calibration. The model
9555 incorporates data calibration step (a.k.a. normalization), a model for the
9556 dependence of the variance on the mean intensity and a variance stabilizing
9557 data transformation. Differences between transformed intensities are
9558 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9559 their variance is independent of the mean, and they are usually more sensitive
9560 and specific in detecting differential transcription.")
9561 (license license:artistic2.0)))
9563 (define-public r-mzid
9570 (uri (bioconductor-uri "mzID" version))
9573 "060k0xlhg8q802c6zsb4b8ps0ccd9ybyaz0gnsvqkxb786i2vk40"))))
9574 (properties `((upstream-name . "mzID")))
9575 (build-system r-build-system)
9577 `(("r-doparallel" ,r-doparallel)
9578 ("r-foreach" ,r-foreach)
9579 ("r-iterators" ,r-iterators)
9581 ("r-protgenerics" ,r-protgenerics)
9584 (home-page "https://bioconductor.org/packages/mzID")
9585 (synopsis "Parser for mzIdentML files")
9587 "This package provides a parser for mzIdentML files implemented using the
9588 XML package. The parser tries to be general and able to handle all types of
9589 mzIdentML files with the drawback of having less pretty output than a vendor
9591 (license license:gpl2+)))
9593 (define-public r-pcamethods
9595 (name "r-pcamethods")
9600 (uri (bioconductor-uri "pcaMethods" version))
9603 "0v99yf8m7ryh6z0r3z0ggpqfnflcq5bn1q1i1cl9b7q4p6b4sa07"))))
9604 (properties `((upstream-name . "pcaMethods")))
9605 (build-system r-build-system)
9607 `(("r-biobase" ,r-biobase)
9608 ("r-biocgenerics" ,r-biocgenerics)
9610 ("r-rcpp" ,r-rcpp)))
9611 (home-page "https://github.com/hredestig/pcamethods")
9612 (synopsis "Collection of PCA methods")
9614 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9615 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9616 for missing value estimation is included for comparison. BPCA, PPCA and
9617 NipalsPCA may be used to perform PCA on incomplete data as well as for
9618 accurate missing value estimation. A set of methods for printing and plotting
9619 the results is also provided. All PCA methods make use of the same data
9620 structure (pcaRes) to provide a common interface to the PCA results.")
9621 (license license:gpl3+)))
9623 (define-public r-msnbase
9630 (uri (bioconductor-uri "MSnbase" version))
9633 "0zrpx9r93q5ca2zdak5rs2m9sjm0wjdra1xfj3d3sx6p5gzfyg6n"))))
9634 (properties `((upstream-name . "MSnbase")))
9635 (build-system r-build-system)
9637 `(("r-affy" ,r-affy)
9638 ("r-biobase" ,r-biobase)
9639 ("r-biocgenerics" ,r-biocgenerics)
9640 ("r-biocparallel" ,r-biocparallel)
9641 ("r-digest" ,r-digest)
9642 ("r-ggplot2" ,r-ggplot2)
9643 ("r-impute" ,r-impute)
9644 ("r-iranges" ,r-iranges)
9645 ("r-lattice" ,r-lattice)
9646 ("r-maldiquant" ,r-maldiquant)
9650 ("r-pcamethods" ,r-pcamethods)
9652 ("r-preprocesscore" ,r-preprocesscore)
9653 ("r-protgenerics" ,r-protgenerics)
9655 ("r-s4vectors" ,r-s4vectors)
9656 ("r-scales" ,r-scales)
9659 (home-page "https://github.com/lgatto/MSnbase")
9660 (synopsis "Base functions and classes for MS-based proteomics")
9662 "This package provides basic plotting, data manipulation and processing
9663 of mass spectrometry based proteomics data.")
9664 (license license:artistic2.0)))
9666 (define-public r-msnid
9673 (uri (bioconductor-uri "MSnID" version))
9676 "172q5chi44104iz4y0g42wrimfp7hlhrfa8vzybx6m0ccrkkhl17"))))
9677 (properties `((upstream-name . "MSnID")))
9678 (build-system r-build-system)
9680 `(("r-biobase" ,r-biobase)
9681 ("r-data-table" ,r-data-table)
9682 ("r-doparallel" ,r-doparallel)
9683 ("r-dplyr" ,r-dplyr)
9684 ("r-foreach" ,r-foreach)
9685 ("r-iterators" ,r-iterators)
9686 ("r-msnbase" ,r-msnbase)
9689 ("r-protgenerics" ,r-protgenerics)
9690 ("r-r-cache" ,r-r-cache)
9692 ("r-reshape2" ,r-reshape2)))
9693 (home-page "https://bioconductor.org/packages/MSnID")
9694 (synopsis "Utilities for LC-MSn proteomics identifications")
9696 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9697 from mzIdentML (leveraging the mzID package) or text files. After collating
9698 the search results from multiple datasets it assesses their identification
9699 quality and optimize filtering criteria to achieve the maximum number of
9700 identifications while not exceeding a specified false discovery rate. It also
9701 contains a number of utilities to explore the MS/MS results and assess missed
9702 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9703 (license license:artistic2.0)))
9705 (define-public r-seurat
9711 (uri (cran-uri "Seurat" version))
9714 "0hi59rgdrr2iqfvx5bq7yq02hbjxkjl1fzidqj14z0ypq0nzbjys"))
9715 ;; Delete pre-built jar.
9717 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9719 (properties `((upstream-name . "Seurat")))
9720 (build-system r-build-system)
9723 (modify-phases %standard-phases
9724 (add-after 'unpack 'build-jar
9725 (lambda* (#:key inputs #:allow-other-keys)
9726 (let ((classesdir "tmp-classes"))
9727 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9729 (with-output-to-file "manifest"
9731 (display "Manifest-Version: 1.0
9732 Main-Class: ModularityOptimizer\n")))
9733 (and (zero? (apply system* `("javac" "-d" ,classesdir
9734 ,@(find-files "java" "\\.java$"))))
9735 (zero? (system* "jar"
9737 "inst/java/ModularityOptimizer.jar"
9738 "-C" classesdir ".")))))))))
9740 `(("jdk" ,icedtea "jdk")))
9743 ("r-caret" ,r-caret)
9744 ("r-cluster" ,r-cluster)
9745 ("r-cowplot" ,r-cowplot)
9746 ("r-diffusionmap" ,r-diffusionmap)
9747 ("r-dosnow" ,r-dosnow)
9748 ("r-dplyr" ,r-dplyr)
9750 ("r-fitdistrplus" ,r-fitdistrplus)
9752 ("r-foreach" ,r-foreach)
9754 ("r-gdata" ,r-gdata)
9755 ("r-ggplot2" ,r-ggplot2)
9756 ("r-ggridges" ,r-ggridges)
9757 ("r-gplots" ,r-gplots)
9758 ("r-hmisc" ,r-hmisc)
9760 ("r-igraph" ,r-igraph)
9761 ("r-irlba" ,r-irlba)
9763 ("r-lmtest" ,r-lmtest)
9765 ("r-matrix" ,r-matrix)
9766 ("r-metap" ,r-metap)
9767 ("r-mixtools" ,r-mixtools)
9768 ("r-pbapply" ,r-pbapply)
9769 ("r-plotly" ,r-plotly)
9771 ("r-ranger" ,r-ranger)
9773 ("r-rcolorbrewer" ,r-rcolorbrewer)
9775 ("r-rcppeigen" ,r-rcppeigen)
9776 ("r-rcppprogress" ,r-rcppprogress)
9777 ("r-reshape2" ,r-reshape2)
9778 ("r-reticulate" ,r-reticulate)
9780 ("r-rtsne" ,r-rtsne)
9781 ("r-sdmtools" ,r-sdmtools)
9782 ("r-stringr" ,r-stringr)
9783 ("r-tclust" ,r-tclust)
9784 ("r-tidyr" ,r-tidyr)
9786 ("r-vgam" ,r-vgam)))
9787 (home-page "http://www.satijalab.org/seurat")
9788 (synopsis "Seurat is an R toolkit for single cell genomics")
9790 "This package is an R package designed for QC, analysis, and
9791 exploration of single cell RNA-seq data. It easily enables widely-used
9792 analytical techniques, including the identification of highly variable genes,
9793 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9794 algorithms; density clustering, hierarchical clustering, k-means, and the
9795 discovery of differentially expressed genes and markers.")
9796 (license license:gpl3)))
9798 (define-public r-aroma-light
9800 (name "r-aroma-light")
9805 (uri (bioconductor-uri "aroma.light" version))
9808 "1dxsiwsrwcq9mj573f9vpdzrhagdqzal328ma8076px4gg6khxkn"))))
9809 (properties `((upstream-name . "aroma.light")))
9810 (build-system r-build-system)
9812 `(("r-matrixstats" ,r-matrixstats)
9813 ("r-r-methodss3" ,r-r-methodss3)
9815 ("r-r-utils" ,r-r-utils)))
9816 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9817 (synopsis "Methods for normalization and visualization of microarray data")
9819 "This package provides methods for microarray analysis that take basic
9820 data types such as matrices and lists of vectors. These methods can be used
9821 standalone, be utilized in other packages, or be wrapped up in higher-level
9823 (license license:gpl2+)))
9825 (define-public r-deseq
9832 (uri (bioconductor-uri "DESeq" version))
9835 "0ykxw8ksif026xy25wx50j2sdsrp156aqkmhcgfjkpgcw699glnm"))))
9836 (properties `((upstream-name . "DESeq")))
9837 (build-system r-build-system)
9839 `(("r-biobase" ,r-biobase)
9840 ("r-biocgenerics" ,r-biocgenerics)
9841 ("r-genefilter" ,r-genefilter)
9842 ("r-geneplotter" ,r-geneplotter)
9843 ("r-lattice" ,r-lattice)
9844 ("r-locfit" ,r-locfit)
9846 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9847 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9848 (synopsis "Differential gene expression analysis")
9850 "This package provides tools for estimating variance-mean dependence in
9851 count data from high-throughput genetic sequencing assays and for testing for
9852 differential expression based on a model using the negative binomial
9854 (license license:gpl3+)))
9856 (define-public r-edaseq
9863 (uri (bioconductor-uri "EDASeq" version))
9866 "1832pb3jkim4vrqzb8lajwx9r482bhww5n9nz3s6crvyamlp2dj0"))))
9867 (properties `((upstream-name . "EDASeq")))
9868 (build-system r-build-system)
9870 `(("r-annotationdbi" ,r-annotationdbi)
9871 ("r-aroma-light" ,r-aroma-light)
9872 ("r-biobase" ,r-biobase)
9873 ("r-biocgenerics" ,r-biocgenerics)
9874 ("r-biomart" ,r-biomart)
9875 ("r-biostrings" ,r-biostrings)
9876 ("r-deseq" ,r-deseq)
9877 ("r-genomicfeatures" ,r-genomicfeatures)
9878 ("r-genomicranges" ,r-genomicranges)
9879 ("r-iranges" ,r-iranges)
9880 ("r-rsamtools" ,r-rsamtools)
9881 ("r-shortread" ,r-shortread)))
9882 (home-page "https://github.com/drisso/EDASeq")
9883 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9885 "This package provides support for numerical and graphical summaries of
9886 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9887 adjust for GC-content effect (or other gene-level effects) on read counts:
9888 loess robust local regression, global-scaling, and full-quantile
9889 normalization. Between-lane normalization procedures to adjust for
9890 distributional differences between lanes (e.g., sequencing depth):
9891 global-scaling and full-quantile normalization.")
9892 (license license:artistic2.0)))
9894 (define-public r-interactivedisplaybase
9896 (name "r-interactivedisplaybase")
9901 (uri (bioconductor-uri "interactiveDisplayBase" version))
9904 "05w58z3i9vkma4jd6rhjaxls4yiq4kwrppgcdq9xrr1pxp99k575"))))
9906 `((upstream-name . "interactiveDisplayBase")))
9907 (build-system r-build-system)
9909 `(("r-biocgenerics" ,r-biocgenerics)
9910 ("r-shiny" ,r-shiny)))
9911 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9912 (synopsis "Base package for web displays of Bioconductor objects")
9914 "This package contains the basic methods needed to generate interactive
9915 Shiny-based display methods for Bioconductor objects.")
9916 (license license:artistic2.0)))
9918 (define-public r-annotationhub
9920 (name "r-annotationhub")
9925 (uri (bioconductor-uri "AnnotationHub" version))
9928 "11gh7qkgazs90czdqgv74gh2hz26xrmdp6wsz9x5pygbxls8xdw3"))))
9929 (properties `((upstream-name . "AnnotationHub")))
9930 (build-system r-build-system)
9932 `(("r-annotationdbi" ,r-annotationdbi)
9933 ("r-biocgenerics" ,r-biocgenerics)
9934 ("r-biocinstaller" ,r-biocinstaller)
9937 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9938 ("r-rsqlite" ,r-rsqlite)
9939 ("r-s4vectors" ,r-s4vectors)
9940 ("r-yaml" ,r-yaml)))
9941 (home-page "https://bioconductor.org/packages/AnnotationHub")
9942 (synopsis "Client to access AnnotationHub resources")
9944 "This package provides a client for the Bioconductor AnnotationHub web
9945 resource. The AnnotationHub web resource provides a central location where
9946 genomic files (e.g. VCF, bed, wig) and other resources from standard
9947 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9948 metadata about each resource, e.g., a textual description, tags, and date of
9949 modification. The client creates and manages a local cache of files retrieved
9950 by the user, helping with quick and reproducible access.")
9951 (license license:artistic2.0)))
9953 (define-public r-fastseg
9960 (uri (bioconductor-uri "fastseg" version))
9963 "1yw6hai6hb8qy7akdm4frfp6h4zy93zb68kdj094sanm7kgqmgik"))))
9964 (build-system r-build-system)
9966 `(("r-biobase" ,r-biobase)
9967 ("r-biocgenerics" ,r-biocgenerics)
9968 ("r-genomicranges" ,r-genomicranges)
9969 ("r-iranges" ,r-iranges)
9970 ("r-s4vectors" ,r-s4vectors)))
9971 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9972 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9974 "Fastseg implements a very fast and efficient segmentation algorithm.
9975 It can segment data from DNA microarrays and data from next generation
9976 sequencing for example to detect copy number segments. Further it can segment
9977 data from RNA microarrays like tiling arrays to identify transcripts. Most
9978 generally, it can segment data given as a matrix or as a vector. Various data
9979 formats can be used as input to fastseg like expression set objects for
9980 microarrays or GRanges for sequencing data.")
