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>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
16 ;;; This file is part of GNU Guix.
18 ;;; GNU Guix is free software; you can redistribute it and/or modify it
19 ;;; under the terms of the GNU General Public License as published by
20 ;;; the Free Software Foundation; either version 3 of the License, or (at
21 ;;; your option) any later version.
23 ;;; GNU Guix is distributed in the hope that it will be useful, but
24 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
25 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
26 ;;; GNU General Public License for more details.
28 ;;; You should have received a copy of the GNU General Public License
29 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
31 (define-module (gnu packages bioinformatics)
32 #:use-module ((guix licenses) #:prefix license:)
33 #:use-module (guix packages)
34 #:use-module (guix utils)
35 #:use-module (guix download)
36 #:use-module (guix git-download)
37 #:use-module (guix hg-download)
38 #:use-module (guix build-system ant)
39 #:use-module (guix build-system gnu)
40 #:use-module (guix build-system cmake)
41 #:use-module (guix build-system ocaml)
42 #:use-module (guix build-system perl)
43 #:use-module (guix build-system python)
44 #:use-module (guix build-system r)
45 #:use-module (guix build-system ruby)
46 #:use-module (guix build-system scons)
47 #:use-module (guix build-system trivial)
48 #:use-module (gnu packages)
49 #:use-module (gnu packages autotools)
50 #:use-module (gnu packages algebra)
51 #:use-module (gnu packages base)
52 #:use-module (gnu packages bash)
53 #:use-module (gnu packages bison)
54 #:use-module (gnu packages boost)
55 #:use-module (gnu packages check)
56 #:use-module (gnu packages compression)
57 #:use-module (gnu packages cpio)
58 #:use-module (gnu packages cran)
59 #:use-module (gnu packages curl)
60 #:use-module (gnu packages documentation)
61 #:use-module (gnu packages databases)
62 #:use-module (gnu packages datastructures)
63 #:use-module (gnu packages file)
64 #:use-module (gnu packages flex)
65 #:use-module (gnu packages gawk)
66 #:use-module (gnu packages gcc)
67 #:use-module (gnu packages gd)
68 #:use-module (gnu packages gtk)
69 #:use-module (gnu packages glib)
70 #:use-module (gnu packages graph)
71 #:use-module (gnu packages groff)
72 #:use-module (gnu packages guile)
73 #:use-module (gnu packages haskell)
74 #:use-module (gnu packages image)
75 #:use-module (gnu packages imagemagick)
76 #:use-module (gnu packages java)
77 #:use-module (gnu packages jemalloc)
78 #:use-module (gnu packages ldc)
79 #:use-module (gnu packages linux)
80 #:use-module (gnu packages logging)
81 #:use-module (gnu packages machine-learning)
82 #:use-module (gnu packages man)
83 #:use-module (gnu packages maths)
84 #:use-module (gnu packages mpi)
85 #:use-module (gnu packages ncurses)
86 #:use-module (gnu packages ocaml)
87 #:use-module (gnu packages pcre)
88 #:use-module (gnu packages parallel)
89 #:use-module (gnu packages pdf)
90 #:use-module (gnu packages perl)
91 #:use-module (gnu packages perl-check)
92 #:use-module (gnu packages pkg-config)
93 #:use-module (gnu packages popt)
94 #:use-module (gnu packages protobuf)
95 #:use-module (gnu packages python)
96 #:use-module (gnu packages python-web)
97 #:use-module (gnu packages readline)
98 #:use-module (gnu packages ruby)
99 #:use-module (gnu packages serialization)
100 #:use-module (gnu packages shells)
101 #:use-module (gnu packages statistics)
102 #:use-module (gnu packages swig)
103 #:use-module (gnu packages tbb)
104 #:use-module (gnu packages tex)
105 #:use-module (gnu packages texinfo)
106 #:use-module (gnu packages textutils)
107 #:use-module (gnu packages time)
108 #:use-module (gnu packages tls)
109 #:use-module (gnu packages vim)
110 #:use-module (gnu packages web)
111 #:use-module (gnu packages xml)
112 #:use-module (gnu packages xorg)
113 #:use-module (srfi srfi-1)
114 #:use-module (ice-9 match))
116 (define-public aragorn
123 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
127 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
128 (build-system gnu-build-system)
130 `(#:tests? #f ; there are no tests
132 (modify-phases %standard-phases
136 (zero? (system* "gcc"
142 (string-append "aragorn" ,version ".c")))))
144 (lambda* (#:key outputs #:allow-other-keys)
145 (let* ((out (assoc-ref outputs "out"))
146 (bin (string-append out "/bin"))
147 (man (string-append out "/share/man/man1")))
149 (install-file "aragorn" bin)
151 (install-file "aragorn.1" man))
153 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
154 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
156 "Aragorn identifies transfer RNA, mitochondrial RNA and
157 transfer-messenger RNA from nucleotide sequences, based on homology to known
158 tRNA consensus sequences and RNA structure. It also outputs the secondary
159 structure of the predicted RNA.")
160 (license license:gpl2)))
168 ;; BamM is not available on pypi.
170 "https://github.com/Ecogenomics/BamM/archive/"
172 (file-name (string-append name "-" version ".tar.gz"))
175 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
176 (modules '((guix build utils)))
179 ;; Delete bundled htslib.
180 (delete-file-recursively "c/htslib-1.3.1")
182 (build-system python-build-system)
184 `(#:python ,python-2 ; BamM is Python 2 only.
185 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
186 ;; been modified from its original form.
188 (let ((htslib (assoc-ref %build-inputs "htslib")))
189 (list "--with-libhts-lib" (string-append htslib "/lib")
190 "--with-libhts-inc" (string-append htslib "/include/htslib")))
192 (modify-phases %standard-phases
193 (add-after 'unpack 'autogen
195 (with-directory-excursion "c"
196 (let ((sh (which "sh")))
197 ;; Use autogen so that 'configure' works.
198 (substitute* "autogen.sh" (("/bin/sh") sh))
199 (setenv "CONFIG_SHELL" sh)
200 (substitute* "configure" (("/bin/sh") sh))
201 (zero? (system* "./autogen.sh"))))))
203 ;; Run tests after installation so compilation only happens once.
205 (add-after 'install 'wrap-executable
206 (lambda* (#:key outputs #:allow-other-keys)
207 (let* ((out (assoc-ref outputs "out"))
208 (path (getenv "PATH")))
209 (wrap-program (string-append out "/bin/bamm")
210 `("PATH" ":" prefix (,path))))
212 (add-after 'wrap-executable 'post-install-check
213 (lambda* (#:key inputs outputs #:allow-other-keys)
215 (string-append (assoc-ref outputs "out")
220 (assoc-ref outputs "out")
222 (string-take (string-take-right
223 (assoc-ref inputs "python") 5) 3)
225 (getenv "PYTHONPATH")))
226 ;; There are 2 errors printed, but they are safe to ignore:
227 ;; 1) [E::hts_open_format] fail to open file ...
228 ;; 2) samtools view: failed to open ...
229 (zero? (system* "nosetests")))))))
231 `(("autoconf" ,autoconf)
232 ("automake" ,automake)
235 ("python-nose" ,python2-nose)
236 ("python-pysam" ,python2-pysam)))
238 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
239 ("samtools" ,samtools)
243 ("coreutils" ,coreutils)))
245 `(("python-numpy" ,python2-numpy)))
246 (home-page "http://ecogenomics.github.io/BamM/")
247 (synopsis "Metagenomics-focused BAM file manipulator")
249 "BamM is a C library, wrapped in python, to efficiently generate and
250 parse BAM files, specifically for the analysis of metagenomic data. For
251 instance, it implements several methods to assess contig-wise read coverage.")
252 (license license:lgpl3+)))
254 (define-public bamtools
261 "https://github.com/pezmaster31/bamtools/archive/v"
263 (file-name (string-append name "-" version ".tar.gz"))
266 "1z3kg24qrwq13a88n9d86izngrar4fll7gr6phddb2faw75pdgaa"))))
267 (build-system cmake-build-system)
269 `(#:tests? #f ;no "check" target
271 (modify-phases %standard-phases
273 'configure 'set-ldflags
274 (lambda* (#:key outputs #:allow-other-keys)
278 (assoc-ref outputs "out") "/lib/bamtools")))))))
279 (inputs `(("zlib" ,zlib)))
280 (home-page "https://github.com/pezmaster31/bamtools")
281 (synopsis "C++ API and command-line toolkit for working with BAM data")
283 "BamTools provides both a C++ API and a command-line toolkit for handling
285 (license license:expat)))
287 (define-public bcftools
294 "https://github.com/samtools/bcftools/releases/download/"
295 version "/bcftools-" version ".tar.bz2"))
298 "1vgw2mwngq20c530zim52zvgmw1lci8rzl33pvh44xqk3xlzvjsa"))
299 (modules '((guix build utils)))
301 ;; Delete bundled htslib.
302 (delete-file-recursively "htslib-1.8")
304 (build-system gnu-build-system)
306 `(#:test-target "test"
307 #:configure-flags (list "--with-htslib=system")
311 "LIBS=-lgsl -lgslcblas"
312 (string-append "prefix=" (assoc-ref %outputs "out"))
313 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
314 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
315 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
316 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
317 (string-append "PACKAGE_VERSION=" ,version))
319 (modify-phases %standard-phases
320 (add-before 'check 'patch-tests
322 (substitute* "test/test.pl"
323 (("/bin/bash") (which "bash")))
331 (home-page "https://samtools.github.io/bcftools/")
332 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
334 "BCFtools is a set of utilities that manipulate variant calls in the
335 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
336 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
337 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
338 (license (list license:gpl3+ license:expat))))
340 (define-public bedops
346 (uri (string-append "https://github.com/bedops/bedops/archive/v"
348 (file-name (string-append name "-" version ".tar.gz"))
351 "0kx4awrwby8f33wqyx8w7ms7v25xhf0d421csgf96a3hfzn2mb0m"))))
352 (build-system gnu-build-system)
355 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
357 (modify-phases %standard-phases
358 (add-after 'unpack 'unpack-tarballs
360 ;; FIXME: Bedops includes tarballs of minimally patched upstream
361 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
362 ;; libraries because at least one of the libraries (zlib) is
363 ;; patched to add a C++ function definition (deflateInit2cpp).
364 ;; Until the Bedops developers offer a way to link against system
365 ;; libraries we have to build the in-tree copies of these three
368 ;; See upstream discussion:
369 ;; https://github.com/bedops/bedops/issues/124
371 ;; Unpack the tarballs to benefit from shebang patching.
372 (with-directory-excursion "third-party"
373 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
374 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
375 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
376 ;; Disable unpacking of tarballs in Makefile.
377 (substitute* "system.mk/Makefile.linux"
378 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
379 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
380 (substitute* "third-party/zlib-1.2.7/Makefile.in"
381 (("^SHELL=.*$") "SHELL=bash\n"))
383 (delete 'configure))))
384 (home-page "https://github.com/bedops/bedops")
385 (synopsis "Tools for high-performance genomic feature operations")
387 "BEDOPS is a suite of tools to address common questions raised in genomic
388 studies---mostly with regard to overlap and proximity relationships between
389 data sets. It aims to be scalable and flexible, facilitating the efficient
390 and accurate analysis and management of large-scale genomic data.
392 BEDOPS provides tools that perform highly efficient and scalable Boolean and
393 other set operations, statistical calculations, archiving, conversion and
394 other management of genomic data of arbitrary scale. Tasks can be easily
395 split by chromosome for distributing whole-genome analyses across a
396 computational cluster.")
397 (license license:gpl2+)))
399 (define-public bedtools
405 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
406 "download/v" version "/"
407 "bedtools-" version ".tar.gz"))
410 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
411 (build-system gnu-build-system)
413 '(#:test-target "test"
415 (list (string-append "prefix=" (assoc-ref %outputs "out")))
417 (modify-phases %standard-phases
418 (delete 'configure))))
419 (native-inputs `(("python" ,python-2)))
421 `(("samtools" ,samtools)
423 (home-page "https://github.com/arq5x/bedtools2")
424 (synopsis "Tools for genome analysis and arithmetic")
426 "Collectively, the bedtools utilities are a swiss-army knife of tools for
427 a wide-range of genomics analysis tasks. The most widely-used tools enable
428 genome arithmetic: that is, set theory on the genome. For example, bedtools
429 allows one to intersect, merge, count, complement, and shuffle genomic
430 intervals from multiple files in widely-used genomic file formats such as BAM,
432 (license license:gpl2)))
434 ;; Later releases of bedtools produce files with more columns than
435 ;; what Ribotaper expects.
436 (define-public bedtools-2.18
437 (package (inherit bedtools)
442 (uri (string-append "https://github.com/arq5x/bedtools2/"
443 "archive/v" version ".tar.gz"))
444 (file-name (string-append name "-" version ".tar.gz"))
447 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
449 '(#:test-target "test"
451 (modify-phases %standard-phases
454 (lambda* (#:key outputs #:allow-other-keys)
455 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
456 (for-each (lambda (file)
457 (install-file file bin))
458 (find-files "bin" ".*")))
461 (define-public ribotaper
467 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
468 "files/RiboTaper/RiboTaper_Version_"
472 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
473 (build-system gnu-build-system)
476 (modify-phases %standard-phases
477 (add-after 'install 'wrap-executables
478 (lambda* (#:key inputs outputs #:allow-other-keys)
479 (let* ((out (assoc-ref outputs "out")))
482 (wrap-program (string-append out "/bin/" script)
483 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
484 '("create_annotations_files.bash"
485 "create_metaplots.bash"
486 "Ribotaper_ORF_find.sh"
487 "Ribotaper.sh"))))))))
489 `(("bedtools" ,bedtools-2.18)
490 ("samtools" ,samtools-0.1)
491 ("r-minimal" ,r-minimal)
492 ("r-foreach" ,r-foreach)
493 ("r-xnomial" ,r-xnomial)
495 ("r-multitaper" ,r-multitaper)
496 ("r-seqinr" ,r-seqinr)))
497 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
498 (synopsis "Define translated ORFs using ribosome profiling data")
500 "Ribotaper is a method for defining translated @dfn{open reading
501 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
502 provides the Ribotaper pipeline.")
503 (license license:gpl3+)))
505 (define-public ribodiff
512 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
513 "archive/v" version ".tar.gz"))
514 (file-name (string-append name "-" version ".tar.gz"))
517 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
518 (build-system python-build-system)
522 (modify-phases %standard-phases
523 ;; Generate an installable executable script wrapper.
524 (add-after 'unpack 'patch-setup.py
526 (substitute* "setup.py"
527 (("^(.*)packages=.*" line prefix)
528 (string-append line "\n"
529 prefix "scripts=['scripts/TE.py'],\n")))
532 `(("python-numpy" ,python2-numpy)
533 ("python-matplotlib" ,python2-matplotlib)
534 ("python-scipy" ,python2-scipy)
535 ("python-statsmodels" ,python2-statsmodels)))
537 `(("python-mock" ,python2-mock)
538 ("python-nose" ,python2-nose)))
539 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
540 (synopsis "Detect translation efficiency changes from ribosome footprints")
541 (description "RiboDiff is a statistical tool that detects the protein
542 translational efficiency change from Ribo-Seq (ribosome footprinting) and
543 RNA-Seq data. It uses a generalized linear model to detect genes showing
544 difference in translational profile taking mRNA abundance into account. It
545 facilitates us to decipher the translational regulation that behave
546 independently with transcriptional regulation.")
547 (license license:gpl3+)))
549 (define-public bioawk
555 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
557 (file-name (string-append name "-" version ".tar.gz"))
559 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
560 (build-system gnu-build-system)
566 `(#:tests? #f ; There are no tests to run.
567 ;; Bison must generate files, before other targets can build.
570 (modify-phases %standard-phases
571 (delete 'configure) ; There is no configure phase.
573 (lambda* (#:key outputs #:allow-other-keys)
574 (let* ((out (assoc-ref outputs "out"))
575 (bin (string-append out "/bin"))
576 (man (string-append out "/share/man/man1")))
578 (copy-file "awk.1" (string-append man "/bioawk.1"))
579 (install-file "bioawk" bin)))))))
580 (home-page "https://github.com/lh3/bioawk")
581 (synopsis "AWK with bioinformatics extensions")
582 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
583 support of several common biological data formats, including optionally gzip'ed
584 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
585 also adds a few built-in functions and a command line option to use TAB as the
586 input/output delimiter. When the new functionality is not used, bioawk is
587 intended to behave exactly the same as the original BWK awk.")
588 (license license:x11)))
590 (define-public python2-pybedtools
592 (name "python2-pybedtools")
597 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
601 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
602 (build-system python-build-system)
603 (arguments `(#:python ,python-2)) ; no Python 3 support
605 `(("python-matplotlib" ,python2-matplotlib)))
607 `(("bedtools" ,bedtools)
608 ("samtools" ,samtools)))
610 `(("python-cython" ,python2-cython)
611 ("python-pyyaml" ,python2-pyyaml)
612 ("python-nose" ,python2-nose)))
613 (home-page "https://pythonhosted.org/pybedtools/")
614 (synopsis "Python wrapper for BEDtools programs")
616 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
617 which are widely used for genomic interval manipulation or \"genome algebra\".
618 pybedtools extends BEDTools by offering feature-level manipulations from with
620 (license license:gpl2+)))
622 (define-public python-biom-format
624 (name "python-biom-format")
629 ;; Use GitHub as source because PyPI distribution does not contain
630 ;; test data: https://github.com/biocore/biom-format/issues/693
631 (uri (string-append "https://github.com/biocore/biom-format/archive/"
633 (file-name (string-append name "-" version ".tar.gz"))
636 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
637 (build-system python-build-system)
639 `(("python-numpy" ,python-numpy)
640 ("python-scipy" ,python-scipy)
641 ("python-future" ,python-future)
642 ("python-click" ,python-click)
643 ("python-h5py" ,python-h5py)
644 ("python-pandas" ,python-pandas)))
646 `(("python-nose" ,python-nose)))
647 (home-page "http://www.biom-format.org")
648 (synopsis "Biological Observation Matrix (BIOM) format utilities")
650 "The BIOM file format is designed to be a general-use format for
651 representing counts of observations e.g. operational taxonomic units, KEGG
652 orthology groups or lipid types, in one or more biological samples
653 e.g. microbiome samples, genomes, metagenomes.")
654 (license license:bsd-3)
655 (properties `((python2-variant . ,(delay python2-biom-format))))))
657 (define-public python2-biom-format
658 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
663 (modify-phases %standard-phases
664 ;; Do not require the unmaintained pyqi library.
665 (add-after 'unpack 'remove-pyqi
667 (substitute* "setup.py"
668 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
670 ,@(package-arguments base))))))
672 (define-public bioperl-minimal
673 (let* ((inputs `(("perl-module-build" ,perl-module-build)
674 ("perl-data-stag" ,perl-data-stag)
675 ("perl-libwww" ,perl-libwww)
676 ("perl-uri" ,perl-uri)))
678 (map (compose package-name cadr)
681 (map (compose package-transitive-target-inputs cadr) inputs))))))
683 (name "bioperl-minimal")
688 (uri (string-append "https://github.com/bioperl/bioperl-live/"
690 (string-map (lambda (c)
696 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
697 (build-system perl-build-system)
700 (modify-phases %standard-phases
702 'install 'wrap-programs
703 (lambda* (#:key outputs #:allow-other-keys)
704 ;; Make sure all executables in "bin" find the required Perl
705 ;; modules at runtime. As the PERL5LIB variable contains also
706 ;; the paths of native inputs, we pick the transitive target
707 ;; inputs from %build-inputs.
708 (let* ((out (assoc-ref outputs "out"))
709 (bin (string-append out "/bin/"))
711 (cons (string-append out "/lib/perl5/site_perl")
713 (assoc-ref %build-inputs name))
714 ',transitive-inputs))
716 (for-each (lambda (file)
718 `("PERL5LIB" ":" prefix (,path))))
719 (find-files bin "\\.pl$"))
723 `(("perl-test-most" ,perl-test-most)))
724 (home-page "https://metacpan.org/release/BioPerl")
725 (synopsis "Bioinformatics toolkit")
727 "BioPerl is the product of a community effort to produce Perl code which
728 is useful in biology. Examples include Sequence objects, Alignment objects
729 and database searching objects. These objects not only do what they are
730 advertised to do in the documentation, but they also interact - Alignment
731 objects are made from the Sequence objects, Sequence objects have access to
732 Annotation and SeqFeature objects and databases, Blast objects can be
733 converted to Alignment objects, and so on. This means that the objects
734 provide a coordinated and extensible framework to do computational biology.")
735 (license license:perl-license))))
737 (define-public python-biopython
739 (name "python-biopython")
743 ;; use PyPi rather than biopython.org to ease updating
744 (uri (pypi-uri "biopython" version))
747 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
748 (build-system python-build-system)
751 (modify-phases %standard-phases
752 (add-before 'check 'set-home
753 ;; Some tests require a home directory to be set.
754 (lambda _ (setenv "HOME" "/tmp") #t)))))
756 `(("python-numpy" ,python-numpy)))
757 (home-page "http://biopython.org/")
758 (synopsis "Tools for biological computation in Python")
760 "Biopython is a set of tools for biological computation including parsers
761 for bioinformatics files into Python data structures; interfaces to common
762 bioinformatics programs; a standard sequence class and tools for performing
763 common operations on them; code to perform data classification; code for
764 dealing with alignments; code making it easy to split up parallelizable tasks
765 into separate processes; and more.")
766 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
768 (define-public python2-biopython
769 (package-with-python2 python-biopython))
771 (define-public python-fastalite
773 (name "python-fastalite")
778 (uri (pypi-uri "fastalite" version))
781 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
782 (build-system python-build-system)
784 `(#:tests? #f)) ; Test data is not distributed.
785 (home-page "https://github.com/nhoffman/fastalite")
786 (synopsis "Simplest possible FASTA parser")
787 (description "This library implements a FASTA and a FASTQ parser without
788 relying on a complex dependency tree.")
789 (license license:expat)))
791 (define-public python2-fastalite
792 (package-with-python2 python-fastalite))
794 (define-public bpp-core
795 ;; The last release was in 2014 and the recommended way to install from source
796 ;; is to clone the git repository, so we do this.
797 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
798 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
801 (version (string-append "2.2.0-1." (string-take commit 7)))
805 (url "http://biopp.univ-montp2.fr/git/bpp-core")
807 (file-name (string-append name "-" version "-checkout"))
810 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
811 (build-system cmake-build-system)
813 `(#:parallel-build? #f))
815 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
816 ; compile all of the bpp packages with GCC 5.
817 (home-page "http://biopp.univ-montp2.fr")
818 (synopsis "C++ libraries for Bioinformatics")
820 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
821 analysis, phylogenetics, molecular evolution and population genetics. It is
822 Object Oriented and is designed to be both easy to use and computer efficient.
823 Bio++ intends to help programmers to write computer expensive programs, by
824 providing them a set of re-usable tools.")
825 (license license:cecill-c))))
827 (define-public bpp-phyl
828 ;; The last release was in 2014 and the recommended way to install from source
829 ;; is to clone the git repository, so we do this.
830 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
831 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
834 (version (string-append "2.2.0-1." (string-take commit 7)))
838 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
840 (file-name (string-append name "-" version "-checkout"))
843 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
844 (build-system cmake-build-system)
846 `(#:parallel-build? #f
847 ;; If out-of-source, test data is not copied into the build directory
848 ;; so the tests fail.
849 #:out-of-source? #f))
851 `(("bpp-core" ,bpp-core)
853 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
856 (home-page "http://biopp.univ-montp2.fr")
857 (synopsis "Bio++ phylogenetic Library")
859 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
860 analysis, phylogenetics, molecular evolution and population genetics. This
861 library provides phylogenetics-related modules.")
862 (license license:cecill-c))))
864 (define-public bpp-popgen
865 ;; The last release was in 2014 and the recommended way to install from source
866 ;; is to clone the git repository, so we do this.
867 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
868 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
871 (version (string-append "2.2.0-1." (string-take commit 7)))
875 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
877 (file-name (string-append name "-" version "-checkout"))
880 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
881 (build-system cmake-build-system)
883 `(#:parallel-build? #f
884 #:tests? #f)) ; There are no tests.
886 `(("bpp-core" ,bpp-core)
889 (home-page "http://biopp.univ-montp2.fr")
890 (synopsis "Bio++ population genetics library")
892 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
893 analysis, phylogenetics, molecular evolution and population genetics. This
894 library provides population genetics-related modules.")
895 (license license:cecill-c))))
897 (define-public bpp-seq
898 ;; The last release was in 2014 and the recommended way to install from source
899 ;; is to clone the git repository, so we do this.
900 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
901 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
904 (version (string-append "2.2.0-1." (string-take commit 7)))
908 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
910 (file-name (string-append name "-" version "-checkout"))
913 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
914 (build-system cmake-build-system)
916 `(#:parallel-build? #f
917 ;; If out-of-source, test data is not copied into the build directory
918 ;; so the tests fail.
919 #:out-of-source? #f))
921 `(("bpp-core" ,bpp-core)
922 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
923 (home-page "http://biopp.univ-montp2.fr")
924 (synopsis "Bio++ sequence library")
926 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
927 analysis, phylogenetics, molecular evolution and population genetics. This
928 library provides sequence-related modules.")
929 (license license:cecill-c))))
931 (define-public bppsuite
932 ;; The last release was in 2014 and the recommended way to install from source
933 ;; is to clone the git repository, so we do this.
934 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
935 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
938 (version (string-append "2.2.0-1." (string-take commit 7)))
942 (url "http://biopp.univ-montp2.fr/git/bppsuite")
944 (file-name (string-append name "-" version "-checkout"))
947 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
948 (build-system cmake-build-system)
950 `(#:parallel-build? #f
951 #:tests? #f)) ; There are no tests.
955 ("texinfo" ,texinfo)))
957 `(("bpp-core" ,bpp-core)
959 ("bpp-phyl" ,bpp-phyl)
960 ("bpp-phyl" ,bpp-popgen)
962 (home-page "http://biopp.univ-montp2.fr")
963 (synopsis "Bioinformatics tools written with the Bio++ libraries")
965 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
966 analysis, phylogenetics, molecular evolution and population genetics. This
967 package provides command line tools using the Bio++ library.")
968 (license license:cecill-c))))
970 (define-public blast+
977 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
978 version "/ncbi-blast-" version "+-src.tar.gz"))
981 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
982 (patches (search-patches "blast+-fix-makefile.patch"))
983 (modules '((guix build utils)))
986 ;; Remove bundled bzip2, zlib and pcre.
987 (delete-file-recursively "c++/src/util/compress/bzip2")
988 (delete-file-recursively "c++/src/util/compress/zlib")
989 (delete-file-recursively "c++/src/util/regexp")
990 (substitute* "c++/src/util/compress/Makefile.in"
991 (("bzip2 zlib api") "api"))
992 ;; Remove useless msbuild directory
993 (delete-file-recursively
994 "c++/src/build-system/project_tree_builder/msbuild")
996 (build-system gnu-build-system)
998 `(;; There are two(!) tests for this massive library, and both fail with
999 ;; "unparsable timing stats".
1000 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1001 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1004 #:parallel-build? #f ; not supported
1006 (modify-phases %standard-phases
1008 'configure 'set-HOME
1009 ;; $HOME needs to be set at some point during the configure phase
1010 (lambda _ (setenv "HOME" "/tmp") #t))
1013 (lambda _ (chdir "c++") #t))
1015 'enter-dir 'fix-build-system
1017 (define (which* cmd)
1018 (cond ((string=? cmd "date")
1019 ;; make call to "date" deterministic
1024 (format (current-error-port)
1025 "WARNING: Unable to find absolute path for ~s~%"
1029 ;; Rewrite hardcoded paths to various tools
1030 (substitute* (append '("src/build-system/configure.ac"
1031 "src/build-system/configure"
1032 "src/build-system/helpers/run_with_lock.c"
1033 "scripts/common/impl/if_diff.sh"
1034 "scripts/common/impl/run_with_lock.sh"
1035 "src/build-system/Makefile.configurables.real"
1036 "src/build-system/Makefile.in.top"
1037 "src/build-system/Makefile.meta.gmake=no"
1038 "src/build-system/Makefile.meta.in"
1039 "src/build-system/Makefile.meta_l"
1040 "src/build-system/Makefile.meta_p"
1041 "src/build-system/Makefile.meta_r"
1042 "src/build-system/Makefile.mk.in"
1043 "src/build-system/Makefile.requirements"
1044 "src/build-system/Makefile.rules_with_autodep.in")
1045 (find-files "scripts/common/check" "\\.sh$"))
1046 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1047 (or (which* cmd) all)))
1049 (substitute* (find-files "src/build-system" "^config.*")
1050 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1053 ;; rewrite "/var/tmp" in check script
1054 (substitute* "scripts/common/check/check_make_unix.sh"
1055 (("/var/tmp") "/tmp"))
1057 ;; do not reset PATH
1058 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1060 (("action=/bin/") "action=")
1061 (("export PATH") ":"))
1065 (lambda* (#:key inputs outputs #:allow-other-keys)
1066 (let ((out (assoc-ref outputs "out"))
1067 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1068 (include (string-append (assoc-ref outputs "include")
1069 "/include/ncbi-tools++")))
1070 ;; The 'configure' script doesn't recognize things like
1071 ;; '--enable-fast-install'.
1072 (zero? (system* "./configure.orig"
1073 (string-append "--with-build-root=" (getcwd) "/build")
1074 (string-append "--prefix=" out)
1075 (string-append "--libdir=" lib)
1076 (string-append "--includedir=" include)
1077 (string-append "--with-bz2="
1078 (assoc-ref inputs "bzip2"))
1079 (string-append "--with-z="
1080 (assoc-ref inputs "zlib"))
1081 (string-append "--with-pcre="
1082 (assoc-ref inputs "pcre"))
1083 ;; Each library is built twice by default, once
1084 ;; with "-static" in its name, and again
1087 "--with-dll"))))))))
1088 (outputs '("out" ; 21 MB
1096 ("python" ,python-wrapper)))
1099 (home-page "http://blast.ncbi.nlm.nih.gov")
1100 (synopsis "Basic local alignment search tool")
1102 "BLAST is a popular method of performing a DNA or protein sequence
1103 similarity search, using heuristics to produce results quickly. It also
1104 calculates an “expect value” that estimates how many matches would have
1105 occurred at a given score by chance, which can aid a user in judging how much
1106 confidence to have in an alignment.")
1107 ;; Most of the sources are in the public domain, with the following
1110 ;; * ./c++/include/util/bitset/
1111 ;; * ./c++/src/html/ncbi_menu*.js
1113 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1115 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1117 ;; * ./c++/src/corelib/teamcity_*
1118 (license (list license:public-domain
1124 (define-public bless
1130 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1134 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1135 (modules '((guix build utils)))
1138 ;; Remove bundled boost, pigz, zlib, and .git directory
1139 ;; FIXME: also remove bundled sources for murmurhash3 and
1140 ;; kmc once packaged.
1141 (delete-file-recursively "boost")
1142 (delete-file-recursively "pigz")
1143 (delete-file-recursively "google-sparsehash")
1144 (delete-file-recursively "zlib")
1145 (delete-file-recursively ".git")
1147 (build-system gnu-build-system)
1149 '(#:tests? #f ;no "check" target
1151 (list (string-append "ZLIB="
1152 (assoc-ref %build-inputs "zlib")
1154 (string-append "LDFLAGS="
1155 (string-join '("-lboost_filesystem"
1162 (modify-phases %standard-phases
1163 (add-after 'unpack 'do-not-build-bundled-pigz
1164 (lambda* (#:key inputs outputs #:allow-other-keys)
1165 (substitute* "Makefile"
1166 (("cd pigz/pigz-2.3.3; make") ""))
1168 (add-after 'unpack 'patch-paths-to-executables
1169 (lambda* (#:key inputs outputs #:allow-other-keys)
1170 (substitute* "parse_args.cpp"
1171 (("kmc_binary = .*")
1172 (string-append "kmc_binary = \""
1173 (assoc-ref outputs "out")
1175 (("pigz_binary = .*")
1176 (string-append "pigz_binary = \""
1177 (assoc-ref inputs "pigz")
1181 (lambda* (#:key outputs #:allow-other-keys)
1182 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1183 (for-each (lambda (file)
1184 (install-file file bin))
1185 '("bless" "kmc/bin/kmc"))
1187 (delete 'configure))))
1191 `(("openmpi" ,openmpi)
1193 ("sparsehash" ,sparsehash)
1196 (supported-systems '("x86_64-linux"))
1197 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1198 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1200 "@dfn{Bloom-filter-based error correction solution for high-throughput
1201 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1202 correction tool for genomic reads produced by @dfn{Next-generation
1203 sequencing} (NGS). BLESS produces accurate correction results with much less
1204 memory compared with previous solutions and is also able to tolerate a higher
1205 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1206 errors at the end of reads.")
1207 (license license:gpl3+)))
1209 (define-public bowtie
1215 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1217 (file-name (string-append name "-" version ".tar.gz"))
1220 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1221 (modules '((guix build utils)))
1224 (substitute* "Makefile"
1225 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1226 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1227 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1229 (build-system gnu-build-system)
1232 ("perl-clone" ,perl-clone)
1233 ("perl-test-deep" ,perl-test-deep)
1234 ("perl-test-simple" ,perl-test-simple)
1235 ("python" ,python-2)
1242 (string-append "prefix=" (assoc-ref %outputs "out")))
1244 (modify-phases %standard-phases
1247 (lambda* (#:key outputs #:allow-other-keys)
1248 (zero? (system* "perl"
1249 "scripts/test/simple_tests.pl"
1250 "--bowtie2=./bowtie2"
1251 "--bowtie2-build=./bowtie2-build")))))))
1252 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1253 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1255 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1256 reads to long reference sequences. It is particularly good at aligning reads
1257 of about 50 up to 100s or 1,000s of characters, and particularly good at
1258 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1259 genome with an FM Index to keep its memory footprint small: for the human
1260 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1261 gapped, local, and paired-end alignment modes.")
1262 (supported-systems '("x86_64-linux"))
1263 (license license:gpl3+)))
1265 (define-public tophat
1272 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1276 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1277 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1278 (modules '((guix build utils)))
1281 ;; Remove bundled SeqAn and samtools
1282 (delete-file-recursively "src/SeqAn-1.3")
1283 (delete-file-recursively "src/samtools-0.1.18")
1285 (build-system gnu-build-system)
1287 '(#:parallel-build? #f ; not supported
1289 (modify-phases %standard-phases
1290 (add-after 'unpack 'use-system-samtools
1291 (lambda* (#:key inputs #:allow-other-keys)
1292 (substitute* "src/Makefile.in"
1293 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1294 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1295 (("SAMPROG = samtools_0\\.1\\.18") "")
1296 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1297 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1298 (substitute* '("src/common.cpp"
1300 (("samtools_0.1.18") (which "samtools")))
1301 (substitute* '("src/common.h"
1302 "src/bam2fastx.cpp")
1303 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1304 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1305 (substitute* '("src/bwt_map.h"
1307 "src/align_status.h")
1308 (("#include <bam.h>") "#include <samtools/bam.h>")
1309 (("#include <sam.h>") "#include <samtools/sam.h>"))
1314 ("samtools" ,samtools-0.1)
1315 ("ncurses" ,ncurses)
1316 ("python" ,python-2)
1320 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1321 (synopsis "Spliced read mapper for RNA-Seq data")
1323 "TopHat is a fast splice junction mapper for nucleotide sequence
1324 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1325 mammalian-sized genomes using the ultra high-throughput short read
1326 aligner Bowtie, and then analyzes the mapping results to identify
1327 splice junctions between exons.")
1328 ;; TopHat is released under the Boost Software License, Version 1.0
1329 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1330 (license license:boost1.0)))
1339 "https://github.com/lh3/bwa/releases/download/v"
1340 version "/bwa-" version ".tar.bz2"))
1343 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1344 (build-system gnu-build-system)
1346 '(#:tests? #f ;no "check" target
1348 (modify-phases %standard-phases
1350 (lambda* (#:key outputs #:allow-other-keys)
1351 (let ((bin (string-append
1352 (assoc-ref outputs "out") "/bin"))
1354 (assoc-ref outputs "out") "/share/doc/bwa"))
1356 (assoc-ref outputs "out") "/share/man/man1")))
1357 (install-file "bwa" bin)
1358 (install-file "README.md" doc)
1359 (install-file "bwa.1" man))
1361 ;; no "configure" script
1362 (delete 'configure))))
1363 (inputs `(("zlib" ,zlib)))
1364 ;; Non-portable SSE instructions are used so building fails on platforms
1365 ;; other than x86_64.
1366 (supported-systems '("x86_64-linux"))
1367 (home-page "http://bio-bwa.sourceforge.net/")
1368 (synopsis "Burrows-Wheeler sequence aligner")
1370 "BWA is a software package for mapping low-divergent sequences against a
1371 large reference genome, such as the human genome. It consists of three
1372 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1373 designed for Illumina sequence reads up to 100bp, while the rest two for
1374 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1375 features such as long-read support and split alignment, but BWA-MEM, which is
1376 the latest, is generally recommended for high-quality queries as it is faster
1377 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1378 70-100bp Illumina reads.")
1379 (license license:gpl3+)))
1381 (define-public bwa-pssm
1382 (package (inherit bwa)
1387 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1388 "archive/" version ".tar.gz"))
1389 (file-name (string-append name "-" version ".tar.gz"))
1392 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1393 (build-system gnu-build-system)
1398 (home-page "http://bwa-pssm.binf.ku.dk/")
1399 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1401 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1402 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1403 existing aligners it is fast and sensitive. Unlike most other aligners,
1404 however, it is also adaptible in the sense that one can direct the alignment
1405 based on known biases within the data set. It is coded as a modification of
1406 the original BWA alignment program and shares the genome index structure as
1407 well as many of the command line options.")
1408 (license license:gpl3+)))
1410 (define-public python2-bx-python
1412 (name "python2-bx-python")
1416 (uri (pypi-uri "bx-python" version))
1419 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1420 (modules '((guix build utils)))
1423 (substitute* "setup.py"
1424 ;; remove dependency on outdated "distribute" module
1425 (("^from distribute_setup import use_setuptools") "")
1426 (("^use_setuptools\\(\\)") ""))
1428 (build-system python-build-system)
1430 `(#:tests? #f ;tests fail because test data are not included
1431 #:python ,python-2))
1433 `(("python-numpy" ,python2-numpy)
1436 `(("python-nose" ,python2-nose)))
1437 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1438 (synopsis "Tools for manipulating biological data")
1440 "bx-python provides tools for manipulating biological data, particularly
1441 multiple sequence alignments.")
1442 (license license:expat)))
1444 (define-public python-pysam
1446 (name "python-pysam")
1450 ;; Test data is missing on PyPi.
1452 "https://github.com/pysam-developers/pysam/archive/v"
1454 (file-name (string-append name "-" version ".tar.gz"))
1457 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1458 (modules '((guix build utils)))
1460 ;; Drop bundled htslib. TODO: Also remove samtools
1462 (delete-file-recursively "htslib")
1464 (build-system python-build-system)
1466 `(#:modules ((ice-9 ftw)
1468 (guix build python-build-system)
1471 (modify-phases %standard-phases
1472 (add-before 'build 'set-flags
1473 (lambda* (#:key inputs #:allow-other-keys)
1474 (setenv "HTSLIB_MODE" "external")
1475 (setenv "HTSLIB_LIBRARY_DIR"
1476 (string-append (assoc-ref inputs "htslib") "/lib"))
1477 (setenv "HTSLIB_INCLUDE_DIR"
1478 (string-append (assoc-ref inputs "htslib") "/include"))
1479 (setenv "LDFLAGS" "-lncurses")
1480 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1483 (lambda* (#:key inputs outputs #:allow-other-keys)
1484 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1485 (setenv "PYTHONPATH"
1487 (getenv "PYTHONPATH")
1488 ":" (getcwd) "/build/"
1489 (car (scandir "build"
1490 (negate (cut string-prefix? "." <>))))))
1491 ;; Step out of source dir so python does not import from CWD.
1492 (with-directory-excursion "tests"
1493 (setenv "HOME" "/tmp")
1494 (and (zero? (system* "make" "-C" "pysam_data"))
1495 (zero? (system* "make" "-C" "cbcf_data"))
1496 ;; Running nosetests without explicitly asking for a
1497 ;; single process leads to a crash. Running with multiple
1498 ;; processes fails because the tests are not designed to
1501 ;; FIXME: tests keep timing out on some systems.
1502 ;; (zero? (system* "nosetests" "-v"
1503 ;; "--processes" "1"))
1506 `(("htslib" ,htslib))) ; Included from installed header files.
1508 `(("ncurses" ,ncurses)
1511 `(("python-cython" ,python-cython)
1512 ;; Dependencies below are are for tests only.
1513 ("samtools" ,samtools)
1514 ("bcftools" ,bcftools)
1515 ("python-nose" ,python-nose)))
1516 (home-page "https://github.com/pysam-developers/pysam")
1517 (synopsis "Python bindings to the SAMtools C API")
1519 "Pysam is a Python module for reading and manipulating files in the
1520 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1521 also includes an interface for tabix.")
1522 (license license:expat)))
1524 (define-public python2-pysam
1525 (package-with-python2 python-pysam))
1527 (define-public python-twobitreader
1529 (name "python-twobitreader")
1533 (uri (pypi-uri "twobitreader" version))
1536 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1537 (build-system python-build-system)
1539 '(;; Tests are not distributed in the PyPi release.
1540 ;; TODO Try building from the Git repo or asking the upstream maintainer
1541 ;; to distribute the tests on PyPi.
1544 `(("python-sphinx" ,python-sphinx)))
1545 (home-page "https://github.com/benjschiller/twobitreader")
1546 (synopsis "Python library for reading .2bit files")
1548 "twobitreader is a Python library for reading .2bit files as used by the
1549 UCSC genome browser.")
1550 (license license:artistic2.0)))
1552 (define-public python2-twobitreader
1553 (package-with-python2 python-twobitreader))
1555 (define-public python-plastid
1557 (name "python-plastid")
1561 (uri (pypi-uri "plastid" version))
1564 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1565 (build-system python-build-system)
1567 ;; Some test files are not included.
1570 `(("python-numpy" ,python-numpy)
1571 ("python-scipy" ,python-scipy)
1572 ("python-pandas" ,python-pandas)
1573 ("python-pysam" ,python-pysam)
1574 ("python-matplotlib" ,python-matplotlib)
1575 ("python-biopython" ,python-biopython)
1576 ("python-twobitreader" ,python-twobitreader)
1577 ("python-termcolor" ,python-termcolor)))
1579 `(("python-cython" ,python-cython)
1580 ("python-nose" ,python-nose)))
1581 (home-page "https://github.com/joshuagryphon/plastid")
1582 (synopsis "Python library for genomic analysis")
1584 "plastid is a Python library for genomic analysis – in particular,
1585 high-throughput sequencing data – with an emphasis on simplicity.")
1586 (license license:bsd-3)))
1588 (define-public python2-plastid
1589 (package-with-python2 python-plastid))
1591 (define-public cd-hit
1597 (uri (string-append "https://github.com/weizhongli/cdhit"
1598 "/releases/download/V" version
1600 "-2017-0621-source.tar.gz"))
1603 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1604 (build-system gnu-build-system)
1606 `(#:tests? #f ; there are no tests
1608 ;; Executables are copied directly to the PREFIX.
1609 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1611 (modify-phases %standard-phases
1612 ;; No "configure" script
1614 ;; Remove sources of non-determinism
1615 (add-after 'unpack 'be-timeless
1617 (substitute* "cdhit-utility.c++"
1618 ((" \\(built on \" __DATE__ \"\\)") ""))
1619 (substitute* "cdhit-common.c++"
1620 (("__DATE__") "\"0\"")
1621 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1623 ;; The "install" target does not create the target directory.
1624 (add-before 'install 'create-target-dir
1625 (lambda* (#:key outputs #:allow-other-keys)
1626 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1630 (home-page "http://weizhongli-lab.org/cd-hit/")
1631 (synopsis "Cluster and compare protein or nucleotide sequences")
1633 "CD-HIT is a program for clustering and comparing protein or nucleotide
1634 sequences. CD-HIT is designed to be fast and handle extremely large
1636 ;; The manual says: "It can be copied under the GNU General Public License
1637 ;; version 2 (GPLv2)."
1638 (license license:gpl2)))
1640 (define-public clipper
1647 "https://github.com/YeoLab/clipper/archive/"
1649 (file-name (string-append name "-" version ".tar.gz"))
1652 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1653 (modules '((guix build utils)))
1656 ;; remove unnecessary setup dependency
1657 (substitute* "setup.py"
1658 (("setup_requires = .*") ""))
1659 (for-each delete-file
1660 '("clipper/src/peaks.so"
1661 "clipper/src/readsToWiggle.so"))
1662 (delete-file-recursively "dist/")
1664 (build-system python-build-system)
1665 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1667 `(("htseq" ,python2-htseq)
1668 ("python-pybedtools" ,python2-pybedtools)
1669 ("python-cython" ,python2-cython)
1670 ("python-scikit-learn" ,python2-scikit-learn)
1671 ("python-matplotlib" ,python2-matplotlib)
1672 ("python-pandas" ,python2-pandas)
1673 ("python-pysam" ,python2-pysam)
1674 ("python-numpy" ,python2-numpy)
1675 ("python-scipy" ,python2-scipy)))
1677 `(("python-mock" ,python2-mock) ; for tests
1678 ("python-nose" ,python2-nose) ; for tests
1679 ("python-pytz" ,python2-pytz))) ; for tests
1680 (home-page "https://github.com/YeoLab/clipper")
1681 (synopsis "CLIP peak enrichment recognition")
1683 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1684 (license license:gpl2)))
1686 (define-public codingquarry
1688 (name "codingquarry")
1693 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1697 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1698 (build-system gnu-build-system)
1700 '(#:tests? #f ; no "check" target
1702 (modify-phases %standard-phases
1705 (lambda* (#:key outputs #:allow-other-keys)
1706 (let* ((out (assoc-ref outputs "out"))
1707 (bin (string-append out "/bin"))
1708 (doc (string-append out "/share/doc/codingquarry")))
1709 (install-file "INSTRUCTIONS.pdf" doc)
1710 (copy-recursively "QuarryFiles"
1711 (string-append out "/QuarryFiles"))
1712 (install-file "CodingQuarry" bin)
1713 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1714 (inputs `(("openmpi" ,openmpi)))
1715 (native-search-paths
1716 (list (search-path-specification
1717 (variable "QUARRY_PATH")
1718 (files '("QuarryFiles")))))
1719 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1720 (synopsis "Fungal gene predictor")
1721 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1722 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1723 (home-page "https://sourceforge.net/projects/codingquarry/")
1724 (license license:gpl3+)))
1726 (define-public couger
1733 "http://couger.oit.duke.edu/static/assets/COUGER"
1737 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1738 (build-system gnu-build-system)
1742 (modify-phases %standard-phases
1747 (lambda* (#:key outputs #:allow-other-keys)
1748 (let* ((out (assoc-ref outputs "out"))
1749 (bin (string-append out "/bin")))
1750 (copy-recursively "src" (string-append out "/src"))
1752 ;; Add "src" directory to module lookup path.
1753 (substitute* "couger"
1755 (string-append "import sys\nsys.path.append(\""
1756 out "\")\nfrom argparse")))
1757 (install-file "couger" bin))
1760 'install 'wrap-program
1761 (lambda* (#:key inputs outputs #:allow-other-keys)
1762 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1763 (let* ((out (assoc-ref outputs "out"))
1764 (path (getenv "PYTHONPATH")))
1765 (wrap-program (string-append out "/bin/couger")
1766 `("PYTHONPATH" ":" prefix (,path))))
1769 `(("python" ,python-2)
1770 ("python2-pillow" ,python2-pillow)
1771 ("python2-numpy" ,python2-numpy)
1772 ("python2-scipy" ,python2-scipy)
1773 ("python2-matplotlib" ,python2-matplotlib)))
1775 `(("r-minimal" ,r-minimal)
1777 ("randomjungle" ,randomjungle)))
1779 `(("unzip" ,unzip)))
1780 (home-page "http://couger.oit.duke.edu")
1781 (synopsis "Identify co-factors in sets of genomic regions")
1783 "COUGER can be applied to any two sets of genomic regions bound by
1784 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1785 putative co-factors that provide specificity to each TF. The framework
1786 determines the genomic targets uniquely-bound by each TF, and identifies a
1787 small set of co-factors that best explain the in vivo binding differences
1788 between the two TFs.
1790 COUGER uses classification algorithms (support vector machines and random
1791 forests) with features that reflect the DNA binding specificities of putative
1792 co-factors. The features are generated either from high-throughput TF-DNA
1793 binding data (from protein binding microarray experiments), or from large
1794 collections of DNA motifs.")
1795 (license license:gpl3+)))
1797 (define-public clustal-omega
1799 (name "clustal-omega")
1803 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1807 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1808 (build-system gnu-build-system)
1810 `(("argtable" ,argtable)))
1811 (home-page "http://www.clustal.org/omega/")
1812 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1814 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1815 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1816 of handling data-sets of hundreds of thousands of sequences in reasonable
1818 (license license:gpl2+)))
1820 (define-public crossmap
1826 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1830 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1831 ;; This patch has been sent upstream already and is available
1832 ;; for download from Sourceforge, but it has not been merged.
