1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
14 ;;; This file is part of GNU Guix.
16 ;;; GNU Guix is free software; you can redistribute it and/or modify it
17 ;;; under the terms of the GNU General Public License as published by
18 ;;; the Free Software Foundation; either version 3 of the License, or (at
19 ;;; your option) any later version.
21 ;;; GNU Guix is distributed in the hope that it will be useful, but
22 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;;; GNU General Public License for more details.
26 ;;; You should have received a copy of the GNU General Public License
27 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
29 (define-module (gnu packages bioinformatics)
30 #:use-module ((guix licenses) #:prefix license:)
31 #:use-module (guix packages)
32 #:use-module (guix utils)
33 #:use-module (guix download)
34 #:use-module (guix git-download)
35 #:use-module (guix hg-download)
36 #:use-module (guix build-system ant)
37 #:use-module (guix build-system gnu)
38 #:use-module (guix build-system cmake)
39 #:use-module (guix build-system ocaml)
40 #:use-module (guix build-system perl)
41 #:use-module (guix build-system python)
42 #:use-module (guix build-system r)
43 #:use-module (guix build-system ruby)
44 #:use-module (guix build-system scons)
45 #:use-module (guix build-system trivial)
46 #:use-module (gnu packages)
47 #:use-module (gnu packages autotools)
48 #:use-module (gnu packages algebra)
49 #:use-module (gnu packages base)
50 #:use-module (gnu packages bash)
51 #:use-module (gnu packages bison)
52 #:use-module (gnu packages boost)
53 #:use-module (gnu packages check)
54 #:use-module (gnu packages compression)
55 #:use-module (gnu packages cpio)
56 #:use-module (gnu packages cran)
57 #:use-module (gnu packages curl)
58 #:use-module (gnu packages documentation)
59 #:use-module (gnu packages databases)
60 #:use-module (gnu packages datastructures)
61 #:use-module (gnu packages file)
62 #:use-module (gnu packages flex)
63 #:use-module (gnu packages gawk)
64 #:use-module (gnu packages gcc)
65 #:use-module (gnu packages gd)
66 #:use-module (gnu packages gtk)
67 #:use-module (gnu packages glib)
68 #:use-module (gnu packages graph)
69 #:use-module (gnu packages groff)
70 #:use-module (gnu packages guile)
71 #:use-module (gnu packages haskell)
72 #:use-module (gnu packages image)
73 #:use-module (gnu packages imagemagick)
74 #:use-module (gnu packages java)
75 #:use-module (gnu packages jemalloc)
76 #:use-module (gnu packages ldc)
77 #:use-module (gnu packages linux)
78 #:use-module (gnu packages logging)
79 #:use-module (gnu packages machine-learning)
80 #:use-module (gnu packages man)
81 #:use-module (gnu packages maths)
82 #:use-module (gnu packages mpi)
83 #:use-module (gnu packages ncurses)
84 #:use-module (gnu packages ocaml)
85 #:use-module (gnu packages pcre)
86 #:use-module (gnu packages parallel)
87 #:use-module (gnu packages pdf)
88 #:use-module (gnu packages perl)
89 #:use-module (gnu packages perl-check)
90 #:use-module (gnu packages pkg-config)
91 #:use-module (gnu packages popt)
92 #:use-module (gnu packages protobuf)
93 #:use-module (gnu packages python)
94 #:use-module (gnu packages python-web)
95 #:use-module (gnu packages readline)
96 #:use-module (gnu packages ruby)
97 #:use-module (gnu packages serialization)
98 #:use-module (gnu packages shells)
99 #:use-module (gnu packages statistics)
100 #:use-module (gnu packages swig)
101 #:use-module (gnu packages tbb)
102 #:use-module (gnu packages tex)
103 #:use-module (gnu packages texinfo)
104 #:use-module (gnu packages textutils)
105 #:use-module (gnu packages time)
106 #:use-module (gnu packages tls)
107 #:use-module (gnu packages vim)
108 #:use-module (gnu packages web)
109 #:use-module (gnu packages xml)
110 #:use-module (gnu packages xorg)
111 #:use-module (srfi srfi-1)
112 #:use-module (ice-9 match))
114 (define-public aragorn
121 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
125 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
126 (build-system gnu-build-system)
128 `(#:tests? #f ; there are no tests
130 (modify-phases %standard-phases
134 (zero? (system* "gcc"
140 (string-append "aragorn" ,version ".c")))))
142 (lambda* (#:key outputs #:allow-other-keys)
143 (let* ((out (assoc-ref outputs "out"))
144 (bin (string-append out "/bin"))
145 (man (string-append out "/share/man/man1")))
147 (install-file "aragorn" bin)
149 (install-file "aragorn.1" man))
151 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
152 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
154 "Aragorn identifies transfer RNA, mitochondrial RNA and
155 transfer-messenger RNA from nucleotide sequences, based on homology to known
156 tRNA consensus sequences and RNA structure. It also outputs the secondary
157 structure of the predicted RNA.")
158 (license license:gpl2)))
166 ;; BamM is not available on pypi.
168 "https://github.com/Ecogenomics/BamM/archive/"
170 (file-name (string-append name "-" version ".tar.gz"))
173 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
174 (modules '((guix build utils)))
177 ;; Delete bundled htslib.
178 (delete-file-recursively "c/htslib-1.3.1")
180 (build-system python-build-system)
182 `(#:python ,python-2 ; BamM is Python 2 only.
183 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
184 ;; been modified from its original form.
186 (let ((htslib (assoc-ref %build-inputs "htslib")))
187 (list "--with-libhts-lib" (string-append htslib "/lib")
188 "--with-libhts-inc" (string-append htslib "/include/htslib")))
190 (modify-phases %standard-phases
191 (add-after 'unpack 'autogen
193 (with-directory-excursion "c"
194 (let ((sh (which "sh")))
195 ;; Use autogen so that 'configure' works.
196 (substitute* "autogen.sh" (("/bin/sh") sh))
197 (setenv "CONFIG_SHELL" sh)
198 (substitute* "configure" (("/bin/sh") sh))
199 (zero? (system* "./autogen.sh"))))))
201 ;; Run tests after installation so compilation only happens once.
203 (add-after 'install 'wrap-executable
204 (lambda* (#:key outputs #:allow-other-keys)
205 (let* ((out (assoc-ref outputs "out"))
206 (path (getenv "PATH")))
207 (wrap-program (string-append out "/bin/bamm")
208 `("PATH" ":" prefix (,path))))
210 (add-after 'wrap-executable 'post-install-check
211 (lambda* (#:key inputs outputs #:allow-other-keys)
213 (string-append (assoc-ref outputs "out")
218 (assoc-ref outputs "out")
220 (string-take (string-take-right
221 (assoc-ref inputs "python") 5) 3)
223 (getenv "PYTHONPATH")))
224 ;; There are 2 errors printed, but they are safe to ignore:
225 ;; 1) [E::hts_open_format] fail to open file ...
226 ;; 2) samtools view: failed to open ...
227 (zero? (system* "nosetests")))))))
229 `(("autoconf" ,autoconf)
230 ("automake" ,automake)
233 ("python-nose" ,python2-nose)
234 ("python-pysam" ,python2-pysam)))
236 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
237 ("samtools" ,samtools)
241 ("coreutils" ,coreutils)))
243 `(("python-numpy" ,python2-numpy)))
244 (home-page "http://ecogenomics.github.io/BamM/")
245 (synopsis "Metagenomics-focused BAM file manipulator")
247 "BamM is a C library, wrapped in python, to efficiently generate and
248 parse BAM files, specifically for the analysis of metagenomic data. For
249 instance, it implements several methods to assess contig-wise read coverage.")
250 (license license:lgpl3+)))
252 (define-public bamtools
259 "https://github.com/pezmaster31/bamtools/archive/v"
261 (file-name (string-append name "-" version ".tar.gz"))
264 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
265 (build-system cmake-build-system)
267 `(#:tests? #f ;no "check" target
269 (modify-phases %standard-phases
271 'configure 'set-ldflags
272 (lambda* (#:key outputs #:allow-other-keys)
276 (assoc-ref outputs "out") "/lib/bamtools")))))))
277 (inputs `(("zlib" ,zlib)))
278 (home-page "https://github.com/pezmaster31/bamtools")
279 (synopsis "C++ API and command-line toolkit for working with BAM data")
281 "BamTools provides both a C++ API and a command-line toolkit for handling
283 (license license:expat)))
285 (define-public bcftools
292 "https://github.com/samtools/bcftools/releases/download/"
293 version "/bcftools-" version ".tar.bz2"))
296 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
297 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
298 (modules '((guix build utils)))
300 ;; Delete bundled htslib.
301 '(delete-file-recursively "htslib-1.5"))))
302 (build-system gnu-build-system)
304 `(#:test-target "test"
305 #:configure-flags (list "--with-htslib=system")
309 "LIBS=-lgsl -lgslcblas"
310 (string-append "prefix=" (assoc-ref %outputs "out"))
311 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
312 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
313 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
314 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
315 (string-append "PACKAGE_VERSION=" ,version))
317 (modify-phases %standard-phases
318 (add-before 'check 'patch-tests
320 (substitute* "test/test.pl"
321 (("/bin/bash") (which "bash")))
329 (home-page "https://samtools.github.io/bcftools/")
330 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
332 "BCFtools is a set of utilities that manipulate variant calls in the
333 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
334 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
335 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
336 (license (list license:gpl3+ license:expat))))
338 (define-public bedops
344 (uri (string-append "https://github.com/bedops/bedops/archive/v"
346 (file-name (string-append name "-" version ".tar.gz"))
349 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
350 (build-system gnu-build-system)
353 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
355 (modify-phases %standard-phases
356 (add-after 'unpack 'unpack-tarballs
358 ;; FIXME: Bedops includes tarballs of minimally patched upstream
359 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
360 ;; libraries because at least one of the libraries (zlib) is
361 ;; patched to add a C++ function definition (deflateInit2cpp).
362 ;; Until the Bedops developers offer a way to link against system
363 ;; libraries we have to build the in-tree copies of these three
366 ;; See upstream discussion:
367 ;; https://github.com/bedops/bedops/issues/124
369 ;; Unpack the tarballs to benefit from shebang patching.
370 (with-directory-excursion "third-party"
371 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
372 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
373 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
374 ;; Disable unpacking of tarballs in Makefile.
375 (substitute* "system.mk/Makefile.linux"
376 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
377 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
378 (substitute* "third-party/zlib-1.2.7/Makefile.in"
379 (("^SHELL=.*$") "SHELL=bash\n"))
381 (delete 'configure))))
382 (home-page "https://github.com/bedops/bedops")
383 (synopsis "Tools for high-performance genomic feature operations")
385 "BEDOPS is a suite of tools to address common questions raised in genomic
386 studies---mostly with regard to overlap and proximity relationships between
387 data sets. It aims to be scalable and flexible, facilitating the efficient
388 and accurate analysis and management of large-scale genomic data.
390 BEDOPS provides tools that perform highly efficient and scalable Boolean and
391 other set operations, statistical calculations, archiving, conversion and
392 other management of genomic data of arbitrary scale. Tasks can be easily
393 split by chromosome for distributing whole-genome analyses across a
394 computational cluster.")
395 (license license:gpl2+)))
397 (define-public bedtools
403 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
404 "download/v" version "/"
405 "bedtools-" version ".tar.gz"))
408 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
409 (build-system gnu-build-system)
411 '(#:test-target "test"
413 (list (string-append "prefix=" (assoc-ref %outputs "out")))
415 (modify-phases %standard-phases
416 (delete 'configure))))
417 (native-inputs `(("python" ,python-2)))
419 `(("samtools" ,samtools)
421 (home-page "https://github.com/arq5x/bedtools2")
422 (synopsis "Tools for genome analysis and arithmetic")
424 "Collectively, the bedtools utilities are a swiss-army knife of tools for
425 a wide-range of genomics analysis tasks. The most widely-used tools enable
426 genome arithmetic: that is, set theory on the genome. For example, bedtools
427 allows one to intersect, merge, count, complement, and shuffle genomic
428 intervals from multiple files in widely-used genomic file formats such as BAM,
430 (license license:gpl2)))
432 ;; Later releases of bedtools produce files with more columns than
433 ;; what Ribotaper expects.
434 (define-public bedtools-2.18
435 (package (inherit bedtools)
440 (uri (string-append "https://github.com/arq5x/bedtools2/"
441 "archive/v" version ".tar.gz"))
442 (file-name (string-append name "-" version ".tar.gz"))
445 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
447 '(#:test-target "test"
449 (modify-phases %standard-phases
452 (lambda* (#:key outputs #:allow-other-keys)
453 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
454 (for-each (lambda (file)
455 (install-file file bin))
456 (find-files "bin" ".*")))
459 (define-public ribotaper
465 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
466 "files/RiboTaper/RiboTaper_Version_"
470 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
471 (build-system gnu-build-system)
474 (modify-phases %standard-phases
475 (add-after 'install 'wrap-executables
476 (lambda* (#:key inputs outputs #:allow-other-keys)
477 (let* ((out (assoc-ref outputs "out")))
480 (wrap-program (string-append out "/bin/" script)
481 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
482 '("create_annotations_files.bash"
483 "create_metaplots.bash"
484 "Ribotaper_ORF_find.sh"
485 "Ribotaper.sh"))))))))
487 `(("bedtools" ,bedtools-2.18)
488 ("samtools" ,samtools-0.1)
489 ("r-minimal" ,r-minimal)
490 ("r-foreach" ,r-foreach)
491 ("r-xnomial" ,r-xnomial)
493 ("r-multitaper" ,r-multitaper)
494 ("r-seqinr" ,r-seqinr)))
495 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
496 (synopsis "Define translated ORFs using ribosome profiling data")
498 "Ribotaper is a method for defining translated @dfn{open reading
499 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
500 provides the Ribotaper pipeline.")
501 (license license:gpl3+)))
503 (define-public ribodiff
510 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
511 "archive/v" version ".tar.gz"))
512 (file-name (string-append name "-" version ".tar.gz"))
515 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
516 (build-system python-build-system)
520 (modify-phases %standard-phases
521 ;; Generate an installable executable script wrapper.
522 (add-after 'unpack 'patch-setup.py
524 (substitute* "setup.py"
525 (("^(.*)packages=.*" line prefix)
526 (string-append line "\n"
527 prefix "scripts=['scripts/TE.py'],\n")))
530 `(("python-numpy" ,python2-numpy)
531 ("python-matplotlib" ,python2-matplotlib)
532 ("python-scipy" ,python2-scipy)
533 ("python-statsmodels" ,python2-statsmodels)))
535 `(("python-mock" ,python2-mock)
536 ("python-nose" ,python2-nose)))
537 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
538 (synopsis "Detect translation efficiency changes from ribosome footprints")
539 (description "RiboDiff is a statistical tool that detects the protein
540 translational efficiency change from Ribo-Seq (ribosome footprinting) and
541 RNA-Seq data. It uses a generalized linear model to detect genes showing
542 difference in translational profile taking mRNA abundance into account. It
543 facilitates us to decipher the translational regulation that behave
544 independently with transcriptional regulation.")
545 (license license:gpl3+)))
547 (define-public bioawk
553 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
555 (file-name (string-append name "-" version ".tar.gz"))
557 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
558 (build-system gnu-build-system)
564 `(#:tests? #f ; There are no tests to run.
565 ;; Bison must generate files, before other targets can build.
568 (modify-phases %standard-phases
569 (delete 'configure) ; There is no configure phase.
571 (lambda* (#:key outputs #:allow-other-keys)
572 (let* ((out (assoc-ref outputs "out"))
573 (bin (string-append out "/bin"))
574 (man (string-append out "/share/man/man1")))
576 (copy-file "awk.1" (string-append man "/bioawk.1"))
577 (install-file "bioawk" bin)))))))
578 (home-page "https://github.com/lh3/bioawk")
579 (synopsis "AWK with bioinformatics extensions")
580 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
581 support of several common biological data formats, including optionally gzip'ed
582 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
583 also adds a few built-in functions and a command line option to use TAB as the
584 input/output delimiter. When the new functionality is not used, bioawk is
585 intended to behave exactly the same as the original BWK awk.")
586 (license license:x11)))
588 (define-public python2-pybedtools
590 (name "python2-pybedtools")
595 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
599 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
600 (build-system python-build-system)
601 (arguments `(#:python ,python-2)) ; no Python 3 support
603 `(("python-matplotlib" ,python2-matplotlib)))
605 `(("bedtools" ,bedtools)
606 ("samtools" ,samtools)))
608 `(("python-cython" ,python2-cython)
609 ("python-pyyaml" ,python2-pyyaml)
610 ("python-nose" ,python2-nose)))
611 (home-page "https://pythonhosted.org/pybedtools/")
612 (synopsis "Python wrapper for BEDtools programs")
614 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
615 which are widely used for genomic interval manipulation or \"genome algebra\".
616 pybedtools extends BEDTools by offering feature-level manipulations from with
618 (license license:gpl2+)))
620 (define-public python-biom-format
622 (name "python-biom-format")
627 ;; Use GitHub as source because PyPI distribution does not contain
628 ;; test data: https://github.com/biocore/biom-format/issues/693
629 (uri (string-append "https://github.com/biocore/biom-format/archive/"
631 (file-name (string-append name "-" version ".tar.gz"))
634 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
635 (build-system python-build-system)
637 `(("python-numpy" ,python-numpy)
638 ("python-scipy" ,python-scipy)
639 ("python-future" ,python-future)
640 ("python-click" ,python-click)
641 ("python-h5py" ,python-h5py)
642 ("python-pandas" ,python-pandas)))
644 `(("python-nose" ,python-nose)))
645 (home-page "http://www.biom-format.org")
646 (synopsis "Biological Observation Matrix (BIOM) format utilities")
648 "The BIOM file format is designed to be a general-use format for
649 representing counts of observations e.g. operational taxonomic units, KEGG
650 orthology groups or lipid types, in one or more biological samples
651 e.g. microbiome samples, genomes, metagenomes.")
652 (license license:bsd-3)
653 (properties `((python2-variant . ,(delay python2-biom-format))))))
655 (define-public python2-biom-format
656 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
661 (modify-phases %standard-phases
662 ;; Do not require the unmaintained pyqi library.
