1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
14 ;;; This file is part of GNU Guix.
16 ;;; GNU Guix is free software; you can redistribute it and/or modify it
17 ;;; under the terms of the GNU General Public License as published by
18 ;;; the Free Software Foundation; either version 3 of the License, or (at
19 ;;; your option) any later version.
21 ;;; GNU Guix is distributed in the hope that it will be useful, but
22 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;;; GNU General Public License for more details.
26 ;;; You should have received a copy of the GNU General Public License
27 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
29 (define-module (gnu packages bioinformatics)
30 #:use-module ((guix licenses) #:prefix license:)
31 #:use-module (guix packages)
32 #:use-module (guix utils)
33 #:use-module (guix download)
34 #:use-module (guix git-download)
35 #:use-module (guix hg-download)
36 #:use-module (guix build-system ant)
37 #:use-module (guix build-system gnu)
38 #:use-module (guix build-system cmake)
39 #:use-module (guix build-system ocaml)
40 #:use-module (guix build-system perl)
41 #:use-module (guix build-system python)
42 #:use-module (guix build-system r)
43 #:use-module (guix build-system ruby)
44 #:use-module (guix build-system scons)
45 #:use-module (guix build-system trivial)
46 #:use-module (gnu packages)
47 #:use-module (gnu packages autotools)
48 #:use-module (gnu packages algebra)
49 #:use-module (gnu packages base)
50 #:use-module (gnu packages bash)
51 #:use-module (gnu packages bison)
52 #:use-module (gnu packages boost)
53 #:use-module (gnu packages check)
54 #:use-module (gnu packages compression)
55 #:use-module (gnu packages cpio)
56 #:use-module (gnu packages cran)
57 #:use-module (gnu packages curl)
58 #:use-module (gnu packages documentation)
59 #:use-module (gnu packages databases)
60 #:use-module (gnu packages datastructures)
61 #:use-module (gnu packages file)
62 #:use-module (gnu packages flex)
63 #:use-module (gnu packages gawk)
64 #:use-module (gnu packages gcc)
65 #:use-module (gnu packages gd)
66 #:use-module (gnu packages gtk)
67 #:use-module (gnu packages glib)
68 #:use-module (gnu packages graph)
69 #:use-module (gnu packages groff)
70 #:use-module (gnu packages guile)
71 #:use-module (gnu packages haskell)
72 #:use-module (gnu packages image)
73 #:use-module (gnu packages imagemagick)
74 #:use-module (gnu packages java)
75 #:use-module (gnu packages jemalloc)
76 #:use-module (gnu packages ldc)
77 #:use-module (gnu packages linux)
78 #:use-module (gnu packages logging)
79 #:use-module (gnu packages machine-learning)
80 #:use-module (gnu packages man)
81 #:use-module (gnu packages maths)
82 #:use-module (gnu packages mpi)
83 #:use-module (gnu packages ncurses)
84 #:use-module (gnu packages ocaml)
85 #:use-module (gnu packages pcre)
86 #:use-module (gnu packages parallel)
87 #:use-module (gnu packages pdf)
88 #:use-module (gnu packages perl)
89 #:use-module (gnu packages perl-check)
90 #:use-module (gnu packages pkg-config)
91 #:use-module (gnu packages popt)
92 #:use-module (gnu packages protobuf)
93 #:use-module (gnu packages python)
94 #:use-module (gnu packages python-web)
95 #:use-module (gnu packages readline)
96 #:use-module (gnu packages ruby)
97 #:use-module (gnu packages serialization)
98 #:use-module (gnu packages shells)
99 #:use-module (gnu packages statistics)
100 #:use-module (gnu packages swig)
101 #:use-module (gnu packages tbb)
102 #:use-module (gnu packages tex)
103 #:use-module (gnu packages texinfo)
104 #:use-module (gnu packages textutils)
105 #:use-module (gnu packages time)
106 #:use-module (gnu packages tls)
107 #:use-module (gnu packages vim)
108 #:use-module (gnu packages web)
109 #:use-module (gnu packages xml)
110 #:use-module (gnu packages xorg)
111 #:use-module (srfi srfi-1)
112 #:use-module (ice-9 match))
114 (define-public aragorn
121 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
125 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
126 (build-system gnu-build-system)
128 `(#:tests? #f ; there are no tests
130 (modify-phases %standard-phases
134 (zero? (system* "gcc"
140 (string-append "aragorn" ,version ".c")))))
142 (lambda* (#:key outputs #:allow-other-keys)
143 (let* ((out (assoc-ref outputs "out"))
144 (bin (string-append out "/bin"))
145 (man (string-append out "/share/man/man1")))
147 (install-file "aragorn" bin)
149 (install-file "aragorn.1" man))
151 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
152 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
154 "Aragorn identifies transfer RNA, mitochondrial RNA and
155 transfer-messenger RNA from nucleotide sequences, based on homology to known
156 tRNA consensus sequences and RNA structure. It also outputs the secondary
157 structure of the predicted RNA.")
158 (license license:gpl2)))
166 ;; BamM is not available on pypi.
168 "https://github.com/Ecogenomics/BamM/archive/"
170 (file-name (string-append name "-" version ".tar.gz"))
173 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
174 (modules '((guix build utils)))
177 ;; Delete bundled htslib.
178 (delete-file-recursively "c/htslib-1.3.1")
180 (build-system python-build-system)
182 `(#:python ,python-2 ; BamM is Python 2 only.
183 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
184 ;; been modified from its original form.
186 (let ((htslib (assoc-ref %build-inputs "htslib")))
187 (list "--with-libhts-lib" (string-append htslib "/lib")
188 "--with-libhts-inc" (string-append htslib "/include/htslib")))
190 (modify-phases %standard-phases
191 (add-after 'unpack 'autogen
193 (with-directory-excursion "c"
194 (let ((sh (which "sh")))
195 ;; Use autogen so that 'configure' works.
196 (substitute* "autogen.sh" (("/bin/sh") sh))
197 (setenv "CONFIG_SHELL" sh)
198 (substitute* "configure" (("/bin/sh") sh))
199 (zero? (system* "./autogen.sh"))))))
201 ;; Run tests after installation so compilation only happens once.
203 (add-after 'install 'wrap-executable
204 (lambda* (#:key outputs #:allow-other-keys)
205 (let* ((out (assoc-ref outputs "out"))
206 (path (getenv "PATH")))
207 (wrap-program (string-append out "/bin/bamm")
208 `("PATH" ":" prefix (,path))))
210 (add-after 'wrap-executable 'post-install-check
211 (lambda* (#:key inputs outputs #:allow-other-keys)
213 (string-append (assoc-ref outputs "out")
218 (assoc-ref outputs "out")
220 (string-take (string-take-right
221 (assoc-ref inputs "python") 5) 3)
223 (getenv "PYTHONPATH")))
224 ;; There are 2 errors printed, but they are safe to ignore:
225 ;; 1) [E::hts_open_format] fail to open file ...
226 ;; 2) samtools view: failed to open ...
227 (zero? (system* "nosetests")))))))
229 `(("autoconf" ,autoconf)
230 ("automake" ,automake)
233 ("python-nose" ,python2-nose)
234 ("python-pysam" ,python2-pysam)))
236 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
237 ("samtools" ,samtools)
241 ("coreutils" ,coreutils)))
243 `(("python-numpy" ,python2-numpy)))
244 (home-page "http://ecogenomics.github.io/BamM/")
245 (synopsis "Metagenomics-focused BAM file manipulator")
247 "BamM is a C library, wrapped in python, to efficiently generate and
248 parse BAM files, specifically for the analysis of metagenomic data. For
249 instance, it implements several methods to assess contig-wise read coverage.")
250 (license license:lgpl3+)))
252 (define-public bamtools
259 "https://github.com/pezmaster31/bamtools/archive/v"
261 (file-name (string-append name "-" version ".tar.gz"))
264 "1z3kg24qrwq13a88n9d86izngrar4fll7gr6phddb2faw75pdgaa"))))
265 (build-system cmake-build-system)
267 `(#:tests? #f ;no "check" target
269 (modify-phases %standard-phases
271 'configure 'set-ldflags
272 (lambda* (#:key outputs #:allow-other-keys)
276 (assoc-ref outputs "out") "/lib/bamtools")))))))
277 (inputs `(("zlib" ,zlib)))
278 (home-page "https://github.com/pezmaster31/bamtools")
279 (synopsis "C++ API and command-line toolkit for working with BAM data")
281 "BamTools provides both a C++ API and a command-line toolkit for handling
283 (license license:expat)))
285 (define-public bcftools
292 "https://github.com/samtools/bcftools/releases/download/"
293 version "/bcftools-" version ".tar.bz2"))
296 "1vgw2mwngq20c530zim52zvgmw1lci8rzl33pvh44xqk3xlzvjsa"))
297 (modules '((guix build utils)))
299 ;; Delete bundled htslib.
300 '(delete-file-recursively "htslib-1.8"))))
301 (build-system gnu-build-system)
303 `(#:test-target "test"
304 #:configure-flags (list "--with-htslib=system")
308 "LIBS=-lgsl -lgslcblas"
309 (string-append "prefix=" (assoc-ref %outputs "out"))
310 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
311 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
312 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
313 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
314 (string-append "PACKAGE_VERSION=" ,version))
316 (modify-phases %standard-phases
317 (add-before 'check 'patch-tests
319 (substitute* "test/test.pl"
320 (("/bin/bash") (which "bash")))
328 (home-page "https://samtools.github.io/bcftools/")
329 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
331 "BCFtools is a set of utilities that manipulate variant calls in the
332 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
333 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
334 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
335 (license (list license:gpl3+ license:expat))))
337 (define-public bedops
343 (uri (string-append "https://github.com/bedops/bedops/archive/v"
345 (file-name (string-append name "-" version ".tar.gz"))
348 "0kx4awrwby8f33wqyx8w7ms7v25xhf0d421csgf96a3hfzn2mb0m"))))
349 (build-system gnu-build-system)
352 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
354 (modify-phases %standard-phases
355 (add-after 'unpack 'unpack-tarballs
357 ;; FIXME: Bedops includes tarballs of minimally patched upstream
358 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
359 ;; libraries because at least one of the libraries (zlib) is
360 ;; patched to add a C++ function definition (deflateInit2cpp).
361 ;; Until the Bedops developers offer a way to link against system
362 ;; libraries we have to build the in-tree copies of these three
365 ;; See upstream discussion:
366 ;; https://github.com/bedops/bedops/issues/124
368 ;; Unpack the tarballs to benefit from shebang patching.
369 (with-directory-excursion "third-party"
370 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
371 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
372 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
373 ;; Disable unpacking of tarballs in Makefile.
374 (substitute* "system.mk/Makefile.linux"
375 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
376 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
377 (substitute* "third-party/zlib-1.2.7/Makefile.in"
378 (("^SHELL=.*$") "SHELL=bash\n"))
380 (delete 'configure))))
381 (home-page "https://github.com/bedops/bedops")
382 (synopsis "Tools for high-performance genomic feature operations")
384 "BEDOPS is a suite of tools to address common questions raised in genomic
385 studies---mostly with regard to overlap and proximity relationships between
386 data sets. It aims to be scalable and flexible, facilitating the efficient
387 and accurate analysis and management of large-scale genomic data.
389 BEDOPS provides tools that perform highly efficient and scalable Boolean and
390 other set operations, statistical calculations, archiving, conversion and
391 other management of genomic data of arbitrary scale. Tasks can be easily
392 split by chromosome for distributing whole-genome analyses across a
393 computational cluster.")
394 (license license:gpl2+)))
396 (define-public bedtools
402 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
403 "download/v" version "/"
404 "bedtools-" version ".tar.gz"))
407 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
408 (build-system gnu-build-system)
410 '(#:test-target "test"
412 (list (string-append "prefix=" (assoc-ref %outputs "out")))
414 (modify-phases %standard-phases
415 (delete 'configure))))
416 (native-inputs `(("python" ,python-2)))
418 `(("samtools" ,samtools)
420 (home-page "https://github.com/arq5x/bedtools2")
421 (synopsis "Tools for genome analysis and arithmetic")
423 "Collectively, the bedtools utilities are a swiss-army knife of tools for
424 a wide-range of genomics analysis tasks. The most widely-used tools enable
425 genome arithmetic: that is, set theory on the genome. For example, bedtools
426 allows one to intersect, merge, count, complement, and shuffle genomic
427 intervals from multiple files in widely-used genomic file formats such as BAM,
429 (license license:gpl2)))
431 ;; Later releases of bedtools produce files with more columns than
432 ;; what Ribotaper expects.
433 (define-public bedtools-2.18
434 (package (inherit bedtools)
439 (uri (string-append "https://github.com/arq5x/bedtools2/"
440 "archive/v" version ".tar.gz"))
441 (file-name (string-append name "-" version ".tar.gz"))
444 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
446 '(#:test-target "test"
448 (modify-phases %standard-phases
451 (lambda* (#:key outputs #:allow-other-keys)
452 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
453 (for-each (lambda (file)
454 (install-file file bin))
455 (find-files "bin" ".*")))
458 (define-public ribotaper
464 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
465 "files/RiboTaper/RiboTaper_Version_"
469 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
470 (build-system gnu-build-system)
473 (modify-phases %standard-phases
474 (add-after 'install 'wrap-executables
475 (lambda* (#:key inputs outputs #:allow-other-keys)
476 (let* ((out (assoc-ref outputs "out")))
479 (wrap-program (string-append out "/bin/" script)
480 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
481 '("create_annotations_files.bash"
482 "create_metaplots.bash"
483 "Ribotaper_ORF_find.sh"
484 "Ribotaper.sh"))))))))
486 `(("bedtools" ,bedtools-2.18)
487 ("samtools" ,samtools-0.1)
488 ("r-minimal" ,r-minimal)
489 ("r-foreach" ,r-foreach)
490 ("r-xnomial" ,r-xnomial)
492 ("r-multitaper" ,r-multitaper)
493 ("r-seqinr" ,r-seqinr)))
494 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
495 (synopsis "Define translated ORFs using ribosome profiling data")
497 "Ribotaper is a method for defining translated @dfn{open reading
498 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
499 provides the Ribotaper pipeline.")
500 (license license:gpl3+)))
502 (define-public ribodiff
509 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
510 "archive/v" version ".tar.gz"))
511 (file-name (string-append name "-" version ".tar.gz"))
514 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
515 (build-system python-build-system)
519 (modify-phases %standard-phases
520 ;; Generate an installable executable script wrapper.
521 (add-after 'unpack 'patch-setup.py
523 (substitute* "setup.py"
524 (("^(.*)packages=.*" line prefix)
525 (string-append line "\n"
526 prefix "scripts=['scripts/TE.py'],\n")))
529 `(("python-numpy" ,python2-numpy)
530 ("python-matplotlib" ,python2-matplotlib)
531 ("python-scipy" ,python2-scipy)
532 ("python-statsmodels" ,python2-statsmodels)))
534 `(("python-mock" ,python2-mock)
535 ("python-nose" ,python2-nose)))
536 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
537 (synopsis "Detect translation efficiency changes from ribosome footprints")
538 (description "RiboDiff is a statistical tool that detects the protein
539 translational efficiency change from Ribo-Seq (ribosome footprinting) and
540 RNA-Seq data. It uses a generalized linear model to detect genes showing
541 difference in translational profile taking mRNA abundance into account. It
542 facilitates us to decipher the translational regulation that behave
543 independently with transcriptional regulation.")
544 (license license:gpl3+)))
546 (define-public bioawk
552 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
554 (file-name (string-append name "-" version ".tar.gz"))
556 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
557 (build-system gnu-build-system)
563 `(#:tests? #f ; There are no tests to run.
564 ;; Bison must generate files, before other targets can build.
567 (modify-phases %standard-phases
568 (delete 'configure) ; There is no configure phase.
570 (lambda* (#:key outputs #:allow-other-keys)
571 (let* ((out (assoc-ref outputs "out"))
572 (bin (string-append out "/bin"))
573 (man (string-append out "/share/man/man1")))
575 (copy-file "awk.1" (string-append man "/bioawk.1"))
576 (install-file "bioawk" bin)))))))
577 (home-page "https://github.com/lh3/bioawk")
578 (synopsis "AWK with bioinformatics extensions")
579 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
580 support of several common biological data formats, including optionally gzip'ed
581 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
582 also adds a few built-in functions and a command line option to use TAB as the
583 input/output delimiter. When the new functionality is not used, bioawk is
584 intended to behave exactly the same as the original BWK awk.")
585 (license license:x11)))
587 (define-public python2-pybedtools
589 (name "python2-pybedtools")
594 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
598 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
599 (build-system python-build-system)
600 (arguments `(#:python ,python-2)) ; no Python 3 support
602 `(("python-matplotlib" ,python2-matplotlib)))
604 `(("bedtools" ,bedtools)
605 ("samtools" ,samtools)))
607 `(("python-cython" ,python2-cython)
608 ("python-pyyaml" ,python2-pyyaml)
609 ("python-nose" ,python2-nose)))
610 (home-page "https://pythonhosted.org/pybedtools/")
611 (synopsis "Python wrapper for BEDtools programs")
613 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
614 which are widely used for genomic interval manipulation or \"genome algebra\".
615 pybedtools extends BEDTools by offering feature-level manipulations from with
617 (license license:gpl2+)))
619 (define-public python-biom-format
621 (name "python-biom-format")
626 ;; Use GitHub as source because PyPI distribution does not contain
627 ;; test data: https://github.com/biocore/biom-format/issues/693
628 (uri (string-append "https://github.com/biocore/biom-format/archive/"
630 (file-name (string-append name "-" version ".tar.gz"))
633 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
634 (build-system python-build-system)
636 `(("python-numpy" ,python-numpy)
637 ("python-scipy" ,python-scipy)
638 ("python-future" ,python-future)
639 ("python-click" ,python-click)
640 ("python-h5py" ,python-h5py)
641 ("python-pandas" ,python-pandas)))
643 `(("python-nose" ,python-nose)))
644 (home-page "http://www.biom-format.org")
645 (synopsis "Biological Observation Matrix (BIOM) format utilities")
647 "The BIOM file format is designed to be a general-use format for
648 representing counts of observations e.g. operational taxonomic units, KEGG
649 orthology groups or lipid types, in one or more biological samples
650 e.g. microbiome samples, genomes, metagenomes.")
651 (license license:bsd-3)
652 (properties `((python2-variant . ,(delay python2-biom-format))))))
654 (define-public python2-biom-format
655 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
660 (modify-phases %standard-phases
661 ;; Do not require the unmaintained pyqi library.
662 (add-after 'unpack 'remove-pyqi
664 (substitute* "setup.py"
665 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
667 ,@(package-arguments base))))))
669 (define-public bioperl-minimal
670 (let* ((inputs `(("perl-module-build" ,perl-module-build)
671 ("perl-data-stag" ,perl-data-stag)
672 ("perl-libwww" ,perl-libwww)
673 ("perl-uri" ,perl-uri)))
675 (map (compose package-name cadr)
678 (map (compose package-transitive-target-inputs cadr) inputs))))))
680 (name "bioperl-minimal")
685 (uri (string-append "https://github.com/bioperl/bioperl-live/"
687 (string-map (lambda (c)
693 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
694 (build-system perl-build-system)
697 (modify-phases %standard-phases
699 'install 'wrap-programs
700 (lambda* (#:key outputs #:allow-other-keys)
701 ;; Make sure all executables in "bin" find the required Perl
702 ;; modules at runtime. As the PERL5LIB variable contains also
703 ;; the paths of native inputs, we pick the transitive target
704 ;; inputs from %build-inputs.
705 (let* ((out (assoc-ref outputs "out"))
706 (bin (string-append out "/bin/"))
708 (cons (string-append out "/lib/perl5/site_perl")
710 (assoc-ref %build-inputs name))
711 ',transitive-inputs))
713 (for-each (lambda (file)
715 `("PERL5LIB" ":" prefix (,path))))
716 (find-files bin "\\.pl$"))
720 `(("perl-test-most" ,perl-test-most)))
721 (home-page "http://search.cpan.org/dist/BioPerl")
722 (synopsis "Bioinformatics toolkit")
724 "BioPerl is the product of a community effort to produce Perl code which
725 is useful in biology. Examples include Sequence objects, Alignment objects
726 and database searching objects. These objects not only do what they are
727 advertised to do in the documentation, but they also interact - Alignment
728 objects are made from the Sequence objects, Sequence objects have access to
729 Annotation and SeqFeature objects and databases, Blast objects can be
730 converted to Alignment objects, and so on. This means that the objects
731 provide a coordinated and extensible framework to do computational biology.")
732 (license license:perl-license))))
734 (define-public python-biopython
736 (name "python-biopython")
740 ;; use PyPi rather than biopython.org to ease updating
741 (uri (pypi-uri "biopython" version))
744 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
745 (build-system python-build-system)
748 (modify-phases %standard-phases
749 (add-before 'check 'set-home
750 ;; Some tests require a home directory to be set.
751 (lambda _ (setenv "HOME" "/tmp") #t)))))
753 `(("python-numpy" ,python-numpy)))
754 (home-page "http://biopython.org/")
755 (synopsis "Tools for biological computation in Python")
757 "Biopython is a set of tools for biological computation including parsers
758 for bioinformatics files into Python data structures; interfaces to common
759 bioinformatics programs; a standard sequence class and tools for performing
760 common operations on them; code to perform data classification; code for
761 dealing with alignments; code making it easy to split up parallelizable tasks
762 into separate processes; and more.")
763 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
765 (define-public python2-biopython
766 (package-with-python2 python-biopython))
768 (define-public bpp-core
769 ;; The last release was in 2014 and the recommended way to install from source
770 ;; is to clone the git repository, so we do this.
771 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
772 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
775 (version (string-append "2.2.0-1." (string-take commit 7)))
779 (url "http://biopp.univ-montp2.fr/git/bpp-core")
781 (file-name (string-append name "-" version "-checkout"))
784 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
785 (build-system cmake-build-system)
787 `(#:parallel-build? #f))
789 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
790 ; compile all of the bpp packages with GCC 5.
791 (home-page "http://biopp.univ-montp2.fr")
792 (synopsis "C++ libraries for Bioinformatics")
794 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
795 analysis, phylogenetics, molecular evolution and population genetics. It is
796 Object Oriented and is designed to be both easy to use and computer efficient.
797 Bio++ intends to help programmers to write computer expensive programs, by
798 providing them a set of re-usable tools.")
799 (license license:cecill-c))))
801 (define-public bpp-phyl
802 ;; The last release was in 2014 and the recommended way to install from source
803 ;; is to clone the git repository, so we do this.
804 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
805 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
808 (version (string-append "2.2.0-1." (string-take commit 7)))
812 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
814 (file-name (string-append name "-" version "-checkout"))
817 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
818 (build-system cmake-build-system)
820 `(#:parallel-build? #f
821 ;; If out-of-source, test data is not copied into the build directory
822 ;; so the tests fail.
823 #:out-of-source? #f))
825 `(("bpp-core" ,bpp-core)
827 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
830 (home-page "http://biopp.univ-montp2.fr")
831 (synopsis "Bio++ phylogenetic Library")
833 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
834 analysis, phylogenetics, molecular evolution and population genetics. This
835 library provides phylogenetics-related modules.")
836 (license license:cecill-c))))
838 (define-public bpp-popgen
839 ;; The last release was in 2014 and the recommended way to install from source
840 ;; is to clone the git repository, so we do this.
841 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
842 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
845 (version (string-append "2.2.0-1." (string-take commit 7)))
849 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
851 (file-name (string-append name "-" version "-checkout"))
854 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
855 (build-system cmake-build-system)
857 `(#:parallel-build? #f
858 #:tests? #f)) ; There are no tests.
860 `(("bpp-core" ,bpp-core)
863 (home-page "http://biopp.univ-montp2.fr")
864 (synopsis "Bio++ population genetics library")
866 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
867 analysis, phylogenetics, molecular evolution and population genetics. This
868 library provides population genetics-related modules.")
869 (license license:cecill-c))))
871 (define-public bpp-seq
872 ;; The last release was in 2014 and the recommended way to install from source
873 ;; is to clone the git repository, so we do this.
874 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
875 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
878 (version (string-append "2.2.0-1." (string-take commit 7)))
882 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
884 (file-name (string-append name "-" version "-checkout"))
887 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
888 (build-system cmake-build-system)
890 `(#:parallel-build? #f
891 ;; If out-of-source, test data is not copied into the build directory
892 ;; so the tests fail.
893 #:out-of-source? #f))
895 `(("bpp-core" ,bpp-core)
896 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
897 (home-page "http://biopp.univ-montp2.fr")
898 (synopsis "Bio++ sequence library")
900 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
901 analysis, phylogenetics, molecular evolution and population genetics. This
902 library provides sequence-related modules.")
903 (license license:cecill-c))))
905 (define-public bppsuite
906 ;; The last release was in 2014 and the recommended way to install from source
907 ;; is to clone the git repository, so we do this.
908 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
909 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
912 (version (string-append "2.2.0-1." (string-take commit 7)))
916 (url "http://biopp.univ-montp2.fr/git/bppsuite")
918 (file-name (string-append name "-" version "-checkout"))
921 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
922 (build-system cmake-build-system)
924 `(#:parallel-build? #f
925 #:tests? #f)) ; There are no tests.
929 ("texinfo" ,texinfo)))
931 `(("bpp-core" ,bpp-core)
933 ("bpp-phyl" ,bpp-phyl)
934 ("bpp-phyl" ,bpp-popgen)
936 (home-page "http://biopp.univ-montp2.fr")
937 (synopsis "Bioinformatics tools written with the Bio++ libraries")
939 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
940 analysis, phylogenetics, molecular evolution and population genetics. This
941 package provides command line tools using the Bio++ library.")
942 (license license:cecill-c))))
944 (define-public blast+
951 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
952 version "/ncbi-blast-" version "+-src.tar.gz"))
955 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
956 (patches (search-patches "blast+-fix-makefile.patch"))
957 (modules '((guix build utils)))
960 ;; Remove bundled bzip2, zlib and pcre.
961 (delete-file-recursively "c++/src/util/compress/bzip2")
962 (delete-file-recursively "c++/src/util/compress/zlib")
963 (delete-file-recursively "c++/src/util/regexp")
964 (substitute* "c++/src/util/compress/Makefile.in"
965 (("bzip2 zlib api") "api"))
966 ;; Remove useless msbuild directory
967 (delete-file-recursively
968 "c++/src/build-system/project_tree_builder/msbuild")
970 (build-system gnu-build-system)
972 `(;; There are two(!) tests for this massive library, and both fail with
973 ;; "unparsable timing stats".
974 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
975 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
978 #:parallel-build? #f ; not supported
980 (modify-phases %standard-phases
983 ;; $HOME needs to be set at some point during the configure phase
984 (lambda _ (setenv "HOME" "/tmp") #t))
987 (lambda _ (chdir "c++") #t))
989 'enter-dir 'fix-build-system
992 (cond ((string=? cmd "date")
993 ;; make call to "date" deterministic
998 (format (current-error-port)
999 "WARNING: Unable to find absolute path for ~s~%"
1003 ;; Rewrite hardcoded paths to various tools
1004 (substitute* (append '("src/build-system/configure.ac"
1005 "src/build-system/configure"
1006 "src/build-system/helpers/run_with_lock.c"
1007 "scripts/common/impl/if_diff.sh"
1008 "scripts/common/impl/run_with_lock.sh"
1009 "src/build-system/Makefile.configurables.real"
1010 "src/build-system/Makefile.in.top"
1011 "src/build-system/Makefile.meta.gmake=no"
1012 "src/build-system/Makefile.meta.in"
1013 "src/build-system/Makefile.meta_l"
1014 "src/build-system/Makefile.meta_p"
1015 "src/build-system/Makefile.meta_r"
1016 "src/build-system/Makefile.mk.in"
1017 "src/build-system/Makefile.requirements"
1018 "src/build-system/Makefile.rules_with_autodep.in")
1019 (find-files "scripts/common/check" "\\.sh$"))
1020 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1021 (or (which* cmd) all)))
1023 (substitute* (find-files "src/build-system" "^config.*")
1024 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1027 ;; rewrite "/var/tmp" in check script
1028 (substitute* "scripts/common/check/check_make_unix.sh"
1029 (("/var/tmp") "/tmp"))
1031 ;; do not reset PATH
1032 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1034 (("action=/bin/") "action=")
1035 (("export PATH") ":"))
1039 (lambda* (#:key inputs outputs #:allow-other-keys)
1040 (let ((out (assoc-ref outputs "out"))
1041 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1042 (include (string-append (assoc-ref outputs "include")
1043 "/include/ncbi-tools++")))
1044 ;; The 'configure' script doesn't recognize things like
1045 ;; '--enable-fast-install'.
1046 (zero? (system* "./configure.orig"
1047 (string-append "--with-build-root=" (getcwd) "/build")
1048 (string-append "--prefix=" out)
1049 (string-append "--libdir=" lib)
1050 (string-append "--includedir=" include)
1051 (string-append "--with-bz2="
1052 (assoc-ref inputs "bzip2"))
1053 (string-append "--with-z="
1054 (assoc-ref inputs "zlib"))
1055 (string-append "--with-pcre="
1056 (assoc-ref inputs "pcre"))
1057 ;; Each library is built twice by default, once
1058 ;; with "-static" in its name, and again
1061 "--with-dll"))))))))
1062 (outputs '("out" ; 21 MB
1070 ("python" ,python-wrapper)))
1073 (home-page "http://blast.ncbi.nlm.nih.gov")
1074 (synopsis "Basic local alignment search tool")
1076 "BLAST is a popular method of performing a DNA or protein sequence
1077 similarity search, using heuristics to produce results quickly. It also
1078 calculates an “expect value” that estimates how many matches would have
1079 occurred at a given score by chance, which can aid a user in judging how much
1080 confidence to have in an alignment.")
1081 ;; Most of the sources are in the public domain, with the following
1084 ;; * ./c++/include/util/bitset/
1085 ;; * ./c++/src/html/ncbi_menu*.js
1087 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1089 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1091 ;; * ./c++/src/corelib/teamcity_*
1092 (license (list license:public-domain
1098 (define-public bless
1104 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1108 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1109 (modules '((guix build utils)))
1112 ;; Remove bundled boost, pigz, zlib, and .git directory
1113 ;; FIXME: also remove bundled sources for murmurhash3 and
1114 ;; kmc once packaged.
1115 (delete-file-recursively "boost")
1116 (delete-file-recursively "pigz")
1117 (delete-file-recursively "google-sparsehash")
1118 (delete-file-recursively "zlib")
1119 (delete-file-recursively ".git")
1121 (build-system gnu-build-system)
1123 '(#:tests? #f ;no "check" target
1125 (list (string-append "ZLIB="
1126 (assoc-ref %build-inputs "zlib")
1128 (string-append "LDFLAGS="
1129 (string-join '("-lboost_filesystem"
1136 (modify-phases %standard-phases
1137 (add-after 'unpack 'do-not-build-bundled-pigz
1138 (lambda* (#:key inputs outputs #:allow-other-keys)
1139 (substitute* "Makefile"
1140 (("cd pigz/pigz-2.3.3; make") ""))
1142 (add-after 'unpack 'patch-paths-to-executables
1143 (lambda* (#:key inputs outputs #:allow-other-keys)
1144 (substitute* "parse_args.cpp"
1145 (("kmc_binary = .*")
1146 (string-append "kmc_binary = \""
1147 (assoc-ref outputs "out")
1149 (("pigz_binary = .*")
1150 (string-append "pigz_binary = \""
1151 (assoc-ref inputs "pigz")
1155 (lambda* (#:key outputs #:allow-other-keys)
1156 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1157 (for-each (lambda (file)
1158 (install-file file bin))
1159 '("bless" "kmc/bin/kmc"))
1161 (delete 'configure))))
1165 `(("openmpi" ,openmpi)
1167 ("sparsehash" ,sparsehash)
1170 (supported-systems '("x86_64-linux"))
1171 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1172 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1174 "@dfn{Bloom-filter-based error correction solution for high-throughput
1175 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1176 correction tool for genomic reads produced by @dfn{Next-generation
1177 sequencing} (NGS). BLESS produces accurate correction results with much less
1178 memory compared with previous solutions and is also able to tolerate a higher
1179 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1180 errors at the end of reads.")
1181 (license license:gpl3+)))
1183 (define-public bowtie
1189 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1191 (file-name (string-append name "-" version ".tar.gz"))
1194 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1195 (modules '((guix build utils)))
1197 '(substitute* "Makefile"
1198 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1199 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1200 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1201 (build-system gnu-build-system)
1204 ("perl-clone" ,perl-clone)
1205 ("perl-test-deep" ,perl-test-deep)
1206 ("perl-test-simple" ,perl-test-simple)
1207 ("python" ,python-2)
1214 (string-append "prefix=" (assoc-ref %outputs "out")))
1216 (modify-phases %standard-phases
1219 (lambda* (#:key outputs #:allow-other-keys)
1220 (zero? (system* "perl"
1221 "scripts/test/simple_tests.pl"
1222 "--bowtie2=./bowtie2"
1223 "--bowtie2-build=./bowtie2-build")))))))
1224 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1225 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1227 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1228 reads to long reference sequences. It is particularly good at aligning reads
1229 of about 50 up to 100s or 1,000s of characters, and particularly good at
1230 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1231 genome with an FM Index to keep its memory footprint small: for the human
1232 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1233 gapped, local, and paired-end alignment modes.")
1234 (supported-systems '("x86_64-linux"))
1235 (license license:gpl3+)))
1237 (define-public tophat
1244 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1248 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1249 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1250 (modules '((guix build utils)))
1253 ;; Remove bundled SeqAn and samtools
1254 (delete-file-recursively "src/SeqAn-1.3")
1255 (delete-file-recursively "src/samtools-0.1.18")
1257 (build-system gnu-build-system)
1259 '(#:parallel-build? #f ; not supported
1261 (modify-phases %standard-phases
1262 (add-after 'unpack 'use-system-samtools
1263 (lambda* (#:key inputs #:allow-other-keys)
1264 (substitute* "src/Makefile.in"
1265 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1266 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1267 (("SAMPROG = samtools_0\\.1\\.18") "")
1268 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1269 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1270 (substitute* '("src/common.cpp"
1272 (("samtools_0.1.18") (which "samtools")))
1273 (substitute* '("src/common.h"
1274 "src/bam2fastx.cpp")
1275 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1276 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1277 (substitute* '("src/bwt_map.h"
1279 "src/align_status.h")
1280 (("#include <bam.h>") "#include <samtools/bam.h>")
1281 (("#include <sam.h>") "#include <samtools/sam.h>"))
1286 ("samtools" ,samtools-0.1)
1287 ("ncurses" ,ncurses)
1288 ("python" ,python-2)
1292 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1293 (synopsis "Spliced read mapper for RNA-Seq data")
1295 "TopHat is a fast splice junction mapper for nucleotide sequence
1296 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1297 mammalian-sized genomes using the ultra high-throughput short read
1298 aligner Bowtie, and then analyzes the mapping results to identify
1299 splice junctions between exons.")