1833 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1834 (modules '((guix build utils)))
1836 ;; remove bundled copy of pysam
1837 (delete-file-recursively "lib/pysam")
1839 (build-system python-build-system)
1841 `(#:python ,python-2
1843 (modify-phases %standard-phases
1844 (add-after 'unpack 'set-env
1845 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1847 `(("python-numpy" ,python2-numpy)
1848 ("python-pysam" ,python2-pysam)
1851 `(("python-cython" ,python2-cython)
1852 ("python-nose" ,python2-nose)))
1853 (home-page "http://crossmap.sourceforge.net/")
1854 (synopsis "Convert genome coordinates between assemblies")
1856 "CrossMap is a program for conversion of genome coordinates or annotation
1857 files between different genome assemblies. It supports most commonly used
1858 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1859 (license license:gpl2+)))
1861 (define-public cutadapt
1868 (url "https://github.com/marcelm/cutadapt.git")
1869 (commit (string-append "v" version))))
1870 (file-name (string-append name "-" version "-checkout"))
1873 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1874 (build-system python-build-system)
1876 `(("python-xopen" ,python-xopen)))
1878 `(("python-cython" ,python-cython)
1879 ("python-pytest" ,python-pytest)))
1880 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1881 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1883 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1884 other types of unwanted sequence from high-throughput sequencing reads.")
1885 (license license:expat)))
1887 (define-public libbigwig
1894 (url "https://github.com/dpryan79/libBigWig.git")
1896 (file-name (string-append name "-" version "-checkout"))
1899 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
1900 (build-system gnu-build-system)
1902 `(#:test-target "test"
1903 #:tests? #f ; tests require access to the web
1906 (string-append "prefix=" (assoc-ref %outputs "out")))
1908 (modify-phases %standard-phases
1909 (delete 'configure))))
1914 `(("doxygen" ,doxygen)
1916 ("python" ,python-2)))
1917 (home-page "https://github.com/dpryan79/libBigWig")
1918 (synopsis "C library for handling bigWig files")
1920 "This package provides a C library for parsing local and remote BigWig
1922 (license license:expat)))
1924 (define-public python-pybigwig
1926 (name "python-pybigwig")
1930 (uri (pypi-uri "pyBigWig" version))
1933 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
1934 (modules '((guix build utils)))
1937 ;; Delete bundled libBigWig sources
1938 (delete-file-recursively "libBigWig")
1940 (build-system python-build-system)
1943 (modify-phases %standard-phases
1944 (add-after 'unpack 'link-with-libBigWig
1945 (lambda* (#:key inputs #:allow-other-keys)
1946 (substitute* "setup.py"
1947 (("libs=\\[") "libs=[\"BigWig\", "))
1950 `(("python-numpy" ,python-numpy)))
1952 `(("libbigwig" ,libbigwig)
1955 (home-page "https://github.com/dpryan79/pyBigWig")
1956 (synopsis "Access bigWig files in Python using libBigWig")
1958 "This package provides Python bindings to the libBigWig library for
1959 accessing bigWig files.")
1960 (license license:expat)))
1962 (define-public python2-pybigwig
1963 (package-with-python2 python-pybigwig))
1965 (define-public python-dendropy
1967 (name "python-dendropy")
1972 ;; Source from GitHub so that tests are included.
1974 (string-append "https://github.com/jeetsukumaran/DendroPy/archive/v"
1976 (file-name (string-append name "-" version ".tar.gz"))
1979 "0v2fccny5xjaah546bsch1mw4kh61qq5frz2ibllxs9mp6ih9bsn"))))
1980 (build-system python-build-system)
1981 (home-page "http://packages.python.org/DendroPy/")
1982 (synopsis "Library for phylogenetics and phylogenetic computing")
1984 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1985 writing, simulation, processing and manipulation of phylogenetic
1986 trees (phylogenies) and characters.")
1987 (license license:bsd-3)))
1989 (define-public python2-dendropy
1990 (package-with-python2 python-dendropy))
1992 (define-public python-py2bit
1994 (name "python-py2bit")
1999 (uri (pypi-uri "py2bit" version))
2002 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2003 (build-system python-build-system)
2004 (home-page "https://github.com/dpryan79/py2bit")
2005 (synopsis "Access 2bit files using lib2bit")
2007 "This package provides Python bindings for lib2bit to access 2bit files
2009 (license license:expat)))
2011 (define-public deeptools
2017 (uri (string-append "https://github.com/deeptools/deepTools/"
2018 "archive/" version ".tar.gz"))
2019 (file-name (string-append name "-" version ".tar.gz"))
2022 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2023 (build-system python-build-system)
2025 `(("python-scipy" ,python-scipy)
2026 ("python-numpy" ,python-numpy)
2027 ("python-numpydoc" ,python-numpydoc)
2028 ("python-matplotlib" ,python-matplotlib)
2029 ("python-pysam" ,python-pysam)
2030 ("python-py2bit" ,python-py2bit)
2031 ("python-pybigwig" ,python-pybigwig)))
2033 `(("python-mock" ,python-mock) ;for tests
2034 ("python-nose" ,python-nose) ;for tests
2035 ("python-pytz" ,python-pytz))) ;for tests
2036 (home-page "https://github.com/deeptools/deepTools")
2037 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2039 "DeepTools addresses the challenge of handling the large amounts of data
2040 that are now routinely generated from DNA sequencing centers. To do so,
2041 deepTools contains useful modules to process the mapped reads data to create
2042 coverage files in standard bedGraph and bigWig file formats. By doing so,
2043 deepTools allows the creation of normalized coverage files or the comparison
2044 between two files (for example, treatment and control). Finally, using such
2045 normalized and standardized files, multiple visualizations can be created to
2046 identify enrichments with functional annotations of the genome.")
2047 (license license:gpl3+)))
2049 (define-public delly
2056 "https://github.com/tobiasrausch/delly/archive/v"
2058 (file-name (string-append name "-" version ".tar.gz"))
2060 (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj"))
2061 (patches (search-patches "delly-use-system-libraries.patch"))))
2062 (build-system gnu-build-system)
2064 `(#:tests? #f ; There are no tests to run.
2065 #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time.
2067 (modify-phases %standard-phases
2068 (delete 'configure) ; There is no configure phase.
2071 (let ((bin (string-append (assoc-ref %outputs "out") "/bin"))
2072 (templates (string-append (assoc-ref %outputs "out")
2073 "/share/delly/templates")))
2076 (copy-recursively "excludeTemplates" templates)
2077 (install-file "src/cov" bin)
2078 (install-file "src/delly" bin)
2079 (install-file "src/dpe" bin)))))))
2081 `(("python" ,python-2)))
2087 (home-page "https://github.com/tobiasrausch/delly")
2088 (synopsis "Integrated structural variant prediction method")
2089 (description "Delly is an integrated structural variant prediction method
2090 that can discover and genotype deletions, tandem duplications, inversions and
2091 translocations at single-nucleotide resolution in short-read massively parallel
2092 sequencing data. It uses paired-ends and split-reads to sensitively and
2093 accurately delineate genomic rearrangements throughout the genome.")
2094 (license license:gpl3+)))
2096 (define-public diamond
2103 "https://github.com/bbuchfink/diamond/archive/v"
2105 (file-name (string-append name "-" version ".tar.gz"))
2108 "0adp87r9ak63frdrdmrdfhsn6g0jnnyq1lr2wibvqbxcl37iir9m"))))
2109 (build-system cmake-build-system)
2111 '(#:tests? #f ; no "check" target
2113 (modify-phases %standard-phases
2114 (add-after 'unpack 'remove-native-compilation
2116 (substitute* "CMakeLists.txt" (("-march=native") ""))
2120 (home-page "https://github.com/bbuchfink/diamond")
2121 (synopsis "Accelerated BLAST compatible local sequence aligner")
2123 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2124 translated DNA query sequences against a protein reference database (BLASTP
2125 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2126 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2127 data and settings.")
2128 (license license:agpl3+)))
2130 (define-public discrover
2137 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2139 (file-name (string-append name "-" version ".tar.gz"))
2142 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2143 (build-system cmake-build-system)
2145 `(#:tests? #f ; there are no tests
2147 (modify-phases %standard-phases
2148 (add-after 'unpack 'add-missing-includes
2150 (substitute* "src/executioninformation.hpp"
2151 (("#define EXECUTIONINFORMATION_HPP" line)
2152 (string-append line "\n#include <random>")))
2153 (substitute* "src/plasma/fasta.hpp"
2154 (("#define FASTA_HPP" line)
2155 (string-append line "\n#include <random>")))
2161 `(("texlive" ,texlive)
2162 ("imagemagick" ,imagemagick)))
2163 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2164 (synopsis "Discover discriminative nucleotide sequence motifs")
2165 (description "Discrover is a motif discovery method to find binding sites
2166 of nucleic acid binding proteins.")
2167 (license license:gpl3+)))
2169 (define-public eigensoft
2170 (let ((revision "1")
2171 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2174 (version (string-append "6.1.2-"
2176 (string-take commit 9)))
2181 (url "https://github.com/DReichLab/EIG.git")
2183 (file-name (string-append "eigensoft-" commit "-checkout"))
2186 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2187 (modules '((guix build utils)))
2188 ;; Remove pre-built binaries.
2190 (delete-file-recursively "bin")
2193 (build-system gnu-build-system)
2195 `(#:tests? #f ; There are no tests.
2196 #:make-flags '("CC=gcc")
2198 (modify-phases %standard-phases
2199 ;; There is no configure phase, but the Makefile is in a
2204 ;; The link flags are incomplete.
2205 (substitute* "Makefile"
2206 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2208 ;; The provided install target only copies executables to
2209 ;; the "bin" directory in the build root.
2210 (add-after 'install 'actually-install
2211 (lambda* (#:key outputs #:allow-other-keys)
2212 (let* ((out (assoc-ref outputs "out"))
2213 (bin (string-append out "/bin")))
2214 (for-each (lambda (file)
2215 (install-file file bin))
2216 (find-files "../bin" ".*"))
2221 ("openblas" ,openblas)
2223 ("gfortran" ,gfortran "lib")))
2224 (home-page "https://github.com/DReichLab/EIG")
2225 (synopsis "Tools for population genetics")
2226 (description "The EIGENSOFT package provides tools for population
2227 genetics and stratification correction. EIGENSOFT implements methods commonly
2228 used in population genetics analyses such as PCA, computation of Tracy-Widom
2229 statistics, and finding related individuals in structured populations. It
2230 comes with a built-in plotting script and supports multiple file formats and
2231 quantitative phenotypes.")
2232 ;; The license of the eigensoft tools is Expat, but since it's
2233 ;; linking with the GNU Scientific Library (GSL) the effective
2234 ;; license is the GPL.
2235 (license license:gpl3+))))
2237 (define-public edirect
2243 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2244 "versions/2016-05-03/edirect.tar.gz"))
2247 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2248 (build-system perl-build-system)
2250 `(#:tests? #f ;no "check" target
2252 (modify-phases %standard-phases
2256 (lambda* (#:key outputs #:allow-other-keys)
2257 (let ((target (string-append (assoc-ref outputs "out")
2260 (install-file "edirect.pl" target)
2263 'install 'wrap-program
2264 (lambda* (#:key inputs outputs #:allow-other-keys)
2265 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2266 (let* ((out (assoc-ref outputs "out"))
2267 (path (getenv "PERL5LIB")))
2268 (wrap-program (string-append out "/bin/edirect.pl")
2269 `("PERL5LIB" ":" prefix (,path)))))))))
2271 `(("perl-html-parser" ,perl-html-parser)
2272 ("perl-encode-locale" ,perl-encode-locale)
2273 ("perl-file-listing" ,perl-file-listing)
2274 ("perl-html-tagset" ,perl-html-tagset)
2275 ("perl-html-tree" ,perl-html-tree)
2276 ("perl-http-cookies" ,perl-http-cookies)
2277 ("perl-http-date" ,perl-http-date)
2278 ("perl-http-message" ,perl-http-message)
2279 ("perl-http-negotiate" ,perl-http-negotiate)
2280 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2281 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2282 ("perl-net-http" ,perl-net-http)
2283 ("perl-uri" ,perl-uri)
2284 ("perl-www-robotrules" ,perl-www-robotrules)
2286 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2287 (synopsis "Tools for accessing the NCBI's set of databases")
2289 "Entrez Direct (EDirect) is a method for accessing the National Center
2290 for Biotechnology Information's (NCBI) set of interconnected
2291 databases (publication, sequence, structure, gene, variation, expression,
2292 etc.) from a terminal. Functions take search terms from command-line
2293 arguments. Individual operations are combined to build multi-step queries.
2294 Record retrieval and formatting normally complete the process.
2296 EDirect also provides an argument-driven function that simplifies the
2297 extraction of data from document summaries or other results that are returned
2298 in structured XML format. This can eliminate the need for writing custom
2299 software to answer ad hoc questions.")
2300 (license license:public-domain)))
2302 (define-public exonerate
2311 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2312 "exonerate-" version ".tar.gz"))
2315 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2316 (build-system gnu-build-system)
2318 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2320 `(("pkg-config" ,pkg-config)))
2324 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2325 (synopsis "Generic tool for biological sequence alignment")
2327 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2328 the alignment of sequences using a many alignment models, either exhaustive
2329 dynamic programming or a variety of heuristics.")
2330 (license license:gpl3)))
2332 (define-public express
2340 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2341 version "/express-" version "-src.tgz"))
2344 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2345 (build-system cmake-build-system)
2347 `(#:tests? #f ;no "check" target
2349 (modify-phases %standard-phases
2350 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2351 (lambda* (#:key inputs #:allow-other-keys)
2352 (substitute* "CMakeLists.txt"
2353 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2354 "set(Boost_USE_STATIC_LIBS OFF)")
2355 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2356 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2357 (substitute* "src/CMakeLists.txt"
2358 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2359 (string-append (assoc-ref inputs "bamtools") "/lib"))
2360 (("libprotobuf.a") "libprotobuf.so"))
2364 ("bamtools" ,bamtools)
2365 ("protobuf" ,protobuf)
2367 (home-page "http://bio.math.berkeley.edu/eXpress")
2368 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2370 "eXpress is a streaming tool for quantifying the abundances of a set of
2371 target sequences from sampled subsequences. Example applications include
2372 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2373 analysis (from RNA-Seq), transcription factor binding quantification in
2374 ChIP-Seq, and analysis of metagenomic data.")
2375 (license license:artistic2.0)))
2377 (define-public express-beta-diversity
2379 (name "express-beta-diversity")
2385 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2387 (file-name (string-append name "-" version ".tar.gz"))
2390 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2391 (build-system gnu-build-system)
2394 (modify-phases %standard-phases
2396 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2398 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2400 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2402 (lambda* (#:key outputs #:allow-other-keys)
2403 (let ((bin (string-append (assoc-ref outputs "out")
2406 (install-file "scripts/convertToEBD.py" bin)
2407 (install-file "bin/ExpressBetaDiversity" bin)
2410 `(("python" ,python-2)))
2411 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2412 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2414 "Express Beta Diversity (EBD) calculates ecological beta diversity
2415 (dissimilarity) measures between biological communities. EBD implements a
2416 variety of diversity measures including those that make use of phylogenetic
2417 similarity of community members.")
2418 (license license:gpl3+)))
2420 (define-public fasttree
2427 "http://www.microbesonline.org/fasttree/FastTree-"
2431 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2432 (build-system gnu-build-system)
2434 `(#:tests? #f ; no "check" target
2436 (modify-phases %standard-phases
2440 (lambda* (#:key source #:allow-other-keys)
2441 (and (zero? (system* "gcc"
2443 "-finline-functions"
2450 (zero? (system* "gcc"
2454 "-finline-functions"
2462 (lambda* (#:key outputs #:allow-other-keys)
2463 (let ((bin (string-append (assoc-ref outputs "out")
2466 (install-file "FastTree" bin)
2467 (install-file "FastTreeMP" bin)
2469 (home-page "http://www.microbesonline.org/fasttree")
2470 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2472 "FastTree can handle alignments with up to a million of sequences in a
2473 reasonable amount of time and memory. For large alignments, FastTree is
2474 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2475 (license license:gpl2+)))
2477 (define-public fastx-toolkit
2479 (name "fastx-toolkit")
2485 "https://github.com/agordon/fastx_toolkit/releases/download/"
2486 version "/fastx_toolkit-" version ".tar.bz2"))
2489 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2490 (build-system gnu-build-system)
2492 `(("libgtextutils" ,libgtextutils)))
2494 `(("pkg-config" ,pkg-config)))
2495 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2496 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2498 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2499 FASTA/FASTQ files preprocessing.
2501 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2502 containing multiple short-reads sequences. The main processing of such
2503 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2504 is sometimes more productive to preprocess the files before mapping the
2505 sequences to the genome---manipulating the sequences to produce better mapping
2506 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2507 (license license:agpl3+)))
2509 (define-public flexbar
2516 (string-append "mirror://sourceforge/flexbar/"
2517 version "/flexbar_v" version "_src.tgz"))
2520 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2521 (build-system cmake-build-system)
2523 `(#:configure-flags (list
2524 (string-append "-DFLEXBAR_BINARY_DIR="
2525 (assoc-ref %outputs "out")
2528 (modify-phases %standard-phases
2530 (lambda* (#:key outputs #:allow-other-keys)
2531 (setenv "PATH" (string-append
2532 (assoc-ref outputs "out") "/bin:"
2534 (chdir "../flexbar_v2.5_src/test")
2535 (zero? (system* "bash" "flexbar_validate.sh"))))
2536 (delete 'install))))
2541 `(("pkg-config" ,pkg-config)
2543 (home-page "http://flexbar.sourceforge.net")
2544 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2546 "Flexbar preprocesses high-throughput nucleotide sequencing data
2547 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2548 Moreover, trimming and filtering features are provided. Flexbar increases
2549 read mapping rates and improves genome and transcriptome assemblies. It
2550 supports next-generation sequencing data in fasta/q and csfasta/q format from
2551 Illumina, Roche 454, and the SOLiD platform.")
2552 (license license:gpl3)))
2554 (define-public fraggenescan
2556 (name "fraggenescan")
2562 (string-append "mirror://sourceforge/fraggenescan/"
2563 "FragGeneScan" version ".tar.gz"))
2565 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2566 (build-system gnu-build-system)
2569 (modify-phases %standard-phases
2571 (add-before 'build 'patch-paths
2572 (lambda* (#:key outputs #:allow-other-keys)
2573 (let* ((out (string-append (assoc-ref outputs "out")))
2574 (share (string-append out "/share/fraggenescan/")))
2575 (substitute* "run_FragGeneScan.pl"
2577 (string-append "system(\"" (which "rm")))
2579 (string-append "system(\"" (which "mv")))
2580 (("\\\"awk") (string-append "\"" (which "awk")))
2581 ;; This script and other programs expect the training files
2582 ;; to be in the non-standard location bin/train/XXX. Change
2583 ;; this to be share/fraggenescan/train/XXX instead.
2584 (("^\\$train.file = \\$dir.*")
2585 (string-append "$train_file = \""
2587 "train/\".$FGS_train_file;")))
2588 (substitute* "run_hmm.c"
2589 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2590 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2593 (lambda _ (and (zero? (system* "make" "clean"))
2594 (zero? (system* "make" "fgs")))))
2596 (lambda* (#:key outputs #:allow-other-keys)
2597 (let* ((out (string-append (assoc-ref outputs "out")))
2598 (bin (string-append out "/bin/"))
2599 (share (string-append out "/share/fraggenescan/train")))
2600 (install-file "run_FragGeneScan.pl" bin)
2601 (install-file "FragGeneScan" bin)
2602 (copy-recursively "train" share))))
2604 (add-after 'install 'post-install-check
2605 ;; In lieu of 'make check', run one of the examples and check the
2606 ;; output files gets created.
2607 (lambda* (#:key outputs #:allow-other-keys)
2608 (let* ((out (string-append (assoc-ref outputs "out")))
2609 (bin (string-append out "/bin/"))
2610 (frag (string-append bin "run_FragGeneScan.pl")))
2611 (and (zero? (system* frag ; Test complete genome.
2612 "-genome=./example/NC_000913.fna"
2616 (file-exists? "test2.faa")
2617 (file-exists? "test2.ffn")
2618 (file-exists? "test2.gff")
2619 (file-exists? "test2.out")
2620 (zero? (system* ; Test incomplete sequences.
2622 "-genome=./example/NC_000913-fgs.ffn"
2625 "-train=454_30")))))))))
2628 ("python" ,python-2))) ;not compatible with python 3.
2629 (home-page "https://sourceforge.net/projects/fraggenescan/")
2630 (synopsis "Finds potentially fragmented genes in short reads")
2632 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2633 short and error-prone DNA sequencing reads. It can also be applied to predict
2634 genes in incomplete assemblies or complete genomes.")
2635 ;; GPL3+ according to private correspondense with the authors.
2636 (license license:gpl3+)))
2638 (define-public fxtract
2639 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2647 "https://github.com/ctSkennerton/fxtract/archive/"
2649 (file-name (string-append "ctstennerton-util-"
2650 (string-take util-commit 7)
2654 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2655 (build-system gnu-build-system)
2657 `(#:make-flags (list
2658 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2660 #:test-target "fxtract_test"
2662 (modify-phases %standard-phases
2664 (add-before 'build 'copy-util
2665 (lambda* (#:key inputs #:allow-other-keys)
2667 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2669 ;; Do not use make install as this requires additional dependencies.
2671 (lambda* (#:key outputs #:allow-other-keys)
2672 (let* ((out (assoc-ref outputs "out"))
2673 (bin (string-append out"/bin")))
2674 (install-file "fxtract" bin)
2680 ;; ctskennerton-util is licensed under GPL2.
2681 `(("ctskennerton-util"
2685 (url "https://github.com/ctSkennerton/util.git")
2686 (commit util-commit)))
2687 (file-name (string-append
2688 "ctstennerton-util-" util-commit "-checkout"))
2691 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2692 (home-page "https://github.com/ctSkennerton/fxtract")
2693 (synopsis "Extract sequences from FASTA and FASTQ files")
2695 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2696 or FASTQ) file given a subsequence. It uses a simple substring search for
2697 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2698 lookups or multi-pattern searching as required. By default fxtract looks in
2699 the sequence of each record but can also be told to look in the header,
2700 comment or quality sections.")
2701 ;; 'util' requires SSE instructions.
2702 (supported-systems '("x86_64-linux"))
2703 (license license:expat))))
2705 (define-public gemma
2711 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2713 (file-name (string-append name "-" version ".tar.gz"))
2716 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2717 (patches (search-patches "gemma-intel-compat.patch"))))
2722 (build-system gnu-build-system)
2725 '(,@(match (%current-system)
2727 '("FORCE_DYNAMIC=1"))
2729 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2731 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2733 (modify-phases %standard-phases
2735 (add-before 'build 'bin-mkdir
2740 (lambda* (#:key outputs #:allow-other-keys)
2741 (let ((out (assoc-ref outputs "out")))
2742 (install-file "bin/gemma"
2746 #:tests? #f)) ; no tests included yet
2747 (home-page "https://github.com/xiangzhou/GEMMA")
2748 (synopsis "Tool for genome-wide efficient mixed model association")
2750 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2751 standard linear mixed model resolver with application in genome-wide
2752 association studies (GWAS).")
2753 (license license:gpl3)))
2762 "https://github.com/nboley/grit/archive/"
2764 (file-name (string-append name "-" version ".tar.gz"))
2767 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2768 (build-system python-build-system)
2770 `(#:python ,python-2
2772 (modify-phases %standard-phases
2773 (add-after 'unpack 'generate-from-cython-sources
2774 (lambda* (#:key inputs outputs #:allow-other-keys)
2775 ;; Delete these C files to force fresh generation from pyx sources.
2776 (delete-file "grit/sparsify_support_fns.c")
2777 (delete-file "grit/call_peaks_support_fns.c")
2778 (substitute* "setup.py"
2779 (("Cython.Setup") "Cython.Build")
2780 ;; Add numpy include path to fix compilation
2782 (string-append "pyx\", ], include_dirs = ['"
2783 (assoc-ref inputs "python-numpy")
2784 "/lib/python2.7/site-packages/numpy/core/include/"
2788 `(("python-scipy" ,python2-scipy)
2789 ("python-numpy" ,python2-numpy)
2790 ("python-pysam" ,python2-pysam)
2791 ("python-networkx" ,python2-networkx)))
2793 `(("python-cython" ,python2-cython)))
2794 (home-page "http://grit-bio.org")
2795 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2797 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2798 full length transcript models. When none of these data sources are available,
2799 GRIT can be run by providing a candidate set of TES or TSS sites. In
2800 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2801 also be run in quantification mode, where it uses a provided GTF file and just
2802 estimates transcript expression.")
2803 (license license:gpl3+)))
2805 (define-public hisat
2812 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2813 version "-beta-source.zip"))
2816 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2817 (build-system gnu-build-system)
2819 `(#:tests? #f ;no check target
2820 #:make-flags '("allall"
2821 ;; Disable unsupported `popcnt' instructions on
2822 ;; architectures other than x86_64
2823 ,@(if (string-prefix? "x86_64"
2824 (or (%current-target-system)
2827 '("POPCNT_CAPABILITY=0")))
2829 (modify-phases %standard-phases
2830 (add-after 'unpack 'patch-sources
2832 ;; XXX Cannot use snippet because zip files are not supported
2833 (substitute* "Makefile"
2834 (("^CC = .*$") "CC = gcc")
2835 (("^CPP = .*$") "CPP = g++")
2836 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2837 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2838 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2839 (substitute* '("hisat-build" "hisat-inspect")
2840 (("/usr/bin/env") (which "env")))
2843 (lambda* (#:key outputs #:allow-other-keys)
2844 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2845 (for-each (lambda (file)
2846 (install-file file bin))
2849 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2851 (delete 'configure))))
2853 `(("unzip" ,unzip)))
2858 ;; Non-portable SSE instructions are used so building fails on platforms
2859 ;; other than x86_64.
2860 (supported-systems '("x86_64-linux"))
2861 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2862 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2864 "HISAT is a fast and sensitive spliced alignment program for mapping
2865 RNA-seq reads. In addition to one global FM index that represents a whole
2866 genome, HISAT uses a large set of small FM indexes that collectively cover the
2867 whole genome. These small indexes (called local indexes) combined with
2868 several alignment strategies enable effective alignment of RNA-seq reads, in
2869 particular, reads spanning multiple exons.")
2870 (license license:gpl3+)))
2872 (define-public hisat2
2879 ;; FIXME: a better source URL is
2880 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2881 ;; "/downloads/hisat2-" version "-source.zip")
2882 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2883 ;; but it is currently unavailable.
2884 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2885 (file-name (string-append name "-" version ".tar.gz"))
2888 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2889 (build-system gnu-build-system)
2891 `(#:tests? #f ; no check target
2892 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2893 #:modules ((guix build gnu-build-system)
2897 (modify-phases %standard-phases
2898 (add-after 'unpack 'make-deterministic
2900 (substitute* "Makefile"
2905 (lambda* (#:key outputs #:allow-other-keys)
2906 (let* ((out (assoc-ref outputs "out"))
2907 (bin (string-append out "/bin/"))
2908 (doc (string-append out "/share/doc/hisat2/")))
2910 (cut install-file <> bin)
2912 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2914 (install-file "doc/manual.inc.html" doc))
2917 `(("unzip" ,unzip) ; needed for archive from ftp
2919 ("pandoc" ,ghc-pandoc))) ; for documentation
2920 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2921 (synopsis "Graph-based alignment of genomic sequencing reads")
2922 (description "HISAT2 is a fast and sensitive alignment program for mapping
2923 next-generation sequencing reads (both DNA and RNA) to a population of human
2924 genomes (as well as to a single reference genome). In addition to using one
2925 global @dfn{graph FM} (GFM) index that represents a population of human
2926 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2927 the whole genome. These small indexes, combined with several alignment
2928 strategies, enable rapid and accurate alignment of sequencing reads. This new
2929 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2930 ;; HISAT2 contains files from Bowtie2, which is released under
2931 ;; GPLv2 or later. The HISAT2 source files are released under
2933 (license license:gpl3+)))
2935 (define-public hmmer
2943 "http://eddylab.org/software/hmmer"
2944 (version-major version) "/"
2945 version "/hmmer-" version ".tar.gz"))
2948 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2949 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2950 (build-system gnu-build-system)
2951 (native-inputs `(("perl" ,perl)))
2952 (home-page "http://hmmer.org/")
2953 (synopsis "Biosequence analysis using profile hidden Markov models")
2955 "HMMER is used for searching sequence databases for homologs of protein
2956 sequences, and for making protein sequence alignments. It implements methods
2957 using probabilistic models called profile hidden Markov models (profile
2959 (license (list license:gpl3+
2960 ;; The bundled library 'easel' is distributed
2961 ;; under The Janelia Farm Software License.
2962 (license:non-copyleft
2963 "file://easel/LICENSE"
2964 "See easel/LICENSE in the distribution.")))))
2966 (define-public htseq
2972 (uri (pypi-uri "HTSeq" version))
2975 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2976 (build-system python-build-system)
2978 `(("python-cython" ,python-cython)))
2979 ;; Numpy needs to be propagated when htseq is used as a Python library.
2981 `(("python-numpy" ,python-numpy)))
2983 `(("python-pysam" ,python-pysam)
2984 ("python-matplotlib" ,python-matplotlib)))
2985 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2986 (synopsis "Analysing high-throughput sequencing data with Python")
2988 "HTSeq is a Python package that provides infrastructure to process data
2989 from high-throughput sequencing assays.")
2990 (license license:gpl3+)))
2992 (define-public python2-htseq
2993 (package-with-python2 htseq))
2995 (define-public java-htsjdk
2997 (name "java-htsjdk")
2998 (version "2.3.0") ; last version without build dependency on gradle
3002 "https://github.com/samtools/htsjdk/archive/"
3004 (file-name (string-append name "-" version ".tar.gz"))
3007 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
3008 (modules '((guix build utils)))
3010 ;; Delete pre-built binaries
3012 (delete-file-recursively "lib")
3015 (build-system ant-build-system)
3017 `(#:tests? #f ; test require Internet access
3020 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3021 "/share/java/htsjdk/"))
3022 #:build-target "all"
3024 (modify-phases %standard-phases
3025 ;; The build phase also installs the jars
3026 (delete 'install))))
3028 `(("java-ngs" ,java-ngs)
3029 ("java-snappy-1" ,java-snappy-1)
3030 ("java-commons-compress" ,java-commons-compress)
3031 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3032 ("java-commons-jexl-2" ,java-commons-jexl-2)
3033 ("java-xz" ,java-xz)))
3035 `(("java-testng" ,java-testng)))
3036 (home-page "http://samtools.github.io/htsjdk/")
3037 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3039 "HTSJDK is an implementation of a unified Java library for accessing
3040 common file formats, such as SAM and VCF, used for high-throughput
3041 sequencing (HTS) data. There are also an number of useful utilities for
3042 manipulating HTS data.")
3043 (license license:expat)))
3045 (define-public java-htsjdk-latest
3047 (name "java-htsjdk")
3052 (url "https://github.com/samtools/htsjdk.git")
3054 (file-name (string-append name "-" version "-checkout"))
3057 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3058 (build-system ant-build-system)
3060 `(#:tests? #f ; test require Scala
3062 #:jar-name "htsjdk.jar"
3064 (modify-phases %standard-phases
3065 (add-after 'unpack 'remove-useless-build.xml
3066 (lambda _ (delete-file "build.xml") #t))
3067 ;; The tests require the scalatest package.
3068 (add-after 'unpack 'remove-tests
3069 (lambda _ (delete-file-recursively "src/test") #t)))))
3071 `(("java-ngs" ,java-ngs)
3072 ("java-snappy-1" ,java-snappy-1)
3073 ("java-commons-compress" ,java-commons-compress)
3074 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3075 ("java-commons-jexl-2" ,java-commons-jexl-2)
3076 ("java-xz" ,java-xz)))
3078 `(("java-junit" ,java-junit)))
3079 (home-page "http://samtools.github.io/htsjdk/")
3080 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3082 "HTSJDK is an implementation of a unified Java library for accessing
3083 common file formats, such as SAM and VCF, used for high-throughput
3084 sequencing (HTS) data. There are also an number of useful utilities for
3085 manipulating HTS data.")
3086 (license license:expat)))
3088 ;; This is needed for picard 2.10.3
3089 (define-public java-htsjdk-2.10.1
3090 (package (inherit java-htsjdk-latest)
3091 (name "java-htsjdk")
3096 (url "https://github.com/samtools/htsjdk.git")
3098 (file-name (string-append name "-" version "-checkout"))
3101 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3102 (build-system ant-build-system)
3104 `(#:tests? #f ; tests require Scala
3106 #:jar-name "htsjdk.jar"
3108 (modify-phases %standard-phases
3109 (add-after 'unpack 'remove-useless-build.xml
3110 (lambda _ (delete-file "build.xml") #t))
3111 ;; The tests require the scalatest package.
3112 (add-after 'unpack 'remove-tests
3113 (lambda _ (delete-file-recursively "src/test") #t)))))))
3115 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3116 ;; recent version of java-htsjdk, which depends on gradle.
3117 (define-public java-picard
3119 (name "java-picard")
3124 (url "https://github.com/broadinstitute/picard.git")
3126 (file-name (string-append "java-picard-" version "-checkout"))
3129 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3130 (modules '((guix build utils)))
3133 ;; Delete pre-built binaries.
3134 (delete-file-recursively "lib")
3136 (substitute* "build.xml"
3137 ;; Remove build-time dependency on git.
3138 (("failifexecutionfails=\"true\"")
3139 "failifexecutionfails=\"false\"")
3141 (("depends=\"compile-htsjdk, ")
3143 (("depends=\"compile-htsjdk-tests, ")
3145 ;; Build picard-lib.jar before building picard.jar
3146 (("name=\"picard-jar\" depends=\"" line)
3147 (string-append line "picard-lib-jar, ")))
3149 (build-system ant-build-system)
3151 `(#:build-target "picard-jar"
3152 #:test-target "test"
3153 ;; Tests require jacoco:coverage.
3156 (list (string-append "-Dhtsjdk_lib_dir="
3157 (assoc-ref %build-inputs "java-htsjdk")
3158 "/share/java/htsjdk/")
3159 "-Dhtsjdk-classes=dist/tmp"
3160 (string-append "-Dhtsjdk-version="
3161 ,(package-version java-htsjdk)))
3164 (modify-phases %standard-phases
3165 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3166 (delete 'generate-jar-indices)
3167 (add-after 'unpack 'use-our-htsjdk
3168 (lambda* (#:key inputs #:allow-other-keys)
3169 (substitute* "build.xml"
3170 (("\\$\\{htsjdk\\}/lib")
3171 (string-append (assoc-ref inputs "java-htsjdk")
3172 "/share/java/htsjdk/")))
3174 (add-after 'unpack 'make-test-target-independent
3175 (lambda* (#:key inputs #:allow-other-keys)
3176 (substitute* "build.xml"
3177 (("name=\"test\" depends=\"compile, ")
3178 "name=\"test\" depends=\""))
3180 (replace 'install (install-jars "dist")))))
3182 `(("java-htsjdk" ,java-htsjdk)
3183 ("java-guava" ,java-guava)))
3185 `(("java-testng" ,java-testng)))
3186 (home-page "http://broadinstitute.github.io/picard/")
3187 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3188 (description "Picard is a set of Java command line tools for manipulating
3189 high-throughput sequencing (HTS) data and formats. Picard is implemented
3190 using the HTSJDK Java library to support accessing file formats that are
3191 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3193 (license license:expat)))
3195 ;; This is needed for dropseq-tools
3196 (define-public java-picard-2.10.3
3198 (name "java-picard")
3203 (url "https://github.com/broadinstitute/picard.git")
3205 (file-name (string-append "java-picard-" version "-checkout"))
3208 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3209 (build-system ant-build-system)
3211 `(#:jar-name "picard.jar"
3212 ;; Tests require jacoco:coverage.
3215 #:main-class "picard.cmdline.PicardCommandLine"
3216 #:modules ((guix build ant-build-system)
3218 (guix build java-utils)
3223 (modify-phases %standard-phases
3224 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3225 (delete 'generate-jar-indices)
3226 (add-after 'unpack 'remove-useless-build.xml
3227 (lambda _ (delete-file "build.xml") #t))
3228 ;; This is necessary to ensure that htsjdk is found when using
3229 ;; picard.jar as an executable.
3230 (add-before 'build 'edit-classpath-in-manifest
3231 (lambda* (#:key inputs #:allow-other-keys)
3232 (chmod "build.xml" #o664)
3233 (call-with-output-file "build.xml.new"
3237 (with-input-from-file "build.xml"
3238 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3239 `((target . ,(lambda (tag . kids)
3240 (let ((name ((sxpath '(name *text*))
3242 ;; FIXME: We're breaking the line
3243 ;; early with a dummy path to
3244 ;; ensure that the store reference
3245 ;; isn't broken apart and can still
3246 ;; be found by the reference
3251 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3252 ;; maximum line length is 70
3253 (string-tabulate (const #\b) 57)
3254 (assoc-ref inputs "java-htsjdk"))))
3255 (if (member "manifest" name)
3258 (@ (file "${manifest.file}")
3259 (match "\\r\\n\\r\\n")
3260 (replace "${line.separator}")))
3263 (file "${manifest.file}")
3266 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3267 (*text* . ,(lambda (_ txt) txt))))
3269 (rename-file "build.xml.new" "build.xml")
3272 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3274 `(("java-testng" ,java-testng)
3275 ("java-guava" ,java-guava)))
3276 (home-page "http://broadinstitute.github.io/picard/")
3277 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3278 (description "Picard is a set of Java command line tools for manipulating
3279 high-throughput sequencing (HTS) data and formats. Picard is implemented
3280 using the HTSJDK Java library to support accessing file formats that are
3281 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3283 (license license:expat)))
3285 ;; This is the last version of Picard to provide net.sf.samtools
3286 (define-public java-picard-1.113
3287 (package (inherit java-picard)
3288 (name "java-picard")
3293 (url "https://github.com/broadinstitute/picard.git")
3295 (file-name (string-append "java-picard-" version "-checkout"))
3298 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3299 (modules '((guix build utils)))
3302 ;; Delete pre-built binaries.
3303 (delete-file-recursively "lib")
3306 (build-system ant-build-system)
3308 `(#:build-target "picard-jar"
3309 #:test-target "test"
3310 ;; FIXME: the class path at test time is wrong.
3311 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3312 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3315 ;; This is only used for tests.
3317 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3319 (modify-phases %standard-phases
3320 ;; FIXME: This phase fails.
3321 (delete 'generate-jar-indices)
3322 ;; Do not use bundled ant bzip2.
3323 (add-after 'unpack 'use-ant-bzip
3324 (lambda* (#:key inputs #:allow-other-keys)
3325 (substitute* "build.xml"
3326 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3327 (string-append (assoc-ref inputs "ant")
3330 (add-after 'unpack 'make-test-target-independent
3331 (lambda* (#:key inputs #:allow-other-keys)
3332 (substitute* "build.xml"
3333 (("name=\"test\" depends=\"compile, ")
3334 "name=\"test\" depends=\"compile-tests, ")
3335 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3336 "name=\"compile\" depends=\"compile-src\""))
3338 (add-after 'unpack 'fix-deflater-path
3339 (lambda* (#:key outputs #:allow-other-keys)
3340 (substitute* "src/java/net/sf/samtools/Defaults.java"
3341 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3342 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3343 (assoc-ref outputs "out")
3344 "/lib/jni/libIntelDeflater.so"
3347 ;; Build the deflater library, because we've previously deleted the
3348 ;; pre-built one. This can only be built with access to the JDK
3350 (add-after 'build 'build-jni
3351 (lambda* (#:key inputs #:allow-other-keys)
3354 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3355 "-xf" (assoc-ref inputs "jdk-src")))
3356 (zero? (system* "javah" "-jni"
3357 "-classpath" "classes"
3359 "net.sf.samtools.util.zip.IntelDeflater"))
3360 (with-directory-excursion "src/c/inteldeflater"
3361 (zero? (system* "gcc" "-I../../../lib" "-I."
3362 (string-append "-I" (assoc-ref inputs "jdk")
3364 "-I../../../jdk-src/src/share/native/common/"
3365 "-I../../../jdk-src/src/solaris/native/common/"
3366 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3367 (zero? (system* "gcc" "-shared"
3368 "-o" "../../../lib/jni/libIntelDeflater.so"
3369 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3370 ;; We can only build everything else after building the JNI library.
3371 (add-after 'build-jni 'build-rest
3372 (lambda* (#:key make-flags #:allow-other-keys)
3373 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3374 (add-before 'build 'set-JAVA6_HOME
3376 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3378 (replace 'install (install-jars "dist"))
3379 (add-after 'install 'install-jni-lib
3380 (lambda* (#:key outputs #:allow-other-keys)
3381 (let ((jni (string-append (assoc-ref outputs "out")
3384 (install-file "lib/jni/libIntelDeflater.so" jni)
3387 `(("java-snappy-1" ,java-snappy-1)
3388 ("java-commons-jexl-2" ,java-commons-jexl-2)
3389 ("java-cofoja" ,java-cofoja)
3390 ("ant" ,ant) ; for bzip2 support at runtime
3393 `(("ant-apache-bcel" ,ant-apache-bcel)
3394 ("ant-junit" ,ant-junit)
3395 ("java-testng" ,java-testng)
3396 ("java-commons-bcel" ,java-commons-bcel)
3397 ("java-jcommander" ,java-jcommander)
3398 ("jdk" ,icedtea-8 "jdk")
3399 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3401 (define-public fastqc
3408 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3409 "projects/fastqc/fastqc_v"
3410 version "_source.zip"))
3413 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3414 (build-system ant-build-system)
3416 `(#:tests? #f ; there are no tests
3417 #:build-target "build"
3419 (modify-phases %standard-phases
3420 (add-after 'unpack 'fix-dependencies
3421 (lambda* (#:key inputs #:allow-other-keys)
3422 (substitute* "build.xml"
3424 (string-append (assoc-ref inputs "java-jbzip2")
3425 "/share/java/jbzip2.jar"))
3427 (string-append (assoc-ref inputs "java-picard-1.113")
3428 "/share/java/sam-1.112.jar"))
3430 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3431 "/share/java/sis-jhdf5.jar")))
3433 ;; There is no installation target
3435 (lambda* (#:key inputs outputs #:allow-other-keys)
3436 (let* ((out (assoc-ref outputs "out"))
3437 (bin (string-append out "/bin"))
3438 (share (string-append out "/share/fastqc/"))
3439 (exe (string-append share "/fastqc")))
3440 (for-each mkdir-p (list bin share))
3441 (copy-recursively "bin" share)
3443 (("my \\$java_bin = 'java';")
3444 (string-append "my $java_bin = '"
3445 (assoc-ref inputs "java")
3448 (symlink exe (string-append bin "/fastqc"))
3452 ("perl" ,perl) ; needed for the wrapper script
3453 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3454 ("java-picard-1.113" ,java-picard-1.113)
3455 ("java-jbzip2" ,java-jbzip2)))
3457 `(("unzip" ,unzip)))
3458 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3459 (synopsis "Quality control tool for high throughput sequence data")
3461 "FastQC aims to provide a simple way to do some quality control
3462 checks on raw sequence data coming from high throughput sequencing
3463 pipelines. It provides a modular set of analyses which you can use to
3464 give a quick impression of whether your data has any problems of which
3465 you should be aware before doing any further analysis.
3467 The main functions of FastQC are:
3470 @item Import of data from BAM, SAM or FastQ files (any variant);
3471 @item Providing a quick overview to tell you in which areas there may
3473 @item Summary graphs and tables to quickly assess your data;
3474 @item Export of results to an HTML based permanent report;
3475 @item Offline operation to allow automated generation of reports
3476 without running the interactive application.
3478 (license license:gpl3+)))
3480 (define-public fastp
3488 (url "https://github.com/OpenGene/fastp.git")
3489 (commit (string-append "v" version))))
3490 (file-name (git-file-name name version))
3493 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3494 (build-system gnu-build-system)
3496 `(#:tests? #f ; there are none
3498 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3500 (modify-phases %standard-phases
3502 (add-before 'install 'create-target-dir
3503 (lambda* (#:key outputs #:allow-other-keys)
3504 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3508 (home-page "https://github.com/OpenGene/fastp/")
3509 (synopsis "All-in-one FastQ preprocessor")
3511 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3512 FastQ files. This tool has multi-threading support to afford high
3514 (license license:expat)))
3516 (define-public htslib
3523 "https://github.com/samtools/htslib/releases/download/"
3524 version "/htslib-" version ".tar.bz2"))
3527 "18bw0mn9pj5wgarnlaxmf1bb8pdqgl1zd6czirqcr62ajpn1xvy0"))))
3528 (build-system gnu-build-system)
3530 `(("openssl" ,openssl)
3535 (home-page "http://www.htslib.org")
3536 (synopsis "C library for reading/writing high-throughput sequencing data")
3538 "HTSlib is a C library for reading/writing high-throughput sequencing
3539 data. It also provides the @command{bgzip}, @command{htsfile}, and
3540 @command{tabix} utilities.")
3541 ;; Files under cram/ are released under the modified BSD license;
3542 ;; the rest is released under the Expat license
3543 (license (list license:expat license:bsd-3))))
3545 ;; This package should be removed once no packages rely upon it.
3553 "https://github.com/samtools/htslib/releases/download/"
3554 version "/htslib-" version ".tar.bz2"))
3557 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3566 "https://github.com/nboley/idr/archive/"
3568 (file-name (string-append name "-" version ".tar.gz"))
3571 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3572 ;; Delete generated C code.
3574 '(begin (delete-file "idr/inv_cdf.c") #t))))
3575 (build-system python-build-system)
3576 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3577 ;; are no longer part of this package. It also asserts False, which
3578 ;; causes the tests to always fail.
3579 (arguments `(#:tests? #f))
3581 `(("python-scipy" ,python-scipy)
3582 ("python-sympy" ,python-sympy)
3583 ("python-numpy" ,python-numpy)
3584 ("python-matplotlib" ,python-matplotlib)))
3586 `(("python-cython" ,python-cython)))
3587 (home-page "https://github.com/nboley/idr")
3588 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3590 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3591 to measure the reproducibility of findings identified from replicate
3592 experiments and provide highly stable thresholds based on reproducibility.")
3593 (license license:gpl2+)))
3595 (define-public jellyfish
3601 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3602 "releases/download/v" version
3603 "/jellyfish-" version ".tar.gz"))
3606 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3607 (build-system gnu-build-system)
3608 (outputs '("out" ;for library
3609 "ruby" ;for Ruby bindings
3610 "python")) ;for Python bindings
3613 (list (string-append "--enable-ruby-binding="
3614 (assoc-ref %outputs "ruby"))
3615 (string-append "--enable-python-binding="
3616 (assoc-ref %outputs "python")))
3618 (modify-phases %standard-phases
3619 (add-before 'check 'set-SHELL-variable
3621 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3623 (setenv "SHELL" (which "bash"))
3629 ("python" ,python-2)
3630 ("pkg-config" ,pkg-config)))
3632 `(("htslib" ,htslib)))
3633 (synopsis "Tool for fast counting of k-mers in DNA")
3635 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3636 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3637 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3638 is a command-line program that reads FASTA and multi-FASTA files containing
3639 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3640 translated into a human-readable text format using the @code{jellyfish dump}
3641 command, or queried for specific k-mers with @code{jellyfish query}.")
3642 (home-page "http://www.genome.umd.edu/jellyfish.html")
3643 ;; JELLYFISH seems to be 64-bit only.
3644 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3645 ;; The combined work is published under the GPLv3 or later. Individual
3646 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3647 (license (list license:gpl3+ license:expat))))
3649 (define-public khmer
3656 (uri (pypi-uri "khmer" version))
3659 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3660 (patches (search-patches "khmer-use-libraries.patch"))))
3661 (build-system python-build-system)
3664 (modify-phases %standard-phases
3665 (add-after 'unpack 'set-paths
3666 (lambda* (#:key inputs outputs #:allow-other-keys)
3667 ;; Delete bundled libraries.
3668 (delete-file-recursively "third-party/zlib")
3669 (delete-file-recursively "third-party/bzip2")
3670 ;; Replace bundled seqan.
3671 (let* ((seqan-all "third-party/seqan")
3672 (seqan-include (string-append
3673 seqan-all "/core/include")))
3674 (delete-file-recursively seqan-all)
3675 (copy-recursively (string-append (assoc-ref inputs "seqan")
3677 (string-append seqan-include "/seqan")))
3678 ;; We do not replace the bundled MurmurHash as the canonical
3679 ;; repository for this code 'SMHasher' is unsuitable for
3680 ;; providing a library. See
3681 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3683 (add-after 'unpack 'set-cc
3687 ;; It is simpler to test after installation.
3689 (add-after 'install 'post-install-check
3690 (lambda* (#:key inputs outputs #:allow-other-keys)
3691 (let ((out (assoc-ref outputs "out")))
3696 (assoc-ref outputs "out")
3698 (setenv "PYTHONPATH"
3700 (getenv "PYTHONPATH")
3704 (string-take (string-take-right
3705 (assoc-ref inputs "python") 5) 3)
3707 (with-directory-excursion "build"
3708 (zero? (system* "nosetests" "khmer" "--attr"
3709 "!known_failing")))))))))
3712 ("python-nose" ,python-nose)))
3716 ("python-screed" ,python-screed)
3717 ("python-bz2file" ,python-bz2file)
3718 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3719 ;; until the next version of khmer (likely 2.1) is released.
