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>
15 ;;; This file is part of GNU Guix.
17 ;;; GNU Guix is free software; you can redistribute it and/or modify it
18 ;;; under the terms of the GNU General Public License as published by
19 ;;; the Free Software Foundation; either version 3 of the License, or (at
20 ;;; your option) any later version.
22 ;;; GNU Guix is distributed in the hope that it will be useful, but
23 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
24 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
25 ;;; GNU General Public License for more details.
27 ;;; You should have received a copy of the GNU General Public License
28 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
30 (define-module (gnu packages bioinformatics)
31 #:use-module ((guix licenses) #:prefix license:)
32 #:use-module (guix packages)
33 #:use-module (guix utils)
34 #:use-module (guix download)
35 #:use-module (guix git-download)
36 #:use-module (guix hg-download)
37 #:use-module (guix build-system ant)
38 #:use-module (guix build-system gnu)
39 #:use-module (guix build-system cmake)
40 #:use-module (guix build-system ocaml)
41 #:use-module (guix build-system perl)
42 #:use-module (guix build-system python)
43 #:use-module (guix build-system r)
44 #:use-module (guix build-system ruby)
45 #:use-module (guix build-system scons)
46 #:use-module (guix build-system trivial)
47 #:use-module (gnu packages)
48 #:use-module (gnu packages autotools)
49 #:use-module (gnu packages algebra)
50 #:use-module (gnu packages base)
51 #:use-module (gnu packages bash)
52 #:use-module (gnu packages bison)
53 #:use-module (gnu packages boost)
54 #:use-module (gnu packages check)
55 #:use-module (gnu packages compression)
56 #:use-module (gnu packages cpio)
57 #:use-module (gnu packages cran)
58 #:use-module (gnu packages curl)
59 #:use-module (gnu packages documentation)
60 #:use-module (gnu packages databases)
61 #:use-module (gnu packages datastructures)
62 #:use-module (gnu packages file)
63 #:use-module (gnu packages flex)
64 #:use-module (gnu packages gawk)
65 #:use-module (gnu packages gcc)
66 #:use-module (gnu packages gd)
67 #:use-module (gnu packages gtk)
68 #:use-module (gnu packages glib)
69 #:use-module (gnu packages graph)
70 #:use-module (gnu packages groff)
71 #:use-module (gnu packages guile)
72 #:use-module (gnu packages haskell)
73 #:use-module (gnu packages image)
74 #:use-module (gnu packages imagemagick)
75 #:use-module (gnu packages java)
76 #:use-module (gnu packages jemalloc)
77 #:use-module (gnu packages ldc)
78 #:use-module (gnu packages linux)
79 #:use-module (gnu packages logging)
80 #:use-module (gnu packages machine-learning)
81 #:use-module (gnu packages man)
82 #:use-module (gnu packages maths)
83 #:use-module (gnu packages mpi)
84 #:use-module (gnu packages ncurses)
85 #:use-module (gnu packages ocaml)
86 #:use-module (gnu packages pcre)
87 #:use-module (gnu packages parallel)
88 #:use-module (gnu packages pdf)
89 #:use-module (gnu packages perl)
90 #:use-module (gnu packages perl-check)
91 #:use-module (gnu packages pkg-config)
92 #:use-module (gnu packages popt)
93 #:use-module (gnu packages protobuf)
94 #:use-module (gnu packages python)
95 #:use-module (gnu packages python-web)
96 #:use-module (gnu packages readline)
97 #:use-module (gnu packages ruby)
98 #:use-module (gnu packages serialization)
99 #:use-module (gnu packages shells)
100 #:use-module (gnu packages statistics)
101 #:use-module (gnu packages swig)
102 #:use-module (gnu packages tbb)
103 #:use-module (gnu packages tex)
104 #:use-module (gnu packages texinfo)
105 #:use-module (gnu packages textutils)
106 #:use-module (gnu packages time)
107 #:use-module (gnu packages tls)
108 #:use-module (gnu packages vim)
109 #:use-module (gnu packages web)
110 #:use-module (gnu packages xml)
111 #:use-module (gnu packages xorg)
112 #:use-module (srfi srfi-1)
113 #:use-module (ice-9 match))
115 (define-public aragorn
122 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
126 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
127 (build-system gnu-build-system)
129 `(#:tests? #f ; there are no tests
131 (modify-phases %standard-phases
135 (zero? (system* "gcc"
141 (string-append "aragorn" ,version ".c")))))
143 (lambda* (#:key outputs #:allow-other-keys)
144 (let* ((out (assoc-ref outputs "out"))
145 (bin (string-append out "/bin"))
146 (man (string-append out "/share/man/man1")))
148 (install-file "aragorn" bin)
150 (install-file "aragorn.1" man))
152 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
153 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
155 "Aragorn identifies transfer RNA, mitochondrial RNA and
156 transfer-messenger RNA from nucleotide sequences, based on homology to known
157 tRNA consensus sequences and RNA structure. It also outputs the secondary
158 structure of the predicted RNA.")
159 (license license:gpl2)))
167 ;; BamM is not available on pypi.
169 "https://github.com/Ecogenomics/BamM/archive/"
171 (file-name (string-append name "-" version ".tar.gz"))
174 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
175 (modules '((guix build utils)))
178 ;; Delete bundled htslib.
179 (delete-file-recursively "c/htslib-1.3.1")
181 (build-system python-build-system)
183 `(#:python ,python-2 ; BamM is Python 2 only.
184 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
185 ;; been modified from its original form.
187 (let ((htslib (assoc-ref %build-inputs "htslib")))
188 (list "--with-libhts-lib" (string-append htslib "/lib")
189 "--with-libhts-inc" (string-append htslib "/include/htslib")))
191 (modify-phases %standard-phases
192 (add-after 'unpack 'autogen
194 (with-directory-excursion "c"
195 (let ((sh (which "sh")))
196 ;; Use autogen so that 'configure' works.
197 (substitute* "autogen.sh" (("/bin/sh") sh))
198 (setenv "CONFIG_SHELL" sh)
199 (substitute* "configure" (("/bin/sh") sh))
200 (zero? (system* "./autogen.sh"))))))
202 ;; Run tests after installation so compilation only happens once.
204 (add-after 'install 'wrap-executable
205 (lambda* (#:key outputs #:allow-other-keys)
206 (let* ((out (assoc-ref outputs "out"))
207 (path (getenv "PATH")))
208 (wrap-program (string-append out "/bin/bamm")
209 `("PATH" ":" prefix (,path))))
211 (add-after 'wrap-executable 'post-install-check
212 (lambda* (#:key inputs outputs #:allow-other-keys)
214 (string-append (assoc-ref outputs "out")
219 (assoc-ref outputs "out")
221 (string-take (string-take-right
222 (assoc-ref inputs "python") 5) 3)
224 (getenv "PYTHONPATH")))
225 ;; There are 2 errors printed, but they are safe to ignore:
226 ;; 1) [E::hts_open_format] fail to open file ...
227 ;; 2) samtools view: failed to open ...
228 (zero? (system* "nosetests")))))))
230 `(("autoconf" ,autoconf)
231 ("automake" ,automake)
234 ("python-nose" ,python2-nose)
235 ("python-pysam" ,python2-pysam)))
237 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
238 ("samtools" ,samtools)
242 ("coreutils" ,coreutils)))
244 `(("python-numpy" ,python2-numpy)))
245 (home-page "http://ecogenomics.github.io/BamM/")
246 (synopsis "Metagenomics-focused BAM file manipulator")
248 "BamM is a C library, wrapped in python, to efficiently generate and
249 parse BAM files, specifically for the analysis of metagenomic data. For
250 instance, it implements several methods to assess contig-wise read coverage.")
251 (license license:lgpl3+)))
253 (define-public bamtools
260 "https://github.com/pezmaster31/bamtools/archive/v"
262 (file-name (string-append name "-" version ".tar.gz"))
265 "1z3kg24qrwq13a88n9d86izngrar4fll7gr6phddb2faw75pdgaa"))))
266 (build-system cmake-build-system)
268 `(#:tests? #f ;no "check" target
270 (modify-phases %standard-phases
272 'configure 'set-ldflags
273 (lambda* (#:key outputs #:allow-other-keys)
277 (assoc-ref outputs "out") "/lib/bamtools")))))))
278 (inputs `(("zlib" ,zlib)))
279 (home-page "https://github.com/pezmaster31/bamtools")
280 (synopsis "C++ API and command-line toolkit for working with BAM data")
282 "BamTools provides both a C++ API and a command-line toolkit for handling
284 (license license:expat)))
286 (define-public bcftools
293 "https://github.com/samtools/bcftools/releases/download/"
294 version "/bcftools-" version ".tar.bz2"))
297 "1vgw2mwngq20c530zim52zvgmw1lci8rzl33pvh44xqk3xlzvjsa"))
298 (modules '((guix build utils)))
300 ;; Delete bundled htslib.
301 (delete-file-recursively "htslib-1.8")
303 (build-system gnu-build-system)
305 `(#:test-target "test"
306 #:configure-flags (list "--with-htslib=system")
310 "LIBS=-lgsl -lgslcblas"
311 (string-append "prefix=" (assoc-ref %outputs "out"))
312 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
313 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
314 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
315 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
316 (string-append "PACKAGE_VERSION=" ,version))
318 (modify-phases %standard-phases
319 (add-before 'check 'patch-tests
321 (substitute* "test/test.pl"
322 (("/bin/bash") (which "bash")))
330 (home-page "https://samtools.github.io/bcftools/")
331 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
333 "BCFtools is a set of utilities that manipulate variant calls in the
334 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
335 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
336 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
337 (license (list license:gpl3+ license:expat))))
339 (define-public bedops
345 (uri (string-append "https://github.com/bedops/bedops/archive/v"
347 (file-name (string-append name "-" version ".tar.gz"))
350 "0kx4awrwby8f33wqyx8w7ms7v25xhf0d421csgf96a3hfzn2mb0m"))))
351 (build-system gnu-build-system)
354 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
356 (modify-phases %standard-phases
357 (add-after 'unpack 'unpack-tarballs
359 ;; FIXME: Bedops includes tarballs of minimally patched upstream
360 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
361 ;; libraries because at least one of the libraries (zlib) is
362 ;; patched to add a C++ function definition (deflateInit2cpp).
363 ;; Until the Bedops developers offer a way to link against system
364 ;; libraries we have to build the in-tree copies of these three
367 ;; See upstream discussion:
368 ;; https://github.com/bedops/bedops/issues/124
370 ;; Unpack the tarballs to benefit from shebang patching.
371 (with-directory-excursion "third-party"
372 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
373 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
374 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
375 ;; Disable unpacking of tarballs in Makefile.
376 (substitute* "system.mk/Makefile.linux"
377 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
378 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
379 (substitute* "third-party/zlib-1.2.7/Makefile.in"
380 (("^SHELL=.*$") "SHELL=bash\n"))
382 (delete 'configure))))
383 (home-page "https://github.com/bedops/bedops")
384 (synopsis "Tools for high-performance genomic feature operations")
386 "BEDOPS is a suite of tools to address common questions raised in genomic
387 studies---mostly with regard to overlap and proximity relationships between
388 data sets. It aims to be scalable and flexible, facilitating the efficient
389 and accurate analysis and management of large-scale genomic data.
391 BEDOPS provides tools that perform highly efficient and scalable Boolean and
392 other set operations, statistical calculations, archiving, conversion and
393 other management of genomic data of arbitrary scale. Tasks can be easily
394 split by chromosome for distributing whole-genome analyses across a
395 computational cluster.")
396 (license license:gpl2+)))
398 (define-public bedtools
404 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
405 "download/v" version "/"
406 "bedtools-" version ".tar.gz"))
409 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
410 (build-system gnu-build-system)
412 '(#:test-target "test"
414 (list (string-append "prefix=" (assoc-ref %outputs "out")))
416 (modify-phases %standard-phases
417 (delete 'configure))))
418 (native-inputs `(("python" ,python-2)))
420 `(("samtools" ,samtools)
422 (home-page "https://github.com/arq5x/bedtools2")
423 (synopsis "Tools for genome analysis and arithmetic")
425 "Collectively, the bedtools utilities are a swiss-army knife of tools for
426 a wide-range of genomics analysis tasks. The most widely-used tools enable
427 genome arithmetic: that is, set theory on the genome. For example, bedtools
428 allows one to intersect, merge, count, complement, and shuffle genomic
429 intervals from multiple files in widely-used genomic file formats such as BAM,
431 (license license:gpl2)))
433 ;; Later releases of bedtools produce files with more columns than
434 ;; what Ribotaper expects.
435 (define-public bedtools-2.18
436 (package (inherit bedtools)
441 (uri (string-append "https://github.com/arq5x/bedtools2/"
442 "archive/v" version ".tar.gz"))
443 (file-name (string-append name "-" version ".tar.gz"))
446 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
448 '(#:test-target "test"
450 (modify-phases %standard-phases
453 (lambda* (#:key outputs #:allow-other-keys)
454 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
455 (for-each (lambda (file)
456 (install-file file bin))
457 (find-files "bin" ".*")))
460 (define-public ribotaper
466 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
467 "files/RiboTaper/RiboTaper_Version_"
471 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
472 (build-system gnu-build-system)
475 (modify-phases %standard-phases
476 (add-after 'install 'wrap-executables
477 (lambda* (#:key inputs outputs #:allow-other-keys)
478 (let* ((out (assoc-ref outputs "out")))
481 (wrap-program (string-append out "/bin/" script)
482 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
483 '("create_annotations_files.bash"
484 "create_metaplots.bash"
485 "Ribotaper_ORF_find.sh"
486 "Ribotaper.sh"))))))))
488 `(("bedtools" ,bedtools-2.18)
489 ("samtools" ,samtools-0.1)
490 ("r-minimal" ,r-minimal)
491 ("r-foreach" ,r-foreach)
492 ("r-xnomial" ,r-xnomial)
494 ("r-multitaper" ,r-multitaper)
495 ("r-seqinr" ,r-seqinr)))
496 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
497 (synopsis "Define translated ORFs using ribosome profiling data")
499 "Ribotaper is a method for defining translated @dfn{open reading
500 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
501 provides the Ribotaper pipeline.")
502 (license license:gpl3+)))
504 (define-public ribodiff
511 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
512 "archive/v" version ".tar.gz"))
513 (file-name (string-append name "-" version ".tar.gz"))
516 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
517 (build-system python-build-system)
521 (modify-phases %standard-phases
522 ;; Generate an installable executable script wrapper.
523 (add-after 'unpack 'patch-setup.py
525 (substitute* "setup.py"
526 (("^(.*)packages=.*" line prefix)
527 (string-append line "\n"
528 prefix "scripts=['scripts/TE.py'],\n")))
531 `(("python-numpy" ,python2-numpy)
532 ("python-matplotlib" ,python2-matplotlib)
533 ("python-scipy" ,python2-scipy)
534 ("python-statsmodels" ,python2-statsmodels)))
536 `(("python-mock" ,python2-mock)
537 ("python-nose" ,python2-nose)))
538 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
539 (synopsis "Detect translation efficiency changes from ribosome footprints")
540 (description "RiboDiff is a statistical tool that detects the protein
541 translational efficiency change from Ribo-Seq (ribosome footprinting) and
542 RNA-Seq data. It uses a generalized linear model to detect genes showing
543 difference in translational profile taking mRNA abundance into account. It
544 facilitates us to decipher the translational regulation that behave
545 independently with transcriptional regulation.")
546 (license license:gpl3+)))
548 (define-public bioawk
554 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
556 (file-name (string-append name "-" version ".tar.gz"))
558 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
559 (build-system gnu-build-system)
565 `(#:tests? #f ; There are no tests to run.
566 ;; Bison must generate files, before other targets can build.
569 (modify-phases %standard-phases
570 (delete 'configure) ; There is no configure phase.
572 (lambda* (#:key outputs #:allow-other-keys)
573 (let* ((out (assoc-ref outputs "out"))
574 (bin (string-append out "/bin"))
575 (man (string-append out "/share/man/man1")))
577 (copy-file "awk.1" (string-append man "/bioawk.1"))
578 (install-file "bioawk" bin)))))))
579 (home-page "https://github.com/lh3/bioawk")
580 (synopsis "AWK with bioinformatics extensions")
581 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
582 support of several common biological data formats, including optionally gzip'ed
583 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
584 also adds a few built-in functions and a command line option to use TAB as the
585 input/output delimiter. When the new functionality is not used, bioawk is
586 intended to behave exactly the same as the original BWK awk.")
587 (license license:x11)))
589 (define-public python2-pybedtools
591 (name "python2-pybedtools")
596 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
600 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
601 (build-system python-build-system)
602 (arguments `(#:python ,python-2)) ; no Python 3 support
604 `(("python-matplotlib" ,python2-matplotlib)))
606 `(("bedtools" ,bedtools)
607 ("samtools" ,samtools)))
609 `(("python-cython" ,python2-cython)
610 ("python-pyyaml" ,python2-pyyaml)
611 ("python-nose" ,python2-nose)))
612 (home-page "https://pythonhosted.org/pybedtools/")
613 (synopsis "Python wrapper for BEDtools programs")
615 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
616 which are widely used for genomic interval manipulation or \"genome algebra\".
617 pybedtools extends BEDTools by offering feature-level manipulations from with
619 (license license:gpl2+)))
621 (define-public python-biom-format
623 (name "python-biom-format")
628 ;; Use GitHub as source because PyPI distribution does not contain
629 ;; test data: https://github.com/biocore/biom-format/issues/693
630 (uri (string-append "https://github.com/biocore/biom-format/archive/"
632 (file-name (string-append name "-" version ".tar.gz"))
635 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
636 (build-system python-build-system)
638 `(("python-numpy" ,python-numpy)
639 ("python-scipy" ,python-scipy)
640 ("python-future" ,python-future)
641 ("python-click" ,python-click)
642 ("python-h5py" ,python-h5py)
643 ("python-pandas" ,python-pandas)))
645 `(("python-nose" ,python-nose)))
646 (home-page "http://www.biom-format.org")
647 (synopsis "Biological Observation Matrix (BIOM) format utilities")
649 "The BIOM file format is designed to be a general-use format for
650 representing counts of observations e.g. operational taxonomic units, KEGG
651 orthology groups or lipid types, in one or more biological samples
652 e.g. microbiome samples, genomes, metagenomes.")
653 (license license:bsd-3)
654 (properties `((python2-variant . ,(delay python2-biom-format))))))
656 (define-public python2-biom-format
657 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
662 (modify-phases %standard-phases
663 ;; Do not require the unmaintained pyqi library.
664 (add-after 'unpack 'remove-pyqi
666 (substitute* "setup.py"
667 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
669 ,@(package-arguments base))))))
671 (define-public bioperl-minimal
672 (let* ((inputs `(("perl-module-build" ,perl-module-build)
673 ("perl-data-stag" ,perl-data-stag)
674 ("perl-libwww" ,perl-libwww)
675 ("perl-uri" ,perl-uri)))
677 (map (compose package-name cadr)
680 (map (compose package-transitive-target-inputs cadr) inputs))))))
682 (name "bioperl-minimal")
687 (uri (string-append "https://github.com/bioperl/bioperl-live/"
689 (string-map (lambda (c)
695 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
696 (build-system perl-build-system)
699 (modify-phases %standard-phases
701 'install 'wrap-programs
702 (lambda* (#:key outputs #:allow-other-keys)
703 ;; Make sure all executables in "bin" find the required Perl
704 ;; modules at runtime. As the PERL5LIB variable contains also
705 ;; the paths of native inputs, we pick the transitive target
706 ;; inputs from %build-inputs.
707 (let* ((out (assoc-ref outputs "out"))
708 (bin (string-append out "/bin/"))
710 (cons (string-append out "/lib/perl5/site_perl")
712 (assoc-ref %build-inputs name))
713 ',transitive-inputs))
715 (for-each (lambda (file)
717 `("PERL5LIB" ":" prefix (,path))))
718 (find-files bin "\\.pl$"))
722 `(("perl-test-most" ,perl-test-most)))
723 (home-page "http://search.cpan.org/dist/BioPerl")
724 (synopsis "Bioinformatics toolkit")
726 "BioPerl is the product of a community effort to produce Perl code which
727 is useful in biology. Examples include Sequence objects, Alignment objects
728 and database searching objects. These objects not only do what they are
729 advertised to do in the documentation, but they also interact - Alignment
730 objects are made from the Sequence objects, Sequence objects have access to
731 Annotation and SeqFeature objects and databases, Blast objects can be
732 converted to Alignment objects, and so on. This means that the objects
733 provide a coordinated and extensible framework to do computational biology.")
734 (license license:perl-license))))
736 (define-public python-biopython
738 (name "python-biopython")
742 ;; use PyPi rather than biopython.org to ease updating
743 (uri (pypi-uri "biopython" version))
746 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
747 (build-system python-build-system)
750 (modify-phases %standard-phases
751 (add-before 'check 'set-home
752 ;; Some tests require a home directory to be set.
753 (lambda _ (setenv "HOME" "/tmp") #t)))))
755 `(("python-numpy" ,python-numpy)))
756 (home-page "http://biopython.org/")
757 (synopsis "Tools for biological computation in Python")
759 "Biopython is a set of tools for biological computation including parsers
760 for bioinformatics files into Python data structures; interfaces to common
761 bioinformatics programs; a standard sequence class and tools for performing
762 common operations on them; code to perform data classification; code for
763 dealing with alignments; code making it easy to split up parallelizable tasks
764 into separate processes; and more.")
765 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
767 (define-public python2-biopython
768 (package-with-python2 python-biopython))
770 (define-public python-fastalite
772 (name "python-fastalite")
777 (uri (pypi-uri "fastalite" version))
780 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
781 (build-system python-build-system)
783 `(#:tests? #f)) ; Test data is not distributed.
784 (home-page "https://github.com/nhoffman/fastalite")
785 (synopsis "Simplest possible FASTA parser")
786 (description "This library implements a FASTA and a FASTQ parser without
787 relying on a complex dependency tree.")
788 (license license:expat)))
790 (define-public python2-fastalite
791 (package-with-python2 python-fastalite))
793 (define-public bpp-core
794 ;; The last release was in 2014 and the recommended way to install from source
795 ;; is to clone the git repository, so we do this.
796 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
797 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
800 (version (string-append "2.2.0-1." (string-take commit 7)))
804 (url "http://biopp.univ-montp2.fr/git/bpp-core")
806 (file-name (string-append name "-" version "-checkout"))
809 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
810 (build-system cmake-build-system)
812 `(#:parallel-build? #f))
814 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
815 ; compile all of the bpp packages with GCC 5.
816 (home-page "http://biopp.univ-montp2.fr")
817 (synopsis "C++ libraries for Bioinformatics")
819 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
820 analysis, phylogenetics, molecular evolution and population genetics. It is
821 Object Oriented and is designed to be both easy to use and computer efficient.
822 Bio++ intends to help programmers to write computer expensive programs, by
823 providing them a set of re-usable tools.")
824 (license license:cecill-c))))
826 (define-public bpp-phyl
827 ;; The last release was in 2014 and the recommended way to install from source
828 ;; is to clone the git repository, so we do this.
829 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
830 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
833 (version (string-append "2.2.0-1." (string-take commit 7)))
837 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
839 (file-name (string-append name "-" version "-checkout"))
842 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
843 (build-system cmake-build-system)
845 `(#:parallel-build? #f
846 ;; If out-of-source, test data is not copied into the build directory
847 ;; so the tests fail.
848 #:out-of-source? #f))
850 `(("bpp-core" ,bpp-core)
852 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
855 (home-page "http://biopp.univ-montp2.fr")
856 (synopsis "Bio++ phylogenetic Library")
858 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
859 analysis, phylogenetics, molecular evolution and population genetics. This
860 library provides phylogenetics-related modules.")
861 (license license:cecill-c))))
863 (define-public bpp-popgen
864 ;; The last release was in 2014 and the recommended way to install from source
865 ;; is to clone the git repository, so we do this.
866 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
867 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
870 (version (string-append "2.2.0-1." (string-take commit 7)))
874 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
876 (file-name (string-append name "-" version "-checkout"))
879 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
880 (build-system cmake-build-system)
882 `(#:parallel-build? #f
883 #:tests? #f)) ; There are no tests.
885 `(("bpp-core" ,bpp-core)
888 (home-page "http://biopp.univ-montp2.fr")
889 (synopsis "Bio++ population genetics library")
891 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
892 analysis, phylogenetics, molecular evolution and population genetics. This
893 library provides population genetics-related modules.")
894 (license license:cecill-c))))
896 (define-public bpp-seq
897 ;; The last release was in 2014 and the recommended way to install from source
898 ;; is to clone the git repository, so we do this.
899 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
900 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
903 (version (string-append "2.2.0-1." (string-take commit 7)))
907 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
909 (file-name (string-append name "-" version "-checkout"))
912 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
913 (build-system cmake-build-system)
915 `(#:parallel-build? #f
916 ;; If out-of-source, test data is not copied into the build directory
917 ;; so the tests fail.
918 #:out-of-source? #f))
920 `(("bpp-core" ,bpp-core)
921 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
922 (home-page "http://biopp.univ-montp2.fr")
923 (synopsis "Bio++ sequence library")
925 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
926 analysis, phylogenetics, molecular evolution and population genetics. This
927 library provides sequence-related modules.")
928 (license license:cecill-c))))
930 (define-public bppsuite
931 ;; The last release was in 2014 and the recommended way to install from source
932 ;; is to clone the git repository, so we do this.
933 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
934 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
937 (version (string-append "2.2.0-1." (string-take commit 7)))
941 (url "http://biopp.univ-montp2.fr/git/bppsuite")
943 (file-name (string-append name "-" version "-checkout"))
946 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
947 (build-system cmake-build-system)
949 `(#:parallel-build? #f
950 #:tests? #f)) ; There are no tests.
954 ("texinfo" ,texinfo)))
956 `(("bpp-core" ,bpp-core)
958 ("bpp-phyl" ,bpp-phyl)
959 ("bpp-phyl" ,bpp-popgen)
961 (home-page "http://biopp.univ-montp2.fr")
962 (synopsis "Bioinformatics tools written with the Bio++ libraries")
964 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
965 analysis, phylogenetics, molecular evolution and population genetics. This
966 package provides command line tools using the Bio++ library.")
967 (license license:cecill-c))))
969 (define-public blast+
976 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
977 version "/ncbi-blast-" version "+-src.tar.gz"))
980 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
981 (patches (search-patches "blast+-fix-makefile.patch"))
982 (modules '((guix build utils)))
985 ;; Remove bundled bzip2, zlib and pcre.
986 (delete-file-recursively "c++/src/util/compress/bzip2")
987 (delete-file-recursively "c++/src/util/compress/zlib")
988 (delete-file-recursively "c++/src/util/regexp")
989 (substitute* "c++/src/util/compress/Makefile.in"
990 (("bzip2 zlib api") "api"))
991 ;; Remove useless msbuild directory
992 (delete-file-recursively
993 "c++/src/build-system/project_tree_builder/msbuild")
995 (build-system gnu-build-system)
997 `(;; There are two(!) tests for this massive library, and both fail with
998 ;; "unparsable timing stats".
999 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1000 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1003 #:parallel-build? #f ; not supported
1005 (modify-phases %standard-phases
1007 'configure 'set-HOME
1008 ;; $HOME needs to be set at some point during the configure phase
1009 (lambda _ (setenv "HOME" "/tmp") #t))
1012 (lambda _ (chdir "c++") #t))
1014 'enter-dir 'fix-build-system
1016 (define (which* cmd)
1017 (cond ((string=? cmd "date")
1018 ;; make call to "date" deterministic
1023 (format (current-error-port)
1024 "WARNING: Unable to find absolute path for ~s~%"
1028 ;; Rewrite hardcoded paths to various tools
1029 (substitute* (append '("src/build-system/configure.ac"
1030 "src/build-system/configure"
1031 "src/build-system/helpers/run_with_lock.c"
1032 "scripts/common/impl/if_diff.sh"
1033 "scripts/common/impl/run_with_lock.sh"
1034 "src/build-system/Makefile.configurables.real"
1035 "src/build-system/Makefile.in.top"
1036 "src/build-system/Makefile.meta.gmake=no"
1037 "src/build-system/Makefile.meta.in"
1038 "src/build-system/Makefile.meta_l"
1039 "src/build-system/Makefile.meta_p"
1040 "src/build-system/Makefile.meta_r"
1041 "src/build-system/Makefile.mk.in"
1042 "src/build-system/Makefile.requirements"
1043 "src/build-system/Makefile.rules_with_autodep.in")
1044 (find-files "scripts/common/check" "\\.sh$"))
1045 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1046 (or (which* cmd) all)))
1048 (substitute* (find-files "src/build-system" "^config.*")
1049 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1052 ;; rewrite "/var/tmp" in check script
1053 (substitute* "scripts/common/check/check_make_unix.sh"
1054 (("/var/tmp") "/tmp"))
1056 ;; do not reset PATH
1057 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1059 (("action=/bin/") "action=")
1060 (("export PATH") ":"))
1064 (lambda* (#:key inputs outputs #:allow-other-keys)
1065 (let ((out (assoc-ref outputs "out"))
1066 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1067 (include (string-append (assoc-ref outputs "include")
1068 "/include/ncbi-tools++")))
1069 ;; The 'configure' script doesn't recognize things like
1070 ;; '--enable-fast-install'.
1071 (zero? (system* "./configure.orig"
1072 (string-append "--with-build-root=" (getcwd) "/build")
1073 (string-append "--prefix=" out)
1074 (string-append "--libdir=" lib)
1075 (string-append "--includedir=" include)
1076 (string-append "--with-bz2="
1077 (assoc-ref inputs "bzip2"))
1078 (string-append "--with-z="
1079 (assoc-ref inputs "zlib"))
1080 (string-append "--with-pcre="
1081 (assoc-ref inputs "pcre"))
1082 ;; Each library is built twice by default, once
1083 ;; with "-static" in its name, and again
1086 "--with-dll"))))))))
1087 (outputs '("out" ; 21 MB
1095 ("python" ,python-wrapper)))
1098 (home-page "http://blast.ncbi.nlm.nih.gov")
1099 (synopsis "Basic local alignment search tool")
1101 "BLAST is a popular method of performing a DNA or protein sequence
1102 similarity search, using heuristics to produce results quickly. It also
1103 calculates an “expect value” that estimates how many matches would have
1104 occurred at a given score by chance, which can aid a user in judging how much
1105 confidence to have in an alignment.")
1106 ;; Most of the sources are in the public domain, with the following
1109 ;; * ./c++/include/util/bitset/
1110 ;; * ./c++/src/html/ncbi_menu*.js
1112 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1114 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1116 ;; * ./c++/src/corelib/teamcity_*
1117 (license (list license:public-domain
1123 (define-public bless
1129 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1133 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1134 (modules '((guix build utils)))
1137 ;; Remove bundled boost, pigz, zlib, and .git directory
1138 ;; FIXME: also remove bundled sources for murmurhash3 and
1139 ;; kmc once packaged.
1140 (delete-file-recursively "boost")
1141 (delete-file-recursively "pigz")
1142 (delete-file-recursively "google-sparsehash")
1143 (delete-file-recursively "zlib")
1144 (delete-file-recursively ".git")
1146 (build-system gnu-build-system)
1148 '(#:tests? #f ;no "check" target
1150 (list (string-append "ZLIB="
1151 (assoc-ref %build-inputs "zlib")
1153 (string-append "LDFLAGS="
1154 (string-join '("-lboost_filesystem"
1161 (modify-phases %standard-phases
1162 (add-after 'unpack 'do-not-build-bundled-pigz
1163 (lambda* (#:key inputs outputs #:allow-other-keys)
1164 (substitute* "Makefile"
1165 (("cd pigz/pigz-2.3.3; make") ""))
1167 (add-after 'unpack 'patch-paths-to-executables
1168 (lambda* (#:key inputs outputs #:allow-other-keys)
1169 (substitute* "parse_args.cpp"
1170 (("kmc_binary = .*")
1171 (string-append "kmc_binary = \""
1172 (assoc-ref outputs "out")
1174 (("pigz_binary = .*")
1175 (string-append "pigz_binary = \""
1176 (assoc-ref inputs "pigz")
1180 (lambda* (#:key outputs #:allow-other-keys)
1181 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1182 (for-each (lambda (file)
1183 (install-file file bin))
1184 '("bless" "kmc/bin/kmc"))
1186 (delete 'configure))))
1190 `(("openmpi" ,openmpi)
1192 ("sparsehash" ,sparsehash)
1195 (supported-systems '("x86_64-linux"))
1196 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1197 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1199 "@dfn{Bloom-filter-based error correction solution for high-throughput
1200 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1201 correction tool for genomic reads produced by @dfn{Next-generation
1202 sequencing} (NGS). BLESS produces accurate correction results with much less
1203 memory compared with previous solutions and is also able to tolerate a higher
1204 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1205 errors at the end of reads.")
1206 (license license:gpl3+)))
1208 (define-public bowtie
1214 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1216 (file-name (string-append name "-" version ".tar.gz"))
1219 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1220 (modules '((guix build utils)))
1223 (substitute* "Makefile"
1224 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1225 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1226 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1228 (build-system gnu-build-system)
1231 ("perl-clone" ,perl-clone)
1232 ("perl-test-deep" ,perl-test-deep)
1233 ("perl-test-simple" ,perl-test-simple)
1234 ("python" ,python-2)
1241 (string-append "prefix=" (assoc-ref %outputs "out")))
1243 (modify-phases %standard-phases
1246 (lambda* (#:key outputs #:allow-other-keys)
1247 (zero? (system* "perl"
1248 "scripts/test/simple_tests.pl"
1249 "--bowtie2=./bowtie2"
1250 "--bowtie2-build=./bowtie2-build")))))))
1251 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1252 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1254 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1255 reads to long reference sequences. It is particularly good at aligning reads
1256 of about 50 up to 100s or 1,000s of characters, and particularly good at
1257 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1258 genome with an FM Index to keep its memory footprint small: for the human
1259 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1260 gapped, local, and paired-end alignment modes.")
1261 (supported-systems '("x86_64-linux"))
1262 (license license:gpl3+)))
1264 (define-public tophat
1271 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1275 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1276 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1277 (modules '((guix build utils)))
1280 ;; Remove bundled SeqAn and samtools
1281 (delete-file-recursively "src/SeqAn-1.3")
1282 (delete-file-recursively "src/samtools-0.1.18")
1284 (build-system gnu-build-system)
1286 '(#:parallel-build? #f ; not supported
1288 (modify-phases %standard-phases
1289 (add-after 'unpack 'use-system-samtools
1290 (lambda* (#:key inputs #:allow-other-keys)
1291 (substitute* "src/Makefile.in"
1292 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1293 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1294 (("SAMPROG = samtools_0\\.1\\.18") "")
1295 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1296 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1297 (substitute* '("src/common.cpp"
1299 (("samtools_0.1.18") (which "samtools")))
1300 (substitute* '("src/common.h"
1301 "src/bam2fastx.cpp")
1302 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1303 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1304 (substitute* '("src/bwt_map.h"
1306 "src/align_status.h")
1307 (("#include <bam.h>") "#include <samtools/bam.h>")
1308 (("#include <sam.h>") "#include <samtools/sam.h>"))
1313 ("samtools" ,samtools-0.1)
1314 ("ncurses" ,ncurses)
1315 ("python" ,python-2)
1319 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1320 (synopsis "Spliced read mapper for RNA-Seq data")
1322 "TopHat is a fast splice junction mapper for nucleotide sequence
1323 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1324 mammalian-sized genomes using the ultra high-throughput short read
1325 aligner Bowtie, and then analyzes the mapping results to identify
1326 splice junctions between exons.")
1327 ;; TopHat is released under the Boost Software License, Version 1.0
1328 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1329 (license license:boost1.0)))
1338 "https://github.com/lh3/bwa/releases/download/v"
1339 version "/bwa-" version ".tar.bz2"))
1342 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1343 (build-system gnu-build-system)
1345 '(#:tests? #f ;no "check" target
1347 (modify-phases %standard-phases
1349 (lambda* (#:key outputs #:allow-other-keys)
1350 (let ((bin (string-append
1351 (assoc-ref outputs "out") "/bin"))
1353 (assoc-ref outputs "out") "/share/doc/bwa"))
1355 (assoc-ref outputs "out") "/share/man/man1")))
1356 (install-file "bwa" bin)
1357 (install-file "README.md" doc)
1358 (install-file "bwa.1" man))
1360 ;; no "configure" script
1361 (delete 'configure))))
1362 (inputs `(("zlib" ,zlib)))
1363 ;; Non-portable SSE instructions are used so building fails on platforms
1364 ;; other than x86_64.
1365 (supported-systems '("x86_64-linux"))
1366 (home-page "http://bio-bwa.sourceforge.net/")
1367 (synopsis "Burrows-Wheeler sequence aligner")
1369 "BWA is a software package for mapping low-divergent sequences against a
1370 large reference genome, such as the human genome. It consists of three
1371 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1372 designed for Illumina sequence reads up to 100bp, while the rest two for
1373 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1374 features such as long-read support and split alignment, but BWA-MEM, which is
1375 the latest, is generally recommended for high-quality queries as it is faster
1376 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1377 70-100bp Illumina reads.")
1378 (license license:gpl3+)))
1380 (define-public bwa-pssm
1381 (package (inherit bwa)
1386 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1387 "archive/" version ".tar.gz"))
1388 (file-name (string-append name "-" version ".tar.gz"))
1391 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1392 (build-system gnu-build-system)
1397 (home-page "http://bwa-pssm.binf.ku.dk/")
1398 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1400 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1401 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1402 existing aligners it is fast and sensitive. Unlike most other aligners,
1403 however, it is also adaptible in the sense that one can direct the alignment
1404 based on known biases within the data set. It is coded as a modification of
1405 the original BWA alignment program and shares the genome index structure as
1406 well as many of the command line options.")
1407 (license license:gpl3+)))
1409 (define-public python2-bx-python
1411 (name "python2-bx-python")
1415 (uri (pypi-uri "bx-python" version))
1418 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1419 (modules '((guix build utils)))
1422 (substitute* "setup.py"
1423 ;; remove dependency on outdated "distribute" module
1424 (("^from distribute_setup import use_setuptools") "")
1425 (("^use_setuptools\\(\\)") ""))
1427 (build-system python-build-system)
1429 `(#:tests? #f ;tests fail because test data are not included
1430 #:python ,python-2))
1432 `(("python-numpy" ,python2-numpy)
1435 `(("python-nose" ,python2-nose)))
1436 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1437 (synopsis "Tools for manipulating biological data")
1439 "bx-python provides tools for manipulating biological data, particularly
1440 multiple sequence alignments.")
1441 (license license:expat)))
1443 (define-public python-pysam
1445 (name "python-pysam")
1449 ;; Test data is missing on PyPi.
1451 "https://github.com/pysam-developers/pysam/archive/v"
1453 (file-name (string-append name "-" version ".tar.gz"))
1456 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1457 (modules '((guix build utils)))
1459 ;; Drop bundled htslib. TODO: Also remove samtools
1461 (delete-file-recursively "htslib")
1463 (build-system python-build-system)
1465 `(#:modules ((ice-9 ftw)
1467 (guix build python-build-system)
1470 (modify-phases %standard-phases
1471 (add-before 'build 'set-flags
1472 (lambda* (#:key inputs #:allow-other-keys)
1473 (setenv "HTSLIB_MODE" "external")
1474 (setenv "HTSLIB_LIBRARY_DIR"
1475 (string-append (assoc-ref inputs "htslib") "/lib"))
1476 (setenv "HTSLIB_INCLUDE_DIR"
1477 (string-append (assoc-ref inputs "htslib") "/include"))
1478 (setenv "LDFLAGS" "-lncurses")
1479 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1482 (lambda* (#:key inputs outputs #:allow-other-keys)
1483 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1484 (setenv "PYTHONPATH"
1486 (getenv "PYTHONPATH")
1487 ":" (getcwd) "/build/"
1488 (car (scandir "build"
1489 (negate (cut string-prefix? "." <>))))))
1490 ;; Step out of source dir so python does not import from CWD.
1491 (with-directory-excursion "tests"
1492 (setenv "HOME" "/tmp")
1493 (and (zero? (system* "make" "-C" "pysam_data"))
1494 (zero? (system* "make" "-C" "cbcf_data"))
1495 ;; Running nosetests without explicitly asking for a
1496 ;; single process leads to a crash. Running with multiple
1497 ;; processes fails because the tests are not designed to
1500 ;; FIXME: tests keep timing out on some systems.
1501 ;; (zero? (system* "nosetests" "-v"
1502 ;; "--processes" "1"))
1505 `(("htslib" ,htslib))) ; Included from installed header files.
1507 `(("ncurses" ,ncurses)
1510 `(("python-cython" ,python-cython)
1511 ;; Dependencies below are are for tests only.
1512 ("samtools" ,samtools)
1513 ("bcftools" ,bcftools)
1514 ("python-nose" ,python-nose)))
1515 (home-page "https://github.com/pysam-developers/pysam")
1516 (synopsis "Python bindings to the SAMtools C API")
1518 "Pysam is a Python module for reading and manipulating files in the
1519 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1520 also includes an interface for tabix.")
1521 (license license:expat)))
1523 (define-public python2-pysam
1524 (package-with-python2 python-pysam))
1526 (define-public python-twobitreader
1528 (name "python-twobitreader")
1532 (uri (pypi-uri "twobitreader" version))
1535 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1536 (build-system python-build-system)
1538 '(;; Tests are not distributed in the PyPi release.
1539 ;; TODO Try building from the Git repo or asking the upstream maintainer
1540 ;; to distribute the tests on PyPi.
1543 `(("python-sphinx" ,python-sphinx)))
1544 (home-page "https://github.com/benjschiller/twobitreader")
1545 (synopsis "Python library for reading .2bit files")
1547 "twobitreader is a Python library for reading .2bit files as used by the
1548 UCSC genome browser.")
1549 (license license:artistic2.0)))
1551 (define-public python2-twobitreader
1552 (package-with-python2 python-twobitreader))
1554 (define-public python-plastid
1556 (name "python-plastid")
1560 (uri (pypi-uri "plastid" version))
1563 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1564 (build-system python-build-system)
1566 ;; Some test files are not included.
1569 `(("python-numpy" ,python-numpy)
1570 ("python-scipy" ,python-scipy)
1571 ("python-pandas" ,python-pandas)
1572 ("python-pysam" ,python-pysam)
1573 ("python-matplotlib" ,python-matplotlib)
1574 ("python-biopython" ,python-biopython)
1575 ("python-twobitreader" ,python-twobitreader)
1576 ("python-termcolor" ,python-termcolor)))
1578 `(("python-cython" ,python-cython)
1579 ("python-nose" ,python-nose)))
1580 (home-page "https://github.com/joshuagryphon/plastid")
1581 (synopsis "Python library for genomic analysis")
1583 "plastid is a Python library for genomic analysis – in particular,
1584 high-throughput sequencing data – with an emphasis on simplicity.")
1585 (license license:bsd-3)))
1587 (define-public python2-plastid
1588 (package-with-python2 python-plastid))
1590 (define-public cd-hit
1596 (uri (string-append "https://github.com/weizhongli/cdhit"
1597 "/releases/download/V" version
1599 "-2017-0621-source.tar.gz"))
1602 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1603 (build-system gnu-build-system)
1605 `(#:tests? #f ; there are no tests
1607 ;; Executables are copied directly to the PREFIX.
1608 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1610 (modify-phases %standard-phases
1611 ;; No "configure" script
1613 ;; Remove sources of non-determinism
1614 (add-after 'unpack 'be-timeless
1616 (substitute* "cdhit-utility.c++"
1617 ((" \\(built on \" __DATE__ \"\\)") ""))
1618 (substitute* "cdhit-common.c++"
1619 (("__DATE__") "\"0\"")
1620 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1622 ;; The "install" target does not create the target directory.
1623 (add-before 'install 'create-target-dir
1624 (lambda* (#:key outputs #:allow-other-keys)
1625 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1629 (home-page "http://weizhongli-lab.org/cd-hit/")
1630 (synopsis "Cluster and compare protein or nucleotide sequences")
1632 "CD-HIT is a program for clustering and comparing protein or nucleotide
1633 sequences. CD-HIT is designed to be fast and handle extremely large
1635 ;; The manual says: "It can be copied under the GNU General Public License
1636 ;; version 2 (GPLv2)."
1637 (license license:gpl2)))
1639 (define-public clipper
1646 "https://github.com/YeoLab/clipper/archive/"
1648 (file-name (string-append name "-" version ".tar.gz"))
1651 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1652 (modules '((guix build utils)))
1655 ;; remove unnecessary setup dependency
1656 (substitute* "setup.py"
1657 (("setup_requires = .*") ""))
1658 (for-each delete-file
1659 '("clipper/src/peaks.so"
1660 "clipper/src/readsToWiggle.so"))
1661 (delete-file-recursively "dist/")
1663 (build-system python-build-system)
1664 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1666 `(("htseq" ,python2-htseq)
1667 ("python-pybedtools" ,python2-pybedtools)
1668 ("python-cython" ,python2-cython)
1669 ("python-scikit-learn" ,python2-scikit-learn)
1670 ("python-matplotlib" ,python2-matplotlib)
1671 ("python-pandas" ,python2-pandas)
1672 ("python-pysam" ,python2-pysam)
1673 ("python-numpy" ,python2-numpy)
1674 ("python-scipy" ,python2-scipy)))
1676 `(("python-mock" ,python2-mock) ; for tests
1677 ("python-nose" ,python2-nose) ; for tests
1678 ("python-pytz" ,python2-pytz))) ; for tests
1679 (home-page "https://github.com/YeoLab/clipper")
1680 (synopsis "CLIP peak enrichment recognition")
1682 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1683 (license license:gpl2)))
1685 (define-public codingquarry
1687 (name "codingquarry")
1692 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1696 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1697 (build-system gnu-build-system)
1699 '(#:tests? #f ; no "check" target
1701 (modify-phases %standard-phases
1704 (lambda* (#:key outputs #:allow-other-keys)
1705 (let* ((out (assoc-ref outputs "out"))
1706 (bin (string-append out "/bin"))
1707 (doc (string-append out "/share/doc/codingquarry")))
1708 (install-file "INSTRUCTIONS.pdf" doc)
1709 (copy-recursively "QuarryFiles"
1710 (string-append out "/QuarryFiles"))
1711 (install-file "CodingQuarry" bin)
1712 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1713 (inputs `(("openmpi" ,openmpi)))
1714 (native-search-paths
1715 (list (search-path-specification
1716 (variable "QUARRY_PATH")
1717 (files '("QuarryFiles")))))
1718 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1719 (synopsis "Fungal gene predictor")
1720 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1721 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1722 (home-page "https://sourceforge.net/projects/codingquarry/")
1723 (license license:gpl3+)))
1725 (define-public couger
1732 "http://couger.oit.duke.edu/static/assets/COUGER"
1736 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1737 (build-system gnu-build-system)
1741 (modify-phases %standard-phases
1746 (lambda* (#:key outputs #:allow-other-keys)
1747 (let* ((out (assoc-ref outputs "out"))
1748 (bin (string-append out "/bin")))
1749 (copy-recursively "src" (string-append out "/src"))
1751 ;; Add "src" directory to module lookup path.
1752 (substitute* "couger"
1754 (string-append "import sys\nsys.path.append(\""
1755 out "\")\nfrom argparse")))
1756 (install-file "couger" bin))
1759 'install 'wrap-program
1760 (lambda* (#:key inputs outputs #:allow-other-keys)
1761 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1762 (let* ((out (assoc-ref outputs "out"))
1763 (path (getenv "PYTHONPATH")))
1764 (wrap-program (string-append out "/bin/couger")
1765 `("PYTHONPATH" ":" prefix (,path))))
1768 `(("python" ,python-2)
1769 ("python2-pillow" ,python2-pillow)
1770 ("python2-numpy" ,python2-numpy)
1771 ("python2-scipy" ,python2-scipy)
1772 ("python2-matplotlib" ,python2-matplotlib)))
1774 `(("r-minimal" ,r-minimal)
1776 ("randomjungle" ,randomjungle)))
1778 `(("unzip" ,unzip)))
1779 (home-page "http://couger.oit.duke.edu")
1780 (synopsis "Identify co-factors in sets of genomic regions")
1782 "COUGER can be applied to any two sets of genomic regions bound by
1783 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1784 putative co-factors that provide specificity to each TF. The framework
1785 determines the genomic targets uniquely-bound by each TF, and identifies a
1786 small set of co-factors that best explain the in vivo binding differences
1787 between the two TFs.
1789 COUGER uses classification algorithms (support vector machines and random
1790 forests) with features that reflect the DNA binding specificities of putative
1791 co-factors. The features are generated either from high-throughput TF-DNA
1792 binding data (from protein binding microarray experiments), or from large
1793 collections of DNA motifs.")
