1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
14 ;;; This file is part of GNU Guix.
16 ;;; GNU Guix is free software; you can redistribute it and/or modify it
17 ;;; under the terms of the GNU General Public License as published by
18 ;;; the Free Software Foundation; either version 3 of the License, or (at
19 ;;; your option) any later version.
21 ;;; GNU Guix is distributed in the hope that it will be useful, but
22 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;;; GNU General Public License for more details.
26 ;;; You should have received a copy of the GNU General Public License
27 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
29 (define-module (gnu packages bioinformatics)
30 #:use-module ((guix licenses) #:prefix license:)
31 #:use-module (guix packages)
32 #:use-module (guix utils)
33 #:use-module (guix download)
34 #:use-module (guix git-download)
35 #:use-module (guix hg-download)
36 #:use-module (guix build-system ant)
37 #:use-module (guix build-system gnu)
38 #:use-module (guix build-system cmake)
39 #:use-module (guix build-system ocaml)
40 #:use-module (guix build-system perl)
41 #:use-module (guix build-system python)
42 #:use-module (guix build-system r)
43 #:use-module (guix build-system ruby)
44 #:use-module (guix build-system scons)
45 #:use-module (guix build-system trivial)
46 #:use-module (gnu packages)
47 #:use-module (gnu packages autotools)
48 #:use-module (gnu packages algebra)
49 #:use-module (gnu packages base)
50 #:use-module (gnu packages bash)
51 #:use-module (gnu packages bison)
52 #:use-module (gnu packages boost)
53 #:use-module (gnu packages check)
54 #:use-module (gnu packages compression)
55 #:use-module (gnu packages cpio)
56 #:use-module (gnu packages cran)
57 #:use-module (gnu packages curl)
58 #:use-module (gnu packages documentation)
59 #:use-module (gnu packages databases)
60 #:use-module (gnu packages datastructures)
61 #:use-module (gnu packages file)
62 #:use-module (gnu packages flex)
63 #:use-module (gnu packages gawk)
64 #:use-module (gnu packages gcc)
65 #:use-module (gnu packages gd)
66 #:use-module (gnu packages gtk)
67 #:use-module (gnu packages glib)
68 #:use-module (gnu packages graph)
69 #:use-module (gnu packages groff)
70 #:use-module (gnu packages guile)
71 #:use-module (gnu packages haskell)
72 #:use-module (gnu packages image)
73 #:use-module (gnu packages imagemagick)
74 #:use-module (gnu packages java)
75 #:use-module (gnu packages jemalloc)
76 #:use-module (gnu packages ldc)
77 #:use-module (gnu packages linux)
78 #:use-module (gnu packages logging)
79 #:use-module (gnu packages machine-learning)
80 #:use-module (gnu packages man)
81 #:use-module (gnu packages maths)
82 #:use-module (gnu packages mpi)
83 #:use-module (gnu packages ncurses)
84 #:use-module (gnu packages ocaml)
85 #:use-module (gnu packages pcre)
86 #:use-module (gnu packages parallel)
87 #:use-module (gnu packages pdf)
88 #:use-module (gnu packages perl)
89 #:use-module (gnu packages perl-check)
90 #:use-module (gnu packages pkg-config)
91 #:use-module (gnu packages popt)
92 #:use-module (gnu packages protobuf)
93 #:use-module (gnu packages python)
94 #:use-module (gnu packages python-web)
95 #:use-module (gnu packages readline)
96 #:use-module (gnu packages ruby)
97 #:use-module (gnu packages serialization)
98 #:use-module (gnu packages shells)
99 #:use-module (gnu packages statistics)
100 #:use-module (gnu packages swig)
101 #:use-module (gnu packages tbb)
102 #:use-module (gnu packages tex)
103 #:use-module (gnu packages texinfo)
104 #:use-module (gnu packages textutils)
105 #:use-module (gnu packages time)
106 #:use-module (gnu packages tls)
107 #:use-module (gnu packages vim)
108 #:use-module (gnu packages web)
109 #:use-module (gnu packages xml)
110 #:use-module (gnu packages xorg)
111 #:use-module (srfi srfi-1)
112 #:use-module (ice-9 match))
114 (define-public aragorn
121 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
125 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
126 (build-system gnu-build-system)
128 `(#:tests? #f ; there are no tests
130 (modify-phases %standard-phases
134 (zero? (system* "gcc"
140 (string-append "aragorn" ,version ".c")))))
142 (lambda* (#:key outputs #:allow-other-keys)
143 (let* ((out (assoc-ref outputs "out"))
144 (bin (string-append out "/bin"))
145 (man (string-append out "/share/man/man1")))
147 (install-file "aragorn" bin)
149 (install-file "aragorn.1" man))
151 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
152 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
154 "Aragorn identifies transfer RNA, mitochondrial RNA and
155 transfer-messenger RNA from nucleotide sequences, based on homology to known
156 tRNA consensus sequences and RNA structure. It also outputs the secondary
157 structure of the predicted RNA.")
158 (license license:gpl2)))
166 ;; BamM is not available on pypi.
168 "https://github.com/Ecogenomics/BamM/archive/"
170 (file-name (string-append name "-" version ".tar.gz"))
173 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
174 (modules '((guix build utils)))
177 ;; Delete bundled htslib.
178 (delete-file-recursively "c/htslib-1.3.1")
180 (build-system python-build-system)
182 `(#:python ,python-2 ; BamM is Python 2 only.
183 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
184 ;; been modified from its original form.
186 (let ((htslib (assoc-ref %build-inputs "htslib")))
187 (list "--with-libhts-lib" (string-append htslib "/lib")
188 "--with-libhts-inc" (string-append htslib "/include/htslib")))
190 (modify-phases %standard-phases
191 (add-after 'unpack 'autogen
193 (with-directory-excursion "c"
194 (let ((sh (which "sh")))
195 ;; Use autogen so that 'configure' works.
196 (substitute* "autogen.sh" (("/bin/sh") sh))
197 (setenv "CONFIG_SHELL" sh)
198 (substitute* "configure" (("/bin/sh") sh))
199 (zero? (system* "./autogen.sh"))))))
201 ;; Run tests after installation so compilation only happens once.
203 (add-after 'install 'wrap-executable
204 (lambda* (#:key outputs #:allow-other-keys)
205 (let* ((out (assoc-ref outputs "out"))
206 (path (getenv "PATH")))
207 (wrap-program (string-append out "/bin/bamm")
208 `("PATH" ":" prefix (,path))))
210 (add-after 'wrap-executable 'post-install-check
211 (lambda* (#:key inputs outputs #:allow-other-keys)
213 (string-append (assoc-ref outputs "out")
218 (assoc-ref outputs "out")
220 (string-take (string-take-right
221 (assoc-ref inputs "python") 5) 3)
223 (getenv "PYTHONPATH")))
224 ;; There are 2 errors printed, but they are safe to ignore:
225 ;; 1) [E::hts_open_format] fail to open file ...
226 ;; 2) samtools view: failed to open ...
227 (zero? (system* "nosetests")))))))
229 `(("autoconf" ,autoconf)
230 ("automake" ,automake)
233 ("python-nose" ,python2-nose)
234 ("python-pysam" ,python2-pysam)))
236 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
237 ("samtools" ,samtools)
241 ("coreutils" ,coreutils)))
243 `(("python-numpy" ,python2-numpy)))
244 (home-page "http://ecogenomics.github.io/BamM/")
245 (synopsis "Metagenomics-focused BAM file manipulator")
247 "BamM is a C library, wrapped in python, to efficiently generate and
248 parse BAM files, specifically for the analysis of metagenomic data. For
249 instance, it implements several methods to assess contig-wise read coverage.")
250 (license license:lgpl3+)))
252 (define-public bamtools
259 "https://github.com/pezmaster31/bamtools/archive/v"
261 (file-name (string-append name "-" version ".tar.gz"))
264 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
265 (build-system cmake-build-system)
267 `(#:tests? #f ;no "check" target
269 (modify-phases %standard-phases
271 'configure 'set-ldflags
272 (lambda* (#:key outputs #:allow-other-keys)
276 (assoc-ref outputs "out") "/lib/bamtools")))))))
277 (inputs `(("zlib" ,zlib)))
278 (home-page "https://github.com/pezmaster31/bamtools")
279 (synopsis "C++ API and command-line toolkit for working with BAM data")
281 "BamTools provides both a C++ API and a command-line toolkit for handling
283 (license license:expat)))
285 (define-public bcftools
292 "https://github.com/samtools/bcftools/releases/download/"
293 version "/bcftools-" version ".tar.bz2"))
296 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
297 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
298 (modules '((guix build utils)))
300 ;; Delete bundled htslib.
301 '(delete-file-recursively "htslib-1.5"))))
302 (build-system gnu-build-system)
304 `(#:test-target "test"
305 #:configure-flags (list "--with-htslib=system")
309 "LIBS=-lgsl -lgslcblas"
310 (string-append "prefix=" (assoc-ref %outputs "out"))
311 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
312 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
313 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
314 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
315 (string-append "PACKAGE_VERSION=" ,version))
317 (modify-phases %standard-phases
318 (add-before 'check 'patch-tests
320 (substitute* "test/test.pl"
321 (("/bin/bash") (which "bash")))
329 (home-page "https://samtools.github.io/bcftools/")
330 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
332 "BCFtools is a set of utilities that manipulate variant calls in the
333 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
334 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
335 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
336 (license (list license:gpl3+ license:expat))))
338 (define-public bedops
344 (uri (string-append "https://github.com/bedops/bedops/archive/v"
346 (file-name (string-append name "-" version ".tar.gz"))
349 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
350 (build-system gnu-build-system)
353 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
355 (modify-phases %standard-phases
356 (add-after 'unpack 'unpack-tarballs
358 ;; FIXME: Bedops includes tarballs of minimally patched upstream
359 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
360 ;; libraries because at least one of the libraries (zlib) is
361 ;; patched to add a C++ function definition (deflateInit2cpp).
362 ;; Until the Bedops developers offer a way to link against system
363 ;; libraries we have to build the in-tree copies of these three
366 ;; See upstream discussion:
367 ;; https://github.com/bedops/bedops/issues/124
369 ;; Unpack the tarballs to benefit from shebang patching.
370 (with-directory-excursion "third-party"
371 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
372 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
373 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
374 ;; Disable unpacking of tarballs in Makefile.
375 (substitute* "system.mk/Makefile.linux"
376 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
377 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
378 (substitute* "third-party/zlib-1.2.7/Makefile.in"
379 (("^SHELL=.*$") "SHELL=bash\n"))
381 (delete 'configure))))
382 (home-page "https://github.com/bedops/bedops")
383 (synopsis "Tools for high-performance genomic feature operations")
385 "BEDOPS is a suite of tools to address common questions raised in genomic
386 studies---mostly with regard to overlap and proximity relationships between
387 data sets. It aims to be scalable and flexible, facilitating the efficient
388 and accurate analysis and management of large-scale genomic data.
390 BEDOPS provides tools that perform highly efficient and scalable Boolean and
391 other set operations, statistical calculations, archiving, conversion and
392 other management of genomic data of arbitrary scale. Tasks can be easily
393 split by chromosome for distributing whole-genome analyses across a
394 computational cluster.")
395 (license license:gpl2+)))
397 (define-public bedtools
403 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
404 "download/v" version "/"
405 "bedtools-" version ".tar.gz"))
408 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
409 (build-system gnu-build-system)
411 '(#:test-target "test"
413 (list (string-append "prefix=" (assoc-ref %outputs "out")))
415 (modify-phases %standard-phases
416 (delete 'configure))))
417 (native-inputs `(("python" ,python-2)))
419 `(("samtools" ,samtools)
421 (home-page "https://github.com/arq5x/bedtools2")
422 (synopsis "Tools for genome analysis and arithmetic")
424 "Collectively, the bedtools utilities are a swiss-army knife of tools for
425 a wide-range of genomics analysis tasks. The most widely-used tools enable
426 genome arithmetic: that is, set theory on the genome. For example, bedtools
427 allows one to intersect, merge, count, complement, and shuffle genomic
428 intervals from multiple files in widely-used genomic file formats such as BAM,
430 (license license:gpl2)))
432 ;; Later releases of bedtools produce files with more columns than
433 ;; what Ribotaper expects.
434 (define-public bedtools-2.18
435 (package (inherit bedtools)
440 (uri (string-append "https://github.com/arq5x/bedtools2/"
441 "archive/v" version ".tar.gz"))
442 (file-name (string-append name "-" version ".tar.gz"))
445 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
447 '(#:test-target "test"
449 (modify-phases %standard-phases
452 (lambda* (#:key outputs #:allow-other-keys)
453 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
454 (for-each (lambda (file)
455 (install-file file bin))
456 (find-files "bin" ".*")))
459 (define-public ribotaper
465 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
466 "files/RiboTaper/RiboTaper_Version_"
470 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
471 (build-system gnu-build-system)
474 (modify-phases %standard-phases
475 (add-after 'install 'wrap-executables
476 (lambda* (#:key inputs outputs #:allow-other-keys)
477 (let* ((out (assoc-ref outputs "out")))
480 (wrap-program (string-append out "/bin/" script)
481 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
482 '("create_annotations_files.bash"
483 "create_metaplots.bash"
484 "Ribotaper_ORF_find.sh"
485 "Ribotaper.sh"))))))))
487 `(("bedtools" ,bedtools-2.18)
488 ("samtools" ,samtools-0.1)
489 ("r-minimal" ,r-minimal)
490 ("r-foreach" ,r-foreach)
491 ("r-xnomial" ,r-xnomial)
493 ("r-multitaper" ,r-multitaper)
494 ("r-seqinr" ,r-seqinr)))
495 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
496 (synopsis "Define translated ORFs using ribosome profiling data")
498 "Ribotaper is a method for defining translated @dfn{open reading
499 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
500 provides the Ribotaper pipeline.")
501 (license license:gpl3+)))
503 (define-public ribodiff
510 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
511 "archive/v" version ".tar.gz"))
512 (file-name (string-append name "-" version ".tar.gz"))
515 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
516 (build-system python-build-system)
520 (modify-phases %standard-phases
521 ;; Generate an installable executable script wrapper.
522 (add-after 'unpack 'patch-setup.py
524 (substitute* "setup.py"
525 (("^(.*)packages=.*" line prefix)
526 (string-append line "\n"
527 prefix "scripts=['scripts/TE.py'],\n")))
530 `(("python-numpy" ,python2-numpy)
531 ("python-matplotlib" ,python2-matplotlib)
532 ("python-scipy" ,python2-scipy)
533 ("python-statsmodels" ,python2-statsmodels)))
535 `(("python-mock" ,python2-mock)
536 ("python-nose" ,python2-nose)))
537 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
538 (synopsis "Detect translation efficiency changes from ribosome footprints")
539 (description "RiboDiff is a statistical tool that detects the protein
540 translational efficiency change from Ribo-Seq (ribosome footprinting) and
541 RNA-Seq data. It uses a generalized linear model to detect genes showing
542 difference in translational profile taking mRNA abundance into account. It
543 facilitates us to decipher the translational regulation that behave
544 independently with transcriptional regulation.")
545 (license license:gpl3+)))
547 (define-public bioawk
553 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
555 (file-name (string-append name "-" version ".tar.gz"))
557 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
558 (build-system gnu-build-system)
564 `(#:tests? #f ; There are no tests to run.
565 ;; Bison must generate files, before other targets can build.
568 (modify-phases %standard-phases
569 (delete 'configure) ; There is no configure phase.
571 (lambda* (#:key outputs #:allow-other-keys)
572 (let* ((out (assoc-ref outputs "out"))
573 (bin (string-append out "/bin"))
574 (man (string-append out "/share/man/man1")))
576 (copy-file "awk.1" (string-append man "/bioawk.1"))
577 (install-file "bioawk" bin)))))))
578 (home-page "https://github.com/lh3/bioawk")
579 (synopsis "AWK with bioinformatics extensions")
580 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
581 support of several common biological data formats, including optionally gzip'ed
582 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
583 also adds a few built-in functions and a command line option to use TAB as the
584 input/output delimiter. When the new functionality is not used, bioawk is
585 intended to behave exactly the same as the original BWK awk.")
586 (license license:x11)))
588 (define-public python2-pybedtools
590 (name "python2-pybedtools")
595 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
599 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
600 (build-system python-build-system)
601 (arguments `(#:python ,python-2)) ; no Python 3 support
603 `(("python-matplotlib" ,python2-matplotlib)))
605 `(("bedtools" ,bedtools)
606 ("samtools" ,samtools)))
608 `(("python-cython" ,python2-cython)
609 ("python-pyyaml" ,python2-pyyaml)
610 ("python-nose" ,python2-nose)))
611 (home-page "https://pythonhosted.org/pybedtools/")
612 (synopsis "Python wrapper for BEDtools programs")
614 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
615 which are widely used for genomic interval manipulation or \"genome algebra\".
616 pybedtools extends BEDTools by offering feature-level manipulations from with
618 (license license:gpl2+)))
620 (define-public python-biom-format
622 (name "python-biom-format")
627 ;; Use GitHub as source because PyPI distribution does not contain
628 ;; test data: https://github.com/biocore/biom-format/issues/693
629 (uri (string-append "https://github.com/biocore/biom-format/archive/"
631 (file-name (string-append name "-" version ".tar.gz"))
634 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
635 (build-system python-build-system)
637 `(("python-numpy" ,python-numpy)
638 ("python-scipy" ,python-scipy)
639 ("python-future" ,python-future)
640 ("python-click" ,python-click)
641 ("python-h5py" ,python-h5py)
642 ("python-pandas" ,python-pandas)))
644 `(("python-nose" ,python-nose)))
645 (home-page "http://www.biom-format.org")
646 (synopsis "Biological Observation Matrix (BIOM) format utilities")
648 "The BIOM file format is designed to be a general-use format for
649 representing counts of observations e.g. operational taxonomic units, KEGG
650 orthology groups or lipid types, in one or more biological samples
651 e.g. microbiome samples, genomes, metagenomes.")
652 (license license:bsd-3)
653 (properties `((python2-variant . ,(delay python2-biom-format))))))
655 (define-public python2-biom-format
656 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
661 (modify-phases %standard-phases
662 ;; Do not require the unmaintained pyqi library.
663 (add-after 'unpack 'remove-pyqi
665 (substitute* "setup.py"
666 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
668 ,@(package-arguments base))))))
670 (define-public bioperl-minimal
671 (let* ((inputs `(("perl-module-build" ,perl-module-build)
672 ("perl-data-stag" ,perl-data-stag)
673 ("perl-libwww" ,perl-libwww)
674 ("perl-uri" ,perl-uri)))
676 (map (compose package-name cadr)
679 (map (compose package-transitive-target-inputs cadr) inputs))))))
681 (name "bioperl-minimal")
686 (uri (string-append "https://github.com/bioperl/bioperl-live/"
688 (string-map (lambda (c)
694 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
695 (build-system perl-build-system)
698 (modify-phases %standard-phases
700 'install 'wrap-programs
701 (lambda* (#:key outputs #:allow-other-keys)
702 ;; Make sure all executables in "bin" find the required Perl
703 ;; modules at runtime. As the PERL5LIB variable contains also
704 ;; the paths of native inputs, we pick the transitive target
705 ;; inputs from %build-inputs.
706 (let* ((out (assoc-ref outputs "out"))
707 (bin (string-append out "/bin/"))
709 (cons (string-append out "/lib/perl5/site_perl")
711 (assoc-ref %build-inputs name))
712 ',transitive-inputs))
714 (for-each (lambda (file)
716 `("PERL5LIB" ":" prefix (,path))))
717 (find-files bin "\\.pl$"))
721 `(("perl-test-most" ,perl-test-most)))
722 (home-page "http://search.cpan.org/dist/BioPerl")
723 (synopsis "Bioinformatics toolkit")
725 "BioPerl is the product of a community effort to produce Perl code which
726 is useful in biology. Examples include Sequence objects, Alignment objects
727 and database searching objects. These objects not only do what they are
728 advertised to do in the documentation, but they also interact - Alignment
729 objects are made from the Sequence objects, Sequence objects have access to
730 Annotation and SeqFeature objects and databases, Blast objects can be
731 converted to Alignment objects, and so on. This means that the objects
732 provide a coordinated and extensible framework to do computational biology.")
733 (license license:perl-license))))
735 (define-public python-biopython
737 (name "python-biopython")
741 ;; use PyPi rather than biopython.org to ease updating
742 (uri (pypi-uri "biopython" version))
745 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
746 (build-system python-build-system)
749 (modify-phases %standard-phases
750 (add-before 'check 'set-home
751 ;; Some tests require a home directory to be set.
752 (lambda _ (setenv "HOME" "/tmp") #t)))))
754 `(("python-numpy" ,python-numpy)))
755 (home-page "http://biopython.org/")
756 (synopsis "Tools for biological computation in Python")
758 "Biopython is a set of tools for biological computation including parsers
759 for bioinformatics files into Python data structures; interfaces to common
760 bioinformatics programs; a standard sequence class and tools for performing
761 common operations on them; code to perform data classification; code for
762 dealing with alignments; code making it easy to split up parallelizable tasks
763 into separate processes; and more.")
764 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
766 (define-public python2-biopython
767 (package-with-python2 python-biopython))
769 (define-public bpp-core
770 ;; The last release was in 2014 and the recommended way to install from source
771 ;; is to clone the git repository, so we do this.
772 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
773 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
776 (version (string-append "2.2.0-1." (string-take commit 7)))
780 (url "http://biopp.univ-montp2.fr/git/bpp-core")
782 (file-name (string-append name "-" version "-checkout"))
785 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
786 (build-system cmake-build-system)
788 `(#:parallel-build? #f))
790 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
791 ; compile all of the bpp packages with GCC 5.
792 (home-page "http://biopp.univ-montp2.fr")
793 (synopsis "C++ libraries for Bioinformatics")
795 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
796 analysis, phylogenetics, molecular evolution and population genetics. It is
797 Object Oriented and is designed to be both easy to use and computer efficient.
798 Bio++ intends to help programmers to write computer expensive programs, by
799 providing them a set of re-usable tools.")
800 (license license:cecill-c))))
802 (define-public bpp-phyl
803 ;; The last release was in 2014 and the recommended way to install from source
804 ;; is to clone the git repository, so we do this.
805 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
806 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
809 (version (string-append "2.2.0-1." (string-take commit 7)))
813 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
815 (file-name (string-append name "-" version "-checkout"))
818 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
819 (build-system cmake-build-system)
821 `(#:parallel-build? #f
822 ;; If out-of-source, test data is not copied into the build directory
823 ;; so the tests fail.
824 #:out-of-source? #f))
826 `(("bpp-core" ,bpp-core)
828 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
831 (home-page "http://biopp.univ-montp2.fr")
832 (synopsis "Bio++ phylogenetic Library")
834 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
835 analysis, phylogenetics, molecular evolution and population genetics. This
836 library provides phylogenetics-related modules.")
837 (license license:cecill-c))))
839 (define-public bpp-popgen
840 ;; The last release was in 2014 and the recommended way to install from source
841 ;; is to clone the git repository, so we do this.
842 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
843 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
846 (version (string-append "2.2.0-1." (string-take commit 7)))
850 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
852 (file-name (string-append name "-" version "-checkout"))
855 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
856 (build-system cmake-build-system)
858 `(#:parallel-build? #f
859 #:tests? #f)) ; There are no tests.
861 `(("bpp-core" ,bpp-core)
864 (home-page "http://biopp.univ-montp2.fr")
865 (synopsis "Bio++ population genetics library")
867 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
868 analysis, phylogenetics, molecular evolution and population genetics. This
869 library provides population genetics-related modules.")
870 (license license:cecill-c))))
872 (define-public bpp-seq
873 ;; The last release was in 2014 and the recommended way to install from source
874 ;; is to clone the git repository, so we do this.
875 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
876 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
879 (version (string-append "2.2.0-1." (string-take commit 7)))
883 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
885 (file-name (string-append name "-" version "-checkout"))
888 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
889 (build-system cmake-build-system)
891 `(#:parallel-build? #f
892 ;; If out-of-source, test data is not copied into the build directory
893 ;; so the tests fail.
894 #:out-of-source? #f))
896 `(("bpp-core" ,bpp-core)
897 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
898 (home-page "http://biopp.univ-montp2.fr")
899 (synopsis "Bio++ sequence library")
901 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
902 analysis, phylogenetics, molecular evolution and population genetics. This
903 library provides sequence-related modules.")
904 (license license:cecill-c))))
906 (define-public bppsuite
907 ;; The last release was in 2014 and the recommended way to install from source
908 ;; is to clone the git repository, so we do this.
909 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
910 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
913 (version (string-append "2.2.0-1." (string-take commit 7)))
917 (url "http://biopp.univ-montp2.fr/git/bppsuite")
919 (file-name (string-append name "-" version "-checkout"))
922 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
923 (build-system cmake-build-system)
925 `(#:parallel-build? #f
926 #:tests? #f)) ; There are no tests.
930 ("texinfo" ,texinfo)))
932 `(("bpp-core" ,bpp-core)
934 ("bpp-phyl" ,bpp-phyl)
935 ("bpp-phyl" ,bpp-popgen)
937 (home-page "http://biopp.univ-montp2.fr")
938 (synopsis "Bioinformatics tools written with the Bio++ libraries")
940 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
941 analysis, phylogenetics, molecular evolution and population genetics. This
942 package provides command line tools using the Bio++ library.")
943 (license license:cecill-c))))
945 (define-public blast+
952 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
953 version "/ncbi-blast-" version "+-src.tar.gz"))
956 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
957 (patches (search-patches "blast+-fix-makefile.patch"))
958 (modules '((guix build utils)))
961 ;; Remove bundled bzip2, zlib and pcre.
962 (delete-file-recursively "c++/src/util/compress/bzip2")
963 (delete-file-recursively "c++/src/util/compress/zlib")
964 (delete-file-recursively "c++/src/util/regexp")
965 (substitute* "c++/src/util/compress/Makefile.in"
966 (("bzip2 zlib api") "api"))
967 ;; Remove useless msbuild directory
968 (delete-file-recursively
969 "c++/src/build-system/project_tree_builder/msbuild")
971 (build-system gnu-build-system)
973 `(;; There are two(!) tests for this massive library, and both fail with
974 ;; "unparsable timing stats".
975 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
976 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
979 #:parallel-build? #f ; not supported
981 (modify-phases %standard-phases
984 ;; $HOME needs to be set at some point during the configure phase
985 (lambda _ (setenv "HOME" "/tmp") #t))
988 (lambda _ (chdir "c++") #t))
990 'enter-dir 'fix-build-system
993 (cond ((string=? cmd "date")
994 ;; make call to "date" deterministic
999 (format (current-error-port)
1000 "WARNING: Unable to find absolute path for ~s~%"
1004 ;; Rewrite hardcoded paths to various tools
1005 (substitute* (append '("src/build-system/configure.ac"
1006 "src/build-system/configure"
1007 "src/build-system/helpers/run_with_lock.c"
1008 "scripts/common/impl/if_diff.sh"
1009 "scripts/common/impl/run_with_lock.sh"
1010 "src/build-system/Makefile.configurables.real"
1011 "src/build-system/Makefile.in.top"
1012 "src/build-system/Makefile.meta.gmake=no"
1013 "src/build-system/Makefile.meta.in"
1014 "src/build-system/Makefile.meta_l"
1015 "src/build-system/Makefile.meta_p"
1016 "src/build-system/Makefile.meta_r"
1017 "src/build-system/Makefile.mk.in"
1018 "src/build-system/Makefile.requirements"
1019 "src/build-system/Makefile.rules_with_autodep.in")
1020 (find-files "scripts/common/check" "\\.sh$"))
1021 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1022 (or (which* cmd) all)))
1024 (substitute* (find-files "src/build-system" "^config.*")
1025 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1028 ;; rewrite "/var/tmp" in check script
1029 (substitute* "scripts/common/check/check_make_unix.sh"
1030 (("/var/tmp") "/tmp"))
1032 ;; do not reset PATH
1033 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1035 (("action=/bin/") "action=")
1036 (("export PATH") ":"))
1040 (lambda* (#:key inputs outputs #:allow-other-keys)
1041 (let ((out (assoc-ref outputs "out"))
1042 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1043 (include (string-append (assoc-ref outputs "include")
1044 "/include/ncbi-tools++")))
1045 ;; The 'configure' script doesn't recognize things like
1046 ;; '--enable-fast-install'.
1047 (zero? (system* "./configure.orig"
1048 (string-append "--with-build-root=" (getcwd) "/build")
1049 (string-append "--prefix=" out)
1050 (string-append "--libdir=" lib)
1051 (string-append "--includedir=" include)
1052 (string-append "--with-bz2="
1053 (assoc-ref inputs "bzip2"))
1054 (string-append "--with-z="
1055 (assoc-ref inputs "zlib"))
1056 (string-append "--with-pcre="
1057 (assoc-ref inputs "pcre"))
1058 ;; Each library is built twice by default, once
1059 ;; with "-static" in its name, and again
1062 "--with-dll"))))))))
1063 (outputs '("out" ; 21 MB
1071 ("python" ,python-wrapper)))
1074 (home-page "http://blast.ncbi.nlm.nih.gov")
1075 (synopsis "Basic local alignment search tool")
1077 "BLAST is a popular method of performing a DNA or protein sequence
1078 similarity search, using heuristics to produce results quickly. It also
1079 calculates an “expect value” that estimates how many matches would have
1080 occurred at a given score by chance, which can aid a user in judging how much
1081 confidence to have in an alignment.")
1082 ;; Most of the sources are in the public domain, with the following
1085 ;; * ./c++/include/util/bitset/
1086 ;; * ./c++/src/html/ncbi_menu*.js
1088 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1090 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1092 ;; * ./c++/src/corelib/teamcity_*
1093 (license (list license:public-domain
1099 (define-public bless
1105 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1109 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1110 (modules '((guix build utils)))
1113 ;; Remove bundled boost, pigz, zlib, and .git directory
1114 ;; FIXME: also remove bundled sources for murmurhash3 and
1115 ;; kmc once packaged.
1116 (delete-file-recursively "boost")
1117 (delete-file-recursively "pigz")
1118 (delete-file-recursively "google-sparsehash")
1119 (delete-file-recursively "zlib")
1120 (delete-file-recursively ".git")
1122 (build-system gnu-build-system)
1124 '(#:tests? #f ;no "check" target
1126 (list (string-append "ZLIB="
1127 (assoc-ref %build-inputs "zlib")
1129 (string-append "LDFLAGS="
1130 (string-join '("-lboost_filesystem"
1137 (modify-phases %standard-phases
1138 (add-after 'unpack 'do-not-build-bundled-pigz
1139 (lambda* (#:key inputs outputs #:allow-other-keys)
1140 (substitute* "Makefile"
1141 (("cd pigz/pigz-2.3.3; make") ""))
1143 (add-after 'unpack 'patch-paths-to-executables
1144 (lambda* (#:key inputs outputs #:allow-other-keys)
1145 (substitute* "parse_args.cpp"
1146 (("kmc_binary = .*")
1147 (string-append "kmc_binary = \""
1148 (assoc-ref outputs "out")
1150 (("pigz_binary = .*")
1151 (string-append "pigz_binary = \""
1152 (assoc-ref inputs "pigz")
1156 (lambda* (#:key outputs #:allow-other-keys)
1157 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1158 (for-each (lambda (file)
1159 (install-file file bin))
1160 '("bless" "kmc/bin/kmc"))
1162 (delete 'configure))))
1166 `(("openmpi" ,openmpi)
1168 ("sparsehash" ,sparsehash)
1171 (supported-systems '("x86_64-linux"))
1172 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1173 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1175 "@dfn{Bloom-filter-based error correction solution for high-throughput
1176 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1177 correction tool for genomic reads produced by @dfn{Next-generation
1178 sequencing} (NGS). BLESS produces accurate correction results with much less
1179 memory compared with previous solutions and is also able to tolerate a higher
1180 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1181 errors at the end of reads.")
1182 (license license:gpl3+)))
1184 (define-public bowtie
1190 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1192 (file-name (string-append name "-" version ".tar.gz"))
1195 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1196 (modules '((guix build utils)))
1198 '(substitute* "Makefile"
1199 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1200 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1201 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1202 (build-system gnu-build-system)
1205 ("perl-clone" ,perl-clone)
1206 ("perl-test-deep" ,perl-test-deep)
1207 ("perl-test-simple" ,perl-test-simple)
1208 ("python" ,python-2)
1215 (string-append "prefix=" (assoc-ref %outputs "out")))
1217 (modify-phases %standard-phases
1220 (lambda* (#:key outputs #:allow-other-keys)
1221 (zero? (system* "perl"
1222 "scripts/test/simple_tests.pl"
1223 "--bowtie2=./bowtie2"
1224 "--bowtie2-build=./bowtie2-build")))))))
1225 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1226 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1228 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1229 reads to long reference sequences. It is particularly good at aligning reads
1230 of about 50 up to 100s or 1,000s of characters, and particularly good at
1231 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1232 genome with an FM Index to keep its memory footprint small: for the human
1233 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1234 gapped, local, and paired-end alignment modes.")
1235 (supported-systems '("x86_64-linux"))
1236 (license license:gpl3+)))
1238 (define-public tophat
1245 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1249 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1250 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1251 (modules '((guix build utils)))
1254 ;; Remove bundled SeqAn and samtools
1255 (delete-file-recursively "src/SeqAn-1.3")
1256 (delete-file-recursively "src/samtools-0.1.18")
1258 (build-system gnu-build-system)
1260 '(#:parallel-build? #f ; not supported
1262 (modify-phases %standard-phases
1263 (add-after 'unpack 'use-system-samtools
1264 (lambda* (#:key inputs #:allow-other-keys)
1265 (substitute* "src/Makefile.in"
1266 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1267 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1268 (("SAMPROG = samtools_0\\.1\\.18") "")
1269 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1270 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1271 (substitute* '("src/common.cpp"
1273 (("samtools_0.1.18") (which "samtools")))
1274 (substitute* '("src/common.h"
1275 "src/bam2fastx.cpp")
1276 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1277 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1278 (substitute* '("src/bwt_map.h"
1280 "src/align_status.h")
1281 (("#include <bam.h>") "#include <samtools/bam.h>")
1282 (("#include <sam.h>") "#include <samtools/sam.h>"))
1287 ("samtools" ,samtools-0.1)
1288 ("ncurses" ,ncurses)
1289 ("python" ,python-2)
1293 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1294 (synopsis "Spliced read mapper for RNA-Seq data")
1296 "TopHat is a fast splice junction mapper for nucleotide sequence
1297 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1298 mammalian-sized genomes using the ultra high-throughput short read
1299 aligner Bowtie, and then analyzes the mapping results to identify
1300 splice junctions between exons.")
1301 ;; TopHat is released under the Boost Software License, Version 1.0
1302 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1303 (license license:boost1.0)))
1312 "https://github.com/lh3/bwa/releases/download/v"
1313 version "/bwa-" version ".tar.bz2"))
1316 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1317 (build-system gnu-build-system)
1319 '(#:tests? #f ;no "check" target
1321 (modify-phases %standard-phases
1323 (lambda* (#:key outputs #:allow-other-keys)
1324 (let ((bin (string-append
1325 (assoc-ref outputs "out") "/bin"))
1327 (assoc-ref outputs "out") "/share/doc/bwa"))
1329 (assoc-ref outputs "out") "/share/man/man1")))
1330 (install-file "bwa" bin)
1331 (install-file "README.md" doc)
1332 (install-file "bwa.1" man))
1334 ;; no "configure" script
1335 (delete 'configure))))
1336 (inputs `(("zlib" ,zlib)))
1337 ;; Non-portable SSE instructions are used so building fails on platforms
1338 ;; other than x86_64.
1339 (supported-systems '("x86_64-linux"))
1340 (home-page "http://bio-bwa.sourceforge.net/")
1341 (synopsis "Burrows-Wheeler sequence aligner")
1343 "BWA is a software package for mapping low-divergent sequences against a
1344 large reference genome, such as the human genome. It consists of three
1345 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1346 designed for Illumina sequence reads up to 100bp, while the rest two for
1347 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1348 features such as long-read support and split alignment, but BWA-MEM, which is
1349 the latest, is generally recommended for high-quality queries as it is faster
1350 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1351 70-100bp Illumina reads.")
1352 (license license:gpl3+)))
1354 (define-public bwa-pssm
1355 (package (inherit bwa)
1360 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1361 "archive/" version ".tar.gz"))
1362 (file-name (string-append name "-" version ".tar.gz"))
1365 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1366 (build-system gnu-build-system)
1371 (home-page "http://bwa-pssm.binf.ku.dk/")
1372 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1374 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1375 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1376 existing aligners it is fast and sensitive. Unlike most other aligners,
1377 however, it is also adaptible in the sense that one can direct the alignment
1378 based on known biases within the data set. It is coded as a modification of
1379 the original BWA alignment program and shares the genome index structure as
1380 well as many of the command line options.")
1381 (license license:gpl3+)))
1383 (define-public python2-bx-python
1385 (name "python2-bx-python")
1389 (uri (pypi-uri "bx-python" version))
1392 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1393 (modules '((guix build utils)))
1395 '(substitute* "setup.py"
1396 ;; remove dependency on outdated "distribute" module
1397 (("^from distribute_setup import use_setuptools") "")
1398 (("^use_setuptools\\(\\)") "")))))
1399 (build-system python-build-system)
1401 `(#:tests? #f ;tests fail because test data are not included
1402 #:python ,python-2))
1404 `(("python-numpy" ,python2-numpy)
1407 `(("python-nose" ,python2-nose)))
1408 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1409 (synopsis "Tools for manipulating biological data")
1411 "bx-python provides tools for manipulating biological data, particularly
1412 multiple sequence alignments.")
1413 (license license:expat)))
1415 (define-public python-pysam
1417 (name "python-pysam")
1421 ;; Test data is missing on PyPi.
1423 "https://github.com/pysam-developers/pysam/archive/v"
1425 (file-name (string-append name "-" version ".tar.gz"))
1428 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1429 (modules '((guix build utils)))
1431 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1432 '(delete-file-recursively "htslib"))))
1433 (build-system python-build-system)
1435 `(#:modules ((ice-9 ftw)
1437 (guix build python-build-system)
1440 (modify-phases %standard-phases
1441 (add-before 'build 'set-flags
1442 (lambda* (#:key inputs #:allow-other-keys)
1443 (setenv "HTSLIB_MODE" "external")
1444 (setenv "HTSLIB_LIBRARY_DIR"
1445 (string-append (assoc-ref inputs "htslib") "/lib"))
1446 (setenv "HTSLIB_INCLUDE_DIR"
1447 (string-append (assoc-ref inputs "htslib") "/include"))
1448 (setenv "LDFLAGS" "-lncurses")
1449 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1452 (lambda* (#:key inputs outputs #:allow-other-keys)
1453 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1454 (setenv "PYTHONPATH"
1456 (getenv "PYTHONPATH")
1457 ":" (getcwd) "/build/"
1458 (car (scandir "build"
1459 (negate (cut string-prefix? "." <>))))))
1460 ;; Step out of source dir so python does not import from CWD.
1461 (with-directory-excursion "tests"
1462 (setenv "HOME" "/tmp")
1463 (and (zero? (system* "make" "-C" "pysam_data"))
1464 (zero? (system* "make" "-C" "cbcf_data"))
1465 ;; Running nosetests without explicitly asking for a
1466 ;; single process leads to a crash. Running with multiple
1467 ;; processes fails because the tests are not designed to
1470 ;; FIXME: tests keep timing out on some systems.
1471 ;; (zero? (system* "nosetests" "-v"
1472 ;; "--processes" "1"))
1475 `(("htslib" ,htslib))) ; Included from installed header files.
1477 `(("ncurses" ,ncurses)
1480 `(("python-cython" ,python-cython)
1481 ;; Dependencies below are are for tests only.
1482 ("samtools" ,samtools)
1483 ("bcftools" ,bcftools)
1484 ("python-nose" ,python-nose)))
1485 (home-page "https://github.com/pysam-developers/pysam")
1486 (synopsis "Python bindings to the SAMtools C API")
1488 "Pysam is a Python module for reading and manipulating files in the
1489 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1490 also includes an interface for tabix.")
1491 (license license:expat)))
1493 (define-public python2-pysam
1494 (package-with-python2 python-pysam))
1496 (define-public python-twobitreader
1498 (name "python-twobitreader")
1502 (uri (pypi-uri "twobitreader" version))
1505 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1506 (build-system python-build-system)
1508 '(;; Tests are not distributed in the PyPi release.
1509 ;; TODO Try building from the Git repo or asking the upstream maintainer
1510 ;; to distribute the tests on PyPi.
1513 `(("python-sphinx" ,python-sphinx)))
1514 (home-page "https://github.com/benjschiller/twobitreader")
1515 (synopsis "Python library for reading .2bit files")
1517 "twobitreader is a Python library for reading .2bit files as used by the
1518 UCSC genome browser.")
1519 (license license:artistic2.0)))
1521 (define-public python2-twobitreader
1522 (package-with-python2 python-twobitreader))
1524 (define-public python-plastid
1526 (name "python-plastid")
1530 (uri (pypi-uri "plastid" version))
1533 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1534 (build-system python-build-system)
1536 ;; Some test files are not included.
1539 `(("python-numpy" ,python-numpy)
1540 ("python-scipy" ,python-scipy)
1541 ("python-pandas" ,python-pandas)
1542 ("python-pysam" ,python-pysam)
1543 ("python-matplotlib" ,python-matplotlib)
1544 ("python-biopython" ,python-biopython)
1545 ("python-twobitreader" ,python-twobitreader)
1546 ("python-termcolor" ,python-termcolor)))
1548 `(("python-cython" ,python-cython)
1549 ("python-nose" ,python-nose)))
1550 (home-page "https://github.com/joshuagryphon/plastid")
1551 (synopsis "Python library for genomic analysis")
1553 "plastid is a Python library for genomic analysis – in particular,
1554 high-throughput sequencing data – with an emphasis on simplicity.")
1555 (license license:bsd-3)))
1557 (define-public python2-plastid
1558 (package-with-python2 python-plastid))
1560 (define-public cd-hit
1566 (uri (string-append "https://github.com/weizhongli/cdhit"
1567 "/releases/download/V" version
1569 "-2017-0621-source.tar.gz"))
1572 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1573 (build-system gnu-build-system)
1575 `(#:tests? #f ; there are no tests
1577 ;; Executables are copied directly to the PREFIX.
1578 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1580 (modify-phases %standard-phases
1581 ;; No "configure" script
1583 ;; Remove sources of non-determinism
1584 (add-after 'unpack 'be-timeless
1586 (substitute* "cdhit-utility.c++"
1587 ((" \\(built on \" __DATE__ \"\\)") ""))
1588 (substitute* "cdhit-common.c++"
1589 (("__DATE__") "\"0\"")
1590 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1592 ;; The "install" target does not create the target directory.
1593 (add-before 'install 'create-target-dir
1594 (lambda* (#:key outputs #:allow-other-keys)
1595 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1599 (home-page "http://weizhongli-lab.org/cd-hit/")
1600 (synopsis "Cluster and compare protein or nucleotide sequences")
1602 "CD-HIT is a program for clustering and comparing protein or nucleotide
1603 sequences. CD-HIT is designed to be fast and handle extremely large
1605 ;; The manual says: "It can be copied under the GNU General Public License
1606 ;; version 2 (GPLv2)."
1607 (license license:gpl2)))
1609 (define-public clipper
1616 "https://github.com/YeoLab/clipper/archive/"
1618 (file-name (string-append name "-" version ".tar.gz"))
1621 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1622 (modules '((guix build utils)))
1625 ;; remove unnecessary setup dependency
1626 (substitute* "setup.py"
1627 (("setup_requires = .*") ""))
1628 (for-each delete-file
1629 '("clipper/src/peaks.so"
1630 "clipper/src/readsToWiggle.so"))
1631 (delete-file-recursively "dist/")
1633 (build-system python-build-system)
1634 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1636 `(("htseq" ,python2-htseq)
1637 ("python-pybedtools" ,python2-pybedtools)
1638 ("python-cython" ,python2-cython)
1639 ("python-scikit-learn" ,python2-scikit-learn)
1640 ("python-matplotlib" ,python2-matplotlib)
1641 ("python-pandas" ,python2-pandas)
1642 ("python-pysam" ,python2-pysam)
1643 ("python-numpy" ,python2-numpy)
1644 ("python-scipy" ,python2-scipy)))
1646 `(("python-mock" ,python2-mock) ; for tests
1647 ("python-nose" ,python2-nose) ; for tests
1648 ("python-pytz" ,python2-pytz))) ; for tests
1649 (home-page "https://github.com/YeoLab/clipper")
1650 (synopsis "CLIP peak enrichment recognition")
1652 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1653 (license license:gpl2)))
1655 (define-public codingquarry
1657 (name "codingquarry")
1662 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1666 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1667 (build-system gnu-build-system)
1669 '(#:tests? #f ; no "check" target
1671 (modify-phases %standard-phases
1674 (lambda* (#:key outputs #:allow-other-keys)
1675 (let* ((out (assoc-ref outputs "out"))
1676 (bin (string-append out "/bin"))
1677 (doc (string-append out "/share/doc/codingquarry")))
1678 (install-file "INSTRUCTIONS.pdf" doc)
1679 (copy-recursively "QuarryFiles"
1680 (string-append out "/QuarryFiles"))
1681 (install-file "CodingQuarry" bin)
1682 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1683 (inputs `(("openmpi" ,openmpi)))
1684 (native-search-paths
1685 (list (search-path-specification
1686 (variable "QUARRY_PATH")
1687 (files '("QuarryFiles")))))
1688 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1689 (synopsis "Fungal gene predictor")
1690 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1691 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1692 (home-page "https://sourceforge.net/projects/codingquarry/")
1693 (license license:gpl3+)))
1695 (define-public couger
1702 "http://couger.oit.duke.edu/static/assets/COUGER"
1706 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1707 (build-system gnu-build-system)
1711 (modify-phases %standard-phases
1716 (lambda* (#:key outputs #:allow-other-keys)
1717 (let* ((out (assoc-ref outputs "out"))
1718 (bin (string-append out "/bin")))
1719 (copy-recursively "src" (string-append out "/src"))
1721 ;; Add "src" directory to module lookup path.