1300 ;; TopHat is released under the Boost Software License, Version 1.0
1301 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1302 (license license:boost1.0)))
1311 "https://github.com/lh3/bwa/releases/download/v"
1312 version "/bwa-" version ".tar.bz2"))
1315 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1316 (build-system gnu-build-system)
1318 '(#:tests? #f ;no "check" target
1320 (modify-phases %standard-phases
1322 (lambda* (#:key outputs #:allow-other-keys)
1323 (let ((bin (string-append
1324 (assoc-ref outputs "out") "/bin"))
1326 (assoc-ref outputs "out") "/share/doc/bwa"))
1328 (assoc-ref outputs "out") "/share/man/man1")))
1329 (install-file "bwa" bin)
1330 (install-file "README.md" doc)
1331 (install-file "bwa.1" man))
1333 ;; no "configure" script
1334 (delete 'configure))))
1335 (inputs `(("zlib" ,zlib)))
1336 ;; Non-portable SSE instructions are used so building fails on platforms
1337 ;; other than x86_64.
1338 (supported-systems '("x86_64-linux"))
1339 (home-page "http://bio-bwa.sourceforge.net/")
1340 (synopsis "Burrows-Wheeler sequence aligner")
1342 "BWA is a software package for mapping low-divergent sequences against a
1343 large reference genome, such as the human genome. It consists of three
1344 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1345 designed for Illumina sequence reads up to 100bp, while the rest two for
1346 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1347 features such as long-read support and split alignment, but BWA-MEM, which is
1348 the latest, is generally recommended for high-quality queries as it is faster
1349 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1350 70-100bp Illumina reads.")
1351 (license license:gpl3+)))
1353 (define-public bwa-pssm
1354 (package (inherit bwa)
1359 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1360 "archive/" version ".tar.gz"))
1361 (file-name (string-append name "-" version ".tar.gz"))
1364 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1365 (build-system gnu-build-system)
1370 (home-page "http://bwa-pssm.binf.ku.dk/")
1371 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1373 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1374 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1375 existing aligners it is fast and sensitive. Unlike most other aligners,
1376 however, it is also adaptible in the sense that one can direct the alignment
1377 based on known biases within the data set. It is coded as a modification of
1378 the original BWA alignment program and shares the genome index structure as
1379 well as many of the command line options.")
1380 (license license:gpl3+)))
1382 (define-public python2-bx-python
1384 (name "python2-bx-python")
1388 (uri (pypi-uri "bx-python" version))
1391 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1392 (modules '((guix build utils)))
1394 '(substitute* "setup.py"
1395 ;; remove dependency on outdated "distribute" module
1396 (("^from distribute_setup import use_setuptools") "")
1397 (("^use_setuptools\\(\\)") "")))))
1398 (build-system python-build-system)
1400 `(#:tests? #f ;tests fail because test data are not included
1401 #:python ,python-2))
1403 `(("python-numpy" ,python2-numpy)
1406 `(("python-nose" ,python2-nose)))
1407 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1408 (synopsis "Tools for manipulating biological data")
1410 "bx-python provides tools for manipulating biological data, particularly
1411 multiple sequence alignments.")
1412 (license license:expat)))
1414 (define-public python-pysam
1416 (name "python-pysam")
1420 ;; Test data is missing on PyPi.
1422 "https://github.com/pysam-developers/pysam/archive/v"
1424 (file-name (string-append name "-" version ".tar.gz"))
1427 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1428 (modules '((guix build utils)))
1430 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1431 '(delete-file-recursively "htslib"))))
1432 (build-system python-build-system)
1434 `(#:modules ((ice-9 ftw)
1436 (guix build python-build-system)
1439 (modify-phases %standard-phases
1440 (add-before 'build 'set-flags
1441 (lambda* (#:key inputs #:allow-other-keys)
1442 (setenv "HTSLIB_MODE" "external")
1443 (setenv "HTSLIB_LIBRARY_DIR"
1444 (string-append (assoc-ref inputs "htslib") "/lib"))
1445 (setenv "HTSLIB_INCLUDE_DIR"
1446 (string-append (assoc-ref inputs "htslib") "/include"))
1447 (setenv "LDFLAGS" "-lncurses")
1448 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1451 (lambda* (#:key inputs outputs #:allow-other-keys)
1452 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1453 (setenv "PYTHONPATH"
1455 (getenv "PYTHONPATH")
1456 ":" (getcwd) "/build/"
1457 (car (scandir "build"
1458 (negate (cut string-prefix? "." <>))))))
1459 ;; Step out of source dir so python does not import from CWD.
1460 (with-directory-excursion "tests"
1461 (setenv "HOME" "/tmp")
1462 (and (zero? (system* "make" "-C" "pysam_data"))
1463 (zero? (system* "make" "-C" "cbcf_data"))
1464 ;; Running nosetests without explicitly asking for a
1465 ;; single process leads to a crash. Running with multiple
1466 ;; processes fails because the tests are not designed to
1469 ;; FIXME: tests keep timing out on some systems.
1470 ;; (zero? (system* "nosetests" "-v"
1471 ;; "--processes" "1"))
1474 `(("htslib" ,htslib))) ; Included from installed header files.
1476 `(("ncurses" ,ncurses)
1479 `(("python-cython" ,python-cython)
1480 ;; Dependencies below are are for tests only.
1481 ("samtools" ,samtools)
1482 ("bcftools" ,bcftools)
1483 ("python-nose" ,python-nose)))
1484 (home-page "https://github.com/pysam-developers/pysam")
1485 (synopsis "Python bindings to the SAMtools C API")
1487 "Pysam is a Python module for reading and manipulating files in the
1488 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1489 also includes an interface for tabix.")
1490 (license license:expat)))
1492 (define-public python2-pysam
1493 (package-with-python2 python-pysam))
1495 (define-public python-twobitreader
1497 (name "python-twobitreader")
1501 (uri (pypi-uri "twobitreader" version))
1504 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1505 (build-system python-build-system)
1507 '(;; Tests are not distributed in the PyPi release.
1508 ;; TODO Try building from the Git repo or asking the upstream maintainer
1509 ;; to distribute the tests on PyPi.
1512 `(("python-sphinx" ,python-sphinx)))
1513 (home-page "https://github.com/benjschiller/twobitreader")
1514 (synopsis "Python library for reading .2bit files")
1516 "twobitreader is a Python library for reading .2bit files as used by the
1517 UCSC genome browser.")
1518 (license license:artistic2.0)))
1520 (define-public python2-twobitreader
1521 (package-with-python2 python-twobitreader))
1523 (define-public python-plastid
1525 (name "python-plastid")
1529 (uri (pypi-uri "plastid" version))
1532 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1533 (build-system python-build-system)
1535 ;; Some test files are not included.
1538 `(("python-numpy" ,python-numpy)
1539 ("python-scipy" ,python-scipy)
1540 ("python-pandas" ,python-pandas)
1541 ("python-pysam" ,python-pysam)
1542 ("python-matplotlib" ,python-matplotlib)
1543 ("python-biopython" ,python-biopython)
1544 ("python-twobitreader" ,python-twobitreader)
1545 ("python-termcolor" ,python-termcolor)))
1547 `(("python-cython" ,python-cython)
1548 ("python-nose" ,python-nose)))
1549 (home-page "https://github.com/joshuagryphon/plastid")
1550 (synopsis "Python library for genomic analysis")
1552 "plastid is a Python library for genomic analysis – in particular,
1553 high-throughput sequencing data – with an emphasis on simplicity.")
1554 (license license:bsd-3)))
1556 (define-public python2-plastid
1557 (package-with-python2 python-plastid))
1559 (define-public cd-hit
1565 (uri (string-append "https://github.com/weizhongli/cdhit"
1566 "/releases/download/V" version
1568 "-2017-0621-source.tar.gz"))
1571 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1572 (build-system gnu-build-system)
1574 `(#:tests? #f ; there are no tests
1576 ;; Executables are copied directly to the PREFIX.
1577 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1579 (modify-phases %standard-phases
1580 ;; No "configure" script
1582 ;; Remove sources of non-determinism
1583 (add-after 'unpack 'be-timeless
1585 (substitute* "cdhit-utility.c++"
1586 ((" \\(built on \" __DATE__ \"\\)") ""))
1587 (substitute* "cdhit-common.c++"
1588 (("__DATE__") "\"0\"")
1589 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1591 ;; The "install" target does not create the target directory.
1592 (add-before 'install 'create-target-dir
1593 (lambda* (#:key outputs #:allow-other-keys)
1594 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1598 (home-page "http://weizhongli-lab.org/cd-hit/")
1599 (synopsis "Cluster and compare protein or nucleotide sequences")
1601 "CD-HIT is a program for clustering and comparing protein or nucleotide
1602 sequences. CD-HIT is designed to be fast and handle extremely large
1604 ;; The manual says: "It can be copied under the GNU General Public License
1605 ;; version 2 (GPLv2)."
1606 (license license:gpl2)))
1608 (define-public clipper
1615 "https://github.com/YeoLab/clipper/archive/"
1617 (file-name (string-append name "-" version ".tar.gz"))
1620 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1621 (modules '((guix build utils)))
1624 ;; remove unnecessary setup dependency
1625 (substitute* "setup.py"
1626 (("setup_requires = .*") ""))
1627 (for-each delete-file
1628 '("clipper/src/peaks.so"
1629 "clipper/src/readsToWiggle.so"))
1630 (delete-file-recursively "dist/")
1632 (build-system python-build-system)
1633 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1635 `(("htseq" ,python2-htseq)
1636 ("python-pybedtools" ,python2-pybedtools)
1637 ("python-cython" ,python2-cython)
1638 ("python-scikit-learn" ,python2-scikit-learn)
1639 ("python-matplotlib" ,python2-matplotlib)
1640 ("python-pandas" ,python2-pandas)
1641 ("python-pysam" ,python2-pysam)
1642 ("python-numpy" ,python2-numpy)
1643 ("python-scipy" ,python2-scipy)))
1645 `(("python-mock" ,python2-mock) ; for tests
1646 ("python-nose" ,python2-nose) ; for tests
1647 ("python-pytz" ,python2-pytz))) ; for tests
1648 (home-page "https://github.com/YeoLab/clipper")
1649 (synopsis "CLIP peak enrichment recognition")
1651 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1652 (license license:gpl2)))
1654 (define-public codingquarry
1656 (name "codingquarry")
1661 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1665 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1666 (build-system gnu-build-system)
1668 '(#:tests? #f ; no "check" target
1670 (modify-phases %standard-phases
1673 (lambda* (#:key outputs #:allow-other-keys)
1674 (let* ((out (assoc-ref outputs "out"))
1675 (bin (string-append out "/bin"))
1676 (doc (string-append out "/share/doc/codingquarry")))
1677 (install-file "INSTRUCTIONS.pdf" doc)
1678 (copy-recursively "QuarryFiles"
1679 (string-append out "/QuarryFiles"))
1680 (install-file "CodingQuarry" bin)
1681 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1682 (inputs `(("openmpi" ,openmpi)))
1683 (native-search-paths
1684 (list (search-path-specification
1685 (variable "QUARRY_PATH")
1686 (files '("QuarryFiles")))))
1687 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1688 (synopsis "Fungal gene predictor")
1689 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1690 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1691 (home-page "https://sourceforge.net/projects/codingquarry/")
1692 (license license:gpl3+)))
1694 (define-public couger
1701 "http://couger.oit.duke.edu/static/assets/COUGER"
1705 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1706 (build-system gnu-build-system)
1710 (modify-phases %standard-phases
1715 (lambda* (#:key outputs #:allow-other-keys)
1716 (let* ((out (assoc-ref outputs "out"))
1717 (bin (string-append out "/bin")))
1718 (copy-recursively "src" (string-append out "/src"))
1720 ;; Add "src" directory to module lookup path.
1721 (substitute* "couger"
1723 (string-append "import sys\nsys.path.append(\""
1724 out "\")\nfrom argparse")))
1725 (install-file "couger" bin))
1728 'install 'wrap-program
1729 (lambda* (#:key inputs outputs #:allow-other-keys)
1730 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1731 (let* ((out (assoc-ref outputs "out"))
1732 (path (getenv "PYTHONPATH")))
1733 (wrap-program (string-append out "/bin/couger")
1734 `("PYTHONPATH" ":" prefix (,path))))
1737 `(("python" ,python-2)
1738 ("python2-pillow" ,python2-pillow)
1739 ("python2-numpy" ,python2-numpy)
1740 ("python2-scipy" ,python2-scipy)
1741 ("python2-matplotlib" ,python2-matplotlib)))
1743 `(("r-minimal" ,r-minimal)
1745 ("randomjungle" ,randomjungle)))
1747 `(("unzip" ,unzip)))
1748 (home-page "http://couger.oit.duke.edu")
1749 (synopsis "Identify co-factors in sets of genomic regions")
1751 "COUGER can be applied to any two sets of genomic regions bound by
1752 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1753 putative co-factors that provide specificity to each TF. The framework
1754 determines the genomic targets uniquely-bound by each TF, and identifies a
1755 small set of co-factors that best explain the in vivo binding differences
1756 between the two TFs.
1758 COUGER uses classification algorithms (support vector machines and random
1759 forests) with features that reflect the DNA binding specificities of putative
1760 co-factors. The features are generated either from high-throughput TF-DNA
1761 binding data (from protein binding microarray experiments), or from large
1762 collections of DNA motifs.")
1763 (license license:gpl3+)))
1765 (define-public clustal-omega
1767 (name "clustal-omega")
1771 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1775 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1776 (build-system gnu-build-system)
1778 `(("argtable" ,argtable)))
1779 (home-page "http://www.clustal.org/omega/")
1780 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1782 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1783 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1784 of handling data-sets of hundreds of thousands of sequences in reasonable
1786 (license license:gpl2+)))
1788 (define-public crossmap
1794 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1798 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1799 ;; This patch has been sent upstream already and is available
1800 ;; for download from Sourceforge, but it has not been merged.
1801 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1802 (modules '((guix build utils)))
1803 ;; remove bundled copy of pysam
1805 '(delete-file-recursively "lib/pysam"))))
1806 (build-system python-build-system)
1808 `(#:python ,python-2
1810 (modify-phases %standard-phases
1811 (add-after 'unpack 'set-env
1812 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1814 `(("python-numpy" ,python2-numpy)
1815 ("python-pysam" ,python2-pysam)
1818 `(("python-cython" ,python2-cython)
1819 ("python-nose" ,python2-nose)))
1820 (home-page "http://crossmap.sourceforge.net/")
1821 (synopsis "Convert genome coordinates between assemblies")
1823 "CrossMap is a program for conversion of genome coordinates or annotation
1824 files between different genome assemblies. It supports most commonly used
1825 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1826 (license license:gpl2+)))
1828 (define-public cutadapt
1835 (url "https://github.com/marcelm/cutadapt.git")
1836 (commit (string-append "v" version))))
1837 (file-name (string-append name "-" version "-checkout"))
1840 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1841 (build-system python-build-system)
1843 `(("python-xopen" ,python-xopen)))
1845 `(("python-cython" ,python-cython)
1846 ("python-pytest" ,python-pytest)))
1847 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1848 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1850 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1851 other types of unwanted sequence from high-throughput sequencing reads.")
1852 (license license:expat)))
1854 (define-public libbigwig
1860 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1861 "archive/" version ".tar.gz"))
1862 (file-name (string-append name "-" version ".tar.gz"))
1865 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1866 (build-system gnu-build-system)
1868 `(#:test-target "test"
1871 (string-append "prefix=" (assoc-ref %outputs "out")))
1873 (modify-phases %standard-phases
1875 (add-before 'check 'disable-curl-test
1877 (substitute* "Makefile"
1878 (("./test/testRemote.*") ""))
1880 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1881 ;; there has not yet been a release containing this change.
1882 (add-before 'install 'create-target-dirs
1883 (lambda* (#:key outputs #:allow-other-keys)
1884 (let ((out (assoc-ref outputs "out")))
1885 (mkdir-p (string-append out "/lib"))
1886 (mkdir-p (string-append out "/include"))
1892 `(("doxygen" ,doxygen)))
1893 (home-page "https://github.com/dpryan79/libBigWig")
1894 (synopsis "C library for handling bigWig files")
1896 "This package provides a C library for parsing local and remote BigWig
1898 (license license:expat)))
1900 (define-public python-pybigwig
1902 (name "python-pybigwig")
1906 (uri (pypi-uri "pyBigWig" version))
1909 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1910 (modules '((guix build utils)))
1913 ;; Delete bundled libBigWig sources
1914 (delete-file-recursively "libBigWig")))))
1915 (build-system python-build-system)
1918 (modify-phases %standard-phases
1919 (add-after 'unpack 'link-with-libBigWig
1920 (lambda* (#:key inputs #:allow-other-keys)
1921 (substitute* "setup.py"
1922 (("libs=\\[") "libs=[\"BigWig\", "))
1925 `(("libbigwig" ,libbigwig)
1928 (home-page "https://github.com/dpryan79/pyBigWig")
1929 (synopsis "Access bigWig files in Python using libBigWig")
1931 "This package provides Python bindings to the libBigWig library for
1932 accessing bigWig files.")
1933 (license license:expat)))
1935 (define-public python2-pybigwig
1936 (package-with-python2 python-pybigwig))
1938 (define-public python-dendropy
1940 (name "python-dendropy")
1945 (uri (pypi-uri "DendroPy" version))
1948 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1949 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1950 (build-system python-build-system)
1951 (home-page "http://packages.python.org/DendroPy/")
1952 (synopsis "Library for phylogenetics and phylogenetic computing")
1954 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1955 writing, simulation, processing and manipulation of phylogenetic
1956 trees (phylogenies) and characters.")
1957 (license license:bsd-3)
1958 (properties `((python2-variant . ,(delay python2-dendropy))))))
1960 (define-public python2-dendropy
1961 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1965 `(#:python ,python-2
1967 (modify-phases %standard-phases
1969 ;; There is currently a test failure that only happens on some
1970 ;; systems, and only using "setup.py test"
1971 (lambda _ (zero? (system* "nosetests")))))))
1972 (native-inputs `(("python2-nose" ,python2-nose)
1973 ,@(package-native-inputs base))))))
1975 (define-public python-py2bit
1977 (name "python-py2bit")
1982 (uri (pypi-uri "py2bit" version))
1985 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
1986 (build-system python-build-system)
1987 (home-page "https://github.com/dpryan79/py2bit")
1988 (synopsis "Access 2bit files using lib2bit")
1990 "This package provides Python bindings for lib2bit to access 2bit files
1992 (license license:expat)))
1994 (define-public deeptools
2000 (uri (string-append "https://github.com/deeptools/deepTools/"
2001 "archive/" version ".tar.gz"))
2002 (file-name (string-append name "-" version ".tar.gz"))
2005 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2006 (build-system python-build-system)
2008 `(("python-scipy" ,python-scipy)
2009 ("python-numpy" ,python-numpy)
2010 ("python-numpydoc" ,python-numpydoc)
2011 ("python-matplotlib" ,python-matplotlib)
2012 ("python-pysam" ,python-pysam)
2013 ("python-py2bit" ,python-py2bit)
2014 ("python-pybigwig" ,python-pybigwig)))
2016 `(("python-mock" ,python-mock) ;for tests
2017 ("python-nose" ,python-nose) ;for tests
2018 ("python-pytz" ,python-pytz))) ;for tests
2019 (home-page "https://github.com/deeptools/deepTools")
2020 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2022 "DeepTools addresses the challenge of handling the large amounts of data
2023 that are now routinely generated from DNA sequencing centers. To do so,
2024 deepTools contains useful modules to process the mapped reads data to create
2025 coverage files in standard bedGraph and bigWig file formats. By doing so,
2026 deepTools allows the creation of normalized coverage files or the comparison
2027 between two files (for example, treatment and control). Finally, using such
2028 normalized and standardized files, multiple visualizations can be created to
2029 identify enrichments with functional annotations of the genome.")
2030 (license license:gpl3+)))
2032 (define-public delly
2039 "https://github.com/tobiasrausch/delly/archive/v"
2041 (file-name (string-append name "-" version ".tar.gz"))
2043 (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj"))
2044 (patches (search-patches "delly-use-system-libraries.patch"))))
2045 (build-system gnu-build-system)
2047 `(#:tests? #f ; There are no tests to run.
2048 #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time.
2050 (modify-phases %standard-phases
2051 (delete 'configure) ; There is no configure phase.
2054 (let ((bin (string-append (assoc-ref %outputs "out") "/bin"))
2055 (templates (string-append (assoc-ref %outputs "out")
2056 "/share/delly/templates")))
2059 (copy-recursively "excludeTemplates" templates)
2060 (install-file "src/cov" bin)
2061 (install-file "src/delly" bin)
2062 (install-file "src/dpe" bin)))))))
2064 `(("python" ,python-2)))
2070 (home-page "https://github.com/tobiasrausch/delly")
2071 (synopsis "Integrated structural variant prediction method")
2072 (description "Delly is an integrated structural variant prediction method
2073 that can discover and genotype deletions, tandem duplications, inversions and
2074 translocations at single-nucleotide resolution in short-read massively parallel
2075 sequencing data. It uses paired-ends and split-reads to sensitively and
2076 accurately delineate genomic rearrangements throughout the genome.")
2077 (license license:gpl3+)))
2079 (define-public diamond
2086 "https://github.com/bbuchfink/diamond/archive/v"
2088 (file-name (string-append name "-" version ".tar.gz"))
2091 "1cf98vcsiwcv3c4apg50w1240v1mpw0zln1sdw3g692dqa4y041z"))))
2092 (build-system cmake-build-system)
2094 '(#:tests? #f ; no "check" target
2096 (modify-phases %standard-phases
2097 (add-after 'unpack 'remove-native-compilation
2099 (substitute* "CMakeLists.txt" (("-march=native") ""))
2103 (home-page "https://github.com/bbuchfink/diamond")
2104 (synopsis "Accelerated BLAST compatible local sequence aligner")
2106 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2107 translated DNA query sequences against a protein reference database (BLASTP
2108 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2109 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2110 data and settings.")
2111 (license license:agpl3+)))
2113 (define-public discrover
2120 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2122 (file-name (string-append name "-" version ".tar.gz"))
2125 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2126 (build-system cmake-build-system)
2128 `(#:tests? #f ; there are no tests
2130 (modify-phases %standard-phases
2131 (add-after 'unpack 'add-missing-includes
2133 (substitute* "src/executioninformation.hpp"
2134 (("#define EXECUTIONINFORMATION_HPP" line)
2135 (string-append line "\n#include <random>")))
2136 (substitute* "src/plasma/fasta.hpp"
2137 (("#define FASTA_HPP" line)
2138 (string-append line "\n#include <random>")))
2144 `(("texlive" ,texlive)
2145 ("imagemagick" ,imagemagick)))
2146 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2147 (synopsis "Discover discriminative nucleotide sequence motifs")
2148 (description "Discrover is a motif discovery method to find binding sites
2149 of nucleic acid binding proteins.")
2150 (license license:gpl3+)))
2152 (define-public eigensoft
2153 (let ((revision "1")
2154 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2157 (version (string-append "6.1.2-"
2159 (string-take commit 9)))
2164 (url "https://github.com/DReichLab/EIG.git")
2166 (file-name (string-append "eigensoft-" commit "-checkout"))
2169 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2170 (modules '((guix build utils)))
2171 ;; Remove pre-built binaries.
2173 (delete-file-recursively "bin")
2176 (build-system gnu-build-system)
2178 `(#:tests? #f ; There are no tests.
2179 #:make-flags '("CC=gcc")
2181 (modify-phases %standard-phases
2182 ;; There is no configure phase, but the Makefile is in a
2187 ;; The link flags are incomplete.
2188 (substitute* "Makefile"
2189 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2191 ;; The provided install target only copies executables to
2192 ;; the "bin" directory in the build root.
2193 (add-after 'install 'actually-install
2194 (lambda* (#:key outputs #:allow-other-keys)
2195 (let* ((out (assoc-ref outputs "out"))
2196 (bin (string-append out "/bin")))
2197 (for-each (lambda (file)
2198 (install-file file bin))
2199 (find-files "../bin" ".*"))
2204 ("openblas" ,openblas)
2206 ("gfortran" ,gfortran "lib")))
2207 (home-page "https://github.com/DReichLab/EIG")
2208 (synopsis "Tools for population genetics")
2209 (description "The EIGENSOFT package provides tools for population
2210 genetics and stratification correction. EIGENSOFT implements methods commonly
2211 used in population genetics analyses such as PCA, computation of Tracy-Widom
2212 statistics, and finding related individuals in structured populations. It
2213 comes with a built-in plotting script and supports multiple file formats and
2214 quantitative phenotypes.")
2215 ;; The license of the eigensoft tools is Expat, but since it's
2216 ;; linking with the GNU Scientific Library (GSL) the effective
2217 ;; license is the GPL.
2218 (license license:gpl3+))))
2220 (define-public edirect
2226 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2227 "versions/2016-05-03/edirect.tar.gz"))
2230 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2231 (build-system perl-build-system)
2233 `(#:tests? #f ;no "check" target
2235 (modify-phases %standard-phases
2239 (lambda* (#:key outputs #:allow-other-keys)
2240 (let ((target (string-append (assoc-ref outputs "out")
2243 (install-file "edirect.pl" target)
2246 'install 'wrap-program
2247 (lambda* (#:key inputs outputs #:allow-other-keys)
2248 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2249 (let* ((out (assoc-ref outputs "out"))
2250 (path (getenv "PERL5LIB")))
2251 (wrap-program (string-append out "/bin/edirect.pl")
2252 `("PERL5LIB" ":" prefix (,path)))))))))
2254 `(("perl-html-parser" ,perl-html-parser)
2255 ("perl-encode-locale" ,perl-encode-locale)
2256 ("perl-file-listing" ,perl-file-listing)
2257 ("perl-html-tagset" ,perl-html-tagset)
2258 ("perl-html-tree" ,perl-html-tree)
2259 ("perl-http-cookies" ,perl-http-cookies)
2260 ("perl-http-date" ,perl-http-date)
2261 ("perl-http-message" ,perl-http-message)
2262 ("perl-http-negotiate" ,perl-http-negotiate)
2263 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2264 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2265 ("perl-net-http" ,perl-net-http)
2266 ("perl-uri" ,perl-uri)
2267 ("perl-www-robotrules" ,perl-www-robotrules)
2269 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2270 (synopsis "Tools for accessing the NCBI's set of databases")
2272 "Entrez Direct (EDirect) is a method for accessing the National Center
2273 for Biotechnology Information's (NCBI) set of interconnected
2274 databases (publication, sequence, structure, gene, variation, expression,
2275 etc.) from a terminal. Functions take search terms from command-line
2276 arguments. Individual operations are combined to build multi-step queries.
2277 Record retrieval and formatting normally complete the process.
2279 EDirect also provides an argument-driven function that simplifies the
2280 extraction of data from document summaries or other results that are returned
2281 in structured XML format. This can eliminate the need for writing custom
2282 software to answer ad hoc questions.")
2283 (license license:public-domain)))
2285 (define-public exonerate
2294 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2295 "exonerate-" version ".tar.gz"))
2298 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2299 (build-system gnu-build-system)
2301 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2303 `(("pkg-config" ,pkg-config)))
2307 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2308 (synopsis "Generic tool for biological sequence alignment")
2310 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2311 the alignment of sequences using a many alignment models, either exhaustive
2312 dynamic programming or a variety of heuristics.")
2313 (license license:gpl3)))
2315 (define-public express
2323 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2324 version "/express-" version "-src.tgz"))
2327 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2328 (build-system cmake-build-system)
2330 `(#:tests? #f ;no "check" target
2332 (modify-phases %standard-phases
2333 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2334 (lambda* (#:key inputs #:allow-other-keys)
2335 (substitute* "CMakeLists.txt"
2336 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2337 "set(Boost_USE_STATIC_LIBS OFF)")
2338 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2339 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2340 (substitute* "src/CMakeLists.txt"
2341 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2342 (string-append (assoc-ref inputs "bamtools") "/lib"))
2343 (("libprotobuf.a") "libprotobuf.so"))
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 "18bw0mn9pj5wgarnlaxmf1bb8pdqgl1zd6czirqcr62ajpn1xvy0"))))
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 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
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 "05myg7bs90i68qbqab9cdg9rqj2xh39azibrx82ipzc5kcfvqhn9"))))
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 "0yci4ymy4407kjh0lqp021nzccp6r31wgrkixkmix5p130cxvc56"))
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 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
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 "0pynr02d1xngda6c3va8fc4nxpgfkawhzcnz1ws4dnarp9b1w90r"))))
6094 (build-system r-build-system)
6096 `(("gfortran" ,gfortran)))
6098 `(("r-cluster" ,r-cluster)
6099 ("r-knitr" ,r-knitr)
6100 ("r-lattice" ,r-lattice)
6103 ("r-permute" ,r-permute)))
6104 (home-page "https://cran.r-project.org/web/packages/vegan")
6105 (synopsis "Functions for community ecology")
6107 "The vegan package provides tools for descriptive community ecology. It
6108 has most basic functions of diversity analysis, community ordination and
6109 dissimilarity analysis. Most of its multivariate tools can be used for other
6110 data types as well.")
6111 (license license:gpl2+)))
6113 (define-public r-annotate
6120 (uri (bioconductor-uri "annotate" version))
6123 "0ybg9k1s289h15nj1kp9821i1rsk1gkn8i8blplmk7gsgpbw1f42"))))
6124 (build-system r-build-system)
6126 `(("r-annotationdbi" ,r-annotationdbi)
6127 ("r-biobase" ,r-biobase)
6128 ("r-biocgenerics" ,r-biocgenerics)
6130 ("r-rcurl" ,r-rcurl)
6132 ("r-xtable" ,r-xtable)))
6134 "https://bioconductor.org/packages/annotate")
6135 (synopsis "Annotation for microarrays")
6136 (description "This package provides R environments for the annotation of
6138 (license license:artistic2.0)))
6140 (define-public r-copynumber
6142 (name "r-copynumber")
6146 (uri (bioconductor-uri "copynumber" version))
6149 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6150 (build-system r-build-system)
6152 `(("r-s4vectors" ,r-s4vectors)
6153 ("r-iranges" ,r-iranges)
6154 ("r-genomicranges" ,r-genomicranges)
6155 ("r-biocgenerics" ,r-biocgenerics)))
6156 (home-page "https://bioconductor.org/packages/copynumber")
6157 (synopsis "Segmentation of single- and multi-track copy number data")
6159 "This package segments single- and multi-track copy number data by a
6160 penalized least squares regression method.")
6161 (license license:artistic2.0)))
6163 (define-public r-geneplotter
6165 (name "r-geneplotter")
6170 (uri (bioconductor-uri "geneplotter" version))
6173 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6174 (build-system r-build-system)
6176 `(("r-annotate" ,r-annotate)
6177 ("r-annotationdbi" ,r-annotationdbi)
6178 ("r-biobase" ,r-biobase)
6179 ("r-biocgenerics" ,r-biocgenerics)
6180 ("r-lattice" ,r-lattice)
6181 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6182 (home-page "https://bioconductor.org/packages/geneplotter")
6183 (synopsis "Graphics functions for genomic data")
6185 "This package provides functions for plotting genomic data.")
6186 (license license:artistic2.0)))
6188 (define-public r-genefilter
6190 (name "r-genefilter")
6195 (uri (bioconductor-uri "genefilter" version))
6198 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6199 (build-system r-build-system)
6201 `(("gfortran" ,gfortran)))
6203 `(("r-annotate" ,r-annotate)
6204 ("r-annotationdbi" ,r-annotationdbi)
6205 ("r-biobase" ,r-biobase)
6206 ("r-s4vectors" ,r-s4vectors)
6207 ("r-survival" ,r-survival)))
6208 (home-page "https://bioconductor.org/packages/genefilter")
6209 (synopsis "Filter genes from high-throughput experiments")
6211 "This package provides basic functions for filtering genes from
6212 high-throughput sequencing experiments.")
6213 (license license:artistic2.0)))
6215 (define-public r-deseq2
6222 (uri (bioconductor-uri "DESeq2" version))
6225 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6226 (properties `((upstream-name . "DESeq2")))
6227 (build-system r-build-system)
6229 `(("r-biobase" ,r-biobase)
6230 ("r-biocgenerics" ,r-biocgenerics)
6231 ("r-biocparallel" ,r-biocparallel)
6232 ("r-genefilter" ,r-genefilter)
6233 ("r-geneplotter" ,r-geneplotter)
6234 ("r-genomicranges" ,r-genomicranges)
6235 ("r-ggplot2" ,r-ggplot2)
6236 ("r-hmisc" ,r-hmisc)
6237 ("r-iranges" ,r-iranges)
6238 ("r-locfit" ,r-locfit)
6240 ("r-rcpparmadillo" ,r-rcpparmadillo)
6241 ("r-s4vectors" ,r-s4vectors)
6242 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6243 (home-page "https://bioconductor.org/packages/DESeq2")
6244 (synopsis "Differential gene expression analysis")
6246 "This package provides functions to estimate variance-mean dependence in
6247 count data from high-throughput nucleotide sequencing assays and test for
6248 differential expression based on a model using the negative binomial
6250 (license license:lgpl3+)))
6252 (define-public r-dexseq
6259 (uri (bioconductor-uri "DEXSeq" version))
6262 "1a80yv742fx5c7qav7imsdybphf0d5bixsqyf8w5zng7fk8j16d5"))))
6263 (properties `((upstream-name . "DEXSeq")))
6264 (build-system r-build-system)
6266 `(("r-annotationdbi" ,r-annotationdbi)
6267 ("r-biobase" ,r-biobase)
6268 ("r-biocgenerics" ,r-biocgenerics)
6269 ("r-biocparallel" ,r-biocparallel)
6270 ("r-biomart" ,r-biomart)
6271 ("r-deseq2" ,r-deseq2)
6272 ("r-genefilter" ,r-genefilter)
6273 ("r-geneplotter" ,r-geneplotter)
6274 ("r-genomicranges" ,r-genomicranges)
6275 ("r-hwriter" ,r-hwriter)
6276 ("r-iranges" ,r-iranges)
6277 ("r-rcolorbrewer" ,r-rcolorbrewer)
6278 ("r-rsamtools" ,r-rsamtools)
6279 ("r-s4vectors" ,r-s4vectors)
6280 ("r-statmod" ,r-statmod)
6281 ("r-stringr" ,r-stringr)
6282 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6283 (home-page "https://bioconductor.org/packages/DEXSeq")
6284 (synopsis "Inference of differential exon usage in RNA-Seq")
6286 "This package is focused on finding differential exon usage using RNA-seq
6287 exon counts between samples with different experimental designs. It provides
6288 functions that allows the user to make the necessary statistical tests based
6289 on a model that uses the negative binomial distribution to estimate the
6290 variance between biological replicates and generalized linear models for
6291 testing. The package also provides functions for the visualization and
6292 exploration of the results.")