1794 (license license:gpl3+)))
1796 (define-public clustal-omega
1798 (name "clustal-omega")
1802 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1806 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1807 (build-system gnu-build-system)
1809 `(("argtable" ,argtable)))
1810 (home-page "http://www.clustal.org/omega/")
1811 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1813 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1814 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1815 of handling data-sets of hundreds of thousands of sequences in reasonable
1817 (license license:gpl2+)))
1819 (define-public crossmap
1825 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1829 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1830 ;; This patch has been sent upstream already and is available
1831 ;; for download from Sourceforge, but it has not been merged.
1832 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1833 (modules '((guix build utils)))
1835 ;; remove bundled copy of pysam
1836 (delete-file-recursively "lib/pysam")
1838 (build-system python-build-system)
1840 `(#:python ,python-2
1842 (modify-phases %standard-phases
1843 (add-after 'unpack 'set-env
1844 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1846 `(("python-numpy" ,python2-numpy)
1847 ("python-pysam" ,python2-pysam)
1850 `(("python-cython" ,python2-cython)
1851 ("python-nose" ,python2-nose)))
1852 (home-page "http://crossmap.sourceforge.net/")
1853 (synopsis "Convert genome coordinates between assemblies")
1855 "CrossMap is a program for conversion of genome coordinates or annotation
1856 files between different genome assemblies. It supports most commonly used
1857 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1858 (license license:gpl2+)))
1860 (define-public cutadapt
1867 (url "https://github.com/marcelm/cutadapt.git")
1868 (commit (string-append "v" version))))
1869 (file-name (string-append name "-" version "-checkout"))
1872 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1873 (build-system python-build-system)
1875 `(("python-xopen" ,python-xopen)))
1877 `(("python-cython" ,python-cython)
1878 ("python-pytest" ,python-pytest)))
1879 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1880 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1882 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1883 other types of unwanted sequence from high-throughput sequencing reads.")
1884 (license license:expat)))
1886 (define-public libbigwig
1892 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1893 "archive/" version ".tar.gz"))
1894 (file-name (string-append name "-" version ".tar.gz"))
1897 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1898 (build-system gnu-build-system)
1900 `(#:test-target "test"
1903 (string-append "prefix=" (assoc-ref %outputs "out")))
1905 (modify-phases %standard-phases
1907 (add-before 'check 'disable-curl-test
1909 (substitute* "Makefile"
1910 (("./test/testRemote.*") ""))
1912 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1913 ;; there has not yet been a release containing this change.
1914 (add-before 'install 'create-target-dirs
1915 (lambda* (#:key outputs #:allow-other-keys)
1916 (let ((out (assoc-ref outputs "out")))
1917 (mkdir-p (string-append out "/lib"))
1918 (mkdir-p (string-append out "/include"))
1924 `(("doxygen" ,doxygen)))
1925 (home-page "https://github.com/dpryan79/libBigWig")
1926 (synopsis "C library for handling bigWig files")
1928 "This package provides a C library for parsing local and remote BigWig
1930 (license license:expat)))
1932 (define-public python-pybigwig
1934 (name "python-pybigwig")
1938 (uri (pypi-uri "pyBigWig" version))
1941 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1942 (modules '((guix build utils)))
1945 ;; Delete bundled libBigWig sources
1946 (delete-file-recursively "libBigWig")
1948 (build-system python-build-system)
1951 (modify-phases %standard-phases
1952 (add-after 'unpack 'link-with-libBigWig
1953 (lambda* (#:key inputs #:allow-other-keys)
1954 (substitute* "setup.py"
1955 (("libs=\\[") "libs=[\"BigWig\", "))
1958 `(("libbigwig" ,libbigwig)
1961 (home-page "https://github.com/dpryan79/pyBigWig")
1962 (synopsis "Access bigWig files in Python using libBigWig")
1964 "This package provides Python bindings to the libBigWig library for
1965 accessing bigWig files.")
1966 (license license:expat)))
1968 (define-public python2-pybigwig
1969 (package-with-python2 python-pybigwig))
1971 (define-public python-dendropy
1973 (name "python-dendropy")
1978 ;; Source from GitHub so that tests are included.
1980 (string-append "https://github.com/jeetsukumaran/DendroPy/archive/v"
1982 (file-name (string-append name "-" version ".tar.gz"))
1985 "0v2fccny5xjaah546bsch1mw4kh61qq5frz2ibllxs9mp6ih9bsn"))))
1986 (build-system python-build-system)
1987 (home-page "http://packages.python.org/DendroPy/")
1988 (synopsis "Library for phylogenetics and phylogenetic computing")
1990 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1991 writing, simulation, processing and manipulation of phylogenetic
1992 trees (phylogenies) and characters.")
1993 (license license:bsd-3)))
1995 (define-public python2-dendropy
1996 (package-with-python2 python-dendropy))
1998 (define-public python-py2bit
2000 (name "python-py2bit")
2005 (uri (pypi-uri "py2bit" version))
2008 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2009 (build-system python-build-system)
2010 (home-page "https://github.com/dpryan79/py2bit")
2011 (synopsis "Access 2bit files using lib2bit")
2013 "This package provides Python bindings for lib2bit to access 2bit files
2015 (license license:expat)))
2017 (define-public deeptools
2023 (uri (string-append "https://github.com/deeptools/deepTools/"
2024 "archive/" version ".tar.gz"))
2025 (file-name (string-append name "-" version ".tar.gz"))
2028 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2029 (build-system python-build-system)
2031 `(("python-scipy" ,python-scipy)
2032 ("python-numpy" ,python-numpy)
2033 ("python-numpydoc" ,python-numpydoc)
2034 ("python-matplotlib" ,python-matplotlib)
2035 ("python-pysam" ,python-pysam)
2036 ("python-py2bit" ,python-py2bit)
2037 ("python-pybigwig" ,python-pybigwig)))
2039 `(("python-mock" ,python-mock) ;for tests
2040 ("python-nose" ,python-nose) ;for tests
2041 ("python-pytz" ,python-pytz))) ;for tests
2042 (home-page "https://github.com/deeptools/deepTools")
2043 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2045 "DeepTools addresses the challenge of handling the large amounts of data
2046 that are now routinely generated from DNA sequencing centers. To do so,
2047 deepTools contains useful modules to process the mapped reads data to create
2048 coverage files in standard bedGraph and bigWig file formats. By doing so,
2049 deepTools allows the creation of normalized coverage files or the comparison
2050 between two files (for example, treatment and control). Finally, using such
2051 normalized and standardized files, multiple visualizations can be created to
2052 identify enrichments with functional annotations of the genome.")
2053 (license license:gpl3+)))
2055 (define-public delly
2062 "https://github.com/tobiasrausch/delly/archive/v"
2064 (file-name (string-append name "-" version ".tar.gz"))
2066 (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj"))
2067 (patches (search-patches "delly-use-system-libraries.patch"))))
2068 (build-system gnu-build-system)
2070 `(#:tests? #f ; There are no tests to run.
2071 #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time.
2073 (modify-phases %standard-phases
2074 (delete 'configure) ; There is no configure phase.
2077 (let ((bin (string-append (assoc-ref %outputs "out") "/bin"))
2078 (templates (string-append (assoc-ref %outputs "out")
2079 "/share/delly/templates")))
2082 (copy-recursively "excludeTemplates" templates)
2083 (install-file "src/cov" bin)
2084 (install-file "src/delly" bin)
2085 (install-file "src/dpe" bin)))))))
2087 `(("python" ,python-2)))
2093 (home-page "https://github.com/tobiasrausch/delly")
2094 (synopsis "Integrated structural variant prediction method")
2095 (description "Delly is an integrated structural variant prediction method
2096 that can discover and genotype deletions, tandem duplications, inversions and
2097 translocations at single-nucleotide resolution in short-read massively parallel
2098 sequencing data. It uses paired-ends and split-reads to sensitively and
2099 accurately delineate genomic rearrangements throughout the genome.")
2100 (license license:gpl3+)))
2102 (define-public diamond
2109 "https://github.com/bbuchfink/diamond/archive/v"
2111 (file-name (string-append name "-" version ".tar.gz"))
2114 "0adp87r9ak63frdrdmrdfhsn6g0jnnyq1lr2wibvqbxcl37iir9m"))))
2115 (build-system cmake-build-system)
2117 '(#:tests? #f ; no "check" target
2119 (modify-phases %standard-phases
2120 (add-after 'unpack 'remove-native-compilation
2122 (substitute* "CMakeLists.txt" (("-march=native") ""))
2126 (home-page "https://github.com/bbuchfink/diamond")
2127 (synopsis "Accelerated BLAST compatible local sequence aligner")
2129 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2130 translated DNA query sequences against a protein reference database (BLASTP
2131 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2132 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2133 data and settings.")
2134 (license license:agpl3+)))
2136 (define-public discrover
2143 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2145 (file-name (string-append name "-" version ".tar.gz"))
2148 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2149 (build-system cmake-build-system)
2151 `(#:tests? #f ; there are no tests
2153 (modify-phases %standard-phases
2154 (add-after 'unpack 'add-missing-includes
2156 (substitute* "src/executioninformation.hpp"
2157 (("#define EXECUTIONINFORMATION_HPP" line)
2158 (string-append line "\n#include <random>")))
2159 (substitute* "src/plasma/fasta.hpp"
2160 (("#define FASTA_HPP" line)
2161 (string-append line "\n#include <random>")))
2167 `(("texlive" ,texlive)
2168 ("imagemagick" ,imagemagick)))
2169 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2170 (synopsis "Discover discriminative nucleotide sequence motifs")
2171 (description "Discrover is a motif discovery method to find binding sites
2172 of nucleic acid binding proteins.")
2173 (license license:gpl3+)))
2175 (define-public eigensoft
2176 (let ((revision "1")
2177 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2180 (version (string-append "6.1.2-"
2182 (string-take commit 9)))
2187 (url "https://github.com/DReichLab/EIG.git")
2189 (file-name (string-append "eigensoft-" commit "-checkout"))
2192 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2193 (modules '((guix build utils)))
2194 ;; Remove pre-built binaries.
2196 (delete-file-recursively "bin")
2199 (build-system gnu-build-system)
2201 `(#:tests? #f ; There are no tests.
2202 #:make-flags '("CC=gcc")
2204 (modify-phases %standard-phases
2205 ;; There is no configure phase, but the Makefile is in a
2210 ;; The link flags are incomplete.
2211 (substitute* "Makefile"
2212 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2214 ;; The provided install target only copies executables to
2215 ;; the "bin" directory in the build root.
2216 (add-after 'install 'actually-install
2217 (lambda* (#:key outputs #:allow-other-keys)
2218 (let* ((out (assoc-ref outputs "out"))
2219 (bin (string-append out "/bin")))
2220 (for-each (lambda (file)
2221 (install-file file bin))
2222 (find-files "../bin" ".*"))
2227 ("openblas" ,openblas)
2229 ("gfortran" ,gfortran "lib")))
2230 (home-page "https://github.com/DReichLab/EIG")
2231 (synopsis "Tools for population genetics")
2232 (description "The EIGENSOFT package provides tools for population
2233 genetics and stratification correction. EIGENSOFT implements methods commonly
2234 used in population genetics analyses such as PCA, computation of Tracy-Widom
2235 statistics, and finding related individuals in structured populations. It
2236 comes with a built-in plotting script and supports multiple file formats and
2237 quantitative phenotypes.")
2238 ;; The license of the eigensoft tools is Expat, but since it's
2239 ;; linking with the GNU Scientific Library (GSL) the effective
2240 ;; license is the GPL.
2241 (license license:gpl3+))))
2243 (define-public edirect
2249 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2250 "versions/2016-05-03/edirect.tar.gz"))
2253 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2254 (build-system perl-build-system)
2256 `(#:tests? #f ;no "check" target
2258 (modify-phases %standard-phases
2262 (lambda* (#:key outputs #:allow-other-keys)
2263 (let ((target (string-append (assoc-ref outputs "out")
2266 (install-file "edirect.pl" target)
2269 'install 'wrap-program
2270 (lambda* (#:key inputs outputs #:allow-other-keys)
2271 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2272 (let* ((out (assoc-ref outputs "out"))
2273 (path (getenv "PERL5LIB")))
2274 (wrap-program (string-append out "/bin/edirect.pl")
2275 `("PERL5LIB" ":" prefix (,path)))))))))
2277 `(("perl-html-parser" ,perl-html-parser)
2278 ("perl-encode-locale" ,perl-encode-locale)
2279 ("perl-file-listing" ,perl-file-listing)
2280 ("perl-html-tagset" ,perl-html-tagset)
2281 ("perl-html-tree" ,perl-html-tree)
2282 ("perl-http-cookies" ,perl-http-cookies)
2283 ("perl-http-date" ,perl-http-date)
2284 ("perl-http-message" ,perl-http-message)
2285 ("perl-http-negotiate" ,perl-http-negotiate)
2286 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2287 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2288 ("perl-net-http" ,perl-net-http)
2289 ("perl-uri" ,perl-uri)
2290 ("perl-www-robotrules" ,perl-www-robotrules)
2292 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2293 (synopsis "Tools for accessing the NCBI's set of databases")
2295 "Entrez Direct (EDirect) is a method for accessing the National Center
2296 for Biotechnology Information's (NCBI) set of interconnected
2297 databases (publication, sequence, structure, gene, variation, expression,
2298 etc.) from a terminal. Functions take search terms from command-line
2299 arguments. Individual operations are combined to build multi-step queries.
2300 Record retrieval and formatting normally complete the process.
2302 EDirect also provides an argument-driven function that simplifies the
2303 extraction of data from document summaries or other results that are returned
2304 in structured XML format. This can eliminate the need for writing custom
2305 software to answer ad hoc questions.")
2306 (license license:public-domain)))
2308 (define-public exonerate
2317 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2318 "exonerate-" version ".tar.gz"))
2321 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2322 (build-system gnu-build-system)
2324 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2326 `(("pkg-config" ,pkg-config)))
2330 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2331 (synopsis "Generic tool for biological sequence alignment")
2333 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2334 the alignment of sequences using a many alignment models, either exhaustive
2335 dynamic programming or a variety of heuristics.")
2336 (license license:gpl3)))
2338 (define-public express
2346 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2347 version "/express-" version "-src.tgz"))
2350 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2351 (build-system cmake-build-system)
2353 `(#:tests? #f ;no "check" target
2355 (modify-phases %standard-phases
2356 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2357 (lambda* (#:key inputs #:allow-other-keys)
2358 (substitute* "CMakeLists.txt"
2359 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2360 "set(Boost_USE_STATIC_LIBS OFF)")
2361 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2362 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2363 (substitute* "src/CMakeLists.txt"
2364 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2365 (string-append (assoc-ref inputs "bamtools") "/lib"))
2366 (("libprotobuf.a") "libprotobuf.so"))
2370 ("bamtools" ,bamtools)
2371 ("protobuf" ,protobuf)
2373 (home-page "http://bio.math.berkeley.edu/eXpress")
2374 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2376 "eXpress is a streaming tool for quantifying the abundances of a set of
2377 target sequences from sampled subsequences. Example applications include
2378 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2379 analysis (from RNA-Seq), transcription factor binding quantification in
2380 ChIP-Seq, and analysis of metagenomic data.")
2381 (license license:artistic2.0)))
2383 (define-public express-beta-diversity
2385 (name "express-beta-diversity")
2391 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2393 (file-name (string-append name "-" version ".tar.gz"))
2396 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2397 (build-system gnu-build-system)
2400 (modify-phases %standard-phases
2402 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2404 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2406 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2408 (lambda* (#:key outputs #:allow-other-keys)
2409 (let ((bin (string-append (assoc-ref outputs "out")
2412 (install-file "scripts/convertToEBD.py" bin)
2413 (install-file "bin/ExpressBetaDiversity" bin)
2416 `(("python" ,python-2)))
2417 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2418 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2420 "Express Beta Diversity (EBD) calculates ecological beta diversity
2421 (dissimilarity) measures between biological communities. EBD implements a
2422 variety of diversity measures including those that make use of phylogenetic
2423 similarity of community members.")
2424 (license license:gpl3+)))
2426 (define-public fasttree
2433 "http://www.microbesonline.org/fasttree/FastTree-"
2437 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2438 (build-system gnu-build-system)
2440 `(#:tests? #f ; no "check" target
2442 (modify-phases %standard-phases
2446 (lambda* (#:key source #:allow-other-keys)
2447 (and (zero? (system* "gcc"
2449 "-finline-functions"
2456 (zero? (system* "gcc"
2460 "-finline-functions"
2468 (lambda* (#:key outputs #:allow-other-keys)
2469 (let ((bin (string-append (assoc-ref outputs "out")
2472 (install-file "FastTree" bin)
2473 (install-file "FastTreeMP" bin)
2475 (home-page "http://www.microbesonline.org/fasttree")
2476 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2478 "FastTree can handle alignments with up to a million of sequences in a
2479 reasonable amount of time and memory. For large alignments, FastTree is
2480 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2481 (license license:gpl2+)))
2483 (define-public fastx-toolkit
2485 (name "fastx-toolkit")
2491 "https://github.com/agordon/fastx_toolkit/releases/download/"
2492 version "/fastx_toolkit-" version ".tar.bz2"))
2495 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2496 (build-system gnu-build-system)
2498 `(("libgtextutils" ,libgtextutils)))
2500 `(("pkg-config" ,pkg-config)))
2501 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2502 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2504 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2505 FASTA/FASTQ files preprocessing.
2507 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2508 containing multiple short-reads sequences. The main processing of such
2509 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2510 is sometimes more productive to preprocess the files before mapping the
2511 sequences to the genome---manipulating the sequences to produce better mapping
2512 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2513 (license license:agpl3+)))
2515 (define-public flexbar
2522 (string-append "mirror://sourceforge/flexbar/"
2523 version "/flexbar_v" version "_src.tgz"))
2526 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2527 (build-system cmake-build-system)
2529 `(#:configure-flags (list
2530 (string-append "-DFLEXBAR_BINARY_DIR="
2531 (assoc-ref %outputs "out")
2534 (modify-phases %standard-phases
2536 (lambda* (#:key outputs #:allow-other-keys)
2537 (setenv "PATH" (string-append
2538 (assoc-ref outputs "out") "/bin:"
2540 (chdir "../flexbar_v2.5_src/test")
2541 (zero? (system* "bash" "flexbar_validate.sh"))))
2542 (delete 'install))))
2547 `(("pkg-config" ,pkg-config)
2549 (home-page "http://flexbar.sourceforge.net")
2550 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2552 "Flexbar preprocesses high-throughput nucleotide sequencing data
2553 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2554 Moreover, trimming and filtering features are provided. Flexbar increases
2555 read mapping rates and improves genome and transcriptome assemblies. It
2556 supports next-generation sequencing data in fasta/q and csfasta/q format from
2557 Illumina, Roche 454, and the SOLiD platform.")
2558 (license license:gpl3)))
2560 (define-public fraggenescan
2562 (name "fraggenescan")
2568 (string-append "mirror://sourceforge/fraggenescan/"
2569 "FragGeneScan" version ".tar.gz"))
2571 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2572 (build-system gnu-build-system)
2575 (modify-phases %standard-phases
2577 (add-before 'build 'patch-paths
2578 (lambda* (#:key outputs #:allow-other-keys)
2579 (let* ((out (string-append (assoc-ref outputs "out")))
2580 (share (string-append out "/share/fraggenescan/")))
2581 (substitute* "run_FragGeneScan.pl"
2583 (string-append "system(\"" (which "rm")))
2585 (string-append "system(\"" (which "mv")))
2586 (("\\\"awk") (string-append "\"" (which "awk")))
2587 ;; This script and other programs expect the training files
2588 ;; to be in the non-standard location bin/train/XXX. Change
2589 ;; this to be share/fraggenescan/train/XXX instead.
2590 (("^\\$train.file = \\$dir.*")
2591 (string-append "$train_file = \""
2593 "train/\".$FGS_train_file;")))
2594 (substitute* "run_hmm.c"
2595 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2596 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2599 (lambda _ (and (zero? (system* "make" "clean"))
2600 (zero? (system* "make" "fgs")))))
2602 (lambda* (#:key outputs #:allow-other-keys)
2603 (let* ((out (string-append (assoc-ref outputs "out")))
2604 (bin (string-append out "/bin/"))
2605 (share (string-append out "/share/fraggenescan/train")))
2606 (install-file "run_FragGeneScan.pl" bin)
2607 (install-file "FragGeneScan" bin)
2608 (copy-recursively "train" share))))
2610 (add-after 'install 'post-install-check
2611 ;; In lieu of 'make check', run one of the examples and check the
2612 ;; output files gets created.
2613 (lambda* (#:key outputs #:allow-other-keys)
2614 (let* ((out (string-append (assoc-ref outputs "out")))
2615 (bin (string-append out "/bin/"))
2616 (frag (string-append bin "run_FragGeneScan.pl")))
2617 (and (zero? (system* frag ; Test complete genome.
2618 "-genome=./example/NC_000913.fna"
2622 (file-exists? "test2.faa")
2623 (file-exists? "test2.ffn")
2624 (file-exists? "test2.gff")
2625 (file-exists? "test2.out")
2626 (zero? (system* ; Test incomplete sequences.
2628 "-genome=./example/NC_000913-fgs.ffn"
2631 "-train=454_30")))))))))
2634 ("python" ,python-2))) ;not compatible with python 3.
2635 (home-page "https://sourceforge.net/projects/fraggenescan/")
2636 (synopsis "Finds potentially fragmented genes in short reads")
2638 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2639 short and error-prone DNA sequencing reads. It can also be applied to predict
2640 genes in incomplete assemblies or complete genomes.")
2641 ;; GPL3+ according to private correspondense with the authors.
2642 (license license:gpl3+)))
2644 (define-public fxtract
2645 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2653 "https://github.com/ctSkennerton/fxtract/archive/"
2655 (file-name (string-append "ctstennerton-util-"
2656 (string-take util-commit 7)
2660 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2661 (build-system gnu-build-system)
2663 `(#:make-flags (list
2664 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2666 #:test-target "fxtract_test"
2668 (modify-phases %standard-phases
2670 (add-before 'build 'copy-util
2671 (lambda* (#:key inputs #:allow-other-keys)
2673 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2675 ;; Do not use make install as this requires additional dependencies.
2677 (lambda* (#:key outputs #:allow-other-keys)
2678 (let* ((out (assoc-ref outputs "out"))
2679 (bin (string-append out"/bin")))
2680 (install-file "fxtract" bin)
2686 ;; ctskennerton-util is licensed under GPL2.
2687 `(("ctskennerton-util"
2691 (url "https://github.com/ctSkennerton/util.git")
2692 (commit util-commit)))
2693 (file-name (string-append
2694 "ctstennerton-util-" util-commit "-checkout"))
2697 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2698 (home-page "https://github.com/ctSkennerton/fxtract")
2699 (synopsis "Extract sequences from FASTA and FASTQ files")
2701 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2702 or FASTQ) file given a subsequence. It uses a simple substring search for
2703 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2704 lookups or multi-pattern searching as required. By default fxtract looks in
2705 the sequence of each record but can also be told to look in the header,
2706 comment or quality sections.")
2707 ;; 'util' requires SSE instructions.
2708 (supported-systems '("x86_64-linux"))
2709 (license license:expat))))
2711 (define-public gemma
2717 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2719 (file-name (string-append name "-" version ".tar.gz"))
2722 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2723 (patches (search-patches "gemma-intel-compat.patch"))))
2728 (build-system gnu-build-system)
2731 '(,@(match (%current-system)
2733 '("FORCE_DYNAMIC=1"))
2735 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2737 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2739 (modify-phases %standard-phases
2741 (add-before 'build 'bin-mkdir
2746 (lambda* (#:key outputs #:allow-other-keys)
2747 (let ((out (assoc-ref outputs "out")))
2748 (install-file "bin/gemma"
2752 #:tests? #f)) ; no tests included yet
2753 (home-page "https://github.com/xiangzhou/GEMMA")
2754 (synopsis "Tool for genome-wide efficient mixed model association")
2756 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2757 standard linear mixed model resolver with application in genome-wide
2758 association studies (GWAS).")
2759 (license license:gpl3)))
2768 "https://github.com/nboley/grit/archive/"
2770 (file-name (string-append name "-" version ".tar.gz"))
2773 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2774 (build-system python-build-system)
2776 `(#:python ,python-2
2778 (modify-phases %standard-phases
2779 (add-after 'unpack 'generate-from-cython-sources
2780 (lambda* (#:key inputs outputs #:allow-other-keys)
2781 ;; Delete these C files to force fresh generation from pyx sources.
2782 (delete-file "grit/sparsify_support_fns.c")
2783 (delete-file "grit/call_peaks_support_fns.c")
2784 (substitute* "setup.py"
2785 (("Cython.Setup") "Cython.Build")
2786 ;; Add numpy include path to fix compilation
2788 (string-append "pyx\", ], include_dirs = ['"
2789 (assoc-ref inputs "python-numpy")
2790 "/lib/python2.7/site-packages/numpy/core/include/"
2794 `(("python-scipy" ,python2-scipy)
2795 ("python-numpy" ,python2-numpy)
2796 ("python-pysam" ,python2-pysam)
2797 ("python-networkx" ,python2-networkx)))
2799 `(("python-cython" ,python2-cython)))
2800 (home-page "http://grit-bio.org")
2801 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2803 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2804 full length transcript models. When none of these data sources are available,
2805 GRIT can be run by providing a candidate set of TES or TSS sites. In
2806 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2807 also be run in quantification mode, where it uses a provided GTF file and just
2808 estimates transcript expression.")
2809 (license license:gpl3+)))
2811 (define-public hisat
2818 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2819 version "-beta-source.zip"))
2822 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2823 (build-system gnu-build-system)
2825 `(#:tests? #f ;no check target
2826 #:make-flags '("allall"
2827 ;; Disable unsupported `popcnt' instructions on
2828 ;; architectures other than x86_64
2829 ,@(if (string-prefix? "x86_64"
2830 (or (%current-target-system)
2833 '("POPCNT_CAPABILITY=0")))
2835 (modify-phases %standard-phases
2836 (add-after 'unpack 'patch-sources
2838 ;; XXX Cannot use snippet because zip files are not supported
2839 (substitute* "Makefile"
2840 (("^CC = .*$") "CC = gcc")
2841 (("^CPP = .*$") "CPP = g++")
2842 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2843 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2844 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2845 (substitute* '("hisat-build" "hisat-inspect")
2846 (("/usr/bin/env") (which "env")))
2849 (lambda* (#:key outputs #:allow-other-keys)
2850 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2851 (for-each (lambda (file)
2852 (install-file file bin))
2855 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2857 (delete 'configure))))
2859 `(("unzip" ,unzip)))
2864 ;; Non-portable SSE instructions are used so building fails on platforms
2865 ;; other than x86_64.
2866 (supported-systems '("x86_64-linux"))
2867 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2868 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2870 "HISAT is a fast and sensitive spliced alignment program for mapping
2871 RNA-seq reads. In addition to one global FM index that represents a whole
2872 genome, HISAT uses a large set of small FM indexes that collectively cover the
2873 whole genome. These small indexes (called local indexes) combined with
2874 several alignment strategies enable effective alignment of RNA-seq reads, in
2875 particular, reads spanning multiple exons.")
2876 (license license:gpl3+)))
2878 (define-public hisat2
2885 ;; FIXME: a better source URL is
2886 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2887 ;; "/downloads/hisat2-" version "-source.zip")
2888 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2889 ;; but it is currently unavailable.
2890 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2891 (file-name (string-append name "-" version ".tar.gz"))
2894 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2895 (build-system gnu-build-system)
2897 `(#:tests? #f ; no check target
2898 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2899 #:modules ((guix build gnu-build-system)
2903 (modify-phases %standard-phases
2904 (add-after 'unpack 'make-deterministic
2906 (substitute* "Makefile"
2911 (lambda* (#:key outputs #:allow-other-keys)
2912 (let* ((out (assoc-ref outputs "out"))
2913 (bin (string-append out "/bin/"))
2914 (doc (string-append out "/share/doc/hisat2/")))
2916 (cut install-file <> bin)
2918 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2920 (install-file "doc/manual.inc.html" doc))
2923 `(("unzip" ,unzip) ; needed for archive from ftp
2925 ("pandoc" ,ghc-pandoc))) ; for documentation
2926 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2927 (synopsis "Graph-based alignment of genomic sequencing reads")
2928 (description "HISAT2 is a fast and sensitive alignment program for mapping
2929 next-generation sequencing reads (both DNA and RNA) to a population of human
2930 genomes (as well as to a single reference genome). In addition to using one
2931 global @dfn{graph FM} (GFM) index that represents a population of human
2932 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2933 the whole genome. These small indexes, combined with several alignment
2934 strategies, enable rapid and accurate alignment of sequencing reads. This new
2935 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2936 ;; HISAT2 contains files from Bowtie2, which is released under
2937 ;; GPLv2 or later. The HISAT2 source files are released under
2939 (license license:gpl3+)))
2941 (define-public hmmer
2949 "http://eddylab.org/software/hmmer"
2950 (version-major version) "/"
2951 version "/hmmer-" version ".tar.gz"))
2954 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2955 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2956 (build-system gnu-build-system)
2957 (native-inputs `(("perl" ,perl)))
2958 (home-page "http://hmmer.org/")
2959 (synopsis "Biosequence analysis using profile hidden Markov models")
2961 "HMMER is used for searching sequence databases for homologs of protein
2962 sequences, and for making protein sequence alignments. It implements methods
2963 using probabilistic models called profile hidden Markov models (profile
2965 (license (list license:gpl3+
2966 ;; The bundled library 'easel' is distributed
2967 ;; under The Janelia Farm Software License.
2968 (license:non-copyleft
2969 "file://easel/LICENSE"
2970 "See easel/LICENSE in the distribution.")))))
2972 (define-public htseq
2978 (uri (pypi-uri "HTSeq" version))
2981 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2982 (build-system python-build-system)
2984 `(("python-cython" ,python-cython)))
2985 ;; Numpy needs to be propagated when htseq is used as a Python library.
2987 `(("python-numpy" ,python-numpy)))
2989 `(("python-pysam" ,python-pysam)
2990 ("python-matplotlib" ,python-matplotlib)))
2991 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2992 (synopsis "Analysing high-throughput sequencing data with Python")
2994 "HTSeq is a Python package that provides infrastructure to process data
2995 from high-throughput sequencing assays.")
2996 (license license:gpl3+)))
2998 (define-public python2-htseq
2999 (package-with-python2 htseq))
3001 (define-public java-htsjdk
3003 (name "java-htsjdk")
3004 (version "2.3.0") ; last version without build dependency on gradle
3008 "https://github.com/samtools/htsjdk/archive/"
3010 (file-name (string-append name "-" version ".tar.gz"))
3013 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
3014 (modules '((guix build utils)))
3016 ;; Delete pre-built binaries
3018 (delete-file-recursively "lib")
3021 (build-system ant-build-system)
3023 `(#:tests? #f ; test require Internet access
3026 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3027 "/share/java/htsjdk/"))
3028 #:build-target "all"
3030 (modify-phases %standard-phases
3031 ;; The build phase also installs the jars
3032 (delete 'install))))
3034 `(("java-ngs" ,java-ngs)
3035 ("java-snappy-1" ,java-snappy-1)
3036 ("java-commons-compress" ,java-commons-compress)
3037 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3038 ("java-commons-jexl-2" ,java-commons-jexl-2)
3039 ("java-xz" ,java-xz)))
3041 `(("java-testng" ,java-testng)))
3042 (home-page "http://samtools.github.io/htsjdk/")
3043 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3045 "HTSJDK is an implementation of a unified Java library for accessing
3046 common file formats, such as SAM and VCF, used for high-throughput
3047 sequencing (HTS) data. There are also an number of useful utilities for
3048 manipulating HTS data.")
3049 (license license:expat)))
3051 (define-public java-htsjdk-latest
3053 (name "java-htsjdk")
3058 (url "https://github.com/samtools/htsjdk.git")
3060 (file-name (string-append name "-" version "-checkout"))
3063 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3064 (build-system ant-build-system)
3066 `(#:tests? #f ; test require Scala
3068 #:jar-name "htsjdk.jar"
3070 (modify-phases %standard-phases
3071 (add-after 'unpack 'remove-useless-build.xml
3072 (lambda _ (delete-file "build.xml") #t))
3073 ;; The tests require the scalatest package.
3074 (add-after 'unpack 'remove-tests
3075 (lambda _ (delete-file-recursively "src/test") #t)))))
3077 `(("java-ngs" ,java-ngs)
3078 ("java-snappy-1" ,java-snappy-1)
3079 ("java-commons-compress" ,java-commons-compress)
3080 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3081 ("java-commons-jexl-2" ,java-commons-jexl-2)
3082 ("java-xz" ,java-xz)))
3084 `(("java-junit" ,java-junit)))
3085 (home-page "http://samtools.github.io/htsjdk/")
3086 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3088 "HTSJDK is an implementation of a unified Java library for accessing
3089 common file formats, such as SAM and VCF, used for high-throughput
3090 sequencing (HTS) data. There are also an number of useful utilities for
3091 manipulating HTS data.")
3092 (license license:expat)))
3094 ;; This is needed for picard 2.10.3
3095 (define-public java-htsjdk-2.10.1
3096 (package (inherit java-htsjdk-latest)
3097 (name "java-htsjdk")
3102 (url "https://github.com/samtools/htsjdk.git")
3104 (file-name (string-append name "-" version "-checkout"))
3107 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3108 (build-system ant-build-system)
3110 `(#:tests? #f ; tests require Scala
3112 #:jar-name "htsjdk.jar"
3114 (modify-phases %standard-phases
3115 (add-after 'unpack 'remove-useless-build.xml
3116 (lambda _ (delete-file "build.xml") #t))
3117 ;; The tests require the scalatest package.
3118 (add-after 'unpack 'remove-tests
3119 (lambda _ (delete-file-recursively "src/test") #t)))))))
3121 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3122 ;; recent version of java-htsjdk, which depends on gradle.
3123 (define-public java-picard
3125 (name "java-picard")
3130 (url "https://github.com/broadinstitute/picard.git")
3132 (file-name (string-append "java-picard-" version "-checkout"))
3135 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3136 (modules '((guix build utils)))
3139 ;; Delete pre-built binaries.
3140 (delete-file-recursively "lib")
3142 (substitute* "build.xml"
3143 ;; Remove build-time dependency on git.
3144 (("failifexecutionfails=\"true\"")
3145 "failifexecutionfails=\"false\"")
3147 (("depends=\"compile-htsjdk, ")
3149 (("depends=\"compile-htsjdk-tests, ")
3151 ;; Build picard-lib.jar before building picard.jar
3152 (("name=\"picard-jar\" depends=\"" line)
3153 (string-append line "picard-lib-jar, ")))
3155 (build-system ant-build-system)
3157 `(#:build-target "picard-jar"
3158 #:test-target "test"
3159 ;; Tests require jacoco:coverage.
3162 (list (string-append "-Dhtsjdk_lib_dir="
3163 (assoc-ref %build-inputs "java-htsjdk")
3164 "/share/java/htsjdk/")
3165 "-Dhtsjdk-classes=dist/tmp"
3166 (string-append "-Dhtsjdk-version="
3167 ,(package-version java-htsjdk)))
3170 (modify-phases %standard-phases
3171 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3172 (delete 'generate-jar-indices)
3173 (add-after 'unpack 'use-our-htsjdk
3174 (lambda* (#:key inputs #:allow-other-keys)
3175 (substitute* "build.xml"
3176 (("\\$\\{htsjdk\\}/lib")
3177 (string-append (assoc-ref inputs "java-htsjdk")
3178 "/share/java/htsjdk/")))
3180 (add-after 'unpack 'make-test-target-independent
3181 (lambda* (#:key inputs #:allow-other-keys)
3182 (substitute* "build.xml"
3183 (("name=\"test\" depends=\"compile, ")
3184 "name=\"test\" depends=\""))
3186 (replace 'install (install-jars "dist")))))
3188 `(("java-htsjdk" ,java-htsjdk)
3189 ("java-guava" ,java-guava)))
3191 `(("java-testng" ,java-testng)))
3192 (home-page "http://broadinstitute.github.io/picard/")
3193 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3194 (description "Picard is a set of Java command line tools for manipulating
3195 high-throughput sequencing (HTS) data and formats. Picard is implemented
3196 using the HTSJDK Java library to support accessing file formats that are
3197 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3199 (license license:expat)))
3201 ;; This is needed for dropseq-tools
3202 (define-public java-picard-2.10.3
3204 (name "java-picard")
3209 (url "https://github.com/broadinstitute/picard.git")
3211 (file-name (string-append "java-picard-" version "-checkout"))
3214 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3215 (build-system ant-build-system)
3217 `(#:jar-name "picard.jar"
3218 ;; Tests require jacoco:coverage.
3221 #:main-class "picard.cmdline.PicardCommandLine"
3222 #:modules ((guix build ant-build-system)
3224 (guix build java-utils)
3229 (modify-phases %standard-phases
3230 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3231 (delete 'generate-jar-indices)
3232 (add-after 'unpack 'remove-useless-build.xml
3233 (lambda _ (delete-file "build.xml") #t))
3234 ;; This is necessary to ensure that htsjdk is found when using
3235 ;; picard.jar as an executable.
3236 (add-before 'build 'edit-classpath-in-manifest
3237 (lambda* (#:key inputs #:allow-other-keys)
3238 (chmod "build.xml" #o664)
3239 (call-with-output-file "build.xml.new"
3243 (with-input-from-file "build.xml"
3244 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3245 `((target . ,(lambda (tag . kids)
3246 (let ((name ((sxpath '(name *text*))
3248 ;; FIXME: We're breaking the line
3249 ;; early with a dummy path to
3250 ;; ensure that the store reference
3251 ;; isn't broken apart and can still
3252 ;; be found by the reference
3257 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3258 ;; maximum line length is 70
3259 (string-tabulate (const #\b) 57)
3260 (assoc-ref inputs "java-htsjdk"))))
3261 (if (member "manifest" name)
3264 (@ (file "${manifest.file}")
3265 (match "\\r\\n\\r\\n")
3266 (replace "${line.separator}")))
3269 (file "${manifest.file}")
3272 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3273 (*text* . ,(lambda (_ txt) txt))))
3275 (rename-file "build.xml.new" "build.xml")
3278 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3280 `(("java-testng" ,java-testng)
3281 ("java-guava" ,java-guava)))
3282 (home-page "http://broadinstitute.github.io/picard/")
3283 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3284 (description "Picard is a set of Java command line tools for manipulating
3285 high-throughput sequencing (HTS) data and formats. Picard is implemented
3286 using the HTSJDK Java library to support accessing file formats that are
3287 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3289 (license license:expat)))
3291 ;; This is the last version of Picard to provide net.sf.samtools
3292 (define-public java-picard-1.113
3293 (package (inherit java-picard)
3294 (name "java-picard")
3299 (url "https://github.com/broadinstitute/picard.git")
3301 (file-name (string-append "java-picard-" version "-checkout"))
3304 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3305 (modules '((guix build utils)))
3308 ;; Delete pre-built binaries.
3309 (delete-file-recursively "lib")
3312 (build-system ant-build-system)
3314 `(#:build-target "picard-jar"
3315 #:test-target "test"
3316 ;; FIXME: the class path at test time is wrong.
3317 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3318 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3321 ;; This is only used for tests.
3323 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3325 (modify-phases %standard-phases
3326 ;; FIXME: This phase fails.
3327 (delete 'generate-jar-indices)
3328 ;; Do not use bundled ant bzip2.
3329 (add-after 'unpack 'use-ant-bzip
3330 (lambda* (#:key inputs #:allow-other-keys)
3331 (substitute* "build.xml"
3332 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3333 (string-append (assoc-ref inputs "ant")
3336 (add-after 'unpack 'make-test-target-independent
3337 (lambda* (#:key inputs #:allow-other-keys)
3338 (substitute* "build.xml"
3339 (("name=\"test\" depends=\"compile, ")
3340 "name=\"test\" depends=\"compile-tests, ")
3341 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3342 "name=\"compile\" depends=\"compile-src\""))
3344 (add-after 'unpack 'fix-deflater-path
3345 (lambda* (#:key outputs #:allow-other-keys)
3346 (substitute* "src/java/net/sf/samtools/Defaults.java"
3347 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3348 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3349 (assoc-ref outputs "out")
3350 "/lib/jni/libIntelDeflater.so"
3353 ;; Build the deflater library, because we've previously deleted the
3354 ;; pre-built one. This can only be built with access to the JDK
3356 (add-after 'build 'build-jni
3357 (lambda* (#:key inputs #:allow-other-keys)
3360 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3361 "-xf" (assoc-ref inputs "jdk-src")))
3362 (zero? (system* "javah" "-jni"
3363 "-classpath" "classes"
3365 "net.sf.samtools.util.zip.IntelDeflater"))
3366 (with-directory-excursion "src/c/inteldeflater"
3367 (zero? (system* "gcc" "-I../../../lib" "-I."
3368 (string-append "-I" (assoc-ref inputs "jdk")
3370 "-I../../../jdk-src/src/share/native/common/"
3371 "-I../../../jdk-src/src/solaris/native/common/"
3372 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3373 (zero? (system* "gcc" "-shared"
3374 "-o" "../../../lib/jni/libIntelDeflater.so"
3375 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3376 ;; We can only build everything else after building the JNI library.
3377 (add-after 'build-jni 'build-rest
3378 (lambda* (#:key make-flags #:allow-other-keys)
3379 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3380 (add-before 'build 'set-JAVA6_HOME
3382 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3384 (replace 'install (install-jars "dist"))
3385 (add-after 'install 'install-jni-lib
3386 (lambda* (#:key outputs #:allow-other-keys)
3387 (let ((jni (string-append (assoc-ref outputs "out")
3390 (install-file "lib/jni/libIntelDeflater.so" jni)
3393 `(("java-snappy-1" ,java-snappy-1)
3394 ("java-commons-jexl-2" ,java-commons-jexl-2)
3395 ("java-cofoja" ,java-cofoja)
3396 ("ant" ,ant) ; for bzip2 support at runtime
3399 `(("ant-apache-bcel" ,ant-apache-bcel)
3400 ("ant-junit" ,ant-junit)
3401 ("java-testng" ,java-testng)
3402 ("java-commons-bcel" ,java-commons-bcel)
3403 ("java-jcommander" ,java-jcommander)
3404 ("jdk" ,icedtea-8 "jdk")
3405 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3407 (define-public fastqc
3414 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3415 "projects/fastqc/fastqc_v"
3416 version "_source.zip"))
3419 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3420 (build-system ant-build-system)
3422 `(#:tests? #f ; there are no tests
3423 #:build-target "build"
3425 (modify-phases %standard-phases
3426 (add-after 'unpack 'fix-dependencies
3427 (lambda* (#:key inputs #:allow-other-keys)
3428 (substitute* "build.xml"
3430 (string-append (assoc-ref inputs "java-jbzip2")
3431 "/share/java/jbzip2.jar"))
3433 (string-append (assoc-ref inputs "java-picard-1.113")
3434 "/share/java/sam-1.112.jar"))
3436 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3437 "/share/java/sis-jhdf5.jar")))
3439 ;; There is no installation target
3441 (lambda* (#:key inputs outputs #:allow-other-keys)
3442 (let* ((out (assoc-ref outputs "out"))
3443 (bin (string-append out "/bin"))
3444 (share (string-append out "/share/fastqc/"))
3445 (exe (string-append share "/fastqc")))
3446 (for-each mkdir-p (list bin share))
3447 (copy-recursively "bin" share)
3449 (("my \\$java_bin = 'java';")
3450 (string-append "my $java_bin = '"
3451 (assoc-ref inputs "java")
3454 (symlink exe (string-append bin "/fastqc"))
3458 ("perl" ,perl) ; needed for the wrapper script
3459 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3460 ("java-picard-1.113" ,java-picard-1.113)
3461 ("java-jbzip2" ,java-jbzip2)))
3463 `(("unzip" ,unzip)))
3464 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3465 (synopsis "Quality control tool for high throughput sequence data")
3467 "FastQC aims to provide a simple way to do some quality control
3468 checks on raw sequence data coming from high throughput sequencing
3469 pipelines. It provides a modular set of analyses which you can use to
3470 give a quick impression of whether your data has any problems of which
3471 you should be aware before doing any further analysis.
3473 The main functions of FastQC are:
3476 @item Import of data from BAM, SAM or FastQ files (any variant);
3477 @item Providing a quick overview to tell you in which areas there may
3479 @item Summary graphs and tables to quickly assess your data;
3480 @item Export of results to an HTML based permanent report;
3481 @item Offline operation to allow automated generation of reports
3482 without running the interactive application.
3484 (license license:gpl3+)))
3486 (define-public fastp
3494 (url "https://github.com/OpenGene/fastp.git")
3495 (commit (string-append "v" version))))
3496 (file-name (git-file-name name version))
3499 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3500 (build-system gnu-build-system)
3502 `(#:tests? #f ; there are none
3504 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3506 (modify-phases %standard-phases
3508 (add-before 'install 'create-target-dir
3509 (lambda* (#:key outputs #:allow-other-keys)
3510 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3514 (home-page "https://github.com/OpenGene/fastp/")
3515 (synopsis "All-in-one FastQ preprocessor")
3517 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3518 FastQ files. This tool has multi-threading support to afford high
3520 (license license:expat)))
3522 (define-public htslib
3529 "https://github.com/samtools/htslib/releases/download/"
3530 version "/htslib-" version ".tar.bz2"))
3533 "18bw0mn9pj5wgarnlaxmf1bb8pdqgl1zd6czirqcr62ajpn1xvy0"))))
3534 (build-system gnu-build-system)
3536 `(("openssl" ,openssl)
3541 (home-page "http://www.htslib.org")
3542 (synopsis "C library for reading/writing high-throughput sequencing data")
3544 "HTSlib is a C library for reading/writing high-throughput sequencing
3545 data. It also provides the @command{bgzip}, @command{htsfile}, and
3546 @command{tabix} utilities.")
3547 ;; Files under cram/ are released under the modified BSD license;
3548 ;; the rest is released under the Expat license
3549 (license (list license:expat license:bsd-3))))
3551 ;; This package should be removed once no packages rely upon it.
3559 "https://github.com/samtools/htslib/releases/download/"
3560 version "/htslib-" version ".tar.bz2"))
3563 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3572 "https://github.com/nboley/idr/archive/"
3574 (file-name (string-append name "-" version ".tar.gz"))
3577 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3578 ;; Delete generated C code.
3580 '(begin (delete-file "idr/inv_cdf.c") #t))))
3581 (build-system python-build-system)
3582 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3583 ;; are no longer part of this package. It also asserts False, which
3584 ;; causes the tests to always fail.
3585 (arguments `(#:tests? #f))
3587 `(("python-scipy" ,python-scipy)
3588 ("python-sympy" ,python-sympy)
3589 ("python-numpy" ,python-numpy)
3590 ("python-matplotlib" ,python-matplotlib)))
3592 `(("python-cython" ,python-cython)))
3593 (home-page "https://github.com/nboley/idr")
3594 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3596 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3597 to measure the reproducibility of findings identified from replicate
3598 experiments and provide highly stable thresholds based on reproducibility.")
3599 (license license:gpl2+)))
3601 (define-public jellyfish
3607 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3608 "releases/download/v" version
3609 "/jellyfish-" version ".tar.gz"))
3612 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3613 (build-system gnu-build-system)
3614 (outputs '("out" ;for library
3615 "ruby" ;for Ruby bindings
3616 "python")) ;for Python bindings
3619 (list (string-append "--enable-ruby-binding="
3620 (assoc-ref %outputs "ruby"))
3621 (string-append "--enable-python-binding="
3622 (assoc-ref %outputs "python")))
3624 (modify-phases %standard-phases
3625 (add-before 'check 'set-SHELL-variable
3627 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3629 (setenv "SHELL" (which "bash"))
3635 ("python" ,python-2)
3636 ("pkg-config" ,pkg-config)))
3638 `(("htslib" ,htslib)))
3639 (synopsis "Tool for fast counting of k-mers in DNA")
3641 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3642 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3643 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3644 is a command-line program that reads FASTA and multi-FASTA files containing
3645 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3646 translated into a human-readable text format using the @code{jellyfish dump}
3647 command, or queried for specific k-mers with @code{jellyfish query}.")