1722 (substitute* "couger"
1724 (string-append "import sys\nsys.path.append(\""
1725 out "\")\nfrom argparse")))
1726 (install-file "couger" bin))
1729 'install 'wrap-program
1730 (lambda* (#:key inputs outputs #:allow-other-keys)
1731 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1732 (let* ((out (assoc-ref outputs "out"))
1733 (path (getenv "PYTHONPATH")))
1734 (wrap-program (string-append out "/bin/couger")
1735 `("PYTHONPATH" ":" prefix (,path))))
1738 `(("python" ,python-2)
1739 ("python2-pillow" ,python2-pillow)
1740 ("python2-numpy" ,python2-numpy)
1741 ("python2-scipy" ,python2-scipy)
1742 ("python2-matplotlib" ,python2-matplotlib)))
1744 `(("r-minimal" ,r-minimal)
1746 ("randomjungle" ,randomjungle)))
1748 `(("unzip" ,unzip)))
1749 (home-page "http://couger.oit.duke.edu")
1750 (synopsis "Identify co-factors in sets of genomic regions")
1752 "COUGER can be applied to any two sets of genomic regions bound by
1753 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1754 putative co-factors that provide specificity to each TF. The framework
1755 determines the genomic targets uniquely-bound by each TF, and identifies a
1756 small set of co-factors that best explain the in vivo binding differences
1757 between the two TFs.
1759 COUGER uses classification algorithms (support vector machines and random
1760 forests) with features that reflect the DNA binding specificities of putative
1761 co-factors. The features are generated either from high-throughput TF-DNA
1762 binding data (from protein binding microarray experiments), or from large
1763 collections of DNA motifs.")
1764 (license license:gpl3+)))
1766 (define-public clustal-omega
1768 (name "clustal-omega")
1772 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1776 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1777 (build-system gnu-build-system)
1779 `(("argtable" ,argtable)))
1780 (home-page "http://www.clustal.org/omega/")
1781 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1783 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1784 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1785 of handling data-sets of hundreds of thousands of sequences in reasonable
1787 (license license:gpl2+)))
1789 (define-public crossmap
1795 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1799 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1800 ;; This patch has been sent upstream already and is available
1801 ;; for download from Sourceforge, but it has not been merged.
1802 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1803 (modules '((guix build utils)))
1804 ;; remove bundled copy of pysam
1806 '(delete-file-recursively "lib/pysam"))))
1807 (build-system python-build-system)
1809 `(#:python ,python-2
1811 (modify-phases %standard-phases
1812 (add-after 'unpack 'set-env
1813 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1815 `(("python-numpy" ,python2-numpy)
1816 ("python-pysam" ,python2-pysam)
1819 `(("python-cython" ,python2-cython)
1820 ("python-nose" ,python2-nose)))
1821 (home-page "http://crossmap.sourceforge.net/")
1822 (synopsis "Convert genome coordinates between assemblies")
1824 "CrossMap is a program for conversion of genome coordinates or annotation
1825 files between different genome assemblies. It supports most commonly used
1826 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1827 (license license:gpl2+)))
1829 (define-public cutadapt
1836 (url "https://github.com/marcelm/cutadapt.git")
1837 (commit (string-append "v" version))))
1838 (file-name (string-append name "-" version "-checkout"))
1841 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1842 (build-system python-build-system)
1844 `(("python-xopen" ,python-xopen)))
1846 `(("python-cython" ,python-cython)
1847 ("python-pytest" ,python-pytest)))
1848 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1849 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1851 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1852 other types of unwanted sequence from high-throughput sequencing reads.")
1853 (license license:expat)))
1855 (define-public libbigwig
1861 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1862 "archive/" version ".tar.gz"))
1863 (file-name (string-append name "-" version ".tar.gz"))
1866 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1867 (build-system gnu-build-system)
1869 `(#:test-target "test"
1872 (string-append "prefix=" (assoc-ref %outputs "out")))
1874 (modify-phases %standard-phases
1876 (add-before 'check 'disable-curl-test
1878 (substitute* "Makefile"
1879 (("./test/testRemote.*") ""))
1881 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1882 ;; there has not yet been a release containing this change.
1883 (add-before 'install 'create-target-dirs
1884 (lambda* (#:key outputs #:allow-other-keys)
1885 (let ((out (assoc-ref outputs "out")))
1886 (mkdir-p (string-append out "/lib"))
1887 (mkdir-p (string-append out "/include"))
1893 `(("doxygen" ,doxygen)))
1894 (home-page "https://github.com/dpryan79/libBigWig")
1895 (synopsis "C library for handling bigWig files")
1897 "This package provides a C library for parsing local and remote BigWig
1899 (license license:expat)))
1901 (define-public python-pybigwig
1903 (name "python-pybigwig")
1907 (uri (pypi-uri "pyBigWig" version))
1910 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1911 (modules '((guix build utils)))
1914 ;; Delete bundled libBigWig sources
1915 (delete-file-recursively "libBigWig")))))
1916 (build-system python-build-system)
1919 (modify-phases %standard-phases
1920 (add-after 'unpack 'link-with-libBigWig
1921 (lambda* (#:key inputs #:allow-other-keys)
1922 (substitute* "setup.py"
1923 (("libs=\\[") "libs=[\"BigWig\", "))
1926 `(("libbigwig" ,libbigwig)
1929 (home-page "https://github.com/dpryan79/pyBigWig")
1930 (synopsis "Access bigWig files in Python using libBigWig")
1932 "This package provides Python bindings to the libBigWig library for
1933 accessing bigWig files.")
1934 (license license:expat)))
1936 (define-public python2-pybigwig
1937 (package-with-python2 python-pybigwig))
1939 (define-public python-dendropy
1941 (name "python-dendropy")
1946 (uri (pypi-uri "DendroPy" version))
1949 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1950 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1951 (build-system python-build-system)
1952 (home-page "http://packages.python.org/DendroPy/")
1953 (synopsis "Library for phylogenetics and phylogenetic computing")
1955 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1956 writing, simulation, processing and manipulation of phylogenetic
1957 trees (phylogenies) and characters.")
1958 (license license:bsd-3)
1959 (properties `((python2-variant . ,(delay python2-dendropy))))))
1961 (define-public python2-dendropy
1962 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1966 `(#:python ,python-2
1968 (modify-phases %standard-phases
1970 ;; There is currently a test failure that only happens on some
1971 ;; systems, and only using "setup.py test"
1972 (lambda _ (zero? (system* "nosetests")))))))
1973 (native-inputs `(("python2-nose" ,python2-nose)
1974 ,@(package-native-inputs base))))))
1976 (define-public python-py2bit
1978 (name "python-py2bit")
1983 (uri (pypi-uri "py2bit" version))
1986 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
1987 (build-system python-build-system)
1988 (home-page "https://github.com/dpryan79/py2bit")
1989 (synopsis "Access 2bit files using lib2bit")
1991 "This package provides Python bindings for lib2bit to access 2bit files
1993 (license license:expat)))
1995 (define-public deeptools
2001 (uri (string-append "https://github.com/deeptools/deepTools/"
2002 "archive/" version ".tar.gz"))
2003 (file-name (string-append name "-" version ".tar.gz"))
2006 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2007 (build-system python-build-system)
2009 `(("python-scipy" ,python-scipy)
2010 ("python-numpy" ,python-numpy)
2011 ("python-numpydoc" ,python-numpydoc)
2012 ("python-matplotlib" ,python-matplotlib)
2013 ("python-pysam" ,python-pysam)
2014 ("python-py2bit" ,python-py2bit)
2015 ("python-pybigwig" ,python-pybigwig)))
2017 `(("python-mock" ,python-mock) ;for tests
2018 ("python-nose" ,python-nose) ;for tests
2019 ("python-pytz" ,python-pytz))) ;for tests
2020 (home-page "https://github.com/deeptools/deepTools")
2021 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2023 "DeepTools addresses the challenge of handling the large amounts of data
2024 that are now routinely generated from DNA sequencing centers. To do so,
2025 deepTools contains useful modules to process the mapped reads data to create
2026 coverage files in standard bedGraph and bigWig file formats. By doing so,
2027 deepTools allows the creation of normalized coverage files or the comparison
2028 between two files (for example, treatment and control). Finally, using such
2029 normalized and standardized files, multiple visualizations can be created to
2030 identify enrichments with functional annotations of the genome.")
2031 (license license:gpl3+)))
2033 (define-public delly
2040 "https://github.com/tobiasrausch/delly/archive/v"
2042 (file-name (string-append name "-" version ".tar.gz"))
2044 (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj"))
2045 (patches (search-patches "delly-use-system-libraries.patch"))))
2046 (build-system gnu-build-system)
2048 `(#:tests? #f ; There are no tests to run.
2049 #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time.
2051 (modify-phases %standard-phases
2052 (delete 'configure) ; There is no configure phase.
2055 (let ((bin (string-append (assoc-ref %outputs "out") "/bin"))
2056 (templates (string-append (assoc-ref %outputs "out")
2057 "/share/delly/templates")))
2060 (copy-recursively "excludeTemplates" templates)
2061 (install-file "src/cov" bin)
2062 (install-file "src/delly" bin)
2063 (install-file "src/dpe" bin)))))))
2065 `(("python" ,python-2)))
2071 (home-page "https://github.com/tobiasrausch/delly")
2072 (synopsis "Integrated structural variant prediction method")
2073 (description "Delly is an integrated structural variant prediction method
2074 that can discover and genotype deletions, tandem duplications, inversions and
2075 translocations at single-nucleotide resolution in short-read massively parallel
2076 sequencing data. It uses paired-ends and split-reads to sensitively and
2077 accurately delineate genomic rearrangements throughout the genome.")
2078 (license license:gpl3+)))
2080 (define-public diamond
2087 "https://github.com/bbuchfink/diamond/archive/v"
2089 (file-name (string-append name "-" version ".tar.gz"))
2092 "0c4y8l90vdxmglb0w37y0413v11qzcwg8sdmy9k0c0gr3bsq7dzs"))))
2093 (build-system cmake-build-system)
2095 '(#:tests? #f ; no "check" target
2097 (modify-phases %standard-phases
2098 (add-after 'unpack 'remove-native-compilation
2100 (substitute* "CMakeLists.txt" (("-march=native") ""))
2104 (home-page "https://github.com/bbuchfink/diamond")
2105 (synopsis "Accelerated BLAST compatible local sequence aligner")
2107 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2108 translated DNA query sequences against a protein reference database (BLASTP
2109 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2110 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2111 data and settings.")
2112 (license license:agpl3+)))
2114 (define-public discrover
2121 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2123 (file-name (string-append name "-" version ".tar.gz"))
2126 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2127 (build-system cmake-build-system)
2129 `(#:tests? #f ; there are no tests
2131 (modify-phases %standard-phases
2132 (add-after 'unpack 'add-missing-includes
2134 (substitute* "src/executioninformation.hpp"
2135 (("#define EXECUTIONINFORMATION_HPP" line)
2136 (string-append line "\n#include <random>")))
2137 (substitute* "src/plasma/fasta.hpp"
2138 (("#define FASTA_HPP" line)
2139 (string-append line "\n#include <random>")))
2145 `(("texlive" ,texlive)
2146 ("imagemagick" ,imagemagick)))
2147 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2148 (synopsis "Discover discriminative nucleotide sequence motifs")
2149 (description "Discrover is a motif discovery method to find binding sites
2150 of nucleic acid binding proteins.")
2151 (license license:gpl3+)))
2153 (define-public eigensoft
2154 (let ((revision "1")
2155 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2158 (version (string-append "6.1.2-"
2160 (string-take commit 9)))
2165 (url "https://github.com/DReichLab/EIG.git")
2167 (file-name (string-append "eigensoft-" commit "-checkout"))
2170 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2171 (modules '((guix build utils)))
2172 ;; Remove pre-built binaries.
2174 (delete-file-recursively "bin")
2177 (build-system gnu-build-system)
2179 `(#:tests? #f ; There are no tests.
2180 #:make-flags '("CC=gcc")
2182 (modify-phases %standard-phases
2183 ;; There is no configure phase, but the Makefile is in a
2188 ;; The link flags are incomplete.
2189 (substitute* "Makefile"
2190 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2192 ;; The provided install target only copies executables to
2193 ;; the "bin" directory in the build root.
2194 (add-after 'install 'actually-install
2195 (lambda* (#:key outputs #:allow-other-keys)
2196 (let* ((out (assoc-ref outputs "out"))
2197 (bin (string-append out "/bin")))
2198 (for-each (lambda (file)
2199 (install-file file bin))
2200 (find-files "../bin" ".*"))
2205 ("openblas" ,openblas)
2207 ("gfortran" ,gfortran "lib")))
2208 (home-page "https://github.com/DReichLab/EIG")
2209 (synopsis "Tools for population genetics")
2210 (description "The EIGENSOFT package provides tools for population
2211 genetics and stratification correction. EIGENSOFT implements methods commonly
2212 used in population genetics analyses such as PCA, computation of Tracy-Widom
2213 statistics, and finding related individuals in structured populations. It
2214 comes with a built-in plotting script and supports multiple file formats and
2215 quantitative phenotypes.")
2216 ;; The license of the eigensoft tools is Expat, but since it's
2217 ;; linking with the GNU Scientific Library (GSL) the effective
2218 ;; license is the GPL.
2219 (license license:gpl3+))))
2221 (define-public edirect
2227 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2228 "versions/2016-05-03/edirect.tar.gz"))
2231 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2232 (build-system perl-build-system)
2234 `(#:tests? #f ;no "check" target
2236 (modify-phases %standard-phases
2240 (lambda* (#:key outputs #:allow-other-keys)
2241 (let ((target (string-append (assoc-ref outputs "out")
2244 (install-file "edirect.pl" target)
2247 'install 'wrap-program
2248 (lambda* (#:key inputs outputs #:allow-other-keys)
2249 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2250 (let* ((out (assoc-ref outputs "out"))
2251 (path (getenv "PERL5LIB")))
2252 (wrap-program (string-append out "/bin/edirect.pl")
2253 `("PERL5LIB" ":" prefix (,path)))))))))
2255 `(("perl-html-parser" ,perl-html-parser)
2256 ("perl-encode-locale" ,perl-encode-locale)
2257 ("perl-file-listing" ,perl-file-listing)
2258 ("perl-html-tagset" ,perl-html-tagset)
2259 ("perl-html-tree" ,perl-html-tree)
2260 ("perl-http-cookies" ,perl-http-cookies)
2261 ("perl-http-date" ,perl-http-date)
2262 ("perl-http-message" ,perl-http-message)
2263 ("perl-http-negotiate" ,perl-http-negotiate)
2264 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2265 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2266 ("perl-net-http" ,perl-net-http)
2267 ("perl-uri" ,perl-uri)
2268 ("perl-www-robotrules" ,perl-www-robotrules)
2270 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2271 (synopsis "Tools for accessing the NCBI's set of databases")
2273 "Entrez Direct (EDirect) is a method for accessing the National Center
2274 for Biotechnology Information's (NCBI) set of interconnected
2275 databases (publication, sequence, structure, gene, variation, expression,
2276 etc.) from a terminal. Functions take search terms from command-line
2277 arguments. Individual operations are combined to build multi-step queries.
2278 Record retrieval and formatting normally complete the process.
2280 EDirect also provides an argument-driven function that simplifies the
2281 extraction of data from document summaries or other results that are returned
2282 in structured XML format. This can eliminate the need for writing custom
2283 software to answer ad hoc questions.")
2284 (license license:public-domain)))
2286 (define-public exonerate
2295 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2296 "exonerate-" version ".tar.gz"))
2299 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2300 (build-system gnu-build-system)
2302 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2304 `(("pkg-config" ,pkg-config)))
2308 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2309 (synopsis "Generic tool for biological sequence alignment")
2311 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2312 the alignment of sequences using a many alignment models, either exhaustive
2313 dynamic programming or a variety of heuristics.")
2314 (license license:gpl3)))
2316 (define-public express
2324 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2325 version "/express-" version "-src.tgz"))
2328 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2329 (build-system cmake-build-system)
2331 `(#:tests? #f ;no "check" target
2333 (modify-phases %standard-phases
2334 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2335 (lambda* (#:key inputs #:allow-other-keys)
2336 (substitute* "CMakeLists.txt"
2337 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2338 "set(Boost_USE_STATIC_LIBS OFF)")
2339 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2340 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2341 (substitute* "src/CMakeLists.txt"
2342 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2343 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2347 ("bamtools" ,bamtools)
2348 ("protobuf" ,protobuf)
2350 (home-page "http://bio.math.berkeley.edu/eXpress")
2351 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2353 "eXpress is a streaming tool for quantifying the abundances of a set of
2354 target sequences from sampled subsequences. Example applications include
2355 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2356 analysis (from RNA-Seq), transcription factor binding quantification in
2357 ChIP-Seq, and analysis of metagenomic data.")
2358 (license license:artistic2.0)))
2360 (define-public express-beta-diversity
2362 (name "express-beta-diversity")
2368 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2370 (file-name (string-append name "-" version ".tar.gz"))
2373 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2374 (build-system gnu-build-system)
2377 (modify-phases %standard-phases
2379 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2381 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2383 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2385 (lambda* (#:key outputs #:allow-other-keys)
2386 (let ((bin (string-append (assoc-ref outputs "out")
2389 (install-file "scripts/convertToEBD.py" bin)
2390 (install-file "bin/ExpressBetaDiversity" bin)
2393 `(("python" ,python-2)))
2394 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2395 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2397 "Express Beta Diversity (EBD) calculates ecological beta diversity
2398 (dissimilarity) measures between biological communities. EBD implements a
2399 variety of diversity measures including those that make use of phylogenetic
2400 similarity of community members.")
2401 (license license:gpl3+)))
2403 (define-public fasttree
2410 "http://www.microbesonline.org/fasttree/FastTree-"
2414 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2415 (build-system gnu-build-system)
2417 `(#:tests? #f ; no "check" target
2419 (modify-phases %standard-phases
2423 (lambda* (#:key source #:allow-other-keys)
2424 (and (zero? (system* "gcc"
2426 "-finline-functions"
2433 (zero? (system* "gcc"
2437 "-finline-functions"
2445 (lambda* (#:key outputs #:allow-other-keys)
2446 (let ((bin (string-append (assoc-ref outputs "out")
2449 (install-file "FastTree" bin)
2450 (install-file "FastTreeMP" bin)
2452 (home-page "http://www.microbesonline.org/fasttree")
2453 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2455 "FastTree can handle alignments with up to a million of sequences in a
2456 reasonable amount of time and memory. For large alignments, FastTree is
2457 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2458 (license license:gpl2+)))
2460 (define-public fastx-toolkit
2462 (name "fastx-toolkit")
2468 "https://github.com/agordon/fastx_toolkit/releases/download/"
2469 version "/fastx_toolkit-" version ".tar.bz2"))
2472 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2473 (build-system gnu-build-system)
2475 `(("libgtextutils" ,libgtextutils)))
2477 `(("pkg-config" ,pkg-config)))
2478 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2479 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2481 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2482 FASTA/FASTQ files preprocessing.
2484 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2485 containing multiple short-reads sequences. The main processing of such
2486 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2487 is sometimes more productive to preprocess the files before mapping the
2488 sequences to the genome---manipulating the sequences to produce better mapping
2489 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2490 (license license:agpl3+)))
2492 (define-public flexbar
2499 (string-append "mirror://sourceforge/flexbar/"
2500 version "/flexbar_v" version "_src.tgz"))
2503 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2504 (build-system cmake-build-system)
2506 `(#:configure-flags (list
2507 (string-append "-DFLEXBAR_BINARY_DIR="
2508 (assoc-ref %outputs "out")
2511 (modify-phases %standard-phases
2513 (lambda* (#:key outputs #:allow-other-keys)
2514 (setenv "PATH" (string-append
2515 (assoc-ref outputs "out") "/bin:"
2517 (chdir "../flexbar_v2.5_src/test")
2518 (zero? (system* "bash" "flexbar_validate.sh"))))
2519 (delete 'install))))
2524 `(("pkg-config" ,pkg-config)
2526 (home-page "http://flexbar.sourceforge.net")
2527 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2529 "Flexbar preprocesses high-throughput nucleotide sequencing data
2530 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2531 Moreover, trimming and filtering features are provided. Flexbar increases
2532 read mapping rates and improves genome and transcriptome assemblies. It
2533 supports next-generation sequencing data in fasta/q and csfasta/q format from
2534 Illumina, Roche 454, and the SOLiD platform.")
2535 (license license:gpl3)))
2537 (define-public fraggenescan
2539 (name "fraggenescan")
2545 (string-append "mirror://sourceforge/fraggenescan/"
2546 "FragGeneScan" version ".tar.gz"))
2548 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2549 (build-system gnu-build-system)
2552 (modify-phases %standard-phases
2554 (add-before 'build 'patch-paths
2555 (lambda* (#:key outputs #:allow-other-keys)
2556 (let* ((out (string-append (assoc-ref outputs "out")))
2557 (share (string-append out "/share/fraggenescan/")))
2558 (substitute* "run_FragGeneScan.pl"
2560 (string-append "system(\"" (which "rm")))
2562 (string-append "system(\"" (which "mv")))
2563 (("\\\"awk") (string-append "\"" (which "awk")))
2564 ;; This script and other programs expect the training files
2565 ;; to be in the non-standard location bin/train/XXX. Change
2566 ;; this to be share/fraggenescan/train/XXX instead.
2567 (("^\\$train.file = \\$dir.*")
2568 (string-append "$train_file = \""
2570 "train/\".$FGS_train_file;")))
2571 (substitute* "run_hmm.c"
2572 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2573 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2576 (lambda _ (and (zero? (system* "make" "clean"))
2577 (zero? (system* "make" "fgs")))))
2579 (lambda* (#:key outputs #:allow-other-keys)
2580 (let* ((out (string-append (assoc-ref outputs "out")))
2581 (bin (string-append out "/bin/"))
2582 (share (string-append out "/share/fraggenescan/train")))
2583 (install-file "run_FragGeneScan.pl" bin)
2584 (install-file "FragGeneScan" bin)
2585 (copy-recursively "train" share))))
2587 (add-after 'install 'post-install-check
2588 ;; In lieu of 'make check', run one of the examples and check the
2589 ;; output files gets created.
2590 (lambda* (#:key outputs #:allow-other-keys)
2591 (let* ((out (string-append (assoc-ref outputs "out")))
2592 (bin (string-append out "/bin/"))
2593 (frag (string-append bin "run_FragGeneScan.pl")))
2594 (and (zero? (system* frag ; Test complete genome.
2595 "-genome=./example/NC_000913.fna"
2599 (file-exists? "test2.faa")
2600 (file-exists? "test2.ffn")
2601 (file-exists? "test2.gff")
2602 (file-exists? "test2.out")
2603 (zero? (system* ; Test incomplete sequences.
2605 "-genome=./example/NC_000913-fgs.ffn"
2608 "-train=454_30")))))))))
2611 ("python" ,python-2))) ;not compatible with python 3.
2612 (home-page "https://sourceforge.net/projects/fraggenescan/")
2613 (synopsis "Finds potentially fragmented genes in short reads")
2615 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2616 short and error-prone DNA sequencing reads. It can also be applied to predict
2617 genes in incomplete assemblies or complete genomes.")
2618 ;; GPL3+ according to private correspondense with the authors.
2619 (license license:gpl3+)))
2621 (define-public fxtract
2622 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2630 "https://github.com/ctSkennerton/fxtract/archive/"
2632 (file-name (string-append "ctstennerton-util-"
2633 (string-take util-commit 7)
2637 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2638 (build-system gnu-build-system)
2640 `(#:make-flags (list
2641 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2643 #:test-target "fxtract_test"
2645 (modify-phases %standard-phases
2647 (add-before 'build 'copy-util
2648 (lambda* (#:key inputs #:allow-other-keys)
2650 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2652 ;; Do not use make install as this requires additional dependencies.
2654 (lambda* (#:key outputs #:allow-other-keys)
2655 (let* ((out (assoc-ref outputs "out"))
2656 (bin (string-append out"/bin")))
2657 (install-file "fxtract" bin)
2663 ;; ctskennerton-util is licensed under GPL2.
2664 `(("ctskennerton-util"
2668 (url "https://github.com/ctSkennerton/util.git")
2669 (commit util-commit)))
2670 (file-name (string-append
2671 "ctstennerton-util-" util-commit "-checkout"))
2674 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2675 (home-page "https://github.com/ctSkennerton/fxtract")
2676 (synopsis "Extract sequences from FASTA and FASTQ files")
2678 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2679 or FASTQ) file given a subsequence. It uses a simple substring search for
2680 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2681 lookups or multi-pattern searching as required. By default fxtract looks in
2682 the sequence of each record but can also be told to look in the header,
2683 comment or quality sections.")
2684 ;; 'util' requires SSE instructions.
2685 (supported-systems '("x86_64-linux"))
2686 (license license:expat))))
2688 (define-public gemma
2694 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2696 (file-name (string-append name "-" version ".tar.gz"))
2699 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2700 (patches (search-patches "gemma-intel-compat.patch"))))
2705 (build-system gnu-build-system)
2708 '(,@(match (%current-system)
2710 '("FORCE_DYNAMIC=1"))
2712 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2714 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2716 (modify-phases %standard-phases
2718 (add-before 'build 'bin-mkdir
2723 (lambda* (#:key outputs #:allow-other-keys)
2724 (let ((out (assoc-ref outputs "out")))
2725 (install-file "bin/gemma"
2729 #:tests? #f)) ; no tests included yet
2730 (home-page "https://github.com/xiangzhou/GEMMA")
2731 (synopsis "Tool for genome-wide efficient mixed model association")
2733 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2734 standard linear mixed model resolver with application in genome-wide
2735 association studies (GWAS).")
2736 (license license:gpl3)))
2745 "https://github.com/nboley/grit/archive/"
2747 (file-name (string-append name "-" version ".tar.gz"))
2750 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2751 (build-system python-build-system)
2753 `(#:python ,python-2
2755 (modify-phases %standard-phases
2756 (add-after 'unpack 'generate-from-cython-sources
2757 (lambda* (#:key inputs outputs #:allow-other-keys)
2758 ;; Delete these C files to force fresh generation from pyx sources.
2759 (delete-file "grit/sparsify_support_fns.c")
2760 (delete-file "grit/call_peaks_support_fns.c")
2761 (substitute* "setup.py"
2762 (("Cython.Setup") "Cython.Build")
2763 ;; Add numpy include path to fix compilation
2765 (string-append "pyx\", ], include_dirs = ['"
2766 (assoc-ref inputs "python-numpy")
2767 "/lib/python2.7/site-packages/numpy/core/include/"
2771 `(("python-scipy" ,python2-scipy)
2772 ("python-numpy" ,python2-numpy)
2773 ("python-pysam" ,python2-pysam)
2774 ("python-networkx" ,python2-networkx)))
2776 `(("python-cython" ,python2-cython)))
2777 (home-page "http://grit-bio.org")
2778 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2780 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2781 full length transcript models. When none of these data sources are available,
2782 GRIT can be run by providing a candidate set of TES or TSS sites. In
2783 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2784 also be run in quantification mode, where it uses a provided GTF file and just
2785 estimates transcript expression.")
2786 (license license:gpl3+)))
2788 (define-public hisat
2795 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2796 version "-beta-source.zip"))
2799 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2800 (build-system gnu-build-system)
2802 `(#:tests? #f ;no check target
2803 #:make-flags '("allall"
2804 ;; Disable unsupported `popcnt' instructions on
2805 ;; architectures other than x86_64
2806 ,@(if (string-prefix? "x86_64"
2807 (or (%current-target-system)
2810 '("POPCNT_CAPABILITY=0")))
2812 (modify-phases %standard-phases
2813 (add-after 'unpack 'patch-sources
2815 ;; XXX Cannot use snippet because zip files are not supported
2816 (substitute* "Makefile"
2817 (("^CC = .*$") "CC = gcc")
2818 (("^CPP = .*$") "CPP = g++")
2819 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2820 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2821 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2822 (substitute* '("hisat-build" "hisat-inspect")
2823 (("/usr/bin/env") (which "env")))
2826 (lambda* (#:key outputs #:allow-other-keys)
2827 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2828 (for-each (lambda (file)
2829 (install-file file bin))
2832 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2834 (delete 'configure))))
2836 `(("unzip" ,unzip)))
2841 ;; Non-portable SSE instructions are used so building fails on platforms
2842 ;; other than x86_64.
2843 (supported-systems '("x86_64-linux"))
2844 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2845 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2847 "HISAT is a fast and sensitive spliced alignment program for mapping
2848 RNA-seq reads. In addition to one global FM index that represents a whole
2849 genome, HISAT uses a large set of small FM indexes that collectively cover the
2850 whole genome. These small indexes (called local indexes) combined with
2851 several alignment strategies enable effective alignment of RNA-seq reads, in
2852 particular, reads spanning multiple exons.")
2853 (license license:gpl3+)))
2855 (define-public hisat2
2862 ;; FIXME: a better source URL is
2863 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2864 ;; "/downloads/hisat2-" version "-source.zip")
2865 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2866 ;; but it is currently unavailable.
2867 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2868 (file-name (string-append name "-" version ".tar.gz"))
2871 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2872 (build-system gnu-build-system)
2874 `(#:tests? #f ; no check target
2875 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2876 #:modules ((guix build gnu-build-system)
2880 (modify-phases %standard-phases
2881 (add-after 'unpack 'make-deterministic
2883 (substitute* "Makefile"
2888 (lambda* (#:key outputs #:allow-other-keys)
2889 (let* ((out (assoc-ref outputs "out"))
2890 (bin (string-append out "/bin/"))
2891 (doc (string-append out "/share/doc/hisat2/")))
2893 (cut install-file <> bin)
2895 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2897 (install-file "doc/manual.inc.html" doc))
2900 `(("unzip" ,unzip) ; needed for archive from ftp
2902 ("pandoc" ,ghc-pandoc))) ; for documentation
2903 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2904 (synopsis "Graph-based alignment of genomic sequencing reads")
2905 (description "HISAT2 is a fast and sensitive alignment program for mapping
2906 next-generation sequencing reads (both DNA and RNA) to a population of human
2907 genomes (as well as to a single reference genome). In addition to using one
2908 global @dfn{graph FM} (GFM) index that represents a population of human
2909 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2910 the whole genome. These small indexes, combined with several alignment
2911 strategies, enable rapid and accurate alignment of sequencing reads. This new
2912 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2913 ;; HISAT2 contains files from Bowtie2, which is released under
2914 ;; GPLv2 or later. The HISAT2 source files are released under
2916 (license license:gpl3+)))
2918 (define-public hmmer
2926 "http://eddylab.org/software/hmmer"
2927 (version-major version) "/"
2928 version "/hmmer-" version ".tar.gz"))
2931 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2932 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2933 (build-system gnu-build-system)
2934 (native-inputs `(("perl" ,perl)))
2935 (home-page "http://hmmer.org/")
2936 (synopsis "Biosequence analysis using profile hidden Markov models")
2938 "HMMER is used for searching sequence databases for homologs of protein
2939 sequences, and for making protein sequence alignments. It implements methods
2940 using probabilistic models called profile hidden Markov models (profile
2942 (license (list license:gpl3+
2943 ;; The bundled library 'easel' is distributed
2944 ;; under The Janelia Farm Software License.
2945 (license:non-copyleft
2946 "file://easel/LICENSE"
2947 "See easel/LICENSE in the distribution.")))))
2949 (define-public htseq
2955 (uri (pypi-uri "HTSeq" version))
2958 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2959 (build-system python-build-system)
2961 `(("python-cython" ,python-cython)))
2962 ;; Numpy needs to be propagated when htseq is used as a Python library.
2964 `(("python-numpy" ,python-numpy)))
2966 `(("python-pysam" ,python-pysam)
2967 ("python-matplotlib" ,python-matplotlib)))
2968 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2969 (synopsis "Analysing high-throughput sequencing data with Python")
2971 "HTSeq is a Python package that provides infrastructure to process data
2972 from high-throughput sequencing assays.")
2973 (license license:gpl3+)))
2975 (define-public python2-htseq
2976 (package-with-python2 htseq))
2978 (define-public java-htsjdk
2980 (name "java-htsjdk")
2981 (version "2.3.0") ; last version without build dependency on gradle
2985 "https://github.com/samtools/htsjdk/archive/"
2987 (file-name (string-append name "-" version ".tar.gz"))
2990 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2991 (modules '((guix build utils)))
2993 ;; Delete pre-built binaries
2995 (delete-file-recursively "lib")
2998 (build-system ant-build-system)
3000 `(#:tests? #f ; test require Internet access
3003 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3004 "/share/java/htsjdk/"))
3005 #:build-target "all"
3007 (modify-phases %standard-phases
3008 ;; The build phase also installs the jars
3009 (delete 'install))))
3011 `(("java-ngs" ,java-ngs)
3012 ("java-snappy-1" ,java-snappy-1)
3013 ("java-commons-compress" ,java-commons-compress)
3014 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3015 ("java-commons-jexl-2" ,java-commons-jexl-2)
3016 ("java-xz" ,java-xz)))
3018 `(("java-testng" ,java-testng)))
3019 (home-page "http://samtools.github.io/htsjdk/")
3020 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3022 "HTSJDK is an implementation of a unified Java library for accessing
3023 common file formats, such as SAM and VCF, used for high-throughput
3024 sequencing (HTS) data. There are also an number of useful utilities for
3025 manipulating HTS data.")
3026 (license license:expat)))
3028 (define-public java-htsjdk-latest
3030 (name "java-htsjdk")
3035 (url "https://github.com/samtools/htsjdk.git")
3037 (file-name (string-append name "-" version "-checkout"))
3040 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3041 (build-system ant-build-system)
3043 `(#:tests? #f ; test require Scala
3045 #:jar-name "htsjdk.jar"
3047 (modify-phases %standard-phases
3048 (add-after 'unpack 'remove-useless-build.xml
3049 (lambda _ (delete-file "build.xml") #t))
3050 ;; The tests require the scalatest package.
3051 (add-after 'unpack 'remove-tests
3052 (lambda _ (delete-file-recursively "src/test") #t)))))
3054 `(("java-ngs" ,java-ngs)
3055 ("java-snappy-1" ,java-snappy-1)
3056 ("java-commons-compress" ,java-commons-compress)
3057 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3058 ("java-commons-jexl-2" ,java-commons-jexl-2)
3059 ("java-xz" ,java-xz)))
3061 `(("java-junit" ,java-junit)))
3062 (home-page "http://samtools.github.io/htsjdk/")
3063 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3065 "HTSJDK is an implementation of a unified Java library for accessing
3066 common file formats, such as SAM and VCF, used for high-throughput
3067 sequencing (HTS) data. There are also an number of useful utilities for
3068 manipulating HTS data.")
3069 (license license:expat)))
3071 ;; This is needed for picard 2.10.3
3072 (define-public java-htsjdk-2.10.1
3073 (package (inherit java-htsjdk-latest)
3074 (name "java-htsjdk")
3079 (url "https://github.com/samtools/htsjdk.git")
3081 (file-name (string-append name "-" version "-checkout"))
3084 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3085 (build-system ant-build-system)
3087 `(#:tests? #f ; tests require Scala
3089 #:jar-name "htsjdk.jar"
3091 (modify-phases %standard-phases
3092 (add-after 'unpack 'remove-useless-build.xml
3093 (lambda _ (delete-file "build.xml") #t))
3094 ;; The tests require the scalatest package.
3095 (add-after 'unpack 'remove-tests
3096 (lambda _ (delete-file-recursively "src/test") #t)))))))
3098 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3099 ;; recent version of java-htsjdk, which depends on gradle.
3100 (define-public java-picard
3102 (name "java-picard")
3107 (url "https://github.com/broadinstitute/picard.git")
3109 (file-name (string-append "java-picard-" version "-checkout"))
3112 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3113 (modules '((guix build utils)))
3116 ;; Delete pre-built binaries.
3117 (delete-file-recursively "lib")
3119 (substitute* "build.xml"
3120 ;; Remove build-time dependency on git.
3121 (("failifexecutionfails=\"true\"")
3122 "failifexecutionfails=\"false\"")
3124 (("depends=\"compile-htsjdk, ")
3126 (("depends=\"compile-htsjdk-tests, ")
3128 ;; Build picard-lib.jar before building picard.jar
3129 (("name=\"picard-jar\" depends=\"" line)
3130 (string-append line "picard-lib-jar, ")))
3132 (build-system ant-build-system)
3134 `(#:build-target "picard-jar"
3135 #:test-target "test"
3136 ;; Tests require jacoco:coverage.
3139 (list (string-append "-Dhtsjdk_lib_dir="
3140 (assoc-ref %build-inputs "java-htsjdk")
3141 "/share/java/htsjdk/")
3142 "-Dhtsjdk-classes=dist/tmp"
3143 (string-append "-Dhtsjdk-version="
3144 ,(package-version java-htsjdk)))
3147 (modify-phases %standard-phases
3148 (add-after 'unpack 'use-our-htsjdk
3149 (lambda* (#:key inputs #:allow-other-keys)
3150 (substitute* "build.xml"
3151 (("\\$\\{htsjdk\\}/lib")
3152 (string-append (assoc-ref inputs "java-htsjdk")
3153 "/share/java/htsjdk/")))
3155 (add-after 'unpack 'make-test-target-independent
3156 (lambda* (#:key inputs #:allow-other-keys)
3157 (substitute* "build.xml"
3158 (("name=\"test\" depends=\"compile, ")
3159 "name=\"test\" depends=\""))
3161 (replace 'install (install-jars "dist")))))
3163 `(("java-htsjdk" ,java-htsjdk)
3164 ("java-guava" ,java-guava)))
3166 `(("java-testng" ,java-testng)))
3167 (home-page "http://broadinstitute.github.io/picard/")
3168 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3169 (description "Picard is a set of Java command line tools for manipulating
3170 high-throughput sequencing (HTS) data and formats. Picard is implemented
3171 using the HTSJDK Java library to support accessing file formats that are
3172 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3174 (license license:expat)))
3176 ;; This is needed for dropseq-tools
3177 (define-public java-picard-2.10.3
3179 (name "java-picard")
3184 (url "https://github.com/broadinstitute/picard.git")
3186 (file-name (string-append "java-picard-" version "-checkout"))
3189 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3190 (build-system ant-build-system)
3192 `(#:jar-name "picard.jar"
3193 ;; Tests require jacoco:coverage.
3196 #:main-class "picard.cmdline.PicardCommandLine"
3197 #:modules ((guix build ant-build-system)
3199 (guix build java-utils)
3204 (modify-phases %standard-phases
3205 (add-after 'unpack 'remove-useless-build.xml
3206 (lambda _ (delete-file "build.xml") #t))
3207 ;; This is necessary to ensure that htsjdk is found when using
3208 ;; picard.jar as an executable.
3209 (add-before 'build 'edit-classpath-in-manifest
3210 (lambda* (#:key inputs #:allow-other-keys)
3211 (chmod "build.xml" #o664)
3212 (call-with-output-file "build.xml.new"
3216 (with-input-from-file "build.xml"
3217 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3218 `((target . ,(lambda (tag . kids)
3219 (let ((name ((sxpath '(name *text*))
3221 ;; FIXME: We're breaking the line
3222 ;; early with a dummy path to
3223 ;; ensure that the store reference
3224 ;; isn't broken apart and can still
3225 ;; be found by the reference
3230 ~a/share/java/htsjdk.jar${line.separator}"
3231 ;; maximum line length is 70
3232 (string-tabulate (const #\b) 57)
3233 (assoc-ref inputs "java-htsjdk"))))
3234 (if (member "manifest" name)
3238 (file "${manifest.file}")
3241 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3242 (*text* . ,(lambda (_ txt) txt))))
3244 (rename-file "build.xml.new" "build.xml")
3247 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3249 `(("java-testng" ,java-testng)
3250 ("java-guava" ,java-guava)))
3251 (home-page "http://broadinstitute.github.io/picard/")
3252 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3253 (description "Picard is a set of Java command line tools for manipulating
3254 high-throughput sequencing (HTS) data and formats. Picard is implemented
3255 using the HTSJDK Java library to support accessing file formats that are
3256 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3258 (license license:expat)))
3260 ;; This is the last version of Picard to provide net.sf.samtools
3261 (define-public java-picard-1.113
3262 (package (inherit java-picard)
3263 (name "java-picard")
3268 (url "https://github.com/broadinstitute/picard.git")
3270 (file-name (string-append "java-picard-" version "-checkout"))
3273 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3274 (modules '((guix build utils)))
3277 ;; Delete pre-built binaries.
3278 (delete-file-recursively "lib")
3281 (build-system ant-build-system)
3283 `(#:build-target "picard-jar"
3284 #:test-target "test"
3285 ;; FIXME: the class path at test time is wrong.
3286 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3287 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3290 ;; This is only used for tests.
3292 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3294 (modify-phases %standard-phases
3295 ;; Do not use bundled ant bzip2.
3296 (add-after 'unpack 'use-ant-bzip
3297 (lambda* (#:key inputs #:allow-other-keys)
3298 (substitute* "build.xml"
3299 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3300 (string-append (assoc-ref inputs "ant")
3303 (add-after 'unpack 'make-test-target-independent
3304 (lambda* (#:key inputs #:allow-other-keys)
3305 (substitute* "build.xml"
3306 (("name=\"test\" depends=\"compile, ")
3307 "name=\"test\" depends=\"compile-tests, ")
3308 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3309 "name=\"compile\" depends=\"compile-src\""))
3311 (add-after 'unpack 'fix-deflater-path
3312 (lambda* (#:key outputs #:allow-other-keys)
3313 (substitute* "src/java/net/sf/samtools/Defaults.java"
3314 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3315 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3316 (assoc-ref outputs "out")
3317 "/lib/jni/libIntelDeflater.so"
3320 ;; Build the deflater library, because we've previously deleted the
3321 ;; pre-built one. This can only be built with access to the JDK
3323 (add-after 'build 'build-jni
3324 (lambda* (#:key inputs #:allow-other-keys)
3327 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3328 "-xf" (assoc-ref inputs "jdk-src")))
3329 (zero? (system* "javah" "-jni"
3330 "-classpath" "classes"
3332 "net.sf.samtools.util.zip.IntelDeflater"))
3333 (with-directory-excursion "src/c/inteldeflater"
3334 (zero? (system* "gcc" "-I../../../lib" "-I."
3335 (string-append "-I" (assoc-ref inputs "jdk")
3337 "-I../../../jdk-src/src/share/native/common/"
3338 "-I../../../jdk-src/src/solaris/native/common/"
3339 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3340 (zero? (system* "gcc" "-shared"
3341 "-o" "../../../lib/jni/libIntelDeflater.so"
3342 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3343 ;; We can only build everything else after building the JNI library.
3344 (add-after 'build-jni 'build-rest
3345 (lambda* (#:key make-flags #:allow-other-keys)
3346 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3347 (add-before 'build 'set-JAVA6_HOME
3349 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3351 (replace 'install (install-jars "dist"))
3352 (add-after 'install 'install-jni-lib
3353 (lambda* (#:key outputs #:allow-other-keys)
3354 (let ((jni (string-append (assoc-ref outputs "out")
3357 (install-file "lib/jni/libIntelDeflater.so" jni)
3360 `(("java-snappy-1" ,java-snappy-1)
3361 ("java-commons-jexl-2" ,java-commons-jexl-2)
3362 ("java-cofoja" ,java-cofoja)
3363 ("ant" ,ant) ; for bzip2 support at runtime
3366 `(("ant-apache-bcel" ,ant-apache-bcel)
3367 ("ant-junit" ,ant-junit)
3368 ("java-testng" ,java-testng)
3369 ("java-commons-bcel" ,java-commons-bcel)
3370 ("java-jcommander" ,java-jcommander)
3371 ("jdk" ,icedtea-8 "jdk")
3372 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3374 (define-public fastqc
3381 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3382 "projects/fastqc/fastqc_v"
3383 version "_source.zip"))
3386 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3387 (build-system ant-build-system)
3389 `(#:tests? #f ; there are no tests
3390 #:build-target "build"
3392 (modify-phases %standard-phases
3393 (add-after 'unpack 'fix-dependencies
3394 (lambda* (#:key inputs #:allow-other-keys)
3395 (substitute* "build.xml"
3397 (string-append (assoc-ref inputs "java-jbzip2")
3398 "/share/java/jbzip2.jar"))
3400 (string-append (assoc-ref inputs "java-picard-1.113")
3401 "/share/java/sam-1.112.jar"))
3403 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3404 "/share/java/sis-jhdf5.jar")))
3406 ;; There is no installation target
3408 (lambda* (#:key inputs outputs #:allow-other-keys)
3409 (let* ((out (assoc-ref outputs "out"))
3410 (bin (string-append out "/bin"))
3411 (share (string-append out "/share/fastqc/"))
3412 (exe (string-append share "/fastqc")))
3413 (for-each mkdir-p (list bin share))
3414 (copy-recursively "bin" share)
3416 (("my \\$java_bin = 'java';")
3417 (string-append "my $java_bin = '"
3418 (assoc-ref inputs "java")
3421 (symlink exe (string-append bin "/fastqc"))
3425 ("perl" ,perl) ; needed for the wrapper script
3426 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3427 ("java-picard-1.113" ,java-picard-1.113)
3428 ("java-jbzip2" ,java-jbzip2)))
3430 `(("unzip" ,unzip)))
3431 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3432 (synopsis "Quality control tool for high throughput sequence data")
3434 "FastQC aims to provide a simple way to do some quality control
3435 checks on raw sequence data coming from high throughput sequencing
3436 pipelines. It provides a modular set of analyses which you can use to
3437 give a quick impression of whether your data has any problems of which
3438 you should be aware before doing any further analysis.
3440 The main functions of FastQC are:
3443 @item Import of data from BAM, SAM or FastQ files (any variant);
3444 @item Providing a quick overview to tell you in which areas there may
3446 @item Summary graphs and tables to quickly assess your data;
3447 @item Export of results to an HTML based permanent report;
3448 @item Offline operation to allow automated generation of reports
3449 without running the interactive application.
3451 (license license:gpl3+)))
3453 (define-public htslib
3460 "https://github.com/samtools/htslib/releases/download/"
3461 version "/htslib-" version ".tar.bz2"))
3464 "1il6i2p84b0y9c93dhvzzki1ifw9bvapm2mvpr0xvb2nq8jlwgdy"))))
3465 (build-system gnu-build-system)
3467 `(("openssl" ,openssl)
3472 (home-page "http://www.htslib.org")
3473 (synopsis "C library for reading/writing high-throughput sequencing data")
3475 "HTSlib is a C library for reading/writing high-throughput sequencing
3476 data. It also provides the @command{bgzip}, @command{htsfile}, and
3477 @command{tabix} utilities.")
3478 ;; Files under cram/ are released under the modified BSD license;
3479 ;; the rest is released under the Expat license
3480 (license (list license:expat license:bsd-3))))
3482 ;; This package should be removed once no packages rely upon it.