6293 (license license:gpl3+)))
6295 (define-public r-annotationforge
6297 (name "r-annotationforge")
6302 (uri (bioconductor-uri "AnnotationForge" version))
6305 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6307 `((upstream-name . "AnnotationForge")))
6308 (build-system r-build-system)
6310 `(("r-annotationdbi" ,r-annotationdbi)
6311 ("r-biobase" ,r-biobase)
6312 ("r-biocgenerics" ,r-biocgenerics)
6314 ("r-rcurl" ,r-rcurl)
6315 ("r-rsqlite" ,r-rsqlite)
6316 ("r-s4vectors" ,r-s4vectors)
6318 (home-page "https://bioconductor.org/packages/AnnotationForge")
6319 (synopsis "Code for building annotation database packages")
6321 "This package provides code for generating Annotation packages and their
6322 databases. Packages produced are intended to be used with AnnotationDbi.")
6323 (license license:artistic2.0)))
6325 (define-public r-rbgl
6332 (uri (bioconductor-uri "RBGL" version))
6335 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6336 (properties `((upstream-name . "RBGL")))
6337 (build-system r-build-system)
6338 (propagated-inputs `(("r-graph" ,r-graph)))
6339 (home-page "https://www.bioconductor.org/packages/RBGL")
6340 (synopsis "Interface to the Boost graph library")
6342 "This package provides a fairly extensive and comprehensive interface to
6343 the graph algorithms contained in the Boost library.")
6344 (license license:artistic2.0)))
6346 (define-public r-gseabase
6353 (uri (bioconductor-uri "GSEABase" version))
6356 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6357 (properties `((upstream-name . "GSEABase")))
6358 (build-system r-build-system)
6360 `(("r-annotate" ,r-annotate)
6361 ("r-annotationdbi" ,r-annotationdbi)
6362 ("r-biobase" ,r-biobase)
6363 ("r-biocgenerics" ,r-biocgenerics)
6364 ("r-graph" ,r-graph)
6366 (home-page "https://bioconductor.org/packages/GSEABase")
6367 (synopsis "Gene set enrichment data structures and methods")
6369 "This package provides classes and methods to support @dfn{Gene Set
6370 Enrichment Analysis} (GSEA).")
6371 (license license:artistic2.0)))
6373 (define-public r-category
6380 (uri (bioconductor-uri "Category" version))
6383 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6384 (properties `((upstream-name . "Category")))
6385 (build-system r-build-system)
6387 `(("r-annotate" ,r-annotate)
6388 ("r-annotationdbi" ,r-annotationdbi)
6389 ("r-biobase" ,r-biobase)
6390 ("r-biocgenerics" ,r-biocgenerics)
6391 ("r-genefilter" ,r-genefilter)
6392 ("r-graph" ,r-graph)
6393 ("r-gseabase" ,r-gseabase)
6394 ("r-matrix" ,r-matrix)
6397 (home-page "https://bioconductor.org/packages/Category")
6398 (synopsis "Category analysis")
6400 "This package provides a collection of tools for performing category
6402 (license license:artistic2.0)))
6404 (define-public r-gostats
6411 (uri (bioconductor-uri "GOstats" version))
6414 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6415 (properties `((upstream-name . "GOstats")))
6416 (build-system r-build-system)
6418 `(("r-annotate" ,r-annotate)
6419 ("r-annotationdbi" ,r-annotationdbi)
6420 ("r-annotationforge" ,r-annotationforge)
6421 ("r-biobase" ,r-biobase)
6422 ("r-category" ,r-category)
6423 ("r-go-db" ,r-go-db)
6424 ("r-graph" ,r-graph)
6425 ("r-rgraphviz" ,r-rgraphviz)
6426 ("r-rbgl" ,r-rbgl)))
6427 (home-page "https://bioconductor.org/packages/GOstats")
6428 (synopsis "Tools for manipulating GO and microarrays")
6430 "This package provides a set of tools for interacting with GO and
6431 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6432 testing and other simple calculations.")
6433 (license license:artistic2.0)))
6435 (define-public r-shortread
6437 (name "r-shortread")
6442 (uri (bioconductor-uri "ShortRead" version))
6445 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6446 (properties `((upstream-name . "ShortRead")))
6447 (build-system r-build-system)
6451 `(("r-biobase" ,r-biobase)
6452 ("r-biocgenerics" ,r-biocgenerics)
6453 ("r-biocparallel" ,r-biocparallel)
6454 ("r-biostrings" ,r-biostrings)
6455 ("r-genomeinfodb" ,r-genomeinfodb)
6456 ("r-genomicalignments" ,r-genomicalignments)
6457 ("r-genomicranges" ,r-genomicranges)
6458 ("r-hwriter" ,r-hwriter)
6459 ("r-iranges" ,r-iranges)
6460 ("r-lattice" ,r-lattice)
6461 ("r-latticeextra" ,r-latticeextra)
6462 ("r-rsamtools" ,r-rsamtools)
6463 ("r-s4vectors" ,r-s4vectors)
6464 ("r-xvector" ,r-xvector)
6465 ("r-zlibbioc" ,r-zlibbioc)))
6466 (home-page "https://bioconductor.org/packages/ShortRead")
6467 (synopsis "FASTQ input and manipulation tools")
6469 "This package implements sampling, iteration, and input of FASTQ files.
6470 It includes functions for filtering and trimming reads, and for generating a
6471 quality assessment report. Data are represented as
6472 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6473 purposes. The package also contains legacy support for early single-end,
6474 ungapped alignment formats.")
6475 (license license:artistic2.0)))
6477 (define-public r-systempiper
6479 (name "r-systempiper")
6484 (uri (bioconductor-uri "systemPipeR" version))
6487 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6488 (properties `((upstream-name . "systemPipeR")))
6489 (build-system r-build-system)
6491 `(("r-annotate" ,r-annotate)
6492 ("r-batchjobs" ,r-batchjobs)
6493 ("r-biocgenerics" ,r-biocgenerics)
6494 ("r-biostrings" ,r-biostrings)
6495 ("r-deseq2" ,r-deseq2)
6496 ("r-edger" ,r-edger)
6497 ("r-genomicfeatures" ,r-genomicfeatures)
6498 ("r-genomicranges" ,r-genomicranges)
6499 ("r-ggplot2" ,r-ggplot2)
6500 ("r-go-db" ,r-go-db)
6501 ("r-gostats" ,r-gostats)
6502 ("r-limma" ,r-limma)
6503 ("r-pheatmap" ,r-pheatmap)
6504 ("r-rjson" ,r-rjson)
6505 ("r-rsamtools" ,r-rsamtools)
6506 ("r-shortread" ,r-shortread)
6507 ("r-summarizedexperiment" ,r-summarizedexperiment)
6508 ("r-variantannotation" ,r-variantannotation)))
6509 (home-page "https://github.com/tgirke/systemPipeR")
6510 (synopsis "Next generation sequencing workflow and reporting environment")
6512 "This R package provides tools for building and running automated
6513 end-to-end analysis workflows for a wide range of @dfn{next generation
6514 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6515 Important features include a uniform workflow interface across different NGS
6516 applications, automated report generation, and support for running both R and
6517 command-line software, such as NGS aligners or peak/variant callers, on local
6518 computers or compute clusters. Efficient handling of complex sample sets and
6519 experimental designs is facilitated by a consistently implemented sample
6520 annotation infrastructure.")
6521 (license license:artistic2.0)))
6523 (define-public r-grohmm
6530 (uri (bioconductor-uri "groHMM" version))
6533 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6534 (properties `((upstream-name . "groHMM")))
6535 (build-system r-build-system)
6537 `(("r-genomeinfodb" ,r-genomeinfodb)
6538 ("r-genomicalignments" ,r-genomicalignments)
6539 ("r-genomicranges" ,r-genomicranges)
6540 ("r-iranges" ,r-iranges)
6542 ("r-rtracklayer" ,r-rtracklayer)
6543 ("r-s4vectors" ,r-s4vectors)))
6544 (home-page "https://github.com/Kraus-Lab/groHMM")
6545 (synopsis "GRO-seq analysis pipeline")
6547 "This package provides a pipeline for the analysis of GRO-seq data.")
6548 (license license:gpl3+)))
6550 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6552 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6556 ;; We cannot use bioconductor-uri here because this tarball is
6557 ;; located under "data/annotation/" instead of "bioc/".
6558 (uri (string-append "https://bioconductor.org/packages/"
6559 "release/data/annotation/src/contrib"
6560 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6564 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6566 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6567 (build-system r-build-system)
6568 ;; As this package provides little more than a very large data file it
6569 ;; doesn't make sense to build substitutes.
6570 (arguments `(#:substitutable? #f))
6572 `(("r-genomicfeatures" ,r-genomicfeatures)))
6574 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6575 (synopsis "Annotation package for human genome in TxDb format")
6577 "This package provides an annotation database of Homo sapiens genome
6578 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6579 track. The database is exposed as a @code{TxDb} object.")
6580 (license license:artistic2.0)))
6582 (define-public r-sparql
6588 (uri (cran-uri "SPARQL" version))
6591 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6592 (properties `((upstream-name . "SPARQL")))
6593 (build-system r-build-system)
6595 `(("r-rcurl" ,r-rcurl)
6597 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6598 (synopsis "SPARQL client for R")
6599 (description "This package provides an interface to use SPARQL to pose
6600 SELECT or UPDATE queries to an end-point.")
6601 ;; The only license indication is found in the DESCRIPTION file,
6602 ;; which states GPL-3. So we cannot assume GPLv3+.
6603 (license license:gpl3)))
6605 (define-public vsearch
6613 "https://github.com/torognes/vsearch/archive/v"
6615 (file-name (string-append name "-" version ".tar.gz"))
6618 "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3"))
6619 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6622 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6623 ;; for this in the patch.
6624 (delete-file "src/city.h")
6625 (delete-file "src/citycrc.h")
6626 (delete-file "src/city.cc")
6628 (build-system gnu-build-system)
6631 (modify-phases %standard-phases
6632 (add-after 'unpack 'autogen
6633 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6637 ("cityhash" ,cityhash)))
6639 `(("autoconf" ,autoconf)
6640 ("automake" ,automake)))
6641 (synopsis "Sequence search tools for metagenomics")
6643 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6644 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6645 masking. The tool takes advantage of parallelism in the form of SIMD
6646 vectorization as well as multiple threads to perform accurate alignments at
6647 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6648 Needleman-Wunsch).")
6649 (home-page "https://github.com/torognes/vsearch")
6650 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6652 (supported-systems '("x86_64-linux"))
6653 ;; Dual licensed; also includes public domain source.
6654 (license (list license:gpl3 license:bsd-2))))
6656 (define-public pardre
6659 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6664 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6668 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6669 (build-system gnu-build-system)
6671 `(#:tests? #f ; no tests included
6673 (modify-phases %standard-phases
6676 (lambda* (#:key outputs #:allow-other-keys)
6677 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6678 (install-file "ParDRe" bin)
6681 `(("openmpi" ,openmpi)
6683 (synopsis "Parallel tool to remove duplicate DNA reads")
6685 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6686 Duplicate reads can be seen as identical or nearly identical sequences with
6687 some mismatches. This tool lets users avoid the analysis of unnecessary
6688 reads, reducing the time of subsequent procedures with the
6689 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6690 in order to exploit the parallel capabilities of multicore clusters. It is
6691 faster than multithreaded counterparts (end of 2015) for the same number of
6692 cores and, thanks to the message-passing technology, it can be executed on
6694 (home-page "https://sourceforge.net/projects/pardre/")
6695 (license license:gpl3+)))
6697 (define-public ruby-bio-kseq
6699 (name "ruby-bio-kseq")
6704 (uri (rubygems-uri "bio-kseq" version))
6707 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6708 (build-system ruby-build-system)
6710 `(#:test-target "spec"))
6712 `(("bundler" ,bundler)
6713 ("ruby-rspec" ,ruby-rspec)
6714 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6717 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6719 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6720 FASTQ parsing code. It provides a fast iterator over sequences and their
6722 (home-page "https://github.com/gusevfe/bio-kseq")
6723 (license license:expat)))
6725 (define-public bio-locus
6732 (uri (rubygems-uri "bio-locus" version))
6735 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6736 (build-system ruby-build-system)
6738 `(("ruby-rspec" ,ruby-rspec)))
6739 (synopsis "Tool for fast querying of genome locations")
6741 "Bio-locus is a tabix-like tool for fast querying of genome
6742 locations. Many file formats in bioinformatics contain records that
6743 start with a chromosome name and a position for a SNP, or a start-end
6744 position for indels. Bio-locus allows users to store this chr+pos or
6745 chr+pos+alt information in a database.")
6746 (home-page "https://github.com/pjotrp/bio-locus")
6747 (license license:expat)))
6749 (define-public bio-blastxmlparser
6751 (name "bio-blastxmlparser")
6755 (uri (rubygems-uri "bio-blastxmlparser" version))
6758 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6759 (build-system ruby-build-system)
6761 `(("ruby-bio-logger" ,ruby-bio-logger)
6762 ("ruby-nokogiri" ,ruby-nokogiri)))
6764 `(("ruby-rspec" ,ruby-rspec)))
6765 (synopsis "Fast big data BLAST XML parser and library")
6767 "Very fast parallel big-data BLAST XML file parser which can be used as
6768 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6769 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6770 (home-page "https://github.com/pjotrp/blastxmlparser")
6771 (license license:expat)))
6773 (define-public bioruby
6780 (uri (rubygems-uri "bio" version))
6783 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6784 (build-system ruby-build-system)
6786 `(("ruby-libxml" ,ruby-libxml)))
6788 `(("which" ,which))) ; required for test phase
6791 (modify-phases %standard-phases
6792 (add-before 'build 'patch-test-command
6794 (substitute* '("test/functional/bio/test_command.rb")
6795 (("/bin/sh") (which "sh")))
6796 (substitute* '("test/functional/bio/test_command.rb")
6797 (("/bin/ls") (which "ls")))
6798 (substitute* '("test/functional/bio/test_command.rb")
6799 (("which") (which "which")))
6800 (substitute* '("test/functional/bio/test_command.rb",
6801 "test/data/command/echoarg2.sh")
6802 (("/bin/echo") (which "echo")))
6804 (synopsis "Ruby library, shell and utilities for bioinformatics")
6805 (description "BioRuby comes with a comprehensive set of Ruby development
6806 tools and libraries for bioinformatics and molecular biology. BioRuby has
6807 components for sequence analysis, pathway analysis, protein modelling and
6808 phylogenetic analysis; it supports many widely used data formats and provides
6809 easy access to databases, external programs and public web services, including
6810 BLAST, KEGG, GenBank, MEDLINE and GO.")
6811 (home-page "http://bioruby.org/")
6812 ;; Code is released under Ruby license, except for setup
6813 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6814 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6816 (define-public r-acsnminer
6818 (name "r-acsnminer")
6819 (version "0.16.8.25")
6822 (uri (cran-uri "ACSNMineR" version))
6825 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6826 (properties `((upstream-name . "ACSNMineR")))
6827 (build-system r-build-system)
6829 `(("r-ggplot2" ,r-ggplot2)
6830 ("r-gridextra" ,r-gridextra)))
6831 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6832 (synopsis "Gene enrichment analysis")
6834 "This package provides tools to compute and represent gene set enrichment
6835 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6836 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6837 enrichment can be run with hypergeometric test or Fisher exact test, and can
6838 use multiple corrections. Visualization of data can be done either by
6839 barplots or heatmaps.")
6840 (license license:gpl2+)))
6842 (define-public r-biocgenerics
6844 (name "r-biocgenerics")
6848 (uri (bioconductor-uri "BiocGenerics" version))
6851 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6853 `((upstream-name . "BiocGenerics")))
6854 (build-system r-build-system)
6855 (home-page "https://bioconductor.org/packages/BiocGenerics")
6856 (synopsis "S4 generic functions for Bioconductor")
6858 "This package provides S4 generic functions needed by many Bioconductor
6860 (license license:artistic2.0)))
6862 (define-public r-biocinstaller
6864 (name "r-biocinstaller")
6868 (uri (bioconductor-uri "BiocInstaller" version))
6871 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6873 `((upstream-name . "BiocInstaller")))
6874 (build-system r-build-system)
6875 (home-page "https://bioconductor.org/packages/BiocInstaller")
6876 (synopsis "Install Bioconductor packages")
6877 (description "This package is used to install and update R packages from
6878 Bioconductor, CRAN, and Github.")
6879 (license license:artistic2.0)))
6881 (define-public r-biocviews
6883 (name "r-biocviews")
6887 (uri (bioconductor-uri "biocViews" version))
6890 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6892 `((upstream-name . "biocViews")))
6893 (build-system r-build-system)
6895 `(("r-biobase" ,r-biobase)
6896 ("r-graph" ,r-graph)
6898 ("r-rcurl" ,r-rcurl)
6900 ("r-runit" ,r-runit)))
6901 (home-page "https://bioconductor.org/packages/biocViews")
6902 (synopsis "Bioconductor package categorization helper")
6903 (description "The purpose of biocViews is to create HTML pages that
6904 categorize packages in a Bioconductor package repository according to keywords,
6905 also known as views, in a controlled vocabulary.")
6906 (license license:artistic2.0)))
6908 (define-public r-bookdown
6914 (uri (cran-uri "bookdown" version))
6917 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6918 (build-system r-build-system)
6920 `(("r-htmltools" ,r-htmltools)
6921 ("r-knitr" ,r-knitr)
6922 ("r-rmarkdown" ,r-rmarkdown)
6923 ("r-tinytex" ,r-tinytex)
6925 ("r-xfun" ,r-xfun)))
6926 (home-page "https://github.com/rstudio/bookdown")
6927 (synopsis "Authoring books and technical documents with R markdown")
6928 (description "This package provides output formats and utilities for
6929 authoring books and technical documents with R Markdown.")
6930 (license license:gpl3)))
6932 (define-public r-biocstyle
6934 (name "r-biocstyle")
6938 (uri (bioconductor-uri "BiocStyle" version))
6941 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6943 `((upstream-name . "BiocStyle")))
6944 (build-system r-build-system)
6946 `(("r-bookdown" ,r-bookdown)
6947 ("r-knitr" ,r-knitr)
6948 ("r-rmarkdown" ,r-rmarkdown)
6949 ("r-yaml" ,r-yaml)))
6950 (home-page "https://bioconductor.org/packages/BiocStyle")
6951 (synopsis "Bioconductor formatting styles")
6952 (description "This package provides standard formatting styles for
6953 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6955 (license license:artistic2.0)))
6957 (define-public r-bioccheck
6959 (name "r-bioccheck")
6963 (uri (bioconductor-uri "BiocCheck" version))
6966 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6968 `((upstream-name . "BiocCheck")))
6969 (build-system r-build-system)
6972 (modify-phases %standard-phases
6973 ;; This package can be used by calling BiocCheck(<package>) from
6974 ;; within R, or by running R CMD BiocCheck <package>. This phase
6975 ;; makes sure the latter works. For this to work, the BiocCheck
6976 ;; script must be somewhere on the PATH (not the R bin directory).
6977 (add-after 'install 'install-bioccheck-subcommand
6978 (lambda* (#:key outputs #:allow-other-keys)
6979 (let* ((out (assoc-ref outputs "out"))
6980 (dest-dir (string-append out "/bin"))
6982 (string-append out "/site-library/BiocCheck/script/")))
6984 (symlink (string-append script-dir "/checkBadDeps.R")
6985 (string-append dest-dir "/checkBadDeps.R"))
6986 (symlink (string-append script-dir "/BiocCheck")
6987 (string-append dest-dir "/BiocCheck")))
6990 `(("r-codetools" ,r-codetools)
6991 ("r-graph" ,r-graph)
6993 ("r-optparse" ,r-optparse)
6994 ("r-biocinstaller" ,r-biocinstaller)
6995 ("r-biocviews" ,r-biocviews)
6996 ("r-stringdist" ,r-stringdist)))
6997 (home-page "https://bioconductor.org/packages/BiocCheck")
6998 (synopsis "Executes Bioconductor-specific package checks")
6999 (description "This package contains tools to perform additional quality
7000 checks on R packages that are to be submitted to the Bioconductor repository.")
7001 (license license:artistic2.0)))
7003 (define-public r-getopt
7010 (uri (cran-uri "getopt" version))
7013 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
7014 (build-system r-build-system)
7015 (home-page "https://github.com/trevorld/getopt")
7016 (synopsis "Command-line option processor for R")
7018 "This package is designed to be used with Rscript to write shebang
7019 scripts that accept short and long options. Many users will prefer to
7020 use the packages @code{optparse} or @code{argparse} which add extra
7021 features like automatically generated help options and usage texts,
7022 support for default values, positional argument support, etc.")
7023 (license license:gpl2+)))
7025 (define-public r-optparse
7032 (uri (cran-uri "optparse" version))
7035 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
7036 (build-system r-build-system)
7038 `(("r-getopt" ,r-getopt)))
7040 "https://github.com/trevorld/optparse")
7041 (synopsis "Command line option parser")
7043 "This package provides a command line parser inspired by Python's
7044 @code{optparse} library to be used with Rscript to write shebang scripts
7045 that accept short and long options.")
7046 (license license:gpl2+)))
7048 (define-public r-dnacopy
7054 (uri (bioconductor-uri "DNAcopy" version))
7057 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
7059 `((upstream-name . "DNAcopy")))
7060 (build-system r-build-system)
7062 `(("gfortran" ,gfortran)))
7063 (home-page "https://bioconductor.org/packages/DNAcopy")
7064 (synopsis "Implementation of a circular binary segmentation algorithm")
7065 (description "This package implements the circular binary segmentation (CBS)
7066 algorithm to segment DNA copy number data and identify genomic regions with
7067 abnormal copy number.")
7068 (license license:gpl2+)))
7070 (define-public r-s4vectors
7072 (name "r-s4vectors")
7076 (uri (bioconductor-uri "S4Vectors" version))
7079 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7081 `((upstream-name . "S4Vectors")))
7082 (build-system r-build-system)
7084 `(("r-biocgenerics" ,r-biocgenerics)))
7085 (home-page "https://bioconductor.org/packages/S4Vectors")
7086 (synopsis "S4 implementation of vectors and lists")
7088 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7089 classes and a set of generic functions that extend the semantic of ordinary
7090 vectors and lists in R. Package developers can easily implement vector-like
7091 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7092 In addition, a few low-level concrete subclasses of general interest (e.g.
7093 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7094 S4Vectors package itself.")
7095 (license license:artistic2.0)))
7097 (define-public r-seqinr
7104 (uri (cran-uri "seqinr" version))
7107 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7108 (build-system r-build-system)
7110 `(("r-ade4" ,r-ade4)
7111 ("r-segmented" ,r-segmented)))
7114 (home-page "http://seqinr.r-forge.r-project.org/")
7115 (synopsis "Biological sequences retrieval and analysis")
7117 "This package provides tools for exploratory data analysis and data
7118 visualization of biological sequence (DNA and protein) data. It also includes
7119 utilities for sequence data management under the ACNUC system.")
7120 (license license:gpl2+)))
7122 (define-public r-iranges
7128 (uri (bioconductor-uri "IRanges" version))
7131 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7133 `((upstream-name . "IRanges")))
7134 (build-system r-build-system)
7136 `(("r-biocgenerics" ,r-biocgenerics)
7137 ("r-s4vectors" ,r-s4vectors)))
7138 (home-page "https://bioconductor.org/packages/IRanges")
7139 (synopsis "Infrastructure for manipulating intervals on sequences")
7141 "This package provides efficient low-level and highly reusable S4 classes
7142 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7143 generally, data that can be organized sequentially (formally defined as
7144 @code{Vector} objects), as well as views on these @code{Vector} objects.
7145 Efficient list-like classes are also provided for storing big collections of
7146 instances of the basic classes. All classes in the package use consistent
7147 naming and share the same rich and consistent \"Vector API\" as much as
7149 (license license:artistic2.0)))
7151 (define-public r-genomeinfodbdata
7153 (name "r-genomeinfodbdata")
7157 ;; We cannot use bioconductor-uri here because this tarball is
7158 ;; located under "data/annotation/" instead of "bioc/".
7159 (uri (string-append "https://bioconductor.org/packages/release/"
7160 "data/annotation/src/contrib/GenomeInfoDbData_"
7164 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7166 `((upstream-name . "GenomeInfoDbData")))
7167 (build-system r-build-system)
7168 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7169 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7170 (description "This package contains data for mapping between NCBI taxonomy
7171 ID and species. It is used by functions in the GenomeInfoDb package.")
7172 (license license:artistic2.0)))
7174 (define-public r-genomeinfodb
7176 (name "r-genomeinfodb")
7180 (uri (bioconductor-uri "GenomeInfoDb" version))
7183 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7185 `((upstream-name . "GenomeInfoDb")))
7186 (build-system r-build-system)
7188 `(("r-biocgenerics" ,r-biocgenerics)
7189 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7190 ("r-iranges" ,r-iranges)
7191 ("r-rcurl" ,r-rcurl)
7192 ("r-s4vectors" ,r-s4vectors)))
7193 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7194 (synopsis "Utilities for manipulating chromosome identifiers")
7196 "This package contains data and functions that define and allow
7197 translation between different chromosome sequence naming conventions (e.g.,
7198 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7199 names in their natural, rather than lexicographic, order.")
7200 (license license:artistic2.0)))
7202 (define-public r-edger
7208 (uri (bioconductor-uri "edgeR" version))
7211 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7212 (properties `((upstream-name . "edgeR")))
7213 (build-system r-build-system)
7215 `(("r-limma" ,r-limma)
7216 ("r-locfit" ,r-locfit)
7218 ("r-statmod" ,r-statmod))) ;for estimateDisp
7219 (home-page "http://bioinf.wehi.edu.au/edgeR")
7220 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7221 (description "This package can do differential expression analysis of
7222 RNA-seq expression profiles with biological replication. It implements a range
7223 of statistical methodology based on the negative binomial distributions,
7224 including empirical Bayes estimation, exact tests, generalized linear models
7225 and quasi-likelihood tests. It be applied to differential signal analysis of
7226 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7228 (license license:gpl2+)))
7230 (define-public r-variantannotation
7232 (name "r-variantannotation")
7236 (uri (bioconductor-uri "VariantAnnotation" version))
7239 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7241 `((upstream-name . "VariantAnnotation")))
7245 `(("r-annotationdbi" ,r-annotationdbi)
7246 ("r-biobase" ,r-biobase)
7247 ("r-biocgenerics" ,r-biocgenerics)
7248 ("r-biostrings" ,r-biostrings)
7249 ("r-bsgenome" ,r-bsgenome)
7251 ("r-genomeinfodb" ,r-genomeinfodb)
7252 ("r-genomicfeatures" ,r-genomicfeatures)
7253 ("r-genomicranges" ,r-genomicranges)
7254 ("r-iranges" ,r-iranges)
7255 ("r-summarizedexperiment" ,r-summarizedexperiment)
7256 ("r-rsamtools" ,r-rsamtools)
7257 ("r-rtracklayer" ,r-rtracklayer)
7258 ("r-s4vectors" ,r-s4vectors)
7259 ("r-xvector" ,r-xvector)
7260 ("r-zlibbioc" ,r-zlibbioc)))
7261 (build-system r-build-system)
7262 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7263 (synopsis "Package for annotation of genetic variants")
7264 (description "This R package can annotate variants, compute amino acid
7265 coding changes and predict coding outcomes.")
7266 (license license:artistic2.0)))
7268 (define-public r-limma
7274 (uri (bioconductor-uri "limma" version))
7277 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7278 (build-system r-build-system)
7279 (home-page "http://bioinf.wehi.edu.au/limma")
7280 (synopsis "Package for linear models for microarray and RNA-seq data")
7281 (description "This package can be used for the analysis of gene expression
7282 studies, especially the use of linear models for analysing designed experiments
7283 and the assessment of differential expression. The analysis methods apply to
7284 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7285 (license license:gpl2+)))
7287 (define-public r-xvector
7293 (uri (bioconductor-uri "XVector" version))
7296 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7298 `((upstream-name . "XVector")))
7299 (build-system r-build-system)
7302 (modify-phases %standard-phases
7303 (add-after 'unpack 'use-system-zlib
7305 (substitute* "DESCRIPTION"
7306 (("zlibbioc, ") ""))
7307 (substitute* "NAMESPACE"
7308 (("import\\(zlibbioc\\)") ""))
7313 `(("r-biocgenerics" ,r-biocgenerics)
7314 ("r-iranges" ,r-iranges)
7315 ("r-s4vectors" ,r-s4vectors)))
7316 (home-page "https://bioconductor.org/packages/XVector")
7317 (synopsis "Representation and manpulation of external sequences")
7319 "This package provides memory efficient S4 classes for storing sequences
7320 \"externally\" (behind an R external pointer, or on disk).")
7321 (license license:artistic2.0)))
7323 (define-public r-genomicranges
7325 (name "r-genomicranges")
7329 (uri (bioconductor-uri "GenomicRanges" version))
7332 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7334 `((upstream-name . "GenomicRanges")))
7335 (build-system r-build-system)
7337 `(("r-biocgenerics" ,r-biocgenerics)
7338 ("r-genomeinfodb" ,r-genomeinfodb)
7339 ("r-iranges" ,r-iranges)
7340 ("r-s4vectors" ,r-s4vectors)
7341 ("r-xvector" ,r-xvector)))
7342 (home-page "https://bioconductor.org/packages/GenomicRanges")
7343 (synopsis "Representation and manipulation of genomic intervals")
7345 "This package provides tools to efficiently represent and manipulate
7346 genomic annotations and alignments is playing a central role when it comes to
7347 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7348 GenomicRanges package defines general purpose containers for storing and
7349 manipulating genomic intervals and variables defined along a genome.")
7350 (license license:artistic2.0)))
7352 (define-public r-biobase
7358 (uri (bioconductor-uri "Biobase" version))
7361 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7363 `((upstream-name . "Biobase")))
7364 (build-system r-build-system)
7366 `(("r-biocgenerics" ,r-biocgenerics)))
7367 (home-page "https://bioconductor.org/packages/Biobase")
7368 (synopsis "Base functions for Bioconductor")
7370 "This package provides functions that are needed by many other packages
7371 on Bioconductor or which replace R functions.")
7372 (license license:artistic2.0)))
7374 (define-public r-annotationdbi
7376 (name "r-annotationdbi")
7380 (uri (bioconductor-uri "AnnotationDbi" version))
7383 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7385 `((upstream-name . "AnnotationDbi")))
7386 (build-system r-build-system)
7388 `(("r-biobase" ,r-biobase)
7389 ("r-biocgenerics" ,r-biocgenerics)
7391 ("r-iranges" ,r-iranges)
7392 ("r-rsqlite" ,r-rsqlite)
7393 ("r-s4vectors" ,r-s4vectors)))
7394 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7395 (synopsis "Annotation database interface")
7397 "This package provides user interface and database connection code for
7398 annotation data packages using SQLite data storage.")
7399 (license license:artistic2.0)))
7401 (define-public r-biomart
7407 (uri (bioconductor-uri "biomaRt" version))
7410 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7412 `((upstream-name . "biomaRt")))
7413 (build-system r-build-system)
7415 `(("r-annotationdbi" ,r-annotationdbi)
7417 ("r-progress" ,r-progress)
7418 ("r-rcurl" ,r-rcurl)
7419 ("r-stringr" ,r-stringr)
7421 (home-page "https://bioconductor.org/packages/biomaRt")
7422 (synopsis "Interface to BioMart databases")
7424 "biomaRt provides an interface to a growing collection of databases
7425 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7426 package enables retrieval of large amounts of data in a uniform way without
7427 the need to know the underlying database schemas or write complex SQL queries.
7428 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7429 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7430 users direct access to a diverse set of data and enable a wide range of
7431 powerful online queries from gene annotation to database mining.")
7432 (license license:artistic2.0)))
7434 (define-public r-biocparallel
7436 (name "r-biocparallel")
7440 (uri (bioconductor-uri "BiocParallel" version))
7443 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7445 `((upstream-name . "BiocParallel")))
7446 (build-system r-build-system)
7448 `(("r-futile-logger" ,r-futile-logger)
7451 (home-page "https://bioconductor.org/packages/BiocParallel")
7452 (synopsis "Bioconductor facilities for parallel evaluation")
7454 "This package provides modified versions and novel implementation of
7455 functions for parallel evaluation, tailored to use with Bioconductor
7457 (license (list license:gpl2+ license:gpl3+))))
7459 (define-public r-biostrings
7461 (name "r-biostrings")
7465 (uri (bioconductor-uri "Biostrings" version))
7468 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7470 `((upstream-name . "Biostrings")))
7471 (build-system r-build-system)
7473 `(("r-biocgenerics" ,r-biocgenerics)
7474 ("r-iranges" ,r-iranges)
7475 ("r-s4vectors" ,r-s4vectors)
7476 ("r-xvector" ,r-xvector)))
7477 (home-page "https://bioconductor.org/packages/Biostrings")
7478 (synopsis "String objects and algorithms for biological sequences")
7480 "This package provides memory efficient string containers, string
7481 matching algorithms, and other utilities, for fast manipulation of large
7482 biological sequences or sets of sequences.")