3648 (home-page "http://www.genome.umd.edu/jellyfish.html")
3649 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3650 (supported-systems '("x86_64-linux"))
3651 ;; The combined work is published under the GPLv3 or later. Individual
3652 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3653 (license (list license:gpl3+ license:expat))))
3655 (define-public khmer
3662 (uri (pypi-uri "khmer" version))
3665 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3666 (patches (search-patches "khmer-use-libraries.patch"))))
3667 (build-system python-build-system)
3670 (modify-phases %standard-phases
3671 (add-after 'unpack 'set-paths
3672 (lambda* (#:key inputs outputs #:allow-other-keys)
3673 ;; Delete bundled libraries.
3674 (delete-file-recursively "third-party/zlib")
3675 (delete-file-recursively "third-party/bzip2")
3676 ;; Replace bundled seqan.
3677 (let* ((seqan-all "third-party/seqan")
3678 (seqan-include (string-append
3679 seqan-all "/core/include")))
3680 (delete-file-recursively seqan-all)
3681 (copy-recursively (string-append (assoc-ref inputs "seqan")
3683 (string-append seqan-include "/seqan")))
3684 ;; We do not replace the bundled MurmurHash as the canonical
3685 ;; repository for this code 'SMHasher' is unsuitable for
3686 ;; providing a library. See
3687 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3689 (add-after 'unpack 'set-cc
3693 ;; It is simpler to test after installation.
3695 (add-after 'install 'post-install-check
3696 (lambda* (#:key inputs outputs #:allow-other-keys)
3697 (let ((out (assoc-ref outputs "out")))
3702 (assoc-ref outputs "out")
3704 (setenv "PYTHONPATH"
3706 (getenv "PYTHONPATH")
3710 (string-take (string-take-right
3711 (assoc-ref inputs "python") 5) 3)
3713 (with-directory-excursion "build"
3714 (zero? (system* "nosetests" "khmer" "--attr"
3715 "!known_failing")))))))))
3718 ("python-nose" ,python-nose)))
3722 ("python-screed" ,python-screed)
3723 ("python-bz2file" ,python-bz2file)
3724 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3725 ;; until the next version of khmer (likely 2.1) is released.
3727 (home-page "https://khmer.readthedocs.org/")
3728 (synopsis "K-mer counting, filtering and graph traversal library")
3729 (description "The khmer software is a set of command-line tools for
3730 working with DNA shotgun sequencing data from genomes, transcriptomes,
3731 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3732 sometimes better. Khmer can also identify and fix problems with shotgun
3734 ;; When building on i686, armhf and mips64el, we get the following error:
3735 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3736 (supported-systems '("x86_64-linux" "aarch64-linux"))
3737 (license license:bsd-3)))
3739 (define-public kaiju
3746 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3748 (file-name (string-append name "-" version ".tar.gz"))
3751 "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7"))))
3752 (build-system gnu-build-system)
3754 `(#:tests? #f ; There are no tests.
3756 (modify-phases %standard-phases
3758 (add-before 'build 'move-to-src-dir
3759 (lambda _ (chdir "src") #t))
3761 (lambda* (#:key inputs outputs #:allow-other-keys)
3762 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3765 (copy-recursively "bin" bin)
3766 (copy-recursively "util" bin))
3771 (home-page "http://kaiju.binf.ku.dk/")
3772 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3773 (description "Kaiju is a program for sensitive taxonomic classification
3774 of high-throughput sequencing reads from metagenomic whole genome sequencing
3776 (license license:gpl3+)))
3781 (version "2.1.1.20160309")
3784 (uri (pypi-uri "MACS2" version))
3787 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3788 (build-system python-build-system)
3790 `(#:python ,python-2 ; only compatible with Python 2.7
3791 #:tests? #f)) ; no test target
3793 `(("python-numpy" ,python2-numpy)))
3794 (home-page "https://github.com/taoliu/MACS/")
3795 (synopsis "Model based analysis for ChIP-Seq data")
3797 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3798 identifying transcript factor binding sites named Model-based Analysis of
3799 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3800 the significance of enriched ChIP regions and it improves the spatial
3801 resolution of binding sites through combining the information of both
3802 sequencing tag position and orientation.")
3803 (license license:bsd-3)))
3805 (define-public mafft
3812 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3813 "-without-extensions-src.tgz"))
3814 (file-name (string-append name "-" version ".tgz"))
3817 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3818 (build-system gnu-build-system)
3820 `(#:tests? #f ; no automated tests, though there are tests in the read me
3821 #:make-flags (let ((out (assoc-ref %outputs "out")))
3822 (list (string-append "PREFIX=" out)
3823 (string-append "BINDIR="
3824 (string-append out "/bin"))))
3826 (modify-phases %standard-phases
3827 (add-after 'unpack 'enter-dir
3828 (lambda _ (chdir "core") #t))
3829 (add-after 'enter-dir 'patch-makefile
3831 ;; on advice from the MAFFT authors, there is no need to
3832 ;; distribute mafft-profile, mafft-distance, or
3833 ;; mafft-homologs.rb as they are too "specialised".
3834 (substitute* "Makefile"
3835 ;; remove mafft-homologs.rb from SCRIPTS
3836 (("^SCRIPTS = mafft mafft-homologs.rb")
3838 ;; remove mafft-homologs from MANPAGES
3839 (("^MANPAGES = mafft.1 mafft-homologs.1")
3840 "MANPAGES = mafft.1")
3841 ;; remove mafft-distance from PROGS
3842 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3843 "PROGS = dvtditr dndfast7 dndblast sextet5")
3844 ;; remove mafft-profile from PROGS
3845 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3846 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3847 (("^rm -f mafft-profile mafft-profile.exe") "#")
3848 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3849 ;; do not install MAN pages in libexec folder
3850 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3851 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3853 (add-after 'enter-dir 'patch-paths
3854 (lambda* (#:key inputs #:allow-other-keys)
3855 (substitute* '("pairash.c"
3857 (("perl") (which "perl"))
3858 (("([\"`| ])awk" _ prefix)
3859 (string-append prefix (which "awk")))
3860 (("grep") (which "grep")))
3863 (add-after 'install 'wrap-programs
3864 (lambda* (#:key outputs #:allow-other-keys)
3865 (let* ((out (assoc-ref outputs "out"))
3866 (bin (string-append out "/bin"))
3867 (path (string-append
3868 (assoc-ref %build-inputs "coreutils") "/bin:")))
3869 (for-each (lambda (file)
3871 `("PATH" ":" prefix (,path))))
3879 ("coreutils" ,coreutils)))
3880 (home-page "http://mafft.cbrc.jp/alignment/software/")
3881 (synopsis "Multiple sequence alignment program")
3883 "MAFFT offers a range of multiple alignment methods for nucleotide and
3884 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3885 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3887 (license (license:non-copyleft
3888 "http://mafft.cbrc.jp/alignment/software/license.txt"
3889 "BSD-3 with different formatting"))))
3898 "https://github.com/marbl/mash/archive/v"
3900 (file-name (string-append name "-" version ".tar.gz"))
3903 "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv"))
3904 (modules '((guix build utils)))
3907 ;; Delete bundled kseq.
3908 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3909 (delete-file "src/mash/kseq.h")
3911 (build-system gnu-build-system)
3913 `(#:tests? #f ; No tests.
3916 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3917 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3918 #:make-flags (list "CC=gcc")
3920 (modify-phases %standard-phases
3921 (add-after 'unpack 'fix-includes
3923 (substitute* '("src/mash/Sketch.cpp"
3924 "src/mash/CommandFind.cpp"
3925 "src/mash/CommandScreen.cpp")
3926 (("^#include \"kseq\\.h\"")
3927 "#include \"htslib/kseq.h\""))
3929 (add-after 'fix-includes 'autoconf
3930 (lambda _ (zero? (system* "autoconf")))))))
3932 `(("autoconf" ,autoconf)
3933 ;; Capnproto and htslib are statically embedded in the final
3934 ;; application. Therefore we also list their licenses, below.
3935 ("capnproto" ,capnproto)
3936 ("htslib" ,htslib)))
3940 (supported-systems '("x86_64-linux"))
3941 (home-page "https://mash.readthedocs.io")
3942 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3943 (description "Mash is a fast sequence distance estimator that uses the
3944 MinHash algorithm and is designed to work with genomes and metagenomes in the
3945 form of assemblies or reads.")
3946 (license (list license:bsd-3 ; Mash
3947 license:expat ; HTSlib and capnproto
3948 license:public-domain ; MurmurHash 3
3949 license:cpl1.0)))) ; Open Bloom Filter
3951 (define-public metabat
3958 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3960 (file-name (string-append name "-" version ".tar.gz"))
3963 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3964 (patches (search-patches "metabat-fix-compilation.patch"))))
3965 (build-system scons-build-system)
3967 `(#:scons ,scons-python2
3969 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3970 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3971 #:tests? #f ;; Tests are run during the build phase.
3973 (modify-phases %standard-phases
3974 (add-after 'unpack 'fix-includes
3976 (substitute* "src/BamUtils.h"
3977 (("^#include \"bam/bam\\.h\"")
3978 "#include \"samtools/bam.h\"")
3979 (("^#include \"bam/sam\\.h\"")
3980 "#include \"samtools/sam.h\""))
3981 (substitute* "src/KseqReader.h"
3982 (("^#include \"bam/kseq\\.h\"")
3983 "#include \"htslib/kseq.h\""))
3985 (add-after 'unpack 'fix-scons
3986 (lambda* (#:key inputs #:allow-other-keys)
3987 (substitute* "SConstruct"
3988 (("^htslib_dir += 'samtools'")
3989 (string-append "htslib_dir = '"
3990 (assoc-ref inputs "htslib")
3992 (("^samtools_dir = 'samtools'")
3993 (string-append "samtools_dir = '"
3994 (assoc-ref inputs "samtools")
3996 (("^findStaticOrShared\\('bam', hts_lib")
3997 (string-append "findStaticOrShared('bam', '"
3998 (assoc-ref inputs "samtools")
4000 ;; Do not distribute README.
4001 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4006 ("samtools" ,samtools)
4009 (home-page "https://bitbucket.org/berkeleylab/metabat")
4011 "Reconstruction of single genomes from complex microbial communities")
4013 "Grouping large genomic fragments assembled from shotgun metagenomic
4014 sequences to deconvolute complex microbial communities, or metagenome binning,
4015 enables the study of individual organisms and their interactions. MetaBAT is
4016 an automated metagenome binning software, which integrates empirical
4017 probabilistic distances of genome abundance and tetranucleotide frequency.")
4018 ;; The source code contains inline assembly.
4019 (supported-systems '("x86_64-linux" "i686-linux"))
4020 (license (license:non-copyleft "file://license.txt"
4021 "See license.txt in the distribution."))))
4023 (define-public minced
4030 "https://github.com/ctSkennerton/minced/archive/"
4032 (file-name (string-append name "-" version ".tar.gz"))
4035 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
4036 (build-system gnu-build-system)
4038 `(#:test-target "test"
4040 (modify-phases %standard-phases
4042 (add-before 'check 'fix-test
4044 ;; Fix test for latest version.
4045 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4046 (("minced:0.1.6") "minced:0.2.0"))
4048 (replace 'install ; No install target.
4049 (lambda* (#:key inputs outputs #:allow-other-keys)
4050 (let* ((out (assoc-ref outputs "out"))
4051 (bin (string-append out "/bin"))
4052 (wrapper (string-append bin "/minced")))
4053 ;; Minced comes with a wrapper script that tries to figure out where
4054 ;; it is located before running the JAR. Since these paths are known
4055 ;; to us, we build our own wrapper to avoid coreutils dependency.
4056 (install-file "minced.jar" bin)
4057 (with-output-to-file wrapper
4061 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4062 (assoc-ref inputs "jre") "/bin/java -jar "
4063 bin "/minced.jar \"$@\"\n"))))
4064 (chmod wrapper #o555)))))))
4066 `(("jdk" ,icedtea "jdk")))
4069 ("jre" ,icedtea "out")))
4070 (home-page "https://github.com/ctSkennerton/minced")
4071 (synopsis "Mining CRISPRs in Environmental Datasets")
4073 "MinCED is a program to find Clustered Regularly Interspaced Short
4074 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4075 unassembled metagenomic reads, but is mainly designed for full genomes and
4076 assembled metagenomic sequence.")
4077 (license license:gpl3+)))
4085 (uri (pypi-uri "misopy" version))
4088 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4089 (modules '((guix build utils)))
4091 (substitute* "setup.py"
4092 ;; Use setuptools, or else the executables are not
4094 (("distutils.core") "setuptools")
4095 ;; use "gcc" instead of "cc" for compilation
4097 "cc.set_executables(
4101 linker_so='gcc -shared'); defines"))
4103 (build-system python-build-system)
4105 `(#:python ,python-2 ; only Python 2 is supported
4106 #:tests? #f)) ; no "test" target
4108 `(("samtools" ,samtools)
4109 ("python-numpy" ,python2-numpy)
4110 ("python-pysam" ,python2-pysam)
4111 ("python-scipy" ,python2-scipy)
4112 ("python-matplotlib" ,python2-matplotlib)))
4114 `(("python-mock" ,python2-mock) ;for tests
4115 ("python-pytz" ,python2-pytz))) ;for tests
4116 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4117 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4119 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4120 the expression level of alternatively spliced genes from RNA-Seq data, and
4121 identifies differentially regulated isoforms or exons across samples. By
4122 modeling the generative process by which reads are produced from isoforms in
4123 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4124 that a read originated from a particular isoform.")
4125 (license license:gpl2)))
4127 (define-public muscle
4130 (version "3.8.1551")
4132 (method url-fetch/tarbomb)
4134 "http://www.drive5.com/muscle/muscle_src_"
4138 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4139 (build-system gnu-build-system)
4141 `(#:make-flags (list "LDLIBS = -lm")
4143 (modify-phases %standard-phases
4146 ;; There are no tests, so just test if it runs.
4147 (lambda _ (zero? (system* "./muscle" "-version"))))
4149 (lambda* (#:key outputs #:allow-other-keys)
4150 (let* ((out (assoc-ref outputs "out"))
4151 (bin (string-append out "/bin")))
4152 (install-file "muscle" bin)))))))
4153 (home-page "http://www.drive5.com/muscle")
4154 (synopsis "Multiple sequence alignment program")
4156 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4157 program for nucleotide and protein sequences.")
4158 ;; License information found in 'muscle -h' and usage.cpp.
4159 (license license:public-domain)))
4161 (define-public newick-utils
4162 ;; There are no recent releases so we package from git.
4163 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4165 (name "newick-utils")
4166 (version (string-append "1.6-1." (string-take commit 8)))
4170 (url "https://github.com/tjunier/newick_utils.git")
4172 (file-name (string-append name "-" version "-checkout"))
4175 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4176 (build-system gnu-build-system)
4179 (modify-phases %standard-phases
4180 (add-after 'unpack 'autoconf
4181 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4183 ;; XXX: TODO: Enable Lua and Guile bindings.
4184 ;; https://github.com/tjunier/newick_utils/issues/13
4185 `(("libxml2" ,libxml2)
4189 `(("autoconf" ,autoconf)
4190 ("automake" ,automake)
4191 ("libtool" ,libtool)))
4192 (synopsis "Programs for working with newick format phylogenetic trees")
4194 "Newick-utils is a suite of utilities for processing phylogenetic trees
4195 in Newick format. Functions include re-rooting, extracting subtrees,
4196 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4197 (home-page "https://github.com/tjunier/newick_utils")
4198 (license license:bsd-3))))
4207 "https://github.com/wwood/OrfM/releases/download/v"
4208 version "/orfm-" version ".tar.gz"))
4211 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4212 (build-system gnu-build-system)
4213 (inputs `(("zlib" ,zlib)))
4215 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4216 ("ruby-rspec" ,ruby-rspec)
4218 (synopsis "Simple and not slow open reading frame (ORF) caller")
4220 "An ORF caller finds stretches of DNA that, when translated, are not
4221 interrupted by stop codons. OrfM finds and prints these ORFs.")
4222 (home-page "https://github.com/wwood/OrfM")
4223 (license license:lgpl3+)))
4225 (define-public pplacer
4226 (let ((commit "g807f6f3"))
4229 ;; The commit should be updated with each version change.
4230 (version "1.1.alpha19")
4234 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4236 (file-name (string-append name "-" version ".tar.gz"))
4238 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4239 (build-system ocaml-build-system)
4241 `(#:ocaml ,ocaml-4.01
4242 #:findlib ,ocaml4.01-findlib
4243 #:modules ((guix build ocaml-build-system)
4247 (modify-phases %standard-phases
4249 (add-after 'unpack 'replace-bundled-cddlib
4250 (lambda* (#:key inputs #:allow-other-keys)
4251 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4252 (local-dir "cddlib_guix"))
4254 (with-directory-excursion local-dir
4255 (system* "tar" "xvf" cddlib-src))
4256 (let ((cddlib-src-folder
4257 (string-append local-dir "/"
4258 (list-ref (scandir local-dir) 2)
4263 (string-append "cdd_src/" (basename file))))
4264 (find-files cddlib-src-folder ".*[ch]$")))
4266 (add-after 'unpack 'fix-makefile
4268 ;; Remove system calls to 'git'.
4269 (substitute* "Makefile"
4270 (("^DESCRIPT:=pplacer-.*")
4272 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4273 (substitute* "myocamlbuild.ml"
4274 (("git describe --tags --long .*\\\" with")
4276 "echo -n v" ,version "-" ,commit "\" with")))
4279 (lambda* (#:key outputs #:allow-other-keys)
4280 (let* ((out (assoc-ref outputs "out"))
4281 (bin (string-append out "/bin")))
4282 (copy-recursively "bin" bin))
4287 ("ocaml-ounit" ,ocaml4.01-ounit)
4288 ("ocaml-batteries" ,ocaml4.01-batteries)
4289 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4290 ("ocaml-csv" ,ocaml4.01-csv)
4291 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4292 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4293 ("ocaml-mcl" ,ocaml4.01-mcl)
4294 ("ocaml-gsl" ,ocaml4.01-gsl)
4295 ("cddlib-src" ,(package-source cddlib))))
4297 `(("pplacer-scripts" ,pplacer-scripts)))
4298 (synopsis "Phylogenetic placement of biological sequences")
4300 "Pplacer places query sequences on a fixed reference phylogenetic tree
4301 to maximize phylogenetic likelihood or posterior probability according to a
4302 reference alignment. Pplacer is designed to be fast, to give useful
4303 information about uncertainty, and to offer advanced visualization and
4304 downstream analysis.")
4305 (home-page "http://matsen.fhcrc.org/pplacer")
4306 (license license:gpl3))))
4308 ;; This package is installed alongside 'pplacer'. It is a separate package so
4309 ;; that it can use the python-build-system for the scripts that are
4310 ;; distributed alongside the main OCaml binaries.
4311 (define pplacer-scripts
4314 (name "pplacer-scripts")
4315 (build-system python-build-system)
4317 `(#:python ,python-2
4319 (modify-phases %standard-phases
4320 (add-after 'unpack 'enter-scripts-dir
4321 (lambda _ (chdir "scripts")))
4324 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4325 (add-after 'install 'wrap-executables
4326 (lambda* (#:key inputs outputs #:allow-other-keys)
4327 (let* ((out (assoc-ref outputs "out"))
4328 (bin (string-append out "/bin")))
4329 (let ((path (string-append
4330 (assoc-ref inputs "hmmer") "/bin:"
4331 (assoc-ref inputs "infernal") "/bin")))
4333 (wrap-program (string-append bin "/refpkg_align.py")
4334 `("PATH" ":" prefix (,path))))
4335 (let ((path (string-append
4336 (assoc-ref inputs "hmmer") "/bin")))
4337 (wrap-program (string-append bin "/hrefpkg_query.py")
4338 `("PATH" ":" prefix (,path)))))
4341 `(("infernal" ,infernal)
4344 `(("python-biopython" ,python2-biopython)
4345 ("taxtastic" ,taxtastic)))
4346 (synopsis "Pplacer Python scripts")))
4348 (define-public python2-pbcore
4350 (name "python2-pbcore")
4354 (uri (pypi-uri "pbcore" version))
4357 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4358 (build-system python-build-system)
4359 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4361 `(("python-cython" ,python2-cython)
4362 ("python-numpy" ,python2-numpy)
4363 ("python-pysam" ,python2-pysam)
4364 ("python-h5py" ,python2-h5py)))
4366 `(("python-nose" ,python2-nose)
4367 ("python-sphinx" ,python2-sphinx)
4368 ("python-pyxb" ,python2-pyxb)))
4369 (home-page "http://pacificbiosciences.github.io/pbcore/")
4370 (synopsis "Library for reading and writing PacBio data files")
4372 "The pbcore package provides Python APIs for interacting with PacBio data
4373 files and writing bioinformatics applications.")
4374 (license license:bsd-3)))
4376 (define-public python2-warpedlmm
4378 (name "python2-warpedlmm")
4384 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4388 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4389 (build-system python-build-system)
4391 `(#:python ,python-2)) ; requires Python 2.7
4393 `(("python-scipy" ,python2-scipy)
4394 ("python-numpy" ,python2-numpy)
4395 ("python-matplotlib" ,python2-matplotlib)
4396 ("python-fastlmm" ,python2-fastlmm)
4397 ("python-pandas" ,python2-pandas)
4398 ("python-pysnptools" ,python2-pysnptools)))
4400 `(("python-mock" ,python2-mock)
4401 ("python-nose" ,python2-nose)
4403 (home-page "https://github.com/PMBio/warpedLMM")
4404 (synopsis "Implementation of warped linear mixed models")
4406 "WarpedLMM is a Python implementation of the warped linear mixed model,
4407 which automatically learns an optimal warping function (or transformation) for
4408 the phenotype as it models the data.")
4409 (license license:asl2.0)))
4411 (define-public pbtranscript-tofu
4412 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4414 (name "pbtranscript-tofu")
4415 (version (string-append "2.2.3." (string-take commit 7)))
4419 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4421 (file-name (string-append name "-" version "-checkout"))
4424 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4425 (modules '((guix build utils)))
4428 ;; remove bundled Cython sources
4429 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4431 (build-system python-build-system)
4433 `(#:python ,python-2
4434 ;; FIXME: Tests fail with "No such file or directory:
4435 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4438 (modify-phases %standard-phases
4439 (add-after 'unpack 'enter-directory
4441 (chdir "pbtranscript-tofu/pbtranscript/")
4443 ;; With setuptools version 18.0 and later this setup.py hack causes
4444 ;; a build error, so we disable it.
4445 (add-after 'enter-directory 'patch-setuppy
4447 (substitute* "setup.py"
4448 (("if 'setuptools.extension' in sys.modules:")
4452 `(("python-numpy" ,python2-numpy)
4453 ("python-bx-python" ,python2-bx-python)
4454 ("python-networkx" ,python2-networkx)
4455 ("python-scipy" ,python2-scipy)
4456 ("python-pbcore" ,python2-pbcore)
4457 ("python-h5py" ,python2-h5py)))
4459 `(("python-cython" ,python2-cython)
4460 ("python-nose" ,python2-nose)))
4461 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4462 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4464 "pbtranscript-tofu contains scripts to analyze transcriptome data
4465 generated using the PacBio Iso-Seq protocol.")
4466 (license license:bsd-3))))
4468 (define-public prank
4475 "http://wasabiapp.org/download/prank/prank.source."
4479 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4480 (build-system gnu-build-system)
4483 (modify-phases %standard-phases
4484 (add-after 'unpack 'enter-src-dir
4488 (add-after 'unpack 'remove-m64-flag
4489 ;; Prank will build with the correct 'bit-ness' without this flag
4490 ;; and this allows building on 32-bit machines.
4491 (lambda _ (substitute* "src/Makefile"
4496 (lambda* (#:key outputs #:allow-other-keys)
4497 (let* ((out (assoc-ref outputs "out"))
4498 (bin (string-append out "/bin"))
4499 (man (string-append out "/share/man/man1"))
4500 (path (string-append
4501 (assoc-ref %build-inputs "mafft") "/bin:"
4502 (assoc-ref %build-inputs "exonerate") "/bin:"
4503 (assoc-ref %build-inputs "bppsuite") "/bin")))
4504 (install-file "prank" bin)
4505 (wrap-program (string-append bin "/prank")
4506 `("PATH" ":" prefix (,path)))
4507 (install-file "prank.1" man))
4511 ("exonerate" ,exonerate)
4512 ("bppsuite" ,bppsuite)))
4513 (home-page "http://wasabiapp.org/software/prank/")
4514 (synopsis "Probabilistic multiple sequence alignment program")
4516 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4517 codon and amino-acid sequences. It is based on a novel algorithm that treats
4518 insertions correctly and avoids over-estimation of the number of deletion
4519 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4520 in phylogenetics and correctly takes into account the evolutionary distances
4521 between sequences. Lastly, PRANK allows for defining a potential structure
4522 for sequences to be aligned and then, simultaneously with the alignment,
4523 predicts the locations of structural units in the sequences.")
4524 (license license:gpl2+)))
4526 (define-public proteinortho
4528 (name "proteinortho")
4535 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4536 version "_src.tar.gz"))
4539 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4540 (build-system gnu-build-system)
4542 `(#:test-target "test"
4544 (modify-phases %standard-phases
4546 ;; There is no configure script, so we modify the Makefile directly.
4547 (lambda* (#:key outputs #:allow-other-keys)
4548 (substitute* "Makefile"
4551 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4553 (add-before 'install 'make-install-directory
4554 ;; The install directory is not created during 'make install'.
4555 (lambda* (#:key outputs #:allow-other-keys)
4556 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4558 (add-after 'install 'wrap-programs
4559 (lambda* (#:key inputs outputs #:allow-other-keys)
4560 (let* ((path (getenv "PATH"))
4561 (out (assoc-ref outputs "out"))
4562 (binary (string-append out "/bin/proteinortho5.pl")))
4563 (wrap-program binary `("PATH" ":" prefix (,path))))
4567 ("python" ,python-2)
4568 ("blast+" ,blast+)))
4569 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4570 (synopsis "Detect orthologous genes across species")
4572 "Proteinortho is a tool to detect orthologous genes across different
4573 species. For doing so, it compares similarities of given gene sequences and
4574 clusters them to find significant groups. The algorithm was designed to handle
4575 large-scale data and can be applied to hundreds of species at once.")
4576 (license license:gpl2+)))
4578 (define-public pyicoteo
4585 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4586 "pyicoteo/get/v" version ".tar.bz2"))
4587 (file-name (string-append name "-" version ".tar.bz2"))
4590 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4591 (build-system python-build-system)
4593 `(#:python ,python-2 ; does not work with Python 3
4594 #:tests? #f)) ; there are no tests
4596 `(("python2-matplotlib" ,python2-matplotlib)))
4597 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4598 (synopsis "Analyze high-throughput genetic sequencing data")
4600 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4601 sequencing data. It works with genomic coordinates. There are currently six
4602 different command-line tools:
4605 @item pyicoregion: for generating exploratory regions automatically;
4606 @item pyicoenrich: for differential enrichment between two conditions;
4607 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4608 @item pyicos: for genomic coordinates manipulation;
4609 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4610 @item pyicount: to count how many reads from N experiment files overlap in a
4612 @item pyicotrocol: to combine operations from pyicoteo.
4614 (license license:gpl3+)))
4616 (define-public prodigal
4623 "https://github.com/hyattpd/Prodigal/archive/v"
4625 (file-name (string-append name "-" version ".tar.gz"))
4628 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4629 (build-system gnu-build-system)
4631 `(#:tests? #f ;no check target
4632 #:make-flags (list (string-append "INSTALLDIR="
4633 (assoc-ref %outputs "out")
4636 (modify-phases %standard-phases
4637 (delete 'configure))))
4638 (home-page "http://prodigal.ornl.gov")
4639 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4641 "Prodigal runs smoothly on finished genomes, draft genomes, and
4642 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4643 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4644 partial genes, and identifies translation initiation sites.")
4645 (license license:gpl3+)))
4647 (define-public roary
4655 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4659 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4660 (build-system perl-build-system)
4663 (modify-phases %standard-phases
4668 ;; The tests are not run by default, so we run each test file
4670 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4672 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4673 (getenv "PERL5LIB")))
4674 (zero? (length (filter (lambda (file)
4675 (display file)(display "\n")
4676 (not (zero? (system* "perl" file))))
4677 (find-files "t" ".*\\.t$"))))))
4679 ;; There is no 'install' target in the Makefile.
4680 (lambda* (#:key outputs #:allow-other-keys)
4681 (let* ((out (assoc-ref outputs "out"))
4682 (bin (string-append out "/bin"))
4683 (perl (string-append out "/lib/perl5/site_perl"))
4684 (roary-plots "contrib/roary_plots"))
4687 (copy-recursively "bin" bin)
4688 (copy-recursively "lib" perl)
4690 (add-after 'install 'wrap-programs
4691 (lambda* (#:key inputs outputs #:allow-other-keys)
4692 (let* ((out (assoc-ref outputs "out"))
4693 (perl5lib (getenv "PERL5LIB"))
4694 (path (getenv "PATH")))
4695 (for-each (lambda (prog)
4696 (let ((binary (string-append out "/" prog)))
4697 (wrap-program binary
4698 `("PERL5LIB" ":" prefix
4699 (,(string-append perl5lib ":" out
4700 "/lib/perl5/site_perl"))))
4701 (wrap-program binary
4703 (,(string-append path ":" out "/bin"))))))
4704 (find-files "bin" ".*[^R]$"))
4706 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4707 (r-site-lib (getenv "R_LIBS_SITE"))
4709 (string-append (assoc-ref inputs "coreutils") "/bin")))
4711 `("R_LIBS_SITE" ":" prefix
4712 (,(string-append r-site-lib ":" out "/site-library/"))))
4715 (,(string-append coreutils-path ":" out "/bin"))))))
4718 `(("perl-env-path" ,perl-env-path)
4719 ("perl-test-files" ,perl-test-files)
4720 ("perl-test-most" ,perl-test-most)
4721 ("perl-test-output" ,perl-test-output)))
4723 `(("perl-array-utils" ,perl-array-utils)
4724 ("bioperl" ,bioperl-minimal)
4725 ("perl-digest-md5-file" ,perl-digest-md5-file)
4726 ("perl-exception-class" ,perl-exception-class)
4727 ("perl-file-find-rule" ,perl-file-find-rule)
4728 ("perl-file-grep" ,perl-file-grep)
4729 ("perl-file-slurper" ,perl-file-slurper)
4730 ("perl-file-which" ,perl-file-which)
4731 ("perl-graph" ,perl-graph)
4732 ("perl-graph-readwrite" ,perl-graph-readwrite)
4733 ("perl-log-log4perl" ,perl-log-log4perl)
4734 ("perl-moose" ,perl-moose)
4735 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4736 ("perl-text-csv" ,perl-text-csv)
4737 ("bedtools" ,bedtools)
4741 ("parallel" ,parallel)
4744 ("fasttree" ,fasttree)
4748 ("r-minimal" ,r-minimal)
4749 ("r-ggplot2" ,r-ggplot2)
4750 ("coreutils" ,coreutils)))
4751 (home-page "http://sanger-pathogens.github.io/Roary")
4752 (synopsis "High speed stand-alone pan genome pipeline")
4754 "Roary is a high speed stand alone pan genome pipeline, which takes
4755 annotated assemblies in GFF3 format (produced by the Prokka program) and
4756 calculates the pan genome. Using a standard desktop PC, it can analyse
4757 datasets with thousands of samples, without compromising the quality of the
4758 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4759 single processor. Roary is not intended for metagenomics or for comparing
4760 extremely diverse sets of genomes.")
4761 (license license:gpl3)))
4763 (define-public raxml
4772 "https://github.com/stamatak/standard-RAxML/archive/v"
4774 (file-name (string-append name "-" version ".tar.gz"))
4777 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4778 (build-system gnu-build-system)
4780 `(#:tests? #f ; There are no tests.
4781 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4782 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4784 (modify-phases %standard-phases
4787 (lambda* (#:key outputs #:allow-other-keys)
4788 (let* ((out (assoc-ref outputs "out"))
4789 (bin (string-append out "/bin"))
4790 (executable "raxmlHPC-HYBRID"))
4791 (install-file executable bin)
4792 (symlink (string-append bin "/" executable) "raxml"))
4795 `(("openmpi" ,openmpi)))
4796 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4797 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4799 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4801 ;; The source includes x86 specific code
4802 (supported-systems '("x86_64-linux" "i686-linux"))
4803 (license license:gpl2+)))
4813 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4816 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4817 (patches (search-patches "rsem-makefile.patch"))
4818 (modules '((guix build utils)))
4821 ;; remove bundled copy of boost
4822 (delete-file-recursively "boost")
4824 (build-system gnu-build-system)
4826 `(#:tests? #f ;no "check" target
4828 (modify-phases %standard-phases
4829 ;; No "configure" script.
4830 ;; Do not build bundled samtools library.
4833 (substitute* "Makefile"
4834 (("^all : sam/libbam.a") "all : "))
4837 (lambda* (#:key outputs #:allow-other-keys)
4838 (let* ((out (string-append (assoc-ref outputs "out")))
4839 (bin (string-append out "/bin/"))
4840 (perl (string-append out "/lib/perl5/site_perl")))
4843 (for-each (lambda (file)
4844 (install-file file bin))
4845 (find-files "." "rsem-.*"))
4846 (install-file "rsem_perl_utils.pm" perl))
4849 'install 'wrap-program
4850 (lambda* (#:key outputs #:allow-other-keys)
4851 (let ((out (assoc-ref outputs "out")))
4852 (for-each (lambda (prog)
4853 (wrap-program (string-append out "/bin/" prog)
4854 `("PERL5LIB" ":" prefix
4855 (,(string-append out "/lib/perl5/site_perl")))))
4856 '("rsem-plot-transcript-wiggles"
4857 "rsem-calculate-expression"
4858 "rsem-generate-ngvector"
4860 "rsem-prepare-reference")))
4864 ("ncurses" ,ncurses)
4865 ("r-minimal" ,r-minimal)
4867 ("samtools" ,samtools-0.1)
4869 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4870 (synopsis "Estimate gene expression levels from RNA-Seq data")
4872 "RSEM is a software package for estimating gene and isoform expression
4873 levels from RNA-Seq data. The RSEM package provides a user-friendly
4874 interface, supports threads for parallel computation of the EM algorithm,
4875 single-end and paired-end read data, quality scores, variable-length reads and
4876 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4877 interval estimates for expression levels. For visualization, it can generate
4878 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4879 (license license:gpl3+)))
4881 (define-public rseqc
4889 (string-append "mirror://sourceforge/rseqc/"
4890 "RSeQC-" version ".tar.gz"))
4892 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4893 (modules '((guix build utils)))
4896 ;; remove bundled copy of pysam
4897 (delete-file-recursively "lib/pysam")
4898 (substitute* "setup.py"
4899 ;; remove dependency on outdated "distribute" module
4900 (("^from distribute_setup import use_setuptools") "")
4901 (("^use_setuptools\\(\\)") "")
4902 ;; do not use bundled copy of pysam
4903 (("^have_pysam = False") "have_pysam = True"))
4905 (build-system python-build-system)
4906 (arguments `(#:python ,python-2))
4908 `(("python-cython" ,python2-cython)
4909 ("python-pysam" ,python2-pysam)
4910 ("python-numpy" ,python2-numpy)
4913 `(("python-nose" ,python2-nose)))
4914 (home-page "http://rseqc.sourceforge.net/")
4915 (synopsis "RNA-seq quality control package")
4917 "RSeQC provides a number of modules that can comprehensively evaluate
4918 high throughput sequence data, especially RNA-seq data. Some basic modules
4919 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4920 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4921 distribution, coverage uniformity, strand specificity, etc.")
4922 (license license:gpl3+)))
4925 ;; There are no release tarballs. According to the installation
4926 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4927 ;; stable release is identified by this changeset ID.
4928 (let ((changeset "2329130")
4932 (version (string-append "0-" revision "." changeset))
4936 (url "https://bitbucket.org/libsleipnir/sleipnir")
4937 (changeset changeset)))
4938 (file-name (string-append name "-" version "-checkout"))
4941 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4942 (build-system gnu-build-system)
4944 `(#:modules ((srfi srfi-1)
4945 (guix build gnu-build-system)
4948 (let ((dirs '("SeekMiner"
4954 (modify-phases %standard-phases
4957 (invoke "bash" "gen_auto")))
4958 (add-after 'build 'build-additional-tools
4959 (lambda* (#:key make-flags #:allow-other-keys)
4960 (every (lambda (dir)
4961 (with-directory-excursion (string-append "tools/" dir)
4962 (zero? (apply system* "make" make-flags))))
4964 (add-after 'install 'install-additional-tools
4965 (lambda* (#:key make-flags #:allow-other-keys)
4966 (fold (lambda (dir result)
4967 (with-directory-excursion (string-append "tools/" dir)
4969 (zero? (apply system*
4970 `("make" ,@make-flags "install"))))))
4976 ("readline" ,readline)
4977 ("gengetopt" ,gengetopt)
4978 ("log4cpp" ,log4cpp)))
4980 `(("autoconf" ,autoconf)
4981 ("automake" ,automake)
4983 (home-page "http://seek.princeton.edu")
4984 (synopsis "Gene co-expression search engine")
4986 "SEEK is a computational gene co-expression search engine. SEEK provides
4987 biologists with a way to navigate the massive human expression compendium that
4988 now contains thousands of expression datasets. SEEK returns a robust ranking
4989 of co-expressed genes in the biological area of interest defined by the user's
4990 query genes. It also prioritizes thousands of expression datasets according
4991 to the user's query of interest.")
4992 (license license:cc-by3.0))))
4994 (define-public samtools
5002 (string-append "mirror://sourceforge/samtools/samtools/"
5003 version "/samtools-" version ".tar.bz2"))
5006 "05myg7bs90i68qbqab9cdg9rqj2xh39azibrx82ipzc5kcfvqhn9"))))
5007 (build-system gnu-build-system)
5009 `(#:modules ((ice-9 ftw)
5011 (guix build gnu-build-system)
5013 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
5014 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
5016 (modify-phases %standard-phases
5017 (add-after 'unpack 'patch-tests
5019 (substitute* "test/test.pl"
5020 ;; The test script calls out to /bin/bash
5021 (("/bin/bash") (which "bash")))
5023 (add-after 'install 'install-library
5024 (lambda* (#:key outputs #:allow-other-keys)
5025 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5026 (install-file "libbam.a" lib)
5028 (add-after 'install 'install-headers
5029 (lambda* (#:key outputs #:allow-other-keys)
5030 (let ((include (string-append (assoc-ref outputs "out")
5031 "/include/samtools/")))
5032 (for-each (lambda (file)
5033 (install-file file include))
5034 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5036 (native-inputs `(("pkg-config" ,pkg-config)))
5038 `(("htslib" ,htslib)
5039 ("ncurses" ,ncurses)
5043 (home-page "http://samtools.sourceforge.net")
5044 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5046 "Samtools implements various utilities for post-processing nucleotide
5047 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5048 variant calling (in conjunction with bcftools), and a simple alignment
5050 (license license:expat)))
5052 (define-public samtools-0.1
5053 ;; This is the most recent version of the 0.1 line of samtools. The input
5054 ;; and output formats differ greatly from that used and produced by samtools
5055 ;; 1.x and is still used in many bioinformatics pipelines.
5056 (package (inherit samtools)
5062 (string-append "mirror://sourceforge/samtools/samtools/"
5063 version "/samtools-" version ".tar.bz2"))
5065 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5067 `(#:tests? #f ;no "check" target
5068 ,@(substitute-keyword-arguments (package-arguments samtools)
5069 ((#:make-flags flags)
5070 `(cons "LIBCURSES=-lncurses" ,flags))
5072 `(modify-phases ,phases
5074 (lambda* (#:key outputs #:allow-other-keys)
5075 (let ((bin (string-append
5076 (assoc-ref outputs "out") "/bin")))
5078 (install-file "samtools" bin)
5080 (delete 'patch-tests)
5081 (delete 'configure))))))))
5083 (define-public mosaik
5084 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5089 ;; There are no release tarballs nor tags.
5092 (url "https://github.com/wanpinglee/MOSAIK.git")
5094 (file-name (string-append name "-" version))
5097 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5098 (build-system gnu-build-system)
5100 `(#:tests? #f ; no tests
5101 #:make-flags (list "CC=gcc")
5103 (modify-phases %standard-phases
5105 (lambda _ (chdir "src") #t))
5107 (lambda* (#:key outputs #:allow-other-keys)
5108 (let ((bin (string-append (assoc-ref outputs "out")
5111 (copy-recursively "../bin" bin)
5116 (supported-systems '("x86_64-linux"))
5117 (home-page "https://github.com/wanpinglee/MOSAIK")
5118 (synopsis "Map nucleotide sequence reads to reference genomes")
5120 "MOSAIK is a program for mapping second and third-generation sequencing
5121 reads to a reference genome. MOSAIK can align reads generated by all the
5122 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5123 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5124 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5125 ;; code released into the public domain:
5126 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5127 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5128 (license (list license:gpl2+ license:public-domain)))))
5130 (define-public ngs-sdk
5138 (string-append "https://github.com/ncbi/ngs/archive/"
5140 (file-name (string-append name "-" version ".tar.gz"))
5143 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5144 (build-system gnu-build-system)
5146 `(#:parallel-build? #f ; not supported
5147 #:tests? #f ; no "check" target
5149 (modify-phases %standard-phases
5151 (lambda* (#:key outputs #:allow-other-keys)
5152 (let ((out (assoc-ref outputs "out")))
5153 ;; Allow 'konfigure.perl' to find 'package.prl'.
5155 (string-append ".:" (getenv "PERL5LIB")))
5157 ;; The 'configure' script doesn't recognize things like
5158 ;; '--enable-fast-install'.
5159 (zero? (system* "./configure"
5160 (string-append "--build-prefix=" (getcwd) "/build")
5161 (string-append "--prefix=" out))))))
5162 (add-after 'unpack 'enter-dir
5163 (lambda _ (chdir "ngs-sdk") #t)))))
5164 (native-inputs `(("perl" ,perl)))
5165 ;; According to the test
5166 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5167 ;; in ngs-sdk/setup/konfigure.perl
5168 (supported-systems '("i686-linux" "x86_64-linux"))
5169 (home-page "https://github.com/ncbi/ngs")
5170 (synopsis "API for accessing Next Generation Sequencing data")
5172 "NGS is a domain-specific API for accessing reads, alignments and pileups
5173 produced from Next Generation Sequencing. The API itself is independent from
5174 any particular back-end implementation, and supports use of multiple back-ends
5176 (license license:public-domain)))
5178 (define-public java-ngs
5179 (package (inherit ngs-sdk)
5182 `(,@(substitute-keyword-arguments
5183 `(#:modules ((guix build gnu-build-system)
5187 ,@(package-arguments ngs-sdk))
5189 `(modify-phases ,phases
5190 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5192 `(("jdk" ,icedtea "jdk")
5193 ("ngs-sdk" ,ngs-sdk)))
5194 (synopsis "Java bindings for NGS SDK")))
5196 (define-public ncbi-vdb
5204 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5206 (file-name (string-append name "-" version ".tar.gz"))
5209 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5210 (build-system gnu-build-system)
5212 `(#:parallel-build? #f ; not supported
5213 #:tests? #f ; no "check" target
5215 (modify-phases %standard-phases
5216 (add-before 'configure 'set-perl-search-path
5218 ;; Work around "dotless @INC" build failure.
5220 (string-append (getcwd) "/setup:"
5221 (getenv "PERL5LIB")))
5224 (lambda* (#:key inputs outputs #:allow-other-keys)
5225 (let ((out (assoc-ref outputs "out")))
5226 ;; Override include path for libmagic
5227 (substitute* "setup/package.prl"
5228 (("name => 'magic', Include => '/usr/include'")
5229 (string-append "name=> 'magic', Include => '"
5230 (assoc-ref inputs "libmagic")
5233 ;; Install kdf5 library (needed by sra-tools)
5234 (substitute* "build/Makefile.install"
5235 (("LIBRARIES_TO_INSTALL =")
5236 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5238 (substitute* "build/Makefile.env"
5239 (("CFLAGS =" prefix)
5240 (string-append prefix "-msse2 ")))
5242 ;; Override search path for ngs-java
5243 (substitute* "setup/package.prl"
5244 (("/usr/local/ngs/ngs-java")
5245 (assoc-ref inputs "java-ngs")))
5247 ;; The 'configure' script doesn't recognize things like
5248 ;; '--enable-fast-install'.
5251 (string-append "--build-prefix=" (getcwd) "/build")
5252 (string-append "--prefix=" (assoc-ref outputs "out"))
5253 (string-append "--debug")
5254 (string-append "--with-xml2-prefix="
5255 (assoc-ref inputs "libxml2"))
5256 (string-append "--with-ngs-sdk-prefix="
5257 (assoc-ref inputs "ngs-sdk"))
5258 (string-append "--with-hdf5-prefix="
5259 (assoc-ref inputs "hdf5")))))))
5260 (add-after 'install 'install-interfaces
5261 (lambda* (#:key outputs #:allow-other-keys)
5262 ;; Install interface libraries. On i686 the interface libraries
5263 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5264 ;; architecture name ("i386") instead of the target system prefix
5266 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5267 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5268 ,(system->linux-architecture
5269 (or (%current-target-system)
5272 (string-append (assoc-ref outputs "out")
5274 ;; Install interface headers
5275 (copy-recursively "interfaces"
5276 (string-append (assoc-ref outputs "out")
5279 ;; These files are needed by sra-tools.
5280 (add-after 'install 'install-configuration-files
5281 (lambda* (#:key outputs #:allow-other-keys)
5282 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5284 (install-file "libs/kfg/default.kfg" target)
5285 (install-file "libs/kfg/certs.kfg" target))
5288 `(("libxml2" ,libxml2)
5289 ("ngs-sdk" ,ngs-sdk)
5290 ("java-ngs" ,java-ngs)
5293 (native-inputs `(("perl" ,perl)))
5294 ;; NCBI-VDB requires SSE capability.
5295 (supported-systems '("i686-linux" "x86_64-linux"))
5296 (home-page "https://github.com/ncbi/ncbi-vdb")
5297 (synopsis "Database engine for genetic information")
5299 "The NCBI-VDB library implements a highly compressed columnar data
5300 warehousing engine that is most often used to store genetic information.
5301 Databases are stored in a portable image within the file system, and can be
5302 accessed/downloaded on demand across HTTP.")
5303 (license license:public-domain)))
5305 (define-public plink
5313 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5314 version "-src.zip"))
5316 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5317 (patches (search-patches "plink-1.07-unclobber-i.patch"
5318 "plink-endian-detection.patch"))))
5319 (build-system gnu-build-system)
5321 '(#:tests? #f ;no "check" target
5322 #:make-flags (list (string-append "LIB_LAPACK="
5323 (assoc-ref %build-inputs "lapack")
5324 "/lib/liblapack.so")
5327 ;; disable phoning home
5330 (modify-phases %standard-phases
5331 ;; no "configure" script
5334 (lambda* (#:key outputs #:allow-other-keys)
5335 (let ((bin (string-append (assoc-ref outputs "out")
5337 (install-file "plink" bin)
5341 ("lapack" ,lapack)))
5343 `(("unzip" ,unzip)))
5344 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5345 (synopsis "Whole genome association analysis toolset")
5347 "PLINK is a whole genome association analysis toolset, designed to
5348 perform a range of basic, large-scale analyses in a computationally efficient
5349 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5350 so there is no support for steps prior to this (e.g. study design and
5351 planning, generating genotype or CNV calls from raw data). Through
5352 integration with gPLINK and Haploview, there is some support for the
5353 subsequent visualization, annotation and storage of results.")
5354 ;; Code is released under GPLv2, except for fisher.h, which is under
5356 (license (list license:gpl2 license:lgpl2.1+))))
5358 (define-public plink-ng
5359 (package (inherit plink)
5365 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5367 (file-name (string-append name "-" version ".tar.gz"))
5369 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5370 (build-system gnu-build-system)
5372 '(#:tests? #f ;no "check" target
5373 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5374 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5376 "-f" "Makefile.std")
5378 (modify-phases %standard-phases
5379 (add-after 'unpack 'chdir
5380 (lambda _ (chdir "1.9") #t))
5381 (delete 'configure) ; no "configure" script
5383 (lambda* (#:key outputs #:allow-other-keys)
5384 (let ((bin (string-append (assoc-ref outputs "out")
5386 (install-file "plink" bin)
5391 ("openblas" ,openblas)))
5392 (home-page "https://www.cog-genomics.org/plink/")
5393 (license license:gpl3+)))
5395 (define-public smithlab-cpp
5396 (let ((revision "1")
5397 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5399 (name "smithlab-cpp")
5400 (version (string-append "0." revision "." (string-take commit 7)))
5404 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5406 (file-name (string-append name "-" version "-checkout"))
5409 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5410 (build-system gnu-build-system)
5412 `(#:modules ((guix build gnu-build-system)
5415 #:tests? #f ;no "check" target
5417 (modify-phases %standard-phases
5418 (add-after 'unpack 'use-samtools-headers
5420 (substitute* '("SAM.cpp"
5422 (("sam.h") "samtools/sam.h"))
5425 (lambda* (#:key outputs #:allow-other-keys)
5426 (let* ((out (assoc-ref outputs "out"))
5427 (lib (string-append out "/lib"))
5428 (include (string-append out "/include/smithlab-cpp")))
5431 (for-each (cut install-file <> lib)
5432 (find-files "." "\\.o$"))
5433 (for-each (cut install-file <> include)
5434 (find-files "." "\\.hpp$")))
5436 (delete 'configure))))
5438 `(("samtools" ,samtools-0.1)
5440 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5441 (synopsis "C++ helper library for functions used in Smith lab projects")
5443 "Smithlab CPP is a C++ library that includes functions used in many of
5444 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5445 structures, classes for genomic regions, mapped sequencing reads, etc.")