3490 "https://github.com/samtools/htslib/releases/download/"
3491 version "/htslib-" version ".tar.bz2"))
3494 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3503 "https://github.com/nboley/idr/archive/"
3505 (file-name (string-append name "-" version ".tar.gz"))
3508 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3509 ;; Delete generated C code.
3511 '(begin (delete-file "idr/inv_cdf.c") #t))))
3512 (build-system python-build-system)
3513 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3514 ;; are no longer part of this package. It also asserts False, which
3515 ;; causes the tests to always fail.
3516 (arguments `(#:tests? #f))
3518 `(("python-scipy" ,python-scipy)
3519 ("python-sympy" ,python-sympy)
3520 ("python-numpy" ,python-numpy)
3521 ("python-matplotlib" ,python-matplotlib)))
3523 `(("python-cython" ,python-cython)))
3524 (home-page "https://github.com/nboley/idr")
3525 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3527 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3528 to measure the reproducibility of findings identified from replicate
3529 experiments and provide highly stable thresholds based on reproducibility.")
3530 (license license:gpl2+)))
3532 (define-public jellyfish
3538 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3539 "releases/download/v" version
3540 "/jellyfish-" version ".tar.gz"))
3543 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3544 (build-system gnu-build-system)
3545 (outputs '("out" ;for library
3546 "ruby" ;for Ruby bindings
3547 "python")) ;for Python bindings
3550 (list (string-append "--enable-ruby-binding="
3551 (assoc-ref %outputs "ruby"))
3552 (string-append "--enable-python-binding="
3553 (assoc-ref %outputs "python")))
3555 (modify-phases %standard-phases
3556 (add-before 'check 'set-SHELL-variable
3558 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3560 (setenv "SHELL" (which "bash"))
3566 ("python" ,python-2)
3567 ("pkg-config" ,pkg-config)))
3569 `(("htslib" ,htslib)))
3570 (synopsis "Tool for fast counting of k-mers in DNA")
3572 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3573 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3574 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3575 is a command-line program that reads FASTA and multi-FASTA files containing
3576 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3577 translated into a human-readable text format using the @code{jellyfish dump}
3578 command, or queried for specific k-mers with @code{jellyfish query}.")
3579 (home-page "http://www.genome.umd.edu/jellyfish.html")
3580 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3581 (supported-systems '("x86_64-linux"))
3582 ;; The combined work is published under the GPLv3 or later. Individual
3583 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3584 (license (list license:gpl3+ license:expat))))
3586 (define-public khmer
3593 (uri (pypi-uri "khmer" version))
3596 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3597 (patches (search-patches "khmer-use-libraries.patch"))))
3598 (build-system python-build-system)
3601 (modify-phases %standard-phases
3602 (add-after 'unpack 'set-paths
3603 (lambda* (#:key inputs outputs #:allow-other-keys)
3604 ;; Delete bundled libraries.
3605 (delete-file-recursively "third-party/zlib")
3606 (delete-file-recursively "third-party/bzip2")
3607 ;; Replace bundled seqan.
3608 (let* ((seqan-all "third-party/seqan")
3609 (seqan-include (string-append
3610 seqan-all "/core/include")))
3611 (delete-file-recursively seqan-all)
3612 (copy-recursively (string-append (assoc-ref inputs "seqan")
3614 (string-append seqan-include "/seqan")))
3615 ;; We do not replace the bundled MurmurHash as the canonical
3616 ;; repository for this code 'SMHasher' is unsuitable for
3617 ;; providing a library. See
3618 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3620 (add-after 'unpack 'set-cc
3624 ;; It is simpler to test after installation.
3626 (add-after 'install 'post-install-check
3627 (lambda* (#:key inputs outputs #:allow-other-keys)
3628 (let ((out (assoc-ref outputs "out")))
3633 (assoc-ref outputs "out")
3635 (setenv "PYTHONPATH"
3637 (getenv "PYTHONPATH")
3641 (string-take (string-take-right
3642 (assoc-ref inputs "python") 5) 3)
3644 (with-directory-excursion "build"
3645 (zero? (system* "nosetests" "khmer" "--attr"
3646 "!known_failing")))))))))
3649 ("python-nose" ,python-nose)))
3653 ("python-screed" ,python-screed)
3654 ("python-bz2file" ,python-bz2file)
3655 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3656 ;; until the next version of khmer (likely 2.1) is released.
3658 (home-page "https://khmer.readthedocs.org/")
3659 (synopsis "K-mer counting, filtering and graph traversal library")
3660 (description "The khmer software is a set of command-line tools for
3661 working with DNA shotgun sequencing data from genomes, transcriptomes,
3662 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3663 sometimes better. Khmer can also identify and fix problems with shotgun
3665 ;; When building on i686, armhf and mips64el, we get the following error:
3666 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3667 (supported-systems '("x86_64-linux" "aarch64-linux"))
3668 (license license:bsd-3)))
3670 (define-public kaiju
3677 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3679 (file-name (string-append name "-" version ".tar.gz"))
3682 "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7"))))
3683 (build-system gnu-build-system)
3685 `(#:tests? #f ; There are no tests.
3687 (modify-phases %standard-phases
3689 (add-before 'build 'move-to-src-dir
3690 (lambda _ (chdir "src") #t))
3692 (lambda* (#:key inputs outputs #:allow-other-keys)
3693 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3696 (copy-recursively "bin" bin)
3697 (copy-recursively "util" bin))
3702 (home-page "http://kaiju.binf.ku.dk/")
3703 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3704 (description "Kaiju is a program for sensitive taxonomic classification
3705 of high-throughput sequencing reads from metagenomic whole genome sequencing
3707 (license license:gpl3+)))
3712 (version "2.1.0.20151222")
3715 (uri (pypi-uri "MACS2" version))
3718 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3719 (build-system python-build-system)
3721 `(#:python ,python-2 ; only compatible with Python 2.7
3722 #:tests? #f)) ; no test target
3724 `(("python-numpy" ,python2-numpy)))
3725 (home-page "https://github.com/taoliu/MACS/")
3726 (synopsis "Model based analysis for ChIP-Seq data")
3728 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3729 identifying transcript factor binding sites named Model-based Analysis of
3730 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3731 the significance of enriched ChIP regions and it improves the spatial
3732 resolution of binding sites through combining the information of both
3733 sequencing tag position and orientation.")
3734 (license license:bsd-3)))
3736 (define-public mafft
3743 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3744 "-without-extensions-src.tgz"))
3745 (file-name (string-append name "-" version ".tgz"))
3748 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3749 (build-system gnu-build-system)
3751 `(#:tests? #f ; no automated tests, though there are tests in the read me
3752 #:make-flags (let ((out (assoc-ref %outputs "out")))
3753 (list (string-append "PREFIX=" out)
3754 (string-append "BINDIR="
3755 (string-append out "/bin"))))
3757 (modify-phases %standard-phases
3758 (add-after 'unpack 'enter-dir
3759 (lambda _ (chdir "core") #t))
3760 (add-after 'enter-dir 'patch-makefile
3762 ;; on advice from the MAFFT authors, there is no need to
3763 ;; distribute mafft-profile, mafft-distance, or
3764 ;; mafft-homologs.rb as they are too "specialised".
3765 (substitute* "Makefile"
3766 ;; remove mafft-homologs.rb from SCRIPTS
3767 (("^SCRIPTS = mafft mafft-homologs.rb")
3769 ;; remove mafft-homologs from MANPAGES
3770 (("^MANPAGES = mafft.1 mafft-homologs.1")
3771 "MANPAGES = mafft.1")
3772 ;; remove mafft-distance from PROGS
3773 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3774 "PROGS = dvtditr dndfast7 dndblast sextet5")
3775 ;; remove mafft-profile from PROGS
3776 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3777 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3778 (("^rm -f mafft-profile mafft-profile.exe") "#")
3779 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3780 ;; do not install MAN pages in libexec folder
3781 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3782 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3784 (add-after 'enter-dir 'patch-paths
3785 (lambda* (#:key inputs #:allow-other-keys)
3786 (substitute* '("pairash.c"
3788 (("perl") (which "perl"))
3789 (("([\"`| ])awk" _ prefix)
3790 (string-append prefix (which "awk")))
3791 (("grep") (which "grep")))
3794 (add-after 'install 'wrap-programs
3795 (lambda* (#:key outputs #:allow-other-keys)
3796 (let* ((out (assoc-ref outputs "out"))
3797 (bin (string-append out "/bin"))
3798 (path (string-append
3799 (assoc-ref %build-inputs "coreutils") "/bin:")))
3800 (for-each (lambda (file)
3802 `("PATH" ":" prefix (,path))))
3810 ("coreutils" ,coreutils)))
3811 (home-page "http://mafft.cbrc.jp/alignment/software/")
3812 (synopsis "Multiple sequence alignment program")
3814 "MAFFT offers a range of multiple alignment methods for nucleotide and
3815 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3816 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3818 (license (license:non-copyleft
3819 "http://mafft.cbrc.jp/alignment/software/license.txt"
3820 "BSD-3 with different formatting"))))
3829 "https://github.com/marbl/mash/archive/v"
3831 (file-name (string-append name "-" version ".tar.gz"))
3834 "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv"))
3835 (modules '((guix build utils)))
3837 ;; Delete bundled kseq.
3838 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3839 '(delete-file "src/mash/kseq.h"))))
3840 (build-system gnu-build-system)
3842 `(#:tests? #f ; No tests.
3845 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3846 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3847 #:make-flags (list "CC=gcc")
3849 (modify-phases %standard-phases
3850 (add-after 'unpack 'fix-includes
3852 (substitute* '("src/mash/Sketch.cpp"
3853 "src/mash/CommandFind.cpp"
3854 "src/mash/CommandScreen.cpp")
3855 (("^#include \"kseq\\.h\"")
3856 "#include \"htslib/kseq.h\""))
3858 (add-after 'fix-includes 'autoconf
3859 (lambda _ (zero? (system* "autoconf")))))))
3861 `(("autoconf" ,autoconf)
3862 ;; Capnproto and htslib are statically embedded in the final
3863 ;; application. Therefore we also list their licenses, below.
3864 ("capnproto" ,capnproto)
3865 ("htslib" ,htslib)))
3869 (supported-systems '("x86_64-linux"))
3870 (home-page "https://mash.readthedocs.io")
3871 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3872 (description "Mash is a fast sequence distance estimator that uses the
3873 MinHash algorithm and is designed to work with genomes and metagenomes in the
3874 form of assemblies or reads.")
3875 (license (list license:bsd-3 ; Mash
3876 license:expat ; HTSlib and capnproto
3877 license:public-domain ; MurmurHash 3
3878 license:cpl1.0)))) ; Open Bloom Filter
3880 (define-public metabat
3887 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3889 (file-name (string-append name "-" version ".tar.gz"))
3892 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3893 (patches (search-patches "metabat-fix-compilation.patch"))))
3894 (build-system scons-build-system)
3896 `(#:scons ,scons-python2
3898 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3899 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3900 #:tests? #f ;; Tests are run during the build phase.
3902 (modify-phases %standard-phases
3903 (add-after 'unpack 'fix-includes
3905 (substitute* "src/BamUtils.h"
3906 (("^#include \"bam/bam\\.h\"")
3907 "#include \"samtools/bam.h\"")
3908 (("^#include \"bam/sam\\.h\"")
3909 "#include \"samtools/sam.h\""))
3910 (substitute* "src/KseqReader.h"
3911 (("^#include \"bam/kseq\\.h\"")
3912 "#include \"htslib/kseq.h\""))
3914 (add-after 'unpack 'fix-scons
3915 (lambda* (#:key inputs #:allow-other-keys)
3916 (substitute* "SConstruct"
3917 (("^htslib_dir += 'samtools'")
3918 (string-append "htslib_dir = '"
3919 (assoc-ref inputs "htslib")
3921 (("^samtools_dir = 'samtools'")
3922 (string-append "samtools_dir = '"
3923 (assoc-ref inputs "samtools")
3925 (("^findStaticOrShared\\('bam', hts_lib")
3926 (string-append "findStaticOrShared('bam', '"
3927 (assoc-ref inputs "samtools")
3929 ;; Do not distribute README.
3930 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3935 ("samtools" ,samtools)
3938 (home-page "https://bitbucket.org/berkeleylab/metabat")
3940 "Reconstruction of single genomes from complex microbial communities")
3942 "Grouping large genomic fragments assembled from shotgun metagenomic
3943 sequences to deconvolute complex microbial communities, or metagenome binning,
3944 enables the study of individual organisms and their interactions. MetaBAT is
3945 an automated metagenome binning software, which integrates empirical
3946 probabilistic distances of genome abundance and tetranucleotide frequency.")
3947 ;; The source code contains inline assembly.
3948 (supported-systems '("x86_64-linux" "i686-linux"))
3949 (license (license:non-copyleft "file://license.txt"
3950 "See license.txt in the distribution."))))
3952 (define-public minced
3959 "https://github.com/ctSkennerton/minced/archive/"
3961 (file-name (string-append name "-" version ".tar.gz"))
3964 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3965 (build-system gnu-build-system)
3967 `(#:test-target "test"
3969 (modify-phases %standard-phases
3971 (add-before 'check 'fix-test
3973 ;; Fix test for latest version.
3974 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3975 (("minced:0.1.6") "minced:0.2.0"))
3977 (replace 'install ; No install target.
3978 (lambda* (#:key inputs outputs #:allow-other-keys)
3979 (let* ((out (assoc-ref outputs "out"))
3980 (bin (string-append out "/bin"))
3981 (wrapper (string-append bin "/minced")))
3982 ;; Minced comes with a wrapper script that tries to figure out where
3983 ;; it is located before running the JAR. Since these paths are known
3984 ;; to us, we build our own wrapper to avoid coreutils dependency.
3985 (install-file "minced.jar" bin)
3986 (with-output-to-file wrapper
3990 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3991 (assoc-ref inputs "jre") "/bin/java -jar "
3992 bin "/minced.jar \"$@\"\n"))))
3993 (chmod wrapper #o555)))))))
3995 `(("jdk" ,icedtea "jdk")))
3998 ("jre" ,icedtea "out")))
3999 (home-page "https://github.com/ctSkennerton/minced")
4000 (synopsis "Mining CRISPRs in Environmental Datasets")
4002 "MinCED is a program to find Clustered Regularly Interspaced Short
4003 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4004 unassembled metagenomic reads, but is mainly designed for full genomes and
4005 assembled metagenomic sequence.")
4006 (license license:gpl3+)))
4014 (uri (pypi-uri "misopy" version))
4017 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4018 (modules '((guix build utils)))
4020 '(substitute* "setup.py"
4021 ;; Use setuptools, or else the executables are not
4023 (("distutils.core") "setuptools")
4024 ;; use "gcc" instead of "cc" for compilation
4026 "cc.set_executables(
4030 linker_so='gcc -shared'); defines")))))
4031 (build-system python-build-system)
4033 `(#:python ,python-2 ; only Python 2 is supported
4034 #:tests? #f)) ; no "test" target
4036 `(("samtools" ,samtools)
4037 ("python-numpy" ,python2-numpy)
4038 ("python-pysam" ,python2-pysam)
4039 ("python-scipy" ,python2-scipy)
4040 ("python-matplotlib" ,python2-matplotlib)))
4042 `(("python-mock" ,python2-mock) ;for tests
4043 ("python-pytz" ,python2-pytz))) ;for tests
4044 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4045 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4047 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4048 the expression level of alternatively spliced genes from RNA-Seq data, and
4049 identifies differentially regulated isoforms or exons across samples. By
4050 modeling the generative process by which reads are produced from isoforms in
4051 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4052 that a read originated from a particular isoform.")
4053 (license license:gpl2)))
4055 (define-public muscle
4058 (version "3.8.1551")
4060 (method url-fetch/tarbomb)
4062 "http://www.drive5.com/muscle/muscle_src_"
4066 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4067 (build-system gnu-build-system)
4069 `(#:make-flags (list "LDLIBS = -lm")
4071 (modify-phases %standard-phases
4074 ;; There are no tests, so just test if it runs.
4075 (lambda _ (zero? (system* "./muscle" "-version"))))
4077 (lambda* (#:key outputs #:allow-other-keys)
4078 (let* ((out (assoc-ref outputs "out"))
4079 (bin (string-append out "/bin")))
4080 (install-file "muscle" bin)))))))
4081 (home-page "http://www.drive5.com/muscle")
4082 (synopsis "Multiple sequence alignment program")
4084 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4085 program for nucleotide and protein sequences.")
4086 ;; License information found in 'muscle -h' and usage.cpp.
4087 (license license:public-domain)))
4089 (define-public newick-utils
4090 ;; There are no recent releases so we package from git.
4091 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4093 (name "newick-utils")
4094 (version (string-append "1.6-1." (string-take commit 8)))
4098 (url "https://github.com/tjunier/newick_utils.git")
4100 (file-name (string-append name "-" version "-checkout"))
4103 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4104 (build-system gnu-build-system)
4107 (modify-phases %standard-phases
4108 (add-after 'unpack 'autoconf
4109 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4111 ;; XXX: TODO: Enable Lua and Guile bindings.
4112 ;; https://github.com/tjunier/newick_utils/issues/13
4113 `(("libxml2" ,libxml2)
4117 `(("autoconf" ,autoconf)
4118 ("automake" ,automake)
4119 ("libtool" ,libtool)))
4120 (synopsis "Programs for working with newick format phylogenetic trees")
4122 "Newick-utils is a suite of utilities for processing phylogenetic trees
4123 in Newick format. Functions include re-rooting, extracting subtrees,
4124 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4125 (home-page "https://github.com/tjunier/newick_utils")
4126 (license license:bsd-3))))
4135 "https://github.com/wwood/OrfM/releases/download/v"
4136 version "/orfm-" version ".tar.gz"))
4139 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4140 (build-system gnu-build-system)
4141 (inputs `(("zlib" ,zlib)))
4143 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4144 ("ruby-rspec" ,ruby-rspec)
4146 (synopsis "Simple and not slow open reading frame (ORF) caller")
4148 "An ORF caller finds stretches of DNA that, when translated, are not
4149 interrupted by stop codons. OrfM finds and prints these ORFs.")
4150 (home-page "https://github.com/wwood/OrfM")
4151 (license license:lgpl3+)))
4153 (define-public pplacer
4154 (let ((commit "g807f6f3"))
4157 ;; The commit should be updated with each version change.
4158 (version "1.1.alpha19")
4162 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4164 (file-name (string-append name "-" version ".tar.gz"))
4166 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4167 (build-system ocaml-build-system)
4169 `(#:ocaml ,ocaml-4.01
4170 #:findlib ,ocaml4.01-findlib
4171 #:modules ((guix build ocaml-build-system)
4175 (modify-phases %standard-phases
4177 (add-after 'unpack 'replace-bundled-cddlib
4178 (lambda* (#:key inputs #:allow-other-keys)
4179 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4180 (local-dir "cddlib_guix"))
4182 (with-directory-excursion local-dir
4183 (system* "tar" "xvf" cddlib-src))
4184 (let ((cddlib-src-folder
4185 (string-append local-dir "/"
4186 (list-ref (scandir local-dir) 2)
4191 (string-append "cdd_src/" (basename file))))
4192 (find-files cddlib-src-folder ".*[ch]$")))
4194 (add-after 'unpack 'fix-makefile
4196 ;; Remove system calls to 'git'.
4197 (substitute* "Makefile"
4198 (("^DESCRIPT:=pplacer-.*")
4200 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4201 (substitute* "myocamlbuild.ml"
4202 (("git describe --tags --long .*\\\" with")
4204 "echo -n v" ,version "-" ,commit "\" with")))
4207 (lambda* (#:key outputs #:allow-other-keys)
4208 (let* ((out (assoc-ref outputs "out"))
4209 (bin (string-append out "/bin")))
4210 (copy-recursively "bin" bin))
4215 ("ocaml-ounit" ,ocaml4.01-ounit)
4216 ("ocaml-batteries" ,ocaml4.01-batteries)
4217 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4218 ("ocaml-csv" ,ocaml4.01-csv)
4219 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4220 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4221 ("ocaml-mcl" ,ocaml4.01-mcl)
4222 ("ocaml-gsl" ,ocaml4.01-gsl)
4223 ("cddlib-src" ,(package-source cddlib))))
4225 `(("pplacer-scripts" ,pplacer-scripts)))
4226 (synopsis "Phylogenetic placement of biological sequences")
4228 "Pplacer places query sequences on a fixed reference phylogenetic tree
4229 to maximize phylogenetic likelihood or posterior probability according to a
4230 reference alignment. Pplacer is designed to be fast, to give useful
4231 information about uncertainty, and to offer advanced visualization and
4232 downstream analysis.")
4233 (home-page "http://matsen.fhcrc.org/pplacer")
4234 (license license:gpl3))))
4236 ;; This package is installed alongside 'pplacer'. It is a separate package so
4237 ;; that it can use the python-build-system for the scripts that are
4238 ;; distributed alongside the main OCaml binaries.
4239 (define pplacer-scripts
4242 (name "pplacer-scripts")
4243 (build-system python-build-system)
4245 `(#:python ,python-2
4247 (modify-phases %standard-phases
4248 (add-after 'unpack 'enter-scripts-dir
4249 (lambda _ (chdir "scripts")))
4252 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4253 (add-after 'install 'wrap-executables
4254 (lambda* (#:key inputs outputs #:allow-other-keys)
4255 (let* ((out (assoc-ref outputs "out"))
4256 (bin (string-append out "/bin")))
4257 (let ((path (string-append
4258 (assoc-ref inputs "hmmer") "/bin:"
4259 (assoc-ref inputs "infernal") "/bin")))
4261 (wrap-program (string-append bin "/refpkg_align.py")
4262 `("PATH" ":" prefix (,path))))
4263 (let ((path (string-append
4264 (assoc-ref inputs "hmmer") "/bin")))
4265 (wrap-program (string-append bin "/hrefpkg_query.py")
4266 `("PATH" ":" prefix (,path)))))
4269 `(("infernal" ,infernal)
4272 `(("python-biopython" ,python2-biopython)
4273 ("taxtastic" ,taxtastic)))
4274 (synopsis "Pplacer Python scripts")))
4276 (define-public python2-pbcore
4278 (name "python2-pbcore")
4282 (uri (pypi-uri "pbcore" version))
4285 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4286 (build-system python-build-system)
4287 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4289 `(("python-cython" ,python2-cython)
4290 ("python-numpy" ,python2-numpy)
4291 ("python-pysam" ,python2-pysam)
4292 ("python-h5py" ,python2-h5py)))
4294 `(("python-nose" ,python2-nose)
4295 ("python-sphinx" ,python2-sphinx)
4296 ("python-pyxb" ,python2-pyxb)))
4297 (home-page "http://pacificbiosciences.github.io/pbcore/")
4298 (synopsis "Library for reading and writing PacBio data files")
4300 "The pbcore package provides Python APIs for interacting with PacBio data
4301 files and writing bioinformatics applications.")
4302 (license license:bsd-3)))
4304 (define-public python2-warpedlmm
4306 (name "python2-warpedlmm")
4312 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4316 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4317 (build-system python-build-system)
4319 `(#:python ,python-2)) ; requires Python 2.7
4321 `(("python-scipy" ,python2-scipy)
4322 ("python-numpy" ,python2-numpy)
4323 ("python-matplotlib" ,python2-matplotlib)
4324 ("python-fastlmm" ,python2-fastlmm)
4325 ("python-pandas" ,python2-pandas)
4326 ("python-pysnptools" ,python2-pysnptools)))
4328 `(("python-mock" ,python2-mock)
4329 ("python-nose" ,python2-nose)
4331 (home-page "https://github.com/PMBio/warpedLMM")
4332 (synopsis "Implementation of warped linear mixed models")
4334 "WarpedLMM is a Python implementation of the warped linear mixed model,
4335 which automatically learns an optimal warping function (or transformation) for
4336 the phenotype as it models the data.")
4337 (license license:asl2.0)))
4339 (define-public pbtranscript-tofu
4340 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4342 (name "pbtranscript-tofu")
4343 (version (string-append "2.2.3." (string-take commit 7)))
4347 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4349 (file-name (string-append name "-" version "-checkout"))
4352 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4353 (modules '((guix build utils)))
4356 ;; remove bundled Cython sources
4357 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4359 (build-system python-build-system)
4361 `(#:python ,python-2
4362 ;; FIXME: Tests fail with "No such file or directory:
4363 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4366 (modify-phases %standard-phases
4367 (add-after 'unpack 'enter-directory
4369 (chdir "pbtranscript-tofu/pbtranscript/")
4371 ;; With setuptools version 18.0 and later this setup.py hack causes
4372 ;; a build error, so we disable it.
4373 (add-after 'enter-directory 'patch-setuppy
4375 (substitute* "setup.py"
4376 (("if 'setuptools.extension' in sys.modules:")
4380 `(("python-numpy" ,python2-numpy)
4381 ("python-bx-python" ,python2-bx-python)
4382 ("python-networkx" ,python2-networkx)
4383 ("python-scipy" ,python2-scipy)
4384 ("python-pbcore" ,python2-pbcore)
4385 ("python-h5py" ,python2-h5py)))
4387 `(("python-cython" ,python2-cython)
4388 ("python-nose" ,python2-nose)))
4389 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4390 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4392 "pbtranscript-tofu contains scripts to analyze transcriptome data
4393 generated using the PacBio Iso-Seq protocol.")
4394 (license license:bsd-3))))
4396 (define-public prank
4403 "http://wasabiapp.org/download/prank/prank.source."
4407 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4408 (build-system gnu-build-system)
4411 (modify-phases %standard-phases
4412 (add-after 'unpack 'enter-src-dir
4416 (add-after 'unpack 'remove-m64-flag
4417 ;; Prank will build with the correct 'bit-ness' without this flag
4418 ;; and this allows building on 32-bit machines.
4419 (lambda _ (substitute* "src/Makefile"
4424 (lambda* (#:key outputs #:allow-other-keys)
4425 (let* ((out (assoc-ref outputs "out"))
4426 (bin (string-append out "/bin"))
4427 (man (string-append out "/share/man/man1"))
4428 (path (string-append
4429 (assoc-ref %build-inputs "mafft") "/bin:"
4430 (assoc-ref %build-inputs "exonerate") "/bin:"
4431 (assoc-ref %build-inputs "bppsuite") "/bin")))
4432 (install-file "prank" bin)
4433 (wrap-program (string-append bin "/prank")
4434 `("PATH" ":" prefix (,path)))
4435 (install-file "prank.1" man))
4439 ("exonerate" ,exonerate)
4440 ("bppsuite" ,bppsuite)))
4441 (home-page "http://wasabiapp.org/software/prank/")
4442 (synopsis "Probabilistic multiple sequence alignment program")
4444 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4445 codon and amino-acid sequences. It is based on a novel algorithm that treats
4446 insertions correctly and avoids over-estimation of the number of deletion
4447 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4448 in phylogenetics and correctly takes into account the evolutionary distances
4449 between sequences. Lastly, PRANK allows for defining a potential structure
4450 for sequences to be aligned and then, simultaneously with the alignment,
4451 predicts the locations of structural units in the sequences.")
4452 (license license:gpl2+)))
4454 (define-public proteinortho
4456 (name "proteinortho")
4463 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4464 version "_src.tar.gz"))
4467 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4468 (build-system gnu-build-system)
4470 `(#:test-target "test"
4472 (modify-phases %standard-phases
4474 ;; There is no configure script, so we modify the Makefile directly.
4475 (lambda* (#:key outputs #:allow-other-keys)
4476 (substitute* "Makefile"
4479 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4481 (add-before 'install 'make-install-directory
4482 ;; The install directory is not created during 'make install'.
4483 (lambda* (#:key outputs #:allow-other-keys)
4484 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4486 (add-after 'install 'wrap-programs
4487 (lambda* (#:key inputs outputs #:allow-other-keys)
4488 (let* ((path (getenv "PATH"))
4489 (out (assoc-ref outputs "out"))
4490 (binary (string-append out "/bin/proteinortho5.pl")))
4491 (wrap-program binary `("PATH" ":" prefix (,path))))
4495 ("python" ,python-2)
4496 ("blast+" ,blast+)))
4497 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4498 (synopsis "Detect orthologous genes across species")
4500 "Proteinortho is a tool to detect orthologous genes across different
4501 species. For doing so, it compares similarities of given gene sequences and
4502 clusters them to find significant groups. The algorithm was designed to handle
4503 large-scale data and can be applied to hundreds of species at once.")
4504 (license license:gpl2+)))
4506 (define-public pyicoteo
4513 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4514 "pyicoteo/get/v" version ".tar.bz2"))
4515 (file-name (string-append name "-" version ".tar.bz2"))
4518 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4519 (build-system python-build-system)
4521 `(#:python ,python-2 ; does not work with Python 3
4522 #:tests? #f)) ; there are no tests
4524 `(("python2-matplotlib" ,python2-matplotlib)))
4525 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4526 (synopsis "Analyze high-throughput genetic sequencing data")
4528 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4529 sequencing data. It works with genomic coordinates. There are currently six
4530 different command-line tools:
4533 @item pyicoregion: for generating exploratory regions automatically;
4534 @item pyicoenrich: for differential enrichment between two conditions;
4535 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4536 @item pyicos: for genomic coordinates manipulation;
4537 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4538 @item pyicount: to count how many reads from N experiment files overlap in a
4540 @item pyicotrocol: to combine operations from pyicoteo.
4542 (license license:gpl3+)))
4544 (define-public prodigal
4551 "https://github.com/hyattpd/Prodigal/archive/v"
4553 (file-name (string-append name "-" version ".tar.gz"))
4556 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4557 (build-system gnu-build-system)
4559 `(#:tests? #f ;no check target
4560 #:make-flags (list (string-append "INSTALLDIR="
4561 (assoc-ref %outputs "out")
4564 (modify-phases %standard-phases
4565 (delete 'configure))))
4566 (home-page "http://prodigal.ornl.gov")
4567 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4569 "Prodigal runs smoothly on finished genomes, draft genomes, and
4570 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4571 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4572 partial genes, and identifies translation initiation sites.")
4573 (license license:gpl3+)))
4575 (define-public roary
4583 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4587 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4588 (build-system perl-build-system)
4591 (modify-phases %standard-phases
4596 ;; The tests are not run by default, so we run each test file
4598 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4600 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4601 (getenv "PERL5LIB")))
4602 (zero? (length (filter (lambda (file)
4603 (display file)(display "\n")
4604 (not (zero? (system* "perl" file))))
4605 (find-files "t" ".*\\.t$"))))))
4607 ;; There is no 'install' target in the Makefile.
4608 (lambda* (#:key outputs #:allow-other-keys)
4609 (let* ((out (assoc-ref outputs "out"))
4610 (bin (string-append out "/bin"))
4611 (perl (string-append out "/lib/perl5/site_perl"))
4612 (roary-plots "contrib/roary_plots"))
4615 (copy-recursively "bin" bin)
4616 (copy-recursively "lib" perl)
4618 (add-after 'install 'wrap-programs
4619 (lambda* (#:key inputs outputs #:allow-other-keys)
4620 (let* ((out (assoc-ref outputs "out"))
4621 (perl5lib (getenv "PERL5LIB"))
4622 (path (getenv "PATH")))
4623 (for-each (lambda (prog)
4624 (let ((binary (string-append out "/" prog)))
4625 (wrap-program binary
4626 `("PERL5LIB" ":" prefix
4627 (,(string-append perl5lib ":" out
4628 "/lib/perl5/site_perl"))))
4629 (wrap-program binary
4631 (,(string-append path ":" out "/bin"))))))
4632 (find-files "bin" ".*[^R]$"))
4634 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4635 (r-site-lib (getenv "R_LIBS_SITE"))
4637 (string-append (assoc-ref inputs "coreutils") "/bin")))
4639 `("R_LIBS_SITE" ":" prefix
4640 (,(string-append r-site-lib ":" out "/site-library/"))))
4643 (,(string-append coreutils-path ":" out "/bin"))))))
4646 `(("perl-env-path" ,perl-env-path)
4647 ("perl-test-files" ,perl-test-files)
4648 ("perl-test-most" ,perl-test-most)
4649 ("perl-test-output" ,perl-test-output)))
4651 `(("perl-array-utils" ,perl-array-utils)
4652 ("bioperl" ,bioperl-minimal)
4653 ("perl-digest-md5-file" ,perl-digest-md5-file)
4654 ("perl-exception-class" ,perl-exception-class)
4655 ("perl-file-find-rule" ,perl-file-find-rule)
4656 ("perl-file-grep" ,perl-file-grep)
4657 ("perl-file-slurper" ,perl-file-slurper)
4658 ("perl-file-which" ,perl-file-which)
4659 ("perl-graph" ,perl-graph)
4660 ("perl-graph-readwrite" ,perl-graph-readwrite)
4661 ("perl-log-log4perl" ,perl-log-log4perl)
4662 ("perl-moose" ,perl-moose)
4663 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4664 ("perl-text-csv" ,perl-text-csv)
4665 ("bedtools" ,bedtools)
4669 ("parallel" ,parallel)
4672 ("fasttree" ,fasttree)
4676 ("r-minimal" ,r-minimal)
4677 ("r-ggplot2" ,r-ggplot2)
4678 ("coreutils" ,coreutils)))
4679 (home-page "http://sanger-pathogens.github.io/Roary")
4680 (synopsis "High speed stand-alone pan genome pipeline")
4682 "Roary is a high speed stand alone pan genome pipeline, which takes
4683 annotated assemblies in GFF3 format (produced by the Prokka program) and
4684 calculates the pan genome. Using a standard desktop PC, it can analyse
4685 datasets with thousands of samples, without compromising the quality of the
4686 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4687 single processor. Roary is not intended for metagenomics or for comparing
4688 extremely diverse sets of genomes.")
4689 (license license:gpl3)))
4691 (define-public raxml
4700 "https://github.com/stamatak/standard-RAxML/archive/v"
4702 (file-name (string-append name "-" version ".tar.gz"))
4705 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4706 (build-system gnu-build-system)
4708 `(#:tests? #f ; There are no tests.
4709 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4710 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4712 (modify-phases %standard-phases
4715 (lambda* (#:key outputs #:allow-other-keys)
4716 (let* ((out (assoc-ref outputs "out"))
4717 (bin (string-append out "/bin"))
4718 (executable "raxmlHPC-HYBRID"))
4719 (install-file executable bin)
4720 (symlink (string-append bin "/" executable) "raxml"))
4723 `(("openmpi" ,openmpi)))
4724 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4725 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4727 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4729 ;; The source includes x86 specific code
4730 (supported-systems '("x86_64-linux" "i686-linux"))
4731 (license license:gpl2+)))
4741 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4744 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4745 (patches (search-patches "rsem-makefile.patch"))
4746 (modules '((guix build utils)))
4749 ;; remove bundled copy of boost
4750 (delete-file-recursively "boost")
4752 (build-system gnu-build-system)
4754 `(#:tests? #f ;no "check" target
4756 (modify-phases %standard-phases
4757 ;; No "configure" script.
4758 ;; Do not build bundled samtools library.
4761 (substitute* "Makefile"
4762 (("^all : sam/libbam.a") "all : "))
4765 (lambda* (#:key outputs #:allow-other-keys)
4766 (let* ((out (string-append (assoc-ref outputs "out")))
4767 (bin (string-append out "/bin/"))
4768 (perl (string-append out "/lib/perl5/site_perl")))
4771 (for-each (lambda (file)
4772 (install-file file bin))
4773 (find-files "." "rsem-.*"))
4774 (install-file "rsem_perl_utils.pm" perl))
4777 'install 'wrap-program
4778 (lambda* (#:key outputs #:allow-other-keys)
4779 (let ((out (assoc-ref outputs "out")))
4780 (for-each (lambda (prog)
4781 (wrap-program (string-append out "/bin/" prog)
4782 `("PERL5LIB" ":" prefix
4783 (,(string-append out "/lib/perl5/site_perl")))))
4784 '("rsem-plot-transcript-wiggles"
4785 "rsem-calculate-expression"
4786 "rsem-generate-ngvector"
4788 "rsem-prepare-reference")))
4792 ("ncurses" ,ncurses)
4793 ("r-minimal" ,r-minimal)
4795 ("samtools" ,samtools-0.1)
4797 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4798 (synopsis "Estimate gene expression levels from RNA-Seq data")
4800 "RSEM is a software package for estimating gene and isoform expression
4801 levels from RNA-Seq data. The RSEM package provides a user-friendly
4802 interface, supports threads for parallel computation of the EM algorithm,
4803 single-end and paired-end read data, quality scores, variable-length reads and
4804 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4805 interval estimates for expression levels. For visualization, it can generate
4806 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4807 (license license:gpl3+)))
4809 (define-public rseqc
4817 (string-append "mirror://sourceforge/rseqc/"
4818 "RSeQC-" version ".tar.gz"))
4820 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4821 (modules '((guix build utils)))
4824 ;; remove bundled copy of pysam
4825 (delete-file-recursively "lib/pysam")
4826 (substitute* "setup.py"
4827 ;; remove dependency on outdated "distribute" module
4828 (("^from distribute_setup import use_setuptools") "")
4829 (("^use_setuptools\\(\\)") "")
4830 ;; do not use bundled copy of pysam
4831 (("^have_pysam = False") "have_pysam = True"))))))
4832 (build-system python-build-system)
4833 (arguments `(#:python ,python-2))
4835 `(("python-cython" ,python2-cython)
4836 ("python-pysam" ,python2-pysam)
4837 ("python-numpy" ,python2-numpy)
4840 `(("python-nose" ,python2-nose)))
4841 (home-page "http://rseqc.sourceforge.net/")
4842 (synopsis "RNA-seq quality control package")
4844 "RSeQC provides a number of modules that can comprehensively evaluate
4845 high throughput sequence data, especially RNA-seq data. Some basic modules
4846 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4847 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4848 distribution, coverage uniformity, strand specificity, etc.")
4849 (license license:gpl3+)))
4852 ;; There are no release tarballs. According to the installation
4853 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4854 ;; stable release is identified by this changeset ID.
4855 (let ((changeset "2329130")
4859 (version (string-append "0-" revision "." changeset))
4863 (url "https://bitbucket.org/libsleipnir/sleipnir")
4864 (changeset changeset)))
4865 (file-name (string-append name "-" version "-checkout"))
4868 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4869 (build-system gnu-build-system)
4871 `(#:modules ((srfi srfi-1)
4872 (guix build gnu-build-system)
4875 (let ((dirs '("SeekMiner"
4881 (modify-phases %standard-phases
4882 (add-before 'configure 'bootstrap
4884 (zero? (system* "bash" "gen_auto"))))
4885 (add-after 'build 'build-additional-tools
4886 (lambda* (#:key make-flags #:allow-other-keys)
4887 (every (lambda (dir)
4888 (with-directory-excursion (string-append "tools/" dir)
4889 (zero? (apply system* "make" make-flags))))
4891 (add-after 'install 'install-additional-tools
4892 (lambda* (#:key make-flags #:allow-other-keys)
4893 (fold (lambda (dir result)
4894 (with-directory-excursion (string-append "tools/" dir)
4896 (zero? (apply system*
4897 `("make" ,@make-flags "install"))))))
4903 ("readline" ,readline)
4904 ("gengetopt" ,gengetopt)
4905 ("log4cpp" ,log4cpp)))
4907 `(("autoconf" ,autoconf)
4908 ("automake" ,automake)
4910 (home-page "http://seek.princeton.edu")
4911 (synopsis "Gene co-expression search engine")
4913 "SEEK is a computational gene co-expression search engine. SEEK provides
4914 biologists with a way to navigate the massive human expression compendium that
4915 now contains thousands of expression datasets. SEEK returns a robust ranking
4916 of co-expressed genes in the biological area of interest defined by the user's
4917 query genes. It also prioritizes thousands of expression datasets according
4918 to the user's query of interest.")
4919 (license license:cc-by3.0))))
4921 (define-public samtools
4929 (string-append "mirror://sourceforge/samtools/samtools/"
4930 version "/samtools-" version ".tar.bz2"))
4933 "18acyqysbxpydlc44lqv2hpp57l06bs9a3yqmcvjk8va2xrrdc77"))))
4934 (build-system gnu-build-system)
4936 `(#:modules ((ice-9 ftw)
4938 (guix build gnu-build-system)
4940 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4941 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4943 (modify-phases %standard-phases
4944 (add-after 'unpack 'patch-tests
4946 (substitute* "test/test.pl"
4947 ;; The test script calls out to /bin/bash
4948 (("/bin/bash") (which "bash")))
4950 (add-after 'install 'install-library
4951 (lambda* (#:key outputs #:allow-other-keys)
4952 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4953 (install-file "libbam.a" lib)
4955 (add-after 'install 'install-headers
4956 (lambda* (#:key outputs #:allow-other-keys)
4957 (let ((include (string-append (assoc-ref outputs "out")
4958 "/include/samtools/")))
4959 (for-each (lambda (file)
4960 (install-file file include))
4961 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4963 (native-inputs `(("pkg-config" ,pkg-config)))
4965 `(("htslib" ,htslib)
4966 ("ncurses" ,ncurses)
4970 (home-page "http://samtools.sourceforge.net")
4971 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4973 "Samtools implements various utilities for post-processing nucleotide
4974 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4975 variant calling (in conjunction with bcftools), and a simple alignment
4977 (license license:expat)))
4979 (define-public samtools-0.1
4980 ;; This is the most recent version of the 0.1 line of samtools. The input
4981 ;; and output formats differ greatly from that used and produced by samtools
4982 ;; 1.x and is still used in many bioinformatics pipelines.
4983 (package (inherit samtools)
4989 (string-append "mirror://sourceforge/samtools/samtools/"
4990 version "/samtools-" version ".tar.bz2"))
4992 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4994 `(#:tests? #f ;no "check" target
4995 ,@(substitute-keyword-arguments (package-arguments samtools)
4996 ((#:make-flags flags)
4997 `(cons "LIBCURSES=-lncurses" ,flags))
4999 `(modify-phases ,phases
5001 (lambda* (#:key outputs #:allow-other-keys)
5002 (let ((bin (string-append
5003 (assoc-ref outputs "out") "/bin")))
5005 (install-file "samtools" bin)
5007 (delete 'patch-tests)
5008 (delete 'configure))))))))
5010 (define-public mosaik
5011 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5016 ;; There are no release tarballs nor tags.
5019 (url "https://github.com/wanpinglee/MOSAIK.git")
5021 (file-name (string-append name "-" version))
5024 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5025 (build-system gnu-build-system)
5027 `(#:tests? #f ; no tests
5028 #:make-flags (list "CC=gcc")
5030 (modify-phases %standard-phases
5032 (lambda _ (chdir "src") #t))
5034 (lambda* (#:key outputs #:allow-other-keys)
5035 (let ((bin (string-append (assoc-ref outputs "out")
5038 (copy-recursively "../bin" bin)
5043 (supported-systems '("x86_64-linux"))
5044 (home-page "https://github.com/wanpinglee/MOSAIK")
5045 (synopsis "Map nucleotide sequence reads to reference genomes")
5047 "MOSAIK is a program for mapping second and third-generation sequencing
5048 reads to a reference genome. MOSAIK can align reads generated by all the
5049 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5050 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5051 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5052 ;; code released into the public domain:
5053 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5054 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5055 (license (list license:gpl2+ license:public-domain)))))
5057 (define-public ngs-sdk
5065 (string-append "https://github.com/ncbi/ngs/archive/"
5067 (file-name (string-append name "-" version ".tar.gz"))
5070 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5071 (build-system gnu-build-system)
5073 `(#:parallel-build? #f ; not supported
5074 #:tests? #f ; no "check" target
5076 (modify-phases %standard-phases
5078 (lambda* (#:key outputs #:allow-other-keys)
5079 (let ((out (assoc-ref outputs "out")))
5080 ;; Allow 'konfigure.perl' to find 'package.prl'.
5082 (string-append ".:" (getenv "PERL5LIB")))
5084 ;; The 'configure' script doesn't recognize things like
5085 ;; '--enable-fast-install'.
5086 (zero? (system* "./configure"
5087 (string-append "--build-prefix=" (getcwd) "/build")
5088 (string-append "--prefix=" out))))))
5089 (add-after 'unpack 'enter-dir
5090 (lambda _ (chdir "ngs-sdk") #t)))))
5091 (native-inputs `(("perl" ,perl)))
5092 ;; According to the test
5093 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5094 ;; in ngs-sdk/setup/konfigure.perl
5095 (supported-systems '("i686-linux" "x86_64-linux"))
5096 (home-page "https://github.com/ncbi/ngs")
5097 (synopsis "API for accessing Next Generation Sequencing data")
5099 "NGS is a domain-specific API for accessing reads, alignments and pileups
5100 produced from Next Generation Sequencing. The API itself is independent from
5101 any particular back-end implementation, and supports use of multiple back-ends
5103 (license license:public-domain)))
5105 (define-public java-ngs
5106 (package (inherit ngs-sdk)
5109 `(,@(substitute-keyword-arguments
5110 `(#:modules ((guix build gnu-build-system)
5114 ,@(package-arguments ngs-sdk))
5116 `(modify-phases ,phases
5117 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5119 `(("jdk" ,icedtea "jdk")
5120 ("ngs-sdk" ,ngs-sdk)))
5121 (synopsis "Java bindings for NGS SDK")))
5123 (define-public ncbi-vdb
5131 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5133 (file-name (string-append name "-" version ".tar.gz"))
5136 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5137 (build-system gnu-build-system)
5139 `(#:parallel-build? #f ; not supported
5140 #:tests? #f ; no "check" target
5142 (modify-phases %standard-phases
5143 (add-before 'configure 'set-perl-search-path
5145 ;; Work around "dotless @INC" build failure.
5147 (string-append (getcwd) "/setup:"
5148 (getenv "PERL5LIB")))
5151 (lambda* (#:key inputs outputs #:allow-other-keys)
5152 (let ((out (assoc-ref outputs "out")))
5153 ;; Override include path for libmagic
5154 (substitute* "setup/package.prl"
5155 (("name => 'magic', Include => '/usr/include'")
5156 (string-append "name=> 'magic', Include => '"
5157 (assoc-ref inputs "libmagic")
5160 ;; Install kdf5 library (needed by sra-tools)
5161 (substitute* "build/Makefile.install"
5162 (("LIBRARIES_TO_INSTALL =")
5163 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5165 (substitute* "build/Makefile.env"
5166 (("CFLAGS =" prefix)
5167 (string-append prefix "-msse2 ")))
5169 ;; Override search path for ngs-java
5170 (substitute* "setup/package.prl"
5171 (("/usr/local/ngs/ngs-java")
5172 (assoc-ref inputs "java-ngs")))
5174 ;; The 'configure' script doesn't recognize things like
5175 ;; '--enable-fast-install'.