3721 (home-page "https://khmer.readthedocs.org/")
3722 (synopsis "K-mer counting, filtering and graph traversal library")
3723 (description "The khmer software is a set of command-line tools for
3724 working with DNA shotgun sequencing data from genomes, transcriptomes,
3725 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3726 sometimes better. Khmer can also identify and fix problems with shotgun
3728 ;; When building on i686, armhf and mips64el, we get the following error:
3729 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3730 (supported-systems '("x86_64-linux" "aarch64-linux"))
3731 (license license:bsd-3)))
3733 (define-public kaiju
3740 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3742 (file-name (string-append name "-" version ".tar.gz"))
3745 "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7"))))
3746 (build-system gnu-build-system)
3748 `(#:tests? #f ; There are no tests.
3750 (modify-phases %standard-phases
3752 (add-before 'build 'move-to-src-dir
3753 (lambda _ (chdir "src") #t))
3755 (lambda* (#:key inputs outputs #:allow-other-keys)
3756 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3759 (copy-recursively "bin" bin)
3760 (copy-recursively "util" bin))
3765 (home-page "http://kaiju.binf.ku.dk/")
3766 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3767 (description "Kaiju is a program for sensitive taxonomic classification
3768 of high-throughput sequencing reads from metagenomic whole genome sequencing
3770 (license license:gpl3+)))
3775 (version "2.1.1.20160309")
3778 (uri (pypi-uri "MACS2" version))
3781 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3782 (build-system python-build-system)
3784 `(#:python ,python-2 ; only compatible with Python 2.7
3785 #:tests? #f)) ; no test target
3787 `(("python-numpy" ,python2-numpy)))
3788 (home-page "https://github.com/taoliu/MACS/")
3789 (synopsis "Model based analysis for ChIP-Seq data")
3791 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3792 identifying transcript factor binding sites named Model-based Analysis of
3793 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3794 the significance of enriched ChIP regions and it improves the spatial
3795 resolution of binding sites through combining the information of both
3796 sequencing tag position and orientation.")
3797 (license license:bsd-3)))
3799 (define-public mafft
3806 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3807 "-without-extensions-src.tgz"))
3808 (file-name (string-append name "-" version ".tgz"))
3811 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3812 (build-system gnu-build-system)
3814 `(#:tests? #f ; no automated tests, though there are tests in the read me
3815 #:make-flags (let ((out (assoc-ref %outputs "out")))
3816 (list (string-append "PREFIX=" out)
3817 (string-append "BINDIR="
3818 (string-append out "/bin"))))
3820 (modify-phases %standard-phases
3821 (add-after 'unpack 'enter-dir
3822 (lambda _ (chdir "core") #t))
3823 (add-after 'enter-dir 'patch-makefile
3825 ;; on advice from the MAFFT authors, there is no need to
3826 ;; distribute mafft-profile, mafft-distance, or
3827 ;; mafft-homologs.rb as they are too "specialised".
3828 (substitute* "Makefile"
3829 ;; remove mafft-homologs.rb from SCRIPTS
3830 (("^SCRIPTS = mafft mafft-homologs.rb")
3832 ;; remove mafft-homologs from MANPAGES
3833 (("^MANPAGES = mafft.1 mafft-homologs.1")
3834 "MANPAGES = mafft.1")
3835 ;; remove mafft-distance from PROGS
3836 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3837 "PROGS = dvtditr dndfast7 dndblast sextet5")
3838 ;; remove mafft-profile from PROGS
3839 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3840 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3841 (("^rm -f mafft-profile mafft-profile.exe") "#")
3842 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3843 ;; do not install MAN pages in libexec folder
3844 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3845 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3847 (add-after 'enter-dir 'patch-paths
3848 (lambda* (#:key inputs #:allow-other-keys)
3849 (substitute* '("pairash.c"
3851 (("perl") (which "perl"))
3852 (("([\"`| ])awk" _ prefix)
3853 (string-append prefix (which "awk")))
3854 (("grep") (which "grep")))
3857 (add-after 'install 'wrap-programs
3858 (lambda* (#:key outputs #:allow-other-keys)
3859 (let* ((out (assoc-ref outputs "out"))
3860 (bin (string-append out "/bin"))
3861 (path (string-append
3862 (assoc-ref %build-inputs "coreutils") "/bin:")))
3863 (for-each (lambda (file)
3865 `("PATH" ":" prefix (,path))))
3873 ("coreutils" ,coreutils)))
3874 (home-page "http://mafft.cbrc.jp/alignment/software/")
3875 (synopsis "Multiple sequence alignment program")
3877 "MAFFT offers a range of multiple alignment methods for nucleotide and
3878 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3879 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3881 (license (license:non-copyleft
3882 "http://mafft.cbrc.jp/alignment/software/license.txt"
3883 "BSD-3 with different formatting"))))
3892 "https://github.com/marbl/mash/archive/v"
3894 (file-name (string-append name "-" version ".tar.gz"))
3897 "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv"))
3898 (modules '((guix build utils)))
3901 ;; Delete bundled kseq.
3902 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3903 (delete-file "src/mash/kseq.h")
3905 (build-system gnu-build-system)
3907 `(#:tests? #f ; No tests.
3910 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3911 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3912 #:make-flags (list "CC=gcc")
3914 (modify-phases %standard-phases
3915 (add-after 'unpack 'fix-includes
3917 (substitute* '("src/mash/Sketch.cpp"
3918 "src/mash/CommandFind.cpp"
3919 "src/mash/CommandScreen.cpp")
3920 (("^#include \"kseq\\.h\"")
3921 "#include \"htslib/kseq.h\""))
3923 (add-after 'fix-includes 'autoconf
3924 (lambda _ (zero? (system* "autoconf")))))))
3926 `(("autoconf" ,autoconf)
3927 ;; Capnproto and htslib are statically embedded in the final
3928 ;; application. Therefore we also list their licenses, below.
3929 ("capnproto" ,capnproto)
3930 ("htslib" ,htslib)))
3934 (supported-systems '("x86_64-linux"))
3935 (home-page "https://mash.readthedocs.io")
3936 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3937 (description "Mash is a fast sequence distance estimator that uses the
3938 MinHash algorithm and is designed to work with genomes and metagenomes in the
3939 form of assemblies or reads.")
3940 (license (list license:bsd-3 ; Mash
3941 license:expat ; HTSlib and capnproto
3942 license:public-domain ; MurmurHash 3
3943 license:cpl1.0)))) ; Open Bloom Filter
3945 (define-public metabat
3952 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3954 (file-name (string-append name "-" version ".tar.gz"))
3957 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3958 (patches (search-patches "metabat-fix-compilation.patch"))))
3959 (build-system scons-build-system)
3961 `(#:scons ,scons-python2
3963 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3964 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3965 #:tests? #f ;; Tests are run during the build phase.
3967 (modify-phases %standard-phases
3968 (add-after 'unpack 'fix-includes
3970 (substitute* "src/BamUtils.h"
3971 (("^#include \"bam/bam\\.h\"")
3972 "#include \"samtools/bam.h\"")
3973 (("^#include \"bam/sam\\.h\"")
3974 "#include \"samtools/sam.h\""))
3975 (substitute* "src/KseqReader.h"
3976 (("^#include \"bam/kseq\\.h\"")
3977 "#include \"htslib/kseq.h\""))
3979 (add-after 'unpack 'fix-scons
3980 (lambda* (#:key inputs #:allow-other-keys)
3981 (substitute* "SConstruct"
3982 (("^htslib_dir += 'samtools'")
3983 (string-append "htslib_dir = '"
3984 (assoc-ref inputs "htslib")
3986 (("^samtools_dir = 'samtools'")
3987 (string-append "samtools_dir = '"
3988 (assoc-ref inputs "samtools")
3990 (("^findStaticOrShared\\('bam', hts_lib")
3991 (string-append "findStaticOrShared('bam', '"
3992 (assoc-ref inputs "samtools")
3994 ;; Do not distribute README.
3995 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4000 ("samtools" ,samtools)
4003 (home-page "https://bitbucket.org/berkeleylab/metabat")
4005 "Reconstruction of single genomes from complex microbial communities")
4007 "Grouping large genomic fragments assembled from shotgun metagenomic
4008 sequences to deconvolute complex microbial communities, or metagenome binning,
4009 enables the study of individual organisms and their interactions. MetaBAT is
4010 an automated metagenome binning software, which integrates empirical
4011 probabilistic distances of genome abundance and tetranucleotide frequency.")
4012 ;; The source code contains inline assembly.
4013 (supported-systems '("x86_64-linux" "i686-linux"))
4014 (license (license:non-copyleft "file://license.txt"
4015 "See license.txt in the distribution."))))
4017 (define-public minced
4024 "https://github.com/ctSkennerton/minced/archive/"
4026 (file-name (string-append name "-" version ".tar.gz"))
4029 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
4030 (build-system gnu-build-system)
4032 `(#:test-target "test"
4034 (modify-phases %standard-phases
4036 (add-before 'check 'fix-test
4038 ;; Fix test for latest version.
4039 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4040 (("minced:0.1.6") "minced:0.2.0"))
4042 (replace 'install ; No install target.
4043 (lambda* (#:key inputs outputs #:allow-other-keys)
4044 (let* ((out (assoc-ref outputs "out"))
4045 (bin (string-append out "/bin"))
4046 (wrapper (string-append bin "/minced")))
4047 ;; Minced comes with a wrapper script that tries to figure out where
4048 ;; it is located before running the JAR. Since these paths are known
4049 ;; to us, we build our own wrapper to avoid coreutils dependency.
4050 (install-file "minced.jar" bin)
4051 (with-output-to-file wrapper
4055 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4056 (assoc-ref inputs "jre") "/bin/java -jar "
4057 bin "/minced.jar \"$@\"\n"))))
4058 (chmod wrapper #o555)))))))
4060 `(("jdk" ,icedtea "jdk")))
4063 ("jre" ,icedtea "out")))
4064 (home-page "https://github.com/ctSkennerton/minced")
4065 (synopsis "Mining CRISPRs in Environmental Datasets")
4067 "MinCED is a program to find Clustered Regularly Interspaced Short
4068 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4069 unassembled metagenomic reads, but is mainly designed for full genomes and
4070 assembled metagenomic sequence.")
4071 (license license:gpl3+)))
4079 (uri (pypi-uri "misopy" version))
4082 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4083 (modules '((guix build utils)))
4085 (substitute* "setup.py"
4086 ;; Use setuptools, or else the executables are not
4088 (("distutils.core") "setuptools")
4089 ;; use "gcc" instead of "cc" for compilation
4091 "cc.set_executables(
4095 linker_so='gcc -shared'); defines"))
4097 (build-system python-build-system)
4099 `(#:python ,python-2 ; only Python 2 is supported
4100 #:tests? #f)) ; no "test" target
4102 `(("samtools" ,samtools)
4103 ("python-numpy" ,python2-numpy)
4104 ("python-pysam" ,python2-pysam)
4105 ("python-scipy" ,python2-scipy)
4106 ("python-matplotlib" ,python2-matplotlib)))
4108 `(("python-mock" ,python2-mock) ;for tests
4109 ("python-pytz" ,python2-pytz))) ;for tests
4110 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4111 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4113 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4114 the expression level of alternatively spliced genes from RNA-Seq data, and
4115 identifies differentially regulated isoforms or exons across samples. By
4116 modeling the generative process by which reads are produced from isoforms in
4117 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4118 that a read originated from a particular isoform.")
4119 (license license:gpl2)))
4121 (define-public muscle
4124 (version "3.8.1551")
4126 (method url-fetch/tarbomb)
4128 "http://www.drive5.com/muscle/muscle_src_"
4132 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4133 (build-system gnu-build-system)
4135 `(#:make-flags (list "LDLIBS = -lm")
4137 (modify-phases %standard-phases
4140 ;; There are no tests, so just test if it runs.
4141 (lambda _ (zero? (system* "./muscle" "-version"))))
4143 (lambda* (#:key outputs #:allow-other-keys)
4144 (let* ((out (assoc-ref outputs "out"))
4145 (bin (string-append out "/bin")))
4146 (install-file "muscle" bin)))))))
4147 (home-page "http://www.drive5.com/muscle")
4148 (synopsis "Multiple sequence alignment program")
4150 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4151 program for nucleotide and protein sequences.")
4152 ;; License information found in 'muscle -h' and usage.cpp.
4153 (license license:public-domain)))
4155 (define-public newick-utils
4156 ;; There are no recent releases so we package from git.
4157 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4159 (name "newick-utils")
4160 (version (string-append "1.6-1." (string-take commit 8)))
4164 (url "https://github.com/tjunier/newick_utils.git")
4166 (file-name (string-append name "-" version "-checkout"))
4169 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4170 (build-system gnu-build-system)
4173 (modify-phases %standard-phases
4174 (add-after 'unpack 'autoconf
4175 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4177 ;; XXX: TODO: Enable Lua and Guile bindings.
4178 ;; https://github.com/tjunier/newick_utils/issues/13
4179 `(("libxml2" ,libxml2)
4183 `(("autoconf" ,autoconf)
4184 ("automake" ,automake)
4185 ("libtool" ,libtool)))
4186 (synopsis "Programs for working with newick format phylogenetic trees")
4188 "Newick-utils is a suite of utilities for processing phylogenetic trees
4189 in Newick format. Functions include re-rooting, extracting subtrees,
4190 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4191 (home-page "https://github.com/tjunier/newick_utils")
4192 (license license:bsd-3))))
4201 "https://github.com/wwood/OrfM/releases/download/v"
4202 version "/orfm-" version ".tar.gz"))
4205 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4206 (build-system gnu-build-system)
4207 (inputs `(("zlib" ,zlib)))
4209 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4210 ("ruby-rspec" ,ruby-rspec)
4212 (synopsis "Simple and not slow open reading frame (ORF) caller")
4214 "An ORF caller finds stretches of DNA that, when translated, are not
4215 interrupted by stop codons. OrfM finds and prints these ORFs.")
4216 (home-page "https://github.com/wwood/OrfM")
4217 (license license:lgpl3+)))
4219 (define-public pplacer
4220 (let ((commit "g807f6f3"))
4223 ;; The commit should be updated with each version change.
4224 (version "1.1.alpha19")
4228 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4230 (file-name (string-append name "-" version ".tar.gz"))
4232 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4233 (build-system ocaml-build-system)
4235 `(#:ocaml ,ocaml-4.01
4236 #:findlib ,ocaml4.01-findlib
4237 #:modules ((guix build ocaml-build-system)
4241 (modify-phases %standard-phases
4243 (add-after 'unpack 'replace-bundled-cddlib
4244 (lambda* (#:key inputs #:allow-other-keys)
4245 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4246 (local-dir "cddlib_guix"))
4248 (with-directory-excursion local-dir
4249 (system* "tar" "xvf" cddlib-src))
4250 (let ((cddlib-src-folder
4251 (string-append local-dir "/"
4252 (list-ref (scandir local-dir) 2)
4257 (string-append "cdd_src/" (basename file))))
4258 (find-files cddlib-src-folder ".*[ch]$")))
4260 (add-after 'unpack 'fix-makefile
4262 ;; Remove system calls to 'git'.
4263 (substitute* "Makefile"
4264 (("^DESCRIPT:=pplacer-.*")
4266 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4267 (substitute* "myocamlbuild.ml"
4268 (("git describe --tags --long .*\\\" with")
4270 "echo -n v" ,version "-" ,commit "\" with")))
4273 (lambda* (#:key outputs #:allow-other-keys)
4274 (let* ((out (assoc-ref outputs "out"))
4275 (bin (string-append out "/bin")))
4276 (copy-recursively "bin" bin))
4281 ("ocaml-ounit" ,ocaml4.01-ounit)
4282 ("ocaml-batteries" ,ocaml4.01-batteries)
4283 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4284 ("ocaml-csv" ,ocaml4.01-csv)
4285 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4286 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4287 ("ocaml-mcl" ,ocaml4.01-mcl)
4288 ("ocaml-gsl" ,ocaml4.01-gsl)
4289 ("cddlib-src" ,(package-source cddlib))))
4291 `(("pplacer-scripts" ,pplacer-scripts)))
4292 (synopsis "Phylogenetic placement of biological sequences")
4294 "Pplacer places query sequences on a fixed reference phylogenetic tree
4295 to maximize phylogenetic likelihood or posterior probability according to a
4296 reference alignment. Pplacer is designed to be fast, to give useful
4297 information about uncertainty, and to offer advanced visualization and
4298 downstream analysis.")
4299 (home-page "http://matsen.fhcrc.org/pplacer")
4300 (license license:gpl3))))
4302 ;; This package is installed alongside 'pplacer'. It is a separate package so
4303 ;; that it can use the python-build-system for the scripts that are
4304 ;; distributed alongside the main OCaml binaries.
4305 (define pplacer-scripts
4308 (name "pplacer-scripts")
4309 (build-system python-build-system)
4311 `(#:python ,python-2
4313 (modify-phases %standard-phases
4314 (add-after 'unpack 'enter-scripts-dir
4315 (lambda _ (chdir "scripts")))
4318 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4319 (add-after 'install 'wrap-executables
4320 (lambda* (#:key inputs outputs #:allow-other-keys)
4321 (let* ((out (assoc-ref outputs "out"))
4322 (bin (string-append out "/bin")))
4323 (let ((path (string-append
4324 (assoc-ref inputs "hmmer") "/bin:"
4325 (assoc-ref inputs "infernal") "/bin")))
4327 (wrap-program (string-append bin "/refpkg_align.py")
4328 `("PATH" ":" prefix (,path))))
4329 (let ((path (string-append
4330 (assoc-ref inputs "hmmer") "/bin")))
4331 (wrap-program (string-append bin "/hrefpkg_query.py")
4332 `("PATH" ":" prefix (,path)))))
4335 `(("infernal" ,infernal)
4338 `(("python-biopython" ,python2-biopython)
4339 ("taxtastic" ,taxtastic)))
4340 (synopsis "Pplacer Python scripts")))
4342 (define-public python2-pbcore
4344 (name "python2-pbcore")
4348 (uri (pypi-uri "pbcore" version))
4351 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4352 (build-system python-build-system)
4353 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4355 `(("python-cython" ,python2-cython)
4356 ("python-numpy" ,python2-numpy)
4357 ("python-pysam" ,python2-pysam)
4358 ("python-h5py" ,python2-h5py)))
4360 `(("python-nose" ,python2-nose)
4361 ("python-sphinx" ,python2-sphinx)
4362 ("python-pyxb" ,python2-pyxb)))
4363 (home-page "http://pacificbiosciences.github.io/pbcore/")
4364 (synopsis "Library for reading and writing PacBio data files")
4366 "The pbcore package provides Python APIs for interacting with PacBio data
4367 files and writing bioinformatics applications.")
4368 (license license:bsd-3)))
4370 (define-public python2-warpedlmm
4372 (name "python2-warpedlmm")
4378 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4382 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4383 (build-system python-build-system)
4385 `(#:python ,python-2)) ; requires Python 2.7
4387 `(("python-scipy" ,python2-scipy)
4388 ("python-numpy" ,python2-numpy)
4389 ("python-matplotlib" ,python2-matplotlib)
4390 ("python-fastlmm" ,python2-fastlmm)
4391 ("python-pandas" ,python2-pandas)
4392 ("python-pysnptools" ,python2-pysnptools)))
4394 `(("python-mock" ,python2-mock)
4395 ("python-nose" ,python2-nose)
4397 (home-page "https://github.com/PMBio/warpedLMM")
4398 (synopsis "Implementation of warped linear mixed models")
4400 "WarpedLMM is a Python implementation of the warped linear mixed model,
4401 which automatically learns an optimal warping function (or transformation) for
4402 the phenotype as it models the data.")
4403 (license license:asl2.0)))
4405 (define-public pbtranscript-tofu
4406 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4408 (name "pbtranscript-tofu")
4409 (version (string-append "2.2.3." (string-take commit 7)))
4413 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4415 (file-name (string-append name "-" version "-checkout"))
4418 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4419 (modules '((guix build utils)))
4422 ;; remove bundled Cython sources
4423 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4425 (build-system python-build-system)
4427 `(#:python ,python-2
4428 ;; FIXME: Tests fail with "No such file or directory:
4429 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4432 (modify-phases %standard-phases
4433 (add-after 'unpack 'enter-directory
4435 (chdir "pbtranscript-tofu/pbtranscript/")
4437 ;; With setuptools version 18.0 and later this setup.py hack causes
4438 ;; a build error, so we disable it.
4439 (add-after 'enter-directory 'patch-setuppy
4441 (substitute* "setup.py"
4442 (("if 'setuptools.extension' in sys.modules:")
4446 `(("python-numpy" ,python2-numpy)
4447 ("python-bx-python" ,python2-bx-python)
4448 ("python-networkx" ,python2-networkx)
4449 ("python-scipy" ,python2-scipy)
4450 ("python-pbcore" ,python2-pbcore)
4451 ("python-h5py" ,python2-h5py)))
4453 `(("python-cython" ,python2-cython)
4454 ("python-nose" ,python2-nose)))
4455 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4456 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4458 "pbtranscript-tofu contains scripts to analyze transcriptome data
4459 generated using the PacBio Iso-Seq protocol.")
4460 (license license:bsd-3))))
4462 (define-public prank
4469 "http://wasabiapp.org/download/prank/prank.source."
4473 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4474 (build-system gnu-build-system)
4477 (modify-phases %standard-phases
4478 (add-after 'unpack 'enter-src-dir
4482 (add-after 'unpack 'remove-m64-flag
4483 ;; Prank will build with the correct 'bit-ness' without this flag
4484 ;; and this allows building on 32-bit machines.
4485 (lambda _ (substitute* "src/Makefile"
4490 (lambda* (#:key outputs #:allow-other-keys)
4491 (let* ((out (assoc-ref outputs "out"))
4492 (bin (string-append out "/bin"))
4493 (man (string-append out "/share/man/man1"))
4494 (path (string-append
4495 (assoc-ref %build-inputs "mafft") "/bin:"
4496 (assoc-ref %build-inputs "exonerate") "/bin:"
4497 (assoc-ref %build-inputs "bppsuite") "/bin")))
4498 (install-file "prank" bin)
4499 (wrap-program (string-append bin "/prank")
4500 `("PATH" ":" prefix (,path)))
4501 (install-file "prank.1" man))
4505 ("exonerate" ,exonerate)
4506 ("bppsuite" ,bppsuite)))
4507 (home-page "http://wasabiapp.org/software/prank/")
4508 (synopsis "Probabilistic multiple sequence alignment program")
4510 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4511 codon and amino-acid sequences. It is based on a novel algorithm that treats
4512 insertions correctly and avoids over-estimation of the number of deletion
4513 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4514 in phylogenetics and correctly takes into account the evolutionary distances
4515 between sequences. Lastly, PRANK allows for defining a potential structure
4516 for sequences to be aligned and then, simultaneously with the alignment,
4517 predicts the locations of structural units in the sequences.")
4518 (license license:gpl2+)))
4520 (define-public proteinortho
4522 (name "proteinortho")
4529 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4530 version "_src.tar.gz"))
4533 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4534 (build-system gnu-build-system)
4536 `(#:test-target "test"
4538 (modify-phases %standard-phases
4540 ;; There is no configure script, so we modify the Makefile directly.
4541 (lambda* (#:key outputs #:allow-other-keys)
4542 (substitute* "Makefile"
4545 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4547 (add-before 'install 'make-install-directory
4548 ;; The install directory is not created during 'make install'.
4549 (lambda* (#:key outputs #:allow-other-keys)
4550 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4552 (add-after 'install 'wrap-programs
4553 (lambda* (#:key inputs outputs #:allow-other-keys)
4554 (let* ((path (getenv "PATH"))
4555 (out (assoc-ref outputs "out"))
4556 (binary (string-append out "/bin/proteinortho5.pl")))
4557 (wrap-program binary `("PATH" ":" prefix (,path))))
4561 ("python" ,python-2)
4562 ("blast+" ,blast+)))
4563 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4564 (synopsis "Detect orthologous genes across species")
4566 "Proteinortho is a tool to detect orthologous genes across different
4567 species. For doing so, it compares similarities of given gene sequences and
4568 clusters them to find significant groups. The algorithm was designed to handle
4569 large-scale data and can be applied to hundreds of species at once.")
4570 (license license:gpl2+)))
4572 (define-public pyicoteo
4579 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4580 "pyicoteo/get/v" version ".tar.bz2"))
4581 (file-name (string-append name "-" version ".tar.bz2"))
4584 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4585 (build-system python-build-system)
4587 `(#:python ,python-2 ; does not work with Python 3
4588 #:tests? #f)) ; there are no tests
4590 `(("python2-matplotlib" ,python2-matplotlib)))
4591 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4592 (synopsis "Analyze high-throughput genetic sequencing data")
4594 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4595 sequencing data. It works with genomic coordinates. There are currently six
4596 different command-line tools:
4599 @item pyicoregion: for generating exploratory regions automatically;
4600 @item pyicoenrich: for differential enrichment between two conditions;
4601 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4602 @item pyicos: for genomic coordinates manipulation;
4603 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4604 @item pyicount: to count how many reads from N experiment files overlap in a
4606 @item pyicotrocol: to combine operations from pyicoteo.
4608 (license license:gpl3+)))
4610 (define-public prodigal
4617 "https://github.com/hyattpd/Prodigal/archive/v"
4619 (file-name (string-append name "-" version ".tar.gz"))
4622 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4623 (build-system gnu-build-system)
4625 `(#:tests? #f ;no check target
4626 #:make-flags (list (string-append "INSTALLDIR="
4627 (assoc-ref %outputs "out")
4630 (modify-phases %standard-phases
4631 (delete 'configure))))
4632 (home-page "http://prodigal.ornl.gov")
4633 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4635 "Prodigal runs smoothly on finished genomes, draft genomes, and
4636 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4637 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4638 partial genes, and identifies translation initiation sites.")
4639 (license license:gpl3+)))
4641 (define-public roary
4649 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4653 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4654 (build-system perl-build-system)
4657 (modify-phases %standard-phases
4662 ;; The tests are not run by default, so we run each test file
4664 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4666 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4667 (getenv "PERL5LIB")))
4668 (zero? (length (filter (lambda (file)
4669 (display file)(display "\n")
4670 (not (zero? (system* "perl" file))))
4671 (find-files "t" ".*\\.t$"))))))
4673 ;; There is no 'install' target in the Makefile.
4674 (lambda* (#:key outputs #:allow-other-keys)
4675 (let* ((out (assoc-ref outputs "out"))
4676 (bin (string-append out "/bin"))
4677 (perl (string-append out "/lib/perl5/site_perl"))
4678 (roary-plots "contrib/roary_plots"))
4681 (copy-recursively "bin" bin)
4682 (copy-recursively "lib" perl)
4684 (add-after 'install 'wrap-programs
4685 (lambda* (#:key inputs outputs #:allow-other-keys)
4686 (let* ((out (assoc-ref outputs "out"))
4687 (perl5lib (getenv "PERL5LIB"))
4688 (path (getenv "PATH")))
4689 (for-each (lambda (prog)
4690 (let ((binary (string-append out "/" prog)))
4691 (wrap-program binary
4692 `("PERL5LIB" ":" prefix
4693 (,(string-append perl5lib ":" out
4694 "/lib/perl5/site_perl"))))
4695 (wrap-program binary
4697 (,(string-append path ":" out "/bin"))))))
4698 (find-files "bin" ".*[^R]$"))
4700 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4701 (r-site-lib (getenv "R_LIBS_SITE"))
4703 (string-append (assoc-ref inputs "coreutils") "/bin")))
4705 `("R_LIBS_SITE" ":" prefix
4706 (,(string-append r-site-lib ":" out "/site-library/"))))
4709 (,(string-append coreutils-path ":" out "/bin"))))))
4712 `(("perl-env-path" ,perl-env-path)
4713 ("perl-test-files" ,perl-test-files)
4714 ("perl-test-most" ,perl-test-most)
4715 ("perl-test-output" ,perl-test-output)))
4717 `(("perl-array-utils" ,perl-array-utils)
4718 ("bioperl" ,bioperl-minimal)
4719 ("perl-digest-md5-file" ,perl-digest-md5-file)
4720 ("perl-exception-class" ,perl-exception-class)
4721 ("perl-file-find-rule" ,perl-file-find-rule)
4722 ("perl-file-grep" ,perl-file-grep)
4723 ("perl-file-slurper" ,perl-file-slurper)
4724 ("perl-file-which" ,perl-file-which)
4725 ("perl-graph" ,perl-graph)
4726 ("perl-graph-readwrite" ,perl-graph-readwrite)
4727 ("perl-log-log4perl" ,perl-log-log4perl)
4728 ("perl-moose" ,perl-moose)
4729 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4730 ("perl-text-csv" ,perl-text-csv)
4731 ("bedtools" ,bedtools)
4735 ("parallel" ,parallel)
4738 ("fasttree" ,fasttree)
4742 ("r-minimal" ,r-minimal)
4743 ("r-ggplot2" ,r-ggplot2)
4744 ("coreutils" ,coreutils)))
4745 (home-page "http://sanger-pathogens.github.io/Roary")
4746 (synopsis "High speed stand-alone pan genome pipeline")
4748 "Roary is a high speed stand alone pan genome pipeline, which takes
4749 annotated assemblies in GFF3 format (produced by the Prokka program) and
4750 calculates the pan genome. Using a standard desktop PC, it can analyse
4751 datasets with thousands of samples, without compromising the quality of the
4752 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4753 single processor. Roary is not intended for metagenomics or for comparing
4754 extremely diverse sets of genomes.")
4755 (license license:gpl3)))
4757 (define-public raxml
4766 "https://github.com/stamatak/standard-RAxML/archive/v"
4768 (file-name (string-append name "-" version ".tar.gz"))
4771 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4772 (build-system gnu-build-system)
4774 `(#:tests? #f ; There are no tests.
4775 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4776 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4778 (modify-phases %standard-phases
4781 (lambda* (#:key outputs #:allow-other-keys)
4782 (let* ((out (assoc-ref outputs "out"))
4783 (bin (string-append out "/bin"))
4784 (executable "raxmlHPC-HYBRID"))
4785 (install-file executable bin)
4786 (symlink (string-append bin "/" executable) "raxml"))
4789 `(("openmpi" ,openmpi)))
4790 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4791 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4793 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4795 ;; The source includes x86 specific code
4796 (supported-systems '("x86_64-linux" "i686-linux"))
4797 (license license:gpl2+)))
4807 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4810 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4811 (patches (search-patches "rsem-makefile.patch"))
4812 (modules '((guix build utils)))
4815 ;; remove bundled copy of boost
4816 (delete-file-recursively "boost")
4818 (build-system gnu-build-system)
4820 `(#:tests? #f ;no "check" target
4822 (modify-phases %standard-phases
4823 ;; No "configure" script.
4824 ;; Do not build bundled samtools library.
4827 (substitute* "Makefile"
4828 (("^all : sam/libbam.a") "all : "))
4831 (lambda* (#:key outputs #:allow-other-keys)
4832 (let* ((out (string-append (assoc-ref outputs "out")))
4833 (bin (string-append out "/bin/"))
4834 (perl (string-append out "/lib/perl5/site_perl")))
4837 (for-each (lambda (file)
4838 (install-file file bin))
4839 (find-files "." "rsem-.*"))
4840 (install-file "rsem_perl_utils.pm" perl))
4843 'install 'wrap-program
4844 (lambda* (#:key outputs #:allow-other-keys)
4845 (let ((out (assoc-ref outputs "out")))
4846 (for-each (lambda (prog)
4847 (wrap-program (string-append out "/bin/" prog)
4848 `("PERL5LIB" ":" prefix
4849 (,(string-append out "/lib/perl5/site_perl")))))
4850 '("rsem-plot-transcript-wiggles"
4851 "rsem-calculate-expression"
4852 "rsem-generate-ngvector"
4854 "rsem-prepare-reference")))
4858 ("ncurses" ,ncurses)
4859 ("r-minimal" ,r-minimal)
4861 ("samtools" ,samtools-0.1)
4863 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4864 (synopsis "Estimate gene expression levels from RNA-Seq data")
4866 "RSEM is a software package for estimating gene and isoform expression
4867 levels from RNA-Seq data. The RSEM package provides a user-friendly
4868 interface, supports threads for parallel computation of the EM algorithm,
4869 single-end and paired-end read data, quality scores, variable-length reads and
4870 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4871 interval estimates for expression levels. For visualization, it can generate
4872 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4873 (license license:gpl3+)))
4875 (define-public rseqc
4883 (string-append "mirror://sourceforge/rseqc/"
4884 "RSeQC-" version ".tar.gz"))
4886 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4887 (modules '((guix build utils)))
4890 ;; remove bundled copy of pysam
4891 (delete-file-recursively "lib/pysam")
4892 (substitute* "setup.py"
4893 ;; remove dependency on outdated "distribute" module
4894 (("^from distribute_setup import use_setuptools") "")
4895 (("^use_setuptools\\(\\)") "")
4896 ;; do not use bundled copy of pysam
4897 (("^have_pysam = False") "have_pysam = True"))
4899 (build-system python-build-system)
4900 (arguments `(#:python ,python-2))
4902 `(("python-cython" ,python2-cython)
4903 ("python-pysam" ,python2-pysam)
4904 ("python-numpy" ,python2-numpy)
4907 `(("python-nose" ,python2-nose)))
4908 (home-page "http://rseqc.sourceforge.net/")
4909 (synopsis "RNA-seq quality control package")
4911 "RSeQC provides a number of modules that can comprehensively evaluate
4912 high throughput sequence data, especially RNA-seq data. Some basic modules
4913 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4914 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4915 distribution, coverage uniformity, strand specificity, etc.")
4916 (license license:gpl3+)))
4919 ;; There are no release tarballs. According to the installation
4920 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4921 ;; stable release is identified by this changeset ID.
4922 (let ((changeset "2329130")
4926 (version (string-append "0-" revision "." changeset))
4930 (url "https://bitbucket.org/libsleipnir/sleipnir")
4931 (changeset changeset)))
4932 (file-name (string-append name "-" version "-checkout"))
4935 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4936 (build-system gnu-build-system)
4938 `(#:modules ((srfi srfi-1)
4939 (guix build gnu-build-system)
4942 (let ((dirs '("SeekMiner"
4948 (modify-phases %standard-phases
4951 (invoke "bash" "gen_auto")))
4952 (add-after 'build 'build-additional-tools
4953 (lambda* (#:key make-flags #:allow-other-keys)
4954 (every (lambda (dir)
4955 (with-directory-excursion (string-append "tools/" dir)
4956 (zero? (apply system* "make" make-flags))))
4958 (add-after 'install 'install-additional-tools
4959 (lambda* (#:key make-flags #:allow-other-keys)
4960 (fold (lambda (dir result)
4961 (with-directory-excursion (string-append "tools/" dir)
4963 (zero? (apply system*
4964 `("make" ,@make-flags "install"))))))
4970 ("readline" ,readline)
4971 ("gengetopt" ,gengetopt)
4972 ("log4cpp" ,log4cpp)))
4974 `(("autoconf" ,autoconf)
4975 ("automake" ,automake)
4977 (home-page "http://seek.princeton.edu")
4978 (synopsis "Gene co-expression search engine")
4980 "SEEK is a computational gene co-expression search engine. SEEK provides
4981 biologists with a way to navigate the massive human expression compendium that
4982 now contains thousands of expression datasets. SEEK returns a robust ranking
4983 of co-expressed genes in the biological area of interest defined by the user's
4984 query genes. It also prioritizes thousands of expression datasets according
4985 to the user's query of interest.")
4986 (license license:cc-by3.0))))
4988 (define-public samtools
4996 (string-append "mirror://sourceforge/samtools/samtools/"
4997 version "/samtools-" version ".tar.bz2"))
5000 "05myg7bs90i68qbqab9cdg9rqj2xh39azibrx82ipzc5kcfvqhn9"))))
5001 (build-system gnu-build-system)
5003 `(#:modules ((ice-9 ftw)
5005 (guix build gnu-build-system)
5007 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
5008 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
5010 (modify-phases %standard-phases
5011 (add-after 'unpack 'patch-tests
5013 (substitute* "test/test.pl"
5014 ;; The test script calls out to /bin/bash
5015 (("/bin/bash") (which "bash")))
5017 (add-after 'install 'install-library
5018 (lambda* (#:key outputs #:allow-other-keys)
5019 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5020 (install-file "libbam.a" lib)
5022 (add-after 'install 'install-headers
5023 (lambda* (#:key outputs #:allow-other-keys)
5024 (let ((include (string-append (assoc-ref outputs "out")
5025 "/include/samtools/")))
5026 (for-each (lambda (file)
5027 (install-file file include))
5028 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5030 (native-inputs `(("pkg-config" ,pkg-config)))
5032 `(("htslib" ,htslib)
5033 ("ncurses" ,ncurses)
5037 (home-page "http://samtools.sourceforge.net")
5038 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5040 "Samtools implements various utilities for post-processing nucleotide
5041 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5042 variant calling (in conjunction with bcftools), and a simple alignment
5044 (license license:expat)))
5046 (define-public samtools-0.1
5047 ;; This is the most recent version of the 0.1 line of samtools. The input
5048 ;; and output formats differ greatly from that used and produced by samtools
5049 ;; 1.x and is still used in many bioinformatics pipelines.
5050 (package (inherit samtools)
5056 (string-append "mirror://sourceforge/samtools/samtools/"
5057 version "/samtools-" version ".tar.bz2"))
5059 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5061 `(#:tests? #f ;no "check" target
5062 ,@(substitute-keyword-arguments (package-arguments samtools)
5063 ((#:make-flags flags)
5064 `(cons "LIBCURSES=-lncurses" ,flags))
5066 `(modify-phases ,phases
5068 (lambda* (#:key outputs #:allow-other-keys)
5069 (let ((bin (string-append
5070 (assoc-ref outputs "out") "/bin")))
5072 (install-file "samtools" bin)
5074 (delete 'patch-tests)
5075 (delete 'configure))))))))
5077 (define-public mosaik
5078 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5083 ;; There are no release tarballs nor tags.
5086 (url "https://github.com/wanpinglee/MOSAIK.git")
5088 (file-name (string-append name "-" version))
5091 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5092 (build-system gnu-build-system)
5094 `(#:tests? #f ; no tests
5095 #:make-flags (list "CC=gcc")
5097 (modify-phases %standard-phases
5099 (lambda _ (chdir "src") #t))
5101 (lambda* (#:key outputs #:allow-other-keys)
5102 (let ((bin (string-append (assoc-ref outputs "out")
5105 (copy-recursively "../bin" bin)
5110 (supported-systems '("x86_64-linux"))
5111 (home-page "https://github.com/wanpinglee/MOSAIK")
5112 (synopsis "Map nucleotide sequence reads to reference genomes")
5114 "MOSAIK is a program for mapping second and third-generation sequencing
5115 reads to a reference genome. MOSAIK can align reads generated by all the
5116 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5117 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5118 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5119 ;; code released into the public domain:
5120 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5121 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5122 (license (list license:gpl2+ license:public-domain)))))
5124 (define-public ngs-sdk
5132 (string-append "https://github.com/ncbi/ngs/archive/"
5134 (file-name (string-append name "-" version ".tar.gz"))
5137 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5138 (build-system gnu-build-system)
5140 `(#:parallel-build? #f ; not supported
5141 #:tests? #f ; no "check" target
5143 (modify-phases %standard-phases
5145 (lambda* (#:key outputs #:allow-other-keys)
5146 (let ((out (assoc-ref outputs "out")))
5147 ;; Allow 'konfigure.perl' to find 'package.prl'.
5149 (string-append ".:" (getenv "PERL5LIB")))
5151 ;; The 'configure' script doesn't recognize things like
5152 ;; '--enable-fast-install'.
5153 (zero? (system* "./configure"
5154 (string-append "--build-prefix=" (getcwd) "/build")
5155 (string-append "--prefix=" out))))))
5156 (add-after 'unpack 'enter-dir
5157 (lambda _ (chdir "ngs-sdk") #t)))))
5158 (native-inputs `(("perl" ,perl)))
5159 ;; According to the test
5160 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5161 ;; in ngs-sdk/setup/konfigure.perl
5162 (supported-systems '("i686-linux" "x86_64-linux"))
5163 (home-page "https://github.com/ncbi/ngs")
5164 (synopsis "API for accessing Next Generation Sequencing data")
5166 "NGS is a domain-specific API for accessing reads, alignments and pileups
5167 produced from Next Generation Sequencing. The API itself is independent from
5168 any particular back-end implementation, and supports use of multiple back-ends
5170 (license license:public-domain)))
5172 (define-public java-ngs
5173 (package (inherit ngs-sdk)
5176 `(,@(substitute-keyword-arguments
5177 `(#:modules ((guix build gnu-build-system)
5181 ,@(package-arguments ngs-sdk))
5183 `(modify-phases ,phases
5184 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5186 `(("jdk" ,icedtea "jdk")
5187 ("ngs-sdk" ,ngs-sdk)))
5188 (synopsis "Java bindings for NGS SDK")))
5190 (define-public ncbi-vdb
5198 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5200 (file-name (string-append name "-" version ".tar.gz"))
5203 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5204 (build-system gnu-build-system)
5206 `(#:parallel-build? #f ; not supported
5207 #:tests? #f ; no "check" target
5209 (modify-phases %standard-phases
5210 (add-before 'configure 'set-perl-search-path
5212 ;; Work around "dotless @INC" build failure.
5214 (string-append (getcwd) "/setup:"
5215 (getenv "PERL5LIB")))
5218 (lambda* (#:key inputs outputs #:allow-other-keys)
5219 (let ((out (assoc-ref outputs "out")))
5220 ;; Override include path for libmagic
5221 (substitute* "setup/package.prl"
5222 (("name => 'magic', Include => '/usr/include'")
5223 (string-append "name=> 'magic', Include => '"
5224 (assoc-ref inputs "libmagic")
5227 ;; Install kdf5 library (needed by sra-tools)
5228 (substitute* "build/Makefile.install"
5229 (("LIBRARIES_TO_INSTALL =")
5230 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5232 (substitute* "build/Makefile.env"
5233 (("CFLAGS =" prefix)
5234 (string-append prefix "-msse2 ")))
5236 ;; Override search path for ngs-java
5237 (substitute* "setup/package.prl"
5238 (("/usr/local/ngs/ngs-java")
5239 (assoc-ref inputs "java-ngs")))
5241 ;; The 'configure' script doesn't recognize things like
5242 ;; '--enable-fast-install'.
5245 (string-append "--build-prefix=" (getcwd) "/build")
5246 (string-append "--prefix=" (assoc-ref outputs "out"))
5247 (string-append "--debug")
5248 (string-append "--with-xml2-prefix="
5249 (assoc-ref inputs "libxml2"))
5250 (string-append "--with-ngs-sdk-prefix="
5251 (assoc-ref inputs "ngs-sdk"))
5252 (string-append "--with-hdf5-prefix="
5253 (assoc-ref inputs "hdf5")))))))
5254 (add-after 'install 'install-interfaces
5255 (lambda* (#:key outputs #:allow-other-keys)
5256 ;; Install interface libraries. On i686 the interface libraries
5257 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5258 ;; architecture name ("i386") instead of the target system prefix
5260 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5261 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5262 ,(system->linux-architecture
5263 (or (%current-target-system)
5266 (string-append (assoc-ref outputs "out")
5268 ;; Install interface headers
5269 (copy-recursively "interfaces"
5270 (string-append (assoc-ref outputs "out")
5273 ;; These files are needed by sra-tools.
5274 (add-after 'install 'install-configuration-files
5275 (lambda* (#:key outputs #:allow-other-keys)
5276 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5278 (install-file "libs/kfg/default.kfg" target)
5279 (install-file "libs/kfg/certs.kfg" target))
5282 `(("libxml2" ,libxml2)
5283 ("ngs-sdk" ,ngs-sdk)
5284 ("java-ngs" ,java-ngs)
5287 (native-inputs `(("perl" ,perl)))
5288 ;; NCBI-VDB requires SSE capability.
5289 (supported-systems '("i686-linux" "x86_64-linux"))
5290 (home-page "https://github.com/ncbi/ncbi-vdb")
5291 (synopsis "Database engine for genetic information")
5293 "The NCBI-VDB library implements a highly compressed columnar data
5294 warehousing engine that is most often used to store genetic information.
5295 Databases are stored in a portable image within the file system, and can be
5296 accessed/downloaded on demand across HTTP.")
5297 (license license:public-domain)))
5299 (define-public plink
5307 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5308 version "-src.zip"))
5310 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5311 (patches (search-patches "plink-1.07-unclobber-i.patch"
5312 "plink-endian-detection.patch"))))
5313 (build-system gnu-build-system)
5315 '(#:tests? #f ;no "check" target
5316 #:make-flags (list (string-append "LIB_LAPACK="
5317 (assoc-ref %build-inputs "lapack")
5318 "/lib/liblapack.so")
5321 ;; disable phoning home
5324 (modify-phases %standard-phases
5325 ;; no "configure" script
5328 (lambda* (#:key outputs #:allow-other-keys)
5329 (let ((bin (string-append (assoc-ref outputs "out")
5331 (install-file "plink" bin)
5335 ("lapack" ,lapack)))
5337 `(("unzip" ,unzip)))
5338 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5339 (synopsis "Whole genome association analysis toolset")
5341 "PLINK is a whole genome association analysis toolset, designed to
5342 perform a range of basic, large-scale analyses in a computationally efficient
5343 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5344 so there is no support for steps prior to this (e.g. study design and
5345 planning, generating genotype or CNV calls from raw data). Through
5346 integration with gPLINK and Haploview, there is some support for the
5347 subsequent visualization, annotation and storage of results.")
5348 ;; Code is released under GPLv2, except for fisher.h, which is under
5350 (license (list license:gpl2 license:lgpl2.1+))))
5352 (define-public plink-ng
5353 (package (inherit plink)
5359 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5361 (file-name (string-append name "-" version ".tar.gz"))
5363 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5364 (build-system gnu-build-system)
5366 '(#:tests? #f ;no "check" target
5367 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5368 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5370 "-f" "Makefile.std")
5372 (modify-phases %standard-phases
5373 (add-after 'unpack 'chdir
5374 (lambda _ (chdir "1.9") #t))
5375 (delete 'configure) ; no "configure" script
5377 (lambda* (#:key outputs #:allow-other-keys)
5378 (let ((bin (string-append (assoc-ref outputs "out")
5380 (install-file "plink" bin)
5385 ("openblas" ,openblas)))
5386 (home-page "https://www.cog-genomics.org/plink/")
5387 (license license:gpl3+)))
5389 (define-public smithlab-cpp
5390 (let ((revision "1")
5391 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5393 (name "smithlab-cpp")
5394 (version (string-append "0." revision "." (string-take commit 7)))
5398 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5400 (file-name (string-append name "-" version "-checkout"))
5403 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5404 (build-system gnu-build-system)
5406 `(#:modules ((guix build gnu-build-system)
5409 #:tests? #f ;no "check" target
5411 (modify-phases %standard-phases
5412 (add-after 'unpack 'use-samtools-headers
5414 (substitute* '("SAM.cpp"
5416 (("sam.h") "samtools/sam.h"))
5419 (lambda* (#:key outputs #:allow-other-keys)
5420 (let* ((out (assoc-ref outputs "out"))
5421 (lib (string-append out "/lib"))
5422 (include (string-append out "/include/smithlab-cpp")))
5425 (for-each (cut install-file <> lib)
5426 (find-files "." "\\.o$"))
5427 (for-each (cut install-file <> include)
5428 (find-files "." "\\.hpp$")))
5430 (delete 'configure))))
5432 `(("samtools" ,samtools-0.1)
5434 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5435 (synopsis "C++ helper library for functions used in Smith lab projects")
5437 "Smithlab CPP is a C++ library that includes functions used in many of
5438 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5439 structures, classes for genomic regions, mapped sequencing reads, etc.")
5440 (license license:gpl3+))))
5442 (define-public preseq
5448 (uri (string-append "https://github.com/smithlabcode/"
5449 "preseq/archive/v" version ".tar.gz"))
5450 (file-name (string-append name "-" version ".tar.gz"))
5452 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5453 (modules '((guix build utils)))
5455 ;; Remove bundled samtools.
5456 (delete-file-recursively "samtools")
5458 (build-system gnu-build-system)
5460 `(#:tests? #f ;no "check" target
5462 (modify-phases %standard-phases
5463 (delete 'configure))
5465 (list (string-append "PREFIX="
5466 (assoc-ref %outputs "out"))
5467 (string-append "LIBBAM="
5468 (assoc-ref %build-inputs "samtools")
5470 (string-append "SMITHLAB_CPP="
5471 (assoc-ref %build-inputs "smithlab-cpp")
5474 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5477 ("samtools" ,samtools-0.1)
5478 ("smithlab-cpp" ,smithlab-cpp)
5480 (home-page "http://smithlabresearch.org/software/preseq/")
5481 (synopsis "Program for analyzing library complexity")
5483 "The preseq package is aimed at predicting and estimating the complexity
5484 of a genomic sequencing library, equivalent to predicting and estimating the
5485 number of redundant reads from a given sequencing depth and how many will be
5486 expected from additional sequencing using an initial sequencing experiment.
5487 The estimates can then be used to examine the utility of further sequencing,
5488 optimize the sequencing depth, or to screen multiple libraries to avoid low
5489 complexity samples.")
5490 (license license:gpl3+)))
5492 (define-public python-screed
5494 (name "python-screed")
5499 (uri (pypi-uri "screed" version))
5502 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5503 (build-system python-build-system)
5506 (modify-phases %standard-phases
5509 (setenv "PYTHONPATH"
5510 (string-append (getenv "PYTHONPATH") ":."))