5446 (license license:gpl3+))))
5448 (define-public preseq
5454 (uri (string-append "https://github.com/smithlabcode/"
5455 "preseq/archive/v" version ".tar.gz"))
5456 (file-name (string-append name "-" version ".tar.gz"))
5458 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5459 (modules '((guix build utils)))
5461 ;; Remove bundled samtools.
5462 (delete-file-recursively "samtools")
5464 (build-system gnu-build-system)
5466 `(#:tests? #f ;no "check" target
5468 (modify-phases %standard-phases
5469 (delete 'configure))
5471 (list (string-append "PREFIX="
5472 (assoc-ref %outputs "out"))
5473 (string-append "LIBBAM="
5474 (assoc-ref %build-inputs "samtools")
5476 (string-append "SMITHLAB_CPP="
5477 (assoc-ref %build-inputs "smithlab-cpp")
5480 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5483 ("samtools" ,samtools-0.1)
5484 ("smithlab-cpp" ,smithlab-cpp)
5486 (home-page "http://smithlabresearch.org/software/preseq/")
5487 (synopsis "Program for analyzing library complexity")
5489 "The preseq package is aimed at predicting and estimating the complexity
5490 of a genomic sequencing library, equivalent to predicting and estimating the
5491 number of redundant reads from a given sequencing depth and how many will be
5492 expected from additional sequencing using an initial sequencing experiment.
5493 The estimates can then be used to examine the utility of further sequencing,
5494 optimize the sequencing depth, or to screen multiple libraries to avoid low
5495 complexity samples.")
5496 (license license:gpl3+)))
5498 (define-public python-screed
5500 (name "python-screed")
5505 (uri (pypi-uri "screed" version))
5508 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5509 (build-system python-build-system)
5512 (modify-phases %standard-phases
5515 (setenv "PYTHONPATH"
5516 (string-append (getenv "PYTHONPATH") ":."))
5517 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5519 `(("python-nose" ,python-nose)))
5521 `(("python-bz2file" ,python-bz2file)))
5522 (home-page "https://github.com/dib-lab/screed/")
5523 (synopsis "Short read sequence database utilities")
5524 (description "Screed parses FASTA and FASTQ files and generates databases.
5525 Values such as sequence name, sequence description, sequence quality and the
5526 sequence itself can be retrieved from these databases.")
5527 (license license:bsd-3)))
5529 (define-public python2-screed
5530 (package-with-python2 python-screed))
5532 (define-public sra-tools
5540 (string-append "https://github.com/ncbi/sra-tools/archive/"
5542 (file-name (string-append name "-" version ".tar.gz"))
5545 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5546 (build-system gnu-build-system)
5548 `(#:parallel-build? #f ; not supported
5549 #:tests? #f ; no "check" target
5551 (list (string-append "DEFAULT_CRT="
5552 (assoc-ref %build-inputs "ncbi-vdb")
5554 (string-append "DEFAULT_KFG="
5555 (assoc-ref %build-inputs "ncbi-vdb")
5557 (string-append "VDB_LIBDIR="
5558 (assoc-ref %build-inputs "ncbi-vdb")
5559 ,(if (string-prefix? "x86_64"
5560 (or (%current-target-system)
5565 (modify-phases %standard-phases
5566 (add-before 'configure 'set-perl-search-path
5568 ;; Work around "dotless @INC" build failure.
5570 (string-append (getcwd) "/setup:"
5571 (getenv "PERL5LIB")))
5574 (lambda* (#:key inputs outputs #:allow-other-keys)
5575 ;; The build system expects a directory containing the sources and
5576 ;; raw build output of ncbi-vdb, including files that are not
5577 ;; installed. Since we are building against an installed version of
5578 ;; ncbi-vdb, the following modifications are needed.
5579 (substitute* "setup/konfigure.perl"
5580 ;; Make the configure script look for the "ilib" directory of
5581 ;; "ncbi-vdb" without first checking for the existence of a
5582 ;; matching library in its "lib" directory.
5583 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5584 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5585 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5586 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5587 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5590 (substitute* "tools/copycat/Makefile"
5591 (("smagic-static") "lmagic"))
5593 ;; The 'configure' script doesn't recognize things like
5594 ;; '--enable-fast-install'.
5597 (string-append "--build-prefix=" (getcwd) "/build")
5598 (string-append "--prefix=" (assoc-ref outputs "out"))
5599 (string-append "--debug")
5600 (string-append "--with-fuse-prefix="
5601 (assoc-ref inputs "fuse"))
5602 (string-append "--with-magic-prefix="
5603 (assoc-ref inputs "libmagic"))
5604 ;; TODO: building with libxml2 fails with linker errors
5605 ;; (string-append "--with-xml2-prefix="
5606 ;; (assoc-ref inputs "libxml2"))
5607 (string-append "--with-ncbi-vdb-sources="
5608 (assoc-ref inputs "ncbi-vdb"))
5609 (string-append "--with-ncbi-vdb-build="
5610 (assoc-ref inputs "ncbi-vdb"))
5611 (string-append "--with-ngs-sdk-prefix="
5612 (assoc-ref inputs "ngs-sdk"))
5613 (string-append "--with-hdf5-prefix="
5614 (assoc-ref inputs "hdf5"))))))
5615 ;; This version of sra-tools fails to build with glibc because of a
5616 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5617 ;; contains a definition of "canonicalize", so we rename it.
5619 ;; See upstream bug report:
5620 ;; https://github.com/ncbi/sra-tools/issues/67
5621 (add-after 'unpack 'patch-away-glibc-conflict
5623 (substitute* "tools/bam-loader/bam.c"
5624 (("canonicalize\\(" line)
5625 (string-append "sra_tools_" line)))
5627 (native-inputs `(("perl" ,perl)))
5629 `(("ngs-sdk" ,ngs-sdk)
5630 ("ncbi-vdb" ,ncbi-vdb)
5635 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5636 (synopsis "Tools and libraries for reading and writing sequencing data")
5638 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5639 reading of sequencing files from the Sequence Read Archive (SRA) database and
5640 writing files into the .sra format.")
5641 (license license:public-domain)))
5643 (define-public seqan
5649 (uri (string-append "http://packages.seqan.de/seqan-library/"
5650 "seqan-library-" version ".tar.bz2"))
5653 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5654 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5655 ;; makes sense to split the outputs.
5656 (outputs '("out" "doc"))
5657 (build-system trivial-build-system)
5659 `(#:modules ((guix build utils))
5662 (use-modules (guix build utils))
5663 (let ((tar (assoc-ref %build-inputs "tar"))
5664 (bzip (assoc-ref %build-inputs "bzip2"))
5665 (out (assoc-ref %outputs "out"))
5666 (doc (assoc-ref %outputs "doc")))
5667 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5668 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5669 (chdir (string-append "seqan-library-" ,version))
5670 (copy-recursively "include" (string-append out "/include"))
5671 (copy-recursively "share" (string-append doc "/share"))
5674 `(("source" ,source)
5677 (home-page "http://www.seqan.de")
5678 (synopsis "Library for nucleotide sequence analysis")
5680 "SeqAn is a C++ library of efficient algorithms and data structures for
5681 the analysis of sequences with the focus on biological data. It contains
5682 algorithms and data structures for string representation and their
5683 manipulation, online and indexed string search, efficient I/O of
5684 bioinformatics file formats, sequence alignment, and more.")
5685 (license license:bsd-3)))
5687 (define-public seqmagick
5694 (uri (pypi-uri "seqmagick" version))
5697 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5698 (build-system python-build-system)
5700 `(("python-biopython" ,python-biopython)))
5702 `(("python-nose" ,python-nose)))
5703 (home-page "https://github.com/fhcrc/seqmagick")
5704 (synopsis "Tools for converting and modifying sequence files")
5706 "Bioinformaticians often have to convert sequence files between formats
5707 and do little manipulations on them, and it's not worth writing scripts for
5708 that. Seqmagick is a utility to expose the file format conversion in
5709 BioPython in a convenient way. Instead of having a big mess of scripts, there
5710 is one that takes arguments.")
5711 (license license:gpl3)))
5713 (define-public seqtk
5720 "https://github.com/lh3/seqtk/archive/v"
5722 (file-name (string-append name "-" version ".tar.gz"))
5725 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5726 (modules '((guix build utils)))
5729 ;; Remove extraneous header files, as is done in the seqtk
5731 (for-each (lambda (file) (delete-file file))
5732 (list "ksort.h" "kstring.h" "kvec.h"))
5734 (build-system gnu-build-system)
5737 (modify-phases %standard-phases
5740 ;; There are no tests, so we just run a sanity check.
5741 (lambda _ (zero? (system* "./seqtk" "seq"))))
5743 (lambda* (#:key outputs #:allow-other-keys)
5744 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5745 (install-file "seqtk" bin)))))))
5748 (home-page "https://github.com/lh3/seqtk")
5749 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5751 "Seqtk is a fast and lightweight tool for processing sequences in the
5752 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5753 optionally compressed by gzip.")
5754 (license license:expat)))
5756 (define-public snap-aligner
5758 (name "snap-aligner")
5759 (version "1.0beta.18")
5763 "https://github.com/amplab/snap/archive/v"
5765 (file-name (string-append name "-" version ".tar.gz"))
5768 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5769 (build-system gnu-build-system)
5772 (modify-phases %standard-phases
5774 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5776 (lambda* (#:key outputs #:allow-other-keys)
5777 (let* ((out (assoc-ref outputs "out"))
5778 (bin (string-append out "/bin")))
5779 (install-file "snap-aligner" bin)
5780 (install-file "SNAPCommand" bin)
5784 (home-page "http://snap.cs.berkeley.edu/")
5785 (synopsis "Short read DNA sequence aligner")
5787 "SNAP is a fast and accurate aligner for short DNA reads. It is
5788 optimized for modern read lengths of 100 bases or higher, and takes advantage
5789 of these reads to align data quickly through a hash-based indexing scheme.")
5790 ;; 32-bit systems are not supported by the unpatched code.
5791 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5792 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5793 ;; systems without a lot of memory cannot make good use of this program.
5794 (supported-systems '("x86_64-linux"))
5795 (license license:asl2.0)))
5797 (define-public sortmerna
5805 "https://github.com/biocore/sortmerna/archive/"
5807 (file-name (string-append name "-" version ".tar.gz"))
5810 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5811 (build-system gnu-build-system)
5812 (outputs '("out" ;for binaries
5813 "db")) ;for sequence databases
5816 (modify-phases %standard-phases
5818 (lambda* (#:key outputs #:allow-other-keys)
5819 (let* ((out (assoc-ref outputs "out"))
5820 (bin (string-append out "/bin"))
5821 (db (assoc-ref outputs "db"))
5823 (string-append db "/share/sortmerna/rRNA_databases")))
5824 (install-file "sortmerna" bin)
5825 (install-file "indexdb_rna" bin)
5826 (for-each (lambda (file)
5827 (install-file file share))
5828 (find-files "rRNA_databases" ".*fasta"))
5832 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5833 (synopsis "Biological sequence analysis tool for NGS reads")
5835 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5836 and operational taxonomic unit (OTU) picking of next generation
5837 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5838 allows for fast and sensitive analyses of nucleotide sequences. The main
5839 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5840 ;; The source includes x86 specific code
5841 (supported-systems '("x86_64-linux" "i686-linux"))
5842 (license license:lgpl3)))
5851 (url "https://github.com/alexdobin/STAR.git")
5853 (file-name (string-append name "-" version "-checkout"))
5856 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
5857 (modules '((guix build utils)))
5860 (substitute* "source/Makefile"
5862 ;; Remove pre-built binaries and bundled htslib sources.
5863 (delete-file-recursively "bin/MacOSX_x86_64")
5864 (delete-file-recursively "bin/Linux_x86_64")
5865 (delete-file-recursively "bin/Linux_x86_64_static")
5866 (delete-file-recursively "source/htslib")
5868 (build-system gnu-build-system)
5870 '(#:tests? #f ;no check target
5871 #:make-flags '("STAR")
5873 (modify-phases %standard-phases
5874 (add-after 'unpack 'enter-source-dir
5875 (lambda _ (chdir "source") #t))
5876 (add-after 'enter-source-dir 'make-reproducible
5878 (substitute* "Makefile"
5879 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5880 (string-append pre "Built with Guix" post)))))
5881 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5883 (substitute* "Makefile"
5884 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5886 (substitute* '("BAMfunctions.cpp"
5891 "bamRemoveDuplicates.cpp")
5892 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5893 (string-append "#include <" header ">")))
5894 (substitute* "IncludeDefine.h"
5895 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5896 (string-append "<" header ">")))
5899 (lambda* (#:key outputs #:allow-other-keys)
5900 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5901 (install-file "STAR" bin))
5903 (delete 'configure))))
5907 `(("htslib" ,htslib)
5909 (home-page "https://github.com/alexdobin/STAR")
5910 (synopsis "Universal RNA-seq aligner")
5912 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5913 based on a previously undescribed RNA-seq alignment algorithm that uses
5914 sequential maximum mappable seed search in uncompressed suffix arrays followed
5915 by seed clustering and stitching procedure. In addition to unbiased de novo
5916 detection of canonical junctions, STAR can discover non-canonical splices and
5917 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5919 ;; Only 64-bit systems are supported according to the README.
5920 (supported-systems '("x86_64-linux" "mips64el-linux"))
5921 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5922 (license license:gpl3+)))
5924 (define-public subread
5930 (uri (string-append "mirror://sourceforge/subread/subread-"
5931 version "/subread-" version "-source.tar.gz"))
5934 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5935 (build-system gnu-build-system)
5937 `(#:tests? #f ;no "check" target
5938 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5939 ;; optimizations by default, so we override these flags such that x86_64
5940 ;; flags are only added when the build target is an x86_64 system.
5942 (list (let ((system ,(or (%current-target-system)
5944 (flags '("-ggdb" "-fomit-frame-pointer"
5945 "-ffast-math" "-funroll-loops"
5946 "-fmessage-length=0"
5947 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5949 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5950 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5951 (if (string-prefix? "x86_64" system)
5952 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5953 (string-append "CCFLAGS=" (string-join flags))))
5954 "-f" "Makefile.Linux"
5955 "CC=gcc ${CCFLAGS}")
5957 (modify-phases %standard-phases
5958 (add-after 'unpack 'enter-dir
5959 (lambda _ (chdir "src") #t))
5961 (lambda* (#:key outputs #:allow-other-keys)
5962 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5964 (copy-recursively "../bin" bin))))
5965 ;; no "configure" script
5966 (delete 'configure))))
5967 (inputs `(("zlib" ,zlib)))
5968 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5969 (synopsis "Tool kit for processing next-gen sequencing data")
5971 "The subread package contains the following tools: subread aligner, a
5972 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5973 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5974 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5975 against local background noises.")
5976 (license license:gpl3+)))
5978 (define-public stringtie
5984 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5985 "stringtie-" version ".tar.gz"))
5988 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5989 (modules '((guix build utils)))
5992 (delete-file-recursively "samtools-0.1.18")
5994 (build-system gnu-build-system)
5996 `(#:tests? #f ;no test suite
5998 (modify-phases %standard-phases
5999 ;; no configure script
6001 (add-before 'build 'use-system-samtools
6003 (substitute* "Makefile"
6004 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6006 (substitute* '("gclib/GBam.h"
6008 (("#include \"(bam|sam|kstring).h\"" _ header)
6009 (string-append "#include <samtools/" header ".h>")))
6011 (add-after 'unpack 'remove-duplicate-typedef
6013 ;; This typedef conflicts with the typedef in
6014 ;; glibc-2.25/include/bits/types.h
6015 (substitute* "gclib/GThreads.h"
6016 (("typedef long long __intmax_t;") ""))
6019 (lambda* (#:key outputs #:allow-other-keys)
6020 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6021 (install-file "stringtie" bin)
6024 `(("samtools" ,samtools-0.1)
6026 (home-page "http://ccb.jhu.edu/software/stringtie/")
6027 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6029 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6030 alignments into potential transcripts. It uses a novel network flow algorithm
6031 as well as an optional de novo assembly step to assemble and quantitate
6032 full-length transcripts representing multiple splice variants for each gene
6033 locus. Its input can include not only the alignments of raw reads used by
6034 other transcript assemblers, but also alignments of longer sequences that have
6035 been assembled from those reads. To identify differentially expressed genes
6036 between experiments, StringTie's output can be processed either by the
6037 Cuffdiff or Ballgown programs.")
6038 (license license:artistic2.0)))
6040 (define-public taxtastic
6046 (uri (pypi-uri "taxtastic" version))
6049 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6050 (build-system python-build-system)
6052 `(#:python ,python-2
6054 (modify-phases %standard-phases
6057 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
6059 `(("python-sqlalchemy" ,python2-sqlalchemy)
6060 ("python-decorator" ,python2-decorator)
6061 ("python-biopython" ,python2-biopython)
6062 ("python-pandas" ,python2-pandas)
6063 ("python-psycopg2" ,python2-psycopg2)
6064 ("python-fastalite" ,python2-fastalite)
6065 ("python-pyyaml" ,python2-pyyaml)
6066 ("python-six" ,python2-six)
6067 ("python-jinja2" ,python2-jinja2)
6068 ("python-dendropy" ,python2-dendropy)))
6069 (home-page "https://github.com/fhcrc/taxtastic")
6070 (synopsis "Tools for taxonomic naming and annotation")
6072 "Taxtastic is software written in python used to build and maintain
6073 reference packages i.e. collections of reference trees, reference alignments,
6074 profiles, and associated taxonomic information.")
6075 (license license:gpl3+)))
6077 (define-public vcftools
6084 "https://github.com/vcftools/vcftools/releases/download/v"
6085 version "/vcftools-" version ".tar.gz"))
6088 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6089 (build-system gnu-build-system)
6091 `(#:tests? #f ; no "check" target
6093 "CFLAGS=-O2" ; override "-m64" flag
6094 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6095 (string-append "MANDIR=" (assoc-ref %outputs "out")
6096 "/share/man/man1"))))
6098 `(("pkg-config" ,pkg-config)))
6102 (home-page "https://vcftools.github.io/")
6103 (synopsis "Tools for working with VCF files")
6105 "VCFtools is a program package designed for working with VCF files, such
6106 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6107 provide easily accessible methods for working with complex genetic variation
6108 data in the form of VCF files.")
6109 ;; The license is declared as LGPLv3 in the README and
6110 ;; at https://vcftools.github.io/license.html
6111 (license license:lgpl3)))
6113 (define-public infernal
6119 (uri (string-append "http://eddylab.org/software/infernal/"
6120 "infernal-" version ".tar.gz"))
6123 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6124 (build-system gnu-build-system)
6126 `(("perl" ,perl))) ; for tests
6127 (home-page "http://eddylab.org/infernal/")
6128 (synopsis "Inference of RNA alignments")
6129 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6130 searching DNA sequence databases for RNA structure and sequence similarities.
6131 It is an implementation of a special case of profile stochastic context-free
6132 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6133 profile, but it scores a combination of sequence consensus and RNA secondary
6134 structure consensus, so in many cases, it is more capable of identifying RNA
6135 homologs that conserve their secondary structure more than their primary
6137 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6138 (supported-systems '("i686-linux" "x86_64-linux"))
6139 (license license:bsd-3)))
6141 (define-public r-centipede
6143 (name "r-centipede")
6147 (uri (string-append "http://download.r-forge.r-project.org/"
6148 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6151 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6152 (build-system r-build-system)
6153 (home-page "http://centipede.uchicago.edu/")
6154 (synopsis "Predict transcription factor binding sites")
6156 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6157 of the genome that are bound by particular transcription factors. It starts
6158 by identifying a set of candidate binding sites, and then aims to classify the
6159 sites according to whether each site is bound or not bound by a transcription
6160 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6161 between two different types of motif instances using as much relevant
6162 information as possible.")
6163 (license (list license:gpl2+ license:gpl3+))))
6165 (define-public r-vegan
6172 (uri (cran-uri "vegan" version))
6175 "13pyqvlpz64qibi8k5d109v7q09j06mbv6ndix3n4cn21mjx391c"))))
6176 (build-system r-build-system)
6178 `(("gfortran" ,gfortran)))
6180 `(("r-cluster" ,r-cluster)
6181 ("r-knitr" ,r-knitr) ; needed for vignettes
6182 ("r-lattice" ,r-lattice)
6185 ("r-permute" ,r-permute)))
6186 (home-page "https://cran.r-project.org/web/packages/vegan")
6187 (synopsis "Functions for community ecology")
6189 "The vegan package provides tools for descriptive community ecology. It
6190 has most basic functions of diversity analysis, community ordination and
6191 dissimilarity analysis. Most of its multivariate tools can be used for other
6192 data types as well.")
6193 (license license:gpl2+)))
6195 (define-public r-annotate
6202 (uri (bioconductor-uri "annotate" version))
6205 "1qmncyvy147a1ll3iri45p822kcs3s7583jfnq9jf6sz9ilk8cjf"))))
6206 (build-system r-build-system)
6208 `(("r-annotationdbi" ,r-annotationdbi)
6209 ("r-biobase" ,r-biobase)
6210 ("r-biocgenerics" ,r-biocgenerics)
6212 ("r-rcurl" ,r-rcurl)
6214 ("r-xtable" ,r-xtable)))
6216 "https://bioconductor.org/packages/annotate")
6217 (synopsis "Annotation for microarrays")
6218 (description "This package provides R environments for the annotation of
6220 (license license:artistic2.0)))
6222 (define-public r-copynumber
6224 (name "r-copynumber")
6228 (uri (bioconductor-uri "copynumber" version))
6231 "0y9nnwb0psphp3ix88wj2f8z5gr45r5znf55w892ysm27isdpmms"))))
6232 (build-system r-build-system)
6234 `(("r-s4vectors" ,r-s4vectors)
6235 ("r-iranges" ,r-iranges)
6236 ("r-genomicranges" ,r-genomicranges)
6237 ("r-biocgenerics" ,r-biocgenerics)))
6238 (home-page "https://bioconductor.org/packages/copynumber")
6239 (synopsis "Segmentation of single- and multi-track copy number data")
6241 "This package segments single- and multi-track copy number data by a
6242 penalized least squares regression method.")
6243 (license license:artistic2.0)))
6245 (define-public r-geneplotter
6247 (name "r-geneplotter")
6252 (uri (bioconductor-uri "geneplotter" version))
6255 "055g28xgiazl4l0gkg8xiamks64f5yckjjyvw1abd6d6qjavwx0g"))))
6256 (build-system r-build-system)
6258 `(("r-annotate" ,r-annotate)
6259 ("r-annotationdbi" ,r-annotationdbi)
6260 ("r-biobase" ,r-biobase)
6261 ("r-biocgenerics" ,r-biocgenerics)
6262 ("r-lattice" ,r-lattice)
6263 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6264 (home-page "https://bioconductor.org/packages/geneplotter")
6265 (synopsis "Graphics functions for genomic data")
6267 "This package provides functions for plotting genomic data.")
6268 (license license:artistic2.0)))
6270 (define-public r-genefilter
6272 (name "r-genefilter")
6277 (uri (bioconductor-uri "genefilter" version))
6280 "14l0ff02spmjwxj0m1czhg5vlkgwcfi73cym8m2n9vn6i7bjdaqi"))))
6281 (build-system r-build-system)
6283 `(("gfortran" ,gfortran)))
6285 `(("r-annotate" ,r-annotate)
6286 ("r-annotationdbi" ,r-annotationdbi)
6287 ("r-biobase" ,r-biobase)
6288 ("r-s4vectors" ,r-s4vectors)
6289 ("r-survival" ,r-survival)))
6290 (home-page "https://bioconductor.org/packages/genefilter")
6291 (synopsis "Filter genes from high-throughput experiments")
6293 "This package provides basic functions for filtering genes from
6294 high-throughput sequencing experiments.")
6295 (license license:artistic2.0)))
6297 (define-public r-deseq2
6304 (uri (bioconductor-uri "DESeq2" version))
6307 "1wjnfpb41a9mmf9a22bz4zh7r1d4id50vpdc1mn5vfzrz7li9qik"))))
6308 (properties `((upstream-name . "DESeq2")))
6309 (build-system r-build-system)
6311 `(("r-biobase" ,r-biobase)
6312 ("r-biocgenerics" ,r-biocgenerics)
6313 ("r-biocparallel" ,r-biocparallel)
6314 ("r-genefilter" ,r-genefilter)
6315 ("r-geneplotter" ,r-geneplotter)
6316 ("r-genomicranges" ,r-genomicranges)
6317 ("r-ggplot2" ,r-ggplot2)
6318 ("r-hmisc" ,r-hmisc)
6319 ("r-iranges" ,r-iranges)
6320 ("r-locfit" ,r-locfit)
6322 ("r-rcpparmadillo" ,r-rcpparmadillo)
6323 ("r-s4vectors" ,r-s4vectors)
6324 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6325 (home-page "https://bioconductor.org/packages/DESeq2")
6326 (synopsis "Differential gene expression analysis")
6328 "This package provides functions to estimate variance-mean dependence in
6329 count data from high-throughput nucleotide sequencing assays and test for
6330 differential expression based on a model using the negative binomial
6332 (license license:lgpl3+)))
6334 (define-public r-dexseq
6341 (uri (bioconductor-uri "DEXSeq" version))
6344 "1mqb3mdxcsi3largsl7k27bvqrgps9ixv806xvmf29pw0xn05sg1"))))
6345 (properties `((upstream-name . "DEXSeq")))
6346 (build-system r-build-system)
6348 `(("r-annotationdbi" ,r-annotationdbi)
6349 ("r-biobase" ,r-biobase)
6350 ("r-biocgenerics" ,r-biocgenerics)
6351 ("r-biocparallel" ,r-biocparallel)
6352 ("r-biomart" ,r-biomart)
6353 ("r-deseq2" ,r-deseq2)
6354 ("r-genefilter" ,r-genefilter)
6355 ("r-geneplotter" ,r-geneplotter)
6356 ("r-genomicranges" ,r-genomicranges)
6357 ("r-hwriter" ,r-hwriter)
6358 ("r-iranges" ,r-iranges)
6359 ("r-rcolorbrewer" ,r-rcolorbrewer)
6360 ("r-rsamtools" ,r-rsamtools)
6361 ("r-s4vectors" ,r-s4vectors)
6362 ("r-statmod" ,r-statmod)
6363 ("r-stringr" ,r-stringr)
6364 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6365 (home-page "https://bioconductor.org/packages/DEXSeq")
6366 (synopsis "Inference of differential exon usage in RNA-Seq")
6368 "This package is focused on finding differential exon usage using RNA-seq
6369 exon counts between samples with different experimental designs. It provides
6370 functions that allows the user to make the necessary statistical tests based
6371 on a model that uses the negative binomial distribution to estimate the
6372 variance between biological replicates and generalized linear models for
6373 testing. The package also provides functions for the visualization and
6374 exploration of the results.")
6375 (license license:gpl3+)))
6377 (define-public r-annotationforge
6379 (name "r-annotationforge")
6384 (uri (bioconductor-uri "AnnotationForge" version))
6387 "12ffj7h95adiya5mzyjxazqn1qgr434ajpabfcyhrj5v83s4vk65"))))
6389 `((upstream-name . "AnnotationForge")))
6390 (build-system r-build-system)
6392 `(("r-annotationdbi" ,r-annotationdbi)
6393 ("r-biobase" ,r-biobase)
6394 ("r-biocgenerics" ,r-biocgenerics)
6396 ("r-rcurl" ,r-rcurl)
6397 ("r-rsqlite" ,r-rsqlite)
6398 ("r-s4vectors" ,r-s4vectors)
6400 (home-page "https://bioconductor.org/packages/AnnotationForge")
6401 (synopsis "Code for building annotation database packages")
6403 "This package provides code for generating Annotation packages and their
6404 databases. Packages produced are intended to be used with AnnotationDbi.")
6405 (license license:artistic2.0)))
6407 (define-public r-rbgl
6414 (uri (bioconductor-uri "RBGL" version))
6417 "0hj972mmqpyi5fx1rq33kysavdyz4nspi6gcffzi3rv339m0anhf"))))
6418 (properties `((upstream-name . "RBGL")))
6419 (build-system r-build-system)
6420 (propagated-inputs `(("r-graph" ,r-graph)))
6421 (home-page "https://www.bioconductor.org/packages/RBGL")
6422 (synopsis "Interface to the Boost graph library")
6424 "This package provides a fairly extensive and comprehensive interface to
6425 the graph algorithms contained in the Boost library.")
6426 (license license:artistic2.0)))
6428 (define-public r-gseabase
6435 (uri (bioconductor-uri "GSEABase" version))
6438 "11bv92svik399q677jv96b71i4bq68xxyxn1yijpdik2lq4hgl7a"))))
6439 (properties `((upstream-name . "GSEABase")))
6440 (build-system r-build-system)
6442 `(("r-annotate" ,r-annotate)
6443 ("r-annotationdbi" ,r-annotationdbi)
6444 ("r-biobase" ,r-biobase)
6445 ("r-biocgenerics" ,r-biocgenerics)
6446 ("r-graph" ,r-graph)
6448 (home-page "https://bioconductor.org/packages/GSEABase")
6449 (synopsis "Gene set enrichment data structures and methods")
6451 "This package provides classes and methods to support @dfn{Gene Set
6452 Enrichment Analysis} (GSEA).")
6453 (license license:artistic2.0)))
6455 (define-public r-category
6462 (uri (bioconductor-uri "Category" version))
6465 "03wfqa8d1dgwsm327zl2mpkq7dq3mzhq12598qz3ylfhrwplbgx0"))))
6466 (properties `((upstream-name . "Category")))
6467 (build-system r-build-system)
6469 `(("r-annotate" ,r-annotate)
6470 ("r-annotationdbi" ,r-annotationdbi)
6471 ("r-biobase" ,r-biobase)
6472 ("r-biocgenerics" ,r-biocgenerics)
6473 ("r-genefilter" ,r-genefilter)
6474 ("r-graph" ,r-graph)
6475 ("r-gseabase" ,r-gseabase)
6476 ("r-matrix" ,r-matrix)
6479 (home-page "https://bioconductor.org/packages/Category")
6480 (synopsis "Category analysis")
6482 "This package provides a collection of tools for performing category
6484 (license license:artistic2.0)))
6486 (define-public r-gostats
6493 (uri (bioconductor-uri "GOstats" version))
6496 "1i5mydz5d95w2k28qr9j01hmbnl2id55jq94jvcpcyp1pvinkdq0"))))
6497 (properties `((upstream-name . "GOstats")))
6498 (build-system r-build-system)
6500 `(("r-annotate" ,r-annotate)
6501 ("r-annotationdbi" ,r-annotationdbi)
6502 ("r-annotationforge" ,r-annotationforge)
6503 ("r-biobase" ,r-biobase)
6504 ("r-category" ,r-category)
6505 ("r-go-db" ,r-go-db)
6506 ("r-graph" ,r-graph)
6507 ("r-rgraphviz" ,r-rgraphviz)
6508 ("r-rbgl" ,r-rbgl)))
6509 (home-page "https://bioconductor.org/packages/GOstats")
6510 (synopsis "Tools for manipulating GO and microarrays")
6512 "This package provides a set of tools for interacting with GO and
6513 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6514 testing and other simple calculations.")
6515 (license license:artistic2.0)))
6517 (define-public r-shortread
6519 (name "r-shortread")
6524 (uri (bioconductor-uri "ShortRead" version))
6527 "038z3z7qaw5bpgjzy91sjkybsny6jwjjsrnnq4gdqdw9ss1qy1fb"))))
6528 (properties `((upstream-name . "ShortRead")))
6529 (build-system r-build-system)
6533 `(("r-biobase" ,r-biobase)
6534 ("r-biocgenerics" ,r-biocgenerics)
6535 ("r-biocparallel" ,r-biocparallel)
6536 ("r-biostrings" ,r-biostrings)
6537 ("r-genomeinfodb" ,r-genomeinfodb)
6538 ("r-genomicalignments" ,r-genomicalignments)
6539 ("r-genomicranges" ,r-genomicranges)
6540 ("r-hwriter" ,r-hwriter)
6541 ("r-iranges" ,r-iranges)
6542 ("r-lattice" ,r-lattice)
6543 ("r-latticeextra" ,r-latticeextra)
6544 ("r-rsamtools" ,r-rsamtools)
6545 ("r-s4vectors" ,r-s4vectors)
6546 ("r-xvector" ,r-xvector)
6547 ("r-zlibbioc" ,r-zlibbioc)))
6548 (home-page "https://bioconductor.org/packages/ShortRead")
6549 (synopsis "FASTQ input and manipulation tools")
6551 "This package implements sampling, iteration, and input of FASTQ files.
6552 It includes functions for filtering and trimming reads, and for generating a
6553 quality assessment report. Data are represented as
6554 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6555 purposes. The package also contains legacy support for early single-end,
6556 ungapped alignment formats.")
6557 (license license:artistic2.0)))
6559 (define-public r-systempiper
6561 (name "r-systempiper")
6566 (uri (bioconductor-uri "systemPipeR" version))
6569 "1550pd63mmky0vgkmpni7zf14kqz1741wv63nfaw29kcmhh3m5lm"))))
6570 (properties `((upstream-name . "systemPipeR")))
6571 (build-system r-build-system)
6573 `(("r-annotate" ,r-annotate)
6574 ("r-batchjobs" ,r-batchjobs)
6575 ("r-biocgenerics" ,r-biocgenerics)
6576 ("r-biostrings" ,r-biostrings)
6577 ("r-deseq2" ,r-deseq2)
6578 ("r-edger" ,r-edger)
6579 ("r-genomicfeatures" ,r-genomicfeatures)
6580 ("r-genomicranges" ,r-genomicranges)
6581 ("r-ggplot2" ,r-ggplot2)
6582 ("r-go-db" ,r-go-db)
6583 ("r-gostats" ,r-gostats)
6584 ("r-limma" ,r-limma)
6585 ("r-pheatmap" ,r-pheatmap)
6586 ("r-rjson" ,r-rjson)
6587 ("r-rsamtools" ,r-rsamtools)
6588 ("r-shortread" ,r-shortread)
6589 ("r-summarizedexperiment" ,r-summarizedexperiment)
6590 ("r-variantannotation" ,r-variantannotation)))
6591 (home-page "https://github.com/tgirke/systemPipeR")
6592 (synopsis "Next generation sequencing workflow and reporting environment")
6594 "This R package provides tools for building and running automated
6595 end-to-end analysis workflows for a wide range of @dfn{next generation
6596 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6597 Important features include a uniform workflow interface across different NGS
6598 applications, automated report generation, and support for running both R and
6599 command-line software, such as NGS aligners or peak/variant callers, on local
6600 computers or compute clusters. Efficient handling of complex sample sets and
6601 experimental designs is facilitated by a consistently implemented sample
6602 annotation infrastructure.")
6603 (license license:artistic2.0)))
6605 (define-public r-grohmm
6612 (uri (bioconductor-uri "groHMM" version))
6615 "1kjb14apyly44qdlx2ld6gr69wlazd4mbhs58l35hir12aphgrzp"))))
6616 (properties `((upstream-name . "groHMM")))
6617 (build-system r-build-system)
6619 `(("r-genomeinfodb" ,r-genomeinfodb)
6620 ("r-genomicalignments" ,r-genomicalignments)
6621 ("r-genomicranges" ,r-genomicranges)
6622 ("r-iranges" ,r-iranges)
6624 ("r-rtracklayer" ,r-rtracklayer)
6625 ("r-s4vectors" ,r-s4vectors)))
6626 (home-page "https://github.com/Kraus-Lab/groHMM")
6627 (synopsis "GRO-seq analysis pipeline")
6629 "This package provides a pipeline for the analysis of GRO-seq data.")
6630 (license license:gpl3+)))
6632 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6634 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6638 ;; We cannot use bioconductor-uri here because this tarball is
6639 ;; located under "data/annotation/" instead of "bioc/".
6640 (uri (string-append "https://bioconductor.org/packages/"
6641 "release/data/annotation/src/contrib"
6642 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6646 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6648 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6649 (build-system r-build-system)
6650 ;; As this package provides little more than a very large data file it
6651 ;; doesn't make sense to build substitutes.
6652 (arguments `(#:substitutable? #f))
6654 `(("r-genomicfeatures" ,r-genomicfeatures)))
6656 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6657 (synopsis "Annotation package for human genome in TxDb format")
6659 "This package provides an annotation database of Homo sapiens genome
6660 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6661 track. The database is exposed as a @code{TxDb} object.")
6662 (license license:artistic2.0)))
6664 (define-public r-sparql
6670 (uri (cran-uri "SPARQL" version))
6673 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6674 (properties `((upstream-name . "SPARQL")))
6675 (build-system r-build-system)
6677 `(("r-rcurl" ,r-rcurl)
6679 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6680 (synopsis "SPARQL client for R")
6681 (description "This package provides an interface to use SPARQL to pose
6682 SELECT or UPDATE queries to an end-point.")
6683 ;; The only license indication is found in the DESCRIPTION file,
6684 ;; which states GPL-3. So we cannot assume GPLv3+.
6685 (license license:gpl3)))
6687 (define-public vsearch
6695 "https://github.com/torognes/vsearch/archive/v"
6697 (file-name (string-append name "-" version ".tar.gz"))
6700 "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3"))
6701 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6704 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6705 ;; for this in the patch.
6706 (delete-file "src/city.h")
6707 (delete-file "src/citycrc.h")
6708 (delete-file "src/city.cc")
6710 (build-system gnu-build-system)
6713 (modify-phases %standard-phases
6714 (add-after 'unpack 'autogen
6715 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6719 ("cityhash" ,cityhash)))
6721 `(("autoconf" ,autoconf)
6722 ("automake" ,automake)))
6723 (synopsis "Sequence search tools for metagenomics")
6725 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6726 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6727 masking. The tool takes advantage of parallelism in the form of SIMD
6728 vectorization as well as multiple threads to perform accurate alignments at
6729 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6730 Needleman-Wunsch).")
6731 (home-page "https://github.com/torognes/vsearch")
6732 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6734 (supported-systems '("x86_64-linux"))
6735 ;; Dual licensed; also includes public domain source.
6736 (license (list license:gpl3 license:bsd-2))))
6738 (define-public pardre
6741 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6746 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6750 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6751 (build-system gnu-build-system)
6753 `(#:tests? #f ; no tests included
6755 (modify-phases %standard-phases
6758 (lambda* (#:key outputs #:allow-other-keys)
6759 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6760 (install-file "ParDRe" bin)
6763 `(("openmpi" ,openmpi)
6765 (synopsis "Parallel tool to remove duplicate DNA reads")
6767 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6768 Duplicate reads can be seen as identical or nearly identical sequences with
6769 some mismatches. This tool lets users avoid the analysis of unnecessary
6770 reads, reducing the time of subsequent procedures with the
6771 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6772 in order to exploit the parallel capabilities of multicore clusters. It is
6773 faster than multithreaded counterparts (end of 2015) for the same number of
6774 cores and, thanks to the message-passing technology, it can be executed on
6776 (home-page "https://sourceforge.net/projects/pardre/")
6777 (license license:gpl3+)))
6779 (define-public ruby-bio-kseq
6781 (name "ruby-bio-kseq")
6786 (uri (rubygems-uri "bio-kseq" version))
6789 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6790 (build-system ruby-build-system)
6792 `(#:test-target "spec"))
6794 `(("bundler" ,bundler)
6795 ("ruby-rspec" ,ruby-rspec)
6796 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6799 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6801 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6802 FASTQ parsing code. It provides a fast iterator over sequences and their
6804 (home-page "https://github.com/gusevfe/bio-kseq")
6805 (license license:expat)))
6807 (define-public bio-locus
6814 (uri (rubygems-uri "bio-locus" version))
6817 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6818 (build-system ruby-build-system)
6820 `(("ruby-rspec" ,ruby-rspec)))
6821 (synopsis "Tool for fast querying of genome locations")
6823 "Bio-locus is a tabix-like tool for fast querying of genome
6824 locations. Many file formats in bioinformatics contain records that
6825 start with a chromosome name and a position for a SNP, or a start-end
6826 position for indels. Bio-locus allows users to store this chr+pos or
6827 chr+pos+alt information in a database.")
6828 (home-page "https://github.com/pjotrp/bio-locus")
6829 (license license:expat)))
6831 (define-public bio-blastxmlparser
6833 (name "bio-blastxmlparser")
6837 (uri (rubygems-uri "bio-blastxmlparser" version))
6840 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6841 (build-system ruby-build-system)
6843 `(("ruby-bio-logger" ,ruby-bio-logger)
6844 ("ruby-nokogiri" ,ruby-nokogiri)))
6846 `(("ruby-rspec" ,ruby-rspec)))
6847 (synopsis "Fast big data BLAST XML parser and library")
6849 "Very fast parallel big-data BLAST XML file parser which can be used as
6850 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6851 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6852 (home-page "https://github.com/pjotrp/blastxmlparser")
6853 (license license:expat)))
6855 (define-public bioruby
6862 (uri (rubygems-uri "bio" version))
6865 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6866 (build-system ruby-build-system)
6868 `(("ruby-libxml" ,ruby-libxml)))
6870 `(("which" ,which))) ; required for test phase
6873 (modify-phases %standard-phases
6874 (add-before 'build 'patch-test-command
6876 (substitute* '("test/functional/bio/test_command.rb")
6877 (("/bin/sh") (which "sh")))
6878 (substitute* '("test/functional/bio/test_command.rb")
6879 (("/bin/ls") (which "ls")))
6880 (substitute* '("test/functional/bio/test_command.rb")
6881 (("which") (which "which")))
6882 (substitute* '("test/functional/bio/test_command.rb",
6883 "test/data/command/echoarg2.sh")
6884 (("/bin/echo") (which "echo")))
6886 (synopsis "Ruby library, shell and utilities for bioinformatics")
6887 (description "BioRuby comes with a comprehensive set of Ruby development
6888 tools and libraries for bioinformatics and molecular biology. BioRuby has
6889 components for sequence analysis, pathway analysis, protein modelling and
6890 phylogenetic analysis; it supports many widely used data formats and provides
6891 easy access to databases, external programs and public web services, including
6892 BLAST, KEGG, GenBank, MEDLINE and GO.")
6893 (home-page "http://bioruby.org/")
6894 ;; Code is released under Ruby license, except for setup
6895 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6896 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6898 (define-public r-acsnminer
6900 (name "r-acsnminer")
6901 (version "0.16.8.25")
6904 (uri (cran-uri "ACSNMineR" version))
6907 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6908 (properties `((upstream-name . "ACSNMineR")))
6909 (build-system r-build-system)
6911 `(("r-ggplot2" ,r-ggplot2)
6912 ("r-gridextra" ,r-gridextra)))
6913 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6914 (synopsis "Gene enrichment analysis")
6916 "This package provides tools to compute and represent gene set enrichment
6917 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6918 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6919 enrichment can be run with hypergeometric test or Fisher exact test, and can
6920 use multiple corrections. Visualization of data can be done either by
6921 barplots or heatmaps.")
6922 (license license:gpl2+)))
6924 (define-public r-biocgenerics
6926 (name "r-biocgenerics")
6930 (uri (bioconductor-uri "BiocGenerics" version))
6933 "19qxhy2cd3pykkhzbb5q3crgaxf65cpzf2mkfsz16gqhi8flj72p"))))
6935 `((upstream-name . "BiocGenerics")))
6936 (build-system r-build-system)
6937 (home-page "https://bioconductor.org/packages/BiocGenerics")
6938 (synopsis "S4 generic functions for Bioconductor")
6940 "This package provides S4 generic functions needed by many Bioconductor
6942 (license license:artistic2.0)))
6944 (define-public r-biocinstaller
6946 (name "r-biocinstaller")
6950 (uri (bioconductor-uri "BiocInstaller" version))
6953 "1xg1gi1hf5vflp71ji21gnmr4kcjpx8a6c47cllpc7yqnjv5nfg0"))))
6955 `((upstream-name . "BiocInstaller")))
6956 (build-system r-build-system)
6957 (home-page "https://bioconductor.org/packages/BiocInstaller")
6958 (synopsis "Install Bioconductor packages")
6959 (description "This package is used to install and update R packages from
6960 Bioconductor, CRAN, and Github.")
6961 (license license:artistic2.0)))
6963 (define-public r-biocviews
6965 (name "r-biocviews")
6969 (uri (bioconductor-uri "biocViews" version))
6972 "01yiafayl1m5704xdd2cn3zjc78rs10dqyz66lr3qkf6d8w66938"))))
6974 `((upstream-name . "biocViews")))
6975 (build-system r-build-system)
6977 `(("r-biobase" ,r-biobase)
6978 ("r-graph" ,r-graph)
6980 ("r-rcurl" ,r-rcurl)
6982 ("r-runit" ,r-runit)))
6983 (home-page "https://bioconductor.org/packages/biocViews")
6984 (synopsis "Bioconductor package categorization helper")
6985 (description "The purpose of biocViews is to create HTML pages that
6986 categorize packages in a Bioconductor package repository according to keywords,
6987 also known as views, in a controlled vocabulary.")
6988 (license license:artistic2.0)))
6990 (define-public r-bookdown
6996 (uri (cran-uri "bookdown" version))
6999 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
7000 (build-system r-build-system)
7002 `(("r-htmltools" ,r-htmltools)
7003 ("r-knitr" ,r-knitr)
7004 ("r-rmarkdown" ,r-rmarkdown)
7005 ("r-tinytex" ,r-tinytex)
7007 ("r-xfun" ,r-xfun)))
7008 (home-page "https://github.com/rstudio/bookdown")
7009 (synopsis "Authoring books and technical documents with R markdown")
7010 (description "This package provides output formats and utilities for
7011 authoring books and technical documents with R Markdown.")
7012 (license license:gpl3)))
7014 (define-public r-biocstyle
7016 (name "r-biocstyle")
7020 (uri (bioconductor-uri "BiocStyle" version))
7023 "17m901ylz00w1a3nq5f910v55zixm1nr6rb3qrsbhqd94qzr0l2p"))))
7025 `((upstream-name . "BiocStyle")))
7026 (build-system r-build-system)
7028 `(("r-bookdown" ,r-bookdown)
7029 ("r-knitr" ,r-knitr)
7030 ("r-rmarkdown" ,r-rmarkdown)
7031 ("r-yaml" ,r-yaml)))
7032 (home-page "https://bioconductor.org/packages/BiocStyle")
7033 (synopsis "Bioconductor formatting styles")
7034 (description "This package provides standard formatting styles for
7035 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7037 (license license:artistic2.0)))
7039 (define-public r-bioccheck
7041 (name "r-bioccheck")
7045 (uri (bioconductor-uri "BiocCheck" version))
7048 "1srp1g809f1nn0fyqknr7r6dq89bw1xpjvmygr7cw6ffknbc671s"))))
7050 `((upstream-name . "BiocCheck")))
7051 (build-system r-build-system)
7054 (modify-phases %standard-phases
7055 ;; This package can be used by calling BiocCheck(<package>) from
7056 ;; within R, or by running R CMD BiocCheck <package>. This phase
7057 ;; makes sure the latter works. For this to work, the BiocCheck
7058 ;; script must be somewhere on the PATH (not the R bin directory).
7059 (add-after 'install 'install-bioccheck-subcommand
7060 (lambda* (#:key outputs #:allow-other-keys)
7061 (let* ((out (assoc-ref outputs "out"))
7062 (dest-dir (string-append out "/bin"))
7064 (string-append out "/site-library/BiocCheck/script/")))
7066 (symlink (string-append script-dir "/checkBadDeps.R")
7067 (string-append dest-dir "/checkBadDeps.R"))
7068 (symlink (string-append script-dir "/BiocCheck")
7069 (string-append dest-dir "/BiocCheck")))
7072 `(("r-codetools" ,r-codetools)
7073 ("r-graph" ,r-graph)
7075 ("r-optparse" ,r-optparse)
7076 ("r-biocinstaller" ,r-biocinstaller)
7077 ("r-biocviews" ,r-biocviews)
7078 ("r-stringdist" ,r-stringdist)))
7079 (home-page "https://bioconductor.org/packages/BiocCheck")
7080 (synopsis "Executes Bioconductor-specific package checks")
7081 (description "This package contains tools to perform additional quality
7082 checks on R packages that are to be submitted to the Bioconductor repository.")