5178 (string-append "--build-prefix=" (getcwd) "/build")
5179 (string-append "--prefix=" (assoc-ref outputs "out"))
5180 (string-append "--debug")
5181 (string-append "--with-xml2-prefix="
5182 (assoc-ref inputs "libxml2"))
5183 (string-append "--with-ngs-sdk-prefix="
5184 (assoc-ref inputs "ngs-sdk"))
5185 (string-append "--with-hdf5-prefix="
5186 (assoc-ref inputs "hdf5")))))))
5187 (add-after 'install 'install-interfaces
5188 (lambda* (#:key outputs #:allow-other-keys)
5189 ;; Install interface libraries. On i686 the interface libraries
5190 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5191 ;; architecture name ("i386") instead of the target system prefix
5193 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5194 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5195 ,(system->linux-architecture
5196 (or (%current-target-system)
5199 (string-append (assoc-ref outputs "out")
5201 ;; Install interface headers
5202 (copy-recursively "interfaces"
5203 (string-append (assoc-ref outputs "out")
5206 ;; These files are needed by sra-tools.
5207 (add-after 'install 'install-configuration-files
5208 (lambda* (#:key outputs #:allow-other-keys)
5209 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5211 (install-file "libs/kfg/default.kfg" target)
5212 (install-file "libs/kfg/certs.kfg" target))
5215 `(("libxml2" ,libxml2)
5216 ("ngs-sdk" ,ngs-sdk)
5217 ("java-ngs" ,java-ngs)
5220 (native-inputs `(("perl" ,perl)))
5221 ;; NCBI-VDB requires SSE capability.
5222 (supported-systems '("i686-linux" "x86_64-linux"))
5223 (home-page "https://github.com/ncbi/ncbi-vdb")
5224 (synopsis "Database engine for genetic information")
5226 "The NCBI-VDB library implements a highly compressed columnar data
5227 warehousing engine that is most often used to store genetic information.
5228 Databases are stored in a portable image within the file system, and can be
5229 accessed/downloaded on demand across HTTP.")
5230 (license license:public-domain)))
5232 (define-public plink
5240 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5241 version "-src.zip"))
5243 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5244 (patches (search-patches "plink-1.07-unclobber-i.patch"
5245 "plink-endian-detection.patch"))))
5246 (build-system gnu-build-system)
5248 '(#:tests? #f ;no "check" target
5249 #:make-flags (list (string-append "LIB_LAPACK="
5250 (assoc-ref %build-inputs "lapack")
5251 "/lib/liblapack.so")
5254 ;; disable phoning home
5257 (modify-phases %standard-phases
5258 ;; no "configure" script
5261 (lambda* (#:key outputs #:allow-other-keys)
5262 (let ((bin (string-append (assoc-ref outputs "out")
5264 (install-file "plink" bin)
5268 ("lapack" ,lapack)))
5270 `(("unzip" ,unzip)))
5271 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5272 (synopsis "Whole genome association analysis toolset")
5274 "PLINK is a whole genome association analysis toolset, designed to
5275 perform a range of basic, large-scale analyses in a computationally efficient
5276 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5277 so there is no support for steps prior to this (e.g. study design and
5278 planning, generating genotype or CNV calls from raw data). Through
5279 integration with gPLINK and Haploview, there is some support for the
5280 subsequent visualization, annotation and storage of results.")
5281 ;; Code is released under GPLv2, except for fisher.h, which is under
5283 (license (list license:gpl2 license:lgpl2.1+))))
5285 (define-public plink-ng
5286 (package (inherit plink)
5292 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5294 (file-name (string-append name "-" version ".tar.gz"))
5296 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5297 (build-system gnu-build-system)
5299 '(#:tests? #f ;no "check" target
5300 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5301 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5303 "-f" "Makefile.std")
5305 (modify-phases %standard-phases
5306 (add-after 'unpack 'chdir
5307 (lambda _ (chdir "1.9") #t))
5308 (delete 'configure) ; no "configure" script
5310 (lambda* (#:key outputs #:allow-other-keys)
5311 (let ((bin (string-append (assoc-ref outputs "out")
5313 (install-file "plink" bin)
5318 ("openblas" ,openblas)))
5319 (home-page "https://www.cog-genomics.org/plink/")
5320 (license license:gpl3+)))
5322 (define-public smithlab-cpp
5323 (let ((revision "1")
5324 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5326 (name "smithlab-cpp")
5327 (version (string-append "0." revision "." (string-take commit 7)))
5331 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5333 (file-name (string-append name "-" version "-checkout"))
5336 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5337 (build-system gnu-build-system)
5339 `(#:modules ((guix build gnu-build-system)
5342 #:tests? #f ;no "check" target
5344 (modify-phases %standard-phases
5345 (add-after 'unpack 'use-samtools-headers
5347 (substitute* '("SAM.cpp"
5349 (("sam.h") "samtools/sam.h"))
5352 (lambda* (#:key outputs #:allow-other-keys)
5353 (let* ((out (assoc-ref outputs "out"))
5354 (lib (string-append out "/lib"))
5355 (include (string-append out "/include/smithlab-cpp")))
5358 (for-each (cut install-file <> lib)
5359 (find-files "." "\\.o$"))
5360 (for-each (cut install-file <> include)
5361 (find-files "." "\\.hpp$")))
5363 (delete 'configure))))
5365 `(("samtools" ,samtools-0.1)
5367 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5368 (synopsis "C++ helper library for functions used in Smith lab projects")
5370 "Smithlab CPP is a C++ library that includes functions used in many of
5371 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5372 structures, classes for genomic regions, mapped sequencing reads, etc.")
5373 (license license:gpl3+))))
5375 (define-public preseq
5381 (uri (string-append "https://github.com/smithlabcode/"
5382 "preseq/archive/v" version ".tar.gz"))
5383 (file-name (string-append name "-" version ".tar.gz"))
5385 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5386 (modules '((guix build utils)))
5388 ;; Remove bundled samtools.
5389 '(delete-file-recursively "samtools"))))
5390 (build-system gnu-build-system)
5392 `(#:tests? #f ;no "check" target
5394 (modify-phases %standard-phases
5395 (delete 'configure))
5397 (list (string-append "PREFIX="
5398 (assoc-ref %outputs "out"))
5399 (string-append "LIBBAM="
5400 (assoc-ref %build-inputs "samtools")
5402 (string-append "SMITHLAB_CPP="
5403 (assoc-ref %build-inputs "smithlab-cpp")
5406 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5409 ("samtools" ,samtools-0.1)
5410 ("smithlab-cpp" ,smithlab-cpp)
5412 (home-page "http://smithlabresearch.org/software/preseq/")
5413 (synopsis "Program for analyzing library complexity")
5415 "The preseq package is aimed at predicting and estimating the complexity
5416 of a genomic sequencing library, equivalent to predicting and estimating the
5417 number of redundant reads from a given sequencing depth and how many will be
5418 expected from additional sequencing using an initial sequencing experiment.
5419 The estimates can then be used to examine the utility of further sequencing,
5420 optimize the sequencing depth, or to screen multiple libraries to avoid low
5421 complexity samples.")
5422 (license license:gpl3+)))
5424 (define-public python-screed
5426 (name "python-screed")
5431 (uri (pypi-uri "screed" version))
5434 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5435 (build-system python-build-system)
5438 (modify-phases %standard-phases
5441 (setenv "PYTHONPATH"
5442 (string-append (getenv "PYTHONPATH") ":."))
5443 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5445 `(("python-nose" ,python-nose)))
5447 `(("python-bz2file" ,python-bz2file)))
5448 (home-page "https://github.com/dib-lab/screed/")
5449 (synopsis "Short read sequence database utilities")
5450 (description "Screed parses FASTA and FASTQ files and generates databases.
5451 Values such as sequence name, sequence description, sequence quality and the
5452 sequence itself can be retrieved from these databases.")
5453 (license license:bsd-3)))
5455 (define-public python2-screed
5456 (package-with-python2 python-screed))
5458 (define-public sra-tools
5466 (string-append "https://github.com/ncbi/sra-tools/archive/"
5468 (file-name (string-append name "-" version ".tar.gz"))
5471 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5472 (build-system gnu-build-system)
5474 `(#:parallel-build? #f ; not supported
5475 #:tests? #f ; no "check" target
5477 (list (string-append "DEFAULT_CRT="
5478 (assoc-ref %build-inputs "ncbi-vdb")
5480 (string-append "DEFAULT_KFG="
5481 (assoc-ref %build-inputs "ncbi-vdb")
5483 (string-append "VDB_LIBDIR="
5484 (assoc-ref %build-inputs "ncbi-vdb")
5485 ,(if (string-prefix? "x86_64"
5486 (or (%current-target-system)
5491 (modify-phases %standard-phases
5492 (add-before 'configure 'set-perl-search-path
5494 ;; Work around "dotless @INC" build failure.
5496 (string-append (getcwd) "/setup:"
5497 (getenv "PERL5LIB")))
5500 (lambda* (#:key inputs outputs #:allow-other-keys)
5501 ;; The build system expects a directory containing the sources and
5502 ;; raw build output of ncbi-vdb, including files that are not
5503 ;; installed. Since we are building against an installed version of
5504 ;; ncbi-vdb, the following modifications are needed.
5505 (substitute* "setup/konfigure.perl"
5506 ;; Make the configure script look for the "ilib" directory of
5507 ;; "ncbi-vdb" without first checking for the existence of a
5508 ;; matching library in its "lib" directory.
5509 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5510 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5511 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5512 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5513 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5516 (substitute* "tools/copycat/Makefile"
5517 (("smagic-static") "lmagic"))
5519 ;; The 'configure' script doesn't recognize things like
5520 ;; '--enable-fast-install'.
5523 (string-append "--build-prefix=" (getcwd) "/build")
5524 (string-append "--prefix=" (assoc-ref outputs "out"))
5525 (string-append "--debug")
5526 (string-append "--with-fuse-prefix="
5527 (assoc-ref inputs "fuse"))
5528 (string-append "--with-magic-prefix="
5529 (assoc-ref inputs "libmagic"))
5530 ;; TODO: building with libxml2 fails with linker errors
5531 ;; (string-append "--with-xml2-prefix="
5532 ;; (assoc-ref inputs "libxml2"))
5533 (string-append "--with-ncbi-vdb-sources="
5534 (assoc-ref inputs "ncbi-vdb"))
5535 (string-append "--with-ncbi-vdb-build="
5536 (assoc-ref inputs "ncbi-vdb"))
5537 (string-append "--with-ngs-sdk-prefix="
5538 (assoc-ref inputs "ngs-sdk"))
5539 (string-append "--with-hdf5-prefix="
5540 (assoc-ref inputs "hdf5"))))))
5541 ;; This version of sra-tools fails to build with glibc because of a
5542 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5543 ;; contains a definition of "canonicalize", so we rename it.
5545 ;; See upstream bug report:
5546 ;; https://github.com/ncbi/sra-tools/issues/67
5547 (add-after 'unpack 'patch-away-glibc-conflict
5549 (substitute* "tools/bam-loader/bam.c"
5550 (("canonicalize\\(" line)
5551 (string-append "sra_tools_" line)))
5553 (native-inputs `(("perl" ,perl)))
5555 `(("ngs-sdk" ,ngs-sdk)
5556 ("ncbi-vdb" ,ncbi-vdb)
5561 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5562 (synopsis "Tools and libraries for reading and writing sequencing data")
5564 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5565 reading of sequencing files from the Sequence Read Archive (SRA) database and
5566 writing files into the .sra format.")
5567 (license license:public-domain)))
5569 (define-public seqan
5575 (uri (string-append "http://packages.seqan.de/seqan-library/"
5576 "seqan-library-" version ".tar.bz2"))
5579 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5580 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5581 ;; makes sense to split the outputs.
5582 (outputs '("out" "doc"))
5583 (build-system trivial-build-system)
5585 `(#:modules ((guix build utils))
5588 (use-modules (guix build utils))
5589 (let ((tar (assoc-ref %build-inputs "tar"))
5590 (bzip (assoc-ref %build-inputs "bzip2"))
5591 (out (assoc-ref %outputs "out"))
5592 (doc (assoc-ref %outputs "doc")))
5593 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5594 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5595 (chdir (string-append "seqan-library-" ,version))
5596 (copy-recursively "include" (string-append out "/include"))
5597 (copy-recursively "share" (string-append doc "/share"))))))
5599 `(("source" ,source)
5602 (home-page "http://www.seqan.de")
5603 (synopsis "Library for nucleotide sequence analysis")
5605 "SeqAn is a C++ library of efficient algorithms and data structures for
5606 the analysis of sequences with the focus on biological data. It contains
5607 algorithms and data structures for string representation and their
5608 manipulation, online and indexed string search, efficient I/O of
5609 bioinformatics file formats, sequence alignment, and more.")
5610 (license license:bsd-3)))
5612 (define-public seqmagick
5619 (uri (pypi-uri "seqmagick" version))
5622 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5623 (build-system python-build-system)
5625 `(("python-biopython" ,python-biopython)))
5627 `(("python-nose" ,python-nose)))
5628 (home-page "https://github.com/fhcrc/seqmagick")
5629 (synopsis "Tools for converting and modifying sequence files")
5631 "Bioinformaticians often have to convert sequence files between formats
5632 and do little manipulations on them, and it's not worth writing scripts for
5633 that. Seqmagick is a utility to expose the file format conversion in
5634 BioPython in a convenient way. Instead of having a big mess of scripts, there
5635 is one that takes arguments.")
5636 (license license:gpl3)))
5638 (define-public seqtk
5645 "https://github.com/lh3/seqtk/archive/v"
5647 (file-name (string-append name "-" version ".tar.gz"))
5650 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5651 (modules '((guix build utils)))
5654 ;; Remove extraneous header files, as is done in the seqtk
5656 (for-each (lambda (file) (delete-file file))
5657 (list "ksort.h" "kstring.h" "kvec.h"))
5659 (build-system gnu-build-system)
5662 (modify-phases %standard-phases
5665 ;; There are no tests, so we just run a sanity check.
5666 (lambda _ (zero? (system* "./seqtk" "seq"))))
5668 (lambda* (#:key outputs #:allow-other-keys)
5669 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5670 (install-file "seqtk" bin)))))))
5673 (home-page "https://github.com/lh3/seqtk")
5674 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5676 "Seqtk is a fast and lightweight tool for processing sequences in the
5677 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5678 optionally compressed by gzip.")
5679 (license license:expat)))
5681 (define-public snap-aligner
5683 (name "snap-aligner")
5684 (version "1.0beta.18")
5688 "https://github.com/amplab/snap/archive/v"
5690 (file-name (string-append name "-" version ".tar.gz"))
5693 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5694 (build-system gnu-build-system)
5697 (modify-phases %standard-phases
5699 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5701 (lambda* (#:key outputs #:allow-other-keys)
5702 (let* ((out (assoc-ref outputs "out"))
5703 (bin (string-append out "/bin")))
5704 (install-file "snap-aligner" bin)
5705 (install-file "SNAPCommand" bin)
5709 (home-page "http://snap.cs.berkeley.edu/")
5710 (synopsis "Short read DNA sequence aligner")
5712 "SNAP is a fast and accurate aligner for short DNA reads. It is
5713 optimized for modern read lengths of 100 bases or higher, and takes advantage
5714 of these reads to align data quickly through a hash-based indexing scheme.")
5715 ;; 32-bit systems are not supported by the unpatched code.
5716 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5717 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5718 ;; systems without a lot of memory cannot make good use of this program.
5719 (supported-systems '("x86_64-linux"))
5720 (license license:asl2.0)))
5722 (define-public sortmerna
5730 "https://github.com/biocore/sortmerna/archive/"
5732 (file-name (string-append name "-" version ".tar.gz"))
5735 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5736 (build-system gnu-build-system)
5737 (outputs '("out" ;for binaries
5738 "db")) ;for sequence databases
5741 (modify-phases %standard-phases
5743 (lambda* (#:key outputs #:allow-other-keys)
5744 (let* ((out (assoc-ref outputs "out"))
5745 (bin (string-append out "/bin"))
5746 (db (assoc-ref outputs "db"))
5748 (string-append db "/share/sortmerna/rRNA_databases")))
5749 (install-file "sortmerna" bin)
5750 (install-file "indexdb_rna" bin)
5751 (for-each (lambda (file)
5752 (install-file file share))
5753 (find-files "rRNA_databases" ".*fasta"))
5757 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5758 (synopsis "Biological sequence analysis tool for NGS reads")
5760 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5761 and operational taxonomic unit (OTU) picking of next generation
5762 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5763 allows for fast and sensitive analyses of nucleotide sequences. The main
5764 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5765 ;; The source includes x86 specific code
5766 (supported-systems '("x86_64-linux" "i686-linux"))
5767 (license license:lgpl3)))
5775 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5777 (file-name (string-append name "-" version ".tar.gz"))
5780 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5781 (modules '((guix build utils)))
5784 (substitute* "source/Makefile"
5786 ;; Remove pre-built binaries and bundled htslib sources.
5787 (delete-file-recursively "bin/MacOSX_x86_64")
5788 (delete-file-recursively "bin/Linux_x86_64")
5789 (delete-file-recursively "bin/Linux_x86_64_static")
5790 (delete-file-recursively "source/htslib")
5792 (build-system gnu-build-system)
5794 '(#:tests? #f ;no check target
5795 #:make-flags '("STAR")
5797 (modify-phases %standard-phases
5798 (add-after 'unpack 'enter-source-dir
5799 (lambda _ (chdir "source") #t))
5800 (add-after 'enter-source-dir 'make-reproducible
5802 (substitute* "Makefile"
5803 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5804 (string-append pre "Built with Guix" post)))))
5805 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5807 (substitute* "Makefile"
5808 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5810 (substitute* '("BAMfunctions.cpp"
5815 "bamRemoveDuplicates.cpp")
5816 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5817 (string-append "#include <" header ">")))
5818 (substitute* "IncludeDefine.h"
5819 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5820 (string-append "<" header ">")))
5823 (lambda* (#:key outputs #:allow-other-keys)
5824 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5825 (install-file "STAR" bin))
5827 (delete 'configure))))
5831 `(("htslib" ,htslib)
5833 (home-page "https://github.com/alexdobin/STAR")
5834 (synopsis "Universal RNA-seq aligner")
5836 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5837 based on a previously undescribed RNA-seq alignment algorithm that uses
5838 sequential maximum mappable seed search in uncompressed suffix arrays followed
5839 by seed clustering and stitching procedure. In addition to unbiased de novo
5840 detection of canonical junctions, STAR can discover non-canonical splices and
5841 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5843 ;; Only 64-bit systems are supported according to the README.
5844 (supported-systems '("x86_64-linux" "mips64el-linux"))
5845 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5846 (license license:gpl3+)))
5848 (define-public subread
5854 (uri (string-append "mirror://sourceforge/subread/subread-"
5855 version "/subread-" version "-source.tar.gz"))
5858 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5859 (build-system gnu-build-system)
5861 `(#:tests? #f ;no "check" target
5862 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5863 ;; optimizations by default, so we override these flags such that x86_64
5864 ;; flags are only added when the build target is an x86_64 system.
5866 (list (let ((system ,(or (%current-target-system)
5868 (flags '("-ggdb" "-fomit-frame-pointer"
5869 "-ffast-math" "-funroll-loops"
5870 "-fmessage-length=0"
5871 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5873 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5874 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5875 (if (string-prefix? "x86_64" system)
5876 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5877 (string-append "CCFLAGS=" (string-join flags))))
5878 "-f" "Makefile.Linux"
5879 "CC=gcc ${CCFLAGS}")
5881 (modify-phases %standard-phases
5882 (add-after 'unpack 'enter-dir
5883 (lambda _ (chdir "src") #t))
5885 (lambda* (#:key outputs #:allow-other-keys)
5886 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5888 (copy-recursively "../bin" bin))))
5889 ;; no "configure" script
5890 (delete 'configure))))
5891 (inputs `(("zlib" ,zlib)))
5892 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5893 (synopsis "Tool kit for processing next-gen sequencing data")
5895 "The subread package contains the following tools: subread aligner, a
5896 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5897 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5898 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5899 against local background noises.")
5900 (license license:gpl3+)))
5902 (define-public stringtie
5908 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5909 "stringtie-" version ".tar.gz"))
5912 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5913 (modules '((guix build utils)))
5916 (delete-file-recursively "samtools-0.1.18")
5918 (build-system gnu-build-system)
5920 `(#:tests? #f ;no test suite
5922 (modify-phases %standard-phases
5923 ;; no configure script
5925 (add-before 'build 'use-system-samtools
5927 (substitute* "Makefile"
5928 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5930 (substitute* '("gclib/GBam.h"
5932 (("#include \"(bam|sam|kstring).h\"" _ header)
5933 (string-append "#include <samtools/" header ".h>")))
5935 (add-after 'unpack 'remove-duplicate-typedef
5937 ;; This typedef conflicts with the typedef in
5938 ;; glibc-2.25/include/bits/types.h
5939 (substitute* "gclib/GThreads.h"
5940 (("typedef long long __intmax_t;") ""))
5943 (lambda* (#:key outputs #:allow-other-keys)
5944 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5945 (install-file "stringtie" bin)
5948 `(("samtools" ,samtools-0.1)
5950 (home-page "http://ccb.jhu.edu/software/stringtie/")
5951 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5953 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5954 alignments into potential transcripts. It uses a novel network flow algorithm
5955 as well as an optional de novo assembly step to assemble and quantitate
5956 full-length transcripts representing multiple splice variants for each gene
5957 locus. Its input can include not only the alignments of raw reads used by
5958 other transcript assemblers, but also alignments of longer sequences that have
5959 been assembled from those reads. To identify differentially expressed genes
5960 between experiments, StringTie's output can be processed either by the
5961 Cuffdiff or Ballgown programs.")
5962 (license license:artistic2.0)))
5964 (define-public taxtastic
5970 (uri (pypi-uri "taxtastic" version))
5973 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5974 (build-system python-build-system)
5976 `(#:python ,python-2
5978 (modify-phases %standard-phases
5981 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5983 `(("python-sqlalchemy" ,python2-sqlalchemy)
5984 ("python-decorator" ,python2-decorator)
5985 ("python-biopython" ,python2-biopython)
5986 ("python-pandas" ,python2-pandas)))
5987 (home-page "https://github.com/fhcrc/taxtastic")
5988 (synopsis "Tools for taxonomic naming and annotation")
5990 "Taxtastic is software written in python used to build and maintain
5991 reference packages i.e. collections of reference trees, reference alignments,
5992 profiles, and associated taxonomic information.")
5993 (license license:gpl3+)))
5995 (define-public vcftools
6002 "https://github.com/vcftools/vcftools/releases/download/v"
6003 version "/vcftools-" version ".tar.gz"))
6006 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6007 (build-system gnu-build-system)
6009 `(#:tests? #f ; no "check" target
6011 "CFLAGS=-O2" ; override "-m64" flag
6012 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6013 (string-append "MANDIR=" (assoc-ref %outputs "out")
6014 "/share/man/man1"))))
6016 `(("pkg-config" ,pkg-config)))
6020 (home-page "https://vcftools.github.io/")
6021 (synopsis "Tools for working with VCF files")
6023 "VCFtools is a program package designed for working with VCF files, such
6024 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6025 provide easily accessible methods for working with complex genetic variation
6026 data in the form of VCF files.")
6027 ;; The license is declared as LGPLv3 in the README and
6028 ;; at https://vcftools.github.io/license.html
6029 (license license:lgpl3)))
6031 (define-public infernal
6037 (uri (string-append "http://eddylab.org/software/infernal/"
6038 "infernal-" version ".tar.gz"))
6041 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6042 (build-system gnu-build-system)
6044 `(("perl" ,perl))) ; for tests
6045 (home-page "http://eddylab.org/infernal/")
6046 (synopsis "Inference of RNA alignments")
6047 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6048 searching DNA sequence databases for RNA structure and sequence similarities.
6049 It is an implementation of a special case of profile stochastic context-free
6050 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6051 profile, but it scores a combination of sequence consensus and RNA secondary
6052 structure consensus, so in many cases, it is more capable of identifying RNA
6053 homologs that conserve their secondary structure more than their primary
6055 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6056 (supported-systems '("i686-linux" "x86_64-linux"))
6057 (license license:bsd-3)))
6059 (define-public r-centipede
6061 (name "r-centipede")
6065 (uri (string-append "http://download.r-forge.r-project.org/"
6066 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6069 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6070 (build-system r-build-system)
6071 (home-page "http://centipede.uchicago.edu/")
6072 (synopsis "Predict transcription factor binding sites")
6074 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6075 of the genome that are bound by particular transcription factors. It starts
6076 by identifying a set of candidate binding sites, and then aims to classify the
6077 sites according to whether each site is bound or not bound by a transcription
6078 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6079 between two different types of motif instances using as much relevant
6080 information as possible.")
6081 (license (list license:gpl2+ license:gpl3+))))
6083 (define-public r-vegan
6090 (uri (cran-uri "vegan" version))
6093 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
6094 (build-system r-build-system)
6096 `(("gfortran" ,gfortran)))
6098 `(("r-cluster" ,r-cluster)
6099 ("r-lattice" ,r-lattice)
6102 ("r-permute" ,r-permute)))
6103 (home-page "https://cran.r-project.org/web/packages/vegan")
6104 (synopsis "Functions for community ecology")
6106 "The vegan package provides tools for descriptive community ecology. It
6107 has most basic functions of diversity analysis, community ordination and
6108 dissimilarity analysis. Most of its multivariate tools can be used for other
6109 data types as well.")
6110 (license license:gpl2+)))
6112 (define-public r-annotate
6119 (uri (bioconductor-uri "annotate" version))
6122 "0ybg9k1s289h15nj1kp9821i1rsk1gkn8i8blplmk7gsgpbw1f42"))))
6123 (build-system r-build-system)
6125 `(("r-annotationdbi" ,r-annotationdbi)
6126 ("r-biobase" ,r-biobase)
6127 ("r-biocgenerics" ,r-biocgenerics)
6129 ("r-rcurl" ,r-rcurl)
6131 ("r-xtable" ,r-xtable)))
6133 "https://bioconductor.org/packages/annotate")
6134 (synopsis "Annotation for microarrays")
6135 (description "This package provides R environments for the annotation of
6137 (license license:artistic2.0)))
6139 (define-public r-copynumber
6141 (name "r-copynumber")
6145 (uri (bioconductor-uri "copynumber" version))
6148 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6149 (build-system r-build-system)
6151 `(("r-s4vectors" ,r-s4vectors)
6152 ("r-iranges" ,r-iranges)
6153 ("r-genomicranges" ,r-genomicranges)
6154 ("r-biocgenerics" ,r-biocgenerics)))
6155 (home-page "https://bioconductor.org/packages/copynumber")
6156 (synopsis "Segmentation of single- and multi-track copy number data")
6158 "This package segments single- and multi-track copy number data by a
6159 penalized least squares regression method.")
6160 (license license:artistic2.0)))
6162 (define-public r-geneplotter
6164 (name "r-geneplotter")
6169 (uri (bioconductor-uri "geneplotter" version))
6172 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6173 (build-system r-build-system)
6175 `(("r-annotate" ,r-annotate)
6176 ("r-annotationdbi" ,r-annotationdbi)
6177 ("r-biobase" ,r-biobase)
6178 ("r-biocgenerics" ,r-biocgenerics)
6179 ("r-lattice" ,r-lattice)
6180 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6181 (home-page "https://bioconductor.org/packages/geneplotter")
6182 (synopsis "Graphics functions for genomic data")
6184 "This package provides functions for plotting genomic data.")
6185 (license license:artistic2.0)))
6187 (define-public r-genefilter
6189 (name "r-genefilter")
6194 (uri (bioconductor-uri "genefilter" version))
6197 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6198 (build-system r-build-system)
6200 `(("gfortran" ,gfortran)))
6202 `(("r-annotate" ,r-annotate)
6203 ("r-annotationdbi" ,r-annotationdbi)
6204 ("r-biobase" ,r-biobase)
6205 ("r-s4vectors" ,r-s4vectors)
6206 ("r-survival" ,r-survival)))
6207 (home-page "https://bioconductor.org/packages/genefilter")
6208 (synopsis "Filter genes from high-throughput experiments")
6210 "This package provides basic functions for filtering genes from
6211 high-throughput sequencing experiments.")
6212 (license license:artistic2.0)))
6214 (define-public r-deseq2
6221 (uri (bioconductor-uri "DESeq2" version))
6224 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6225 (properties `((upstream-name . "DESeq2")))
6226 (build-system r-build-system)
6228 `(("r-biobase" ,r-biobase)
6229 ("r-biocgenerics" ,r-biocgenerics)
6230 ("r-biocparallel" ,r-biocparallel)
6231 ("r-genefilter" ,r-genefilter)
6232 ("r-geneplotter" ,r-geneplotter)
6233 ("r-genomicranges" ,r-genomicranges)
6234 ("r-ggplot2" ,r-ggplot2)
6235 ("r-hmisc" ,r-hmisc)
6236 ("r-iranges" ,r-iranges)
6237 ("r-locfit" ,r-locfit)
6239 ("r-rcpparmadillo" ,r-rcpparmadillo)
6240 ("r-s4vectors" ,r-s4vectors)
6241 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6242 (home-page "https://bioconductor.org/packages/DESeq2")
6243 (synopsis "Differential gene expression analysis")
6245 "This package provides functions to estimate variance-mean dependence in
6246 count data from high-throughput nucleotide sequencing assays and test for
6247 differential expression based on a model using the negative binomial
6249 (license license:lgpl3+)))
6251 (define-public r-dexseq
6258 (uri (bioconductor-uri "DEXSeq" version))
6261 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6262 (properties `((upstream-name . "DEXSeq")))
6263 (build-system r-build-system)
6265 `(("r-annotationdbi" ,r-annotationdbi)
6266 ("r-biobase" ,r-biobase)
6267 ("r-biocgenerics" ,r-biocgenerics)
6268 ("r-biocparallel" ,r-biocparallel)
6269 ("r-biomart" ,r-biomart)
6270 ("r-deseq2" ,r-deseq2)
6271 ("r-genefilter" ,r-genefilter)
6272 ("r-geneplotter" ,r-geneplotter)
6273 ("r-genomicranges" ,r-genomicranges)
6274 ("r-hwriter" ,r-hwriter)
6275 ("r-iranges" ,r-iranges)
6276 ("r-rcolorbrewer" ,r-rcolorbrewer)
6277 ("r-rsamtools" ,r-rsamtools)
6278 ("r-s4vectors" ,r-s4vectors)
6279 ("r-statmod" ,r-statmod)
6280 ("r-stringr" ,r-stringr)
6281 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6282 (home-page "https://bioconductor.org/packages/DEXSeq")
6283 (synopsis "Inference of differential exon usage in RNA-Seq")
6285 "This package is focused on finding differential exon usage using RNA-seq
6286 exon counts between samples with different experimental designs. It provides
6287 functions that allows the user to make the necessary statistical tests based
6288 on a model that uses the negative binomial distribution to estimate the
6289 variance between biological replicates and generalized linear models for
6290 testing. The package also provides functions for the visualization and
6291 exploration of the results.")
6292 (license license:gpl3+)))
6294 (define-public r-annotationforge
6296 (name "r-annotationforge")
6301 (uri (bioconductor-uri "AnnotationForge" version))
6304 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6306 `((upstream-name . "AnnotationForge")))
6307 (build-system r-build-system)
6309 `(("r-annotationdbi" ,r-annotationdbi)
6310 ("r-biobase" ,r-biobase)
6311 ("r-biocgenerics" ,r-biocgenerics)
6313 ("r-rcurl" ,r-rcurl)
6314 ("r-rsqlite" ,r-rsqlite)
6315 ("r-s4vectors" ,r-s4vectors)
6317 (home-page "https://bioconductor.org/packages/AnnotationForge")
6318 (synopsis "Code for building annotation database packages")
6320 "This package provides code for generating Annotation packages and their
6321 databases. Packages produced are intended to be used with AnnotationDbi.")
6322 (license license:artistic2.0)))
6324 (define-public r-rbgl
6331 (uri (bioconductor-uri "RBGL" version))
6334 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6335 (properties `((upstream-name . "RBGL")))
6336 (build-system r-build-system)
6337 (propagated-inputs `(("r-graph" ,r-graph)))
6338 (home-page "https://www.bioconductor.org/packages/RBGL")
6339 (synopsis "Interface to the Boost graph library")
6341 "This package provides a fairly extensive and comprehensive interface to
6342 the graph algorithms contained in the Boost library.")
6343 (license license:artistic2.0)))
6345 (define-public r-gseabase
6352 (uri (bioconductor-uri "GSEABase" version))
6355 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6356 (properties `((upstream-name . "GSEABase")))
6357 (build-system r-build-system)
6359 `(("r-annotate" ,r-annotate)
6360 ("r-annotationdbi" ,r-annotationdbi)
6361 ("r-biobase" ,r-biobase)
6362 ("r-biocgenerics" ,r-biocgenerics)
6363 ("r-graph" ,r-graph)
6365 (home-page "https://bioconductor.org/packages/GSEABase")
6366 (synopsis "Gene set enrichment data structures and methods")
6368 "This package provides classes and methods to support @dfn{Gene Set
6369 Enrichment Analysis} (GSEA).")
6370 (license license:artistic2.0)))
6372 (define-public r-category
6379 (uri (bioconductor-uri "Category" version))
6382 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6383 (properties `((upstream-name . "Category")))
6384 (build-system r-build-system)
6386 `(("r-annotate" ,r-annotate)
6387 ("r-annotationdbi" ,r-annotationdbi)
6388 ("r-biobase" ,r-biobase)
6389 ("r-biocgenerics" ,r-biocgenerics)
6390 ("r-genefilter" ,r-genefilter)
6391 ("r-graph" ,r-graph)
6392 ("r-gseabase" ,r-gseabase)
6393 ("r-matrix" ,r-matrix)
6396 (home-page "https://bioconductor.org/packages/Category")
6397 (synopsis "Category analysis")
6399 "This package provides a collection of tools for performing category
6401 (license license:artistic2.0)))
6403 (define-public r-gostats
6410 (uri (bioconductor-uri "GOstats" version))
6413 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6414 (properties `((upstream-name . "GOstats")))
6415 (build-system r-build-system)
6417 `(("r-annotate" ,r-annotate)
6418 ("r-annotationdbi" ,r-annotationdbi)
6419 ("r-annotationforge" ,r-annotationforge)
6420 ("r-biobase" ,r-biobase)
6421 ("r-category" ,r-category)
6422 ("r-go-db" ,r-go-db)
6423 ("r-graph" ,r-graph)
6424 ("r-rgraphviz" ,r-rgraphviz)
6425 ("r-rbgl" ,r-rbgl)))
6426 (home-page "https://bioconductor.org/packages/GOstats")
6427 (synopsis "Tools for manipulating GO and microarrays")
6429 "This package provides a set of tools for interacting with GO and
6430 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6431 testing and other simple calculations.")
6432 (license license:artistic2.0)))
6434 (define-public r-shortread
6436 (name "r-shortread")
6441 (uri (bioconductor-uri "ShortRead" version))
6444 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6445 (properties `((upstream-name . "ShortRead")))
6446 (build-system r-build-system)
6450 `(("r-biobase" ,r-biobase)
6451 ("r-biocgenerics" ,r-biocgenerics)
6452 ("r-biocparallel" ,r-biocparallel)
6453 ("r-biostrings" ,r-biostrings)
6454 ("r-genomeinfodb" ,r-genomeinfodb)
6455 ("r-genomicalignments" ,r-genomicalignments)
6456 ("r-genomicranges" ,r-genomicranges)
6457 ("r-hwriter" ,r-hwriter)
6458 ("r-iranges" ,r-iranges)
6459 ("r-lattice" ,r-lattice)
6460 ("r-latticeextra" ,r-latticeextra)
6461 ("r-rsamtools" ,r-rsamtools)
6462 ("r-s4vectors" ,r-s4vectors)
6463 ("r-xvector" ,r-xvector)
6464 ("r-zlibbioc" ,r-zlibbioc)))
6465 (home-page "https://bioconductor.org/packages/ShortRead")
6466 (synopsis "FASTQ input and manipulation tools")
6468 "This package implements sampling, iteration, and input of FASTQ files.
6469 It includes functions for filtering and trimming reads, and for generating a
6470 quality assessment report. Data are represented as
6471 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6472 purposes. The package also contains legacy support for early single-end,
6473 ungapped alignment formats.")
6474 (license license:artistic2.0)))
6476 (define-public r-systempiper
6478 (name "r-systempiper")
6483 (uri (bioconductor-uri "systemPipeR" version))
6486 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6487 (properties `((upstream-name . "systemPipeR")))
6488 (build-system r-build-system)
6490 `(("r-annotate" ,r-annotate)
6491 ("r-batchjobs" ,r-batchjobs)
6492 ("r-biocgenerics" ,r-biocgenerics)
6493 ("r-biostrings" ,r-biostrings)
6494 ("r-deseq2" ,r-deseq2)
6495 ("r-edger" ,r-edger)
6496 ("r-genomicfeatures" ,r-genomicfeatures)
6497 ("r-genomicranges" ,r-genomicranges)
6498 ("r-ggplot2" ,r-ggplot2)
6499 ("r-go-db" ,r-go-db)
6500 ("r-gostats" ,r-gostats)
6501 ("r-limma" ,r-limma)
6502 ("r-pheatmap" ,r-pheatmap)
6503 ("r-rjson" ,r-rjson)
6504 ("r-rsamtools" ,r-rsamtools)
6505 ("r-shortread" ,r-shortread)
6506 ("r-summarizedexperiment" ,r-summarizedexperiment)
6507 ("r-variantannotation" ,r-variantannotation)))
6508 (home-page "https://github.com/tgirke/systemPipeR")
6509 (synopsis "Next generation sequencing workflow and reporting environment")
6511 "This R package provides tools for building and running automated
6512 end-to-end analysis workflows for a wide range of @dfn{next generation
6513 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6514 Important features include a uniform workflow interface across different NGS
6515 applications, automated report generation, and support for running both R and
6516 command-line software, such as NGS aligners or peak/variant callers, on local
6517 computers or compute clusters. Efficient handling of complex sample sets and
6518 experimental designs is facilitated by a consistently implemented sample
6519 annotation infrastructure.")
6520 (license license:artistic2.0)))
6522 (define-public r-grohmm
6529 (uri (bioconductor-uri "groHMM" version))
6532 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6533 (properties `((upstream-name . "groHMM")))
6534 (build-system r-build-system)
6536 `(("r-genomeinfodb" ,r-genomeinfodb)
6537 ("r-genomicalignments" ,r-genomicalignments)
6538 ("r-genomicranges" ,r-genomicranges)
6539 ("r-iranges" ,r-iranges)
6541 ("r-rtracklayer" ,r-rtracklayer)
6542 ("r-s4vectors" ,r-s4vectors)))
6543 (home-page "https://github.com/Kraus-Lab/groHMM")
6544 (synopsis "GRO-seq analysis pipeline")
6546 "This package provides a pipeline for the analysis of GRO-seq data.")
6547 (license license:gpl3+)))
6549 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6551 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6555 ;; We cannot use bioconductor-uri here because this tarball is
6556 ;; located under "data/annotation/" instead of "bioc/".
6557 (uri (string-append "https://bioconductor.org/packages/"
6558 "release/data/annotation/src/contrib"
6559 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6563 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6565 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6566 (build-system r-build-system)
6567 ;; As this package provides little more than a very large data file it
6568 ;; doesn't make sense to build substitutes.
6569 (arguments `(#:substitutable? #f))
6571 `(("r-genomicfeatures" ,r-genomicfeatures)))
6573 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6574 (synopsis "Annotation package for human genome in TxDb format")
6576 "This package provides an annotation database of Homo sapiens genome
6577 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6578 track. The database is exposed as a @code{TxDb} object.")
6579 (license license:artistic2.0)))
6581 (define-public r-sparql
6587 (uri (cran-uri "SPARQL" version))
6590 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6591 (properties `((upstream-name . "SPARQL")))
6592 (build-system r-build-system)
6594 `(("r-rcurl" ,r-rcurl)
6596 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6597 (synopsis "SPARQL client for R")
6598 (description "This package provides an interface to use SPARQL to pose
6599 SELECT or UPDATE queries to an end-point.")
6600 ;; The only license indication is found in the DESCRIPTION file,
6601 ;; which states GPL-3. So we cannot assume GPLv3+.
6602 (license license:gpl3)))
6604 (define-public vsearch
6612 "https://github.com/torognes/vsearch/archive/v"
6614 (file-name (string-append name "-" version ".tar.gz"))
6617 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6618 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6621 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6622 ;; for this in the patch.
6623 (delete-file "src/city.h")
6624 (delete-file "src/citycrc.h")
6625 (delete-file "src/city.cc")
6627 (build-system gnu-build-system)
6630 (modify-phases %standard-phases
6631 (add-after 'unpack 'autogen
6632 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6636 ("cityhash" ,cityhash)))
6638 `(("autoconf" ,autoconf)
6639 ("automake" ,automake)))
6640 (synopsis "Sequence search tools for metagenomics")
6642 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6643 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6644 masking. The tool takes advantage of parallelism in the form of SIMD
6645 vectorization as well as multiple threads to perform accurate alignments at
6646 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6647 Needleman-Wunsch).")
6648 (home-page "https://github.com/torognes/vsearch")
6649 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6651 (supported-systems '("x86_64-linux"))
6652 ;; Dual licensed; also includes public domain source.
6653 (license (list license:gpl3 license:bsd-2))))
6655 (define-public pardre
6658 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6663 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6667 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6668 (build-system gnu-build-system)
6670 `(#:tests? #f ; no tests included
6672 (modify-phases %standard-phases
6675 (lambda* (#:key outputs #:allow-other-keys)
6676 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6677 (install-file "ParDRe" bin)
6680 `(("openmpi" ,openmpi)
6682 (synopsis "Parallel tool to remove duplicate DNA reads")
6684 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6685 Duplicate reads can be seen as identical or nearly identical sequences with
6686 some mismatches. This tool lets users avoid the analysis of unnecessary
6687 reads, reducing the time of subsequent procedures with the
6688 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6689 in order to exploit the parallel capabilities of multicore clusters. It is
6690 faster than multithreaded counterparts (end of 2015) for the same number of
6691 cores and, thanks to the message-passing technology, it can be executed on
6693 (home-page "https://sourceforge.net/projects/pardre/")
6694 (license license:gpl3+)))
6696 (define-public ruby-bio-kseq
6698 (name "ruby-bio-kseq")
6703 (uri (rubygems-uri "bio-kseq" version))
6706 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6707 (build-system ruby-build-system)
6709 `(#:test-target "spec"))
6711 `(("bundler" ,bundler)
6712 ("ruby-rspec" ,ruby-rspec)
6713 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6716 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6718 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6719 FASTQ parsing code. It provides a fast iterator over sequences and their
6721 (home-page "https://github.com/gusevfe/bio-kseq")
6722 (license license:expat)))
6724 (define-public bio-locus
6731 (uri (rubygems-uri "bio-locus" version))
6734 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6735 (build-system ruby-build-system)
6737 `(("ruby-rspec" ,ruby-rspec)))
6738 (synopsis "Tool for fast querying of genome locations")
6740 "Bio-locus is a tabix-like tool for fast querying of genome
6741 locations. Many file formats in bioinformatics contain records that
6742 start with a chromosome name and a position for a SNP, or a start-end
6743 position for indels. Bio-locus allows users to store this chr+pos or
6744 chr+pos+alt information in a database.")
6745 (home-page "https://github.com/pjotrp/bio-locus")
6746 (license license:expat)))
6748 (define-public bio-blastxmlparser
6750 (name "bio-blastxmlparser")
6754 (uri (rubygems-uri "bio-blastxmlparser" version))
6757 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6758 (build-system ruby-build-system)
6760 `(("ruby-bio-logger" ,ruby-bio-logger)
6761 ("ruby-nokogiri" ,ruby-nokogiri)))
6763 `(("ruby-rspec" ,ruby-rspec)))
6764 (synopsis "Fast big data BLAST XML parser and library")
6766 "Very fast parallel big-data BLAST XML file parser which can be used as
6767 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6768 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6769 (home-page "https://github.com/pjotrp/blastxmlparser")
6770 (license license:expat)))
6772 (define-public bioruby
6779 (uri (rubygems-uri "bio" version))
6782 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6783 (build-system ruby-build-system)
6785 `(("ruby-libxml" ,ruby-libxml)))
6787 `(("which" ,which))) ; required for test phase
6790 (modify-phases %standard-phases
6791 (add-before 'build 'patch-test-command
6793 (substitute* '("test/functional/bio/test_command.rb")
6794 (("/bin/sh") (which "sh")))
6795 (substitute* '("test/functional/bio/test_command.rb")
6796 (("/bin/ls") (which "ls")))
6797 (substitute* '("test/functional/bio/test_command.rb")
6798 (("which") (which "which")))
6799 (substitute* '("test/functional/bio/test_command.rb",
6800 "test/data/command/echoarg2.sh")
6801 (("/bin/echo") (which "echo")))
6803 (synopsis "Ruby library, shell and utilities for bioinformatics")
6804 (description "BioRuby comes with a comprehensive set of Ruby development
6805 tools and libraries for bioinformatics and molecular biology. BioRuby has
6806 components for sequence analysis, pathway analysis, protein modelling and
6807 phylogenetic analysis; it supports many widely used data formats and provides
6808 easy access to databases, external programs and public web services, including
6809 BLAST, KEGG, GenBank, MEDLINE and GO.")
6810 (home-page "http://bioruby.org/")
6811 ;; Code is released under Ruby license, except for setup
6812 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6813 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6815 (define-public r-acsnminer
6817 (name "r-acsnminer")
6818 (version "0.16.8.25")
6821 (uri (cran-uri "ACSNMineR" version))
6824 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6825 (properties `((upstream-name . "ACSNMineR")))
6826 (build-system r-build-system)
6828 `(("r-ggplot2" ,r-ggplot2)
6829 ("r-gridextra" ,r-gridextra)))
6830 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6831 (synopsis "Gene enrichment analysis")
6833 "This package provides tools to compute and represent gene set enrichment
6834 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6835 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6836 enrichment can be run with hypergeometric test or Fisher exact test, and can
6837 use multiple corrections. Visualization of data can be done either by
6838 barplots or heatmaps.")