9981 (license license:lgpl2.0+)))
9983 (define-public r-keggrest
9990 (uri (bioconductor-uri "KEGGREST" version))
9993 "1349vidgl9m10l1rbrp3pkwwgi2xcbsw9h9z2xqbvg97lmqc4r8j"))))
9994 (properties `((upstream-name . "KEGGREST")))
9995 (build-system r-build-system)
9997 `(("r-biostrings" ,r-biostrings)
10000 (home-page "https://bioconductor.org/packages/KEGGREST")
10001 (synopsis "Client-side REST access to KEGG")
10003 "This package provides a package that provides a client interface to the
10004 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10005 (license license:artistic2.0)))
10007 (define-public r-gage
10014 (uri (bioconductor-uri "gage" version))
10017 "0j3cqxy97lpf146wkmdfaq9680gicmzxvhp6w5pxq3j7ipiy7262"))))
10018 (build-system r-build-system)
10020 `(("r-annotationdbi" ,r-annotationdbi)
10021 ("r-graph" ,r-graph)
10022 ("r-keggrest" ,r-keggrest)))
10023 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10024 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10026 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10027 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10028 data attributes including sample sizes, experimental designs, assay platforms,
10029 and other types of heterogeneity. The gage package provides functions for
10030 basic GAGE analysis, result processing and presentation. In addition, it
10031 provides demo microarray data and commonly used gene set data based on KEGG
10032 pathways and GO terms. These funtions and data are also useful for gene set
10033 analysis using other methods.")
10034 (license license:gpl2+)))
10036 (define-public r-genomicfiles
10038 (name "r-genomicfiles")
10043 (uri (bioconductor-uri "GenomicFiles" version))
10046 "0bhsq5czigrjyl9gkb2kpkpl367b3ac5g8s280adkcxggn9g7sxq"))))
10047 (properties `((upstream-name . "GenomicFiles")))
10048 (build-system r-build-system)
10050 `(("r-biocgenerics" ,r-biocgenerics)
10051 ("r-biocparallel" ,r-biocparallel)
10052 ("r-genomeinfodb" ,r-genomeinfodb)
10053 ("r-genomicalignments" ,r-genomicalignments)
10054 ("r-genomicranges" ,r-genomicranges)
10055 ("r-iranges" ,r-iranges)
10056 ("r-rsamtools" ,r-rsamtools)
10057 ("r-rtracklayer" ,r-rtracklayer)
10058 ("r-s4vectors" ,r-s4vectors)
10059 ("r-summarizedexperiment" ,r-summarizedexperiment)
10060 ("r-variantannotation" ,r-variantannotation)))
10061 (home-page "https://bioconductor.org/packages/GenomicFiles")
10062 (synopsis "Distributed computing by file or by range")
10064 "This package provides infrastructure for parallel computations
10065 distributed by file or by range. User defined mapper and reducer functions
10066 provide added flexibility for data combination and manipulation.")
10067 (license license:artistic2.0)))
10069 (define-public r-complexheatmap
10071 (name "r-complexheatmap")
10076 (uri (bioconductor-uri "ComplexHeatmap" version))
10079 "0z57mrginzd40niy51dvnyqgbrij05ji0dbwqs3x2as80sq28i3q"))))
10081 `((upstream-name . "ComplexHeatmap")))
10082 (build-system r-build-system)
10084 `(("r-circlize" ,r-circlize)
10085 ("r-colorspace" ,r-colorspace)
10086 ("r-getoptlong" ,r-getoptlong)
10087 ("r-globaloptions" ,r-globaloptions)
10088 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10090 "https://github.com/jokergoo/ComplexHeatmap")
10091 (synopsis "Making Complex Heatmaps")
10093 "Complex heatmaps are efficient to visualize associations between
10094 different sources of data sets and reveal potential structures. This package
10095 provides a highly flexible way to arrange multiple heatmaps and supports
10096 self-defined annotation graphics.")
10097 (license license:gpl2+)))
10099 (define-public r-dirichletmultinomial
10101 (name "r-dirichletmultinomial")
10106 (uri (bioconductor-uri "DirichletMultinomial" version))
10109 "0vcyp81b90in4ls5nbadc66cw2g9aydr94aqifq5j4b7diq74yfs"))))
10111 `((upstream-name . "DirichletMultinomial")))
10112 (build-system r-build-system)
10116 `(("r-biocgenerics" ,r-biocgenerics)
10117 ("r-iranges" ,r-iranges)
10118 ("r-s4vectors" ,r-s4vectors)))
10119 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10120 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10122 "Dirichlet-multinomial mixture models can be used to describe variability
10123 in microbial metagenomic data. This package is an interface to code
10124 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10126 (license license:lgpl3)))
10128 (define-public r-ensembldb
10130 (name "r-ensembldb")
10135 (uri (bioconductor-uri "ensembldb" version))
10138 "1l2b4cxiycv05mz4z4f3dhx57r9ksha02psc114h30ldm5rxz8w6"))))
10139 (build-system r-build-system)
10141 `(("r-annotationdbi" ,r-annotationdbi)
10142 ("r-annotationfilter" ,r-annotationfilter)
10143 ("r-biobase" ,r-biobase)
10144 ("r-biocgenerics" ,r-biocgenerics)
10145 ("r-biostrings" ,r-biostrings)
10148 ("r-genomeinfodb" ,r-genomeinfodb)
10149 ("r-genomicfeatures" ,r-genomicfeatures)
10150 ("r-genomicranges" ,r-genomicranges)
10151 ("r-iranges" ,r-iranges)
10152 ("r-protgenerics" ,r-protgenerics)
10153 ("r-rsamtools" ,r-rsamtools)
10154 ("r-rsqlite" ,r-rsqlite)
10155 ("r-rtracklayer" ,r-rtracklayer)
10156 ("r-s4vectors" ,r-s4vectors)))
10157 (home-page "https://github.com/jotsetung/ensembldb")
10158 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10160 "The package provides functions to create and use transcript-centric
10161 annotation databases/packages. The annotation for the databases are directly
10162 fetched from Ensembl using their Perl API. The functionality and data is
10163 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10164 but, in addition to retrieve all gene/transcript models and annotations from
10165 the database, the @code{ensembldb} package also provides a filter framework
10166 allowing to retrieve annotations for specific entries like genes encoded on a
10167 chromosome region or transcript models of lincRNA genes.")
10168 ;; No version specified
10169 (license license:lgpl3+)))
10171 (define-public r-organismdbi
10173 (name "r-organismdbi")
10178 (uri (bioconductor-uri "OrganismDbi" version))
10181 "0hb9ni41bjfy5s5ryw2qmqs2sx3i7j47w1g0l8g1pvn7ppnxb6cv"))))
10182 (properties `((upstream-name . "OrganismDbi")))
10183 (build-system r-build-system)
10185 `(("r-annotationdbi" ,r-annotationdbi)
10186 ("r-biobase" ,r-biobase)
10187 ("r-biocgenerics" ,r-biocgenerics)
10188 ("r-biocinstaller" ,r-biocinstaller)
10190 ("r-genomicfeatures" ,r-genomicfeatures)
10191 ("r-genomicranges" ,r-genomicranges)
10192 ("r-graph" ,r-graph)
10193 ("r-iranges" ,r-iranges)
10195 ("r-s4vectors" ,r-s4vectors)))
10196 (home-page "https://bioconductor.org/packages/OrganismDbi")
10197 (synopsis "Software to enable the smooth interfacing of database packages")
10198 (description "The package enables a simple unified interface to several
10199 annotation packages each of which has its own schema by taking advantage of
10200 the fact that each of these packages implements a select methods.")
10201 (license license:artistic2.0)))
10203 (define-public r-biovizbase
10205 (name "r-biovizbase")
10210 (uri (bioconductor-uri "biovizBase" version))
10213 "0lkiqdr3ics6hgv47lwkykcy761823bbkhffbn4ykyfzyqwl4p67"))))
10214 (properties `((upstream-name . "biovizBase")))
10215 (build-system r-build-system)
10217 `(("r-annotationdbi" ,r-annotationdbi)
10218 ("r-annotationfilter" ,r-annotationfilter)
10219 ("r-biocgenerics" ,r-biocgenerics)
10220 ("r-biostrings" ,r-biostrings)
10221 ("r-dichromat" ,r-dichromat)
10222 ("r-ensembldb" ,r-ensembldb)
10223 ("r-genomeinfodb" ,r-genomeinfodb)
10224 ("r-genomicalignments" ,r-genomicalignments)
10225 ("r-genomicfeatures" ,r-genomicfeatures)
10226 ("r-genomicranges" ,r-genomicranges)
10227 ("r-hmisc" ,r-hmisc)
10228 ("r-iranges" ,r-iranges)
10229 ("r-rcolorbrewer" ,r-rcolorbrewer)
10230 ("r-rsamtools" ,r-rsamtools)
10231 ("r-s4vectors" ,r-s4vectors)
10232 ("r-scales" ,r-scales)
10233 ("r-summarizedexperiment" ,r-summarizedexperiment)
10234 ("r-variantannotation" ,r-variantannotation)))
10235 (home-page "https://bioconductor.org/packages/biovizBase")
10236 (synopsis "Basic graphic utilities for visualization of genomic data")
10238 "The biovizBase package is designed to provide a set of utilities, color
10239 schemes and conventions for genomic data. It serves as the base for various
10240 high-level packages for biological data visualization. This saves development
10241 effort and encourages consistency.")
10242 (license license:artistic2.0)))
10244 (define-public r-ggbio
10251 (uri (bioconductor-uri "ggbio" version))
10254 "0wszh3w8yia5zw758h837i1q35k99sn444y2hahcxqbdmmlbf7in"))))
10255 (build-system r-build-system)
10257 `(("r-annotationdbi" ,r-annotationdbi)
10258 ("r-annotationfilter" ,r-annotationfilter)
10259 ("r-biobase" ,r-biobase)
10260 ("r-biocgenerics" ,r-biocgenerics)
10261 ("r-biostrings" ,r-biostrings)
10262 ("r-biovizbase" ,r-biovizbase)
10263 ("r-bsgenome" ,r-bsgenome)
10264 ("r-ensembldb" ,r-ensembldb)
10265 ("r-genomeinfodb" ,r-genomeinfodb)
10266 ("r-genomicalignments" ,r-genomicalignments)
10267 ("r-genomicfeatures" ,r-genomicfeatures)
10268 ("r-genomicranges" ,r-genomicranges)
10269 ("r-ggally" ,r-ggally)
10270 ("r-ggplot2" ,r-ggplot2)
10271 ("r-gridextra" ,r-gridextra)
10272 ("r-gtable" ,r-gtable)
10273 ("r-hmisc" ,r-hmisc)
10274 ("r-iranges" ,r-iranges)
10275 ("r-organismdbi" ,r-organismdbi)
10276 ("r-reshape2" ,r-reshape2)
10277 ("r-rsamtools" ,r-rsamtools)
10278 ("r-rtracklayer" ,r-rtracklayer)
10279 ("r-s4vectors" ,r-s4vectors)
10280 ("r-scales" ,r-scales)
10281 ("r-summarizedexperiment" ,r-summarizedexperiment)
10282 ("r-variantannotation" ,r-variantannotation)))
10283 (home-page "http://www.tengfei.name/ggbio/")
10284 (synopsis "Visualization tools for genomic data")
10286 "The ggbio package extends and specializes the grammar of graphics for
10287 biological data. The graphics are designed to answer common scientific
10288 questions, in particular those often asked of high throughput genomics data.
10289 All core Bioconductor data structures are supported, where appropriate. The
10290 package supports detailed views of particular genomic regions, as well as
10291 genome-wide overviews. Supported overviews include ideograms and grand linear
10292 views. High-level plots include sequence fragment length, edge-linked
10293 interval to data view, mismatch pileup, and several splicing summaries.")
10294 (license license:artistic2.0)))
10296 (define-public r-gprofiler
10298 (name "r-gprofiler")
10303 (uri (cran-uri "gProfileR" version))
10306 "1n6cj12j102b4x9vhyl4dljp1i0r43p23cnhqbx4als2xfxdlqgi"))))
10307 (properties `((upstream-name . "gProfileR")))
10308 (build-system r-build-system)
10310 `(("r-plyr" ,r-plyr)
10311 ("r-rcurl" ,r-rcurl)))
10312 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10313 (synopsis "Interface to the g:Profiler toolkit")
10315 "This package provides tools for functional enrichment analysis,
10316 gene identifier conversion and mapping homologous genes across related
10317 organisms via the @code{g:Profiler} toolkit.")
10318 (license license:gpl2+)))
10320 (define-public r-gqtlbase
10322 (name "r-gqtlbase")
10327 (uri (bioconductor-uri "gQTLBase" version))
10330 "1m3ajpqjhw1nwwsn372r44xfxq0a9a0pzsnrprzdjp6mh52p9b5m"))))
10331 (properties `((upstream-name . "gQTLBase")))
10332 (build-system r-build-system)
10334 `(("r-batchjobs" ,r-batchjobs)
10335 ("r-bbmisc" ,r-bbmisc)
10336 ("r-biocgenerics" ,r-biocgenerics)
10338 ("r-doparallel" ,r-doparallel)
10340 ("r-ffbase" ,r-ffbase)
10341 ("r-foreach" ,r-foreach)
10342 ("r-genomicfiles" ,r-genomicfiles)
10343 ("r-genomicranges" ,r-genomicranges)
10344 ("r-rtracklayer" ,r-rtracklayer)
10345 ("r-s4vectors" ,r-s4vectors)
10346 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10347 (home-page "https://bioconductor.org/packages/gQTLBase")
10348 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10350 "The purpose of this package is to simplify the storage and interrogation
10351 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10353 (license license:artistic2.0)))
10355 (define-public r-snpstats
10357 (name "r-snpstats")
10362 (uri (bioconductor-uri "snpStats" version))
10365 "0iydgfnm053iw860qa1bbh4f6nwzlsf3vhgq92gvl2v4xsz1jbbs"))))
10366 (properties `((upstream-name . "snpStats")))
10367 (build-system r-build-system)
10368 (inputs `(("zlib" ,zlib)))
10370 `(("r-biocgenerics" ,r-biocgenerics)
10371 ("r-matrix" ,r-matrix)
10372 ("r-survival" ,r-survival)
10373 ("r-zlibbioc" ,r-zlibbioc)))
10374 (home-page "https://bioconductor.org/packages/snpStats")
10375 (synopsis "Methods for SNP association studies")
10377 "This package provides classes and statistical methods for large
10378 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10379 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10380 (license license:gpl3)))
10382 (define-public r-homo-sapiens
10384 (name "r-homo-sapiens")
10388 ;; We cannot use bioconductor-uri here because this tarball is
10389 ;; located under "data/annotation/" instead of "bioc/".
10390 (uri (string-append "http://www.bioconductor.org/packages/"
10391 "release/data/annotation/src/contrib/"
10393 version ".tar.gz"))
10396 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10398 `((upstream-name . "Homo.sapiens")))
10399 (build-system r-build-system)
10401 `(("r-genomicfeatures" ,r-genomicfeatures)
10402 ("r-go-db" ,r-go-db)
10403 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10404 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10405 ("r-organismdbi" ,r-organismdbi)
10406 ("r-annotationdbi" ,r-annotationdbi)))
10407 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10408 (synopsis "Annotation package for the Homo.sapiens object")
10410 "This package contains the Homo.sapiens object to access data from
10411 several related annotation packages.")