7083 (license license:artistic2.0)))
7085 (define-public r-optparse
7092 (uri (cran-uri "optparse" version))
7095 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7096 (build-system r-build-system)
7098 `(("r-getopt" ,r-getopt)))
7100 "https://github.com/trevorld/optparse")
7101 (synopsis "Command line option parser")
7103 "This package provides a command line parser inspired by Python's
7104 @code{optparse} library to be used with Rscript to write shebang scripts
7105 that accept short and long options.")
7106 (license license:gpl2+)))
7108 (define-public r-dnacopy
7114 (uri (bioconductor-uri "DNAcopy" version))
7117 "03hfhmmc5y60r2gcgm367w2fr7qj115l74m9bp3h9qpn5yci0d8n"))))
7119 `((upstream-name . "DNAcopy")))
7120 (build-system r-build-system)
7122 `(("gfortran" ,gfortran)))
7123 (home-page "https://bioconductor.org/packages/DNAcopy")
7124 (synopsis "Implementation of a circular binary segmentation algorithm")
7125 (description "This package implements the circular binary segmentation (CBS)
7126 algorithm to segment DNA copy number data and identify genomic regions with
7127 abnormal copy number.")
7128 (license license:gpl2+)))
7130 (define-public r-s4vectors
7132 (name "r-s4vectors")
7136 (uri (bioconductor-uri "S4Vectors" version))
7139 "02bps2rpjqx2npwxq3x62ncwi9ggr165cwi56h6hld28bw2gddy8"))))
7141 `((upstream-name . "S4Vectors")))
7142 (build-system r-build-system)
7144 `(("r-biocgenerics" ,r-biocgenerics)))
7145 (home-page "https://bioconductor.org/packages/S4Vectors")
7146 (synopsis "S4 implementation of vectors and lists")
7148 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7149 classes and a set of generic functions that extend the semantic of ordinary
7150 vectors and lists in R. Package developers can easily implement vector-like
7151 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7152 In addition, a few low-level concrete subclasses of general interest (e.g.
7153 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7154 S4Vectors package itself.")
7155 (license license:artistic2.0)))
7157 (define-public r-seqinr
7164 (uri (cran-uri "seqinr" version))
7167 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7168 (build-system r-build-system)
7170 `(("r-ade4" ,r-ade4)
7171 ("r-segmented" ,r-segmented)))
7174 (home-page "http://seqinr.r-forge.r-project.org/")
7175 (synopsis "Biological sequences retrieval and analysis")
7177 "This package provides tools for exploratory data analysis and data
7178 visualization of biological sequence (DNA and protein) data. It also includes
7179 utilities for sequence data management under the ACNUC system.")
7180 (license license:gpl2+)))
7182 (define-public r-iranges
7188 (uri (bioconductor-uri "IRanges" version))
7191 "10ccw930vfmkskkrzbps14xglqlkxf588623dr7f1a9ckx7yr2p6"))))
7193 `((upstream-name . "IRanges")))
7194 (build-system r-build-system)
7196 `(("r-biocgenerics" ,r-biocgenerics)
7197 ("r-s4vectors" ,r-s4vectors)))
7198 (home-page "https://bioconductor.org/packages/IRanges")
7199 (synopsis "Infrastructure for manipulating intervals on sequences")
7201 "This package provides efficient low-level and highly reusable S4 classes
7202 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7203 generally, data that can be organized sequentially (formally defined as
7204 @code{Vector} objects), as well as views on these @code{Vector} objects.
7205 Efficient list-like classes are also provided for storing big collections of
7206 instances of the basic classes. All classes in the package use consistent
7207 naming and share the same rich and consistent \"Vector API\" as much as
7209 (license license:artistic2.0)))
7211 (define-public r-genomeinfodbdata
7213 (name "r-genomeinfodbdata")
7217 ;; We cannot use bioconductor-uri here because this tarball is
7218 ;; located under "data/annotation/" instead of "bioc/".
7219 (uri (string-append "https://bioconductor.org/packages/release/"
7220 "data/annotation/src/contrib/GenomeInfoDbData_"
7224 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7226 `((upstream-name . "GenomeInfoDbData")))
7227 (build-system r-build-system)
7228 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7229 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7230 (description "This package contains data for mapping between NCBI taxonomy
7231 ID and species. It is used by functions in the GenomeInfoDb package.")
7232 (license license:artistic2.0)))
7234 (define-public r-genomeinfodb
7236 (name "r-genomeinfodb")
7240 (uri (bioconductor-uri "GenomeInfoDb" version))
7243 "0yhnqhaydmmq7ihmhj3rbal4afq5p993l2qqrd0n5wmbyg7glg2d"))))
7245 `((upstream-name . "GenomeInfoDb")))
7246 (build-system r-build-system)
7248 `(("r-biocgenerics" ,r-biocgenerics)
7249 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7250 ("r-iranges" ,r-iranges)
7251 ("r-rcurl" ,r-rcurl)
7252 ("r-s4vectors" ,r-s4vectors)))
7253 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7254 (synopsis "Utilities for manipulating chromosome identifiers")
7256 "This package contains data and functions that define and allow
7257 translation between different chromosome sequence naming conventions (e.g.,
7258 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7259 names in their natural, rather than lexicographic, order.")
7260 (license license:artistic2.0)))
7262 (define-public r-edger
7268 (uri (bioconductor-uri "edgeR" version))
7271 "07py2g6vg9jbflwhc1hnzr2silbinrjwxq3mkq30nzjgf0n0hrf3"))))
7272 (properties `((upstream-name . "edgeR")))
7273 (build-system r-build-system)
7275 `(("r-limma" ,r-limma)
7276 ("r-locfit" ,r-locfit)
7278 ("r-statmod" ,r-statmod))) ;for estimateDisp
7279 (home-page "http://bioinf.wehi.edu.au/edgeR")
7280 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7281 (description "This package can do differential expression analysis of
7282 RNA-seq expression profiles with biological replication. It implements a range
7283 of statistical methodology based on the negative binomial distributions,
7284 including empirical Bayes estimation, exact tests, generalized linear models
7285 and quasi-likelihood tests. It be applied to differential signal analysis of
7286 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7288 (license license:gpl2+)))
7290 (define-public r-variantannotation
7292 (name "r-variantannotation")
7296 (uri (bioconductor-uri "VariantAnnotation" version))
7299 "06bccdf57vja7m63chmgc4539lwng3q3b8zxn285fj8524l6mcn7"))))
7301 `((upstream-name . "VariantAnnotation")))
7305 `(("r-annotationdbi" ,r-annotationdbi)
7306 ("r-biobase" ,r-biobase)
7307 ("r-biocgenerics" ,r-biocgenerics)
7308 ("r-biostrings" ,r-biostrings)
7309 ("r-bsgenome" ,r-bsgenome)
7311 ("r-genomeinfodb" ,r-genomeinfodb)
7312 ("r-genomicfeatures" ,r-genomicfeatures)
7313 ("r-genomicranges" ,r-genomicranges)
7314 ("r-iranges" ,r-iranges)
7315 ("r-summarizedexperiment" ,r-summarizedexperiment)
7316 ("r-rsamtools" ,r-rsamtools)
7317 ("r-rtracklayer" ,r-rtracklayer)
7318 ("r-s4vectors" ,r-s4vectors)
7319 ("r-xvector" ,r-xvector)
7320 ("r-zlibbioc" ,r-zlibbioc)))
7321 (build-system r-build-system)
7322 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7323 (synopsis "Package for annotation of genetic variants")
7324 (description "This R package can annotate variants, compute amino acid
7325 coding changes and predict coding outcomes.")
7326 (license license:artistic2.0)))
7328 (define-public r-limma
7334 (uri (bioconductor-uri "limma" version))
7337 "1982g5v35ilfgxm2vkq1p3j1bbir795pjvfzx4nzam2rlqqymbqm"))))
7338 (build-system r-build-system)
7339 (home-page "http://bioinf.wehi.edu.au/limma")
7340 (synopsis "Package for linear models for microarray and RNA-seq data")
7341 (description "This package can be used for the analysis of gene expression
7342 studies, especially the use of linear models for analysing designed experiments
7343 and the assessment of differential expression. The analysis methods apply to
7344 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7345 (license license:gpl2+)))
7347 (define-public r-xvector
7353 (uri (bioconductor-uri "XVector" version))
7356 "1zjlhh9lsyhg0js1858csyw2389kbrzdqnqnha833wazkwxilp3f"))))
7358 `((upstream-name . "XVector")))
7359 (build-system r-build-system)
7362 (modify-phases %standard-phases
7363 (add-after 'unpack 'use-system-zlib
7365 (substitute* "DESCRIPTION"
7366 (("zlibbioc, ") ""))
7367 (substitute* "NAMESPACE"
7368 (("import\\(zlibbioc\\)") ""))
7373 `(("r-biocgenerics" ,r-biocgenerics)
7374 ("r-iranges" ,r-iranges)
7375 ("r-s4vectors" ,r-s4vectors)))
7376 (home-page "https://bioconductor.org/packages/XVector")
7377 (synopsis "Representation and manpulation of external sequences")
7379 "This package provides memory efficient S4 classes for storing sequences
7380 \"externally\" (behind an R external pointer, or on disk).")
7381 (license license:artistic2.0)))
7383 (define-public r-genomicranges
7385 (name "r-genomicranges")
7389 (uri (bioconductor-uri "GenomicRanges" version))
7392 "03gmka6rlz18vd4229796l5l3l6446v5cb90sn2nb5knjbp84hni"))))
7394 `((upstream-name . "GenomicRanges")))
7395 (build-system r-build-system)
7397 `(("r-biocgenerics" ,r-biocgenerics)
7398 ("r-genomeinfodb" ,r-genomeinfodb)
7399 ("r-iranges" ,r-iranges)
7400 ("r-s4vectors" ,r-s4vectors)
7401 ("r-xvector" ,r-xvector)))
7402 (home-page "https://bioconductor.org/packages/GenomicRanges")
7403 (synopsis "Representation and manipulation of genomic intervals")
7405 "This package provides tools to efficiently represent and manipulate
7406 genomic annotations and alignments is playing a central role when it comes to
7407 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7408 GenomicRanges package defines general purpose containers for storing and
7409 manipulating genomic intervals and variables defined along a genome.")
7410 (license license:artistic2.0)))
7412 (define-public r-biobase
7418 (uri (bioconductor-uri "Biobase" version))
7421 "1iwds2a5ir29k19dbpynlc7nn836cw2gamchhgpi2jf2xar9m9jz"))))
7423 `((upstream-name . "Biobase")))
7424 (build-system r-build-system)
7426 `(("r-biocgenerics" ,r-biocgenerics)))
7427 (home-page "https://bioconductor.org/packages/Biobase")
7428 (synopsis "Base functions for Bioconductor")
7430 "This package provides functions that are needed by many other packages
7431 on Bioconductor or which replace R functions.")
7432 (license license:artistic2.0)))
7434 (define-public r-annotationdbi
7436 (name "r-annotationdbi")
7440 (uri (bioconductor-uri "AnnotationDbi" version))
7443 "0afkbzli08vq02r2pr9phrz3rxd6ilp1w7yw8y99nbjiz14f8b1c"))))
7445 `((upstream-name . "AnnotationDbi")))
7446 (build-system r-build-system)
7448 `(("r-biobase" ,r-biobase)
7449 ("r-biocgenerics" ,r-biocgenerics)
7451 ("r-iranges" ,r-iranges)
7452 ("r-rsqlite" ,r-rsqlite)
7453 ("r-s4vectors" ,r-s4vectors)))
7454 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7455 (synopsis "Annotation database interface")
7457 "This package provides user interface and database connection code for
7458 annotation data packages using SQLite data storage.")
7459 (license license:artistic2.0)))
7461 (define-public r-biomart
7467 (uri (bioconductor-uri "biomaRt" version))
7470 "0b70s350ffc74v3xz5c3jpazr9zxdb7gjmjfj7aghlsrizrspill"))))
7472 `((upstream-name . "biomaRt")))
7473 (build-system r-build-system)
7475 `(("r-annotationdbi" ,r-annotationdbi)
7477 ("r-progress" ,r-progress)
7478 ("r-rcurl" ,r-rcurl)
7479 ("r-stringr" ,r-stringr)
7481 (home-page "https://bioconductor.org/packages/biomaRt")
7482 (synopsis "Interface to BioMart databases")
7484 "biomaRt provides an interface to a growing collection of databases
7485 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7486 package enables retrieval of large amounts of data in a uniform way without
7487 the need to know the underlying database schemas or write complex SQL queries.
7488 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7489 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7490 users direct access to a diverse set of data and enable a wide range of
7491 powerful online queries from gene annotation to database mining.")
7492 (license license:artistic2.0)))
7494 (define-public r-biocparallel
7496 (name "r-biocparallel")
7500 (uri (bioconductor-uri "BiocParallel" version))
7503 "00qg1kg2l9qqpyjaw5q910cmf84vwfiw1fhsx3ig784gwinwgj6n"))))
7505 `((upstream-name . "BiocParallel")))
7506 (build-system r-build-system)
7508 `(("r-futile-logger" ,r-futile-logger)
7511 (home-page "https://bioconductor.org/packages/BiocParallel")
7512 (synopsis "Bioconductor facilities for parallel evaluation")
7514 "This package provides modified versions and novel implementation of
7515 functions for parallel evaluation, tailored to use with Bioconductor
7517 (license (list license:gpl2+ license:gpl3+))))
7519 (define-public r-biostrings
7521 (name "r-biostrings")
7525 (uri (bioconductor-uri "Biostrings" version))
7528 "118b490jk87ydigm6ln25ms4kskzkw0akmh77clzznhzpqnxsi6j"))))
7530 `((upstream-name . "Biostrings")))
7531 (build-system r-build-system)
7533 `(("r-biocgenerics" ,r-biocgenerics)
7534 ("r-iranges" ,r-iranges)
7535 ("r-s4vectors" ,r-s4vectors)
7536 ("r-xvector" ,r-xvector)))
7537 (home-page "https://bioconductor.org/packages/Biostrings")
7538 (synopsis "String objects and algorithms for biological sequences")
7540 "This package provides memory efficient string containers, string
7541 matching algorithms, and other utilities, for fast manipulation of large
7542 biological sequences or sets of sequences.")
7543 (license license:artistic2.0)))
7545 (define-public r-rsamtools
7547 (name "r-rsamtools")
7551 (uri (bioconductor-uri "Rsamtools" version))
7554 "1s65y5wn4d0x8zsljg2kmhcl6r9884h95kr041j7hp49bmxg3an6"))))
7556 `((upstream-name . "Rsamtools")))
7557 (build-system r-build-system)
7560 (modify-phases %standard-phases
7561 (add-after 'unpack 'use-system-zlib
7563 (substitute* "DESCRIPTION"
7564 (("zlibbioc, ") ""))
7565 (substitute* "NAMESPACE"
7566 (("import\\(zlibbioc\\)") ""))
7571 `(("r-biocgenerics" ,r-biocgenerics)
7572 ("r-biocparallel" ,r-biocparallel)
7573 ("r-biostrings" ,r-biostrings)
7574 ("r-bitops" ,r-bitops)
7575 ("r-genomeinfodb" ,r-genomeinfodb)
7576 ("r-genomicranges" ,r-genomicranges)
7577 ("r-iranges" ,r-iranges)
7578 ("r-s4vectors" ,r-s4vectors)
7579 ("r-xvector" ,r-xvector)))
7580 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7581 (synopsis "Interface to samtools, bcftools, and tabix")
7583 "This package provides an interface to the 'samtools', 'bcftools', and
7584 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7585 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7587 (license license:expat)))
7589 (define-public r-delayedarray
7591 (name "r-delayedarray")
7595 (uri (bioconductor-uri "DelayedArray" version))
7598 "0sjwszxdi0vkj2i2di5i46gh9chc660yr3gs5nk9qnqp77713zds"))))
7600 `((upstream-name . "DelayedArray")))
7601 (build-system r-build-system)
7603 `(("r-biocgenerics" ,r-biocgenerics)
7604 ("r-biocparallel" ,r-biocparallel)
7605 ("r-s4vectors" ,r-s4vectors)
7606 ("r-iranges" ,r-iranges)
7607 ("r-matrixstats" ,r-matrixstats)))
7608 (home-page "https://bioconductor.org/packages/DelayedArray")
7609 (synopsis "Delayed operations on array-like objects")
7611 "Wrapping an array-like object (typically an on-disk object) in a
7612 @code{DelayedArray} object allows one to perform common array operations on it
7613 without loading the object in memory. In order to reduce memory usage and
7614 optimize performance, operations on the object are either delayed or executed
7615 using a block processing mechanism. Note that this also works on in-memory
7616 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7617 @code{Matrix} objects, and ordinary arrays and data frames.")
7618 (license license:artistic2.0)))
7620 (define-public r-summarizedexperiment
7622 (name "r-summarizedexperiment")
7626 (uri (bioconductor-uri "SummarizedExperiment" version))
7629 "0v3zxl9cqsv79ag5cnvzlhvgaz5cr8f4rn7flmwnwpqd508cznl1"))))
7631 `((upstream-name . "SummarizedExperiment")))
7632 (build-system r-build-system)
7634 `(("r-biobase" ,r-biobase)
7635 ("r-biocgenerics" ,r-biocgenerics)
7636 ("r-delayedarray" ,r-delayedarray)
7637 ("r-genomeinfodb" ,r-genomeinfodb)
7638 ("r-genomicranges" ,r-genomicranges)
7639 ("r-iranges" ,r-iranges)
7640 ("r-matrix" ,r-matrix)
7641 ("r-s4vectors" ,r-s4vectors)))
7642 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7643 (synopsis "Container for representing genomic ranges by sample")
7645 "The SummarizedExperiment container contains one or more assays, each
7646 represented by a matrix-like object of numeric or other mode. The rows
7647 typically represent genomic ranges of interest and the columns represent
7649 (license license:artistic2.0)))
7651 (define-public r-genomicalignments
7653 (name "r-genomicalignments")
7657 (uri (bioconductor-uri "GenomicAlignments" version))
7660 "00pi2cnkkbj2023fg2x2cmglkdalwzy1vr3glsikwz7ix9yylcaw"))))
7662 `((upstream-name . "GenomicAlignments")))
7663 (build-system r-build-system)
7665 `(("r-biocgenerics" ,r-biocgenerics)
7666 ("r-biocparallel" ,r-biocparallel)
7667 ("r-biostrings" ,r-biostrings)
7668 ("r-genomeinfodb" ,r-genomeinfodb)
7669 ("r-genomicranges" ,r-genomicranges)
7670 ("r-iranges" ,r-iranges)
7671 ("r-rsamtools" ,r-rsamtools)
7672 ("r-s4vectors" ,r-s4vectors)
7673 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7674 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7675 (synopsis "Representation and manipulation of short genomic alignments")
7677 "This package provides efficient containers for storing and manipulating
7678 short genomic alignments (typically obtained by aligning short reads to a
7679 reference genome). This includes read counting, computing the coverage,
7680 junction detection, and working with the nucleotide content of the
7682 (license license:artistic2.0)))
7684 (define-public r-rtracklayer
7686 (name "r-rtracklayer")
7690 (uri (bioconductor-uri "rtracklayer" version))
7693 "0kvsjdaypn1jnxbnsxpycildwdyxwnjkigfq8qm8mlyfc4ahdgy3"))))
7694 (build-system r-build-system)
7697 (modify-phases %standard-phases
7698 (add-after 'unpack 'use-system-zlib
7700 (substitute* "DESCRIPTION"
7701 ((" zlibbioc,") ""))
7702 (substitute* "NAMESPACE"
7703 (("import\\(zlibbioc\\)") ""))
7706 `(("pkg-config" ,pkg-config)))
7710 `(("r-biocgenerics" ,r-biocgenerics)
7711 ("r-biostrings" ,r-biostrings)
7712 ("r-genomeinfodb" ,r-genomeinfodb)
7713 ("r-genomicalignments" ,r-genomicalignments)
7714 ("r-genomicranges" ,r-genomicranges)
7715 ("r-iranges" ,r-iranges)
7716 ("r-rcurl" ,r-rcurl)
7717 ("r-rsamtools" ,r-rsamtools)
7718 ("r-s4vectors" ,r-s4vectors)
7720 ("r-xvector" ,r-xvector)))
7721 (home-page "https://bioconductor.org/packages/rtracklayer")
7722 (synopsis "R interface to genome browsers and their annotation tracks")
7724 "rtracklayer is an extensible framework for interacting with multiple
7725 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7726 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7727 built-in). The user may export/import tracks to/from the supported browsers,
7728 as well as query and modify the browser state, such as the current viewport.")
7729 (license license:artistic2.0)))
7731 (define-public r-genomicfeatures
7733 (name "r-genomicfeatures")
7737 (uri (bioconductor-uri "GenomicFeatures" version))
7740 "1cqcl72q0k5wylw1brn4g4h7xzys1v06piry19cvp0gjcvm5sp7a"))))
7742 `((upstream-name . "GenomicFeatures")))
7743 (build-system r-build-system)
7745 `(("r-annotationdbi" ,r-annotationdbi)
7746 ("r-biobase" ,r-biobase)
7747 ("r-biocgenerics" ,r-biocgenerics)
7748 ("r-biomart" ,r-biomart)
7749 ("r-biostrings" ,r-biostrings)
7751 ("r-genomeinfodb" ,r-genomeinfodb)
7752 ("r-genomicranges" ,r-genomicranges)
7753 ("r-iranges" ,r-iranges)
7754 ("r-rcurl" ,r-rcurl)
7755 ("r-rsqlite" ,r-rsqlite)
7756 ("r-rtracklayer" ,r-rtracklayer)
7757 ("r-s4vectors" ,r-s4vectors)
7758 ("r-xvector" ,r-xvector)))
7759 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7760 (synopsis "Tools for working with transcript centric annotations")
7762 "This package provides a set of tools and methods for making and
7763 manipulating transcript centric annotations. With these tools the user can
7764 easily download the genomic locations of the transcripts, exons and cds of a
7765 given organism, from either the UCSC Genome Browser or a BioMart
7766 database (more sources will be supported in the future). This information is
7767 then stored in a local database that keeps track of the relationship between
7768 transcripts, exons, cds and genes. Flexible methods are provided for
7769 extracting the desired features in a convenient format.")
7770 (license license:artistic2.0)))
7772 (define-public r-go-db
7778 (uri (string-append "https://www.bioconductor.org/packages/"
7779 "release/data/annotation/src/contrib/GO.db_"
7783 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7785 `((upstream-name . "GO.db")))
7786 (build-system r-build-system)
7788 `(("r-annotationdbi" ,r-annotationdbi)))
7789 (home-page "https://bioconductor.org/packages/GO.db")
7790 (synopsis "Annotation maps describing the entire Gene Ontology")
7792 "The purpose of this GO.db annotation package is to provide detailed
7793 information about the latest version of the Gene Ontologies.")
7794 (license license:artistic2.0)))
7796 (define-public r-graph
7802 (uri (bioconductor-uri "graph" version))
7805 "1zx445lk36g1s6i5dbhhf00nzzazyklfjxxjfax6q8hnhvgm9759"))))
7806 (build-system r-build-system)
7808 `(("r-biocgenerics" ,r-biocgenerics)))
7809 (home-page "https://bioconductor.org/packages/graph")
7810 (synopsis "Handle graph data structures in R")
7812 "This package implements some simple graph handling capabilities for R.")
7813 (license license:artistic2.0)))
7815 (define-public r-topgo
7821 (uri (bioconductor-uri "topGO" version))
7824 "05yxnkid8bgw9lkm90if9fg63djhgvbailfa3qsfqa5c0zjmixw1"))))
7826 `((upstream-name . "topGO")))
7827 (build-system r-build-system)
7829 `(("r-annotationdbi" ,r-annotationdbi)
7831 ("r-biobase" ,r-biobase)
7832 ("r-biocgenerics" ,r-biocgenerics)
7833 ("r-go-db" ,r-go-db)
7834 ("r-graph" ,r-graph)
7835 ("r-lattice" ,r-lattice)
7836 ("r-matrixstats" ,r-matrixstats)
7837 ("r-sparsem" ,r-sparsem)))
7838 (home-page "https://bioconductor.org/packages/topGO")
7839 (synopsis "Enrichment analysis for gene ontology")
7841 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7842 terms while accounting for the topology of the GO graph. Different test
7843 statistics and different methods for eliminating local similarities and
7844 dependencies between GO terms can be implemented and applied.")
7845 ;; Any version of the LGPL applies.
7846 (license license:lgpl2.1+)))
7848 (define-public r-bsgenome
7854 (uri (bioconductor-uri "BSgenome" version))
7857 "1rk2piqq5dppkd51ln3r872d7ng3rvq98071mnd0xdv2xwnyn5g8"))))
7859 `((upstream-name . "BSgenome")))
7860 (build-system r-build-system)
7862 `(("r-biocgenerics" ,r-biocgenerics)
7863 ("r-biostrings" ,r-biostrings)
7864 ("r-genomeinfodb" ,r-genomeinfodb)
7865 ("r-genomicranges" ,r-genomicranges)
7866 ("r-iranges" ,r-iranges)
7867 ("r-rsamtools" ,r-rsamtools)
7868 ("r-rtracklayer" ,r-rtracklayer)
7869 ("r-s4vectors" ,r-s4vectors)
7870 ("r-xvector" ,r-xvector)))
7871 (home-page "https://bioconductor.org/packages/BSgenome")
7872 (synopsis "Infrastructure for Biostrings-based genome data packages")
7874 "This package provides infrastructure shared by all Biostrings-based
7875 genome data packages and support for efficient SNP representation.")
7876 (license license:artistic2.0)))
7878 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7880 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7884 ;; We cannot use bioconductor-uri here because this tarball is
7885 ;; located under "data/annotation/" instead of "bioc/".
7886 (uri (string-append "https://www.bioconductor.org/packages/"
7887 "release/data/annotation/src/contrib/"
7888 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7892 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7894 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7895 (build-system r-build-system)
7896 ;; As this package provides little more than a very large data file it
7897 ;; doesn't make sense to build substitutes.
7898 (arguments `(#:substitutable? #f))
7900 `(("r-bsgenome" ,r-bsgenome)))
7902 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7903 (synopsis "Full genome sequences for Homo sapiens")
7905 "This package provides full genome sequences for Homo sapiens from
7906 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7907 (license license:artistic2.0)))
7909 (define-public r-impute
7915 (uri (bioconductor-uri "impute" version))
7918 "1d3cpfaqlq2gnb3hsc2yhxwkrnbd7m6ifif32yp0ya0jr5brl4hr"))))
7920 `(("gfortran" ,gfortran)))
7921 (build-system r-build-system)
7922 (home-page "https://bioconductor.org/packages/impute")
7923 (synopsis "Imputation for microarray data")
7925 "This package provides a function to impute missing gene expression
7926 microarray data, using nearest neighbor averaging.")
7927 (license license:gpl2+)))
7929 (define-public r-seqpattern
7931 (name "r-seqpattern")
7935 (uri (bioconductor-uri "seqPattern" version))
7938 "0dw0yldfcf0ibvpqxlpx1ijnjf9lma47w9w22siszzhw09i0wp3w"))))
7940 `((upstream-name . "seqPattern")))
7941 (build-system r-build-system)
7943 `(("r-biostrings" ,r-biostrings)
7944 ("r-genomicranges" ,r-genomicranges)
7945 ("r-iranges" ,r-iranges)
7946 ("r-kernsmooth" ,r-kernsmooth)
7947 ("r-plotrix" ,r-plotrix)))
7948 (home-page "https://bioconductor.org/packages/seqPattern")
7949 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7951 "This package provides tools to visualize oligonucleotide patterns and
7952 sequence motif occurrences across a large set of sequences centred at a common
7953 reference point and sorted by a user defined feature.")
7954 (license license:gpl3+)))
7956 (define-public r-genomation
7958 (name "r-genomation")
7962 (uri (bioconductor-uri "genomation" version))
7965 "1vdmdyrq0n7pf8cvy2950v7hrcrcbd9zl4fg7dcmyly3iiwdyirp"))))
7966 (build-system r-build-system)
7968 `(("r-biostrings" ,r-biostrings)
7969 ("r-bsgenome" ,r-bsgenome)
7970 ("r-data-table" ,r-data-table)
7971 ("r-genomeinfodb" ,r-genomeinfodb)
7972 ("r-genomicalignments" ,r-genomicalignments)
7973 ("r-genomicranges" ,r-genomicranges)
7974 ("r-ggplot2" ,r-ggplot2)
7975 ("r-gridbase" ,r-gridbase)
7976 ("r-impute" ,r-impute)
7977 ("r-iranges" ,r-iranges)
7978 ("r-matrixstats" ,r-matrixstats)
7979 ("r-plotrix" ,r-plotrix)
7982 ("r-readr" ,r-readr)
7983 ("r-reshape2" ,r-reshape2)
7984 ("r-rsamtools" ,r-rsamtools)
7985 ("r-rtracklayer" ,r-rtracklayer)
7986 ("r-runit" ,r-runit)
7987 ("r-s4vectors" ,r-s4vectors)
7988 ("r-seqpattern" ,r-seqpattern)))
7989 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7990 (synopsis "Summary, annotation and visualization of genomic data")
7992 "This package provides a package for summary and annotation of genomic
7993 intervals. Users can visualize and quantify genomic intervals over
7994 pre-defined functional regions, such as promoters, exons, introns, etc. The
7995 genomic intervals represent regions with a defined chromosome position, which
7996 may be associated with a score, such as aligned reads from HT-seq experiments,
7997 TF binding sites, methylation scores, etc. The package can use any tabular
7998 genomic feature data as long as it has minimal information on the locations of
7999 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8000 (license license:artistic2.0)))
8002 (define-public r-genomationdata
8004 (name "r-genomationdata")
8008 ;; We cannot use bioconductor-uri here because this tarball is
8009 ;; located under "data/annotation/" instead of "bioc/".
8010 (uri (string-append "https://bioconductor.org/packages/"
8011 "release/data/experiment/src/contrib/"
8012 "genomationData_" version ".tar.gz"))
8015 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
8016 (build-system r-build-system)
8017 ;; As this package provides little more than large data files, it doesn't
8018 ;; make sense to build substitutes.
8019 (arguments `(#:substitutable? #f))
8021 `(("r-knitr" ,r-knitr)))
8022 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8023 (synopsis "Experimental data for use with the genomation package")
8025 "This package contains experimental genetic data for use with the
8026 genomation package. Included are Chip Seq, Methylation and Cage data,
8027 downloaded from Encode.")
8028 (license license:gpl3+)))
8030 (define-public r-org-hs-eg-db
8032 (name "r-org-hs-eg-db")
8036 ;; We cannot use bioconductor-uri here because this tarball is
8037 ;; located under "data/annotation/" instead of "bioc/".
8038 (uri (string-append "https://www.bioconductor.org/packages/"
8039 "release/data/annotation/src/contrib/"
8040 "org.Hs.eg.db_" version ".tar.gz"))
8043 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
8045 `((upstream-name . "org.Hs.eg.db")))
8046 (build-system r-build-system)
8048 `(("r-annotationdbi" ,r-annotationdbi)))
8049 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8050 (synopsis "Genome wide annotation for Human")
8052 "This package contains genome-wide annotations for Human, primarily based
8053 on mapping using Entrez Gene identifiers.")
8054 (license license:artistic2.0)))
8056 (define-public r-org-ce-eg-db
8058 (name "r-org-ce-eg-db")
8062 ;; We cannot use bioconductor-uri here because this tarball is
8063 ;; located under "data/annotation/" instead of "bioc/".
8064 (uri (string-append "https://www.bioconductor.org/packages/"
8065 "release/data/annotation/src/contrib/"
8066 "org.Ce.eg.db_" version ".tar.gz"))
8069 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8071 `((upstream-name . "org.Ce.eg.db")))
8072 (build-system r-build-system)
8074 `(("r-annotationdbi" ,r-annotationdbi)))
8075 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8076 (synopsis "Genome wide annotation for Worm")
8078 "This package provides mappings from Entrez gene identifiers to various
8079 annotations for the genome of the model worm Caenorhabditis elegans.")
8080 (license license:artistic2.0)))
8082 (define-public r-org-dm-eg-db
8084 (name "r-org-dm-eg-db")
8088 ;; We cannot use bioconductor-uri here because this tarball is
8089 ;; located under "data/annotation/" instead of "bioc/".
8090 (uri (string-append "https://www.bioconductor.org/packages/"
8091 "release/data/annotation/src/contrib/"
8092 "org.Dm.eg.db_" version ".tar.gz"))
8095 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8097 `((upstream-name . "org.Dm.eg.db")))
8098 (build-system r-build-system)
8100 `(("r-annotationdbi" ,r-annotationdbi)))
8101 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8102 (synopsis "Genome wide annotation for Fly")
8104 "This package provides mappings from Entrez gene identifiers to various
8105 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8106 (license license:artistic2.0)))
8108 (define-public r-org-mm-eg-db
8110 (name "r-org-mm-eg-db")
8114 ;; We cannot use bioconductor-uri here because this tarball is
8115 ;; located under "data/annotation/" instead of "bioc/".
8116 (uri (string-append "https://www.bioconductor.org/packages/"
8117 "release/data/annotation/src/contrib/"
8118 "org.Mm.eg.db_" version ".tar.gz"))
8121 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8123 `((upstream-name . "org.Mm.eg.db")))
8124 (build-system r-build-system)
8126 `(("r-annotationdbi" ,r-annotationdbi)))
8127 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8128 (synopsis "Genome wide annotation for Mouse")
8130 "This package provides mappings from Entrez gene identifiers to various
8131 annotations for the genome of the model mouse Mus musculus.")
8132 (license license:artistic2.0)))
8134 (define-public r-seqlogo
8141 (uri (bioconductor-uri "seqLogo" version))
8144 "16xvqcdknix9vjm8mrixi6nyfsr45jm844jh1x90m8044lwrsic1"))))
8145 (properties `((upstream-name . "seqLogo")))
8146 (build-system r-build-system)
8147 (home-page "https://bioconductor.org/packages/seqLogo")
8148 (synopsis "Sequence logos for DNA sequence alignments")
8150 "seqLogo takes the position weight matrix of a DNA sequence motif and
8151 plots the corresponding sequence logo as introduced by Schneider and
8153 (license license:lgpl2.0+)))
8155 (define-public r-bsgenome-hsapiens-ucsc-hg19
8157 (name "r-bsgenome-hsapiens-ucsc-hg19")
8161 ;; We cannot use bioconductor-uri here because this tarball is
8162 ;; located under "data/annotation/" instead of "bioc/".
8163 (uri (string-append "https://www.bioconductor.org/packages/"
8164 "release/data/annotation/src/contrib/"
8165 "BSgenome.Hsapiens.UCSC.hg19_"
8169 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8171 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8172 (build-system r-build-system)
8173 ;; As this package provides little more than a very large data file it
8174 ;; doesn't make sense to build substitutes.
8175 (arguments `(#:substitutable? #f))
8177 `(("r-bsgenome" ,r-bsgenome)))
8179 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8180 (synopsis "Full genome sequences for Homo sapiens")
8182 "This package provides full genome sequences for Homo sapiens as provided
8183 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8184 (license license:artistic2.0)))
8186 (define-public r-bsgenome-mmusculus-ucsc-mm9
8188 (name "r-bsgenome-mmusculus-ucsc-mm9")
8192 ;; We cannot use bioconductor-uri here because this tarball is
8193 ;; located under "data/annotation/" instead of "bioc/".
8194 (uri (string-append "https://www.bioconductor.org/packages/"
8195 "release/data/annotation/src/contrib/"
8196 "BSgenome.Mmusculus.UCSC.mm9_"
8200 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8202 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8203 (build-system r-build-system)
8204 ;; As this package provides little more than a very large data file it
8205 ;; doesn't make sense to build substitutes.
8206 (arguments `(#:substitutable? #f))
8208 `(("r-bsgenome" ,r-bsgenome)))
8210 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8211 (synopsis "Full genome sequences for Mouse")
8213 "This package provides full genome sequences for Mus musculus (Mouse) as
8214 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8215 (license license:artistic2.0)))
8217 (define-public r-bsgenome-mmusculus-ucsc-mm10
8219 (name "r-bsgenome-mmusculus-ucsc-mm10")
8223 ;; We cannot use bioconductor-uri here because this tarball is
8224 ;; located under "data/annotation/" instead of "bioc/".
8225 (uri (string-append "https://www.bioconductor.org/packages/"
8226 "release/data/annotation/src/contrib/"
8227 "BSgenome.Mmusculus.UCSC.mm10_"
8231 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8233 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8234 (build-system r-build-system)
8235 ;; As this package provides little more than a very large data file it
8236 ;; doesn't make sense to build substitutes.
8237 (arguments `(#:substitutable? #f))
8239 `(("r-bsgenome" ,r-bsgenome)))
8241 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8242 (synopsis "Full genome sequences for Mouse")
8244 "This package provides full genome sequences for Mus
8245 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8246 in Biostrings objects.")
8247 (license license:artistic2.0)))
8249 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8251 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8255 ;; We cannot use bioconductor-uri here because this tarball is
8256 ;; located under "data/annotation/" instead of "bioc/".
8257 (uri (string-append "https://www.bioconductor.org/packages/"
8258 "release/data/annotation/src/contrib/"
8259 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8263 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8265 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8266 (build-system r-build-system)
8267 ;; As this package provides little more than a very large data file it
8268 ;; doesn't make sense to build substitutes.
8269 (arguments `(#:substitutable? #f))
8271 `(("r-bsgenome" ,r-bsgenome)
8272 ("r-genomicfeatures" ,r-genomicfeatures)
8273 ("r-annotationdbi" ,r-annotationdbi)))
8275 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8276 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8278 "This package loads a TxDb object, which is an R interface to
8279 prefabricated databases contained in this package. This package provides
8280 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8281 based on the knownGene track.")
8282 (license license:artistic2.0)))
8284 (define-public r-bsgenome-celegans-ucsc-ce6
8286 (name "r-bsgenome-celegans-ucsc-ce6")
8290 ;; We cannot use bioconductor-uri here because this tarball is
8291 ;; located under "data/annotation/" instead of "bioc/".
8292 (uri (string-append "https://www.bioconductor.org/packages/"
8293 "release/data/annotation/src/contrib/"
8294 "BSgenome.Celegans.UCSC.ce6_"
8298 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8300 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8301 (build-system r-build-system)
8302 ;; As this package provides little more than a very large data file it
8303 ;; doesn't make sense to build substitutes.
8304 (arguments `(#:substitutable? #f))
8306 `(("r-bsgenome" ,r-bsgenome)))
8308 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8309 (synopsis "Full genome sequences for Worm")
8311 "This package provides full genome sequences for Caenorhabditis
8312 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8314 (license license:artistic2.0)))
8316 (define-public r-bsgenome-celegans-ucsc-ce10
8318 (name "r-bsgenome-celegans-ucsc-ce10")
8322 ;; We cannot use bioconductor-uri here because this tarball is
8323 ;; located under "data/annotation/" instead of "bioc/".
8324 (uri (string-append "https://www.bioconductor.org/packages/"
8325 "release/data/annotation/src/contrib/"
8326 "BSgenome.Celegans.UCSC.ce10_"
8330 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8332 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8333 (build-system r-build-system)
8334 ;; As this package provides little more than a very large data file it
8335 ;; doesn't make sense to build substitutes.
8336 (arguments `(#:substitutable? #f))
8338 `(("r-bsgenome" ,r-bsgenome)))
8340 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8341 (synopsis "Full genome sequences for Worm")
8343 "This package provides full genome sequences for Caenorhabditis
8344 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8346 (license license:artistic2.0)))
8348 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8350 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8354 ;; We cannot use bioconductor-uri here because this tarball is
8355 ;; located under "data/annotation/" instead of "bioc/".
8356 (uri (string-append "https://www.bioconductor.org/packages/"
8357 "release/data/annotation/src/contrib/"
8358 "BSgenome.Dmelanogaster.UCSC.dm3_"
8362 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8364 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8365 (build-system r-build-system)
8366 ;; As this package provides little more than a very large data file it
8367 ;; doesn't make sense to build substitutes.
8368 (arguments `(#:substitutable? #f))
8370 `(("r-bsgenome" ,r-bsgenome)))
8372 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8373 (synopsis "Full genome sequences for Fly")
8375 "This package provides full genome sequences for Drosophila
8376 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8377 Biostrings objects.")
8378 (license license:artistic2.0)))
8380 (define-public r-motifrg
8387 (uri (bioconductor-uri "motifRG" version))
8390 "0mxhyidkyd2zqahdbg69y20r550z78lvr1r3pbjymnwfg4hcfq1p"))))
8391 (properties `((upstream-name . "motifRG")))
8392 (build-system r-build-system)
8394 `(("r-biostrings" ,r-biostrings)
8395 ("r-bsgenome" ,r-bsgenome)
8396 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8397 ("r-iranges" ,r-iranges)
8398 ("r-seqlogo" ,r-seqlogo)
8399 ("r-xvector" ,r-xvector)))
8400 (home-page "https://bioconductor.org/packages/motifRG")
8401 (synopsis "Discover motifs in high throughput sequencing data")
8403 "This package provides tools for discriminative motif discovery in high
8404 throughput genetic sequencing data sets using regression methods.")
8405 (license license:artistic2.0)))
8407 (define-public r-qtl
8414 (uri (string-append "mirror://cran/src/contrib/qtl_"
8418 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8419 (build-system r-build-system)
8420 (home-page "http://rqtl.org/")
8421 (synopsis "R package for analyzing QTL experiments in genetics")
8422 (description "R/qtl is an extension library for the R statistics
8423 system. It is used to analyze experimental crosses for identifying
8424 genes contributing to variation in quantitative traits (so-called
8425 quantitative trait loci, QTLs).
8427 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8428 identify genotyping errors, and to perform single-QTL and two-QTL,
8429 two-dimensional genome scans.")
8430 (license license:gpl3)))
8432 (define-public r-zlibbioc
8438 (uri (bioconductor-uri "zlibbioc" version))
8441 "1rwr0mci8a712q0isavi4jmhm94gwivc4nr8j7r4kw05flp4g7gz"))))
8443 `((upstream-name . "zlibbioc")))
8444 (build-system r-build-system)
8445 (home-page "https://bioconductor.org/packages/zlibbioc")
8446 (synopsis "Provider for zlib-1.2.5 to R packages")
8447 (description "This package uses the source code of zlib-1.2.5 to create
8448 libraries for systems that do not have these available via other means.")
8449 (license license:artistic2.0)))
8451 (define-public r-r4rna
8458 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8462 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8463 (build-system r-build-system)
8465 `(("r-optparse" ,r-optparse)
8466 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8467 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8468 (synopsis "Analysis framework for RNA secondary structure")
8470 "The R4RNA package aims to be a general framework for the analysis of RNA
8471 secondary structure and comparative analysis in R.")
8472 (license license:gpl3+)))
8474 (define-public r-rhtslib
8481 (uri (bioconductor-uri "Rhtslib" version))
8484 "16ywnb8cmr2xabd1i21b92rfziw7xfbv25yv16ipw617p41wa39z"))))
8485 (properties `((upstream-name . "Rhtslib")))
8486 (build-system r-build-system)
8488 `(("r-zlibbioc" ,r-zlibbioc)))
8492 `(("pkg-config" ,pkg-config)))
8493 (home-page "https://github.com/nhayden/Rhtslib")
8494 (synopsis "High-throughput sequencing library as an R package")
8496 "This package provides the HTSlib C library for high-throughput
8497 nucleotide sequence analysis. The package is primarily useful to developers
8498 of other R packages who wish to make use of HTSlib.")
8499 (license license:lgpl2.0+)))
8501 (define-public r-bamsignals
8503 (name "r-bamsignals")
8508 (uri (bioconductor-uri "bamsignals" version))
8511 "141q3p4lzwiqk1mfxi8q1q84axjl0gyiqg59xd3sp4viny4jqmgv"))))
8512 (build-system r-build-system)
8514 `(("r-biocgenerics" ,r-biocgenerics)
8515 ("r-genomicranges" ,r-genomicranges)
8516 ("r-iranges" ,r-iranges)
8518 ("r-rhtslib" ,r-rhtslib)
8519 ("r-zlibbioc" ,r-zlibbioc)))
8522 (home-page "https://bioconductor.org/packages/bamsignals")
8523 (synopsis "Extract read count signals from bam files")
8525 "This package allows to efficiently obtain count vectors from indexed bam
8526 files. It counts the number of nucleotide sequence reads in given genomic
8527 ranges and it computes reads profiles and coverage profiles. It also handles
8529 (license license:gpl2+)))
8531 (define-public r-rcas
8537 (uri (bioconductor-uri "RCAS" version))
8540 "0vmn7a0rm2ban0kaxrf5danhss2r4hfhnwh5889fjcgqy300fdd5"))))
8541 (build-system r-build-system)
8543 `(("r-testthat" ,r-testthat)
8544 ;; During vignette building knitr checks that "pandoc-citeproc"
8546 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8548 `(("r-biocgenerics" ,r-biocgenerics)
8549 ("r-biomart" ,r-biomart)
8550 ("r-biostrings" ,r-biostrings)
8551 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8552 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8553 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8554 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8555 ("r-cowplot" ,r-cowplot)
8556 ("r-data-table" ,r-data-table)
8559 ("r-genomation" ,r-genomation)
8560 ("r-genomicfeatures" ,r-genomicfeatures)
8561 ("r-ggplot2" ,r-ggplot2)
8562 ("r-ggseqlogo" ,r-ggseqlogo)
8563 ("r-knitr" ,r-knitr)
8564 ("r-motifrg" ,r-motifrg)
8565 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8566 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8567 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8568 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8569 ("r-pbapply" ,r-pbapply)
8570 ("r-pheatmap" ,r-pheatmap)
8571 ("r-plotly" ,r-plotly)
8572 ("r-plotrix" ,r-plotrix)
8573 ("r-proxy" ,r-proxy)
8574 ("r-rsqlite" ,r-rsqlite)
8575 ("r-rtracklayer" ,r-rtracklayer)
8576 ("r-rmarkdown" ,r-rmarkdown)
8577 ("r-s4vectors" ,r-s4vectors)
8578 ("r-topgo" ,r-topgo)))
8579 (synopsis "RNA-centric annotation system")
8581 "RCAS aims to be a standalone RNA-centric annotation system that provides
8582 intuitive reports and publication-ready graphics. This package provides the R
8583 library implementing most of the pipeline's features.")
8584 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8585 (license license:artistic2.0)))
8587 (define-public rcas-web
8594 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8595 "releases/download/v" version
8596 "/rcas-web-" version ".tar.gz"))
8599 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8600 (build-system gnu-build-system)
8603 (modify-phases %standard-phases
8604 (add-after 'install 'wrap-executable
8605 (lambda* (#:key inputs outputs #:allow-other-keys)
8606 (let* ((out (assoc-ref outputs "out"))
8607 (json (assoc-ref inputs "guile-json"))
8608 (redis (assoc-ref inputs "guile-redis"))
8609 (path (string-append
8610 json "/share/guile/site/2.2:"
8611 redis "/share/guile/site/2.2")))
8612 (wrap-program (string-append out "/bin/rcas-web")
8613 `("GUILE_LOAD_PATH" ":" = (,path))
8614 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8615 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8618 `(("r-minimal" ,r-minimal)
8620 ("guile-next" ,guile-2.2)
8621 ("guile-json" ,guile-json)
8622 ("guile-redis" ,guile2.2-redis)))
8624 `(("pkg-config" ,pkg-config)))
8625 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8626 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8627 (description "This package provides a simple web interface for the
8628 @dfn{RNA-centric annotation system} (RCAS).")
8629 (license license:agpl3+)))
8631 (define-public r-mutationalpatterns
8633 (name "r-mutationalpatterns")
8638 (uri (bioconductor-uri "MutationalPatterns" version))
8641 "1yq7351j42mjxn8fd3c5bdxzb2l5s4lvqhjdvv4rwj4f600n6wj9"))))
8642 (build-system r-build-system)
8644 `(("r-biocgenerics" ,r-biocgenerics)
8645 ("r-biostrings" ,r-biostrings)
8646 ;; These two packages are suggested packages
8647 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8648 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8649 ("r-genomicranges" ,r-genomicranges)
8650 ("r-genomeinfodb" ,r-genomeinfodb)
8651 ("r-ggplot2" ,r-ggplot2)
8652 ("r-iranges" ,r-iranges)
8655 ("r-pracma" ,r-pracma)
8656 ("r-reshape2" ,r-reshape2)
8657 ("r-cowplot" ,r-cowplot)
8658 ("r-ggdendro" ,r-ggdendro)
8659 ("r-s4vectors" ,r-s4vectors)
8660 ("r-summarizedexperiment" ,r-summarizedexperiment)
8661 ("r-variantannotation" ,r-variantannotation)))
8662 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8663 (synopsis "Extract and visualize mutational patterns in genomic data")
8664 (description "This package provides an extensive toolset for the
8665 characterization and visualization of a wide range of mutational patterns
8666 in SNV base substitution data.")