5511 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5513 `(("python-nose" ,python-nose)))
5515 `(("python-bz2file" ,python-bz2file)))
5516 (home-page "https://github.com/dib-lab/screed/")
5517 (synopsis "Short read sequence database utilities")
5518 (description "Screed parses FASTA and FASTQ files and generates databases.
5519 Values such as sequence name, sequence description, sequence quality and the
5520 sequence itself can be retrieved from these databases.")
5521 (license license:bsd-3)))
5523 (define-public python2-screed
5524 (package-with-python2 python-screed))
5526 (define-public sra-tools
5534 (string-append "https://github.com/ncbi/sra-tools/archive/"
5536 (file-name (string-append name "-" version ".tar.gz"))
5539 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5540 (build-system gnu-build-system)
5542 `(#:parallel-build? #f ; not supported
5543 #:tests? #f ; no "check" target
5545 (list (string-append "DEFAULT_CRT="
5546 (assoc-ref %build-inputs "ncbi-vdb")
5548 (string-append "DEFAULT_KFG="
5549 (assoc-ref %build-inputs "ncbi-vdb")
5551 (string-append "VDB_LIBDIR="
5552 (assoc-ref %build-inputs "ncbi-vdb")
5553 ,(if (string-prefix? "x86_64"
5554 (or (%current-target-system)
5559 (modify-phases %standard-phases
5560 (add-before 'configure 'set-perl-search-path
5562 ;; Work around "dotless @INC" build failure.
5564 (string-append (getcwd) "/setup:"
5565 (getenv "PERL5LIB")))
5568 (lambda* (#:key inputs outputs #:allow-other-keys)
5569 ;; The build system expects a directory containing the sources and
5570 ;; raw build output of ncbi-vdb, including files that are not
5571 ;; installed. Since we are building against an installed version of
5572 ;; ncbi-vdb, the following modifications are needed.
5573 (substitute* "setup/konfigure.perl"
5574 ;; Make the configure script look for the "ilib" directory of
5575 ;; "ncbi-vdb" without first checking for the existence of a
5576 ;; matching library in its "lib" directory.
5577 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5578 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5579 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5580 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5581 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5584 (substitute* "tools/copycat/Makefile"
5585 (("smagic-static") "lmagic"))
5587 ;; The 'configure' script doesn't recognize things like
5588 ;; '--enable-fast-install'.
5591 (string-append "--build-prefix=" (getcwd) "/build")
5592 (string-append "--prefix=" (assoc-ref outputs "out"))
5593 (string-append "--debug")
5594 (string-append "--with-fuse-prefix="
5595 (assoc-ref inputs "fuse"))
5596 (string-append "--with-magic-prefix="
5597 (assoc-ref inputs "libmagic"))
5598 ;; TODO: building with libxml2 fails with linker errors
5599 ;; (string-append "--with-xml2-prefix="
5600 ;; (assoc-ref inputs "libxml2"))
5601 (string-append "--with-ncbi-vdb-sources="
5602 (assoc-ref inputs "ncbi-vdb"))
5603 (string-append "--with-ncbi-vdb-build="
5604 (assoc-ref inputs "ncbi-vdb"))
5605 (string-append "--with-ngs-sdk-prefix="
5606 (assoc-ref inputs "ngs-sdk"))
5607 (string-append "--with-hdf5-prefix="
5608 (assoc-ref inputs "hdf5"))))))
5609 ;; This version of sra-tools fails to build with glibc because of a
5610 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5611 ;; contains a definition of "canonicalize", so we rename it.
5613 ;; See upstream bug report:
5614 ;; https://github.com/ncbi/sra-tools/issues/67
5615 (add-after 'unpack 'patch-away-glibc-conflict
5617 (substitute* "tools/bam-loader/bam.c"
5618 (("canonicalize\\(" line)
5619 (string-append "sra_tools_" line)))
5621 (native-inputs `(("perl" ,perl)))
5623 `(("ngs-sdk" ,ngs-sdk)
5624 ("ncbi-vdb" ,ncbi-vdb)
5629 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5630 (synopsis "Tools and libraries for reading and writing sequencing data")
5632 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5633 reading of sequencing files from the Sequence Read Archive (SRA) database and
5634 writing files into the .sra format.")
5635 (license license:public-domain)))
5637 (define-public seqan
5643 (uri (string-append "http://packages.seqan.de/seqan-library/"
5644 "seqan-library-" version ".tar.bz2"))
5647 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5648 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5649 ;; makes sense to split the outputs.
5650 (outputs '("out" "doc"))
5651 (build-system trivial-build-system)
5653 `(#:modules ((guix build utils))
5656 (use-modules (guix build utils))
5657 (let ((tar (assoc-ref %build-inputs "tar"))
5658 (bzip (assoc-ref %build-inputs "bzip2"))
5659 (out (assoc-ref %outputs "out"))
5660 (doc (assoc-ref %outputs "doc")))
5661 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5662 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5663 (chdir (string-append "seqan-library-" ,version))
5664 (copy-recursively "include" (string-append out "/include"))
5665 (copy-recursively "share" (string-append doc "/share"))
5668 `(("source" ,source)
5671 (home-page "http://www.seqan.de")
5672 (synopsis "Library for nucleotide sequence analysis")
5674 "SeqAn is a C++ library of efficient algorithms and data structures for
5675 the analysis of sequences with the focus on biological data. It contains
5676 algorithms and data structures for string representation and their
5677 manipulation, online and indexed string search, efficient I/O of
5678 bioinformatics file formats, sequence alignment, and more.")
5679 (license license:bsd-3)))
5681 (define-public seqmagick
5688 (uri (pypi-uri "seqmagick" version))
5691 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5692 (build-system python-build-system)
5694 `(("python-biopython" ,python-biopython)))
5696 `(("python-nose" ,python-nose)))
5697 (home-page "https://github.com/fhcrc/seqmagick")
5698 (synopsis "Tools for converting and modifying sequence files")
5700 "Bioinformaticians often have to convert sequence files between formats
5701 and do little manipulations on them, and it's not worth writing scripts for
5702 that. Seqmagick is a utility to expose the file format conversion in
5703 BioPython in a convenient way. Instead of having a big mess of scripts, there
5704 is one that takes arguments.")
5705 (license license:gpl3)))
5707 (define-public seqtk
5714 "https://github.com/lh3/seqtk/archive/v"
5716 (file-name (string-append name "-" version ".tar.gz"))
5719 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5720 (modules '((guix build utils)))
5723 ;; Remove extraneous header files, as is done in the seqtk
5725 (for-each (lambda (file) (delete-file file))
5726 (list "ksort.h" "kstring.h" "kvec.h"))
5728 (build-system gnu-build-system)
5731 (modify-phases %standard-phases
5734 ;; There are no tests, so we just run a sanity check.
5735 (lambda _ (zero? (system* "./seqtk" "seq"))))
5737 (lambda* (#:key outputs #:allow-other-keys)
5738 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5739 (install-file "seqtk" bin)))))))
5742 (home-page "https://github.com/lh3/seqtk")
5743 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5745 "Seqtk is a fast and lightweight tool for processing sequences in the
5746 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5747 optionally compressed by gzip.")
5748 (license license:expat)))
5750 (define-public snap-aligner
5752 (name "snap-aligner")
5753 (version "1.0beta.18")
5757 "https://github.com/amplab/snap/archive/v"
5759 (file-name (string-append name "-" version ".tar.gz"))
5762 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5763 (build-system gnu-build-system)
5766 (modify-phases %standard-phases
5768 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5770 (lambda* (#:key outputs #:allow-other-keys)
5771 (let* ((out (assoc-ref outputs "out"))
5772 (bin (string-append out "/bin")))
5773 (install-file "snap-aligner" bin)
5774 (install-file "SNAPCommand" bin)
5778 (home-page "http://snap.cs.berkeley.edu/")
5779 (synopsis "Short read DNA sequence aligner")
5781 "SNAP is a fast and accurate aligner for short DNA reads. It is
5782 optimized for modern read lengths of 100 bases or higher, and takes advantage
5783 of these reads to align data quickly through a hash-based indexing scheme.")
5784 ;; 32-bit systems are not supported by the unpatched code.
5785 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5786 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5787 ;; systems without a lot of memory cannot make good use of this program.
5788 (supported-systems '("x86_64-linux"))
5789 (license license:asl2.0)))
5791 (define-public sortmerna
5799 "https://github.com/biocore/sortmerna/archive/"
5801 (file-name (string-append name "-" version ".tar.gz"))
5804 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5805 (build-system gnu-build-system)
5806 (outputs '("out" ;for binaries
5807 "db")) ;for sequence databases
5810 (modify-phases %standard-phases
5812 (lambda* (#:key outputs #:allow-other-keys)
5813 (let* ((out (assoc-ref outputs "out"))
5814 (bin (string-append out "/bin"))
5815 (db (assoc-ref outputs "db"))
5817 (string-append db "/share/sortmerna/rRNA_databases")))
5818 (install-file "sortmerna" bin)
5819 (install-file "indexdb_rna" bin)
5820 (for-each (lambda (file)
5821 (install-file file share))
5822 (find-files "rRNA_databases" ".*fasta"))
5826 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5827 (synopsis "Biological sequence analysis tool for NGS reads")
5829 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5830 and operational taxonomic unit (OTU) picking of next generation
5831 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5832 allows for fast and sensitive analyses of nucleotide sequences. The main
5833 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5834 ;; The source includes x86 specific code
5835 (supported-systems '("x86_64-linux" "i686-linux"))
5836 (license license:lgpl3)))
5845 (url "https://github.com/alexdobin/STAR.git")
5847 (file-name (string-append name "-" version "-checkout"))
5850 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
5851 (modules '((guix build utils)))
5854 (substitute* "source/Makefile"
5856 ;; Remove pre-built binaries and bundled htslib sources.
5857 (delete-file-recursively "bin/MacOSX_x86_64")
5858 (delete-file-recursively "bin/Linux_x86_64")
5859 (delete-file-recursively "bin/Linux_x86_64_static")
5860 (delete-file-recursively "source/htslib")
5862 (build-system gnu-build-system)
5864 '(#:tests? #f ;no check target
5865 #:make-flags '("STAR")
5867 (modify-phases %standard-phases
5868 (add-after 'unpack 'enter-source-dir
5869 (lambda _ (chdir "source") #t))
5870 (add-after 'enter-source-dir 'make-reproducible
5872 (substitute* "Makefile"
5873 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5874 (string-append pre "Built with Guix" post)))))
5875 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5877 (substitute* "Makefile"
5878 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5880 (substitute* '("BAMfunctions.cpp"
5885 "bamRemoveDuplicates.cpp")
5886 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5887 (string-append "#include <" header ">")))
5888 (substitute* "IncludeDefine.h"
5889 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5890 (string-append "<" header ">")))
5893 (lambda* (#:key outputs #:allow-other-keys)
5894 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5895 (install-file "STAR" bin))
5897 (delete 'configure))))
5901 `(("htslib" ,htslib)
5903 (home-page "https://github.com/alexdobin/STAR")
5904 (synopsis "Universal RNA-seq aligner")
5906 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5907 based on a previously undescribed RNA-seq alignment algorithm that uses
5908 sequential maximum mappable seed search in uncompressed suffix arrays followed
5909 by seed clustering and stitching procedure. In addition to unbiased de novo
5910 detection of canonical junctions, STAR can discover non-canonical splices and
5911 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5913 ;; Only 64-bit systems are supported according to the README.
5914 (supported-systems '("x86_64-linux" "mips64el-linux"))
5915 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5916 (license license:gpl3+)))
5918 (define-public subread
5924 (uri (string-append "mirror://sourceforge/subread/subread-"
5925 version "/subread-" version "-source.tar.gz"))
5928 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5929 (build-system gnu-build-system)
5931 `(#:tests? #f ;no "check" target
5932 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5933 ;; optimizations by default, so we override these flags such that x86_64
5934 ;; flags are only added when the build target is an x86_64 system.
5936 (list (let ((system ,(or (%current-target-system)
5938 (flags '("-ggdb" "-fomit-frame-pointer"
5939 "-ffast-math" "-funroll-loops"
5940 "-fmessage-length=0"
5941 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5943 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5944 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5945 (if (string-prefix? "x86_64" system)
5946 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5947 (string-append "CCFLAGS=" (string-join flags))))
5948 "-f" "Makefile.Linux"
5949 "CC=gcc ${CCFLAGS}")
5951 (modify-phases %standard-phases
5952 (add-after 'unpack 'enter-dir
5953 (lambda _ (chdir "src") #t))
5955 (lambda* (#:key outputs #:allow-other-keys)
5956 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5958 (copy-recursively "../bin" bin))))
5959 ;; no "configure" script
5960 (delete 'configure))))
5961 (inputs `(("zlib" ,zlib)))
5962 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5963 (synopsis "Tool kit for processing next-gen sequencing data")
5965 "The subread package contains the following tools: subread aligner, a
5966 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5967 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5968 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5969 against local background noises.")
5970 (license license:gpl3+)))
5972 (define-public stringtie
5978 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5979 "stringtie-" version ".tar.gz"))
5982 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5983 (modules '((guix build utils)))
5986 (delete-file-recursively "samtools-0.1.18")
5988 (build-system gnu-build-system)
5990 `(#:tests? #f ;no test suite
5992 (modify-phases %standard-phases
5993 ;; no configure script
5995 (add-before 'build 'use-system-samtools
5997 (substitute* "Makefile"
5998 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6000 (substitute* '("gclib/GBam.h"
6002 (("#include \"(bam|sam|kstring).h\"" _ header)
6003 (string-append "#include <samtools/" header ".h>")))
6005 (add-after 'unpack 'remove-duplicate-typedef
6007 ;; This typedef conflicts with the typedef in
6008 ;; glibc-2.25/include/bits/types.h
6009 (substitute* "gclib/GThreads.h"
6010 (("typedef long long __intmax_t;") ""))
6013 (lambda* (#:key outputs #:allow-other-keys)
6014 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6015 (install-file "stringtie" bin)
6018 `(("samtools" ,samtools-0.1)
6020 (home-page "http://ccb.jhu.edu/software/stringtie/")
6021 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6023 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6024 alignments into potential transcripts. It uses a novel network flow algorithm
6025 as well as an optional de novo assembly step to assemble and quantitate
6026 full-length transcripts representing multiple splice variants for each gene
6027 locus. Its input can include not only the alignments of raw reads used by
6028 other transcript assemblers, but also alignments of longer sequences that have
6029 been assembled from those reads. To identify differentially expressed genes
6030 between experiments, StringTie's output can be processed either by the
6031 Cuffdiff or Ballgown programs.")
6032 (license license:artistic2.0)))
6034 (define-public taxtastic
6040 (uri (pypi-uri "taxtastic" version))
6043 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6044 (build-system python-build-system)
6046 `(#:python ,python-2
6048 (modify-phases %standard-phases
6051 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
6053 `(("python-sqlalchemy" ,python2-sqlalchemy)
6054 ("python-decorator" ,python2-decorator)
6055 ("python-biopython" ,python2-biopython)
6056 ("python-pandas" ,python2-pandas)
6057 ("python-psycopg2" ,python2-psycopg2)
6058 ("python-fastalite" ,python2-fastalite)
6059 ("python-pyyaml" ,python2-pyyaml)
6060 ("python-six" ,python2-six)
6061 ("python-jinja2" ,python2-jinja2)
6062 ("python-dendropy" ,python2-dendropy)))
6063 (home-page "https://github.com/fhcrc/taxtastic")
6064 (synopsis "Tools for taxonomic naming and annotation")
6066 "Taxtastic is software written in python used to build and maintain
6067 reference packages i.e. collections of reference trees, reference alignments,
6068 profiles, and associated taxonomic information.")
6069 (license license:gpl3+)))
6071 (define-public vcftools
6078 "https://github.com/vcftools/vcftools/releases/download/v"
6079 version "/vcftools-" version ".tar.gz"))
6082 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6083 (build-system gnu-build-system)
6085 `(#:tests? #f ; no "check" target
6087 "CFLAGS=-O2" ; override "-m64" flag
6088 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6089 (string-append "MANDIR=" (assoc-ref %outputs "out")
6090 "/share/man/man1"))))
6092 `(("pkg-config" ,pkg-config)))
6096 (home-page "https://vcftools.github.io/")
6097 (synopsis "Tools for working with VCF files")
6099 "VCFtools is a program package designed for working with VCF files, such
6100 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6101 provide easily accessible methods for working with complex genetic variation
6102 data in the form of VCF files.")
6103 ;; The license is declared as LGPLv3 in the README and
6104 ;; at https://vcftools.github.io/license.html
6105 (license license:lgpl3)))
6107 (define-public infernal
6113 (uri (string-append "http://eddylab.org/software/infernal/"
6114 "infernal-" version ".tar.gz"))
6117 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6118 (build-system gnu-build-system)
6120 `(("perl" ,perl))) ; for tests
6121 (home-page "http://eddylab.org/infernal/")
6122 (synopsis "Inference of RNA alignments")
6123 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6124 searching DNA sequence databases for RNA structure and sequence similarities.
6125 It is an implementation of a special case of profile stochastic context-free
6126 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6127 profile, but it scores a combination of sequence consensus and RNA secondary
6128 structure consensus, so in many cases, it is more capable of identifying RNA
6129 homologs that conserve their secondary structure more than their primary
6131 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6132 (supported-systems '("i686-linux" "x86_64-linux"))
6133 (license license:bsd-3)))
6135 (define-public r-centipede
6137 (name "r-centipede")
6141 (uri (string-append "http://download.r-forge.r-project.org/"
6142 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6145 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6146 (build-system r-build-system)
6147 (home-page "http://centipede.uchicago.edu/")
6148 (synopsis "Predict transcription factor binding sites")
6150 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6151 of the genome that are bound by particular transcription factors. It starts
6152 by identifying a set of candidate binding sites, and then aims to classify the
6153 sites according to whether each site is bound or not bound by a transcription
6154 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6155 between two different types of motif instances using as much relevant
6156 information as possible.")
6157 (license (list license:gpl2+ license:gpl3+))))
6159 (define-public r-vegan
6166 (uri (cran-uri "vegan" version))
6169 "13pyqvlpz64qibi8k5d109v7q09j06mbv6ndix3n4cn21mjx391c"))))
6170 (build-system r-build-system)
6172 `(("gfortran" ,gfortran)))
6174 `(("r-cluster" ,r-cluster)
6175 ("r-knitr" ,r-knitr) ; needed for vignettes
6176 ("r-lattice" ,r-lattice)
6179 ("r-permute" ,r-permute)))
6180 (home-page "https://cran.r-project.org/web/packages/vegan")
6181 (synopsis "Functions for community ecology")
6183 "The vegan package provides tools for descriptive community ecology. It
6184 has most basic functions of diversity analysis, community ordination and
6185 dissimilarity analysis. Most of its multivariate tools can be used for other
6186 data types as well.")
6187 (license license:gpl2+)))
6189 (define-public r-annotate
6196 (uri (bioconductor-uri "annotate" version))
6199 "1qmncyvy147a1ll3iri45p822kcs3s7583jfnq9jf6sz9ilk8cjf"))))
6200 (build-system r-build-system)
6202 `(("r-annotationdbi" ,r-annotationdbi)
6203 ("r-biobase" ,r-biobase)
6204 ("r-biocgenerics" ,r-biocgenerics)
6206 ("r-rcurl" ,r-rcurl)
6208 ("r-xtable" ,r-xtable)))
6210 "https://bioconductor.org/packages/annotate")
6211 (synopsis "Annotation for microarrays")
6212 (description "This package provides R environments for the annotation of
6214 (license license:artistic2.0)))
6216 (define-public r-copynumber
6218 (name "r-copynumber")
6222 (uri (bioconductor-uri "copynumber" version))
6225 "0y9nnwb0psphp3ix88wj2f8z5gr45r5znf55w892ysm27isdpmms"))))
6226 (build-system r-build-system)
6228 `(("r-s4vectors" ,r-s4vectors)
6229 ("r-iranges" ,r-iranges)
6230 ("r-genomicranges" ,r-genomicranges)
6231 ("r-biocgenerics" ,r-biocgenerics)))
6232 (home-page "https://bioconductor.org/packages/copynumber")
6233 (synopsis "Segmentation of single- and multi-track copy number data")
6235 "This package segments single- and multi-track copy number data by a
6236 penalized least squares regression method.")
6237 (license license:artistic2.0)))
6239 (define-public r-geneplotter
6241 (name "r-geneplotter")
6246 (uri (bioconductor-uri "geneplotter" version))
6249 "055g28xgiazl4l0gkg8xiamks64f5yckjjyvw1abd6d6qjavwx0g"))))
6250 (build-system r-build-system)
6252 `(("r-annotate" ,r-annotate)
6253 ("r-annotationdbi" ,r-annotationdbi)
6254 ("r-biobase" ,r-biobase)
6255 ("r-biocgenerics" ,r-biocgenerics)
6256 ("r-lattice" ,r-lattice)
6257 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6258 (home-page "https://bioconductor.org/packages/geneplotter")
6259 (synopsis "Graphics functions for genomic data")
6261 "This package provides functions for plotting genomic data.")
6262 (license license:artistic2.0)))
6264 (define-public r-genefilter
6266 (name "r-genefilter")
6271 (uri (bioconductor-uri "genefilter" version))
6274 "14l0ff02spmjwxj0m1czhg5vlkgwcfi73cym8m2n9vn6i7bjdaqi"))))
6275 (build-system r-build-system)
6277 `(("gfortran" ,gfortran)))
6279 `(("r-annotate" ,r-annotate)
6280 ("r-annotationdbi" ,r-annotationdbi)
6281 ("r-biobase" ,r-biobase)
6282 ("r-s4vectors" ,r-s4vectors)
6283 ("r-survival" ,r-survival)))
6284 (home-page "https://bioconductor.org/packages/genefilter")
6285 (synopsis "Filter genes from high-throughput experiments")
6287 "This package provides basic functions for filtering genes from
6288 high-throughput sequencing experiments.")
6289 (license license:artistic2.0)))
6291 (define-public r-deseq2
6298 (uri (bioconductor-uri "DESeq2" version))
6301 "1wjnfpb41a9mmf9a22bz4zh7r1d4id50vpdc1mn5vfzrz7li9qik"))))
6302 (properties `((upstream-name . "DESeq2")))
6303 (build-system r-build-system)
6305 `(("r-biobase" ,r-biobase)
6306 ("r-biocgenerics" ,r-biocgenerics)
6307 ("r-biocparallel" ,r-biocparallel)
6308 ("r-genefilter" ,r-genefilter)
6309 ("r-geneplotter" ,r-geneplotter)
6310 ("r-genomicranges" ,r-genomicranges)
6311 ("r-ggplot2" ,r-ggplot2)
6312 ("r-hmisc" ,r-hmisc)
6313 ("r-iranges" ,r-iranges)
6314 ("r-locfit" ,r-locfit)
6316 ("r-rcpparmadillo" ,r-rcpparmadillo)
6317 ("r-s4vectors" ,r-s4vectors)
6318 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6319 (home-page "https://bioconductor.org/packages/DESeq2")
6320 (synopsis "Differential gene expression analysis")
6322 "This package provides functions to estimate variance-mean dependence in
6323 count data from high-throughput nucleotide sequencing assays and test for
6324 differential expression based on a model using the negative binomial
6326 (license license:lgpl3+)))
6328 (define-public r-dexseq
6335 (uri (bioconductor-uri "DEXSeq" version))
6338 "1mqb3mdxcsi3largsl7k27bvqrgps9ixv806xvmf29pw0xn05sg1"))))
6339 (properties `((upstream-name . "DEXSeq")))
6340 (build-system r-build-system)
6342 `(("r-annotationdbi" ,r-annotationdbi)
6343 ("r-biobase" ,r-biobase)
6344 ("r-biocgenerics" ,r-biocgenerics)
6345 ("r-biocparallel" ,r-biocparallel)
6346 ("r-biomart" ,r-biomart)
6347 ("r-deseq2" ,r-deseq2)
6348 ("r-genefilter" ,r-genefilter)
6349 ("r-geneplotter" ,r-geneplotter)
6350 ("r-genomicranges" ,r-genomicranges)
6351 ("r-hwriter" ,r-hwriter)
6352 ("r-iranges" ,r-iranges)
6353 ("r-rcolorbrewer" ,r-rcolorbrewer)
6354 ("r-rsamtools" ,r-rsamtools)
6355 ("r-s4vectors" ,r-s4vectors)
6356 ("r-statmod" ,r-statmod)
6357 ("r-stringr" ,r-stringr)
6358 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6359 (home-page "https://bioconductor.org/packages/DEXSeq")
6360 (synopsis "Inference of differential exon usage in RNA-Seq")
6362 "This package is focused on finding differential exon usage using RNA-seq
6363 exon counts between samples with different experimental designs. It provides
6364 functions that allows the user to make the necessary statistical tests based
6365 on a model that uses the negative binomial distribution to estimate the
6366 variance between biological replicates and generalized linear models for
6367 testing. The package also provides functions for the visualization and
6368 exploration of the results.")
6369 (license license:gpl3+)))
6371 (define-public r-annotationforge
6373 (name "r-annotationforge")
6378 (uri (bioconductor-uri "AnnotationForge" version))
6381 "17kmy7nvpyyj6w5jyrjciw87rydmmmc8q6cnwqjv1j7li9bp09gr"))))
6383 `((upstream-name . "AnnotationForge")))
6384 (build-system r-build-system)
6386 `(("r-annotationdbi" ,r-annotationdbi)
6387 ("r-biobase" ,r-biobase)
6388 ("r-biocgenerics" ,r-biocgenerics)
6390 ("r-rcurl" ,r-rcurl)
6391 ("r-rsqlite" ,r-rsqlite)
6392 ("r-s4vectors" ,r-s4vectors)
6394 (home-page "https://bioconductor.org/packages/AnnotationForge")
6395 (synopsis "Code for building annotation database packages")
6397 "This package provides code for generating Annotation packages and their
6398 databases. Packages produced are intended to be used with AnnotationDbi.")
6399 (license license:artistic2.0)))
6401 (define-public r-rbgl
6408 (uri (bioconductor-uri "RBGL" version))
6411 "0hj972mmqpyi5fx1rq33kysavdyz4nspi6gcffzi3rv339m0anhf"))))
6412 (properties `((upstream-name . "RBGL")))
6413 (build-system r-build-system)
6414 (propagated-inputs `(("r-graph" ,r-graph)))
6415 (home-page "https://www.bioconductor.org/packages/RBGL")
6416 (synopsis "Interface to the Boost graph library")
6418 "This package provides a fairly extensive and comprehensive interface to
6419 the graph algorithms contained in the Boost library.")
6420 (license license:artistic2.0)))
6422 (define-public r-gseabase
6429 (uri (bioconductor-uri "GSEABase" version))
6432 "11bv92svik399q677jv96b71i4bq68xxyxn1yijpdik2lq4hgl7a"))))
6433 (properties `((upstream-name . "GSEABase")))
6434 (build-system r-build-system)
6436 `(("r-annotate" ,r-annotate)
6437 ("r-annotationdbi" ,r-annotationdbi)
6438 ("r-biobase" ,r-biobase)
6439 ("r-biocgenerics" ,r-biocgenerics)
6440 ("r-graph" ,r-graph)
6442 (home-page "https://bioconductor.org/packages/GSEABase")
6443 (synopsis "Gene set enrichment data structures and methods")
6445 "This package provides classes and methods to support @dfn{Gene Set
6446 Enrichment Analysis} (GSEA).")
6447 (license license:artistic2.0)))
6449 (define-public r-category
6456 (uri (bioconductor-uri "Category" version))
6459 "03wfqa8d1dgwsm327zl2mpkq7dq3mzhq12598qz3ylfhrwplbgx0"))))
6460 (properties `((upstream-name . "Category")))
6461 (build-system r-build-system)
6463 `(("r-annotate" ,r-annotate)
6464 ("r-annotationdbi" ,r-annotationdbi)
6465 ("r-biobase" ,r-biobase)
6466 ("r-biocgenerics" ,r-biocgenerics)
6467 ("r-genefilter" ,r-genefilter)
6468 ("r-graph" ,r-graph)
6469 ("r-gseabase" ,r-gseabase)
6470 ("r-matrix" ,r-matrix)
6473 (home-page "https://bioconductor.org/packages/Category")
6474 (synopsis "Category analysis")
6476 "This package provides a collection of tools for performing category
6478 (license license:artistic2.0)))
6480 (define-public r-gostats
6487 (uri (bioconductor-uri "GOstats" version))
6490 "1i5mydz5d95w2k28qr9j01hmbnl2id55jq94jvcpcyp1pvinkdq0"))))
6491 (properties `((upstream-name . "GOstats")))
6492 (build-system r-build-system)
6494 `(("r-annotate" ,r-annotate)
6495 ("r-annotationdbi" ,r-annotationdbi)
6496 ("r-annotationforge" ,r-annotationforge)
6497 ("r-biobase" ,r-biobase)
6498 ("r-category" ,r-category)
6499 ("r-go-db" ,r-go-db)
6500 ("r-graph" ,r-graph)
6501 ("r-rgraphviz" ,r-rgraphviz)
6502 ("r-rbgl" ,r-rbgl)))
6503 (home-page "https://bioconductor.org/packages/GOstats")
6504 (synopsis "Tools for manipulating GO and microarrays")
6506 "This package provides a set of tools for interacting with GO and
6507 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6508 testing and other simple calculations.")
6509 (license license:artistic2.0)))
6511 (define-public r-shortread
6513 (name "r-shortread")
6518 (uri (bioconductor-uri "ShortRead" version))
6521 "038z3z7qaw5bpgjzy91sjkybsny6jwjjsrnnq4gdqdw9ss1qy1fb"))))
6522 (properties `((upstream-name . "ShortRead")))
6523 (build-system r-build-system)
6527 `(("r-biobase" ,r-biobase)
6528 ("r-biocgenerics" ,r-biocgenerics)
6529 ("r-biocparallel" ,r-biocparallel)
6530 ("r-biostrings" ,r-biostrings)
6531 ("r-genomeinfodb" ,r-genomeinfodb)
6532 ("r-genomicalignments" ,r-genomicalignments)
6533 ("r-genomicranges" ,r-genomicranges)
6534 ("r-hwriter" ,r-hwriter)
6535 ("r-iranges" ,r-iranges)
6536 ("r-lattice" ,r-lattice)
6537 ("r-latticeextra" ,r-latticeextra)
6538 ("r-rsamtools" ,r-rsamtools)
6539 ("r-s4vectors" ,r-s4vectors)
6540 ("r-xvector" ,r-xvector)
6541 ("r-zlibbioc" ,r-zlibbioc)))
6542 (home-page "https://bioconductor.org/packages/ShortRead")
6543 (synopsis "FASTQ input and manipulation tools")
6545 "This package implements sampling, iteration, and input of FASTQ files.
6546 It includes functions for filtering and trimming reads, and for generating a
6547 quality assessment report. Data are represented as
6548 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6549 purposes. The package also contains legacy support for early single-end,
6550 ungapped alignment formats.")
6551 (license license:artistic2.0)))
6553 (define-public r-systempiper
6555 (name "r-systempiper")
6560 (uri (bioconductor-uri "systemPipeR" version))
6563 "1550pd63mmky0vgkmpni7zf14kqz1741wv63nfaw29kcmhh3m5lm"))))
6564 (properties `((upstream-name . "systemPipeR")))
6565 (build-system r-build-system)
6567 `(("r-annotate" ,r-annotate)
6568 ("r-batchjobs" ,r-batchjobs)
6569 ("r-biocgenerics" ,r-biocgenerics)
6570 ("r-biostrings" ,r-biostrings)
6571 ("r-deseq2" ,r-deseq2)
6572 ("r-edger" ,r-edger)
6573 ("r-genomicfeatures" ,r-genomicfeatures)
6574 ("r-genomicranges" ,r-genomicranges)
6575 ("r-ggplot2" ,r-ggplot2)
6576 ("r-go-db" ,r-go-db)
6577 ("r-gostats" ,r-gostats)
6578 ("r-limma" ,r-limma)
6579 ("r-pheatmap" ,r-pheatmap)
6580 ("r-rjson" ,r-rjson)
6581 ("r-rsamtools" ,r-rsamtools)
6582 ("r-shortread" ,r-shortread)
6583 ("r-summarizedexperiment" ,r-summarizedexperiment)
6584 ("r-variantannotation" ,r-variantannotation)))
6585 (home-page "https://github.com/tgirke/systemPipeR")
6586 (synopsis "Next generation sequencing workflow and reporting environment")
6588 "This R package provides tools for building and running automated
6589 end-to-end analysis workflows for a wide range of @dfn{next generation
6590 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6591 Important features include a uniform workflow interface across different NGS
6592 applications, automated report generation, and support for running both R and
6593 command-line software, such as NGS aligners or peak/variant callers, on local
6594 computers or compute clusters. Efficient handling of complex sample sets and
6595 experimental designs is facilitated by a consistently implemented sample
6596 annotation infrastructure.")
6597 (license license:artistic2.0)))
6599 (define-public r-grohmm
6606 (uri (bioconductor-uri "groHMM" version))
6609 "1kjb14apyly44qdlx2ld6gr69wlazd4mbhs58l35hir12aphgrzp"))))
6610 (properties `((upstream-name . "groHMM")))
6611 (build-system r-build-system)
6613 `(("r-genomeinfodb" ,r-genomeinfodb)
6614 ("r-genomicalignments" ,r-genomicalignments)
6615 ("r-genomicranges" ,r-genomicranges)
6616 ("r-iranges" ,r-iranges)
6618 ("r-rtracklayer" ,r-rtracklayer)
6619 ("r-s4vectors" ,r-s4vectors)))
6620 (home-page "https://github.com/Kraus-Lab/groHMM")
6621 (synopsis "GRO-seq analysis pipeline")
6623 "This package provides a pipeline for the analysis of GRO-seq data.")
6624 (license license:gpl3+)))
6626 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6628 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6632 ;; We cannot use bioconductor-uri here because this tarball is
6633 ;; located under "data/annotation/" instead of "bioc/".
6634 (uri (string-append "https://bioconductor.org/packages/"
6635 "release/data/annotation/src/contrib"
6636 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6640 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6642 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6643 (build-system r-build-system)
6644 ;; As this package provides little more than a very large data file it
6645 ;; doesn't make sense to build substitutes.
6646 (arguments `(#:substitutable? #f))
6648 `(("r-genomicfeatures" ,r-genomicfeatures)))
6650 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6651 (synopsis "Annotation package for human genome in TxDb format")
6653 "This package provides an annotation database of Homo sapiens genome
6654 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6655 track. The database is exposed as a @code{TxDb} object.")
6656 (license license:artistic2.0)))
6658 (define-public r-sparql
6664 (uri (cran-uri "SPARQL" version))
6667 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6668 (properties `((upstream-name . "SPARQL")))
6669 (build-system r-build-system)
6671 `(("r-rcurl" ,r-rcurl)
6673 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6674 (synopsis "SPARQL client for R")
6675 (description "This package provides an interface to use SPARQL to pose
6676 SELECT or UPDATE queries to an end-point.")
6677 ;; The only license indication is found in the DESCRIPTION file,
6678 ;; which states GPL-3. So we cannot assume GPLv3+.
6679 (license license:gpl3)))
6681 (define-public vsearch
6689 "https://github.com/torognes/vsearch/archive/v"
6691 (file-name (string-append name "-" version ".tar.gz"))
6694 "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3"))
6695 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6698 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6699 ;; for this in the patch.
6700 (delete-file "src/city.h")
6701 (delete-file "src/citycrc.h")
6702 (delete-file "src/city.cc")
6704 (build-system gnu-build-system)
6707 (modify-phases %standard-phases
6708 (add-after 'unpack 'autogen
6709 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6713 ("cityhash" ,cityhash)))
6715 `(("autoconf" ,autoconf)
6716 ("automake" ,automake)))
6717 (synopsis "Sequence search tools for metagenomics")
6719 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6720 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6721 masking. The tool takes advantage of parallelism in the form of SIMD
6722 vectorization as well as multiple threads to perform accurate alignments at
6723 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6724 Needleman-Wunsch).")
6725 (home-page "https://github.com/torognes/vsearch")
6726 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6728 (supported-systems '("x86_64-linux"))
6729 ;; Dual licensed; also includes public domain source.
6730 (license (list license:gpl3 license:bsd-2))))
6732 (define-public pardre
6735 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6740 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6744 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6745 (build-system gnu-build-system)
6747 `(#:tests? #f ; no tests included
6749 (modify-phases %standard-phases
6752 (lambda* (#:key outputs #:allow-other-keys)
6753 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6754 (install-file "ParDRe" bin)
6757 `(("openmpi" ,openmpi)
6759 (synopsis "Parallel tool to remove duplicate DNA reads")
6761 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6762 Duplicate reads can be seen as identical or nearly identical sequences with
6763 some mismatches. This tool lets users avoid the analysis of unnecessary
6764 reads, reducing the time of subsequent procedures with the
6765 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6766 in order to exploit the parallel capabilities of multicore clusters. It is
6767 faster than multithreaded counterparts (end of 2015) for the same number of
6768 cores and, thanks to the message-passing technology, it can be executed on
6770 (home-page "https://sourceforge.net/projects/pardre/")
6771 (license license:gpl3+)))
6773 (define-public ruby-bio-kseq
6775 (name "ruby-bio-kseq")
6780 (uri (rubygems-uri "bio-kseq" version))
6783 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6784 (build-system ruby-build-system)
6786 `(#:test-target "spec"))
6788 `(("bundler" ,bundler)
6789 ("ruby-rspec" ,ruby-rspec)
6790 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6793 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6795 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6796 FASTQ parsing code. It provides a fast iterator over sequences and their
6798 (home-page "https://github.com/gusevfe/bio-kseq")
6799 (license license:expat)))
6801 (define-public bio-locus
6808 (uri (rubygems-uri "bio-locus" version))
6811 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6812 (build-system ruby-build-system)
6814 `(("ruby-rspec" ,ruby-rspec)))
6815 (synopsis "Tool for fast querying of genome locations")
6817 "Bio-locus is a tabix-like tool for fast querying of genome
6818 locations. Many file formats in bioinformatics contain records that
6819 start with a chromosome name and a position for a SNP, or a start-end
6820 position for indels. Bio-locus allows users to store this chr+pos or
6821 chr+pos+alt information in a database.")
6822 (home-page "https://github.com/pjotrp/bio-locus")
6823 (license license:expat)))
6825 (define-public bio-blastxmlparser
6827 (name "bio-blastxmlparser")
6831 (uri (rubygems-uri "bio-blastxmlparser" version))
6834 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6835 (build-system ruby-build-system)
6837 `(("ruby-bio-logger" ,ruby-bio-logger)
6838 ("ruby-nokogiri" ,ruby-nokogiri)))
6840 `(("ruby-rspec" ,ruby-rspec)))
6841 (synopsis "Fast big data BLAST XML parser and library")
6843 "Very fast parallel big-data BLAST XML file parser which can be used as
6844 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6845 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6846 (home-page "https://github.com/pjotrp/blastxmlparser")
6847 (license license:expat)))
6849 (define-public bioruby
6856 (uri (rubygems-uri "bio" version))
6859 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6860 (build-system ruby-build-system)
6862 `(("ruby-libxml" ,ruby-libxml)))
6864 `(("which" ,which))) ; required for test phase
6867 (modify-phases %standard-phases
6868 (add-before 'build 'patch-test-command
6870 (substitute* '("test/functional/bio/test_command.rb")
6871 (("/bin/sh") (which "sh")))
6872 (substitute* '("test/functional/bio/test_command.rb")
6873 (("/bin/ls") (which "ls")))
6874 (substitute* '("test/functional/bio/test_command.rb")
6875 (("which") (which "which")))
6876 (substitute* '("test/functional/bio/test_command.rb",
6877 "test/data/command/echoarg2.sh")
6878 (("/bin/echo") (which "echo")))
6880 (synopsis "Ruby library, shell and utilities for bioinformatics")
6881 (description "BioRuby comes with a comprehensive set of Ruby development
6882 tools and libraries for bioinformatics and molecular biology. BioRuby has
6883 components for sequence analysis, pathway analysis, protein modelling and
6884 phylogenetic analysis; it supports many widely used data formats and provides
6885 easy access to databases, external programs and public web services, including
6886 BLAST, KEGG, GenBank, MEDLINE and GO.")
6887 (home-page "http://bioruby.org/")
6888 ;; Code is released under Ruby license, except for setup
6889 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6890 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6892 (define-public r-acsnminer
6894 (name "r-acsnminer")
6895 (version "0.16.8.25")
6898 (uri (cran-uri "ACSNMineR" version))
6901 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6902 (properties `((upstream-name . "ACSNMineR")))
6903 (build-system r-build-system)
6905 `(("r-ggplot2" ,r-ggplot2)
6906 ("r-gridextra" ,r-gridextra)))
6907 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6908 (synopsis "Gene enrichment analysis")
6910 "This package provides tools to compute and represent gene set enrichment
6911 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6912 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6913 enrichment can be run with hypergeometric test or Fisher exact test, and can
6914 use multiple corrections. Visualization of data can be done either by
6915 barplots or heatmaps.")
6916 (license license:gpl2+)))
6918 (define-public r-biocgenerics
6920 (name "r-biocgenerics")
6924 (uri (bioconductor-uri "BiocGenerics" version))
6927 "19qxhy2cd3pykkhzbb5q3crgaxf65cpzf2mkfsz16gqhi8flj72p"))))
6929 `((upstream-name . "BiocGenerics")))
6930 (build-system r-build-system)
6931 (home-page "https://bioconductor.org/packages/BiocGenerics")
6932 (synopsis "S4 generic functions for Bioconductor")
6934 "This package provides S4 generic functions needed by many Bioconductor
6936 (license license:artistic2.0)))
6938 (define-public r-biocinstaller
6940 (name "r-biocinstaller")
6944 (uri (bioconductor-uri "BiocInstaller" version))
6947 "1xg1gi1hf5vflp71ji21gnmr4kcjpx8a6c47cllpc7yqnjv5nfg0"))))
6949 `((upstream-name . "BiocInstaller")))
6950 (build-system r-build-system)
6951 (home-page "https://bioconductor.org/packages/BiocInstaller")
6952 (synopsis "Install Bioconductor packages")
6953 (description "This package is used to install and update R packages from
6954 Bioconductor, CRAN, and Github.")
6955 (license license:artistic2.0)))
6957 (define-public r-biocviews
6959 (name "r-biocviews")
6963 (uri (bioconductor-uri "biocViews" version))
6966 "1rxvwikqivsgxjjcazlszy8xgz346lfh5rw4llxw6fz38fjgb0k5"))))
6968 `((upstream-name . "biocViews")))
6969 (build-system r-build-system)
6971 `(("r-biobase" ,r-biobase)
6972 ("r-graph" ,r-graph)
6974 ("r-rcurl" ,r-rcurl)
6976 ("r-runit" ,r-runit)))
6977 (home-page "https://bioconductor.org/packages/biocViews")
6978 (synopsis "Bioconductor package categorization helper")
6979 (description "The purpose of biocViews is to create HTML pages that
6980 categorize packages in a Bioconductor package repository according to keywords,
6981 also known as views, in a controlled vocabulary.")
6982 (license license:artistic2.0)))
6984 (define-public r-bookdown
6990 (uri (cran-uri "bookdown" version))
6993 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6994 (build-system r-build-system)
6996 `(("r-htmltools" ,r-htmltools)
6997 ("r-knitr" ,r-knitr)
6998 ("r-rmarkdown" ,r-rmarkdown)
6999 ("r-tinytex" ,r-tinytex)
7001 ("r-xfun" ,r-xfun)))
7002 (home-page "https://github.com/rstudio/bookdown")
7003 (synopsis "Authoring books and technical documents with R markdown")
7004 (description "This package provides output formats and utilities for
7005 authoring books and technical documents with R Markdown.")
7006 (license license:gpl3)))
7008 (define-public r-biocstyle
7010 (name "r-biocstyle")
7014 (uri (bioconductor-uri "BiocStyle" version))
7017 "17m901ylz00w1a3nq5f910v55zixm1nr6rb3qrsbhqd94qzr0l2p"))))
7019 `((upstream-name . "BiocStyle")))
7020 (build-system r-build-system)
7022 `(("r-bookdown" ,r-bookdown)
7023 ("r-knitr" ,r-knitr)
7024 ("r-rmarkdown" ,r-rmarkdown)
7025 ("r-yaml" ,r-yaml)))
7026 (home-page "https://bioconductor.org/packages/BiocStyle")
7027 (synopsis "Bioconductor formatting styles")
7028 (description "This package provides standard formatting styles for
7029 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7031 (license license:artistic2.0)))
7033 (define-public r-bioccheck
7035 (name "r-bioccheck")
7039 (uri (bioconductor-uri "BiocCheck" version))
7042 "1srp1g809f1nn0fyqknr7r6dq89bw1xpjvmygr7cw6ffknbc671s"))))
7044 `((upstream-name . "BiocCheck")))
7045 (build-system r-build-system)
7048 (modify-phases %standard-phases
7049 ;; This package can be used by calling BiocCheck(<package>) from
7050 ;; within R, or by running R CMD BiocCheck <package>. This phase
7051 ;; makes sure the latter works. For this to work, the BiocCheck
7052 ;; script must be somewhere on the PATH (not the R bin directory).
7053 (add-after 'install 'install-bioccheck-subcommand
7054 (lambda* (#:key outputs #:allow-other-keys)
7055 (let* ((out (assoc-ref outputs "out"))
7056 (dest-dir (string-append out "/bin"))
7058 (string-append out "/site-library/BiocCheck/script/")))
7060 (symlink (string-append script-dir "/checkBadDeps.R")
7061 (string-append dest-dir "/checkBadDeps.R"))
7062 (symlink (string-append script-dir "/BiocCheck")
7063 (string-append dest-dir "/BiocCheck")))
7066 `(("r-codetools" ,r-codetools)
7067 ("r-graph" ,r-graph)
7069 ("r-optparse" ,r-optparse)
7070 ("r-biocinstaller" ,r-biocinstaller)
7071 ("r-biocviews" ,r-biocviews)
7072 ("r-stringdist" ,r-stringdist)))
7073 (home-page "https://bioconductor.org/packages/BiocCheck")
7074 (synopsis "Executes Bioconductor-specific package checks")
7075 (description "This package contains tools to perform additional quality
7076 checks on R packages that are to be submitted to the Bioconductor repository.")
7077 (license license:artistic2.0)))
7079 (define-public r-optparse
7086 (uri (cran-uri "optparse" version))
7089 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7090 (build-system r-build-system)
7092 `(("r-getopt" ,r-getopt)))
7094 "https://github.com/trevorld/optparse")
7095 (synopsis "Command line option parser")
7097 "This package provides a command line parser inspired by Python's
7098 @code{optparse} library to be used with Rscript to write shebang scripts
7099 that accept short and long options.")
7100 (license license:gpl2+)))
7102 (define-public r-dnacopy
7108 (uri (bioconductor-uri "DNAcopy" version))
7111 "03hfhmmc5y60r2gcgm367w2fr7qj115l74m9bp3h9qpn5yci0d8n"))))
7113 `((upstream-name . "DNAcopy")))
7114 (build-system r-build-system)
7116 `(("gfortran" ,gfortran)))
7117 (home-page "https://bioconductor.org/packages/DNAcopy")
7118 (synopsis "Implementation of a circular binary segmentation algorithm")
7119 (description "This package implements the circular binary segmentation (CBS)
7120 algorithm to segment DNA copy number data and identify genomic regions with
7121 abnormal copy number.")
7122 (license license:gpl2+)))
7124 (define-public r-s4vectors
7126 (name "r-s4vectors")
7130 (uri (bioconductor-uri "S4Vectors" version))
7133 "02bps2rpjqx2npwxq3x62ncwi9ggr165cwi56h6hld28bw2gddy8"))))
7135 `((upstream-name . "S4Vectors")))
7136 (build-system r-build-system)
7138 `(("r-biocgenerics" ,r-biocgenerics)))
7139 (home-page "https://bioconductor.org/packages/S4Vectors")
7140 (synopsis "S4 implementation of vectors and lists")
7142 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7143 classes and a set of generic functions that extend the semantic of ordinary
7144 vectors and lists in R. Package developers can easily implement vector-like
7145 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7146 In addition, a few low-level concrete subclasses of general interest (e.g.
7147 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7148 S4Vectors package itself.")
7149 (license license:artistic2.0)))
7151 (define-public r-seqinr
7158 (uri (cran-uri "seqinr" version))
7161 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7162 (build-system r-build-system)
7164 `(("r-ade4" ,r-ade4)
7165 ("r-segmented" ,r-segmented)))
7168 (home-page "http://seqinr.r-forge.r-project.org/")
7169 (synopsis "Biological sequences retrieval and analysis")
7171 "This package provides tools for exploratory data analysis and data
7172 visualization of biological sequence (DNA and protein) data. It also includes
7173 utilities for sequence data management under the ACNUC system.")
7174 (license license:gpl2+)))
7176 (define-public r-iranges
7182 (uri (bioconductor-uri "IRanges" version))
7185 "0wz63hysspyjihqadg91dbvllc5a61zzjrsz0b9498lihqc6m1la"))))
7187 `((upstream-name . "IRanges")))
7188 (build-system r-build-system)
7190 `(("r-biocgenerics" ,r-biocgenerics)
7191 ("r-s4vectors" ,r-s4vectors)))
7192 (home-page "https://bioconductor.org/packages/IRanges")
7193 (synopsis "Infrastructure for manipulating intervals on sequences")
7195 "This package provides efficient low-level and highly reusable S4 classes
7196 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7197 generally, data that can be organized sequentially (formally defined as
7198 @code{Vector} objects), as well as views on these @code{Vector} objects.