10412 (license license:artistic2.0)))
10414 (define-public r-erma
10421 (uri (bioconductor-uri "erma" version))
10424 "1ka68n18yizlyvb8bpwwcl4hqbsasg8hw8jb3vgy3cd4szji87hh"))))
10425 (build-system r-build-system)
10427 `(("r-annotationdbi" ,r-annotationdbi)
10428 ("r-biobase" ,r-biobase)
10429 ("r-biocgenerics" ,r-biocgenerics)
10430 ("r-biocparallel" ,r-biocparallel)
10431 ("r-genomeinfodb" ,r-genomeinfodb)
10432 ("r-genomicfiles" ,r-genomicfiles)
10433 ("r-genomicranges" ,r-genomicranges)
10434 ("r-ggplot2" ,r-ggplot2)
10435 ("r-homo-sapiens" ,r-homo-sapiens)
10436 ("r-iranges" ,r-iranges)
10437 ("r-rtracklayer" ,r-rtracklayer)
10438 ("r-s4vectors" ,r-s4vectors)
10439 ("r-shiny" ,r-shiny)
10440 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10441 (home-page "https://bioconductor.org/packages/erma")
10442 (synopsis "Epigenomic road map adventures")
10444 "The epigenomics road map describes locations of epigenetic marks in DNA
10445 from a variety of cell types. Of interest are locations of histone
10446 modifications, sites of DNA methylation, and regions of accessible chromatin.
10447 This package presents a selection of elements of the road map including
10448 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10449 by Ernst and Kellis.")
10450 (license license:artistic2.0)))
10452 (define-public r-ldblock
10459 (uri (bioconductor-uri "ldblock" version))
10462 "0c24zvnwsp39d3q0bps13sc441jj9ms2zi34xsb8c392lqmbypvd"))))
10463 (build-system r-build-system)
10465 `(("r-biocgenerics" ,r-biocgenerics)
10467 ("r-genomeinfodb" ,r-genomeinfodb)
10468 ("r-genomicfiles" ,r-genomicfiles)
10469 ("r-go-db" ,r-go-db)
10470 ("r-homo-sapiens" ,r-homo-sapiens)
10471 ("r-matrix" ,r-matrix)
10472 ("r-rsamtools" ,r-rsamtools)
10473 ("r-snpstats" ,r-snpstats)
10474 ("r-variantannotation" ,r-variantannotation)))
10475 (home-page "https://bioconductor.org/packages/ldblock")
10476 (synopsis "Data structures for linkage disequilibrium measures in populations")
10478 "This package defines data structures for @dfn{linkage
10479 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10480 handling of existing population-level data for the purpose of flexibly
10481 defining LD blocks.")
10482 (license license:artistic2.0)))
10484 (define-public r-gqtlstats
10486 (name "r-gqtlstats")
10491 (uri (bioconductor-uri "gQTLstats" version))
10494 "19g8qhfgngdc14cw9k4i44cxhs3qva87x56gjzmn25k1yj8qgsp1"))))
10495 (properties `((upstream-name . "gQTLstats")))
10496 (build-system r-build-system)
10498 `(("r-annotationdbi" ,r-annotationdbi)
10499 ("r-batchjobs" ,r-batchjobs)
10500 ("r-bbmisc" ,r-bbmisc)
10501 ("r-beeswarm" ,r-beeswarm)
10502 ("r-biobase" ,r-biobase)
10503 ("r-biocgenerics" ,r-biocgenerics)
10504 ("r-doparallel" ,r-doparallel)
10505 ("r-dplyr" ,r-dplyr)
10507 ("r-ffbase" ,r-ffbase)
10508 ("r-foreach" ,r-foreach)
10509 ("r-genomeinfodb" ,r-genomeinfodb)
10510 ("r-genomicfeatures" ,r-genomicfeatures)
10511 ("r-genomicfiles" ,r-genomicfiles)
10512 ("r-genomicranges" ,r-genomicranges)
10513 ("r-ggbeeswarm" ,r-ggbeeswarm)
10514 ("r-ggplot2" ,r-ggplot2)
10515 ("r-gqtlbase" ,r-gqtlbase)
10516 ("r-hardyweinberg" ,r-hardyweinberg)
10517 ("r-homo-sapiens" ,r-homo-sapiens)
10518 ("r-iranges" ,r-iranges)
10519 ("r-limma" ,r-limma)
10521 ("r-plotly" ,r-plotly)
10522 ("r-reshape2" ,r-reshape2)
10523 ("r-s4vectors" ,r-s4vectors)
10524 ("r-shiny" ,r-shiny)
10525 ("r-snpstats" ,r-snpstats)
10526 ("r-summarizedexperiment" ,r-summarizedexperiment)
10527 ("r-variantannotation" ,r-variantannotation)))
10528 (home-page "https://bioconductor.org/packages/gQTLstats")
10529 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10531 "This package provides tools for the computationally efficient analysis
10532 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10533 The software in this package aims to support refinements and functional
10534 interpretation of members of a collection of association statistics on a
10535 family of feature/genome hypotheses.")
10536 (license license:artistic2.0)))
10538 (define-public r-gviz
10545 (uri (bioconductor-uri "Gviz" version))
10548 "1fhli7ahkl5r43j0hc89ib41mfadj6qyrg36i03ncz8zs6iqwpx4"))))
10549 (properties `((upstream-name . "Gviz")))
10550 (build-system r-build-system)
10552 `(("r-annotationdbi" ,r-annotationdbi)
10553 ("r-biobase" ,r-biobase)
10554 ("r-biocgenerics" ,r-biocgenerics)
10555 ("r-biomart" ,r-biomart)
10556 ("r-biostrings" ,r-biostrings)
10557 ("r-biovizbase" ,r-biovizbase)
10558 ("r-bsgenome" ,r-bsgenome)
10559 ("r-digest" ,r-digest)
10560 ("r-genomeinfodb" ,r-genomeinfodb)
10561 ("r-genomicalignments" ,r-genomicalignments)
10562 ("r-genomicfeatures" ,r-genomicfeatures)
10563 ("r-genomicranges" ,r-genomicranges)
10564 ("r-iranges" ,r-iranges)
10565 ("r-lattice" ,r-lattice)
10566 ("r-latticeextra" ,r-latticeextra)
10567 ("r-matrixstats" ,r-matrixstats)
10568 ("r-rcolorbrewer" ,r-rcolorbrewer)
10569 ("r-rsamtools" ,r-rsamtools)
10570 ("r-rtracklayer" ,r-rtracklayer)
10571 ("r-s4vectors" ,r-s4vectors)
10572 ("r-xvector" ,r-xvector)))
10573 (home-page "https://bioconductor.org/packages/Gviz")
10574 (synopsis "Plotting data and annotation information along genomic coordinates")
10576 "Genomic data analyses requires integrated visualization of known genomic
10577 information and new experimental data. Gviz uses the biomaRt and the
10578 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10579 and translates this to e.g. gene/transcript structures in viewports of the
10580 grid graphics package. This results in genomic information plotted together
10582 (license license:artistic2.0)))
10584 (define-public r-gwascat
10591 (uri (bioconductor-uri "gwascat" version))
10594 "08ba9il4vbjjwlbwmqg4ai6ya1p09js9agn95sw0dhc9gqln42hx"))))
10595 (build-system r-build-system)
10597 `(("r-annotationdbi" ,r-annotationdbi)
10598 ("r-annotationhub" ,r-annotationhub)
10599 ("r-biocgenerics" ,r-biocgenerics)
10600 ("r-biostrings" ,r-biostrings)
10601 ("r-genomeinfodb" ,r-genomeinfodb)
10602 ("r-genomicfeatures" ,r-genomicfeatures)
10603 ("r-genomicranges" ,r-genomicranges)
10604 ("r-ggbio" ,r-ggbio)
10605 ("r-ggplot2" ,r-ggplot2)
10606 ("r-gqtlstats" ,r-gqtlstats)
10607 ("r-graph" ,r-graph)
10609 ("r-homo-sapiens" ,r-homo-sapiens)
10610 ("r-iranges" ,r-iranges)
10611 ("r-rsamtools" ,r-rsamtools)
10612 ("r-rtracklayer" ,r-rtracklayer)
10613 ("r-s4vectors" ,r-s4vectors)
10614 ("r-snpstats" ,r-snpstats)
10615 ("r-summarizedexperiment" ,r-summarizedexperiment)
10616 ("r-variantannotation" ,r-variantannotation)))
10617 (home-page "https://bioconductor.org/packages/gwascat")
10618 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10620 "This package provides tools for representing and modeling data in the
10621 EMBL-EBI GWAS catalog.")
10622 (license license:artistic2.0)))
10624 (define-public r-sushi
10630 (uri (bioconductor-uri "Sushi" version))
10633 "1m15hmg4k0qhshyn65xfj5hx7xbaf0kxqw70lxisak6pj1w00l41"))))
10634 (properties `((upstream-name . "Sushi")))
10635 (build-system r-build-system)
10637 `(("r-biomart" ,r-biomart)
10639 (home-page "https://bioconductor.org/packages/Sushi")
10640 (synopsis "Tools for visualizing genomics data")
10642 "This package provides flexible, quantitative, and integrative genomic
10643 visualizations for publication-quality multi-panel figures.")
10644 (license license:gpl2+)))
10646 (define-public r-fithic
10652 (uri (bioconductor-uri "FitHiC" version))
10655 "06w4q836bi1mvkbl1saghv4r5p4hxpjg8cp7kgad13ls450kqmyd"))))
10656 (properties `((upstream-name . "FitHiC")))
10657 (build-system r-build-system)
10659 `(("r-data-table" ,r-data-table)
10660 ("r-fdrtool" ,r-fdrtool)
10661 ("r-rcpp" ,r-rcpp)))
10662 (home-page "https://bioconductor.org/packages/FitHiC")
10663 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10665 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10666 intra-chromosomal contact maps produced by genome-wide genome architecture
10667 assays such as Hi-C.")
10668 (license license:gpl2+)))
10670 (define-public r-hitc
10676 (uri (bioconductor-uri "HiTC" version))
10679 "0qkk5139f51lwwy1yh7nbkflh5d69prirmhniwam34nlg9rzjm2z"))))
10680 (properties `((upstream-name . "HiTC")))
10681 (build-system r-build-system)
10683 `(("r-biostrings" ,r-biostrings)
10684 ("r-genomeinfodb" ,r-genomeinfodb)
10685 ("r-genomicranges" ,r-genomicranges)
10686 ("r-iranges" ,r-iranges)
10687 ("r-matrix" ,r-matrix)
10688 ("r-rcolorbrewer" ,r-rcolorbrewer)
10689 ("r-rtracklayer" ,r-rtracklayer)))
10690 (home-page "https://bioconductor.org/packages/HiTC")
10691 (synopsis "High throughput chromosome conformation capture analysis")
10693 "The HiTC package was developed to explore high-throughput \"C\" data
10694 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10695 quality controls, normalization, visualization, and further analysis are also
10697 (license license:artistic2.0)))
10699 (define-public r-qvalue
10706 (uri (bioconductor-uri "qvalue" version))
10709 "1ndwkj0hh7v4lwylq1v0fkxqs7mfmbcj8kxbdpj1wkvf131z2ns8"))))
10710 (build-system r-build-system)
10712 `(("r-ggplot2" ,r-ggplot2)
10713 ("r-reshape2" ,r-reshape2)))
10714 (home-page "http://github.com/jdstorey/qvalue")
10715 (synopsis "Q-value estimation for false discovery rate control")
10717 "This package takes a list of p-values resulting from the simultaneous
10718 testing of many hypotheses and estimates their q-values and local @dfn{false
10719 discovery rate} (FDR) values. The q-value of a test measures the proportion
10720 of false positives incurred when that particular test is called significant.
10721 The local FDR measures the posterior probability the null hypothesis is true
10722 given the test's p-value. Various plots are automatically generated, allowing
10723 one to make sensible significance cut-offs. The software can be applied to
10724 problems in genomics, brain imaging, astrophysics, and data mining.")
10725 ;; Any version of the LGPL.
10726 (license license:lgpl3+)))
10728 (define-public r-hdf5array
10730 (name "r-hdf5array")
10735 (uri (bioconductor-uri "HDF5Array" version))
10738 "1l0276qxkhgdxsfck3jmi8jvnsr20g10gjki53g0mqa45wnhm3ck"))))
10739 (properties `((upstream-name . "HDF5Array")))
10740 (build-system r-build-system)
10742 `(("r-biocgenerics" ,r-biocgenerics)
10743 ("r-delayedarray" ,r-delayedarray)
10744 ("r-iranges" ,r-iranges)
10745 ("r-rhdf5" ,r-rhdf5)
10746 ("r-s4vectors" ,r-s4vectors)))
10747 (home-page "https://bioconductor.org/packages/HDF5Array")
10748 (synopsis "HDF5 back end for DelayedArray objects")
10749 (description "This package provides an array-like container for convenient
10750 access and manipulation of HDF5 datasets. It supports delayed operations and
10751 block processing.")
10752 (license license:artistic2.0)))
10754 (define-public r-rhdf5lib
10756 (name "r-rhdf5lib")
10761 (uri (bioconductor-uri "Rhdf5lib" version))
10764 "1y59acac6v8hrhv84gghn9ifsni9xxxacaj177rrl4frmkrz4x3c"))))
10765 (properties `((upstream-name . "Rhdf5lib")))
10766 (build-system r-build-system)
10769 (modify-phases %standard-phases
10770 (add-after 'unpack 'do-not-use-bundled-hdf5
10771 (lambda* (#:key inputs #:allow-other-keys)
10772 (for-each delete-file '("configure" "configure.ac"))
10773 ;; Do not make other packages link with the proprietary libsz.
10774 (substitute* "R/zzz.R"
10775 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10776 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10777 (("'%s/libhdf5.a %s/libsz.a -lz'")
10778 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10779 (with-directory-excursion "src"
10780 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10781 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10783 ;; Remove timestamp and host system information to make
10784 ;; the build reproducible.
10785 (substitute* "hdf5/src/libhdf5.settings.in"
10786 (("Configured on: @CONFIG_DATE@")
10787 "Configured on: Guix")
10788 (("Uname information:.*")
10789 "Uname information: Linux\n")
10790 ;; Remove unnecessary store reference.