8667 (license license:expat)))
8669 (define-public r-wgcna
8676 (uri (cran-uri "WGCNA" version))
8679 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8680 (properties `((upstream-name . "WGCNA")))
8681 (build-system r-build-system)
8683 `(("r-annotationdbi" ,r-annotationdbi)
8684 ("r-doparallel" ,r-doparallel)
8685 ("r-dynamictreecut" ,r-dynamictreecut)
8686 ("r-fastcluster" ,r-fastcluster)
8687 ("r-foreach" ,r-foreach)
8688 ("r-go-db" ,r-go-db)
8689 ("r-hmisc" ,r-hmisc)
8690 ("r-impute" ,r-impute)
8692 ("r-robust" ,r-robust)
8693 ("r-survival" ,r-survival)
8694 ("r-matrixstats" ,r-matrixstats)
8695 ("r-preprocesscore" ,r-preprocesscore)))
8697 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8698 (synopsis "Weighted correlation network analysis")
8700 "This package provides functions necessary to perform Weighted
8701 Correlation Network Analysis on high-dimensional data. It includes functions
8702 for rudimentary data cleaning, construction and summarization of correlation
8703 networks, module identification and functions for relating both variables and
8704 modules to sample traits. It also includes a number of utility functions for
8705 data manipulation and visualization.")
8706 (license license:gpl2+)))
8708 (define-public r-chipkernels
8709 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8712 (name "r-chipkernels")
8713 (version (string-append "1.1-" revision "." (string-take commit 9)))
8718 (url "https://github.com/ManuSetty/ChIPKernels.git")
8720 (file-name (string-append name "-" version))
8723 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8724 (build-system r-build-system)
8726 `(("r-iranges" ,r-iranges)
8727 ("r-xvector" ,r-xvector)
8728 ("r-biostrings" ,r-biostrings)
8729 ("r-bsgenome" ,r-bsgenome)
8730 ("r-gtools" ,r-gtools)
8731 ("r-genomicranges" ,r-genomicranges)
8732 ("r-sfsmisc" ,r-sfsmisc)
8733 ("r-kernlab" ,r-kernlab)
8734 ("r-s4vectors" ,r-s4vectors)
8735 ("r-biocgenerics" ,r-biocgenerics)))
8736 (home-page "https://github.com/ManuSetty/ChIPKernels")
8737 (synopsis "Build string kernels for DNA Sequence analysis")
8738 (description "ChIPKernels is an R package for building different string
8739 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8740 must be built and this dictionary can be used for determining kernels for DNA
8742 (license license:gpl2+))))
8744 (define-public r-seqgl
8751 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8752 "archive/" version ".tar.gz"))
8753 (file-name (string-append name "-" version ".tar.gz"))
8756 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8757 (build-system r-build-system)
8759 `(("r-biostrings" ,r-biostrings)
8760 ("r-chipkernels" ,r-chipkernels)
8761 ("r-genomicranges" ,r-genomicranges)
8762 ("r-spams" ,r-spams)
8763 ("r-wgcna" ,r-wgcna)
8764 ("r-fastcluster" ,r-fastcluster)))
8765 (home-page "https://github.com/ManuSetty/SeqGL")
8766 (synopsis "Group lasso for Dnase/ChIP-seq data")
8767 (description "SeqGL is a group lasso based algorithm to extract
8768 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8769 This package presents a method which uses group lasso to discriminate between
8770 bound and non bound genomic regions to accurately identify transcription
8771 factors bound at the specific regions.")
8772 (license license:gpl2+)))
8774 (define-public r-gkmsvm
8781 (uri (cran-uri "gkmSVM" version))
8784 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8785 (properties `((upstream-name . "gkmSVM")))
8786 (build-system r-build-system)
8788 `(("r-biocgenerics" ,r-biocgenerics)
8789 ("r-biostrings" ,r-biostrings)
8790 ("r-genomeinfodb" ,r-genomeinfodb)
8791 ("r-genomicranges" ,r-genomicranges)
8792 ("r-iranges" ,r-iranges)
8793 ("r-kernlab" ,r-kernlab)
8796 ("r-rtracklayer" ,r-rtracklayer)
8797 ("r-s4vectors" ,r-s4vectors)
8798 ("r-seqinr" ,r-seqinr)))
8799 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8800 (synopsis "Gapped-kmer support vector machine")
8802 "This R package provides tools for training gapped-kmer SVM classifiers
8803 for DNA and protein sequences. This package supports several sequence
8804 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8805 (license license:gpl2+)))
8807 (define-public r-tximport
8813 (uri (bioconductor-uri "tximport" version))
8816 "1qjc7ah9dzccpvcjrp9k4qnaz13x6kvy1c1xpdj503km6k528lip"))))
8817 (build-system r-build-system)
8818 (home-page "https://bioconductor.org/packages/tximport")
8819 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8821 "This package provides tools to import transcript-level abundance,
8822 estimated counts and transcript lengths, and to summarize them into matrices
8823 for use with downstream gene-level analysis packages. Average transcript
8824 length, weighted by sample-specific transcript abundance estimates, is
8825 provided as a matrix which can be used as an offset for different expression
8826 of gene-level counts.")
8827 (license license:gpl2+)))
8829 (define-public r-rhdf5
8835 (uri (bioconductor-uri "rhdf5" version))
8838 "15cmmchhk8bnp94gxg0zk9qyzdjx5kv16dzpbnb62mkq7ydmifx6"))))
8839 (build-system r-build-system)
8841 `(("r-rhdf5lib" ,r-rhdf5lib)))
8844 (home-page "https://bioconductor.org/packages/rhdf5")
8845 (synopsis "HDF5 interface to R")
8847 "This R/Bioconductor package provides an interface between HDF5 and R.
8848 HDF5's main features are the ability to store and access very large and/or
8849 complex datasets and a wide variety of metadata on mass storage (disk) through
8850 a completely portable file format. The rhdf5 package is thus suited for the
8851 exchange of large and/or complex datasets between R and other software
8852 package, and for letting R applications work on datasets that are larger than
8853 the available RAM.")
8854 (license license:artistic2.0)))
8856 (define-public r-annotationfilter
8858 (name "r-annotationfilter")
8862 (uri (bioconductor-uri "AnnotationFilter" version))
8865 "1w8ypfdz4g7vnwfrvnhjcpm8waciqyq2cn883ajdwg4vv7a5mj9a"))))
8867 `((upstream-name . "AnnotationFilter")))
8868 (build-system r-build-system)
8870 `(("r-genomicranges" ,r-genomicranges)
8871 ("r-lazyeval" ,r-lazyeval)))
8872 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8873 (synopsis "Facilities for filtering Bioconductor annotation resources")
8875 "This package provides classes and other infrastructure to implement
8876 filters for manipulating Bioconductor annotation resources. The filters are
8877 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8878 (license license:artistic2.0)))
8880 (define-public emboss
8886 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8887 (version-major+minor version) ".0/"
8888 "EMBOSS-" version ".tar.gz"))
8891 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8892 (build-system gnu-build-system)
8895 (list (string-append "--with-hpdf="
8896 (assoc-ref %build-inputs "libharu")))
8898 (modify-phases %standard-phases
8899 (add-after 'unpack 'fix-checks
8901 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8902 ;; and zlib, but assume that they are all found at the same
8904 (substitute* "configure.in"
8905 (("CHECK_PNGDRIVER")
8906 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8907 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8908 AM_CONDITIONAL(AMPNG, true)"))
8910 (add-after 'fix-checks 'disable-update-check
8912 ;; At build time there is no connection to the Internet, so
8913 ;; looking for updates will not work.
8914 (substitute* "Makefile.am"
8915 (("\\$\\(bindir\\)/embossupdate") ""))
8917 (add-after 'disable-update-check 'autogen
8918 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8924 ("libharu" ,libharu)
8927 `(("autoconf" ,autoconf)
8928 ("automake" ,automake)
8929 ("libtool" ,libtool)
8930 ("pkg-config" ,pkg-config)))
8931 (home-page "http://emboss.sourceforge.net")
8932 (synopsis "Molecular biology analysis suite")
8933 (description "EMBOSS is the \"European Molecular Biology Open Software
8934 Suite\". EMBOSS is an analysis package specially developed for the needs of
8935 the molecular biology (e.g. EMBnet) user community. The software
8936 automatically copes with data in a variety of formats and even allows
8937 transparent retrieval of sequence data from the web. It also provides a
8938 number of libraries for the development of software in the field of molecular
8939 biology. EMBOSS also integrates a range of currently available packages and
8940 tools for sequence analysis into a seamless whole.")
8941 (license license:gpl2+)))
8944 (let ((revision "1")
8945 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8948 ;; The version is 2.13.0 even though no release archives have been
8949 ;; published as yet.
8950 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8954 (url "https://github.com/arq5x/bits.git")
8956 (file-name (string-append name "-" version "-checkout"))
8959 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8960 (build-system gnu-build-system)
8962 `(#:tests? #f ;no tests included
8964 (modify-phases %standard-phases
8966 (add-after 'unpack 'remove-cuda
8968 (substitute* "Makefile"
8970 (("(bits_test_intersections) \\\\" _ match) match))
8973 (lambda* (#:key outputs #:allow-other-keys)
8975 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8980 (home-page "https://github.com/arq5x/bits")
8981 (synopsis "Implementation of binary interval search algorithm")
8982 (description "This package provides an implementation of the
8983 BITS (Binary Interval Search) algorithm, an approach to interval set
8984 intersection. It is especially suited for the comparison of diverse genomic
8985 datasets and the exploration of large datasets of genome
8986 intervals (e.g. genes, sequence alignments).")
8987 (license license:gpl2))))
8989 (define-public piranha
8990 ;; There is no release tarball for the latest version. The latest commit is
8991 ;; older than one year at the time of this writing.
8992 (let ((revision "1")
8993 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8996 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9000 (url "https://github.com/smithlabcode/piranha.git")
9002 (file-name (git-file-name name version))
9005 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9006 (build-system gnu-build-system)
9008 `(#:test-target "test"
9010 (modify-phases %standard-phases
9011 (add-after 'unpack 'copy-smithlab-cpp
9012 (lambda* (#:key inputs #:allow-other-keys)
9013 (for-each (lambda (file)
9014 (install-file file "./src/smithlab_cpp/"))
9015 (find-files (assoc-ref inputs "smithlab-cpp")))
9017 (add-after 'install 'install-to-store
9018 (lambda* (#:key outputs #:allow-other-keys)
9019 (let* ((out (assoc-ref outputs "out"))
9020 (bin (string-append out "/bin")))
9021 (for-each (lambda (file)
9022 (install-file file bin))
9023 (find-files "bin" ".*")))
9026 (list (string-append "--with-bam_tools_headers="
9027 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9028 (string-append "--with-bam_tools_library="
9029 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9031 `(("bamtools" ,bamtools)
9032 ("samtools" ,samtools-0.1)
9035 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9039 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9041 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9044 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9046 `(("python" ,python-2)))
9047 (home-page "https://github.com/smithlabcode/piranha")
9048 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9050 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9051 RIP-seq experiments. It takes input in BED or BAM format and identifies
9052 regions of statistically significant read enrichment. Additional covariates
9053 may optionally be provided to further inform the peak-calling process.")
9054 (license license:gpl3+))))
9062 (uri (string-append "https://pypi.python.org/packages/source/P"
9063 "/PePr/PePr-" version ".tar.gz"))
9066 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9067 (build-system python-build-system)
9069 `(#:python ,python-2 ; python2 only
9070 #:tests? #f)) ; no tests included
9072 `(("python2-numpy" ,python2-numpy)
9073 ("python2-scipy" ,python2-scipy)
9074 ("python2-pysam" ,python2-pysam)))
9075 (home-page "https://github.com/shawnzhangyx/PePr")
9076 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9078 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9079 that is primarily designed for data with biological replicates. It uses a
9080 negative binomial distribution to model the read counts among the samples in
9081 the same group, and look for consistent differences between ChIP and control
9082 group or two ChIP groups run under different conditions.")
9083 (license license:gpl3+)))
9085 (define-public filevercmp
9086 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9089 (version (string-append "0-1." (string-take commit 7)))
9092 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9094 (file-name (string-append name "-" version ".tar.gz"))
9096 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9097 (build-system gnu-build-system)
9099 `(#:tests? #f ; There are no tests to run.
9101 (modify-phases %standard-phases
9102 (delete 'configure) ; There is no configure phase.
9104 (lambda* (#:key outputs #:allow-other-keys)
9105 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9106 (install-file "filevercmp" bin)))))))
9107 (home-page "https://github.com/ekg/filevercmp")
9108 (synopsis "This program compares version strings")
9109 (description "This program compares version strings. It intends to be a
9110 replacement for strverscmp.")
9111 (license license:gpl3+))))
9113 (define-public multiqc
9120 (uri (pypi-uri "multiqc" version))
9123 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9124 (build-system python-build-system)
9126 `(("python-jinja2" ,python-jinja2)
9127 ("python-simplejson" ,python-simplejson)
9128 ("python-pyyaml" ,python-pyyaml)
9129 ("python-click" ,python-click)
9130 ("python-spectra" ,python-spectra)
9131 ("python-requests" ,python-requests)
9132 ("python-markdown" ,python-markdown)
9133 ("python-lzstring" ,python-lzstring)
9134 ("python-matplotlib" ,python-matplotlib)
9135 ("python-numpy" ,python-numpy)
9136 ;; MultQC checks for the presence of nose at runtime.
9137 ("python-nose" ,python-nose)))
9140 (modify-phases %standard-phases
9141 (add-after 'unpack 'relax-requirements
9143 (substitute* "setup.py"
9144 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9145 ;; than the one in Guix, but should work fine with 2.2.2.
9146 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9147 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9148 (("['\"]matplotlib.*?['\"]")
9151 (home-page "http://multiqc.info")
9152 (synopsis "Aggregate bioinformatics analysis reports")
9154 "MultiQC is a tool to aggregate bioinformatics results across many
9155 samples into a single report. It contains modules for a large number of
9156 common bioinformatics tools.")
9157 (license license:gpl3+)))
9159 (define-public r-chipseq
9166 (uri (bioconductor-uri "chipseq" version))
9169 "09f8dgl5ni75qkf7nvvppwr3irpplv4xb3ks59ld7l8i2mplcrx7"))))
9170 (build-system r-build-system)
9172 `(("r-biocgenerics" ,r-biocgenerics)
9173 ("r-genomicranges" ,r-genomicranges)
9174 ("r-iranges" ,r-iranges)
9175 ("r-lattice" ,r-lattice)
9176 ("r-s4vectors" ,r-s4vectors)
9177 ("r-shortread" ,r-shortread)))
9178 (home-page "https://bioconductor.org/packages/chipseq")
9179 (synopsis "Package for analyzing ChIPseq data")
9181 "This package provides tools for processing short read data from ChIPseq
9183 (license license:artistic2.0)))
9185 (define-public r-copyhelper
9187 (name "r-copyhelper")
9192 (uri (string-append "https://bioconductor.org/packages/release/"
9193 "data/experiment/src/contrib/CopyhelpeR_"
9197 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9198 (properties `((upstream-name . "CopyhelpeR")))
9199 (build-system r-build-system)
9200 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9201 (synopsis "Helper files for CopywriteR")
9203 "This package contains the helper files that are required to run the
9204 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9205 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9206 mm10. In addition, it contains a blacklist filter to remove regions that
9207 display copy number variation. Files are stored as GRanges objects from the
9208 GenomicRanges Bioconductor package.")
9209 (license license:gpl2)))
9211 (define-public r-copywriter
9213 (name "r-copywriter")
9218 (uri (bioconductor-uri "CopywriteR" version))
9221 "0b7xwq1va2zclb54f07c5ipmmq4iv2hrlph3j93jz5hmyayv50z3"))))
9222 (properties `((upstream-name . "CopywriteR")))
9223 (build-system r-build-system)
9225 `(("r-biocparallel" ,r-biocparallel)
9226 ("r-chipseq" ,r-chipseq)
9227 ("r-copyhelper" ,r-copyhelper)
9228 ("r-data-table" ,r-data-table)
9229 ("r-dnacopy" ,r-dnacopy)
9230 ("r-futile-logger" ,r-futile-logger)
9231 ("r-genomeinfodb" ,r-genomeinfodb)
9232 ("r-genomicalignments" ,r-genomicalignments)
9233 ("r-genomicranges" ,r-genomicranges)
9234 ("r-gtools" ,r-gtools)
9235 ("r-iranges" ,r-iranges)
9236 ("r-matrixstats" ,r-matrixstats)
9237 ("r-rsamtools" ,r-rsamtools)
9238 ("r-s4vectors" ,r-s4vectors)))
9239 (home-page "https://github.com/PeeperLab/CopywriteR")
9240 (synopsis "Copy number information from targeted sequencing")
9242 "CopywriteR extracts DNA copy number information from targeted sequencing
9243 by utilizing off-target reads. It allows for extracting uniformly distributed
9244 copy number information, can be used without reference, and can be applied to
9245 sequencing data obtained from various techniques including chromatin
9246 immunoprecipitation and target enrichment on small gene panels. Thereby,
9247 CopywriteR constitutes a widely applicable alternative to available copy
9248 number detection tools.")
9249 (license license:gpl2)))
9251 (define-public r-methylkit
9253 (name "r-methylkit")
9257 (uri (bioconductor-uri "methylKit" version))
9260 "1hr2czi5ybdf7hdmqsv39d17f3mvmw94wa38bc14zzm9mgy9gfy7"))))
9261 (properties `((upstream-name . "methylKit")))
9262 (build-system r-build-system)
9264 `(("r-data-table" ,r-data-table)
9265 ("r-emdbook" ,r-emdbook)
9266 ("r-fastseg" ,r-fastseg)
9267 ("r-genomeinfodb" ,r-genomeinfodb)
9268 ("r-genomicranges" ,r-genomicranges)
9269 ("r-gtools" ,r-gtools)
9270 ("r-iranges" ,r-iranges)
9271 ("r-kernsmooth" ,r-kernsmooth)
9272 ("r-limma" ,r-limma)
9273 ("r-mclust" ,r-mclust)
9274 ("r-qvalue" ,r-qvalue)
9275 ("r-r-utils" ,r-r-utils)
9277 ("r-rhtslib" ,r-rhtslib)
9278 ("r-rsamtools" ,r-rsamtools)
9279 ("r-rtracklayer" ,r-rtracklayer)
9280 ("r-s4vectors" ,r-s4vectors)
9281 ("r-zlibbioc" ,r-zlibbioc)))
9284 (home-page "https://github.com/al2na/methylKit")
9286 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9288 "MethylKit is an R package for DNA methylation analysis and annotation
9289 from high-throughput bisulfite sequencing. The package is designed to deal
9290 with sequencing data from @dfn{Reduced representation bisulfite
9291 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9292 genome bisulfite sequencing. It also has functions to analyze base-pair
9293 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9295 (license license:artistic2.0)))
9297 (define-public r-sva
9304 (uri (bioconductor-uri "sva" version))
9307 "0a3jqbz0jp1jxrnjkqfpmca840yqcdwxprdl608bzzx2zb4jl52s"))))
9308 (build-system r-build-system)
9310 `(("r-genefilter" ,r-genefilter)
9312 ("r-biocparallel" ,r-biocparallel)
9313 ("r-matrixstats" ,r-matrixstats)
9314 ("r-limma" ,r-limma)))
9315 (home-page "https://bioconductor.org/packages/sva")
9316 (synopsis "Surrogate variable analysis")
9318 "This package contains functions for removing batch effects and other
9319 unwanted variation in high-throughput experiment. It also contains functions
9320 for identifying and building surrogate variables for high-dimensional data
9321 sets. Surrogate variables are covariates constructed directly from
9322 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9323 imaging data that can be used in subsequent analyses to adjust for unknown,
9324 unmodeled, or latent sources of noise.")
9325 (license license:artistic2.0)))
9327 (define-public r-seqminer
9334 (uri (cran-uri "seqminer" version))
9337 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9338 (build-system r-build-system)
9341 (home-page "http://seqminer.genomic.codes")
9342 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9344 "This package provides tools to integrate nucleotide sequencing
9345 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9346 ;; Any version of the GPL is acceptable
9347 (license (list license:gpl2+ license:gpl3+))))
9349 (define-public r-raremetals2
9351 (name "r-raremetals2")
9356 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9357 "b/b7/RareMETALS2_" version ".tar.gz"))
9360 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9361 (properties `((upstream-name . "RareMETALS2")))
9362 (build-system r-build-system)
9364 `(("r-seqminer" ,r-seqminer)
9365 ("r-mvtnorm" ,r-mvtnorm)
9367 ("r-compquadform" ,r-compquadform)
9368 ("r-getopt" ,r-getopt)))
9369 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9370 (synopsis "Analyze gene-level association tests for binary trait")
9372 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9373 It was designed to meta-analyze gene-level association tests for binary trait.
9374 While rareMETALS offers a near-complete solution for meta-analysis of
9375 gene-level tests for quantitative trait, it does not offer the optimal
9376 solution for binary trait. The package rareMETALS2 offers improved features
9377 for analyzing gene-level association tests in meta-analyses for binary
9379 (license license:gpl3)))
9381 (define-public r-maldiquant
9383 (name "r-maldiquant")
9388 (uri (cran-uri "MALDIquant" version))
9391 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9392 (properties `((upstream-name . "MALDIquant")))
9393 (build-system r-build-system)
9394 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9395 (synopsis "Quantitative analysis of mass spectrometry data")
9397 "This package provides a complete analysis pipeline for matrix-assisted
9398 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9399 two-dimensional mass spectrometry data. In addition to commonly used plotting
9400 and processing methods it includes distinctive features, namely baseline
9401 subtraction methods such as morphological filters (TopHat) or the
9402 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9403 alignment using warping functions, handling of replicated measurements as well
9404 as allowing spectra with different resolutions.")
9405 (license license:gpl3+)))
9407 (define-public r-protgenerics
9409 (name "r-protgenerics")
9414 (uri (bioconductor-uri "ProtGenerics" version))
9417 "05jbadw2aiwy8vi2ia0jxg06cmwhly2cq4dy1ag7kdxf1c5i9ccn"))))
9418 (properties `((upstream-name . "ProtGenerics")))
9419 (build-system r-build-system)
9420 (home-page "https://github.com/lgatto/ProtGenerics")
9421 (synopsis "S4 generic functions for proteomics infrastructure")
9423 "This package provides S4 generic functions needed by Bioconductor
9424 proteomics packages.")
9425 (license license:artistic2.0)))
9427 (define-public r-mzr
9434 (uri (bioconductor-uri "mzR" version))
9437 "190m2bq5bqxhljaj4f7vz9wj5h5laaxd8zp5jampnql6xc4zmarg"))
9438 (modules '((guix build utils)))
9441 (delete-file-recursively "src/boost")
9443 (properties `((upstream-name . "mzR")))
9444 (build-system r-build-system)
9447 (modify-phases %standard-phases
9448 (add-after 'unpack 'use-system-boost
9450 (substitute* "src/Makevars"
9451 (("\\./boost/libs.*") "")
9452 (("ARCH_OBJS=" line)
9454 "\nARCH_LIBS=-lboost_system -lboost_regex \
9455 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9458 `(("boost" ,boost) ; use this instead of the bundled boost sources
9462 `(("r-biobase" ,r-biobase)
9463 ("r-biocgenerics" ,r-biocgenerics)
9464 ("r-protgenerics" ,r-protgenerics)
9466 ("r-rhdf5lib" ,r-rhdf5lib)
9467 ("r-zlibbioc" ,r-zlibbioc)))
9468 (home-page "https://github.com/sneumann/mzR/")
9469 (synopsis "Parser for mass spectrometry data files")
9471 "The mzR package provides a unified API to the common file formats and
9472 parsers available for mass spectrometry data. It comes with a wrapper for the
9473 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9474 The package contains the original code written by the ISB, and a subset of the
9475 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9476 previously been used in XCMS.")
9477 (license license:artistic2.0)))
9479 (define-public r-affyio
9486 (uri (bioconductor-uri "affyio" version))
9489 "0sh5wnnchyfpq5n6rchbqmb27byn7kdzn5rgran6i39c81i5z22n"))))
9490 (build-system r-build-system)
9492 `(("r-zlibbioc" ,r-zlibbioc)))
9495 (home-page "https://github.com/bmbolstad/affyio")
9496 (synopsis "Tools for parsing Affymetrix data files")
9498 "This package provides routines for parsing Affymetrix data files based
9499 upon file format information. The primary focus is on accessing the CEL and
9501 (license license:lgpl2.0+)))
9503 (define-public r-affy
9510 (uri (bioconductor-uri "affy" version))
9513 "0sxq875sigm21sf3qncrfrwfdz9nqw1vldxn3d3hj6aq64jg1ki6"))))
9514 (build-system r-build-system)
9516 `(("r-affyio" ,r-affyio)
9517 ("r-biobase" ,r-biobase)
9518 ("r-biocgenerics" ,r-biocgenerics)
9519 ("r-biocinstaller" ,r-biocinstaller)
9520 ("r-preprocesscore" ,r-preprocesscore)
9521 ("r-zlibbioc" ,r-zlibbioc)))
9524 (home-page "https://bioconductor.org/packages/affy")
9525 (synopsis "Methods for affymetrix oligonucleotide arrays")
9527 "This package contains functions for exploratory oligonucleotide array
9529 (license license:lgpl2.0+)))
9531 (define-public r-vsn
9538 (uri (bioconductor-uri "vsn" version))
9541 "0k6mah3g3zqbfap31xmvig4fn452a18xwwa5y0mfj5mj8588p57h"))))
9542 (build-system r-build-system)
9544 `(("r-affy" ,r-affy)
9545 ("r-biobase" ,r-biobase)
9546 ("r-ggplot2" ,r-ggplot2)
9547 ("r-lattice" ,r-lattice)
9548 ("r-limma" ,r-limma)))
9549 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9550 (synopsis "Variance stabilization and calibration for microarray data")
9552 "The package implements a method for normalising microarray intensities,
9553 and works for single- and multiple-color arrays. It can also be used for data
9554 from other technologies, as long as they have similar format. The method uses
9555 a robust variant of the maximum-likelihood estimator for an
9556 additive-multiplicative error model and affine calibration. The model
9557 incorporates data calibration step (a.k.a. normalization), a model for the
9558 dependence of the variance on the mean intensity and a variance stabilizing
9559 data transformation. Differences between transformed intensities are
9560 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9561 their variance is independent of the mean, and they are usually more sensitive
9562 and specific in detecting differential transcription.")
9563 (license license:artistic2.0)))
9565 (define-public r-mzid
9572 (uri (bioconductor-uri "mzID" version))
9575 "060k0xlhg8q802c6zsb4b8ps0ccd9ybyaz0gnsvqkxb786i2vk40"))))
9576 (properties `((upstream-name . "mzID")))
9577 (build-system r-build-system)
9579 `(("r-doparallel" ,r-doparallel)
9580 ("r-foreach" ,r-foreach)
9581 ("r-iterators" ,r-iterators)
9583 ("r-protgenerics" ,r-protgenerics)
9586 (home-page "https://bioconductor.org/packages/mzID")
9587 (synopsis "Parser for mzIdentML files")
9589 "This package provides a parser for mzIdentML files implemented using the
9590 XML package. The parser tries to be general and able to handle all types of
9591 mzIdentML files with the drawback of having less pretty output than a vendor
9593 (license license:gpl2+)))
9595 (define-public r-pcamethods
9597 (name "r-pcamethods")
9602 (uri (bioconductor-uri "pcaMethods" version))
9605 "0v99yf8m7ryh6z0r3z0ggpqfnflcq5bn1q1i1cl9b7q4p6b4sa07"))))
9606 (properties `((upstream-name . "pcaMethods")))
9607 (build-system r-build-system)
9609 `(("r-biobase" ,r-biobase)
9610 ("r-biocgenerics" ,r-biocgenerics)
9612 ("r-rcpp" ,r-rcpp)))
9613 (home-page "https://github.com/hredestig/pcamethods")
9614 (synopsis "Collection of PCA methods")
9616 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9617 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9618 for missing value estimation is included for comparison. BPCA, PPCA and
9619 NipalsPCA may be used to perform PCA on incomplete data as well as for
9620 accurate missing value estimation. A set of methods for printing and plotting
9621 the results is also provided. All PCA methods make use of the same data
9622 structure (pcaRes) to provide a common interface to the PCA results.")
9623 (license license:gpl3+)))
9625 (define-public r-msnbase
9632 (uri (bioconductor-uri "MSnbase" version))
9635 "0zrpx9r93q5ca2zdak5rs2m9sjm0wjdra1xfj3d3sx6p5gzfyg6n"))))
9636 (properties `((upstream-name . "MSnbase")))
9637 (build-system r-build-system)
9639 `(("r-affy" ,r-affy)
9640 ("r-biobase" ,r-biobase)
9641 ("r-biocgenerics" ,r-biocgenerics)
9642 ("r-biocparallel" ,r-biocparallel)
9643 ("r-digest" ,r-digest)
9644 ("r-ggplot2" ,r-ggplot2)
9645 ("r-impute" ,r-impute)
9646 ("r-iranges" ,r-iranges)
9647 ("r-lattice" ,r-lattice)
9648 ("r-maldiquant" ,r-maldiquant)
9652 ("r-pcamethods" ,r-pcamethods)
9654 ("r-preprocesscore" ,r-preprocesscore)
9655 ("r-protgenerics" ,r-protgenerics)
9657 ("r-s4vectors" ,r-s4vectors)
9658 ("r-scales" ,r-scales)
9661 (home-page "https://github.com/lgatto/MSnbase")
9662 (synopsis "Base functions and classes for MS-based proteomics")
9664 "This package provides basic plotting, data manipulation and processing
9665 of mass spectrometry based proteomics data.")
9666 (license license:artistic2.0)))
9668 (define-public r-msnid
9675 (uri (bioconductor-uri "MSnID" version))
9678 "172q5chi44104iz4y0g42wrimfp7hlhrfa8vzybx6m0ccrkkhl17"))))
9679 (properties `((upstream-name . "MSnID")))
9680 (build-system r-build-system)
9682 `(("r-biobase" ,r-biobase)
9683 ("r-data-table" ,r-data-table)
9684 ("r-doparallel" ,r-doparallel)
9685 ("r-dplyr" ,r-dplyr)
9686 ("r-foreach" ,r-foreach)
9687 ("r-iterators" ,r-iterators)
9688 ("r-msnbase" ,r-msnbase)
9691 ("r-protgenerics" ,r-protgenerics)
9692 ("r-r-cache" ,r-r-cache)
9694 ("r-reshape2" ,r-reshape2)))
9695 (home-page "https://bioconductor.org/packages/MSnID")
9696 (synopsis "Utilities for LC-MSn proteomics identifications")
9698 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9699 from mzIdentML (leveraging the mzID package) or text files. After collating
9700 the search results from multiple datasets it assesses their identification
9701 quality and optimize filtering criteria to achieve the maximum number of
9702 identifications while not exceeding a specified false discovery rate. It also
9703 contains a number of utilities to explore the MS/MS results and assess missed
9704 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9705 (license license:artistic2.0)))
9707 (define-public r-seurat
9713 (uri (cran-uri "Seurat" version))
9716 "1sjpy5rrpvlpm6hs7qy7qpglgbp7zrgfybcsalpmjb51rhxhgcg1"))
9717 ;; Delete pre-built jar.
9719 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9721 (properties `((upstream-name . "Seurat")))
9722 (build-system r-build-system)
9725 (modify-phases %standard-phases
9726 (add-after 'unpack 'build-jar
9727 (lambda* (#:key inputs #:allow-other-keys)
9728 (let ((classesdir "tmp-classes"))
9729 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9731 (with-output-to-file "manifest"
9733 (display "Manifest-Version: 1.0
9734 Main-Class: ModularityOptimizer\n")))
9735 (and (zero? (apply system* `("javac" "-d" ,classesdir
9736 ,@(find-files "java" "\\.java$"))))
9737 (zero? (system* "jar"
9739 "inst/java/ModularityOptimizer.jar"
9740 "-C" classesdir ".")))))))))
9742 `(("jdk" ,icedtea "jdk")))
9745 ("r-caret" ,r-caret)
9746 ("r-cluster" ,r-cluster)
9747 ("r-cowplot" ,r-cowplot)
9748 ("r-diffusionmap" ,r-diffusionmap)
9749 ("r-dosnow" ,r-dosnow)
9750 ("r-dplyr" ,r-dplyr)
9752 ("r-fitdistrplus" ,r-fitdistrplus)
9754 ("r-foreach" ,r-foreach)
9756 ("r-gdata" ,r-gdata)
9757 ("r-ggplot2" ,r-ggplot2)
9758 ("r-ggridges" ,r-ggridges)
9759 ("r-gplots" ,r-gplots)
9760 ("r-hdf5r" ,r-hdf5r)
9761 ("r-hmisc" ,r-hmisc)
9763 ("r-igraph" ,r-igraph)
9764 ("r-irlba" ,r-irlba)
9766 ("r-lmtest" ,r-lmtest)
9768 ("r-matrix" ,r-matrix)
9769 ("r-metap" ,r-metap)
9770 ("r-mixtools" ,r-mixtools)
9771 ("r-pbapply" ,r-pbapply)
9772 ("r-plotly" ,r-plotly)
9774 ("r-ranger" ,r-ranger)
9776 ("r-rcolorbrewer" ,r-rcolorbrewer)
9778 ("r-rcppeigen" ,r-rcppeigen)
9779 ("r-rcppprogress" ,r-rcppprogress)
9780 ("r-reshape2" ,r-reshape2)
9781 ("r-reticulate" ,r-reticulate)
9783 ("r-rtsne" ,r-rtsne)
9784 ("r-sdmtools" ,r-sdmtools)
9785 ("r-stringr" ,r-stringr)
9786 ("r-tclust" ,r-tclust)
9787 ("r-tidyr" ,r-tidyr)
9789 ("r-vgam" ,r-vgam)))
9790 (home-page "http://www.satijalab.org/seurat")
9791 (synopsis "Seurat is an R toolkit for single cell genomics")
9793 "This package is an R package designed for QC, analysis, and
9794 exploration of single cell RNA-seq data. It easily enables widely-used
9795 analytical techniques, including the identification of highly variable genes,
9796 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9797 algorithms; density clustering, hierarchical clustering, k-means, and the
9798 discovery of differentially expressed genes and markers.")
9799 (license license:gpl3)))
9801 (define-public r-aroma-light
9803 (name "r-aroma-light")
9808 (uri (bioconductor-uri "aroma.light" version))
9811 "1dxsiwsrwcq9mj573f9vpdzrhagdqzal328ma8076px4gg6khxkn"))))
9812 (properties `((upstream-name . "aroma.light")))
9813 (build-system r-build-system)
9815 `(("r-matrixstats" ,r-matrixstats)
9816 ("r-r-methodss3" ,r-r-methodss3)
9818 ("r-r-utils" ,r-r-utils)))
9819 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9820 (synopsis "Methods for normalization and visualization of microarray data")
9822 "This package provides methods for microarray analysis that take basic
9823 data types such as matrices and lists of vectors. These methods can be used
9824 standalone, be utilized in other packages, or be wrapped up in higher-level
9826 (license license:gpl2+)))
9828 (define-public r-deseq
9835 (uri (bioconductor-uri "DESeq" version))
9838 "0ykxw8ksif026xy25wx50j2sdsrp156aqkmhcgfjkpgcw699glnm"))))
9839 (properties `((upstream-name . "DESeq")))
9840 (build-system r-build-system)
9842 `(("r-biobase" ,r-biobase)
9843 ("r-biocgenerics" ,r-biocgenerics)
9844 ("r-genefilter" ,r-genefilter)
9845 ("r-geneplotter" ,r-geneplotter)
9846 ("r-lattice" ,r-lattice)
9847 ("r-locfit" ,r-locfit)
9849 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9850 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9851 (synopsis "Differential gene expression analysis")
9853 "This package provides tools for estimating variance-mean dependence in
9854 count data from high-throughput genetic sequencing assays and for testing for
9855 differential expression based on a model using the negative binomial
9857 (license license:gpl3+)))
9859 (define-public r-edaseq
9866 (uri (bioconductor-uri "EDASeq" version))
9869 "1832pb3jkim4vrqzb8lajwx9r482bhww5n9nz3s6crvyamlp2dj0"))))
9870 (properties `((upstream-name . "EDASeq")))
9871 (build-system r-build-system)
9873 `(("r-annotationdbi" ,r-annotationdbi)
9874 ("r-aroma-light" ,r-aroma-light)
9875 ("r-biobase" ,r-biobase)
9876 ("r-biocgenerics" ,r-biocgenerics)
9877 ("r-biomart" ,r-biomart)
9878 ("r-biostrings" ,r-biostrings)
9879 ("r-deseq" ,r-deseq)
9880 ("r-genomicfeatures" ,r-genomicfeatures)
9881 ("r-genomicranges" ,r-genomicranges)
9882 ("r-iranges" ,r-iranges)
9883 ("r-rsamtools" ,r-rsamtools)
9884 ("r-shortread" ,r-shortread)))
9885 (home-page "https://github.com/drisso/EDASeq")
9886 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9888 "This package provides support for numerical and graphical summaries of
9889 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9890 adjust for GC-content effect (or other gene-level effects) on read counts:
9891 loess robust local regression, global-scaling, and full-quantile
9892 normalization. Between-lane normalization procedures to adjust for
9893 distributional differences between lanes (e.g., sequencing depth):
9894 global-scaling and full-quantile normalization.")
9895 (license license:artistic2.0)))
9897 (define-public r-interactivedisplaybase
9899 (name "r-interactivedisplaybase")
9904 (uri (bioconductor-uri "interactiveDisplayBase" version))
9907 "05w58z3i9vkma4jd6rhjaxls4yiq4kwrppgcdq9xrr1pxp99k575"))))
9909 `((upstream-name . "interactiveDisplayBase")))
9910 (build-system r-build-system)
9912 `(("r-biocgenerics" ,r-biocgenerics)
9913 ("r-shiny" ,r-shiny)))
9914 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9915 (synopsis "Base package for web displays of Bioconductor objects")
9917 "This package contains the basic methods needed to generate interactive
9918 Shiny-based display methods for Bioconductor objects.")
9919 (license license:artistic2.0)))
9921 (define-public r-annotationhub
9923 (name "r-annotationhub")
9928 (uri (bioconductor-uri "AnnotationHub" version))
9931 "11gh7qkgazs90czdqgv74gh2hz26xrmdp6wsz9x5pygbxls8xdw3"))))
9932 (properties `((upstream-name . "AnnotationHub")))
9933 (build-system r-build-system)
9935 `(("r-annotationdbi" ,r-annotationdbi)
9936 ("r-biocgenerics" ,r-biocgenerics)
9937 ("r-biocinstaller" ,r-biocinstaller)
9940 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9941 ("r-rsqlite" ,r-rsqlite)
9942 ("r-s4vectors" ,r-s4vectors)
9943 ("r-yaml" ,r-yaml)))
9944 (home-page "https://bioconductor.org/packages/AnnotationHub")
9945 (synopsis "Client to access AnnotationHub resources")
9947 "This package provides a client for the Bioconductor AnnotationHub web
9948 resource. The AnnotationHub web resource provides a central location where
9949 genomic files (e.g. VCF, bed, wig) and other resources from standard
9950 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9951 metadata about each resource, e.g., a textual description, tags, and date of
9952 modification. The client creates and manages a local cache of files retrieved
9953 by the user, helping with quick and reproducible access.")
9954 (license license:artistic2.0)))
9956 (define-public r-fastseg
9963 (uri (bioconductor-uri "fastseg" version))
9966 "1yw6hai6hb8qy7akdm4frfp6h4zy93zb68kdj094sanm7kgqmgik"))))
9967 (build-system r-build-system)
9969 `(("r-biobase" ,r-biobase)
9970 ("r-biocgenerics" ,r-biocgenerics)
9971 ("r-genomicranges" ,r-genomicranges)
9972 ("r-iranges" ,r-iranges)
9973 ("r-s4vectors" ,r-s4vectors)))
9974 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9975 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9977 "Fastseg implements a very fast and efficient segmentation algorithm.
9978 It can segment data from DNA microarrays and data from next generation
9979 sequencing for example to detect copy number segments. Further it can segment
9980 data from RNA microarrays like tiling arrays to identify transcripts. Most
9981 generally, it can segment data given as a matrix or as a vector. Various data
9982 formats can be used as input to fastseg like expression set objects for
9983 microarrays or GRanges for sequencing data.")
9984 (license license:lgpl2.0+)))
9986 (define-public r-keggrest
9993 (uri (bioconductor-uri "KEGGREST" version))
9996 "1349vidgl9m10l1rbrp3pkwwgi2xcbsw9h9z2xqbvg97lmqc4r8j"))))
9997 (properties `((upstream-name . "KEGGREST")))
9998 (build-system r-build-system)
10000 `(("r-biostrings" ,r-biostrings)
10003 (home-page "https://bioconductor.org/packages/KEGGREST")
10004 (synopsis "Client-side REST access to KEGG")
10006 "This package provides a package that provides a client interface to the
10007 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10008 (license license:artistic2.0)))
10010 (define-public r-gage
10017 (uri (bioconductor-uri "gage" version))
10020 "0j3cqxy97lpf146wkmdfaq9680gicmzxvhp6w5pxq3j7ipiy7262"))))
10021 (build-system r-build-system)
10023 `(("r-annotationdbi" ,r-annotationdbi)
10024 ("r-graph" ,r-graph)
10025 ("r-keggrest" ,r-keggrest)))
10026 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10027 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10029 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10030 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10031 data attributes including sample sizes, experimental designs, assay platforms,
10032 and other types of heterogeneity. The gage package provides functions for
10033 basic GAGE analysis, result processing and presentation. In addition, it
10034 provides demo microarray data and commonly used gene set data based on KEGG
10035 pathways and GO terms. These funtions and data are also useful for gene set
10036 analysis using other methods.")
10037 (license license:gpl2+)))
10039 (define-public r-genomicfiles
10041 (name "r-genomicfiles")
10046 (uri (bioconductor-uri "GenomicFiles" version))
10049 "0bhsq5czigrjyl9gkb2kpkpl367b3ac5g8s280adkcxggn9g7sxq"))))
10050 (properties `((upstream-name . "GenomicFiles")))
10051 (build-system r-build-system)
10053 `(("r-biocgenerics" ,r-biocgenerics)
10054 ("r-biocparallel" ,r-biocparallel)
10055 ("r-genomeinfodb" ,r-genomeinfodb)
10056 ("r-genomicalignments" ,r-genomicalignments)
10057 ("r-genomicranges" ,r-genomicranges)
10058 ("r-iranges" ,r-iranges)
10059 ("r-rsamtools" ,r-rsamtools)
10060 ("r-rtracklayer" ,r-rtracklayer)
10061 ("r-s4vectors" ,r-s4vectors)
10062 ("r-summarizedexperiment" ,r-summarizedexperiment)
10063 ("r-variantannotation" ,r-variantannotation)))
10064 (home-page "https://bioconductor.org/packages/GenomicFiles")
10065 (synopsis "Distributed computing by file or by range")
10067 "This package provides infrastructure for parallel computations
10068 distributed by file or by range. User defined mapper and reducer functions
10069 provide added flexibility for data combination and manipulation.")
10070 (license license:artistic2.0)))
10072 (define-public r-complexheatmap
10074 (name "r-complexheatmap")
10079 (uri (bioconductor-uri "ComplexHeatmap" version))
10082 "0qjwz1hzpjnc90jiinjkikfnr0shi72q3zfdjjz7pxydy0mglq8n"))))
10084 `((upstream-name . "ComplexHeatmap")))
10085 (build-system r-build-system)
10087 `(("r-circlize" ,r-circlize)
10088 ("r-colorspace" ,r-colorspace)
10089 ("r-getoptlong" ,r-getoptlong)
10090 ("r-globaloptions" ,r-globaloptions)
10091 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10093 "https://github.com/jokergoo/ComplexHeatmap")
10094 (synopsis "Making Complex Heatmaps")
10096 "Complex heatmaps are efficient to visualize associations between
10097 different sources of data sets and reveal potential structures. This package
10098 provides a highly flexible way to arrange multiple heatmaps and supports
10099 self-defined annotation graphics.")
10100 (license license:gpl2+)))
10102 (define-public r-dirichletmultinomial
10104 (name "r-dirichletmultinomial")
10109 (uri (bioconductor-uri "DirichletMultinomial" version))
10112 "0vcyp81b90in4ls5nbadc66cw2g9aydr94aqifq5j4b7diq74yfs"))))
10114 `((upstream-name . "DirichletMultinomial")))
10115 (build-system r-build-system)
10119 `(("r-biocgenerics" ,r-biocgenerics)
10120 ("r-iranges" ,r-iranges)
10121 ("r-s4vectors" ,r-s4vectors)))
10122 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10123 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10125 "Dirichlet-multinomial mixture models can be used to describe variability
10126 in microbial metagenomic data. This package is an interface to code
10127 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10129 (license license:lgpl3)))
10131 (define-public r-ensembldb
10133 (name "r-ensembldb")
10138 (uri (bioconductor-uri "ensembldb" version))
10141 "1l2b4cxiycv05mz4z4f3dhx57r9ksha02psc114h30ldm5rxz8w6"))))
10142 (build-system r-build-system)
10144 `(("r-annotationdbi" ,r-annotationdbi)
10145 ("r-annotationfilter" ,r-annotationfilter)
10146 ("r-biobase" ,r-biobase)
10147 ("r-biocgenerics" ,r-biocgenerics)
10148 ("r-biostrings" ,r-biostrings)
10151 ("r-genomeinfodb" ,r-genomeinfodb)
10152 ("r-genomicfeatures" ,r-genomicfeatures)
10153 ("r-genomicranges" ,r-genomicranges)
10154 ("r-iranges" ,r-iranges)
10155 ("r-protgenerics" ,r-protgenerics)
10156 ("r-rsamtools" ,r-rsamtools)
10157 ("r-rsqlite" ,r-rsqlite)
10158 ("r-rtracklayer" ,r-rtracklayer)
10159 ("r-s4vectors" ,r-s4vectors)))
10160 (home-page "https://github.com/jotsetung/ensembldb")
10161 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10163 "The package provides functions to create and use transcript-centric
10164 annotation databases/packages. The annotation for the databases are directly
10165 fetched from Ensembl using their Perl API. The functionality and data is
10166 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10167 but, in addition to retrieve all gene/transcript models and annotations from
10168 the database, the @code{ensembldb} package also provides a filter framework
10169 allowing to retrieve annotations for specific entries like genes encoded on a
10170 chromosome region or transcript models of lincRNA genes.")
10171 ;; No version specified
10172 (license license:lgpl3+)))
10174 (define-public r-organismdbi
10176 (name "r-organismdbi")
10181 (uri (bioconductor-uri "OrganismDbi" version))
10184 "0hb9ni41bjfy5s5ryw2qmqs2sx3i7j47w1g0l8g1pvn7ppnxb6cv"))))
10185 (properties `((upstream-name . "OrganismDbi")))
10186 (build-system r-build-system)
10188 `(("r-annotationdbi" ,r-annotationdbi)
10189 ("r-biobase" ,r-biobase)
10190 ("r-biocgenerics" ,r-biocgenerics)
10191 ("r-biocinstaller" ,r-biocinstaller)
10193 ("r-genomicfeatures" ,r-genomicfeatures)
10194 ("r-genomicranges" ,r-genomicranges)
10195 ("r-graph" ,r-graph)
10196 ("r-iranges" ,r-iranges)
10198 ("r-s4vectors" ,r-s4vectors)))
10199 (home-page "https://bioconductor.org/packages/OrganismDbi")
10200 (synopsis "Software to enable the smooth interfacing of database packages")
10201 (description "The package enables a simple unified interface to several
10202 annotation packages each of which has its own schema by taking advantage of
10203 the fact that each of these packages implements a select methods.")