663 (add-after 'unpack 'remove-pyqi
665 (substitute* "setup.py"
666 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
668 ,@(package-arguments base))))))
670 (define-public bioperl-minimal
671 (let* ((inputs `(("perl-module-build" ,perl-module-build)
672 ("perl-data-stag" ,perl-data-stag)
673 ("perl-libwww" ,perl-libwww)
674 ("perl-uri" ,perl-uri)))
676 (map (compose package-name cadr)
679 (map (compose package-transitive-target-inputs cadr) inputs))))))
681 (name "bioperl-minimal")
686 (uri (string-append "https://github.com/bioperl/bioperl-live/"
688 (string-map (lambda (c)
694 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
695 (build-system perl-build-system)
698 (modify-phases %standard-phases
700 'install 'wrap-programs
701 (lambda* (#:key outputs #:allow-other-keys)
702 ;; Make sure all executables in "bin" find the required Perl
703 ;; modules at runtime. As the PERL5LIB variable contains also
704 ;; the paths of native inputs, we pick the transitive target
705 ;; inputs from %build-inputs.
706 (let* ((out (assoc-ref outputs "out"))
707 (bin (string-append out "/bin/"))
709 (cons (string-append out "/lib/perl5/site_perl")
711 (assoc-ref %build-inputs name))
712 ',transitive-inputs))
714 (for-each (lambda (file)
716 `("PERL5LIB" ":" prefix (,path))))
717 (find-files bin "\\.pl$"))
721 `(("perl-test-most" ,perl-test-most)))
722 (home-page "http://search.cpan.org/dist/BioPerl")
723 (synopsis "Bioinformatics toolkit")
725 "BioPerl is the product of a community effort to produce Perl code which
726 is useful in biology. Examples include Sequence objects, Alignment objects
727 and database searching objects. These objects not only do what they are
728 advertised to do in the documentation, but they also interact - Alignment
729 objects are made from the Sequence objects, Sequence objects have access to
730 Annotation and SeqFeature objects and databases, Blast objects can be
731 converted to Alignment objects, and so on. This means that the objects
732 provide a coordinated and extensible framework to do computational biology.")
733 (license license:perl-license))))
735 (define-public python-biopython
737 (name "python-biopython")
741 ;; use PyPi rather than biopython.org to ease updating
742 (uri (pypi-uri "biopython" version))
745 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
746 (build-system python-build-system)
749 (modify-phases %standard-phases
750 (add-before 'check 'set-home
751 ;; Some tests require a home directory to be set.
752 (lambda _ (setenv "HOME" "/tmp") #t)))))
754 `(("python-numpy" ,python-numpy)))
755 (home-page "http://biopython.org/")
756 (synopsis "Tools for biological computation in Python")
758 "Biopython is a set of tools for biological computation including parsers
759 for bioinformatics files into Python data structures; interfaces to common
760 bioinformatics programs; a standard sequence class and tools for performing
761 common operations on them; code to perform data classification; code for
762 dealing with alignments; code making it easy to split up parallelizable tasks
763 into separate processes; and more.")
764 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
766 (define-public python2-biopython
767 (package-with-python2 python-biopython))
769 (define-public bpp-core
770 ;; The last release was in 2014 and the recommended way to install from source
771 ;; is to clone the git repository, so we do this.
772 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
773 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
776 (version (string-append "2.2.0-1." (string-take commit 7)))
780 (url "http://biopp.univ-montp2.fr/git/bpp-core")
782 (file-name (string-append name "-" version "-checkout"))
785 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
786 (build-system cmake-build-system)
788 `(#:parallel-build? #f))
790 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
791 ; compile all of the bpp packages with GCC 5.
792 (home-page "http://biopp.univ-montp2.fr")
793 (synopsis "C++ libraries for Bioinformatics")
795 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
796 analysis, phylogenetics, molecular evolution and population genetics. It is
797 Object Oriented and is designed to be both easy to use and computer efficient.
798 Bio++ intends to help programmers to write computer expensive programs, by
799 providing them a set of re-usable tools.")
800 (license license:cecill-c))))
802 (define-public bpp-phyl
803 ;; The last release was in 2014 and the recommended way to install from source
804 ;; is to clone the git repository, so we do this.
805 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
806 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
809 (version (string-append "2.2.0-1." (string-take commit 7)))
813 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
815 (file-name (string-append name "-" version "-checkout"))
818 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
819 (build-system cmake-build-system)
821 `(#:parallel-build? #f
822 ;; If out-of-source, test data is not copied into the build directory
823 ;; so the tests fail.
824 #:out-of-source? #f))
826 `(("bpp-core" ,bpp-core)
828 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
831 (home-page "http://biopp.univ-montp2.fr")
832 (synopsis "Bio++ phylogenetic Library")
834 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
835 analysis, phylogenetics, molecular evolution and population genetics. This
836 library provides phylogenetics-related modules.")
837 (license license:cecill-c))))
839 (define-public bpp-popgen
840 ;; The last release was in 2014 and the recommended way to install from source
841 ;; is to clone the git repository, so we do this.
842 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
843 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
846 (version (string-append "2.2.0-1." (string-take commit 7)))
850 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
852 (file-name (string-append name "-" version "-checkout"))
855 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
856 (build-system cmake-build-system)
858 `(#:parallel-build? #f
859 #:tests? #f)) ; There are no tests.
861 `(("bpp-core" ,bpp-core)
864 (home-page "http://biopp.univ-montp2.fr")
865 (synopsis "Bio++ population genetics library")
867 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
868 analysis, phylogenetics, molecular evolution and population genetics. This
869 library provides population genetics-related modules.")
870 (license license:cecill-c))))
872 (define-public bpp-seq
873 ;; The last release was in 2014 and the recommended way to install from source
874 ;; is to clone the git repository, so we do this.
875 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
876 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
879 (version (string-append "2.2.0-1." (string-take commit 7)))
883 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
885 (file-name (string-append name "-" version "-checkout"))
888 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
889 (build-system cmake-build-system)
891 `(#:parallel-build? #f
892 ;; If out-of-source, test data is not copied into the build directory
893 ;; so the tests fail.
894 #:out-of-source? #f))
896 `(("bpp-core" ,bpp-core)
897 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
898 (home-page "http://biopp.univ-montp2.fr")
899 (synopsis "Bio++ sequence library")
901 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
902 analysis, phylogenetics, molecular evolution and population genetics. This
903 library provides sequence-related modules.")
904 (license license:cecill-c))))
906 (define-public bppsuite
907 ;; The last release was in 2014 and the recommended way to install from source
908 ;; is to clone the git repository, so we do this.
909 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
910 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
913 (version (string-append "2.2.0-1." (string-take commit 7)))
917 (url "http://biopp.univ-montp2.fr/git/bppsuite")
919 (file-name (string-append name "-" version "-checkout"))
922 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
923 (build-system cmake-build-system)
925 `(#:parallel-build? #f
926 #:tests? #f)) ; There are no tests.
930 ("texinfo" ,texinfo)))
932 `(("bpp-core" ,bpp-core)
934 ("bpp-phyl" ,bpp-phyl)
935 ("bpp-phyl" ,bpp-popgen)
937 (home-page "http://biopp.univ-montp2.fr")
938 (synopsis "Bioinformatics tools written with the Bio++ libraries")
940 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
941 analysis, phylogenetics, molecular evolution and population genetics. This
942 package provides command line tools using the Bio++ library.")
943 (license license:cecill-c))))
945 (define-public blast+
952 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
953 version "/ncbi-blast-" version "+-src.tar.gz"))
956 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
957 (patches (search-patches "blast+-fix-makefile.patch"))
958 (modules '((guix build utils)))
961 ;; Remove bundled bzip2, zlib and pcre.
962 (delete-file-recursively "c++/src/util/compress/bzip2")
963 (delete-file-recursively "c++/src/util/compress/zlib")
964 (delete-file-recursively "c++/src/util/regexp")
965 (substitute* "c++/src/util/compress/Makefile.in"
966 (("bzip2 zlib api") "api"))
967 ;; Remove useless msbuild directory
968 (delete-file-recursively
969 "c++/src/build-system/project_tree_builder/msbuild")
971 (build-system gnu-build-system)
973 `(;; There are two(!) tests for this massive library, and both fail with
974 ;; "unparsable timing stats".
975 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
976 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
979 #:parallel-build? #f ; not supported
981 (modify-phases %standard-phases
984 ;; $HOME needs to be set at some point during the configure phase
985 (lambda _ (setenv "HOME" "/tmp") #t))
988 (lambda _ (chdir "c++") #t))
990 'enter-dir 'fix-build-system
993 (cond ((string=? cmd "date")
994 ;; make call to "date" deterministic
999 (format (current-error-port)
1000 "WARNING: Unable to find absolute path for ~s~%"
1004 ;; Rewrite hardcoded paths to various tools
1005 (substitute* (append '("src/build-system/configure.ac"
1006 "src/build-system/configure"
1007 "src/build-system/helpers/run_with_lock.c"
1008 "scripts/common/impl/if_diff.sh"
1009 "scripts/common/impl/run_with_lock.sh"
1010 "src/build-system/Makefile.configurables.real"
1011 "src/build-system/Makefile.in.top"
1012 "src/build-system/Makefile.meta.gmake=no"
1013 "src/build-system/Makefile.meta.in"
1014 "src/build-system/Makefile.meta_l"
1015 "src/build-system/Makefile.meta_p"
1016 "src/build-system/Makefile.meta_r"
1017 "src/build-system/Makefile.mk.in"
1018 "src/build-system/Makefile.requirements"
1019 "src/build-system/Makefile.rules_with_autodep.in")
1020 (find-files "scripts/common/check" "\\.sh$"))
1021 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1022 (or (which* cmd) all)))
1024 (substitute* (find-files "src/build-system" "^config.*")
1025 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1028 ;; rewrite "/var/tmp" in check script
1029 (substitute* "scripts/common/check/check_make_unix.sh"
1030 (("/var/tmp") "/tmp"))
1032 ;; do not reset PATH
1033 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1035 (("action=/bin/") "action=")
1036 (("export PATH") ":"))
1040 (lambda* (#:key inputs outputs #:allow-other-keys)
1041 (let ((out (assoc-ref outputs "out"))
1042 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1043 (include (string-append (assoc-ref outputs "include")
1044 "/include/ncbi-tools++")))
1045 ;; The 'configure' script doesn't recognize things like
1046 ;; '--enable-fast-install'.
1047 (zero? (system* "./configure.orig"
1048 (string-append "--with-build-root=" (getcwd) "/build")
1049 (string-append "--prefix=" out)
1050 (string-append "--libdir=" lib)
1051 (string-append "--includedir=" include)
1052 (string-append "--with-bz2="
1053 (assoc-ref inputs "bzip2"))
1054 (string-append "--with-z="
1055 (assoc-ref inputs "zlib"))
1056 (string-append "--with-pcre="
1057 (assoc-ref inputs "pcre"))
1058 ;; Each library is built twice by default, once
1059 ;; with "-static" in its name, and again
1062 "--with-dll"))))))))
1063 (outputs '("out" ; 21 MB
1071 ("python" ,python-wrapper)))
1074 (home-page "http://blast.ncbi.nlm.nih.gov")
1075 (synopsis "Basic local alignment search tool")
1077 "BLAST is a popular method of performing a DNA or protein sequence
1078 similarity search, using heuristics to produce results quickly. It also
1079 calculates an “expect value” that estimates how many matches would have
1080 occurred at a given score by chance, which can aid a user in judging how much
1081 confidence to have in an alignment.")
1082 ;; Most of the sources are in the public domain, with the following
1085 ;; * ./c++/include/util/bitset/
1086 ;; * ./c++/src/html/ncbi_menu*.js
1088 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1090 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1092 ;; * ./c++/src/corelib/teamcity_*
1093 (license (list license:public-domain
1099 (define-public bless
1105 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1109 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1110 (modules '((guix build utils)))
1113 ;; Remove bundled boost, pigz, zlib, and .git directory
1114 ;; FIXME: also remove bundled sources for murmurhash3 and
1115 ;; kmc once packaged.
1116 (delete-file-recursively "boost")
1117 (delete-file-recursively "pigz")
1118 (delete-file-recursively "google-sparsehash")
1119 (delete-file-recursively "zlib")
1120 (delete-file-recursively ".git")
1122 (build-system gnu-build-system)
1124 '(#:tests? #f ;no "check" target
1126 (list (string-append "ZLIB="
1127 (assoc-ref %build-inputs "zlib")
1129 (string-append "LDFLAGS="
1130 (string-join '("-lboost_filesystem"
1137 (modify-phases %standard-phases
1138 (add-after 'unpack 'do-not-build-bundled-pigz
1139 (lambda* (#:key inputs outputs #:allow-other-keys)
1140 (substitute* "Makefile"
1141 (("cd pigz/pigz-2.3.3; make") ""))
1143 (add-after 'unpack 'patch-paths-to-executables
1144 (lambda* (#:key inputs outputs #:allow-other-keys)
1145 (substitute* "parse_args.cpp"
1146 (("kmc_binary = .*")
1147 (string-append "kmc_binary = \""
1148 (assoc-ref outputs "out")
1150 (("pigz_binary = .*")
1151 (string-append "pigz_binary = \""
1152 (assoc-ref inputs "pigz")
1156 (lambda* (#:key outputs #:allow-other-keys)
1157 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1158 (for-each (lambda (file)
1159 (install-file file bin))
1160 '("bless" "kmc/bin/kmc"))
1162 (delete 'configure))))
1166 `(("openmpi" ,openmpi)
1168 ("sparsehash" ,sparsehash)
1171 (supported-systems '("x86_64-linux"))
1172 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1173 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1175 "@dfn{Bloom-filter-based error correction solution for high-throughput
1176 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1177 correction tool for genomic reads produced by @dfn{Next-generation
1178 sequencing} (NGS). BLESS produces accurate correction results with much less
1179 memory compared with previous solutions and is also able to tolerate a higher
1180 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1181 errors at the end of reads.")
1182 (license license:gpl3+)))
1184 (define-public bowtie
1190 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1192 (file-name (string-append name "-" version ".tar.gz"))
1195 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1196 (modules '((guix build utils)))
1198 '(substitute* "Makefile"
1199 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1200 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1201 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1202 (build-system gnu-build-system)
1205 ("perl-clone" ,perl-clone)
1206 ("perl-test-deep" ,perl-test-deep)
1207 ("perl-test-simple" ,perl-test-simple)
1208 ("python" ,python-2)
1215 (string-append "prefix=" (assoc-ref %outputs "out")))
1217 (modify-phases %standard-phases
1220 (lambda* (#:key outputs #:allow-other-keys)
1221 (zero? (system* "perl"
1222 "scripts/test/simple_tests.pl"
1223 "--bowtie2=./bowtie2"
1224 "--bowtie2-build=./bowtie2-build")))))))
1225 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1226 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1228 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1229 reads to long reference sequences. It is particularly good at aligning reads
1230 of about 50 up to 100s or 1,000s of characters, and particularly good at
1231 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1232 genome with an FM Index to keep its memory footprint small: for the human
1233 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1234 gapped, local, and paired-end alignment modes.")
1235 (supported-systems '("x86_64-linux"))
1236 (license license:gpl3+)))
1238 (define-public tophat
1245 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1249 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1250 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1251 (modules '((guix build utils)))
1254 ;; Remove bundled SeqAn and samtools
1255 (delete-file-recursively "src/SeqAn-1.3")
1256 (delete-file-recursively "src/samtools-0.1.18")
1258 (build-system gnu-build-system)
1260 '(#:parallel-build? #f ; not supported
1262 (modify-phases %standard-phases
1263 (add-after 'unpack 'use-system-samtools
1264 (lambda* (#:key inputs #:allow-other-keys)
1265 (substitute* "src/Makefile.in"
1266 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1267 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1268 (("SAMPROG = samtools_0\\.1\\.18") "")
1269 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1270 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1271 (substitute* '("src/common.cpp"
1273 (("samtools_0.1.18") (which "samtools")))
1274 (substitute* '("src/common.h"
1275 "src/bam2fastx.cpp")
1276 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1277 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1278 (substitute* '("src/bwt_map.h"
1280 "src/align_status.h")
1281 (("#include <bam.h>") "#include <samtools/bam.h>")
1282 (("#include <sam.h>") "#include <samtools/sam.h>"))
1287 ("samtools" ,samtools-0.1)
1288 ("ncurses" ,ncurses)
1289 ("python" ,python-2)
1293 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1294 (synopsis "Spliced read mapper for RNA-Seq data")
1296 "TopHat is a fast splice junction mapper for nucleotide sequence
1297 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1298 mammalian-sized genomes using the ultra high-throughput short read
1299 aligner Bowtie, and then analyzes the mapping results to identify
1300 splice junctions between exons.")
1301 ;; TopHat is released under the Boost Software License, Version 1.0
1302 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1303 (license license:boost1.0)))
1312 "https://github.com/lh3/bwa/releases/download/v"
1313 version "/bwa-" version ".tar.bz2"))
1316 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1317 (build-system gnu-build-system)
1319 '(#:tests? #f ;no "check" target
1321 (modify-phases %standard-phases
1323 (lambda* (#:key outputs #:allow-other-keys)
1324 (let ((bin (string-append
1325 (assoc-ref outputs "out") "/bin"))
1327 (assoc-ref outputs "out") "/share/doc/bwa"))
1329 (assoc-ref outputs "out") "/share/man/man1")))
1330 (install-file "bwa" bin)
1331 (install-file "README.md" doc)
1332 (install-file "bwa.1" man))
1334 ;; no "configure" script
1335 (delete 'configure))))
1336 (inputs `(("zlib" ,zlib)))
1337 ;; Non-portable SSE instructions are used so building fails on platforms
1338 ;; other than x86_64.
1339 (supported-systems '("x86_64-linux"))
1340 (home-page "http://bio-bwa.sourceforge.net/")
1341 (synopsis "Burrows-Wheeler sequence aligner")
1343 "BWA is a software package for mapping low-divergent sequences against a
1344 large reference genome, such as the human genome. It consists of three
1345 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1346 designed for Illumina sequence reads up to 100bp, while the rest two for
1347 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1348 features such as long-read support and split alignment, but BWA-MEM, which is
1349 the latest, is generally recommended for high-quality queries as it is faster
1350 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1351 70-100bp Illumina reads.")
1352 (license license:gpl3+)))
1354 (define-public bwa-pssm
1355 (package (inherit bwa)
1360 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1361 "archive/" version ".tar.gz"))
1362 (file-name (string-append name "-" version ".tar.gz"))
1365 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1366 (build-system gnu-build-system)
1371 (home-page "http://bwa-pssm.binf.ku.dk/")
1372 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1374 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1375 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1376 existing aligners it is fast and sensitive. Unlike most other aligners,
1377 however, it is also adaptible in the sense that one can direct the alignment
1378 based on known biases within the data set. It is coded as a modification of
1379 the original BWA alignment program and shares the genome index structure as
1380 well as many of the command line options.")