7483 (license license:artistic2.0)))
7485 (define-public r-rsamtools
7487 (name "r-rsamtools")
7491 (uri (bioconductor-uri "Rsamtools" version))
7494 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7496 `((upstream-name . "Rsamtools")))
7497 (build-system r-build-system)
7500 (modify-phases %standard-phases
7501 (add-after 'unpack 'use-system-zlib
7503 (substitute* "DESCRIPTION"
7504 (("zlibbioc, ") ""))
7505 (substitute* "NAMESPACE"
7506 (("import\\(zlibbioc\\)") ""))
7511 `(("r-biocgenerics" ,r-biocgenerics)
7512 ("r-biocparallel" ,r-biocparallel)
7513 ("r-biostrings" ,r-biostrings)
7514 ("r-bitops" ,r-bitops)
7515 ("r-genomeinfodb" ,r-genomeinfodb)
7516 ("r-genomicranges" ,r-genomicranges)
7517 ("r-iranges" ,r-iranges)
7518 ("r-s4vectors" ,r-s4vectors)
7519 ("r-xvector" ,r-xvector)))
7520 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7521 (synopsis "Interface to samtools, bcftools, and tabix")
7523 "This package provides an interface to the 'samtools', 'bcftools', and
7524 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7525 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7527 (license license:expat)))
7529 (define-public r-delayedarray
7531 (name "r-delayedarray")
7535 (uri (bioconductor-uri "DelayedArray" version))
7538 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7540 `((upstream-name . "DelayedArray")))
7541 (build-system r-build-system)
7543 `(("r-biocgenerics" ,r-biocgenerics)
7544 ("r-s4vectors" ,r-s4vectors)
7545 ("r-iranges" ,r-iranges)
7546 ("r-matrixstats" ,r-matrixstats)))
7547 (home-page "https://bioconductor.org/packages/DelayedArray")
7548 (synopsis "Delayed operations on array-like objects")
7550 "Wrapping an array-like object (typically an on-disk object) in a
7551 @code{DelayedArray} object allows one to perform common array operations on it
7552 without loading the object in memory. In order to reduce memory usage and
7553 optimize performance, operations on the object are either delayed or executed
7554 using a block processing mechanism. Note that this also works on in-memory
7555 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7556 @code{Matrix} objects, and ordinary arrays and data frames.")
7557 (license license:artistic2.0)))
7559 (define-public r-summarizedexperiment
7561 (name "r-summarizedexperiment")
7565 (uri (bioconductor-uri "SummarizedExperiment" version))
7568 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7570 `((upstream-name . "SummarizedExperiment")))
7571 (build-system r-build-system)
7573 `(("r-biobase" ,r-biobase)
7574 ("r-biocgenerics" ,r-biocgenerics)
7575 ("r-delayedarray" ,r-delayedarray)
7576 ("r-genomeinfodb" ,r-genomeinfodb)
7577 ("r-genomicranges" ,r-genomicranges)
7578 ("r-iranges" ,r-iranges)
7579 ("r-matrix" ,r-matrix)
7580 ("r-s4vectors" ,r-s4vectors)))
7581 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7582 (synopsis "Container for representing genomic ranges by sample")
7584 "The SummarizedExperiment container contains one or more assays, each
7585 represented by a matrix-like object of numeric or other mode. The rows
7586 typically represent genomic ranges of interest and the columns represent
7588 (license license:artistic2.0)))
7590 (define-public r-genomicalignments
7592 (name "r-genomicalignments")
7596 (uri (bioconductor-uri "GenomicAlignments" version))
7599 "1659nj1xps7vliy5955i51x6hvrf16n1z0dfh10mmpaaswn2d2mv"))))
7601 `((upstream-name . "GenomicAlignments")))
7602 (build-system r-build-system)
7604 `(("r-biocgenerics" ,r-biocgenerics)
7605 ("r-biocparallel" ,r-biocparallel)
7606 ("r-biostrings" ,r-biostrings)
7607 ("r-genomeinfodb" ,r-genomeinfodb)
7608 ("r-genomicranges" ,r-genomicranges)
7609 ("r-iranges" ,r-iranges)
7610 ("r-rsamtools" ,r-rsamtools)
7611 ("r-s4vectors" ,r-s4vectors)
7612 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7613 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7614 (synopsis "Representation and manipulation of short genomic alignments")
7616 "This package provides efficient containers for storing and manipulating
7617 short genomic alignments (typically obtained by aligning short reads to a
7618 reference genome). This includes read counting, computing the coverage,
7619 junction detection, and working with the nucleotide content of the
7621 (license license:artistic2.0)))
7623 (define-public r-rtracklayer
7625 (name "r-rtracklayer")
7629 (uri (bioconductor-uri "rtracklayer" version))
7632 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7633 (build-system r-build-system)
7636 (modify-phases %standard-phases
7637 (add-after 'unpack 'use-system-zlib
7639 (substitute* "DESCRIPTION"
7640 ((" zlibbioc,") ""))
7641 (substitute* "NAMESPACE"
7642 (("import\\(zlibbioc\\)") ""))
7647 `(("r-biocgenerics" ,r-biocgenerics)
7648 ("r-biostrings" ,r-biostrings)
7649 ("r-genomeinfodb" ,r-genomeinfodb)
7650 ("r-genomicalignments" ,r-genomicalignments)
7651 ("r-genomicranges" ,r-genomicranges)
7652 ("r-iranges" ,r-iranges)
7653 ("r-rcurl" ,r-rcurl)
7654 ("r-rsamtools" ,r-rsamtools)
7655 ("r-s4vectors" ,r-s4vectors)
7657 ("r-xvector" ,r-xvector)))
7658 (home-page "https://bioconductor.org/packages/rtracklayer")
7659 (synopsis "R interface to genome browsers and their annotation tracks")
7661 "rtracklayer is an extensible framework for interacting with multiple
7662 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7663 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7664 built-in). The user may export/import tracks to/from the supported browsers,
7665 as well as query and modify the browser state, such as the current viewport.")
7666 (license license:artistic2.0)))
7668 (define-public r-genomicfeatures
7670 (name "r-genomicfeatures")
7674 (uri (bioconductor-uri "GenomicFeatures" version))
7677 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7679 `((upstream-name . "GenomicFeatures")))
7680 (build-system r-build-system)
7682 `(("r-annotationdbi" ,r-annotationdbi)
7683 ("r-biobase" ,r-biobase)
7684 ("r-biocgenerics" ,r-biocgenerics)
7685 ("r-biomart" ,r-biomart)
7686 ("r-biostrings" ,r-biostrings)
7688 ("r-genomeinfodb" ,r-genomeinfodb)
7689 ("r-genomicranges" ,r-genomicranges)
7690 ("r-iranges" ,r-iranges)
7691 ("r-rcurl" ,r-rcurl)
7692 ("r-rsqlite" ,r-rsqlite)
7693 ("r-rmysql" ,r-rmysql)
7694 ("r-rtracklayer" ,r-rtracklayer)
7695 ("r-s4vectors" ,r-s4vectors)
7696 ("r-xvector" ,r-xvector)))
7697 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7698 (synopsis "Tools for working with transcript centric annotations")
7700 "This package provides a set of tools and methods for making and
7701 manipulating transcript centric annotations. With these tools the user can
7702 easily download the genomic locations of the transcripts, exons and cds of a
7703 given organism, from either the UCSC Genome Browser or a BioMart
7704 database (more sources will be supported in the future). This information is
7705 then stored in a local database that keeps track of the relationship between
7706 transcripts, exons, cds and genes. Flexible methods are provided for
7707 extracting the desired features in a convenient format.")
7708 (license license:artistic2.0)))
7710 (define-public r-go-db
7716 (uri (string-append "https://www.bioconductor.org/packages/"
7717 "release/data/annotation/src/contrib/GO.db_"
7721 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7723 `((upstream-name . "GO.db")))
7724 (build-system r-build-system)
7726 `(("r-annotationdbi" ,r-annotationdbi)))
7727 (home-page "https://bioconductor.org/packages/GO.db")
7728 (synopsis "Annotation maps describing the entire Gene Ontology")
7730 "The purpose of this GO.db annotation package is to provide detailed
7731 information about the latest version of the Gene Ontologies.")
7732 (license license:artistic2.0)))
7734 (define-public r-graph
7740 (uri (bioconductor-uri "graph" version))
7743 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7744 (build-system r-build-system)
7746 `(("r-biocgenerics" ,r-biocgenerics)))
7747 (home-page "https://bioconductor.org/packages/graph")
7748 (synopsis "Handle graph data structures in R")
7750 "This package implements some simple graph handling capabilities for R.")
7751 (license license:artistic2.0)))
7753 (define-public r-topgo
7759 (uri (bioconductor-uri "topGO" version))
7762 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7764 `((upstream-name . "topGO")))
7765 (build-system r-build-system)
7767 `(("r-annotationdbi" ,r-annotationdbi)
7769 ("r-biobase" ,r-biobase)
7770 ("r-biocgenerics" ,r-biocgenerics)
7771 ("r-go-db" ,r-go-db)
7772 ("r-graph" ,r-graph)
7773 ("r-lattice" ,r-lattice)
7774 ("r-matrixstats" ,r-matrixstats)
7775 ("r-sparsem" ,r-sparsem)))
7776 (home-page "https://bioconductor.org/packages/topGO")
7777 (synopsis "Enrichment analysis for gene ontology")
7779 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7780 terms while accounting for the topology of the GO graph. Different test
7781 statistics and different methods for eliminating local similarities and
7782 dependencies between GO terms can be implemented and applied.")
7783 ;; Any version of the LGPL applies.
7784 (license license:lgpl2.1+)))
7786 (define-public r-bsgenome
7792 (uri (bioconductor-uri "BSgenome" version))
7795 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7797 `((upstream-name . "BSgenome")))
7798 (build-system r-build-system)
7800 `(("r-biocgenerics" ,r-biocgenerics)
7801 ("r-biostrings" ,r-biostrings)
7802 ("r-genomeinfodb" ,r-genomeinfodb)
7803 ("r-genomicranges" ,r-genomicranges)
7804 ("r-iranges" ,r-iranges)
7805 ("r-rsamtools" ,r-rsamtools)
7806 ("r-rtracklayer" ,r-rtracklayer)
7807 ("r-s4vectors" ,r-s4vectors)
7808 ("r-xvector" ,r-xvector)))
7809 (home-page "https://bioconductor.org/packages/BSgenome")
7810 (synopsis "Infrastructure for Biostrings-based genome data packages")
7812 "This package provides infrastructure shared by all Biostrings-based
7813 genome data packages and support for efficient SNP representation.")
7814 (license license:artistic2.0)))
7816 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7818 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7822 ;; We cannot use bioconductor-uri here because this tarball is
7823 ;; located under "data/annotation/" instead of "bioc/".
7824 (uri (string-append "https://www.bioconductor.org/packages/"
7825 "release/data/annotation/src/contrib/"
7826 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7830 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7832 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7833 (build-system r-build-system)
7834 ;; As this package provides little more than a very large data file it
7835 ;; doesn't make sense to build substitutes.
7836 (arguments `(#:substitutable? #f))
7838 `(("r-bsgenome" ,r-bsgenome)))
7840 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7841 (synopsis "Full genome sequences for Homo sapiens")
7843 "This package provides full genome sequences for Homo sapiens from
7844 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7845 (license license:artistic2.0)))
7847 (define-public r-impute
7853 (uri (bioconductor-uri "impute" version))
7856 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7858 `(("gfortran" ,gfortran)))
7859 (build-system r-build-system)
7860 (home-page "https://bioconductor.org/packages/impute")
7861 (synopsis "Imputation for microarray data")
7863 "This package provides a function to impute missing gene expression
7864 microarray data, using nearest neighbor averaging.")
7865 (license license:gpl2+)))
7867 (define-public r-seqpattern
7869 (name "r-seqpattern")
7873 (uri (bioconductor-uri "seqPattern" version))
7876 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7878 `((upstream-name . "seqPattern")))
7879 (build-system r-build-system)
7881 `(("r-biostrings" ,r-biostrings)
7882 ("r-genomicranges" ,r-genomicranges)
7883 ("r-iranges" ,r-iranges)
7884 ("r-kernsmooth" ,r-kernsmooth)
7885 ("r-plotrix" ,r-plotrix)))
7886 (home-page "https://bioconductor.org/packages/seqPattern")
7887 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7889 "This package provides tools to visualize oligonucleotide patterns and
7890 sequence motif occurrences across a large set of sequences centred at a common
7891 reference point and sorted by a user defined feature.")
7892 (license license:gpl3+)))
7894 (define-public r-genomation
7896 (name "r-genomation")
7900 (uri (bioconductor-uri "genomation" version))
7903 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7904 (build-system r-build-system)
7906 `(("r-biostrings" ,r-biostrings)
7907 ("r-bsgenome" ,r-bsgenome)
7908 ("r-data-table" ,r-data-table)
7909 ("r-genomeinfodb" ,r-genomeinfodb)
7910 ("r-genomicalignments" ,r-genomicalignments)
7911 ("r-genomicranges" ,r-genomicranges)
7912 ("r-ggplot2" ,r-ggplot2)
7913 ("r-gridbase" ,r-gridbase)
7914 ("r-impute" ,r-impute)
7915 ("r-iranges" ,r-iranges)
7916 ("r-matrixstats" ,r-matrixstats)
7917 ("r-plotrix" ,r-plotrix)
7920 ("r-readr" ,r-readr)
7921 ("r-reshape2" ,r-reshape2)
7922 ("r-rsamtools" ,r-rsamtools)
7923 ("r-rtracklayer" ,r-rtracklayer)
7924 ("r-runit" ,r-runit)
7925 ("r-s4vectors" ,r-s4vectors)
7926 ("r-seqpattern" ,r-seqpattern)))
7927 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7928 (synopsis "Summary, annotation and visualization of genomic data")
7930 "This package provides a package for summary and annotation of genomic
7931 intervals. Users can visualize and quantify genomic intervals over
7932 pre-defined functional regions, such as promoters, exons, introns, etc. The
7933 genomic intervals represent regions with a defined chromosome position, which
7934 may be associated with a score, such as aligned reads from HT-seq experiments,
7935 TF binding sites, methylation scores, etc. The package can use any tabular
7936 genomic feature data as long as it has minimal information on the locations of
7937 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7938 (license license:artistic2.0)))
7940 (define-public r-genomationdata
7942 (name "r-genomationdata")
7946 ;; We cannot use bioconductor-uri here because this tarball is
7947 ;; located under "data/annotation/" instead of "bioc/".
7948 (uri (string-append "https://bioconductor.org/packages/"
7949 "release/data/experiment/src/contrib/"
7950 "genomationData_" version ".tar.gz"))
7953 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7954 (build-system r-build-system)
7955 ;; As this package provides little more than large data files, it doesn't
7956 ;; make sense to build substitutes.
7957 (arguments `(#:substitutable? #f))
7959 `(("r-knitr" ,r-knitr)))
7960 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7961 (synopsis "Experimental data for use with the genomation package")
7963 "This package contains experimental genetic data for use with the
7964 genomation package. Included are Chip Seq, Methylation and Cage data,
7965 downloaded from Encode.")
7966 (license license:gpl3+)))
7968 (define-public r-org-hs-eg-db
7970 (name "r-org-hs-eg-db")
7974 ;; We cannot use bioconductor-uri here because this tarball is
7975 ;; located under "data/annotation/" instead of "bioc/".
7976 (uri (string-append "https://www.bioconductor.org/packages/"
7977 "release/data/annotation/src/contrib/"
7978 "org.Hs.eg.db_" version ".tar.gz"))
7981 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7983 `((upstream-name . "org.Hs.eg.db")))
7984 (build-system r-build-system)
7986 `(("r-annotationdbi" ,r-annotationdbi)))
7987 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7988 (synopsis "Genome wide annotation for Human")
7990 "This package contains genome-wide annotations for Human, primarily based
7991 on mapping using Entrez Gene identifiers.")
7992 (license license:artistic2.0)))
7994 (define-public r-org-ce-eg-db
7996 (name "r-org-ce-eg-db")
8000 ;; We cannot use bioconductor-uri here because this tarball is
8001 ;; located under "data/annotation/" instead of "bioc/".
8002 (uri (string-append "https://www.bioconductor.org/packages/"
8003 "release/data/annotation/src/contrib/"
8004 "org.Ce.eg.db_" version ".tar.gz"))
8007 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8009 `((upstream-name . "org.Ce.eg.db")))
8010 (build-system r-build-system)
8012 `(("r-annotationdbi" ,r-annotationdbi)))
8013 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8014 (synopsis "Genome wide annotation for Worm")
8016 "This package provides mappings from Entrez gene identifiers to various
8017 annotations for the genome of the model worm Caenorhabditis elegans.")
8018 (license license:artistic2.0)))
8020 (define-public r-org-dm-eg-db
8022 (name "r-org-dm-eg-db")
8026 ;; We cannot use bioconductor-uri here because this tarball is
8027 ;; located under "data/annotation/" instead of "bioc/".
8028 (uri (string-append "https://www.bioconductor.org/packages/"
8029 "release/data/annotation/src/contrib/"
8030 "org.Dm.eg.db_" version ".tar.gz"))
8033 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8035 `((upstream-name . "org.Dm.eg.db")))
8036 (build-system r-build-system)
8038 `(("r-annotationdbi" ,r-annotationdbi)))
8039 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8040 (synopsis "Genome wide annotation for Fly")
8042 "This package provides mappings from Entrez gene identifiers to various
8043 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8044 (license license:artistic2.0)))
8046 (define-public r-org-mm-eg-db
8048 (name "r-org-mm-eg-db")
8052 ;; We cannot use bioconductor-uri here because this tarball is
8053 ;; located under "data/annotation/" instead of "bioc/".
8054 (uri (string-append "https://www.bioconductor.org/packages/"
8055 "release/data/annotation/src/contrib/"
8056 "org.Mm.eg.db_" version ".tar.gz"))
8059 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8061 `((upstream-name . "org.Mm.eg.db")))
8062 (build-system r-build-system)
8064 `(("r-annotationdbi" ,r-annotationdbi)))
8065 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8066 (synopsis "Genome wide annotation for Mouse")
8068 "This package provides mappings from Entrez gene identifiers to various
8069 annotations for the genome of the model mouse Mus musculus.")
8070 (license license:artistic2.0)))
8072 (define-public r-seqlogo
8079 (uri (bioconductor-uri "seqLogo" version))
8082 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
8083 (properties `((upstream-name . "seqLogo")))
8084 (build-system r-build-system)
8085 (home-page "https://bioconductor.org/packages/seqLogo")
8086 (synopsis "Sequence logos for DNA sequence alignments")
8088 "seqLogo takes the position weight matrix of a DNA sequence motif and
8089 plots the corresponding sequence logo as introduced by Schneider and
8091 (license license:lgpl2.0+)))
8093 (define-public r-bsgenome-hsapiens-ucsc-hg19
8095 (name "r-bsgenome-hsapiens-ucsc-hg19")
8099 ;; We cannot use bioconductor-uri here because this tarball is
8100 ;; located under "data/annotation/" instead of "bioc/".
8101 (uri (string-append "https://www.bioconductor.org/packages/"
8102 "release/data/annotation/src/contrib/"
8103 "BSgenome.Hsapiens.UCSC.hg19_"
8107 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8109 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8110 (build-system r-build-system)
8111 ;; As this package provides little more than a very large data file it
8112 ;; doesn't make sense to build substitutes.
8113 (arguments `(#:substitutable? #f))
8115 `(("r-bsgenome" ,r-bsgenome)))
8117 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8118 (synopsis "Full genome sequences for Homo sapiens")
8120 "This package provides full genome sequences for Homo sapiens as provided
8121 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8122 (license license:artistic2.0)))
8124 (define-public r-bsgenome-mmusculus-ucsc-mm9
8126 (name "r-bsgenome-mmusculus-ucsc-mm9")
8130 ;; We cannot use bioconductor-uri here because this tarball is
8131 ;; located under "data/annotation/" instead of "bioc/".
8132 (uri (string-append "https://www.bioconductor.org/packages/"
8133 "release/data/annotation/src/contrib/"
8134 "BSgenome.Mmusculus.UCSC.mm9_"
8138 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8140 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8141 (build-system r-build-system)
8142 ;; As this package provides little more than a very large data file it
8143 ;; doesn't make sense to build substitutes.
8144 (arguments `(#:substitutable? #f))
8146 `(("r-bsgenome" ,r-bsgenome)))
8148 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8149 (synopsis "Full genome sequences for Mouse")
8151 "This package provides full genome sequences for Mus musculus (Mouse) as
8152 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8153 (license license:artistic2.0)))
8155 (define-public r-bsgenome-mmusculus-ucsc-mm10
8157 (name "r-bsgenome-mmusculus-ucsc-mm10")
8161 ;; We cannot use bioconductor-uri here because this tarball is
8162 ;; located under "data/annotation/" instead of "bioc/".
8163 (uri (string-append "https://www.bioconductor.org/packages/"
8164 "release/data/annotation/src/contrib/"
8165 "BSgenome.Mmusculus.UCSC.mm10_"
8169 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8171 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8172 (build-system r-build-system)
8173 ;; As this package provides little more than a very large data file it
8174 ;; doesn't make sense to build substitutes.
8175 (arguments `(#:substitutable? #f))
8177 `(("r-bsgenome" ,r-bsgenome)))
8179 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8180 (synopsis "Full genome sequences for Mouse")
8182 "This package provides full genome sequences for Mus
8183 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8184 in Biostrings objects.")
8185 (license license:artistic2.0)))
8187 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8189 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8193 ;; We cannot use bioconductor-uri here because this tarball is
8194 ;; located under "data/annotation/" instead of "bioc/".
8195 (uri (string-append "https://www.bioconductor.org/packages/"
8196 "release/data/annotation/src/contrib/"
8197 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8201 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8203 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8204 (build-system r-build-system)
8205 ;; As this package provides little more than a very large data file it
8206 ;; doesn't make sense to build substitutes.
8207 (arguments `(#:substitutable? #f))
8209 `(("r-bsgenome" ,r-bsgenome)
8210 ("r-genomicfeatures" ,r-genomicfeatures)
8211 ("r-annotationdbi" ,r-annotationdbi)))
8213 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8214 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8216 "This package loads a TxDb object, which is an R interface to
8217 prefabricated databases contained in this package. This package provides
8218 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8219 based on the knownGene track.")
8220 (license license:artistic2.0)))
8222 (define-public r-bsgenome-celegans-ucsc-ce6
8224 (name "r-bsgenome-celegans-ucsc-ce6")
8228 ;; We cannot use bioconductor-uri here because this tarball is
8229 ;; located under "data/annotation/" instead of "bioc/".
8230 (uri (string-append "https://www.bioconductor.org/packages/"
8231 "release/data/annotation/src/contrib/"
8232 "BSgenome.Celegans.UCSC.ce6_"
8236 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8238 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8239 (build-system r-build-system)
8240 ;; As this package provides little more than a very large data file it
8241 ;; doesn't make sense to build substitutes.
8242 (arguments `(#:substitutable? #f))
8244 `(("r-bsgenome" ,r-bsgenome)))
8246 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8247 (synopsis "Full genome sequences for Worm")
8249 "This package provides full genome sequences for Caenorhabditis
8250 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8252 (license license:artistic2.0)))
8254 (define-public r-bsgenome-celegans-ucsc-ce10
8256 (name "r-bsgenome-celegans-ucsc-ce10")
8260 ;; We cannot use bioconductor-uri here because this tarball is
8261 ;; located under "data/annotation/" instead of "bioc/".
8262 (uri (string-append "https://www.bioconductor.org/packages/"
8263 "release/data/annotation/src/contrib/"
8264 "BSgenome.Celegans.UCSC.ce10_"
8268 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8270 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8271 (build-system r-build-system)
8272 ;; As this package provides little more than a very large data file it
8273 ;; doesn't make sense to build substitutes.
8274 (arguments `(#:substitutable? #f))
8276 `(("r-bsgenome" ,r-bsgenome)))
8278 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8279 (synopsis "Full genome sequences for Worm")
8281 "This package provides full genome sequences for Caenorhabditis
8282 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8284 (license license:artistic2.0)))
8286 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8288 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8292 ;; We cannot use bioconductor-uri here because this tarball is
8293 ;; located under "data/annotation/" instead of "bioc/".
8294 (uri (string-append "https://www.bioconductor.org/packages/"
8295 "release/data/annotation/src/contrib/"
8296 "BSgenome.Dmelanogaster.UCSC.dm3_"
8300 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8302 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8303 (build-system r-build-system)
8304 ;; As this package provides little more than a very large data file it
8305 ;; doesn't make sense to build substitutes.
8306 (arguments `(#:substitutable? #f))
8308 `(("r-bsgenome" ,r-bsgenome)))
8310 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8311 (synopsis "Full genome sequences for Fly")
8313 "This package provides full genome sequences for Drosophila
8314 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8315 Biostrings objects.")
8316 (license license:artistic2.0)))
8318 (define-public r-motifrg
8325 (uri (bioconductor-uri "motifRG" version))
8328 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8329 (properties `((upstream-name . "motifRG")))
8330 (build-system r-build-system)
8332 `(("r-biostrings" ,r-biostrings)
8333 ("r-bsgenome" ,r-bsgenome)
8334 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8335 ("r-iranges" ,r-iranges)
8336 ("r-seqlogo" ,r-seqlogo)
8337 ("r-xvector" ,r-xvector)))
8338 (home-page "https://bioconductor.org/packages/motifRG")
8339 (synopsis "Discover motifs in high throughput sequencing data")
8341 "This package provides tools for discriminative motif discovery in high
8342 throughput genetic sequencing data sets using regression methods.")
8343 (license license:artistic2.0)))
8345 (define-public r-qtl
8352 (uri (string-append "mirror://cran/src/contrib/qtl_"
8356 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8357 (build-system r-build-system)
8358 (home-page "http://rqtl.org/")
8359 (synopsis "R package for analyzing QTL experiments in genetics")
8360 (description "R/qtl is an extension library for the R statistics
8361 system. It is used to analyze experimental crosses for identifying
8362 genes contributing to variation in quantitative traits (so-called
8363 quantitative trait loci, QTLs).
8365 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8366 identify genotyping errors, and to perform single-QTL and two-QTL,
8367 two-dimensional genome scans.")
8368 (license license:gpl3)))
8370 (define-public r-zlibbioc
8376 (uri (bioconductor-uri "zlibbioc" version))
8379 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8381 `((upstream-name . "zlibbioc")))
8382 (build-system r-build-system)
8383 (home-page "https://bioconductor.org/packages/zlibbioc")
8384 (synopsis "Provider for zlib-1.2.5 to R packages")
8385 (description "This package uses the source code of zlib-1.2.5 to create
8386 libraries for systems that do not have these available via other means.")
8387 (license license:artistic2.0)))
8389 (define-public r-r4rna
8396 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8400 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8401 (build-system r-build-system)
8403 `(("r-optparse" ,r-optparse)
8404 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8405 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8406 (synopsis "Analysis framework for RNA secondary structure")
8408 "The R4RNA package aims to be a general framework for the analysis of RNA
8409 secondary structure and comparative analysis in R.")
8410 (license license:gpl3+)))
8412 (define-public r-rhtslib
8419 (uri (bioconductor-uri "Rhtslib" version))
8422 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8423 (properties `((upstream-name . "Rhtslib")))
8424 (build-system r-build-system)
8426 `(("r-zlibbioc" ,r-zlibbioc)))
8430 `(("autoconf" ,autoconf)))
8431 (home-page "https://github.com/nhayden/Rhtslib")
8432 (synopsis "High-throughput sequencing library as an R package")
8434 "This package provides the HTSlib C library for high-throughput
8435 nucleotide sequence analysis. The package is primarily useful to developers
8436 of other R packages who wish to make use of HTSlib.")
8437 (license license:lgpl2.0+)))
8439 (define-public r-bamsignals
8441 (name "r-bamsignals")
8446 (uri (bioconductor-uri "bamsignals" version))
8449 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8450 (build-system r-build-system)
8452 `(("r-biocgenerics" ,r-biocgenerics)
8453 ("r-genomicranges" ,r-genomicranges)
8454 ("r-iranges" ,r-iranges)
8456 ("r-rhtslib" ,r-rhtslib)
8457 ("r-zlibbioc" ,r-zlibbioc)))
8460 (home-page "https://bioconductor.org/packages/bamsignals")
8461 (synopsis "Extract read count signals from bam files")
8463 "This package allows to efficiently obtain count vectors from indexed bam
8464 files. It counts the number of nucleotide sequence reads in given genomic
8465 ranges and it computes reads profiles and coverage profiles. It also handles
8467 (license license:gpl2+)))
8469 (define-public r-rcas
8475 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8477 (file-name (string-append name "-" version ".tar.gz"))
8480 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8481 (build-system r-build-system)
8483 `(("r-knitr" ,r-knitr)
8484 ("r-testthat" ,r-testthat)
8485 ;; During vignette building knitr checks that "pandoc-citeproc"
8487 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8489 `(("r-data-table" ,r-data-table)
8490 ("r-biomart" ,r-biomart)
8491 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8492 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8493 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8494 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8495 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8496 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8497 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8498 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8499 ("r-topgo" ,r-topgo)
8501 ("r-pbapply" ,r-pbapply)
8502 ("r-plotly" ,r-plotly)
8503 ("r-plotrix" ,r-plotrix)
8504 ("r-motifrg" ,r-motifrg)
8505 ("r-genomation" ,r-genomation)
8506 ("r-genomicfeatures" ,r-genomicfeatures)
8507 ("r-rtracklayer" ,r-rtracklayer)
8508 ("r-rmarkdown" ,r-rmarkdown)))
8509 (synopsis "RNA-centric annotation system")
8511 "RCAS aims to be a standalone RNA-centric annotation system that provides
8512 intuitive reports and publication-ready graphics. This package provides the R
8513 library implementing most of the pipeline's features.")
8514 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8515 (license license:artistic2.0)))
8517 (define-public rcas-web
8524 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8525 "releases/download/v" version
8526 "/rcas-web-" version ".tar.gz"))
8529 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8530 (build-system gnu-build-system)
8533 (modify-phases %standard-phases
8534 (add-after 'install 'wrap-executable
8535 (lambda* (#:key inputs outputs #:allow-other-keys)
8536 (let* ((out (assoc-ref outputs "out"))
8537 (json (assoc-ref inputs "guile-json"))
8538 (redis (assoc-ref inputs "guile-redis"))
8539 (path (string-append
8540 json "/share/guile/site/2.2:"
8541 redis "/share/guile/site/2.2")))
8542 (wrap-program (string-append out "/bin/rcas-web")
8543 `("GUILE_LOAD_PATH" ":" = (,path))
8544 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8545 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8548 `(("r-minimal" ,r-minimal)
8550 ("guile-next" ,guile-2.2)
8551 ("guile-json" ,guile-json)
8552 ("guile-redis" ,guile2.2-redis)))
8554 `(("pkg-config" ,pkg-config)))
8555 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8556 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8557 (description "This package provides a simple web interface for the
8558 @dfn{RNA-centric annotation system} (RCAS).")
8559 (license license:agpl3+)))
8561 (define-public r-mutationalpatterns
8563 (name "r-mutationalpatterns")
8568 (uri (bioconductor-uri "MutationalPatterns" version))
8571 "0ml4gsp5dfv23xqrknxh25q8q65hly1xb1215lcwyc8hj9z8f941"))))
8572 (build-system r-build-system)
8574 `(("r-biocgenerics" ,r-biocgenerics)
8575 ("r-biostrings" ,r-biostrings)
8576 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8577 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8578 ("r-genomicranges" ,r-genomicranges)
8579 ("r-genomeinfodb" ,r-genomeinfodb)
8580 ("r-ggplot2" ,r-ggplot2)
8581 ("r-iranges" ,r-iranges)
8584 ("r-pracma" ,r-pracma)
8585 ("r-reshape2" ,r-reshape2)
8586 ("r-cowplot" ,r-cowplot)
8587 ("r-ggdendro" ,r-ggdendro)
8588 ("r-s4vectors" ,r-s4vectors)
8589 ("r-summarizedexperiment" ,r-summarizedexperiment)
8590 ("r-variantannotation" ,r-variantannotation)))
8591 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8592 (synopsis "Extract and visualize mutational patterns in genomic data")
8593 (description "This package provides an extensive toolset for the
8594 characterization and visualization of a wide range of mutational patterns
8595 in SNV base substitution data.")
8596 (license license:expat)))
8598 (define-public r-wgcna
8605 (uri (cran-uri "WGCNA" version))
8608 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8609 (properties `((upstream-name . "WGCNA")))
8610 (build-system r-build-system)
8612 `(("r-annotationdbi" ,r-annotationdbi)
8613 ("r-doparallel" ,r-doparallel)
8614 ("r-dynamictreecut" ,r-dynamictreecut)
8615 ("r-fastcluster" ,r-fastcluster)
8616 ("r-foreach" ,r-foreach)
8617 ("r-go-db" ,r-go-db)
8618 ("r-hmisc" ,r-hmisc)
8619 ("r-impute" ,r-impute)
8621 ("r-robust" ,r-robust)
8622 ("r-survival" ,r-survival)
8623 ("r-matrixstats" ,r-matrixstats)
8624 ("r-preprocesscore" ,r-preprocesscore)))
8626 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8627 (synopsis "Weighted correlation network analysis")
8629 "This package provides functions necessary to perform Weighted
8630 Correlation Network Analysis on high-dimensional data. It includes functions
8631 for rudimentary data cleaning, construction and summarization of correlation
8632 networks, module identification and functions for relating both variables and
8633 modules to sample traits. It also includes a number of utility functions for
8634 data manipulation and visualization.")