10204 (license license:artistic2.0)))
10206 (define-public r-biovizbase
10208 (name "r-biovizbase")
10213 (uri (bioconductor-uri "biovizBase" version))
10216 "0lkiqdr3ics6hgv47lwkykcy761823bbkhffbn4ykyfzyqwl4p67"))))
10217 (properties `((upstream-name . "biovizBase")))
10218 (build-system r-build-system)
10220 `(("r-annotationdbi" ,r-annotationdbi)
10221 ("r-annotationfilter" ,r-annotationfilter)
10222 ("r-biocgenerics" ,r-biocgenerics)
10223 ("r-biostrings" ,r-biostrings)
10224 ("r-dichromat" ,r-dichromat)
10225 ("r-ensembldb" ,r-ensembldb)
10226 ("r-genomeinfodb" ,r-genomeinfodb)
10227 ("r-genomicalignments" ,r-genomicalignments)
10228 ("r-genomicfeatures" ,r-genomicfeatures)
10229 ("r-genomicranges" ,r-genomicranges)
10230 ("r-hmisc" ,r-hmisc)
10231 ("r-iranges" ,r-iranges)
10232 ("r-rcolorbrewer" ,r-rcolorbrewer)
10233 ("r-rsamtools" ,r-rsamtools)
10234 ("r-s4vectors" ,r-s4vectors)
10235 ("r-scales" ,r-scales)
10236 ("r-summarizedexperiment" ,r-summarizedexperiment)
10237 ("r-variantannotation" ,r-variantannotation)))
10238 (home-page "https://bioconductor.org/packages/biovizBase")
10239 (synopsis "Basic graphic utilities for visualization of genomic data")
10241 "The biovizBase package is designed to provide a set of utilities, color
10242 schemes and conventions for genomic data. It serves as the base for various
10243 high-level packages for biological data visualization. This saves development
10244 effort and encourages consistency.")
10245 (license license:artistic2.0)))
10247 (define-public r-ggbio
10254 (uri (bioconductor-uri "ggbio" version))
10257 "0wszh3w8yia5zw758h837i1q35k99sn444y2hahcxqbdmmlbf7in"))))
10258 (build-system r-build-system)
10260 `(("r-annotationdbi" ,r-annotationdbi)
10261 ("r-annotationfilter" ,r-annotationfilter)
10262 ("r-biobase" ,r-biobase)
10263 ("r-biocgenerics" ,r-biocgenerics)
10264 ("r-biostrings" ,r-biostrings)
10265 ("r-biovizbase" ,r-biovizbase)
10266 ("r-bsgenome" ,r-bsgenome)
10267 ("r-ensembldb" ,r-ensembldb)
10268 ("r-genomeinfodb" ,r-genomeinfodb)
10269 ("r-genomicalignments" ,r-genomicalignments)
10270 ("r-genomicfeatures" ,r-genomicfeatures)
10271 ("r-genomicranges" ,r-genomicranges)
10272 ("r-ggally" ,r-ggally)
10273 ("r-ggplot2" ,r-ggplot2)
10274 ("r-gridextra" ,r-gridextra)
10275 ("r-gtable" ,r-gtable)
10276 ("r-hmisc" ,r-hmisc)
10277 ("r-iranges" ,r-iranges)
10278 ("r-organismdbi" ,r-organismdbi)
10279 ("r-reshape2" ,r-reshape2)
10280 ("r-rsamtools" ,r-rsamtools)
10281 ("r-rtracklayer" ,r-rtracklayer)
10282 ("r-s4vectors" ,r-s4vectors)
10283 ("r-scales" ,r-scales)
10284 ("r-summarizedexperiment" ,r-summarizedexperiment)
10285 ("r-variantannotation" ,r-variantannotation)))
10286 (home-page "http://www.tengfei.name/ggbio/")
10287 (synopsis "Visualization tools for genomic data")
10289 "The ggbio package extends and specializes the grammar of graphics for
10290 biological data. The graphics are designed to answer common scientific
10291 questions, in particular those often asked of high throughput genomics data.
10292 All core Bioconductor data structures are supported, where appropriate. The
10293 package supports detailed views of particular genomic regions, as well as
10294 genome-wide overviews. Supported overviews include ideograms and grand linear
10295 views. High-level plots include sequence fragment length, edge-linked
10296 interval to data view, mismatch pileup, and several splicing summaries.")
10297 (license license:artistic2.0)))
10299 (define-public r-gprofiler
10301 (name "r-gprofiler")
10306 (uri (cran-uri "gProfileR" version))
10309 "1n6cj12j102b4x9vhyl4dljp1i0r43p23cnhqbx4als2xfxdlqgi"))))
10310 (properties `((upstream-name . "gProfileR")))
10311 (build-system r-build-system)
10313 `(("r-plyr" ,r-plyr)
10314 ("r-rcurl" ,r-rcurl)))
10315 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10316 (synopsis "Interface to the g:Profiler toolkit")
10318 "This package provides tools for functional enrichment analysis,
10319 gene identifier conversion and mapping homologous genes across related
10320 organisms via the @code{g:Profiler} toolkit.")
10321 (license license:gpl2+)))
10323 (define-public r-gqtlbase
10325 (name "r-gqtlbase")
10330 (uri (bioconductor-uri "gQTLBase" version))
10333 "1m3ajpqjhw1nwwsn372r44xfxq0a9a0pzsnrprzdjp6mh52p9b5m"))))
10334 (properties `((upstream-name . "gQTLBase")))
10335 (build-system r-build-system)
10337 `(("r-batchjobs" ,r-batchjobs)
10338 ("r-bbmisc" ,r-bbmisc)
10339 ("r-biocgenerics" ,r-biocgenerics)
10341 ("r-doparallel" ,r-doparallel)
10343 ("r-ffbase" ,r-ffbase)
10344 ("r-foreach" ,r-foreach)
10345 ("r-genomicfiles" ,r-genomicfiles)
10346 ("r-genomicranges" ,r-genomicranges)
10347 ("r-rtracklayer" ,r-rtracklayer)
10348 ("r-s4vectors" ,r-s4vectors)
10349 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10350 (home-page "https://bioconductor.org/packages/gQTLBase")
10351 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10353 "The purpose of this package is to simplify the storage and interrogation
10354 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10356 (license license:artistic2.0)))
10358 (define-public r-snpstats
10360 (name "r-snpstats")
10365 (uri (bioconductor-uri "snpStats" version))
10368 "0iydgfnm053iw860qa1bbh4f6nwzlsf3vhgq92gvl2v4xsz1jbbs"))))
10369 (properties `((upstream-name . "snpStats")))
10370 (build-system r-build-system)
10371 (inputs `(("zlib" ,zlib)))
10373 `(("r-biocgenerics" ,r-biocgenerics)
10374 ("r-matrix" ,r-matrix)
10375 ("r-survival" ,r-survival)
10376 ("r-zlibbioc" ,r-zlibbioc)))
10377 (home-page "https://bioconductor.org/packages/snpStats")
10378 (synopsis "Methods for SNP association studies")
10380 "This package provides classes and statistical methods for large
10381 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10382 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10383 (license license:gpl3)))
10385 (define-public r-homo-sapiens
10387 (name "r-homo-sapiens")
10391 ;; We cannot use bioconductor-uri here because this tarball is
10392 ;; located under "data/annotation/" instead of "bioc/".
10393 (uri (string-append "http://www.bioconductor.org/packages/"
10394 "release/data/annotation/src/contrib/"
10396 version ".tar.gz"))
10399 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10401 `((upstream-name . "Homo.sapiens")))
10402 (build-system r-build-system)
10404 `(("r-genomicfeatures" ,r-genomicfeatures)
10405 ("r-go-db" ,r-go-db)
10406 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10407 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10408 ("r-organismdbi" ,r-organismdbi)
10409 ("r-annotationdbi" ,r-annotationdbi)))
10410 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10411 (synopsis "Annotation package for the Homo.sapiens object")
10413 "This package contains the Homo.sapiens object to access data from
10414 several related annotation packages.")
10415 (license license:artistic2.0)))
10417 (define-public r-erma
10424 (uri (bioconductor-uri "erma" version))
10427 "1ka68n18yizlyvb8bpwwcl4hqbsasg8hw8jb3vgy3cd4szji87hh"))))
10428 (build-system r-build-system)
10430 `(("r-annotationdbi" ,r-annotationdbi)
10431 ("r-biobase" ,r-biobase)
10432 ("r-biocgenerics" ,r-biocgenerics)
10433 ("r-biocparallel" ,r-biocparallel)
10434 ("r-genomeinfodb" ,r-genomeinfodb)
10435 ("r-genomicfiles" ,r-genomicfiles)
10436 ("r-genomicranges" ,r-genomicranges)
10437 ("r-ggplot2" ,r-ggplot2)
10438 ("r-homo-sapiens" ,r-homo-sapiens)
10439 ("r-iranges" ,r-iranges)
10440 ("r-rtracklayer" ,r-rtracklayer)
10441 ("r-s4vectors" ,r-s4vectors)
10442 ("r-shiny" ,r-shiny)
10443 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10444 (home-page "https://bioconductor.org/packages/erma")
10445 (synopsis "Epigenomic road map adventures")
10447 "The epigenomics road map describes locations of epigenetic marks in DNA
10448 from a variety of cell types. Of interest are locations of histone
10449 modifications, sites of DNA methylation, and regions of accessible chromatin.
10450 This package presents a selection of elements of the road map including
10451 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10452 by Ernst and Kellis.")
10453 (license license:artistic2.0)))
10455 (define-public r-ldblock
10462 (uri (bioconductor-uri "ldblock" version))
10465 "0c24zvnwsp39d3q0bps13sc441jj9ms2zi34xsb8c392lqmbypvd"))))
10466 (build-system r-build-system)
10468 `(("r-biocgenerics" ,r-biocgenerics)
10470 ("r-genomeinfodb" ,r-genomeinfodb)
10471 ("r-genomicfiles" ,r-genomicfiles)
10472 ("r-go-db" ,r-go-db)
10473 ("r-homo-sapiens" ,r-homo-sapiens)
10474 ("r-matrix" ,r-matrix)
10475 ("r-rsamtools" ,r-rsamtools)
10476 ("r-snpstats" ,r-snpstats)
10477 ("r-variantannotation" ,r-variantannotation)))
10478 (home-page "https://bioconductor.org/packages/ldblock")
10479 (synopsis "Data structures for linkage disequilibrium measures in populations")
10481 "This package defines data structures for @dfn{linkage
10482 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10483 handling of existing population-level data for the purpose of flexibly
10484 defining LD blocks.")
10485 (license license:artistic2.0)))
10487 (define-public r-gqtlstats
10489 (name "r-gqtlstats")
10494 (uri (bioconductor-uri "gQTLstats" version))
10497 "19g8qhfgngdc14cw9k4i44cxhs3qva87x56gjzmn25k1yj8qgsp1"))))
10498 (properties `((upstream-name . "gQTLstats")))
10499 (build-system r-build-system)
10501 `(("r-annotationdbi" ,r-annotationdbi)
10502 ("r-batchjobs" ,r-batchjobs)
10503 ("r-bbmisc" ,r-bbmisc)
10504 ("r-beeswarm" ,r-beeswarm)
10505 ("r-biobase" ,r-biobase)
10506 ("r-biocgenerics" ,r-biocgenerics)
10507 ("r-doparallel" ,r-doparallel)
10508 ("r-dplyr" ,r-dplyr)
10510 ("r-ffbase" ,r-ffbase)
10511 ("r-foreach" ,r-foreach)
10512 ("r-genomeinfodb" ,r-genomeinfodb)
10513 ("r-genomicfeatures" ,r-genomicfeatures)
10514 ("r-genomicfiles" ,r-genomicfiles)
10515 ("r-genomicranges" ,r-genomicranges)
10516 ("r-ggbeeswarm" ,r-ggbeeswarm)
10517 ("r-ggplot2" ,r-ggplot2)
10518 ("r-gqtlbase" ,r-gqtlbase)
10519 ("r-hardyweinberg" ,r-hardyweinberg)
10520 ("r-homo-sapiens" ,r-homo-sapiens)
10521 ("r-iranges" ,r-iranges)
10522 ("r-limma" ,r-limma)
10524 ("r-plotly" ,r-plotly)
10525 ("r-reshape2" ,r-reshape2)
10526 ("r-s4vectors" ,r-s4vectors)
10527 ("r-shiny" ,r-shiny)
10528 ("r-snpstats" ,r-snpstats)
10529 ("r-summarizedexperiment" ,r-summarizedexperiment)
10530 ("r-variantannotation" ,r-variantannotation)))
10531 (home-page "https://bioconductor.org/packages/gQTLstats")
10532 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10534 "This package provides tools for the computationally efficient analysis
10535 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10536 The software in this package aims to support refinements and functional
10537 interpretation of members of a collection of association statistics on a
10538 family of feature/genome hypotheses.")
10539 (license license:artistic2.0)))
10541 (define-public r-gviz
10548 (uri (bioconductor-uri "Gviz" version))
10551 "1fhli7ahkl5r43j0hc89ib41mfadj6qyrg36i03ncz8zs6iqwpx4"))))
10552 (properties `((upstream-name . "Gviz")))
10553 (build-system r-build-system)
10555 `(("r-annotationdbi" ,r-annotationdbi)
10556 ("r-biobase" ,r-biobase)
10557 ("r-biocgenerics" ,r-biocgenerics)
10558 ("r-biomart" ,r-biomart)
10559 ("r-biostrings" ,r-biostrings)
10560 ("r-biovizbase" ,r-biovizbase)
10561 ("r-bsgenome" ,r-bsgenome)
10562 ("r-digest" ,r-digest)
10563 ("r-genomeinfodb" ,r-genomeinfodb)
10564 ("r-genomicalignments" ,r-genomicalignments)
10565 ("r-genomicfeatures" ,r-genomicfeatures)
10566 ("r-genomicranges" ,r-genomicranges)
10567 ("r-iranges" ,r-iranges)
10568 ("r-lattice" ,r-lattice)
10569 ("r-latticeextra" ,r-latticeextra)
10570 ("r-matrixstats" ,r-matrixstats)
10571 ("r-rcolorbrewer" ,r-rcolorbrewer)
10572 ("r-rsamtools" ,r-rsamtools)
10573 ("r-rtracklayer" ,r-rtracklayer)
10574 ("r-s4vectors" ,r-s4vectors)
10575 ("r-xvector" ,r-xvector)))
10576 (home-page "https://bioconductor.org/packages/Gviz")
10577 (synopsis "Plotting data and annotation information along genomic coordinates")
10579 "Genomic data analyses requires integrated visualization of known genomic
10580 information and new experimental data. Gviz uses the biomaRt and the
10581 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10582 and translates this to e.g. gene/transcript structures in viewports of the
10583 grid graphics package. This results in genomic information plotted together
10585 (license license:artistic2.0)))
10587 (define-public r-gwascat
10594 (uri (bioconductor-uri "gwascat" version))
10597 "08ba9il4vbjjwlbwmqg4ai6ya1p09js9agn95sw0dhc9gqln42hx"))))
10598 (build-system r-build-system)
10600 `(("r-annotationdbi" ,r-annotationdbi)
10601 ("r-annotationhub" ,r-annotationhub)
10602 ("r-biocgenerics" ,r-biocgenerics)
10603 ("r-biostrings" ,r-biostrings)
10604 ("r-genomeinfodb" ,r-genomeinfodb)
10605 ("r-genomicfeatures" ,r-genomicfeatures)
10606 ("r-genomicranges" ,r-genomicranges)
10607 ("r-ggbio" ,r-ggbio)
10608 ("r-ggplot2" ,r-ggplot2)
10609 ("r-gqtlstats" ,r-gqtlstats)
10610 ("r-graph" ,r-graph)
10612 ("r-homo-sapiens" ,r-homo-sapiens)
10613 ("r-iranges" ,r-iranges)
10614 ("r-rsamtools" ,r-rsamtools)
10615 ("r-rtracklayer" ,r-rtracklayer)
10616 ("r-s4vectors" ,r-s4vectors)
10617 ("r-snpstats" ,r-snpstats)
10618 ("r-summarizedexperiment" ,r-summarizedexperiment)
10619 ("r-variantannotation" ,r-variantannotation)))
10620 (home-page "https://bioconductor.org/packages/gwascat")
10621 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10623 "This package provides tools for representing and modeling data in the
10624 EMBL-EBI GWAS catalog.")
10625 (license license:artistic2.0)))
10627 (define-public r-sushi
10633 (uri (bioconductor-uri "Sushi" version))
10636 "1m15hmg4k0qhshyn65xfj5hx7xbaf0kxqw70lxisak6pj1w00l41"))))
10637 (properties `((upstream-name . "Sushi")))
10638 (build-system r-build-system)
10640 `(("r-biomart" ,r-biomart)
10642 (home-page "https://bioconductor.org/packages/Sushi")
10643 (synopsis "Tools for visualizing genomics data")
10645 "This package provides flexible, quantitative, and integrative genomic
10646 visualizations for publication-quality multi-panel figures.")
10647 (license license:gpl2+)))
10649 (define-public r-fithic
10655 (uri (bioconductor-uri "FitHiC" version))
10658 "06w4q836bi1mvkbl1saghv4r5p4hxpjg8cp7kgad13ls450kqmyd"))))
10659 (properties `((upstream-name . "FitHiC")))
10660 (build-system r-build-system)
10662 `(("r-data-table" ,r-data-table)
10663 ("r-fdrtool" ,r-fdrtool)
10664 ("r-rcpp" ,r-rcpp)))
10665 (home-page "https://bioconductor.org/packages/FitHiC")
10666 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10668 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10669 intra-chromosomal contact maps produced by genome-wide genome architecture
10670 assays such as Hi-C.")
10671 (license license:gpl2+)))
10673 (define-public r-hitc
10679 (uri (bioconductor-uri "HiTC" version))
10682 "0qkk5139f51lwwy1yh7nbkflh5d69prirmhniwam34nlg9rzjm2z"))))
10683 (properties `((upstream-name . "HiTC")))
10684 (build-system r-build-system)
10686 `(("r-biostrings" ,r-biostrings)
10687 ("r-genomeinfodb" ,r-genomeinfodb)
10688 ("r-genomicranges" ,r-genomicranges)
10689 ("r-iranges" ,r-iranges)
10690 ("r-matrix" ,r-matrix)
10691 ("r-rcolorbrewer" ,r-rcolorbrewer)
10692 ("r-rtracklayer" ,r-rtracklayer)))
10693 (home-page "https://bioconductor.org/packages/HiTC")
10694 (synopsis "High throughput chromosome conformation capture analysis")
10696 "The HiTC package was developed to explore high-throughput \"C\" data
10697 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10698 quality controls, normalization, visualization, and further analysis are also
10700 (license license:artistic2.0)))
10702 (define-public r-qvalue
10709 (uri (bioconductor-uri "qvalue" version))
10712 "1ndwkj0hh7v4lwylq1v0fkxqs7mfmbcj8kxbdpj1wkvf131z2ns8"))))
10713 (build-system r-build-system)
10715 `(("r-ggplot2" ,r-ggplot2)
10716 ("r-reshape2" ,r-reshape2)))
10717 (home-page "http://github.com/jdstorey/qvalue")
10718 (synopsis "Q-value estimation for false discovery rate control")
10720 "This package takes a list of p-values resulting from the simultaneous
10721 testing of many hypotheses and estimates their q-values and local @dfn{false
10722 discovery rate} (FDR) values. The q-value of a test measures the proportion
10723 of false positives incurred when that particular test is called significant.
10724 The local FDR measures the posterior probability the null hypothesis is true
10725 given the test's p-value. Various plots are automatically generated, allowing
10726 one to make sensible significance cut-offs. The software can be applied to
10727 problems in genomics, brain imaging, astrophysics, and data mining.")
10728 ;; Any version of the LGPL.
10729 (license license:lgpl3+)))
10731 (define-public r-hdf5array
10733 (name "r-hdf5array")
10738 (uri (bioconductor-uri "HDF5Array" version))
10741 "1l0276qxkhgdxsfck3jmi8jvnsr20g10gjki53g0mqa45wnhm3ck"))))
10742 (properties `((upstream-name . "HDF5Array")))
10743 (build-system r-build-system)
10745 `(("r-biocgenerics" ,r-biocgenerics)
10746 ("r-delayedarray" ,r-delayedarray)
10747 ("r-iranges" ,r-iranges)
10748 ("r-rhdf5" ,r-rhdf5)
10749 ("r-s4vectors" ,r-s4vectors)))
10750 (home-page "https://bioconductor.org/packages/HDF5Array")
10751 (synopsis "HDF5 back end for DelayedArray objects")
10752 (description "This package provides an array-like container for convenient
10753 access and manipulation of HDF5 datasets. It supports delayed operations and
10754 block processing.")
10755 (license license:artistic2.0)))
10757 (define-public r-rhdf5lib
10759 (name "r-rhdf5lib")
10764 (uri (bioconductor-uri "Rhdf5lib" version))
10767 "1y59acac6v8hrhv84gghn9ifsni9xxxacaj177rrl4frmkrz4x3c"))))
10768 (properties `((upstream-name . "Rhdf5lib")))
10769 (build-system r-build-system)
10772 (modify-phases %standard-phases
10773 (add-after 'unpack 'do-not-use-bundled-hdf5
10774 (lambda* (#:key inputs #:allow-other-keys)
10775 (for-each delete-file '("configure" "configure.ac"))
10776 ;; Do not make other packages link with the proprietary libsz.
10777 (substitute* "R/zzz.R"
10778 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10779 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10780 (("'%s/libhdf5.a %s/libsz.a -lz'")
10781 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10782 (with-directory-excursion "src"
10783 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10784 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10786 ;; Remove timestamp and host system information to make
10787 ;; the build reproducible.
10788 (substitute* "hdf5/src/libhdf5.settings.in"
10789 (("Configured on: @CONFIG_DATE@")
10790 "Configured on: Guix")
10791 (("Uname information:.*")
10792 "Uname information: Linux\n")
10793 ;; Remove unnecessary store reference.
10795 "C Compiler: GCC\n"))
10796 (rename-file "Makevars.in" "Makevars")
10797 (substitute* "Makevars"
10798 (("HDF5_CXX_LIB=.*")
10799 (string-append "HDF5_CXX_LIB="
10800 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10802 (string-append "HDF5_LIB="
10803 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10804 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10805 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10806 ;; szip is non-free software
10807 (("cp \\$\\{SZIP_LIB\\}.*") "")
10808 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10815 `(("hdf5-source" ,(package-source hdf5))))
10816 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10817 (synopsis "HDF5 library as an R package")
10818 (description "This package provides C and C++ HDF5 libraries for use in R
10820 (license license:artistic2.0)))
10822 (define-public r-beachmat
10824 (name "r-beachmat")
10829 (uri (bioconductor-uri "beachmat" version))
10832 "1w90v0jx1zgrfxzx99gdkk0dz2vi25hr51jml1bvq33i64rj7996"))))
10833 (build-system r-build-system)
10838 `(("r-delayedarray" ,r-delayedarray)
10839 ("r-hdf5array" ,r-hdf5array)
10841 ("r-rhdf5" ,r-rhdf5)
10842 ("r-rhdf5lib" ,r-rhdf5lib)))
10843 (home-page "https://bioconductor.org/packages/beachmat")
10844 (synopsis "Compiling Bioconductor to handle each matrix type")
10845 (description "This package provides a consistent C++ class interface for a
10846 variety of commonly used matrix types, including sparse and HDF5-backed
10848 (license license:gpl3)))
10850 (define-public r-singlecellexperiment
10852 (name "r-singlecellexperiment")
10857 (uri (bioconductor-uri "SingleCellExperiment" version))
10860 "0mz3chia250v8v6q8r5cqv5fc4bpcw1hhrfr3p7l5i4xi85scpka"))))
10862 `((upstream-name . "SingleCellExperiment")))
10863 (build-system r-build-system)
10865 `(("r-biocgenerics" ,r-biocgenerics)
10866 ("r-s4vectors" ,r-s4vectors)
10867 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10868 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10869 (synopsis "S4 classes for single cell data")
10870 (description "This package defines an S4 class for storing data from
10871 single-cell experiments. This includes specialized methods to store and
10872 retrieve spike-in information, dimensionality reduction coordinates and size
10873 factors for each cell, along with the usual metadata for genes and
10875 (license license:gpl3)))
10877 (define-public r-scater
10883 (uri (bioconductor-uri "scater" version))
10886 "0bhpikgz3b9f510dawsay4zry9rlp8vjx5n6zvwbcpwrd94p3903"))))
10887 (build-system r-build-system)
10889 `(("r-beachmat" ,r-beachmat)
10890 ("r-biobase" ,r-biobase)
10891 ("r-biocgenerics" ,r-biocgenerics)
10892 ("r-data-table" ,r-data-table)
10893 ("r-delayedarray" ,r-delayedarray)
10894 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10895 ("r-dplyr" ,r-dplyr)
10896 ("r-edger" ,r-edger)
10897 ("r-ggbeeswarm" ,r-ggbeeswarm)
10898 ("r-ggplot2" ,r-ggplot2)
10899 ("r-limma" ,r-limma)
10900 ("r-matrix" ,r-matrix)
10903 ("r-reshape2" ,r-reshape2)
10904 ("r-rhdf5" ,r-rhdf5)
10905 ("r-rhdf5lib" ,r-rhdf5lib)
10906 ("r-rjson" ,r-rjson)
10907 ("r-s4vectors" ,r-s4vectors)
10908 ("r-shiny" ,r-shiny)
10909 ("r-shinydashboard" ,r-shinydashboard)
10910 ("r-singlecellexperiment" ,r-singlecellexperiment)
10911 ("r-summarizedexperiment" ,r-summarizedexperiment)
10912 ("r-tximport" ,r-tximport)
10913 ("r-viridis" ,r-viridis)))
10914 (home-page "https://github.com/davismcc/scater")
10915 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10916 (description "This package provides a collection of tools for doing
10917 various analyses of single-cell RNA-seq gene expression data, with a focus on
10919 (license license:gpl2+)))
10921 (define-public r-scran
10928 (uri (bioconductor-uri "scran" version))
10931 "0nbn5x75gf9d0p18w7vpkbv30cpdqvp5bz8xvila0h7jla7xdyih"))))
10932 (build-system r-build-system)
10934 `(("r-beachmat" ,r-beachmat)
10935 ("r-biocgenerics" ,r-biocgenerics)
10936 ("r-biocparallel" ,r-biocparallel)
10937 ("r-delayedarray" ,r-delayedarray)
10938 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10940 ("r-dynamictreecut" ,r-dynamictreecut)
10941 ("r-edger" ,r-edger)
10943 ("r-ggplot2" ,r-ggplot2)
10944 ("r-igraph" ,r-igraph)
10945 ("r-limma" ,r-limma)
10946 ("r-matrix" ,r-matrix)
10948 ("r-rhdf5lib" ,r-rhdf5lib)
10949 ("r-s4vectors" ,r-s4vectors)
10950 ("r-scater" ,r-scater)
10951 ("r-shiny" ,r-shiny)
10952 ("r-singlecellexperiment" ,r-singlecellexperiment)
10953 ("r-statmod" ,r-statmod)
10954 ("r-summarizedexperiment" ,r-summarizedexperiment)
10955 ("r-viridis" ,r-viridis)))
10956 (home-page "https://bioconductor.org/packages/scran")
10957 (synopsis "Methods for single-cell RNA-Seq data analysis")
10958 (description "This package implements a variety of low-level analyses of
10959 single-cell RNA-seq data. Methods are provided for normalization of
10960 cell-specific biases, assignment of cell cycle phase, and detection of highly
10961 variable and significantly correlated genes.")
10962 (license license:gpl3)))
10964 (define-public r-delayedmatrixstats
10966 (name "r-delayedmatrixstats")
10971 (uri (bioconductor-uri "DelayedMatrixStats" version))
10974 "1dasghfy8x27zzmd0igag4mc1gxxxbchsl4hpc1050dj3wnw9w3y"))))
10976 `((upstream-name . "DelayedMatrixStats")))
10977 (build-system r-build-system)
10979 `(("r-delayedarray" ,r-delayedarray)
10980 ("r-iranges" ,r-iranges)
10981 ("r-matrix" ,r-matrix)
10982 ("r-matrixstats" ,r-matrixstats)
10983 ("r-s4vectors" ,r-s4vectors)))
10984 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10985 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10987 "This package provides a port of the @code{matrixStats} API for use with
10988 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10989 contains high-performing functions operating on rows and columns of
10990 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10991 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10992 are optimized per data type and for subsetted calculations such that both
10993 memory usage and processing time is minimized.")
10994 (license license:expat)))
10996 (define-public r-phangorn
10998 (name "r-phangorn")
11003 (uri (cran-uri "phangorn" version))
11006 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11007 (build-system r-build-system)
11010 ("r-fastmatch" ,r-fastmatch)
11011 ("r-igraph" ,r-igraph)
11012 ("r-magrittr" ,r-magrittr)
11013 ("r-matrix" ,r-matrix)
11014 ("r-quadprog" ,r-quadprog)
11015 ("r-rcpp" ,r-rcpp)))
11016 (home-page "https://github.com/KlausVigo/phangorn")
11017 (synopsis "Phylogenetic analysis in R")
11019 "Phangorn is a package for phylogenetic analysis in R. It supports
11020 estimation of phylogenetic trees and networks using Maximum Likelihood,
11021 Maximum Parsimony, distance methods and Hadamard conjugation.")
11022 (license license:gpl2+)))
11024 (define-public r-dropbead
11025 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11028 (name "r-dropbead")
11029 (version (string-append "0-" revision "." (string-take commit 7)))
11033 (uri (git-reference
11034 (url "https://github.com/rajewsky-lab/dropbead.git")
11036 (file-name (git-file-name name version))
11039 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11040 (build-system r-build-system)
11042 `(("r-ggplot2" ,r-ggplot2)
11043 ("r-rcolorbrewer" ,r-rcolorbrewer)
11044 ("r-gridextra" ,r-gridextra)
11045 ("r-gplots" ,r-gplots)
11046 ("r-plyr" ,r-plyr)))
11047 (home-page "https://github.com/rajewsky-lab/dropbead")
11048 (synopsis "Basic exploration and analysis of Drop-seq data")
11049 (description "This package offers a quick and straight-forward way to
11050 explore and perform basic analysis of single cell sequencing data coming from
11051 droplet sequencing. It has been particularly tailored for Drop-seq.")
11052 (license license:gpl3))))
11054 (define htslib-for-sambamba
11055 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11058 (name "htslib-for-sambamba")
11059 (version (string-append "1.3.1-1." (string-take commit 9)))
11063 (uri (git-reference
11064 (url "https://github.com/lomereiter/htslib.git")
11066 (file-name (string-append "htslib-" version "-checkout"))
11069 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11071 `(("autoconf" ,autoconf)
11072 ("automake" ,automake)
11073 ,@(package-native-inputs htslib))))))
11075 (define-public sambamba
11078 (version "0.6.7-10-g223fa20")
11082 (uri (git-reference
11083 (url "https://github.com/lomereiter/sambamba.git")
11084 (commit (string-append "v" version))))
11085 (file-name (string-append name "-" version "-checkout"))
11088 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11089 (build-system gnu-build-system)
11091 `(#:tests? #f ; there is no test target
11092 #:parallel-build? #f ; not supported
11094 (modify-phases %standard-phases
11095 (delete 'configure)
11096 (add-after 'unpack 'fix-ldc-version
11098 (substitute* "gen_ldc_version_info.py"
11099 (("/usr/bin/env.*") (which "python")))
11100 (substitute* "Makefile"
11101 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11103 (add-after 'unpack 'place-biod-and-undead
11104 (lambda* (#:key inputs #:allow-other-keys)
11105 (copy-recursively (assoc-ref inputs "biod") "BioD")
11106 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11108 (add-after 'unpack 'unbundle-prerequisites
11110 (substitute* "Makefile"
11111 (("htslib/libhts.a lz4/lib/liblz4.a")
11113 ((" htslib-static lz4-static") ""))
11116 (lambda* (#:key outputs #:allow-other-keys)
11117 (let* ((out (assoc-ref outputs "out"))
11118 (bin (string-append out "/bin")))
11120 (install-file "build/sambamba" bin)
11125 ("python" ,python2-minimal)
11127 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11130 (uri (git-reference
11131 (url "https://github.com/biod/BioD.git")
11133 (file-name (string-append "biod-"
11134 (string-take commit 9)
11138 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11140 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11143 (uri (git-reference
11144 (url "https://github.com/dlang/undeaD.git")
11146 (file-name (string-append "undead-"
11147 (string-take commit 9)
11151 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11154 ("htslib" ,htslib-for-sambamba)))
11155 (home-page "http://lomereiter.github.io/sambamba")
11156 (synopsis "Tools for working with SAM/BAM data")
11157 (description "Sambamba is a high performance modern robust and
11158 fast tool (and library), written in the D programming language, for
11159 working with SAM and BAM files. Current parallelised functionality is
11160 an important subset of samtools functionality, including view, index,
11161 sort, markdup, and depth.")
11162 (license license:gpl2+)))
11164 (define-public ritornello
11166 (name "ritornello")
11170 (uri (string-append "https://github.com/KlugerLab/"
11171 "Ritornello/archive/v"
11172 version ".tar.gz"))
11173 (file-name (string-append name "-" version ".tar.gz"))
11176 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11177 (build-system gnu-build-system)
11179 `(#:tests? #f ; there are no tests
11181 (modify-phases %standard-phases
11182 (add-after 'unpack 'patch-samtools-references
11183 (lambda* (#:key inputs #:allow-other-keys)
11184 (substitute* '("src/SamStream.h"
11185 "src/BufferedGenomeReader.h")
11186 (("<sam.h>") "<samtools/sam.h>"))
11188 (delete 'configure)
11190 (lambda* (#:key inputs outputs #:allow-other-keys)
11191 (let* ((out (assoc-ref outputs "out"))
11192 (bin (string-append out "/bin/")))
11194 (install-file "bin/Ritornello" bin)
11197 `(("samtools" ,samtools-0.1)
11201 (home-page "https://github.com/KlugerLab/Ritornello")
11202 (synopsis "Control-free peak caller for ChIP-seq data")
11203 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11204 signal processing that can accurately call binding events without the need to
11205 do a pair total DNA input or IgG control sample. It has been tested for use
11206 with narrow binding events such as transcription factor ChIP-seq.")
11207 (license license:gpl3+)))
11209 (define-public trim-galore
11211 (name "trim-galore")
11216 (uri (git-reference
11217 (url "https://github.com/FelixKrueger/TrimGalore.git")
11219 (file-name (string-append name "-" version "-checkout"))
11222 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11223 (build-system gnu-build-system)
11225 `(#:tests? #f ; no tests
11227 (modify-phases %standard-phases
11228 (delete 'configure)
11230 (add-after 'unpack 'hardcode-tool-references
11231 (lambda* (#:key inputs #:allow-other-keys)
11232 (substitute* "trim_galore"
11233 (("\\$path_to_cutadapt = 'cutadapt'")
11234 (string-append "$path_to_cutadapt = '"
11235 (assoc-ref inputs "cutadapt")
11238 (string-append "| "
11239 (assoc-ref inputs "gzip")
11242 (string-append "\""
11243 (assoc-ref inputs "gzip")
11247 (lambda* (#:key outputs #:allow-other-keys)
11248 (let ((bin (string-append (assoc-ref outputs "out")
11251 (install-file "trim_galore" bin)
11256 ("cutadapt" ,cutadapt)))
11258 `(("unzip" ,unzip)))
11259 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11260 (synopsis "Wrapper around Cutadapt and FastQC")
11261 (description "Trim Galore! is a wrapper script to automate quality and
11262 adapter trimming as well as quality control, with some added functionality to
11263 remove biased methylation positions for RRBS sequence files.")
11264 (license license:gpl3+)))
11266 (define-public gess
11272 (uri (string-append "http://compbio.uthscsa.edu/"
11274 "gess-" version ".src.tar.gz"))
11277 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11278 (build-system gnu-build-system)
11280 `(#:tests? #f ; no tests
11282 (modify-phases %standard-phases
11283 (delete 'configure)
11286 (lambda* (#:key inputs outputs #:allow-other-keys)
11287 (let* ((python (assoc-ref inputs "python"))
11288 (out (assoc-ref outputs "out"))
11289 (bin (string-append out "/bin/"))
11290 (target (string-append
11291 out "/lib/python2.7/site-packages/gess/")))
11293 (copy-recursively "." target)
11294 ;; Make GESS.py executable
11295 (chmod (string-append target "GESS.py") #o555)
11296 ;; Add Python shebang to the top and make Matplotlib
11298 (substitute* (string-append target "GESS.py")
11299 (("\"\"\"Description:" line)
11300 (string-append "#!" (which "python") "
11302 matplotlib.use('Agg')
11304 ;; Make sure GESS has all modules in its path
11305 (wrap-program (string-append target "GESS.py")
11306 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11308 (symlink (string-append target "GESS.py")
11309 (string-append bin "GESS.py"))
11312 `(("python" ,python-2)
11313 ("python2-pysam" ,python2-pysam)
11314 ("python2-scipy" ,python2-scipy)
11315 ("python2-numpy" ,python2-numpy)
11316 ("python2-networkx" ,python2-networkx)
11317 ("python2-biopython" ,python2-biopython)))
11318 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11319 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11321 "GESS is an implementation of a novel computational method to detect de
11322 novo exon-skipping events directly from raw RNA-seq data without the prior
11323 knowledge of gene annotation information. GESS stands for the graph-based
11324 exon-skipping scanner detection scheme.")
11325 (license license:bsd-3)))
11327 (define-public phylip
11334 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11335 "download/phylip-" version ".tar.gz"))
11338 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11339 (build-system gnu-build-system)
11341 `(#:tests? #f ; no check target
11342 #:make-flags (list "-f" "Makefile.unx" "install")
11343 #:parallel-build? #f ; not supported
11345 (modify-phases %standard-phases
11346 (add-after 'unpack 'enter-dir
11347 (lambda _ (chdir "src") #t))
11348 (delete 'configure)
11350 (lambda* (#:key inputs outputs #:allow-other-keys)
11351 (let ((target (string-append (assoc-ref outputs "out")
11354 (for-each (lambda (file)
11355 (install-file file target))
11356 (find-files "../exe" ".*")))
11358 (home-page "http://evolution.genetics.washington.edu/phylip/")
11359 (synopsis "Tools for inferring phylogenies")
11360 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11361 programs for inferring phylogenies (evolutionary trees).")
11362 (license license:bsd-2)))
11371 (uri (string-append "https://integrativemodeling.org/"
11372 version "/download/imp-" version ".tar.gz"))
11375 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11376 (build-system cmake-build-system)
11378 `(;; FIXME: Some tests fail because they produce warnings, others fail
11379 ;; because the PYTHONPATH does not include the modeller's directory.
11387 ("python" ,python-2)))
11389 `(("python2-numpy" ,python2-numpy)
11390 ("python2-scipy" ,python2-scipy)
11391 ("python2-pandas" ,python2-pandas)
11392 ("python2-scikit-learn" ,python2-scikit-learn)
11393 ("python2-networkx" ,python2-networkx)))
11394 (home-page "https://integrativemodeling.org")
11395 (synopsis "Integrative modeling platform")
11396 (description "IMP's broad goal is to contribute to a comprehensive
11397 structural characterization of biomolecules ranging in size and complexity
11398 from small peptides to large macromolecular assemblies, by integrating data
11399 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11400 Python toolbox for solving complex modeling problems, and a number of
11401 applications for tackling some common problems in a user-friendly way.")
11402 ;; IMP is largely available under the GNU Lesser GPL; see the file
11403 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11404 ;; available under the GNU GPL (see the file COPYING.GPL).
11405 (license (list license:lgpl2.1+
11408 (define-public tadbit
11414 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11415 "archive/v" version ".tar.gz"))
11416 (file-name (string-append name "-" version ".tar.gz"))
11419 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11420 (build-system python-build-system)
11422 `(;; Tests are included and must be run after installation, but
11423 ;; they are incomplete and thus cannot be run.
11427 (modify-phases %standard-phases
11428 (add-after 'unpack 'fix-problems-with-setup.py
11429 (lambda* (#:key outputs #:allow-other-keys)
11430 ;; setup.py opens these files for writing
11431 (chmod "_pytadbit/_version.py" #o664)
11432 (chmod "README.rst" #o664)
11434 ;; Don't attempt to install the bash completions to
11435 ;; the home directory.
11436 (rename-file "extras/.bash_completion"
11438 (substitute* "setup.py"
11439 (("\\(path.expanduser\\('~'\\)")
11440 (string-append "(\""
11441 (assoc-ref outputs "out")
11442 "/etc/bash_completion.d\""))
11443 (("extras/\\.bash_completion")
11447 ;; TODO: add Chimera for visualization
11450 ("python2-scipy" ,python2-scipy)
11451 ("python2-numpy" ,python2-numpy)
11452 ("python2-matplotlib" ,python2-matplotlib)
11453 ("python2-pysam" ,python2-pysam)))
11454 (home-page "https://3dgenomes.github.io/TADbit/")
11455 (synopsis "Analyze, model, and explore 3C-based data")
11457 "TADbit is a complete Python library to deal with all steps to analyze,
11458 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11459 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11460 correct interaction matrices, identify and compare the so-called
11461 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11462 interaction matrices, and finally, extract structural properties from the
11463 models. TADbit is complemented by TADkit for visualizing 3D models.")
11464 (license license:gpl3+)))
11466 (define-public kentutils
11469 ;; 302.1.0 is out, but the only difference is the inclusion of
11470 ;; pre-built binaries.
11471 (version "302.0.0")
11475 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11476 "archive/v" version ".tar.gz"))
11477 (file-name (string-append name "-" version ".tar.gz"))
11480 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11481 (modules '((guix build utils)
11486 ;; Only the contents of the specified directories are free
11487 ;; for all uses, so we remove the rest. "hg/autoSql" and
11488 ;; "hg/autoXml" are nominally free, but they depend on a
11489 ;; library that is built from the sources in "hg/lib",
11490 ;; which is nonfree.
11491 (let ((free (list "." ".."
11492 "utils" "lib" "inc" "tagStorm"
11493 "parasol" "htslib"))
11494 (directory? (lambda (file)
11495 (eq? 'directory (stat:type (stat file))))))
11496 (for-each (lambda (file)
11497 (and (directory? file)
11498 (delete-file-recursively file)))
11499 (map (cut string-append "src/" <>)
11502 (not (member file free)))))))
11503 ;; Only make the utils target, not the userApps target,
11504 ;; because that requires libraries we won't build.
11505 (substitute* "Makefile"
11506 ((" userApps") " utils"))
11507 ;; Only build libraries that are free.
11508 (substitute* "src/makefile"
11509 (("DIRS =.*") "DIRS =\n")
11510 (("cd jkOwnLib.*") "")
11513 (substitute* "src/utils/makefile"
11514 ;; These tools depend on "jkhgap.a", which is part of the
11515 ;; nonfree "src/hg/lib" directory.
11516 (("raSqlQuery") "")
11517 (("pslLiftSubrangeBlat") "")
11519 ;; Do not build UCSC tools, which may require nonfree
11521 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11523 (build-system gnu-build-system)
11525 `( ;; There is no global test target and the test target for
11526 ;; individual tools depends on input files that are not
11530 (modify-phases %standard-phases
11531 (add-after 'unpack 'fix-paths
11533 (substitute* "Makefile"
11534 (("/bin/echo") (which "echo")))
11536 (add-after 'unpack 'prepare-samtabix
11537 (lambda* (#:key inputs #:allow-other-keys)
11538 (copy-recursively (assoc-ref inputs "samtabix")
11541 (delete 'configure)
11543 (lambda* (#:key outputs #:allow-other-keys)
11544 (let ((bin (string-append (assoc-ref outputs "out")
11546 (copy-recursively "bin" bin))
11552 (uri (git-reference
11553 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11554 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11557 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11563 ("mariadb" ,mariadb)
11564 ("openssl" ,openssl)))
11565 (home-page "http://genome.cse.ucsc.edu/index.html")
11566 (synopsis "Assorted bioinformatics utilities")
11567 (description "This package provides the kentUtils, a selection of
11568 bioinformatics utilities used in combination with the UCSC genome
11570 ;; Only a subset of the sources are released under a non-copyleft
11571 ;; free software license. All other sources are removed in a
11572 ;; snippet. See this bug report for an explanation of how the
11573 ;; license statements apply:
11574 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11575 (license (license:non-copyleft
11576 "http://genome.ucsc.edu/license/"
11577 "The contents of this package are free for all uses."))))
11579 (define-public f-seq
11580 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11584 (version (string-append "1.1-" revision "." (string-take commit 7)))
11587 (uri (git-reference
11588 (url "https://github.com/aboyle/F-seq.git")
11590 (file-name (string-append name "-" version))
11593 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11594 (modules '((guix build utils)))
11595 ;; Remove bundled Java library archives.
11598 (for-each delete-file (find-files "lib" ".*"))
11600 (build-system ant-build-system)
11602 `(#:tests? #f ; no tests included
11604 (modify-phases %standard-phases
11606 (lambda* (#:key inputs outputs #:allow-other-keys)
11607 (let* ((target (assoc-ref outputs "out"))
11608 (bin (string-append target "/bin"))
11609 (doc (string-append target "/share/doc/f-seq"))
11610 (lib (string-append target "/lib")))
11613 (substitute* "bin/linux/fseq"
11614 (("java") (which "java"))
11615 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11616 (string-append (assoc-ref inputs "java-commons-cli")
11617 "/share/java/commons-cli.jar"))
11619 (string-append "REALDIR=" bin "\n")))
11620 (install-file "README.txt" doc)
11621 (install-file "bin/linux/fseq" bin)
11622 (install-file "build~/fseq.jar" lib)
11623 (copy-recursively "lib" lib)
11627 ("java-commons-cli" ,java-commons-cli)))
11628 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11629 (synopsis "Feature density estimator for high-throughput sequence tags")
11631 "F-Seq is a software package that generates a continuous tag sequence
11632 density estimation allowing identification of biologically meaningful sites
11633 such as transcription factor binding sites (ChIP-seq) or regions of open
11634 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11636 (license license:gpl3+))))
11638 (define-public bismark
11645 (uri (git-reference
11646 (url "https://github.com/FelixKrueger/Bismark.git")
11648 (file-name (string-append name "-" version "-checkout"))
11651 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11654 ;; highcharts.js is non-free software. The code is available under
11655 ;; CC-BY-NC or proprietary licenses only.
11656 (delete-file "bismark_sitrep/highcharts.js")
11658 (build-system perl-build-system)
11660 `(#:tests? #f ; there are no tests
11662 (modify-phases %standard-phases
11663 (delete 'configure)
11666 (lambda* (#:key inputs outputs #:allow-other-keys)
11667 (let* ((out (assoc-ref outputs "out"))
11668 (bin (string-append out "/bin"))
11669 (share (string-append out "/share/bismark"))
11670 (docdir (string-append out "/share/doc/bismark"))
11671 (docs '("Docs/Bismark_User_Guide.html"))
11672 (scripts '("bismark"
11673 "bismark_genome_preparation"
11674 "bismark_methylation_extractor"
11677 "coverage2cytosine"
11678 "deduplicate_bismark"
11679 "filter_non_conversion"
11681 "bismark2summary")))
11682 (substitute* "bismark2report"
11683 (("\\$RealBin/bismark_sitrep")
11684 (string-append share "/bismark_sitrep")))
11688 (for-each (lambda (file) (install-file file bin))
11690 (for-each (lambda (file) (install-file file docdir))
11692 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11693 (copy-recursively "bismark_sitrep"
11694 (string-append share "/bismark_sitrep"))
11696 ;; Fix references to gunzip
11697 (substitute* (map (lambda (file)
11698 (string-append bin "/" file))
11701 (string-append "\"" (assoc-ref inputs "gzip")
11702 "/bin/gunzip -c")))
11706 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11707 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11708 (description "Bismark is a program to map bisulfite treated sequencing
11709 reads to a genome of interest and perform methylation calls in a single step.
11710 The output can be easily imported into a genome viewer, such as SeqMonk, and
11711 enables a researcher to analyse the methylation levels of their samples
11712 straight away. Its main features are:
11715 @item Bisulfite mapping and methylation calling in one single step
11716 @item Supports single-end and paired-end read alignments
11717 @item Supports ungapped and gapped alignments
11718 @item Alignment seed length, number of mismatches etc are adjustable
11719 @item Output discriminates between cytosine methylation in CpG, CHG
11722 (license license:gpl3+)))
11724 (define-public paml
11730 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11731 "paml" version ".tgz"))
11734 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11735 (modules '((guix build utils)))
11736 ;; Remove Windows binaries
11739 (for-each delete-file (find-files "." "\\.exe$"))
11741 (build-system gnu-build-system)
11743 `(#:tests? #f ; there are no tests
11744 #:make-flags '("CC=gcc")
11746 (modify-phases %standard-phases
11747 (replace 'configure
11749 (substitute* "src/BFdriver.c"
11750 (("/bin/bash") (which "bash")))
11754 (lambda* (#:key outputs #:allow-other-keys)
11755 (let ((tools '("baseml" "basemlg" "codeml"
11756 "pamp" "evolver" "yn00" "chi2"))
11757 (bin (string-append (assoc-ref outputs "out") "/bin"))
11758 (docdir (string-append (assoc-ref outputs "out")
11759 "/share/doc/paml")))
11761 (for-each (lambda (file) (install-file file bin)) tools)
11762 (copy-recursively "../doc" docdir)
11764 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11765 (synopsis "Phylogentic analysis by maximum likelihood")
11766 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11767 contains a few programs for model fitting and phylogenetic tree reconstruction
11768 using nucleotide or amino-acid sequence data.")