1381 (license license:gpl3+)))
1383 (define-public python2-bx-python
1385 (name "python2-bx-python")
1389 (uri (pypi-uri "bx-python" version))
1392 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1393 (modules '((guix build utils)))
1395 '(substitute* "setup.py"
1396 ;; remove dependency on outdated "distribute" module
1397 (("^from distribute_setup import use_setuptools") "")
1398 (("^use_setuptools\\(\\)") "")))))
1399 (build-system python-build-system)
1401 `(#:tests? #f ;tests fail because test data are not included
1402 #:python ,python-2))
1404 `(("python-numpy" ,python2-numpy)
1407 `(("python-nose" ,python2-nose)))
1408 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1409 (synopsis "Tools for manipulating biological data")
1411 "bx-python provides tools for manipulating biological data, particularly
1412 multiple sequence alignments.")
1413 (license license:expat)))
1415 (define-public python-pysam
1417 (name "python-pysam")
1421 ;; Test data is missing on PyPi.
1423 "https://github.com/pysam-developers/pysam/archive/v"
1425 (file-name (string-append name "-" version ".tar.gz"))
1428 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1429 (modules '((guix build utils)))
1431 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1432 '(delete-file-recursively "htslib"))))
1433 (build-system python-build-system)
1435 `(#:modules ((ice-9 ftw)
1437 (guix build python-build-system)
1440 (modify-phases %standard-phases
1441 (add-before 'build 'set-flags
1442 (lambda* (#:key inputs #:allow-other-keys)
1443 (setenv "HTSLIB_MODE" "external")
1444 (setenv "HTSLIB_LIBRARY_DIR"
1445 (string-append (assoc-ref inputs "htslib") "/lib"))
1446 (setenv "HTSLIB_INCLUDE_DIR"
1447 (string-append (assoc-ref inputs "htslib") "/include"))
1448 (setenv "LDFLAGS" "-lncurses")
1449 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1452 (lambda* (#:key inputs outputs #:allow-other-keys)
1453 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1454 (setenv "PYTHONPATH"
1456 (getenv "PYTHONPATH")
1457 ":" (getcwd) "/build/"
1458 (car (scandir "build"
1459 (negate (cut string-prefix? "." <>))))))
1460 ;; Step out of source dir so python does not import from CWD.
1461 (with-directory-excursion "tests"
1462 (setenv "HOME" "/tmp")
1463 (and (zero? (system* "make" "-C" "pysam_data"))
1464 (zero? (system* "make" "-C" "cbcf_data"))
1465 ;; Running nosetests without explicitly asking for a
1466 ;; single process leads to a crash. Running with multiple
1467 ;; processes fails because the tests are not designed to
1470 ;; FIXME: tests keep timing out on some systems.
1471 ;; (zero? (system* "nosetests" "-v"
1472 ;; "--processes" "1"))
1475 `(("htslib" ,htslib))) ; Included from installed header files.
1477 `(("ncurses" ,ncurses)
1480 `(("python-cython" ,python-cython)
1481 ;; Dependencies below are are for tests only.
1482 ("samtools" ,samtools)
1483 ("bcftools" ,bcftools)
1484 ("python-nose" ,python-nose)))
1485 (home-page "https://github.com/pysam-developers/pysam")
1486 (synopsis "Python bindings to the SAMtools C API")
1488 "Pysam is a Python module for reading and manipulating files in the
1489 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1490 also includes an interface for tabix.")
1491 (license license:expat)))
1493 (define-public python2-pysam
1494 (package-with-python2 python-pysam))
1496 (define-public python-twobitreader
1498 (name "python-twobitreader")
1502 (uri (pypi-uri "twobitreader" version))
1505 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1506 (build-system python-build-system)
1508 '(;; Tests are not distributed in the PyPi release.
1509 ;; TODO Try building from the Git repo or asking the upstream maintainer
1510 ;; to distribute the tests on PyPi.
1513 `(("python-sphinx" ,python-sphinx)))
1514 (home-page "https://github.com/benjschiller/twobitreader")
1515 (synopsis "Python library for reading .2bit files")
1517 "twobitreader is a Python library for reading .2bit files as used by the
1518 UCSC genome browser.")
1519 (license license:artistic2.0)))
1521 (define-public python2-twobitreader
1522 (package-with-python2 python-twobitreader))
1524 (define-public python-plastid
1526 (name "python-plastid")
1530 (uri (pypi-uri "plastid" version))
1533 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1534 (build-system python-build-system)
1536 ;; Some test files are not included.
1539 `(("python-numpy" ,python-numpy)
1540 ("python-scipy" ,python-scipy)
1541 ("python-pandas" ,python-pandas)
1542 ("python-pysam" ,python-pysam)
1543 ("python-matplotlib" ,python-matplotlib)
1544 ("python-biopython" ,python-biopython)
1545 ("python-twobitreader" ,python-twobitreader)
1546 ("python-termcolor" ,python-termcolor)))
1548 `(("python-cython" ,python-cython)
1549 ("python-nose" ,python-nose)))
1550 (home-page "https://github.com/joshuagryphon/plastid")
1551 (synopsis "Python library for genomic analysis")
1553 "plastid is a Python library for genomic analysis – in particular,
1554 high-throughput sequencing data – with an emphasis on simplicity.")
1555 (license license:bsd-3)))
1557 (define-public python2-plastid
1558 (package-with-python2 python-plastid))
1560 (define-public cd-hit
1566 (uri (string-append "https://github.com/weizhongli/cdhit"
1567 "/releases/download/V" version
1569 "-2017-0621-source.tar.gz"))
1572 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1573 (build-system gnu-build-system)
1575 `(#:tests? #f ; there are no tests
1577 ;; Executables are copied directly to the PREFIX.
1578 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1580 (modify-phases %standard-phases
1581 ;; No "configure" script
1583 ;; Remove sources of non-determinism
1584 (add-after 'unpack 'be-timeless
1586 (substitute* "cdhit-utility.c++"
1587 ((" \\(built on \" __DATE__ \"\\)") ""))
1588 (substitute* "cdhit-common.c++"
1589 (("__DATE__") "\"0\"")
1590 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1592 ;; The "install" target does not create the target directory.
1593 (add-before 'install 'create-target-dir
1594 (lambda* (#:key outputs #:allow-other-keys)
1595 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1599 (home-page "http://weizhongli-lab.org/cd-hit/")
1600 (synopsis "Cluster and compare protein or nucleotide sequences")
1602 "CD-HIT is a program for clustering and comparing protein or nucleotide
1603 sequences. CD-HIT is designed to be fast and handle extremely large
1605 ;; The manual says: "It can be copied under the GNU General Public License
1606 ;; version 2 (GPLv2)."
1607 (license license:gpl2)))
1609 (define-public clipper
1616 "https://github.com/YeoLab/clipper/archive/"
1618 (file-name (string-append name "-" version ".tar.gz"))
1621 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1622 (modules '((guix build utils)))
1625 ;; remove unnecessary setup dependency
1626 (substitute* "setup.py"
1627 (("setup_requires = .*") ""))
1628 (for-each delete-file
1629 '("clipper/src/peaks.so"
1630 "clipper/src/readsToWiggle.so"))
1631 (delete-file-recursively "dist/")
1633 (build-system python-build-system)
1634 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1636 `(("htseq" ,python2-htseq)
1637 ("python-pybedtools" ,python2-pybedtools)
1638 ("python-cython" ,python2-cython)
1639 ("python-scikit-learn" ,python2-scikit-learn)
1640 ("python-matplotlib" ,python2-matplotlib)
1641 ("python-pandas" ,python2-pandas)
1642 ("python-pysam" ,python2-pysam)
1643 ("python-numpy" ,python2-numpy)
1644 ("python-scipy" ,python2-scipy)))
1646 `(("python-mock" ,python2-mock) ; for tests
1647 ("python-nose" ,python2-nose) ; for tests
1648 ("python-pytz" ,python2-pytz))) ; for tests
1649 (home-page "https://github.com/YeoLab/clipper")
1650 (synopsis "CLIP peak enrichment recognition")
1652 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1653 (license license:gpl2)))
1655 (define-public codingquarry
1657 (name "codingquarry")
1662 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1666 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1667 (build-system gnu-build-system)
1669 '(#:tests? #f ; no "check" target
1671 (modify-phases %standard-phases
1674 (lambda* (#:key outputs #:allow-other-keys)
1675 (let* ((out (assoc-ref outputs "out"))
1676 (bin (string-append out "/bin"))
1677 (doc (string-append out "/share/doc/codingquarry")))
1678 (install-file "INSTRUCTIONS.pdf" doc)
1679 (copy-recursively "QuarryFiles"
1680 (string-append out "/QuarryFiles"))
1681 (install-file "CodingQuarry" bin)
1682 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1683 (inputs `(("openmpi" ,openmpi)))
1684 (native-search-paths
1685 (list (search-path-specification
1686 (variable "QUARRY_PATH")
1687 (files '("QuarryFiles")))))
1688 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1689 (synopsis "Fungal gene predictor")
1690 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1691 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1692 (home-page "https://sourceforge.net/projects/codingquarry/")
1693 (license license:gpl3+)))
1695 (define-public couger
1702 "http://couger.oit.duke.edu/static/assets/COUGER"
1706 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1707 (build-system gnu-build-system)
1711 (modify-phases %standard-phases
1716 (lambda* (#:key outputs #:allow-other-keys)
1717 (let* ((out (assoc-ref outputs "out"))
1718 (bin (string-append out "/bin")))
1719 (copy-recursively "src" (string-append out "/src"))
1721 ;; Add "src" directory to module lookup path.
1722 (substitute* "couger"
1724 (string-append "import sys\nsys.path.append(\""
1725 out "\")\nfrom argparse")))
1726 (install-file "couger" bin))
1729 'install 'wrap-program
1730 (lambda* (#:key inputs outputs #:allow-other-keys)
1731 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1732 (let* ((out (assoc-ref outputs "out"))
1733 (path (getenv "PYTHONPATH")))
1734 (wrap-program (string-append out "/bin/couger")
1735 `("PYTHONPATH" ":" prefix (,path))))
1738 `(("python" ,python-2)
1739 ("python2-pillow" ,python2-pillow)
1740 ("python2-numpy" ,python2-numpy)
1741 ("python2-scipy" ,python2-scipy)
1742 ("python2-matplotlib" ,python2-matplotlib)))
1744 `(("r-minimal" ,r-minimal)
1746 ("randomjungle" ,randomjungle)))
1748 `(("unzip" ,unzip)))
1749 (home-page "http://couger.oit.duke.edu")
1750 (synopsis "Identify co-factors in sets of genomic regions")
1752 "COUGER can be applied to any two sets of genomic regions bound by
1753 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1754 putative co-factors that provide specificity to each TF. The framework
1755 determines the genomic targets uniquely-bound by each TF, and identifies a
1756 small set of co-factors that best explain the in vivo binding differences
1757 between the two TFs.
1759 COUGER uses classification algorithms (support vector machines and random
1760 forests) with features that reflect the DNA binding specificities of putative
1761 co-factors. The features are generated either from high-throughput TF-DNA
1762 binding data (from protein binding microarray experiments), or from large
1763 collections of DNA motifs.")
1764 (license license:gpl3+)))
1766 (define-public clustal-omega
1768 (name "clustal-omega")
1772 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1776 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1777 (build-system gnu-build-system)
1779 `(("argtable" ,argtable)))
1780 (home-page "http://www.clustal.org/omega/")
1781 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1783 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1784 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1785 of handling data-sets of hundreds of thousands of sequences in reasonable
1787 (license license:gpl2+)))
1789 (define-public crossmap
1795 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1799 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1800 ;; This patch has been sent upstream already and is available
1801 ;; for download from Sourceforge, but it has not been merged.
1802 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1803 (modules '((guix build utils)))
1804 ;; remove bundled copy of pysam
1806 '(delete-file-recursively "lib/pysam"))))
1807 (build-system python-build-system)
1809 `(#:python ,python-2
1811 (modify-phases %standard-phases
1812 (add-after 'unpack 'set-env
1813 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1815 `(("python-numpy" ,python2-numpy)
1816 ("python-pysam" ,python2-pysam)
1819 `(("python-cython" ,python2-cython)
1820 ("python-nose" ,python2-nose)))
1821 (home-page "http://crossmap.sourceforge.net/")
1822 (synopsis "Convert genome coordinates between assemblies")
1824 "CrossMap is a program for conversion of genome coordinates or annotation
1825 files between different genome assemblies. It supports most commonly used
1826 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1827 (license license:gpl2+)))
1829 (define-public cutadapt
1836 (url "https://github.com/marcelm/cutadapt.git")
1837 (commit (string-append "v" version))))
1838 (file-name (string-append name "-" version "-checkout"))
1841 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1842 (build-system python-build-system)
1844 `(("python-xopen" ,python-xopen)))
1846 `(("python-cython" ,python-cython)
1847 ("python-pytest" ,python-pytest)))
1848 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1849 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1851 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1852 other types of unwanted sequence from high-throughput sequencing reads.")
1853 (license license:expat)))
1855 (define-public libbigwig
1861 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1862 "archive/" version ".tar.gz"))
1863 (file-name (string-append name "-" version ".tar.gz"))
1866 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1867 (build-system gnu-build-system)
1869 `(#:test-target "test"
1872 (string-append "prefix=" (assoc-ref %outputs "out")))
1874 (modify-phases %standard-phases
1876 (add-before 'check 'disable-curl-test
1878 (substitute* "Makefile"
1879 (("./test/testRemote.*") ""))
1881 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1882 ;; there has not yet been a release containing this change.
1883 (add-before 'install 'create-target-dirs
1884 (lambda* (#:key outputs #:allow-other-keys)
1885 (let ((out (assoc-ref outputs "out")))
1886 (mkdir-p (string-append out "/lib"))
1887 (mkdir-p (string-append out "/include"))
1893 `(("doxygen" ,doxygen)))
1894 (home-page "https://github.com/dpryan79/libBigWig")
1895 (synopsis "C library for handling bigWig files")
1897 "This package provides a C library for parsing local and remote BigWig
1899 (license license:expat)))
1901 (define-public python-pybigwig
1903 (name "python-pybigwig")
1907 (uri (pypi-uri "pyBigWig" version))
1910 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1911 (modules '((guix build utils)))
1914 ;; Delete bundled libBigWig sources
1915 (delete-file-recursively "libBigWig")))))
1916 (build-system python-build-system)
1919 (modify-phases %standard-phases
1920 (add-after 'unpack 'link-with-libBigWig
1921 (lambda* (#:key inputs #:allow-other-keys)
1922 (substitute* "setup.py"
1923 (("libs=\\[") "libs=[\"BigWig\", "))
1926 `(("libbigwig" ,libbigwig)
1929 (home-page "https://github.com/dpryan79/pyBigWig")
1930 (synopsis "Access bigWig files in Python using libBigWig")
1932 "This package provides Python bindings to the libBigWig library for
1933 accessing bigWig files.")
1934 (license license:expat)))
1936 (define-public python2-pybigwig
1937 (package-with-python2 python-pybigwig))
1939 (define-public python-dendropy
1941 (name "python-dendropy")
1946 (uri (pypi-uri "DendroPy" version))
1949 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1950 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1951 (build-system python-build-system)
1952 (home-page "http://packages.python.org/DendroPy/")
1953 (synopsis "Library for phylogenetics and phylogenetic computing")
1955 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1956 writing, simulation, processing and manipulation of phylogenetic
1957 trees (phylogenies) and characters.")
1958 (license license:bsd-3)
1959 (properties `((python2-variant . ,(delay python2-dendropy))))))
1961 (define-public python2-dendropy
1962 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1966 `(#:python ,python-2
1968 (modify-phases %standard-phases
1970 ;; There is currently a test failure that only happens on some
1971 ;; systems, and only using "setup.py test"
1972 (lambda _ (zero? (system* "nosetests")))))))
1973 (native-inputs `(("python2-nose" ,python2-nose)
1974 ,@(package-native-inputs base))))))
1976 (define-public python-py2bit
1978 (name "python-py2bit")
1983 (uri (pypi-uri "py2bit" version))
1986 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
1987 (build-system python-build-system)
1988 (home-page "https://github.com/dpryan79/py2bit")
1989 (synopsis "Access 2bit files using lib2bit")
1991 "This package provides Python bindings for lib2bit to access 2bit files
1993 (license license:expat)))
1995 (define-public deeptools
2001 (uri (string-append "https://github.com/deeptools/deepTools/"
2002 "archive/" version ".tar.gz"))
2003 (file-name (string-append name "-" version ".tar.gz"))
2006 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2007 (build-system python-build-system)
2009 `(("python-scipy" ,python-scipy)
2010 ("python-numpy" ,python-numpy)
2011 ("python-numpydoc" ,python-numpydoc)
2012 ("python-matplotlib" ,python-matplotlib)
2013 ("python-pysam" ,python-pysam)
2014 ("python-py2bit" ,python-py2bit)
2015 ("python-pybigwig" ,python-pybigwig)))
2017 `(("python-mock" ,python-mock) ;for tests
2018 ("python-nose" ,python-nose) ;for tests
2019 ("python-pytz" ,python-pytz))) ;for tests
2020 (home-page "https://github.com/deeptools/deepTools")
2021 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2023 "DeepTools addresses the challenge of handling the large amounts of data
2024 that are now routinely generated from DNA sequencing centers. To do so,
2025 deepTools contains useful modules to process the mapped reads data to create
2026 coverage files in standard bedGraph and bigWig file formats. By doing so,
2027 deepTools allows the creation of normalized coverage files or the comparison
2028 between two files (for example, treatment and control). Finally, using such
2029 normalized and standardized files, multiple visualizations can be created to
2030 identify enrichments with functional annotations of the genome.")
2031 (license license:gpl3+)))
2033 (define-public diamond
2040 "https://github.com/bbuchfink/diamond/archive/v"
2042 (file-name (string-append name "-" version ".tar.gz"))
2045 "1vi2nddmy7knrv8gsprwqp6a40k63n3f2dfvx22ipjhrg9xir96f"))))
2046 (build-system cmake-build-system)
2048 '(#:tests? #f ; no "check" target
2050 (modify-phases %standard-phases
2051 (add-after 'unpack 'remove-native-compilation
2053 (substitute* "CMakeLists.txt" (("-march=native") ""))
2057 (home-page "https://github.com/bbuchfink/diamond")
2058 (synopsis "Accelerated BLAST compatible local sequence aligner")
2060 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2061 translated DNA query sequences against a protein reference database (BLASTP
2062 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2063 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2064 data and settings.")