6839 (license license:gpl2+)))
6841 (define-public r-biocgenerics
6843 (name "r-biocgenerics")
6847 (uri (bioconductor-uri "BiocGenerics" version))
6850 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6852 `((upstream-name . "BiocGenerics")))
6853 (build-system r-build-system)
6854 (home-page "https://bioconductor.org/packages/BiocGenerics")
6855 (synopsis "S4 generic functions for Bioconductor")
6857 "This package provides S4 generic functions needed by many Bioconductor
6859 (license license:artistic2.0)))
6861 (define-public r-biocinstaller
6863 (name "r-biocinstaller")
6867 (uri (bioconductor-uri "BiocInstaller" version))
6870 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6872 `((upstream-name . "BiocInstaller")))
6873 (build-system r-build-system)
6874 (home-page "https://bioconductor.org/packages/BiocInstaller")
6875 (synopsis "Install Bioconductor packages")
6876 (description "This package is used to install and update R packages from
6877 Bioconductor, CRAN, and Github.")
6878 (license license:artistic2.0)))
6880 (define-public r-biocviews
6882 (name "r-biocviews")
6886 (uri (bioconductor-uri "biocViews" version))
6889 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6891 `((upstream-name . "biocViews")))
6892 (build-system r-build-system)
6894 `(("r-biobase" ,r-biobase)
6895 ("r-graph" ,r-graph)
6897 ("r-rcurl" ,r-rcurl)
6899 ("r-runit" ,r-runit)))
6900 (home-page "https://bioconductor.org/packages/biocViews")
6901 (synopsis "Bioconductor package categorization helper")
6902 (description "The purpose of biocViews is to create HTML pages that
6903 categorize packages in a Bioconductor package repository according to keywords,
6904 also known as views, in a controlled vocabulary.")
6905 (license license:artistic2.0)))
6907 (define-public r-bookdown
6913 (uri (cran-uri "bookdown" version))
6916 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6917 (build-system r-build-system)
6919 `(("r-htmltools" ,r-htmltools)
6920 ("r-knitr" ,r-knitr)
6921 ("r-rmarkdown" ,r-rmarkdown)
6922 ("r-tinytex" ,r-tinytex)
6924 ("r-xfun" ,r-xfun)))
6925 (home-page "https://github.com/rstudio/bookdown")
6926 (synopsis "Authoring books and technical documents with R markdown")
6927 (description "This package provides output formats and utilities for
6928 authoring books and technical documents with R Markdown.")
6929 (license license:gpl3)))
6931 (define-public r-biocstyle
6933 (name "r-biocstyle")
6937 (uri (bioconductor-uri "BiocStyle" version))
6940 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6942 `((upstream-name . "BiocStyle")))
6943 (build-system r-build-system)
6945 `(("r-bookdown" ,r-bookdown)
6946 ("r-knitr" ,r-knitr)
6947 ("r-rmarkdown" ,r-rmarkdown)
6948 ("r-yaml" ,r-yaml)))
6949 (home-page "https://bioconductor.org/packages/BiocStyle")
6950 (synopsis "Bioconductor formatting styles")
6951 (description "This package provides standard formatting styles for
6952 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6954 (license license:artistic2.0)))
6956 (define-public r-bioccheck
6958 (name "r-bioccheck")
6962 (uri (bioconductor-uri "BiocCheck" version))
6965 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6967 `((upstream-name . "BiocCheck")))
6968 (build-system r-build-system)
6971 (modify-phases %standard-phases
6972 ;; This package can be used by calling BiocCheck(<package>) from
6973 ;; within R, or by running R CMD BiocCheck <package>. This phase
6974 ;; makes sure the latter works. For this to work, the BiocCheck
6975 ;; script must be somewhere on the PATH (not the R bin directory).
6976 (add-after 'install 'install-bioccheck-subcommand
6977 (lambda* (#:key outputs #:allow-other-keys)
6978 (let* ((out (assoc-ref outputs "out"))
6979 (dest-dir (string-append out "/bin"))
6981 (string-append out "/site-library/BiocCheck/script/")))
6983 (symlink (string-append script-dir "/checkBadDeps.R")
6984 (string-append dest-dir "/checkBadDeps.R"))
6985 (symlink (string-append script-dir "/BiocCheck")
6986 (string-append dest-dir "/BiocCheck")))
6989 `(("r-codetools" ,r-codetools)
6990 ("r-graph" ,r-graph)
6992 ("r-optparse" ,r-optparse)
6993 ("r-biocinstaller" ,r-biocinstaller)
6994 ("r-biocviews" ,r-biocviews)
6995 ("r-stringdist" ,r-stringdist)))
6996 (home-page "https://bioconductor.org/packages/BiocCheck")
6997 (synopsis "Executes Bioconductor-specific package checks")
6998 (description "This package contains tools to perform additional quality
6999 checks on R packages that are to be submitted to the Bioconductor repository.")
7000 (license license:artistic2.0)))
7002 (define-public r-getopt
7009 (uri (cran-uri "getopt" version))
7012 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
7013 (build-system r-build-system)
7014 (home-page "https://github.com/trevorld/getopt")
7015 (synopsis "Command-line option processor for R")
7017 "This package is designed to be used with Rscript to write shebang
7018 scripts that accept short and long options. Many users will prefer to
7019 use the packages @code{optparse} or @code{argparse} which add extra
7020 features like automatically generated help options and usage texts,
7021 support for default values, positional argument support, etc.")
7022 (license license:gpl2+)))
7024 (define-public r-optparse
7031 (uri (cran-uri "optparse" version))
7034 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
7035 (build-system r-build-system)
7037 `(("r-getopt" ,r-getopt)))
7039 "https://github.com/trevorld/optparse")
7040 (synopsis "Command line option parser")
7042 "This package provides a command line parser inspired by Python's
7043 @code{optparse} library to be used with Rscript to write shebang scripts
7044 that accept short and long options.")
7045 (license license:gpl2+)))
7047 (define-public r-dnacopy
7053 (uri (bioconductor-uri "DNAcopy" version))
7056 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
7058 `((upstream-name . "DNAcopy")))
7059 (build-system r-build-system)
7061 `(("gfortran" ,gfortran)))
7062 (home-page "https://bioconductor.org/packages/DNAcopy")
7063 (synopsis "Implementation of a circular binary segmentation algorithm")
7064 (description "This package implements the circular binary segmentation (CBS)
7065 algorithm to segment DNA copy number data and identify genomic regions with
7066 abnormal copy number.")
7067 (license license:gpl2+)))
7069 (define-public r-s4vectors
7071 (name "r-s4vectors")
7075 (uri (bioconductor-uri "S4Vectors" version))
7078 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7080 `((upstream-name . "S4Vectors")))
7081 (build-system r-build-system)
7083 `(("r-biocgenerics" ,r-biocgenerics)))
7084 (home-page "https://bioconductor.org/packages/S4Vectors")
7085 (synopsis "S4 implementation of vectors and lists")
7087 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7088 classes and a set of generic functions that extend the semantic of ordinary
7089 vectors and lists in R. Package developers can easily implement vector-like
7090 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7091 In addition, a few low-level concrete subclasses of general interest (e.g.
7092 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7093 S4Vectors package itself.")
7094 (license license:artistic2.0)))
7096 (define-public r-seqinr
7103 (uri (cran-uri "seqinr" version))
7106 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7107 (build-system r-build-system)
7109 `(("r-ade4" ,r-ade4)
7110 ("r-segmented" ,r-segmented)))
7113 (home-page "http://seqinr.r-forge.r-project.org/")
7114 (synopsis "Biological sequences retrieval and analysis")
7116 "This package provides tools for exploratory data analysis and data
7117 visualization of biological sequence (DNA and protein) data. It also includes
7118 utilities for sequence data management under the ACNUC system.")
7119 (license license:gpl2+)))
7121 (define-public r-iranges
7127 (uri (bioconductor-uri "IRanges" version))
7130 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7132 `((upstream-name . "IRanges")))
7133 (build-system r-build-system)
7135 `(("r-biocgenerics" ,r-biocgenerics)
7136 ("r-s4vectors" ,r-s4vectors)))
7137 (home-page "https://bioconductor.org/packages/IRanges")
7138 (synopsis "Infrastructure for manipulating intervals on sequences")
7140 "This package provides efficient low-level and highly reusable S4 classes
7141 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7142 generally, data that can be organized sequentially (formally defined as
7143 @code{Vector} objects), as well as views on these @code{Vector} objects.
7144 Efficient list-like classes are also provided for storing big collections of
7145 instances of the basic classes. All classes in the package use consistent
7146 naming and share the same rich and consistent \"Vector API\" as much as
7148 (license license:artistic2.0)))
7150 (define-public r-genomeinfodbdata
7152 (name "r-genomeinfodbdata")
7156 ;; We cannot use bioconductor-uri here because this tarball is
7157 ;; located under "data/annotation/" instead of "bioc/".
7158 (uri (string-append "https://bioconductor.org/packages/release/"
7159 "data/annotation/src/contrib/GenomeInfoDbData_"
7163 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7165 `((upstream-name . "GenomeInfoDbData")))
7166 (build-system r-build-system)
7167 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7168 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7169 (description "This package contains data for mapping between NCBI taxonomy
7170 ID and species. It is used by functions in the GenomeInfoDb package.")
7171 (license license:artistic2.0)))
7173 (define-public r-genomeinfodb
7175 (name "r-genomeinfodb")
7179 (uri (bioconductor-uri "GenomeInfoDb" version))
7182 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7184 `((upstream-name . "GenomeInfoDb")))
7185 (build-system r-build-system)
7187 `(("r-biocgenerics" ,r-biocgenerics)
7188 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7189 ("r-iranges" ,r-iranges)
7190 ("r-rcurl" ,r-rcurl)
7191 ("r-s4vectors" ,r-s4vectors)))
7192 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7193 (synopsis "Utilities for manipulating chromosome identifiers")
7195 "This package contains data and functions that define and allow
7196 translation between different chromosome sequence naming conventions (e.g.,
7197 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7198 names in their natural, rather than lexicographic, order.")
7199 (license license:artistic2.0)))
7201 (define-public r-edger
7207 (uri (bioconductor-uri "edgeR" version))
7210 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7211 (properties `((upstream-name . "edgeR")))
7212 (build-system r-build-system)
7214 `(("r-limma" ,r-limma)
7215 ("r-locfit" ,r-locfit)
7217 ("r-statmod" ,r-statmod))) ;for estimateDisp
7218 (home-page "http://bioinf.wehi.edu.au/edgeR")
7219 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7220 (description "This package can do differential expression analysis of
7221 RNA-seq expression profiles with biological replication. It implements a range
7222 of statistical methodology based on the negative binomial distributions,
7223 including empirical Bayes estimation, exact tests, generalized linear models
7224 and quasi-likelihood tests. It be applied to differential signal analysis of
7225 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7227 (license license:gpl2+)))
7229 (define-public r-variantannotation
7231 (name "r-variantannotation")
7235 (uri (bioconductor-uri "VariantAnnotation" version))
7238 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7240 `((upstream-name . "VariantAnnotation")))
7244 `(("r-annotationdbi" ,r-annotationdbi)
7245 ("r-biobase" ,r-biobase)
7246 ("r-biocgenerics" ,r-biocgenerics)
7247 ("r-biostrings" ,r-biostrings)
7248 ("r-bsgenome" ,r-bsgenome)
7250 ("r-genomeinfodb" ,r-genomeinfodb)
7251 ("r-genomicfeatures" ,r-genomicfeatures)
7252 ("r-genomicranges" ,r-genomicranges)
7253 ("r-iranges" ,r-iranges)
7254 ("r-summarizedexperiment" ,r-summarizedexperiment)
7255 ("r-rsamtools" ,r-rsamtools)
7256 ("r-rtracklayer" ,r-rtracklayer)
7257 ("r-s4vectors" ,r-s4vectors)
7258 ("r-xvector" ,r-xvector)
7259 ("r-zlibbioc" ,r-zlibbioc)))
7260 (build-system r-build-system)
7261 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7262 (synopsis "Package for annotation of genetic variants")
7263 (description "This R package can annotate variants, compute amino acid
7264 coding changes and predict coding outcomes.")
7265 (license license:artistic2.0)))
7267 (define-public r-limma
7273 (uri (bioconductor-uri "limma" version))
7276 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7277 (build-system r-build-system)
7278 (home-page "http://bioinf.wehi.edu.au/limma")
7279 (synopsis "Package for linear models for microarray and RNA-seq data")
7280 (description "This package can be used for the analysis of gene expression
7281 studies, especially the use of linear models for analysing designed experiments
7282 and the assessment of differential expression. The analysis methods apply to
7283 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7284 (license license:gpl2+)))
7286 (define-public r-xvector
7292 (uri (bioconductor-uri "XVector" version))
7295 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7297 `((upstream-name . "XVector")))
7298 (build-system r-build-system)
7301 (modify-phases %standard-phases
7302 (add-after 'unpack 'use-system-zlib
7304 (substitute* "DESCRIPTION"
7305 (("zlibbioc, ") ""))
7306 (substitute* "NAMESPACE"
7307 (("import\\(zlibbioc\\)") ""))
7312 `(("r-biocgenerics" ,r-biocgenerics)
7313 ("r-iranges" ,r-iranges)
7314 ("r-s4vectors" ,r-s4vectors)))
7315 (home-page "https://bioconductor.org/packages/XVector")
7316 (synopsis "Representation and manpulation of external sequences")
7318 "This package provides memory efficient S4 classes for storing sequences
7319 \"externally\" (behind an R external pointer, or on disk).")
7320 (license license:artistic2.0)))
7322 (define-public r-genomicranges
7324 (name "r-genomicranges")
7328 (uri (bioconductor-uri "GenomicRanges" version))
7331 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7333 `((upstream-name . "GenomicRanges")))
7334 (build-system r-build-system)
7336 `(("r-biocgenerics" ,r-biocgenerics)
7337 ("r-genomeinfodb" ,r-genomeinfodb)
7338 ("r-iranges" ,r-iranges)
7339 ("r-s4vectors" ,r-s4vectors)
7340 ("r-xvector" ,r-xvector)))
7341 (home-page "https://bioconductor.org/packages/GenomicRanges")
7342 (synopsis "Representation and manipulation of genomic intervals")
7344 "This package provides tools to efficiently represent and manipulate
7345 genomic annotations and alignments is playing a central role when it comes to
7346 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7347 GenomicRanges package defines general purpose containers for storing and
7348 manipulating genomic intervals and variables defined along a genome.")
7349 (license license:artistic2.0)))
7351 (define-public r-biobase
7357 (uri (bioconductor-uri "Biobase" version))
7360 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7362 `((upstream-name . "Biobase")))
7363 (build-system r-build-system)
7365 `(("r-biocgenerics" ,r-biocgenerics)))
7366 (home-page "https://bioconductor.org/packages/Biobase")
7367 (synopsis "Base functions for Bioconductor")
7369 "This package provides functions that are needed by many other packages
7370 on Bioconductor or which replace R functions.")
7371 (license license:artistic2.0)))
7373 (define-public r-annotationdbi
7375 (name "r-annotationdbi")
7379 (uri (bioconductor-uri "AnnotationDbi" version))
7382 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7384 `((upstream-name . "AnnotationDbi")))
7385 (build-system r-build-system)
7387 `(("r-biobase" ,r-biobase)
7388 ("r-biocgenerics" ,r-biocgenerics)
7390 ("r-iranges" ,r-iranges)
7391 ("r-rsqlite" ,r-rsqlite)
7392 ("r-s4vectors" ,r-s4vectors)))
7393 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7394 (synopsis "Annotation database interface")
7396 "This package provides user interface and database connection code for
7397 annotation data packages using SQLite data storage.")
7398 (license license:artistic2.0)))
7400 (define-public r-biomart
7406 (uri (bioconductor-uri "biomaRt" version))
7409 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7411 `((upstream-name . "biomaRt")))
7412 (build-system r-build-system)
7414 `(("r-annotationdbi" ,r-annotationdbi)
7416 ("r-progress" ,r-progress)
7417 ("r-rcurl" ,r-rcurl)
7418 ("r-stringr" ,r-stringr)
7420 (home-page "https://bioconductor.org/packages/biomaRt")
7421 (synopsis "Interface to BioMart databases")
7423 "biomaRt provides an interface to a growing collection of databases
7424 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7425 package enables retrieval of large amounts of data in a uniform way without
7426 the need to know the underlying database schemas or write complex SQL queries.
7427 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7428 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7429 users direct access to a diverse set of data and enable a wide range of
7430 powerful online queries from gene annotation to database mining.")
7431 (license license:artistic2.0)))
7433 (define-public r-biocparallel
7435 (name "r-biocparallel")
7439 (uri (bioconductor-uri "BiocParallel" version))
7442 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7444 `((upstream-name . "BiocParallel")))
7445 (build-system r-build-system)
7447 `(("r-futile-logger" ,r-futile-logger)
7450 (home-page "https://bioconductor.org/packages/BiocParallel")
7451 (synopsis "Bioconductor facilities for parallel evaluation")
7453 "This package provides modified versions and novel implementation of
7454 functions for parallel evaluation, tailored to use with Bioconductor
7456 (license (list license:gpl2+ license:gpl3+))))
7458 (define-public r-biostrings
7460 (name "r-biostrings")
7464 (uri (bioconductor-uri "Biostrings" version))
7467 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7469 `((upstream-name . "Biostrings")))
7470 (build-system r-build-system)
7472 `(("r-biocgenerics" ,r-biocgenerics)
7473 ("r-iranges" ,r-iranges)
7474 ("r-s4vectors" ,r-s4vectors)
7475 ("r-xvector" ,r-xvector)))
7476 (home-page "https://bioconductor.org/packages/Biostrings")
7477 (synopsis "String objects and algorithms for biological sequences")
7479 "This package provides memory efficient string containers, string
7480 matching algorithms, and other utilities, for fast manipulation of large
7481 biological sequences or sets of sequences.")
7482 (license license:artistic2.0)))
7484 (define-public r-rsamtools
7486 (name "r-rsamtools")
7490 (uri (bioconductor-uri "Rsamtools" version))
7493 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7495 `((upstream-name . "Rsamtools")))
7496 (build-system r-build-system)
7499 (modify-phases %standard-phases
7500 (add-after 'unpack 'use-system-zlib
7502 (substitute* "DESCRIPTION"
7503 (("zlibbioc, ") ""))
7504 (substitute* "NAMESPACE"
7505 (("import\\(zlibbioc\\)") ""))
7510 `(("r-biocgenerics" ,r-biocgenerics)
7511 ("r-biocparallel" ,r-biocparallel)
7512 ("r-biostrings" ,r-biostrings)
7513 ("r-bitops" ,r-bitops)
7514 ("r-genomeinfodb" ,r-genomeinfodb)
7515 ("r-genomicranges" ,r-genomicranges)
7516 ("r-iranges" ,r-iranges)
7517 ("r-s4vectors" ,r-s4vectors)
7518 ("r-xvector" ,r-xvector)))
7519 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7520 (synopsis "Interface to samtools, bcftools, and tabix")
7522 "This package provides an interface to the 'samtools', 'bcftools', and
7523 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7524 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7526 (license license:expat)))
7528 (define-public r-delayedarray
7530 (name "r-delayedarray")
7534 (uri (bioconductor-uri "DelayedArray" version))
7537 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7539 `((upstream-name . "DelayedArray")))
7540 (build-system r-build-system)
7542 `(("r-biocgenerics" ,r-biocgenerics)
7543 ("r-s4vectors" ,r-s4vectors)
7544 ("r-iranges" ,r-iranges)
7545 ("r-matrixstats" ,r-matrixstats)))
7546 (home-page "https://bioconductor.org/packages/DelayedArray")
7547 (synopsis "Delayed operations on array-like objects")
7549 "Wrapping an array-like object (typically an on-disk object) in a
7550 @code{DelayedArray} object allows one to perform common array operations on it
7551 without loading the object in memory. In order to reduce memory usage and
7552 optimize performance, operations on the object are either delayed or executed
7553 using a block processing mechanism. Note that this also works on in-memory
7554 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7555 @code{Matrix} objects, and ordinary arrays and data frames.")
7556 (license license:artistic2.0)))
7558 (define-public r-summarizedexperiment
7560 (name "r-summarizedexperiment")
7564 (uri (bioconductor-uri "SummarizedExperiment" version))
7567 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7569 `((upstream-name . "SummarizedExperiment")))
7570 (build-system r-build-system)
7572 `(("r-biobase" ,r-biobase)
7573 ("r-biocgenerics" ,r-biocgenerics)
7574 ("r-delayedarray" ,r-delayedarray)
7575 ("r-genomeinfodb" ,r-genomeinfodb)
7576 ("r-genomicranges" ,r-genomicranges)
7577 ("r-iranges" ,r-iranges)
7578 ("r-matrix" ,r-matrix)
7579 ("r-s4vectors" ,r-s4vectors)))
7580 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7581 (synopsis "Container for representing genomic ranges by sample")
7583 "The SummarizedExperiment container contains one or more assays, each
7584 represented by a matrix-like object of numeric or other mode. The rows
7585 typically represent genomic ranges of interest and the columns represent
7587 (license license:artistic2.0)))
7589 (define-public r-genomicalignments
7591 (name "r-genomicalignments")
7595 (uri (bioconductor-uri "GenomicAlignments" version))
7598 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7600 `((upstream-name . "GenomicAlignments")))
7601 (build-system r-build-system)
7603 `(("r-biocgenerics" ,r-biocgenerics)
7604 ("r-biocparallel" ,r-biocparallel)
7605 ("r-biostrings" ,r-biostrings)
7606 ("r-genomeinfodb" ,r-genomeinfodb)
7607 ("r-genomicranges" ,r-genomicranges)
7608 ("r-iranges" ,r-iranges)
7609 ("r-rsamtools" ,r-rsamtools)
7610 ("r-s4vectors" ,r-s4vectors)
7611 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7612 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7613 (synopsis "Representation and manipulation of short genomic alignments")
7615 "This package provides efficient containers for storing and manipulating
7616 short genomic alignments (typically obtained by aligning short reads to a
7617 reference genome). This includes read counting, computing the coverage,
7618 junction detection, and working with the nucleotide content of the
7620 (license license:artistic2.0)))
7622 (define-public r-rtracklayer
7624 (name "r-rtracklayer")
7628 (uri (bioconductor-uri "rtracklayer" version))
7631 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7632 (build-system r-build-system)
7635 (modify-phases %standard-phases
7636 (add-after 'unpack 'use-system-zlib
7638 (substitute* "DESCRIPTION"
7639 ((" zlibbioc,") ""))
7640 (substitute* "NAMESPACE"
7641 (("import\\(zlibbioc\\)") ""))
7646 `(("r-biocgenerics" ,r-biocgenerics)
7647 ("r-biostrings" ,r-biostrings)
7648 ("r-genomeinfodb" ,r-genomeinfodb)
7649 ("r-genomicalignments" ,r-genomicalignments)
7650 ("r-genomicranges" ,r-genomicranges)
7651 ("r-iranges" ,r-iranges)
7652 ("r-rcurl" ,r-rcurl)
7653 ("r-rsamtools" ,r-rsamtools)
7654 ("r-s4vectors" ,r-s4vectors)
7656 ("r-xvector" ,r-xvector)))
7657 (home-page "https://bioconductor.org/packages/rtracklayer")
7658 (synopsis "R interface to genome browsers and their annotation tracks")
7660 "rtracklayer is an extensible framework for interacting with multiple
7661 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7662 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7663 built-in). The user may export/import tracks to/from the supported browsers,
7664 as well as query and modify the browser state, such as the current viewport.")
7665 (license license:artistic2.0)))
7667 (define-public r-genomicfeatures
7669 (name "r-genomicfeatures")
7673 (uri (bioconductor-uri "GenomicFeatures" version))
7676 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7678 `((upstream-name . "GenomicFeatures")))
7679 (build-system r-build-system)
7681 `(("r-annotationdbi" ,r-annotationdbi)
7682 ("r-biobase" ,r-biobase)
7683 ("r-biocgenerics" ,r-biocgenerics)
7684 ("r-biomart" ,r-biomart)
7685 ("r-biostrings" ,r-biostrings)
7687 ("r-genomeinfodb" ,r-genomeinfodb)
7688 ("r-genomicranges" ,r-genomicranges)
7689 ("r-iranges" ,r-iranges)
7690 ("r-rcurl" ,r-rcurl)
7691 ("r-rsqlite" ,r-rsqlite)
7692 ("r-rmysql" ,r-rmysql)
7693 ("r-rtracklayer" ,r-rtracklayer)
7694 ("r-s4vectors" ,r-s4vectors)
7695 ("r-xvector" ,r-xvector)))
7696 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7697 (synopsis "Tools for working with transcript centric annotations")
7699 "This package provides a set of tools and methods for making and
7700 manipulating transcript centric annotations. With these tools the user can
7701 easily download the genomic locations of the transcripts, exons and cds of a
7702 given organism, from either the UCSC Genome Browser or a BioMart
7703 database (more sources will be supported in the future). This information is
7704 then stored in a local database that keeps track of the relationship between
7705 transcripts, exons, cds and genes. Flexible methods are provided for
7706 extracting the desired features in a convenient format.")
7707 (license license:artistic2.0)))
7709 (define-public r-go-db
7715 (uri (string-append "https://www.bioconductor.org/packages/"
7716 "release/data/annotation/src/contrib/GO.db_"
7720 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7722 `((upstream-name . "GO.db")))
7723 (build-system r-build-system)
7725 `(("r-annotationdbi" ,r-annotationdbi)))
7726 (home-page "https://bioconductor.org/packages/GO.db")
7727 (synopsis "Annotation maps describing the entire Gene Ontology")
7729 "The purpose of this GO.db annotation package is to provide detailed
7730 information about the latest version of the Gene Ontologies.")
7731 (license license:artistic2.0)))
7733 (define-public r-graph
7739 (uri (bioconductor-uri "graph" version))
7742 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7743 (build-system r-build-system)
7745 `(("r-biocgenerics" ,r-biocgenerics)))
7746 (home-page "https://bioconductor.org/packages/graph")
7747 (synopsis "Handle graph data structures in R")
7749 "This package implements some simple graph handling capabilities for R.")
7750 (license license:artistic2.0)))
7752 (define-public r-topgo
7758 (uri (bioconductor-uri "topGO" version))
7761 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7763 `((upstream-name . "topGO")))
7764 (build-system r-build-system)
7766 `(("r-annotationdbi" ,r-annotationdbi)
7768 ("r-biobase" ,r-biobase)
7769 ("r-biocgenerics" ,r-biocgenerics)
7770 ("r-go-db" ,r-go-db)
7771 ("r-graph" ,r-graph)
7772 ("r-lattice" ,r-lattice)
7773 ("r-matrixstats" ,r-matrixstats)
7774 ("r-sparsem" ,r-sparsem)))
7775 (home-page "https://bioconductor.org/packages/topGO")
7776 (synopsis "Enrichment analysis for gene ontology")
7778 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7779 terms while accounting for the topology of the GO graph. Different test
7780 statistics and different methods for eliminating local similarities and
7781 dependencies between GO terms can be implemented and applied.")
7782 ;; Any version of the LGPL applies.
7783 (license license:lgpl2.1+)))
7785 (define-public r-bsgenome
7791 (uri (bioconductor-uri "BSgenome" version))
7794 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7796 `((upstream-name . "BSgenome")))
7797 (build-system r-build-system)
7799 `(("r-biocgenerics" ,r-biocgenerics)
7800 ("r-biostrings" ,r-biostrings)
7801 ("r-genomeinfodb" ,r-genomeinfodb)
7802 ("r-genomicranges" ,r-genomicranges)
7803 ("r-iranges" ,r-iranges)
7804 ("r-rsamtools" ,r-rsamtools)
7805 ("r-rtracklayer" ,r-rtracklayer)
7806 ("r-s4vectors" ,r-s4vectors)
7807 ("r-xvector" ,r-xvector)))
7808 (home-page "https://bioconductor.org/packages/BSgenome")
7809 (synopsis "Infrastructure for Biostrings-based genome data packages")
7811 "This package provides infrastructure shared by all Biostrings-based
7812 genome data packages and support for efficient SNP representation.")
7813 (license license:artistic2.0)))
7815 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7817 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7821 ;; We cannot use bioconductor-uri here because this tarball is
7822 ;; located under "data/annotation/" instead of "bioc/".
7823 (uri (string-append "https://www.bioconductor.org/packages/"
7824 "release/data/annotation/src/contrib/"
7825 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7829 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7831 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7832 (build-system r-build-system)
7833 ;; As this package provides little more than a very large data file it
7834 ;; doesn't make sense to build substitutes.
7835 (arguments `(#:substitutable? #f))
7837 `(("r-bsgenome" ,r-bsgenome)))
7839 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7840 (synopsis "Full genome sequences for Homo sapiens")
7842 "This package provides full genome sequences for Homo sapiens from
7843 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7844 (license license:artistic2.0)))
7846 (define-public r-impute
7852 (uri (bioconductor-uri "impute" version))
7855 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7857 `(("gfortran" ,gfortran)))
7858 (build-system r-build-system)
7859 (home-page "https://bioconductor.org/packages/impute")
7860 (synopsis "Imputation for microarray data")
7862 "This package provides a function to impute missing gene expression
7863 microarray data, using nearest neighbor averaging.")
7864 (license license:gpl2+)))
7866 (define-public r-seqpattern
7868 (name "r-seqpattern")
7872 (uri (bioconductor-uri "seqPattern" version))
7875 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7877 `((upstream-name . "seqPattern")))
7878 (build-system r-build-system)
7880 `(("r-biostrings" ,r-biostrings)
7881 ("r-genomicranges" ,r-genomicranges)
7882 ("r-iranges" ,r-iranges)
7883 ("r-kernsmooth" ,r-kernsmooth)
7884 ("r-plotrix" ,r-plotrix)))
7885 (home-page "https://bioconductor.org/packages/seqPattern")
7886 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7888 "This package provides tools to visualize oligonucleotide patterns and
7889 sequence motif occurrences across a large set of sequences centred at a common
7890 reference point and sorted by a user defined feature.")
7891 (license license:gpl3+)))
7893 (define-public r-genomation
7895 (name "r-genomation")
7899 (uri (bioconductor-uri "genomation" version))
7902 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7903 (build-system r-build-system)
7905 `(("r-biostrings" ,r-biostrings)
7906 ("r-bsgenome" ,r-bsgenome)
7907 ("r-data-table" ,r-data-table)
7908 ("r-genomeinfodb" ,r-genomeinfodb)
7909 ("r-genomicalignments" ,r-genomicalignments)
7910 ("r-genomicranges" ,r-genomicranges)
7911 ("r-ggplot2" ,r-ggplot2)
7912 ("r-gridbase" ,r-gridbase)
7913 ("r-impute" ,r-impute)
7914 ("r-iranges" ,r-iranges)
7915 ("r-matrixstats" ,r-matrixstats)
7916 ("r-plotrix" ,r-plotrix)
7919 ("r-readr" ,r-readr)
7920 ("r-reshape2" ,r-reshape2)
7921 ("r-rsamtools" ,r-rsamtools)
7922 ("r-rtracklayer" ,r-rtracklayer)
7923 ("r-runit" ,r-runit)
7924 ("r-s4vectors" ,r-s4vectors)
7925 ("r-seqpattern" ,r-seqpattern)))
7926 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7927 (synopsis "Summary, annotation and visualization of genomic data")
7929 "This package provides a package for summary and annotation of genomic
7930 intervals. Users can visualize and quantify genomic intervals over
7931 pre-defined functional regions, such as promoters, exons, introns, etc. The
7932 genomic intervals represent regions with a defined chromosome position, which
7933 may be associated with a score, such as aligned reads from HT-seq experiments,
7934 TF binding sites, methylation scores, etc. The package can use any tabular
7935 genomic feature data as long as it has minimal information on the locations of
7936 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7937 (license license:artistic2.0)))
7939 (define-public r-genomationdata
7941 (name "r-genomationdata")
7945 ;; We cannot use bioconductor-uri here because this tarball is
7946 ;; located under "data/annotation/" instead of "bioc/".
7947 (uri (string-append "https://bioconductor.org/packages/"
7948 "release/data/experiment/src/contrib/"
7949 "genomationData_" version ".tar.gz"))
7952 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7953 (build-system r-build-system)
7954 ;; As this package provides little more than large data files, it doesn't
7955 ;; make sense to build substitutes.
7956 (arguments `(#:substitutable? #f))
7958 `(("r-knitr" ,r-knitr)))
7959 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7960 (synopsis "Experimental data for use with the genomation package")
7962 "This package contains experimental genetic data for use with the
7963 genomation package. Included are Chip Seq, Methylation and Cage data,
7964 downloaded from Encode.")
7965 (license license:gpl3+)))
7967 (define-public r-org-hs-eg-db
7969 (name "r-org-hs-eg-db")
7973 ;; We cannot use bioconductor-uri here because this tarball is
7974 ;; located under "data/annotation/" instead of "bioc/".
7975 (uri (string-append "https://www.bioconductor.org/packages/"
7976 "release/data/annotation/src/contrib/"
7977 "org.Hs.eg.db_" version ".tar.gz"))
7980 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7982 `((upstream-name . "org.Hs.eg.db")))
7983 (build-system r-build-system)
7985 `(("r-annotationdbi" ,r-annotationdbi)))
7986 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7987 (synopsis "Genome wide annotation for Human")
7989 "This package contains genome-wide annotations for Human, primarily based
7990 on mapping using Entrez Gene identifiers.")
7991 (license license:artistic2.0)))
7993 (define-public r-org-ce-eg-db
7995 (name "r-org-ce-eg-db")
7999 ;; We cannot use bioconductor-uri here because this tarball is
8000 ;; located under "data/annotation/" instead of "bioc/".
8001 (uri (string-append "https://www.bioconductor.org/packages/"
8002 "release/data/annotation/src/contrib/"
8003 "org.Ce.eg.db_" version ".tar.gz"))
8006 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8008 `((upstream-name . "org.Ce.eg.db")))
8009 (build-system r-build-system)
8011 `(("r-annotationdbi" ,r-annotationdbi)))
8012 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8013 (synopsis "Genome wide annotation for Worm")
8015 "This package provides mappings from Entrez gene identifiers to various
8016 annotations for the genome of the model worm Caenorhabditis elegans.")
8017 (license license:artistic2.0)))
8019 (define-public r-org-dm-eg-db
8021 (name "r-org-dm-eg-db")
8025 ;; We cannot use bioconductor-uri here because this tarball is
8026 ;; located under "data/annotation/" instead of "bioc/".
8027 (uri (string-append "https://www.bioconductor.org/packages/"
8028 "release/data/annotation/src/contrib/"
8029 "org.Dm.eg.db_" version ".tar.gz"))
8032 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8034 `((upstream-name . "org.Dm.eg.db")))
8035 (build-system r-build-system)
8037 `(("r-annotationdbi" ,r-annotationdbi)))
8038 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8039 (synopsis "Genome wide annotation for Fly")
8041 "This package provides mappings from Entrez gene identifiers to various
8042 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8043 (license license:artistic2.0)))
8045 (define-public r-org-mm-eg-db
8047 (name "r-org-mm-eg-db")
8051 ;; We cannot use bioconductor-uri here because this tarball is
8052 ;; located under "data/annotation/" instead of "bioc/".
8053 (uri (string-append "https://www.bioconductor.org/packages/"
8054 "release/data/annotation/src/contrib/"
8055 "org.Mm.eg.db_" version ".tar.gz"))
8058 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8060 `((upstream-name . "org.Mm.eg.db")))
8061 (build-system r-build-system)
8063 `(("r-annotationdbi" ,r-annotationdbi)))
8064 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8065 (synopsis "Genome wide annotation for Mouse")
8067 "This package provides mappings from Entrez gene identifiers to various
8068 annotations for the genome of the model mouse Mus musculus.")
8069 (license license:artistic2.0)))
8071 (define-public r-seqlogo
8078 (uri (bioconductor-uri "seqLogo" version))
8081 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
8082 (properties `((upstream-name . "seqLogo")))
8083 (build-system r-build-system)
8084 (home-page "https://bioconductor.org/packages/seqLogo")
8085 (synopsis "Sequence logos for DNA sequence alignments")
8087 "seqLogo takes the position weight matrix of a DNA sequence motif and
8088 plots the corresponding sequence logo as introduced by Schneider and
8090 (license license:lgpl2.0+)))
8092 (define-public r-bsgenome-hsapiens-ucsc-hg19
8094 (name "r-bsgenome-hsapiens-ucsc-hg19")
8098 ;; We cannot use bioconductor-uri here because this tarball is
8099 ;; located under "data/annotation/" instead of "bioc/".
8100 (uri (string-append "https://www.bioconductor.org/packages/"
8101 "release/data/annotation/src/contrib/"
8102 "BSgenome.Hsapiens.UCSC.hg19_"
8106 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8108 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8109 (build-system r-build-system)
8110 ;; As this package provides little more than a very large data file it
8111 ;; doesn't make sense to build substitutes.
8112 (arguments `(#:substitutable? #f))
8114 `(("r-bsgenome" ,r-bsgenome)))
8116 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8117 (synopsis "Full genome sequences for Homo sapiens")
8119 "This package provides full genome sequences for Homo sapiens as provided
8120 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8121 (license license:artistic2.0)))
8123 (define-public r-bsgenome-mmusculus-ucsc-mm9
8125 (name "r-bsgenome-mmusculus-ucsc-mm9")
8129 ;; We cannot use bioconductor-uri here because this tarball is
8130 ;; located under "data/annotation/" instead of "bioc/".
8131 (uri (string-append "https://www.bioconductor.org/packages/"
8132 "release/data/annotation/src/contrib/"
8133 "BSgenome.Mmusculus.UCSC.mm9_"
8137 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8139 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8140 (build-system r-build-system)
8141 ;; As this package provides little more than a very large data file it
8142 ;; doesn't make sense to build substitutes.
8143 (arguments `(#:substitutable? #f))
8145 `(("r-bsgenome" ,r-bsgenome)))
8147 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8148 (synopsis "Full genome sequences for Mouse")
8150 "This package provides full genome sequences for Mus musculus (Mouse) as
8151 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8152 (license license:artistic2.0)))
8154 (define-public r-bsgenome-mmusculus-ucsc-mm10
8156 (name "r-bsgenome-mmusculus-ucsc-mm10")
8160 ;; We cannot use bioconductor-uri here because this tarball is
8161 ;; located under "data/annotation/" instead of "bioc/".
8162 (uri (string-append "https://www.bioconductor.org/packages/"
8163 "release/data/annotation/src/contrib/"
8164 "BSgenome.Mmusculus.UCSC.mm10_"
8168 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8170 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8171 (build-system r-build-system)
8172 ;; As this package provides little more than a very large data file it
8173 ;; doesn't make sense to build substitutes.
8174 (arguments `(#:substitutable? #f))
8176 `(("r-bsgenome" ,r-bsgenome)))
8178 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8179 (synopsis "Full genome sequences for Mouse")
8181 "This package provides full genome sequences for Mus
8182 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8183 in Biostrings objects.")
8184 (license license:artistic2.0)))
8186 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8188 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
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 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8200 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8202 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
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)
8209 ("r-genomicfeatures" ,r-genomicfeatures)
8210 ("r-annotationdbi" ,r-annotationdbi)))
8212 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8213 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8215 "This package loads a TxDb object, which is an R interface to
8216 prefabricated databases contained in this package. This package provides
8217 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8218 based on the knownGene track.")
8219 (license license:artistic2.0)))
8221 (define-public r-bsgenome-celegans-ucsc-ce6
8223 (name "r-bsgenome-celegans-ucsc-ce6")
8227 ;; We cannot use bioconductor-uri here because this tarball is
8228 ;; located under "data/annotation/" instead of "bioc/".
8229 (uri (string-append "https://www.bioconductor.org/packages/"
8230 "release/data/annotation/src/contrib/"
8231 "BSgenome.Celegans.UCSC.ce6_"
8235 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8237 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8238 (build-system r-build-system)
8239 ;; As this package provides little more than a very large data file it
8240 ;; doesn't make sense to build substitutes.
8241 (arguments `(#:substitutable? #f))
8243 `(("r-bsgenome" ,r-bsgenome)))
8245 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8246 (synopsis "Full genome sequences for Worm")
8248 "This package provides full genome sequences for Caenorhabditis
8249 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8251 (license license:artistic2.0)))
8253 (define-public r-bsgenome-celegans-ucsc-ce10
8255 (name "r-bsgenome-celegans-ucsc-ce10")
8259 ;; We cannot use bioconductor-uri here because this tarball is
8260 ;; located under "data/annotation/" instead of "bioc/".
8261 (uri (string-append "https://www.bioconductor.org/packages/"
8262 "release/data/annotation/src/contrib/"
8263 "BSgenome.Celegans.UCSC.ce10_"
8267 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8269 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8270 (build-system r-build-system)
8271 ;; As this package provides little more than a very large data file it
8272 ;; doesn't make sense to build substitutes.
8273 (arguments `(#:substitutable? #f))
8275 `(("r-bsgenome" ,r-bsgenome)))
8277 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8278 (synopsis "Full genome sequences for Worm")
8280 "This package provides full genome sequences for Caenorhabditis
8281 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8283 (license license:artistic2.0)))
8285 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8287 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8291 ;; We cannot use bioconductor-uri here because this tarball is
8292 ;; located under "data/annotation/" instead of "bioc/".
8293 (uri (string-append "https://www.bioconductor.org/packages/"
8294 "release/data/annotation/src/contrib/"
8295 "BSgenome.Dmelanogaster.UCSC.dm3_"
8299 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8301 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8302 (build-system r-build-system)
8303 ;; As this package provides little more than a very large data file it
8304 ;; doesn't make sense to build substitutes.
8305 (arguments `(#:substitutable? #f))
8307 `(("r-bsgenome" ,r-bsgenome)))
8309 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8310 (synopsis "Full genome sequences for Fly")
8312 "This package provides full genome sequences for Drosophila
8313 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8314 Biostrings objects.")
8315 (license license:artistic2.0)))
8317 (define-public r-motifrg
8324 (uri (bioconductor-uri "motifRG" version))
8327 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8328 (properties `((upstream-name . "motifRG")))
8329 (build-system r-build-system)
8331 `(("r-biostrings" ,r-biostrings)
8332 ("r-bsgenome" ,r-bsgenome)
8333 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8334 ("r-iranges" ,r-iranges)
8335 ("r-seqlogo" ,r-seqlogo)
8336 ("r-xvector" ,r-xvector)))
8337 (home-page "https://bioconductor.org/packages/motifRG")
8338 (synopsis "Discover motifs in high throughput sequencing data")
8340 "This package provides tools for discriminative motif discovery in high
8341 throughput genetic sequencing data sets using regression methods.")
8342 (license license:artistic2.0)))
8344 (define-public r-qtl
8351 (uri (string-append "mirror://cran/src/contrib/qtl_"
8355 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8356 (build-system r-build-system)
8357 (home-page "http://rqtl.org/")
8358 (synopsis "R package for analyzing QTL experiments in genetics")
8359 (description "R/qtl is an extension library for the R statistics
8360 system. It is used to analyze experimental crosses for identifying
8361 genes contributing to variation in quantitative traits (so-called
8362 quantitative trait loci, QTLs).
8364 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8365 identify genotyping errors, and to perform single-QTL and two-QTL,
8366 two-dimensional genome scans.")
8367 (license license:gpl3)))
8369 (define-public r-zlibbioc
8375 (uri (bioconductor-uri "zlibbioc" version))
8378 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8380 `((upstream-name . "zlibbioc")))
8381 (build-system r-build-system)
8382 (home-page "https://bioconductor.org/packages/zlibbioc")
8383 (synopsis "Provider for zlib-1.2.5 to R packages")
8384 (description "This package uses the source code of zlib-1.2.5 to create
8385 libraries for systems that do not have these available via other means.")
8386 (license license:artistic2.0)))
8388 (define-public r-r4rna
8395 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8399 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8400 (build-system r-build-system)
8402 `(("r-optparse" ,r-optparse)
8403 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8404 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8405 (synopsis "Analysis framework for RNA secondary structure")
8407 "The R4RNA package aims to be a general framework for the analysis of RNA
8408 secondary structure and comparative analysis in R.")
8409 (license license:gpl3+)))
8411 (define-public r-rhtslib
8418 (uri (bioconductor-uri "Rhtslib" version))
8421 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8422 (properties `((upstream-name . "Rhtslib")))
8423 (build-system r-build-system)
8425 `(("r-zlibbioc" ,r-zlibbioc)))
8429 `(("autoconf" ,autoconf)))
8430 (home-page "https://github.com/nhayden/Rhtslib")
8431 (synopsis "High-throughput sequencing library as an R package")
8433 "This package provides the HTSlib C library for high-throughput
8434 nucleotide sequence analysis. The package is primarily useful to developers
8435 of other R packages who wish to make use of HTSlib.")
8436 (license license:lgpl2.0+)))
8438 (define-public r-bamsignals
8440 (name "r-bamsignals")
8445 (uri (bioconductor-uri "bamsignals" version))
8448 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8449 (build-system r-build-system)
8451 `(("r-biocgenerics" ,r-biocgenerics)
8452 ("r-genomicranges" ,r-genomicranges)
8453 ("r-iranges" ,r-iranges)
8455 ("r-rhtslib" ,r-rhtslib)
8456 ("r-zlibbioc" ,r-zlibbioc)))
8459 (home-page "https://bioconductor.org/packages/bamsignals")
8460 (synopsis "Extract read count signals from bam files")
8462 "This package allows to efficiently obtain count vectors from indexed bam
8463 files. It counts the number of nucleotide sequence reads in given genomic
8464 ranges and it computes reads profiles and coverage profiles. It also handles
8466 (license license:gpl2+)))
8468 (define-public r-rcas
8474 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8476 (file-name (string-append name "-" version ".tar.gz"))
8479 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8480 (build-system r-build-system)
8482 `(("r-knitr" ,r-knitr)
8483 ("r-testthat" ,r-testthat)
8484 ;; During vignette building knitr checks that "pandoc-citeproc"
8486 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8488 `(("r-data-table" ,r-data-table)
8489 ("r-biomart" ,r-biomart)
8490 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8491 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8492 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8493 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8494 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8495 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8496 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8497 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8498 ("r-topgo" ,r-topgo)
8500 ("r-pbapply" ,r-pbapply)
8501 ("r-plotly" ,r-plotly)
8502 ("r-plotrix" ,r-plotrix)
8503 ("r-motifrg" ,r-motifrg)
8504 ("r-genomation" ,r-genomation)
8505 ("r-genomicfeatures" ,r-genomicfeatures)
8506 ("r-rtracklayer" ,r-rtracklayer)
8507 ("r-rmarkdown" ,r-rmarkdown)))
8508 (synopsis "RNA-centric annotation system")
8510 "RCAS aims to be a standalone RNA-centric annotation system that provides
8511 intuitive reports and publication-ready graphics. This package provides the R
8512 library implementing most of the pipeline's features.")