7199 Efficient list-like classes are also provided for storing big collections of
7200 instances of the basic classes. All classes in the package use consistent
7201 naming and share the same rich and consistent \"Vector API\" as much as
7203 (license license:artistic2.0)))
7205 (define-public r-genomeinfodbdata
7207 (name "r-genomeinfodbdata")
7211 ;; We cannot use bioconductor-uri here because this tarball is
7212 ;; located under "data/annotation/" instead of "bioc/".
7213 (uri (string-append "https://bioconductor.org/packages/release/"
7214 "data/annotation/src/contrib/GenomeInfoDbData_"
7218 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7220 `((upstream-name . "GenomeInfoDbData")))
7221 (build-system r-build-system)
7222 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7223 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7224 (description "This package contains data for mapping between NCBI taxonomy
7225 ID and species. It is used by functions in the GenomeInfoDb package.")
7226 (license license:artistic2.0)))
7228 (define-public r-genomeinfodb
7230 (name "r-genomeinfodb")
7234 (uri (bioconductor-uri "GenomeInfoDb" version))
7237 "0yhnqhaydmmq7ihmhj3rbal4afq5p993l2qqrd0n5wmbyg7glg2d"))))
7239 `((upstream-name . "GenomeInfoDb")))
7240 (build-system r-build-system)
7242 `(("r-biocgenerics" ,r-biocgenerics)
7243 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7244 ("r-iranges" ,r-iranges)
7245 ("r-rcurl" ,r-rcurl)
7246 ("r-s4vectors" ,r-s4vectors)))
7247 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7248 (synopsis "Utilities for manipulating chromosome identifiers")
7250 "This package contains data and functions that define and allow
7251 translation between different chromosome sequence naming conventions (e.g.,
7252 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7253 names in their natural, rather than lexicographic, order.")
7254 (license license:artistic2.0)))
7256 (define-public r-edger
7262 (uri (bioconductor-uri "edgeR" version))
7265 "0w3jv29n0kkaiig8dbbdqy2dkng8xfaihch82mj9ci5hphrx3nng"))))
7266 (properties `((upstream-name . "edgeR")))
7267 (build-system r-build-system)
7269 `(("r-limma" ,r-limma)
7270 ("r-locfit" ,r-locfit)
7272 ("r-statmod" ,r-statmod))) ;for estimateDisp
7273 (home-page "http://bioinf.wehi.edu.au/edgeR")
7274 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7275 (description "This package can do differential expression analysis of
7276 RNA-seq expression profiles with biological replication. It implements a range
7277 of statistical methodology based on the negative binomial distributions,
7278 including empirical Bayes estimation, exact tests, generalized linear models
7279 and quasi-likelihood tests. It be applied to differential signal analysis of
7280 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7282 (license license:gpl2+)))
7284 (define-public r-variantannotation
7286 (name "r-variantannotation")
7290 (uri (bioconductor-uri "VariantAnnotation" version))
7293 "1r55ki951dj81qvy73knfcy69ik5vzkd56wnk3f6vvf9vngqb8jr"))))
7295 `((upstream-name . "VariantAnnotation")))
7299 `(("r-annotationdbi" ,r-annotationdbi)
7300 ("r-biobase" ,r-biobase)
7301 ("r-biocgenerics" ,r-biocgenerics)
7302 ("r-biostrings" ,r-biostrings)
7303 ("r-bsgenome" ,r-bsgenome)
7305 ("r-genomeinfodb" ,r-genomeinfodb)
7306 ("r-genomicfeatures" ,r-genomicfeatures)
7307 ("r-genomicranges" ,r-genomicranges)
7308 ("r-iranges" ,r-iranges)
7309 ("r-summarizedexperiment" ,r-summarizedexperiment)
7310 ("r-rsamtools" ,r-rsamtools)
7311 ("r-rtracklayer" ,r-rtracklayer)
7312 ("r-s4vectors" ,r-s4vectors)
7313 ("r-xvector" ,r-xvector)
7314 ("r-zlibbioc" ,r-zlibbioc)))
7315 (build-system r-build-system)
7316 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7317 (synopsis "Package for annotation of genetic variants")
7318 (description "This R package can annotate variants, compute amino acid
7319 coding changes and predict coding outcomes.")
7320 (license license:artistic2.0)))
7322 (define-public r-limma
7328 (uri (bioconductor-uri "limma" version))
7331 "0iiifszr6hcqih6kszdsbkx3gacfg3d7v8hdx0lbjqnjqgqz7pwk"))))
7332 (build-system r-build-system)
7333 (home-page "http://bioinf.wehi.edu.au/limma")
7334 (synopsis "Package for linear models for microarray and RNA-seq data")
7335 (description "This package can be used for the analysis of gene expression
7336 studies, especially the use of linear models for analysing designed experiments
7337 and the assessment of differential expression. The analysis methods apply to
7338 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7339 (license license:gpl2+)))
7341 (define-public r-xvector
7347 (uri (bioconductor-uri "XVector" version))
7350 "1zjlhh9lsyhg0js1858csyw2389kbrzdqnqnha833wazkwxilp3f"))))
7352 `((upstream-name . "XVector")))
7353 (build-system r-build-system)
7356 (modify-phases %standard-phases
7357 (add-after 'unpack 'use-system-zlib
7359 (substitute* "DESCRIPTION"
7360 (("zlibbioc, ") ""))
7361 (substitute* "NAMESPACE"
7362 (("import\\(zlibbioc\\)") ""))
7367 `(("r-biocgenerics" ,r-biocgenerics)
7368 ("r-iranges" ,r-iranges)
7369 ("r-s4vectors" ,r-s4vectors)))
7370 (home-page "https://bioconductor.org/packages/XVector")
7371 (synopsis "Representation and manpulation of external sequences")
7373 "This package provides memory efficient S4 classes for storing sequences
7374 \"externally\" (behind an R external pointer, or on disk).")
7375 (license license:artistic2.0)))
7377 (define-public r-genomicranges
7379 (name "r-genomicranges")
7383 (uri (bioconductor-uri "GenomicRanges" version))
7386 "0p58yk2i5gqvjlkx548mnrr49wvs0xfcl06l9rqj2hi6hkkbvnp3"))))
7388 `((upstream-name . "GenomicRanges")))
7389 (build-system r-build-system)
7391 `(("r-biocgenerics" ,r-biocgenerics)
7392 ("r-genomeinfodb" ,r-genomeinfodb)
7393 ("r-iranges" ,r-iranges)
7394 ("r-s4vectors" ,r-s4vectors)
7395 ("r-xvector" ,r-xvector)))
7396 (home-page "https://bioconductor.org/packages/GenomicRanges")
7397 (synopsis "Representation and manipulation of genomic intervals")
7399 "This package provides tools to efficiently represent and manipulate
7400 genomic annotations and alignments is playing a central role when it comes to
7401 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7402 GenomicRanges package defines general purpose containers for storing and
7403 manipulating genomic intervals and variables defined along a genome.")
7404 (license license:artistic2.0)))
7406 (define-public r-biobase
7412 (uri (bioconductor-uri "Biobase" version))
7415 "1iwds2a5ir29k19dbpynlc7nn836cw2gamchhgpi2jf2xar9m9jz"))))
7417 `((upstream-name . "Biobase")))
7418 (build-system r-build-system)
7420 `(("r-biocgenerics" ,r-biocgenerics)))
7421 (home-page "https://bioconductor.org/packages/Biobase")
7422 (synopsis "Base functions for Bioconductor")
7424 "This package provides functions that are needed by many other packages
7425 on Bioconductor or which replace R functions.")
7426 (license license:artistic2.0)))
7428 (define-public r-annotationdbi
7430 (name "r-annotationdbi")
7434 (uri (bioconductor-uri "AnnotationDbi" version))
7437 "0afkbzli08vq02r2pr9phrz3rxd6ilp1w7yw8y99nbjiz14f8b1c"))))
7439 `((upstream-name . "AnnotationDbi")))
7440 (build-system r-build-system)
7442 `(("r-biobase" ,r-biobase)
7443 ("r-biocgenerics" ,r-biocgenerics)
7445 ("r-iranges" ,r-iranges)
7446 ("r-rsqlite" ,r-rsqlite)
7447 ("r-s4vectors" ,r-s4vectors)))
7448 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7449 (synopsis "Annotation database interface")
7451 "This package provides user interface and database connection code for
7452 annotation data packages using SQLite data storage.")
7453 (license license:artistic2.0)))
7455 (define-public r-biomart
7461 (uri (bioconductor-uri "biomaRt" version))
7464 "0b70s350ffc74v3xz5c3jpazr9zxdb7gjmjfj7aghlsrizrspill"))))
7466 `((upstream-name . "biomaRt")))
7467 (build-system r-build-system)
7469 `(("r-annotationdbi" ,r-annotationdbi)
7471 ("r-progress" ,r-progress)
7472 ("r-rcurl" ,r-rcurl)
7473 ("r-stringr" ,r-stringr)
7475 (home-page "https://bioconductor.org/packages/biomaRt")
7476 (synopsis "Interface to BioMart databases")
7478 "biomaRt provides an interface to a growing collection of databases
7479 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7480 package enables retrieval of large amounts of data in a uniform way without
7481 the need to know the underlying database schemas or write complex SQL queries.
7482 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7483 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7484 users direct access to a diverse set of data and enable a wide range of
7485 powerful online queries from gene annotation to database mining.")
7486 (license license:artistic2.0)))
7488 (define-public r-biocparallel
7490 (name "r-biocparallel")
7494 (uri (bioconductor-uri "BiocParallel" version))
7497 "1llb5a62hn4yxpdgqdh2l7i5zd06mjkk8hagsna69cq65wv6iifm"))))
7499 `((upstream-name . "BiocParallel")))
7500 (build-system r-build-system)
7502 `(("r-futile-logger" ,r-futile-logger)
7505 (home-page "https://bioconductor.org/packages/BiocParallel")
7506 (synopsis "Bioconductor facilities for parallel evaluation")
7508 "This package provides modified versions and novel implementation of
7509 functions for parallel evaluation, tailored to use with Bioconductor
7511 (license (list license:gpl2+ license:gpl3+))))
7513 (define-public r-biostrings
7515 (name "r-biostrings")
7519 (uri (bioconductor-uri "Biostrings" version))
7522 "118b490jk87ydigm6ln25ms4kskzkw0akmh77clzznhzpqnxsi6j"))))
7524 `((upstream-name . "Biostrings")))
7525 (build-system r-build-system)
7527 `(("r-biocgenerics" ,r-biocgenerics)
7528 ("r-iranges" ,r-iranges)
7529 ("r-s4vectors" ,r-s4vectors)
7530 ("r-xvector" ,r-xvector)))
7531 (home-page "https://bioconductor.org/packages/Biostrings")
7532 (synopsis "String objects and algorithms for biological sequences")
7534 "This package provides memory efficient string containers, string
7535 matching algorithms, and other utilities, for fast manipulation of large
7536 biological sequences or sets of sequences.")
7537 (license license:artistic2.0)))
7539 (define-public r-rsamtools
7541 (name "r-rsamtools")
7545 (uri (bioconductor-uri "Rsamtools" version))
7548 "1hpjr22h33pf4fgv0sj83rqzv6l5l7s6fpmmqvchh45ikks1mnhq"))))
7550 `((upstream-name . "Rsamtools")))
7551 (build-system r-build-system)
7554 (modify-phases %standard-phases
7555 (add-after 'unpack 'use-system-zlib
7557 (substitute* "DESCRIPTION"
7558 (("zlibbioc, ") ""))
7559 (substitute* "NAMESPACE"
7560 (("import\\(zlibbioc\\)") ""))
7565 `(("r-biocgenerics" ,r-biocgenerics)
7566 ("r-biocparallel" ,r-biocparallel)
7567 ("r-biostrings" ,r-biostrings)
7568 ("r-bitops" ,r-bitops)
7569 ("r-genomeinfodb" ,r-genomeinfodb)
7570 ("r-genomicranges" ,r-genomicranges)
7571 ("r-iranges" ,r-iranges)
7572 ("r-s4vectors" ,r-s4vectors)
7573 ("r-xvector" ,r-xvector)))
7574 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7575 (synopsis "Interface to samtools, bcftools, and tabix")
7577 "This package provides an interface to the 'samtools', 'bcftools', and
7578 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7579 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7581 (license license:expat)))
7583 (define-public r-delayedarray
7585 (name "r-delayedarray")
7589 (uri (bioconductor-uri "DelayedArray" version))
7592 "10b03zrnvz5isfh4z55hasya2m71lrfx10l5lm2sdmqs0gwkanrd"))))
7594 `((upstream-name . "DelayedArray")))
7595 (build-system r-build-system)
7597 `(("r-biocgenerics" ,r-biocgenerics)
7598 ("r-biocparallel" ,r-biocparallel)
7599 ("r-s4vectors" ,r-s4vectors)
7600 ("r-iranges" ,r-iranges)
7601 ("r-matrixstats" ,r-matrixstats)))
7602 (home-page "https://bioconductor.org/packages/DelayedArray")
7603 (synopsis "Delayed operations on array-like objects")
7605 "Wrapping an array-like object (typically an on-disk object) in a
7606 @code{DelayedArray} object allows one to perform common array operations on it
7607 without loading the object in memory. In order to reduce memory usage and
7608 optimize performance, operations on the object are either delayed or executed
7609 using a block processing mechanism. Note that this also works on in-memory
7610 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7611 @code{Matrix} objects, and ordinary arrays and data frames.")
7612 (license license:artistic2.0)))
7614 (define-public r-summarizedexperiment
7616 (name "r-summarizedexperiment")
7620 (uri (bioconductor-uri "SummarizedExperiment" version))
7623 "0v3zxl9cqsv79ag5cnvzlhvgaz5cr8f4rn7flmwnwpqd508cznl1"))))
7625 `((upstream-name . "SummarizedExperiment")))
7626 (build-system r-build-system)
7628 `(("r-biobase" ,r-biobase)
7629 ("r-biocgenerics" ,r-biocgenerics)
7630 ("r-delayedarray" ,r-delayedarray)
7631 ("r-genomeinfodb" ,r-genomeinfodb)
7632 ("r-genomicranges" ,r-genomicranges)
7633 ("r-iranges" ,r-iranges)
7634 ("r-matrix" ,r-matrix)
7635 ("r-s4vectors" ,r-s4vectors)))
7636 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7637 (synopsis "Container for representing genomic ranges by sample")
7639 "The SummarizedExperiment container contains one or more assays, each
7640 represented by a matrix-like object of numeric or other mode. The rows
7641 typically represent genomic ranges of interest and the columns represent
7643 (license license:artistic2.0)))
7645 (define-public r-genomicalignments
7647 (name "r-genomicalignments")
7651 (uri (bioconductor-uri "GenomicAlignments" version))
7654 "00pi2cnkkbj2023fg2x2cmglkdalwzy1vr3glsikwz7ix9yylcaw"))))
7656 `((upstream-name . "GenomicAlignments")))
7657 (build-system r-build-system)
7659 `(("r-biocgenerics" ,r-biocgenerics)
7660 ("r-biocparallel" ,r-biocparallel)
7661 ("r-biostrings" ,r-biostrings)
7662 ("r-genomeinfodb" ,r-genomeinfodb)
7663 ("r-genomicranges" ,r-genomicranges)
7664 ("r-iranges" ,r-iranges)
7665 ("r-rsamtools" ,r-rsamtools)
7666 ("r-s4vectors" ,r-s4vectors)
7667 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7668 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7669 (synopsis "Representation and manipulation of short genomic alignments")
7671 "This package provides efficient containers for storing and manipulating
7672 short genomic alignments (typically obtained by aligning short reads to a
7673 reference genome). This includes read counting, computing the coverage,
7674 junction detection, and working with the nucleotide content of the
7676 (license license:artistic2.0)))
7678 (define-public r-rtracklayer
7680 (name "r-rtracklayer")
7684 (uri (bioconductor-uri "rtracklayer" version))
7687 "1wxxxlyps19dw3i0pw4mlm3kinnswsc35rgvlnbwvpnpjbca6w4l"))))
7688 (build-system r-build-system)
7691 (modify-phases %standard-phases
7692 (add-after 'unpack 'use-system-zlib
7694 (substitute* "DESCRIPTION"
7695 ((" zlibbioc,") ""))
7696 (substitute* "NAMESPACE"
7697 (("import\\(zlibbioc\\)") ""))
7700 `(("pkg-config" ,pkg-config)))
7704 `(("r-biocgenerics" ,r-biocgenerics)
7705 ("r-biostrings" ,r-biostrings)
7706 ("r-genomeinfodb" ,r-genomeinfodb)
7707 ("r-genomicalignments" ,r-genomicalignments)
7708 ("r-genomicranges" ,r-genomicranges)
7709 ("r-iranges" ,r-iranges)
7710 ("r-rcurl" ,r-rcurl)
7711 ("r-rsamtools" ,r-rsamtools)
7712 ("r-s4vectors" ,r-s4vectors)
7714 ("r-xvector" ,r-xvector)))
7715 (home-page "https://bioconductor.org/packages/rtracklayer")
7716 (synopsis "R interface to genome browsers and their annotation tracks")
7718 "rtracklayer is an extensible framework for interacting with multiple
7719 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7720 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7721 built-in). The user may export/import tracks to/from the supported browsers,
7722 as well as query and modify the browser state, such as the current viewport.")
7723 (license license:artistic2.0)))
7725 (define-public r-genomicfeatures
7727 (name "r-genomicfeatures")
7731 (uri (bioconductor-uri "GenomicFeatures" version))
7734 "0kfyyg1ib8fkq2hxraal10z4bx3rg8figdskw4yhn1mbh6l42q5f"))))
7736 `((upstream-name . "GenomicFeatures")))
7737 (build-system r-build-system)
7739 `(("r-annotationdbi" ,r-annotationdbi)
7740 ("r-biobase" ,r-biobase)
7741 ("r-biocgenerics" ,r-biocgenerics)
7742 ("r-biomart" ,r-biomart)
7743 ("r-biostrings" ,r-biostrings)
7745 ("r-genomeinfodb" ,r-genomeinfodb)
7746 ("r-genomicranges" ,r-genomicranges)
7747 ("r-iranges" ,r-iranges)
7748 ("r-rcurl" ,r-rcurl)
7749 ("r-rsqlite" ,r-rsqlite)
7750 ("r-rtracklayer" ,r-rtracklayer)
7751 ("r-s4vectors" ,r-s4vectors)
7752 ("r-xvector" ,r-xvector)))
7753 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7754 (synopsis "Tools for working with transcript centric annotations")
7756 "This package provides a set of tools and methods for making and
7757 manipulating transcript centric annotations. With these tools the user can
7758 easily download the genomic locations of the transcripts, exons and cds of a
7759 given organism, from either the UCSC Genome Browser or a BioMart
7760 database (more sources will be supported in the future). This information is
7761 then stored in a local database that keeps track of the relationship between
7762 transcripts, exons, cds and genes. Flexible methods are provided for
7763 extracting the desired features in a convenient format.")
7764 (license license:artistic2.0)))
7766 (define-public r-go-db
7772 (uri (string-append "https://www.bioconductor.org/packages/"
7773 "release/data/annotation/src/contrib/GO.db_"
7777 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7779 `((upstream-name . "GO.db")))
7780 (build-system r-build-system)
7782 `(("r-annotationdbi" ,r-annotationdbi)))
7783 (home-page "https://bioconductor.org/packages/GO.db")
7784 (synopsis "Annotation maps describing the entire Gene Ontology")
7786 "The purpose of this GO.db annotation package is to provide detailed
7787 information about the latest version of the Gene Ontologies.")
7788 (license license:artistic2.0)))
7790 (define-public r-graph
7796 (uri (bioconductor-uri "graph" version))
7799 "1zx445lk36g1s6i5dbhhf00nzzazyklfjxxjfax6q8hnhvgm9759"))))
7800 (build-system r-build-system)
7802 `(("r-biocgenerics" ,r-biocgenerics)))
7803 (home-page "https://bioconductor.org/packages/graph")
7804 (synopsis "Handle graph data structures in R")
7806 "This package implements some simple graph handling capabilities for R.")
7807 (license license:artistic2.0)))
7809 (define-public r-topgo
7815 (uri (bioconductor-uri "topGO" version))
7818 "05yxnkid8bgw9lkm90if9fg63djhgvbailfa3qsfqa5c0zjmixw1"))))
7820 `((upstream-name . "topGO")))
7821 (build-system r-build-system)
7823 `(("r-annotationdbi" ,r-annotationdbi)
7825 ("r-biobase" ,r-biobase)
7826 ("r-biocgenerics" ,r-biocgenerics)
7827 ("r-go-db" ,r-go-db)
7828 ("r-graph" ,r-graph)
7829 ("r-lattice" ,r-lattice)
7830 ("r-matrixstats" ,r-matrixstats)
7831 ("r-sparsem" ,r-sparsem)))
7832 (home-page "https://bioconductor.org/packages/topGO")
7833 (synopsis "Enrichment analysis for gene ontology")
7835 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7836 terms while accounting for the topology of the GO graph. Different test
7837 statistics and different methods for eliminating local similarities and
7838 dependencies between GO terms can be implemented and applied.")
7839 ;; Any version of the LGPL applies.
7840 (license license:lgpl2.1+)))
7842 (define-public r-bsgenome
7848 (uri (bioconductor-uri "BSgenome" version))
7851 "1rk2piqq5dppkd51ln3r872d7ng3rvq98071mnd0xdv2xwnyn5g8"))))
7853 `((upstream-name . "BSgenome")))
7854 (build-system r-build-system)
7856 `(("r-biocgenerics" ,r-biocgenerics)
7857 ("r-biostrings" ,r-biostrings)
7858 ("r-genomeinfodb" ,r-genomeinfodb)
7859 ("r-genomicranges" ,r-genomicranges)
7860 ("r-iranges" ,r-iranges)
7861 ("r-rsamtools" ,r-rsamtools)
7862 ("r-rtracklayer" ,r-rtracklayer)
7863 ("r-s4vectors" ,r-s4vectors)
7864 ("r-xvector" ,r-xvector)))
7865 (home-page "https://bioconductor.org/packages/BSgenome")
7866 (synopsis "Infrastructure for Biostrings-based genome data packages")
7868 "This package provides infrastructure shared by all Biostrings-based
7869 genome data packages and support for efficient SNP representation.")
7870 (license license:artistic2.0)))
7872 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7874 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7878 ;; We cannot use bioconductor-uri here because this tarball is
7879 ;; located under "data/annotation/" instead of "bioc/".
7880 (uri (string-append "https://www.bioconductor.org/packages/"
7881 "release/data/annotation/src/contrib/"
7882 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7886 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7888 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7889 (build-system r-build-system)
7890 ;; As this package provides little more than a very large data file it
7891 ;; doesn't make sense to build substitutes.
7892 (arguments `(#:substitutable? #f))
7894 `(("r-bsgenome" ,r-bsgenome)))
7896 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7897 (synopsis "Full genome sequences for Homo sapiens")
7899 "This package provides full genome sequences for Homo sapiens from
7900 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7901 (license license:artistic2.0)))
7903 (define-public r-impute
7909 (uri (bioconductor-uri "impute" version))
7912 "1d3cpfaqlq2gnb3hsc2yhxwkrnbd7m6ifif32yp0ya0jr5brl4hr"))))
7914 `(("gfortran" ,gfortran)))
7915 (build-system r-build-system)
7916 (home-page "https://bioconductor.org/packages/impute")
7917 (synopsis "Imputation for microarray data")
7919 "This package provides a function to impute missing gene expression
7920 microarray data, using nearest neighbor averaging.")
7921 (license license:gpl2+)))
7923 (define-public r-seqpattern
7925 (name "r-seqpattern")
7929 (uri (bioconductor-uri "seqPattern" version))
7932 "0dw0yldfcf0ibvpqxlpx1ijnjf9lma47w9w22siszzhw09i0wp3w"))))
7934 `((upstream-name . "seqPattern")))
7935 (build-system r-build-system)
7937 `(("r-biostrings" ,r-biostrings)
7938 ("r-genomicranges" ,r-genomicranges)
7939 ("r-iranges" ,r-iranges)
7940 ("r-kernsmooth" ,r-kernsmooth)
7941 ("r-plotrix" ,r-plotrix)))
7942 (home-page "https://bioconductor.org/packages/seqPattern")
7943 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7945 "This package provides tools to visualize oligonucleotide patterns and
7946 sequence motif occurrences across a large set of sequences centred at a common
7947 reference point and sorted by a user defined feature.")
7948 (license license:gpl3+)))
7950 (define-public r-genomation
7952 (name "r-genomation")
7956 (uri (bioconductor-uri "genomation" version))
7959 "1vdmdyrq0n7pf8cvy2950v7hrcrcbd9zl4fg7dcmyly3iiwdyirp"))))
7960 (build-system r-build-system)
7962 `(("r-biostrings" ,r-biostrings)
7963 ("r-bsgenome" ,r-bsgenome)
7964 ("r-data-table" ,r-data-table)
7965 ("r-genomeinfodb" ,r-genomeinfodb)
7966 ("r-genomicalignments" ,r-genomicalignments)
7967 ("r-genomicranges" ,r-genomicranges)
7968 ("r-ggplot2" ,r-ggplot2)
7969 ("r-gridbase" ,r-gridbase)
7970 ("r-impute" ,r-impute)
7971 ("r-iranges" ,r-iranges)
7972 ("r-matrixstats" ,r-matrixstats)
7973 ("r-plotrix" ,r-plotrix)
7976 ("r-readr" ,r-readr)
7977 ("r-reshape2" ,r-reshape2)
7978 ("r-rsamtools" ,r-rsamtools)
7979 ("r-rtracklayer" ,r-rtracklayer)
7980 ("r-runit" ,r-runit)
7981 ("r-s4vectors" ,r-s4vectors)
7982 ("r-seqpattern" ,r-seqpattern)))
7983 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7984 (synopsis "Summary, annotation and visualization of genomic data")
7986 "This package provides a package for summary and annotation of genomic
7987 intervals. Users can visualize and quantify genomic intervals over
7988 pre-defined functional regions, such as promoters, exons, introns, etc. The
7989 genomic intervals represent regions with a defined chromosome position, which
7990 may be associated with a score, such as aligned reads from HT-seq experiments,
7991 TF binding sites, methylation scores, etc. The package can use any tabular
7992 genomic feature data as long as it has minimal information on the locations of
7993 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7994 (license license:artistic2.0)))
7996 (define-public r-genomationdata
7998 (name "r-genomationdata")
8002 ;; We cannot use bioconductor-uri here because this tarball is
8003 ;; located under "data/annotation/" instead of "bioc/".
8004 (uri (string-append "https://bioconductor.org/packages/"
8005 "release/data/experiment/src/contrib/"
8006 "genomationData_" version ".tar.gz"))
8009 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
8010 (build-system r-build-system)
8011 ;; As this package provides little more than large data files, it doesn't
8012 ;; make sense to build substitutes.
8013 (arguments `(#:substitutable? #f))
8015 `(("r-knitr" ,r-knitr)))
8016 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8017 (synopsis "Experimental data for use with the genomation package")
8019 "This package contains experimental genetic data for use with the
8020 genomation package. Included are Chip Seq, Methylation and Cage data,
8021 downloaded from Encode.")
8022 (license license:gpl3+)))
8024 (define-public r-org-hs-eg-db
8026 (name "r-org-hs-eg-db")
8030 ;; We cannot use bioconductor-uri here because this tarball is
8031 ;; located under "data/annotation/" instead of "bioc/".
8032 (uri (string-append "https://www.bioconductor.org/packages/"
8033 "release/data/annotation/src/contrib/"
8034 "org.Hs.eg.db_" version ".tar.gz"))
8037 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
8039 `((upstream-name . "org.Hs.eg.db")))
8040 (build-system r-build-system)
8042 `(("r-annotationdbi" ,r-annotationdbi)))
8043 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8044 (synopsis "Genome wide annotation for Human")
8046 "This package contains genome-wide annotations for Human, primarily based
8047 on mapping using Entrez Gene identifiers.")
8048 (license license:artistic2.0)))
8050 (define-public r-org-ce-eg-db
8052 (name "r-org-ce-eg-db")
8056 ;; We cannot use bioconductor-uri here because this tarball is
8057 ;; located under "data/annotation/" instead of "bioc/".
8058 (uri (string-append "https://www.bioconductor.org/packages/"
8059 "release/data/annotation/src/contrib/"
8060 "org.Ce.eg.db_" version ".tar.gz"))
8063 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8065 `((upstream-name . "org.Ce.eg.db")))
8066 (build-system r-build-system)
8068 `(("r-annotationdbi" ,r-annotationdbi)))
8069 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8070 (synopsis "Genome wide annotation for Worm")
8072 "This package provides mappings from Entrez gene identifiers to various
8073 annotations for the genome of the model worm Caenorhabditis elegans.")
8074 (license license:artistic2.0)))
8076 (define-public r-org-dm-eg-db
8078 (name "r-org-dm-eg-db")
8082 ;; We cannot use bioconductor-uri here because this tarball is
8083 ;; located under "data/annotation/" instead of "bioc/".
8084 (uri (string-append "https://www.bioconductor.org/packages/"
8085 "release/data/annotation/src/contrib/"
8086 "org.Dm.eg.db_" version ".tar.gz"))
8089 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8091 `((upstream-name . "org.Dm.eg.db")))
8092 (build-system r-build-system)
8094 `(("r-annotationdbi" ,r-annotationdbi)))
8095 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8096 (synopsis "Genome wide annotation for Fly")
8098 "This package provides mappings from Entrez gene identifiers to various
8099 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8100 (license license:artistic2.0)))
8102 (define-public r-org-mm-eg-db
8104 (name "r-org-mm-eg-db")
8108 ;; We cannot use bioconductor-uri here because this tarball is
8109 ;; located under "data/annotation/" instead of "bioc/".
8110 (uri (string-append "https://www.bioconductor.org/packages/"
8111 "release/data/annotation/src/contrib/"
8112 "org.Mm.eg.db_" version ".tar.gz"))
8115 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8117 `((upstream-name . "org.Mm.eg.db")))
8118 (build-system r-build-system)
8120 `(("r-annotationdbi" ,r-annotationdbi)))
8121 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8122 (synopsis "Genome wide annotation for Mouse")
8124 "This package provides mappings from Entrez gene identifiers to various
8125 annotations for the genome of the model mouse Mus musculus.")
8126 (license license:artistic2.0)))
8128 (define-public r-seqlogo
8135 (uri (bioconductor-uri "seqLogo" version))
8138 "16xvqcdknix9vjm8mrixi6nyfsr45jm844jh1x90m8044lwrsic1"))))
8139 (properties `((upstream-name . "seqLogo")))
8140 (build-system r-build-system)
8141 (home-page "https://bioconductor.org/packages/seqLogo")
8142 (synopsis "Sequence logos for DNA sequence alignments")
8144 "seqLogo takes the position weight matrix of a DNA sequence motif and
8145 plots the corresponding sequence logo as introduced by Schneider and
8147 (license license:lgpl2.0+)))
8149 (define-public r-bsgenome-hsapiens-ucsc-hg19
8151 (name "r-bsgenome-hsapiens-ucsc-hg19")
8155 ;; We cannot use bioconductor-uri here because this tarball is
8156 ;; located under "data/annotation/" instead of "bioc/".
8157 (uri (string-append "https://www.bioconductor.org/packages/"
8158 "release/data/annotation/src/contrib/"
8159 "BSgenome.Hsapiens.UCSC.hg19_"
8163 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8165 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8166 (build-system r-build-system)
8167 ;; As this package provides little more than a very large data file it
8168 ;; doesn't make sense to build substitutes.
8169 (arguments `(#:substitutable? #f))
8171 `(("r-bsgenome" ,r-bsgenome)))
8173 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8174 (synopsis "Full genome sequences for Homo sapiens")
8176 "This package provides full genome sequences for Homo sapiens as provided
8177 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8178 (license license:artistic2.0)))
8180 (define-public r-bsgenome-mmusculus-ucsc-mm9
8182 (name "r-bsgenome-mmusculus-ucsc-mm9")
8186 ;; We cannot use bioconductor-uri here because this tarball is
8187 ;; located under "data/annotation/" instead of "bioc/".
8188 (uri (string-append "https://www.bioconductor.org/packages/"
8189 "release/data/annotation/src/contrib/"
8190 "BSgenome.Mmusculus.UCSC.mm9_"
8194 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8196 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8197 (build-system r-build-system)
8198 ;; As this package provides little more than a very large data file it
8199 ;; doesn't make sense to build substitutes.
8200 (arguments `(#:substitutable? #f))
8202 `(("r-bsgenome" ,r-bsgenome)))
8204 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8205 (synopsis "Full genome sequences for Mouse")
8207 "This package provides full genome sequences for Mus musculus (Mouse) as
8208 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8209 (license license:artistic2.0)))
8211 (define-public r-bsgenome-mmusculus-ucsc-mm10
8213 (name "r-bsgenome-mmusculus-ucsc-mm10")
8217 ;; We cannot use bioconductor-uri here because this tarball is
8218 ;; located under "data/annotation/" instead of "bioc/".
8219 (uri (string-append "https://www.bioconductor.org/packages/"
8220 "release/data/annotation/src/contrib/"
8221 "BSgenome.Mmusculus.UCSC.mm10_"
8225 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8227 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8228 (build-system r-build-system)
8229 ;; As this package provides little more than a very large data file it
8230 ;; doesn't make sense to build substitutes.
8231 (arguments `(#:substitutable? #f))
8233 `(("r-bsgenome" ,r-bsgenome)))
8235 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8236 (synopsis "Full genome sequences for Mouse")
8238 "This package provides full genome sequences for Mus
8239 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8240 in Biostrings objects.")
8241 (license license:artistic2.0)))
8243 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8245 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8249 ;; We cannot use bioconductor-uri here because this tarball is
8250 ;; located under "data/annotation/" instead of "bioc/".
8251 (uri (string-append "https://www.bioconductor.org/packages/"
8252 "release/data/annotation/src/contrib/"
8253 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8257 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8259 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8260 (build-system r-build-system)
8261 ;; As this package provides little more than a very large data file it
8262 ;; doesn't make sense to build substitutes.
8263 (arguments `(#:substitutable? #f))
8265 `(("r-bsgenome" ,r-bsgenome)
8266 ("r-genomicfeatures" ,r-genomicfeatures)
8267 ("r-annotationdbi" ,r-annotationdbi)))
8269 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8270 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8272 "This package loads a TxDb object, which is an R interface to
8273 prefabricated databases contained in this package. This package provides
8274 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8275 based on the knownGene track.")
8276 (license license:artistic2.0)))
8278 (define-public r-bsgenome-celegans-ucsc-ce6
8280 (name "r-bsgenome-celegans-ucsc-ce6")
8284 ;; We cannot use bioconductor-uri here because this tarball is
8285 ;; located under "data/annotation/" instead of "bioc/".
8286 (uri (string-append "https://www.bioconductor.org/packages/"
8287 "release/data/annotation/src/contrib/"
8288 "BSgenome.Celegans.UCSC.ce6_"
8292 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8294 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8295 (build-system r-build-system)
8296 ;; As this package provides little more than a very large data file it
8297 ;; doesn't make sense to build substitutes.
8298 (arguments `(#:substitutable? #f))
8300 `(("r-bsgenome" ,r-bsgenome)))
8302 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8303 (synopsis "Full genome sequences for Worm")
8305 "This package provides full genome sequences for Caenorhabditis
8306 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8308 (license license:artistic2.0)))
8310 (define-public r-bsgenome-celegans-ucsc-ce10
8312 (name "r-bsgenome-celegans-ucsc-ce10")
8316 ;; We cannot use bioconductor-uri here because this tarball is
8317 ;; located under "data/annotation/" instead of "bioc/".
8318 (uri (string-append "https://www.bioconductor.org/packages/"
8319 "release/data/annotation/src/contrib/"
8320 "BSgenome.Celegans.UCSC.ce10_"
8324 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8326 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8327 (build-system r-build-system)
8328 ;; As this package provides little more than a very large data file it
8329 ;; doesn't make sense to build substitutes.
8330 (arguments `(#:substitutable? #f))
8332 `(("r-bsgenome" ,r-bsgenome)))
8334 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8335 (synopsis "Full genome sequences for Worm")
8337 "This package provides full genome sequences for Caenorhabditis
8338 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8340 (license license:artistic2.0)))
8342 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8344 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8348 ;; We cannot use bioconductor-uri here because this tarball is
8349 ;; located under "data/annotation/" instead of "bioc/".
8350 (uri (string-append "https://www.bioconductor.org/packages/"
8351 "release/data/annotation/src/contrib/"
8352 "BSgenome.Dmelanogaster.UCSC.dm3_"
8356 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8358 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8359 (build-system r-build-system)
8360 ;; As this package provides little more than a very large data file it
8361 ;; doesn't make sense to build substitutes.
8362 (arguments `(#:substitutable? #f))
8364 `(("r-bsgenome" ,r-bsgenome)))
8366 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8367 (synopsis "Full genome sequences for Fly")
8369 "This package provides full genome sequences for Drosophila
8370 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8371 Biostrings objects.")
8372 (license license:artistic2.0)))
8374 (define-public r-motifrg
8381 (uri (bioconductor-uri "motifRG" version))
8384 "0mxhyidkyd2zqahdbg69y20r550z78lvr1r3pbjymnwfg4hcfq1p"))))
8385 (properties `((upstream-name . "motifRG")))
8386 (build-system r-build-system)
8388 `(("r-biostrings" ,r-biostrings)
8389 ("r-bsgenome" ,r-bsgenome)
8390 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8391 ("r-iranges" ,r-iranges)
8392 ("r-seqlogo" ,r-seqlogo)
8393 ("r-xvector" ,r-xvector)))
8394 (home-page "https://bioconductor.org/packages/motifRG")
8395 (synopsis "Discover motifs in high throughput sequencing data")
8397 "This package provides tools for discriminative motif discovery in high
8398 throughput genetic sequencing data sets using regression methods.")
8399 (license license:artistic2.0)))
8401 (define-public r-qtl
8408 (uri (string-append "mirror://cran/src/contrib/qtl_"
8412 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8413 (build-system r-build-system)
8414 (home-page "http://rqtl.org/")
8415 (synopsis "R package for analyzing QTL experiments in genetics")
8416 (description "R/qtl is an extension library for the R statistics
8417 system. It is used to analyze experimental crosses for identifying
8418 genes contributing to variation in quantitative traits (so-called
8419 quantitative trait loci, QTLs).
8421 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8422 identify genotyping errors, and to perform single-QTL and two-QTL,
8423 two-dimensional genome scans.")
8424 (license license:gpl3)))
8426 (define-public r-zlibbioc
8432 (uri (bioconductor-uri "zlibbioc" version))
8435 "1rwr0mci8a712q0isavi4jmhm94gwivc4nr8j7r4kw05flp4g7gz"))))
8437 `((upstream-name . "zlibbioc")))
8438 (build-system r-build-system)
8439 (home-page "https://bioconductor.org/packages/zlibbioc")
8440 (synopsis "Provider for zlib-1.2.5 to R packages")
8441 (description "This package uses the source code of zlib-1.2.5 to create
8442 libraries for systems that do not have these available via other means.")
8443 (license license:artistic2.0)))
8445 (define-public r-r4rna
8452 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8456 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8457 (build-system r-build-system)
8459 `(("r-optparse" ,r-optparse)
8460 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8461 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8462 (synopsis "Analysis framework for RNA secondary structure")
8464 "The R4RNA package aims to be a general framework for the analysis of RNA
8465 secondary structure and comparative analysis in R.")
8466 (license license:gpl3+)))
8468 (define-public r-rhtslib
8475 (uri (bioconductor-uri "Rhtslib" version))
8478 "16ywnb8cmr2xabd1i21b92rfziw7xfbv25yv16ipw617p41wa39z"))))
8479 (properties `((upstream-name . "Rhtslib")))
8480 (build-system r-build-system)
8482 `(("r-zlibbioc" ,r-zlibbioc)))
8486 `(("pkg-config" ,pkg-config)))
8487 (home-page "https://github.com/nhayden/Rhtslib")
8488 (synopsis "High-throughput sequencing library as an R package")
8490 "This package provides the HTSlib C library for high-throughput
8491 nucleotide sequence analysis. The package is primarily useful to developers
8492 of other R packages who wish to make use of HTSlib.")
8493 (license license:lgpl2.0+)))
8495 (define-public r-bamsignals
8497 (name "r-bamsignals")
8502 (uri (bioconductor-uri "bamsignals" version))
8505 "141q3p4lzwiqk1mfxi8q1q84axjl0gyiqg59xd3sp4viny4jqmgv"))))
8506 (build-system r-build-system)
8508 `(("r-biocgenerics" ,r-biocgenerics)
8509 ("r-genomicranges" ,r-genomicranges)
8510 ("r-iranges" ,r-iranges)
8512 ("r-rhtslib" ,r-rhtslib)
8513 ("r-zlibbioc" ,r-zlibbioc)))
8516 (home-page "https://bioconductor.org/packages/bamsignals")
8517 (synopsis "Extract read count signals from bam files")
8519 "This package allows to efficiently obtain count vectors from indexed bam
8520 files. It counts the number of nucleotide sequence reads in given genomic
8521 ranges and it computes reads profiles and coverage profiles. It also handles
8523 (license license:gpl2+)))
8525 (define-public r-rcas
8531 (uri (bioconductor-uri "RCAS" version))
8534 "0vmn7a0rm2ban0kaxrf5danhss2r4hfhnwh5889fjcgqy300fdd5"))))
8535 (build-system r-build-system)
8537 `(("r-testthat" ,r-testthat)
8538 ;; During vignette building knitr checks that "pandoc-citeproc"
8540 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8542 `(("r-biocgenerics" ,r-biocgenerics)
8543 ("r-biomart" ,r-biomart)
8544 ("r-biostrings" ,r-biostrings)
8545 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8546 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8547 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8548 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8549 ("r-cowplot" ,r-cowplot)
8550 ("r-data-table" ,r-data-table)
8553 ("r-genomation" ,r-genomation)
8554 ("r-genomicfeatures" ,r-genomicfeatures)
8555 ("r-ggplot2" ,r-ggplot2)
8556 ("r-ggseqlogo" ,r-ggseqlogo)
8557 ("r-knitr" ,r-knitr)
8558 ("r-motifrg" ,r-motifrg)
8559 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8560 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8561 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8562 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8563 ("r-pbapply" ,r-pbapply)
8564 ("r-pheatmap" ,r-pheatmap)
8565 ("r-plotly" ,r-plotly)
8566 ("r-plotrix" ,r-plotrix)
8567 ("r-proxy" ,r-proxy)
8568 ("r-rsqlite" ,r-rsqlite)
8569 ("r-rtracklayer" ,r-rtracklayer)
8570 ("r-rmarkdown" ,r-rmarkdown)
8571 ("r-s4vectors" ,r-s4vectors)
8572 ("r-topgo" ,r-topgo)))
8573 (synopsis "RNA-centric annotation system")
8575 "RCAS aims to be a standalone RNA-centric annotation system that provides
8576 intuitive reports and publication-ready graphics. This package provides the R
8577 library implementing most of the pipeline's features.")
8578 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8579 (license license:artistic2.0)))
8581 (define-public rcas-web
8588 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8589 "releases/download/v" version
8590 "/rcas-web-" version ".tar.gz"))
8593 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8594 (build-system gnu-build-system)
8597 (modify-phases %standard-phases
8598 (add-after 'install 'wrap-executable
8599 (lambda* (#:key inputs outputs #:allow-other-keys)
8600 (let* ((out (assoc-ref outputs "out"))
8601 (json (assoc-ref inputs "guile-json"))
8602 (redis (assoc-ref inputs "guile-redis"))
8603 (path (string-append
8604 json "/share/guile/site/2.2:"
8605 redis "/share/guile/site/2.2")))
8606 (wrap-program (string-append out "/bin/rcas-web")
8607 `("GUILE_LOAD_PATH" ":" = (,path))
8608 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8609 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8612 `(("r-minimal" ,r-minimal)
8614 ("guile-next" ,guile-2.2)
8615 ("guile-json" ,guile-json)
8616 ("guile-redis" ,guile2.2-redis)))
8618 `(("pkg-config" ,pkg-config)))
8619 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8620 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8621 (description "This package provides a simple web interface for the
8622 @dfn{RNA-centric annotation system} (RCAS).")
8623 (license license:agpl3+)))
8625 (define-public r-mutationalpatterns
8627 (name "r-mutationalpatterns")
8632 (uri (bioconductor-uri "MutationalPatterns" version))
8635 "1yq7351j42mjxn8fd3c5bdxzb2l5s4lvqhjdvv4rwj4f600n6wj9"))))
8636 (build-system r-build-system)
8638 `(("r-biocgenerics" ,r-biocgenerics)
8639 ("r-biostrings" ,r-biostrings)
8640 ;; These two packages are suggested packages
8641 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8642 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8643 ("r-genomicranges" ,r-genomicranges)
8644 ("r-genomeinfodb" ,r-genomeinfodb)
8645 ("r-ggplot2" ,r-ggplot2)
8646 ("r-iranges" ,r-iranges)
8649 ("r-pracma" ,r-pracma)
8650 ("r-reshape2" ,r-reshape2)
8651 ("r-cowplot" ,r-cowplot)
8652 ("r-ggdendro" ,r-ggdendro)
8653 ("r-s4vectors" ,r-s4vectors)
8654 ("r-summarizedexperiment" ,r-summarizedexperiment)
8655 ("r-variantannotation" ,r-variantannotation)))
8656 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8657 (synopsis "Extract and visualize mutational patterns in genomic data")
8658 (description "This package provides an extensive toolset for the
8659 characterization and visualization of a wide range of mutational patterns
8660 in SNV base substitution data.")
8661 (license license:expat)))
8663 (define-public r-wgcna
8670 (uri (cran-uri "WGCNA" version))
8673 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8674 (properties `((upstream-name . "WGCNA")))
8675 (build-system r-build-system)
8677 `(("r-annotationdbi" ,r-annotationdbi)
8678 ("r-doparallel" ,r-doparallel)
8679 ("r-dynamictreecut" ,r-dynamictreecut)
8680 ("r-fastcluster" ,r-fastcluster)
8681 ("r-foreach" ,r-foreach)
8682 ("r-go-db" ,r-go-db)
8683 ("r-hmisc" ,r-hmisc)
8684 ("r-impute" ,r-impute)
8686 ("r-robust" ,r-robust)
8687 ("r-survival" ,r-survival)
8688 ("r-matrixstats" ,r-matrixstats)
8689 ("r-preprocesscore" ,r-preprocesscore)))
8691 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8692 (synopsis "Weighted correlation network analysis")
8694 "This package provides functions necessary to perform Weighted
8695 Correlation Network Analysis on high-dimensional data. It includes functions
8696 for rudimentary data cleaning, construction and summarization of correlation
8697 networks, module identification and functions for relating both variables and
8698 modules to sample traits. It also includes a number of utility functions for
8699 data manipulation and visualization.")
8700 (license license:gpl2+)))
8702 (define-public r-chipkernels
8703 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8706 (name "r-chipkernels")
8707 (version (string-append "1.1-" revision "." (string-take commit 9)))
8712 (url "https://github.com/ManuSetty/ChIPKernels.git")
8714 (file-name (string-append name "-" version))
8717 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8718 (build-system r-build-system)
8720 `(("r-iranges" ,r-iranges)
8721 ("r-xvector" ,r-xvector)
8722 ("r-biostrings" ,r-biostrings)
8723 ("r-bsgenome" ,r-bsgenome)
8724 ("r-gtools" ,r-gtools)
8725 ("r-genomicranges" ,r-genomicranges)
8726 ("r-sfsmisc" ,r-sfsmisc)
8727 ("r-kernlab" ,r-kernlab)
8728 ("r-s4vectors" ,r-s4vectors)
8729 ("r-biocgenerics" ,r-biocgenerics)))
8730 (home-page "https://github.com/ManuSetty/ChIPKernels")
8731 (synopsis "Build string kernels for DNA Sequence analysis")
8732 (description "ChIPKernels is an R package for building different string
8733 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8734 must be built and this dictionary can be used for determining kernels for DNA
8736 (license license:gpl2+))))
8738 (define-public r-seqgl
8745 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8746 "archive/" version ".tar.gz"))
8747 (file-name (string-append name "-" version ".tar.gz"))
8750 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8751 (build-system r-build-system)
8753 `(("r-biostrings" ,r-biostrings)
8754 ("r-chipkernels" ,r-chipkernels)
8755 ("r-genomicranges" ,r-genomicranges)
8756 ("r-spams" ,r-spams)
8757 ("r-wgcna" ,r-wgcna)
8758 ("r-fastcluster" ,r-fastcluster)))
8759 (home-page "https://github.com/ManuSetty/SeqGL")
8760 (synopsis "Group lasso for Dnase/ChIP-seq data")
8761 (description "SeqGL is a group lasso based algorithm to extract
8762 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8763 This package presents a method which uses group lasso to discriminate between
8764 bound and non bound genomic regions to accurately identify transcription
8765 factors bound at the specific regions.")