10792 "C Compiler: GCC\n"))
10793 (rename-file "Makevars.in" "Makevars")
10794 (substitute* "Makevars"
10795 (("HDF5_CXX_LIB=.*")
10796 (string-append "HDF5_CXX_LIB="
10797 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10799 (string-append "HDF5_LIB="
10800 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10801 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10802 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10803 ;; szip is non-free software
10804 (("cp \\$\\{SZIP_LIB\\}.*") "")
10805 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10812 `(("hdf5-source" ,(package-source hdf5))))
10813 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10814 (synopsis "HDF5 library as an R package")
10815 (description "This package provides C and C++ HDF5 libraries for use in R
10817 (license license:artistic2.0)))
10819 (define-public r-beachmat
10821 (name "r-beachmat")
10826 (uri (bioconductor-uri "beachmat" version))
10829 "1w90v0jx1zgrfxzx99gdkk0dz2vi25hr51jml1bvq33i64rj7996"))))
10830 (build-system r-build-system)
10835 `(("r-delayedarray" ,r-delayedarray)
10836 ("r-hdf5array" ,r-hdf5array)
10838 ("r-rhdf5" ,r-rhdf5)
10839 ("r-rhdf5lib" ,r-rhdf5lib)))
10840 (home-page "https://bioconductor.org/packages/beachmat")
10841 (synopsis "Compiling Bioconductor to handle each matrix type")
10842 (description "This package provides a consistent C++ class interface for a
10843 variety of commonly used matrix types, including sparse and HDF5-backed
10845 (license license:gpl3)))
10847 (define-public r-singlecellexperiment
10849 (name "r-singlecellexperiment")
10854 (uri (bioconductor-uri "SingleCellExperiment" version))
10857 "0mz3chia250v8v6q8r5cqv5fc4bpcw1hhrfr3p7l5i4xi85scpka"))))
10859 `((upstream-name . "SingleCellExperiment")))
10860 (build-system r-build-system)
10862 `(("r-biocgenerics" ,r-biocgenerics)
10863 ("r-s4vectors" ,r-s4vectors)
10864 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10865 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10866 (synopsis "S4 classes for single cell data")
10867 (description "This package defines an S4 class for storing data from
10868 single-cell experiments. This includes specialized methods to store and
10869 retrieve spike-in information, dimensionality reduction coordinates and size
10870 factors for each cell, along with the usual metadata for genes and
10872 (license license:gpl3)))
10874 (define-public r-scater
10880 (uri (bioconductor-uri "scater" version))
10883 "0bhpikgz3b9f510dawsay4zry9rlp8vjx5n6zvwbcpwrd94p3903"))))
10884 (build-system r-build-system)
10886 `(("r-beachmat" ,r-beachmat)
10887 ("r-biobase" ,r-biobase)
10888 ("r-biocgenerics" ,r-biocgenerics)
10889 ("r-data-table" ,r-data-table)
10890 ("r-delayedarray" ,r-delayedarray)
10891 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10892 ("r-dplyr" ,r-dplyr)
10893 ("r-edger" ,r-edger)
10894 ("r-ggbeeswarm" ,r-ggbeeswarm)
10895 ("r-ggplot2" ,r-ggplot2)
10896 ("r-limma" ,r-limma)
10897 ("r-matrix" ,r-matrix)
10900 ("r-reshape2" ,r-reshape2)
10901 ("r-rhdf5" ,r-rhdf5)
10902 ("r-rhdf5lib" ,r-rhdf5lib)
10903 ("r-rjson" ,r-rjson)
10904 ("r-s4vectors" ,r-s4vectors)
10905 ("r-shiny" ,r-shiny)
10906 ("r-shinydashboard" ,r-shinydashboard)
10907 ("r-singlecellexperiment" ,r-singlecellexperiment)
10908 ("r-summarizedexperiment" ,r-summarizedexperiment)
10909 ("r-tximport" ,r-tximport)
10910 ("r-viridis" ,r-viridis)))
10911 (home-page "https://github.com/davismcc/scater")
10912 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10913 (description "This package provides a collection of tools for doing
10914 various analyses of single-cell RNA-seq gene expression data, with a focus on
10916 (license license:gpl2+)))
10918 (define-public r-scran
10925 (uri (bioconductor-uri "scran" version))
10928 "0nbn5x75gf9d0p18w7vpkbv30cpdqvp5bz8xvila0h7jla7xdyih"))))
10929 (build-system r-build-system)
10931 `(("r-beachmat" ,r-beachmat)
10932 ("r-biocgenerics" ,r-biocgenerics)
10933 ("r-biocparallel" ,r-biocparallel)
10934 ("r-delayedarray" ,r-delayedarray)
10935 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10937 ("r-dynamictreecut" ,r-dynamictreecut)
10938 ("r-edger" ,r-edger)
10940 ("r-ggplot2" ,r-ggplot2)
10941 ("r-igraph" ,r-igraph)
10942 ("r-limma" ,r-limma)
10943 ("r-matrix" ,r-matrix)
10945 ("r-rhdf5lib" ,r-rhdf5lib)
10946 ("r-s4vectors" ,r-s4vectors)
10947 ("r-scater" ,r-scater)
10948 ("r-shiny" ,r-shiny)
10949 ("r-singlecellexperiment" ,r-singlecellexperiment)
10950 ("r-statmod" ,r-statmod)
10951 ("r-summarizedexperiment" ,r-summarizedexperiment)
10952 ("r-viridis" ,r-viridis)))
10953 (home-page "https://bioconductor.org/packages/scran")
10954 (synopsis "Methods for single-cell RNA-Seq data analysis")
10955 (description "This package implements a variety of low-level analyses of
10956 single-cell RNA-seq data. Methods are provided for normalization of
10957 cell-specific biases, assignment of cell cycle phase, and detection of highly
10958 variable and significantly correlated genes.")
10959 (license license:gpl3)))
10961 (define-public r-delayedmatrixstats
10963 (name "r-delayedmatrixstats")
10968 (uri (bioconductor-uri "DelayedMatrixStats" version))
10971 "1dasghfy8x27zzmd0igag4mc1gxxxbchsl4hpc1050dj3wnw9w3y"))))
10973 `((upstream-name . "DelayedMatrixStats")))
10974 (build-system r-build-system)
10976 `(("r-delayedarray" ,r-delayedarray)
10977 ("r-iranges" ,r-iranges)
10978 ("r-matrix" ,r-matrix)
10979 ("r-matrixstats" ,r-matrixstats)
10980 ("r-s4vectors" ,r-s4vectors)))
10981 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10982 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10984 "This package provides a port of the @code{matrixStats} API for use with
10985 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10986 contains high-performing functions operating on rows and columns of
10987 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10988 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10989 are optimized per data type and for subsetted calculations such that both
10990 memory usage and processing time is minimized.")
10991 (license license:expat)))
10993 (define-public r-phangorn
10995 (name "r-phangorn")
11000 (uri (cran-uri "phangorn" version))
11003 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11004 (build-system r-build-system)
11007 ("r-fastmatch" ,r-fastmatch)
11008 ("r-igraph" ,r-igraph)
11009 ("r-magrittr" ,r-magrittr)
11010 ("r-matrix" ,r-matrix)
11011 ("r-quadprog" ,r-quadprog)
11012 ("r-rcpp" ,r-rcpp)))
11013 (home-page "https://github.com/KlausVigo/phangorn")
11014 (synopsis "Phylogenetic analysis in R")
11016 "Phangorn is a package for phylogenetic analysis in R. It supports
11017 estimation of phylogenetic trees and networks using Maximum Likelihood,
11018 Maximum Parsimony, distance methods and Hadamard conjugation.")
11019 (license license:gpl2+)))
11021 (define-public r-dropbead
11022 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11025 (name "r-dropbead")
11026 (version (string-append "0-" revision "." (string-take commit 7)))
11030 (uri (git-reference
11031 (url "https://github.com/rajewsky-lab/dropbead.git")
11033 (file-name (git-file-name name version))
11036 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11037 (build-system r-build-system)
11039 `(("r-ggplot2" ,r-ggplot2)
11040 ("r-rcolorbrewer" ,r-rcolorbrewer)
11041 ("r-gridextra" ,r-gridextra)
11042 ("r-gplots" ,r-gplots)
11043 ("r-plyr" ,r-plyr)))
11044 (home-page "https://github.com/rajewsky-lab/dropbead")
11045 (synopsis "Basic exploration and analysis of Drop-seq data")
11046 (description "This package offers a quick and straight-forward way to
11047 explore and perform basic analysis of single cell sequencing data coming from
11048 droplet sequencing. It has been particularly tailored for Drop-seq.")
11049 (license license:gpl3))))
11051 (define htslib-for-sambamba
11052 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11055 (name "htslib-for-sambamba")
11056 (version (string-append "1.3.1-1." (string-take commit 9)))
11060 (uri (git-reference
11061 (url "https://github.com/lomereiter/htslib.git")
11063 (file-name (string-append "htslib-" version "-checkout"))
11066 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11068 `(("autoconf" ,autoconf)
11069 ("automake" ,automake)
11070 ,@(package-native-inputs htslib))))))
11072 (define-public sambamba
11075 (version "0.6.7-10-g223fa20")
11079 (uri (git-reference
11080 (url "https://github.com/lomereiter/sambamba.git")
11081 (commit (string-append "v" version))))
11082 (file-name (string-append name "-" version "-checkout"))
11085 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11086 (build-system gnu-build-system)
11088 `(#:tests? #f ; there is no test target
11089 #:parallel-build? #f ; not supported
11091 (modify-phases %standard-phases
11092 (delete 'configure)
11093 (add-after 'unpack 'fix-ldc-version
11095 (substitute* "gen_ldc_version_info.py"
11096 (("/usr/bin/env.*") (which "python")))
11097 (substitute* "Makefile"
11098 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11100 (add-after 'unpack 'place-biod-and-undead
11101 (lambda* (#:key inputs #:allow-other-keys)
11102 (copy-recursively (assoc-ref inputs "biod") "BioD")
11103 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11105 (add-after 'unpack 'unbundle-prerequisites
11107 (substitute* "Makefile"
11108 (("htslib/libhts.a lz4/lib/liblz4.a")
11110 ((" htslib-static lz4-static") ""))
11113 (lambda* (#:key outputs #:allow-other-keys)
11114 (let* ((out (assoc-ref outputs "out"))
11115 (bin (string-append out "/bin")))
11117 (install-file "build/sambamba" bin)
11122 ("python" ,python2-minimal)
11124 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11127 (uri (git-reference
11128 (url "https://github.com/biod/BioD.git")
11130 (file-name (string-append "biod-"
11131 (string-take commit 9)
11135 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11137 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11140 (uri (git-reference
11141 (url "https://github.com/dlang/undeaD.git")
11143 (file-name (string-append "undead-"
11144 (string-take commit 9)
11148 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11151 ("htslib" ,htslib-for-sambamba)))
11152 (home-page "http://lomereiter.github.io/sambamba")
11153 (synopsis "Tools for working with SAM/BAM data")
11154 (description "Sambamba is a high performance modern robust and
11155 fast tool (and library), written in the D programming language, for
11156 working with SAM and BAM files. Current parallelised functionality is
11157 an important subset of samtools functionality, including view, index,
11158 sort, markdup, and depth.")
11159 (license license:gpl2+)))
11161 (define-public ritornello
11163 (name "ritornello")
11167 (uri (string-append "https://github.com/KlugerLab/"
11168 "Ritornello/archive/v"
11169 version ".tar.gz"))
11170 (file-name (string-append name "-" version ".tar.gz"))
11173 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11174 (build-system gnu-build-system)
11176 `(#:tests? #f ; there are no tests
11178 (modify-phases %standard-phases
11179 (add-after 'unpack 'patch-samtools-references
11180 (lambda* (#:key inputs #:allow-other-keys)
11181 (substitute* '("src/SamStream.h"
11182 "src/BufferedGenomeReader.h")
11183 (("<sam.h>") "<samtools/sam.h>"))
11185 (delete 'configure)
11187 (lambda* (#:key inputs outputs #:allow-other-keys)
11188 (let* ((out (assoc-ref outputs "out"))
11189 (bin (string-append out "/bin/")))
11191 (install-file "bin/Ritornello" bin)
11194 `(("samtools" ,samtools-0.1)
11198 (home-page "https://github.com/KlugerLab/Ritornello")
11199 (synopsis "Control-free peak caller for ChIP-seq data")
11200 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11201 signal processing that can accurately call binding events without the need to
11202 do a pair total DNA input or IgG control sample. It has been tested for use
11203 with narrow binding events such as transcription factor ChIP-seq.")
11204 (license license:gpl3+)))
11206 (define-public trim-galore
11208 (name "trim-galore")
11213 (uri (git-reference
11214 (url "https://github.com/FelixKrueger/TrimGalore.git")
11216 (file-name (string-append name "-" version "-checkout"))
11219 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11220 (build-system gnu-build-system)
11222 `(#:tests? #f ; no tests
11224 (modify-phases %standard-phases
11225 (delete 'configure)
11227 (add-after 'unpack 'hardcode-tool-references
11228 (lambda* (#:key inputs #:allow-other-keys)
11229 (substitute* "trim_galore"
11230 (("\\$path_to_cutadapt = 'cutadapt'")
11231 (string-append "$path_to_cutadapt = '"
11232 (assoc-ref inputs "cutadapt")
11235 (string-append "| "
11236 (assoc-ref inputs "gzip")
11239 (string-append "\""
11240 (assoc-ref inputs "gzip")
11244 (lambda* (#:key outputs #:allow-other-keys)
11245 (let ((bin (string-append (assoc-ref outputs "out")
11248 (install-file "trim_galore" bin)
11253 ("cutadapt" ,cutadapt)))
11255 `(("unzip" ,unzip)))
11256 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11257 (synopsis "Wrapper around Cutadapt and FastQC")
11258 (description "Trim Galore! is a wrapper script to automate quality and
11259 adapter trimming as well as quality control, with some added functionality to
11260 remove biased methylation positions for RRBS sequence files.")
11261 (license license:gpl3+)))
11263 (define-public gess
11269 (uri (string-append "http://compbio.uthscsa.edu/"
11271 "gess-" version ".src.tar.gz"))
11274 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11275 (build-system gnu-build-system)
11277 `(#:tests? #f ; no tests
11279 (modify-phases %standard-phases
11280 (delete 'configure)
11283 (lambda* (#:key inputs outputs #:allow-other-keys)
11284 (let* ((python (assoc-ref inputs "python"))
11285 (out (assoc-ref outputs "out"))
11286 (bin (string-append out "/bin/"))
11287 (target (string-append
11288 out "/lib/python2.7/site-packages/gess/")))
11290 (copy-recursively "." target)
11291 ;; Make GESS.py executable
11292 (chmod (string-append target "GESS.py") #o555)
11293 ;; Add Python shebang to the top and make Matplotlib
11295 (substitute* (string-append target "GESS.py")
11296 (("\"\"\"Description:" line)
11297 (string-append "#!" (which "python") "
11299 matplotlib.use('Agg')
11301 ;; Make sure GESS has all modules in its path
11302 (wrap-program (string-append target "GESS.py")
11303 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11305 (symlink (string-append target "GESS.py")
11306 (string-append bin "GESS.py"))
11309 `(("python" ,python-2)
11310 ("python2-pysam" ,python2-pysam)
11311 ("python2-scipy" ,python2-scipy)
11312 ("python2-numpy" ,python2-numpy)
11313 ("python2-networkx" ,python2-networkx)
11314 ("python2-biopython" ,python2-biopython)))
11315 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11316 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11318 "GESS is an implementation of a novel computational method to detect de
11319 novo exon-skipping events directly from raw RNA-seq data without the prior
11320 knowledge of gene annotation information. GESS stands for the graph-based
11321 exon-skipping scanner detection scheme.")