8513 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8514 (license license:artistic2.0)))
8516 (define-public rcas-web
8523 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8524 "releases/download/v" version
8525 "/rcas-web-" version ".tar.gz"))
8528 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8529 (build-system gnu-build-system)
8532 (modify-phases %standard-phases
8533 (add-after 'install 'wrap-executable
8534 (lambda* (#:key inputs outputs #:allow-other-keys)
8535 (let* ((out (assoc-ref outputs "out"))
8536 (json (assoc-ref inputs "guile-json"))
8537 (redis (assoc-ref inputs "guile-redis"))
8538 (path (string-append
8539 json "/share/guile/site/2.2:"
8540 redis "/share/guile/site/2.2")))
8541 (wrap-program (string-append out "/bin/rcas-web")
8542 `("GUILE_LOAD_PATH" ":" = (,path))
8543 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8544 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8547 `(("r-minimal" ,r-minimal)
8549 ("guile-next" ,guile-2.2)
8550 ("guile-json" ,guile-json)
8551 ("guile-redis" ,guile2.2-redis)))
8553 `(("pkg-config" ,pkg-config)))
8554 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8555 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8556 (description "This package provides a simple web interface for the
8557 @dfn{RNA-centric annotation system} (RCAS).")
8558 (license license:agpl3+)))
8560 (define-public r-mutationalpatterns
8562 (name "r-mutationalpatterns")
8567 (uri (bioconductor-uri "MutationalPatterns" version))
8570 "0ml4gsp5dfv23xqrknxh25q8q65hly1xb1215lcwyc8hj9z8f941"))))
8571 (build-system r-build-system)
8573 `(("r-biocgenerics" ,r-biocgenerics)
8574 ("r-biostrings" ,r-biostrings)
8575 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8576 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8577 ("r-genomicranges" ,r-genomicranges)
8578 ("r-genomeinfodb" ,r-genomeinfodb)
8579 ("r-ggplot2" ,r-ggplot2)
8580 ("r-iranges" ,r-iranges)
8583 ("r-pracma" ,r-pracma)
8584 ("r-reshape2" ,r-reshape2)
8585 ("r-cowplot" ,r-cowplot)
8586 ("r-ggdendro" ,r-ggdendro)
8587 ("r-s4vectors" ,r-s4vectors)
8588 ("r-summarizedexperiment" ,r-summarizedexperiment)
8589 ("r-variantannotation" ,r-variantannotation)))
8590 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8591 (synopsis "Extract and visualize mutational patterns in genomic data")
8592 (description "This package provides an extensive toolset for the
8593 characterization and visualization of a wide range of mutational patterns
8594 in SNV base substitution data.")
8595 (license license:expat)))
8597 (define-public r-wgcna
8604 (uri (cran-uri "WGCNA" version))
8607 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8608 (properties `((upstream-name . "WGCNA")))
8609 (build-system r-build-system)
8611 `(("r-annotationdbi" ,r-annotationdbi)
8612 ("r-doparallel" ,r-doparallel)
8613 ("r-dynamictreecut" ,r-dynamictreecut)
8614 ("r-fastcluster" ,r-fastcluster)
8615 ("r-foreach" ,r-foreach)
8616 ("r-go-db" ,r-go-db)
8617 ("r-hmisc" ,r-hmisc)
8618 ("r-impute" ,r-impute)
8620 ("r-robust" ,r-robust)
8621 ("r-survival" ,r-survival)
8622 ("r-matrixstats" ,r-matrixstats)
8623 ("r-preprocesscore" ,r-preprocesscore)))
8625 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8626 (synopsis "Weighted correlation network analysis")
8628 "This package provides functions necessary to perform Weighted
8629 Correlation Network Analysis on high-dimensional data. It includes functions
8630 for rudimentary data cleaning, construction and summarization of correlation
8631 networks, module identification and functions for relating both variables and
8632 modules to sample traits. It also includes a number of utility functions for
8633 data manipulation and visualization.")
8634 (license license:gpl2+)))
8636 (define-public r-chipkernels
8637 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8640 (name "r-chipkernels")
8641 (version (string-append "1.1-" revision "." (string-take commit 9)))
8646 (url "https://github.com/ManuSetty/ChIPKernels.git")
8648 (file-name (string-append name "-" version))
8651 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8652 (build-system r-build-system)
8654 `(("r-iranges" ,r-iranges)
8655 ("r-xvector" ,r-xvector)
8656 ("r-biostrings" ,r-biostrings)
8657 ("r-bsgenome" ,r-bsgenome)
8658 ("r-gtools" ,r-gtools)
8659 ("r-genomicranges" ,r-genomicranges)
8660 ("r-sfsmisc" ,r-sfsmisc)
8661 ("r-kernlab" ,r-kernlab)
8662 ("r-s4vectors" ,r-s4vectors)
8663 ("r-biocgenerics" ,r-biocgenerics)))
8664 (home-page "https://github.com/ManuSetty/ChIPKernels")
8665 (synopsis "Build string kernels for DNA Sequence analysis")
8666 (description "ChIPKernels is an R package for building different string
8667 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8668 must be built and this dictionary can be used for determining kernels for DNA
8670 (license license:gpl2+))))
8672 (define-public r-seqgl
8679 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8680 "archive/" version ".tar.gz"))
8681 (file-name (string-append name "-" version ".tar.gz"))
8684 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8685 (build-system r-build-system)
8687 `(("r-biostrings" ,r-biostrings)
8688 ("r-chipkernels" ,r-chipkernels)
8689 ("r-genomicranges" ,r-genomicranges)
8690 ("r-spams" ,r-spams)
8691 ("r-wgcna" ,r-wgcna)
8692 ("r-fastcluster" ,r-fastcluster)))
8693 (home-page "https://github.com/ManuSetty/SeqGL")
8694 (synopsis "Group lasso for Dnase/ChIP-seq data")
8695 (description "SeqGL is a group lasso based algorithm to extract
8696 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8697 This package presents a method which uses group lasso to discriminate between
8698 bound and non bound genomic regions to accurately identify transcription
8699 factors bound at the specific regions.")
8700 (license license:gpl2+)))
8702 (define-public r-gkmsvm
8709 (uri (cran-uri "gkmSVM" version))
8712 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8713 (properties `((upstream-name . "gkmSVM")))
8714 (build-system r-build-system)
8716 `(("r-biocgenerics" ,r-biocgenerics)
8717 ("r-biostrings" ,r-biostrings)
8718 ("r-genomeinfodb" ,r-genomeinfodb)
8719 ("r-genomicranges" ,r-genomicranges)
8720 ("r-iranges" ,r-iranges)
8721 ("r-kernlab" ,r-kernlab)
8724 ("r-rtracklayer" ,r-rtracklayer)
8725 ("r-s4vectors" ,r-s4vectors)
8726 ("r-seqinr" ,r-seqinr)))
8727 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8728 (synopsis "Gapped-kmer support vector machine")
8730 "This R package provides tools for training gapped-kmer SVM classifiers
8731 for DNA and protein sequences. This package supports several sequence
8732 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8733 (license license:gpl2+)))
8735 (define-public r-tximport
8741 (uri (bioconductor-uri "tximport" version))
8744 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8745 (build-system r-build-system)
8746 (home-page "https://bioconductor.org/packages/tximport")
8747 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8749 "This package provides tools to import transcript-level abundance,
8750 estimated counts and transcript lengths, and to summarize them into matrices
8751 for use with downstream gene-level analysis packages. Average transcript
8752 length, weighted by sample-specific transcript abundance estimates, is
8753 provided as a matrix which can be used as an offset for different expression
8754 of gene-level counts.")
8755 (license license:gpl2+)))
8757 (define-public r-rhdf5
8763 (uri (bioconductor-uri "rhdf5" version))
8766 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8767 (build-system r-build-system)
8770 (modify-phases %standard-phases
8771 (add-after 'unpack 'unpack-smallhdf5
8772 (lambda* (#:key outputs #:allow-other-keys)
8773 (system* "tar" "-xzvf"
8774 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8775 (substitute* "src/hdf5/configure"
8777 ;; Remove timestamp and host system information to make
8778 ;; the build reproducible.
8779 (substitute* "src/hdf5/src/libhdf5.settings.in"
8780 (("Configured on: @CONFIG_DATE@")
8781 "Configured on: Guix")
8782 (("Uname information:.*")
8783 "Uname information: Linux\n")
8784 ;; Remove unnecessary store reference.
8786 "C Compiler: GCC\n"))
8789 `(("r-zlibbioc" ,r-zlibbioc)))
8793 (home-page "https://bioconductor.org/packages/rhdf5")
8794 (synopsis "HDF5 interface to R")
8796 "This R/Bioconductor package provides an interface between HDF5 and R.
8797 HDF5's main features are the ability to store and access very large and/or
8798 complex datasets and a wide variety of metadata on mass storage (disk) through
8799 a completely portable file format. The rhdf5 package is thus suited for the
8800 exchange of large and/or complex datasets between R and other software
8801 package, and for letting R applications work on datasets that are larger than
8802 the available RAM.")
8803 (license license:artistic2.0)))
8805 (define-public r-annotationfilter
8807 (name "r-annotationfilter")
8811 (uri (bioconductor-uri "AnnotationFilter" version))
8814 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8816 `((upstream-name . "AnnotationFilter")))
8817 (build-system r-build-system)
8819 `(("r-genomicranges" ,r-genomicranges)
8820 ("r-lazyeval" ,r-lazyeval)))
8821 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8822 (synopsis "Facilities for filtering Bioconductor annotation resources")
8824 "This package provides classes and other infrastructure to implement
8825 filters for manipulating Bioconductor annotation resources. The filters are
8826 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8827 (license license:artistic2.0)))
8829 (define-public emboss
8835 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8836 (version-major+minor version) ".0/"
8837 "EMBOSS-" version ".tar.gz"))
8840 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8841 (build-system gnu-build-system)
8844 (list (string-append "--with-hpdf="
8845 (assoc-ref %build-inputs "libharu")))
8847 (modify-phases %standard-phases
8848 (add-after 'unpack 'fix-checks
8850 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8851 ;; and zlib, but assume that they are all found at the same
8853 (substitute* "configure.in"
8854 (("CHECK_PNGDRIVER")
8855 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8856 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8857 AM_CONDITIONAL(AMPNG, true)"))
8859 (add-after 'fix-checks 'disable-update-check
8861 ;; At build time there is no connection to the Internet, so
8862 ;; looking for updates will not work.
8863 (substitute* "Makefile.am"
8864 (("\\$\\(bindir\\)/embossupdate") ""))
8866 (add-after 'disable-update-check 'autogen
8867 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8873 ("libharu" ,libharu)
8876 `(("autoconf" ,autoconf)
8877 ("automake" ,automake)
8878 ("libtool" ,libtool)
8879 ("pkg-config" ,pkg-config)))
8880 (home-page "http://emboss.sourceforge.net")
8881 (synopsis "Molecular biology analysis suite")
8882 (description "EMBOSS is the \"European Molecular Biology Open Software
8883 Suite\". EMBOSS is an analysis package specially developed for the needs of
8884 the molecular biology (e.g. EMBnet) user community. The software
8885 automatically copes with data in a variety of formats and even allows
8886 transparent retrieval of sequence data from the web. It also provides a
8887 number of libraries for the development of software in the field of molecular
8888 biology. EMBOSS also integrates a range of currently available packages and
8889 tools for sequence analysis into a seamless whole.")
8890 (license license:gpl2+)))
8893 (let ((revision "1")
8894 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8897 ;; The version is 2.13.0 even though no release archives have been
8898 ;; published as yet.
8899 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8903 (url "https://github.com/arq5x/bits.git")
8905 (file-name (string-append name "-" version "-checkout"))
8908 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8909 (build-system gnu-build-system)
8911 `(#:tests? #f ;no tests included
8913 (modify-phases %standard-phases
8915 (add-after 'unpack 'remove-cuda
8917 (substitute* "Makefile"
8919 (("(bits_test_intersections) \\\\" _ match) match))
8922 (lambda* (#:key outputs #:allow-other-keys)
8924 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8929 (home-page "https://github.com/arq5x/bits")
8930 (synopsis "Implementation of binary interval search algorithm")
8931 (description "This package provides an implementation of the
8932 BITS (Binary Interval Search) algorithm, an approach to interval set
8933 intersection. It is especially suited for the comparison of diverse genomic
8934 datasets and the exploration of large datasets of genome
8935 intervals (e.g. genes, sequence alignments).")
8936 (license license:gpl2))))
8938 (define-public piranha
8939 ;; There is no release tarball for the latest version. The latest commit is
8940 ;; older than one year at the time of this writing.
8941 (let ((revision "1")
8942 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8945 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8949 (url "https://github.com/smithlabcode/piranha.git")
8951 (file-name (git-file-name name version))
8954 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8955 (build-system gnu-build-system)
8957 `(#:test-target "test"
8959 (modify-phases %standard-phases
8960 (add-after 'unpack 'copy-smithlab-cpp
8961 (lambda* (#:key inputs #:allow-other-keys)
8962 (for-each (lambda (file)
8963 (install-file file "./src/smithlab_cpp/"))
8964 (find-files (assoc-ref inputs "smithlab-cpp")))
8966 (add-after 'install 'install-to-store
8967 (lambda* (#:key outputs #:allow-other-keys)
8968 (let* ((out (assoc-ref outputs "out"))
8969 (bin (string-append out "/bin")))
8970 (for-each (lambda (file)
8971 (install-file file bin))
8972 (find-files "bin" ".*")))
8975 (list (string-append "--with-bam_tools_headers="
8976 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8977 (string-append "--with-bam_tools_library="
8978 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8980 `(("bamtools" ,bamtools)
8981 ("samtools" ,samtools-0.1)
8984 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8988 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8990 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8993 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8995 `(("python" ,python-2)))
8996 (home-page "https://github.com/smithlabcode/piranha")
8997 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8999 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9000 RIP-seq experiments. It takes input in BED or BAM format and identifies
9001 regions of statistically significant read enrichment. Additional covariates
9002 may optionally be provided to further inform the peak-calling process.")
9003 (license license:gpl3+))))
9011 (uri (string-append "https://pypi.python.org/packages/source/P"
9012 "/PePr/PePr-" version ".tar.gz"))
9015 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9016 (build-system python-build-system)
9018 `(#:python ,python-2 ; python2 only
9019 #:tests? #f)) ; no tests included
9021 `(("python2-numpy" ,python2-numpy)
9022 ("python2-scipy" ,python2-scipy)
9023 ("python2-pysam" ,python2-pysam)))
9024 (home-page "https://github.com/shawnzhangyx/PePr")
9025 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9027 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9028 that is primarily designed for data with biological replicates. It uses a
9029 negative binomial distribution to model the read counts among the samples in
9030 the same group, and look for consistent differences between ChIP and control
9031 group or two ChIP groups run under different conditions.")
9032 (license license:gpl3+)))
9034 (define-public filevercmp
9035 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9038 (version (string-append "0-1." (string-take commit 7)))
9041 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9043 (file-name (string-append name "-" version ".tar.gz"))
9045 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9046 (build-system gnu-build-system)
9048 `(#:tests? #f ; There are no tests to run.
9050 (modify-phases %standard-phases
9051 (delete 'configure) ; There is no configure phase.
9053 (lambda* (#:key outputs #:allow-other-keys)
9054 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9055 (install-file "filevercmp" bin)))))))
9056 (home-page "https://github.com/ekg/filevercmp")
9057 (synopsis "This program compares version strings")
9058 (description "This program compares version strings. It intends to be a
9059 replacement for strverscmp.")
9060 (license license:gpl3+))))
9062 (define-public multiqc
9069 (uri (pypi-uri "multiqc" version))
9072 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
9073 (build-system python-build-system)
9075 `(("python-jinja2" ,python-jinja2)
9076 ("python-simplejson" ,python-simplejson)
9077 ("python-pyyaml" ,python-pyyaml)
9078 ("python-click" ,python-click)
9079 ("python-spectra" ,python-spectra)
9080 ("python-requests" ,python-requests)
9081 ("python-markdown" ,python-markdown)
9082 ("python-lzstring" ,python-lzstring)
9083 ("python-matplotlib" ,python-matplotlib)
9084 ("python-numpy" ,python-numpy)
9085 ;; MultQC checks for the presence of nose at runtime.
9086 ("python-nose" ,python-nose)))
9087 (home-page "http://multiqc.info")
9088 (synopsis "Aggregate bioinformatics analysis reports")
9090 "MultiQC is a tool to aggregate bioinformatics results across many
9091 samples into a single report. It contains modules for a large number of
9092 common bioinformatics tools.")
9093 (license license:gpl3+)))
9095 (define-public r-chipseq
9102 (uri (bioconductor-uri "chipseq" version))
9105 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
9106 (build-system r-build-system)
9108 `(("r-biocgenerics" ,r-biocgenerics)
9109 ("r-genomicranges" ,r-genomicranges)
9110 ("r-iranges" ,r-iranges)
9111 ("r-lattice" ,r-lattice)
9112 ("r-s4vectors" ,r-s4vectors)
9113 ("r-shortread" ,r-shortread)))
9114 (home-page "https://bioconductor.org/packages/chipseq")
9115 (synopsis "Package for analyzing ChIPseq data")
9117 "This package provides tools for processing short read data from ChIPseq
9119 (license license:artistic2.0)))
9121 (define-public r-copyhelper
9123 (name "r-copyhelper")
9128 (uri (string-append "https://bioconductor.org/packages/release/"
9129 "data/experiment/src/contrib/CopyhelpeR_"
9133 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9134 (properties `((upstream-name . "CopyhelpeR")))
9135 (build-system r-build-system)
9136 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9137 (synopsis "Helper files for CopywriteR")
9139 "This package contains the helper files that are required to run the
9140 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9141 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9142 mm10. In addition, it contains a blacklist filter to remove regions that
9143 display copy number variation. Files are stored as GRanges objects from the
9144 GenomicRanges Bioconductor package.")
9145 (license license:gpl2)))
9147 (define-public r-copywriter
9149 (name "r-copywriter")
9154 (uri (bioconductor-uri "CopywriteR" version))
9157 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9158 (properties `((upstream-name . "CopywriteR")))
9159 (build-system r-build-system)
9161 `(("r-biocparallel" ,r-biocparallel)
9162 ("r-chipseq" ,r-chipseq)
9163 ("r-copyhelper" ,r-copyhelper)
9164 ("r-data-table" ,r-data-table)
9165 ("r-dnacopy" ,r-dnacopy)
9166 ("r-futile-logger" ,r-futile-logger)
9167 ("r-genomeinfodb" ,r-genomeinfodb)
9168 ("r-genomicalignments" ,r-genomicalignments)
9169 ("r-genomicranges" ,r-genomicranges)
9170 ("r-gtools" ,r-gtools)
9171 ("r-iranges" ,r-iranges)
9172 ("r-matrixstats" ,r-matrixstats)
9173 ("r-rsamtools" ,r-rsamtools)
9174 ("r-s4vectors" ,r-s4vectors)))
9175 (home-page "https://github.com/PeeperLab/CopywriteR")
9176 (synopsis "Copy number information from targeted sequencing")
9178 "CopywriteR extracts DNA copy number information from targeted sequencing
9179 by utilizing off-target reads. It allows for extracting uniformly distributed
9180 copy number information, can be used without reference, and can be applied to
9181 sequencing data obtained from various techniques including chromatin
9182 immunoprecipitation and target enrichment on small gene panels. Thereby,
9183 CopywriteR constitutes a widely applicable alternative to available copy
9184 number detection tools.")
9185 (license license:gpl2)))
9187 (define-public r-methylkit
9189 (name "r-methylkit")
9193 (uri (bioconductor-uri "methylKit" version))
9196 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9197 (properties `((upstream-name . "methylKit")))
9198 (build-system r-build-system)
9200 `(("r-data-table" ,r-data-table)
9201 ("r-emdbook" ,r-emdbook)
9202 ("r-fastseg" ,r-fastseg)
9203 ("r-genomeinfodb" ,r-genomeinfodb)
9204 ("r-genomicranges" ,r-genomicranges)
9205 ("r-gtools" ,r-gtools)
9206 ("r-iranges" ,r-iranges)
9207 ("r-kernsmooth" ,r-kernsmooth)
9208 ("r-limma" ,r-limma)
9209 ("r-mclust" ,r-mclust)
9210 ("r-qvalue" ,r-qvalue)
9211 ("r-r-utils" ,r-r-utils)
9213 ("r-rhtslib" ,r-rhtslib)
9214 ("r-rsamtools" ,r-rsamtools)
9215 ("r-rtracklayer" ,r-rtracklayer)
9216 ("r-s4vectors" ,r-s4vectors)
9217 ("r-zlibbioc" ,r-zlibbioc)))
9220 (home-page "https://github.com/al2na/methylKit")
9222 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9224 "MethylKit is an R package for DNA methylation analysis and annotation
9225 from high-throughput bisulfite sequencing. The package is designed to deal
9226 with sequencing data from @dfn{Reduced representation bisulfite
9227 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9228 genome bisulfite sequencing. It also has functions to analyze base-pair
9229 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9231 (license license:artistic2.0)))
9233 (define-public r-sva
9240 (uri (bioconductor-uri "sva" version))
9243 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9244 (build-system r-build-system)
9246 `(("r-genefilter" ,r-genefilter)
9248 ("r-biocparallel" ,r-biocparallel)
9249 ("r-matrixstats" ,r-matrixstats)
9250 ("r-limma" ,r-limma)))
9251 (home-page "https://bioconductor.org/packages/sva")
9252 (synopsis "Surrogate variable analysis")
9254 "This package contains functions for removing batch effects and other
9255 unwanted variation in high-throughput experiment. It also contains functions
9256 for identifying and building surrogate variables for high-dimensional data
9257 sets. Surrogate variables are covariates constructed directly from
9258 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9259 imaging data that can be used in subsequent analyses to adjust for unknown,
9260 unmodeled, or latent sources of noise.")
9261 (license license:artistic2.0)))
9263 (define-public r-seqminer
9270 (uri (cran-uri "seqminer" version))
9273 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9274 (build-system r-build-system)
9277 (home-page "http://seqminer.genomic.codes")
9278 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9280 "This package provides tools to integrate nucleotide sequencing
9281 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9282 ;; Any version of the GPL is acceptable
9283 (license (list license:gpl2+ license:gpl3+))))
9285 (define-public r-raremetals2
9287 (name "r-raremetals2")
9292 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9293 "b/b7/RareMETALS2_" version ".tar.gz"))
9296 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9297 (properties `((upstream-name . "RareMETALS2")))
9298 (build-system r-build-system)
9300 `(("r-seqminer" ,r-seqminer)
9301 ("r-mvtnorm" ,r-mvtnorm)
9303 ("r-compquadform" ,r-compquadform)
9304 ("r-getopt" ,r-getopt)))
9305 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9306 (synopsis "Analyze gene-level association tests for binary trait")
9308 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9309 It was designed to meta-analyze gene-level association tests for binary trait.
9310 While rareMETALS offers a near-complete solution for meta-analysis of
9311 gene-level tests for quantitative trait, it does not offer the optimal
9312 solution for binary trait. The package rareMETALS2 offers improved features
9313 for analyzing gene-level association tests in meta-analyses for binary
9315 (license license:gpl3)))
9317 (define-public r-maldiquant
9319 (name "r-maldiquant")
9324 (uri (cran-uri "MALDIquant" version))
9327 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9328 (properties `((upstream-name . "MALDIquant")))
9329 (build-system r-build-system)
9330 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9331 (synopsis "Quantitative analysis of mass spectrometry data")
9333 "This package provides a complete analysis pipeline for matrix-assisted
9334 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9335 two-dimensional mass spectrometry data. In addition to commonly used plotting
9336 and processing methods it includes distinctive features, namely baseline
9337 subtraction methods such as morphological filters (TopHat) or the
9338 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9339 alignment using warping functions, handling of replicated measurements as well
9340 as allowing spectra with different resolutions.")
9341 (license license:gpl3+)))
9343 (define-public r-protgenerics
9345 (name "r-protgenerics")
9350 (uri (bioconductor-uri "ProtGenerics" version))
9353 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9354 (properties `((upstream-name . "ProtGenerics")))
9355 (build-system r-build-system)
9356 (home-page "https://github.com/lgatto/ProtGenerics")
9357 (synopsis "S4 generic functions for proteomics infrastructure")
9359 "This package provides S4 generic functions needed by Bioconductor
9360 proteomics packages.")
9361 (license license:artistic2.0)))
9363 (define-public r-mzr
9370 (uri (bioconductor-uri "mzR" version))
9373 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9374 (modules '((guix build utils)))
9377 (delete-file-recursively "src/boost")
9379 (properties `((upstream-name . "mzR")))
9380 (build-system r-build-system)
9383 (modify-phases %standard-phases
9384 (add-after 'unpack 'use-system-boost
9386 (substitute* "src/Makevars"
9387 (("\\./boost/libs.*") "")
9388 (("ARCH_OBJS=" line)
9390 "\nARCH_LIBS=-lboost_system -lboost_regex \
9391 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9394 `(("boost" ,boost) ; use this instead of the bundled boost sources
9395 ("netcdf" ,netcdf)))
9397 `(("r-biobase" ,r-biobase)
9398 ("r-biocgenerics" ,r-biocgenerics)
9399 ("r-protgenerics" ,r-protgenerics)
9401 ("r-zlibbioc" ,r-zlibbioc)))
9402 (home-page "https://github.com/sneumann/mzR/")
9403 (synopsis "Parser for mass spectrometry data files")
9405 "The mzR package provides a unified API to the common file formats and
9406 parsers available for mass spectrometry data. It comes with a wrapper for the
9407 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9408 The package contains the original code written by the ISB, and a subset of the
9409 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9410 previously been used in XCMS.")
9411 (license license:artistic2.0)))
9413 (define-public r-affyio
9420 (uri (bioconductor-uri "affyio" version))
9423 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9424 (build-system r-build-system)
9426 `(("r-zlibbioc" ,r-zlibbioc)))
9429 (home-page "https://github.com/bmbolstad/affyio")
9430 (synopsis "Tools for parsing Affymetrix data files")
9432 "This package provides routines for parsing Affymetrix data files based
9433 upon file format information. The primary focus is on accessing the CEL and
9435 (license license:lgpl2.0+)))
9437 (define-public r-affy
9444 (uri (bioconductor-uri "affy" version))
9447 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9448 (build-system r-build-system)
9450 `(("r-affyio" ,r-affyio)
9451 ("r-biobase" ,r-biobase)
9452 ("r-biocgenerics" ,r-biocgenerics)
9453 ("r-biocinstaller" ,r-biocinstaller)
9454 ("r-preprocesscore" ,r-preprocesscore)
9455 ("r-zlibbioc" ,r-zlibbioc)))
9456 (home-page "https://bioconductor.org/packages/affy")
9457 (synopsis "Methods for affymetrix oligonucleotide arrays")
9459 "This package contains functions for exploratory oligonucleotide array
9461 (license license:lgpl2.0+)))
9463 (define-public r-vsn
9470 (uri (bioconductor-uri "vsn" version))
9473 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9474 (build-system r-build-system)
9476 `(("r-affy" ,r-affy)
9477 ("r-biobase" ,r-biobase)
9478 ("r-ggplot2" ,r-ggplot2)
9479 ("r-lattice" ,r-lattice)
9480 ("r-limma" ,r-limma)))
9481 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9482 (synopsis "Variance stabilization and calibration for microarray data")
9484 "The package implements a method for normalising microarray intensities,
9485 and works for single- and multiple-color arrays. It can also be used for data
9486 from other technologies, as long as they have similar format. The method uses
9487 a robust variant of the maximum-likelihood estimator for an
9488 additive-multiplicative error model and affine calibration. The model
9489 incorporates data calibration step (a.k.a. normalization), a model for the
9490 dependence of the variance on the mean intensity and a variance stabilizing
9491 data transformation. Differences between transformed intensities are
9492 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9493 their variance is independent of the mean, and they are usually more sensitive
9494 and specific in detecting differential transcription.")
9495 (license license:artistic2.0)))
9497 (define-public r-mzid
9504 (uri (bioconductor-uri "mzID" version))
9507 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9508 (properties `((upstream-name . "mzID")))
9509 (build-system r-build-system)
9511 `(("r-doparallel" ,r-doparallel)
9512 ("r-foreach" ,r-foreach)
9513 ("r-iterators" ,r-iterators)
9515 ("r-protgenerics" ,r-protgenerics)
9518 (home-page "https://bioconductor.org/packages/mzID")
9519 (synopsis "Parser for mzIdentML files")
9521 "This package provides a parser for mzIdentML files implemented using the
9522 XML package. The parser tries to be general and able to handle all types of
9523 mzIdentML files with the drawback of having less pretty output than a vendor
9525 (license license:gpl2+)))
9527 (define-public r-pcamethods
9529 (name "r-pcamethods")
9534 (uri (bioconductor-uri "pcaMethods" version))
9537 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9538 (properties `((upstream-name . "pcaMethods")))
9539 (build-system r-build-system)
9541 `(("r-biobase" ,r-biobase)
9542 ("r-biocgenerics" ,r-biocgenerics)
9544 ("r-rcpp" ,r-rcpp)))
9545 (home-page "https://github.com/hredestig/pcamethods")
9546 (synopsis "Collection of PCA methods")
9548 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9549 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9550 for missing value estimation is included for comparison. BPCA, PPCA and
9551 NipalsPCA may be used to perform PCA on incomplete data as well as for
9552 accurate missing value estimation. A set of methods for printing and plotting
9553 the results is also provided. All PCA methods make use of the same data
9554 structure (pcaRes) to provide a common interface to the PCA results.")
9555 (license license:gpl3+)))
9557 (define-public r-msnbase
9564 (uri (bioconductor-uri "MSnbase" version))
9567 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9568 (properties `((upstream-name . "MSnbase")))
9569 (build-system r-build-system)
9571 `(("r-affy" ,r-affy)
9572 ("r-biobase" ,r-biobase)
9573 ("r-biocgenerics" ,r-biocgenerics)
9574 ("r-biocparallel" ,r-biocparallel)
9575 ("r-digest" ,r-digest)
9576 ("r-ggplot2" ,r-ggplot2)
9577 ("r-impute" ,r-impute)
9578 ("r-iranges" ,r-iranges)
9579 ("r-lattice" ,r-lattice)
9580 ("r-maldiquant" ,r-maldiquant)
9583 ("r-pcamethods" ,r-pcamethods)
9585 ("r-preprocesscore" ,r-preprocesscore)
9586 ("r-protgenerics" ,r-protgenerics)
9588 ("r-s4vectors" ,r-s4vectors)
9591 (home-page "https://github.com/lgatto/MSnbase")
9592 (synopsis "Base functions and classes for MS-based proteomics")
9594 "This package provides basic plotting, data manipulation and processing
9595 of mass spectrometry based proteomics data.")
9596 (license license:artistic2.0)))
9598 (define-public r-msnid
9605 (uri (bioconductor-uri "MSnID" version))
9608 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9609 (properties `((upstream-name . "MSnID")))
9610 (build-system r-build-system)
9612 `(("r-biobase" ,r-biobase)
9613 ("r-data-table" ,r-data-table)
9614 ("r-doparallel" ,r-doparallel)
9615 ("r-dplyr" ,r-dplyr)
9616 ("r-foreach" ,r-foreach)
9617 ("r-iterators" ,r-iterators)
9618 ("r-msnbase" ,r-msnbase)
9621 ("r-protgenerics" ,r-protgenerics)
9622 ("r-r-cache" ,r-r-cache)
9624 ("r-reshape2" ,r-reshape2)))
9625 (home-page "https://bioconductor.org/packages/MSnID")
9626 (synopsis "Utilities for LC-MSn proteomics identifications")
9628 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9629 from mzIdentML (leveraging the mzID package) or text files. After collating
9630 the search results from multiple datasets it assesses their identification
9631 quality and optimize filtering criteria to achieve the maximum number of
9632 identifications while not exceeding a specified false discovery rate. It also
9633 contains a number of utilities to explore the MS/MS results and assess missed
9634 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9635 (license license:artistic2.0)))
9637 (define-public r-seurat
9643 (uri (cran-uri "Seurat" version))
9646 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9647 ;; Delete pre-built jar.
9649 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9651 (properties `((upstream-name . "Seurat")))
9652 (build-system r-build-system)
9655 (modify-phases %standard-phases
9656 (add-after 'unpack 'build-jar
9657 (lambda* (#:key inputs #:allow-other-keys)
9658 (let ((classesdir "tmp-classes"))
9659 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9661 (with-output-to-file "manifest"
9663 (display "Manifest-Version: 1.0
9664 Main-Class: ModularityOptimizer\n")))
9665 (and (zero? (apply system* `("javac" "-d" ,classesdir
9666 ,@(find-files "java" "\\.java$"))))
9667 (zero? (system* "jar"
9669 "inst/java/ModularityOptimizer.jar"
9670 "-C" classesdir ".")))))))))
9672 `(("jdk" ,icedtea "jdk")))
9675 ("r-caret" ,r-caret)
9676 ("r-cowplot" ,r-cowplot)
9677 ("r-diffusionmap" ,r-diffusionmap)
9678 ("r-dplyr" ,r-dplyr)
9682 ("r-gdata" ,r-gdata)
9683 ("r-ggplot2" ,r-ggplot2)
9684 ("r-ggridges" ,r-ggridges)
9685 ("r-gplots" ,r-gplots)
9686 ("r-gridextra" ,r-gridextra)
9687 ("r-hmisc" ,r-hmisc)
9689 ("r-igraph" ,r-igraph)
9690 ("r-irlba" ,r-irlba)
9693 ("r-matrix" ,r-matrix)
9694 ("r-metap" ,r-metap)
9695 ("r-mixtools" ,r-mixtools)
9696 ("r-pbapply" ,r-pbapply)
9697 ("r-plotly" ,r-plotly)
9698 ("r-ranger" ,r-ranger)
9699 ("r-rcolorbrewer" ,r-rcolorbrewer)
9701 ("r-rcppeigen" ,r-rcppeigen)
9702 ("r-rcppprogress" ,r-rcppprogress)
9703 ("r-reshape2" ,r-reshape2)
9705 ("r-rtsne" ,r-rtsne)
9706 ("r-sdmtools" ,r-sdmtools)
9707 ("r-stringr" ,r-stringr)
9708 ("r-tclust" ,r-tclust)
9709 ("r-tidyr" ,r-tidyr)
9711 ("r-vgam" ,r-vgam)))
9712 (home-page "http://www.satijalab.org/seurat")
9713 (synopsis "Seurat is an R toolkit for single cell genomics")
9715 "This package is an R package designed for QC, analysis, and
9716 exploration of single cell RNA-seq data. It easily enables widely-used
9717 analytical techniques, including the identification of highly variable genes,
9718 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9719 algorithms; density clustering, hierarchical clustering, k-means, and the
9720 discovery of differentially expressed genes and markers.")
9721 (license license:gpl3)))
9723 (define-public r-aroma-light
9725 (name "r-aroma-light")
9730 (uri (bioconductor-uri "aroma.light" version))
9733 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9734 (properties `((upstream-name . "aroma.light")))
9735 (build-system r-build-system)
9737 `(("r-matrixstats" ,r-matrixstats)
9738 ("r-r-methodss3" ,r-r-methodss3)
9740 ("r-r-utils" ,r-r-utils)))
9741 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9742 (synopsis "Methods for normalization and visualization of microarray data")
9744 "This package provides methods for microarray analysis that take basic
9745 data types such as matrices and lists of vectors. These methods can be used
9746 standalone, be utilized in other packages, or be wrapped up in higher-level
9748 (license license:gpl2+)))
9750 (define-public r-deseq
9757 (uri (bioconductor-uri "DESeq" version))
9760 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9761 (properties `((upstream-name . "DESeq")))
9762 (build-system r-build-system)
9764 `(("r-biobase" ,r-biobase)
9765 ("r-biocgenerics" ,r-biocgenerics)
9766 ("r-genefilter" ,r-genefilter)
9767 ("r-geneplotter" ,r-geneplotter)
9768 ("r-lattice" ,r-lattice)
9769 ("r-locfit" ,r-locfit)
9771 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9772 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9773 (synopsis "Differential gene expression analysis")
9775 "This package provides tools for estimating variance-mean dependence in
9776 count data from high-throughput genetic sequencing assays and for testing for
9777 differential expression based on a model using the negative binomial
9779 (license license:gpl3+)))
9781 (define-public r-edaseq
9788 (uri (bioconductor-uri "EDASeq" version))
9791 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9792 (properties `((upstream-name . "EDASeq")))
9793 (build-system r-build-system)
9795 `(("r-annotationdbi" ,r-annotationdbi)
9796 ("r-aroma-light" ,r-aroma-light)
9797 ("r-biobase" ,r-biobase)
9798 ("r-biocgenerics" ,r-biocgenerics)
9799 ("r-biomart" ,r-biomart)
9800 ("r-biostrings" ,r-biostrings)
9801 ("r-deseq" ,r-deseq)
9802 ("r-genomicfeatures" ,r-genomicfeatures)
9803 ("r-genomicranges" ,r-genomicranges)
9804 ("r-iranges" ,r-iranges)
9805 ("r-rsamtools" ,r-rsamtools)
9806 ("r-shortread" ,r-shortread)))
9807 (home-page "https://github.com/drisso/EDASeq")
9808 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9810 "This package provides support for numerical and graphical summaries of
9811 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9812 adjust for GC-content effect (or other gene-level effects) on read counts:
9813 loess robust local regression, global-scaling, and full-quantile
9814 normalization. Between-lane normalization procedures to adjust for
9815 distributional differences between lanes (e.g., sequencing depth):
9816 global-scaling and full-quantile normalization.")
9817 (license license:artistic2.0)))
9819 (define-public r-interactivedisplaybase
9821 (name "r-interactivedisplaybase")
9826 (uri (bioconductor-uri "interactiveDisplayBase" version))
9829 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9831 `((upstream-name . "interactiveDisplayBase")))
9832 (build-system r-build-system)
9834 `(("r-biocgenerics" ,r-biocgenerics)
9835 ("r-shiny" ,r-shiny)))
9836 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9837 (synopsis "Base package for web displays of Bioconductor objects")
9839 "This package contains the basic methods needed to generate interactive
9840 Shiny-based display methods for Bioconductor objects.")
9841 (license license:artistic2.0)))
9843 (define-public r-annotationhub
9845 (name "r-annotationhub")
9850 (uri (bioconductor-uri "AnnotationHub" version))
9853 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9854 (properties `((upstream-name . "AnnotationHub")))
9855 (build-system r-build-system)
9857 `(("r-annotationdbi" ,r-annotationdbi)
9858 ("r-biocgenerics" ,r-biocgenerics)
9859 ("r-biocinstaller" ,r-biocinstaller)
9862 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9863 ("r-rsqlite" ,r-rsqlite)
9864 ("r-s4vectors" ,r-s4vectors)
9865 ("r-yaml" ,r-yaml)))
9866 (home-page "https://bioconductor.org/packages/AnnotationHub")
9867 (synopsis "Client to access AnnotationHub resources")
9869 "This package provides a client for the Bioconductor AnnotationHub web
9870 resource. The AnnotationHub web resource provides a central location where
9871 genomic files (e.g. VCF, bed, wig) and other resources from standard
9872 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9873 metadata about each resource, e.g., a textual description, tags, and date of
9874 modification. The client creates and manages a local cache of files retrieved
9875 by the user, helping with quick and reproducible access.")
9876 (license license:artistic2.0)))
9878 (define-public r-fastseg
9885 (uri (bioconductor-uri "fastseg" version))
9888 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9889 (build-system r-build-system)
9891 `(("r-biobase" ,r-biobase)
9892 ("r-biocgenerics" ,r-biocgenerics)
9893 ("r-genomicranges" ,r-genomicranges)
9894 ("r-iranges" ,r-iranges)
9895 ("r-s4vectors" ,r-s4vectors)))
9896 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9897 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9899 "Fastseg implements a very fast and efficient segmentation algorithm.
9900 It can segment data from DNA microarrays and data from next generation
9901 sequencing for example to detect copy number segments. Further it can segment
9902 data from RNA microarrays like tiling arrays to identify transcripts. Most
9903 generally, it can segment data given as a matrix or as a vector. Various data
9904 formats can be used as input to fastseg like expression set objects for
9905 microarrays or GRanges for sequencing data.")
9906 (license license:lgpl2.0+)))
9908 (define-public r-keggrest
9915 (uri (bioconductor-uri "KEGGREST" version))
9918 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9919 (properties `((upstream-name . "KEGGREST")))
9920 (build-system r-build-system)
9922 `(("r-biostrings" ,r-biostrings)
9925 (home-page "https://bioconductor.org/packages/KEGGREST")
9926 (synopsis "Client-side REST access to KEGG")
9928 "This package provides a package that provides a client interface to the
9929 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9930 (license license:artistic2.0)))
9932 (define-public r-gage
9939 (uri (bioconductor-uri "gage" version))
9942 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9943 (build-system r-build-system)
9945 `(("r-annotationdbi" ,r-annotationdbi)
9946 ("r-graph" ,r-graph)
9947 ("r-keggrest" ,r-keggrest)))
9948 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9949 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9951 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9952 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9953 data attributes including sample sizes, experimental designs, assay platforms,
9954 and other types of heterogeneity. The gage package provides functions for
9955 basic GAGE analysis, result processing and presentation. In addition, it
9956 provides demo microarray data and commonly used gene set data based on KEGG
9957 pathways and GO terms. These funtions and data are also useful for gene set
9958 analysis using other methods.")
9959 (license license:gpl2+)))
9961 (define-public r-genomicfiles
9963 (name "r-genomicfiles")
9968 (uri (bioconductor-uri "GenomicFiles" version))
9971 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9972 (properties `((upstream-name . "GenomicFiles")))
9973 (build-system r-build-system)
9975 `(("r-biocgenerics" ,r-biocgenerics)
9976 ("r-biocparallel" ,r-biocparallel)
9977 ("r-genomeinfodb" ,r-genomeinfodb)
9978 ("r-genomicalignments" ,r-genomicalignments)
9979 ("r-genomicranges" ,r-genomicranges)
9980 ("r-iranges" ,r-iranges)
9981 ("r-rsamtools" ,r-rsamtools)
9982 ("r-rtracklayer" ,r-rtracklayer)
9983 ("r-s4vectors" ,r-s4vectors)
9984 ("r-summarizedexperiment" ,r-summarizedexperiment)
9985 ("r-variantannotation" ,r-variantannotation)))
9986 (home-page "https://bioconductor.org/packages/GenomicFiles")
9987 (synopsis "Distributed computing by file or by range")
9989 "This package provides infrastructure for parallel computations
9990 distributed by file or by range. User defined mapper and reducer functions
9991 provide added flexibility for data combination and manipulation.")
9992 (license license:artistic2.0)))
9994 (define-public r-complexheatmap
9996 (name "r-complexheatmap")
10001 (uri (bioconductor-uri "ComplexHeatmap" version))
10004 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
10006 `((upstream-name . "ComplexHeatmap")))
10007 (build-system r-build-system)
10009 `(("r-circlize" ,r-circlize)
10010 ("r-colorspace" ,r-colorspace)
10011 ("r-getoptlong" ,r-getoptlong)
10012 ("r-globaloptions" ,r-globaloptions)
10013 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10015 "https://github.com/jokergoo/ComplexHeatmap")
10016 (synopsis "Making Complex Heatmaps")
10018 "Complex heatmaps are efficient to visualize associations between
10019 different sources of data sets and reveal potential structures. This package
10020 provides a highly flexible way to arrange multiple heatmaps and supports
10021 self-defined annotation graphics.")
10022 (license license:gpl2+)))
10024 (define-public r-dirichletmultinomial
10026 (name "r-dirichletmultinomial")
10031 (uri (bioconductor-uri "DirichletMultinomial" version))
10034 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
10036 `((upstream-name . "DirichletMultinomial")))
10037 (build-system r-build-system)
10041 `(("r-biocgenerics" ,r-biocgenerics)
10042 ("r-iranges" ,r-iranges)
10043 ("r-s4vectors" ,r-s4vectors)))
10044 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10045 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10047 "Dirichlet-multinomial mixture models can be used to describe variability
10048 in microbial metagenomic data. This package is an interface to code
10049 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10051 (license license:lgpl3)))
10053 (define-public r-ensembldb
10055 (name "r-ensembldb")
10060 (uri (bioconductor-uri "ensembldb" version))
10063 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
10064 (build-system r-build-system)
10066 `(("r-annotationdbi" ,r-annotationdbi)
10067 ("r-annotationfilter" ,r-annotationfilter)
10068 ("r-annotationhub" ,r-annotationhub)
10069 ("r-biobase" ,r-biobase)
10070 ("r-biocgenerics" ,r-biocgenerics)
10071 ("r-biostrings" ,r-biostrings)
10074 ("r-genomeinfodb" ,r-genomeinfodb)
10075 ("r-genomicfeatures" ,r-genomicfeatures)
10076 ("r-genomicranges" ,r-genomicranges)
10077 ("r-iranges" ,r-iranges)
10078 ("r-protgenerics" ,r-protgenerics)
10079 ("r-rsamtools" ,r-rsamtools)
10080 ("r-rsqlite" ,r-rsqlite)
10081 ("r-rtracklayer" ,r-rtracklayer)
10082 ("r-s4vectors" ,r-s4vectors)))
10083 (home-page "https://github.com/jotsetung/ensembldb")
10084 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10086 "The package provides functions to create and use transcript-centric
10087 annotation databases/packages. The annotation for the databases are directly
10088 fetched from Ensembl using their Perl API. The functionality and data is
10089 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10090 but, in addition to retrieve all gene/transcript models and annotations from
10091 the database, the @code{ensembldb} package also provides a filter framework
10092 allowing to retrieve annotations for specific entries like genes encoded on a
10093 chromosome region or transcript models of lincRNA genes.")
10094 ;; No version specified
10095 (license license:lgpl3+)))
10097 (define-public r-organismdbi
10099 (name "r-organismdbi")
10104 (uri (bioconductor-uri "OrganismDbi" version))
10107 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
10108 (properties `((upstream-name . "OrganismDbi")))
10109 (build-system r-build-system)
10111 `(("r-annotationdbi" ,r-annotationdbi)
10112 ("r-biobase" ,r-biobase)
10113 ("r-biocgenerics" ,r-biocgenerics)
10114 ("r-biocinstaller" ,r-biocinstaller)
10116 ("r-genomicfeatures" ,r-genomicfeatures)
10117 ("r-genomicranges" ,r-genomicranges)
10118 ("r-graph" ,r-graph)
10119 ("r-iranges" ,r-iranges)
10121 ("r-s4vectors" ,r-s4vectors)))
10122 (home-page "https://bioconductor.org/packages/OrganismDbi")
10123 (synopsis "Software to enable the smooth interfacing of database packages")
10124 (description "The package enables a simple unified interface to several
10125 annotation packages each of which has its own schema by taking advantage of
10126 the fact that each of these packages implements a select methods.")