8766 (license license:gpl2+)))
8768 (define-public r-gkmsvm
8775 (uri (cran-uri "gkmSVM" version))
8778 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8779 (properties `((upstream-name . "gkmSVM")))
8780 (build-system r-build-system)
8782 `(("r-biocgenerics" ,r-biocgenerics)
8783 ("r-biostrings" ,r-biostrings)
8784 ("r-genomeinfodb" ,r-genomeinfodb)
8785 ("r-genomicranges" ,r-genomicranges)
8786 ("r-iranges" ,r-iranges)
8787 ("r-kernlab" ,r-kernlab)
8790 ("r-rtracklayer" ,r-rtracklayer)
8791 ("r-s4vectors" ,r-s4vectors)
8792 ("r-seqinr" ,r-seqinr)))
8793 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8794 (synopsis "Gapped-kmer support vector machine")
8796 "This R package provides tools for training gapped-kmer SVM classifiers
8797 for DNA and protein sequences. This package supports several sequence
8798 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8799 (license license:gpl2+)))
8801 (define-public r-tximport
8807 (uri (bioconductor-uri "tximport" version))
8810 "1qjc7ah9dzccpvcjrp9k4qnaz13x6kvy1c1xpdj503km6k528lip"))))
8811 (build-system r-build-system)
8812 (home-page "https://bioconductor.org/packages/tximport")
8813 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8815 "This package provides tools to import transcript-level abundance,
8816 estimated counts and transcript lengths, and to summarize them into matrices
8817 for use with downstream gene-level analysis packages. Average transcript
8818 length, weighted by sample-specific transcript abundance estimates, is
8819 provided as a matrix which can be used as an offset for different expression
8820 of gene-level counts.")
8821 (license license:gpl2+)))
8823 (define-public r-rhdf5
8829 (uri (bioconductor-uri "rhdf5" version))
8832 "15cmmchhk8bnp94gxg0zk9qyzdjx5kv16dzpbnb62mkq7ydmifx6"))))
8833 (build-system r-build-system)
8835 `(("r-rhdf5lib" ,r-rhdf5lib)))
8838 (home-page "https://bioconductor.org/packages/rhdf5")
8839 (synopsis "HDF5 interface to R")
8841 "This R/Bioconductor package provides an interface between HDF5 and R.
8842 HDF5's main features are the ability to store and access very large and/or
8843 complex datasets and a wide variety of metadata on mass storage (disk) through
8844 a completely portable file format. The rhdf5 package is thus suited for the
8845 exchange of large and/or complex datasets between R and other software
8846 package, and for letting R applications work on datasets that are larger than
8847 the available RAM.")
8848 (license license:artistic2.0)))
8850 (define-public r-annotationfilter
8852 (name "r-annotationfilter")
8856 (uri (bioconductor-uri "AnnotationFilter" version))
8859 "1w8ypfdz4g7vnwfrvnhjcpm8waciqyq2cn883ajdwg4vv7a5mj9a"))))
8861 `((upstream-name . "AnnotationFilter")))
8862 (build-system r-build-system)
8864 `(("r-genomicranges" ,r-genomicranges)
8865 ("r-lazyeval" ,r-lazyeval)))
8866 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8867 (synopsis "Facilities for filtering Bioconductor annotation resources")
8869 "This package provides classes and other infrastructure to implement
8870 filters for manipulating Bioconductor annotation resources. The filters are
8871 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8872 (license license:artistic2.0)))
8874 (define-public emboss
8880 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8881 (version-major+minor version) ".0/"
8882 "EMBOSS-" version ".tar.gz"))
8885 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8886 (build-system gnu-build-system)
8889 (list (string-append "--with-hpdf="
8890 (assoc-ref %build-inputs "libharu")))
8892 (modify-phases %standard-phases
8893 (add-after 'unpack 'fix-checks
8895 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8896 ;; and zlib, but assume that they are all found at the same
8898 (substitute* "configure.in"
8899 (("CHECK_PNGDRIVER")
8900 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8901 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8902 AM_CONDITIONAL(AMPNG, true)"))
8904 (add-after 'fix-checks 'disable-update-check
8906 ;; At build time there is no connection to the Internet, so
8907 ;; looking for updates will not work.
8908 (substitute* "Makefile.am"
8909 (("\\$\\(bindir\\)/embossupdate") ""))
8911 (add-after 'disable-update-check 'autogen
8912 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8918 ("libharu" ,libharu)
8921 `(("autoconf" ,autoconf)
8922 ("automake" ,automake)
8923 ("libtool" ,libtool)
8924 ("pkg-config" ,pkg-config)))
8925 (home-page "http://emboss.sourceforge.net")
8926 (synopsis "Molecular biology analysis suite")
8927 (description "EMBOSS is the \"European Molecular Biology Open Software
8928 Suite\". EMBOSS is an analysis package specially developed for the needs of
8929 the molecular biology (e.g. EMBnet) user community. The software
8930 automatically copes with data in a variety of formats and even allows
8931 transparent retrieval of sequence data from the web. It also provides a
8932 number of libraries for the development of software in the field of molecular
8933 biology. EMBOSS also integrates a range of currently available packages and
8934 tools for sequence analysis into a seamless whole.")
8935 (license license:gpl2+)))
8938 (let ((revision "1")
8939 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8942 ;; The version is 2.13.0 even though no release archives have been
8943 ;; published as yet.
8944 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8948 (url "https://github.com/arq5x/bits.git")
8950 (file-name (string-append name "-" version "-checkout"))
8953 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8954 (build-system gnu-build-system)
8956 `(#:tests? #f ;no tests included
8958 (modify-phases %standard-phases
8960 (add-after 'unpack 'remove-cuda
8962 (substitute* "Makefile"
8964 (("(bits_test_intersections) \\\\" _ match) match))
8967 (lambda* (#:key outputs #:allow-other-keys)
8969 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8974 (home-page "https://github.com/arq5x/bits")
8975 (synopsis "Implementation of binary interval search algorithm")
8976 (description "This package provides an implementation of the
8977 BITS (Binary Interval Search) algorithm, an approach to interval set
8978 intersection. It is especially suited for the comparison of diverse genomic
8979 datasets and the exploration of large datasets of genome
8980 intervals (e.g. genes, sequence alignments).")
8981 (license license:gpl2))))
8983 (define-public piranha
8984 ;; There is no release tarball for the latest version. The latest commit is
8985 ;; older than one year at the time of this writing.
8986 (let ((revision "1")
8987 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8990 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8994 (url "https://github.com/smithlabcode/piranha.git")
8996 (file-name (git-file-name name version))
8999 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9000 (build-system gnu-build-system)
9002 `(#:test-target "test"
9004 (modify-phases %standard-phases
9005 (add-after 'unpack 'copy-smithlab-cpp
9006 (lambda* (#:key inputs #:allow-other-keys)
9007 (for-each (lambda (file)
9008 (install-file file "./src/smithlab_cpp/"))
9009 (find-files (assoc-ref inputs "smithlab-cpp")))
9011 (add-after 'install 'install-to-store
9012 (lambda* (#:key outputs #:allow-other-keys)
9013 (let* ((out (assoc-ref outputs "out"))
9014 (bin (string-append out "/bin")))
9015 (for-each (lambda (file)
9016 (install-file file bin))
9017 (find-files "bin" ".*")))
9020 (list (string-append "--with-bam_tools_headers="
9021 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9022 (string-append "--with-bam_tools_library="
9023 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9025 `(("bamtools" ,bamtools)
9026 ("samtools" ,samtools-0.1)
9029 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9033 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9035 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9038 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9040 `(("python" ,python-2)))
9041 (home-page "https://github.com/smithlabcode/piranha")
9042 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9044 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9045 RIP-seq experiments. It takes input in BED or BAM format and identifies
9046 regions of statistically significant read enrichment. Additional covariates
9047 may optionally be provided to further inform the peak-calling process.")
9048 (license license:gpl3+))))
9056 (uri (string-append "https://pypi.python.org/packages/source/P"
9057 "/PePr/PePr-" version ".tar.gz"))
9060 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9061 (build-system python-build-system)
9063 `(#:python ,python-2 ; python2 only
9064 #:tests? #f)) ; no tests included
9066 `(("python2-numpy" ,python2-numpy)
9067 ("python2-scipy" ,python2-scipy)
9068 ("python2-pysam" ,python2-pysam)))
9069 (home-page "https://github.com/shawnzhangyx/PePr")
9070 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9072 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9073 that is primarily designed for data with biological replicates. It uses a
9074 negative binomial distribution to model the read counts among the samples in
9075 the same group, and look for consistent differences between ChIP and control
9076 group or two ChIP groups run under different conditions.")
9077 (license license:gpl3+)))
9079 (define-public filevercmp
9080 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9083 (version (string-append "0-1." (string-take commit 7)))
9086 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9088 (file-name (string-append name "-" version ".tar.gz"))
9090 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9091 (build-system gnu-build-system)
9093 `(#:tests? #f ; There are no tests to run.
9095 (modify-phases %standard-phases
9096 (delete 'configure) ; There is no configure phase.
9098 (lambda* (#:key outputs #:allow-other-keys)
9099 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9100 (install-file "filevercmp" bin)))))))
9101 (home-page "https://github.com/ekg/filevercmp")
9102 (synopsis "This program compares version strings")
9103 (description "This program compares version strings. It intends to be a
9104 replacement for strverscmp.")
9105 (license license:gpl3+))))
9107 (define-public multiqc
9114 (uri (pypi-uri "multiqc" version))
9117 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9118 (build-system python-build-system)
9120 `(("python-jinja2" ,python-jinja2)
9121 ("python-simplejson" ,python-simplejson)
9122 ("python-pyyaml" ,python-pyyaml)
9123 ("python-click" ,python-click)
9124 ("python-spectra" ,python-spectra)
9125 ("python-requests" ,python-requests)
9126 ("python-markdown" ,python-markdown)
9127 ("python-lzstring" ,python-lzstring)
9128 ("python-matplotlib" ,python-matplotlib)
9129 ("python-numpy" ,python-numpy)
9130 ;; MultQC checks for the presence of nose at runtime.
9131 ("python-nose" ,python-nose)))
9134 (modify-phases %standard-phases
9135 (add-after 'unpack 'relax-requirements
9137 (substitute* "setup.py"
9138 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9139 ;; than the one in Guix, but should work fine with 2.2.2.
9140 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9141 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9142 (("['\"]matplotlib.*?['\"]")
9145 (home-page "http://multiqc.info")
9146 (synopsis "Aggregate bioinformatics analysis reports")
9148 "MultiQC is a tool to aggregate bioinformatics results across many
9149 samples into a single report. It contains modules for a large number of
9150 common bioinformatics tools.")
9151 (license license:gpl3+)))
9153 (define-public r-chipseq
9160 (uri (bioconductor-uri "chipseq" version))
9163 "09f8dgl5ni75qkf7nvvppwr3irpplv4xb3ks59ld7l8i2mplcrx7"))))
9164 (build-system r-build-system)
9166 `(("r-biocgenerics" ,r-biocgenerics)
9167 ("r-genomicranges" ,r-genomicranges)
9168 ("r-iranges" ,r-iranges)
9169 ("r-lattice" ,r-lattice)
9170 ("r-s4vectors" ,r-s4vectors)
9171 ("r-shortread" ,r-shortread)))
9172 (home-page "https://bioconductor.org/packages/chipseq")
9173 (synopsis "Package for analyzing ChIPseq data")
9175 "This package provides tools for processing short read data from ChIPseq
9177 (license license:artistic2.0)))
9179 (define-public r-copyhelper
9181 (name "r-copyhelper")
9186 (uri (string-append "https://bioconductor.org/packages/release/"
9187 "data/experiment/src/contrib/CopyhelpeR_"
9191 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9192 (properties `((upstream-name . "CopyhelpeR")))
9193 (build-system r-build-system)
9194 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9195 (synopsis "Helper files for CopywriteR")
9197 "This package contains the helper files that are required to run the
9198 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9199 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9200 mm10. In addition, it contains a blacklist filter to remove regions that
9201 display copy number variation. Files are stored as GRanges objects from the
9202 GenomicRanges Bioconductor package.")
9203 (license license:gpl2)))
9205 (define-public r-copywriter
9207 (name "r-copywriter")
9212 (uri (bioconductor-uri "CopywriteR" version))
9215 "0b7xwq1va2zclb54f07c5ipmmq4iv2hrlph3j93jz5hmyayv50z3"))))
9216 (properties `((upstream-name . "CopywriteR")))
9217 (build-system r-build-system)
9219 `(("r-biocparallel" ,r-biocparallel)
9220 ("r-chipseq" ,r-chipseq)
9221 ("r-copyhelper" ,r-copyhelper)
9222 ("r-data-table" ,r-data-table)
9223 ("r-dnacopy" ,r-dnacopy)
9224 ("r-futile-logger" ,r-futile-logger)
9225 ("r-genomeinfodb" ,r-genomeinfodb)
9226 ("r-genomicalignments" ,r-genomicalignments)
9227 ("r-genomicranges" ,r-genomicranges)
9228 ("r-gtools" ,r-gtools)
9229 ("r-iranges" ,r-iranges)
9230 ("r-matrixstats" ,r-matrixstats)
9231 ("r-rsamtools" ,r-rsamtools)
9232 ("r-s4vectors" ,r-s4vectors)))
9233 (home-page "https://github.com/PeeperLab/CopywriteR")
9234 (synopsis "Copy number information from targeted sequencing")
9236 "CopywriteR extracts DNA copy number information from targeted sequencing
9237 by utilizing off-target reads. It allows for extracting uniformly distributed
9238 copy number information, can be used without reference, and can be applied to
9239 sequencing data obtained from various techniques including chromatin
9240 immunoprecipitation and target enrichment on small gene panels. Thereby,
9241 CopywriteR constitutes a widely applicable alternative to available copy
9242 number detection tools.")
9243 (license license:gpl2)))
9245 (define-public r-methylkit
9247 (name "r-methylkit")
9251 (uri (bioconductor-uri "methylKit" version))
9254 "1hr2czi5ybdf7hdmqsv39d17f3mvmw94wa38bc14zzm9mgy9gfy7"))))
9255 (properties `((upstream-name . "methylKit")))
9256 (build-system r-build-system)
9258 `(("r-data-table" ,r-data-table)
9259 ("r-emdbook" ,r-emdbook)
9260 ("r-fastseg" ,r-fastseg)
9261 ("r-genomeinfodb" ,r-genomeinfodb)
9262 ("r-genomicranges" ,r-genomicranges)
9263 ("r-gtools" ,r-gtools)
9264 ("r-iranges" ,r-iranges)
9265 ("r-kernsmooth" ,r-kernsmooth)
9266 ("r-limma" ,r-limma)
9267 ("r-mclust" ,r-mclust)
9268 ("r-qvalue" ,r-qvalue)
9269 ("r-r-utils" ,r-r-utils)
9271 ("r-rhtslib" ,r-rhtslib)
9272 ("r-rsamtools" ,r-rsamtools)
9273 ("r-rtracklayer" ,r-rtracklayer)
9274 ("r-s4vectors" ,r-s4vectors)
9275 ("r-zlibbioc" ,r-zlibbioc)))
9278 (home-page "https://github.com/al2na/methylKit")
9280 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9282 "MethylKit is an R package for DNA methylation analysis and annotation
9283 from high-throughput bisulfite sequencing. The package is designed to deal
9284 with sequencing data from @dfn{Reduced representation bisulfite
9285 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9286 genome bisulfite sequencing. It also has functions to analyze base-pair
9287 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9289 (license license:artistic2.0)))
9291 (define-public r-sva
9298 (uri (bioconductor-uri "sva" version))
9301 "0a3jqbz0jp1jxrnjkqfpmca840yqcdwxprdl608bzzx2zb4jl52s"))))
9302 (build-system r-build-system)
9304 `(("r-genefilter" ,r-genefilter)
9306 ("r-biocparallel" ,r-biocparallel)
9307 ("r-matrixstats" ,r-matrixstats)
9308 ("r-limma" ,r-limma)))
9309 (home-page "https://bioconductor.org/packages/sva")
9310 (synopsis "Surrogate variable analysis")
9312 "This package contains functions for removing batch effects and other
9313 unwanted variation in high-throughput experiment. It also contains functions
9314 for identifying and building surrogate variables for high-dimensional data
9315 sets. Surrogate variables are covariates constructed directly from
9316 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9317 imaging data that can be used in subsequent analyses to adjust for unknown,
9318 unmodeled, or latent sources of noise.")
9319 (license license:artistic2.0)))
9321 (define-public r-seqminer
9328 (uri (cran-uri "seqminer" version))
9331 "15yhg4vfc7jg1jnqb3371j00pgbmbyc9l1xx63hq1l3p34lazq2l"))))
9332 (build-system r-build-system)
9335 (home-page "http://seqminer.genomic.codes")
9336 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9338 "This package provides tools to integrate nucleotide sequencing
9339 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9340 ;; Any version of the GPL is acceptable
9341 (license (list license:gpl2+ license:gpl3+))))
9343 (define-public r-raremetals2
9345 (name "r-raremetals2")
9350 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9351 "b/b7/RareMETALS2_" version ".tar.gz"))
9354 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9355 (properties `((upstream-name . "RareMETALS2")))
9356 (build-system r-build-system)
9358 `(("r-seqminer" ,r-seqminer)
9359 ("r-mvtnorm" ,r-mvtnorm)
9361 ("r-compquadform" ,r-compquadform)
9362 ("r-getopt" ,r-getopt)))
9363 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9364 (synopsis "Analyze gene-level association tests for binary trait")
9366 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9367 It was designed to meta-analyze gene-level association tests for binary trait.
9368 While rareMETALS offers a near-complete solution for meta-analysis of
9369 gene-level tests for quantitative trait, it does not offer the optimal
9370 solution for binary trait. The package rareMETALS2 offers improved features
9371 for analyzing gene-level association tests in meta-analyses for binary
9373 (license license:gpl3)))
9375 (define-public r-maldiquant
9377 (name "r-maldiquant")
9382 (uri (cran-uri "MALDIquant" version))
9385 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9386 (properties `((upstream-name . "MALDIquant")))
9387 (build-system r-build-system)
9388 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9389 (synopsis "Quantitative analysis of mass spectrometry data")
9391 "This package provides a complete analysis pipeline for matrix-assisted
9392 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9393 two-dimensional mass spectrometry data. In addition to commonly used plotting
9394 and processing methods it includes distinctive features, namely baseline
9395 subtraction methods such as morphological filters (TopHat) or the
9396 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9397 alignment using warping functions, handling of replicated measurements as well
9398 as allowing spectra with different resolutions.")
9399 (license license:gpl3+)))
9401 (define-public r-protgenerics
9403 (name "r-protgenerics")
9408 (uri (bioconductor-uri "ProtGenerics" version))
9411 "05jbadw2aiwy8vi2ia0jxg06cmwhly2cq4dy1ag7kdxf1c5i9ccn"))))
9412 (properties `((upstream-name . "ProtGenerics")))
9413 (build-system r-build-system)
9414 (home-page "https://github.com/lgatto/ProtGenerics")
9415 (synopsis "S4 generic functions for proteomics infrastructure")
9417 "This package provides S4 generic functions needed by Bioconductor
9418 proteomics packages.")
9419 (license license:artistic2.0)))
9421 (define-public r-mzr
9428 (uri (bioconductor-uri "mzR" version))
9431 "190m2bq5bqxhljaj4f7vz9wj5h5laaxd8zp5jampnql6xc4zmarg"))
9432 (modules '((guix build utils)))
9435 (delete-file-recursively "src/boost")
9437 (properties `((upstream-name . "mzR")))
9438 (build-system r-build-system)
9441 (modify-phases %standard-phases
9442 (add-after 'unpack 'use-system-boost
9444 (substitute* "src/Makevars"
9445 (("\\./boost/libs.*") "")
9446 (("ARCH_OBJS=" line)
9448 "\nARCH_LIBS=-lboost_system -lboost_regex \
9449 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9452 `(("boost" ,boost) ; use this instead of the bundled boost sources
9456 `(("r-biobase" ,r-biobase)
9457 ("r-biocgenerics" ,r-biocgenerics)
9458 ("r-protgenerics" ,r-protgenerics)
9460 ("r-rhdf5lib" ,r-rhdf5lib)
9461 ("r-zlibbioc" ,r-zlibbioc)))
9462 (home-page "https://github.com/sneumann/mzR/")
9463 (synopsis "Parser for mass spectrometry data files")
9465 "The mzR package provides a unified API to the common file formats and
9466 parsers available for mass spectrometry data. It comes with a wrapper for the
9467 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9468 The package contains the original code written by the ISB, and a subset of the
9469 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9470 previously been used in XCMS.")
9471 (license license:artistic2.0)))
9473 (define-public r-affyio
9480 (uri (bioconductor-uri "affyio" version))
9483 "0sh5wnnchyfpq5n6rchbqmb27byn7kdzn5rgran6i39c81i5z22n"))))
9484 (build-system r-build-system)
9486 `(("r-zlibbioc" ,r-zlibbioc)))
9489 (home-page "https://github.com/bmbolstad/affyio")
9490 (synopsis "Tools for parsing Affymetrix data files")
9492 "This package provides routines for parsing Affymetrix data files based
9493 upon file format information. The primary focus is on accessing the CEL and
9495 (license license:lgpl2.0+)))
9497 (define-public r-affy
9504 (uri (bioconductor-uri "affy" version))
9507 "0sxq875sigm21sf3qncrfrwfdz9nqw1vldxn3d3hj6aq64jg1ki6"))))
9508 (build-system r-build-system)
9510 `(("r-affyio" ,r-affyio)
9511 ("r-biobase" ,r-biobase)
9512 ("r-biocgenerics" ,r-biocgenerics)
9513 ("r-biocinstaller" ,r-biocinstaller)
9514 ("r-preprocesscore" ,r-preprocesscore)
9515 ("r-zlibbioc" ,r-zlibbioc)))
9518 (home-page "https://bioconductor.org/packages/affy")
9519 (synopsis "Methods for affymetrix oligonucleotide arrays")
9521 "This package contains functions for exploratory oligonucleotide array
9523 (license license:lgpl2.0+)))
9525 (define-public r-vsn
9532 (uri (bioconductor-uri "vsn" version))
9535 "0k6mah3g3zqbfap31xmvig4fn452a18xwwa5y0mfj5mj8588p57h"))))
9536 (build-system r-build-system)
9538 `(("r-affy" ,r-affy)
9539 ("r-biobase" ,r-biobase)
9540 ("r-ggplot2" ,r-ggplot2)
9541 ("r-lattice" ,r-lattice)
9542 ("r-limma" ,r-limma)))
9543 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9544 (synopsis "Variance stabilization and calibration for microarray data")
9546 "The package implements a method for normalising microarray intensities,
9547 and works for single- and multiple-color arrays. It can also be used for data
9548 from other technologies, as long as they have similar format. The method uses
9549 a robust variant of the maximum-likelihood estimator for an
9550 additive-multiplicative error model and affine calibration. The model
9551 incorporates data calibration step (a.k.a. normalization), a model for the
9552 dependence of the variance on the mean intensity and a variance stabilizing
9553 data transformation. Differences between transformed intensities are
9554 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9555 their variance is independent of the mean, and they are usually more sensitive
9556 and specific in detecting differential transcription.")
9557 (license license:artistic2.0)))
9559 (define-public r-mzid
9566 (uri (bioconductor-uri "mzID" version))
9569 "060k0xlhg8q802c6zsb4b8ps0ccd9ybyaz0gnsvqkxb786i2vk40"))))
9570 (properties `((upstream-name . "mzID")))
9571 (build-system r-build-system)
9573 `(("r-doparallel" ,r-doparallel)
9574 ("r-foreach" ,r-foreach)
9575 ("r-iterators" ,r-iterators)
9577 ("r-protgenerics" ,r-protgenerics)
9580 (home-page "https://bioconductor.org/packages/mzID")
9581 (synopsis "Parser for mzIdentML files")
9583 "This package provides a parser for mzIdentML files implemented using the
9584 XML package. The parser tries to be general and able to handle all types of
9585 mzIdentML files with the drawback of having less pretty output than a vendor
9587 (license license:gpl2+)))
9589 (define-public r-pcamethods
9591 (name "r-pcamethods")
9596 (uri (bioconductor-uri "pcaMethods" version))
9599 "0v99yf8m7ryh6z0r3z0ggpqfnflcq5bn1q1i1cl9b7q4p6b4sa07"))))
9600 (properties `((upstream-name . "pcaMethods")))
9601 (build-system r-build-system)
9603 `(("r-biobase" ,r-biobase)
9604 ("r-biocgenerics" ,r-biocgenerics)
9606 ("r-rcpp" ,r-rcpp)))
9607 (home-page "https://github.com/hredestig/pcamethods")
9608 (synopsis "Collection of PCA methods")
9610 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9611 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9612 for missing value estimation is included for comparison. BPCA, PPCA and
9613 NipalsPCA may be used to perform PCA on incomplete data as well as for
9614 accurate missing value estimation. A set of methods for printing and plotting
9615 the results is also provided. All PCA methods make use of the same data
9616 structure (pcaRes) to provide a common interface to the PCA results.")
9617 (license license:gpl3+)))
9619 (define-public r-msnbase
9626 (uri (bioconductor-uri "MSnbase" version))
9629 "0zrpx9r93q5ca2zdak5rs2m9sjm0wjdra1xfj3d3sx6p5gzfyg6n"))))
9630 (properties `((upstream-name . "MSnbase")))
9631 (build-system r-build-system)
9633 `(("r-affy" ,r-affy)
9634 ("r-biobase" ,r-biobase)
9635 ("r-biocgenerics" ,r-biocgenerics)
9636 ("r-biocparallel" ,r-biocparallel)
9637 ("r-digest" ,r-digest)
9638 ("r-ggplot2" ,r-ggplot2)
9639 ("r-impute" ,r-impute)
9640 ("r-iranges" ,r-iranges)
9641 ("r-lattice" ,r-lattice)
9642 ("r-maldiquant" ,r-maldiquant)
9646 ("r-pcamethods" ,r-pcamethods)
9648 ("r-preprocesscore" ,r-preprocesscore)
9649 ("r-protgenerics" ,r-protgenerics)
9651 ("r-s4vectors" ,r-s4vectors)
9652 ("r-scales" ,r-scales)
9655 (home-page "https://github.com/lgatto/MSnbase")
9656 (synopsis "Base functions and classes for MS-based proteomics")
9658 "This package provides basic plotting, data manipulation and processing
9659 of mass spectrometry based proteomics data.")
9660 (license license:artistic2.0)))
9662 (define-public r-msnid
9669 (uri (bioconductor-uri "MSnID" version))
9672 "172q5chi44104iz4y0g42wrimfp7hlhrfa8vzybx6m0ccrkkhl17"))))
9673 (properties `((upstream-name . "MSnID")))
9674 (build-system r-build-system)
9676 `(("r-biobase" ,r-biobase)
9677 ("r-data-table" ,r-data-table)
9678 ("r-doparallel" ,r-doparallel)
9679 ("r-dplyr" ,r-dplyr)
9680 ("r-foreach" ,r-foreach)
9681 ("r-iterators" ,r-iterators)
9682 ("r-msnbase" ,r-msnbase)
9685 ("r-protgenerics" ,r-protgenerics)
9686 ("r-r-cache" ,r-r-cache)
9688 ("r-reshape2" ,r-reshape2)))
9689 (home-page "https://bioconductor.org/packages/MSnID")
9690 (synopsis "Utilities for LC-MSn proteomics identifications")
9692 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9693 from mzIdentML (leveraging the mzID package) or text files. After collating
9694 the search results from multiple datasets it assesses their identification
9695 quality and optimize filtering criteria to achieve the maximum number of
9696 identifications while not exceeding a specified false discovery rate. It also
9697 contains a number of utilities to explore the MS/MS results and assess missed
9698 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9699 (license license:artistic2.0)))
9701 (define-public r-seurat
9707 (uri (cran-uri "Seurat" version))
9710 "1sjpy5rrpvlpm6hs7qy7qpglgbp7zrgfybcsalpmjb51rhxhgcg1"))
9711 ;; Delete pre-built jar.
9713 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9715 (properties `((upstream-name . "Seurat")))
9716 (build-system r-build-system)
9719 (modify-phases %standard-phases
9720 (add-after 'unpack 'build-jar
9721 (lambda* (#:key inputs #:allow-other-keys)
9722 (let ((classesdir "tmp-classes"))
9723 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9725 (with-output-to-file "manifest"
9727 (display "Manifest-Version: 1.0
9728 Main-Class: ModularityOptimizer\n")))
9729 (and (zero? (apply system* `("javac" "-d" ,classesdir
9730 ,@(find-files "java" "\\.java$"))))
9731 (zero? (system* "jar"
9733 "inst/java/ModularityOptimizer.jar"
9734 "-C" classesdir ".")))))))))
9736 `(("jdk" ,icedtea "jdk")))
9739 ("r-caret" ,r-caret)
9740 ("r-cluster" ,r-cluster)
9741 ("r-cowplot" ,r-cowplot)
9742 ("r-diffusionmap" ,r-diffusionmap)
9743 ("r-dosnow" ,r-dosnow)
9744 ("r-dplyr" ,r-dplyr)
9746 ("r-fitdistrplus" ,r-fitdistrplus)
9748 ("r-foreach" ,r-foreach)
9750 ("r-gdata" ,r-gdata)
9751 ("r-ggplot2" ,r-ggplot2)
9752 ("r-ggridges" ,r-ggridges)
9753 ("r-gplots" ,r-gplots)
9754 ("r-hdf5r" ,r-hdf5r)
9755 ("r-hmisc" ,r-hmisc)
9757 ("r-igraph" ,r-igraph)
9758 ("r-irlba" ,r-irlba)
9760 ("r-lmtest" ,r-lmtest)
9762 ("r-matrix" ,r-matrix)
9763 ("r-metap" ,r-metap)
9764 ("r-mixtools" ,r-mixtools)
9765 ("r-pbapply" ,r-pbapply)
9766 ("r-plotly" ,r-plotly)
9768 ("r-ranger" ,r-ranger)
9770 ("r-rcolorbrewer" ,r-rcolorbrewer)
9772 ("r-rcppeigen" ,r-rcppeigen)
9773 ("r-rcppprogress" ,r-rcppprogress)
9774 ("r-reshape2" ,r-reshape2)
9775 ("r-reticulate" ,r-reticulate)
9777 ("r-rtsne" ,r-rtsne)
9778 ("r-sdmtools" ,r-sdmtools)
9779 ("r-stringr" ,r-stringr)
9780 ("r-tclust" ,r-tclust)
9781 ("r-tidyr" ,r-tidyr)
9783 ("r-vgam" ,r-vgam)))
9784 (home-page "http://www.satijalab.org/seurat")
9785 (synopsis "Seurat is an R toolkit for single cell genomics")
9787 "This package is an R package designed for QC, analysis, and
9788 exploration of single cell RNA-seq data. It easily enables widely-used
9789 analytical techniques, including the identification of highly variable genes,
9790 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9791 algorithms; density clustering, hierarchical clustering, k-means, and the
9792 discovery of differentially expressed genes and markers.")
9793 (license license:gpl3)))
9795 (define-public r-aroma-light
9797 (name "r-aroma-light")
9802 (uri (bioconductor-uri "aroma.light" version))
9805 "1dxsiwsrwcq9mj573f9vpdzrhagdqzal328ma8076px4gg6khxkn"))))
9806 (properties `((upstream-name . "aroma.light")))
9807 (build-system r-build-system)
9809 `(("r-matrixstats" ,r-matrixstats)
9810 ("r-r-methodss3" ,r-r-methodss3)
9812 ("r-r-utils" ,r-r-utils)))
9813 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9814 (synopsis "Methods for normalization and visualization of microarray data")
9816 "This package provides methods for microarray analysis that take basic
9817 data types such as matrices and lists of vectors. These methods can be used
9818 standalone, be utilized in other packages, or be wrapped up in higher-level
9820 (license license:gpl2+)))
9822 (define-public r-deseq
9829 (uri (bioconductor-uri "DESeq" version))
9832 "0ykxw8ksif026xy25wx50j2sdsrp156aqkmhcgfjkpgcw699glnm"))))
9833 (properties `((upstream-name . "DESeq")))
9834 (build-system r-build-system)
9836 `(("r-biobase" ,r-biobase)
9837 ("r-biocgenerics" ,r-biocgenerics)
9838 ("r-genefilter" ,r-genefilter)
9839 ("r-geneplotter" ,r-geneplotter)
9840 ("r-lattice" ,r-lattice)
9841 ("r-locfit" ,r-locfit)
9843 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9844 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9845 (synopsis "Differential gene expression analysis")
9847 "This package provides tools for estimating variance-mean dependence in
9848 count data from high-throughput genetic sequencing assays and for testing for
9849 differential expression based on a model using the negative binomial
9851 (license license:gpl3+)))
9853 (define-public r-edaseq
9860 (uri (bioconductor-uri "EDASeq" version))
9863 "1832pb3jkim4vrqzb8lajwx9r482bhww5n9nz3s6crvyamlp2dj0"))))
9864 (properties `((upstream-name . "EDASeq")))
9865 (build-system r-build-system)
9867 `(("r-annotationdbi" ,r-annotationdbi)
9868 ("r-aroma-light" ,r-aroma-light)
9869 ("r-biobase" ,r-biobase)
9870 ("r-biocgenerics" ,r-biocgenerics)
9871 ("r-biomart" ,r-biomart)
9872 ("r-biostrings" ,r-biostrings)
9873 ("r-deseq" ,r-deseq)
9874 ("r-genomicfeatures" ,r-genomicfeatures)
9875 ("r-genomicranges" ,r-genomicranges)
9876 ("r-iranges" ,r-iranges)
9877 ("r-rsamtools" ,r-rsamtools)
9878 ("r-shortread" ,r-shortread)))
9879 (home-page "https://github.com/drisso/EDASeq")
9880 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9882 "This package provides support for numerical and graphical summaries of
9883 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9884 adjust for GC-content effect (or other gene-level effects) on read counts:
9885 loess robust local regression, global-scaling, and full-quantile
9886 normalization. Between-lane normalization procedures to adjust for
9887 distributional differences between lanes (e.g., sequencing depth):
9888 global-scaling and full-quantile normalization.")
9889 (license license:artistic2.0)))
9891 (define-public r-interactivedisplaybase
9893 (name "r-interactivedisplaybase")
9898 (uri (bioconductor-uri "interactiveDisplayBase" version))
9901 "05w58z3i9vkma4jd6rhjaxls4yiq4kwrppgcdq9xrr1pxp99k575"))))
9903 `((upstream-name . "interactiveDisplayBase")))
9904 (build-system r-build-system)
9906 `(("r-biocgenerics" ,r-biocgenerics)
9907 ("r-shiny" ,r-shiny)))
9908 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9909 (synopsis "Base package for web displays of Bioconductor objects")
9911 "This package contains the basic methods needed to generate interactive
9912 Shiny-based display methods for Bioconductor objects.")
9913 (license license:artistic2.0)))
9915 (define-public r-annotationhub
9917 (name "r-annotationhub")
9922 (uri (bioconductor-uri "AnnotationHub" version))
9925 "11gh7qkgazs90czdqgv74gh2hz26xrmdp6wsz9x5pygbxls8xdw3"))))
9926 (properties `((upstream-name . "AnnotationHub")))
9927 (build-system r-build-system)
9929 `(("r-annotationdbi" ,r-annotationdbi)
9930 ("r-biocgenerics" ,r-biocgenerics)
9931 ("r-biocinstaller" ,r-biocinstaller)
9934 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9935 ("r-rsqlite" ,r-rsqlite)
9936 ("r-s4vectors" ,r-s4vectors)
9937 ("r-yaml" ,r-yaml)))
9938 (home-page "https://bioconductor.org/packages/AnnotationHub")
9939 (synopsis "Client to access AnnotationHub resources")
9941 "This package provides a client for the Bioconductor AnnotationHub web
9942 resource. The AnnotationHub web resource provides a central location where
9943 genomic files (e.g. VCF, bed, wig) and other resources from standard
9944 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9945 metadata about each resource, e.g., a textual description, tags, and date of
9946 modification. The client creates and manages a local cache of files retrieved
9947 by the user, helping with quick and reproducible access.")
9948 (license license:artistic2.0)))
9950 (define-public r-fastseg
9957 (uri (bioconductor-uri "fastseg" version))
9960 "1yw6hai6hb8qy7akdm4frfp6h4zy93zb68kdj094sanm7kgqmgik"))))
9961 (build-system r-build-system)
9963 `(("r-biobase" ,r-biobase)
9964 ("r-biocgenerics" ,r-biocgenerics)
9965 ("r-genomicranges" ,r-genomicranges)
9966 ("r-iranges" ,r-iranges)
9967 ("r-s4vectors" ,r-s4vectors)))
9968 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9969 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9971 "Fastseg implements a very fast and efficient segmentation algorithm.
9972 It can segment data from DNA microarrays and data from next generation
9973 sequencing for example to detect copy number segments. Further it can segment
9974 data from RNA microarrays like tiling arrays to identify transcripts. Most
9975 generally, it can segment data given as a matrix or as a vector. Various data
9976 formats can be used as input to fastseg like expression set objects for
9977 microarrays or GRanges for sequencing data.")
9978 (license license:lgpl2.0+)))
9980 (define-public r-keggrest
9987 (uri (bioconductor-uri "KEGGREST" version))
9990 "1349vidgl9m10l1rbrp3pkwwgi2xcbsw9h9z2xqbvg97lmqc4r8j"))))
9991 (properties `((upstream-name . "KEGGREST")))
9992 (build-system r-build-system)
9994 `(("r-biostrings" ,r-biostrings)
9997 (home-page "https://bioconductor.org/packages/KEGGREST")
9998 (synopsis "Client-side REST access to KEGG")
10000 "This package provides a package that provides a client interface to the
10001 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10002 (license license:artistic2.0)))
10004 (define-public r-gage
10011 (uri (bioconductor-uri "gage" version))
10014 "0j3cqxy97lpf146wkmdfaq9680gicmzxvhp6w5pxq3j7ipiy7262"))))
10015 (build-system r-build-system)
10017 `(("r-annotationdbi" ,r-annotationdbi)
10018 ("r-graph" ,r-graph)
10019 ("r-keggrest" ,r-keggrest)))
10020 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10021 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10023 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10024 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10025 data attributes including sample sizes, experimental designs, assay platforms,
10026 and other types of heterogeneity. The gage package provides functions for
10027 basic GAGE analysis, result processing and presentation. In addition, it
10028 provides demo microarray data and commonly used gene set data based on KEGG
10029 pathways and GO terms. These funtions and data are also useful for gene set
10030 analysis using other methods.")
10031 (license license:gpl2+)))
10033 (define-public r-genomicfiles
10035 (name "r-genomicfiles")
10040 (uri (bioconductor-uri "GenomicFiles" version))
10043 "0bhsq5czigrjyl9gkb2kpkpl367b3ac5g8s280adkcxggn9g7sxq"))))
10044 (properties `((upstream-name . "GenomicFiles")))
10045 (build-system r-build-system)
10047 `(("r-biocgenerics" ,r-biocgenerics)
10048 ("r-biocparallel" ,r-biocparallel)
10049 ("r-genomeinfodb" ,r-genomeinfodb)
10050 ("r-genomicalignments" ,r-genomicalignments)
10051 ("r-genomicranges" ,r-genomicranges)
10052 ("r-iranges" ,r-iranges)
10053 ("r-rsamtools" ,r-rsamtools)
10054 ("r-rtracklayer" ,r-rtracklayer)
10055 ("r-s4vectors" ,r-s4vectors)
10056 ("r-summarizedexperiment" ,r-summarizedexperiment)
10057 ("r-variantannotation" ,r-variantannotation)))
10058 (home-page "https://bioconductor.org/packages/GenomicFiles")
10059 (synopsis "Distributed computing by file or by range")
10061 "This package provides infrastructure for parallel computations
10062 distributed by file or by range. User defined mapper and reducer functions
10063 provide added flexibility for data combination and manipulation.")
10064 (license license:artistic2.0)))
10066 (define-public r-complexheatmap
10068 (name "r-complexheatmap")
10073 (uri (bioconductor-uri "ComplexHeatmap" version))
10076 "0qjwz1hzpjnc90jiinjkikfnr0shi72q3zfdjjz7pxydy0mglq8n"))))
10078 `((upstream-name . "ComplexHeatmap")))
10079 (build-system r-build-system)
10081 `(("r-circlize" ,r-circlize)
10082 ("r-colorspace" ,r-colorspace)
10083 ("r-getoptlong" ,r-getoptlong)
10084 ("r-globaloptions" ,r-globaloptions)
10085 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10087 "https://github.com/jokergoo/ComplexHeatmap")
10088 (synopsis "Making Complex Heatmaps")
10090 "Complex heatmaps are efficient to visualize associations between
10091 different sources of data sets and reveal potential structures. This package
10092 provides a highly flexible way to arrange multiple heatmaps and supports
10093 self-defined annotation graphics.")
10094 (license license:gpl2+)))
10096 (define-public r-dirichletmultinomial
10098 (name "r-dirichletmultinomial")
10103 (uri (bioconductor-uri "DirichletMultinomial" version))
10106 "0vcyp81b90in4ls5nbadc66cw2g9aydr94aqifq5j4b7diq74yfs"))))
10108 `((upstream-name . "DirichletMultinomial")))
10109 (build-system r-build-system)
10113 `(("r-biocgenerics" ,r-biocgenerics)
10114 ("r-iranges" ,r-iranges)
10115 ("r-s4vectors" ,r-s4vectors)))
10116 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10117 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10119 "Dirichlet-multinomial mixture models can be used to describe variability
10120 in microbial metagenomic data. This package is an interface to code
10121 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10123 (license license:lgpl3)))
10125 (define-public r-ensembldb
10127 (name "r-ensembldb")
10132 (uri (bioconductor-uri "ensembldb" version))
10135 "1l2b4cxiycv05mz4z4f3dhx57r9ksha02psc114h30ldm5rxz8w6"))))
10136 (build-system r-build-system)
10138 `(("r-annotationdbi" ,r-annotationdbi)
10139 ("r-annotationfilter" ,r-annotationfilter)
10140 ("r-biobase" ,r-biobase)
10141 ("r-biocgenerics" ,r-biocgenerics)
10142 ("r-biostrings" ,r-biostrings)
10145 ("r-genomeinfodb" ,r-genomeinfodb)
10146 ("r-genomicfeatures" ,r-genomicfeatures)
10147 ("r-genomicranges" ,r-genomicranges)
10148 ("r-iranges" ,r-iranges)
10149 ("r-protgenerics" ,r-protgenerics)
10150 ("r-rsamtools" ,r-rsamtools)
10151 ("r-rsqlite" ,r-rsqlite)
10152 ("r-rtracklayer" ,r-rtracklayer)
10153 ("r-s4vectors" ,r-s4vectors)))
10154 (home-page "https://github.com/jotsetung/ensembldb")
10155 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10157 "The package provides functions to create and use transcript-centric
10158 annotation databases/packages. The annotation for the databases are directly
10159 fetched from Ensembl using their Perl API. The functionality and data is
10160 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10161 but, in addition to retrieve all gene/transcript models and annotations from
10162 the database, the @code{ensembldb} package also provides a filter framework
10163 allowing to retrieve annotations for specific entries like genes encoded on a
10164 chromosome region or transcript models of lincRNA genes.")
10165 ;; No version specified
10166 (license license:lgpl3+)))
10168 (define-public r-organismdbi
10170 (name "r-organismdbi")
10175 (uri (bioconductor-uri "OrganismDbi" version))
10178 "0hb9ni41bjfy5s5ryw2qmqs2sx3i7j47w1g0l8g1pvn7ppnxb6cv"))))
10179 (properties `((upstream-name . "OrganismDbi")))
10180 (build-system r-build-system)
10182 `(("r-annotationdbi" ,r-annotationdbi)
10183 ("r-biobase" ,r-biobase)
10184 ("r-biocgenerics" ,r-biocgenerics)
10185 ("r-biocinstaller" ,r-biocinstaller)
10187 ("r-genomicfeatures" ,r-genomicfeatures)
10188 ("r-genomicranges" ,r-genomicranges)
10189 ("r-graph" ,r-graph)
10190 ("r-iranges" ,r-iranges)
10192 ("r-s4vectors" ,r-s4vectors)))
10193 (home-page "https://bioconductor.org/packages/OrganismDbi")
10194 (synopsis "Software to enable the smooth interfacing of database packages")
10195 (description "The package enables a simple unified interface to several
10196 annotation packages each of which has its own schema by taking advantage of
10197 the fact that each of these packages implements a select methods.")
10198 (license license:artistic2.0)))
10200 (define-public r-biovizbase
10202 (name "r-biovizbase")
10207 (uri (bioconductor-uri "biovizBase" version))
10210 "0lkiqdr3ics6hgv47lwkykcy761823bbkhffbn4ykyfzyqwl4p67"))))
10211 (properties `((upstream-name . "biovizBase")))
10212 (build-system r-build-system)
10214 `(("r-annotationdbi" ,r-annotationdbi)
10215 ("r-annotationfilter" ,r-annotationfilter)
10216 ("r-biocgenerics" ,r-biocgenerics)
10217 ("r-biostrings" ,r-biostrings)
10218 ("r-dichromat" ,r-dichromat)
10219 ("r-ensembldb" ,r-ensembldb)
10220 ("r-genomeinfodb" ,r-genomeinfodb)
10221 ("r-genomicalignments" ,r-genomicalignments)
10222 ("r-genomicfeatures" ,r-genomicfeatures)
10223 ("r-genomicranges" ,r-genomicranges)
10224 ("r-hmisc" ,r-hmisc)
10225 ("r-iranges" ,r-iranges)
10226 ("r-rcolorbrewer" ,r-rcolorbrewer)
10227 ("r-rsamtools" ,r-rsamtools)
10228 ("r-s4vectors" ,r-s4vectors)
10229 ("r-scales" ,r-scales)
10230 ("r-summarizedexperiment" ,r-summarizedexperiment)
10231 ("r-variantannotation" ,r-variantannotation)))
10232 (home-page "https://bioconductor.org/packages/biovizBase")
10233 (synopsis "Basic graphic utilities for visualization of genomic data")
10235 "The biovizBase package is designed to provide a set of utilities, color
10236 schemes and conventions for genomic data. It serves as the base for various
10237 high-level packages for biological data visualization. This saves development
10238 effort and encourages consistency.")
10239 (license license:artistic2.0)))
10241 (define-public r-ggbio
10248 (uri (bioconductor-uri "ggbio" version))
10251 "0wszh3w8yia5zw758h837i1q35k99sn444y2hahcxqbdmmlbf7in"))))
10252 (build-system r-build-system)
10254 `(("r-annotationdbi" ,r-annotationdbi)
10255 ("r-annotationfilter" ,r-annotationfilter)
10256 ("r-biobase" ,r-biobase)
10257 ("r-biocgenerics" ,r-biocgenerics)
10258 ("r-biostrings" ,r-biostrings)
10259 ("r-biovizbase" ,r-biovizbase)
10260 ("r-bsgenome" ,r-bsgenome)
10261 ("r-ensembldb" ,r-ensembldb)
10262 ("r-genomeinfodb" ,r-genomeinfodb)
10263 ("r-genomicalignments" ,r-genomicalignments)
10264 ("r-genomicfeatures" ,r-genomicfeatures)
10265 ("r-genomicranges" ,r-genomicranges)
10266 ("r-ggally" ,r-ggally)
10267 ("r-ggplot2" ,r-ggplot2)
10268 ("r-gridextra" ,r-gridextra)
10269 ("r-gtable" ,r-gtable)
10270 ("r-hmisc" ,r-hmisc)
10271 ("r-iranges" ,r-iranges)
10272 ("r-organismdbi" ,r-organismdbi)
10273 ("r-reshape2" ,r-reshape2)
10274 ("r-rsamtools" ,r-rsamtools)
10275 ("r-rtracklayer" ,r-rtracklayer)
10276 ("r-s4vectors" ,r-s4vectors)
10277 ("r-scales" ,r-scales)
10278 ("r-summarizedexperiment" ,r-summarizedexperiment)
10279 ("r-variantannotation" ,r-variantannotation)))
10280 (home-page "http://www.tengfei.name/ggbio/")
10281 (synopsis "Visualization tools for genomic data")
10283 "The ggbio package extends and specializes the grammar of graphics for
10284 biological data. The graphics are designed to answer common scientific
10285 questions, in particular those often asked of high throughput genomics data.
10286 All core Bioconductor data structures are supported, where appropriate. The
10287 package supports detailed views of particular genomic regions, as well as
10288 genome-wide overviews. Supported overviews include ideograms and grand linear
10289 views. High-level plots include sequence fragment length, edge-linked
10290 interval to data view, mismatch pileup, and several splicing summaries.")
10291 (license license:artistic2.0)))
10293 (define-public r-gprofiler
10295 (name "r-gprofiler")
10300 (uri (cran-uri "gProfileR" version))
10303 "1n6cj12j102b4x9vhyl4dljp1i0r43p23cnhqbx4als2xfxdlqgi"))))
10304 (properties `((upstream-name . "gProfileR")))
10305 (build-system r-build-system)
10307 `(("r-plyr" ,r-plyr)
10308 ("r-rcurl" ,r-rcurl)))
10309 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10310 (synopsis "Interface to the g:Profiler toolkit")
10312 "This package provides tools for functional enrichment analysis,
10313 gene identifier conversion and mapping homologous genes across related
10314 organisms via the @code{g:Profiler} toolkit.")