2065 (license license:agpl3+)))
2067 (define-public discrover
2074 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2076 (file-name (string-append name "-" version ".tar.gz"))
2079 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2080 (build-system cmake-build-system)
2082 `(#:tests? #f ; there are no tests
2084 (modify-phases %standard-phases
2085 (add-after 'unpack 'add-missing-includes
2087 (substitute* "src/executioninformation.hpp"
2088 (("#define EXECUTIONINFORMATION_HPP" line)
2089 (string-append line "\n#include <random>")))
2090 (substitute* "src/plasma/fasta.hpp"
2091 (("#define FASTA_HPP" line)
2092 (string-append line "\n#include <random>")))
2098 `(("texlive" ,texlive)
2099 ("imagemagick" ,imagemagick)))
2100 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2101 (synopsis "Discover discriminative nucleotide sequence motifs")
2102 (description "Discrover is a motif discovery method to find binding sites
2103 of nucleic acid binding proteins.")
2104 (license license:gpl3+)))
2106 (define-public eigensoft
2107 (let ((revision "1")
2108 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2111 (version (string-append "6.1.2-"
2113 (string-take commit 9)))
2118 (url "https://github.com/DReichLab/EIG.git")
2120 (file-name (string-append "eigensoft-" commit "-checkout"))
2123 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2124 (modules '((guix build utils)))
2125 ;; Remove pre-built binaries.
2127 (delete-file-recursively "bin")
2130 (build-system gnu-build-system)
2132 `(#:tests? #f ; There are no tests.
2133 #:make-flags '("CC=gcc")
2135 (modify-phases %standard-phases
2136 ;; There is no configure phase, but the Makefile is in a
2141 ;; The link flags are incomplete.
2142 (substitute* "Makefile"
2143 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2145 ;; The provided install target only copies executables to
2146 ;; the "bin" directory in the build root.
2147 (add-after 'install 'actually-install
2148 (lambda* (#:key outputs #:allow-other-keys)
2149 (let* ((out (assoc-ref outputs "out"))
2150 (bin (string-append out "/bin")))
2151 (for-each (lambda (file)
2152 (install-file file bin))
2153 (find-files "../bin" ".*"))
2158 ("openblas" ,openblas)
2160 ("gfortran" ,gfortran "lib")))
2161 (home-page "https://github.com/DReichLab/EIG")
2162 (synopsis "Tools for population genetics")
2163 (description "The EIGENSOFT package provides tools for population
2164 genetics and stratification correction. EIGENSOFT implements methods commonly
2165 used in population genetics analyses such as PCA, computation of Tracy-Widom
2166 statistics, and finding related individuals in structured populations. It
2167 comes with a built-in plotting script and supports multiple file formats and
2168 quantitative phenotypes.")
2169 ;; The license of the eigensoft tools is Expat, but since it's
2170 ;; linking with the GNU Scientific Library (GSL) the effective
2171 ;; license is the GPL.
2172 (license license:gpl3+))))
2174 (define-public edirect
2180 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2181 "versions/2016-05-03/edirect.tar.gz"))
2184 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2185 (build-system perl-build-system)
2187 `(#:tests? #f ;no "check" target
2189 (modify-phases %standard-phases
2193 (lambda* (#:key outputs #:allow-other-keys)
2194 (let ((target (string-append (assoc-ref outputs "out")
2197 (install-file "edirect.pl" target)
2200 'install 'wrap-program
2201 (lambda* (#:key inputs outputs #:allow-other-keys)
2202 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2203 (let* ((out (assoc-ref outputs "out"))
2204 (path (getenv "PERL5LIB")))
2205 (wrap-program (string-append out "/bin/edirect.pl")
2206 `("PERL5LIB" ":" prefix (,path)))))))))
2208 `(("perl-html-parser" ,perl-html-parser)
2209 ("perl-encode-locale" ,perl-encode-locale)
2210 ("perl-file-listing" ,perl-file-listing)
2211 ("perl-html-tagset" ,perl-html-tagset)
2212 ("perl-html-tree" ,perl-html-tree)
2213 ("perl-http-cookies" ,perl-http-cookies)
2214 ("perl-http-date" ,perl-http-date)
2215 ("perl-http-message" ,perl-http-message)
2216 ("perl-http-negotiate" ,perl-http-negotiate)
2217 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2218 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2219 ("perl-net-http" ,perl-net-http)
2220 ("perl-uri" ,perl-uri)
2221 ("perl-www-robotrules" ,perl-www-robotrules)
2223 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2224 (synopsis "Tools for accessing the NCBI's set of databases")
2226 "Entrez Direct (EDirect) is a method for accessing the National Center
2227 for Biotechnology Information's (NCBI) set of interconnected
2228 databases (publication, sequence, structure, gene, variation, expression,
2229 etc.) from a terminal. Functions take search terms from command-line
2230 arguments. Individual operations are combined to build multi-step queries.
2231 Record retrieval and formatting normally complete the process.
2233 EDirect also provides an argument-driven function that simplifies the
2234 extraction of data from document summaries or other results that are returned
2235 in structured XML format. This can eliminate the need for writing custom
2236 software to answer ad hoc questions.")
2237 (license license:public-domain)))
2239 (define-public exonerate
2248 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2249 "exonerate-" version ".tar.gz"))
2252 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2253 (build-system gnu-build-system)
2255 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2257 `(("pkg-config" ,pkg-config)))
2261 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2262 (synopsis "Generic tool for biological sequence alignment")
2264 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2265 the alignment of sequences using a many alignment models, either exhaustive
2266 dynamic programming or a variety of heuristics.")
2267 (license license:gpl3)))
2269 (define-public express
2277 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2278 version "/express-" version "-src.tgz"))
2281 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2282 (build-system cmake-build-system)
2284 `(#:tests? #f ;no "check" target
2286 (modify-phases %standard-phases
2287 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2288 (lambda* (#:key inputs #:allow-other-keys)
2289 (substitute* "CMakeLists.txt"
2290 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2291 "set(Boost_USE_STATIC_LIBS OFF)")
2292 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2293 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2294 (substitute* "src/CMakeLists.txt"
2295 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2296 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2300 ("bamtools" ,bamtools)
2301 ("protobuf" ,protobuf)
2303 (home-page "http://bio.math.berkeley.edu/eXpress")
2304 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2306 "eXpress is a streaming tool for quantifying the abundances of a set of
2307 target sequences from sampled subsequences. Example applications include
2308 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2309 analysis (from RNA-Seq), transcription factor binding quantification in
2310 ChIP-Seq, and analysis of metagenomic data.")
2311 (license license:artistic2.0)))
2313 (define-public express-beta-diversity
2315 (name "express-beta-diversity")
2321 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2323 (file-name (string-append name "-" version ".tar.gz"))
2326 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2327 (build-system gnu-build-system)
2330 (modify-phases %standard-phases
2332 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2334 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2336 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2338 (lambda* (#:key outputs #:allow-other-keys)
2339 (let ((bin (string-append (assoc-ref outputs "out")
2342 (install-file "scripts/convertToEBD.py" bin)
2343 (install-file "bin/ExpressBetaDiversity" bin)
2346 `(("python" ,python-2)))
2347 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2348 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2350 "Express Beta Diversity (EBD) calculates ecological beta diversity
2351 (dissimilarity) measures between biological communities. EBD implements a
2352 variety of diversity measures including those that make use of phylogenetic
2353 similarity of community members.")
2354 (license license:gpl3+)))
2356 (define-public fasttree
2363 "http://www.microbesonline.org/fasttree/FastTree-"
2367 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2368 (build-system gnu-build-system)
2370 `(#:tests? #f ; no "check" target
2372 (modify-phases %standard-phases
2376 (lambda* (#:key source #:allow-other-keys)
2377 (and (zero? (system* "gcc"
2379 "-finline-functions"
2386 (zero? (system* "gcc"
2390 "-finline-functions"
2398 (lambda* (#:key outputs #:allow-other-keys)
2399 (let ((bin (string-append (assoc-ref outputs "out")
2402 (install-file "FastTree" bin)
2403 (install-file "FastTreeMP" bin)
2405 (home-page "http://www.microbesonline.org/fasttree")
2406 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2408 "FastTree can handle alignments with up to a million of sequences in a
2409 reasonable amount of time and memory. For large alignments, FastTree is
2410 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2411 (license license:gpl2+)))
2413 (define-public fastx-toolkit
2415 (name "fastx-toolkit")
2421 "https://github.com/agordon/fastx_toolkit/releases/download/"
2422 version "/fastx_toolkit-" version ".tar.bz2"))
2425 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2426 (build-system gnu-build-system)
2428 `(("libgtextutils" ,libgtextutils)))
2430 `(("pkg-config" ,pkg-config)))
2431 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2432 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2434 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2435 FASTA/FASTQ files preprocessing.
2437 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2438 containing multiple short-reads sequences. The main processing of such
2439 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2440 is sometimes more productive to preprocess the files before mapping the
2441 sequences to the genome---manipulating the sequences to produce better mapping
2442 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2443 (license license:agpl3+)))
2445 (define-public flexbar
2452 (string-append "mirror://sourceforge/flexbar/"
2453 version "/flexbar_v" version "_src.tgz"))
2456 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2457 (build-system cmake-build-system)
2459 `(#:configure-flags (list
2460 (string-append "-DFLEXBAR_BINARY_DIR="
2461 (assoc-ref %outputs "out")
2464 (modify-phases %standard-phases
2466 (lambda* (#:key outputs #:allow-other-keys)
2467 (setenv "PATH" (string-append
2468 (assoc-ref outputs "out") "/bin:"
2470 (chdir "../flexbar_v2.5_src/test")
2471 (zero? (system* "bash" "flexbar_validate.sh"))))
2472 (delete 'install))))
2477 `(("pkg-config" ,pkg-config)
2479 (home-page "http://flexbar.sourceforge.net")
2480 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2482 "Flexbar preprocesses high-throughput nucleotide sequencing data
2483 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2484 Moreover, trimming and filtering features are provided. Flexbar increases
2485 read mapping rates and improves genome and transcriptome assemblies. It
2486 supports next-generation sequencing data in fasta/q and csfasta/q format from
2487 Illumina, Roche 454, and the SOLiD platform.")
2488 (license license:gpl3)))
2490 (define-public fraggenescan
2492 (name "fraggenescan")
2498 (string-append "mirror://sourceforge/fraggenescan/"
2499 "FragGeneScan" version ".tar.gz"))
2501 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2502 (build-system gnu-build-system)
2505 (modify-phases %standard-phases
2507 (add-before 'build 'patch-paths
2508 (lambda* (#:key outputs #:allow-other-keys)
2509 (let* ((out (string-append (assoc-ref outputs "out")))
2510 (share (string-append out "/share/fraggenescan/")))
2511 (substitute* "run_FragGeneScan.pl"
2513 (string-append "system(\"" (which "rm")))
2515 (string-append "system(\"" (which "mv")))
2516 (("\\\"awk") (string-append "\"" (which "awk")))
2517 ;; This script and other programs expect the training files
2518 ;; to be in the non-standard location bin/train/XXX. Change
2519 ;; this to be share/fraggenescan/train/XXX instead.
2520 (("^\\$train.file = \\$dir.*")
2521 (string-append "$train_file = \""
2523 "train/\".$FGS_train_file;")))
2524 (substitute* "run_hmm.c"
2525 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2526 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2529 (lambda _ (and (zero? (system* "make" "clean"))
2530 (zero? (system* "make" "fgs")))))
2532 (lambda* (#:key outputs #:allow-other-keys)
2533 (let* ((out (string-append (assoc-ref outputs "out")))
2534 (bin (string-append out "/bin/"))
2535 (share (string-append out "/share/fraggenescan/train")))
2536 (install-file "run_FragGeneScan.pl" bin)
2537 (install-file "FragGeneScan" bin)
2538 (copy-recursively "train" share))))
2540 (add-after 'install 'post-install-check
2541 ;; In lieu of 'make check', run one of the examples and check the
2542 ;; output files gets created.
2543 (lambda* (#:key outputs #:allow-other-keys)
2544 (let* ((out (string-append (assoc-ref outputs "out")))
2545 (bin (string-append out "/bin/"))
2546 (frag (string-append bin "run_FragGeneScan.pl")))
2547 (and (zero? (system* frag ; Test complete genome.
2548 "-genome=./example/NC_000913.fna"
2552 (file-exists? "test2.faa")
2553 (file-exists? "test2.ffn")
2554 (file-exists? "test2.gff")
2555 (file-exists? "test2.out")
2556 (zero? (system* ; Test incomplete sequences.
2558 "-genome=./example/NC_000913-fgs.ffn"
2561 "-train=454_30")))))))))
2564 ("python" ,python-2))) ;not compatible with python 3.
2565 (home-page "https://sourceforge.net/projects/fraggenescan/")
2566 (synopsis "Finds potentially fragmented genes in short reads")
2568 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2569 short and error-prone DNA sequencing reads. It can also be applied to predict
2570 genes in incomplete assemblies or complete genomes.")
2571 ;; GPL3+ according to private correspondense with the authors.
2572 (license license:gpl3+)))
2574 (define-public fxtract
2575 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2583 "https://github.com/ctSkennerton/fxtract/archive/"
2585 (file-name (string-append "ctstennerton-util-"
2586 (string-take util-commit 7)
2590 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2591 (build-system gnu-build-system)
2593 `(#:make-flags (list
2594 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2596 #:test-target "fxtract_test"
2598 (modify-phases %standard-phases
2600 (add-before 'build 'copy-util
2601 (lambda* (#:key inputs #:allow-other-keys)
2603 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2605 ;; Do not use make install as this requires additional dependencies.
2607 (lambda* (#:key outputs #:allow-other-keys)
2608 (let* ((out (assoc-ref outputs "out"))
2609 (bin (string-append out"/bin")))
2610 (install-file "fxtract" bin)
2616 ;; ctskennerton-util is licensed under GPL2.
2617 `(("ctskennerton-util"
2621 (url "https://github.com/ctSkennerton/util.git")
2622 (commit util-commit)))
2623 (file-name (string-append
2624 "ctstennerton-util-" util-commit "-checkout"))
2627 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2628 (home-page "https://github.com/ctSkennerton/fxtract")
2629 (synopsis "Extract sequences from FASTA and FASTQ files")
2631 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2632 or FASTQ) file given a subsequence. It uses a simple substring search for
2633 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2634 lookups or multi-pattern searching as required. By default fxtract looks in
2635 the sequence of each record but can also be told to look in the header,
2636 comment or quality sections.")
2637 ;; 'util' requires SSE instructions.
2638 (supported-systems '("x86_64-linux"))
2639 (license license:expat))))
2641 (define-public gemma
2647 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2649 (file-name (string-append name "-" version ".tar.gz"))
2652 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2653 (patches (search-patches "gemma-intel-compat.patch"))))
2658 (build-system gnu-build-system)
2661 '(,@(match (%current-system)
2663 '("FORCE_DYNAMIC=1"))
2665 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2667 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2669 (modify-phases %standard-phases
2671 (add-before 'build 'bin-mkdir
2676 (lambda* (#:key outputs #:allow-other-keys)
2677 (let ((out (assoc-ref outputs "out")))
2678 (install-file "bin/gemma"
2682 #:tests? #f)) ; no tests included yet
2683 (home-page "https://github.com/xiangzhou/GEMMA")
2684 (synopsis "Tool for genome-wide efficient mixed model association")
2686 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2687 standard linear mixed model resolver with application in genome-wide
2688 association studies (GWAS).")
2689 (license license:gpl3)))
2698 "https://github.com/nboley/grit/archive/"
2700 (file-name (string-append name "-" version ".tar.gz"))
2703 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2704 (build-system python-build-system)
2706 `(#:python ,python-2
2708 (modify-phases %standard-phases
2709 (add-after 'unpack 'generate-from-cython-sources
2710 (lambda* (#:key inputs outputs #:allow-other-keys)
2711 ;; Delete these C files to force fresh generation from pyx sources.
2712 (delete-file "grit/sparsify_support_fns.c")
2713 (delete-file "grit/call_peaks_support_fns.c")
2714 (substitute* "setup.py"
2715 (("Cython.Setup") "Cython.Build")
2716 ;; Add numpy include path to fix compilation
2718 (string-append "pyx\", ], include_dirs = ['"
2719 (assoc-ref inputs "python-numpy")
2720 "/lib/python2.7/site-packages/numpy/core/include/"
2724 `(("python-scipy" ,python2-scipy)
2725 ("python-numpy" ,python2-numpy)
2726 ("python-pysam" ,python2-pysam)
2727 ("python-networkx" ,python2-networkx)))
2729 `(("python-cython" ,python2-cython)))
2730 (home-page "http://grit-bio.org")
2731 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2733 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2734 full length transcript models. When none of these data sources are available,
2735 GRIT can be run by providing a candidate set of TES or TSS sites. In
2736 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2737 also be run in quantification mode, where it uses a provided GTF file and just
2738 estimates transcript expression.")
2739 (license license:gpl3+)))
2741 (define-public hisat
2748 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2749 version "-beta-source.zip"))
2752 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2753 (build-system gnu-build-system)
2755 `(#:tests? #f ;no check target
2756 #:make-flags '("allall"
2757 ;; Disable unsupported `popcnt' instructions on
2758 ;; architectures other than x86_64
2759 ,@(if (string-prefix? "x86_64"
2760 (or (%current-target-system)
2763 '("POPCNT_CAPABILITY=0")))
2765 (modify-phases %standard-phases
2766 (add-after 'unpack 'patch-sources
2768 ;; XXX Cannot use snippet because zip files are not supported
2769 (substitute* "Makefile"
2770 (("^CC = .*$") "CC = gcc")
2771 (("^CPP = .*$") "CPP = g++")
2772 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2773 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2774 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2775 (substitute* '("hisat-build" "hisat-inspect")
2776 (("/usr/bin/env") (which "env")))
2779 (lambda* (#:key outputs #:allow-other-keys)
2780 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2781 (for-each (lambda (file)
2782 (install-file file bin))
2785 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2787 (delete 'configure))))
2789 `(("unzip" ,unzip)))
2794 ;; Non-portable SSE instructions are used so building fails on platforms
2795 ;; other than x86_64.
2796 (supported-systems '("x86_64-linux"))
2797 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2798 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2800 "HISAT is a fast and sensitive spliced alignment program for mapping
2801 RNA-seq reads. In addition to one global FM index that represents a whole
2802 genome, HISAT uses a large set of small FM indexes that collectively cover the
2803 whole genome. These small indexes (called local indexes) combined with
2804 several alignment strategies enable effective alignment of RNA-seq reads, in
2805 particular, reads spanning multiple exons.")