8635 (license license:gpl2+)))
8637 (define-public r-chipkernels
8638 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8641 (name "r-chipkernels")
8642 (version (string-append "1.1-" revision "." (string-take commit 9)))
8647 (url "https://github.com/ManuSetty/ChIPKernels.git")
8649 (file-name (string-append name "-" version))
8652 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8653 (build-system r-build-system)
8655 `(("r-iranges" ,r-iranges)
8656 ("r-xvector" ,r-xvector)
8657 ("r-biostrings" ,r-biostrings)
8658 ("r-bsgenome" ,r-bsgenome)
8659 ("r-gtools" ,r-gtools)
8660 ("r-genomicranges" ,r-genomicranges)
8661 ("r-sfsmisc" ,r-sfsmisc)
8662 ("r-kernlab" ,r-kernlab)
8663 ("r-s4vectors" ,r-s4vectors)
8664 ("r-biocgenerics" ,r-biocgenerics)))
8665 (home-page "https://github.com/ManuSetty/ChIPKernels")
8666 (synopsis "Build string kernels for DNA Sequence analysis")
8667 (description "ChIPKernels is an R package for building different string
8668 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8669 must be built and this dictionary can be used for determining kernels for DNA
8671 (license license:gpl2+))))
8673 (define-public r-seqgl
8680 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8681 "archive/" version ".tar.gz"))
8682 (file-name (string-append name "-" version ".tar.gz"))
8685 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8686 (build-system r-build-system)
8688 `(("r-biostrings" ,r-biostrings)
8689 ("r-chipkernels" ,r-chipkernels)
8690 ("r-genomicranges" ,r-genomicranges)
8691 ("r-spams" ,r-spams)
8692 ("r-wgcna" ,r-wgcna)
8693 ("r-fastcluster" ,r-fastcluster)))
8694 (home-page "https://github.com/ManuSetty/SeqGL")
8695 (synopsis "Group lasso for Dnase/ChIP-seq data")
8696 (description "SeqGL is a group lasso based algorithm to extract
8697 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8698 This package presents a method which uses group lasso to discriminate between
8699 bound and non bound genomic regions to accurately identify transcription
8700 factors bound at the specific regions.")
8701 (license license:gpl2+)))
8703 (define-public r-gkmsvm
8710 (uri (cran-uri "gkmSVM" version))
8713 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8714 (properties `((upstream-name . "gkmSVM")))
8715 (build-system r-build-system)
8717 `(("r-biocgenerics" ,r-biocgenerics)
8718 ("r-biostrings" ,r-biostrings)
8719 ("r-genomeinfodb" ,r-genomeinfodb)
8720 ("r-genomicranges" ,r-genomicranges)
8721 ("r-iranges" ,r-iranges)
8722 ("r-kernlab" ,r-kernlab)
8725 ("r-rtracklayer" ,r-rtracklayer)
8726 ("r-s4vectors" ,r-s4vectors)
8727 ("r-seqinr" ,r-seqinr)))
8728 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8729 (synopsis "Gapped-kmer support vector machine")
8731 "This R package provides tools for training gapped-kmer SVM classifiers
8732 for DNA and protein sequences. This package supports several sequence
8733 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8734 (license license:gpl2+)))
8736 (define-public r-tximport
8742 (uri (bioconductor-uri "tximport" version))
8745 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8746 (build-system r-build-system)
8747 (home-page "https://bioconductor.org/packages/tximport")
8748 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8750 "This package provides tools to import transcript-level abundance,
8751 estimated counts and transcript lengths, and to summarize them into matrices
8752 for use with downstream gene-level analysis packages. Average transcript
8753 length, weighted by sample-specific transcript abundance estimates, is
8754 provided as a matrix which can be used as an offset for different expression
8755 of gene-level counts.")
8756 (license license:gpl2+)))
8758 (define-public r-rhdf5
8764 (uri (bioconductor-uri "rhdf5" version))
8767 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8768 (build-system r-build-system)
8771 (modify-phases %standard-phases
8772 (add-after 'unpack 'unpack-smallhdf5
8773 (lambda* (#:key outputs #:allow-other-keys)
8774 (system* "tar" "-xzvf"
8775 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8776 (substitute* "src/hdf5/configure"
8778 ;; Remove timestamp and host system information to make
8779 ;; the build reproducible.
8780 (substitute* "src/hdf5/src/libhdf5.settings.in"
8781 (("Configured on: @CONFIG_DATE@")
8782 "Configured on: Guix")
8783 (("Uname information:.*")
8784 "Uname information: Linux\n")
8785 ;; Remove unnecessary store reference.
8787 "C Compiler: GCC\n"))
8790 `(("r-zlibbioc" ,r-zlibbioc)))
8794 (home-page "https://bioconductor.org/packages/rhdf5")
8795 (synopsis "HDF5 interface to R")
8797 "This R/Bioconductor package provides an interface between HDF5 and R.
8798 HDF5's main features are the ability to store and access very large and/or
8799 complex datasets and a wide variety of metadata on mass storage (disk) through
8800 a completely portable file format. The rhdf5 package is thus suited for the
8801 exchange of large and/or complex datasets between R and other software
8802 package, and for letting R applications work on datasets that are larger than
8803 the available RAM.")
8804 (license license:artistic2.0)))
8806 (define-public r-annotationfilter
8808 (name "r-annotationfilter")
8812 (uri (bioconductor-uri "AnnotationFilter" version))
8815 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8817 `((upstream-name . "AnnotationFilter")))
8818 (build-system r-build-system)
8820 `(("r-genomicranges" ,r-genomicranges)
8821 ("r-lazyeval" ,r-lazyeval)))
8822 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8823 (synopsis "Facilities for filtering Bioconductor annotation resources")
8825 "This package provides classes and other infrastructure to implement
8826 filters for manipulating Bioconductor annotation resources. The filters are
8827 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8828 (license license:artistic2.0)))
8830 (define-public emboss
8836 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8837 (version-major+minor version) ".0/"
8838 "EMBOSS-" version ".tar.gz"))
8841 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8842 (build-system gnu-build-system)
8845 (list (string-append "--with-hpdf="
8846 (assoc-ref %build-inputs "libharu")))
8848 (modify-phases %standard-phases
8849 (add-after 'unpack 'fix-checks
8851 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8852 ;; and zlib, but assume that they are all found at the same
8854 (substitute* "configure.in"
8855 (("CHECK_PNGDRIVER")
8856 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8857 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8858 AM_CONDITIONAL(AMPNG, true)"))
8860 (add-after 'fix-checks 'disable-update-check
8862 ;; At build time there is no connection to the Internet, so
8863 ;; looking for updates will not work.
8864 (substitute* "Makefile.am"
8865 (("\\$\\(bindir\\)/embossupdate") ""))
8867 (add-after 'disable-update-check 'autogen
8868 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8874 ("libharu" ,libharu)
8877 `(("autoconf" ,autoconf)
8878 ("automake" ,automake)
8879 ("libtool" ,libtool)
8880 ("pkg-config" ,pkg-config)))
8881 (home-page "http://emboss.sourceforge.net")
8882 (synopsis "Molecular biology analysis suite")
8883 (description "EMBOSS is the \"European Molecular Biology Open Software
8884 Suite\". EMBOSS is an analysis package specially developed for the needs of
8885 the molecular biology (e.g. EMBnet) user community. The software
8886 automatically copes with data in a variety of formats and even allows
8887 transparent retrieval of sequence data from the web. It also provides a
8888 number of libraries for the development of software in the field of molecular
8889 biology. EMBOSS also integrates a range of currently available packages and
8890 tools for sequence analysis into a seamless whole.")
8891 (license license:gpl2+)))
8894 (let ((revision "1")
8895 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8898 ;; The version is 2.13.0 even though no release archives have been
8899 ;; published as yet.
8900 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8904 (url "https://github.com/arq5x/bits.git")
8906 (file-name (string-append name "-" version "-checkout"))
8909 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8910 (build-system gnu-build-system)
8912 `(#:tests? #f ;no tests included
8914 (modify-phases %standard-phases
8916 (add-after 'unpack 'remove-cuda
8918 (substitute* "Makefile"
8920 (("(bits_test_intersections) \\\\" _ match) match))
8923 (lambda* (#:key outputs #:allow-other-keys)
8925 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8930 (home-page "https://github.com/arq5x/bits")
8931 (synopsis "Implementation of binary interval search algorithm")
8932 (description "This package provides an implementation of the
8933 BITS (Binary Interval Search) algorithm, an approach to interval set
8934 intersection. It is especially suited for the comparison of diverse genomic
8935 datasets and the exploration of large datasets of genome
8936 intervals (e.g. genes, sequence alignments).")
8937 (license license:gpl2))))
8939 (define-public piranha
8940 ;; There is no release tarball for the latest version. The latest commit is
8941 ;; older than one year at the time of this writing.
8942 (let ((revision "1")
8943 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8946 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8950 (url "https://github.com/smithlabcode/piranha.git")
8952 (file-name (git-file-name name version))
8955 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8956 (build-system gnu-build-system)
8958 `(#:test-target "test"
8960 (modify-phases %standard-phases
8961 (add-after 'unpack 'copy-smithlab-cpp
8962 (lambda* (#:key inputs #:allow-other-keys)
8963 (for-each (lambda (file)
8964 (install-file file "./src/smithlab_cpp/"))
8965 (find-files (assoc-ref inputs "smithlab-cpp")))
8967 (add-after 'install 'install-to-store
8968 (lambda* (#:key outputs #:allow-other-keys)
8969 (let* ((out (assoc-ref outputs "out"))
8970 (bin (string-append out "/bin")))
8971 (for-each (lambda (file)
8972 (install-file file bin))
8973 (find-files "bin" ".*")))
8976 (list (string-append "--with-bam_tools_headers="
8977 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8978 (string-append "--with-bam_tools_library="
8979 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8981 `(("bamtools" ,bamtools)
8982 ("samtools" ,samtools-0.1)
8985 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8989 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8991 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8994 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8996 `(("python" ,python-2)))
8997 (home-page "https://github.com/smithlabcode/piranha")
8998 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9000 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9001 RIP-seq experiments. It takes input in BED or BAM format and identifies
9002 regions of statistically significant read enrichment. Additional covariates
9003 may optionally be provided to further inform the peak-calling process.")
9004 (license license:gpl3+))))
9012 (uri (string-append "https://pypi.python.org/packages/source/P"
9013 "/PePr/PePr-" version ".tar.gz"))
9016 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9017 (build-system python-build-system)
9019 `(#:python ,python-2 ; python2 only
9020 #:tests? #f)) ; no tests included
9022 `(("python2-numpy" ,python2-numpy)
9023 ("python2-scipy" ,python2-scipy)
9024 ("python2-pysam" ,python2-pysam)))
9025 (home-page "https://github.com/shawnzhangyx/PePr")
9026 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9028 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9029 that is primarily designed for data with biological replicates. It uses a
9030 negative binomial distribution to model the read counts among the samples in
9031 the same group, and look for consistent differences between ChIP and control
9032 group or two ChIP groups run under different conditions.")
9033 (license license:gpl3+)))
9035 (define-public filevercmp
9036 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9039 (version (string-append "0-1." (string-take commit 7)))
9042 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9044 (file-name (string-append name "-" version ".tar.gz"))
9046 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9047 (build-system gnu-build-system)
9049 `(#:tests? #f ; There are no tests to run.
9051 (modify-phases %standard-phases
9052 (delete 'configure) ; There is no configure phase.
9054 (lambda* (#:key outputs #:allow-other-keys)
9055 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9056 (install-file "filevercmp" bin)))))))
9057 (home-page "https://github.com/ekg/filevercmp")
9058 (synopsis "This program compares version strings")
9059 (description "This program compares version strings. It intends to be a
9060 replacement for strverscmp.")
9061 (license license:gpl3+))))
9063 (define-public multiqc
9070 (uri (pypi-uri "multiqc" version))
9073 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9074 (build-system python-build-system)
9076 `(("python-jinja2" ,python-jinja2)
9077 ("python-simplejson" ,python-simplejson)
9078 ("python-pyyaml" ,python-pyyaml)
9079 ("python-click" ,python-click)
9080 ("python-spectra" ,python-spectra)
9081 ("python-requests" ,python-requests)
9082 ("python-markdown" ,python-markdown)
9083 ("python-lzstring" ,python-lzstring)
9084 ("python-matplotlib" ,python-matplotlib)
9085 ("python-numpy" ,python-numpy)
9086 ;; MultQC checks for the presence of nose at runtime.
9087 ("python-nose" ,python-nose)))
9088 (home-page "http://multiqc.info")
9089 (synopsis "Aggregate bioinformatics analysis reports")
9091 "MultiQC is a tool to aggregate bioinformatics results across many
9092 samples into a single report. It contains modules for a large number of
9093 common bioinformatics tools.")
9094 (license license:gpl3+)))
9096 (define-public r-chipseq
9103 (uri (bioconductor-uri "chipseq" version))
9106 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
9107 (build-system r-build-system)
9109 `(("r-biocgenerics" ,r-biocgenerics)
9110 ("r-genomicranges" ,r-genomicranges)
9111 ("r-iranges" ,r-iranges)
9112 ("r-lattice" ,r-lattice)
9113 ("r-s4vectors" ,r-s4vectors)
9114 ("r-shortread" ,r-shortread)))
9115 (home-page "https://bioconductor.org/packages/chipseq")
9116 (synopsis "Package for analyzing ChIPseq data")
9118 "This package provides tools for processing short read data from ChIPseq
9120 (license license:artistic2.0)))
9122 (define-public r-copyhelper
9124 (name "r-copyhelper")
9129 (uri (string-append "https://bioconductor.org/packages/release/"
9130 "data/experiment/src/contrib/CopyhelpeR_"
9134 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9135 (properties `((upstream-name . "CopyhelpeR")))
9136 (build-system r-build-system)
9137 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9138 (synopsis "Helper files for CopywriteR")
9140 "This package contains the helper files that are required to run the
9141 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9142 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9143 mm10. In addition, it contains a blacklist filter to remove regions that
9144 display copy number variation. Files are stored as GRanges objects from the
9145 GenomicRanges Bioconductor package.")
9146 (license license:gpl2)))
9148 (define-public r-copywriter
9150 (name "r-copywriter")
9155 (uri (bioconductor-uri "CopywriteR" version))
9158 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9159 (properties `((upstream-name . "CopywriteR")))
9160 (build-system r-build-system)
9162 `(("r-biocparallel" ,r-biocparallel)
9163 ("r-chipseq" ,r-chipseq)
9164 ("r-copyhelper" ,r-copyhelper)
9165 ("r-data-table" ,r-data-table)
9166 ("r-dnacopy" ,r-dnacopy)
9167 ("r-futile-logger" ,r-futile-logger)
9168 ("r-genomeinfodb" ,r-genomeinfodb)
9169 ("r-genomicalignments" ,r-genomicalignments)
9170 ("r-genomicranges" ,r-genomicranges)
9171 ("r-gtools" ,r-gtools)
9172 ("r-iranges" ,r-iranges)
9173 ("r-matrixstats" ,r-matrixstats)
9174 ("r-rsamtools" ,r-rsamtools)
9175 ("r-s4vectors" ,r-s4vectors)))
9176 (home-page "https://github.com/PeeperLab/CopywriteR")
9177 (synopsis "Copy number information from targeted sequencing")
9179 "CopywriteR extracts DNA copy number information from targeted sequencing
9180 by utilizing off-target reads. It allows for extracting uniformly distributed
9181 copy number information, can be used without reference, and can be applied to
9182 sequencing data obtained from various techniques including chromatin
9183 immunoprecipitation and target enrichment on small gene panels. Thereby,
9184 CopywriteR constitutes a widely applicable alternative to available copy
9185 number detection tools.")
9186 (license license:gpl2)))
9188 (define-public r-methylkit
9190 (name "r-methylkit")
9194 (uri (bioconductor-uri "methylKit" version))
9197 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9198 (properties `((upstream-name . "methylKit")))
9199 (build-system r-build-system)
9201 `(("r-data-table" ,r-data-table)
9202 ("r-emdbook" ,r-emdbook)
9203 ("r-fastseg" ,r-fastseg)
9204 ("r-genomeinfodb" ,r-genomeinfodb)
9205 ("r-genomicranges" ,r-genomicranges)
9206 ("r-gtools" ,r-gtools)
9207 ("r-iranges" ,r-iranges)
9208 ("r-kernsmooth" ,r-kernsmooth)
9209 ("r-limma" ,r-limma)
9210 ("r-mclust" ,r-mclust)
9211 ("r-qvalue" ,r-qvalue)
9212 ("r-r-utils" ,r-r-utils)
9214 ("r-rhtslib" ,r-rhtslib)
9215 ("r-rsamtools" ,r-rsamtools)
9216 ("r-rtracklayer" ,r-rtracklayer)
9217 ("r-s4vectors" ,r-s4vectors)
9218 ("r-zlibbioc" ,r-zlibbioc)))
9221 (home-page "https://github.com/al2na/methylKit")
9223 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9225 "MethylKit is an R package for DNA methylation analysis and annotation
9226 from high-throughput bisulfite sequencing. The package is designed to deal
9227 with sequencing data from @dfn{Reduced representation bisulfite
9228 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9229 genome bisulfite sequencing. It also has functions to analyze base-pair
9230 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9232 (license license:artistic2.0)))
9234 (define-public r-sva
9241 (uri (bioconductor-uri "sva" version))
9244 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9245 (build-system r-build-system)
9247 `(("r-genefilter" ,r-genefilter)
9249 ("r-biocparallel" ,r-biocparallel)
9250 ("r-matrixstats" ,r-matrixstats)
9251 ("r-limma" ,r-limma)))
9252 (home-page "https://bioconductor.org/packages/sva")
9253 (synopsis "Surrogate variable analysis")
9255 "This package contains functions for removing batch effects and other
9256 unwanted variation in high-throughput experiment. It also contains functions
9257 for identifying and building surrogate variables for high-dimensional data
9258 sets. Surrogate variables are covariates constructed directly from
9259 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9260 imaging data that can be used in subsequent analyses to adjust for unknown,
9261 unmodeled, or latent sources of noise.")
9262 (license license:artistic2.0)))
9264 (define-public r-seqminer
9271 (uri (cran-uri "seqminer" version))
9274 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9275 (build-system r-build-system)
9278 (home-page "http://seqminer.genomic.codes")
9279 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9281 "This package provides tools to integrate nucleotide sequencing
9282 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9283 ;; Any version of the GPL is acceptable
9284 (license (list license:gpl2+ license:gpl3+))))
9286 (define-public r-raremetals2
9288 (name "r-raremetals2")
9293 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9294 "b/b7/RareMETALS2_" version ".tar.gz"))
9297 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9298 (properties `((upstream-name . "RareMETALS2")))
9299 (build-system r-build-system)
9301 `(("r-seqminer" ,r-seqminer)
9302 ("r-mvtnorm" ,r-mvtnorm)
9304 ("r-compquadform" ,r-compquadform)
9305 ("r-getopt" ,r-getopt)))
9306 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9307 (synopsis "Analyze gene-level association tests for binary trait")
9309 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9310 It was designed to meta-analyze gene-level association tests for binary trait.
9311 While rareMETALS offers a near-complete solution for meta-analysis of
9312 gene-level tests for quantitative trait, it does not offer the optimal
9313 solution for binary trait. The package rareMETALS2 offers improved features
9314 for analyzing gene-level association tests in meta-analyses for binary
9316 (license license:gpl3)))
9318 (define-public r-maldiquant
9320 (name "r-maldiquant")
9325 (uri (cran-uri "MALDIquant" version))
9328 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9329 (properties `((upstream-name . "MALDIquant")))
9330 (build-system r-build-system)
9331 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9332 (synopsis "Quantitative analysis of mass spectrometry data")
9334 "This package provides a complete analysis pipeline for matrix-assisted
9335 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9336 two-dimensional mass spectrometry data. In addition to commonly used plotting
9337 and processing methods it includes distinctive features, namely baseline
9338 subtraction methods such as morphological filters (TopHat) or the
9339 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9340 alignment using warping functions, handling of replicated measurements as well
9341 as allowing spectra with different resolutions.")
9342 (license license:gpl3+)))
9344 (define-public r-protgenerics
9346 (name "r-protgenerics")
9351 (uri (bioconductor-uri "ProtGenerics" version))
9354 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9355 (properties `((upstream-name . "ProtGenerics")))
9356 (build-system r-build-system)
9357 (home-page "https://github.com/lgatto/ProtGenerics")
9358 (synopsis "S4 generic functions for proteomics infrastructure")
9360 "This package provides S4 generic functions needed by Bioconductor
9361 proteomics packages.")
9362 (license license:artistic2.0)))
9364 (define-public r-mzr
9371 (uri (bioconductor-uri "mzR" version))
9374 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9375 (modules '((guix build utils)))
9378 (delete-file-recursively "src/boost")
9380 (properties `((upstream-name . "mzR")))
9381 (build-system r-build-system)
9384 (modify-phases %standard-phases
9385 (add-after 'unpack 'use-system-boost
9387 (substitute* "src/Makevars"
9388 (("\\./boost/libs.*") "")
9389 (("ARCH_OBJS=" line)
9391 "\nARCH_LIBS=-lboost_system -lboost_regex \
9392 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9395 `(("boost" ,boost) ; use this instead of the bundled boost sources
9396 ("netcdf" ,netcdf)))
9398 `(("r-biobase" ,r-biobase)
9399 ("r-biocgenerics" ,r-biocgenerics)
9400 ("r-protgenerics" ,r-protgenerics)
9402 ("r-zlibbioc" ,r-zlibbioc)))
9403 (home-page "https://github.com/sneumann/mzR/")
9404 (synopsis "Parser for mass spectrometry data files")
9406 "The mzR package provides a unified API to the common file formats and
9407 parsers available for mass spectrometry data. It comes with a wrapper for the
9408 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9409 The package contains the original code written by the ISB, and a subset of the
9410 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9411 previously been used in XCMS.")
9412 (license license:artistic2.0)))
9414 (define-public r-affyio
9421 (uri (bioconductor-uri "affyio" version))
9424 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9425 (build-system r-build-system)
9427 `(("r-zlibbioc" ,r-zlibbioc)))
9430 (home-page "https://github.com/bmbolstad/affyio")
9431 (synopsis "Tools for parsing Affymetrix data files")
9433 "This package provides routines for parsing Affymetrix data files based
9434 upon file format information. The primary focus is on accessing the CEL and
9436 (license license:lgpl2.0+)))
9438 (define-public r-affy
9445 (uri (bioconductor-uri "affy" version))
9448 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9449 (build-system r-build-system)
9451 `(("r-affyio" ,r-affyio)
9452 ("r-biobase" ,r-biobase)
9453 ("r-biocgenerics" ,r-biocgenerics)
9454 ("r-biocinstaller" ,r-biocinstaller)
9455 ("r-preprocesscore" ,r-preprocesscore)
9456 ("r-zlibbioc" ,r-zlibbioc)))
9457 (home-page "https://bioconductor.org/packages/affy")
9458 (synopsis "Methods for affymetrix oligonucleotide arrays")
9460 "This package contains functions for exploratory oligonucleotide array
9462 (license license:lgpl2.0+)))
9464 (define-public r-vsn
9471 (uri (bioconductor-uri "vsn" version))
9474 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9475 (build-system r-build-system)
9477 `(("r-affy" ,r-affy)
9478 ("r-biobase" ,r-biobase)
9479 ("r-ggplot2" ,r-ggplot2)
9480 ("r-lattice" ,r-lattice)
9481 ("r-limma" ,r-limma)))
9482 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9483 (synopsis "Variance stabilization and calibration for microarray data")
9485 "The package implements a method for normalising microarray intensities,
9486 and works for single- and multiple-color arrays. It can also be used for data
9487 from other technologies, as long as they have similar format. The method uses
9488 a robust variant of the maximum-likelihood estimator for an
9489 additive-multiplicative error model and affine calibration. The model
9490 incorporates data calibration step (a.k.a. normalization), a model for the
9491 dependence of the variance on the mean intensity and a variance stabilizing
9492 data transformation. Differences between transformed intensities are
9493 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9494 their variance is independent of the mean, and they are usually more sensitive
9495 and specific in detecting differential transcription.")
9496 (license license:artistic2.0)))
9498 (define-public r-mzid
9505 (uri (bioconductor-uri "mzID" version))
9508 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9509 (properties `((upstream-name . "mzID")))
9510 (build-system r-build-system)
9512 `(("r-doparallel" ,r-doparallel)
9513 ("r-foreach" ,r-foreach)
9514 ("r-iterators" ,r-iterators)
9516 ("r-protgenerics" ,r-protgenerics)
9519 (home-page "https://bioconductor.org/packages/mzID")
9520 (synopsis "Parser for mzIdentML files")
9522 "This package provides a parser for mzIdentML files implemented using the
9523 XML package. The parser tries to be general and able to handle all types of
9524 mzIdentML files with the drawback of having less pretty output than a vendor
9526 (license license:gpl2+)))
9528 (define-public r-pcamethods
9530 (name "r-pcamethods")
9535 (uri (bioconductor-uri "pcaMethods" version))
9538 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9539 (properties `((upstream-name . "pcaMethods")))
9540 (build-system r-build-system)
9542 `(("r-biobase" ,r-biobase)
9543 ("r-biocgenerics" ,r-biocgenerics)
9545 ("r-rcpp" ,r-rcpp)))
9546 (home-page "https://github.com/hredestig/pcamethods")
9547 (synopsis "Collection of PCA methods")
9549 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9550 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9551 for missing value estimation is included for comparison. BPCA, PPCA and
9552 NipalsPCA may be used to perform PCA on incomplete data as well as for
9553 accurate missing value estimation. A set of methods for printing and plotting
9554 the results is also provided. All PCA methods make use of the same data
9555 structure (pcaRes) to provide a common interface to the PCA results.")
9556 (license license:gpl3+)))
9558 (define-public r-msnbase
9565 (uri (bioconductor-uri "MSnbase" version))
9568 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9569 (properties `((upstream-name . "MSnbase")))
9570 (build-system r-build-system)
9572 `(("r-affy" ,r-affy)
9573 ("r-biobase" ,r-biobase)
9574 ("r-biocgenerics" ,r-biocgenerics)
9575 ("r-biocparallel" ,r-biocparallel)
9576 ("r-digest" ,r-digest)
9577 ("r-ggplot2" ,r-ggplot2)
9578 ("r-impute" ,r-impute)
9579 ("r-iranges" ,r-iranges)
9580 ("r-lattice" ,r-lattice)
9581 ("r-maldiquant" ,r-maldiquant)
9584 ("r-pcamethods" ,r-pcamethods)
9586 ("r-preprocesscore" ,r-preprocesscore)
9587 ("r-protgenerics" ,r-protgenerics)
9589 ("r-s4vectors" ,r-s4vectors)
9592 (home-page "https://github.com/lgatto/MSnbase")
9593 (synopsis "Base functions and classes for MS-based proteomics")
9595 "This package provides basic plotting, data manipulation and processing
9596 of mass spectrometry based proteomics data.")
9597 (license license:artistic2.0)))
9599 (define-public r-msnid
9606 (uri (bioconductor-uri "MSnID" version))
9609 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9610 (properties `((upstream-name . "MSnID")))
9611 (build-system r-build-system)
9613 `(("r-biobase" ,r-biobase)
9614 ("r-data-table" ,r-data-table)
9615 ("r-doparallel" ,r-doparallel)
9616 ("r-dplyr" ,r-dplyr)
9617 ("r-foreach" ,r-foreach)
9618 ("r-iterators" ,r-iterators)
9619 ("r-msnbase" ,r-msnbase)
9622 ("r-protgenerics" ,r-protgenerics)
9623 ("r-r-cache" ,r-r-cache)
9625 ("r-reshape2" ,r-reshape2)))
9626 (home-page "https://bioconductor.org/packages/MSnID")
9627 (synopsis "Utilities for LC-MSn proteomics identifications")
9629 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9630 from mzIdentML (leveraging the mzID package) or text files. After collating
9631 the search results from multiple datasets it assesses their identification
9632 quality and optimize filtering criteria to achieve the maximum number of
9633 identifications while not exceeding a specified false discovery rate. It also
9634 contains a number of utilities to explore the MS/MS results and assess missed
9635 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9636 (license license:artistic2.0)))
9638 (define-public r-seurat
9644 (uri (cran-uri "Seurat" version))
9647 "0kp3lw1s896zkjd6x2wp8qcg7wnm5b40g8vihps13f1m7j4nx7r0"))
9648 ;; Delete pre-built jar.
9650 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9652 (properties `((upstream-name . "Seurat")))
9653 (build-system r-build-system)
9656 (modify-phases %standard-phases
9657 (add-after 'unpack 'build-jar
9658 (lambda* (#:key inputs #:allow-other-keys)
9659 (let ((classesdir "tmp-classes"))
9660 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9662 (with-output-to-file "manifest"
9664 (display "Manifest-Version: 1.0
9665 Main-Class: ModularityOptimizer\n")))
9666 (and (zero? (apply system* `("javac" "-d" ,classesdir
9667 ,@(find-files "java" "\\.java$"))))
9668 (zero? (system* "jar"
9670 "inst/java/ModularityOptimizer.jar"
9671 "-C" classesdir ".")))))))))
9673 `(("jdk" ,icedtea "jdk")))
9676 ("r-caret" ,r-caret)
9677 ("r-cluster" ,r-cluster)
9678 ("r-cowplot" ,r-cowplot)
9679 ("r-diffusionmap" ,r-diffusionmap)
9680 ("r-dosnow" ,r-dosnow)
9681 ("r-dplyr" ,r-dplyr)
9683 ("r-fitdistrplus" ,r-fitdistrplus)
9685 ("r-foreach" ,r-foreach)
9687 ("r-gdata" ,r-gdata)
9688 ("r-ggplot2" ,r-ggplot2)
9689 ("r-ggridges" ,r-ggridges)
9690 ("r-gplots" ,r-gplots)
9691 ("r-gridextra" ,r-gridextra)
9692 ("r-hmisc" ,r-hmisc)
9694 ("r-igraph" ,r-igraph)
9695 ("r-irlba" ,r-irlba)
9697 ("r-lmtest" ,r-lmtest)
9699 ("r-matrix" ,r-matrix)
9700 ("r-metap" ,r-metap)
9701 ("r-mixtools" ,r-mixtools)
9702 ("r-pbapply" ,r-pbapply)
9703 ("r-plotly" ,r-plotly)
9705 ("r-ranger" ,r-ranger)
9707 ("r-rcolorbrewer" ,r-rcolorbrewer)
9709 ("r-rcppeigen" ,r-rcppeigen)
9710 ("r-rcppprogress" ,r-rcppprogress)
9711 ("r-reshape2" ,r-reshape2)
9713 ("r-rtsne" ,r-rtsne)
9714 ("r-sdmtools" ,r-sdmtools)
9715 ("r-stringr" ,r-stringr)
9716 ("r-tclust" ,r-tclust)
9717 ("r-tidyr" ,r-tidyr)
9719 ("r-vgam" ,r-vgam)))
9720 (home-page "http://www.satijalab.org/seurat")
9721 (synopsis "Seurat is an R toolkit for single cell genomics")
9723 "This package is an R package designed for QC, analysis, and
9724 exploration of single cell RNA-seq data. It easily enables widely-used
9725 analytical techniques, including the identification of highly variable genes,
9726 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9727 algorithms; density clustering, hierarchical clustering, k-means, and the
9728 discovery of differentially expressed genes and markers.")
9729 (license license:gpl3)))
9731 (define-public r-aroma-light
9733 (name "r-aroma-light")
9738 (uri (bioconductor-uri "aroma.light" version))
9741 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9742 (properties `((upstream-name . "aroma.light")))
9743 (build-system r-build-system)
9745 `(("r-matrixstats" ,r-matrixstats)
9746 ("r-r-methodss3" ,r-r-methodss3)
9748 ("r-r-utils" ,r-r-utils)))
9749 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9750 (synopsis "Methods for normalization and visualization of microarray data")
9752 "This package provides methods for microarray analysis that take basic
9753 data types such as matrices and lists of vectors. These methods can be used
9754 standalone, be utilized in other packages, or be wrapped up in higher-level
9756 (license license:gpl2+)))
9758 (define-public r-deseq
9765 (uri (bioconductor-uri "DESeq" version))
9768 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9769 (properties `((upstream-name . "DESeq")))
9770 (build-system r-build-system)
9772 `(("r-biobase" ,r-biobase)
9773 ("r-biocgenerics" ,r-biocgenerics)
9774 ("r-genefilter" ,r-genefilter)
9775 ("r-geneplotter" ,r-geneplotter)
9776 ("r-lattice" ,r-lattice)
9777 ("r-locfit" ,r-locfit)
9779 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9780 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9781 (synopsis "Differential gene expression analysis")
9783 "This package provides tools for estimating variance-mean dependence in
9784 count data from high-throughput genetic sequencing assays and for testing for
9785 differential expression based on a model using the negative binomial
9787 (license license:gpl3+)))
9789 (define-public r-edaseq
9796 (uri (bioconductor-uri "EDASeq" version))
9799 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9800 (properties `((upstream-name . "EDASeq")))
9801 (build-system r-build-system)
9803 `(("r-annotationdbi" ,r-annotationdbi)
9804 ("r-aroma-light" ,r-aroma-light)
9805 ("r-biobase" ,r-biobase)
9806 ("r-biocgenerics" ,r-biocgenerics)
9807 ("r-biomart" ,r-biomart)
9808 ("r-biostrings" ,r-biostrings)
9809 ("r-deseq" ,r-deseq)
9810 ("r-genomicfeatures" ,r-genomicfeatures)
9811 ("r-genomicranges" ,r-genomicranges)
9812 ("r-iranges" ,r-iranges)
9813 ("r-rsamtools" ,r-rsamtools)
9814 ("r-shortread" ,r-shortread)))
9815 (home-page "https://github.com/drisso/EDASeq")
9816 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9818 "This package provides support for numerical and graphical summaries of
9819 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9820 adjust for GC-content effect (or other gene-level effects) on read counts:
9821 loess robust local regression, global-scaling, and full-quantile
9822 normalization. Between-lane normalization procedures to adjust for
9823 distributional differences between lanes (e.g., sequencing depth):
9824 global-scaling and full-quantile normalization.")