10315 (license license:gpl2+)))
10317 (define-public r-gqtlbase
10319 (name "r-gqtlbase")
10324 (uri (bioconductor-uri "gQTLBase" version))
10327 "1m3ajpqjhw1nwwsn372r44xfxq0a9a0pzsnrprzdjp6mh52p9b5m"))))
10328 (properties `((upstream-name . "gQTLBase")))
10329 (build-system r-build-system)
10331 `(("r-batchjobs" ,r-batchjobs)
10332 ("r-bbmisc" ,r-bbmisc)
10333 ("r-biocgenerics" ,r-biocgenerics)
10335 ("r-doparallel" ,r-doparallel)
10337 ("r-ffbase" ,r-ffbase)
10338 ("r-foreach" ,r-foreach)
10339 ("r-genomicfiles" ,r-genomicfiles)
10340 ("r-genomicranges" ,r-genomicranges)
10341 ("r-rtracklayer" ,r-rtracklayer)
10342 ("r-s4vectors" ,r-s4vectors)
10343 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10344 (home-page "https://bioconductor.org/packages/gQTLBase")
10345 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10347 "The purpose of this package is to simplify the storage and interrogation
10348 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10350 (license license:artistic2.0)))
10352 (define-public r-snpstats
10354 (name "r-snpstats")
10359 (uri (bioconductor-uri "snpStats" version))
10362 "0iydgfnm053iw860qa1bbh4f6nwzlsf3vhgq92gvl2v4xsz1jbbs"))))
10363 (properties `((upstream-name . "snpStats")))
10364 (build-system r-build-system)
10365 (inputs `(("zlib" ,zlib)))
10367 `(("r-biocgenerics" ,r-biocgenerics)
10368 ("r-matrix" ,r-matrix)
10369 ("r-survival" ,r-survival)
10370 ("r-zlibbioc" ,r-zlibbioc)))
10371 (home-page "https://bioconductor.org/packages/snpStats")
10372 (synopsis "Methods for SNP association studies")
10374 "This package provides classes and statistical methods for large
10375 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10376 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10377 (license license:gpl3)))
10379 (define-public r-homo-sapiens
10381 (name "r-homo-sapiens")
10385 ;; We cannot use bioconductor-uri here because this tarball is
10386 ;; located under "data/annotation/" instead of "bioc/".
10387 (uri (string-append "http://www.bioconductor.org/packages/"
10388 "release/data/annotation/src/contrib/"
10390 version ".tar.gz"))
10393 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10395 `((upstream-name . "Homo.sapiens")))
10396 (build-system r-build-system)
10398 `(("r-genomicfeatures" ,r-genomicfeatures)
10399 ("r-go-db" ,r-go-db)
10400 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10401 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10402 ("r-organismdbi" ,r-organismdbi)
10403 ("r-annotationdbi" ,r-annotationdbi)))
10404 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10405 (synopsis "Annotation package for the Homo.sapiens object")
10407 "This package contains the Homo.sapiens object to access data from
10408 several related annotation packages.")
10409 (license license:artistic2.0)))
10411 (define-public r-erma
10418 (uri (bioconductor-uri "erma" version))
10421 "1ka68n18yizlyvb8bpwwcl4hqbsasg8hw8jb3vgy3cd4szji87hh"))))
10422 (build-system r-build-system)
10424 `(("r-annotationdbi" ,r-annotationdbi)
10425 ("r-biobase" ,r-biobase)
10426 ("r-biocgenerics" ,r-biocgenerics)
10427 ("r-biocparallel" ,r-biocparallel)
10428 ("r-genomeinfodb" ,r-genomeinfodb)
10429 ("r-genomicfiles" ,r-genomicfiles)
10430 ("r-genomicranges" ,r-genomicranges)
10431 ("r-ggplot2" ,r-ggplot2)
10432 ("r-homo-sapiens" ,r-homo-sapiens)
10433 ("r-iranges" ,r-iranges)
10434 ("r-rtracklayer" ,r-rtracklayer)
10435 ("r-s4vectors" ,r-s4vectors)
10436 ("r-shiny" ,r-shiny)
10437 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10438 (home-page "https://bioconductor.org/packages/erma")
10439 (synopsis "Epigenomic road map adventures")
10441 "The epigenomics road map describes locations of epigenetic marks in DNA
10442 from a variety of cell types. Of interest are locations of histone
10443 modifications, sites of DNA methylation, and regions of accessible chromatin.
10444 This package presents a selection of elements of the road map including
10445 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10446 by Ernst and Kellis.")
10447 (license license:artistic2.0)))
10449 (define-public r-ldblock
10456 (uri (bioconductor-uri "ldblock" version))
10459 "0c24zvnwsp39d3q0bps13sc441jj9ms2zi34xsb8c392lqmbypvd"))))
10460 (build-system r-build-system)
10462 `(("r-biocgenerics" ,r-biocgenerics)
10464 ("r-genomeinfodb" ,r-genomeinfodb)
10465 ("r-genomicfiles" ,r-genomicfiles)
10466 ("r-go-db" ,r-go-db)
10467 ("r-homo-sapiens" ,r-homo-sapiens)
10468 ("r-matrix" ,r-matrix)
10469 ("r-rsamtools" ,r-rsamtools)
10470 ("r-snpstats" ,r-snpstats)
10471 ("r-variantannotation" ,r-variantannotation)))
10472 (home-page "https://bioconductor.org/packages/ldblock")
10473 (synopsis "Data structures for linkage disequilibrium measures in populations")
10475 "This package defines data structures for @dfn{linkage
10476 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10477 handling of existing population-level data for the purpose of flexibly
10478 defining LD blocks.")
10479 (license license:artistic2.0)))
10481 (define-public r-gqtlstats
10483 (name "r-gqtlstats")
10488 (uri (bioconductor-uri "gQTLstats" version))
10491 "19g8qhfgngdc14cw9k4i44cxhs3qva87x56gjzmn25k1yj8qgsp1"))))
10492 (properties `((upstream-name . "gQTLstats")))
10493 (build-system r-build-system)
10495 `(("r-annotationdbi" ,r-annotationdbi)
10496 ("r-batchjobs" ,r-batchjobs)
10497 ("r-bbmisc" ,r-bbmisc)
10498 ("r-beeswarm" ,r-beeswarm)
10499 ("r-biobase" ,r-biobase)
10500 ("r-biocgenerics" ,r-biocgenerics)
10501 ("r-doparallel" ,r-doparallel)
10502 ("r-dplyr" ,r-dplyr)
10504 ("r-ffbase" ,r-ffbase)
10505 ("r-foreach" ,r-foreach)
10506 ("r-genomeinfodb" ,r-genomeinfodb)
10507 ("r-genomicfeatures" ,r-genomicfeatures)
10508 ("r-genomicfiles" ,r-genomicfiles)
10509 ("r-genomicranges" ,r-genomicranges)
10510 ("r-ggbeeswarm" ,r-ggbeeswarm)
10511 ("r-ggplot2" ,r-ggplot2)
10512 ("r-gqtlbase" ,r-gqtlbase)
10513 ("r-hardyweinberg" ,r-hardyweinberg)
10514 ("r-homo-sapiens" ,r-homo-sapiens)
10515 ("r-iranges" ,r-iranges)
10516 ("r-limma" ,r-limma)
10518 ("r-plotly" ,r-plotly)
10519 ("r-reshape2" ,r-reshape2)
10520 ("r-s4vectors" ,r-s4vectors)
10521 ("r-shiny" ,r-shiny)
10522 ("r-snpstats" ,r-snpstats)
10523 ("r-summarizedexperiment" ,r-summarizedexperiment)
10524 ("r-variantannotation" ,r-variantannotation)))
10525 (home-page "https://bioconductor.org/packages/gQTLstats")
10526 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10528 "This package provides tools for the computationally efficient analysis
10529 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10530 The software in this package aims to support refinements and functional
10531 interpretation of members of a collection of association statistics on a
10532 family of feature/genome hypotheses.")
10533 (license license:artistic2.0)))
10535 (define-public r-gviz
10542 (uri (bioconductor-uri "Gviz" version))
10545 "1fhli7ahkl5r43j0hc89ib41mfadj6qyrg36i03ncz8zs6iqwpx4"))))
10546 (properties `((upstream-name . "Gviz")))
10547 (build-system r-build-system)
10549 `(("r-annotationdbi" ,r-annotationdbi)
10550 ("r-biobase" ,r-biobase)
10551 ("r-biocgenerics" ,r-biocgenerics)
10552 ("r-biomart" ,r-biomart)
10553 ("r-biostrings" ,r-biostrings)
10554 ("r-biovizbase" ,r-biovizbase)
10555 ("r-bsgenome" ,r-bsgenome)
10556 ("r-digest" ,r-digest)
10557 ("r-genomeinfodb" ,r-genomeinfodb)
10558 ("r-genomicalignments" ,r-genomicalignments)
10559 ("r-genomicfeatures" ,r-genomicfeatures)
10560 ("r-genomicranges" ,r-genomicranges)
10561 ("r-iranges" ,r-iranges)
10562 ("r-lattice" ,r-lattice)
10563 ("r-latticeextra" ,r-latticeextra)
10564 ("r-matrixstats" ,r-matrixstats)
10565 ("r-rcolorbrewer" ,r-rcolorbrewer)
10566 ("r-rsamtools" ,r-rsamtools)
10567 ("r-rtracklayer" ,r-rtracklayer)
10568 ("r-s4vectors" ,r-s4vectors)
10569 ("r-xvector" ,r-xvector)))
10570 (home-page "https://bioconductor.org/packages/Gviz")
10571 (synopsis "Plotting data and annotation information along genomic coordinates")
10573 "Genomic data analyses requires integrated visualization of known genomic
10574 information and new experimental data. Gviz uses the biomaRt and the
10575 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10576 and translates this to e.g. gene/transcript structures in viewports of the
10577 grid graphics package. This results in genomic information plotted together
10579 (license license:artistic2.0)))
10581 (define-public r-gwascat
10588 (uri (bioconductor-uri "gwascat" version))
10591 "08ba9il4vbjjwlbwmqg4ai6ya1p09js9agn95sw0dhc9gqln42hx"))))
10592 (build-system r-build-system)
10594 `(("r-annotationdbi" ,r-annotationdbi)
10595 ("r-annotationhub" ,r-annotationhub)
10596 ("r-biocgenerics" ,r-biocgenerics)
10597 ("r-biostrings" ,r-biostrings)
10598 ("r-genomeinfodb" ,r-genomeinfodb)
10599 ("r-genomicfeatures" ,r-genomicfeatures)
10600 ("r-genomicranges" ,r-genomicranges)
10601 ("r-ggbio" ,r-ggbio)
10602 ("r-ggplot2" ,r-ggplot2)
10603 ("r-gqtlstats" ,r-gqtlstats)
10604 ("r-graph" ,r-graph)
10606 ("r-homo-sapiens" ,r-homo-sapiens)
10607 ("r-iranges" ,r-iranges)
10608 ("r-rsamtools" ,r-rsamtools)
10609 ("r-rtracklayer" ,r-rtracklayer)
10610 ("r-s4vectors" ,r-s4vectors)
10611 ("r-snpstats" ,r-snpstats)
10612 ("r-summarizedexperiment" ,r-summarizedexperiment)
10613 ("r-variantannotation" ,r-variantannotation)))
10614 (home-page "https://bioconductor.org/packages/gwascat")
10615 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10617 "This package provides tools for representing and modeling data in the
10618 EMBL-EBI GWAS catalog.")
10619 (license license:artistic2.0)))
10621 (define-public r-sushi
10627 (uri (bioconductor-uri "Sushi" version))
10630 "1m15hmg4k0qhshyn65xfj5hx7xbaf0kxqw70lxisak6pj1w00l41"))))
10631 (properties `((upstream-name . "Sushi")))
10632 (build-system r-build-system)
10634 `(("r-biomart" ,r-biomart)
10636 (home-page "https://bioconductor.org/packages/Sushi")
10637 (synopsis "Tools for visualizing genomics data")
10639 "This package provides flexible, quantitative, and integrative genomic
10640 visualizations for publication-quality multi-panel figures.")
10641 (license license:gpl2+)))
10643 (define-public r-fithic
10649 (uri (bioconductor-uri "FitHiC" version))
10652 "06w4q836bi1mvkbl1saghv4r5p4hxpjg8cp7kgad13ls450kqmyd"))))
10653 (properties `((upstream-name . "FitHiC")))
10654 (build-system r-build-system)
10656 `(("r-data-table" ,r-data-table)
10657 ("r-fdrtool" ,r-fdrtool)
10658 ("r-rcpp" ,r-rcpp)))
10659 (home-page "https://bioconductor.org/packages/FitHiC")
10660 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10662 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10663 intra-chromosomal contact maps produced by genome-wide genome architecture
10664 assays such as Hi-C.")
10665 (license license:gpl2+)))
10667 (define-public r-hitc
10673 (uri (bioconductor-uri "HiTC" version))
10676 "0qkk5139f51lwwy1yh7nbkflh5d69prirmhniwam34nlg9rzjm2z"))))
10677 (properties `((upstream-name . "HiTC")))
10678 (build-system r-build-system)
10680 `(("r-biostrings" ,r-biostrings)
10681 ("r-genomeinfodb" ,r-genomeinfodb)
10682 ("r-genomicranges" ,r-genomicranges)
10683 ("r-iranges" ,r-iranges)
10684 ("r-matrix" ,r-matrix)
10685 ("r-rcolorbrewer" ,r-rcolorbrewer)
10686 ("r-rtracklayer" ,r-rtracklayer)))
10687 (home-page "https://bioconductor.org/packages/HiTC")
10688 (synopsis "High throughput chromosome conformation capture analysis")
10690 "The HiTC package was developed to explore high-throughput \"C\" data
10691 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10692 quality controls, normalization, visualization, and further analysis are also
10694 (license license:artistic2.0)))
10696 (define-public r-qvalue
10703 (uri (bioconductor-uri "qvalue" version))
10706 "1ndwkj0hh7v4lwylq1v0fkxqs7mfmbcj8kxbdpj1wkvf131z2ns8"))))
10707 (build-system r-build-system)
10709 `(("r-ggplot2" ,r-ggplot2)
10710 ("r-reshape2" ,r-reshape2)))
10711 (home-page "http://github.com/jdstorey/qvalue")
10712 (synopsis "Q-value estimation for false discovery rate control")
10714 "This package takes a list of p-values resulting from the simultaneous
10715 testing of many hypotheses and estimates their q-values and local @dfn{false
10716 discovery rate} (FDR) values. The q-value of a test measures the proportion
10717 of false positives incurred when that particular test is called significant.
10718 The local FDR measures the posterior probability the null hypothesis is true
10719 given the test's p-value. Various plots are automatically generated, allowing
10720 one to make sensible significance cut-offs. The software can be applied to
10721 problems in genomics, brain imaging, astrophysics, and data mining.")
10722 ;; Any version of the LGPL.
10723 (license license:lgpl3+)))
10725 (define-public r-hdf5array
10727 (name "r-hdf5array")
10732 (uri (bioconductor-uri "HDF5Array" version))
10735 "1l0276qxkhgdxsfck3jmi8jvnsr20g10gjki53g0mqa45wnhm3ck"))))
10736 (properties `((upstream-name . "HDF5Array")))
10737 (build-system r-build-system)
10739 `(("r-biocgenerics" ,r-biocgenerics)
10740 ("r-delayedarray" ,r-delayedarray)
10741 ("r-iranges" ,r-iranges)
10742 ("r-rhdf5" ,r-rhdf5)
10743 ("r-s4vectors" ,r-s4vectors)))
10744 (home-page "https://bioconductor.org/packages/HDF5Array")
10745 (synopsis "HDF5 back end for DelayedArray objects")
10746 (description "This package provides an array-like container for convenient
10747 access and manipulation of HDF5 datasets. It supports delayed operations and
10748 block processing.")
10749 (license license:artistic2.0)))
10751 (define-public r-rhdf5lib
10753 (name "r-rhdf5lib")
10758 (uri (bioconductor-uri "Rhdf5lib" version))
10761 "1y59acac6v8hrhv84gghn9ifsni9xxxacaj177rrl4frmkrz4x3c"))))
10762 (properties `((upstream-name . "Rhdf5lib")))
10763 (build-system r-build-system)
10766 (modify-phases %standard-phases
10767 (add-after 'unpack 'do-not-use-bundled-hdf5
10768 (lambda* (#:key inputs #:allow-other-keys)
10769 (for-each delete-file '("configure" "configure.ac"))
10770 ;; Do not make other packages link with the proprietary libsz.
10771 (substitute* "R/zzz.R"
10772 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10773 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10774 (("'%s/libhdf5.a %s/libsz.a -lz'")
10775 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10776 (with-directory-excursion "src"
10777 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10778 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10780 ;; Remove timestamp and host system information to make
10781 ;; the build reproducible.
10782 (substitute* "hdf5/src/libhdf5.settings.in"
10783 (("Configured on: @CONFIG_DATE@")
10784 "Configured on: Guix")
10785 (("Uname information:.*")
10786 "Uname information: Linux\n")
10787 ;; Remove unnecessary store reference.
10789 "C Compiler: GCC\n"))
10790 (rename-file "Makevars.in" "Makevars")
10791 (substitute* "Makevars"
10792 (("HDF5_CXX_LIB=.*")
10793 (string-append "HDF5_CXX_LIB="
10794 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10796 (string-append "HDF5_LIB="
10797 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10798 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10799 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10800 ;; szip is non-free software
10801 (("cp \\$\\{SZIP_LIB\\}.*") "")
10802 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10809 `(("hdf5-source" ,(package-source hdf5))))
10810 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10811 (synopsis "HDF5 library as an R package")
10812 (description "This package provides C and C++ HDF5 libraries for use in R
10814 (license license:artistic2.0)))
10816 (define-public r-beachmat
10818 (name "r-beachmat")
10823 (uri (bioconductor-uri "beachmat" version))
10826 "1w90v0jx1zgrfxzx99gdkk0dz2vi25hr51jml1bvq33i64rj7996"))))
10827 (build-system r-build-system)
10832 `(("r-delayedarray" ,r-delayedarray)
10833 ("r-hdf5array" ,r-hdf5array)
10835 ("r-rhdf5" ,r-rhdf5)
10836 ("r-rhdf5lib" ,r-rhdf5lib)))
10837 (home-page "https://bioconductor.org/packages/beachmat")
10838 (synopsis "Compiling Bioconductor to handle each matrix type")
10839 (description "This package provides a consistent C++ class interface for a
10840 variety of commonly used matrix types, including sparse and HDF5-backed
10842 (license license:gpl3)))
10844 (define-public r-singlecellexperiment
10846 (name "r-singlecellexperiment")
10851 (uri (bioconductor-uri "SingleCellExperiment" version))
10854 "0mz3chia250v8v6q8r5cqv5fc4bpcw1hhrfr3p7l5i4xi85scpka"))))
10856 `((upstream-name . "SingleCellExperiment")))
10857 (build-system r-build-system)
10859 `(("r-biocgenerics" ,r-biocgenerics)
10860 ("r-s4vectors" ,r-s4vectors)
10861 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10862 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10863 (synopsis "S4 classes for single cell data")
10864 (description "This package defines an S4 class for storing data from
10865 single-cell experiments. This includes specialized methods to store and
10866 retrieve spike-in information, dimensionality reduction coordinates and size
10867 factors for each cell, along with the usual metadata for genes and
10869 (license license:gpl3)))
10871 (define-public r-scater
10877 (uri (bioconductor-uri "scater" version))
10880 "0bhpikgz3b9f510dawsay4zry9rlp8vjx5n6zvwbcpwrd94p3903"))))
10881 (build-system r-build-system)
10883 `(("r-beachmat" ,r-beachmat)
10884 ("r-biobase" ,r-biobase)
10885 ("r-biocgenerics" ,r-biocgenerics)
10886 ("r-data-table" ,r-data-table)
10887 ("r-delayedarray" ,r-delayedarray)
10888 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10889 ("r-dplyr" ,r-dplyr)
10890 ("r-edger" ,r-edger)
10891 ("r-ggbeeswarm" ,r-ggbeeswarm)
10892 ("r-ggplot2" ,r-ggplot2)
10893 ("r-limma" ,r-limma)
10894 ("r-matrix" ,r-matrix)
10897 ("r-reshape2" ,r-reshape2)
10898 ("r-rhdf5" ,r-rhdf5)
10899 ("r-rhdf5lib" ,r-rhdf5lib)
10900 ("r-rjson" ,r-rjson)
10901 ("r-s4vectors" ,r-s4vectors)
10902 ("r-shiny" ,r-shiny)
10903 ("r-shinydashboard" ,r-shinydashboard)
10904 ("r-singlecellexperiment" ,r-singlecellexperiment)
10905 ("r-summarizedexperiment" ,r-summarizedexperiment)
10906 ("r-tximport" ,r-tximport)
10907 ("r-viridis" ,r-viridis)))
10908 (home-page "https://github.com/davismcc/scater")
10909 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10910 (description "This package provides a collection of tools for doing
10911 various analyses of single-cell RNA-seq gene expression data, with a focus on
10913 (license license:gpl2+)))
10915 (define-public r-scran
10922 (uri (bioconductor-uri "scran" version))
10925 "0nbn5x75gf9d0p18w7vpkbv30cpdqvp5bz8xvila0h7jla7xdyih"))))
10926 (build-system r-build-system)
10928 `(("r-beachmat" ,r-beachmat)
10929 ("r-biocgenerics" ,r-biocgenerics)
10930 ("r-biocparallel" ,r-biocparallel)
10931 ("r-delayedarray" ,r-delayedarray)
10932 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10934 ("r-dynamictreecut" ,r-dynamictreecut)
10935 ("r-edger" ,r-edger)
10937 ("r-ggplot2" ,r-ggplot2)
10938 ("r-igraph" ,r-igraph)
10939 ("r-limma" ,r-limma)
10940 ("r-matrix" ,r-matrix)
10942 ("r-rhdf5lib" ,r-rhdf5lib)
10943 ("r-s4vectors" ,r-s4vectors)
10944 ("r-scater" ,r-scater)
10945 ("r-shiny" ,r-shiny)
10946 ("r-singlecellexperiment" ,r-singlecellexperiment)
10947 ("r-statmod" ,r-statmod)
10948 ("r-summarizedexperiment" ,r-summarizedexperiment)
10949 ("r-viridis" ,r-viridis)))
10950 (home-page "https://bioconductor.org/packages/scran")
10951 (synopsis "Methods for single-cell RNA-Seq data analysis")
10952 (description "This package implements a variety of low-level analyses of
10953 single-cell RNA-seq data. Methods are provided for normalization of
10954 cell-specific biases, assignment of cell cycle phase, and detection of highly
10955 variable and significantly correlated genes.")
10956 (license license:gpl3)))
10958 (define-public r-delayedmatrixstats
10960 (name "r-delayedmatrixstats")
10965 (uri (bioconductor-uri "DelayedMatrixStats" version))
10968 "1dasghfy8x27zzmd0igag4mc1gxxxbchsl4hpc1050dj3wnw9w3y"))))
10970 `((upstream-name . "DelayedMatrixStats")))
10971 (build-system r-build-system)
10973 `(("r-delayedarray" ,r-delayedarray)
10974 ("r-iranges" ,r-iranges)
10975 ("r-matrix" ,r-matrix)
10976 ("r-matrixstats" ,r-matrixstats)
10977 ("r-s4vectors" ,r-s4vectors)))
10978 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10979 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10981 "This package provides a port of the @code{matrixStats} API for use with
10982 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10983 contains high-performing functions operating on rows and columns of
10984 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10985 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10986 are optimized per data type and for subsetted calculations such that both
10987 memory usage and processing time is minimized.")
10988 (license license:expat)))
10990 (define-public r-phangorn
10992 (name "r-phangorn")
10997 (uri (cran-uri "phangorn" version))
11000 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11001 (build-system r-build-system)
11004 ("r-fastmatch" ,r-fastmatch)
11005 ("r-igraph" ,r-igraph)
11006 ("r-magrittr" ,r-magrittr)
11007 ("r-matrix" ,r-matrix)
11008 ("r-quadprog" ,r-quadprog)
11009 ("r-rcpp" ,r-rcpp)))
11010 (home-page "https://github.com/KlausVigo/phangorn")
11011 (synopsis "Phylogenetic analysis in R")
11013 "Phangorn is a package for phylogenetic analysis in R. It supports
11014 estimation of phylogenetic trees and networks using Maximum Likelihood,
11015 Maximum Parsimony, distance methods and Hadamard conjugation.")
11016 (license license:gpl2+)))
11018 (define-public r-dropbead
11019 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11022 (name "r-dropbead")
11023 (version (string-append "0-" revision "." (string-take commit 7)))
11027 (uri (git-reference
11028 (url "https://github.com/rajewsky-lab/dropbead.git")
11030 (file-name (git-file-name name version))
11033 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11034 (build-system r-build-system)
11036 `(("r-ggplot2" ,r-ggplot2)
11037 ("r-rcolorbrewer" ,r-rcolorbrewer)
11038 ("r-gridextra" ,r-gridextra)
11039 ("r-gplots" ,r-gplots)
11040 ("r-plyr" ,r-plyr)))
11041 (home-page "https://github.com/rajewsky-lab/dropbead")
11042 (synopsis "Basic exploration and analysis of Drop-seq data")
11043 (description "This package offers a quick and straight-forward way to
11044 explore and perform basic analysis of single cell sequencing data coming from
11045 droplet sequencing. It has been particularly tailored for Drop-seq.")
11046 (license license:gpl3))))
11048 (define htslib-for-sambamba
11049 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11052 (name "htslib-for-sambamba")
11053 (version (string-append "1.3.1-1." (string-take commit 9)))
11057 (uri (git-reference
11058 (url "https://github.com/lomereiter/htslib.git")
11060 (file-name (string-append "htslib-" version "-checkout"))
11063 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11065 `(("autoconf" ,autoconf)
11066 ("automake" ,automake)
11067 ,@(package-native-inputs htslib))))))
11069 (define-public sambamba
11072 (version "0.6.7-10-g223fa20")
11076 (uri (git-reference
11077 (url "https://github.com/lomereiter/sambamba.git")
11078 (commit (string-append "v" version))))
11079 (file-name (string-append name "-" version "-checkout"))
11082 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11083 (build-system gnu-build-system)
11085 `(#:tests? #f ; there is no test target
11086 #:parallel-build? #f ; not supported
11088 (modify-phases %standard-phases
11089 (delete 'configure)
11090 (add-after 'unpack 'fix-ldc-version
11092 (substitute* "gen_ldc_version_info.py"
11093 (("/usr/bin/env.*") (which "python")))
11094 (substitute* "Makefile"
11095 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11097 (add-after 'unpack 'place-biod-and-undead
11098 (lambda* (#:key inputs #:allow-other-keys)
11099 (copy-recursively (assoc-ref inputs "biod") "BioD")
11100 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11102 (add-after 'unpack 'unbundle-prerequisites
11104 (substitute* "Makefile"
11105 (("htslib/libhts.a lz4/lib/liblz4.a")
11107 ((" htslib-static lz4-static") ""))
11110 (lambda* (#:key outputs #:allow-other-keys)
11111 (let* ((out (assoc-ref outputs "out"))
11112 (bin (string-append out "/bin")))
11114 (install-file "build/sambamba" bin)
11119 ("python" ,python2-minimal)
11121 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11124 (uri (git-reference
11125 (url "https://github.com/biod/BioD.git")
11127 (file-name (string-append "biod-"
11128 (string-take commit 9)
11132 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11134 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11137 (uri (git-reference
11138 (url "https://github.com/dlang/undeaD.git")
11140 (file-name (string-append "undead-"
11141 (string-take commit 9)
11145 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11148 ("htslib" ,htslib-for-sambamba)))
11149 (home-page "http://lomereiter.github.io/sambamba")
11150 (synopsis "Tools for working with SAM/BAM data")
11151 (description "Sambamba is a high performance modern robust and
11152 fast tool (and library), written in the D programming language, for
11153 working with SAM and BAM files. Current parallelised functionality is
11154 an important subset of samtools functionality, including view, index,
11155 sort, markdup, and depth.")
11156 (license license:gpl2+)))
11158 (define-public ritornello
11160 (name "ritornello")
11164 (uri (string-append "https://github.com/KlugerLab/"
11165 "Ritornello/archive/v"
11166 version ".tar.gz"))
11167 (file-name (string-append name "-" version ".tar.gz"))
11170 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11171 (build-system gnu-build-system)
11173 `(#:tests? #f ; there are no tests
11175 (modify-phases %standard-phases
11176 (add-after 'unpack 'patch-samtools-references
11177 (lambda* (#:key inputs #:allow-other-keys)
11178 (substitute* '("src/SamStream.h"
11179 "src/BufferedGenomeReader.h")
11180 (("<sam.h>") "<samtools/sam.h>"))
11182 (delete 'configure)
11184 (lambda* (#:key inputs outputs #:allow-other-keys)
11185 (let* ((out (assoc-ref outputs "out"))
11186 (bin (string-append out "/bin/")))
11188 (install-file "bin/Ritornello" bin)
11191 `(("samtools" ,samtools-0.1)
11195 (home-page "https://github.com/KlugerLab/Ritornello")
11196 (synopsis "Control-free peak caller for ChIP-seq data")
11197 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11198 signal processing that can accurately call binding events without the need to
11199 do a pair total DNA input or IgG control sample. It has been tested for use
11200 with narrow binding events such as transcription factor ChIP-seq.")
11201 (license license:gpl3+)))
11203 (define-public trim-galore
11205 (name "trim-galore")
11210 (uri (git-reference
11211 (url "https://github.com/FelixKrueger/TrimGalore.git")
11213 (file-name (string-append name "-" version "-checkout"))
11216 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11217 (build-system gnu-build-system)
11219 `(#:tests? #f ; no tests
11221 (modify-phases %standard-phases
11222 (delete 'configure)
11224 (add-after 'unpack 'hardcode-tool-references
11225 (lambda* (#:key inputs #:allow-other-keys)
11226 (substitute* "trim_galore"
11227 (("\\$path_to_cutadapt = 'cutadapt'")
11228 (string-append "$path_to_cutadapt = '"
11229 (assoc-ref inputs "cutadapt")
11232 (string-append "| "
11233 (assoc-ref inputs "gzip")
11236 (string-append "\""
11237 (assoc-ref inputs "gzip")
11241 (lambda* (#:key outputs #:allow-other-keys)
11242 (let ((bin (string-append (assoc-ref outputs "out")
11245 (install-file "trim_galore" bin)
11250 ("cutadapt" ,cutadapt)))
11252 `(("unzip" ,unzip)))
11253 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11254 (synopsis "Wrapper around Cutadapt and FastQC")
11255 (description "Trim Galore! is a wrapper script to automate quality and
11256 adapter trimming as well as quality control, with some added functionality to
11257 remove biased methylation positions for RRBS sequence files.")
11258 (license license:gpl3+)))
11260 (define-public gess
11266 (uri (string-append "http://compbio.uthscsa.edu/"
11268 "gess-" version ".src.tar.gz"))
11271 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11272 (build-system gnu-build-system)
11274 `(#:tests? #f ; no tests
11276 (modify-phases %standard-phases
11277 (delete 'configure)
11280 (lambda* (#:key inputs outputs #:allow-other-keys)
11281 (let* ((python (assoc-ref inputs "python"))
11282 (out (assoc-ref outputs "out"))
11283 (bin (string-append out "/bin/"))
11284 (target (string-append
11285 out "/lib/python2.7/site-packages/gess/")))
11287 (copy-recursively "." target)
11288 ;; Make GESS.py executable
11289 (chmod (string-append target "GESS.py") #o555)
11290 ;; Add Python shebang to the top and make Matplotlib
11292 (substitute* (string-append target "GESS.py")
11293 (("\"\"\"Description:" line)
11294 (string-append "#!" (which "python") "
11296 matplotlib.use('Agg')
11298 ;; Make sure GESS has all modules in its path
11299 (wrap-program (string-append target "GESS.py")
11300 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11302 (symlink (string-append target "GESS.py")
11303 (string-append bin "GESS.py"))
11306 `(("python" ,python-2)
11307 ("python2-pysam" ,python2-pysam)
11308 ("python2-scipy" ,python2-scipy)
11309 ("python2-numpy" ,python2-numpy)
11310 ("python2-networkx" ,python2-networkx)
11311 ("python2-biopython" ,python2-biopython)))
11312 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11313 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11315 "GESS is an implementation of a novel computational method to detect de
11316 novo exon-skipping events directly from raw RNA-seq data without the prior
11317 knowledge of gene annotation information. GESS stands for the graph-based
11318 exon-skipping scanner detection scheme.")
11319 (license license:bsd-3)))
11321 (define-public phylip
11328 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11329 "download/phylip-" version ".tar.gz"))
11332 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11333 (build-system gnu-build-system)
11335 `(#:tests? #f ; no check target
11336 #:make-flags (list "-f" "Makefile.unx" "install")
11337 #:parallel-build? #f ; not supported
11339 (modify-phases %standard-phases
11340 (add-after 'unpack 'enter-dir
11341 (lambda _ (chdir "src") #t))
11342 (delete 'configure)
11344 (lambda* (#:key inputs outputs #:allow-other-keys)
11345 (let ((target (string-append (assoc-ref outputs "out")
11348 (for-each (lambda (file)
11349 (install-file file target))
11350 (find-files "../exe" ".*")))
11352 (home-page "http://evolution.genetics.washington.edu/phylip/")
11353 (synopsis "Tools for inferring phylogenies")
11354 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11355 programs for inferring phylogenies (evolutionary trees).")
11356 (license license:bsd-2)))
11365 (uri (string-append "https://integrativemodeling.org/"
11366 version "/download/imp-" version ".tar.gz"))
11369 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11370 (build-system cmake-build-system)
11372 `(;; FIXME: Some tests fail because they produce warnings, others fail
11373 ;; because the PYTHONPATH does not include the modeller's directory.
11381 ("python" ,python-2)))
11383 `(("python2-numpy" ,python2-numpy)
11384 ("python2-scipy" ,python2-scipy)
11385 ("python2-pandas" ,python2-pandas)
11386 ("python2-scikit-learn" ,python2-scikit-learn)
11387 ("python2-networkx" ,python2-networkx)))
11388 (home-page "https://integrativemodeling.org")
11389 (synopsis "Integrative modeling platform")
11390 (description "IMP's broad goal is to contribute to a comprehensive
11391 structural characterization of biomolecules ranging in size and complexity
11392 from small peptides to large macromolecular assemblies, by integrating data
11393 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11394 Python toolbox for solving complex modeling problems, and a number of
11395 applications for tackling some common problems in a user-friendly way.")
11396 ;; IMP is largely available under the GNU Lesser GPL; see the file
11397 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11398 ;; available under the GNU GPL (see the file COPYING.GPL).
11399 (license (list license:lgpl2.1+
11402 (define-public tadbit
11408 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11409 "archive/v" version ".tar.gz"))
11410 (file-name (string-append name "-" version ".tar.gz"))
11413 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11414 (build-system python-build-system)
11416 `(;; Tests are included and must be run after installation, but
11417 ;; they are incomplete and thus cannot be run.
11421 (modify-phases %standard-phases
11422 (add-after 'unpack 'fix-problems-with-setup.py
11423 (lambda* (#:key outputs #:allow-other-keys)
11424 ;; setup.py opens these files for writing
11425 (chmod "_pytadbit/_version.py" #o664)
11426 (chmod "README.rst" #o664)
11428 ;; Don't attempt to install the bash completions to
11429 ;; the home directory.
11430 (rename-file "extras/.bash_completion"
11432 (substitute* "setup.py"
11433 (("\\(path.expanduser\\('~'\\)")
11434 (string-append "(\""
11435 (assoc-ref outputs "out")
11436 "/etc/bash_completion.d\""))
11437 (("extras/\\.bash_completion")
11441 ;; TODO: add Chimera for visualization
11444 ("python2-scipy" ,python2-scipy)
11445 ("python2-numpy" ,python2-numpy)
11446 ("python2-matplotlib" ,python2-matplotlib)
11447 ("python2-pysam" ,python2-pysam)))
11448 (home-page "https://3dgenomes.github.io/TADbit/")
11449 (synopsis "Analyze, model, and explore 3C-based data")
11451 "TADbit is a complete Python library to deal with all steps to analyze,
11452 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11453 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11454 correct interaction matrices, identify and compare the so-called
11455 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11456 interaction matrices, and finally, extract structural properties from the
11457 models. TADbit is complemented by TADkit for visualizing 3D models.")
11458 (license license:gpl3+)))
11460 (define-public kentutils
11463 ;; 302.1.0 is out, but the only difference is the inclusion of
11464 ;; pre-built binaries.
11465 (version "302.0.0")
11469 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11470 "archive/v" version ".tar.gz"))
11471 (file-name (string-append name "-" version ".tar.gz"))
11474 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11475 (modules '((guix build utils)
11480 ;; Only the contents of the specified directories are free
11481 ;; for all uses, so we remove the rest. "hg/autoSql" and
11482 ;; "hg/autoXml" are nominally free, but they depend on a
11483 ;; library that is built from the sources in "hg/lib",
11484 ;; which is nonfree.
11485 (let ((free (list "." ".."
11486 "utils" "lib" "inc" "tagStorm"
11487 "parasol" "htslib"))
11488 (directory? (lambda (file)
11489 (eq? 'directory (stat:type (stat file))))))
11490 (for-each (lambda (file)
11491 (and (directory? file)
11492 (delete-file-recursively file)))
11493 (map (cut string-append "src/" <>)
11496 (not (member file free)))))))
11497 ;; Only make the utils target, not the userApps target,
11498 ;; because that requires libraries we won't build.
11499 (substitute* "Makefile"
11500 ((" userApps") " utils"))
11501 ;; Only build libraries that are free.
11502 (substitute* "src/makefile"
11503 (("DIRS =.*") "DIRS =\n")
11504 (("cd jkOwnLib.*") "")
11507 (substitute* "src/utils/makefile"
11508 ;; These tools depend on "jkhgap.a", which is part of the
11509 ;; nonfree "src/hg/lib" directory.
11510 (("raSqlQuery") "")
11511 (("pslLiftSubrangeBlat") "")
11513 ;; Do not build UCSC tools, which may require nonfree
11515 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11517 (build-system gnu-build-system)
11519 `( ;; There is no global test target and the test target for
11520 ;; individual tools depends on input files that are not
11524 (modify-phases %standard-phases
11525 (add-after 'unpack 'fix-paths
11527 (substitute* "Makefile"
11528 (("/bin/echo") (which "echo")))
11530 (add-after 'unpack 'prepare-samtabix
11531 (lambda* (#:key inputs #:allow-other-keys)
11532 (copy-recursively (assoc-ref inputs "samtabix")
11535 (delete 'configure)
11537 (lambda* (#:key outputs #:allow-other-keys)
11538 (let ((bin (string-append (assoc-ref outputs "out")
11540 (copy-recursively "bin" bin))
11546 (uri (git-reference
11547 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11548 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11551 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11557 ("mariadb" ,mariadb)
11558 ("openssl" ,openssl)))
11559 (home-page "http://genome.cse.ucsc.edu/index.html")
11560 (synopsis "Assorted bioinformatics utilities")
11561 (description "This package provides the kentUtils, a selection of
11562 bioinformatics utilities used in combination with the UCSC genome
11564 ;; Only a subset of the sources are released under a non-copyleft
11565 ;; free software license. All other sources are removed in a
11566 ;; snippet. See this bug report for an explanation of how the
11567 ;; license statements apply:
11568 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11569 (license (license:non-copyleft
11570 "http://genome.ucsc.edu/license/"
11571 "The contents of this package are free for all uses."))))
11573 (define-public f-seq
11574 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11578 (version (string-append "1.1-" revision "." (string-take commit 7)))
11581 (uri (git-reference
11582 (url "https://github.com/aboyle/F-seq.git")
11584 (file-name (string-append name "-" version))
11587 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11588 (modules '((guix build utils)))
11589 ;; Remove bundled Java library archives.
11592 (for-each delete-file (find-files "lib" ".*"))
11594 (build-system ant-build-system)
11596 `(#:tests? #f ; no tests included
11598 (modify-phases %standard-phases
11600 (lambda* (#:key inputs outputs #:allow-other-keys)
11601 (let* ((target (assoc-ref outputs "out"))
11602 (bin (string-append target "/bin"))
11603 (doc (string-append target "/share/doc/f-seq"))
11604 (lib (string-append target "/lib")))
11607 (substitute* "bin/linux/fseq"
11608 (("java") (which "java"))
11609 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11610 (string-append (assoc-ref inputs "java-commons-cli")
11611 "/share/java/commons-cli.jar"))
11613 (string-append "REALDIR=" bin "\n")))
11614 (install-file "README.txt" doc)
11615 (install-file "bin/linux/fseq" bin)
11616 (install-file "build~/fseq.jar" lib)
11617 (copy-recursively "lib" lib)
11621 ("java-commons-cli" ,java-commons-cli)))
11622 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11623 (synopsis "Feature density estimator for high-throughput sequence tags")
11625 "F-Seq is a software package that generates a continuous tag sequence
11626 density estimation allowing identification of biologically meaningful sites
11627 such as transcription factor binding sites (ChIP-seq) or regions of open
11628 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11630 (license license:gpl3+))))
11632 (define-public bismark
11639 (uri (git-reference
11640 (url "https://github.com/FelixKrueger/Bismark.git")
11642 (file-name (string-append name "-" version "-checkout"))
11645 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11648 ;; highcharts.js is non-free software. The code is available under
11649 ;; CC-BY-NC or proprietary licenses only.
11650 (delete-file "bismark_sitrep/highcharts.js")
11652 (build-system perl-build-system)
11654 `(#:tests? #f ; there are no tests
11656 (modify-phases %standard-phases
11657 (delete 'configure)
11660 (lambda* (#:key inputs outputs #:allow-other-keys)
11661 (let* ((out (assoc-ref outputs "out"))
11662 (bin (string-append out "/bin"))
11663 (share (string-append out "/share/bismark"))
11664 (docdir (string-append out "/share/doc/bismark"))
11665 (docs '("Docs/Bismark_User_Guide.html"))
11666 (scripts '("bismark"
11667 "bismark_genome_preparation"
11668 "bismark_methylation_extractor"
11671 "coverage2cytosine"
11672 "deduplicate_bismark"
11673 "filter_non_conversion"
11675 "bismark2summary")))
11676 (substitute* "bismark2report"
11677 (("\\$RealBin/bismark_sitrep")
11678 (string-append share "/bismark_sitrep")))
11682 (for-each (lambda (file) (install-file file bin))
11684 (for-each (lambda (file) (install-file file docdir))
11686 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11687 (copy-recursively "bismark_sitrep"
11688 (string-append share "/bismark_sitrep"))
11690 ;; Fix references to gunzip
11691 (substitute* (map (lambda (file)
11692 (string-append bin "/" file))
11695 (string-append "\"" (assoc-ref inputs "gzip")
11696 "/bin/gunzip -c")))
11700 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11701 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11702 (description "Bismark is a program to map bisulfite treated sequencing
11703 reads to a genome of interest and perform methylation calls in a single step.
11704 The output can be easily imported into a genome viewer, such as SeqMonk, and
11705 enables a researcher to analyse the methylation levels of their samples
11706 straight away. Its main features are:
11709 @item Bisulfite mapping and methylation calling in one single step
11710 @item Supports single-end and paired-end read alignments
11711 @item Supports ungapped and gapped alignments
11712 @item Alignment seed length, number of mismatches etc are adjustable
11713 @item Output discriminates between cytosine methylation in CpG, CHG
11716 (license license:gpl3+)))
11718 (define-public paml
11724 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11725 "paml" version ".tgz"))
11728 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11729 (modules '((guix build utils)))
11730 ;; Remove Windows binaries
11733 (for-each delete-file (find-files "." "\\.exe$"))
11735 (build-system gnu-build-system)
11737 `(#:tests? #f ; there are no tests
11738 #:make-flags '("CC=gcc")
11740 (modify-phases %standard-phases
11741 (replace 'configure
11743 (substitute* "src/BFdriver.c"
11744 (("/bin/bash") (which "bash")))
11748 (lambda* (#:key outputs #:allow-other-keys)
11749 (let ((tools '("baseml" "basemlg" "codeml"
11750 "pamp" "evolver" "yn00" "chi2"))
11751 (bin (string-append (assoc-ref outputs "out") "/bin"))
11752 (docdir (string-append (assoc-ref outputs "out")
11753 "/share/doc/paml")))
11755 (for-each (lambda (file) (install-file file bin)) tools)
11756 (copy-recursively "../doc" docdir)
11758 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11759 (synopsis "Phylogentic analysis by maximum likelihood")
11760 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11761 contains a few programs for model fitting and phylogenetic tree reconstruction
11762 using nucleotide or amino-acid sequence data.")
11764 (license license:gpl3)))
11766 (define-public kallisto
11772 (uri (string-append "https://github.com/pachterlab/"
11773 "kallisto/archive/v" version ".tar.gz"))
11774 (file-name (string-append name "-" version ".tar.gz"))
11777 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11778 (build-system cmake-build-system)
11779 (arguments `(#:tests? #f)) ; no "check" target
11783 (home-page "http://pachterlab.github.io/kallisto/")
11784 (synopsis "Near-optimal RNA-Seq quantification")
11786 "Kallisto is a program for quantifying abundances of transcripts from
11787 RNA-Seq data, or more generally of target sequences using high-throughput
11788 sequencing reads. It is based on the novel idea of pseudoalignment for
11789 rapidly determining the compatibility of reads with targets, without the need
11790 for alignment. Pseudoalignment of reads preserves the key information needed
11791 for quantification, and kallisto is therefore not only fast, but also as
11792 accurate as existing quantification tools.")
11793 (license license:bsd-2)))
11795 (define-public libgff
11801 (uri (string-append
11802 "https://github.com/Kingsford-Group/"
11803 "libgff/archive/v" version ".tar.gz"))
11804 (file-name (string-append name "-" version ".tar.gz"))
11807 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11808 (build-system cmake-build-system)
11809 (arguments `(#:tests? #f)) ; no tests included
11810 (home-page "https://github.com/Kingsford-Group/libgff")
11811 (synopsis "Parser library for reading/writing GFF files")
11812 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11813 code that is used in the Cufflinks codebase. The goal of this library is to
11814 provide this functionality without the necessity of drawing in a heavy-weight
11815 dependency like SeqAn.")
11816 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11818 (define-public libdivsufsort
11820 (name "libdivsufsort")
11824 (uri (git-reference
11825 (url "https://github.com/y-256/libdivsufsort.git")
11827 (file-name (git-file-name name version))
11830 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11831 (build-system cmake-build-system)
11833 '(#:tests? #f ; there are no tests
11835 ;; Needed for rapmap and sailfish.
11836 '("-DBUILD_DIVSUFSORT64=ON")))
11837 (home-page "https://github.com/y-256/libdivsufsort")
11838 (synopsis "Lightweight suffix-sorting library")
11839 (description "libdivsufsort is a software library that implements a
11840 lightweight suffix array construction algorithm. This library provides a
11841 simple and an efficient C API to construct a suffix array and a
11842 Burrows-Wheeler transformed string from a given string over a constant-size
11843 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11844 bytes of memory space, where n is the length of the string.")
11845 (license license:expat)))
11847 (define-public sailfish
11854 (string-append "https://github.com/kingsfordgroup/"
11855 "sailfish/archive/v" version ".tar.gz"))
11856 (file-name (string-append name "-" version ".tar.gz"))
11859 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11860 (modules '((guix build utils)))
11863 ;; Delete bundled headers for eigen3.
11864 (delete-file-recursively "include/eigen3/")
11866 (build-system cmake-build-system)
11868 `(#:configure-flags
11869 (list (string-append "-DBOOST_INCLUDEDIR="
11870 (assoc-ref %build-inputs "boost")
11872 (string-append "-DBOOST_LIBRARYDIR="
11873 (assoc-ref %build-inputs "boost")
11875 (string-append "-DBoost_LIBRARIES="
11876 "-lboost_iostreams "
11877 "-lboost_filesystem "
11882 "-lboost_program_options")
11883 "-DBoost_FOUND=TRUE"
11884 ;; Don't download RapMap---we already have it!
11885 "-DFETCHED_RAPMAP=1")
11886 ;; Tests must be run after installation and the location of the test
11887 ;; data file must be overridden. But the tests fail. It looks like
11888 ;; they are not really meant to be run.
11891 (modify-phases %standard-phases
11892 ;; Boost cannot be found, even though it's right there.