10127 (license license:artistic2.0)))
10129 (define-public r-biovizbase
10131 (name "r-biovizbase")
10136 (uri (bioconductor-uri "biovizBase" version))
10139 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10140 (properties `((upstream-name . "biovizBase")))
10141 (build-system r-build-system)
10143 `(("r-annotationdbi" ,r-annotationdbi)
10144 ("r-annotationfilter" ,r-annotationfilter)
10145 ("r-biocgenerics" ,r-biocgenerics)
10146 ("r-biostrings" ,r-biostrings)
10147 ("r-dichromat" ,r-dichromat)
10148 ("r-ensembldb" ,r-ensembldb)
10149 ("r-genomeinfodb" ,r-genomeinfodb)
10150 ("r-genomicalignments" ,r-genomicalignments)
10151 ("r-genomicfeatures" ,r-genomicfeatures)
10152 ("r-genomicranges" ,r-genomicranges)
10153 ("r-hmisc" ,r-hmisc)
10154 ("r-iranges" ,r-iranges)
10155 ("r-rcolorbrewer" ,r-rcolorbrewer)
10156 ("r-rsamtools" ,r-rsamtools)
10157 ("r-s4vectors" ,r-s4vectors)
10158 ("r-scales" ,r-scales)
10159 ("r-summarizedexperiment" ,r-summarizedexperiment)
10160 ("r-variantannotation" ,r-variantannotation)))
10161 (home-page "https://bioconductor.org/packages/biovizBase")
10162 (synopsis "Basic graphic utilities for visualization of genomic data")
10164 "The biovizBase package is designed to provide a set of utilities, color
10165 schemes and conventions for genomic data. It serves as the base for various
10166 high-level packages for biological data visualization. This saves development
10167 effort and encourages consistency.")
10168 (license license:artistic2.0)))
10170 (define-public r-ggbio
10177 (uri (bioconductor-uri "ggbio" version))
10180 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10181 (build-system r-build-system)
10183 `(("r-annotationdbi" ,r-annotationdbi)
10184 ("r-annotationfilter" ,r-annotationfilter)
10185 ("r-biobase" ,r-biobase)
10186 ("r-biocgenerics" ,r-biocgenerics)
10187 ("r-biostrings" ,r-biostrings)
10188 ("r-biovizbase" ,r-biovizbase)
10189 ("r-bsgenome" ,r-bsgenome)
10190 ("r-ensembldb" ,r-ensembldb)
10191 ("r-genomeinfodb" ,r-genomeinfodb)
10192 ("r-genomicalignments" ,r-genomicalignments)
10193 ("r-genomicfeatures" ,r-genomicfeatures)
10194 ("r-genomicranges" ,r-genomicranges)
10195 ("r-ggally" ,r-ggally)
10196 ("r-ggplot2" ,r-ggplot2)
10197 ("r-gridextra" ,r-gridextra)
10198 ("r-gtable" ,r-gtable)
10199 ("r-hmisc" ,r-hmisc)
10200 ("r-iranges" ,r-iranges)
10201 ("r-organismdbi" ,r-organismdbi)
10202 ("r-reshape2" ,r-reshape2)
10203 ("r-rsamtools" ,r-rsamtools)
10204 ("r-rtracklayer" ,r-rtracklayer)
10205 ("r-s4vectors" ,r-s4vectors)
10206 ("r-scales" ,r-scales)
10207 ("r-summarizedexperiment" ,r-summarizedexperiment)
10208 ("r-variantannotation" ,r-variantannotation)))
10209 (home-page "http://www.tengfei.name/ggbio/")
10210 (synopsis "Visualization tools for genomic data")
10212 "The ggbio package extends and specializes the grammar of graphics for
10213 biological data. The graphics are designed to answer common scientific
10214 questions, in particular those often asked of high throughput genomics data.
10215 All core Bioconductor data structures are supported, where appropriate. The
10216 package supports detailed views of particular genomic regions, as well as
10217 genome-wide overviews. Supported overviews include ideograms and grand linear
10218 views. High-level plots include sequence fragment length, edge-linked
10219 interval to data view, mismatch pileup, and several splicing summaries.")
10220 (license license:artistic2.0)))
10222 (define-public r-gprofiler
10224 (name "r-gprofiler")
10229 (uri (cran-uri "gProfileR" version))
10232 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10233 (properties `((upstream-name . "gProfileR")))
10234 (build-system r-build-system)
10236 `(("r-plyr" ,r-plyr)
10237 ("r-rcurl" ,r-rcurl)))
10238 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10239 (synopsis "Interface to the g:Profiler toolkit")
10241 "This package provides tools for functional enrichment analysis,
10242 gene identifier conversion and mapping homologous genes across related
10243 organisms via the @code{g:Profiler} toolkit.")
10244 (license license:gpl2+)))
10246 (define-public r-gqtlbase
10248 (name "r-gqtlbase")
10253 (uri (bioconductor-uri "gQTLBase" version))
10256 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10257 (properties `((upstream-name . "gQTLBase")))
10258 (build-system r-build-system)
10260 `(("r-batchjobs" ,r-batchjobs)
10261 ("r-bbmisc" ,r-bbmisc)
10262 ("r-biocgenerics" ,r-biocgenerics)
10264 ("r-doparallel" ,r-doparallel)
10266 ("r-ffbase" ,r-ffbase)
10267 ("r-foreach" ,r-foreach)
10268 ("r-genomicfiles" ,r-genomicfiles)
10269 ("r-genomicranges" ,r-genomicranges)
10270 ("r-rtracklayer" ,r-rtracklayer)
10271 ("r-s4vectors" ,r-s4vectors)
10272 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10273 (home-page "https://bioconductor.org/packages/gQTLBase")
10274 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10276 "The purpose of this package is to simplify the storage and interrogation
10277 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10279 (license license:artistic2.0)))
10281 (define-public r-snpstats
10283 (name "r-snpstats")
10288 (uri (bioconductor-uri "snpStats" version))
10291 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10292 (properties `((upstream-name . "snpStats")))
10293 (build-system r-build-system)
10294 (inputs `(("zlib" ,zlib)))
10296 `(("r-biocgenerics" ,r-biocgenerics)
10297 ("r-matrix" ,r-matrix)
10298 ("r-survival" ,r-survival)
10299 ("r-zlibbioc" ,r-zlibbioc)))
10300 (home-page "https://bioconductor.org/packages/snpStats")
10301 (synopsis "Methods for SNP association studies")
10303 "This package provides classes and statistical methods for large
10304 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10305 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10306 (license license:gpl3)))
10308 (define-public r-homo-sapiens
10310 (name "r-homo-sapiens")
10314 ;; We cannot use bioconductor-uri here because this tarball is
10315 ;; located under "data/annotation/" instead of "bioc/".
10316 (uri (string-append "http://www.bioconductor.org/packages/"
10317 "release/data/annotation/src/contrib/"
10319 version ".tar.gz"))
10322 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10324 `((upstream-name . "Homo.sapiens")))
10325 (build-system r-build-system)
10327 `(("r-genomicfeatures" ,r-genomicfeatures)
10328 ("r-go-db" ,r-go-db)
10329 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10330 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10331 ("r-organismdbi" ,r-organismdbi)
10332 ("r-annotationdbi" ,r-annotationdbi)))
10333 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10334 (synopsis "Annotation package for the Homo.sapiens object")
10336 "This package contains the Homo.sapiens object to access data from
10337 several related annotation packages.")
10338 (license license:artistic2.0)))
10340 (define-public r-erma
10347 (uri (bioconductor-uri "erma" version))
10350 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10351 (build-system r-build-system)
10353 `(("r-annotationdbi" ,r-annotationdbi)
10354 ("r-biobase" ,r-biobase)
10355 ("r-biocgenerics" ,r-biocgenerics)
10356 ("r-foreach" ,r-foreach)
10357 ("r-genomicfiles" ,r-genomicfiles)
10358 ("r-genomicranges" ,r-genomicranges)
10359 ("r-ggplot2" ,r-ggplot2)
10360 ("r-homo-sapiens" ,r-homo-sapiens)
10361 ("r-rtracklayer" ,r-rtracklayer)
10362 ("r-s4vectors" ,r-s4vectors)
10363 ("r-shiny" ,r-shiny)
10364 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10365 (home-page "https://bioconductor.org/packages/erma")
10366 (synopsis "Epigenomic road map adventures")
10368 "The epigenomics road map describes locations of epigenetic marks in DNA
10369 from a variety of cell types. Of interest are locations of histone
10370 modifications, sites of DNA methylation, and regions of accessible chromatin.
10371 This package presents a selection of elements of the road map including
10372 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10373 by Ernst and Kellis.")
10374 (license license:artistic2.0)))
10376 (define-public r-ldblock
10383 (uri (bioconductor-uri "ldblock" version))
10386 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10387 (build-system r-build-system)
10389 `(("r-erma" ,r-erma)
10390 ("r-genomeinfodb" ,r-genomeinfodb)
10391 ("r-genomicfiles" ,r-genomicfiles)
10392 ("r-go-db" ,r-go-db)
10393 ("r-homo-sapiens" ,r-homo-sapiens)
10394 ("r-matrix" ,r-matrix)
10395 ("r-rsamtools" ,r-rsamtools)
10396 ("r-snpstats" ,r-snpstats)
10397 ("r-variantannotation" ,r-variantannotation)))
10398 (home-page "https://bioconductor.org/packages/ldblock")
10399 (synopsis "Data structures for linkage disequilibrium measures in populations")
10401 "This package defines data structures for @dfn{linkage
10402 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10403 handling of existing population-level data for the purpose of flexibly
10404 defining LD blocks.")
10405 (license license:artistic2.0)))
10407 (define-public r-gqtlstats
10409 (name "r-gqtlstats")
10414 (uri (bioconductor-uri "gQTLstats" version))
10417 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10418 (properties `((upstream-name . "gQTLstats")))
10419 (build-system r-build-system)
10421 `(("r-annotationdbi" ,r-annotationdbi)
10422 ("r-batchjobs" ,r-batchjobs)
10423 ("r-bbmisc" ,r-bbmisc)
10424 ("r-beeswarm" ,r-beeswarm)
10425 ("r-biobase" ,r-biobase)
10426 ("r-biocgenerics" ,r-biocgenerics)
10427 ("r-doparallel" ,r-doparallel)
10428 ("r-dplyr" ,r-dplyr)
10430 ("r-ffbase" ,r-ffbase)
10431 ("r-foreach" ,r-foreach)
10432 ("r-genomeinfodb" ,r-genomeinfodb)
10433 ("r-genomicfeatures" ,r-genomicfeatures)
10434 ("r-genomicfiles" ,r-genomicfiles)
10435 ("r-genomicranges" ,r-genomicranges)
10436 ("r-ggbeeswarm" ,r-ggbeeswarm)
10437 ("r-ggplot2" ,r-ggplot2)
10438 ("r-gqtlbase" ,r-gqtlbase)
10439 ("r-hardyweinberg" ,r-hardyweinberg)
10440 ("r-iranges" ,r-iranges)
10441 ("r-ldblock" ,r-ldblock)
10442 ("r-limma" ,r-limma)
10444 ("r-plotly" ,r-plotly)
10445 ("r-reshape2" ,r-reshape2)
10446 ("r-s4vectors" ,r-s4vectors)
10447 ("r-shiny" ,r-shiny)
10448 ("r-snpstats" ,r-snpstats)
10449 ("r-summarizedexperiment" ,r-summarizedexperiment)
10450 ("r-variantannotation" ,r-variantannotation)))
10451 (home-page "https://bioconductor.org/packages/gQTLstats")
10452 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10454 "This package provides tools for the computationally efficient analysis
10455 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10456 The software in this package aims to support refinements and functional
10457 interpretation of members of a collection of association statistics on a
10458 family of feature/genome hypotheses.")
10459 (license license:artistic2.0)))
10461 (define-public r-gviz
10468 (uri (bioconductor-uri "Gviz" version))
10471 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10472 (properties `((upstream-name . "Gviz")))
10473 (build-system r-build-system)
10475 `(("r-annotationdbi" ,r-annotationdbi)
10476 ("r-biobase" ,r-biobase)
10477 ("r-biocgenerics" ,r-biocgenerics)
10478 ("r-biomart" ,r-biomart)
10479 ("r-biostrings" ,r-biostrings)
10480 ("r-biovizbase" ,r-biovizbase)
10481 ("r-bsgenome" ,r-bsgenome)
10482 ("r-digest" ,r-digest)
10483 ("r-genomeinfodb" ,r-genomeinfodb)
10484 ("r-genomicalignments" ,r-genomicalignments)
10485 ("r-genomicfeatures" ,r-genomicfeatures)
10486 ("r-genomicranges" ,r-genomicranges)
10487 ("r-iranges" ,r-iranges)
10488 ("r-lattice" ,r-lattice)
10489 ("r-latticeextra" ,r-latticeextra)
10490 ("r-matrixstats" ,r-matrixstats)
10491 ("r-rcolorbrewer" ,r-rcolorbrewer)
10492 ("r-rsamtools" ,r-rsamtools)
10493 ("r-rtracklayer" ,r-rtracklayer)
10494 ("r-s4vectors" ,r-s4vectors)
10495 ("r-xvector" ,r-xvector)))
10496 (home-page "https://bioconductor.org/packages/Gviz")
10497 (synopsis "Plotting data and annotation information along genomic coordinates")
10499 "Genomic data analyses requires integrated visualization of known genomic
10500 information and new experimental data. Gviz uses the biomaRt and the
10501 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10502 and translates this to e.g. gene/transcript structures in viewports of the
10503 grid graphics package. This results in genomic information plotted together
10505 (license license:artistic2.0)))
10507 (define-public r-gwascat
10514 (uri (bioconductor-uri "gwascat" version))
10517 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10518 (build-system r-build-system)
10520 `(("r-annotationdbi" ,r-annotationdbi)
10521 ("r-annotationhub" ,r-annotationhub)
10522 ("r-biocgenerics" ,r-biocgenerics)
10523 ("r-biostrings" ,r-biostrings)
10524 ("r-genomeinfodb" ,r-genomeinfodb)
10525 ("r-genomicfeatures" ,r-genomicfeatures)
10526 ("r-genomicranges" ,r-genomicranges)
10527 ("r-ggbio" ,r-ggbio)
10528 ("r-ggplot2" ,r-ggplot2)
10529 ("r-gqtlstats" ,r-gqtlstats)
10530 ("r-graph" ,r-graph)
10532 ("r-homo-sapiens" ,r-homo-sapiens)
10533 ("r-iranges" ,r-iranges)
10534 ("r-rsamtools" ,r-rsamtools)
10535 ("r-rtracklayer" ,r-rtracklayer)
10536 ("r-s4vectors" ,r-s4vectors)
10537 ("r-snpstats" ,r-snpstats)
10538 ("r-summarizedexperiment" ,r-summarizedexperiment)
10539 ("r-variantannotation" ,r-variantannotation)))
10540 (home-page "https://bioconductor.org/packages/gwascat")
10541 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10543 "This package provides tools for representing and modeling data in the
10544 EMBL-EBI GWAS catalog.")
10545 (license license:artistic2.0)))
10547 (define-public r-sushi
10553 (uri (bioconductor-uri "Sushi" version))
10556 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10557 (properties `((upstream-name . "Sushi")))
10558 (build-system r-build-system)
10560 `(("r-biomart" ,r-biomart)
10562 (home-page "https://bioconductor.org/packages/Sushi")
10563 (synopsis "Tools for visualizing genomics data")
10565 "This package provides flexible, quantitative, and integrative genomic
10566 visualizations for publication-quality multi-panel figures.")
10567 (license license:gpl2+)))
10569 (define-public r-fithic
10575 (uri (bioconductor-uri "FitHiC" version))
10578 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10579 (properties `((upstream-name . "FitHiC")))
10580 (build-system r-build-system)
10582 `(("r-data-table" ,r-data-table)
10583 ("r-fdrtool" ,r-fdrtool)
10584 ("r-rcpp" ,r-rcpp)))
10585 (home-page "https://bioconductor.org/packages/FitHiC")
10586 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10588 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10589 intra-chromosomal contact maps produced by genome-wide genome architecture
10590 assays such as Hi-C.")
10591 (license license:gpl2+)))
10593 (define-public r-hitc
10599 (uri (bioconductor-uri "HiTC" version))
10602 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10603 (properties `((upstream-name . "HiTC")))
10604 (build-system r-build-system)
10606 `(("r-biostrings" ,r-biostrings)
10607 ("r-genomeinfodb" ,r-genomeinfodb)
10608 ("r-genomicranges" ,r-genomicranges)
10609 ("r-iranges" ,r-iranges)
10610 ("r-matrix" ,r-matrix)
10611 ("r-rcolorbrewer" ,r-rcolorbrewer)
10612 ("r-rtracklayer" ,r-rtracklayer)))
10613 (home-page "https://bioconductor.org/packages/HiTC")
10614 (synopsis "High throughput chromosome conformation capture analysis")
10616 "The HiTC package was developed to explore high-throughput \"C\" data
10617 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10618 quality controls, normalization, visualization, and further analysis are also
10620 (license license:artistic2.0)))
10622 (define-public r-qvalue
10629 (uri (bioconductor-uri "qvalue" version))
10632 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10633 (build-system r-build-system)
10635 `(("r-ggplot2" ,r-ggplot2)
10636 ("r-reshape2" ,r-reshape2)))
10637 (home-page "http://github.com/jdstorey/qvalue")
10638 (synopsis "Q-value estimation for false discovery rate control")
10640 "This package takes a list of p-values resulting from the simultaneous
10641 testing of many hypotheses and estimates their q-values and local @dfn{false
10642 discovery rate} (FDR) values. The q-value of a test measures the proportion
10643 of false positives incurred when that particular test is called significant.
10644 The local FDR measures the posterior probability the null hypothesis is true
10645 given the test's p-value. Various plots are automatically generated, allowing
10646 one to make sensible significance cut-offs. The software can be applied to
10647 problems in genomics, brain imaging, astrophysics, and data mining.")
10648 ;; Any version of the LGPL.
10649 (license license:lgpl3+)))
10651 (define-public r-hdf5array
10653 (name "r-hdf5array")
10658 (uri (bioconductor-uri "HDF5Array" version))
10661 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10662 (properties `((upstream-name . "HDF5Array")))
10663 (build-system r-build-system)
10665 `(("r-biocgenerics" ,r-biocgenerics)
10666 ("r-delayedarray" ,r-delayedarray)
10667 ("r-iranges" ,r-iranges)
10668 ("r-rhdf5" ,r-rhdf5)
10669 ("r-s4vectors" ,r-s4vectors)))
10670 (home-page "https://bioconductor.org/packages/HDF5Array")
10671 (synopsis "HDF5 back end for DelayedArray objects")
10672 (description "This package provides an array-like container for convenient
10673 access and manipulation of HDF5 datasets. It supports delayed operations and
10674 block processing.")
10675 (license license:artistic2.0)))
10677 (define-public r-rhdf5lib
10679 (name "r-rhdf5lib")
10684 (uri (bioconductor-uri "Rhdf5lib" version))
10687 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10688 (properties `((upstream-name . "Rhdf5lib")))
10689 (build-system r-build-system)
10692 (modify-phases %standard-phases
10693 (add-after 'unpack 'do-not-use-bundled-hdf5
10694 (lambda* (#:key inputs #:allow-other-keys)
10695 (for-each delete-file '("configure" "configure.ac"))
10696 ;; Do not make other packages link with the proprietary libsz.
10697 (substitute* "R/zzz.R"
10698 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10699 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10700 (("'%s/libhdf5.a %s/libsz.a'")
10701 "'%s/libhdf5.a %s/libhdf5.a'"))
10702 (with-directory-excursion "src"
10703 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10704 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10706 ;; Remove timestamp and host system information to make
10707 ;; the build reproducible.
10708 (substitute* "hdf5/src/libhdf5.settings.in"
10709 (("Configured on: @CONFIG_DATE@")
10710 "Configured on: Guix")
10711 (("Uname information:.*")
10712 "Uname information: Linux\n")
10713 ;; Remove unnecessary store reference.
10715 "C Compiler: GCC\n"))
10716 (rename-file "Makevars.in" "Makevars")
10717 (substitute* "Makevars"
10718 (("HDF5_CXX_LIB=.*")
10719 (string-append "HDF5_CXX_LIB="
10720 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10722 (string-append "HDF5_LIB="
10723 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10724 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10725 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10726 ;; szip is non-free software
10727 (("cp \\$\\{SZIP_LIB\\}.*") "")
10728 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10729 "PKG_LIBS = ${HDF5_LIB}\n")))
10736 `(("hdf5-source" ,(package-source hdf5))))
10737 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10738 (synopsis "HDF5 library as an R package")
10739 (description "This package provides C and C++ HDF5 libraries for use in R
10741 (license license:artistic2.0)))
10743 (define-public r-beachmat
10745 (name "r-beachmat")
10750 (uri (bioconductor-uri "beachmat" version))
10753 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10754 (build-system r-build-system)
10758 `(("r-delayedarray" ,r-delayedarray)
10759 ("r-hdf5array" ,r-hdf5array)
10761 ("r-rhdf5" ,r-rhdf5)
10762 ("r-rhdf5lib" ,r-rhdf5lib)))
10763 (home-page "https://bioconductor.org/packages/beachmat")
10764 (synopsis "Compiling Bioconductor to handle each matrix type")
10765 (description "This package provides a consistent C++ class interface for a
10766 variety of commonly used matrix types, including sparse and HDF5-backed
10768 (license license:gpl3)))
10770 (define-public r-singlecellexperiment
10772 (name "r-singlecellexperiment")
10777 (uri (bioconductor-uri "SingleCellExperiment" version))
10780 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10782 `((upstream-name . "SingleCellExperiment")))
10783 (build-system r-build-system)
10785 `(("r-biocgenerics" ,r-biocgenerics)
10786 ("r-s4vectors" ,r-s4vectors)
10787 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10788 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10789 (synopsis "S4 classes for single cell data")
10790 (description "This package defines an S4 class for storing data from
10791 single-cell experiments. This includes specialized methods to store and
10792 retrieve spike-in information, dimensionality reduction coordinates and size
10793 factors for each cell, along with the usual metadata for genes and
10795 (license license:gpl3)))
10797 (define-public r-scater
10803 (uri (bioconductor-uri "scater" version))
10806 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10807 (build-system r-build-system)
10809 `(("r-beachmat" ,r-beachmat)
10810 ("r-biobase" ,r-biobase)
10811 ("r-biocgenerics" ,r-biocgenerics)
10812 ("r-biomart" ,r-biomart)
10813 ("r-data-table" ,r-data-table)
10814 ("r-dplyr" ,r-dplyr)
10815 ("r-edger" ,r-edger)
10816 ("r-ggbeeswarm" ,r-ggbeeswarm)
10817 ("r-ggplot2" ,r-ggplot2)
10818 ("r-limma" ,r-limma)
10819 ("r-matrix" ,r-matrix)
10820 ("r-matrixstats" ,r-matrixstats)
10823 ("r-reshape2" ,r-reshape2)
10824 ("r-rhdf5" ,r-rhdf5)
10825 ("r-rhdf5lib" ,r-rhdf5lib)
10826 ("r-rjson" ,r-rjson)
10827 ("r-s4vectors" ,r-s4vectors)
10828 ("r-shiny" ,r-shiny)
10829 ("r-shinydashboard" ,r-shinydashboard)
10830 ("r-singlecellexperiment" ,r-singlecellexperiment)
10831 ("r-summarizedexperiment" ,r-summarizedexperiment)
10832 ("r-tximport" ,r-tximport)
10833 ("r-viridis" ,r-viridis)))
10834 (home-page "https://github.com/davismcc/scater")
10835 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10836 (description "This package provides a collection of tools for doing
10837 various analyses of single-cell RNA-seq gene expression data, with a focus on
10839 (license license:gpl2+)))
10841 (define-public r-scran
10848 (uri (bioconductor-uri "scran" version))
10851 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10852 (build-system r-build-system)
10854 `(("r-beachmat" ,r-beachmat)
10855 ("r-biocgenerics" ,r-biocgenerics)
10856 ("r-biocparallel" ,r-biocparallel)
10858 ("r-dynamictreecut" ,r-dynamictreecut)
10859 ("r-edger" ,r-edger)
10861 ("r-ggplot2" ,r-ggplot2)
10862 ("r-igraph" ,r-igraph)
10863 ("r-limma" ,r-limma)
10864 ("r-matrix" ,r-matrix)
10866 ("r-rhdf5lib" ,r-rhdf5lib)
10867 ("r-s4vectors" ,r-s4vectors)
10868 ("r-scater" ,r-scater)
10869 ("r-shiny" ,r-shiny)
10870 ("r-singlecellexperiment" ,r-singlecellexperiment)
10871 ("r-statmod" ,r-statmod)
10872 ("r-summarizedexperiment" ,r-summarizedexperiment)
10873 ("r-viridis" ,r-viridis)
10875 (home-page "https://bioconductor.org/packages/scran")
10876 (synopsis "Methods for single-cell RNA-Seq data analysis")
10877 (description "This package implements a variety of low-level analyses of
10878 single-cell RNA-seq data. Methods are provided for normalization of
10879 cell-specific biases, assignment of cell cycle phase, and detection of highly
10880 variable and significantly correlated genes.")
10881 (license license:gpl3)))
10883 (define-public r-delayedmatrixstats
10885 (name "r-delayedmatrixstats")
10890 (uri (bioconductor-uri "DelayedMatrixStats" version))
10893 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10895 `((upstream-name . "DelayedMatrixStats")))
10896 (build-system r-build-system)
10898 `(("r-delayedarray" ,r-delayedarray)
10899 ("r-iranges" ,r-iranges)
10900 ("r-matrix" ,r-matrix)
10901 ("r-matrixstats" ,r-matrixstats)
10902 ("r-s4vectors" ,r-s4vectors)))
10903 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10904 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10906 "This package provides a port of the @code{matrixStats} API for use with
10907 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10908 contains high-performing functions operating on rows and columns of
10909 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10910 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10911 are optimized per data type and for subsetted calculations such that both
10912 memory usage and processing time is minimized.")
10913 (license license:expat)))
10915 (define-public r-phangorn
10917 (name "r-phangorn")
10922 (uri (cran-uri "phangorn" version))
10925 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10926 (build-system r-build-system)
10929 ("r-fastmatch" ,r-fastmatch)
10930 ("r-igraph" ,r-igraph)
10931 ("r-magrittr" ,r-magrittr)
10932 ("r-matrix" ,r-matrix)
10933 ("r-quadprog" ,r-quadprog)
10934 ("r-rcpp" ,r-rcpp)))
10935 (home-page "https://github.com/KlausVigo/phangorn")
10936 (synopsis "Phylogenetic analysis in R")
10938 "Phangorn is a package for phylogenetic analysis in R. It supports
10939 estimation of phylogenetic trees and networks using Maximum Likelihood,
10940 Maximum Parsimony, distance methods and Hadamard conjugation.")
10941 (license license:gpl2+)))
10943 (define-public r-dropbead
10944 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10947 (name "r-dropbead")
10948 (version (string-append "0-" revision "." (string-take commit 7)))
10952 (uri (git-reference
10953 (url "https://github.com/rajewsky-lab/dropbead.git")
10955 (file-name (git-file-name name version))
10958 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10959 (build-system r-build-system)
10961 `(("r-ggplot2" ,r-ggplot2)
10962 ("r-rcolorbrewer" ,r-rcolorbrewer)
10963 ("r-gridextra" ,r-gridextra)
10964 ("r-gplots" ,r-gplots)
10965 ("r-plyr" ,r-plyr)))
10966 (home-page "https://github.com/rajewsky-lab/dropbead")
10967 (synopsis "Basic exploration and analysis of Drop-seq data")
10968 (description "This package offers a quick and straight-forward way to
10969 explore and perform basic analysis of single cell sequencing data coming from
10970 droplet sequencing. It has been particularly tailored for Drop-seq.")
10971 (license license:gpl3))))
10973 (define htslib-for-sambamba
10974 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10977 (name "htslib-for-sambamba")
10978 (version (string-append "1.3.1-1." (string-take commit 9)))
10982 (uri (git-reference
10983 (url "https://github.com/lomereiter/htslib.git")
10985 (file-name (string-append "htslib-" version "-checkout"))
10988 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10991 (modify-phases %standard-phases
10992 (add-after 'unpack 'bootstrap
10993 (lambda _ (invoke "autoreconf" "-vif"))))))
10995 `(("autoconf" ,autoconf)
10996 ("automake" ,automake)
10997 ,@(package-native-inputs htslib))))))
10999 (define-public sambamba
11002 (version "0.6.7-10-g223fa20")
11006 (uri (git-reference
11007 (url "https://github.com/lomereiter/sambamba.git")
11008 (commit (string-append "v" version))))
11009 (file-name (string-append name "-" version "-checkout"))
11012 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11013 (build-system gnu-build-system)
11015 `(#:tests? #f ; there is no test target
11016 #:parallel-build? #f ; not supported
11018 (modify-phases %standard-phases
11019 (delete 'configure)
11020 (add-after 'unpack 'fix-ldc-version
11022 (substitute* "gen_ldc_version_info.py"
11023 (("/usr/bin/env.*") (which "python")))
11024 (substitute* "Makefile"
11025 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11027 (add-after 'unpack 'place-biod-and-undead
11028 (lambda* (#:key inputs #:allow-other-keys)
11029 (copy-recursively (assoc-ref inputs "biod") "BioD")
11030 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11032 (add-after 'unpack 'unbundle-prerequisites
11034 (substitute* "Makefile"
11035 (("htslib/libhts.a lz4/lib/liblz4.a")
11037 ((" htslib-static lz4-static") ""))
11040 (lambda* (#:key outputs #:allow-other-keys)
11041 (let* ((out (assoc-ref outputs "out"))
11042 (bin (string-append out "/bin")))
11044 (install-file "build/sambamba" bin)
11049 ("python" ,python2-minimal)
11051 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11054 (uri (git-reference
11055 (url "https://github.com/biod/BioD.git")
11057 (file-name (string-append "biod-"
11058 (string-take commit 9)
11062 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11064 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11067 (uri (git-reference
11068 (url "https://github.com/dlang/undeaD.git")
11070 (file-name (string-append "undead-"
11071 (string-take commit 9)
11075 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11078 ("htslib" ,htslib-for-sambamba)))
11079 (home-page "http://lomereiter.github.io/sambamba")
11080 (synopsis "Tools for working with SAM/BAM data")
11081 (description "Sambamba is a high performance modern robust and
11082 fast tool (and library), written in the D programming language, for
11083 working with SAM and BAM files. Current parallelised functionality is
11084 an important subset of samtools functionality, including view, index,
11085 sort, markdup, and depth.")
11086 (license license:gpl2+)))
11088 (define-public ritornello
11090 (name "ritornello")
11094 (uri (string-append "https://github.com/KlugerLab/"
11095 "Ritornello/archive/v"
11096 version ".tar.gz"))
11097 (file-name (string-append name "-" version ".tar.gz"))
11100 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11101 (build-system gnu-build-system)
11103 `(#:tests? #f ; there are no tests
11105 (modify-phases %standard-phases
11106 (add-after 'unpack 'patch-samtools-references
11107 (lambda* (#:key inputs #:allow-other-keys)
11108 (substitute* '("src/SamStream.h"
11109 "src/BufferedGenomeReader.h")
11110 (("<sam.h>") "<samtools/sam.h>"))
11112 (delete 'configure)
11114 (lambda* (#:key inputs outputs #:allow-other-keys)
11115 (let* ((out (assoc-ref outputs "out"))
11116 (bin (string-append out "/bin/")))
11118 (install-file "bin/Ritornello" bin)
11121 `(("samtools" ,samtools-0.1)
11125 (home-page "https://github.com/KlugerLab/Ritornello")
11126 (synopsis "Control-free peak caller for ChIP-seq data")
11127 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11128 signal processing that can accurately call binding events without the need to
11129 do a pair total DNA input or IgG control sample. It has been tested for use
11130 with narrow binding events such as transcription factor ChIP-seq.")
11131 (license license:gpl3+)))
11133 (define-public trim-galore
11135 (name "trim-galore")
11140 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
11141 "projects/trim_galore/trim_galore_v"
11145 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
11146 (build-system gnu-build-system)
11148 `(#:tests? #f ; no tests
11150 (modify-phases %standard-phases
11151 ;; The archive contains plain files.
11153 (lambda* (#:key source #:allow-other-keys)
11154 (zero? (system* "unzip" source))))
11155 (delete 'configure)
11157 (add-after 'unpack 'hardcode-tool-references
11158 (lambda* (#:key inputs #:allow-other-keys)
11159 (substitute* "trim_galore"
11160 (("\\$path_to_cutadapt = 'cutadapt'")
11161 (string-append "$path_to_cutadapt = '"
11162 (assoc-ref inputs "cutadapt")
11165 (string-append "| "
11166 (assoc-ref inputs "gzip")
11169 (string-append "\""
11170 (assoc-ref inputs "gzip")
11174 (lambda* (#:key outputs #:allow-other-keys)
11175 (let ((bin (string-append (assoc-ref outputs "out")
11178 (install-file "trim_galore" bin)
11183 ("cutadapt" ,cutadapt)))
11185 `(("unzip" ,unzip)))
11186 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11187 (synopsis "Wrapper around Cutadapt and FastQC")
11188 (description "Trim Galore! is a wrapper script to automate quality and
11189 adapter trimming as well as quality control, with some added functionality to
11190 remove biased methylation positions for RRBS sequence files.")
11191 (license license:gpl3+)))
11193 (define-public gess
11199 (uri (string-append "http://compbio.uthscsa.edu/"
11201 "gess-" version ".src.tar.gz"))
11204 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11205 (build-system gnu-build-system)
11207 `(#:tests? #f ; no tests
11209 (modify-phases %standard-phases
11210 (delete 'configure)
11213 (lambda* (#:key inputs outputs #:allow-other-keys)
11214 (let* ((python (assoc-ref inputs "python"))
11215 (out (assoc-ref outputs "out"))
11216 (bin (string-append out "/bin/"))
11217 (target (string-append
11218 out "/lib/python2.7/site-packages/gess/")))
11220 (copy-recursively "." target)
11221 ;; Make GESS.py executable
11222 (chmod (string-append target "GESS.py") #o555)
11223 ;; Add Python shebang to the top and make Matplotlib
11225 (substitute* (string-append target "GESS.py")
11226 (("\"\"\"Description:" line)
11227 (string-append "#!" (which "python") "
11229 matplotlib.use('Agg')
11231 ;; Make sure GESS has all modules in its path
11232 (wrap-program (string-append target "GESS.py")
11233 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11235 (symlink (string-append target "GESS.py")
11236 (string-append bin "GESS.py"))
11239 `(("python" ,python-2)
11240 ("python2-pysam" ,python2-pysam)
11241 ("python2-scipy" ,python2-scipy)
11242 ("python2-numpy" ,python2-numpy)
11243 ("python2-networkx" ,python2-networkx)
11244 ("python2-biopython" ,python2-biopython)))
11245 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11246 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11248 "GESS is an implementation of a novel computational method to detect de
11249 novo exon-skipping events directly from raw RNA-seq data without the prior
11250 knowledge of gene annotation information. GESS stands for the graph-based
11251 exon-skipping scanner detection scheme.")
11252 (license license:bsd-3)))
11254 (define-public phylip
11261 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11262 "download/phylip-" version ".tar.gz"))
11265 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11266 (build-system gnu-build-system)
11268 `(#:tests? #f ; no check target
11269 #:make-flags (list "-f" "Makefile.unx" "install")
11270 #:parallel-build? #f ; not supported
11272 (modify-phases %standard-phases
11273 (add-after 'unpack 'enter-dir
11274 (lambda _ (chdir "src") #t))
11275 (delete 'configure)
11277 (lambda* (#:key inputs outputs #:allow-other-keys)
11278 (let ((target (string-append (assoc-ref outputs "out")
11281 (for-each (lambda (file)
11282 (install-file file target))
11283 (find-files "../exe" ".*")))
11285 (home-page "http://evolution.genetics.washington.edu/phylip/")
11286 (synopsis "Tools for inferring phylogenies")
11287 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11288 programs for inferring phylogenies (evolutionary trees).")
11289 (license license:bsd-2)))
11298 (uri (string-append "https://integrativemodeling.org/"
11299 version "/download/imp-" version ".tar.gz"))
11302 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11303 (build-system cmake-build-system)
11305 `(;; FIXME: Some tests fail because they produce warnings, others fail
11306 ;; because the PYTHONPATH does not include the modeller's directory.
11314 ("python" ,python-2)))
11316 `(("python2-numpy" ,python2-numpy)
11317 ("python2-scipy" ,python2-scipy)
11318 ("python2-pandas" ,python2-pandas)
11319 ("python2-scikit-learn" ,python2-scikit-learn)
11320 ("python2-networkx" ,python2-networkx)))
11321 (home-page "https://integrativemodeling.org")
11322 (synopsis "Integrative modeling platform")
11323 (description "IMP's broad goal is to contribute to a comprehensive
11324 structural characterization of biomolecules ranging in size and complexity
11325 from small peptides to large macromolecular assemblies, by integrating data
11326 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11327 Python toolbox for solving complex modeling problems, and a number of
11328 applications for tackling some common problems in a user-friendly way.")
11329 ;; IMP is largely available under the GNU Lesser GPL; see the file
11330 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11331 ;; available under the GNU GPL (see the file COPYING.GPL).
11332 (license (list license:lgpl2.1+
11335 (define-public tadbit
11341 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11342 "archive/v" version ".tar.gz"))
11343 (file-name (string-append name "-" version ".tar.gz"))
11346 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11347 (build-system python-build-system)
11349 `(;; Tests are included and must be run after installation, but
11350 ;; they are incomplete and thus cannot be run.
11354 (modify-phases %standard-phases
11355 (add-after 'unpack 'fix-problems-with-setup.py
11356 (lambda* (#:key outputs #:allow-other-keys)
11357 ;; setup.py opens these files for writing
11358 (chmod "_pytadbit/_version.py" #o664)
11359 (chmod "README.rst" #o664)
11361 ;; Don't attempt to install the bash completions to
11362 ;; the home directory.
11363 (rename-file "extras/.bash_completion"
11365 (substitute* "setup.py"
11366 (("\\(path.expanduser\\('~'\\)")
11367 (string-append "(\""
11368 (assoc-ref outputs "out")
11369 "/etc/bash_completion.d\""))
11370 (("extras/\\.bash_completion")
11374 ;; TODO: add Chimera for visualization
11377 ("python2-scipy" ,python2-scipy)
11378 ("python2-numpy" ,python2-numpy)
11379 ("python2-matplotlib" ,python2-matplotlib)
11380 ("python2-pysam" ,python2-pysam)))
11381 (home-page "http://3dgenomes.github.io/TADbit/")
11382 (synopsis "Analyze, model, and explore 3C-based data")
11384 "TADbit is a complete Python library to deal with all steps to analyze,
11385 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11386 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11387 correct interaction matrices, identify and compare the so-called
11388 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11389 interaction matrices, and finally, extract structural properties from the
11390 models. TADbit is complemented by TADkit for visualizing 3D models.")
11391 (license license:gpl3+)))
11393 (define-public kentutils
11396 ;; 302.1.0 is out, but the only difference is the inclusion of
11397 ;; pre-built binaries.
11398 (version "302.0.0")
11402 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11403 "archive/v" version ".tar.gz"))
11404 (file-name (string-append name "-" version ".tar.gz"))
11407 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11408 (modules '((guix build utils)
11413 ;; Only the contents of the specified directories are free
11414 ;; for all uses, so we remove the rest. "hg/autoSql" and
11415 ;; "hg/autoXml" are nominally free, but they depend on a
11416 ;; library that is built from the sources in "hg/lib",
11417 ;; which is nonfree.
11418 (let ((free (list "." ".."
11419 "utils" "lib" "inc" "tagStorm"
11420 "parasol" "htslib"))
11421 (directory? (lambda (file)
11422 (eq? 'directory (stat:type (stat file))))))
11423 (for-each (lambda (file)
11424 (and (directory? file)
11425 (delete-file-recursively file)))
11426 (map (cut string-append "src/" <>)
11429 (not (member file free)))))))
11430 ;; Only make the utils target, not the userApps target,
11431 ;; because that requires libraries we won't build.
11432 (substitute* "Makefile"
11433 ((" userApps") " utils"))
11434 ;; Only build libraries that are free.
11435 (substitute* "src/makefile"
11436 (("DIRS =.*") "DIRS =\n")
11437 (("cd jkOwnLib.*") "")
11440 (substitute* "src/utils/makefile"
11441 ;; These tools depend on "jkhgap.a", which is part of the
11442 ;; nonfree "src/hg/lib" directory.
11443 (("raSqlQuery") "")
11444 (("pslLiftSubrangeBlat") "")
11446 ;; Do not build UCSC tools, which may require nonfree
11448 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11450 (build-system gnu-build-system)
11452 `( ;; There is no global test target and the test target for
11453 ;; individual tools depends on input files that are not
11457 (modify-phases %standard-phases
11458 (add-after 'unpack 'fix-paths
11460 (substitute* "Makefile"
11461 (("/bin/echo") (which "echo")))
11463 (add-after 'unpack 'prepare-samtabix
11464 (lambda* (#:key inputs #:allow-other-keys)
11465 (copy-recursively (assoc-ref inputs "samtabix")
11468 (delete 'configure)
11470 (lambda* (#:key outputs #:allow-other-keys)
11471 (let ((bin (string-append (assoc-ref outputs "out")
11473 (copy-recursively "bin" bin))
11479 (uri (git-reference
11480 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11481 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11484 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11490 ("mariadb" ,mariadb)
11491 ("openssl" ,openssl)))
11492 (home-page "http://genome.cse.ucsc.edu/index.html")
11493 (synopsis "Assorted bioinformatics utilities")
11494 (description "This package provides the kentUtils, a selection of
11495 bioinformatics utilities used in combination with the UCSC genome
11497 ;; Only a subset of the sources are released under a non-copyleft
11498 ;; free software license. All other sources are removed in a
11499 ;; snippet. See this bug report for an explanation of how the
11500 ;; license statements apply:
11501 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11502 (license (license:non-copyleft
11503 "http://genome.ucsc.edu/license/"
11504 "The contents of this package are free for all uses."))))
11506 (define-public f-seq
11507 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11511 (version (string-append "1.1-" revision "." (string-take commit 7)))
11514 (uri (git-reference
11515 (url "https://github.com/aboyle/F-seq.git")
11517 (file-name (string-append name "-" version))
11520 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11521 (modules '((guix build utils)))
11522 ;; Remove bundled Java library archives.
11525 (for-each delete-file (find-files "lib" ".*"))
11527 (build-system ant-build-system)
11529 `(#:tests? #f ; no tests included
11531 (modify-phases %standard-phases
11533 (lambda* (#:key inputs outputs #:allow-other-keys)
11534 (let* ((target (assoc-ref outputs "out"))
11535 (doc (string-append target "/share/doc/f-seq/")))
11538 (substitute* "bin/linux/fseq"
11539 (("java") (which "java"))
11540 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11541 (string-append (assoc-ref inputs "java-commons-cli")
11542 "/share/java/commons-cli.jar"))
11544 (string-append "REALDIR=" target "/bin\n")))
11545 (install-file "README.txt" doc)
11546 (install-file "bin/linux/fseq" (string-append target "/bin"))
11547 (install-file "build~/fseq.jar" (string-append target "/lib"))
11548 (copy-recursively "lib" (string-append target "/lib"))
11552 ("java-commons-cli" ,java-commons-cli)))
11553 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11554 (synopsis "Feature density estimator for high-throughput sequence tags")
11556 "F-Seq is a software package that generates a continuous tag sequence
11557 density estimation allowing identification of biologically meaningful sites
11558 such as transcription factor binding sites (ChIP-seq) or regions of open
11559 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11561 (license license:gpl3+))))
11563 (define-public bismark
11570 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11571 "archive/" version ".tar.gz"))
11572 (file-name (string-append name "-" version ".tar.gz"))
11575 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11576 (build-system perl-build-system)
11578 `(#:tests? #f ; there are no tests
11580 (modify-phases %standard-phases
11581 (delete 'configure)
11584 (lambda* (#:key inputs outputs #:allow-other-keys)
11585 (let ((bin (string-append (assoc-ref outputs "out")
11587 (docdir (string-append (assoc-ref outputs "out")
11588 "/share/doc/bismark"))
11589 (docs '("Bismark_User_Guide.pdf"
11590 "RELEASE_NOTES.txt"))
11591 (scripts '("bismark"
11592 "bismark_genome_preparation"
11593 "bismark_methylation_extractor"
11596 "coverage2cytosine"
11597 "deduplicate_bismark"
11598 "bismark_sitrep.tpl"
11600 "bismark2summary")))
11603 (for-each (lambda (file) (install-file file bin))
11605 (for-each (lambda (file) (install-file file docdir))
11607 ;; Fix references to gunzip
11608 (substitute* (map (lambda (file)
11609 (string-append bin "/" file))
11612 (string-append "\"" (assoc-ref inputs "gzip")
11613 "/bin/gunzip -c")))
11617 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11618 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11619 (description "Bismark is a program to map bisulfite treated sequencing
11620 reads to a genome of interest and perform methylation calls in a single step.
11621 The output can be easily imported into a genome viewer, such as SeqMonk, and
11622 enables a researcher to analyse the methylation levels of their samples
11623 straight away. Its main features are:
11626 @item Bisulfite mapping and methylation calling in one single step
11627 @item Supports single-end and paired-end read alignments
11628 @item Supports ungapped and gapped alignments
11629 @item Alignment seed length, number of mismatches etc are adjustable
11630 @item Output discriminates between cytosine methylation in CpG, CHG
11633 (license license:gpl3+)))
11635 (define-public paml
11641 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11642 "paml" version ".tgz"))
11645 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11646 (modules '((guix build utils)))
11647 ;; Remove Windows binaries
11650 (for-each delete-file (find-files "." "\\.exe$"))
11652 (build-system gnu-build-system)
11654 `(#:tests? #f ; there are no tests
11655 #:make-flags '("CC=gcc")
11657 (modify-phases %standard-phases
11658 (replace 'configure
11660 (substitute* "src/BFdriver.c"
11661 (("/bin/bash") (which "bash")))
11665 (lambda* (#:key outputs #:allow-other-keys)
11666 (let ((tools '("baseml" "basemlg" "codeml"
11667 "pamp" "evolver" "yn00" "chi2"))
11668 (bin (string-append (assoc-ref outputs "out") "/bin"))
11669 (docdir (string-append (assoc-ref outputs "out")
11670 "/share/doc/paml")))
11672 (for-each (lambda (file) (install-file file bin)) tools)
11673 (copy-recursively "../doc" docdir)
11675 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11676 (synopsis "Phylogentic analysis by maximum likelihood")
11677 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11678 contains a few programs for model fitting and phylogenetic tree reconstruction
11679 using nucleotide or amino-acid sequence data.")