2806 (license license:gpl3+)))
2808 (define-public hisat2
2815 ;; FIXME: a better source URL is
2816 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2817 ;; "/downloads/hisat2-" version "-source.zip")
2818 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2819 ;; but it is currently unavailable.
2820 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2821 (file-name (string-append name "-" version ".tar.gz"))
2824 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2825 (build-system gnu-build-system)
2827 `(#:tests? #f ; no check target
2828 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2829 #:modules ((guix build gnu-build-system)
2833 (modify-phases %standard-phases
2834 (add-after 'unpack 'make-deterministic
2836 (substitute* "Makefile"
2841 (lambda* (#:key outputs #:allow-other-keys)
2842 (let* ((out (assoc-ref outputs "out"))
2843 (bin (string-append out "/bin/"))
2844 (doc (string-append out "/share/doc/hisat2/")))
2846 (cut install-file <> bin)
2848 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2850 (install-file "doc/manual.inc.html" doc))
2853 `(("unzip" ,unzip) ; needed for archive from ftp
2855 ("pandoc" ,ghc-pandoc))) ; for documentation
2856 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2857 (synopsis "Graph-based alignment of genomic sequencing reads")
2858 (description "HISAT2 is a fast and sensitive alignment program for mapping
2859 next-generation sequencing reads (both DNA and RNA) to a population of human
2860 genomes (as well as to a single reference genome). In addition to using one
2861 global @dfn{graph FM} (GFM) index that represents a population of human
2862 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2863 the whole genome. These small indexes, combined with several alignment
2864 strategies, enable rapid and accurate alignment of sequencing reads. This new
2865 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2866 ;; HISAT2 contains files from Bowtie2, which is released under
2867 ;; GPLv2 or later. The HISAT2 source files are released under
2869 (license license:gpl3+)))
2871 (define-public hmmer
2879 "http://eddylab.org/software/hmmer"
2880 (version-major version) "/"
2881 version "/hmmer-" version ".tar.gz"))
2884 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2885 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2886 (build-system gnu-build-system)
2887 (native-inputs `(("perl" ,perl)))
2888 (home-page "http://hmmer.org/")
2889 (synopsis "Biosequence analysis using profile hidden Markov models")
2891 "HMMER is used for searching sequence databases for homologs of protein
2892 sequences, and for making protein sequence alignments. It implements methods
2893 using probabilistic models called profile hidden Markov models (profile
2895 (license (list license:gpl3+
2896 ;; The bundled library 'easel' is distributed
2897 ;; under The Janelia Farm Software License.
2898 (license:non-copyleft
2899 "file://easel/LICENSE"
2900 "See easel/LICENSE in the distribution.")))))
2902 (define-public htseq
2908 (uri (pypi-uri "HTSeq" version))
2911 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2912 (build-system python-build-system)
2914 `(("python-cython" ,python-cython)))
2915 ;; Numpy needs to be propagated when htseq is used as a Python library.
2917 `(("python-numpy" ,python-numpy)))
2919 `(("python-pysam" ,python-pysam)
2920 ("python-matplotlib" ,python-matplotlib)))
2921 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2922 (synopsis "Analysing high-throughput sequencing data with Python")
2924 "HTSeq is a Python package that provides infrastructure to process data
2925 from high-throughput sequencing assays.")
2926 (license license:gpl3+)))
2928 (define-public python2-htseq
2929 (package-with-python2 htseq))
2931 (define-public java-htsjdk
2933 (name "java-htsjdk")
2934 (version "2.3.0") ; last version without build dependency on gradle
2938 "https://github.com/samtools/htsjdk/archive/"
2940 (file-name (string-append name "-" version ".tar.gz"))
2943 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2944 (modules '((guix build utils)))
2946 ;; Delete pre-built binaries
2948 (delete-file-recursively "lib")
2951 (build-system ant-build-system)
2953 `(#:tests? #f ; test require Internet access
2956 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2957 "/share/java/htsjdk/"))
2958 #:build-target "all"
2960 (modify-phases %standard-phases
2961 ;; The build phase also installs the jars
2962 (delete 'install))))
2964 `(("java-ngs" ,java-ngs)
2965 ("java-snappy-1" ,java-snappy-1)
2966 ("java-commons-compress" ,java-commons-compress)
2967 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
2968 ("java-commons-jexl-2" ,java-commons-jexl-2)
2969 ("java-xz" ,java-xz)))
2971 `(("java-testng" ,java-testng)))
2972 (home-page "http://samtools.github.io/htsjdk/")
2973 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2975 "HTSJDK is an implementation of a unified Java library for accessing
2976 common file formats, such as SAM and VCF, used for high-throughput
2977 sequencing (HTS) data. There are also an number of useful utilities for
2978 manipulating HTS data.")
2979 (license license:expat)))
2981 (define-public java-htsjdk-latest
2983 (name "java-htsjdk")
2988 (url "https://github.com/samtools/htsjdk.git")
2990 (file-name (string-append name "-" version "-checkout"))
2993 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
2994 (build-system ant-build-system)
2996 `(#:tests? #f ; test require Scala
2998 #:jar-name "htsjdk.jar"
3000 (modify-phases %standard-phases
3001 (add-after 'unpack 'remove-useless-build.xml
3002 (lambda _ (delete-file "build.xml") #t))
3003 ;; The tests require the scalatest package.
3004 (add-after 'unpack 'remove-tests
3005 (lambda _ (delete-file-recursively "src/test") #t)))))
3007 `(("java-ngs" ,java-ngs)
3008 ("java-snappy-1" ,java-snappy-1)
3009 ("java-commons-compress" ,java-commons-compress)
3010 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3011 ("java-commons-jexl-2" ,java-commons-jexl-2)
3012 ("java-xz" ,java-xz)))
3014 `(("java-junit" ,java-junit)))
3015 (home-page "http://samtools.github.io/htsjdk/")
3016 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3018 "HTSJDK is an implementation of a unified Java library for accessing
3019 common file formats, such as SAM and VCF, used for high-throughput
3020 sequencing (HTS) data. There are also an number of useful utilities for
3021 manipulating HTS data.")
3022 (license license:expat)))
3024 ;; This is needed for picard 2.10.3
3025 (define-public java-htsjdk-2.10.1
3026 (package (inherit java-htsjdk-latest)
3027 (name "java-htsjdk")
3032 (url "https://github.com/samtools/htsjdk.git")
3034 (file-name (string-append name "-" version "-checkout"))
3037 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3038 (build-system ant-build-system)
3040 `(#:tests? #f ; tests require Scala
3042 #:jar-name "htsjdk.jar"
3044 (modify-phases %standard-phases
3045 (add-after 'unpack 'remove-useless-build.xml
3046 (lambda _ (delete-file "build.xml") #t))
3047 ;; The tests require the scalatest package.
3048 (add-after 'unpack 'remove-tests
3049 (lambda _ (delete-file-recursively "src/test") #t)))))))
3051 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3052 ;; recent version of java-htsjdk, which depends on gradle.
3053 (define-public java-picard
3055 (name "java-picard")
3060 (url "https://github.com/broadinstitute/picard.git")
3062 (file-name (string-append "java-picard-" version "-checkout"))
3065 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3066 (modules '((guix build utils)))
3069 ;; Delete pre-built binaries.
3070 (delete-file-recursively "lib")
3072 (substitute* "build.xml"
3073 ;; Remove build-time dependency on git.
3074 (("failifexecutionfails=\"true\"")
3075 "failifexecutionfails=\"false\"")
3077 (("depends=\"compile-htsjdk, ")
3079 (("depends=\"compile-htsjdk-tests, ")
3081 ;; Build picard-lib.jar before building picard.jar
3082 (("name=\"picard-jar\" depends=\"" line)
3083 (string-append line "picard-lib-jar, ")))
3085 (build-system ant-build-system)
3087 `(#:build-target "picard-jar"
3088 #:test-target "test"
3089 ;; Tests require jacoco:coverage.
3092 (list (string-append "-Dhtsjdk_lib_dir="
3093 (assoc-ref %build-inputs "java-htsjdk")
3094 "/share/java/htsjdk/")
3095 "-Dhtsjdk-classes=dist/tmp"
3096 (string-append "-Dhtsjdk-version="
3097 ,(package-version java-htsjdk)))
3100 (modify-phases %standard-phases
3101 (add-after 'unpack 'use-our-htsjdk
3102 (lambda* (#:key inputs #:allow-other-keys)
3103 (substitute* "build.xml"
3104 (("\\$\\{htsjdk\\}/lib")
3105 (string-append (assoc-ref inputs "java-htsjdk")
3106 "/share/java/htsjdk/")))
3108 (add-after 'unpack 'make-test-target-independent
3109 (lambda* (#:key inputs #:allow-other-keys)
3110 (substitute* "build.xml"
3111 (("name=\"test\" depends=\"compile, ")
3112 "name=\"test\" depends=\""))
3114 (replace 'install (install-jars "dist")))))
3116 `(("java-htsjdk" ,java-htsjdk)
3117 ("java-guava" ,java-guava)))
3119 `(("java-testng" ,java-testng)))
3120 (home-page "http://broadinstitute.github.io/picard/")
3121 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3122 (description "Picard is a set of Java command line tools for manipulating
3123 high-throughput sequencing (HTS) data and formats. Picard is implemented
3124 using the HTSJDK Java library to support accessing file formats that are
3125 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3127 (license license:expat)))
3129 ;; This is needed for dropseq-tools
3130 (define-public java-picard-2.10.3
3132 (name "java-picard")
3137 (url "https://github.com/broadinstitute/picard.git")
3139 (file-name (string-append "java-picard-" version "-checkout"))
3142 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3143 (build-system ant-build-system)
3145 `(#:jar-name "picard.jar"
3146 ;; Tests require jacoco:coverage.
3149 #:main-class "picard.cmdline.PicardCommandLine"
3150 #:modules ((guix build ant-build-system)
3152 (guix build java-utils)
3157 (modify-phases %standard-phases
3158 (add-after 'unpack 'remove-useless-build.xml
3159 (lambda _ (delete-file "build.xml") #t))
3160 ;; This is necessary to ensure that htsjdk is found when using
3161 ;; picard.jar as an executable.
3162 (add-before 'build 'edit-classpath-in-manifest
3163 (lambda* (#:key inputs #:allow-other-keys)
3164 (chmod "build.xml" #o664)
3165 (call-with-output-file "build.xml.new"
3169 (with-input-from-file "build.xml"
3170 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3171 `((target . ,(lambda (tag . kids)
3172 (let ((name ((sxpath '(name *text*))
3174 ;; FIXME: We're breaking the line
3175 ;; early with a dummy path to
3176 ;; ensure that the store reference
3177 ;; isn't broken apart and can still
3178 ;; be found by the reference
3183 ~a/share/java/htsjdk.jar${line.separator}"
3184 ;; maximum line length is 70
3185 (string-tabulate (const #\b) 57)
3186 (assoc-ref inputs "java-htsjdk"))))
3187 (if (member "manifest" name)
3191 (file "${manifest.file}")
3194 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3195 (*text* . ,(lambda (_ txt) txt))))
3197 (rename-file "build.xml.new" "build.xml")
3200 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3202 `(("java-testng" ,java-testng)
3203 ("java-guava" ,java-guava)))
3204 (home-page "http://broadinstitute.github.io/picard/")
3205 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3206 (description "Picard is a set of Java command line tools for manipulating
3207 high-throughput sequencing (HTS) data and formats. Picard is implemented
3208 using the HTSJDK Java library to support accessing file formats that are
3209 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3211 (license license:expat)))
3213 ;; This is the last version of Picard to provide net.sf.samtools
3214 (define-public java-picard-1.113
3215 (package (inherit java-picard)
3216 (name "java-picard")
3221 (url "https://github.com/broadinstitute/picard.git")
3223 (file-name (string-append "java-picard-" version "-checkout"))
3226 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3227 (modules '((guix build utils)))
3230 ;; Delete pre-built binaries.
3231 (delete-file-recursively "lib")
3234 (build-system ant-build-system)
3236 `(#:build-target "picard-jar"
3237 #:test-target "test"
3238 ;; FIXME: the class path at test time is wrong.
3239 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3240 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3243 ;; This is only used for tests.
3245 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3247 (modify-phases %standard-phases
3248 ;; Do not use bundled ant bzip2.
3249 (add-after 'unpack 'use-ant-bzip
3250 (lambda* (#:key inputs #:allow-other-keys)
3251 (substitute* "build.xml"
3252 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3253 (string-append (assoc-ref inputs "ant")
3256 (add-after 'unpack 'make-test-target-independent
3257 (lambda* (#:key inputs #:allow-other-keys)
3258 (substitute* "build.xml"
3259 (("name=\"test\" depends=\"compile, ")
3260 "name=\"test\" depends=\"compile-tests, ")
3261 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3262 "name=\"compile\" depends=\"compile-src\""))
3264 (add-after 'unpack 'fix-deflater-path
3265 (lambda* (#:key outputs #:allow-other-keys)
3266 (substitute* "src/java/net/sf/samtools/Defaults.java"
3267 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3268 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3269 (assoc-ref outputs "out")
3270 "/lib/jni/libIntelDeflater.so"
3273 ;; Build the deflater library, because we've previously deleted the
3274 ;; pre-built one. This can only be built with access to the JDK
3276 (add-after 'build 'build-jni
3277 (lambda* (#:key inputs #:allow-other-keys)
3280 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3281 "-xf" (assoc-ref inputs "jdk-src")))
3282 (zero? (system* "javah" "-jni"
3283 "-classpath" "classes"
3285 "net.sf.samtools.util.zip.IntelDeflater"))
3286 (with-directory-excursion "src/c/inteldeflater"
3287 (zero? (system* "gcc" "-I../../../lib" "-I."
3288 (string-append "-I" (assoc-ref inputs "jdk")
3290 "-I../../../jdk-src/src/share/native/common/"
3291 "-I../../../jdk-src/src/solaris/native/common/"
3292 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3293 (zero? (system* "gcc" "-shared"
3294 "-o" "../../../lib/jni/libIntelDeflater.so"
3295 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3296 ;; We can only build everything else after building the JNI library.
3297 (add-after 'build-jni 'build-rest
3298 (lambda* (#:key make-flags #:allow-other-keys)
3299 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3300 (add-before 'build 'set-JAVA6_HOME
3302 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3304 (replace 'install (install-jars "dist"))
3305 (add-after 'install 'install-jni-lib
3306 (lambda* (#:key outputs #:allow-other-keys)
3307 (let ((jni (string-append (assoc-ref outputs "out")
3310 (install-file "lib/jni/libIntelDeflater.so" jni)
3313 `(("java-snappy-1" ,java-snappy-1)
3314 ("java-commons-jexl-2" ,java-commons-jexl-2)
3315 ("java-cofoja" ,java-cofoja)
3316 ("ant" ,ant) ; for bzip2 support at runtime
3319 `(("ant-apache-bcel" ,ant-apache-bcel)
3320 ("ant-junit" ,ant-junit)
3321 ("java-testng" ,java-testng)
3322 ("java-commons-bcel" ,java-commons-bcel)
3323 ("java-jcommander" ,java-jcommander)
3324 ("jdk" ,icedtea-8 "jdk")
3325 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3327 (define-public fastqc
3334 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3335 "projects/fastqc/fastqc_v"
3336 version "_source.zip"))
3339 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3340 (build-system ant-build-system)
3342 `(#:tests? #f ; there are no tests
3343 #:build-target "build"
3345 (modify-phases %standard-phases
3346 (add-after 'unpack 'fix-dependencies
3347 (lambda* (#:key inputs #:allow-other-keys)
3348 (substitute* "build.xml"
3350 (string-append (assoc-ref inputs "java-jbzip2")
3351 "/share/java/jbzip2.jar"))
3353 (string-append (assoc-ref inputs "java-picard-1.113")
3354 "/share/java/sam-1.112.jar"))
3356 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3357 "/share/java/sis-jhdf5.jar")))
3359 ;; There is no installation target
3361 (lambda* (#:key inputs outputs #:allow-other-keys)
3362 (let* ((out (assoc-ref outputs "out"))
3363 (bin (string-append out "/bin"))
3364 (share (string-append out "/share/fastqc/"))
3365 (exe (string-append share "/fastqc")))
3366 (for-each mkdir-p (list bin share))
3367 (copy-recursively "bin" share)
3369 (("my \\$java_bin = 'java';")
3370 (string-append "my $java_bin = '"
3371 (assoc-ref inputs "java")
3374 (symlink exe (string-append bin "/fastqc"))
3378 ("perl" ,perl) ; needed for the wrapper script
3379 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3380 ("java-picard-1.113" ,java-picard-1.113)
3381 ("java-jbzip2" ,java-jbzip2)))
3383 `(("unzip" ,unzip)))
3384 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3385 (synopsis "Quality control tool for high throughput sequence data")
3387 "FastQC aims to provide a simple way to do some quality control
3388 checks on raw sequence data coming from high throughput sequencing
3389 pipelines. It provides a modular set of analyses which you can use to
3390 give a quick impression of whether your data has any problems of which
3391 you should be aware before doing any further analysis.
3393 The main functions of FastQC are:
3396 @item Import of data from BAM, SAM or FastQ files (any variant);
3397 @item Providing a quick overview to tell you in which areas there may
3399 @item Summary graphs and tables to quickly assess your data;
3400 @item Export of results to an HTML based permanent report;
3401 @item Offline operation to allow automated generation of reports
3402 without running the interactive application.
3404 (license license:gpl3+)))
3406 (define-public htslib
3413 "https://github.com/samtools/htslib/releases/download/"
3414 version "/htslib-" version ".tar.bz2"))
3417 "1il6i2p84b0y9c93dhvzzki1ifw9bvapm2mvpr0xvb2nq8jlwgdy"))))
3418 (build-system gnu-build-system)
3420 `(("openssl" ,openssl)
3425 (home-page "http://www.htslib.org")
3426 (synopsis "C library for reading/writing high-throughput sequencing data")
3428 "HTSlib is a C library for reading/writing high-throughput sequencing
3429 data. It also provides the @command{bgzip}, @command{htsfile}, and
3430 @command{tabix} utilities.")
3431 ;; Files under cram/ are released under the modified BSD license;
3432 ;; the rest is released under the Expat license
3433 (license (list license:expat license:bsd-3))))
3435 ;; This package should be removed once no packages rely upon it.
3443 "https://github.com/samtools/htslib/releases/download/"
3444 version "/htslib-" version ".tar.bz2"))
3447 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3456 "https://github.com/nboley/idr/archive/"
3458 (file-name (string-append name "-" version ".tar.gz"))
3461 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3462 ;; Delete generated C code.