11770 (license license:gpl3)))
11772 (define-public kallisto
11778 (uri (string-append "https://github.com/pachterlab/"
11779 "kallisto/archive/v" version ".tar.gz"))
11780 (file-name (string-append name "-" version ".tar.gz"))
11783 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11784 (build-system cmake-build-system)
11785 (arguments `(#:tests? #f)) ; no "check" target
11789 (home-page "http://pachterlab.github.io/kallisto/")
11790 (synopsis "Near-optimal RNA-Seq quantification")
11792 "Kallisto is a program for quantifying abundances of transcripts from
11793 RNA-Seq data, or more generally of target sequences using high-throughput
11794 sequencing reads. It is based on the novel idea of pseudoalignment for
11795 rapidly determining the compatibility of reads with targets, without the need
11796 for alignment. Pseudoalignment of reads preserves the key information needed
11797 for quantification, and kallisto is therefore not only fast, but also as
11798 accurate as existing quantification tools.")
11799 (license license:bsd-2)))
11801 (define-public libgff
11807 (uri (string-append
11808 "https://github.com/Kingsford-Group/"
11809 "libgff/archive/v" version ".tar.gz"))
11810 (file-name (string-append name "-" version ".tar.gz"))
11813 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11814 (build-system cmake-build-system)
11815 (arguments `(#:tests? #f)) ; no tests included
11816 (home-page "https://github.com/Kingsford-Group/libgff")
11817 (synopsis "Parser library for reading/writing GFF files")
11818 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11819 code that is used in the Cufflinks codebase. The goal of this library is to
11820 provide this functionality without the necessity of drawing in a heavy-weight
11821 dependency like SeqAn.")
11822 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11824 (define-public libdivsufsort
11826 (name "libdivsufsort")
11830 (uri (git-reference
11831 (url "https://github.com/y-256/libdivsufsort.git")
11833 (file-name (git-file-name name version))
11836 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11837 (build-system cmake-build-system)
11839 '(#:tests? #f ; there are no tests
11841 ;; Needed for rapmap and sailfish.
11842 '("-DBUILD_DIVSUFSORT64=ON")))
11843 (home-page "https://github.com/y-256/libdivsufsort")
11844 (synopsis "Lightweight suffix-sorting library")
11845 (description "libdivsufsort is a software library that implements a
11846 lightweight suffix array construction algorithm. This library provides a
11847 simple and an efficient C API to construct a suffix array and a
11848 Burrows-Wheeler transformed string from a given string over a constant-size
11849 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11850 bytes of memory space, where n is the length of the string.")
11851 (license license:expat)))
11853 (define-public sailfish
11860 (string-append "https://github.com/kingsfordgroup/"
11861 "sailfish/archive/v" version ".tar.gz"))
11862 (file-name (string-append name "-" version ".tar.gz"))
11865 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11866 (modules '((guix build utils)))
11869 ;; Delete bundled headers for eigen3.
11870 (delete-file-recursively "include/eigen3/")
11872 (build-system cmake-build-system)
11874 `(#:configure-flags
11875 (list (string-append "-DBOOST_INCLUDEDIR="
11876 (assoc-ref %build-inputs "boost")
11878 (string-append "-DBOOST_LIBRARYDIR="
11879 (assoc-ref %build-inputs "boost")
11881 (string-append "-DBoost_LIBRARIES="
11882 "-lboost_iostreams "
11883 "-lboost_filesystem "
11888 "-lboost_program_options")
11889 "-DBoost_FOUND=TRUE"
11890 ;; Don't download RapMap---we already have it!
11891 "-DFETCHED_RAPMAP=1")
11892 ;; Tests must be run after installation and the location of the test
11893 ;; data file must be overridden. But the tests fail. It looks like
11894 ;; they are not really meant to be run.
11897 (modify-phases %standard-phases
11898 ;; Boost cannot be found, even though it's right there.
11899 (add-after 'unpack 'do-not-look-for-boost
11900 (lambda* (#:key inputs #:allow-other-keys)
11901 (substitute* "CMakeLists.txt"
11902 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11903 (add-after 'unpack 'do-not-assign-to-macro
11905 (substitute* "include/spdlog/details/format.cc"
11906 (("const unsigned CHAR_WIDTH = 1;") ""))))
11907 (add-after 'unpack 'prepare-rapmap
11908 (lambda* (#:key inputs #:allow-other-keys)
11909 (let ((src "external/install/src/rapmap/")
11910 (include "external/install/include/rapmap/")
11911 (rapmap (assoc-ref inputs "rapmap")))
11912 (mkdir-p "/tmp/rapmap")
11913 (system* "tar" "xf"
11914 (assoc-ref inputs "rapmap")
11916 "--strip-components=1")
11919 (for-each (lambda (file)
11920 (install-file file src))
11921 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11922 (copy-recursively "/tmp/rapmap/include" include))))
11923 (add-after 'unpack 'use-system-libraries
11924 (lambda* (#:key inputs #:allow-other-keys)
11925 (substitute* '("src/SailfishIndexer.cpp"
11926 "src/SailfishUtils.cpp"
11927 "src/SailfishQuantify.cpp"
11928 "src/FASTAParser.cpp"
11930 "include/SailfishUtils.hpp"
11931 "include/SailfishIndex.hpp"
11932 "include/CollapsedEMOptimizer.hpp"
11933 "src/CollapsedEMOptimizer.cpp")
11934 (("#include \"jellyfish/config.h\"") ""))
11935 (substitute* "src/CMakeLists.txt"
11936 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11937 (string-append (assoc-ref inputs "jellyfish")
11938 "/include/jellyfish-" ,(package-version jellyfish)))
11939 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11940 (string-append (assoc-ref inputs "jellyfish")
11941 "/lib/libjellyfish-2.0.a"))
11942 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11943 (string-append (assoc-ref inputs "libdivsufsort")
11944 "/lib/libdivsufsort.so"))
11945 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11946 (string-append (assoc-ref inputs "libdivsufsort")
11947 "/lib/libdivsufsort64.so")))
11948 (substitute* "CMakeLists.txt"
11949 ;; Don't prefer static libs
11950 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11951 (("find_package\\(Jellyfish.*") "")
11952 (("ExternalProject_Add\\(libjellyfish") "message(")
11953 (("ExternalProject_Add\\(libgff") "message(")
11954 (("ExternalProject_Add\\(libsparsehash") "message(")
11955 (("ExternalProject_Add\\(libdivsufsort") "message("))
11957 ;; Ensure that Eigen headers can be found
11958 (setenv "CPLUS_INCLUDE_PATH"
11959 (string-append (getenv "CPLUS_INCLUDE_PATH")
11961 (assoc-ref inputs "eigen")
11962 "/include/eigen3")))))))
11966 ("jemalloc" ,jemalloc)
11967 ("jellyfish" ,jellyfish)
11968 ("sparsehash" ,sparsehash)
11971 (uri (git-reference
11972 (url "https://github.com/COMBINE-lab/RapMap.git")
11973 (commit (string-append "sf-v" version))))
11974 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11977 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11978 (modules '((guix build utils)))
11979 ;; These files are expected to be excluded.
11981 '(begin (delete-file-recursively "include/spdlog")
11982 (for-each delete-file '("include/xxhash.h"
11985 ("libdivsufsort" ,libdivsufsort)
11990 `(("pkg-config" ,pkg-config)))
11991 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11992 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11993 (description "Sailfish is a tool for genomic transcript quantification
11994 from RNA-seq data. It requires a set of target transcripts (either from a
11995 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11996 fasta file containing your reference transcripts and a (set of) fasta/fastq
11997 file(s) containing your reads.")
11998 (license license:gpl3+)))
12000 (define libstadenio-for-salmon
12002 (name "libstadenio")
12006 (uri (git-reference
12007 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12008 (commit (string-append "v" version))))
12009 (file-name (string-append name "-" version "-checkout"))
12012 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12013 (build-system gnu-build-system)
12014 (arguments '(#:parallel-tests? #f)) ; not supported
12018 `(("perl" ,perl))) ; for tests
12019 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12020 (synopsis "General purpose trace and experiment file library")
12021 (description "This package provides a library of file reading and writing
12022 code to provide a general purpose Trace file (and Experiment File) reading
12025 The following file formats are supported:
12028 @item SCF trace files
12029 @item ABI trace files
12030 @item ALF trace files
12031 @item ZTR trace files
12032 @item SFF trace archives
12033 @item SRF trace archives
12034 @item Experiment files
12035 @item Plain text files
12036 @item SAM/BAM sequence files
12037 @item CRAM sequence files
12039 (license license:bsd-3)))
12041 (define spdlog-for-salmon
12047 (uri (git-reference
12048 (url "https://github.com/COMBINE-lab/spdlog.git")
12049 (commit (string-append "v" version))))
12050 (file-name (string-append name "-" version "-checkout"))
12053 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12054 (build-system cmake-build-system)
12055 (home-page "https://github.com/COMBINE-lab/spdlog")
12056 (synopsis "Very fast C++ logging library")
12057 (description "Spdlog is a very fast header-only C++ logging library with
12058 performance as its primary goal.")
12059 (license license:expat)))
12061 ;; This is a modified variant of bwa for use with Salmon. It installs a
12062 ;; library to avoid having to build this as part of Salmon.
12063 (define bwa-for-salmon
12064 (package (inherit bwa)
12066 (version "0.7.12.5")
12069 (uri (git-reference
12070 (url "https://github.com/COMBINE-lab/bwa.git")
12071 (commit (string-append "v" version))))
12072 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12075 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12076 (build-system gnu-build-system)
12078 '(#:tests? #f ;no "check" target
12080 (modify-phases %standard-phases
12082 (lambda* (#:key outputs #:allow-other-keys)
12083 (let* ((out (assoc-ref outputs "out"))
12084 (bin (string-append out "/bin"))
12085 (lib (string-append out "/lib"))
12086 (doc (string-append out "/share/doc/bwa"))
12087 (man (string-append out "/share/man/man1"))
12088 (inc (string-append out "/include/bwa")))
12089 (install-file "bwa" bin)
12090 (install-file "README.md" doc)
12091 (install-file "bwa.1" man)
12092 (install-file "libbwa.a" lib)
12095 (for-each (lambda (file)
12096 (install-file file inc))
12097 (find-files "." "\\.h$")))
12099 ;; no "configure" script
12100 (delete 'configure))))))
12102 (define-public salmon
12108 (uri (git-reference
12109 (url "https://github.com/COMBINE-lab/salmon.git")
12110 (commit (string-append "v" version))))
12111 (file-name (string-append name "-" version "-checkout"))
12114 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12115 (modules '((guix build utils)))
12118 ;; Delete bundled headers for eigen3.
12119 (delete-file-recursively "include/eigen3/")
12121 (build-system cmake-build-system)
12123 `(#:configure-flags
12124 (list (string-append "-DBOOST_INCLUDEDIR="
12125 (assoc-ref %build-inputs "boost")
12127 (string-append "-DBOOST_LIBRARYDIR="
12128 (assoc-ref %build-inputs "boost")
12130 (string-append "-DBoost_LIBRARIES="
12131 "-lboost_iostreams "
12132 "-lboost_filesystem "
12137 "-lboost_program_options")
12138 "-DBoost_FOUND=TRUE"
12139 "-DTBB_LIBRARIES=tbb tbbmalloc"
12140 ;; Don't download RapMap---we already have it!
12141 "-DFETCHED_RAPMAP=1")
12143 (modify-phases %standard-phases
12144 ;; Boost cannot be found, even though it's right there.
12145 (add-after 'unpack 'do-not-look-for-boost
12146 (lambda* (#:key inputs #:allow-other-keys)
12147 (substitute* "CMakeLists.txt"
12148 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12149 (add-after 'unpack 'do-not-phone-home
12151 (substitute* "src/Salmon.cpp"
12152 (("getVersionMessage\\(\\)") "\"\""))))
12153 (add-after 'unpack 'prepare-rapmap
12154 (lambda* (#:key inputs #:allow-other-keys)
12155 (let ((src "external/install/src/rapmap/")
12156 (include "external/install/include/rapmap/")
12157 (rapmap (assoc-ref inputs "rapmap")))
12160 (for-each (lambda (file)
12161 (install-file file src))
12162 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12163 (copy-recursively (string-append rapmap "/include") include)
12164 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12165 "external/install/include/rapmap/FastxParser.hpp"
12166 "external/install/include/rapmap/concurrentqueue.h"
12167 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12168 "external/install/src/rapmap/FastxParser.cpp"
12169 "external/install/src/rapmap/xxhash.c")))))
12170 (add-after 'unpack 'use-system-libraries
12171 (lambda* (#:key inputs #:allow-other-keys)
12172 (substitute* "src/CMakeLists.txt"
12173 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12174 (string-append (assoc-ref inputs "jellyfish")
12175 "/include/jellyfish-" ,(package-version jellyfish)))
12176 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12177 (string-append (assoc-ref inputs "jellyfish")
12178 "/lib/libjellyfish-2.0.a"))
12179 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12180 (string-append (assoc-ref inputs "libdivsufsort")
12181 "/lib/libdivsufsort.so"))
12182 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12183 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12184 "/lib/libstaden-read.a"))
12185 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12186 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12187 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12188 (string-append (assoc-ref inputs "libdivsufsort")
12189 "/lib/libdivsufsort64.so")))
12190 (substitute* "CMakeLists.txt"
12191 ;; Don't prefer static libs
12192 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12193 (("set\\(TBB_LIBRARIES") "message(")
12194 (("find_package\\(Jellyfish.*") "")
12195 (("ExternalProject_Add\\(libcereal") "message(")
12196 (("ExternalProject_Add\\(libbwa") "message(")
12197 (("ExternalProject_Add\\(libjellyfish") "message(")
12198 (("ExternalProject_Add\\(libgff") "message(")
12199 (("ExternalProject_Add\\(libtbb") "message(")
12200 (("ExternalProject_Add\\(libspdlog") "message(")
12201 (("ExternalProject_Add\\(libdivsufsort") "message(")
12202 (("ExternalProject_Add\\(libstadenio") "message(")
12203 (("ExternalProject_Add_Step\\(") "message("))
12205 ;; Ensure that all headers can be found
12206 (setenv "CPLUS_INCLUDE_PATH"
12207 (string-append (getenv "CPLUS_INCLUDE_PATH")
12209 (assoc-ref inputs "bwa")
12212 (assoc-ref inputs "eigen")
12213 "/include/eigen3"))
12215 (string-append (assoc-ref inputs "bwa")
12218 (assoc-ref inputs "eigen")
12219 "/include/eigen3"))
12221 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12222 ;; run. It only exists after the install phase.
12223 (add-after 'unpack 'fix-tests
12225 (substitute* "src/CMakeLists.txt"
12226 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12227 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12231 ("bwa" ,bwa-for-salmon)
12237 (uri (git-reference
12238 (url "https://github.com/COMBINE-lab/RapMap.git")
12239 (commit (string-append "salmon-v" version))))
12240 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12243 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12244 ("jemalloc" ,jemalloc)
12245 ("jellyfish" ,jellyfish)
12248 ("libdivsufsort" ,libdivsufsort)
12249 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12250 ("spdlog-for-salmon" ,spdlog-for-salmon)
12253 (home-page "https://github.com/COMBINE-lab/salmon")
12254 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12255 (description "Salmon is a program to produce highly-accurate,
12256 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12257 its accuracy and speed via a number of different innovations, including the
12258 use of lightweight alignments (accurate but fast-to-compute proxies for
12259 traditional read alignments) and massively-parallel stochastic collapsed
12260 variational inference.")
12261 (license license:gpl3+)))
12263 (define-public python-loompy
12265 (name "python-loompy")
12270 (uri (pypi-uri "loompy" version))
12273 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12274 (build-system python-build-system)
12275 ;; There are no tests
12276 (arguments '(#:tests? #f))
12278 `(("python-h5py" ,python-h5py)
12279 ("python-numpy" ,python-numpy)
12280 ("python-scipy" ,python-scipy)
12281 ("python-typing" ,python-typing)))
12282 (home-page "https://github.com/linnarsson-lab/loompy")
12283 (synopsis "Work with .loom files for single-cell RNA-seq data")
12284 (description "The loom file format is an efficient format for very large
12285 omics datasets, consisting of a main matrix, optional additional layers, a
12286 variable number of row and column annotations. Loom also supports sparse
12287 graphs. This library makes it easy to work with @file{.loom} files for
12288 single-cell RNA-seq data.")
12289 (license license:bsd-3)))
12291 ;; We cannot use the latest commit because it requires Java 9.
12292 (define-public java-forester
12293 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12296 (name "java-forester")
12297 (version (string-append "0-" revision "." (string-take commit 7)))
12300 (uri (git-reference
12301 (url "https://github.com/cmzmasek/forester.git")
12303 (file-name (string-append name "-" version "-checkout"))
12306 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12307 (modules '((guix build utils)))
12310 ;; Delete bundled jars and pre-built classes
12311 (delete-file-recursively "forester/java/resources")
12312 (delete-file-recursively "forester/java/classes")
12313 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12314 ;; Delete bundled applications
12315 (delete-file-recursively "forester_applications")
12317 (build-system ant-build-system)
12319 `(#:tests? #f ; there are none
12321 #:modules ((guix build ant-build-system)
12323 (guix build java-utils)
12327 (modify-phases %standard-phases
12328 (add-after 'unpack 'chdir
12329 (lambda _ (chdir "forester/java") #t))
12330 (add-after 'chdir 'fix-dependencies
12332 (chmod "build.xml" #o664)
12333 (call-with-output-file "build.xml.new"
12337 (with-input-from-file "build.xml"
12338 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12339 `(;; Remove all unjar tags to avoid repacking classes.
12340 (unjar . ,(lambda _ '()))
12341 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12342 (*text* . ,(lambda (_ txt) txt))))
12344 (rename-file "build.xml.new" "build.xml")
12346 ;; FIXME: itext is difficult to package as it depends on a few
12347 ;; unpackaged libraries.
12348 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12350 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12351 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12352 (("pdf_written_to = PdfExporter.*")
12353 "throw new IOException(\"PDF export is not available.\");"))
12355 ;; There is no install target
12356 (replace 'install (install-jars ".")))))
12358 `(("java-commons-codec" ,java-commons-codec)
12359 ("java-openchart2" ,java-openchart2)))
12360 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12361 (synopsis "Phylogenomics libraries for Java")
12362 (description "Forester is a collection of Java libraries for
12363 phylogenomics and evolutionary biology research. It includes support for
12364 reading, writing, and exporting phylogenetic trees.")
12365 (license license:lgpl2.1+))))
12367 (define-public java-forester-1.005
12369 (name "java-forester")
12373 (uri (string-append "http://search.maven.org/remotecontent?"
12374 "filepath=org/biojava/thirdparty/forester/"
12375 version "/forester-" version "-sources.jar"))
12376 (file-name (string-append name "-" version ".jar"))
12379 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12380 (build-system ant-build-system)
12382 `(#:tests? #f ; there are none
12384 #:modules ((guix build ant-build-system)
12386 (guix build java-utils)
12390 (modify-phases %standard-phases
12391 (add-after 'unpack 'fix-dependencies
12392 (lambda* (#:key inputs #:allow-other-keys)
12393 (call-with-output-file "build.xml"
12397 (with-input-from-file "src/build.xml"
12398 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12399 `(;; Remove all unjar tags to avoid repacking classes.
12400 (unjar . ,(lambda _ '()))
12401 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12402 (*text* . ,(lambda (_ txt) txt))))
12404 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12405 "synth_look_and_feel_1.xml")
12406 (copy-file (assoc-ref inputs "phyloxml.xsd")
12408 (substitute* "build.xml"
12409 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12410 "synth_look_and_feel_1.xml")
12411 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12414 ;; FIXME: itext is difficult to package as it depends on a few
12415 ;; unpackaged libraries.
12416 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12418 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12419 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12420 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12421 (("pdf_written_to = PdfExporter.*")
12422 "throw new IOException(\"PDF export is not available.\"); /*")
12423 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12424 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12426 (add-after 'unpack 'delete-pre-built-classes
12427 (lambda _ (delete-file-recursively "src/classes") #t))
12428 ;; There is no install target
12429 (replace 'install (install-jars ".")))))
12431 `(("java-commons-codec" ,java-commons-codec)
12432 ("java-openchart2" ,java-openchart2)))
12433 ;; The source archive does not contain the resources.
12438 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12439 "b61cc2dcede0bede317db362472333115756b8c6/"
12440 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12441 (file-name (string-append name "-phyloxml-" version ".xsd"))
12444 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12445 ("synth_look_and_feel_1.xml"
12448 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12449 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12450 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12451 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12454 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12455 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12456 (synopsis "Phylogenomics libraries for Java")
12457 (description "Forester is a collection of Java libraries for
12458 phylogenomics and evolutionary biology research. It includes support for
12459 reading, writing, and exporting phylogenetic trees.")
12460 (license license:lgpl2.1+)))
12462 (define-public java-biojava-core
12464 (name "java-biojava-core")
12468 (uri (git-reference
12469 (url "https://github.com/biojava/biojava")
12470 (commit (string-append "biojava-" version))))
12471 (file-name (string-append name "-" version "-checkout"))
12474 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12475 (build-system ant-build-system)
12478 #:jar-name "biojava-core.jar"
12479 #:source-dir "biojava-core/src/main/java/"
12480 #:test-dir "biojava-core/src/test"
12481 ;; These tests seem to require internet access.
12482 #:test-exclude (list "**/SearchIOTest.java"
12483 "**/BlastXMLParserTest.java"
12484 "**/GenbankCookbookTest.java"
12485 "**/GenbankProxySequenceReaderTest.java")
12487 (modify-phases %standard-phases
12488 (add-before 'build 'copy-resources
12490 (copy-recursively "biojava-core/src/main/resources"
12493 (add-before 'check 'copy-test-resources
12495 (copy-recursively "biojava-core/src/test/resources"
12496 "build/test-classes")
12499 `(("java-log4j-api" ,java-log4j-api)
12500 ("java-log4j-core" ,java-log4j-core)
12501 ("java-slf4j-api" ,java-slf4j-api)
12502 ("java-slf4j-simple" ,java-slf4j-simple)))
12504 `(("java-junit" ,java-junit)
12505 ("java-hamcrest-core" ,java-hamcrest-core)))
12506 (home-page "http://biojava.org")
12507 (synopsis "Core libraries of Java framework for processing biological data")
12508 (description "BioJava is a project dedicated to providing a Java framework
12509 for processing biological data. It provides analytical and statistical
12510 routines, parsers for common file formats, reference implementations of
12511 popular algorithms, and allows the manipulation of sequences and 3D
12512 structures. The goal of the biojava project is to facilitate rapid
12513 application development for bioinformatics.
12515 This package provides the core libraries.")
12516 (license license:lgpl2.1+)))
12518 (define-public java-biojava-phylo
12519 (package (inherit java-biojava-core)
12520 (name "java-biojava-phylo")
12521 (build-system ant-build-system)
12524 #:jar-name "biojava-phylo.jar"
12525 #:source-dir "biojava-phylo/src/main/java/"
12526 #:test-dir "biojava-phylo/src/test"
12528 (modify-phases %standard-phases
12529 (add-before 'build 'copy-resources
12531 (copy-recursively "biojava-phylo/src/main/resources"
12534 (add-before 'check 'copy-test-resources
12536 (copy-recursively "biojava-phylo/src/test/resources"
12537 "build/test-classes")
12540 `(("java-log4j-api" ,java-log4j-api)
12541 ("java-log4j-core" ,java-log4j-core)
12542 ("java-slf4j-api" ,java-slf4j-api)
12543 ("java-slf4j-simple" ,java-slf4j-simple)
12544 ("java-biojava-core" ,java-biojava-core)
12545 ("java-forester" ,java-forester)))
12547 `(("java-junit" ,java-junit)
12548 ("java-hamcrest-core" ,java-hamcrest-core)))
12549 (home-page "http://biojava.org")
12550 (synopsis "Biojava interface to the forester phylogenomics library")
12551 (description "The phylo module provides a biojava interface layer to the
12552 forester phylogenomics library for constructing phylogenetic trees.")))
12554 (define-public java-biojava-alignment
12555 (package (inherit java-biojava-core)
12556 (name "java-biojava-alignment")
12557 (build-system ant-build-system)
12560 #:jar-name "biojava-alignment.jar"
12561 #:source-dir "biojava-alignment/src/main/java/"
12562 #:test-dir "biojava-alignment/src/test"
12564 (modify-phases %standard-phases
12565 (add-before 'build 'copy-resources
12567 (copy-recursively "biojava-alignment/src/main/resources"
12570 (add-before 'check 'copy-test-resources
12572 (copy-recursively "biojava-alignment/src/test/resources"
12573 "build/test-classes")
12576 `(("java-log4j-api" ,java-log4j-api)
12577 ("java-log4j-core" ,java-log4j-core)
12578 ("java-slf4j-api" ,java-slf4j-api)
12579 ("java-slf4j-simple" ,java-slf4j-simple)
12580 ("java-biojava-core" ,java-biojava-core)
12581 ("java-biojava-phylo" ,java-biojava-phylo)
12582 ("java-forester" ,java-forester)))
12584 `(("java-junit" ,java-junit)
12585 ("java-hamcrest-core" ,java-hamcrest-core)))
12586 (home-page "http://biojava.org")
12587 (synopsis "Biojava API for genetic sequence alignment")
12588 (description "The alignment module of BioJava provides an API that
12592 @item implementations of dynamic programming algorithms for sequence
12594 @item reading and writing of popular alignment file formats;
12595 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12598 (define-public java-biojava-core-4.0
12599 (package (inherit java-biojava-core)
12600 (name "java-biojava-core")
12604 (uri (git-reference
12605 (url "https://github.com/biojava/biojava")
12606 (commit (string-append "biojava-" version))))
12607 (file-name (string-append name "-" version "-checkout"))
12610 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12612 (define-public java-biojava-phylo-4.0
12613 (package (inherit java-biojava-core-4.0)
12614 (name "java-biojava-phylo")
12615 (build-system ant-build-system)
12618 #:jar-name "biojava-phylo.jar"
12619 #:source-dir "biojava-phylo/src/main/java/"
12620 #:test-dir "biojava-phylo/src/test"
12622 (modify-phases %standard-phases
12623 (add-before 'build 'copy-resources
12625 (copy-recursively "biojava-phylo/src/main/resources"
12628 (add-before 'check 'copy-test-resources
12630 (copy-recursively "biojava-phylo/src/test/resources"
12631 "build/test-classes")
12634 `(("java-log4j-api" ,java-log4j-api)
12635 ("java-log4j-core" ,java-log4j-core)
12636 ("java-slf4j-api" ,java-slf4j-api)
12637 ("java-slf4j-simple" ,java-slf4j-simple)
12638 ("java-biojava-core" ,java-biojava-core-4.0)
12639 ("java-forester" ,java-forester-1.005)))
12641 `(("java-junit" ,java-junit)
12642 ("java-hamcrest-core" ,java-hamcrest-core)))
12643 (home-page "http://biojava.org")
12644 (synopsis "Biojava interface to the forester phylogenomics library")
12645 (description "The phylo module provides a biojava interface layer to the
12646 forester phylogenomics library for constructing phylogenetic trees.")))
12648 (define-public java-biojava-alignment-4.0
12649 (package (inherit java-biojava-core-4.0)
12650 (name "java-biojava-alignment")
12651 (build-system ant-build-system)
12654 #:jar-name "biojava-alignment.jar"
12655 #:source-dir "biojava-alignment/src/main/java/"
12656 #:test-dir "biojava-alignment/src/test"
12658 (modify-phases %standard-phases
12659 (add-before 'build 'copy-resources
12661 (copy-recursively "biojava-alignment/src/main/resources"
12664 (add-before 'check 'copy-test-resources
12666 (copy-recursively "biojava-alignment/src/test/resources"
12667 "build/test-classes")
12670 `(("java-log4j-api" ,java-log4j-api)
12671 ("java-log4j-core" ,java-log4j-core)
12672 ("java-slf4j-api" ,java-slf4j-api)
12673 ("java-slf4j-simple" ,java-slf4j-simple)
12674 ("java-biojava-core" ,java-biojava-core-4.0)
12675 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12676 ("java-forester" ,java-forester-1.005)))
12678 `(("java-junit" ,java-junit)
12679 ("java-hamcrest-core" ,java-hamcrest-core)))
12680 (home-page "http://biojava.org")
12681 (synopsis "Biojava API for genetic sequence alignment")
12682 (description "The alignment module of BioJava provides an API that
12686 @item implementations of dynamic programming algorithms for sequence
12688 @item reading and writing of popular alignment file formats;
12689 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12692 (define-public dropseq-tools
12694 (name "dropseq-tools")
12699 (uri "http://mccarrolllab.com/download/1276/")
12700 (file-name (string-append "dropseq-tools-" version ".zip"))
12703 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12704 ;; Delete bundled libraries
12705 (modules '((guix build utils)))
12708 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12709 (delete-file-recursively "3rdParty")
12711 (build-system ant-build-system)
12713 `(#:tests? #f ; test data are not included
12714 #:test-target "test"
12715 #:build-target "all"
12716 #:source-dir "public/src/"
12719 (list (string-append "-Dpicard.executable.dir="
12720 (assoc-ref %build-inputs "java-picard")
12722 #:modules ((ice-9 match)
12725 (guix build java-utils)
12726 (guix build ant-build-system))
12728 (modify-phases %standard-phases
12729 ;; FIXME: fails with "java.io.FileNotFoundException:
12730 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12731 (delete 'generate-jar-indices)
12732 ;; All dependencies must be linked to "lib", because that's where
12733 ;; they will be searched for when the Class-Path property of the
12734 ;; manifest is computed.
12735 (add-after 'unpack 'record-references
12736 (lambda* (#:key inputs #:allow-other-keys)
12737 (mkdir-p "jar/lib")
12738 (let ((dirs (filter-map (match-lambda
12740 (if (and (string-prefix? "java-" name)
12741 (not (string=? name "java-testng")))
12744 (for-each (lambda (jar)
12745 (symlink jar (string-append "jar/lib/" (basename jar))))
12746 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12749 ;; There is no installation target
12751 (lambda* (#:key inputs outputs #:allow-other-keys)
12752 (let* ((out (assoc-ref outputs "out"))
12753 (bin (string-append out "/bin"))
12754 (share (string-append out "/share/java/"))
12755 (lib (string-append share "/lib/"))
12756 (scripts (list "BAMTagHistogram"
12757 "BAMTagofTagCounts"
12758 "BaseDistributionAtReadPosition"
12759 "CollapseBarcodesInPlace"
12760 "CollapseTagWithContext"
12762 "CreateIntervalsFiles"
12763 "DetectBeadSynthesisErrors"
12764 "DigitalExpression"
12765 "Drop-seq_alignment.sh"
12768 "GatherGeneGCLength"
12769 "GatherMolecularBarcodeDistributionByGene"
12770 "GatherReadQualityMetrics"
12773 "SelectCellsByNumTranscripts"
12774 "SingleCellRnaSeqMetricsCollector"
12775 "TagBamWithReadSequenceExtended"
12776 "TagReadWithGeneExon"
12777 "TagReadWithInterval"
12778 "TrimStartingSequence"
12779 "ValidateReference")))
12780 (for-each mkdir-p (list bin share lib))
12781 (install-file "dist/dropseq.jar" share)
12782 (for-each (lambda (script)
12783 (chmod script #o555)
12784 (install-file script bin))
12786 (substitute* (map (lambda (script)
12787 (string-append bin "/" script))
12789 (("^java") (which "java"))
12790 (("jar_deploy_dir=.*")
12791 (string-append "jar_deploy_dir=" share "\n"))))
12793 ;; FIXME: We do this after stripping jars because we don't want it to
12794 ;; copy all these jars and strip them. We only want to install
12795 ;; links. Arguably, this is a problem with the ant-build-system.
12796 (add-after 'strip-jar-timestamps 'install-links
12797 (lambda* (#:key outputs #:allow-other-keys)
12798 (let* ((out (assoc-ref outputs "out"))
12799 (share (string-append out "/share/java/"))
12800 (lib (string-append share "/lib/")))
12801 (for-each (lambda (jar)
12802 (symlink (readlink jar)
12803 (string-append lib (basename jar))))
12804 (find-files "jar/lib" "\\.jar$")))
12807 `(("jdk" ,icedtea-8)
12808 ("java-picard" ,java-picard-2.10.3)
12809 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12810 ("java-commons-math3" ,java-commons-math3)
12811 ("java-commons-jexl2" ,java-commons-jexl-2)
12812 ("java-commons-collections4" ,java-commons-collections4)
12813 ("java-commons-lang2" ,java-commons-lang)
12814 ("java-commons-io" ,java-commons-io)
12815 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12816 ("java-guava" ,java-guava)
12817 ("java-la4j" ,java-la4j)
12818 ("java-biojava-core" ,java-biojava-core-4.0)
12819 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12820 ("java-jdistlib" ,java-jdistlib)
12821 ("java-simple-xml" ,java-simple-xml)
12822 ("java-snakeyaml" ,java-snakeyaml)))
12825 ("java-testng" ,java-testng)))
12826 (home-page "http://mccarrolllab.com/dropseq/")
12827 (synopsis "Tools for Drop-seq analyses")
12828 (description "Drop-seq is a technology to enable biologists to
12829 analyze RNA expression genome-wide in thousands of individual cells at
12830 once. This package provides tools to perform Drop-seq analyses.")
12831 (license license:expat)))
12833 (define-public pigx-rnaseq
12835 (name "pigx-rnaseq")
12839 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12840 "releases/download/v" version
12841 "/pigx_rnaseq-" version ".tar.gz"))
12844 "16gla23rmziimqan7w494q0nr7vfbp42zzkrl9fracmr4k7b1kzr"))))
12845 (build-system gnu-build-system)
12847 `(#:parallel-tests? #f ; not supported
12849 (modify-phases %standard-phases
12850 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12851 (add-after 'unpack 'disable-resource-intensive-test
12853 (substitute* "Makefile.in"
12854 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12855 (("^ tests/test_multiqc/test.sh") "")
12856 (("^ test.sh") ""))
12860 ("snakemake" ,snakemake-4)
12862 ("multiqc" ,multiqc)
12864 ("trim-galore" ,trim-galore)
12866 ("samtools" ,samtools)
12867 ("bedtools" ,bedtools)
12868 ("r-minimal" ,r-minimal)
12869 ("r-rmarkdown" ,r-rmarkdown)
12870 ("r-ggplot2" ,r-ggplot2)
12871 ("r-ggrepel" ,r-ggrepel)
12872 ("r-gprofiler" ,r-gprofiler)
12873 ("r-deseq2" ,r-deseq2)
12875 ("r-knitr" ,r-knitr)
12876 ("r-pheatmap" ,r-pheatmap)
12877 ("r-corrplot" ,r-corrplot)
12878 ("r-reshape2" ,r-reshape2)
12879 ("r-plotly" ,r-plotly)
12880 ("r-scales" ,r-scales)
12881 ("r-summarizedexperiment" ,r-summarizedexperiment)
12882 ("r-crosstalk" ,r-crosstalk)
12883 ("r-tximport" ,r-tximport)
12884 ("r-rtracklayer" ,r-rtracklayer)
12885 ("r-rjson" ,r-rjson)
12887 ("ghc-pandoc" ,ghc-pandoc-1)
12888 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12889 ("python-wrapper" ,python-wrapper)
12890 ("python-pyyaml" ,python-pyyaml)))
12891 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12892 (synopsis "Analysis pipeline for RNA sequencing experiments")
12893 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12894 reporting for RNA sequencing experiments. It is easy to use and produces high
12895 quality reports. The inputs are reads files from the sequencing experiment,
12896 and a configuration file which describes the experiment. In addition to
12897 quality control of the experiment, the pipeline produces a differential
12898 expression report comparing samples in an easily configurable manner.")
12899 (license license:gpl3+)))
12901 (define-public pigx-chipseq
12903 (name "pigx-chipseq")
12907 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12908 "releases/download/v" version
12909 "/pigx_chipseq-" version ".tar.gz"))
12912 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
12913 (build-system gnu-build-system)
12914 ;; parts of the tests rely on access to the network
12915 (arguments '(#:tests? #f))
12918 ("coreutils" ,coreutils)
12919 ("r-minimal" ,r-minimal)
12920 ("r-argparser" ,r-argparser)
12921 ("r-biocparallel" ,r-biocparallel)
12922 ("r-biostrings" ,r-biostrings)
12923 ("r-chipseq" ,r-chipseq)
12924 ("r-data-table" ,r-data-table)
12925 ("r-dplyr" ,r-dplyr)
12926 ("r-genomation" ,r-genomation)
12927 ("r-genomicalignments" ,r-genomicalignments)
12928 ("r-genomicranges" ,r-genomicranges)
12929 ("r-rsamtools" ,r-rsamtools)
12930 ("r-rtracklayer" ,r-rtracklayer)
12931 ("r-s4vectors" ,r-s4vectors)
12932 ("r-stringr" ,r-stringr)
12933 ("r-tibble" ,r-tibble)
12934 ("r-tidyr" ,r-tidyr)
12935 ("r-jsonlite" ,r-jsonlite)
12936 ("r-heatmaply" ,r-heatmaply)
12937 ("r-htmlwidgets" ,r-htmlwidgets)
12938 ("r-ggplot2" ,r-ggplot2)
12939 ("r-plotly" ,r-plotly)
12940 ("r-rmarkdown" ,r-rmarkdown)
12941 ("python-wrapper" ,python-wrapper)
12942 ("python-pyyaml" ,python-pyyaml)
12943 ("python-magic" ,python-magic)
12944 ("python-xlrd" ,python-xlrd)
12945 ("trim-galore" ,trim-galore)
12947 ("multiqc" ,multiqc)
12949 ("ghc-pandoc" ,ghc-pandoc-1)
12950 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12954 ("snakemake" ,snakemake-4)
12955 ("samtools" ,samtools)
12956 ("bedtools" ,bedtools)
12957 ("kentutils" ,kentutils)))
12959 `(("python-pytest" ,python-pytest)))
12960 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12961 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12962 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12963 calling and reporting for ChIP sequencing experiments. It is easy to use and
12964 produces high quality reports. The inputs are reads files from the sequencing
12965 experiment, and a configuration file which describes the experiment. In
12966 addition to quality control of the experiment, the pipeline enables to set up
12967 multiple peak calling analysis and allows the generation of a UCSC track hub
12968 in an easily configurable manner.")
12969 (license license:gpl3+)))
12971 (define-public pigx-bsseq
12973 (name "pigx-bsseq")
12977 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12978 "releases/download/v" version
12979 "/pigx_bsseq-" version ".tar.gz"))
12982 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12983 (build-system gnu-build-system)
12986 (modify-phases %standard-phases
12987 (add-before 'check 'set-timezone
12988 ;; The readr package is picky about timezones.
12989 (lambda* (#:key inputs #:allow-other-keys)
12990 (setenv "TZ" "UTC+1")
12992 (string-append (assoc-ref inputs "tzdata")
12993 "/share/zoneinfo"))
12996 `(("tzdata" ,tzdata)))
12998 `(("coreutils" ,coreutils)
13001 ("r-minimal" ,r-minimal)
13002 ("r-annotationhub" ,r-annotationhub)
13004 ("r-genomation" ,r-genomation)
13005 ("r-methylkit" ,r-methylkit)
13006 ("r-rtracklayer" ,r-rtracklayer)
13007 ("r-rmarkdown" ,r-rmarkdown)
13008 ("r-bookdown" ,r-bookdown)
13009 ("r-ggplot2" ,r-ggplot2)
13010 ("r-ggbio" ,r-ggbio)
13011 ("ghc-pandoc" ,ghc-pandoc-1)
13012 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13013 ("python-wrapper" ,python-wrapper)
13014 ("python-pyyaml" ,python-pyyaml)
13015 ("snakemake" ,snakemake-4)
13016 ("bismark" ,bismark)
13019 ("trim-galore" ,trim-galore)
13020 ("cutadapt" ,cutadapt)
13021 ("samtools" ,samtools)))
13022 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13023 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13024 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13025 data of bisulfite experiments; it produces reports on aggregate methylation
13026 and coverage and can be used to produce information on differential
13027 methylation and segmentation.")
13028 (license license:gpl3+)))
13030 (define-public pigx-scrnaseq
13032 (name "pigx-scrnaseq")
13036 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13037 "releases/download/v" version
13038 "/pigx_scrnaseq-" version ".tar.gz"))
13041 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13042 (build-system gnu-build-system)
13044 `(#:configure-flags
13045 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13046 "/share/java/picard.jar")
13047 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13048 "/share/java/dropseq.jar"))))
13050 `(("coreutils" ,coreutils)
13052 ("dropseq-tools" ,dropseq-tools)
13054 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13055 ("java" ,icedtea-8)
13056 ("python-wrapper" ,python-wrapper)
13057 ("python-pyyaml" ,python-pyyaml)
13058 ("python-pandas" ,python-pandas)
13059 ("python-magic" ,python-magic)
13060 ("python-numpy" ,python-numpy)
13061 ("python-loompy" ,python-loompy)
13062 ("ghc-pandoc" ,ghc-pandoc-1)
13063 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13064 ("samtools" ,samtools)
13065 ("snakemake" ,snakemake-4)
13067 ("r-minimal" ,r-minimal)
13068 ("r-argparser" ,r-argparser)
13069 ("r-cowplot" ,r-cowplot)
13070 ("r-data-table" ,r-data-table)
13071 ("r-delayedarray" ,r-delayedarray)
13072 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13073 ("r-dplyr" ,r-dplyr)
13074 ("r-dropbead" ,r-dropbead)
13076 ("r-genomicalignments" ,r-genomicalignments)
13077 ("r-genomicfiles" ,r-genomicfiles)
13078 ("r-genomicranges" ,r-genomicranges)
13079 ("r-ggplot2" ,r-ggplot2)
13080 ("r-hdf5array" ,r-hdf5array)
13081 ("r-pheatmap" ,r-pheatmap)
13082 ("r-rmarkdown" ,r-rmarkdown)
13083 ("r-rsamtools" ,r-rsamtools)
13084 ("r-rtracklayer" ,r-rtracklayer)
13085 ("r-rtsne" ,r-rtsne)
13086 ("r-scater" ,r-scater)
13087 ("r-scran" ,r-scran)
13088 ("r-singlecellexperiment" ,r-singlecellexperiment)
13089 ("r-stringr" ,r-stringr)
13090 ("r-yaml" ,r-yaml)))
13091 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13092 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13093 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13094 quality control for single cell RNA sequencing experiments. The inputs are
13095 read files from the sequencing experiment, and a configuration file which
13096 describes the experiment. It produces processed files for downstream analysis
13097 and interactive quality reports. The pipeline is designed to work with UMI
13099 (license license:gpl3+)))
13101 (define-public pigx
13107 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13108 "releases/download/v" version
13109 "/pigx-" version ".tar.gz"))
13112 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13113 (build-system gnu-build-system)
13115 `(("python" ,python)
13116 ("pigx-bsseq" ,pigx-bsseq)
13117 ("pigx-chipseq" ,pigx-chipseq)
13118 ("pigx-rnaseq" ,pigx-rnaseq)
13119 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13120 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13121 (synopsis "Analysis pipelines for genomics")
13122 (description "PiGx is a collection of genomics pipelines. It includes the
13123 following pipelines:
13126 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13127 @item PiGx RNAseq for RNAseq samples
13128 @item PiGx scRNAseq for single cell dropseq analysis
13129 @item PiGx ChIPseq for reads from ChIPseq experiments
13132 All pipelines are easily configured with a simple sample sheet and a
13133 descriptive settings file. The result is a set of comprehensive, interactive
13134 HTML reports with interesting findings about your samples.")
13135 (license license:gpl3+)))
13137 (define-public r-diversitree
13139 (name "r-diversitree")
13144 (uri (cran-uri "diversitree" version))
13147 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13148 (build-system r-build-system)
13150 `(("gfortran" ,gfortran)))
13151 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13154 ("r-desolve" ,r-desolve)
13156 ("r-suplex" ,r-subplex)))
13157 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13158 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13159 (description "This package contains a number of comparative \"phylogenetic\"
13160 methods, mostly focusing on analysing diversification and character evolution.
13161 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13162 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13163 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13164 include Markov models of discrete and continuous trait evolution and constant
13165 rate speciation and extinction.")
13166 (license license:gpl2+)))
13168 (define-public sjcount
13169 ;; There is no tag for version 3.2, nor is there a release archive.
13170 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13174 (version (git-version "3.2" revision commit))
13177 (uri (git-reference
13178 (url "https://github.com/pervouchine/sjcount-full.git")
13180 (file-name (string-append name "-" version "-checkout"))
13183 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13184 (build-system gnu-build-system)
13186 `(#:tests? #f ; requires a 1.4G test file
13188 (list (string-append "SAMTOOLS_DIR="
13189 (assoc-ref %build-inputs "samtools")
13192 (modify-phases %standard-phases
13193 (replace 'configure
13194 (lambda* (#:key inputs #:allow-other-keys)
13195 (substitute* "makefile"
13196 (("-I \\$\\{SAMTOOLS_DIR\\}")
13197 (string-append "-I" (assoc-ref inputs "samtools")
13198 "/include/samtools"))
13199 (("-lz ") "-lz -lpthread "))
13202 (lambda* (#:key outputs #:allow-other-keys)
13203 (for-each (lambda (tool)
13205 (string-append (assoc-ref outputs "out")
13207 '("j_count" "b_count" "sjcount"))
13210 `(("samtools" ,samtools-0.1)
13212 (home-page "https://github.com/pervouchine/sjcount-full/")
13213 (synopsis "Annotation-agnostic splice junction counting pipeline")
13214 (description "Sjcount is a utility for fast quantification of splice
13215 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13216 version does count multisplits.")
13217 (license license:gpl3+))))
13219 (define-public minimap2
13226 (uri (string-append "https://github.com/lh3/minimap2/"
13227 "releases/download/v" version "/"
13228 "minimap2-" version ".tar.bz2"))
13231 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13232 (build-system gnu-build-system)
13234 `(#:tests? #f ; there are none
13237 (let ((system ,(or (%current-target-system)
13238 (%current-system))))
13240 ((string-prefix? "x86_64" system)
13242 ((or (string-prefix? "armhf" system)
13243 (string-prefix? "aarch64" system))
13245 (_ "sse2only=1"))))
13247 (modify-phases %standard-phases
13248 (delete 'configure)
13250 (lambda* (#:key outputs #:allow-other-keys)
13251 (let* ((out (assoc-ref outputs "out"))
13252 (bin (string-append out "/bin"))
13253 (man (string-append out "/share/man/man1")))
13254 (install-file "minimap2" bin)
13256 (install-file "minimap2.1" man))
13260 (home-page "https://lh3.github.io/minimap2/")
13261 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13262 (description "Minimap2 is a versatile sequence alignment program that
13263 aligns DNA or mRNA sequences against a large reference database. Typical use
13267 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13268 @item finding overlaps between long reads with error rate up to ~15%;
13269 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13270 reads against a reference genome;
13271 @item aligning Illumina single- or paired-end reads;
13272 @item assembly-to-assembly alignment;
13273 @item full-genome alignment between two closely related species with
13274 divergence below ~15%.
13276 (license license:expat)))
13278 (define-public r-loomr
13279 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13283 (version (git-version "0.2.0" revision commit))
13287 (uri (git-reference
13288 (url "https://github.com/mojaveazure/loomR.git")
13290 (file-name (git-file-name name version))
13293 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13294 (build-system r-build-system)
13297 ("r-hdf5r" ,r-hdf5r)
13298 ("r-iterators" ,r-iterators)
13299 ("r-itertools" ,r-itertools)
13300 ("r-matrix" ,r-matrix)))
13301 (home-page "https://github.com/mojaveazure/loomR")
13302 (synopsis "R interface for loom files")
13303 (description "This package provides an R interface to access, create,
13304 and modify loom files. loomR aims to be completely compatible with loompy.")
13305 (license license:gpl3))))