11681 (license license:gpl3)))
11683 (define-public kallisto
11689 (uri (string-append "https://github.com/pachterlab/"
11690 "kallisto/archive/v" version ".tar.gz"))
11691 (file-name (string-append name "-" version ".tar.gz"))
11694 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11695 (build-system cmake-build-system)
11696 (arguments `(#:tests? #f)) ; no "check" target
11700 (home-page "http://pachterlab.github.io/kallisto/")
11701 (synopsis "Near-optimal RNA-Seq quantification")
11703 "Kallisto is a program for quantifying abundances of transcripts from
11704 RNA-Seq data, or more generally of target sequences using high-throughput
11705 sequencing reads. It is based on the novel idea of pseudoalignment for
11706 rapidly determining the compatibility of reads with targets, without the need
11707 for alignment. Pseudoalignment of reads preserves the key information needed
11708 for quantification, and kallisto is therefore not only fast, but also as
11709 accurate as existing quantification tools.")
11710 (license license:bsd-2)))
11712 (define-public libgff
11718 (uri (string-append
11719 "https://github.com/Kingsford-Group/"
11720 "libgff/archive/v" version ".tar.gz"))
11721 (file-name (string-append name "-" version ".tar.gz"))
11724 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11725 (build-system cmake-build-system)
11726 (arguments `(#:tests? #f)) ; no tests included
11727 (home-page "https://github.com/Kingsford-Group/libgff")
11728 (synopsis "Parser library for reading/writing GFF files")
11729 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11730 code that is used in the Cufflinks codebase. The goal of this library is to
11731 provide this functionality without the necessity of drawing in a heavy-weight
11732 dependency like SeqAn.")
11733 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11735 (define-public libdivsufsort
11737 (name "libdivsufsort")
11741 (uri (git-reference
11742 (url "https://github.com/y-256/libdivsufsort.git")
11744 (file-name (git-file-name name version))
11747 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11748 (build-system cmake-build-system)
11750 '(#:tests? #f ; there are no tests
11752 ;; Needed for rapmap and sailfish.
11753 '("-DBUILD_DIVSUFSORT64=ON")))
11754 (home-page "https://github.com/y-256/libdivsufsort")
11755 (synopsis "Lightweight suffix-sorting library")
11756 (description "libdivsufsort is a software library that implements a
11757 lightweight suffix array construction algorithm. This library provides a
11758 simple and an efficient C API to construct a suffix array and a
11759 Burrows-Wheeler transformed string from a given string over a constant-size
11760 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11761 bytes of memory space, where n is the length of the string.")
11762 (license license:expat)))
11764 (define-public sailfish
11771 (string-append "https://github.com/kingsfordgroup/"
11772 "sailfish/archive/v" version ".tar.gz"))
11773 (file-name (string-append name "-" version ".tar.gz"))
11776 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11777 (modules '((guix build utils)))
11780 ;; Delete bundled headers for eigen3.
11781 (delete-file-recursively "include/eigen3/")
11783 (build-system cmake-build-system)
11785 `(#:configure-flags
11786 (list (string-append "-DBOOST_INCLUDEDIR="
11787 (assoc-ref %build-inputs "boost")
11789 (string-append "-DBOOST_LIBRARYDIR="
11790 (assoc-ref %build-inputs "boost")
11792 (string-append "-DBoost_LIBRARIES="
11793 "-lboost_iostreams "
11794 "-lboost_filesystem "
11799 "-lboost_program_options")
11800 "-DBoost_FOUND=TRUE"
11801 ;; Don't download RapMap---we already have it!
11802 "-DFETCHED_RAPMAP=1")
11803 ;; Tests must be run after installation and the location of the test
11804 ;; data file must be overridden. But the tests fail. It looks like
11805 ;; they are not really meant to be run.
11808 (modify-phases %standard-phases
11809 ;; Boost cannot be found, even though it's right there.
11810 (add-after 'unpack 'do-not-look-for-boost
11811 (lambda* (#:key inputs #:allow-other-keys)
11812 (substitute* "CMakeLists.txt"
11813 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11814 (add-after 'unpack 'do-not-assign-to-macro
11816 (substitute* "include/spdlog/details/format.cc"
11817 (("const unsigned CHAR_WIDTH = 1;") ""))))
11818 (add-after 'unpack 'prepare-rapmap
11819 (lambda* (#:key inputs #:allow-other-keys)
11820 (let ((src "external/install/src/rapmap/")
11821 (include "external/install/include/rapmap/")
11822 (rapmap (assoc-ref inputs "rapmap")))
11823 (mkdir-p "/tmp/rapmap")
11824 (system* "tar" "xf"
11825 (assoc-ref inputs "rapmap")
11827 "--strip-components=1")
11830 (for-each (lambda (file)
11831 (install-file file src))
11832 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11833 (copy-recursively "/tmp/rapmap/include" include))))
11834 (add-after 'unpack 'use-system-libraries
11835 (lambda* (#:key inputs #:allow-other-keys)
11836 (substitute* '("src/SailfishIndexer.cpp"
11837 "src/SailfishUtils.cpp"
11838 "src/SailfishQuantify.cpp"
11839 "src/FASTAParser.cpp"
11841 "include/SailfishUtils.hpp"
11842 "include/SailfishIndex.hpp"
11843 "include/CollapsedEMOptimizer.hpp"
11844 "src/CollapsedEMOptimizer.cpp")
11845 (("#include \"jellyfish/config.h\"") ""))
11846 (substitute* "src/CMakeLists.txt"
11847 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11848 (string-append (assoc-ref inputs "jellyfish")
11849 "/include/jellyfish-" ,(package-version jellyfish)))
11850 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11851 (string-append (assoc-ref inputs "jellyfish")
11852 "/lib/libjellyfish-2.0.a"))
11853 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11854 (string-append (assoc-ref inputs "libdivsufsort")
11855 "/lib/libdivsufsort.so"))
11856 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11857 (string-append (assoc-ref inputs "libdivsufsort")
11858 "/lib/libdivsufsort64.so")))
11859 (substitute* "CMakeLists.txt"
11860 ;; Don't prefer static libs
11861 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11862 (("find_package\\(Jellyfish.*") "")
11863 (("ExternalProject_Add\\(libjellyfish") "message(")
11864 (("ExternalProject_Add\\(libgff") "message(")
11865 (("ExternalProject_Add\\(libsparsehash") "message(")
11866 (("ExternalProject_Add\\(libdivsufsort") "message("))
11868 ;; Ensure that Eigen headers can be found
11869 (setenv "CPLUS_INCLUDE_PATH"
11870 (string-append (getenv "CPLUS_INCLUDE_PATH")
11872 (assoc-ref inputs "eigen")
11873 "/include/eigen3")))))))
11877 ("jemalloc" ,jemalloc)
11878 ("jellyfish" ,jellyfish)
11879 ("sparsehash" ,sparsehash)
11882 (uri (git-reference
11883 (url "https://github.com/COMBINE-lab/RapMap.git")
11884 (commit (string-append "sf-v" version))))
11885 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11888 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11889 (modules '((guix build utils)))
11890 ;; These files are expected to be excluded.
11892 '(begin (delete-file-recursively "include/spdlog")
11893 (for-each delete-file '("include/xxhash.h"
11894 "src/xxhash.c"))))))
11895 ("libdivsufsort" ,libdivsufsort)
11900 `(("pkg-config" ,pkg-config)))
11901 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11902 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11903 (description "Sailfish is a tool for genomic transcript quantification
11904 from RNA-seq data. It requires a set of target transcripts (either from a
11905 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11906 fasta file containing your reference transcripts and a (set of) fasta/fastq
11907 file(s) containing your reads.")
11908 (license license:gpl3+)))
11910 (define libstadenio-for-salmon
11912 (name "libstadenio")
11916 (uri (git-reference
11917 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11918 (commit (string-append "v" version))))
11919 (file-name (string-append name "-" version "-checkout"))
11922 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11923 (build-system gnu-build-system)
11924 (arguments '(#:parallel-tests? #f)) ; not supported
11928 `(("perl" ,perl))) ; for tests
11929 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11930 (synopsis "General purpose trace and experiment file library")
11931 (description "This package provides a library of file reading and writing
11932 code to provide a general purpose Trace file (and Experiment File) reading
11935 The following file formats are supported:
11938 @item SCF trace files
11939 @item ABI trace files
11940 @item ALF trace files
11941 @item ZTR trace files
11942 @item SFF trace archives
11943 @item SRF trace archives
11944 @item Experiment files
11945 @item Plain text files
11946 @item SAM/BAM sequence files
11947 @item CRAM sequence files
11949 (license license:bsd-3)))
11951 (define spdlog-for-salmon
11957 (uri (git-reference
11958 (url "https://github.com/COMBINE-lab/spdlog.git")
11959 (commit (string-append "v" version))))
11960 (file-name (string-append name "-" version "-checkout"))
11963 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11964 (build-system cmake-build-system)
11965 (home-page "https://github.com/COMBINE-lab/spdlog")
11966 (synopsis "Very fast C++ logging library")
11967 (description "Spdlog is a very fast header-only C++ logging library with
11968 performance as its primary goal.")
11969 (license license:expat)))
11971 ;; This is a modified variant of bwa for use with Salmon. It installs a
11972 ;; library to avoid having to build this as part of Salmon.
11973 (define bwa-for-salmon
11974 (package (inherit bwa)
11976 (version "0.7.12.5")
11979 (uri (git-reference
11980 (url "https://github.com/COMBINE-lab/bwa.git")
11981 (commit (string-append "v" version))))
11982 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11985 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11986 (build-system gnu-build-system)
11988 '(#:tests? #f ;no "check" target
11990 (modify-phases %standard-phases
11992 (lambda* (#:key outputs #:allow-other-keys)
11993 (let* ((out (assoc-ref outputs "out"))
11994 (bin (string-append out "/bin"))
11995 (lib (string-append out "/lib"))
11996 (doc (string-append out "/share/doc/bwa"))
11997 (man (string-append out "/share/man/man1"))
11998 (inc (string-append out "/include/bwa")))
11999 (install-file "bwa" bin)
12000 (install-file "README.md" doc)
12001 (install-file "bwa.1" man)
12002 (install-file "libbwa.a" lib)
12005 (for-each (lambda (file)
12006 (install-file file inc))
12007 (find-files "." "\\.h$")))
12009 ;; no "configure" script
12010 (delete 'configure))))))
12012 (define-public salmon
12018 (uri (git-reference
12019 (url "https://github.com/COMBINE-lab/salmon.git")
12020 (commit (string-append "v" version))))
12021 (file-name (string-append name "-" version "-checkout"))
12024 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12025 (modules '((guix build utils)))
12028 ;; Delete bundled headers for eigen3.
12029 (delete-file-recursively "include/eigen3/")
12031 (build-system cmake-build-system)
12033 `(#:configure-flags
12034 (list (string-append "-DBOOST_INCLUDEDIR="
12035 (assoc-ref %build-inputs "boost")
12037 (string-append "-DBOOST_LIBRARYDIR="
12038 (assoc-ref %build-inputs "boost")
12040 (string-append "-DBoost_LIBRARIES="
12041 "-lboost_iostreams "
12042 "-lboost_filesystem "
12047 "-lboost_program_options")
12048 "-DBoost_FOUND=TRUE"
12049 "-DTBB_LIBRARIES=tbb tbbmalloc"
12050 ;; Don't download RapMap---we already have it!
12051 "-DFETCHED_RAPMAP=1")
12053 (modify-phases %standard-phases
12054 ;; Boost cannot be found, even though it's right there.
12055 (add-after 'unpack 'do-not-look-for-boost
12056 (lambda* (#:key inputs #:allow-other-keys)
12057 (substitute* "CMakeLists.txt"
12058 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12059 (add-after 'unpack 'do-not-phone-home
12061 (substitute* "src/Salmon.cpp"
12062 (("getVersionMessage\\(\\)") "\"\""))))
12063 (add-after 'unpack 'prepare-rapmap
12064 (lambda* (#:key inputs #:allow-other-keys)
12065 (let ((src "external/install/src/rapmap/")
12066 (include "external/install/include/rapmap/")
12067 (rapmap (assoc-ref inputs "rapmap")))
12070 (for-each (lambda (file)
12071 (install-file file src))
12072 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12073 (copy-recursively (string-append rapmap "/include") include)
12074 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12075 "external/install/include/rapmap/FastxParser.hpp"
12076 "external/install/include/rapmap/concurrentqueue.h"
12077 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12078 "external/install/src/rapmap/FastxParser.cpp"
12079 "external/install/src/rapmap/xxhash.c")))))
12080 (add-after 'unpack 'use-system-libraries
12081 (lambda* (#:key inputs #:allow-other-keys)
12082 (substitute* "src/CMakeLists.txt"
12083 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12084 (string-append (assoc-ref inputs "jellyfish")
12085 "/include/jellyfish-" ,(package-version jellyfish)))
12086 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12087 (string-append (assoc-ref inputs "jellyfish")
12088 "/lib/libjellyfish-2.0.a"))
12089 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12090 (string-append (assoc-ref inputs "libdivsufsort")
12091 "/lib/libdivsufsort.so"))
12092 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12093 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12094 "/lib/libstaden-read.a"))
12095 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12096 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12097 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12098 (string-append (assoc-ref inputs "libdivsufsort")
12099 "/lib/libdivsufsort64.so")))
12100 (substitute* "CMakeLists.txt"
12101 ;; Don't prefer static libs
12102 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12103 (("set\\(TBB_LIBRARIES") "message(")
12104 (("find_package\\(Jellyfish.*") "")
12105 (("ExternalProject_Add\\(libcereal") "message(")
12106 (("ExternalProject_Add\\(libbwa") "message(")
12107 (("ExternalProject_Add\\(libjellyfish") "message(")
12108 (("ExternalProject_Add\\(libgff") "message(")
12109 (("ExternalProject_Add\\(libtbb") "message(")
12110 (("ExternalProject_Add\\(libspdlog") "message(")
12111 (("ExternalProject_Add\\(libdivsufsort") "message(")
12112 (("ExternalProject_Add\\(libstadenio") "message(")
12113 (("ExternalProject_Add_Step\\(") "message("))
12115 ;; Ensure that all headers can be found
12116 (setenv "CPLUS_INCLUDE_PATH"
12117 (string-append (getenv "CPLUS_INCLUDE_PATH")
12119 (assoc-ref inputs "bwa")
12122 (assoc-ref inputs "eigen")
12123 "/include/eigen3"))
12125 (string-append (assoc-ref inputs "bwa")
12128 (assoc-ref inputs "eigen")
12129 "/include/eigen3"))
12131 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12132 ;; run. It only exists after the install phase.
12133 (add-after 'unpack 'fix-tests
12135 (substitute* "src/CMakeLists.txt"
12136 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12137 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12141 ("bwa" ,bwa-for-salmon)
12147 (uri (git-reference
12148 (url "https://github.com/COMBINE-lab/RapMap.git")
12149 (commit (string-append "salmon-v" version))))
12150 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12153 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12154 ("jemalloc" ,jemalloc)
12155 ("jellyfish" ,jellyfish)
12158 ("libdivsufsort" ,libdivsufsort)
12159 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12160 ("spdlog-for-salmon" ,spdlog-for-salmon)
12163 (home-page "https://github.com/COMBINE-lab/salmon")
12164 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12165 (description "Salmon is a program to produce highly-accurate,
12166 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12167 its accuracy and speed via a number of different innovations, including the
12168 use of lightweight alignments (accurate but fast-to-compute proxies for
12169 traditional read alignments) and massively-parallel stochastic collapsed
12170 variational inference.")
12171 (license license:gpl3+)))
12173 (define-public python-loompy
12175 (name "python-loompy")
12180 (uri (pypi-uri "loompy" version))
12183 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12184 (build-system python-build-system)
12185 ;; There are no tests
12186 (arguments '(#:tests? #f))
12188 `(("python-h5py" ,python-h5py)
12189 ("python-numpy" ,python-numpy)
12190 ("python-scipy" ,python-scipy)
12191 ("python-typing" ,python-typing)))
12192 (home-page "https://github.com/linnarsson-lab/loompy")
12193 (synopsis "Work with .loom files for single-cell RNA-seq data")
12194 (description "The loom file format is an efficient format for very large
12195 omics datasets, consisting of a main matrix, optional additional layers, a
12196 variable number of row and column annotations. Loom also supports sparse
12197 graphs. This library makes it easy to work with @file{.loom} files for
12198 single-cell RNA-seq data.")
12199 (license license:bsd-3)))
12201 ;; We cannot use the latest commit because it requires Java 9.
12202 (define-public java-forester
12203 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12206 (name "java-forester")
12207 (version (string-append "0-" revision "." (string-take commit 7)))
12210 (uri (git-reference
12211 (url "https://github.com/cmzmasek/forester.git")
12213 (file-name (string-append name "-" version "-checkout"))
12216 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12217 (modules '((guix build utils)))
12220 ;; Delete bundled jars and pre-built classes
12221 (delete-file-recursively "forester/java/resources")
12222 (delete-file-recursively "forester/java/classes")
12223 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12224 ;; Delete bundled applications
12225 (delete-file-recursively "forester_applications")
12227 (build-system ant-build-system)
12229 `(#:tests? #f ; there are none
12231 #:modules ((guix build ant-build-system)
12233 (guix build java-utils)
12237 (modify-phases %standard-phases
12238 (add-after 'unpack 'chdir
12239 (lambda _ (chdir "forester/java") #t))
12240 (add-after 'chdir 'fix-dependencies
12242 (chmod "build.xml" #o664)
12243 (call-with-output-file "build.xml.new"
12247 (with-input-from-file "build.xml"
12248 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12249 `(;; Remove all unjar tags to avoid repacking classes.
12250 (unjar . ,(lambda _ '()))
12251 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12252 (*text* . ,(lambda (_ txt) txt))))
12254 (rename-file "build.xml.new" "build.xml")
12256 ;; FIXME: itext is difficult to package as it depends on a few
12257 ;; unpackaged libraries.
12258 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12260 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12261 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12262 (("pdf_written_to = PdfExporter.*")
12263 "throw new IOException(\"PDF export is not available.\");"))
12265 ;; There is no install target
12266 (replace 'install (install-jars ".")))))
12268 `(("java-commons-codec" ,java-commons-codec)
12269 ("java-openchart2" ,java-openchart2)))
12270 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12271 (synopsis "Phylogenomics libraries for Java")
12272 (description "Forester is a collection of Java libraries for
12273 phylogenomics and evolutionary biology research. It includes support for
12274 reading, writing, and exporting phylogenetic trees.")
12275 (license license:lgpl2.1+))))
12277 (define-public java-forester-1.005
12279 (name "java-forester")
12283 (uri (string-append "http://search.maven.org/remotecontent?"
12284 "filepath=org/biojava/thirdparty/forester/"
12285 version "/forester-" version "-sources.jar"))
12286 (file-name (string-append name "-" version ".jar"))
12289 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12290 (build-system ant-build-system)
12292 `(#:tests? #f ; there are none
12294 #:modules ((guix build ant-build-system)
12296 (guix build java-utils)
12300 (modify-phases %standard-phases
12301 (add-after 'unpack 'fix-dependencies
12302 (lambda* (#:key inputs #:allow-other-keys)
12303 (call-with-output-file "build.xml"
12307 (with-input-from-file "src/build.xml"
12308 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12309 `(;; Remove all unjar tags to avoid repacking classes.
12310 (unjar . ,(lambda _ '()))
12311 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12312 (*text* . ,(lambda (_ txt) txt))))
12314 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12315 "synth_look_and_feel_1.xml")
12316 (copy-file (assoc-ref inputs "phyloxml.xsd")
12318 (substitute* "build.xml"
12319 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12320 "synth_look_and_feel_1.xml")
12321 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12324 ;; FIXME: itext is difficult to package as it depends on a few
12325 ;; unpackaged libraries.
12326 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12328 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12329 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12330 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12331 (("pdf_written_to = PdfExporter.*")
12332 "throw new IOException(\"PDF export is not available.\"); /*")
12333 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12334 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12336 (add-after 'unpack 'delete-pre-built-classes
12337 (lambda _ (delete-file-recursively "src/classes") #t))
12338 ;; There is no install target
12339 (replace 'install (install-jars ".")))))
12341 `(("java-commons-codec" ,java-commons-codec)
12342 ("java-openchart2" ,java-openchart2)))
12343 ;; The source archive does not contain the resources.
12348 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12349 "b61cc2dcede0bede317db362472333115756b8c6/"
12350 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12351 (file-name (string-append name "-phyloxml-" version ".xsd"))
12354 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12355 ("synth_look_and_feel_1.xml"
12358 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12359 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12360 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12361 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12364 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12365 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12366 (synopsis "Phylogenomics libraries for Java")
12367 (description "Forester is a collection of Java libraries for
12368 phylogenomics and evolutionary biology research. It includes support for
12369 reading, writing, and exporting phylogenetic trees.")
12370 (license license:lgpl2.1+)))
12372 (define-public java-biojava-core
12374 (name "java-biojava-core")
12378 (uri (git-reference
12379 (url "https://github.com/biojava/biojava")
12380 (commit (string-append "biojava-" version))))
12381 (file-name (string-append name "-" version "-checkout"))
12384 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12385 (build-system ant-build-system)
12388 #:jar-name "biojava-core.jar"
12389 #:source-dir "biojava-core/src/main/java/"
12390 #:test-dir "biojava-core/src/test"
12391 ;; These tests seem to require internet access.
12392 #:test-exclude (list "**/SearchIOTest.java"
12393 "**/BlastXMLParserTest.java"
12394 "**/GenbankCookbookTest.java"
12395 "**/GenbankProxySequenceReaderTest.java")
12397 (modify-phases %standard-phases
12398 (add-before 'build 'copy-resources
12400 (copy-recursively "biojava-core/src/main/resources"
12403 (add-before 'check 'copy-test-resources
12405 (copy-recursively "biojava-core/src/test/resources"
12406 "build/test-classes")
12409 `(("java-log4j-api" ,java-log4j-api)
12410 ("java-log4j-core" ,java-log4j-core)
12411 ("java-slf4j-api" ,java-slf4j-api)
12412 ("java-slf4j-simple" ,java-slf4j-simple)))
12414 `(("java-junit" ,java-junit)
12415 ("java-hamcrest-core" ,java-hamcrest-core)))
12416 (home-page "http://biojava.org")
12417 (synopsis "Core libraries of Java framework for processing biological data")
12418 (description "BioJava is a project dedicated to providing a Java framework
12419 for processing biological data. It provides analytical and statistical
12420 routines, parsers for common file formats, reference implementations of
12421 popular algorithms, and allows the manipulation of sequences and 3D
12422 structures. The goal of the biojava project is to facilitate rapid
12423 application development for bioinformatics.
12425 This package provides the core libraries.")
12426 (license license:lgpl2.1+)))
12428 (define-public java-biojava-phylo
12429 (package (inherit java-biojava-core)
12430 (name "java-biojava-phylo")
12431 (build-system ant-build-system)
12434 #:jar-name "biojava-phylo.jar"
12435 #:source-dir "biojava-phylo/src/main/java/"
12436 #:test-dir "biojava-phylo/src/test"
12438 (modify-phases %standard-phases
12439 (add-before 'build 'copy-resources
12441 (copy-recursively "biojava-phylo/src/main/resources"
12444 (add-before 'check 'copy-test-resources
12446 (copy-recursively "biojava-phylo/src/test/resources"
12447 "build/test-classes")
12450 `(("java-log4j-api" ,java-log4j-api)
12451 ("java-log4j-core" ,java-log4j-core)
12452 ("java-slf4j-api" ,java-slf4j-api)
12453 ("java-slf4j-simple" ,java-slf4j-simple)
12454 ("java-biojava-core" ,java-biojava-core)
12455 ("java-forester" ,java-forester)))
12457 `(("java-junit" ,java-junit)
12458 ("java-hamcrest-core" ,java-hamcrest-core)))
12459 (home-page "http://biojava.org")
12460 (synopsis "Biojava interface to the forester phylogenomics library")
12461 (description "The phylo module provides a biojava interface layer to the
12462 forester phylogenomics library for constructing phylogenetic trees.")))
12464 (define-public java-biojava-alignment
12465 (package (inherit java-biojava-core)
12466 (name "java-biojava-alignment")
12467 (build-system ant-build-system)
12470 #:jar-name "biojava-alignment.jar"
12471 #:source-dir "biojava-alignment/src/main/java/"
12472 #:test-dir "biojava-alignment/src/test"
12474 (modify-phases %standard-phases
12475 (add-before 'build 'copy-resources
12477 (copy-recursively "biojava-alignment/src/main/resources"
12480 (add-before 'check 'copy-test-resources
12482 (copy-recursively "biojava-alignment/src/test/resources"
12483 "build/test-classes")
12486 `(("java-log4j-api" ,java-log4j-api)
12487 ("java-log4j-core" ,java-log4j-core)
12488 ("java-slf4j-api" ,java-slf4j-api)
12489 ("java-slf4j-simple" ,java-slf4j-simple)
12490 ("java-biojava-core" ,java-biojava-core)
12491 ("java-biojava-phylo" ,java-biojava-phylo)
12492 ("java-forester" ,java-forester)))
12494 `(("java-junit" ,java-junit)
12495 ("java-hamcrest-core" ,java-hamcrest-core)))
12496 (home-page "http://biojava.org")
12497 (synopsis "Biojava API for genetic sequence alignment")
12498 (description "The alignment module of BioJava provides an API that
12502 @item implementations of dynamic programming algorithms for sequence
12504 @item reading and writing of popular alignment file formats;
12505 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12508 (define-public java-biojava-core-4.0
12509 (package (inherit java-biojava-core)
12510 (name "java-biojava-core")
12514 (uri (git-reference
12515 (url "https://github.com/biojava/biojava")
12516 (commit (string-append "biojava-" version))))
12517 (file-name (string-append name "-" version "-checkout"))
12520 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12522 (define-public java-biojava-phylo-4.0
12523 (package (inherit java-biojava-core-4.0)
12524 (name "java-biojava-phylo")
12525 (build-system ant-build-system)
12528 #:jar-name "biojava-phylo.jar"
12529 #:source-dir "biojava-phylo/src/main/java/"
12530 #:test-dir "biojava-phylo/src/test"
12532 (modify-phases %standard-phases
12533 (add-before 'build 'copy-resources
12535 (copy-recursively "biojava-phylo/src/main/resources"
12538 (add-before 'check 'copy-test-resources
12540 (copy-recursively "biojava-phylo/src/test/resources"
12541 "build/test-classes")
12544 `(("java-log4j-api" ,java-log4j-api)
12545 ("java-log4j-core" ,java-log4j-core)
12546 ("java-slf4j-api" ,java-slf4j-api)
12547 ("java-slf4j-simple" ,java-slf4j-simple)
12548 ("java-biojava-core" ,java-biojava-core-4.0)
12549 ("java-forester" ,java-forester-1.005)))
12551 `(("java-junit" ,java-junit)
12552 ("java-hamcrest-core" ,java-hamcrest-core)))
12553 (home-page "http://biojava.org")
12554 (synopsis "Biojava interface to the forester phylogenomics library")
12555 (description "The phylo module provides a biojava interface layer to the
12556 forester phylogenomics library for constructing phylogenetic trees.")))
12558 (define-public java-biojava-alignment-4.0
12559 (package (inherit java-biojava-core-4.0)
12560 (name "java-biojava-alignment")
12561 (build-system ant-build-system)
12564 #:jar-name "biojava-alignment.jar"
12565 #:source-dir "biojava-alignment/src/main/java/"
12566 #:test-dir "biojava-alignment/src/test"
12568 (modify-phases %standard-phases
12569 (add-before 'build 'copy-resources
12571 (copy-recursively "biojava-alignment/src/main/resources"
12574 (add-before 'check 'copy-test-resources
12576 (copy-recursively "biojava-alignment/src/test/resources"
12577 "build/test-classes")
12580 `(("java-log4j-api" ,java-log4j-api)
12581 ("java-log4j-core" ,java-log4j-core)
12582 ("java-slf4j-api" ,java-slf4j-api)
12583 ("java-slf4j-simple" ,java-slf4j-simple)
12584 ("java-biojava-core" ,java-biojava-core-4.0)
12585 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12586 ("java-forester" ,java-forester-1.005)))
12588 `(("java-junit" ,java-junit)
12589 ("java-hamcrest-core" ,java-hamcrest-core)))
12590 (home-page "http://biojava.org")
12591 (synopsis "Biojava API for genetic sequence alignment")
12592 (description "The alignment module of BioJava provides an API that
12596 @item implementations of dynamic programming algorithms for sequence
12598 @item reading and writing of popular alignment file formats;
12599 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12602 (define-public dropseq-tools
12604 (name "dropseq-tools")
12609 (uri "http://mccarrolllab.com/download/1276/")
12610 (file-name (string-append "dropseq-tools-" version ".zip"))
12613 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12614 ;; Delete bundled libraries
12615 (modules '((guix build utils)))
12618 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12619 (delete-file-recursively "3rdParty")))))
12620 (build-system ant-build-system)
12622 `(#:tests? #f ; test data are not included
12623 #:test-target "test"
12624 #:build-target "all"
12625 #:source-dir "public/src/"
12628 (list (string-append "-Dpicard.executable.dir="
12629 (assoc-ref %build-inputs "java-picard")
12631 #:modules ((ice-9 match)
12634 (guix build java-utils)
12635 (guix build ant-build-system))
12637 (modify-phases %standard-phases
12638 ;; All dependencies must be linked to "lib", because that's where
12639 ;; they will be searched for when the Class-Path property of the
12640 ;; manifest is computed.
12641 (add-after 'unpack 'record-references
12642 (lambda* (#:key inputs #:allow-other-keys)
12643 (mkdir-p "jar/lib")
12644 (let ((dirs (filter-map (match-lambda
12646 (if (and (string-prefix? "java-" name)
12647 (not (string=? name "java-testng")))
12650 (for-each (lambda (jar)
12651 (symlink jar (string-append "jar/lib/" (basename jar))))
12652 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12655 ;; There is no installation target
12657 (lambda* (#:key inputs outputs #:allow-other-keys)
12658 (let* ((out (assoc-ref outputs "out"))
12659 (bin (string-append out "/bin"))
12660 (share (string-append out "/share/java/"))
12661 (lib (string-append share "/lib/"))
12662 (scripts (list "BAMTagHistogram"
12663 "BAMTagofTagCounts"
12664 "BaseDistributionAtReadPosition"
12665 "CollapseBarcodesInPlace"
12666 "CollapseTagWithContext"
12668 "CreateIntervalsFiles"
12669 "DetectBeadSynthesisErrors"
12670 "DigitalExpression"
12671 "Drop-seq_alignment.sh"
12674 "GatherGeneGCLength"
12675 "GatherMolecularBarcodeDistributionByGene"
12676 "GatherReadQualityMetrics"
12679 "SelectCellsByNumTranscripts"
12680 "SingleCellRnaSeqMetricsCollector"
12681 "TagBamWithReadSequenceExtended"
12682 "TagReadWithGeneExon"
12683 "TagReadWithInterval"
12684 "TrimStartingSequence"
12685 "ValidateReference")))
12686 (for-each mkdir-p (list bin share lib))
12687 (install-file "dist/dropseq.jar" share)
12688 (for-each (lambda (script)
12689 (chmod script #o555)
12690 (install-file script bin))
12692 (substitute* (map (lambda (script)
12693 (string-append bin "/" script))
12695 (("^java") (which "java"))
12696 (("jar_deploy_dir=.*")
12697 (string-append "jar_deploy_dir=" share "\n"))))
12699 ;; FIXME: We do this after stripping jars because we don't want it to
12700 ;; copy all these jars and strip them. We only want to install
12701 ;; links. Arguably, this is a problem with the ant-build-system.
12702 (add-after 'strip-jar-timestamps 'install-links
12703 (lambda* (#:key outputs #:allow-other-keys)
12704 (let* ((out (assoc-ref outputs "out"))
12705 (share (string-append out "/share/java/"))
12706 (lib (string-append share "/lib/")))
12707 (for-each (lambda (jar)
12708 (symlink (readlink jar)
12709 (string-append lib (basename jar))))
12710 (find-files "jar/lib" "\\.jar$")))
12713 `(("jdk" ,icedtea-8)
12714 ("java-picard" ,java-picard-2.10.3)
12715 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12716 ("java-commons-math3" ,java-commons-math3)
12717 ("java-commons-jexl2" ,java-commons-jexl-2)
12718 ("java-commons-collections4" ,java-commons-collections4)
12719 ("java-commons-lang2" ,java-commons-lang)
12720 ("java-commons-io" ,java-commons-io)
12721 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12722 ("java-guava" ,java-guava)
12723 ("java-la4j" ,java-la4j)
12724 ("java-biojava-core" ,java-biojava-core-4.0)
12725 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12726 ("java-jdistlib" ,java-jdistlib)
12727 ("java-simple-xml" ,java-simple-xml)
12728 ("java-snakeyaml" ,java-snakeyaml)))
12731 ("java-testng" ,java-testng)))
12732 (home-page "http://mccarrolllab.com/dropseq/")
12733 (synopsis "Tools for Drop-seq analyses")
12734 (description "Drop-seq is a technology to enable biologists to
12735 analyze RNA expression genome-wide in thousands of individual cells at
12736 once. This package provides tools to perform Drop-seq analyses.")
12737 (license license:expat)))
12739 (define-public pigx-rnaseq
12741 (name "pigx-rnaseq")
12745 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12746 "releases/download/v" version
12747 "/pigx_rnaseq-" version ".tar.gz"))
12750 "0pz080k4ajlc4rlznkn3najy2a6874gb56rf9g4ag9wqz31q174j"))))
12751 (build-system gnu-build-system)
12753 `(#:parallel-tests? #f ; not supported
12755 (modify-phases %standard-phases
12756 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12757 (add-after 'unpack 'disable-resource-intensive-test
12759 (substitute* "Makefile.in"
12760 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12761 (("^ test.sh") ""))
12763 (add-after 'install 'wrap-executable
12764 ;; Make sure the executable finds all R modules.
12765 (lambda* (#:key inputs outputs #:allow-other-keys)
12766 (let ((out (assoc-ref outputs "out")))
12767 (wrap-program (string-append out "/bin/pigx-rnaseq")
12768 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12769 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12773 ("snakemake" ,snakemake)
12775 ("multiqc" ,multiqc)
12777 ("trim-galore" ,trim-galore)
12779 ("samtools" ,samtools)
12780 ("bedtools" ,bedtools)
12781 ("r-minimal" ,r-minimal)
12782 ("r-rmarkdown" ,r-rmarkdown)
12783 ("r-ggplot2" ,r-ggplot2)
12784 ("r-ggrepel" ,r-ggrepel)
12785 ("r-gprofiler" ,r-gprofiler)
12786 ("r-deseq2" ,r-deseq2)
12788 ("r-knitr" ,r-knitr)
12789 ("r-pheatmap" ,r-pheatmap)
12790 ("r-corrplot" ,r-corrplot)
12791 ("r-reshape2" ,r-reshape2)
12792 ("r-plotly" ,r-plotly)
12793 ("r-scales" ,r-scales)
12794 ("r-summarizedexperiment" ,r-summarizedexperiment)
12795 ("r-crosstalk" ,r-crosstalk)
12796 ("r-tximport" ,r-tximport)
12797 ("r-rtracklayer" ,r-rtracklayer)
12798 ("r-rjson" ,r-rjson)
12800 ("ghc-pandoc" ,ghc-pandoc-1)
12801 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12802 ("python-wrapper" ,python-wrapper)
12803 ("python-pyyaml" ,python-pyyaml)))
12804 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12805 (synopsis "Analysis pipeline for RNA sequencing experiments")
12806 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12807 reporting for RNA sequencing experiments. It is easy to use and produces high
12808 quality reports. The inputs are reads files from the sequencing experiment,
12809 and a configuration file which describes the experiment. In addition to
12810 quality control of the experiment, the pipeline produces a differential
12811 expression report comparing samples in an easily configurable manner.")
12812 (license license:gpl3+)))
12814 (define-public pigx-chipseq
12816 (name "pigx-chipseq")
12820 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12821 "releases/download/v" version
12822 "/pigx_chipseq-" version ".tar.gz"))
12825 "13w99bkr0w4j28ms0yzpl1x6fkpdqay0vh495q3x20bcilsjwnf1"))))
12826 (build-system gnu-build-system)
12828 `(#:tests? #f ; parts of the tests rely on access to the network
12830 (modify-phases %standard-phases
12831 (add-after 'install 'wrap-executable
12832 ;; Make sure the executable finds all R modules.
12833 (lambda* (#:key inputs outputs #:allow-other-keys)
12834 (let ((out (assoc-ref outputs "out")))
12835 (wrap-program (string-append out "/bin/pigx-chipseq")
12836 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12837 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12841 ("coreutils" ,coreutils)
12842 ("r-minimal" ,r-minimal)
12843 ("r-argparser" ,r-argparser)
12844 ("r-biocparallel" ,r-biocparallel)
12845 ("r-biostrings" ,r-biostrings)
12846 ("r-chipseq" ,r-chipseq)
12847 ("r-data-table" ,r-data-table)
12848 ("r-dplyr" ,r-dplyr)
12849 ("r-genomation" ,r-genomation)
12850 ("r-genomicalignments" ,r-genomicalignments)
12851 ("r-genomicranges" ,r-genomicranges)
12852 ("r-rsamtools" ,r-rsamtools)
12853 ("r-rtracklayer" ,r-rtracklayer)
12854 ("r-s4vectors" ,r-s4vectors)
12855 ("r-stringr" ,r-stringr)
12856 ("r-tibble" ,r-tibble)
12857 ("r-tidyr" ,r-tidyr)
12858 ("r-jsonlite" ,r-jsonlite)
12859 ("r-heatmaply" ,r-heatmaply)
12860 ("r-htmlwidgets" ,r-htmlwidgets)
12861 ("r-ggplot2" ,r-ggplot2)
12862 ("r-plotly" ,r-plotly)
12863 ("r-rmarkdown" ,r-rmarkdown)
12864 ("python-wrapper" ,python-wrapper)
12865 ("python-pyyaml" ,python-pyyaml)
12866 ("python-magic" ,python-magic)
12867 ("python-xlrd" ,python-xlrd)
12868 ("trim-galore" ,trim-galore)
12870 ("multiqc" ,multiqc)
12872 ("ghc-pandoc" ,ghc-pandoc-1)
12873 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12877 ("snakemake" ,snakemake)
12878 ("samtools" ,samtools)
12879 ("bedtools" ,bedtools)
12880 ("kentutils" ,kentutils)))
12882 `(("python-pytest" ,python-pytest)))
12883 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12884 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12885 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12886 calling and reporting for ChIP sequencing experiments. It is easy to use and
12887 produces high quality reports. The inputs are reads files from the sequencing
12888 experiment, and a configuration file which describes the experiment. In
12889 addition to quality control of the experiment, the pipeline enables to set up
12890 multiple peak calling analysis and allows the generation of a UCSC track hub
12891 in an easily configurable manner.")
12892 (license license:gpl3+)))
12894 (define-public pigx-bsseq
12896 (name "pigx-bsseq")
12900 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12901 "releases/download/v" version
12902 "/pigx_bsseq-" version ".tar.gz"))
12905 "0irlnlhhw9fd4ha7hksrxn3y7j76mz5qq1wjswbs9p364laqg69y"))))
12906 (build-system gnu-build-system)
12909 (modify-phases %standard-phases
12910 (add-before 'check 'set-timezone
12911 ;; The readr package is picky about timezones.
12912 (lambda* (#:key inputs #:allow-other-keys)
12913 (setenv "TZ" "UTC+1")
12915 (string-append (assoc-ref inputs "tzdata")
12916 "/share/zoneinfo"))
12918 (add-after 'install 'wrap-executable
12919 ;; Make sure the executable finds all R modules.
12920 (lambda* (#:key inputs outputs #:allow-other-keys)
12921 (let ((out (assoc-ref outputs "out")))
12922 (wrap-program (string-append out "/bin/pigx-bsseq")
12923 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12924 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12927 `(("tzdata" ,tzdata)))
12929 `(("coreutils" ,coreutils)
12932 ("r-minimal" ,r-minimal)
12933 ("r-annotationhub" ,r-annotationhub)
12935 ("r-genomation" ,r-genomation)
12936 ("r-methylkit" ,r-methylkit)
12937 ("r-rtracklayer" ,r-rtracklayer)
12938 ("r-rmarkdown" ,r-rmarkdown)
12939 ("r-bookdown" ,r-bookdown)
12940 ("r-ggplot2" ,r-ggplot2)
12941 ("r-ggbio" ,r-ggbio)
12942 ("ghc-pandoc" ,ghc-pandoc-1)
12943 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12944 ("python-wrapper" ,python-wrapper)
12945 ("python-pyyaml" ,python-pyyaml)
12946 ("snakemake" ,snakemake)
12947 ("bismark" ,bismark)
12950 ("trim-galore" ,trim-galore)
12951 ("cutadapt" ,cutadapt)
12952 ("samtools" ,samtools)))
12953 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12954 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12955 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12956 data of bisulfite experiments; it produces reports on aggregate methylation
12957 and coverage and can be used to produce information on differential
12958 methylation and segmentation.")
12959 (license license:gpl3+)))
12961 (define-public pigx-scrnaseq
12963 (name "pigx-scrnaseq")
12967 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12968 "releases/download/v" version
12969 "/pigx_scrnaseq-" version ".tar.gz"))
12972 "12qdq0nj1wdkyighdxj6924bmbpd1a0b3gam6w64l4hiqrv5sijz"))))
12973 (build-system gnu-build-system)
12975 `(#:configure-flags
12976 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12977 "/share/java/picard.jar")
12978 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12979 "/share/java/dropseq.jar"))
12981 (modify-phases %standard-phases
12982 (add-after 'install 'wrap-executable
12983 ;; Make sure the executable finds all R modules.
12984 (lambda* (#:key inputs outputs #:allow-other-keys)
12985 (let ((out (assoc-ref outputs "out")))
12986 (wrap-program (string-append out "/bin/pigx-scrnaseq")
12987 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12988 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12991 `(("coreutils" ,coreutils)
12993 ("dropseq-tools" ,dropseq-tools)
12995 ("java-picard" ,java-picard)
12996 ("java" ,icedtea-8)
12997 ("python-wrapper" ,python-wrapper)
12998 ("python-pyyaml" ,python-pyyaml)
12999 ("python-pandas" ,python-pandas)
13000 ("python-numpy" ,python-numpy)
13001 ("python-loompy" ,python-loompy)
13002 ("ghc-pandoc" ,ghc-pandoc-1)
13003 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13004 ("snakemake" ,snakemake)
13006 ("r-minimal" ,r-minimal)
13007 ("r-argparser" ,r-argparser)
13008 ("r-cowplot" ,r-cowplot)
13009 ("r-data-table" ,r-data-table)
13010 ("r-delayedarray" ,r-delayedarray)
13011 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13012 ("r-dplyr" ,r-dplyr)
13013 ("r-dropbead" ,r-dropbead)
13015 ("r-genomicalignments" ,r-genomicalignments)
13016 ("r-genomicfiles" ,r-genomicfiles)
13017 ("r-genomicranges" ,r-genomicranges)
13018 ("r-ggplot2" ,r-ggplot2)
13019 ("r-hdf5array" ,r-hdf5array)
13020 ("r-pheatmap" ,r-pheatmap)
13021 ("r-rmarkdown" ,r-rmarkdown)
13022 ("r-rsamtools" ,r-rsamtools)
13023 ("r-rtracklayer" ,r-rtracklayer)
13024 ("r-rtsne" ,r-rtsne)
13025 ("r-scater" ,r-scater)
13026 ("r-scran" ,r-scran)
13027 ("r-singlecellexperiment" ,r-singlecellexperiment)
13028 ("r-stringr" ,r-stringr)
13029 ("r-yaml" ,r-yaml)))
13030 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13031 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13032 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13033 quality control for single cell RNA sequencing experiments. The inputs are
13034 read files from the sequencing experiment, and a configuration file which
13035 describes the experiment. It produces processed files for downstream analysis
13036 and interactive quality reports. The pipeline is designed to work with UMI
13038 (license license:gpl3+)))
13040 (define-public pigx
13046 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13047 "releases/download/v" version
13048 "/pigx-" version ".tar.gz"))
13051 "0sb708sl42h3s5z872jb1w70bbqplwapnsc1wm27zcsvi7li4gw8"))))
13052 (build-system gnu-build-system)
13054 `(("python" ,python)
13055 ("pigx-bsseq" ,pigx-bsseq)
13056 ("pigx-chipseq" ,pigx-chipseq)
13057 ("pigx-rnaseq" ,pigx-rnaseq)
13058 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13059 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13060 (synopsis "Analysis pipelines for genomics")
13061 (description "PiGx is a collection of genomics pipelines. It includes the
13062 following pipelines:
13065 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13066 @item PiGx RNAseq for RNAseq samples
13067 @item PiGx scRNAseq for single cell dropseq analysis
13068 @item PiGx ChIPseq for reads from ChIPseq experiments
13071 All pipelines are easily configured with a simple sample sheet and a
13072 descriptive settings file. The result is a set of comprehensive, interactive
13073 HTML reports with interesting findings about your samples.")
13074 (license license:gpl3+)))
13076 (define-public r-diversitree
13078 (name "r-diversitree")
13083 (uri (cran-uri "diversitree" version))
13086 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13087 (build-system r-build-system)
13089 `(("gfortran" ,gfortran)))
13090 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13093 ("r-desolve" ,r-desolve)
13095 ("r-suplex" ,r-subplex)))
13096 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13097 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13098 (description "This package contains a number of comparative \"phylogenetic\"
13099 methods, mostly focusing on analysing diversification and character evolution.
13100 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13101 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13102 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13103 include Markov models of discrete and continuous trait evolution and constant
13104 rate speciation and extinction.")
13105 (license license:gpl2+)))