9825 (license license:artistic2.0)))
9827 (define-public r-interactivedisplaybase
9829 (name "r-interactivedisplaybase")
9834 (uri (bioconductor-uri "interactiveDisplayBase" version))
9837 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9839 `((upstream-name . "interactiveDisplayBase")))
9840 (build-system r-build-system)
9842 `(("r-biocgenerics" ,r-biocgenerics)
9843 ("r-shiny" ,r-shiny)))
9844 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9845 (synopsis "Base package for web displays of Bioconductor objects")
9847 "This package contains the basic methods needed to generate interactive
9848 Shiny-based display methods for Bioconductor objects.")
9849 (license license:artistic2.0)))
9851 (define-public r-annotationhub
9853 (name "r-annotationhub")
9858 (uri (bioconductor-uri "AnnotationHub" version))
9861 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9862 (properties `((upstream-name . "AnnotationHub")))
9863 (build-system r-build-system)
9865 `(("r-annotationdbi" ,r-annotationdbi)
9866 ("r-biocgenerics" ,r-biocgenerics)
9867 ("r-biocinstaller" ,r-biocinstaller)
9870 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9871 ("r-rsqlite" ,r-rsqlite)
9872 ("r-s4vectors" ,r-s4vectors)
9873 ("r-yaml" ,r-yaml)))
9874 (home-page "https://bioconductor.org/packages/AnnotationHub")
9875 (synopsis "Client to access AnnotationHub resources")
9877 "This package provides a client for the Bioconductor AnnotationHub web
9878 resource. The AnnotationHub web resource provides a central location where
9879 genomic files (e.g. VCF, bed, wig) and other resources from standard
9880 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9881 metadata about each resource, e.g., a textual description, tags, and date of
9882 modification. The client creates and manages a local cache of files retrieved
9883 by the user, helping with quick and reproducible access.")
9884 (license license:artistic2.0)))
9886 (define-public r-fastseg
9893 (uri (bioconductor-uri "fastseg" version))
9896 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9897 (build-system r-build-system)
9899 `(("r-biobase" ,r-biobase)
9900 ("r-biocgenerics" ,r-biocgenerics)
9901 ("r-genomicranges" ,r-genomicranges)
9902 ("r-iranges" ,r-iranges)
9903 ("r-s4vectors" ,r-s4vectors)))
9904 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9905 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9907 "Fastseg implements a very fast and efficient segmentation algorithm.
9908 It can segment data from DNA microarrays and data from next generation
9909 sequencing for example to detect copy number segments. Further it can segment
9910 data from RNA microarrays like tiling arrays to identify transcripts. Most
9911 generally, it can segment data given as a matrix or as a vector. Various data
9912 formats can be used as input to fastseg like expression set objects for
9913 microarrays or GRanges for sequencing data.")
9914 (license license:lgpl2.0+)))
9916 (define-public r-keggrest
9923 (uri (bioconductor-uri "KEGGREST" version))
9926 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9927 (properties `((upstream-name . "KEGGREST")))
9928 (build-system r-build-system)
9930 `(("r-biostrings" ,r-biostrings)
9933 (home-page "https://bioconductor.org/packages/KEGGREST")
9934 (synopsis "Client-side REST access to KEGG")
9936 "This package provides a package that provides a client interface to the
9937 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9938 (license license:artistic2.0)))
9940 (define-public r-gage
9947 (uri (bioconductor-uri "gage" version))
9950 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9951 (build-system r-build-system)
9953 `(("r-annotationdbi" ,r-annotationdbi)
9954 ("r-graph" ,r-graph)
9955 ("r-keggrest" ,r-keggrest)))
9956 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9957 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9959 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9960 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9961 data attributes including sample sizes, experimental designs, assay platforms,
9962 and other types of heterogeneity. The gage package provides functions for
9963 basic GAGE analysis, result processing and presentation. In addition, it
9964 provides demo microarray data and commonly used gene set data based on KEGG
9965 pathways and GO terms. These funtions and data are also useful for gene set
9966 analysis using other methods.")
9967 (license license:gpl2+)))
9969 (define-public r-genomicfiles
9971 (name "r-genomicfiles")
9976 (uri (bioconductor-uri "GenomicFiles" version))
9979 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9980 (properties `((upstream-name . "GenomicFiles")))
9981 (build-system r-build-system)
9983 `(("r-biocgenerics" ,r-biocgenerics)
9984 ("r-biocparallel" ,r-biocparallel)
9985 ("r-genomeinfodb" ,r-genomeinfodb)
9986 ("r-genomicalignments" ,r-genomicalignments)
9987 ("r-genomicranges" ,r-genomicranges)
9988 ("r-iranges" ,r-iranges)
9989 ("r-rsamtools" ,r-rsamtools)
9990 ("r-rtracklayer" ,r-rtracklayer)
9991 ("r-s4vectors" ,r-s4vectors)
9992 ("r-summarizedexperiment" ,r-summarizedexperiment)
9993 ("r-variantannotation" ,r-variantannotation)))
9994 (home-page "https://bioconductor.org/packages/GenomicFiles")
9995 (synopsis "Distributed computing by file or by range")
9997 "This package provides infrastructure for parallel computations
9998 distributed by file or by range. User defined mapper and reducer functions
9999 provide added flexibility for data combination and manipulation.")
10000 (license license:artistic2.0)))
10002 (define-public r-complexheatmap
10004 (name "r-complexheatmap")
10009 (uri (bioconductor-uri "ComplexHeatmap" version))
10012 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
10014 `((upstream-name . "ComplexHeatmap")))
10015 (build-system r-build-system)
10017 `(("r-circlize" ,r-circlize)
10018 ("r-colorspace" ,r-colorspace)
10019 ("r-getoptlong" ,r-getoptlong)
10020 ("r-globaloptions" ,r-globaloptions)
10021 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10023 "https://github.com/jokergoo/ComplexHeatmap")
10024 (synopsis "Making Complex Heatmaps")
10026 "Complex heatmaps are efficient to visualize associations between
10027 different sources of data sets and reveal potential structures. This package
10028 provides a highly flexible way to arrange multiple heatmaps and supports
10029 self-defined annotation graphics.")
10030 (license license:gpl2+)))
10032 (define-public r-dirichletmultinomial
10034 (name "r-dirichletmultinomial")
10039 (uri (bioconductor-uri "DirichletMultinomial" version))
10042 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
10044 `((upstream-name . "DirichletMultinomial")))
10045 (build-system r-build-system)
10049 `(("r-biocgenerics" ,r-biocgenerics)
10050 ("r-iranges" ,r-iranges)
10051 ("r-s4vectors" ,r-s4vectors)))
10052 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10053 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10055 "Dirichlet-multinomial mixture models can be used to describe variability
10056 in microbial metagenomic data. This package is an interface to code
10057 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10059 (license license:lgpl3)))
10061 (define-public r-ensembldb
10063 (name "r-ensembldb")
10068 (uri (bioconductor-uri "ensembldb" version))
10071 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
10072 (build-system r-build-system)
10074 `(("r-annotationdbi" ,r-annotationdbi)
10075 ("r-annotationfilter" ,r-annotationfilter)
10076 ("r-annotationhub" ,r-annotationhub)
10077 ("r-biobase" ,r-biobase)
10078 ("r-biocgenerics" ,r-biocgenerics)
10079 ("r-biostrings" ,r-biostrings)
10082 ("r-genomeinfodb" ,r-genomeinfodb)
10083 ("r-genomicfeatures" ,r-genomicfeatures)
10084 ("r-genomicranges" ,r-genomicranges)
10085 ("r-iranges" ,r-iranges)
10086 ("r-protgenerics" ,r-protgenerics)
10087 ("r-rsamtools" ,r-rsamtools)
10088 ("r-rsqlite" ,r-rsqlite)
10089 ("r-rtracklayer" ,r-rtracklayer)
10090 ("r-s4vectors" ,r-s4vectors)))
10091 (home-page "https://github.com/jotsetung/ensembldb")
10092 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10094 "The package provides functions to create and use transcript-centric
10095 annotation databases/packages. The annotation for the databases are directly
10096 fetched from Ensembl using their Perl API. The functionality and data is
10097 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10098 but, in addition to retrieve all gene/transcript models and annotations from
10099 the database, the @code{ensembldb} package also provides a filter framework
10100 allowing to retrieve annotations for specific entries like genes encoded on a
10101 chromosome region or transcript models of lincRNA genes.")
10102 ;; No version specified
10103 (license license:lgpl3+)))
10105 (define-public r-organismdbi
10107 (name "r-organismdbi")
10112 (uri (bioconductor-uri "OrganismDbi" version))
10115 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
10116 (properties `((upstream-name . "OrganismDbi")))
10117 (build-system r-build-system)
10119 `(("r-annotationdbi" ,r-annotationdbi)
10120 ("r-biobase" ,r-biobase)
10121 ("r-biocgenerics" ,r-biocgenerics)
10122 ("r-biocinstaller" ,r-biocinstaller)
10124 ("r-genomicfeatures" ,r-genomicfeatures)
10125 ("r-genomicranges" ,r-genomicranges)
10126 ("r-graph" ,r-graph)
10127 ("r-iranges" ,r-iranges)
10129 ("r-s4vectors" ,r-s4vectors)))
10130 (home-page "https://bioconductor.org/packages/OrganismDbi")
10131 (synopsis "Software to enable the smooth interfacing of database packages")
10132 (description "The package enables a simple unified interface to several
10133 annotation packages each of which has its own schema by taking advantage of
10134 the fact that each of these packages implements a select methods.")
10135 (license license:artistic2.0)))
10137 (define-public r-biovizbase
10139 (name "r-biovizbase")
10144 (uri (bioconductor-uri "biovizBase" version))
10147 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10148 (properties `((upstream-name . "biovizBase")))
10149 (build-system r-build-system)
10151 `(("r-annotationdbi" ,r-annotationdbi)
10152 ("r-annotationfilter" ,r-annotationfilter)
10153 ("r-biocgenerics" ,r-biocgenerics)
10154 ("r-biostrings" ,r-biostrings)
10155 ("r-dichromat" ,r-dichromat)
10156 ("r-ensembldb" ,r-ensembldb)
10157 ("r-genomeinfodb" ,r-genomeinfodb)
10158 ("r-genomicalignments" ,r-genomicalignments)
10159 ("r-genomicfeatures" ,r-genomicfeatures)
10160 ("r-genomicranges" ,r-genomicranges)
10161 ("r-hmisc" ,r-hmisc)
10162 ("r-iranges" ,r-iranges)
10163 ("r-rcolorbrewer" ,r-rcolorbrewer)
10164 ("r-rsamtools" ,r-rsamtools)
10165 ("r-s4vectors" ,r-s4vectors)
10166 ("r-scales" ,r-scales)
10167 ("r-summarizedexperiment" ,r-summarizedexperiment)
10168 ("r-variantannotation" ,r-variantannotation)))
10169 (home-page "https://bioconductor.org/packages/biovizBase")
10170 (synopsis "Basic graphic utilities for visualization of genomic data")
10172 "The biovizBase package is designed to provide a set of utilities, color
10173 schemes and conventions for genomic data. It serves as the base for various
10174 high-level packages for biological data visualization. This saves development
10175 effort and encourages consistency.")
10176 (license license:artistic2.0)))
10178 (define-public r-ggbio
10185 (uri (bioconductor-uri "ggbio" version))
10188 "1xlmlngn27iwnr21s9di4059kav1a7c1sajx08wja8yn8f7j06hp"))))
10189 (build-system r-build-system)
10191 `(("r-annotationdbi" ,r-annotationdbi)
10192 ("r-annotationfilter" ,r-annotationfilter)
10193 ("r-biobase" ,r-biobase)
10194 ("r-biocgenerics" ,r-biocgenerics)
10195 ("r-biostrings" ,r-biostrings)
10196 ("r-biovizbase" ,r-biovizbase)
10197 ("r-bsgenome" ,r-bsgenome)
10198 ("r-ensembldb" ,r-ensembldb)
10199 ("r-genomeinfodb" ,r-genomeinfodb)
10200 ("r-genomicalignments" ,r-genomicalignments)
10201 ("r-genomicfeatures" ,r-genomicfeatures)
10202 ("r-genomicranges" ,r-genomicranges)
10203 ("r-ggally" ,r-ggally)
10204 ("r-ggplot2" ,r-ggplot2)
10205 ("r-gridextra" ,r-gridextra)
10206 ("r-gtable" ,r-gtable)
10207 ("r-hmisc" ,r-hmisc)
10208 ("r-iranges" ,r-iranges)
10209 ("r-organismdbi" ,r-organismdbi)
10210 ("r-reshape2" ,r-reshape2)
10211 ("r-rsamtools" ,r-rsamtools)
10212 ("r-rtracklayer" ,r-rtracklayer)
10213 ("r-s4vectors" ,r-s4vectors)
10214 ("r-scales" ,r-scales)
10215 ("r-summarizedexperiment" ,r-summarizedexperiment)
10216 ("r-variantannotation" ,r-variantannotation)))
10217 (home-page "http://www.tengfei.name/ggbio/")
10218 (synopsis "Visualization tools for genomic data")
10220 "The ggbio package extends and specializes the grammar of graphics for
10221 biological data. The graphics are designed to answer common scientific
10222 questions, in particular those often asked of high throughput genomics data.
10223 All core Bioconductor data structures are supported, where appropriate. The
10224 package supports detailed views of particular genomic regions, as well as
10225 genome-wide overviews. Supported overviews include ideograms and grand linear
10226 views. High-level plots include sequence fragment length, edge-linked
10227 interval to data view, mismatch pileup, and several splicing summaries.")
10228 (license license:artistic2.0)))
10230 (define-public r-gprofiler
10232 (name "r-gprofiler")
10237 (uri (cran-uri "gProfileR" version))
10240 "1n6cj12j102b4x9vhyl4dljp1i0r43p23cnhqbx4als2xfxdlqgi"))))
10241 (properties `((upstream-name . "gProfileR")))
10242 (build-system r-build-system)
10244 `(("r-plyr" ,r-plyr)
10245 ("r-rcurl" ,r-rcurl)))
10246 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10247 (synopsis "Interface to the g:Profiler toolkit")
10249 "This package provides tools for functional enrichment analysis,
10250 gene identifier conversion and mapping homologous genes across related
10251 organisms via the @code{g:Profiler} toolkit.")
10252 (license license:gpl2+)))
10254 (define-public r-gqtlbase
10256 (name "r-gqtlbase")
10261 (uri (bioconductor-uri "gQTLBase" version))
10264 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10265 (properties `((upstream-name . "gQTLBase")))
10266 (build-system r-build-system)
10268 `(("r-batchjobs" ,r-batchjobs)
10269 ("r-bbmisc" ,r-bbmisc)
10270 ("r-biocgenerics" ,r-biocgenerics)
10272 ("r-doparallel" ,r-doparallel)
10274 ("r-ffbase" ,r-ffbase)
10275 ("r-foreach" ,r-foreach)
10276 ("r-genomicfiles" ,r-genomicfiles)
10277 ("r-genomicranges" ,r-genomicranges)
10278 ("r-rtracklayer" ,r-rtracklayer)
10279 ("r-s4vectors" ,r-s4vectors)
10280 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10281 (home-page "https://bioconductor.org/packages/gQTLBase")
10282 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10284 "The purpose of this package is to simplify the storage and interrogation
10285 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10287 (license license:artistic2.0)))
10289 (define-public r-snpstats
10291 (name "r-snpstats")
10296 (uri (bioconductor-uri "snpStats" version))
10299 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10300 (properties `((upstream-name . "snpStats")))
10301 (build-system r-build-system)
10302 (inputs `(("zlib" ,zlib)))
10304 `(("r-biocgenerics" ,r-biocgenerics)
10305 ("r-matrix" ,r-matrix)
10306 ("r-survival" ,r-survival)
10307 ("r-zlibbioc" ,r-zlibbioc)))
10308 (home-page "https://bioconductor.org/packages/snpStats")
10309 (synopsis "Methods for SNP association studies")
10311 "This package provides classes and statistical methods for large
10312 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10313 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10314 (license license:gpl3)))
10316 (define-public r-homo-sapiens
10318 (name "r-homo-sapiens")
10322 ;; We cannot use bioconductor-uri here because this tarball is
10323 ;; located under "data/annotation/" instead of "bioc/".
10324 (uri (string-append "http://www.bioconductor.org/packages/"
10325 "release/data/annotation/src/contrib/"
10327 version ".tar.gz"))
10330 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10332 `((upstream-name . "Homo.sapiens")))
10333 (build-system r-build-system)
10335 `(("r-genomicfeatures" ,r-genomicfeatures)
10336 ("r-go-db" ,r-go-db)
10337 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10338 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10339 ("r-organismdbi" ,r-organismdbi)
10340 ("r-annotationdbi" ,r-annotationdbi)))
10341 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10342 (synopsis "Annotation package for the Homo.sapiens object")
10344 "This package contains the Homo.sapiens object to access data from
10345 several related annotation packages.")
10346 (license license:artistic2.0)))
10348 (define-public r-erma
10355 (uri (bioconductor-uri "erma" version))
10358 "1fi8nc6fbd7i4p9i9hli31xplmdpsxqcdrb8v3nf8fx9klllbdav"))))
10359 (build-system r-build-system)
10361 `(("r-annotationdbi" ,r-annotationdbi)
10362 ("r-biobase" ,r-biobase)
10363 ("r-biocgenerics" ,r-biocgenerics)
10364 ("r-foreach" ,r-foreach)
10365 ("r-genomicfiles" ,r-genomicfiles)
10366 ("r-genomicranges" ,r-genomicranges)
10367 ("r-ggplot2" ,r-ggplot2)
10368 ("r-homo-sapiens" ,r-homo-sapiens)
10369 ("r-rtracklayer" ,r-rtracklayer)
10370 ("r-s4vectors" ,r-s4vectors)
10371 ("r-shiny" ,r-shiny)
10372 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10373 (home-page "https://bioconductor.org/packages/erma")
10374 (synopsis "Epigenomic road map adventures")
10376 "The epigenomics road map describes locations of epigenetic marks in DNA
10377 from a variety of cell types. Of interest are locations of histone
10378 modifications, sites of DNA methylation, and regions of accessible chromatin.
10379 This package presents a selection of elements of the road map including
10380 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10381 by Ernst and Kellis.")
10382 (license license:artistic2.0)))
10384 (define-public r-ldblock
10391 (uri (bioconductor-uri "ldblock" version))
10394 "1q8dz8wcq1r7kr635s9q21g36sxkdybk8khhpa4p57qv8r0gppl0"))))
10395 (build-system r-build-system)
10397 `(("r-erma" ,r-erma)
10398 ("r-genomeinfodb" ,r-genomeinfodb)
10399 ("r-genomicfiles" ,r-genomicfiles)
10400 ("r-go-db" ,r-go-db)
10401 ("r-homo-sapiens" ,r-homo-sapiens)
10402 ("r-matrix" ,r-matrix)
10403 ("r-rsamtools" ,r-rsamtools)
10404 ("r-snpstats" ,r-snpstats)
10405 ("r-variantannotation" ,r-variantannotation)))
10406 (home-page "https://bioconductor.org/packages/ldblock")
10407 (synopsis "Data structures for linkage disequilibrium measures in populations")
10409 "This package defines data structures for @dfn{linkage
10410 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10411 handling of existing population-level data for the purpose of flexibly
10412 defining LD blocks.")
10413 (license license:artistic2.0)))
10415 (define-public r-gqtlstats
10417 (name "r-gqtlstats")
10422 (uri (bioconductor-uri "gQTLstats" version))
10425 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10426 (properties `((upstream-name . "gQTLstats")))
10427 (build-system r-build-system)
10429 `(("r-annotationdbi" ,r-annotationdbi)
10430 ("r-batchjobs" ,r-batchjobs)
10431 ("r-bbmisc" ,r-bbmisc)
10432 ("r-beeswarm" ,r-beeswarm)
10433 ("r-biobase" ,r-biobase)
10434 ("r-biocgenerics" ,r-biocgenerics)
10435 ("r-doparallel" ,r-doparallel)
10436 ("r-dplyr" ,r-dplyr)
10438 ("r-ffbase" ,r-ffbase)
10439 ("r-foreach" ,r-foreach)
10440 ("r-genomeinfodb" ,r-genomeinfodb)
10441 ("r-genomicfeatures" ,r-genomicfeatures)
10442 ("r-genomicfiles" ,r-genomicfiles)
10443 ("r-genomicranges" ,r-genomicranges)
10444 ("r-ggbeeswarm" ,r-ggbeeswarm)
10445 ("r-ggplot2" ,r-ggplot2)
10446 ("r-gqtlbase" ,r-gqtlbase)
10447 ("r-hardyweinberg" ,r-hardyweinberg)
10448 ("r-iranges" ,r-iranges)
10449 ("r-ldblock" ,r-ldblock)
10450 ("r-limma" ,r-limma)
10452 ("r-plotly" ,r-plotly)
10453 ("r-reshape2" ,r-reshape2)
10454 ("r-s4vectors" ,r-s4vectors)
10455 ("r-shiny" ,r-shiny)
10456 ("r-snpstats" ,r-snpstats)
10457 ("r-summarizedexperiment" ,r-summarizedexperiment)
10458 ("r-variantannotation" ,r-variantannotation)))
10459 (home-page "https://bioconductor.org/packages/gQTLstats")
10460 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10462 "This package provides tools for the computationally efficient analysis
10463 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10464 The software in this package aims to support refinements and functional
10465 interpretation of members of a collection of association statistics on a
10466 family of feature/genome hypotheses.")
10467 (license license:artistic2.0)))
10469 (define-public r-gviz
10476 (uri (bioconductor-uri "Gviz" version))
10479 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10480 (properties `((upstream-name . "Gviz")))
10481 (build-system r-build-system)
10483 `(("r-annotationdbi" ,r-annotationdbi)
10484 ("r-biobase" ,r-biobase)
10485 ("r-biocgenerics" ,r-biocgenerics)
10486 ("r-biomart" ,r-biomart)
10487 ("r-biostrings" ,r-biostrings)
10488 ("r-biovizbase" ,r-biovizbase)
10489 ("r-bsgenome" ,r-bsgenome)
10490 ("r-digest" ,r-digest)
10491 ("r-genomeinfodb" ,r-genomeinfodb)
10492 ("r-genomicalignments" ,r-genomicalignments)
10493 ("r-genomicfeatures" ,r-genomicfeatures)
10494 ("r-genomicranges" ,r-genomicranges)
10495 ("r-iranges" ,r-iranges)
10496 ("r-lattice" ,r-lattice)
10497 ("r-latticeextra" ,r-latticeextra)
10498 ("r-matrixstats" ,r-matrixstats)
10499 ("r-rcolorbrewer" ,r-rcolorbrewer)
10500 ("r-rsamtools" ,r-rsamtools)
10501 ("r-rtracklayer" ,r-rtracklayer)
10502 ("r-s4vectors" ,r-s4vectors)
10503 ("r-xvector" ,r-xvector)))
10504 (home-page "https://bioconductor.org/packages/Gviz")
10505 (synopsis "Plotting data and annotation information along genomic coordinates")
10507 "Genomic data analyses requires integrated visualization of known genomic
10508 information and new experimental data. Gviz uses the biomaRt and the
10509 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10510 and translates this to e.g. gene/transcript structures in viewports of the
10511 grid graphics package. This results in genomic information plotted together
10513 (license license:artistic2.0)))
10515 (define-public r-gwascat
10522 (uri (bioconductor-uri "gwascat" version))
10525 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10526 (build-system r-build-system)
10528 `(("r-annotationdbi" ,r-annotationdbi)
10529 ("r-annotationhub" ,r-annotationhub)
10530 ("r-biocgenerics" ,r-biocgenerics)
10531 ("r-biostrings" ,r-biostrings)
10532 ("r-genomeinfodb" ,r-genomeinfodb)
10533 ("r-genomicfeatures" ,r-genomicfeatures)
10534 ("r-genomicranges" ,r-genomicranges)
10535 ("r-ggbio" ,r-ggbio)
10536 ("r-ggplot2" ,r-ggplot2)
10537 ("r-gqtlstats" ,r-gqtlstats)
10538 ("r-graph" ,r-graph)
10540 ("r-homo-sapiens" ,r-homo-sapiens)
10541 ("r-iranges" ,r-iranges)
10542 ("r-rsamtools" ,r-rsamtools)
10543 ("r-rtracklayer" ,r-rtracklayer)
10544 ("r-s4vectors" ,r-s4vectors)
10545 ("r-snpstats" ,r-snpstats)
10546 ("r-summarizedexperiment" ,r-summarizedexperiment)
10547 ("r-variantannotation" ,r-variantannotation)))
10548 (home-page "https://bioconductor.org/packages/gwascat")
10549 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10551 "This package provides tools for representing and modeling data in the
10552 EMBL-EBI GWAS catalog.")
10553 (license license:artistic2.0)))
10555 (define-public r-sushi
10561 (uri (bioconductor-uri "Sushi" version))
10564 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10565 (properties `((upstream-name . "Sushi")))
10566 (build-system r-build-system)
10568 `(("r-biomart" ,r-biomart)
10570 (home-page "https://bioconductor.org/packages/Sushi")
10571 (synopsis "Tools for visualizing genomics data")
10573 "This package provides flexible, quantitative, and integrative genomic
10574 visualizations for publication-quality multi-panel figures.")
10575 (license license:gpl2+)))
10577 (define-public r-fithic
10583 (uri (bioconductor-uri "FitHiC" version))
10586 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10587 (properties `((upstream-name . "FitHiC")))
10588 (build-system r-build-system)
10590 `(("r-data-table" ,r-data-table)
10591 ("r-fdrtool" ,r-fdrtool)
10592 ("r-rcpp" ,r-rcpp)))
10593 (home-page "https://bioconductor.org/packages/FitHiC")
10594 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10596 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10597 intra-chromosomal contact maps produced by genome-wide genome architecture
10598 assays such as Hi-C.")
10599 (license license:gpl2+)))
10601 (define-public r-hitc
10607 (uri (bioconductor-uri "HiTC" version))
10610 "0da1jw9my2n2gihs31zyn14wwr23d8v2vij39ll7rm6fma3ydfbl"))))
10611 (properties `((upstream-name . "HiTC")))
10612 (build-system r-build-system)
10614 `(("r-biostrings" ,r-biostrings)
10615 ("r-genomeinfodb" ,r-genomeinfodb)
10616 ("r-genomicranges" ,r-genomicranges)
10617 ("r-iranges" ,r-iranges)
10618 ("r-matrix" ,r-matrix)
10619 ("r-rcolorbrewer" ,r-rcolorbrewer)
10620 ("r-rtracklayer" ,r-rtracklayer)))
10621 (home-page "https://bioconductor.org/packages/HiTC")
10622 (synopsis "High throughput chromosome conformation capture analysis")
10624 "The HiTC package was developed to explore high-throughput \"C\" data
10625 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10626 quality controls, normalization, visualization, and further analysis are also
10628 (license license:artistic2.0)))
10630 (define-public r-qvalue
10637 (uri (bioconductor-uri "qvalue" version))
10640 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10641 (build-system r-build-system)
10643 `(("r-ggplot2" ,r-ggplot2)
10644 ("r-reshape2" ,r-reshape2)))
10645 (home-page "http://github.com/jdstorey/qvalue")
10646 (synopsis "Q-value estimation for false discovery rate control")
10648 "This package takes a list of p-values resulting from the simultaneous
10649 testing of many hypotheses and estimates their q-values and local @dfn{false
10650 discovery rate} (FDR) values. The q-value of a test measures the proportion
10651 of false positives incurred when that particular test is called significant.
10652 The local FDR measures the posterior probability the null hypothesis is true
10653 given the test's p-value. Various plots are automatically generated, allowing
10654 one to make sensible significance cut-offs. The software can be applied to
10655 problems in genomics, brain imaging, astrophysics, and data mining.")
10656 ;; Any version of the LGPL.
10657 (license license:lgpl3+)))
10659 (define-public r-hdf5array
10661 (name "r-hdf5array")
10666 (uri (bioconductor-uri "HDF5Array" version))
10669 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10670 (properties `((upstream-name . "HDF5Array")))
10671 (build-system r-build-system)
10673 `(("r-biocgenerics" ,r-biocgenerics)
10674 ("r-delayedarray" ,r-delayedarray)
10675 ("r-iranges" ,r-iranges)
10676 ("r-rhdf5" ,r-rhdf5)
10677 ("r-s4vectors" ,r-s4vectors)))
10678 (home-page "https://bioconductor.org/packages/HDF5Array")
10679 (synopsis "HDF5 back end for DelayedArray objects")
10680 (description "This package provides an array-like container for convenient
10681 access and manipulation of HDF5 datasets. It supports delayed operations and
10682 block processing.")
10683 (license license:artistic2.0)))
10685 (define-public r-rhdf5lib
10687 (name "r-rhdf5lib")
10692 (uri (bioconductor-uri "Rhdf5lib" version))
10695 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10696 (properties `((upstream-name . "Rhdf5lib")))
10697 (build-system r-build-system)
10700 (modify-phases %standard-phases
10701 (add-after 'unpack 'do-not-use-bundled-hdf5
10702 (lambda* (#:key inputs #:allow-other-keys)
10703 (for-each delete-file '("configure" "configure.ac"))
10704 ;; Do not make other packages link with the proprietary libsz.
10705 (substitute* "R/zzz.R"
10706 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10707 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10708 (("'%s/libhdf5.a %s/libsz.a'")
10709 "'%s/libhdf5.a %s/libhdf5.a'"))
10710 (with-directory-excursion "src"
10711 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10712 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10714 ;; Remove timestamp and host system information to make
10715 ;; the build reproducible.
10716 (substitute* "hdf5/src/libhdf5.settings.in"
10717 (("Configured on: @CONFIG_DATE@")
10718 "Configured on: Guix")
10719 (("Uname information:.*")
10720 "Uname information: Linux\n")
10721 ;; Remove unnecessary store reference.
10723 "C Compiler: GCC\n"))
10724 (rename-file "Makevars.in" "Makevars")
10725 (substitute* "Makevars"
10726 (("HDF5_CXX_LIB=.*")
10727 (string-append "HDF5_CXX_LIB="
10728 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10730 (string-append "HDF5_LIB="
10731 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10732 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10733 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10734 ;; szip is non-free software
10735 (("cp \\$\\{SZIP_LIB\\}.*") "")
10736 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10737 "PKG_LIBS = ${HDF5_LIB}\n")))
10744 `(("hdf5-source" ,(package-source hdf5))))
10745 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10746 (synopsis "HDF5 library as an R package")
10747 (description "This package provides C and C++ HDF5 libraries for use in R
10749 (license license:artistic2.0)))
10751 (define-public r-beachmat
10753 (name "r-beachmat")
10758 (uri (bioconductor-uri "beachmat" version))
10761 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10762 (build-system r-build-system)
10766 `(("r-delayedarray" ,r-delayedarray)
10767 ("r-hdf5array" ,r-hdf5array)
10769 ("r-rhdf5" ,r-rhdf5)
10770 ("r-rhdf5lib" ,r-rhdf5lib)))
10771 (home-page "https://bioconductor.org/packages/beachmat")
10772 (synopsis "Compiling Bioconductor to handle each matrix type")
10773 (description "This package provides a consistent C++ class interface for a
10774 variety of commonly used matrix types, including sparse and HDF5-backed
10776 (license license:gpl3)))
10778 (define-public r-singlecellexperiment
10780 (name "r-singlecellexperiment")
10785 (uri (bioconductor-uri "SingleCellExperiment" version))
10788 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10790 `((upstream-name . "SingleCellExperiment")))
10791 (build-system r-build-system)
10793 `(("r-biocgenerics" ,r-biocgenerics)
10794 ("r-s4vectors" ,r-s4vectors)
10795 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10796 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10797 (synopsis "S4 classes for single cell data")
10798 (description "This package defines an S4 class for storing data from
10799 single-cell experiments. This includes specialized methods to store and
10800 retrieve spike-in information, dimensionality reduction coordinates and size
10801 factors for each cell, along with the usual metadata for genes and
10803 (license license:gpl3)))
10805 (define-public r-scater
10811 (uri (bioconductor-uri "scater" version))
10814 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10815 (build-system r-build-system)
10817 `(("r-beachmat" ,r-beachmat)
10818 ("r-biobase" ,r-biobase)
10819 ("r-biocgenerics" ,r-biocgenerics)
10820 ("r-biomart" ,r-biomart)
10821 ("r-data-table" ,r-data-table)
10822 ("r-dplyr" ,r-dplyr)
10823 ("r-edger" ,r-edger)
10824 ("r-ggbeeswarm" ,r-ggbeeswarm)
10825 ("r-ggplot2" ,r-ggplot2)
10826 ("r-limma" ,r-limma)
10827 ("r-matrix" ,r-matrix)
10828 ("r-matrixstats" ,r-matrixstats)
10831 ("r-reshape2" ,r-reshape2)
10832 ("r-rhdf5" ,r-rhdf5)
10833 ("r-rhdf5lib" ,r-rhdf5lib)
10834 ("r-rjson" ,r-rjson)
10835 ("r-s4vectors" ,r-s4vectors)
10836 ("r-shiny" ,r-shiny)
10837 ("r-shinydashboard" ,r-shinydashboard)
10838 ("r-singlecellexperiment" ,r-singlecellexperiment)
10839 ("r-summarizedexperiment" ,r-summarizedexperiment)
10840 ("r-tximport" ,r-tximport)
10841 ("r-viridis" ,r-viridis)))
10842 (home-page "https://github.com/davismcc/scater")
10843 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10844 (description "This package provides a collection of tools for doing
10845 various analyses of single-cell RNA-seq gene expression data, with a focus on
10847 (license license:gpl2+)))
10849 (define-public r-scran
10856 (uri (bioconductor-uri "scran" version))
10859 "0cs64cnf0xjcgmawr210y99j3gxs6aqgh8081n9827kkqnx2y5dm"))))
10860 (build-system r-build-system)
10862 `(("r-beachmat" ,r-beachmat)
10863 ("r-biocgenerics" ,r-biocgenerics)
10864 ("r-biocparallel" ,r-biocparallel)
10866 ("r-dynamictreecut" ,r-dynamictreecut)
10867 ("r-edger" ,r-edger)
10869 ("r-ggplot2" ,r-ggplot2)
10870 ("r-igraph" ,r-igraph)
10871 ("r-limma" ,r-limma)
10872 ("r-matrix" ,r-matrix)
10874 ("r-rhdf5lib" ,r-rhdf5lib)
10875 ("r-s4vectors" ,r-s4vectors)
10876 ("r-scater" ,r-scater)
10877 ("r-shiny" ,r-shiny)
10878 ("r-singlecellexperiment" ,r-singlecellexperiment)
10879 ("r-statmod" ,r-statmod)
10880 ("r-summarizedexperiment" ,r-summarizedexperiment)
10881 ("r-viridis" ,r-viridis)
10883 (home-page "https://bioconductor.org/packages/scran")
10884 (synopsis "Methods for single-cell RNA-Seq data analysis")
10885 (description "This package implements a variety of low-level analyses of
10886 single-cell RNA-seq data. Methods are provided for normalization of
10887 cell-specific biases, assignment of cell cycle phase, and detection of highly
10888 variable and significantly correlated genes.")