11322 (license license:bsd-3)))
11324 (define-public phylip
11331 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11332 "download/phylip-" version ".tar.gz"))
11335 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11336 (build-system gnu-build-system)
11338 `(#:tests? #f ; no check target
11339 #:make-flags (list "-f" "Makefile.unx" "install")
11340 #:parallel-build? #f ; not supported
11342 (modify-phases %standard-phases
11343 (add-after 'unpack 'enter-dir
11344 (lambda _ (chdir "src") #t))
11345 (delete 'configure)
11347 (lambda* (#:key inputs outputs #:allow-other-keys)
11348 (let ((target (string-append (assoc-ref outputs "out")
11351 (for-each (lambda (file)
11352 (install-file file target))
11353 (find-files "../exe" ".*")))
11355 (home-page "http://evolution.genetics.washington.edu/phylip/")
11356 (synopsis "Tools for inferring phylogenies")
11357 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11358 programs for inferring phylogenies (evolutionary trees).")
11359 (license license:bsd-2)))
11368 (uri (string-append "https://integrativemodeling.org/"
11369 version "/download/imp-" version ".tar.gz"))
11372 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11373 (build-system cmake-build-system)
11375 `(;; FIXME: Some tests fail because they produce warnings, others fail
11376 ;; because the PYTHONPATH does not include the modeller's directory.
11384 ("python" ,python-2)))
11386 `(("python2-numpy" ,python2-numpy)
11387 ("python2-scipy" ,python2-scipy)
11388 ("python2-pandas" ,python2-pandas)
11389 ("python2-scikit-learn" ,python2-scikit-learn)
11390 ("python2-networkx" ,python2-networkx)))
11391 (home-page "https://integrativemodeling.org")
11392 (synopsis "Integrative modeling platform")
11393 (description "IMP's broad goal is to contribute to a comprehensive
11394 structural characterization of biomolecules ranging in size and complexity
11395 from small peptides to large macromolecular assemblies, by integrating data
11396 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11397 Python toolbox for solving complex modeling problems, and a number of
11398 applications for tackling some common problems in a user-friendly way.")
11399 ;; IMP is largely available under the GNU Lesser GPL; see the file
11400 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11401 ;; available under the GNU GPL (see the file COPYING.GPL).
11402 (license (list license:lgpl2.1+
11405 (define-public tadbit
11411 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11412 "archive/v" version ".tar.gz"))
11413 (file-name (string-append name "-" version ".tar.gz"))
11416 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11417 (build-system python-build-system)
11419 `(;; Tests are included and must be run after installation, but
11420 ;; they are incomplete and thus cannot be run.
11424 (modify-phases %standard-phases
11425 (add-after 'unpack 'fix-problems-with-setup.py
11426 (lambda* (#:key outputs #:allow-other-keys)
11427 ;; setup.py opens these files for writing
11428 (chmod "_pytadbit/_version.py" #o664)
11429 (chmod "README.rst" #o664)
11431 ;; Don't attempt to install the bash completions to
11432 ;; the home directory.
11433 (rename-file "extras/.bash_completion"
11435 (substitute* "setup.py"
11436 (("\\(path.expanduser\\('~'\\)")
11437 (string-append "(\""
11438 (assoc-ref outputs "out")
11439 "/etc/bash_completion.d\""))
11440 (("extras/\\.bash_completion")
11444 ;; TODO: add Chimera for visualization
11447 ("python2-scipy" ,python2-scipy)
11448 ("python2-numpy" ,python2-numpy)
11449 ("python2-matplotlib" ,python2-matplotlib)
11450 ("python2-pysam" ,python2-pysam)))
11451 (home-page "http://3dgenomes.github.io/TADbit/")
11452 (synopsis "Analyze, model, and explore 3C-based data")
11454 "TADbit is a complete Python library to deal with all steps to analyze,
11455 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11456 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11457 correct interaction matrices, identify and compare the so-called
11458 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11459 interaction matrices, and finally, extract structural properties from the
11460 models. TADbit is complemented by TADkit for visualizing 3D models.")
11461 (license license:gpl3+)))
11463 (define-public kentutils
11466 ;; 302.1.0 is out, but the only difference is the inclusion of
11467 ;; pre-built binaries.
11468 (version "302.0.0")
11472 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11473 "archive/v" version ".tar.gz"))
11474 (file-name (string-append name "-" version ".tar.gz"))
11477 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11478 (modules '((guix build utils)
11483 ;; Only the contents of the specified directories are free
11484 ;; for all uses, so we remove the rest. "hg/autoSql" and
11485 ;; "hg/autoXml" are nominally free, but they depend on a
11486 ;; library that is built from the sources in "hg/lib",
11487 ;; which is nonfree.
11488 (let ((free (list "." ".."
11489 "utils" "lib" "inc" "tagStorm"
11490 "parasol" "htslib"))
11491 (directory? (lambda (file)
11492 (eq? 'directory (stat:type (stat file))))))
11493 (for-each (lambda (file)
11494 (and (directory? file)
11495 (delete-file-recursively file)))
11496 (map (cut string-append "src/" <>)
11499 (not (member file free)))))))
11500 ;; Only make the utils target, not the userApps target,
11501 ;; because that requires libraries we won't build.
11502 (substitute* "Makefile"
11503 ((" userApps") " utils"))
11504 ;; Only build libraries that are free.
11505 (substitute* "src/makefile"
11506 (("DIRS =.*") "DIRS =\n")
11507 (("cd jkOwnLib.*") "")
11510 (substitute* "src/utils/makefile"
11511 ;; These tools depend on "jkhgap.a", which is part of the
11512 ;; nonfree "src/hg/lib" directory.
11513 (("raSqlQuery") "")
11514 (("pslLiftSubrangeBlat") "")
11516 ;; Do not build UCSC tools, which may require nonfree
11518 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11520 (build-system gnu-build-system)
11522 `( ;; There is no global test target and the test target for
11523 ;; individual tools depends on input files that are not
11527 (modify-phases %standard-phases
11528 (add-after 'unpack 'fix-paths
11530 (substitute* "Makefile"
11531 (("/bin/echo") (which "echo")))
11533 (add-after 'unpack 'prepare-samtabix
11534 (lambda* (#:key inputs #:allow-other-keys)
11535 (copy-recursively (assoc-ref inputs "samtabix")
11538 (delete 'configure)
11540 (lambda* (#:key outputs #:allow-other-keys)
11541 (let ((bin (string-append (assoc-ref outputs "out")
11543 (copy-recursively "bin" bin))
11549 (uri (git-reference
11550 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11551 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11554 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11560 ("mariadb" ,mariadb)
11561 ("openssl" ,openssl)))
11562 (home-page "http://genome.cse.ucsc.edu/index.html")
11563 (synopsis "Assorted bioinformatics utilities")
11564 (description "This package provides the kentUtils, a selection of
11565 bioinformatics utilities used in combination with the UCSC genome
11567 ;; Only a subset of the sources are released under a non-copyleft
11568 ;; free software license. All other sources are removed in a
11569 ;; snippet. See this bug report for an explanation of how the
11570 ;; license statements apply:
11571 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11572 (license (license:non-copyleft
11573 "http://genome.ucsc.edu/license/"
11574 "The contents of this package are free for all uses."))))
11576 (define-public f-seq
11577 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11581 (version (string-append "1.1-" revision "." (string-take commit 7)))
11584 (uri (git-reference
11585 (url "https://github.com/aboyle/F-seq.git")
11587 (file-name (string-append name "-" version))
11590 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11591 (modules '((guix build utils)))
11592 ;; Remove bundled Java library archives.
11595 (for-each delete-file (find-files "lib" ".*"))
11597 (build-system ant-build-system)
11599 `(#:tests? #f ; no tests included
11601 (modify-phases %standard-phases
11603 (lambda* (#:key inputs outputs #:allow-other-keys)
11604 (let* ((target (assoc-ref outputs "out"))
11605 (bin (string-append target "/bin"))
11606 (doc (string-append target "/share/doc/f-seq"))
11607 (lib (string-append target "/lib")))
11610 (substitute* "bin/linux/fseq"
11611 (("java") (which "java"))
11612 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11613 (string-append (assoc-ref inputs "java-commons-cli")
11614 "/share/java/commons-cli.jar"))
11616 (string-append "REALDIR=" bin "\n")))
11617 (install-file "README.txt" doc)
11618 (install-file "bin/linux/fseq" bin)
11619 (install-file "build~/fseq.jar" lib)
11620 (copy-recursively "lib" lib)
11624 ("java-commons-cli" ,java-commons-cli)))
11625 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11626 (synopsis "Feature density estimator for high-throughput sequence tags")
11628 "F-Seq is a software package that generates a continuous tag sequence
11629 density estimation allowing identification of biologically meaningful sites
11630 such as transcription factor binding sites (ChIP-seq) or regions of open
11631 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11633 (license license:gpl3+))))
11635 (define-public bismark
11642 (uri (git-reference
11643 (url "https://github.com/FelixKrueger/Bismark.git")
11645 (file-name (string-append name "-" version "-checkout"))
11648 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11651 ;; highcharts.js is non-free software. The code is available under
11652 ;; CC-BY-NC or proprietary licenses only.
11653 (delete-file "bismark_sitrep/highcharts.js")
11655 (build-system perl-build-system)
11657 `(#:tests? #f ; there are no tests
11659 (modify-phases %standard-phases
11660 (delete 'configure)
11663 (lambda* (#:key inputs outputs #:allow-other-keys)
11664 (let* ((out (assoc-ref outputs "out"))
11665 (bin (string-append out "/bin"))
11666 (share (string-append out "/share/bismark"))
11667 (docdir (string-append out "/share/doc/bismark"))
11668 (docs '("Docs/Bismark_User_Guide.html"))
11669 (scripts '("bismark"
11670 "bismark_genome_preparation"
11671 "bismark_methylation_extractor"
11674 "coverage2cytosine"
11675 "deduplicate_bismark"
11676 "filter_non_conversion"
11678 "bismark2summary")))
11679 (substitute* "bismark2report"
11680 (("\\$RealBin/bismark_sitrep")
11681 (string-append share "/bismark_sitrep")))
11685 (for-each (lambda (file) (install-file file bin))
11687 (for-each (lambda (file) (install-file file docdir))
11689 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11690 (copy-recursively "bismark_sitrep"
11691 (string-append share "/bismark_sitrep"))
11693 ;; Fix references to gunzip
11694 (substitute* (map (lambda (file)
11695 (string-append bin "/" file))
11698 (string-append "\"" (assoc-ref inputs "gzip")
11699 "/bin/gunzip -c")))
11703 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11704 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11705 (description "Bismark is a program to map bisulfite treated sequencing
11706 reads to a genome of interest and perform methylation calls in a single step.
11707 The output can be easily imported into a genome viewer, such as SeqMonk, and
11708 enables a researcher to analyse the methylation levels of their samples
11709 straight away. Its main features are:
11712 @item Bisulfite mapping and methylation calling in one single step
11713 @item Supports single-end and paired-end read alignments
11714 @item Supports ungapped and gapped alignments
11715 @item Alignment seed length, number of mismatches etc are adjustable
11716 @item Output discriminates between cytosine methylation in CpG, CHG
11719 (license license:gpl3+)))
11721 (define-public paml
11727 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11728 "paml" version ".tgz"))
11731 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11732 (modules '((guix build utils)))
11733 ;; Remove Windows binaries
11736 (for-each delete-file (find-files "." "\\.exe$"))
11738 (build-system gnu-build-system)
11740 `(#:tests? #f ; there are no tests
11741 #:make-flags '("CC=gcc")
11743 (modify-phases %standard-phases
11744 (replace 'configure
11746 (substitute* "src/BFdriver.c"
11747 (("/bin/bash") (which "bash")))
11751 (lambda* (#:key outputs #:allow-other-keys)
11752 (let ((tools '("baseml" "basemlg" "codeml"
11753 "pamp" "evolver" "yn00" "chi2"))
11754 (bin (string-append (assoc-ref outputs "out") "/bin"))
11755 (docdir (string-append (assoc-ref outputs "out")
11756 "/share/doc/paml")))
11758 (for-each (lambda (file) (install-file file bin)) tools)
11759 (copy-recursively "../doc" docdir)
11761 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11762 (synopsis "Phylogentic analysis by maximum likelihood")
11763 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11764 contains a few programs for model fitting and phylogenetic tree reconstruction
11765 using nucleotide or amino-acid sequence data.")
11767 (license license:gpl3)))
11769 (define-public kallisto
11775 (uri (string-append "https://github.com/pachterlab/"
11776 "kallisto/archive/v" version ".tar.gz"))
11777 (file-name (string-append name "-" version ".tar.gz"))
11780 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11781 (build-system cmake-build-system)
11782 (arguments `(#:tests? #f)) ; no "check" target
11786 (home-page "http://pachterlab.github.io/kallisto/")
11787 (synopsis "Near-optimal RNA-Seq quantification")
11789 "Kallisto is a program for quantifying abundances of transcripts from
11790 RNA-Seq data, or more generally of target sequences using high-throughput
11791 sequencing reads. It is based on the novel idea of pseudoalignment for
11792 rapidly determining the compatibility of reads with targets, without the need
11793 for alignment. Pseudoalignment of reads preserves the key information needed
11794 for quantification, and kallisto is therefore not only fast, but also as
11795 accurate as existing quantification tools.")
11796 (license license:bsd-2)))
11798 (define-public libgff
11804 (uri (string-append
11805 "https://github.com/Kingsford-Group/"
11806 "libgff/archive/v" version ".tar.gz"))
11807 (file-name (string-append name "-" version ".tar.gz"))
11810 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11811 (build-system cmake-build-system)
11812 (arguments `(#:tests? #f)) ; no tests included
11813 (home-page "https://github.com/Kingsford-Group/libgff")
11814 (synopsis "Parser library for reading/writing GFF files")
11815 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11816 code that is used in the Cufflinks codebase. The goal of this library is to
11817 provide this functionality without the necessity of drawing in a heavy-weight
11818 dependency like SeqAn.")
11819 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11821 (define-public libdivsufsort
11823 (name "libdivsufsort")
11827 (uri (git-reference
11828 (url "https://github.com/y-256/libdivsufsort.git")
11830 (file-name (git-file-name name version))
11833 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11834 (build-system cmake-build-system)
11836 '(#:tests? #f ; there are no tests
11838 ;; Needed for rapmap and sailfish.
11839 '("-DBUILD_DIVSUFSORT64=ON")))
11840 (home-page "https://github.com/y-256/libdivsufsort")
11841 (synopsis "Lightweight suffix-sorting library")
11842 (description "libdivsufsort is a software library that implements a
11843 lightweight suffix array construction algorithm. This library provides a
11844 simple and an efficient C API to construct a suffix array and a
11845 Burrows-Wheeler transformed string from a given string over a constant-size
11846 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11847 bytes of memory space, where n is the length of the string.")
11848 (license license:expat)))
11850 (define-public sailfish
11857 (string-append "https://github.com/kingsfordgroup/"
11858 "sailfish/archive/v" version ".tar.gz"))
11859 (file-name (string-append name "-" version ".tar.gz"))
11862 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11863 (modules '((guix build utils)))
11866 ;; Delete bundled headers for eigen3.