3464 '(begin (delete-file "idr/inv_cdf.c") #t))))
3465 (build-system python-build-system)
3466 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3467 ;; are no longer part of this package. It also asserts False, which
3468 ;; causes the tests to always fail.
3469 (arguments `(#:tests? #f))
3471 `(("python-scipy" ,python-scipy)
3472 ("python-sympy" ,python-sympy)
3473 ("python-numpy" ,python-numpy)
3474 ("python-matplotlib" ,python-matplotlib)))
3476 `(("python-cython" ,python-cython)))
3477 (home-page "https://github.com/nboley/idr")
3478 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3480 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3481 to measure the reproducibility of findings identified from replicate
3482 experiments and provide highly stable thresholds based on reproducibility.")
3483 (license license:gpl2+)))
3485 (define-public jellyfish
3491 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3492 "releases/download/v" version
3493 "/jellyfish-" version ".tar.gz"))
3496 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3497 (build-system gnu-build-system)
3498 (outputs '("out" ;for library
3499 "ruby" ;for Ruby bindings
3500 "python")) ;for Python bindings
3503 (list (string-append "--enable-ruby-binding="
3504 (assoc-ref %outputs "ruby"))
3505 (string-append "--enable-python-binding="
3506 (assoc-ref %outputs "python")))
3508 (modify-phases %standard-phases
3509 (add-before 'check 'set-SHELL-variable
3511 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3513 (setenv "SHELL" (which "bash"))
3519 ("python" ,python-2)
3520 ("pkg-config" ,pkg-config)))
3522 `(("htslib" ,htslib)))
3523 (synopsis "Tool for fast counting of k-mers in DNA")
3525 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3526 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3527 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3528 is a command-line program that reads FASTA and multi-FASTA files containing
3529 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3530 translated into a human-readable text format using the @code{jellyfish dump}
3531 command, or queried for specific k-mers with @code{jellyfish query}.")
3532 (home-page "http://www.genome.umd.edu/jellyfish.html")
3533 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3534 (supported-systems '("x86_64-linux"))
3535 ;; The combined work is published under the GPLv3 or later. Individual
3536 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3537 (license (list license:gpl3+ license:expat))))
3539 (define-public khmer
3546 (uri (pypi-uri "khmer" version))
3549 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3550 (patches (search-patches "khmer-use-libraries.patch"))))
3551 (build-system python-build-system)
3554 (modify-phases %standard-phases
3555 (add-after 'unpack 'set-paths
3556 (lambda* (#:key inputs outputs #:allow-other-keys)
3557 ;; Delete bundled libraries.
3558 (delete-file-recursively "third-party/zlib")
3559 (delete-file-recursively "third-party/bzip2")
3560 ;; Replace bundled seqan.
3561 (let* ((seqan-all "third-party/seqan")
3562 (seqan-include (string-append
3563 seqan-all "/core/include")))
3564 (delete-file-recursively seqan-all)
3565 (copy-recursively (string-append (assoc-ref inputs "seqan")
3567 (string-append seqan-include "/seqan")))
3568 ;; We do not replace the bundled MurmurHash as the canonical
3569 ;; repository for this code 'SMHasher' is unsuitable for
3570 ;; providing a library. See
3571 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3573 (add-after 'unpack 'set-cc
3577 ;; It is simpler to test after installation.
3579 (add-after 'install 'post-install-check
3580 (lambda* (#:key inputs outputs #:allow-other-keys)
3581 (let ((out (assoc-ref outputs "out")))
3586 (assoc-ref outputs "out")
3588 (setenv "PYTHONPATH"
3590 (getenv "PYTHONPATH")
3594 (string-take (string-take-right
3595 (assoc-ref inputs "python") 5) 3)
3597 (with-directory-excursion "build"
3598 (zero? (system* "nosetests" "khmer" "--attr"
3599 "!known_failing")))))))))
3602 ("python-nose" ,python-nose)))
3606 ("python-screed" ,python-screed)
3607 ("python-bz2file" ,python-bz2file)
3608 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3609 ;; until the next version of khmer (likely 2.1) is released.
3611 (home-page "https://khmer.readthedocs.org/")
3612 (synopsis "K-mer counting, filtering and graph traversal library")
3613 (description "The khmer software is a set of command-line tools for
3614 working with DNA shotgun sequencing data from genomes, transcriptomes,
3615 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3616 sometimes better. Khmer can also identify and fix problems with shotgun
3618 ;; When building on i686, armhf and mips64el, we get the following error:
3619 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3620 (supported-systems '("x86_64-linux" "aarch64-linux"))
3621 (license license:bsd-3)))
3623 (define-public kaiju
3630 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3632 (file-name (string-append name "-" version ".tar.gz"))
3635 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3636 (build-system gnu-build-system)
3638 `(#:tests? #f ; There are no tests.
3640 (modify-phases %standard-phases
3642 (add-before 'build 'move-to-src-dir
3643 (lambda _ (chdir "src") #t))
3645 (lambda* (#:key inputs outputs #:allow-other-keys)
3646 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3649 (copy-recursively "bin" bin)
3650 (copy-recursively "util" bin))
3654 (home-page "http://kaiju.binf.ku.dk/")
3655 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3656 (description "Kaiju is a program for sensitive taxonomic classification
3657 of high-throughput sequencing reads from metagenomic whole genome sequencing
3659 (license license:gpl3+)))
3664 (version "2.1.0.20151222")
3667 (uri (pypi-uri "MACS2" version))
3670 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3671 (build-system python-build-system)
3673 `(#:python ,python-2 ; only compatible with Python 2.7
3674 #:tests? #f)) ; no test target
3676 `(("python-numpy" ,python2-numpy)))
3677 (home-page "https://github.com/taoliu/MACS/")
3678 (synopsis "Model based analysis for ChIP-Seq data")
3680 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3681 identifying transcript factor binding sites named Model-based Analysis of
3682 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3683 the significance of enriched ChIP regions and it improves the spatial
3684 resolution of binding sites through combining the information of both
3685 sequencing tag position and orientation.")
3686 (license license:bsd-3)))
3688 (define-public mafft
3695 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3696 "-without-extensions-src.tgz"))
3697 (file-name (string-append name "-" version ".tgz"))
3700 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3701 (build-system gnu-build-system)
3703 `(#:tests? #f ; no automated tests, though there are tests in the read me
3704 #:make-flags (let ((out (assoc-ref %outputs "out")))
3705 (list (string-append "PREFIX=" out)
3706 (string-append "BINDIR="
3707 (string-append out "/bin"))))
3709 (modify-phases %standard-phases
3710 (add-after 'unpack 'enter-dir
3711 (lambda _ (chdir "core") #t))
3712 (add-after 'enter-dir 'patch-makefile
3714 ;; on advice from the MAFFT authors, there is no need to
3715 ;; distribute mafft-profile, mafft-distance, or
3716 ;; mafft-homologs.rb as they are too "specialised".
3717 (substitute* "Makefile"
3718 ;; remove mafft-homologs.rb from SCRIPTS
3719 (("^SCRIPTS = mafft mafft-homologs.rb")
3721 ;; remove mafft-homologs from MANPAGES
3722 (("^MANPAGES = mafft.1 mafft-homologs.1")
3723 "MANPAGES = mafft.1")
3724 ;; remove mafft-distance from PROGS
3725 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3726 "PROGS = dvtditr dndfast7 dndblast sextet5")
3727 ;; remove mafft-profile from PROGS
3728 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3729 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3730 (("^rm -f mafft-profile mafft-profile.exe") "#")
3731 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3732 ;; do not install MAN pages in libexec folder
3733 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3734 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3736 (add-after 'enter-dir 'patch-paths
3737 (lambda* (#:key inputs #:allow-other-keys)
3738 (substitute* '("pairash.c"
3740 (("perl") (which "perl"))
3741 (("([\"`| ])awk" _ prefix)
3742 (string-append prefix (which "awk")))
3743 (("grep") (which "grep")))
3746 (add-after 'install 'wrap-programs
3747 (lambda* (#:key outputs #:allow-other-keys)
3748 (let* ((out (assoc-ref outputs "out"))
3749 (bin (string-append out "/bin"))
3750 (path (string-append
3751 (assoc-ref %build-inputs "coreutils") "/bin:")))
3752 (for-each (lambda (file)
3754 `("PATH" ":" prefix (,path))))
3762 ("coreutils" ,coreutils)))
3763 (home-page "http://mafft.cbrc.jp/alignment/software/")
3764 (synopsis "Multiple sequence alignment program")
3766 "MAFFT offers a range of multiple alignment methods for nucleotide and
3767 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3768 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3770 (license (license:non-copyleft
3771 "http://mafft.cbrc.jp/alignment/software/license.txt"
3772 "BSD-3 with different formatting"))))
3781 "https://github.com/marbl/mash/archive/v"
3783 (file-name (string-append name "-" version ".tar.gz"))
3786 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3787 (modules '((guix build utils)))
3789 ;; Delete bundled kseq.
3790 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3791 '(delete-file "src/mash/kseq.h"))))
3792 (build-system gnu-build-system)
3794 `(#:tests? #f ; No tests.
3797 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3798 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3799 #:make-flags (list "CC=gcc")
3801 (modify-phases %standard-phases
3802 (add-after 'unpack 'fix-includes
3804 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3805 (("^#include \"kseq\\.h\"")
3806 "#include \"htslib/kseq.h\""))
3808 (add-after 'fix-includes 'autoconf
3809 (lambda _ (zero? (system* "autoconf")))))))
3811 `(("autoconf" ,autoconf)
3812 ;; Capnproto and htslib are statically embedded in the final
3813 ;; application. Therefore we also list their licenses, below.
3814 ("capnproto" ,capnproto)
3815 ("htslib" ,htslib)))
3819 (supported-systems '("x86_64-linux"))
3820 (home-page "https://mash.readthedocs.io")
3821 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3822 (description "Mash is a fast sequence distance estimator that uses the
3823 MinHash algorithm and is designed to work with genomes and metagenomes in the
3824 form of assemblies or reads.")
3825 (license (list license:bsd-3 ; Mash
3826 license:expat ; HTSlib and capnproto
3827 license:public-domain ; MurmurHash 3
3828 license:cpl1.0)))) ; Open Bloom Filter
3830 (define-public metabat
3837 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3839 (file-name (string-append name "-" version ".tar.gz"))
3842 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3843 (patches (search-patches "metabat-fix-compilation.patch"))))
3844 (build-system scons-build-system)
3846 `(#:scons ,scons-python2
3848 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3849 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3850 #:tests? #f ;; Tests are run during the build phase.
3852 (modify-phases %standard-phases
3853 (add-after 'unpack 'fix-includes
3855 (substitute* "src/BamUtils.h"
3856 (("^#include \"bam/bam\\.h\"")
3857 "#include \"samtools/bam.h\"")
3858 (("^#include \"bam/sam\\.h\"")
3859 "#include \"samtools/sam.h\""))
3860 (substitute* "src/KseqReader.h"
3861 (("^#include \"bam/kseq\\.h\"")
3862 "#include \"htslib/kseq.h\""))
3864 (add-after 'unpack 'fix-scons
3865 (lambda* (#:key inputs #:allow-other-keys)
3866 (substitute* "SConstruct"
3867 (("^htslib_dir += 'samtools'")
3868 (string-append "htslib_dir = '"
3869 (assoc-ref inputs "htslib")
3871 (("^samtools_dir = 'samtools'")
3872 (string-append "samtools_dir = '"
3873 (assoc-ref inputs "samtools")
3875 (("^findStaticOrShared\\('bam', hts_lib")
3876 (string-append "findStaticOrShared('bam', '"
3877 (assoc-ref inputs "samtools")
3879 ;; Do not distribute README.
3880 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3885 ("samtools" ,samtools)
3888 (home-page "https://bitbucket.org/berkeleylab/metabat")
3890 "Reconstruction of single genomes from complex microbial communities")
3892 "Grouping large genomic fragments assembled from shotgun metagenomic
3893 sequences to deconvolute complex microbial communities, or metagenome binning,
3894 enables the study of individual organisms and their interactions. MetaBAT is
3895 an automated metagenome binning software, which integrates empirical
3896 probabilistic distances of genome abundance and tetranucleotide frequency.")
3897 ;; The source code contains inline assembly.
3898 (supported-systems '("x86_64-linux" "i686-linux"))
3899 (license (license:non-copyleft "file://license.txt"
3900 "See license.txt in the distribution."))))
3902 (define-public minced
3909 "https://github.com/ctSkennerton/minced/archive/"
3911 (file-name (string-append name "-" version ".tar.gz"))
3914 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3915 (build-system gnu-build-system)
3917 `(#:test-target "test"
3919 (modify-phases %standard-phases
3921 (add-before 'check 'fix-test
3923 ;; Fix test for latest version.
3924 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3925 (("minced:0.1.6") "minced:0.2.0"))
3927 (replace 'install ; No install target.
3928 (lambda* (#:key inputs outputs #:allow-other-keys)
3929 (let* ((out (assoc-ref outputs "out"))
3930 (bin (string-append out "/bin"))
3931 (wrapper (string-append bin "/minced")))
3932 ;; Minced comes with a wrapper script that tries to figure out where
3933 ;; it is located before running the JAR. Since these paths are known
3934 ;; to us, we build our own wrapper to avoid coreutils dependency.
3935 (install-file "minced.jar" bin)
3936 (with-output-to-file wrapper
3940 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3941 (assoc-ref inputs "jre") "/bin/java -jar "
3942 bin "/minced.jar \"$@\"\n"))))
3943 (chmod wrapper #o555)))))))
3945 `(("jdk" ,icedtea "jdk")))
3948 ("jre" ,icedtea "out")))
3949 (home-page "https://github.com/ctSkennerton/minced")
3950 (synopsis "Mining CRISPRs in Environmental Datasets")
3952 "MinCED is a program to find Clustered Regularly Interspaced Short
3953 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3954 unassembled metagenomic reads, but is mainly designed for full genomes and
3955 assembled metagenomic sequence.")
3956 (license license:gpl3+)))
3964 (uri (pypi-uri "misopy" version))
3967 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3968 (modules '((guix build utils)))
3970 '(substitute* "setup.py"
3971 ;; Use setuptools, or else the executables are not
3973 (("distutils.core") "setuptools")
3974 ;; use "gcc" instead of "cc" for compilation
3976 "cc.set_executables(
3980 linker_so='gcc -shared'); defines")))))
3981 (build-system python-build-system)
3983 `(#:python ,python-2 ; only Python 2 is supported
3984 #:tests? #f)) ; no "test" target
3986 `(("samtools" ,samtools)
3987 ("python-numpy" ,python2-numpy)
3988 ("python-pysam" ,python2-pysam)
3989 ("python-scipy" ,python2-scipy)
3990 ("python-matplotlib" ,python2-matplotlib)))
3992 `(("python-mock" ,python2-mock) ;for tests
3993 ("python-pytz" ,python2-pytz))) ;for tests
3994 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3995 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3997 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3998 the expression level of alternatively spliced genes from RNA-Seq data, and
3999 identifies differentially regulated isoforms or exons across samples. By
4000 modeling the generative process by which reads are produced from isoforms in
4001 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4002 that a read originated from a particular isoform.")
4003 (license license:gpl2)))
4005 (define-public muscle
4008 (version "3.8.1551")
4010 (method url-fetch/tarbomb)
4012 "http://www.drive5.com/muscle/muscle_src_"
4016 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4017 (build-system gnu-build-system)
4019 `(#:make-flags (list "LDLIBS = -lm")
4021 (modify-phases %standard-phases
4024 ;; There are no tests, so just test if it runs.
4025 (lambda _ (zero? (system* "./muscle" "-version"))))
4027 (lambda* (#:key outputs #:allow-other-keys)
4028 (let* ((out (assoc-ref outputs "out"))
4029 (bin (string-append out "/bin")))
4030 (install-file "muscle" bin)))))))
4031 (home-page "http://www.drive5.com/muscle")
4032 (synopsis "Multiple sequence alignment program")
4034 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4035 program for nucleotide and protein sequences.")
4036 ;; License information found in 'muscle -h' and usage.cpp.
4037 (license license:public-domain)))
4039 (define-public newick-utils
4040 ;; There are no recent releases so we package from git.
4041 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4043 (name "newick-utils")
4044 (version (string-append "1.6-1." (string-take commit 8)))
4048 (url "https://github.com/tjunier/newick_utils.git")
4050 (file-name (string-append name "-" version "-checkout"))
4053 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4054 (build-system gnu-build-system)
4057 (modify-phases %standard-phases
4058 (add-after 'unpack 'autoconf
4059 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4061 ;; XXX: TODO: Enable Lua and Guile bindings.
4062 ;; https://github.com/tjunier/newick_utils/issues/13
4063 `(("libxml2" ,libxml2)
4067 `(("autoconf" ,autoconf)
4068 ("automake" ,automake)
4069 ("libtool" ,libtool)))
4070 (synopsis "Programs for working with newick format phylogenetic trees")
4072 "Newick-utils is a suite of utilities for processing phylogenetic trees
4073 in Newick format. Functions include re-rooting, extracting subtrees,
4074 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4075 (home-page "https://github.com/tjunier/newick_utils")
4076 (license license:bsd-3))))
4085 "https://github.com/wwood/OrfM/releases/download/v"
4086 version "/orfm-" version ".tar.gz"))
4089 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4090 (build-system gnu-build-system)
4091 (inputs `(("zlib" ,zlib)))
4093 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4094 ("ruby-rspec" ,ruby-rspec)
4096 (synopsis "Simple and not slow open reading frame (ORF) caller")
4098 "An ORF caller finds stretches of DNA that, when translated, are not
4099 interrupted by stop codons. OrfM finds and prints these ORFs.")
4100 (home-page "https://github.com/wwood/OrfM")
4101 (license license:lgpl3+)))
4103 (define-public pplacer
4104 (let ((commit "g807f6f3"))
4107 ;; The commit should be updated with each version change.
4108 (version "1.1.alpha19")
4112 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4114 (file-name (string-append name "-" version ".tar.gz"))
4116 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4117 (build-system ocaml-build-system)
4119 `(#:ocaml ,ocaml-4.01
4120 #:findlib ,ocaml4.01-findlib
4121 #:modules ((guix build ocaml-build-system)
4125 (modify-phases %standard-phases
4127 (add-after 'unpack 'replace-bundled-cddlib
4128 (lambda* (#:key inputs #:allow-other-keys)
4129 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4130 (local-dir "cddlib_guix"))
4132 (with-directory-excursion local-dir
4133 (system* "tar" "xvf" cddlib-src))
4134 (let ((cddlib-src-folder
4135 (string-append local-dir "/"
4136 (list-ref (scandir local-dir) 2)
4141 (string-append "cdd_src/" (basename file))))
4142 (find-files cddlib-src-folder ".*[ch]$")))
4144 (add-after 'unpack 'fix-makefile
4146 ;; Remove system calls to 'git'.