10889 (license license:gpl3)))
10891 (define-public r-delayedmatrixstats
10893 (name "r-delayedmatrixstats")
10898 (uri (bioconductor-uri "DelayedMatrixStats" version))
10901 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10903 `((upstream-name . "DelayedMatrixStats")))
10904 (build-system r-build-system)
10906 `(("r-delayedarray" ,r-delayedarray)
10907 ("r-iranges" ,r-iranges)
10908 ("r-matrix" ,r-matrix)
10909 ("r-matrixstats" ,r-matrixstats)
10910 ("r-s4vectors" ,r-s4vectors)))
10911 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10912 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10914 "This package provides a port of the @code{matrixStats} API for use with
10915 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10916 contains high-performing functions operating on rows and columns of
10917 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10918 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10919 are optimized per data type and for subsetted calculations such that both
10920 memory usage and processing time is minimized.")
10921 (license license:expat)))
10923 (define-public r-phangorn
10925 (name "r-phangorn")
10930 (uri (cran-uri "phangorn" version))
10933 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10934 (build-system r-build-system)
10937 ("r-fastmatch" ,r-fastmatch)
10938 ("r-igraph" ,r-igraph)
10939 ("r-magrittr" ,r-magrittr)
10940 ("r-matrix" ,r-matrix)
10941 ("r-quadprog" ,r-quadprog)
10942 ("r-rcpp" ,r-rcpp)))
10943 (home-page "https://github.com/KlausVigo/phangorn")
10944 (synopsis "Phylogenetic analysis in R")
10946 "Phangorn is a package for phylogenetic analysis in R. It supports
10947 estimation of phylogenetic trees and networks using Maximum Likelihood,
10948 Maximum Parsimony, distance methods and Hadamard conjugation.")
10949 (license license:gpl2+)))
10951 (define-public r-dropbead
10952 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10955 (name "r-dropbead")
10956 (version (string-append "0-" revision "." (string-take commit 7)))
10960 (uri (git-reference
10961 (url "https://github.com/rajewsky-lab/dropbead.git")
10963 (file-name (git-file-name name version))
10966 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10967 (build-system r-build-system)
10969 `(("r-ggplot2" ,r-ggplot2)
10970 ("r-rcolorbrewer" ,r-rcolorbrewer)
10971 ("r-gridextra" ,r-gridextra)
10972 ("r-gplots" ,r-gplots)
10973 ("r-plyr" ,r-plyr)))
10974 (home-page "https://github.com/rajewsky-lab/dropbead")
10975 (synopsis "Basic exploration and analysis of Drop-seq data")
10976 (description "This package offers a quick and straight-forward way to
10977 explore and perform basic analysis of single cell sequencing data coming from
10978 droplet sequencing. It has been particularly tailored for Drop-seq.")
10979 (license license:gpl3))))
10981 (define htslib-for-sambamba
10982 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10985 (name "htslib-for-sambamba")
10986 (version (string-append "1.3.1-1." (string-take commit 9)))
10990 (uri (git-reference
10991 (url "https://github.com/lomereiter/htslib.git")
10993 (file-name (string-append "htslib-" version "-checkout"))
10996 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10999 (modify-phases %standard-phases
11000 (add-after 'unpack 'bootstrap
11001 (lambda _ (invoke "autoreconf" "-vif"))))))
11003 `(("autoconf" ,autoconf)
11004 ("automake" ,automake)
11005 ,@(package-native-inputs htslib))))))
11007 (define-public sambamba
11010 (version "0.6.7-10-g223fa20")
11014 (uri (git-reference
11015 (url "https://github.com/lomereiter/sambamba.git")
11016 (commit (string-append "v" version))))
11017 (file-name (string-append name "-" version "-checkout"))
11020 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11021 (build-system gnu-build-system)
11023 `(#:tests? #f ; there is no test target
11024 #:parallel-build? #f ; not supported
11026 (modify-phases %standard-phases
11027 (delete 'configure)
11028 (add-after 'unpack 'fix-ldc-version
11030 (substitute* "gen_ldc_version_info.py"
11031 (("/usr/bin/env.*") (which "python")))
11032 (substitute* "Makefile"
11033 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11035 (add-after 'unpack 'place-biod-and-undead
11036 (lambda* (#:key inputs #:allow-other-keys)
11037 (copy-recursively (assoc-ref inputs "biod") "BioD")
11038 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11040 (add-after 'unpack 'unbundle-prerequisites
11042 (substitute* "Makefile"
11043 (("htslib/libhts.a lz4/lib/liblz4.a")
11045 ((" htslib-static lz4-static") ""))
11048 (lambda* (#:key outputs #:allow-other-keys)
11049 (let* ((out (assoc-ref outputs "out"))
11050 (bin (string-append out "/bin")))
11052 (install-file "build/sambamba" bin)
11057 ("python" ,python2-minimal)
11059 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11062 (uri (git-reference
11063 (url "https://github.com/biod/BioD.git")
11065 (file-name (string-append "biod-"
11066 (string-take commit 9)
11070 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11072 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11075 (uri (git-reference
11076 (url "https://github.com/dlang/undeaD.git")
11078 (file-name (string-append "undead-"
11079 (string-take commit 9)
11083 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11086 ("htslib" ,htslib-for-sambamba)))
11087 (home-page "http://lomereiter.github.io/sambamba")
11088 (synopsis "Tools for working with SAM/BAM data")
11089 (description "Sambamba is a high performance modern robust and
11090 fast tool (and library), written in the D programming language, for
11091 working with SAM and BAM files. Current parallelised functionality is
11092 an important subset of samtools functionality, including view, index,
11093 sort, markdup, and depth.")
11094 (license license:gpl2+)))
11096 (define-public ritornello
11098 (name "ritornello")
11102 (uri (string-append "https://github.com/KlugerLab/"
11103 "Ritornello/archive/v"
11104 version ".tar.gz"))
11105 (file-name (string-append name "-" version ".tar.gz"))
11108 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11109 (build-system gnu-build-system)
11111 `(#:tests? #f ; there are no tests
11113 (modify-phases %standard-phases
11114 (add-after 'unpack 'patch-samtools-references
11115 (lambda* (#:key inputs #:allow-other-keys)
11116 (substitute* '("src/SamStream.h"
11117 "src/BufferedGenomeReader.h")
11118 (("<sam.h>") "<samtools/sam.h>"))
11120 (delete 'configure)
11122 (lambda* (#:key inputs outputs #:allow-other-keys)
11123 (let* ((out (assoc-ref outputs "out"))
11124 (bin (string-append out "/bin/")))
11126 (install-file "bin/Ritornello" bin)
11129 `(("samtools" ,samtools-0.1)
11133 (home-page "https://github.com/KlugerLab/Ritornello")
11134 (synopsis "Control-free peak caller for ChIP-seq data")
11135 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11136 signal processing that can accurately call binding events without the need to
11137 do a pair total DNA input or IgG control sample. It has been tested for use
11138 with narrow binding events such as transcription factor ChIP-seq.")
11139 (license license:gpl3+)))
11141 (define-public trim-galore
11143 (name "trim-galore")
11148 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
11149 "projects/trim_galore/trim_galore_v"
11153 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
11154 (build-system gnu-build-system)
11156 `(#:tests? #f ; no tests
11158 (modify-phases %standard-phases
11159 ;; The archive contains plain files.
11161 (lambda* (#:key source #:allow-other-keys)
11162 (zero? (system* "unzip" source))))
11163 (delete 'configure)
11165 (add-after 'unpack 'hardcode-tool-references
11166 (lambda* (#:key inputs #:allow-other-keys)
11167 (substitute* "trim_galore"
11168 (("\\$path_to_cutadapt = 'cutadapt'")
11169 (string-append "$path_to_cutadapt = '"
11170 (assoc-ref inputs "cutadapt")
11173 (string-append "| "
11174 (assoc-ref inputs "gzip")
11177 (string-append "\""
11178 (assoc-ref inputs "gzip")
11182 (lambda* (#:key outputs #:allow-other-keys)
11183 (let ((bin (string-append (assoc-ref outputs "out")
11186 (install-file "trim_galore" bin)
11191 ("cutadapt" ,cutadapt)))
11193 `(("unzip" ,unzip)))
11194 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11195 (synopsis "Wrapper around Cutadapt and FastQC")
11196 (description "Trim Galore! is a wrapper script to automate quality and
11197 adapter trimming as well as quality control, with some added functionality to
11198 remove biased methylation positions for RRBS sequence files.")
11199 (license license:gpl3+)))
11201 (define-public gess
11207 (uri (string-append "http://compbio.uthscsa.edu/"
11209 "gess-" version ".src.tar.gz"))
11212 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11213 (build-system gnu-build-system)
11215 `(#:tests? #f ; no tests
11217 (modify-phases %standard-phases
11218 (delete 'configure)
11221 (lambda* (#:key inputs outputs #:allow-other-keys)
11222 (let* ((python (assoc-ref inputs "python"))
11223 (out (assoc-ref outputs "out"))
11224 (bin (string-append out "/bin/"))
11225 (target (string-append
11226 out "/lib/python2.7/site-packages/gess/")))
11228 (copy-recursively "." target)
11229 ;; Make GESS.py executable
11230 (chmod (string-append target "GESS.py") #o555)
11231 ;; Add Python shebang to the top and make Matplotlib
11233 (substitute* (string-append target "GESS.py")
11234 (("\"\"\"Description:" line)
11235 (string-append "#!" (which "python") "
11237 matplotlib.use('Agg')
11239 ;; Make sure GESS has all modules in its path
11240 (wrap-program (string-append target "GESS.py")
11241 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11243 (symlink (string-append target "GESS.py")
11244 (string-append bin "GESS.py"))
11247 `(("python" ,python-2)
11248 ("python2-pysam" ,python2-pysam)
11249 ("python2-scipy" ,python2-scipy)
11250 ("python2-numpy" ,python2-numpy)
11251 ("python2-networkx" ,python2-networkx)
11252 ("python2-biopython" ,python2-biopython)))
11253 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11254 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11256 "GESS is an implementation of a novel computational method to detect de
11257 novo exon-skipping events directly from raw RNA-seq data without the prior
11258 knowledge of gene annotation information. GESS stands for the graph-based
11259 exon-skipping scanner detection scheme.")
11260 (license license:bsd-3)))
11262 (define-public phylip
11269 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11270 "download/phylip-" version ".tar.gz"))
11273 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11274 (build-system gnu-build-system)
11276 `(#:tests? #f ; no check target
11277 #:make-flags (list "-f" "Makefile.unx" "install")
11278 #:parallel-build? #f ; not supported
11280 (modify-phases %standard-phases
11281 (add-after 'unpack 'enter-dir
11282 (lambda _ (chdir "src") #t))
11283 (delete 'configure)
11285 (lambda* (#:key inputs outputs #:allow-other-keys)
11286 (let ((target (string-append (assoc-ref outputs "out")
11289 (for-each (lambda (file)
11290 (install-file file target))
11291 (find-files "../exe" ".*")))
11293 (home-page "http://evolution.genetics.washington.edu/phylip/")
11294 (synopsis "Tools for inferring phylogenies")
11295 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11296 programs for inferring phylogenies (evolutionary trees).")
11297 (license license:bsd-2)))
11306 (uri (string-append "https://integrativemodeling.org/"
11307 version "/download/imp-" version ".tar.gz"))
11310 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11311 (build-system cmake-build-system)
11313 `(;; FIXME: Some tests fail because they produce warnings, others fail
11314 ;; because the PYTHONPATH does not include the modeller's directory.
11322 ("python" ,python-2)))
11324 `(("python2-numpy" ,python2-numpy)
11325 ("python2-scipy" ,python2-scipy)
11326 ("python2-pandas" ,python2-pandas)
11327 ("python2-scikit-learn" ,python2-scikit-learn)
11328 ("python2-networkx" ,python2-networkx)))
11329 (home-page "https://integrativemodeling.org")
11330 (synopsis "Integrative modeling platform")
11331 (description "IMP's broad goal is to contribute to a comprehensive
11332 structural characterization of biomolecules ranging in size and complexity
11333 from small peptides to large macromolecular assemblies, by integrating data
11334 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11335 Python toolbox for solving complex modeling problems, and a number of
11336 applications for tackling some common problems in a user-friendly way.")
11337 ;; IMP is largely available under the GNU Lesser GPL; see the file
11338 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11339 ;; available under the GNU GPL (see the file COPYING.GPL).
11340 (license (list license:lgpl2.1+
11343 (define-public tadbit
11349 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11350 "archive/v" version ".tar.gz"))
11351 (file-name (string-append name "-" version ".tar.gz"))
11354 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11355 (build-system python-build-system)
11357 `(;; Tests are included and must be run after installation, but
11358 ;; they are incomplete and thus cannot be run.
11362 (modify-phases %standard-phases
11363 (add-after 'unpack 'fix-problems-with-setup.py
11364 (lambda* (#:key outputs #:allow-other-keys)
11365 ;; setup.py opens these files for writing
11366 (chmod "_pytadbit/_version.py" #o664)
11367 (chmod "README.rst" #o664)
11369 ;; Don't attempt to install the bash completions to
11370 ;; the home directory.
11371 (rename-file "extras/.bash_completion"
11373 (substitute* "setup.py"
11374 (("\\(path.expanduser\\('~'\\)")
11375 (string-append "(\""
11376 (assoc-ref outputs "out")
11377 "/etc/bash_completion.d\""))
11378 (("extras/\\.bash_completion")
11382 ;; TODO: add Chimera for visualization
11385 ("python2-scipy" ,python2-scipy)
11386 ("python2-numpy" ,python2-numpy)
11387 ("python2-matplotlib" ,python2-matplotlib)
11388 ("python2-pysam" ,python2-pysam)))
11389 (home-page "http://3dgenomes.github.io/TADbit/")
11390 (synopsis "Analyze, model, and explore 3C-based data")
11392 "TADbit is a complete Python library to deal with all steps to analyze,
11393 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11394 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11395 correct interaction matrices, identify and compare the so-called
11396 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11397 interaction matrices, and finally, extract structural properties from the
11398 models. TADbit is complemented by TADkit for visualizing 3D models.")
11399 (license license:gpl3+)))
11401 (define-public kentutils
11404 ;; 302.1.0 is out, but the only difference is the inclusion of
11405 ;; pre-built binaries.
11406 (version "302.0.0")
11410 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11411 "archive/v" version ".tar.gz"))
11412 (file-name (string-append name "-" version ".tar.gz"))
11415 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11416 (modules '((guix build utils)
11421 ;; Only the contents of the specified directories are free
11422 ;; for all uses, so we remove the rest. "hg/autoSql" and
11423 ;; "hg/autoXml" are nominally free, but they depend on a
11424 ;; library that is built from the sources in "hg/lib",
11425 ;; which is nonfree.
11426 (let ((free (list "." ".."
11427 "utils" "lib" "inc" "tagStorm"
11428 "parasol" "htslib"))
11429 (directory? (lambda (file)
11430 (eq? 'directory (stat:type (stat file))))))
11431 (for-each (lambda (file)
11432 (and (directory? file)
11433 (delete-file-recursively file)))
11434 (map (cut string-append "src/" <>)
11437 (not (member file free)))))))
11438 ;; Only make the utils target, not the userApps target,
11439 ;; because that requires libraries we won't build.
11440 (substitute* "Makefile"
11441 ((" userApps") " utils"))
11442 ;; Only build libraries that are free.
11443 (substitute* "src/makefile"
11444 (("DIRS =.*") "DIRS =\n")
11445 (("cd jkOwnLib.*") "")
11448 (substitute* "src/utils/makefile"
11449 ;; These tools depend on "jkhgap.a", which is part of the
11450 ;; nonfree "src/hg/lib" directory.
11451 (("raSqlQuery") "")
11452 (("pslLiftSubrangeBlat") "")
11454 ;; Do not build UCSC tools, which may require nonfree
11456 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11458 (build-system gnu-build-system)
11460 `( ;; There is no global test target and the test target for
11461 ;; individual tools depends on input files that are not
11465 (modify-phases %standard-phases
11466 (add-after 'unpack 'fix-paths
11468 (substitute* "Makefile"
11469 (("/bin/echo") (which "echo")))
11471 (add-after 'unpack 'prepare-samtabix
11472 (lambda* (#:key inputs #:allow-other-keys)
11473 (copy-recursively (assoc-ref inputs "samtabix")
11476 (delete 'configure)
11478 (lambda* (#:key outputs #:allow-other-keys)
11479 (let ((bin (string-append (assoc-ref outputs "out")
11481 (copy-recursively "bin" bin))
11487 (uri (git-reference
11488 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11489 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11492 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11498 ("mariadb" ,mariadb)
11499 ("openssl" ,openssl)))
11500 (home-page "http://genome.cse.ucsc.edu/index.html")
11501 (synopsis "Assorted bioinformatics utilities")
11502 (description "This package provides the kentUtils, a selection of
11503 bioinformatics utilities used in combination with the UCSC genome
11505 ;; Only a subset of the sources are released under a non-copyleft
11506 ;; free software license. All other sources are removed in a
11507 ;; snippet. See this bug report for an explanation of how the
11508 ;; license statements apply:
11509 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11510 (license (license:non-copyleft
11511 "http://genome.ucsc.edu/license/"
11512 "The contents of this package are free for all uses."))))
11514 (define-public f-seq
11515 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11519 (version (string-append "1.1-" revision "." (string-take commit 7)))
11522 (uri (git-reference
11523 (url "https://github.com/aboyle/F-seq.git")
11525 (file-name (string-append name "-" version))
11528 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11529 (modules '((guix build utils)))
11530 ;; Remove bundled Java library archives.
11533 (for-each delete-file (find-files "lib" ".*"))
11535 (build-system ant-build-system)
11537 `(#:tests? #f ; no tests included
11539 (modify-phases %standard-phases
11541 (lambda* (#:key inputs outputs #:allow-other-keys)
11542 (let* ((target (assoc-ref outputs "out"))
11543 (doc (string-append target "/share/doc/f-seq/")))
11546 (substitute* "bin/linux/fseq"
11547 (("java") (which "java"))
11548 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11549 (string-append (assoc-ref inputs "java-commons-cli")
11550 "/share/java/commons-cli.jar"))
11552 (string-append "REALDIR=" target "/bin\n")))
11553 (install-file "README.txt" doc)
11554 (install-file "bin/linux/fseq" (string-append target "/bin"))
11555 (install-file "build~/fseq.jar" (string-append target "/lib"))
11556 (copy-recursively "lib" (string-append target "/lib"))
11560 ("java-commons-cli" ,java-commons-cli)))
11561 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11562 (synopsis "Feature density estimator for high-throughput sequence tags")
11564 "F-Seq is a software package that generates a continuous tag sequence
11565 density estimation allowing identification of biologically meaningful sites
11566 such as transcription factor binding sites (ChIP-seq) or regions of open
11567 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11569 (license license:gpl3+))))
11571 (define-public bismark
11578 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11579 "archive/" version ".tar.gz"))
11580 (file-name (string-append name "-" version ".tar.gz"))
11583 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11584 (build-system perl-build-system)
11586 `(#:tests? #f ; there are no tests
11588 (modify-phases %standard-phases
11589 (delete 'configure)
11592 (lambda* (#:key inputs outputs #:allow-other-keys)
11593 (let ((bin (string-append (assoc-ref outputs "out")
11595 (docdir (string-append (assoc-ref outputs "out")
11596 "/share/doc/bismark"))
11597 (docs '("Bismark_User_Guide.pdf"
11598 "RELEASE_NOTES.txt"))
11599 (scripts '("bismark"
11600 "bismark_genome_preparation"
11601 "bismark_methylation_extractor"
11604 "coverage2cytosine"
11605 "deduplicate_bismark"
11606 "bismark_sitrep.tpl"
11608 "bismark2summary")))
11611 (for-each (lambda (file) (install-file file bin))
11613 (for-each (lambda (file) (install-file file docdir))
11615 ;; Fix references to gunzip
11616 (substitute* (map (lambda (file)
11617 (string-append bin "/" file))
11620 (string-append "\"" (assoc-ref inputs "gzip")
11621 "/bin/gunzip -c")))
11625 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11626 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11627 (description "Bismark is a program to map bisulfite treated sequencing
11628 reads to a genome of interest and perform methylation calls in a single step.
11629 The output can be easily imported into a genome viewer, such as SeqMonk, and
11630 enables a researcher to analyse the methylation levels of their samples
11631 straight away. Its main features are:
11634 @item Bisulfite mapping and methylation calling in one single step
11635 @item Supports single-end and paired-end read alignments
11636 @item Supports ungapped and gapped alignments
11637 @item Alignment seed length, number of mismatches etc are adjustable
11638 @item Output discriminates between cytosine methylation in CpG, CHG
11641 (license license:gpl3+)))
11643 (define-public paml
11649 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11650 "paml" version ".tgz"))
11653 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11654 (modules '((guix build utils)))
11655 ;; Remove Windows binaries
11658 (for-each delete-file (find-files "." "\\.exe$"))
11660 (build-system gnu-build-system)
11662 `(#:tests? #f ; there are no tests
11663 #:make-flags '("CC=gcc")
11665 (modify-phases %standard-phases
11666 (replace 'configure
11668 (substitute* "src/BFdriver.c"
11669 (("/bin/bash") (which "bash")))
11673 (lambda* (#:key outputs #:allow-other-keys)
11674 (let ((tools '("baseml" "basemlg" "codeml"
11675 "pamp" "evolver" "yn00" "chi2"))
11676 (bin (string-append (assoc-ref outputs "out") "/bin"))
11677 (docdir (string-append (assoc-ref outputs "out")
11678 "/share/doc/paml")))
11680 (for-each (lambda (file) (install-file file bin)) tools)
11681 (copy-recursively "../doc" docdir)
11683 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11684 (synopsis "Phylogentic analysis by maximum likelihood")
11685 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11686 contains a few programs for model fitting and phylogenetic tree reconstruction
11687 using nucleotide or amino-acid sequence data.")
11689 (license license:gpl3)))
11691 (define-public kallisto
11697 (uri (string-append "https://github.com/pachterlab/"
11698 "kallisto/archive/v" version ".tar.gz"))
11699 (file-name (string-append name "-" version ".tar.gz"))
11702 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11703 (build-system cmake-build-system)
11704 (arguments `(#:tests? #f)) ; no "check" target
11708 (home-page "http://pachterlab.github.io/kallisto/")
11709 (synopsis "Near-optimal RNA-Seq quantification")
11711 "Kallisto is a program for quantifying abundances of transcripts from
11712 RNA-Seq data, or more generally of target sequences using high-throughput
11713 sequencing reads. It is based on the novel idea of pseudoalignment for
11714 rapidly determining the compatibility of reads with targets, without the need
11715 for alignment. Pseudoalignment of reads preserves the key information needed
11716 for quantification, and kallisto is therefore not only fast, but also as
11717 accurate as existing quantification tools.")
11718 (license license:bsd-2)))
11720 (define-public libgff
11726 (uri (string-append
11727 "https://github.com/Kingsford-Group/"
11728 "libgff/archive/v" version ".tar.gz"))
11729 (file-name (string-append name "-" version ".tar.gz"))
11732 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11733 (build-system cmake-build-system)
11734 (arguments `(#:tests? #f)) ; no tests included
11735 (home-page "https://github.com/Kingsford-Group/libgff")
11736 (synopsis "Parser library for reading/writing GFF files")
11737 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11738 code that is used in the Cufflinks codebase. The goal of this library is to
11739 provide this functionality without the necessity of drawing in a heavy-weight
11740 dependency like SeqAn.")
11741 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11743 (define-public libdivsufsort
11745 (name "libdivsufsort")
11749 (uri (git-reference
11750 (url "https://github.com/y-256/libdivsufsort.git")
11752 (file-name (git-file-name name version))
11755 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11756 (build-system cmake-build-system)
11758 '(#:tests? #f ; there are no tests
11760 ;; Needed for rapmap and sailfish.
11761 '("-DBUILD_DIVSUFSORT64=ON")))
11762 (home-page "https://github.com/y-256/libdivsufsort")
11763 (synopsis "Lightweight suffix-sorting library")
11764 (description "libdivsufsort is a software library that implements a
11765 lightweight suffix array construction algorithm. This library provides a
11766 simple and an efficient C API to construct a suffix array and a
11767 Burrows-Wheeler transformed string from a given string over a constant-size
11768 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11769 bytes of memory space, where n is the length of the string.")
11770 (license license:expat)))
11772 (define-public sailfish
11779 (string-append "https://github.com/kingsfordgroup/"
11780 "sailfish/archive/v" version ".tar.gz"))
11781 (file-name (string-append name "-" version ".tar.gz"))
11784 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11785 (modules '((guix build utils)))
11788 ;; Delete bundled headers for eigen3.
11789 (delete-file-recursively "include/eigen3/")
11791 (build-system cmake-build-system)
11793 `(#:configure-flags
11794 (list (string-append "-DBOOST_INCLUDEDIR="
11795 (assoc-ref %build-inputs "boost")
11797 (string-append "-DBOOST_LIBRARYDIR="
11798 (assoc-ref %build-inputs "boost")
11800 (string-append "-DBoost_LIBRARIES="
11801 "-lboost_iostreams "
11802 "-lboost_filesystem "
11807 "-lboost_program_options")
11808 "-DBoost_FOUND=TRUE"
11809 ;; Don't download RapMap---we already have it!
11810 "-DFETCHED_RAPMAP=1")
11811 ;; Tests must be run after installation and the location of the test
11812 ;; data file must be overridden. But the tests fail. It looks like
11813 ;; they are not really meant to be run.
11816 (modify-phases %standard-phases
11817 ;; Boost cannot be found, even though it's right there.
11818 (add-after 'unpack 'do-not-look-for-boost
11819 (lambda* (#:key inputs #:allow-other-keys)
11820 (substitute* "CMakeLists.txt"
11821 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11822 (add-after 'unpack 'do-not-assign-to-macro
11824 (substitute* "include/spdlog/details/format.cc"
11825 (("const unsigned CHAR_WIDTH = 1;") ""))))
11826 (add-after 'unpack 'prepare-rapmap
11827 (lambda* (#:key inputs #:allow-other-keys)
11828 (let ((src "external/install/src/rapmap/")
11829 (include "external/install/include/rapmap/")
11830 (rapmap (assoc-ref inputs "rapmap")))
11831 (mkdir-p "/tmp/rapmap")
11832 (system* "tar" "xf"
11833 (assoc-ref inputs "rapmap")
11835 "--strip-components=1")
11838 (for-each (lambda (file)
11839 (install-file file src))
11840 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11841 (copy-recursively "/tmp/rapmap/include" include))))
11842 (add-after 'unpack 'use-system-libraries
11843 (lambda* (#:key inputs #:allow-other-keys)
11844 (substitute* '("src/SailfishIndexer.cpp"
11845 "src/SailfishUtils.cpp"
11846 "src/SailfishQuantify.cpp"
11847 "src/FASTAParser.cpp"
11849 "include/SailfishUtils.hpp"
11850 "include/SailfishIndex.hpp"
11851 "include/CollapsedEMOptimizer.hpp"
11852 "src/CollapsedEMOptimizer.cpp")
11853 (("#include \"jellyfish/config.h\"") ""))
11854 (substitute* "src/CMakeLists.txt"
11855 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11856 (string-append (assoc-ref inputs "jellyfish")
11857 "/include/jellyfish-" ,(package-version jellyfish)))
11858 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11859 (string-append (assoc-ref inputs "jellyfish")
11860 "/lib/libjellyfish-2.0.a"))
11861 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11862 (string-append (assoc-ref inputs "libdivsufsort")
11863 "/lib/libdivsufsort.so"))
11864 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11865 (string-append (assoc-ref inputs "libdivsufsort")
11866 "/lib/libdivsufsort64.so")))
11867 (substitute* "CMakeLists.txt"
11868 ;; Don't prefer static libs
11869 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11870 (("find_package\\(Jellyfish.*") "")
11871 (("ExternalProject_Add\\(libjellyfish") "message(")
11872 (("ExternalProject_Add\\(libgff") "message(")
11873 (("ExternalProject_Add\\(libsparsehash") "message(")
11874 (("ExternalProject_Add\\(libdivsufsort") "message("))
11876 ;; Ensure that Eigen headers can be found
11877 (setenv "CPLUS_INCLUDE_PATH"
11878 (string-append (getenv "CPLUS_INCLUDE_PATH")
11880 (assoc-ref inputs "eigen")
11881 "/include/eigen3")))))))
11885 ("jemalloc" ,jemalloc)
11886 ("jellyfish" ,jellyfish)
11887 ("sparsehash" ,sparsehash)
11890 (uri (git-reference
11891 (url "https://github.com/COMBINE-lab/RapMap.git")
11892 (commit (string-append "sf-v" version))))
11893 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11896 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11897 (modules '((guix build utils)))
11898 ;; These files are expected to be excluded.
11900 '(begin (delete-file-recursively "include/spdlog")
11901 (for-each delete-file '("include/xxhash.h"
11902 "src/xxhash.c"))))))
11903 ("libdivsufsort" ,libdivsufsort)
11908 `(("pkg-config" ,pkg-config)))
11909 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11910 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11911 (description "Sailfish is a tool for genomic transcript quantification
11912 from RNA-seq data. It requires a set of target transcripts (either from a
11913 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11914 fasta file containing your reference transcripts and a (set of) fasta/fastq
11915 file(s) containing your reads.")
11916 (license license:gpl3+)))
11918 (define libstadenio-for-salmon
11920 (name "libstadenio")
11924 (uri (git-reference
11925 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11926 (commit (string-append "v" version))))
11927 (file-name (string-append name "-" version "-checkout"))
11930 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11931 (build-system gnu-build-system)
11932 (arguments '(#:parallel-tests? #f)) ; not supported
11936 `(("perl" ,perl))) ; for tests
11937 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11938 (synopsis "General purpose trace and experiment file library")
11939 (description "This package provides a library of file reading and writing
11940 code to provide a general purpose Trace file (and Experiment File) reading
11943 The following file formats are supported:
11946 @item SCF trace files
11947 @item ABI trace files
11948 @item ALF trace files
11949 @item ZTR trace files
11950 @item SFF trace archives
11951 @item SRF trace archives
11952 @item Experiment files
11953 @item Plain text files
11954 @item SAM/BAM sequence files
11955 @item CRAM sequence files
11957 (license license:bsd-3)))
11959 (define spdlog-for-salmon
11965 (uri (git-reference
11966 (url "https://github.com/COMBINE-lab/spdlog.git")
11967 (commit (string-append "v" version))))
11968 (file-name (string-append name "-" version "-checkout"))
11971 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11972 (build-system cmake-build-system)
11973 (home-page "https://github.com/COMBINE-lab/spdlog")
11974 (synopsis "Very fast C++ logging library")
11975 (description "Spdlog is a very fast header-only C++ logging library with
11976 performance as its primary goal.")
11977 (license license:expat)))
11979 ;; This is a modified variant of bwa for use with Salmon. It installs a
11980 ;; library to avoid having to build this as part of Salmon.
11981 (define bwa-for-salmon
11982 (package (inherit bwa)
11984 (version "0.7.12.5")
11987 (uri (git-reference
11988 (url "https://github.com/COMBINE-lab/bwa.git")
11989 (commit (string-append "v" version))))
11990 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11993 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11994 (build-system gnu-build-system)
11996 '(#:tests? #f ;no "check" target
11998 (modify-phases %standard-phases
12000 (lambda* (#:key outputs #:allow-other-keys)
12001 (let* ((out (assoc-ref outputs "out"))
12002 (bin (string-append out "/bin"))
12003 (lib (string-append out "/lib"))
12004 (doc (string-append out "/share/doc/bwa"))
12005 (man (string-append out "/share/man/man1"))
12006 (inc (string-append out "/include/bwa")))
12007 (install-file "bwa" bin)
12008 (install-file "README.md" doc)
12009 (install-file "bwa.1" man)
12010 (install-file "libbwa.a" lib)
12013 (for-each (lambda (file)
12014 (install-file file inc))
12015 (find-files "." "\\.h$")))
12017 ;; no "configure" script
12018 (delete 'configure))))))
12020 (define-public salmon
12026 (uri (git-reference
12027 (url "https://github.com/COMBINE-lab/salmon.git")
12028 (commit (string-append "v" version))))
12029 (file-name (string-append name "-" version "-checkout"))
12032 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12033 (modules '((guix build utils)))
12036 ;; Delete bundled headers for eigen3.
12037 (delete-file-recursively "include/eigen3/")
12039 (build-system cmake-build-system)
12041 `(#:configure-flags
12042 (list (string-append "-DBOOST_INCLUDEDIR="
12043 (assoc-ref %build-inputs "boost")
12045 (string-append "-DBOOST_LIBRARYDIR="
12046 (assoc-ref %build-inputs "boost")
12048 (string-append "-DBoost_LIBRARIES="
12049 "-lboost_iostreams "
12050 "-lboost_filesystem "
12055 "-lboost_program_options")
12056 "-DBoost_FOUND=TRUE"
12057 "-DTBB_LIBRARIES=tbb tbbmalloc"
12058 ;; Don't download RapMap---we already have it!
12059 "-DFETCHED_RAPMAP=1")
12061 (modify-phases %standard-phases
12062 ;; Boost cannot be found, even though it's right there.