11867 (delete-file-recursively "include/eigen3/")
11869 (build-system cmake-build-system)
11871 `(#:configure-flags
11872 (list (string-append "-DBOOST_INCLUDEDIR="
11873 (assoc-ref %build-inputs "boost")
11875 (string-append "-DBOOST_LIBRARYDIR="
11876 (assoc-ref %build-inputs "boost")
11878 (string-append "-DBoost_LIBRARIES="
11879 "-lboost_iostreams "
11880 "-lboost_filesystem "
11885 "-lboost_program_options")
11886 "-DBoost_FOUND=TRUE"
11887 ;; Don't download RapMap---we already have it!
11888 "-DFETCHED_RAPMAP=1")
11889 ;; Tests must be run after installation and the location of the test
11890 ;; data file must be overridden. But the tests fail. It looks like
11891 ;; they are not really meant to be run.
11894 (modify-phases %standard-phases
11895 ;; Boost cannot be found, even though it's right there.
11896 (add-after 'unpack 'do-not-look-for-boost
11897 (lambda* (#:key inputs #:allow-other-keys)
11898 (substitute* "CMakeLists.txt"
11899 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11900 (add-after 'unpack 'do-not-assign-to-macro
11902 (substitute* "include/spdlog/details/format.cc"
11903 (("const unsigned CHAR_WIDTH = 1;") ""))))
11904 (add-after 'unpack 'prepare-rapmap
11905 (lambda* (#:key inputs #:allow-other-keys)
11906 (let ((src "external/install/src/rapmap/")
11907 (include "external/install/include/rapmap/")
11908 (rapmap (assoc-ref inputs "rapmap")))
11909 (mkdir-p "/tmp/rapmap")
11910 (system* "tar" "xf"
11911 (assoc-ref inputs "rapmap")
11913 "--strip-components=1")
11916 (for-each (lambda (file)
11917 (install-file file src))
11918 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11919 (copy-recursively "/tmp/rapmap/include" include))))
11920 (add-after 'unpack 'use-system-libraries
11921 (lambda* (#:key inputs #:allow-other-keys)
11922 (substitute* '("src/SailfishIndexer.cpp"
11923 "src/SailfishUtils.cpp"
11924 "src/SailfishQuantify.cpp"
11925 "src/FASTAParser.cpp"
11927 "include/SailfishUtils.hpp"
11928 "include/SailfishIndex.hpp"
11929 "include/CollapsedEMOptimizer.hpp"
11930 "src/CollapsedEMOptimizer.cpp")
11931 (("#include \"jellyfish/config.h\"") ""))
11932 (substitute* "src/CMakeLists.txt"
11933 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11934 (string-append (assoc-ref inputs "jellyfish")
11935 "/include/jellyfish-" ,(package-version jellyfish)))
11936 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11937 (string-append (assoc-ref inputs "jellyfish")
11938 "/lib/libjellyfish-2.0.a"))
11939 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11940 (string-append (assoc-ref inputs "libdivsufsort")
11941 "/lib/libdivsufsort.so"))
11942 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11943 (string-append (assoc-ref inputs "libdivsufsort")
11944 "/lib/libdivsufsort64.so")))
11945 (substitute* "CMakeLists.txt"
11946 ;; Don't prefer static libs
11947 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11948 (("find_package\\(Jellyfish.*") "")
11949 (("ExternalProject_Add\\(libjellyfish") "message(")
11950 (("ExternalProject_Add\\(libgff") "message(")
11951 (("ExternalProject_Add\\(libsparsehash") "message(")
11952 (("ExternalProject_Add\\(libdivsufsort") "message("))
11954 ;; Ensure that Eigen headers can be found
11955 (setenv "CPLUS_INCLUDE_PATH"
11956 (string-append (getenv "CPLUS_INCLUDE_PATH")
11958 (assoc-ref inputs "eigen")
11959 "/include/eigen3")))))))
11963 ("jemalloc" ,jemalloc)
11964 ("jellyfish" ,jellyfish)
11965 ("sparsehash" ,sparsehash)
11968 (uri (git-reference
11969 (url "https://github.com/COMBINE-lab/RapMap.git")
11970 (commit (string-append "sf-v" version))))
11971 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11974 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11975 (modules '((guix build utils)))
11976 ;; These files are expected to be excluded.
11978 '(begin (delete-file-recursively "include/spdlog")
11979 (for-each delete-file '("include/xxhash.h"
11982 ("libdivsufsort" ,libdivsufsort)
11987 `(("pkg-config" ,pkg-config)))
11988 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11989 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11990 (description "Sailfish is a tool for genomic transcript quantification
11991 from RNA-seq data. It requires a set of target transcripts (either from a
11992 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11993 fasta file containing your reference transcripts and a (set of) fasta/fastq
11994 file(s) containing your reads.")
11995 (license license:gpl3+)))
11997 (define libstadenio-for-salmon
11999 (name "libstadenio")
12003 (uri (git-reference
12004 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12005 (commit (string-append "v" version))))
12006 (file-name (string-append name "-" version "-checkout"))
12009 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12010 (build-system gnu-build-system)
12011 (arguments '(#:parallel-tests? #f)) ; not supported
12015 `(("perl" ,perl))) ; for tests
12016 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12017 (synopsis "General purpose trace and experiment file library")
12018 (description "This package provides a library of file reading and writing
12019 code to provide a general purpose Trace file (and Experiment File) reading
12022 The following file formats are supported:
12025 @item SCF trace files
12026 @item ABI trace files
12027 @item ALF trace files
12028 @item ZTR trace files
12029 @item SFF trace archives
12030 @item SRF trace archives
12031 @item Experiment files
12032 @item Plain text files
12033 @item SAM/BAM sequence files
12034 @item CRAM sequence files
12036 (license license:bsd-3)))
12038 (define spdlog-for-salmon
12044 (uri (git-reference
12045 (url "https://github.com/COMBINE-lab/spdlog.git")
12046 (commit (string-append "v" version))))
12047 (file-name (string-append name "-" version "-checkout"))
12050 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12051 (build-system cmake-build-system)
12052 (home-page "https://github.com/COMBINE-lab/spdlog")
12053 (synopsis "Very fast C++ logging library")
12054 (description "Spdlog is a very fast header-only C++ logging library with
12055 performance as its primary goal.")
12056 (license license:expat)))
12058 ;; This is a modified variant of bwa for use with Salmon. It installs a
12059 ;; library to avoid having to build this as part of Salmon.
12060 (define bwa-for-salmon
12061 (package (inherit bwa)
12063 (version "0.7.12.5")
12066 (uri (git-reference
12067 (url "https://github.com/COMBINE-lab/bwa.git")
12068 (commit (string-append "v" version))))
12069 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12072 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12073 (build-system gnu-build-system)
12075 '(#:tests? #f ;no "check" target
12077 (modify-phases %standard-phases
12079 (lambda* (#:key outputs #:allow-other-keys)
12080 (let* ((out (assoc-ref outputs "out"))
12081 (bin (string-append out "/bin"))
12082 (lib (string-append out "/lib"))
12083 (doc (string-append out "/share/doc/bwa"))
12084 (man (string-append out "/share/man/man1"))
12085 (inc (string-append out "/include/bwa")))
12086 (install-file "bwa" bin)
12087 (install-file "README.md" doc)
12088 (install-file "bwa.1" man)
12089 (install-file "libbwa.a" lib)
12092 (for-each (lambda (file)
12093 (install-file file inc))
12094 (find-files "." "\\.h$")))
12096 ;; no "configure" script
12097 (delete 'configure))))))
12099 (define-public salmon
12105 (uri (git-reference
12106 (url "https://github.com/COMBINE-lab/salmon.git")
12107 (commit (string-append "v" version))))
12108 (file-name (string-append name "-" version "-checkout"))
12111 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12112 (modules '((guix build utils)))
12115 ;; Delete bundled headers for eigen3.
12116 (delete-file-recursively "include/eigen3/")
12118 (build-system cmake-build-system)
12120 `(#:configure-flags
12121 (list (string-append "-DBOOST_INCLUDEDIR="
12122 (assoc-ref %build-inputs "boost")
12124 (string-append "-DBOOST_LIBRARYDIR="
12125 (assoc-ref %build-inputs "boost")
12127 (string-append "-DBoost_LIBRARIES="
12128 "-lboost_iostreams "
12129 "-lboost_filesystem "
12134 "-lboost_program_options")
12135 "-DBoost_FOUND=TRUE"
12136 "-DTBB_LIBRARIES=tbb tbbmalloc"
12137 ;; Don't download RapMap---we already have it!
12138 "-DFETCHED_RAPMAP=1")
12140 (modify-phases %standard-phases
12141 ;; Boost cannot be found, even though it's right there.
12142 (add-after 'unpack 'do-not-look-for-boost
12143 (lambda* (#:key inputs #:allow-other-keys)
12144 (substitute* "CMakeLists.txt"
12145 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12146 (add-after 'unpack 'do-not-phone-home
12148 (substitute* "src/Salmon.cpp"
12149 (("getVersionMessage\\(\\)") "\"\""))))
12150 (add-after 'unpack 'prepare-rapmap
12151 (lambda* (#:key inputs #:allow-other-keys)
12152 (let ((src "external/install/src/rapmap/")
12153 (include "external/install/include/rapmap/")
12154 (rapmap (assoc-ref inputs "rapmap")))
12157 (for-each (lambda (file)
12158 (install-file file src))
12159 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12160 (copy-recursively (string-append rapmap "/include") include)
12161 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12162 "external/install/include/rapmap/FastxParser.hpp"
12163 "external/install/include/rapmap/concurrentqueue.h"
12164 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12165 "external/install/src/rapmap/FastxParser.cpp"
12166 "external/install/src/rapmap/xxhash.c")))))
12167 (add-after 'unpack 'use-system-libraries
12168 (lambda* (#:key inputs #:allow-other-keys)
12169 (substitute* "src/CMakeLists.txt"
12170 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12171 (string-append (assoc-ref inputs "jellyfish")
12172 "/include/jellyfish-" ,(package-version jellyfish)))
12173 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12174 (string-append (assoc-ref inputs "jellyfish")
12175 "/lib/libjellyfish-2.0.a"))
12176 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12177 (string-append (assoc-ref inputs "libdivsufsort")
12178 "/lib/libdivsufsort.so"))
12179 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12180 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12181 "/lib/libstaden-read.a"))
12182 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12183 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12184 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12185 (string-append (assoc-ref inputs "libdivsufsort")
12186 "/lib/libdivsufsort64.so")))
12187 (substitute* "CMakeLists.txt"
12188 ;; Don't prefer static libs
12189 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12190 (("set\\(TBB_LIBRARIES") "message(")
12191 (("find_package\\(Jellyfish.*") "")
12192 (("ExternalProject_Add\\(libcereal") "message(")
12193 (("ExternalProject_Add\\(libbwa") "message(")
12194 (("ExternalProject_Add\\(libjellyfish") "message(")
12195 (("ExternalProject_Add\\(libgff") "message(")
12196 (("ExternalProject_Add\\(libtbb") "message(")
12197 (("ExternalProject_Add\\(libspdlog") "message(")
12198 (("ExternalProject_Add\\(libdivsufsort") "message(")
12199 (("ExternalProject_Add\\(libstadenio") "message(")
12200 (("ExternalProject_Add_Step\\(") "message("))
12202 ;; Ensure that all headers can be found
12203 (setenv "CPLUS_INCLUDE_PATH"
12204 (string-append (getenv "CPLUS_INCLUDE_PATH")
12206 (assoc-ref inputs "bwa")
12209 (assoc-ref inputs "eigen")
12210 "/include/eigen3"))
12212 (string-append (assoc-ref inputs "bwa")
12215 (assoc-ref inputs "eigen")
12216 "/include/eigen3"))
12218 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12219 ;; run. It only exists after the install phase.
12220 (add-after 'unpack 'fix-tests
12222 (substitute* "src/CMakeLists.txt"
12223 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12224 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12228 ("bwa" ,bwa-for-salmon)
12234 (uri (git-reference
12235 (url "https://github.com/COMBINE-lab/RapMap.git")
12236 (commit (string-append "salmon-v" version))))
12237 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12240 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12241 ("jemalloc" ,jemalloc)
12242 ("jellyfish" ,jellyfish)
12245 ("libdivsufsort" ,libdivsufsort)
12246 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12247 ("spdlog-for-salmon" ,spdlog-for-salmon)
12250 (home-page "https://github.com/COMBINE-lab/salmon")
12251 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12252 (description "Salmon is a program to produce highly-accurate,
12253 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12254 its accuracy and speed via a number of different innovations, including the
12255 use of lightweight alignments (accurate but fast-to-compute proxies for
12256 traditional read alignments) and massively-parallel stochastic collapsed
12257 variational inference.")
12258 (license license:gpl3+)))
12260 (define-public python-loompy
12262 (name "python-loompy")
12267 (uri (pypi-uri "loompy" version))
12270 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12271 (build-system python-build-system)
12272 ;; There are no tests
12273 (arguments '(#:tests? #f))
12275 `(("python-h5py" ,python-h5py)
12276 ("python-numpy" ,python-numpy)
12277 ("python-scipy" ,python-scipy)
12278 ("python-typing" ,python-typing)))
12279 (home-page "https://github.com/linnarsson-lab/loompy")
12280 (synopsis "Work with .loom files for single-cell RNA-seq data")
12281 (description "The loom file format is an efficient format for very large
12282 omics datasets, consisting of a main matrix, optional additional layers, a
12283 variable number of row and column annotations. Loom also supports sparse
12284 graphs. This library makes it easy to work with @file{.loom} files for
12285 single-cell RNA-seq data.")
12286 (license license:bsd-3)))
12288 ;; We cannot use the latest commit because it requires Java 9.
12289 (define-public java-forester
12290 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12293 (name "java-forester")
12294 (version (string-append "0-" revision "." (string-take commit 7)))
12297 (uri (git-reference
12298 (url "https://github.com/cmzmasek/forester.git")
12300 (file-name (string-append name "-" version "-checkout"))
12303 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12304 (modules '((guix build utils)))
12307 ;; Delete bundled jars and pre-built classes
12308 (delete-file-recursively "forester/java/resources")
12309 (delete-file-recursively "forester/java/classes")
12310 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12311 ;; Delete bundled applications
12312 (delete-file-recursively "forester_applications")
12314 (build-system ant-build-system)
12316 `(#:tests? #f ; there are none
12318 #:modules ((guix build ant-build-system)
12320 (guix build java-utils)
12324 (modify-phases %standard-phases
12325 (add-after 'unpack 'chdir
12326 (lambda _ (chdir "forester/java") #t))
12327 (add-after 'chdir 'fix-dependencies
12329 (chmod "build.xml" #o664)
12330 (call-with-output-file "build.xml.new"
12334 (with-input-from-file "build.xml"
12335 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12336 `(;; Remove all unjar tags to avoid repacking classes.
12337 (unjar . ,(lambda _ '()))
12338 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12339 (*text* . ,(lambda (_ txt) txt))))
12341 (rename-file "build.xml.new" "build.xml")
12343 ;; FIXME: itext is difficult to package as it depends on a few
12344 ;; unpackaged libraries.