4147 (substitute* "Makefile"
4148 (("^DESCRIPT:=pplacer-.*")
4150 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4151 (substitute* "myocamlbuild.ml"
4152 (("git describe --tags --long .*\\\" with")
4154 "echo -n v" ,version "-" ,commit "\" with")))
4157 (lambda* (#:key outputs #:allow-other-keys)
4158 (let* ((out (assoc-ref outputs "out"))
4159 (bin (string-append out "/bin")))
4160 (copy-recursively "bin" bin))
4165 ("ocaml-ounit" ,ocaml4.01-ounit)
4166 ("ocaml-batteries" ,ocaml4.01-batteries)
4167 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4168 ("ocaml-csv" ,ocaml4.01-csv)
4169 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4170 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4171 ("ocaml-mcl" ,ocaml4.01-mcl)
4172 ("ocaml-gsl" ,ocaml4.01-gsl)
4173 ("cddlib-src" ,(package-source cddlib))))
4175 `(("pplacer-scripts" ,pplacer-scripts)))
4176 (synopsis "Phylogenetic placement of biological sequences")
4178 "Pplacer places query sequences on a fixed reference phylogenetic tree
4179 to maximize phylogenetic likelihood or posterior probability according to a
4180 reference alignment. Pplacer is designed to be fast, to give useful
4181 information about uncertainty, and to offer advanced visualization and
4182 downstream analysis.")
4183 (home-page "http://matsen.fhcrc.org/pplacer")
4184 (license license:gpl3))))
4186 ;; This package is installed alongside 'pplacer'. It is a separate package so
4187 ;; that it can use the python-build-system for the scripts that are
4188 ;; distributed alongside the main OCaml binaries.
4189 (define pplacer-scripts
4192 (name "pplacer-scripts")
4193 (build-system python-build-system)
4195 `(#:python ,python-2
4197 (modify-phases %standard-phases
4198 (add-after 'unpack 'enter-scripts-dir
4199 (lambda _ (chdir "scripts")))
4202 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4203 (add-after 'install 'wrap-executables
4204 (lambda* (#:key inputs outputs #:allow-other-keys)
4205 (let* ((out (assoc-ref outputs "out"))
4206 (bin (string-append out "/bin")))
4207 (let ((path (string-append
4208 (assoc-ref inputs "hmmer") "/bin:"
4209 (assoc-ref inputs "infernal") "/bin")))
4211 (wrap-program (string-append bin "/refpkg_align.py")
4212 `("PATH" ":" prefix (,path))))
4213 (let ((path (string-append
4214 (assoc-ref inputs "hmmer") "/bin")))
4215 (wrap-program (string-append bin "/hrefpkg_query.py")
4216 `("PATH" ":" prefix (,path)))))
4219 `(("infernal" ,infernal)
4222 `(("python-biopython" ,python2-biopython)
4223 ("taxtastic" ,taxtastic)))
4224 (synopsis "Pplacer Python scripts")))
4226 (define-public python2-pbcore
4228 (name "python2-pbcore")
4232 (uri (pypi-uri "pbcore" version))
4235 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4236 (build-system python-build-system)
4237 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4239 `(("python-cython" ,python2-cython)
4240 ("python-numpy" ,python2-numpy)
4241 ("python-pysam" ,python2-pysam)
4242 ("python-h5py" ,python2-h5py)))
4244 `(("python-nose" ,python2-nose)
4245 ("python-sphinx" ,python2-sphinx)
4246 ("python-pyxb" ,python2-pyxb)))
4247 (home-page "http://pacificbiosciences.github.io/pbcore/")
4248 (synopsis "Library for reading and writing PacBio data files")
4250 "The pbcore package provides Python APIs for interacting with PacBio data
4251 files and writing bioinformatics applications.")
4252 (license license:bsd-3)))
4254 (define-public python2-warpedlmm
4256 (name "python2-warpedlmm")
4262 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4266 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4267 (build-system python-build-system)
4269 `(#:python ,python-2)) ; requires Python 2.7
4271 `(("python-scipy" ,python2-scipy)
4272 ("python-numpy" ,python2-numpy)
4273 ("python-matplotlib" ,python2-matplotlib)
4274 ("python-fastlmm" ,python2-fastlmm)
4275 ("python-pandas" ,python2-pandas)
4276 ("python-pysnptools" ,python2-pysnptools)))
4278 `(("python-mock" ,python2-mock)
4279 ("python-nose" ,python2-nose)
4281 (home-page "https://github.com/PMBio/warpedLMM")
4282 (synopsis "Implementation of warped linear mixed models")
4284 "WarpedLMM is a Python implementation of the warped linear mixed model,
4285 which automatically learns an optimal warping function (or transformation) for
4286 the phenotype as it models the data.")
4287 (license license:asl2.0)))
4289 (define-public pbtranscript-tofu
4290 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4292 (name "pbtranscript-tofu")
4293 (version (string-append "2.2.3." (string-take commit 7)))
4297 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4299 (file-name (string-append name "-" version "-checkout"))
4302 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4303 (modules '((guix build utils)))
4306 ;; remove bundled Cython sources
4307 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4309 (build-system python-build-system)
4311 `(#:python ,python-2
4312 ;; FIXME: Tests fail with "No such file or directory:
4313 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4316 (modify-phases %standard-phases
4317 (add-after 'unpack 'enter-directory
4319 (chdir "pbtranscript-tofu/pbtranscript/")
4321 ;; With setuptools version 18.0 and later this setup.py hack causes
4322 ;; a build error, so we disable it.
4323 (add-after 'enter-directory 'patch-setuppy
4325 (substitute* "setup.py"
4326 (("if 'setuptools.extension' in sys.modules:")
4330 `(("python-numpy" ,python2-numpy)
4331 ("python-bx-python" ,python2-bx-python)
4332 ("python-networkx" ,python2-networkx)
4333 ("python-scipy" ,python2-scipy)
4334 ("python-pbcore" ,python2-pbcore)
4335 ("python-h5py" ,python2-h5py)))
4337 `(("python-cython" ,python2-cython)
4338 ("python-nose" ,python2-nose)))
4339 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4340 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4342 "pbtranscript-tofu contains scripts to analyze transcriptome data
4343 generated using the PacBio Iso-Seq protocol.")
4344 (license license:bsd-3))))
4346 (define-public prank
4353 "http://wasabiapp.org/download/prank/prank.source."
4357 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4358 (build-system gnu-build-system)
4361 (modify-phases %standard-phases
4362 (add-after 'unpack 'enter-src-dir
4366 (add-after 'unpack 'remove-m64-flag
4367 ;; Prank will build with the correct 'bit-ness' without this flag
4368 ;; and this allows building on 32-bit machines.
4369 (lambda _ (substitute* "src/Makefile"
4374 (lambda* (#:key outputs #:allow-other-keys)
4375 (let* ((out (assoc-ref outputs "out"))
4376 (bin (string-append out "/bin"))
4377 (man (string-append out "/share/man/man1"))
4378 (path (string-append
4379 (assoc-ref %build-inputs "mafft") "/bin:"
4380 (assoc-ref %build-inputs "exonerate") "/bin:"
4381 (assoc-ref %build-inputs "bppsuite") "/bin")))
4382 (install-file "prank" bin)
4383 (wrap-program (string-append bin "/prank")
4384 `("PATH" ":" prefix (,path)))
4385 (install-file "prank.1" man))
4389 ("exonerate" ,exonerate)
4390 ("bppsuite" ,bppsuite)))
4391 (home-page "http://wasabiapp.org/software/prank/")
4392 (synopsis "Probabilistic multiple sequence alignment program")
4394 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4395 codon and amino-acid sequences. It is based on a novel algorithm that treats
4396 insertions correctly and avoids over-estimation of the number of deletion
4397 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4398 in phylogenetics and correctly takes into account the evolutionary distances
4399 between sequences. Lastly, PRANK allows for defining a potential structure
4400 for sequences to be aligned and then, simultaneously with the alignment,
4401 predicts the locations of structural units in the sequences.")
4402 (license license:gpl2+)))
4404 (define-public proteinortho
4406 (name "proteinortho")
4413 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4414 version "_src.tar.gz"))
4417 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4418 (build-system gnu-build-system)
4420 `(#:test-target "test"
4422 (modify-phases %standard-phases
4424 ;; There is no configure script, so we modify the Makefile directly.
4425 (lambda* (#:key outputs #:allow-other-keys)
4426 (substitute* "Makefile"
4429 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4431 (add-before 'install 'make-install-directory
4432 ;; The install directory is not created during 'make install'.
4433 (lambda* (#:key outputs #:allow-other-keys)
4434 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4436 (add-after 'install 'wrap-programs
4437 (lambda* (#:key inputs outputs #:allow-other-keys)
4438 (let* ((path (getenv "PATH"))
4439 (out (assoc-ref outputs "out"))
4440 (binary (string-append out "/bin/proteinortho5.pl")))
4441 (wrap-program binary `("PATH" ":" prefix (,path))))
4445 ("python" ,python-2)
4446 ("blast+" ,blast+)))
4447 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4448 (synopsis "Detect orthologous genes across species")
4450 "Proteinortho is a tool to detect orthologous genes across different
4451 species. For doing so, it compares similarities of given gene sequences and
4452 clusters them to find significant groups. The algorithm was designed to handle
4453 large-scale data and can be applied to hundreds of species at once.")
4454 (license license:gpl2+)))
4456 (define-public pyicoteo
4463 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4464 "pyicoteo/get/v" version ".tar.bz2"))
4465 (file-name (string-append name "-" version ".tar.bz2"))
4468 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4469 (build-system python-build-system)
4471 `(#:python ,python-2 ; does not work with Python 3
4472 #:tests? #f)) ; there are no tests
4474 `(("python2-matplotlib" ,python2-matplotlib)))
4475 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4476 (synopsis "Analyze high-throughput genetic sequencing data")
4478 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4479 sequencing data. It works with genomic coordinates. There are currently six
4480 different command-line tools:
4483 @item pyicoregion: for generating exploratory regions automatically;
4484 @item pyicoenrich: for differential enrichment between two conditions;
4485 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4486 @item pyicos: for genomic coordinates manipulation;
4487 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4488 @item pyicount: to count how many reads from N experiment files overlap in a
4490 @item pyicotrocol: to combine operations from pyicoteo.
4492 (license license:gpl3+)))
4494 (define-public prodigal
4501 "https://github.com/hyattpd/Prodigal/archive/v"
4503 (file-name (string-append name "-" version ".tar.gz"))
4506 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4507 (build-system gnu-build-system)
4509 `(#:tests? #f ;no check target
4510 #:make-flags (list (string-append "INSTALLDIR="
4511 (assoc-ref %outputs "out")
4514 (modify-phases %standard-phases
4515 (delete 'configure))))
4516 (home-page "http://prodigal.ornl.gov")
4517 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4519 "Prodigal runs smoothly on finished genomes, draft genomes, and
4520 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4521 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4522 partial genes, and identifies translation initiation sites.")
4523 (license license:gpl3+)))
4525 (define-public roary
4533 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4537 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4538 (build-system perl-build-system)
4541 (modify-phases %standard-phases
4546 ;; The tests are not run by default, so we run each test file
4548 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4550 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4551 (getenv "PERL5LIB")))
4552 (zero? (length (filter (lambda (file)
4553 (display file)(display "\n")
4554 (not (zero? (system* "perl" file))))
4555 (find-files "t" ".*\\.t$"))))))
4557 ;; There is no 'install' target in the Makefile.
4558 (lambda* (#:key outputs #:allow-other-keys)
4559 (let* ((out (assoc-ref outputs "out"))
4560 (bin (string-append out "/bin"))
4561 (perl (string-append out "/lib/perl5/site_perl"))
4562 (roary-plots "contrib/roary_plots"))
4565 (copy-recursively "bin" bin)
4566 (copy-recursively "lib" perl)
4568 (add-after 'install 'wrap-programs
4569 (lambda* (#:key inputs outputs #:allow-other-keys)
4570 (let* ((out (assoc-ref outputs "out"))
4571 (perl5lib (getenv "PERL5LIB"))
4572 (path (getenv "PATH")))
4573 (for-each (lambda (prog)
4574 (let ((binary (string-append out "/" prog)))
4575 (wrap-program binary
4576 `("PERL5LIB" ":" prefix
4577 (,(string-append perl5lib ":" out
4578 "/lib/perl5/site_perl"))))
4579 (wrap-program binary
4581 (,(string-append path ":" out "/bin"))))))
4582 (find-files "bin" ".*[^R]$"))
4584 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4585 (r-site-lib (getenv "R_LIBS_SITE"))
4587 (string-append (assoc-ref inputs "coreutils") "/bin")))
4589 `("R_LIBS_SITE" ":" prefix
4590 (,(string-append r-site-lib ":" out "/site-library/"))))
4593 (,(string-append coreutils-path ":" out "/bin"))))))
4596 `(("perl-env-path" ,perl-env-path)
4597 ("perl-test-files" ,perl-test-files)
4598 ("perl-test-most" ,perl-test-most)
4599 ("perl-test-output" ,perl-test-output)))
4601 `(("perl-array-utils" ,perl-array-utils)
4602 ("bioperl" ,bioperl-minimal)
4603 ("perl-digest-md5-file" ,perl-digest-md5-file)
4604 ("perl-exception-class" ,perl-exception-class)
4605 ("perl-file-find-rule" ,perl-file-find-rule)
4606 ("perl-file-grep" ,perl-file-grep)
4607 ("perl-file-slurper" ,perl-file-slurper)
4608 ("perl-file-which" ,perl-file-which)
4609 ("perl-graph" ,perl-graph)
4610 ("perl-graph-readwrite" ,perl-graph-readwrite)
4611 ("perl-log-log4perl" ,perl-log-log4perl)
4612 ("perl-moose" ,perl-moose)
4613 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4614 ("perl-text-csv" ,perl-text-csv)
4615 ("bedtools" ,bedtools)
4619 ("parallel" ,parallel)
4622 ("fasttree" ,fasttree)
4626 ("r-minimal" ,r-minimal)
4627 ("r-ggplot2" ,r-ggplot2)
4628 ("coreutils" ,coreutils)))
4629 (home-page "http://sanger-pathogens.github.io/Roary")
4630 (synopsis "High speed stand-alone pan genome pipeline")
4632 "Roary is a high speed stand alone pan genome pipeline, which takes
4633 annotated assemblies in GFF3 format (produced by the Prokka program) and
4634 calculates the pan genome. Using a standard desktop PC, it can analyse
4635 datasets with thousands of samples, without compromising the quality of the
4636 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4637 single processor. Roary is not intended for metagenomics or for comparing
4638 extremely diverse sets of genomes.")
4639 (license license:gpl3)))
4641 (define-public raxml
4650 "https://github.com/stamatak/standard-RAxML/archive/v"
4652 (file-name (string-append name "-" version ".tar.gz"))
4655 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4656 (build-system gnu-build-system)
4658 `(#:tests? #f ; There are no tests.
4659 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4660 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4662 (modify-phases %standard-phases
4665 (lambda* (#:key outputs #:allow-other-keys)
4666 (let* ((out (assoc-ref outputs "out"))
4667 (bin (string-append out "/bin"))
4668 (executable "raxmlHPC-HYBRID"))
4669 (install-file executable bin)
4670 (symlink (string-append bin "/" executable) "raxml"))
4673 `(("openmpi" ,openmpi)))
4674 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4675 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4677 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4679 ;; The source includes x86 specific code
4680 (supported-systems '("x86_64-linux" "i686-linux"))
4681 (license license:gpl2+)))
4691 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4694 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4695 (patches (search-patches "rsem-makefile.patch"))
4696 (modules '((guix build utils)))
4699 ;; remove bundled copy of boost
4700 (delete-file-recursively "boost")
4702 (build-system gnu-build-system)
4704 `(#:tests? #f ;no "check" target
4706 (modify-phases %standard-phases
4707 ;; No "configure" script.
4708 ;; Do not build bundled samtools library.
4711 (substitute* "Makefile"
4712 (("^all : sam/libbam.a") "all : "))
4715 (lambda* (#:key outputs #:allow-other-keys)
4716 (let* ((out (string-append (assoc-ref outputs "out")))
4717 (bin (string-append out "/bin/"))
4718 (perl (string-append out "/lib/perl5/site_perl")))
4721 (for-each (lambda (file)
4722 (install-file file bin))
4723 (find-files "." "rsem-.*"))
4724 (install-file "rsem_perl_utils.pm" perl))
4727 'install 'wrap-program
4728 (lambda* (#:key outputs #:allow-other-keys)
4729 (let ((out (assoc-ref outputs "out")))
4730 (for-each (lambda (prog)
4731 (wrap-program (string-append out "/bin/" prog)
4732 `("PERL5LIB" ":" prefix
4733 (,(string-append out "/lib/perl5/site_perl")))))
4734 '("rsem-plot-transcript-wiggles"
4735 "rsem-calculate-expression"
4736 "rsem-generate-ngvector"
4738 "rsem-prepare-reference")))
4742 ("ncurses" ,ncurses)
4743 ("r-minimal" ,r-minimal)
4745 ("samtools" ,samtools-0.1)
4747 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4748 (synopsis "Estimate gene expression levels from RNA-Seq data")
4750 "RSEM is a software package for estimating gene and isoform expression
4751 levels from RNA-Seq data. The RSEM package provides a user-friendly
4752 interface, supports threads for parallel computation of the EM algorithm,
4753 single-end and paired-end read data, quality scores, variable-length reads and
4754 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4755 interval estimates for expression levels. For visualization, it can generate
4756 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4757 (license license:gpl3+)))
4759 (define-public rseqc
4767 (string-append "mirror://sourceforge/rseqc/"
4768 "RSeQC-" version ".tar.gz"))
4770 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4771 (modules '((guix build utils)))
4774 ;; remove bundled copy of pysam
4775 (delete-file-recursively "lib/pysam")
4776 (substitute* "setup.py"
4777 ;; remove dependency on outdated "distribute" module
4778 (("^from distribute_setup import use_setuptools") "")
4779 (("^use_setuptools\\(\\)") "")
4780 ;; do not use bundled copy of pysam
4781 (("^have_pysam = False") "have_pysam = True"))))))
4782 (build-system python-build-system)
4783 (arguments `(#:python ,python-2))
4785 `(("python-cython" ,python2-cython)
4786 ("python-pysam" ,python2-pysam)
4787 ("python-numpy" ,python2-numpy)
4790 `(("python-nose" ,python2-nose)))
4791 (home-page "http://rseqc.sourceforge.net/")
4792 (synopsis "RNA-seq quality control package")
4794 "RSeQC provides a number of modules that can comprehensively evaluate
4795 high throughput sequence data, especially RNA-seq data. Some basic modules
4796 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4797 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4798 distribution, coverage uniformity, strand specificity, etc.")