11893 (add-after 'unpack 'do-not-look-for-boost
11894 (lambda* (#:key inputs #:allow-other-keys)
11895 (substitute* "CMakeLists.txt"
11896 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11897 (add-after 'unpack 'do-not-assign-to-macro
11899 (substitute* "include/spdlog/details/format.cc"
11900 (("const unsigned CHAR_WIDTH = 1;") ""))))
11901 (add-after 'unpack 'prepare-rapmap
11902 (lambda* (#:key inputs #:allow-other-keys)
11903 (let ((src "external/install/src/rapmap/")
11904 (include "external/install/include/rapmap/")
11905 (rapmap (assoc-ref inputs "rapmap")))
11906 (mkdir-p "/tmp/rapmap")
11907 (system* "tar" "xf"
11908 (assoc-ref inputs "rapmap")
11910 "--strip-components=1")
11913 (for-each (lambda (file)
11914 (install-file file src))
11915 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11916 (copy-recursively "/tmp/rapmap/include" include))))
11917 (add-after 'unpack 'use-system-libraries
11918 (lambda* (#:key inputs #:allow-other-keys)
11919 (substitute* '("src/SailfishIndexer.cpp"
11920 "src/SailfishUtils.cpp"
11921 "src/SailfishQuantify.cpp"
11922 "src/FASTAParser.cpp"
11924 "include/SailfishUtils.hpp"
11925 "include/SailfishIndex.hpp"
11926 "include/CollapsedEMOptimizer.hpp"
11927 "src/CollapsedEMOptimizer.cpp")
11928 (("#include \"jellyfish/config.h\"") ""))
11929 (substitute* "src/CMakeLists.txt"
11930 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11931 (string-append (assoc-ref inputs "jellyfish")
11932 "/include/jellyfish-" ,(package-version jellyfish)))
11933 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11934 (string-append (assoc-ref inputs "jellyfish")
11935 "/lib/libjellyfish-2.0.a"))
11936 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11937 (string-append (assoc-ref inputs "libdivsufsort")
11938 "/lib/libdivsufsort.so"))
11939 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11940 (string-append (assoc-ref inputs "libdivsufsort")
11941 "/lib/libdivsufsort64.so")))
11942 (substitute* "CMakeLists.txt"
11943 ;; Don't prefer static libs
11944 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11945 (("find_package\\(Jellyfish.*") "")
11946 (("ExternalProject_Add\\(libjellyfish") "message(")
11947 (("ExternalProject_Add\\(libgff") "message(")
11948 (("ExternalProject_Add\\(libsparsehash") "message(")
11949 (("ExternalProject_Add\\(libdivsufsort") "message("))
11951 ;; Ensure that Eigen headers can be found
11952 (setenv "CPLUS_INCLUDE_PATH"
11953 (string-append (getenv "CPLUS_INCLUDE_PATH")
11955 (assoc-ref inputs "eigen")
11956 "/include/eigen3")))))))
11960 ("jemalloc" ,jemalloc)
11961 ("jellyfish" ,jellyfish)
11962 ("sparsehash" ,sparsehash)
11965 (uri (git-reference
11966 (url "https://github.com/COMBINE-lab/RapMap.git")
11967 (commit (string-append "sf-v" version))))
11968 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11971 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11972 (modules '((guix build utils)))
11973 ;; These files are expected to be excluded.
11975 '(begin (delete-file-recursively "include/spdlog")
11976 (for-each delete-file '("include/xxhash.h"
11979 ("libdivsufsort" ,libdivsufsort)
11984 `(("pkg-config" ,pkg-config)))
11985 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11986 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11987 (description "Sailfish is a tool for genomic transcript quantification
11988 from RNA-seq data. It requires a set of target transcripts (either from a
11989 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11990 fasta file containing your reference transcripts and a (set of) fasta/fastq
11991 file(s) containing your reads.")
11992 (license license:gpl3+)))
11994 (define libstadenio-for-salmon
11996 (name "libstadenio")
12000 (uri (git-reference
12001 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12002 (commit (string-append "v" version))))
12003 (file-name (string-append name "-" version "-checkout"))
12006 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12007 (build-system gnu-build-system)
12008 (arguments '(#:parallel-tests? #f)) ; not supported
12012 `(("perl" ,perl))) ; for tests
12013 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12014 (synopsis "General purpose trace and experiment file library")
12015 (description "This package provides a library of file reading and writing
12016 code to provide a general purpose Trace file (and Experiment File) reading
12019 The following file formats are supported:
12022 @item SCF trace files
12023 @item ABI trace files
12024 @item ALF trace files
12025 @item ZTR trace files
12026 @item SFF trace archives
12027 @item SRF trace archives
12028 @item Experiment files
12029 @item Plain text files
12030 @item SAM/BAM sequence files
12031 @item CRAM sequence files
12033 (license license:bsd-3)))
12035 (define spdlog-for-salmon
12041 (uri (git-reference
12042 (url "https://github.com/COMBINE-lab/spdlog.git")
12043 (commit (string-append "v" version))))
12044 (file-name (string-append name "-" version "-checkout"))
12047 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12048 (build-system cmake-build-system)
12049 (home-page "https://github.com/COMBINE-lab/spdlog")
12050 (synopsis "Very fast C++ logging library")
12051 (description "Spdlog is a very fast header-only C++ logging library with
12052 performance as its primary goal.")
12053 (license license:expat)))
12055 ;; This is a modified variant of bwa for use with Salmon. It installs a
12056 ;; library to avoid having to build this as part of Salmon.
12057 (define bwa-for-salmon
12058 (package (inherit bwa)
12060 (version "0.7.12.5")
12063 (uri (git-reference
12064 (url "https://github.com/COMBINE-lab/bwa.git")
12065 (commit (string-append "v" version))))
12066 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12069 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12070 (build-system gnu-build-system)
12072 '(#:tests? #f ;no "check" target
12074 (modify-phases %standard-phases
12076 (lambda* (#:key outputs #:allow-other-keys)
12077 (let* ((out (assoc-ref outputs "out"))
12078 (bin (string-append out "/bin"))
12079 (lib (string-append out "/lib"))
12080 (doc (string-append out "/share/doc/bwa"))
12081 (man (string-append out "/share/man/man1"))
12082 (inc (string-append out "/include/bwa")))
12083 (install-file "bwa" bin)
12084 (install-file "README.md" doc)
12085 (install-file "bwa.1" man)
12086 (install-file "libbwa.a" lib)
12089 (for-each (lambda (file)
12090 (install-file file inc))
12091 (find-files "." "\\.h$")))
12093 ;; no "configure" script
12094 (delete 'configure))))))
12096 (define-public salmon
12102 (uri (git-reference
12103 (url "https://github.com/COMBINE-lab/salmon.git")
12104 (commit (string-append "v" version))))
12105 (file-name (string-append name "-" version "-checkout"))
12108 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12109 (modules '((guix build utils)))
12112 ;; Delete bundled headers for eigen3.
12113 (delete-file-recursively "include/eigen3/")
12115 (build-system cmake-build-system)
12117 `(#:configure-flags
12118 (list (string-append "-DBOOST_INCLUDEDIR="
12119 (assoc-ref %build-inputs "boost")
12121 (string-append "-DBOOST_LIBRARYDIR="
12122 (assoc-ref %build-inputs "boost")
12124 (string-append "-DBoost_LIBRARIES="
12125 "-lboost_iostreams "
12126 "-lboost_filesystem "
12131 "-lboost_program_options")
12132 "-DBoost_FOUND=TRUE"
12133 "-DTBB_LIBRARIES=tbb tbbmalloc"
12134 ;; Don't download RapMap---we already have it!
12135 "-DFETCHED_RAPMAP=1")
12137 (modify-phases %standard-phases
12138 ;; Boost cannot be found, even though it's right there.
12139 (add-after 'unpack 'do-not-look-for-boost
12140 (lambda* (#:key inputs #:allow-other-keys)
12141 (substitute* "CMakeLists.txt"
12142 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12143 (add-after 'unpack 'do-not-phone-home
12145 (substitute* "src/Salmon.cpp"
12146 (("getVersionMessage\\(\\)") "\"\""))))
12147 (add-after 'unpack 'prepare-rapmap
12148 (lambda* (#:key inputs #:allow-other-keys)
12149 (let ((src "external/install/src/rapmap/")
12150 (include "external/install/include/rapmap/")
12151 (rapmap (assoc-ref inputs "rapmap")))
12154 (for-each (lambda (file)
12155 (install-file file src))
12156 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12157 (copy-recursively (string-append rapmap "/include") include)
12158 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12159 "external/install/include/rapmap/FastxParser.hpp"
12160 "external/install/include/rapmap/concurrentqueue.h"
12161 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12162 "external/install/src/rapmap/FastxParser.cpp"
12163 "external/install/src/rapmap/xxhash.c")))))
12164 (add-after 'unpack 'use-system-libraries
12165 (lambda* (#:key inputs #:allow-other-keys)
12166 (substitute* "src/CMakeLists.txt"
12167 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12168 (string-append (assoc-ref inputs "jellyfish")
12169 "/include/jellyfish-" ,(package-version jellyfish)))
12170 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12171 (string-append (assoc-ref inputs "jellyfish")
12172 "/lib/libjellyfish-2.0.a"))
12173 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12174 (string-append (assoc-ref inputs "libdivsufsort")
12175 "/lib/libdivsufsort.so"))
12176 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12177 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12178 "/lib/libstaden-read.a"))
12179 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12180 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12181 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12182 (string-append (assoc-ref inputs "libdivsufsort")
12183 "/lib/libdivsufsort64.so")))
12184 (substitute* "CMakeLists.txt"
12185 ;; Don't prefer static libs
12186 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12187 (("set\\(TBB_LIBRARIES") "message(")
12188 (("find_package\\(Jellyfish.*") "")
12189 (("ExternalProject_Add\\(libcereal") "message(")
12190 (("ExternalProject_Add\\(libbwa") "message(")
12191 (("ExternalProject_Add\\(libjellyfish") "message(")
12192 (("ExternalProject_Add\\(libgff") "message(")
12193 (("ExternalProject_Add\\(libtbb") "message(")
12194 (("ExternalProject_Add\\(libspdlog") "message(")
12195 (("ExternalProject_Add\\(libdivsufsort") "message(")
12196 (("ExternalProject_Add\\(libstadenio") "message(")
12197 (("ExternalProject_Add_Step\\(") "message("))
12199 ;; Ensure that all headers can be found
12200 (setenv "CPLUS_INCLUDE_PATH"
12201 (string-append (getenv "CPLUS_INCLUDE_PATH")
12203 (assoc-ref inputs "bwa")
12206 (assoc-ref inputs "eigen")
12207 "/include/eigen3"))
12209 (string-append (assoc-ref inputs "bwa")
12212 (assoc-ref inputs "eigen")
12213 "/include/eigen3"))
12215 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12216 ;; run. It only exists after the install phase.
12217 (add-after 'unpack 'fix-tests
12219 (substitute* "src/CMakeLists.txt"
12220 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12221 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12225 ("bwa" ,bwa-for-salmon)
12231 (uri (git-reference
12232 (url "https://github.com/COMBINE-lab/RapMap.git")
12233 (commit (string-append "salmon-v" version))))
12234 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12237 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12238 ("jemalloc" ,jemalloc)
12239 ("jellyfish" ,jellyfish)
12242 ("libdivsufsort" ,libdivsufsort)
12243 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12244 ("spdlog-for-salmon" ,spdlog-for-salmon)
12247 (home-page "https://github.com/COMBINE-lab/salmon")
12248 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12249 (description "Salmon is a program to produce highly-accurate,
12250 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12251 its accuracy and speed via a number of different innovations, including the
12252 use of lightweight alignments (accurate but fast-to-compute proxies for
12253 traditional read alignments) and massively-parallel stochastic collapsed
12254 variational inference.")
12255 (license license:gpl3+)))
12257 (define-public python-loompy
12259 (name "python-loompy")
12264 (uri (pypi-uri "loompy" version))
12267 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12268 (build-system python-build-system)
12269 ;; There are no tests
12270 (arguments '(#:tests? #f))
12272 `(("python-h5py" ,python-h5py)
12273 ("python-numpy" ,python-numpy)
12274 ("python-scipy" ,python-scipy)
12275 ("python-typing" ,python-typing)))
12276 (home-page "https://github.com/linnarsson-lab/loompy")
12277 (synopsis "Work with .loom files for single-cell RNA-seq data")
12278 (description "The loom file format is an efficient format for very large
12279 omics datasets, consisting of a main matrix, optional additional layers, a
12280 variable number of row and column annotations. Loom also supports sparse
12281 graphs. This library makes it easy to work with @file{.loom} files for
12282 single-cell RNA-seq data.")
12283 (license license:bsd-3)))
12285 ;; We cannot use the latest commit because it requires Java 9.
12286 (define-public java-forester
12287 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12290 (name "java-forester")
12291 (version (string-append "0-" revision "." (string-take commit 7)))
12294 (uri (git-reference
12295 (url "https://github.com/cmzmasek/forester.git")
12297 (file-name (string-append name "-" version "-checkout"))
12300 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12301 (modules '((guix build utils)))
12304 ;; Delete bundled jars and pre-built classes
12305 (delete-file-recursively "forester/java/resources")
12306 (delete-file-recursively "forester/java/classes")
12307 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12308 ;; Delete bundled applications
12309 (delete-file-recursively "forester_applications")
12311 (build-system ant-build-system)
12313 `(#:tests? #f ; there are none
12315 #:modules ((guix build ant-build-system)
12317 (guix build java-utils)
12321 (modify-phases %standard-phases
12322 (add-after 'unpack 'chdir
12323 (lambda _ (chdir "forester/java") #t))
12324 (add-after 'chdir 'fix-dependencies
12326 (chmod "build.xml" #o664)
12327 (call-with-output-file "build.xml.new"
12331 (with-input-from-file "build.xml"
12332 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12333 `(;; Remove all unjar tags to avoid repacking classes.
12334 (unjar . ,(lambda _ '()))
12335 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12336 (*text* . ,(lambda (_ txt) txt))))
12338 (rename-file "build.xml.new" "build.xml")
12340 ;; FIXME: itext is difficult to package as it depends on a few
12341 ;; unpackaged libraries.
12342 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12344 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12345 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12346 (("pdf_written_to = PdfExporter.*")
12347 "throw new IOException(\"PDF export is not available.\");"))
12349 ;; There is no install target
12350 (replace 'install (install-jars ".")))))
12352 `(("java-commons-codec" ,java-commons-codec)
12353 ("java-openchart2" ,java-openchart2)))
12354 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12355 (synopsis "Phylogenomics libraries for Java")
12356 (description "Forester is a collection of Java libraries for
12357 phylogenomics and evolutionary biology research. It includes support for
12358 reading, writing, and exporting phylogenetic trees.")
12359 (license license:lgpl2.1+))))
12361 (define-public java-forester-1.005
12363 (name "java-forester")
12367 (uri (string-append "http://search.maven.org/remotecontent?"
12368 "filepath=org/biojava/thirdparty/forester/"
12369 version "/forester-" version "-sources.jar"))
12370 (file-name (string-append name "-" version ".jar"))
12373 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12374 (build-system ant-build-system)
12376 `(#:tests? #f ; there are none
12378 #:modules ((guix build ant-build-system)
12380 (guix build java-utils)
12384 (modify-phases %standard-phases
12385 (add-after 'unpack 'fix-dependencies
12386 (lambda* (#:key inputs #:allow-other-keys)
12387 (call-with-output-file "build.xml"
12391 (with-input-from-file "src/build.xml"
12392 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12393 `(;; Remove all unjar tags to avoid repacking classes.
12394 (unjar . ,(lambda _ '()))
12395 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12396 (*text* . ,(lambda (_ txt) txt))))
12398 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12399 "synth_look_and_feel_1.xml")
12400 (copy-file (assoc-ref inputs "phyloxml.xsd")
12402 (substitute* "build.xml"
12403 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12404 "synth_look_and_feel_1.xml")
12405 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12408 ;; FIXME: itext is difficult to package as it depends on a few
12409 ;; unpackaged libraries.
12410 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12412 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12413 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12414 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12415 (("pdf_written_to = PdfExporter.*")
12416 "throw new IOException(\"PDF export is not available.\"); /*")
12417 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12418 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12420 (add-after 'unpack 'delete-pre-built-classes
12421 (lambda _ (delete-file-recursively "src/classes") #t))
12422 ;; There is no install target
12423 (replace 'install (install-jars ".")))))
12425 `(("java-commons-codec" ,java-commons-codec)
12426 ("java-openchart2" ,java-openchart2)))
12427 ;; The source archive does not contain the resources.
12432 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12433 "b61cc2dcede0bede317db362472333115756b8c6/"
12434 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12435 (file-name (string-append name "-phyloxml-" version ".xsd"))
12438 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12439 ("synth_look_and_feel_1.xml"
12442 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12443 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12444 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12445 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12448 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12449 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12450 (synopsis "Phylogenomics libraries for Java")
12451 (description "Forester is a collection of Java libraries for
12452 phylogenomics and evolutionary biology research. It includes support for
12453 reading, writing, and exporting phylogenetic trees.")
12454 (license license:lgpl2.1+)))
12456 (define-public java-biojava-core
12458 (name "java-biojava-core")
12462 (uri (git-reference
12463 (url "https://github.com/biojava/biojava")
12464 (commit (string-append "biojava-" version))))
12465 (file-name (string-append name "-" version "-checkout"))
12468 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12469 (build-system ant-build-system)
12472 #:jar-name "biojava-core.jar"
12473 #:source-dir "biojava-core/src/main/java/"
12474 #:test-dir "biojava-core/src/test"
12475 ;; These tests seem to require internet access.
12476 #:test-exclude (list "**/SearchIOTest.java"
12477 "**/BlastXMLParserTest.java"
12478 "**/GenbankCookbookTest.java"
12479 "**/GenbankProxySequenceReaderTest.java")
12481 (modify-phases %standard-phases
12482 (add-before 'build 'copy-resources
12484 (copy-recursively "biojava-core/src/main/resources"
12487 (add-before 'check 'copy-test-resources
12489 (copy-recursively "biojava-core/src/test/resources"
12490 "build/test-classes")
12493 `(("java-log4j-api" ,java-log4j-api)
12494 ("java-log4j-core" ,java-log4j-core)
12495 ("java-slf4j-api" ,java-slf4j-api)
12496 ("java-slf4j-simple" ,java-slf4j-simple)))
12498 `(("java-junit" ,java-junit)
12499 ("java-hamcrest-core" ,java-hamcrest-core)))
12500 (home-page "http://biojava.org")
12501 (synopsis "Core libraries of Java framework for processing biological data")
12502 (description "BioJava is a project dedicated to providing a Java framework
12503 for processing biological data. It provides analytical and statistical
12504 routines, parsers for common file formats, reference implementations of
12505 popular algorithms, and allows the manipulation of sequences and 3D
12506 structures. The goal of the biojava project is to facilitate rapid
12507 application development for bioinformatics.
12509 This package provides the core libraries.")
12510 (license license:lgpl2.1+)))
12512 (define-public java-biojava-phylo
12513 (package (inherit java-biojava-core)
12514 (name "java-biojava-phylo")
12515 (build-system ant-build-system)
12518 #:jar-name "biojava-phylo.jar"
12519 #:source-dir "biojava-phylo/src/main/java/"
12520 #:test-dir "biojava-phylo/src/test"
12522 (modify-phases %standard-phases
12523 (add-before 'build 'copy-resources
12525 (copy-recursively "biojava-phylo/src/main/resources"
12528 (add-before 'check 'copy-test-resources
12530 (copy-recursively "biojava-phylo/src/test/resources"
12531 "build/test-classes")
12534 `(("java-log4j-api" ,java-log4j-api)
12535 ("java-log4j-core" ,java-log4j-core)
12536 ("java-slf4j-api" ,java-slf4j-api)
12537 ("java-slf4j-simple" ,java-slf4j-simple)
12538 ("java-biojava-core" ,java-biojava-core)
12539 ("java-forester" ,java-forester)))
12541 `(("java-junit" ,java-junit)
12542 ("java-hamcrest-core" ,java-hamcrest-core)))
12543 (home-page "http://biojava.org")
12544 (synopsis "Biojava interface to the forester phylogenomics library")
12545 (description "The phylo module provides a biojava interface layer to the
12546 forester phylogenomics library for constructing phylogenetic trees.")))
12548 (define-public java-biojava-alignment
12549 (package (inherit java-biojava-core)
12550 (name "java-biojava-alignment")
12551 (build-system ant-build-system)
12554 #:jar-name "biojava-alignment.jar"
12555 #:source-dir "biojava-alignment/src/main/java/"
12556 #:test-dir "biojava-alignment/src/test"
12558 (modify-phases %standard-phases
12559 (add-before 'build 'copy-resources
12561 (copy-recursively "biojava-alignment/src/main/resources"
12564 (add-before 'check 'copy-test-resources
12566 (copy-recursively "biojava-alignment/src/test/resources"
12567 "build/test-classes")
12570 `(("java-log4j-api" ,java-log4j-api)
12571 ("java-log4j-core" ,java-log4j-core)
12572 ("java-slf4j-api" ,java-slf4j-api)
12573 ("java-slf4j-simple" ,java-slf4j-simple)
12574 ("java-biojava-core" ,java-biojava-core)
12575 ("java-biojava-phylo" ,java-biojava-phylo)
12576 ("java-forester" ,java-forester)))
12578 `(("java-junit" ,java-junit)
12579 ("java-hamcrest-core" ,java-hamcrest-core)))
12580 (home-page "http://biojava.org")
12581 (synopsis "Biojava API for genetic sequence alignment")
12582 (description "The alignment module of BioJava provides an API that
12586 @item implementations of dynamic programming algorithms for sequence
12588 @item reading and writing of popular alignment file formats;
12589 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12592 (define-public java-biojava-core-4.0
12593 (package (inherit java-biojava-core)
12594 (name "java-biojava-core")
12598 (uri (git-reference
12599 (url "https://github.com/biojava/biojava")
12600 (commit (string-append "biojava-" version))))
12601 (file-name (string-append name "-" version "-checkout"))
12604 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12606 (define-public java-biojava-phylo-4.0
12607 (package (inherit java-biojava-core-4.0)
12608 (name "java-biojava-phylo")
12609 (build-system ant-build-system)
12612 #:jar-name "biojava-phylo.jar"
12613 #:source-dir "biojava-phylo/src/main/java/"
12614 #:test-dir "biojava-phylo/src/test"
12616 (modify-phases %standard-phases
12617 (add-before 'build 'copy-resources
12619 (copy-recursively "biojava-phylo/src/main/resources"
12622 (add-before 'check 'copy-test-resources
12624 (copy-recursively "biojava-phylo/src/test/resources"
12625 "build/test-classes")
12628 `(("java-log4j-api" ,java-log4j-api)
12629 ("java-log4j-core" ,java-log4j-core)
12630 ("java-slf4j-api" ,java-slf4j-api)
12631 ("java-slf4j-simple" ,java-slf4j-simple)
12632 ("java-biojava-core" ,java-biojava-core-4.0)
12633 ("java-forester" ,java-forester-1.005)))
12635 `(("java-junit" ,java-junit)
12636 ("java-hamcrest-core" ,java-hamcrest-core)))
12637 (home-page "http://biojava.org")
12638 (synopsis "Biojava interface to the forester phylogenomics library")
12639 (description "The phylo module provides a biojava interface layer to the
12640 forester phylogenomics library for constructing phylogenetic trees.")))
12642 (define-public java-biojava-alignment-4.0
12643 (package (inherit java-biojava-core-4.0)
12644 (name "java-biojava-alignment")
12645 (build-system ant-build-system)
12648 #:jar-name "biojava-alignment.jar"
12649 #:source-dir "biojava-alignment/src/main/java/"
12650 #:test-dir "biojava-alignment/src/test"
12652 (modify-phases %standard-phases
12653 (add-before 'build 'copy-resources
12655 (copy-recursively "biojava-alignment/src/main/resources"
12658 (add-before 'check 'copy-test-resources
12660 (copy-recursively "biojava-alignment/src/test/resources"
12661 "build/test-classes")
12664 `(("java-log4j-api" ,java-log4j-api)
12665 ("java-log4j-core" ,java-log4j-core)
12666 ("java-slf4j-api" ,java-slf4j-api)
12667 ("java-slf4j-simple" ,java-slf4j-simple)
12668 ("java-biojava-core" ,java-biojava-core-4.0)
12669 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12670 ("java-forester" ,java-forester-1.005)))
12672 `(("java-junit" ,java-junit)
12673 ("java-hamcrest-core" ,java-hamcrest-core)))
12674 (home-page "http://biojava.org")
12675 (synopsis "Biojava API for genetic sequence alignment")
12676 (description "The alignment module of BioJava provides an API that
12680 @item implementations of dynamic programming algorithms for sequence
12682 @item reading and writing of popular alignment file formats;
12683 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12686 (define-public dropseq-tools
12688 (name "dropseq-tools")
12693 (uri "http://mccarrolllab.com/download/1276/")
12694 (file-name (string-append "dropseq-tools-" version ".zip"))
12697 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12698 ;; Delete bundled libraries
12699 (modules '((guix build utils)))
12702 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12703 (delete-file-recursively "3rdParty")
12705 (build-system ant-build-system)
12707 `(#:tests? #f ; test data are not included
12708 #:test-target "test"
12709 #:build-target "all"
12710 #:source-dir "public/src/"
12713 (list (string-append "-Dpicard.executable.dir="
12714 (assoc-ref %build-inputs "java-picard")
12716 #:modules ((ice-9 match)
12719 (guix build java-utils)
12720 (guix build ant-build-system))
12722 (modify-phases %standard-phases
12723 ;; FIXME: fails with "java.io.FileNotFoundException:
12724 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12725 (delete 'generate-jar-indices)
12726 ;; All dependencies must be linked to "lib", because that's where
12727 ;; they will be searched for when the Class-Path property of the
12728 ;; manifest is computed.
12729 (add-after 'unpack 'record-references
12730 (lambda* (#:key inputs #:allow-other-keys)
12731 (mkdir-p "jar/lib")
12732 (let ((dirs (filter-map (match-lambda
12734 (if (and (string-prefix? "java-" name)
12735 (not (string=? name "java-testng")))
12738 (for-each (lambda (jar)
12739 (symlink jar (string-append "jar/lib/" (basename jar))))
12740 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12743 ;; There is no installation target
12745 (lambda* (#:key inputs outputs #:allow-other-keys)
12746 (let* ((out (assoc-ref outputs "out"))
12747 (bin (string-append out "/bin"))
12748 (share (string-append out "/share/java/"))
12749 (lib (string-append share "/lib/"))
12750 (scripts (list "BAMTagHistogram"
12751 "BAMTagofTagCounts"
12752 "BaseDistributionAtReadPosition"
12753 "CollapseBarcodesInPlace"
12754 "CollapseTagWithContext"
12756 "CreateIntervalsFiles"
12757 "DetectBeadSynthesisErrors"
12758 "DigitalExpression"
12759 "Drop-seq_alignment.sh"
12762 "GatherGeneGCLength"
12763 "GatherMolecularBarcodeDistributionByGene"
12764 "GatherReadQualityMetrics"
12767 "SelectCellsByNumTranscripts"
12768 "SingleCellRnaSeqMetricsCollector"
12769 "TagBamWithReadSequenceExtended"
12770 "TagReadWithGeneExon"
12771 "TagReadWithInterval"
12772 "TrimStartingSequence"
12773 "ValidateReference")))
12774 (for-each mkdir-p (list bin share lib))
12775 (install-file "dist/dropseq.jar" share)
12776 (for-each (lambda (script)
12777 (chmod script #o555)
12778 (install-file script bin))
12780 (substitute* (map (lambda (script)
12781 (string-append bin "/" script))
12783 (("^java") (which "java"))
12784 (("jar_deploy_dir=.*")
12785 (string-append "jar_deploy_dir=" share "\n"))))
12787 ;; FIXME: We do this after stripping jars because we don't want it to
12788 ;; copy all these jars and strip them. We only want to install
12789 ;; links. Arguably, this is a problem with the ant-build-system.
12790 (add-after 'strip-jar-timestamps 'install-links
12791 (lambda* (#:key outputs #:allow-other-keys)
12792 (let* ((out (assoc-ref outputs "out"))
12793 (share (string-append out "/share/java/"))
12794 (lib (string-append share "/lib/")))
12795 (for-each (lambda (jar)
12796 (symlink (readlink jar)
12797 (string-append lib (basename jar))))
12798 (find-files "jar/lib" "\\.jar$")))
12801 `(("jdk" ,icedtea-8)
12802 ("java-picard" ,java-picard-2.10.3)
12803 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12804 ("java-commons-math3" ,java-commons-math3)
12805 ("java-commons-jexl2" ,java-commons-jexl-2)
12806 ("java-commons-collections4" ,java-commons-collections4)
12807 ("java-commons-lang2" ,java-commons-lang)
12808 ("java-commons-io" ,java-commons-io)
12809 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12810 ("java-guava" ,java-guava)
12811 ("java-la4j" ,java-la4j)
12812 ("java-biojava-core" ,java-biojava-core-4.0)
12813 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12814 ("java-jdistlib" ,java-jdistlib)
12815 ("java-simple-xml" ,java-simple-xml)
12816 ("java-snakeyaml" ,java-snakeyaml)))
12819 ("java-testng" ,java-testng)))
12820 (home-page "http://mccarrolllab.com/dropseq/")
12821 (synopsis "Tools for Drop-seq analyses")
12822 (description "Drop-seq is a technology to enable biologists to
12823 analyze RNA expression genome-wide in thousands of individual cells at
12824 once. This package provides tools to perform Drop-seq analyses.")
12825 (license license:expat)))
12827 (define-public pigx-rnaseq
12829 (name "pigx-rnaseq")
12833 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12834 "releases/download/v" version
12835 "/pigx_rnaseq-" version ".tar.gz"))
12838 "16gla23rmziimqan7w494q0nr7vfbp42zzkrl9fracmr4k7b1kzr"))))
12839 (build-system gnu-build-system)
12841 `(#:parallel-tests? #f ; not supported
12843 (modify-phases %standard-phases
12844 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12845 (add-after 'unpack 'disable-resource-intensive-test
12847 (substitute* "Makefile.in"
12848 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12849 (("^ tests/test_multiqc/test.sh") "")
12850 (("^ test.sh") ""))
12854 ("snakemake" ,snakemake-4)
12856 ("multiqc" ,multiqc)
12858 ("trim-galore" ,trim-galore)
12860 ("samtools" ,samtools)
12861 ("bedtools" ,bedtools)
12862 ("r-minimal" ,r-minimal)
12863 ("r-rmarkdown" ,r-rmarkdown)
12864 ("r-ggplot2" ,r-ggplot2)
12865 ("r-ggrepel" ,r-ggrepel)
12866 ("r-gprofiler" ,r-gprofiler)
12867 ("r-deseq2" ,r-deseq2)
12869 ("r-knitr" ,r-knitr)
12870 ("r-pheatmap" ,r-pheatmap)
12871 ("r-corrplot" ,r-corrplot)
12872 ("r-reshape2" ,r-reshape2)
12873 ("r-plotly" ,r-plotly)
12874 ("r-scales" ,r-scales)
12875 ("r-summarizedexperiment" ,r-summarizedexperiment)
12876 ("r-crosstalk" ,r-crosstalk)
12877 ("r-tximport" ,r-tximport)
12878 ("r-rtracklayer" ,r-rtracklayer)
12879 ("r-rjson" ,r-rjson)
12881 ("ghc-pandoc" ,ghc-pandoc-1)
12882 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12883 ("python-wrapper" ,python-wrapper)
12884 ("python-pyyaml" ,python-pyyaml)))
12885 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12886 (synopsis "Analysis pipeline for RNA sequencing experiments")
12887 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12888 reporting for RNA sequencing experiments. It is easy to use and produces high
12889 quality reports. The inputs are reads files from the sequencing experiment,
12890 and a configuration file which describes the experiment. In addition to
12891 quality control of the experiment, the pipeline produces a differential
12892 expression report comparing samples in an easily configurable manner.")
12893 (license license:gpl3+)))
12895 (define-public pigx-chipseq
12897 (name "pigx-chipseq")
12901 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12902 "releases/download/v" version
12903 "/pigx_chipseq-" version ".tar.gz"))
12906 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
12907 (build-system gnu-build-system)
12908 ;; parts of the tests rely on access to the network
12909 (arguments '(#:tests? #f))
12912 ("coreutils" ,coreutils)
12913 ("r-minimal" ,r-minimal)
12914 ("r-argparser" ,r-argparser)
12915 ("r-biocparallel" ,r-biocparallel)
12916 ("r-biostrings" ,r-biostrings)
12917 ("r-chipseq" ,r-chipseq)
12918 ("r-data-table" ,r-data-table)
12919 ("r-dplyr" ,r-dplyr)
12920 ("r-genomation" ,r-genomation)
12921 ("r-genomicalignments" ,r-genomicalignments)
12922 ("r-genomicranges" ,r-genomicranges)
12923 ("r-rsamtools" ,r-rsamtools)
12924 ("r-rtracklayer" ,r-rtracklayer)
12925 ("r-s4vectors" ,r-s4vectors)
12926 ("r-stringr" ,r-stringr)
12927 ("r-tibble" ,r-tibble)
12928 ("r-tidyr" ,r-tidyr)
12929 ("r-jsonlite" ,r-jsonlite)
12930 ("r-heatmaply" ,r-heatmaply)
12931 ("r-htmlwidgets" ,r-htmlwidgets)
12932 ("r-ggplot2" ,r-ggplot2)
12933 ("r-plotly" ,r-plotly)
12934 ("r-rmarkdown" ,r-rmarkdown)
12935 ("python-wrapper" ,python-wrapper)
12936 ("python-pyyaml" ,python-pyyaml)
12937 ("python-magic" ,python-magic)
12938 ("python-xlrd" ,python-xlrd)
12939 ("trim-galore" ,trim-galore)
12941 ("multiqc" ,multiqc)
12943 ("ghc-pandoc" ,ghc-pandoc-1)
12944 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12948 ("snakemake" ,snakemake-4)
12949 ("samtools" ,samtools)
12950 ("bedtools" ,bedtools)
12951 ("kentutils" ,kentutils)))
12953 `(("python-pytest" ,python-pytest)))
12954 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12955 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12956 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12957 calling and reporting for ChIP sequencing experiments. It is easy to use and
12958 produces high quality reports. The inputs are reads files from the sequencing
12959 experiment, and a configuration file which describes the experiment. In
12960 addition to quality control of the experiment, the pipeline enables to set up
12961 multiple peak calling analysis and allows the generation of a UCSC track hub
12962 in an easily configurable manner.")
12963 (license license:gpl3+)))
12965 (define-public pigx-bsseq
12967 (name "pigx-bsseq")
12971 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12972 "releases/download/v" version
12973 "/pigx_bsseq-" version ".tar.gz"))
12976 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12977 (build-system gnu-build-system)
12980 (modify-phases %standard-phases
12981 (add-before 'check 'set-timezone
12982 ;; The readr package is picky about timezones.
12983 (lambda* (#:key inputs #:allow-other-keys)
12984 (setenv "TZ" "UTC+1")
12986 (string-append (assoc-ref inputs "tzdata")
12987 "/share/zoneinfo"))
12990 `(("tzdata" ,tzdata)))
12992 `(("coreutils" ,coreutils)
12995 ("r-minimal" ,r-minimal)
12996 ("r-annotationhub" ,r-annotationhub)
12998 ("r-genomation" ,r-genomation)
12999 ("r-methylkit" ,r-methylkit)
13000 ("r-rtracklayer" ,r-rtracklayer)
13001 ("r-rmarkdown" ,r-rmarkdown)
13002 ("r-bookdown" ,r-bookdown)
13003 ("r-ggplot2" ,r-ggplot2)
13004 ("r-ggbio" ,r-ggbio)
13005 ("ghc-pandoc" ,ghc-pandoc-1)
13006 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13007 ("python-wrapper" ,python-wrapper)
13008 ("python-pyyaml" ,python-pyyaml)
13009 ("snakemake" ,snakemake-4)
13010 ("bismark" ,bismark)
13013 ("trim-galore" ,trim-galore)
13014 ("cutadapt" ,cutadapt)
13015 ("samtools" ,samtools)))
13016 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13017 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13018 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13019 data of bisulfite experiments; it produces reports on aggregate methylation
13020 and coverage and can be used to produce information on differential
13021 methylation and segmentation.")
13022 (license license:gpl3+)))
13024 (define-public pigx-scrnaseq
13026 (name "pigx-scrnaseq")
13030 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13031 "releases/download/v" version
13032 "/pigx_scrnaseq-" version ".tar.gz"))
13035 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13036 (build-system gnu-build-system)
13038 `(#:configure-flags
13039 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13040 "/share/java/picard.jar")
13041 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13042 "/share/java/dropseq.jar"))))
13044 `(("coreutils" ,coreutils)
13046 ("dropseq-tools" ,dropseq-tools)
13048 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13049 ("java" ,icedtea-8)
13050 ("python-wrapper" ,python-wrapper)
13051 ("python-pyyaml" ,python-pyyaml)
13052 ("python-pandas" ,python-pandas)
13053 ("python-magic" ,python-magic)
13054 ("python-numpy" ,python-numpy)
13055 ("python-loompy" ,python-loompy)
13056 ("ghc-pandoc" ,ghc-pandoc-1)
13057 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13058 ("samtools" ,samtools)
13059 ("snakemake" ,snakemake-4)
13061 ("r-minimal" ,r-minimal)
13062 ("r-argparser" ,r-argparser)
13063 ("r-cowplot" ,r-cowplot)
13064 ("r-data-table" ,r-data-table)
13065 ("r-delayedarray" ,r-delayedarray)
13066 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13067 ("r-dplyr" ,r-dplyr)
13068 ("r-dropbead" ,r-dropbead)
13070 ("r-genomicalignments" ,r-genomicalignments)
13071 ("r-genomicfiles" ,r-genomicfiles)
13072 ("r-genomicranges" ,r-genomicranges)
13073 ("r-ggplot2" ,r-ggplot2)
13074 ("r-hdf5array" ,r-hdf5array)
13075 ("r-pheatmap" ,r-pheatmap)
13076 ("r-rmarkdown" ,r-rmarkdown)
13077 ("r-rsamtools" ,r-rsamtools)
13078 ("r-rtracklayer" ,r-rtracklayer)
13079 ("r-rtsne" ,r-rtsne)
13080 ("r-scater" ,r-scater)
13081 ("r-scran" ,r-scran)
13082 ("r-singlecellexperiment" ,r-singlecellexperiment)
13083 ("r-stringr" ,r-stringr)
13084 ("r-yaml" ,r-yaml)))
13085 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13086 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13087 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13088 quality control for single cell RNA sequencing experiments. The inputs are
13089 read files from the sequencing experiment, and a configuration file which
13090 describes the experiment. It produces processed files for downstream analysis
13091 and interactive quality reports. The pipeline is designed to work with UMI
13093 (license license:gpl3+)))
13095 (define-public pigx
13101 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13102 "releases/download/v" version
13103 "/pigx-" version ".tar.gz"))
13106 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13107 (build-system gnu-build-system)
13109 `(("python" ,python)
13110 ("pigx-bsseq" ,pigx-bsseq)
13111 ("pigx-chipseq" ,pigx-chipseq)
13112 ("pigx-rnaseq" ,pigx-rnaseq)
13113 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13114 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13115 (synopsis "Analysis pipelines for genomics")
13116 (description "PiGx is a collection of genomics pipelines. It includes the
13117 following pipelines:
13120 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13121 @item PiGx RNAseq for RNAseq samples
13122 @item PiGx scRNAseq for single cell dropseq analysis
13123 @item PiGx ChIPseq for reads from ChIPseq experiments
13126 All pipelines are easily configured with a simple sample sheet and a
13127 descriptive settings file. The result is a set of comprehensive, interactive
13128 HTML reports with interesting findings about your samples.")
13129 (license license:gpl3+)))
13131 (define-public r-diversitree
13133 (name "r-diversitree")
13138 (uri (cran-uri "diversitree" version))
13141 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13142 (build-system r-build-system)
13144 `(("gfortran" ,gfortran)))
13145 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13148 ("r-desolve" ,r-desolve)
13150 ("r-suplex" ,r-subplex)))
13151 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13152 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13153 (description "This package contains a number of comparative \"phylogenetic\"
13154 methods, mostly focusing on analysing diversification and character evolution.
13155 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13156 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13157 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13158 include Markov models of discrete and continuous trait evolution and constant
13159 rate speciation and extinction.")
13160 (license license:gpl2+)))
13162 (define-public sjcount
13163 ;; There is no tag for version 3.2, nor is there a release archive.
13164 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13168 (version (git-version "3.2" revision commit))
13171 (uri (git-reference
13172 (url "https://github.com/pervouchine/sjcount-full.git")
13174 (file-name (string-append name "-" version "-checkout"))
13177 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13178 (build-system gnu-build-system)
13180 `(#:tests? #f ; requires a 1.4G test file
13182 (list (string-append "SAMTOOLS_DIR="
13183 (assoc-ref %build-inputs "samtools")
13186 (modify-phases %standard-phases
13187 (replace 'configure
13188 (lambda* (#:key inputs #:allow-other-keys)
13189 (substitute* "makefile"
13190 (("-I \\$\\{SAMTOOLS_DIR\\}")
13191 (string-append "-I" (assoc-ref inputs "samtools")
13192 "/include/samtools"))
13193 (("-lz ") "-lz -lpthread "))
13196 (lambda* (#:key outputs #:allow-other-keys)
13197 (for-each (lambda (tool)
13199 (string-append (assoc-ref outputs "out")
13201 '("j_count" "b_count" "sjcount"))
13204 `(("samtools" ,samtools-0.1)
13206 (home-page "https://github.com/pervouchine/sjcount-full/")
13207 (synopsis "Annotation-agnostic splice junction counting pipeline")
13208 (description "Sjcount is a utility for fast quantification of splice
13209 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13210 version does count multisplits.")
13211 (license license:gpl3+))))
13213 (define-public minimap2
13220 (uri (string-append "https://github.com/lh3/minimap2/"
13221 "releases/download/v" version "/"
13222 "minimap2-" version ".tar.bz2"))
13225 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13226 (build-system gnu-build-system)
13228 `(#:tests? #f ; there are none
13231 (let ((system ,(or (%current-target-system)
13232 (%current-system))))
13234 ((string-prefix? "x86_64" system)
13236 ((or (string-prefix? "armhf" system)
13237 (string-prefix? "aarch64" system))
13239 (_ "sse2only=1"))))
13241 (modify-phases %standard-phases
13242 (delete 'configure)
13244 (lambda* (#:key outputs #:allow-other-keys)
13245 (let* ((out (assoc-ref outputs "out"))
13246 (bin (string-append out "/bin"))
13247 (man (string-append out "/share/man/man1")))
13248 (install-file "minimap2" bin)
13250 (install-file "minimap2.1" man))
13254 (home-page "https://lh3.github.io/minimap2/")
13255 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13256 (description "Minimap2 is a versatile sequence alignment program that
13257 aligns DNA or mRNA sequences against a large reference database. Typical use
13261 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13262 @item finding overlaps between long reads with error rate up to ~15%;
13263 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13264 reads against a reference genome;
13265 @item aligning Illumina single- or paired-end reads;
13266 @item assembly-to-assembly alignment;
13267 @item full-genome alignment between two closely related species with
13268 divergence below ~15%.
13270 (license license:expat)))
13272 (define-public r-circus
13279 (uri (git-reference
13280 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13281 (commit (string-append "v" version))))
13282 (file-name (git-file-name name version))
13285 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13286 (build-system r-build-system)
13288 `(("r-annotationdbi" ,r-annotationdbi)
13289 ("r-annotationhub" ,r-annotationhub)
13290 ("r-biomart" ,r-biomart)
13291 ("r-data-table" ,r-data-table)
13293 ("r-genomicfeatures" ,r-genomicfeatures)
13294 ("r-genomicranges" ,r-genomicranges)
13295 ("r-ggplot2" ,r-ggplot2)
13297 ("r-iranges" ,r-iranges)
13298 ("r-rcolorbrewer" ,r-rcolorbrewer)
13299 ("r-rmysql" ,r-rmysql)
13300 ("r-s4vectors" ,r-s4vectors)
13301 ("r-stringr" ,r-stringr)
13302 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13304 `(("r-knitr" ,r-knitr)))
13305 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13306 (synopsis "Annotation, analysis and visualization of circRNA data")
13307 (description "Circus is an R package for annotation, analysis and
13308 visualization of circRNA data. Users can annotate their circRNA candidates
13309 with host genes, gene featrues they are spliced from, and discriminate between
13310 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13311 can be calculated, and a number of descriptive plots easily generated.")
13312 (license license:artistic2.0)))
13314 (define-public r-loomr
13315 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13319 (version (git-version "0.2.0" revision commit))
13323 (uri (git-reference
13324 (url "https://github.com/mojaveazure/loomR.git")
13326 (file-name (git-file-name name version))
13329 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13330 (build-system r-build-system)
13333 ("r-hdf5r" ,r-hdf5r)
13334 ("r-iterators" ,r-iterators)
13335 ("r-itertools" ,r-itertools)
13336 ("r-matrix" ,r-matrix)))
13337 (home-page "https://github.com/mojaveazure/loomR")
13338 (synopsis "R interface for loom files")
13339 (description "This package provides an R interface to access, create,
13340 and modify loom files. loomR aims to be completely compatible with loompy.")
13341 (license license:gpl3))))
13343 (define-public gffread
13344 ;; We cannot use the tagged release because it is not in sync with gclib.
13345 ;; See https://github.com/gpertea/gffread/issues/26
13346 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13350 (version (git-version "0.9.12" revision commit))
13354 (uri (git-reference
13355 (url "https://github.com/gpertea/gffread.git")
13357 (file-name (git-file-name name version))
13360 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13361 (build-system gnu-build-system)
13363 `(#:tests? #f ; no check target
13365 (list "GCLDIR=gclib")
13367 (modify-phases %standard-phases
13368 (delete 'configure)
13369 (add-after 'unpack 'copy-gclib-source
13370 (lambda* (#:key inputs #:allow-other-keys)
13372 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13374 ;; There is no install target
13376 (lambda* (#:key outputs #:allow-other-keys)
13377 (let* ((out (assoc-ref outputs "out"))
13378 (bin (string-append out "/bin")))
13379 (install-file "gffread" bin))
13383 ,(let ((version "0.10.3")
13384 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13388 (uri (git-reference
13389 (url "https://github.com/gpertea/gclib.git")
13391 (file-name (git-file-name "gclib" version))
13394 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13395 (home-page "https://github.com/gpertea/gffread/")
13396 (synopsis "Parse and convert GFF/GTF files")
13398 "This package provides a GFF/GTF file parsing utility providing format
13399 conversions, region filtering, FASTA sequence extraction and more.")
13400 ;; gffread is under Expat, but gclib is under Artistic 2.0
13401 (license (list license:expat
13402 license:artistic2.0)))))
13404 (define-public find-circ
13405 ;; The last release was in 2015. The license was clarified in 2017, so we
13406 ;; take the latest commit.
13407 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13411 (version (git-version "1.2" revision commit))
13415 (uri (git-reference
13416 (url "https://github.com/marvin-jens/find_circ.git")
13418 (file-name (git-file-name name version))
13421 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13422 (build-system gnu-build-system)
13424 `(#:tests? #f ; there are none
13426 ;; There is no actual build system.
13427 (modify-phases %standard-phases
13428 (delete 'configure)
13431 (lambda* (#:key outputs #:allow-other-keys)
13432 (let* ((out (assoc-ref outputs "out"))
13433 (bin (string-append out "/bin"))
13434 (path (getenv "PYTHONPATH")))
13435 (for-each (lambda (script)
13436 (install-file script bin)
13437 (wrap-program (string-append bin "/" script)
13438 `("PYTHONPATH" ":" prefix (,path))))
13443 "unmapped2anchors.py")))
13446 `(("python2" ,python-2)
13447 ("python2-pysam" ,python2-pysam)
13448 ("python2-numpy" ,python2-numpy)))
13449 (home-page "https://github.com/marvin-jens/find_circ")
13450 (synopsis "circRNA detection from RNA-seq reads")
13451 (description "This package provides tools to detect head-to-tail
13452 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13454 (license license:gpl3))))
13456 (define-public python-scanpy
13458 (name "python-scanpy")
13463 (uri (pypi-uri "scanpy" version))
13466 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13467 (build-system python-build-system)
13469 `(("python-anndata" ,python-anndata)
13470 ("python-igraph" ,python-igraph)
13471 ("python-numba" ,python-numba)
13472 ("python-joblib" ,python-joblib)
13473 ("python-natsort" ,python-natsort)
13474 ("python-networkx" ,python-networkx)
13475 ("python-statsmodels" ,python-statsmodels)
13476 ("python-scikit-learn" ,python-scikit-learn)
13477 ("python-matplotlib" ,python-matplotlib)
13478 ("python-pandas" ,python-pandas)
13479 ("python-scipy" ,python-scipy)
13480 ("python-seaborn" ,python-seaborn)
13481 ("python-h5py" ,python-h5py)
13482 ("python-tables" ,python-tables)))
13483 (home-page "http://github.com/theislab/scanpy")
13484 (synopsis "Single-Cell Analysis in Python.")
13485 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13486 expression data. It includes preprocessing, visualization, clustering,
13487 pseudotime and trajectory inference and differential expression testing. The
13488 Python-based implementation efficiently deals with datasets of more than one
13490 (license license:bsd-3)))
13492 (define-public gffcompare
13493 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13496 (name "gffcompare")
13497 (version (git-version "0.10.15" revision commit))
13501 (uri (git-reference
13502 (url "https://github.com/gpertea/gffcompare/")
13504 (file-name (git-file-name name version))
13506 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13507 (build-system gnu-build-system)
13509 `(#:tests? #f ; no check target
13511 (modify-phases %standard-phases
13512 (delete 'configure)
13513 (add-before 'build 'copy-gclib-source
13514 (lambda* (#:key inputs #:allow-other-keys)
13517 (assoc-ref inputs "gclib-source") "../gclib")
13520 (lambda* (#:key outputs #:allow-other-keys)
13521 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13522 (install-file "gffcompare" bin)
13525 `(("gclib-source" ; see 'README.md' of gffcompare
13526 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13529 (version (git-version "0.10.3" revision commit)))
13532 (uri (git-reference
13533 (url "https://github.com/gpertea/gclib/")
13535 (file-name (git-file-name name version))
13537 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13538 (home-page "https://github.com/gpertea/gffcompare/")
13539 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13541 "@code{gffcompare} is a tool that can:
13543 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13544 (Cufflinks, Stringtie);
13545 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13546 resulted from assembly of different samples);
13547 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13548 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13552 license:expat ;license for gffcompare
13553 license:artistic2.0))))) ;license for gclib