12345 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12347 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12348 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12349 (("pdf_written_to = PdfExporter.*")
12350 "throw new IOException(\"PDF export is not available.\");"))
12352 ;; There is no install target
12353 (replace 'install (install-jars ".")))))
12355 `(("java-commons-codec" ,java-commons-codec)
12356 ("java-openchart2" ,java-openchart2)))
12357 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12358 (synopsis "Phylogenomics libraries for Java")
12359 (description "Forester is a collection of Java libraries for
12360 phylogenomics and evolutionary biology research. It includes support for
12361 reading, writing, and exporting phylogenetic trees.")
12362 (license license:lgpl2.1+))))
12364 (define-public java-forester-1.005
12366 (name "java-forester")
12370 (uri (string-append "http://search.maven.org/remotecontent?"
12371 "filepath=org/biojava/thirdparty/forester/"
12372 version "/forester-" version "-sources.jar"))
12373 (file-name (string-append name "-" version ".jar"))
12376 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12377 (build-system ant-build-system)
12379 `(#:tests? #f ; there are none
12381 #:modules ((guix build ant-build-system)
12383 (guix build java-utils)
12387 (modify-phases %standard-phases
12388 (add-after 'unpack 'fix-dependencies
12389 (lambda* (#:key inputs #:allow-other-keys)
12390 (call-with-output-file "build.xml"
12394 (with-input-from-file "src/build.xml"
12395 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12396 `(;; Remove all unjar tags to avoid repacking classes.
12397 (unjar . ,(lambda _ '()))
12398 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12399 (*text* . ,(lambda (_ txt) txt))))
12401 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12402 "synth_look_and_feel_1.xml")
12403 (copy-file (assoc-ref inputs "phyloxml.xsd")
12405 (substitute* "build.xml"
12406 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12407 "synth_look_and_feel_1.xml")
12408 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12411 ;; FIXME: itext is difficult to package as it depends on a few
12412 ;; unpackaged libraries.
12413 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12415 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12416 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12417 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12418 (("pdf_written_to = PdfExporter.*")
12419 "throw new IOException(\"PDF export is not available.\"); /*")
12420 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12421 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12423 (add-after 'unpack 'delete-pre-built-classes
12424 (lambda _ (delete-file-recursively "src/classes") #t))
12425 ;; There is no install target
12426 (replace 'install (install-jars ".")))))
12428 `(("java-commons-codec" ,java-commons-codec)
12429 ("java-openchart2" ,java-openchart2)))
12430 ;; The source archive does not contain the resources.
12435 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12436 "b61cc2dcede0bede317db362472333115756b8c6/"
12437 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12438 (file-name (string-append name "-phyloxml-" version ".xsd"))
12441 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12442 ("synth_look_and_feel_1.xml"
12445 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12446 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12447 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12448 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12451 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12452 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12453 (synopsis "Phylogenomics libraries for Java")
12454 (description "Forester is a collection of Java libraries for
12455 phylogenomics and evolutionary biology research. It includes support for
12456 reading, writing, and exporting phylogenetic trees.")
12457 (license license:lgpl2.1+)))
12459 (define-public java-biojava-core
12461 (name "java-biojava-core")
12465 (uri (git-reference
12466 (url "https://github.com/biojava/biojava")
12467 (commit (string-append "biojava-" version))))
12468 (file-name (string-append name "-" version "-checkout"))
12471 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12472 (build-system ant-build-system)
12475 #:jar-name "biojava-core.jar"
12476 #:source-dir "biojava-core/src/main/java/"
12477 #:test-dir "biojava-core/src/test"
12478 ;; These tests seem to require internet access.
12479 #:test-exclude (list "**/SearchIOTest.java"
12480 "**/BlastXMLParserTest.java"
12481 "**/GenbankCookbookTest.java"
12482 "**/GenbankProxySequenceReaderTest.java")
12484 (modify-phases %standard-phases
12485 (add-before 'build 'copy-resources
12487 (copy-recursively "biojava-core/src/main/resources"
12490 (add-before 'check 'copy-test-resources
12492 (copy-recursively "biojava-core/src/test/resources"
12493 "build/test-classes")
12496 `(("java-log4j-api" ,java-log4j-api)
12497 ("java-log4j-core" ,java-log4j-core)
12498 ("java-slf4j-api" ,java-slf4j-api)
12499 ("java-slf4j-simple" ,java-slf4j-simple)))
12501 `(("java-junit" ,java-junit)
12502 ("java-hamcrest-core" ,java-hamcrest-core)))
12503 (home-page "http://biojava.org")
12504 (synopsis "Core libraries of Java framework for processing biological data")
12505 (description "BioJava is a project dedicated to providing a Java framework
12506 for processing biological data. It provides analytical and statistical
12507 routines, parsers for common file formats, reference implementations of
12508 popular algorithms, and allows the manipulation of sequences and 3D
12509 structures. The goal of the biojava project is to facilitate rapid
12510 application development for bioinformatics.
12512 This package provides the core libraries.")
12513 (license license:lgpl2.1+)))
12515 (define-public java-biojava-phylo
12516 (package (inherit java-biojava-core)
12517 (name "java-biojava-phylo")
12518 (build-system ant-build-system)
12521 #:jar-name "biojava-phylo.jar"
12522 #:source-dir "biojava-phylo/src/main/java/"
12523 #:test-dir "biojava-phylo/src/test"
12525 (modify-phases %standard-phases
12526 (add-before 'build 'copy-resources
12528 (copy-recursively "biojava-phylo/src/main/resources"
12531 (add-before 'check 'copy-test-resources
12533 (copy-recursively "biojava-phylo/src/test/resources"
12534 "build/test-classes")
12537 `(("java-log4j-api" ,java-log4j-api)
12538 ("java-log4j-core" ,java-log4j-core)
12539 ("java-slf4j-api" ,java-slf4j-api)
12540 ("java-slf4j-simple" ,java-slf4j-simple)
12541 ("java-biojava-core" ,java-biojava-core)
12542 ("java-forester" ,java-forester)))
12544 `(("java-junit" ,java-junit)
12545 ("java-hamcrest-core" ,java-hamcrest-core)))
12546 (home-page "http://biojava.org")
12547 (synopsis "Biojava interface to the forester phylogenomics library")
12548 (description "The phylo module provides a biojava interface layer to the
12549 forester phylogenomics library for constructing phylogenetic trees.")))
12551 (define-public java-biojava-alignment
12552 (package (inherit java-biojava-core)
12553 (name "java-biojava-alignment")
12554 (build-system ant-build-system)
12557 #:jar-name "biojava-alignment.jar"
12558 #:source-dir "biojava-alignment/src/main/java/"
12559 #:test-dir "biojava-alignment/src/test"
12561 (modify-phases %standard-phases
12562 (add-before 'build 'copy-resources
12564 (copy-recursively "biojava-alignment/src/main/resources"
12567 (add-before 'check 'copy-test-resources
12569 (copy-recursively "biojava-alignment/src/test/resources"
12570 "build/test-classes")
12573 `(("java-log4j-api" ,java-log4j-api)
12574 ("java-log4j-core" ,java-log4j-core)
12575 ("java-slf4j-api" ,java-slf4j-api)
12576 ("java-slf4j-simple" ,java-slf4j-simple)
12577 ("java-biojava-core" ,java-biojava-core)
12578 ("java-biojava-phylo" ,java-biojava-phylo)
12579 ("java-forester" ,java-forester)))
12581 `(("java-junit" ,java-junit)
12582 ("java-hamcrest-core" ,java-hamcrest-core)))
12583 (home-page "http://biojava.org")
12584 (synopsis "Biojava API for genetic sequence alignment")
12585 (description "The alignment module of BioJava provides an API that
12589 @item implementations of dynamic programming algorithms for sequence
12591 @item reading and writing of popular alignment file formats;
12592 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12595 (define-public java-biojava-core-4.0
12596 (package (inherit java-biojava-core)
12597 (name "java-biojava-core")
12601 (uri (git-reference
12602 (url "https://github.com/biojava/biojava")
12603 (commit (string-append "biojava-" version))))
12604 (file-name (string-append name "-" version "-checkout"))
12607 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12609 (define-public java-biojava-phylo-4.0
12610 (package (inherit java-biojava-core-4.0)
12611 (name "java-biojava-phylo")
12612 (build-system ant-build-system)
12615 #:jar-name "biojava-phylo.jar"
12616 #:source-dir "biojava-phylo/src/main/java/"
12617 #:test-dir "biojava-phylo/src/test"
12619 (modify-phases %standard-phases
12620 (add-before 'build 'copy-resources
12622 (copy-recursively "biojava-phylo/src/main/resources"
12625 (add-before 'check 'copy-test-resources
12627 (copy-recursively "biojava-phylo/src/test/resources"
12628 "build/test-classes")
12631 `(("java-log4j-api" ,java-log4j-api)
12632 ("java-log4j-core" ,java-log4j-core)
12633 ("java-slf4j-api" ,java-slf4j-api)
12634 ("java-slf4j-simple" ,java-slf4j-simple)
12635 ("java-biojava-core" ,java-biojava-core-4.0)
12636 ("java-forester" ,java-forester-1.005)))
12638 `(("java-junit" ,java-junit)
12639 ("java-hamcrest-core" ,java-hamcrest-core)))
12640 (home-page "http://biojava.org")
12641 (synopsis "Biojava interface to the forester phylogenomics library")
12642 (description "The phylo module provides a biojava interface layer to the
12643 forester phylogenomics library for constructing phylogenetic trees.")))
12645 (define-public java-biojava-alignment-4.0
12646 (package (inherit java-biojava-core-4.0)
12647 (name "java-biojava-alignment")
12648 (build-system ant-build-system)
12651 #:jar-name "biojava-alignment.jar"
12652 #:source-dir "biojava-alignment/src/main/java/"
12653 #:test-dir "biojava-alignment/src/test"
12655 (modify-phases %standard-phases
12656 (add-before 'build 'copy-resources
12658 (copy-recursively "biojava-alignment/src/main/resources"
12661 (add-before 'check 'copy-test-resources
12663 (copy-recursively "biojava-alignment/src/test/resources"
12664 "build/test-classes")
12667 `(("java-log4j-api" ,java-log4j-api)
12668 ("java-log4j-core" ,java-log4j-core)
12669 ("java-slf4j-api" ,java-slf4j-api)
12670 ("java-slf4j-simple" ,java-slf4j-simple)
12671 ("java-biojava-core" ,java-biojava-core-4.0)
12672 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12673 ("java-forester" ,java-forester-1.005)))
12675 `(("java-junit" ,java-junit)
12676 ("java-hamcrest-core" ,java-hamcrest-core)))
12677 (home-page "http://biojava.org")
12678 (synopsis "Biojava API for genetic sequence alignment")
12679 (description "The alignment module of BioJava provides an API that
12683 @item implementations of dynamic programming algorithms for sequence
12685 @item reading and writing of popular alignment file formats;
12686 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12689 (define-public dropseq-tools
12691 (name "dropseq-tools")
12696 (uri "http://mccarrolllab.com/download/1276/")
12697 (file-name (string-append "dropseq-tools-" version ".zip"))
12700 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12701 ;; Delete bundled libraries
12702 (modules '((guix build utils)))
12705 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12706 (delete-file-recursively "3rdParty")
12708 (build-system ant-build-system)
12710 `(#:tests? #f ; test data are not included
12711 #:test-target "test"
12712 #:build-target "all"
12713 #:source-dir "public/src/"
12716 (list (string-append "-Dpicard.executable.dir="
12717 (assoc-ref %build-inputs "java-picard")
12719 #:modules ((ice-9 match)
12722 (guix build java-utils)
12723 (guix build ant-build-system))
12725 (modify-phases %standard-phases
12726 ;; FIXME: fails with "java.io.FileNotFoundException:
12727 ;; /gnu/store/q76y0ximcziplgfpbn26kbw4h3s14f33-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12728 (delete 'generate-jar-indices)
12729 ;; All dependencies must be linked to "lib", because that's where
12730 ;; they will be searched for when the Class-Path property of the
12731 ;; manifest is computed.
12732 (add-after 'unpack 'record-references
12733 (lambda* (#:key inputs #:allow-other-keys)
12734 (mkdir-p "jar/lib")
12735 (let ((dirs (filter-map (match-lambda
12737 (if (and (string-prefix? "java-" name)
12738 (not (string=? name "java-testng")))
12741 (for-each (lambda (jar)
12742 (symlink jar (string-append "jar/lib/" (basename jar))))
12743 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12746 ;; There is no installation target
12748 (lambda* (#:key inputs outputs #:allow-other-keys)
12749 (let* ((out (assoc-ref outputs "out"))
12750 (bin (string-append out "/bin"))
12751 (share (string-append out "/share/java/"))
12752 (lib (string-append share "/lib/"))
12753 (scripts (list "BAMTagHistogram"
12754 "BAMTagofTagCounts"
12755 "BaseDistributionAtReadPosition"
12756 "CollapseBarcodesInPlace"
12757 "CollapseTagWithContext"
12759 "CreateIntervalsFiles"
12760 "DetectBeadSynthesisErrors"
12761 "DigitalExpression"
12762 "Drop-seq_alignment.sh"
12765 "GatherGeneGCLength"
12766 "GatherMolecularBarcodeDistributionByGene"
12767 "GatherReadQualityMetrics"
12770 "SelectCellsByNumTranscripts"
12771 "SingleCellRnaSeqMetricsCollector"
12772 "TagBamWithReadSequenceExtended"
12773 "TagReadWithGeneExon"
12774 "TagReadWithInterval"
12775 "TrimStartingSequence"
12776 "ValidateReference")))
12777 (for-each mkdir-p (list bin share lib))
12778 (install-file "dist/dropseq.jar" share)
12779 (for-each (lambda (script)
12780 (chmod script #o555)
12781 (install-file script bin))
12783 (substitute* (map (lambda (script)
12784 (string-append bin "/" script))
12786 (("^java") (which "java"))
12787 (("jar_deploy_dir=.*")
12788 (string-append "jar_deploy_dir=" share "\n"))))
12790 ;; FIXME: We do this after stripping jars because we don't want it to
12791 ;; copy all these jars and strip them. We only want to install
12792 ;; links. Arguably, this is a problem with the ant-build-system.