12063 (add-after 'unpack 'do-not-look-for-boost
12064 (lambda* (#:key inputs #:allow-other-keys)
12065 (substitute* "CMakeLists.txt"
12066 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12067 (add-after 'unpack 'do-not-phone-home
12069 (substitute* "src/Salmon.cpp"
12070 (("getVersionMessage\\(\\)") "\"\""))))
12071 (add-after 'unpack 'prepare-rapmap
12072 (lambda* (#:key inputs #:allow-other-keys)
12073 (let ((src "external/install/src/rapmap/")
12074 (include "external/install/include/rapmap/")
12075 (rapmap (assoc-ref inputs "rapmap")))
12078 (for-each (lambda (file)
12079 (install-file file src))
12080 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12081 (copy-recursively (string-append rapmap "/include") include)
12082 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12083 "external/install/include/rapmap/FastxParser.hpp"
12084 "external/install/include/rapmap/concurrentqueue.h"
12085 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12086 "external/install/src/rapmap/FastxParser.cpp"
12087 "external/install/src/rapmap/xxhash.c")))))
12088 (add-after 'unpack 'use-system-libraries
12089 (lambda* (#:key inputs #:allow-other-keys)
12090 (substitute* "src/CMakeLists.txt"
12091 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12092 (string-append (assoc-ref inputs "jellyfish")
12093 "/include/jellyfish-" ,(package-version jellyfish)))
12094 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12095 (string-append (assoc-ref inputs "jellyfish")
12096 "/lib/libjellyfish-2.0.a"))
12097 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12098 (string-append (assoc-ref inputs "libdivsufsort")
12099 "/lib/libdivsufsort.so"))
12100 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12101 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12102 "/lib/libstaden-read.a"))
12103 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12104 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12105 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12106 (string-append (assoc-ref inputs "libdivsufsort")
12107 "/lib/libdivsufsort64.so")))
12108 (substitute* "CMakeLists.txt"
12109 ;; Don't prefer static libs
12110 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12111 (("set\\(TBB_LIBRARIES") "message(")
12112 (("find_package\\(Jellyfish.*") "")
12113 (("ExternalProject_Add\\(libcereal") "message(")
12114 (("ExternalProject_Add\\(libbwa") "message(")
12115 (("ExternalProject_Add\\(libjellyfish") "message(")
12116 (("ExternalProject_Add\\(libgff") "message(")
12117 (("ExternalProject_Add\\(libtbb") "message(")
12118 (("ExternalProject_Add\\(libspdlog") "message(")
12119 (("ExternalProject_Add\\(libdivsufsort") "message(")
12120 (("ExternalProject_Add\\(libstadenio") "message(")
12121 (("ExternalProject_Add_Step\\(") "message("))
12123 ;; Ensure that all headers can be found
12124 (setenv "CPLUS_INCLUDE_PATH"
12125 (string-append (getenv "CPLUS_INCLUDE_PATH")
12127 (assoc-ref inputs "bwa")
12130 (assoc-ref inputs "eigen")
12131 "/include/eigen3"))
12133 (string-append (assoc-ref inputs "bwa")
12136 (assoc-ref inputs "eigen")
12137 "/include/eigen3"))
12139 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12140 ;; run. It only exists after the install phase.
12141 (add-after 'unpack 'fix-tests
12143 (substitute* "src/CMakeLists.txt"
12144 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12145 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12149 ("bwa" ,bwa-for-salmon)
12155 (uri (git-reference
12156 (url "https://github.com/COMBINE-lab/RapMap.git")
12157 (commit (string-append "salmon-v" version))))
12158 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12161 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12162 ("jemalloc" ,jemalloc)
12163 ("jellyfish" ,jellyfish)
12166 ("libdivsufsort" ,libdivsufsort)
12167 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12168 ("spdlog-for-salmon" ,spdlog-for-salmon)
12171 (home-page "https://github.com/COMBINE-lab/salmon")
12172 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12173 (description "Salmon is a program to produce highly-accurate,
12174 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12175 its accuracy and speed via a number of different innovations, including the
12176 use of lightweight alignments (accurate but fast-to-compute proxies for
12177 traditional read alignments) and massively-parallel stochastic collapsed
12178 variational inference.")
12179 (license license:gpl3+)))
12181 (define-public python-loompy
12183 (name "python-loompy")
12188 (uri (pypi-uri "loompy" version))
12191 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12192 (build-system python-build-system)
12193 ;; There are no tests
12194 (arguments '(#:tests? #f))
12196 `(("python-h5py" ,python-h5py)
12197 ("python-numpy" ,python-numpy)
12198 ("python-scipy" ,python-scipy)
12199 ("python-typing" ,python-typing)))
12200 (home-page "https://github.com/linnarsson-lab/loompy")
12201 (synopsis "Work with .loom files for single-cell RNA-seq data")
12202 (description "The loom file format is an efficient format for very large
12203 omics datasets, consisting of a main matrix, optional additional layers, a
12204 variable number of row and column annotations. Loom also supports sparse
12205 graphs. This library makes it easy to work with @file{.loom} files for
12206 single-cell RNA-seq data.")
12207 (license license:bsd-3)))
12209 ;; We cannot use the latest commit because it requires Java 9.
12210 (define-public java-forester
12211 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12214 (name "java-forester")
12215 (version (string-append "0-" revision "." (string-take commit 7)))
12218 (uri (git-reference
12219 (url "https://github.com/cmzmasek/forester.git")
12221 (file-name (string-append name "-" version "-checkout"))
12224 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12225 (modules '((guix build utils)))
12228 ;; Delete bundled jars and pre-built classes
12229 (delete-file-recursively "forester/java/resources")
12230 (delete-file-recursively "forester/java/classes")
12231 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12232 ;; Delete bundled applications
12233 (delete-file-recursively "forester_applications")
12235 (build-system ant-build-system)
12237 `(#:tests? #f ; there are none
12239 #:modules ((guix build ant-build-system)
12241 (guix build java-utils)
12245 (modify-phases %standard-phases
12246 (add-after 'unpack 'chdir
12247 (lambda _ (chdir "forester/java") #t))
12248 (add-after 'chdir 'fix-dependencies
12250 (chmod "build.xml" #o664)
12251 (call-with-output-file "build.xml.new"
12255 (with-input-from-file "build.xml"
12256 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12257 `(;; Remove all unjar tags to avoid repacking classes.
12258 (unjar . ,(lambda _ '()))
12259 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12260 (*text* . ,(lambda (_ txt) txt))))
12262 (rename-file "build.xml.new" "build.xml")
12264 ;; FIXME: itext is difficult to package as it depends on a few
12265 ;; unpackaged libraries.
12266 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12268 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12269 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12270 (("pdf_written_to = PdfExporter.*")
12271 "throw new IOException(\"PDF export is not available.\");"))
12273 ;; There is no install target
12274 (replace 'install (install-jars ".")))))
12276 `(("java-commons-codec" ,java-commons-codec)
12277 ("java-openchart2" ,java-openchart2)))
12278 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12279 (synopsis "Phylogenomics libraries for Java")
12280 (description "Forester is a collection of Java libraries for
12281 phylogenomics and evolutionary biology research. It includes support for
12282 reading, writing, and exporting phylogenetic trees.")
12283 (license license:lgpl2.1+))))
12285 (define-public java-forester-1.005
12287 (name "java-forester")
12291 (uri (string-append "http://search.maven.org/remotecontent?"
12292 "filepath=org/biojava/thirdparty/forester/"
12293 version "/forester-" version "-sources.jar"))
12294 (file-name (string-append name "-" version ".jar"))
12297 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12298 (build-system ant-build-system)
12300 `(#:tests? #f ; there are none
12302 #:modules ((guix build ant-build-system)
12304 (guix build java-utils)
12308 (modify-phases %standard-phases
12309 (add-after 'unpack 'fix-dependencies
12310 (lambda* (#:key inputs #:allow-other-keys)
12311 (call-with-output-file "build.xml"
12315 (with-input-from-file "src/build.xml"
12316 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12317 `(;; Remove all unjar tags to avoid repacking classes.
12318 (unjar . ,(lambda _ '()))
12319 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12320 (*text* . ,(lambda (_ txt) txt))))
12322 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12323 "synth_look_and_feel_1.xml")
12324 (copy-file (assoc-ref inputs "phyloxml.xsd")
12326 (substitute* "build.xml"
12327 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12328 "synth_look_and_feel_1.xml")
12329 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12332 ;; FIXME: itext is difficult to package as it depends on a few
12333 ;; unpackaged libraries.
12334 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12336 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12337 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12338 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12339 (("pdf_written_to = PdfExporter.*")
12340 "throw new IOException(\"PDF export is not available.\"); /*")
12341 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12342 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12344 (add-after 'unpack 'delete-pre-built-classes
12345 (lambda _ (delete-file-recursively "src/classes") #t))
12346 ;; There is no install target
12347 (replace 'install (install-jars ".")))))
12349 `(("java-commons-codec" ,java-commons-codec)
12350 ("java-openchart2" ,java-openchart2)))
12351 ;; The source archive does not contain the resources.
12356 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12357 "b61cc2dcede0bede317db362472333115756b8c6/"
12358 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12359 (file-name (string-append name "-phyloxml-" version ".xsd"))
12362 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12363 ("synth_look_and_feel_1.xml"
12366 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12367 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12368 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12369 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12372 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12373 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12374 (synopsis "Phylogenomics libraries for Java")
12375 (description "Forester is a collection of Java libraries for
12376 phylogenomics and evolutionary biology research. It includes support for
12377 reading, writing, and exporting phylogenetic trees.")
12378 (license license:lgpl2.1+)))
12380 (define-public java-biojava-core
12382 (name "java-biojava-core")
12386 (uri (git-reference
12387 (url "https://github.com/biojava/biojava")
12388 (commit (string-append "biojava-" version))))
12389 (file-name (string-append name "-" version "-checkout"))
12392 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12393 (build-system ant-build-system)
12396 #:jar-name "biojava-core.jar"
12397 #:source-dir "biojava-core/src/main/java/"
12398 #:test-dir "biojava-core/src/test"
12399 ;; These tests seem to require internet access.
12400 #:test-exclude (list "**/SearchIOTest.java"
12401 "**/BlastXMLParserTest.java"
12402 "**/GenbankCookbookTest.java"
12403 "**/GenbankProxySequenceReaderTest.java")
12405 (modify-phases %standard-phases
12406 (add-before 'build 'copy-resources
12408 (copy-recursively "biojava-core/src/main/resources"
12411 (add-before 'check 'copy-test-resources
12413 (copy-recursively "biojava-core/src/test/resources"
12414 "build/test-classes")
12417 `(("java-log4j-api" ,java-log4j-api)
12418 ("java-log4j-core" ,java-log4j-core)
12419 ("java-slf4j-api" ,java-slf4j-api)
12420 ("java-slf4j-simple" ,java-slf4j-simple)))
12422 `(("java-junit" ,java-junit)
12423 ("java-hamcrest-core" ,java-hamcrest-core)))
12424 (home-page "http://biojava.org")
12425 (synopsis "Core libraries of Java framework for processing biological data")
12426 (description "BioJava is a project dedicated to providing a Java framework
12427 for processing biological data. It provides analytical and statistical
12428 routines, parsers for common file formats, reference implementations of
12429 popular algorithms, and allows the manipulation of sequences and 3D
12430 structures. The goal of the biojava project is to facilitate rapid
12431 application development for bioinformatics.
12433 This package provides the core libraries.")
12434 (license license:lgpl2.1+)))
12436 (define-public java-biojava-phylo
12437 (package (inherit java-biojava-core)
12438 (name "java-biojava-phylo")
12439 (build-system ant-build-system)
12442 #:jar-name "biojava-phylo.jar"
12443 #:source-dir "biojava-phylo/src/main/java/"
12444 #:test-dir "biojava-phylo/src/test"
12446 (modify-phases %standard-phases
12447 (add-before 'build 'copy-resources
12449 (copy-recursively "biojava-phylo/src/main/resources"
12452 (add-before 'check 'copy-test-resources
12454 (copy-recursively "biojava-phylo/src/test/resources"
12455 "build/test-classes")
12458 `(("java-log4j-api" ,java-log4j-api)
12459 ("java-log4j-core" ,java-log4j-core)
12460 ("java-slf4j-api" ,java-slf4j-api)
12461 ("java-slf4j-simple" ,java-slf4j-simple)
12462 ("java-biojava-core" ,java-biojava-core)
12463 ("java-forester" ,java-forester)))
12465 `(("java-junit" ,java-junit)
12466 ("java-hamcrest-core" ,java-hamcrest-core)))
12467 (home-page "http://biojava.org")
12468 (synopsis "Biojava interface to the forester phylogenomics library")
12469 (description "The phylo module provides a biojava interface layer to the
12470 forester phylogenomics library for constructing phylogenetic trees.")))
12472 (define-public java-biojava-alignment
12473 (package (inherit java-biojava-core)
12474 (name "java-biojava-alignment")
12475 (build-system ant-build-system)
12478 #:jar-name "biojava-alignment.jar"
12479 #:source-dir "biojava-alignment/src/main/java/"
12480 #:test-dir "biojava-alignment/src/test"
12482 (modify-phases %standard-phases
12483 (add-before 'build 'copy-resources
12485 (copy-recursively "biojava-alignment/src/main/resources"
12488 (add-before 'check 'copy-test-resources
12490 (copy-recursively "biojava-alignment/src/test/resources"
12491 "build/test-classes")
12494 `(("java-log4j-api" ,java-log4j-api)
12495 ("java-log4j-core" ,java-log4j-core)
12496 ("java-slf4j-api" ,java-slf4j-api)
12497 ("java-slf4j-simple" ,java-slf4j-simple)
12498 ("java-biojava-core" ,java-biojava-core)
12499 ("java-biojava-phylo" ,java-biojava-phylo)
12500 ("java-forester" ,java-forester)))
12502 `(("java-junit" ,java-junit)
12503 ("java-hamcrest-core" ,java-hamcrest-core)))
12504 (home-page "http://biojava.org")
12505 (synopsis "Biojava API for genetic sequence alignment")
12506 (description "The alignment module of BioJava provides an API that
12510 @item implementations of dynamic programming algorithms for sequence
12512 @item reading and writing of popular alignment file formats;
12513 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12516 (define-public java-biojava-core-4.0
12517 (package (inherit java-biojava-core)
12518 (name "java-biojava-core")
12522 (uri (git-reference
12523 (url "https://github.com/biojava/biojava")
12524 (commit (string-append "biojava-" version))))
12525 (file-name (string-append name "-" version "-checkout"))
12528 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12530 (define-public java-biojava-phylo-4.0
12531 (package (inherit java-biojava-core-4.0)
12532 (name "java-biojava-phylo")
12533 (build-system ant-build-system)
12536 #:jar-name "biojava-phylo.jar"
12537 #:source-dir "biojava-phylo/src/main/java/"
12538 #:test-dir "biojava-phylo/src/test"
12540 (modify-phases %standard-phases
12541 (add-before 'build 'copy-resources
12543 (copy-recursively "biojava-phylo/src/main/resources"
12546 (add-before 'check 'copy-test-resources
12548 (copy-recursively "biojava-phylo/src/test/resources"
12549 "build/test-classes")
12552 `(("java-log4j-api" ,java-log4j-api)
12553 ("java-log4j-core" ,java-log4j-core)
12554 ("java-slf4j-api" ,java-slf4j-api)
12555 ("java-slf4j-simple" ,java-slf4j-simple)
12556 ("java-biojava-core" ,java-biojava-core-4.0)
12557 ("java-forester" ,java-forester-1.005)))
12559 `(("java-junit" ,java-junit)
12560 ("java-hamcrest-core" ,java-hamcrest-core)))
12561 (home-page "http://biojava.org")
12562 (synopsis "Biojava interface to the forester phylogenomics library")
12563 (description "The phylo module provides a biojava interface layer to the
12564 forester phylogenomics library for constructing phylogenetic trees.")))
12566 (define-public java-biojava-alignment-4.0
12567 (package (inherit java-biojava-core-4.0)
12568 (name "java-biojava-alignment")
12569 (build-system ant-build-system)
12572 #:jar-name "biojava-alignment.jar"
12573 #:source-dir "biojava-alignment/src/main/java/"
12574 #:test-dir "biojava-alignment/src/test"
12576 (modify-phases %standard-phases
12577 (add-before 'build 'copy-resources
12579 (copy-recursively "biojava-alignment/src/main/resources"
12582 (add-before 'check 'copy-test-resources
12584 (copy-recursively "biojava-alignment/src/test/resources"
12585 "build/test-classes")
12588 `(("java-log4j-api" ,java-log4j-api)
12589 ("java-log4j-core" ,java-log4j-core)
12590 ("java-slf4j-api" ,java-slf4j-api)
12591 ("java-slf4j-simple" ,java-slf4j-simple)
12592 ("java-biojava-core" ,java-biojava-core-4.0)
12593 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12594 ("java-forester" ,java-forester-1.005)))
12596 `(("java-junit" ,java-junit)
12597 ("java-hamcrest-core" ,java-hamcrest-core)))
12598 (home-page "http://biojava.org")
12599 (synopsis "Biojava API for genetic sequence alignment")
12600 (description "The alignment module of BioJava provides an API that
12604 @item implementations of dynamic programming algorithms for sequence
12606 @item reading and writing of popular alignment file formats;
12607 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12610 (define-public dropseq-tools
12612 (name "dropseq-tools")
12617 (uri "http://mccarrolllab.com/download/1276/")
12618 (file-name (string-append "dropseq-tools-" version ".zip"))
12621 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12622 ;; Delete bundled libraries
12623 (modules '((guix build utils)))
12626 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12627 (delete-file-recursively "3rdParty")))))
12628 (build-system ant-build-system)
12630 `(#:tests? #f ; test data are not included
12631 #:test-target "test"
12632 #:build-target "all"
12633 #:source-dir "public/src/"
12636 (list (string-append "-Dpicard.executable.dir="
12637 (assoc-ref %build-inputs "java-picard")
12639 #:modules ((ice-9 match)
12642 (guix build java-utils)
12643 (guix build ant-build-system))
12645 (modify-phases %standard-phases
12646 ;; All dependencies must be linked to "lib", because that's where
12647 ;; they will be searched for when the Class-Path property of the
12648 ;; manifest is computed.
12649 (add-after 'unpack 'record-references
12650 (lambda* (#:key inputs #:allow-other-keys)
12651 (mkdir-p "jar/lib")
12652 (let ((dirs (filter-map (match-lambda
12654 (if (and (string-prefix? "java-" name)
12655 (not (string=? name "java-testng")))
12658 (for-each (lambda (jar)
12659 (symlink jar (string-append "jar/lib/" (basename jar))))
12660 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12663 ;; There is no installation target
12665 (lambda* (#:key inputs outputs #:allow-other-keys)
12666 (let* ((out (assoc-ref outputs "out"))
12667 (bin (string-append out "/bin"))
12668 (share (string-append out "/share/java/"))
12669 (lib (string-append share "/lib/"))
12670 (scripts (list "BAMTagHistogram"
12671 "BAMTagofTagCounts"
12672 "BaseDistributionAtReadPosition"
12673 "CollapseBarcodesInPlace"
12674 "CollapseTagWithContext"
12676 "CreateIntervalsFiles"
12677 "DetectBeadSynthesisErrors"
12678 "DigitalExpression"
12679 "Drop-seq_alignment.sh"
12682 "GatherGeneGCLength"
12683 "GatherMolecularBarcodeDistributionByGene"
12684 "GatherReadQualityMetrics"
12687 "SelectCellsByNumTranscripts"
12688 "SingleCellRnaSeqMetricsCollector"
12689 "TagBamWithReadSequenceExtended"
12690 "TagReadWithGeneExon"
12691 "TagReadWithInterval"
12692 "TrimStartingSequence"
12693 "ValidateReference")))
12694 (for-each mkdir-p (list bin share lib))
12695 (install-file "dist/dropseq.jar" share)
12696 (for-each (lambda (script)
12697 (chmod script #o555)
12698 (install-file script bin))
12700 (substitute* (map (lambda (script)
12701 (string-append bin "/" script))
12703 (("^java") (which "java"))
12704 (("jar_deploy_dir=.*")
12705 (string-append "jar_deploy_dir=" share "\n"))))
12707 ;; FIXME: We do this after stripping jars because we don't want it to
12708 ;; copy all these jars and strip them. We only want to install
12709 ;; links. Arguably, this is a problem with the ant-build-system.
12710 (add-after 'strip-jar-timestamps 'install-links
12711 (lambda* (#:key outputs #:allow-other-keys)
12712 (let* ((out (assoc-ref outputs "out"))
12713 (share (string-append out "/share/java/"))
12714 (lib (string-append share "/lib/")))
12715 (for-each (lambda (jar)
12716 (symlink (readlink jar)
12717 (string-append lib (basename jar))))
12718 (find-files "jar/lib" "\\.jar$")))
12721 `(("jdk" ,icedtea-8)
12722 ("java-picard" ,java-picard-2.10.3)
12723 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12724 ("java-commons-math3" ,java-commons-math3)
12725 ("java-commons-jexl2" ,java-commons-jexl-2)
12726 ("java-commons-collections4" ,java-commons-collections4)
12727 ("java-commons-lang2" ,java-commons-lang)
12728 ("java-commons-io" ,java-commons-io)
12729 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12730 ("java-guava" ,java-guava)
12731 ("java-la4j" ,java-la4j)
12732 ("java-biojava-core" ,java-biojava-core-4.0)
12733 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12734 ("java-jdistlib" ,java-jdistlib)
12735 ("java-simple-xml" ,java-simple-xml)
12736 ("java-snakeyaml" ,java-snakeyaml)))
12739 ("java-testng" ,java-testng)))
12740 (home-page "http://mccarrolllab.com/dropseq/")
12741 (synopsis "Tools for Drop-seq analyses")
12742 (description "Drop-seq is a technology to enable biologists to
12743 analyze RNA expression genome-wide in thousands of individual cells at
12744 once. This package provides tools to perform Drop-seq analyses.")
12745 (license license:expat)))
12747 (define-public pigx-rnaseq
12749 (name "pigx-rnaseq")
12753 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12754 "releases/download/v" version
12755 "/pigx_rnaseq-" version ".tar.gz"))
12758 "0pz080k4ajlc4rlznkn3najy2a6874gb56rf9g4ag9wqz31q174j"))))
12759 (build-system gnu-build-system)
12761 `(#:parallel-tests? #f ; not supported
12763 (modify-phases %standard-phases
12764 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12765 (add-after 'unpack 'disable-resource-intensive-test
12767 (substitute* "Makefile.in"
12768 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12769 (("^ test.sh") ""))
12771 (add-after 'install 'wrap-executable
12772 ;; Make sure the executable finds all R modules.
12773 (lambda* (#:key inputs outputs #:allow-other-keys)
12774 (let ((out (assoc-ref outputs "out")))
12775 (wrap-program (string-append out "/bin/pigx-rnaseq")
12776 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12777 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12781 ("snakemake" ,snakemake)
12783 ("multiqc" ,multiqc)
12785 ("trim-galore" ,trim-galore)
12787 ("samtools" ,samtools)
12788 ("bedtools" ,bedtools)
12789 ("r-minimal" ,r-minimal)
12790 ("r-rmarkdown" ,r-rmarkdown)
12791 ("r-ggplot2" ,r-ggplot2)
12792 ("r-ggrepel" ,r-ggrepel)
12793 ("r-gprofiler" ,r-gprofiler)
12794 ("r-deseq2" ,r-deseq2)
12796 ("r-knitr" ,r-knitr)
12797 ("r-pheatmap" ,r-pheatmap)
12798 ("r-corrplot" ,r-corrplot)
12799 ("r-reshape2" ,r-reshape2)
12800 ("r-plotly" ,r-plotly)
12801 ("r-scales" ,r-scales)
12802 ("r-summarizedexperiment" ,r-summarizedexperiment)
12803 ("r-crosstalk" ,r-crosstalk)
12804 ("r-tximport" ,r-tximport)
12805 ("r-rtracklayer" ,r-rtracklayer)
12806 ("r-rjson" ,r-rjson)
12808 ("ghc-pandoc" ,ghc-pandoc-1)
12809 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12810 ("python-wrapper" ,python-wrapper)
12811 ("python-pyyaml" ,python-pyyaml)))
12812 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12813 (synopsis "Analysis pipeline for RNA sequencing experiments")
12814 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12815 reporting for RNA sequencing experiments. It is easy to use and produces high
12816 quality reports. The inputs are reads files from the sequencing experiment,
12817 and a configuration file which describes the experiment. In addition to
12818 quality control of the experiment, the pipeline produces a differential
12819 expression report comparing samples in an easily configurable manner.")
12820 (license license:gpl3+)))
12822 (define-public pigx-chipseq
12824 (name "pigx-chipseq")
12828 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12829 "releases/download/v" version
12830 "/pigx_chipseq-" version ".tar.gz"))
12833 "11v9v3vyda0sv4cl45nki7mm4v4bjfcdq7a70kcvi9h465nq66wg"))))
12834 (build-system gnu-build-system)
12836 `(#:tests? #f ; parts of the tests rely on access to the network
12838 (modify-phases %standard-phases
12839 (add-after 'install 'wrap-executable
12840 ;; Make sure the executable finds all R modules.
12841 (lambda* (#:key inputs outputs #:allow-other-keys)
12842 (let ((out (assoc-ref outputs "out")))
12843 (wrap-program (string-append out "/bin/pigx-chipseq")
12844 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12845 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12849 ("coreutils" ,coreutils)
12850 ("r-minimal" ,r-minimal)
12851 ("r-argparser" ,r-argparser)
12852 ("r-biocparallel" ,r-biocparallel)
12853 ("r-biostrings" ,r-biostrings)
12854 ("r-chipseq" ,r-chipseq)
12855 ("r-data-table" ,r-data-table)
12856 ("r-dplyr" ,r-dplyr)
12857 ("r-genomation" ,r-genomation)
12858 ("r-genomicalignments" ,r-genomicalignments)
12859 ("r-genomicranges" ,r-genomicranges)
12860 ("r-rsamtools" ,r-rsamtools)
12861 ("r-rtracklayer" ,r-rtracklayer)
12862 ("r-s4vectors" ,r-s4vectors)
12863 ("r-stringr" ,r-stringr)
12864 ("r-tibble" ,r-tibble)
12865 ("r-tidyr" ,r-tidyr)
12866 ("r-jsonlite" ,r-jsonlite)
12867 ("r-heatmaply" ,r-heatmaply)
12868 ("r-htmlwidgets" ,r-htmlwidgets)
12869 ("r-ggplot2" ,r-ggplot2)
12870 ("r-plotly" ,r-plotly)
12871 ("r-rmarkdown" ,r-rmarkdown)
12872 ("python-wrapper" ,python-wrapper)
12873 ("python-pyyaml" ,python-pyyaml)
12874 ("python-magic" ,python-magic)
12875 ("python-xlrd" ,python-xlrd)
12876 ("trim-galore" ,trim-galore)
12878 ("multiqc" ,multiqc)
12880 ("ghc-pandoc" ,ghc-pandoc-1)
12881 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12885 ("snakemake" ,snakemake)
12886 ("samtools" ,samtools)
12887 ("bedtools" ,bedtools)
12888 ("kentutils" ,kentutils)))
12890 `(("python-pytest" ,python-pytest)))
12891 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12892 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12893 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12894 calling and reporting for ChIP sequencing experiments. It is easy to use and
12895 produces high quality reports. The inputs are reads files from the sequencing
12896 experiment, and a configuration file which describes the experiment. In
12897 addition to quality control of the experiment, the pipeline enables to set up
12898 multiple peak calling analysis and allows the generation of a UCSC track hub
12899 in an easily configurable manner.")
12900 (license license:gpl3+)))
12902 (define-public pigx-bsseq
12904 (name "pigx-bsseq")
12908 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12909 "releases/download/v" version
12910 "/pigx_bsseq-" version ".tar.gz"))
12913 "0irlnlhhw9fd4ha7hksrxn3y7j76mz5qq1wjswbs9p364laqg69y"))))
12914 (build-system gnu-build-system)
12917 (modify-phases %standard-phases
12918 (add-before 'check 'set-timezone
12919 ;; The readr package is picky about timezones.
12920 (lambda* (#:key inputs #:allow-other-keys)
12921 (setenv "TZ" "UTC+1")
12923 (string-append (assoc-ref inputs "tzdata")
12924 "/share/zoneinfo"))
12926 (add-after 'install 'wrap-executable
12927 ;; Make sure the executable finds all R modules.
12928 (lambda* (#:key inputs outputs #:allow-other-keys)
12929 (let ((out (assoc-ref outputs "out")))
12930 (wrap-program (string-append out "/bin/pigx-bsseq")
12931 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12932 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12935 `(("tzdata" ,tzdata)))
12937 `(("coreutils" ,coreutils)
12940 ("r-minimal" ,r-minimal)
12941 ("r-annotationhub" ,r-annotationhub)
12943 ("r-genomation" ,r-genomation)
12944 ("r-methylkit" ,r-methylkit)
12945 ("r-rtracklayer" ,r-rtracklayer)
12946 ("r-rmarkdown" ,r-rmarkdown)
12947 ("r-bookdown" ,r-bookdown)
12948 ("r-ggplot2" ,r-ggplot2)
12949 ("r-ggbio" ,r-ggbio)
12950 ("ghc-pandoc" ,ghc-pandoc-1)
12951 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12952 ("python-wrapper" ,python-wrapper)
12953 ("python-pyyaml" ,python-pyyaml)
12954 ("snakemake" ,snakemake)
12955 ("bismark" ,bismark)
12958 ("trim-galore" ,trim-galore)
12959 ("cutadapt" ,cutadapt)
12960 ("samtools" ,samtools)))
12961 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12962 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12963 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12964 data of bisulfite experiments; it produces reports on aggregate methylation
12965 and coverage and can be used to produce information on differential
12966 methylation and segmentation.")
12967 (license license:gpl3+)))
12969 (define-public pigx-scrnaseq
12971 (name "pigx-scrnaseq")
12975 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12976 "releases/download/v" version
12977 "/pigx_scrnaseq-" version ".tar.gz"))
12980 "12qdq0nj1wdkyighdxj6924bmbpd1a0b3gam6w64l4hiqrv5sijz"))))
12981 (build-system gnu-build-system)
12983 `(#:configure-flags
12984 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12985 "/share/java/picard.jar")
12986 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12987 "/share/java/dropseq.jar"))
12989 (modify-phases %standard-phases
12990 (add-after 'install 'wrap-executable
12991 ;; Make sure the executable finds all R modules.
12992 (lambda* (#:key inputs outputs #:allow-other-keys)
12993 (let ((out (assoc-ref outputs "out")))
12994 (wrap-program (string-append out "/bin/pigx-scrnaseq")
12995 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12996 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12999 `(("coreutils" ,coreutils)
13001 ("dropseq-tools" ,dropseq-tools)
13003 ("java-picard" ,java-picard)
13004 ("java" ,icedtea-8)
13005 ("python-wrapper" ,python-wrapper)
13006 ("python-pyyaml" ,python-pyyaml)
13007 ("python-pandas" ,python-pandas)
13008 ("python-numpy" ,python-numpy)
13009 ("python-loompy" ,python-loompy)
13010 ("ghc-pandoc" ,ghc-pandoc-1)
13011 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
13012 ("snakemake" ,snakemake)
13014 ("r-minimal" ,r-minimal)
13015 ("r-argparser" ,r-argparser)
13016 ("r-cowplot" ,r-cowplot)
13017 ("r-data-table" ,r-data-table)
13018 ("r-delayedarray" ,r-delayedarray)
13019 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13020 ("r-dplyr" ,r-dplyr)
13021 ("r-dropbead" ,r-dropbead)
13023 ("r-genomicalignments" ,r-genomicalignments)
13024 ("r-genomicfiles" ,r-genomicfiles)
13025 ("r-genomicranges" ,r-genomicranges)
13026 ("r-ggplot2" ,r-ggplot2)
13027 ("r-hdf5array" ,r-hdf5array)
13028 ("r-pheatmap" ,r-pheatmap)
13029 ("r-rmarkdown" ,r-rmarkdown)
13030 ("r-rsamtools" ,r-rsamtools)
13031 ("r-rtracklayer" ,r-rtracklayer)
13032 ("r-rtsne" ,r-rtsne)
13033 ("r-scater" ,r-scater)
13034 ("r-scran" ,r-scran)
13035 ("r-singlecellexperiment" ,r-singlecellexperiment)
13036 ("r-stringr" ,r-stringr)
13037 ("r-yaml" ,r-yaml)))
13038 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13039 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13040 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13041 quality control for single cell RNA sequencing experiments. The inputs are
13042 read files from the sequencing experiment, and a configuration file which
13043 describes the experiment. It produces processed files for downstream analysis
13044 and interactive quality reports. The pipeline is designed to work with UMI
13046 (license license:gpl3+)))
13048 (define-public pigx
13054 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13055 "releases/download/v" version
13056 "/pigx-" version ".tar.gz"))
13059 "0sb708sl42h3s5z872jb1w70bbqplwapnsc1wm27zcsvi7li4gw8"))))
13060 (build-system gnu-build-system)
13062 `(("python" ,python)
13063 ("pigx-bsseq" ,pigx-bsseq)
13064 ("pigx-chipseq" ,pigx-chipseq)
13065 ("pigx-rnaseq" ,pigx-rnaseq)
13066 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13067 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13068 (synopsis "Analysis pipelines for genomics")
13069 (description "PiGx is a collection of genomics pipelines. It includes the
13070 following pipelines:
13073 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13074 @item PiGx RNAseq for RNAseq samples
13075 @item PiGx scRNAseq for single cell dropseq analysis
13076 @item PiGx ChIPseq for reads from ChIPseq experiments
13079 All pipelines are easily configured with a simple sample sheet and a
13080 descriptive settings file. The result is a set of comprehensive, interactive
13081 HTML reports with interesting findings about your samples.")
13082 (license license:gpl3+)))
13084 (define-public r-diversitree
13086 (name "r-diversitree")
13091 (uri (cran-uri "diversitree" version))
13094 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13095 (build-system r-build-system)
13097 `(("gfortran" ,gfortran)))
13098 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13101 ("r-desolve" ,r-desolve)
13103 ("r-suplex" ,r-subplex)))
13104 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13105 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13106 (description "This package contains a number of comparative \"phylogenetic\"
13107 methods, mostly focusing on analysing diversification and character evolution.
13108 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13109 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13110 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13111 include Markov models of discrete and continuous trait evolution and constant
13112 rate speciation and extinction.")
13113 (license license:gpl2+)))