12793 (add-after 'strip-jar-timestamps 'install-links
12794 (lambda* (#:key outputs #:allow-other-keys)
12795 (let* ((out (assoc-ref outputs "out"))
12796 (share (string-append out "/share/java/"))
12797 (lib (string-append share "/lib/")))
12798 (for-each (lambda (jar)
12799 (symlink (readlink jar)
12800 (string-append lib (basename jar))))
12801 (find-files "jar/lib" "\\.jar$")))
12804 `(("jdk" ,icedtea-8)
12805 ("java-picard" ,java-picard-2.10.3)
12806 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12807 ("java-commons-math3" ,java-commons-math3)
12808 ("java-commons-jexl2" ,java-commons-jexl-2)
12809 ("java-commons-collections4" ,java-commons-collections4)
12810 ("java-commons-lang2" ,java-commons-lang)
12811 ("java-commons-io" ,java-commons-io)
12812 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12813 ("java-guava" ,java-guava)
12814 ("java-la4j" ,java-la4j)
12815 ("java-biojava-core" ,java-biojava-core-4.0)
12816 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12817 ("java-jdistlib" ,java-jdistlib)
12818 ("java-simple-xml" ,java-simple-xml)
12819 ("java-snakeyaml" ,java-snakeyaml)))
12822 ("java-testng" ,java-testng)))
12823 (home-page "http://mccarrolllab.com/dropseq/")
12824 (synopsis "Tools for Drop-seq analyses")
12825 (description "Drop-seq is a technology to enable biologists to
12826 analyze RNA expression genome-wide in thousands of individual cells at
12827 once. This package provides tools to perform Drop-seq analyses.")
12828 (license license:expat)))
12830 (define-public pigx-rnaseq
12832 (name "pigx-rnaseq")
12836 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12837 "releases/download/v" version
12838 "/pigx_rnaseq-" version ".tar.gz"))
12841 "0pz080k4ajlc4rlznkn3najy2a6874gb56rf9g4ag9wqz31q174j"))))
12842 (build-system gnu-build-system)
12844 `(#:parallel-tests? #f ; not supported
12846 (modify-phases %standard-phases
12847 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12848 (add-after 'unpack 'disable-resource-intensive-test
12850 (substitute* "Makefile.in"
12851 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12852 (("^ test.sh") ""))
12854 (add-after 'install 'wrap-executable
12855 ;; Make sure the executable finds all R modules.
12856 (lambda* (#:key inputs outputs #:allow-other-keys)
12857 (let ((out (assoc-ref outputs "out")))
12858 (wrap-program (string-append out "/bin/pigx-rnaseq")
12859 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12860 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12864 ("snakemake" ,snakemake)
12866 ("multiqc" ,multiqc)
12868 ("trim-galore" ,trim-galore)
12870 ("samtools" ,samtools)
12871 ("bedtools" ,bedtools)
12872 ("r-minimal" ,r-minimal)
12873 ("r-rmarkdown" ,r-rmarkdown)
12874 ("r-ggplot2" ,r-ggplot2)
12875 ("r-ggrepel" ,r-ggrepel)
12876 ("r-gprofiler" ,r-gprofiler)
12877 ("r-deseq2" ,r-deseq2)
12879 ("r-knitr" ,r-knitr)
12880 ("r-pheatmap" ,r-pheatmap)
12881 ("r-corrplot" ,r-corrplot)
12882 ("r-reshape2" ,r-reshape2)
12883 ("r-plotly" ,r-plotly)
12884 ("r-scales" ,r-scales)
12885 ("r-summarizedexperiment" ,r-summarizedexperiment)
12886 ("r-crosstalk" ,r-crosstalk)
12887 ("r-tximport" ,r-tximport)
12888 ("r-rtracklayer" ,r-rtracklayer)
12889 ("r-rjson" ,r-rjson)
12891 ("ghc-pandoc" ,ghc-pandoc-1)
12892 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12893 ("python-wrapper" ,python-wrapper)
12894 ("python-pyyaml" ,python-pyyaml)))
12895 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12896 (synopsis "Analysis pipeline for RNA sequencing experiments")
12897 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12898 reporting for RNA sequencing experiments. It is easy to use and produces high
12899 quality reports. The inputs are reads files from the sequencing experiment,
12900 and a configuration file which describes the experiment. In addition to
12901 quality control of the experiment, the pipeline produces a differential
12902 expression report comparing samples in an easily configurable manner.")
12903 (license license:gpl3+)))
12905 (define-public pigx-chipseq
12907 (name "pigx-chipseq")
12911 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12912 "releases/download/v" version
12913 "/pigx_chipseq-" version ".tar.gz"))
12916 "11v9v3vyda0sv4cl45nki7mm4v4bjfcdq7a70kcvi9h465nq66wg"))))
12917 (build-system gnu-build-system)
12919 `(#:tests? #f ; parts of the tests rely on access to the network
12921 (modify-phases %standard-phases
12922 (add-after 'install 'wrap-executable
12923 ;; Make sure the executable finds all R modules.
12924 (lambda* (#:key inputs outputs #:allow-other-keys)
12925 (let ((out (assoc-ref outputs "out")))
12926 (wrap-program (string-append out "/bin/pigx-chipseq")
12927 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12928 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12932 ("coreutils" ,coreutils)
12933 ("r-minimal" ,r-minimal)
12934 ("r-argparser" ,r-argparser)
12935 ("r-biocparallel" ,r-biocparallel)
12936 ("r-biostrings" ,r-biostrings)
12937 ("r-chipseq" ,r-chipseq)
12938 ("r-data-table" ,r-data-table)
12939 ("r-dplyr" ,r-dplyr)
12940 ("r-genomation" ,r-genomation)
12941 ("r-genomicalignments" ,r-genomicalignments)
12942 ("r-genomicranges" ,r-genomicranges)
12943 ("r-rsamtools" ,r-rsamtools)
12944 ("r-rtracklayer" ,r-rtracklayer)
12945 ("r-s4vectors" ,r-s4vectors)
12946 ("r-stringr" ,r-stringr)
12947 ("r-tibble" ,r-tibble)
12948 ("r-tidyr" ,r-tidyr)
12949 ("r-jsonlite" ,r-jsonlite)
12950 ("r-heatmaply" ,r-heatmaply)
12951 ("r-htmlwidgets" ,r-htmlwidgets)
12952 ("r-ggplot2" ,r-ggplot2)
12953 ("r-plotly" ,r-plotly)
12954 ("r-rmarkdown" ,r-rmarkdown)
12955 ("python-wrapper" ,python-wrapper)
12956 ("python-pyyaml" ,python-pyyaml)
12957 ("python-magic" ,python-magic)
12958 ("python-xlrd" ,python-xlrd)
12959 ("trim-galore" ,trim-galore)
12961 ("multiqc" ,multiqc)
12963 ("ghc-pandoc" ,ghc-pandoc-1)
12964 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12968 ("snakemake" ,snakemake)
12969 ("samtools" ,samtools)
12970 ("bedtools" ,bedtools)
12971 ("kentutils" ,kentutils)))
12973 `(("python-pytest" ,python-pytest)))
12974 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12975 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12976 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12977 calling and reporting for ChIP sequencing experiments. It is easy to use and
12978 produces high quality reports. The inputs are reads files from the sequencing
12979 experiment, and a configuration file which describes the experiment. In
12980 addition to quality control of the experiment, the pipeline enables to set up
12981 multiple peak calling analysis and allows the generation of a UCSC track hub
12982 in an easily configurable manner.")
12983 (license license:gpl3+)))
12985 (define-public pigx-bsseq
12987 (name "pigx-bsseq")
12991 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12992 "releases/download/v" version
12993 "/pigx_bsseq-" version ".tar.gz"))
12996 "0irlnlhhw9fd4ha7hksrxn3y7j76mz5qq1wjswbs9p364laqg69y"))))
12997 (build-system gnu-build-system)
13000 (modify-phases %standard-phases
13001 (add-before 'check 'set-timezone
13002 ;; The readr package is picky about timezones.
13003 (lambda* (#:key inputs #:allow-other-keys)
13004 (setenv "TZ" "UTC+1")
13006 (string-append (assoc-ref inputs "tzdata")
13007 "/share/zoneinfo"))
13009 (add-after 'install 'wrap-executable
13010 ;; Make sure the executable finds all R modules.
13011 (lambda* (#:key inputs outputs #:allow-other-keys)
13012 (let ((out (assoc-ref outputs "out")))
13013 (wrap-program (string-append out "/bin/pigx-bsseq")
13014 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
13015 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
13018 `(("tzdata" ,tzdata)))
13020 `(("coreutils" ,coreutils)
13023 ("r-minimal" ,r-minimal)
13024 ("r-annotationhub" ,r-annotationhub)
13026 ("r-genomation" ,r-genomation)
13027 ("r-methylkit" ,r-methylkit)
13028 ("r-rtracklayer" ,r-rtracklayer)
13029 ("r-rmarkdown" ,r-rmarkdown)
13030 ("r-bookdown" ,r-bookdown)
13031 ("r-ggplot2" ,r-ggplot2)
13032 ("r-ggbio" ,r-ggbio)
13033 ("ghc-pandoc" ,ghc-pandoc-1)
13034 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13035 ("python-wrapper" ,python-wrapper)
13036 ("python-pyyaml" ,python-pyyaml)
13037 ("snakemake" ,snakemake)
13038 ("bismark" ,bismark)
13041 ("trim-galore" ,trim-galore)
13042 ("cutadapt" ,cutadapt)
13043 ("samtools" ,samtools)))
13044 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13045 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13046 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13047 data of bisulfite experiments; it produces reports on aggregate methylation
13048 and coverage and can be used to produce information on differential
13049 methylation and segmentation.")
13050 (license license:gpl3+)))
13052 (define-public pigx-scrnaseq
13054 (name "pigx-scrnaseq")
13058 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13059 "releases/download/v" version
13060 "/pigx_scrnaseq-" version ".tar.gz"))
13063 "1pvjm6f3mascprs65vflggwwg5v925knvgal7k7a6nnlmw5qndrf"))))
13064 (build-system gnu-build-system)
13066 `(#:configure-flags
13067 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13068 "/share/java/picard.jar")
13069 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13070 "/share/java/dropseq.jar"))
13072 (modify-phases %standard-phases
13073 (add-after 'install 'wrap-executable
13074 ;; Make sure the executable finds all R modules.
13075 (lambda* (#:key inputs outputs #:allow-other-keys)
13076 (let ((out (assoc-ref outputs "out")))
13077 (wrap-program (string-append out "/bin/pigx-scrnaseq")
13078 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
13079 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
13082 `(("coreutils" ,coreutils)
13084 ("dropseq-tools" ,dropseq-tools)
13086 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13087 ("java" ,icedtea-8)
13088 ("python-wrapper" ,python-wrapper)
13089 ("python-pyyaml" ,python-pyyaml)
13090 ("python-pandas" ,python-pandas)
13091 ("python-numpy" ,python-numpy)
13092 ("python-loompy" ,python-loompy)
13093 ("ghc-pandoc" ,ghc-pandoc-1)
13094 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13095 ("snakemake" ,snakemake)
13097 ("r-minimal" ,r-minimal)
13098 ("r-argparser" ,r-argparser)
13099 ("r-cowplot" ,r-cowplot)
13100 ("r-data-table" ,r-data-table)
13101 ("r-delayedarray" ,r-delayedarray)
13102 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13103 ("r-dplyr" ,r-dplyr)
13104 ("r-dropbead" ,r-dropbead)
13106 ("r-genomicalignments" ,r-genomicalignments)
13107 ("r-genomicfiles" ,r-genomicfiles)
13108 ("r-genomicranges" ,r-genomicranges)
13109 ("r-ggplot2" ,r-ggplot2)
13110 ("r-hdf5array" ,r-hdf5array)
13111 ("r-pheatmap" ,r-pheatmap)
13112 ("r-rmarkdown" ,r-rmarkdown)
13113 ("r-rsamtools" ,r-rsamtools)
13114 ("r-rtracklayer" ,r-rtracklayer)
13115 ("r-rtsne" ,r-rtsne)
13116 ("r-scater" ,r-scater)
13117 ("r-scran" ,r-scran)
13118 ("r-singlecellexperiment" ,r-singlecellexperiment)
13119 ("r-stringr" ,r-stringr)
13120 ("r-yaml" ,r-yaml)))
13121 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13122 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13123 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13124 quality control for single cell RNA sequencing experiments. The inputs are
13125 read files from the sequencing experiment, and a configuration file which
13126 describes the experiment. It produces processed files for downstream analysis
13127 and interactive quality reports. The pipeline is designed to work with UMI
13129 (license license:gpl3+)))
13131 (define-public pigx
13137 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13138 "releases/download/v" version
13139 "/pigx-" version ".tar.gz"))
13142 "0sb708sl42h3s5z872jb1w70bbqplwapnsc1wm27zcsvi7li4gw8"))))
13143 (build-system gnu-build-system)
13145 `(("python" ,python)
13146 ("pigx-bsseq" ,pigx-bsseq)
13147 ("pigx-chipseq" ,pigx-chipseq)
13148 ("pigx-rnaseq" ,pigx-rnaseq)
13149 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13150 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13151 (synopsis "Analysis pipelines for genomics")
13152 (description "PiGx is a collection of genomics pipelines. It includes the
13153 following pipelines:
13156 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13157 @item PiGx RNAseq for RNAseq samples
13158 @item PiGx scRNAseq for single cell dropseq analysis
13159 @item PiGx ChIPseq for reads from ChIPseq experiments
13162 All pipelines are easily configured with a simple sample sheet and a
13163 descriptive settings file. The result is a set of comprehensive, interactive
13164 HTML reports with interesting findings about your samples.")
13165 (license license:gpl3+)))
13167 (define-public r-diversitree
13169 (name "r-diversitree")
13174 (uri (cran-uri "diversitree" version))
13177 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13178 (build-system r-build-system)
13180 `(("gfortran" ,gfortran)))
13181 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13184 ("r-desolve" ,r-desolve)
13186 ("r-suplex" ,r-subplex)))
13187 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13188 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13189 (description "This package contains a number of comparative \"phylogenetic\"
13190 methods, mostly focusing on analysing diversification and character evolution.
13191 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13192 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13193 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13194 include Markov models of discrete and continuous trait evolution and constant
13195 rate speciation and extinction.")
13196 (license license:gpl2+)))
13198 (define-public sjcount
13199 ;; There is no tag for version 3.2, nor is there a release archive.
13200 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13204 (version (git-version "3.2" revision commit))
13207 (uri (git-reference
13208 (url "https://github.com/pervouchine/sjcount-full.git")
13210 (file-name (string-append name "-" version "-checkout"))
13213 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13214 (build-system gnu-build-system)
13216 `(#:tests? #f ; requires a 1.4G test file
13218 (list (string-append "SAMTOOLS_DIR="
13219 (assoc-ref %build-inputs "samtools")
13222 (modify-phases %standard-phases
13223 (replace 'configure
13224 (lambda* (#:key inputs #:allow-other-keys)
13225 (substitute* "makefile"
13226 (("-I \\$\\{SAMTOOLS_DIR\\}")
13227 (string-append "-I" (assoc-ref inputs "samtools")
13228 "/include/samtools"))
13229 (("-lz ") "-lz -lpthread "))
13232 (lambda* (#:key outputs #:allow-other-keys)
13233 (for-each (lambda (tool)
13235 (string-append (assoc-ref outputs "out")
13237 '("j_count" "b_count" "sjcount"))
13240 `(("samtools" ,samtools-0.1)
13242 (home-page "https://github.com/pervouchine/sjcount-full/")
13243 (synopsis "Annotation-agnostic splice junction counting pipeline")
13244 (description "Sjcount is a utility for fast quantification of splice
13245 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13246 version does count multisplits.")
13247 (license license:gpl3+))))