4799 (license license:gpl3+)))
4802 ;; There are no release tarballs. According to the installation
4803 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4804 ;; stable release is identified by this changeset ID.
4805 (let ((changeset "2329130")
4809 (version (string-append "0-" revision "." changeset))
4813 (url "https://bitbucket.org/libsleipnir/sleipnir")
4814 (changeset changeset)))
4815 (file-name (string-append name "-" version "-checkout"))
4818 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4819 (build-system gnu-build-system)
4821 `(#:modules ((srfi srfi-1)
4822 (guix build gnu-build-system)
4825 (let ((dirs '("SeekMiner"
4831 (modify-phases %standard-phases
4832 (add-before 'configure 'bootstrap
4834 (zero? (system* "bash" "gen_auto"))))
4835 (add-after 'build 'build-additional-tools
4836 (lambda* (#:key make-flags #:allow-other-keys)
4837 (every (lambda (dir)
4838 (with-directory-excursion (string-append "tools/" dir)
4839 (zero? (apply system* "make" make-flags))))
4841 (add-after 'install 'install-additional-tools
4842 (lambda* (#:key make-flags #:allow-other-keys)
4843 (fold (lambda (dir result)
4844 (with-directory-excursion (string-append "tools/" dir)
4846 (zero? (apply system*
4847 `("make" ,@make-flags "install"))))))
4853 ("readline" ,readline)
4854 ("gengetopt" ,gengetopt)
4855 ("log4cpp" ,log4cpp)))
4857 `(("autoconf" ,autoconf)
4858 ("automake" ,automake)
4860 (home-page "http://seek.princeton.edu")
4861 (synopsis "Gene co-expression search engine")
4863 "SEEK is a computational gene co-expression search engine. SEEK provides
4864 biologists with a way to navigate the massive human expression compendium that
4865 now contains thousands of expression datasets. SEEK returns a robust ranking
4866 of co-expressed genes in the biological area of interest defined by the user's
4867 query genes. It also prioritizes thousands of expression datasets according
4868 to the user's query of interest.")
4869 (license license:cc-by3.0))))
4871 (define-public samtools
4879 (string-append "mirror://sourceforge/samtools/samtools/"
4880 version "/samtools-" version ".tar.bz2"))
4883 "18acyqysbxpydlc44lqv2hpp57l06bs9a3yqmcvjk8va2xrrdc77"))))
4884 (build-system gnu-build-system)
4886 `(#:modules ((ice-9 ftw)
4888 (guix build gnu-build-system)
4890 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4891 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4893 (modify-phases %standard-phases
4894 (add-after 'unpack 'patch-tests
4896 (substitute* "test/test.pl"
4897 ;; The test script calls out to /bin/bash
4898 (("/bin/bash") (which "bash")))
4900 (add-after 'install 'install-library
4901 (lambda* (#:key outputs #:allow-other-keys)
4902 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4903 (install-file "libbam.a" lib)
4905 (add-after 'install 'install-headers
4906 (lambda* (#:key outputs #:allow-other-keys)
4907 (let ((include (string-append (assoc-ref outputs "out")
4908 "/include/samtools/")))
4909 (for-each (lambda (file)
4910 (install-file file include))
4911 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4913 (native-inputs `(("pkg-config" ,pkg-config)))
4915 `(("htslib" ,htslib)
4916 ("ncurses" ,ncurses)
4920 (home-page "http://samtools.sourceforge.net")
4921 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4923 "Samtools implements various utilities for post-processing nucleotide
4924 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4925 variant calling (in conjunction with bcftools), and a simple alignment
4927 (license license:expat)))
4929 (define-public samtools-0.1
4930 ;; This is the most recent version of the 0.1 line of samtools. The input
4931 ;; and output formats differ greatly from that used and produced by samtools
4932 ;; 1.x and is still used in many bioinformatics pipelines.
4933 (package (inherit samtools)
4939 (string-append "mirror://sourceforge/samtools/samtools/"
4940 version "/samtools-" version ".tar.bz2"))
4942 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4944 `(#:tests? #f ;no "check" target
4945 ,@(substitute-keyword-arguments (package-arguments samtools)
4946 ((#:make-flags flags)
4947 `(cons "LIBCURSES=-lncurses" ,flags))
4949 `(modify-phases ,phases
4951 (lambda* (#:key outputs #:allow-other-keys)
4952 (let ((bin (string-append
4953 (assoc-ref outputs "out") "/bin")))
4955 (install-file "samtools" bin)
4957 (delete 'patch-tests)
4958 (delete 'configure))))))))
4960 (define-public mosaik
4961 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4966 ;; There are no release tarballs nor tags.
4969 (url "https://github.com/wanpinglee/MOSAIK.git")
4971 (file-name (string-append name "-" version))
4974 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4975 (build-system gnu-build-system)
4977 `(#:tests? #f ; no tests
4978 #:make-flags (list "CC=gcc")
4980 (modify-phases %standard-phases
4982 (lambda _ (chdir "src") #t))
4984 (lambda* (#:key outputs #:allow-other-keys)
4985 (let ((bin (string-append (assoc-ref outputs "out")
4988 (copy-recursively "../bin" bin)
4993 (supported-systems '("x86_64-linux"))
4994 (home-page "https://github.com/wanpinglee/MOSAIK")
4995 (synopsis "Map nucleotide sequence reads to reference genomes")
4997 "MOSAIK is a program for mapping second and third-generation sequencing
4998 reads to a reference genome. MOSAIK can align reads generated by all the
4999 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5000 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5001 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5002 ;; code released into the public domain:
5003 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5004 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5005 (license (list license:gpl2+ license:public-domain)))))
5007 (define-public ngs-sdk
5015 (string-append "https://github.com/ncbi/ngs/archive/"
5017 (file-name (string-append name "-" version ".tar.gz"))
5020 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5021 (build-system gnu-build-system)
5023 `(#:parallel-build? #f ; not supported
5024 #:tests? #f ; no "check" target
5026 (modify-phases %standard-phases
5028 (lambda* (#:key outputs #:allow-other-keys)
5029 (let ((out (assoc-ref outputs "out")))
5030 ;; Allow 'konfigure.perl' to find 'package.prl'.
5032 (string-append ".:" (getenv "PERL5LIB")))
5034 ;; The 'configure' script doesn't recognize things like
5035 ;; '--enable-fast-install'.
5036 (zero? (system* "./configure"
5037 (string-append "--build-prefix=" (getcwd) "/build")
5038 (string-append "--prefix=" out))))))
5039 (add-after 'unpack 'enter-dir
5040 (lambda _ (chdir "ngs-sdk") #t)))))
5041 (native-inputs `(("perl" ,perl)))
5042 ;; According to the test
5043 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5044 ;; in ngs-sdk/setup/konfigure.perl
5045 (supported-systems '("i686-linux" "x86_64-linux"))
5046 (home-page "https://github.com/ncbi/ngs")
5047 (synopsis "API for accessing Next Generation Sequencing data")
5049 "NGS is a domain-specific API for accessing reads, alignments and pileups
5050 produced from Next Generation Sequencing. The API itself is independent from
5051 any particular back-end implementation, and supports use of multiple back-ends
5053 (license license:public-domain)))
5055 (define-public java-ngs
5056 (package (inherit ngs-sdk)
5059 `(,@(substitute-keyword-arguments
5060 `(#:modules ((guix build gnu-build-system)
5064 ,@(package-arguments ngs-sdk))
5066 `(modify-phases ,phases
5067 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5069 `(("jdk" ,icedtea "jdk")
5070 ("ngs-sdk" ,ngs-sdk)))
5071 (synopsis "Java bindings for NGS SDK")))
5073 (define-public ncbi-vdb
5081 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5083 (file-name (string-append name "-" version ".tar.gz"))
5086 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5087 (build-system gnu-build-system)
5089 `(#:parallel-build? #f ; not supported
5090 #:tests? #f ; no "check" target
5092 (modify-phases %standard-phases
5093 (add-before 'configure 'set-perl-search-path
5095 ;; Work around "dotless @INC" build failure.
5097 (string-append (getcwd) "/setup:"
5098 (getenv "PERL5LIB")))
5101 (lambda* (#:key inputs outputs #:allow-other-keys)
5102 (let ((out (assoc-ref outputs "out")))
5103 ;; Override include path for libmagic
5104 (substitute* "setup/package.prl"
5105 (("name => 'magic', Include => '/usr/include'")
5106 (string-append "name=> 'magic', Include => '"
5107 (assoc-ref inputs "libmagic")
5110 ;; Install kdf5 library (needed by sra-tools)
5111 (substitute* "build/Makefile.install"
5112 (("LIBRARIES_TO_INSTALL =")
5113 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5115 (substitute* "build/Makefile.env"
5116 (("CFLAGS =" prefix)
5117 (string-append prefix "-msse2 ")))
5119 ;; Override search path for ngs-java
5120 (substitute* "setup/package.prl"
5121 (("/usr/local/ngs/ngs-java")
5122 (assoc-ref inputs "java-ngs")))
5124 ;; The 'configure' script doesn't recognize things like
5125 ;; '--enable-fast-install'.
5128 (string-append "--build-prefix=" (getcwd) "/build")
5129 (string-append "--prefix=" (assoc-ref outputs "out"))
5130 (string-append "--debug")
5131 (string-append "--with-xml2-prefix="
5132 (assoc-ref inputs "libxml2"))
5133 (string-append "--with-ngs-sdk-prefix="
5134 (assoc-ref inputs "ngs-sdk"))
5135 (string-append "--with-hdf5-prefix="
5136 (assoc-ref inputs "hdf5")))))))
5137 (add-after 'install 'install-interfaces
5138 (lambda* (#:key outputs #:allow-other-keys)
5139 ;; Install interface libraries. On i686 the interface libraries
5140 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5141 ;; architecture name ("i386") instead of the target system prefix
5143 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5144 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5145 ,(system->linux-architecture
5146 (or (%current-target-system)
5149 (string-append (assoc-ref outputs "out")
5151 ;; Install interface headers
5152 (copy-recursively "interfaces"
5153 (string-append (assoc-ref outputs "out")
5156 ;; These files are needed by sra-tools.
5157 (add-after 'install 'install-configuration-files
5158 (lambda* (#:key outputs #:allow-other-keys)
5159 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5161 (install-file "libs/kfg/default.kfg" target)
5162 (install-file "libs/kfg/certs.kfg" target))
5165 `(("libxml2" ,libxml2)
5166 ("ngs-sdk" ,ngs-sdk)
5167 ("java-ngs" ,java-ngs)
5170 (native-inputs `(("perl" ,perl)))
5171 ;; NCBI-VDB requires SSE capability.
5172 (supported-systems '("i686-linux" "x86_64-linux"))
5173 (home-page "https://github.com/ncbi/ncbi-vdb")
5174 (synopsis "Database engine for genetic information")
5176 "The NCBI-VDB library implements a highly compressed columnar data
5177 warehousing engine that is most often used to store genetic information.
5178 Databases are stored in a portable image within the file system, and can be
5179 accessed/downloaded on demand across HTTP.")
5180 (license license:public-domain)))
5182 (define-public plink
5190 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5191 version "-src.zip"))
5193 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5194 (patches (search-patches "plink-1.07-unclobber-i.patch"
5195 "plink-endian-detection.patch"))))
5196 (build-system gnu-build-system)
5198 '(#:tests? #f ;no "check" target
5199 #:make-flags (list (string-append "LIB_LAPACK="
5200 (assoc-ref %build-inputs "lapack")
5201 "/lib/liblapack.so")
5204 ;; disable phoning home
5207 (modify-phases %standard-phases
5208 ;; no "configure" script
5211 (lambda* (#:key outputs #:allow-other-keys)
5212 (let ((bin (string-append (assoc-ref outputs "out")
5214 (install-file "plink" bin)
5218 ("lapack" ,lapack)))
5220 `(("unzip" ,unzip)))
5221 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5222 (synopsis "Whole genome association analysis toolset")
5224 "PLINK is a whole genome association analysis toolset, designed to
5225 perform a range of basic, large-scale analyses in a computationally efficient
5226 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5227 so there is no support for steps prior to this (e.g. study design and
5228 planning, generating genotype or CNV calls from raw data). Through
5229 integration with gPLINK and Haploview, there is some support for the
5230 subsequent visualization, annotation and storage of results.")
5231 ;; Code is released under GPLv2, except for fisher.h, which is under
5233 (license (list license:gpl2 license:lgpl2.1+))))
5235 (define-public plink-ng
5236 (package (inherit plink)
5242 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5244 (file-name (string-append name "-" version ".tar.gz"))
5246 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5247 (build-system gnu-build-system)
5249 '(#:tests? #f ;no "check" target
5250 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5251 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5253 "-f" "Makefile.std")
5255 (modify-phases %standard-phases
5256 (add-after 'unpack 'chdir
5257 (lambda _ (chdir "1.9") #t))
5258 (delete 'configure) ; no "configure" script
5260 (lambda* (#:key outputs #:allow-other-keys)
5261 (let ((bin (string-append (assoc-ref outputs "out")
5263 (install-file "plink" bin)
5268 ("openblas" ,openblas)))
5269 (home-page "https://www.cog-genomics.org/plink/")
5270 (license license:gpl3+)))
5272 (define-public smithlab-cpp
5273 (let ((revision "1")
5274 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5276 (name "smithlab-cpp")
5277 (version (string-append "0." revision "." (string-take commit 7)))
5281 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5283 (file-name (string-append name "-" version "-checkout"))
5286 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5287 (build-system gnu-build-system)
5289 `(#:modules ((guix build gnu-build-system)
5292 #:tests? #f ;no "check" target
5294 (modify-phases %standard-phases
5295 (add-after 'unpack 'use-samtools-headers
5297 (substitute* '("SAM.cpp"
5299 (("sam.h") "samtools/sam.h"))
5302 (lambda* (#:key outputs #:allow-other-keys)
5303 (let* ((out (assoc-ref outputs "out"))
5304 (lib (string-append out "/lib"))
5305 (include (string-append out "/include/smithlab-cpp")))
5308 (for-each (cut install-file <> lib)
5309 (find-files "." "\\.o$"))
5310 (for-each (cut install-file <> include)
5311 (find-files "." "\\.hpp$")))
5313 (delete 'configure))))
5315 `(("samtools" ,samtools-0.1)
5317 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5318 (synopsis "C++ helper library for functions used in Smith lab projects")
5320 "Smithlab CPP is a C++ library that includes functions used in many of
5321 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5322 structures, classes for genomic regions, mapped sequencing reads, etc.")
5323 (license license:gpl3+))))
5325 (define-public preseq
5331 (uri (string-append "https://github.com/smithlabcode/"
5332 "preseq/archive/v" version ".tar.gz"))
5333 (file-name (string-append name "-" version ".tar.gz"))
5335 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5336 (modules '((guix build utils)))
5338 ;; Remove bundled samtools.
5339 '(delete-file-recursively "samtools"))))
5340 (build-system gnu-build-system)
5342 `(#:tests? #f ;no "check" target
5344 (modify-phases %standard-phases
5345 (delete 'configure))
5347 (list (string-append "PREFIX="
5348 (assoc-ref %outputs "out"))
5349 (string-append "LIBBAM="
5350 (assoc-ref %build-inputs "samtools")
5352 (string-append "SMITHLAB_CPP="
5353 (assoc-ref %build-inputs "smithlab-cpp")
5356 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5359 ("samtools" ,samtools-0.1)
5360 ("smithlab-cpp" ,smithlab-cpp)
5362 (home-page "http://smithlabresearch.org/software/preseq/")
5363 (synopsis "Program for analyzing library complexity")
5365 "The preseq package is aimed at predicting and estimating the complexity
5366 of a genomic sequencing library, equivalent to predicting and estimating the
5367 number of redundant reads from a given sequencing depth and how many will be
5368 expected from additional sequencing using an initial sequencing experiment.
5369 The estimates can then be used to examine the utility of further sequencing,
5370 optimize the sequencing depth, or to screen multiple libraries to avoid low
5371 complexity samples.")
5372 (license license:gpl3+)))
5374 (define-public python-screed
5376 (name "python-screed")
5381 (uri (pypi-uri "screed" version))
5384 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5385 (build-system python-build-system)
5388 (modify-phases %standard-phases
5391 (setenv "PYTHONPATH"
5392 (string-append (getenv "PYTHONPATH") ":."))
5393 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5395 `(("python-nose" ,python-nose)))
5397 `(("python-bz2file" ,python-bz2file)))
5398 (home-page "https://github.com/dib-lab/screed/")
5399 (synopsis "Short read sequence database utilities")
5400 (description "Screed parses FASTA and FASTQ files and generates databases.
5401 Values such as sequence name, sequence description, sequence quality and the
5402 sequence itself can be retrieved from these databases.")
5403 (license license:bsd-3)))
5405 (define-public python2-screed
5406 (package-with-python2 python-screed))
5408 (define-public sra-tools
5416 (string-append "https://github.com/ncbi/sra-tools/archive/"
5418 (file-name (string-append name "-" version ".tar.gz"))
5421 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5422 (build-system gnu-build-system)
5424 `(#:parallel-build? #f ; not supported
5425 #:tests? #f ; no "check" target
5427 (list (string-append "DEFAULT_CRT="
5428 (assoc-ref %build-inputs "ncbi-vdb")
5430 (string-append "DEFAULT_KFG="
5431 (assoc-ref %build-inputs "ncbi-vdb")
5433 (string-append "VDB_LIBDIR="
5434 (assoc-ref %build-inputs "ncbi-vdb")
5435 ,(if (string-prefix? "x86_64"
5436 (or (%current-target-system)
5441 (modify-phases %standard-phases
5442 (add-before 'configure 'set-perl-search-path
5444 ;; Work around "dotless @INC" build failure.
5446 (string-append (getcwd) "/setup:"
5447 (getenv "PERL5LIB")))
5450 (lambda* (#:key inputs outputs #:allow-other-keys)
5451 ;; The build system expects a directory containing the sources and
5452 ;; raw build output of ncbi-vdb, including files that are not
5453 ;; installed. Since we are building against an installed version of
5454 ;; ncbi-vdb, the following modifications are needed.
5455 (substitute* "setup/konfigure.perl"
5456 ;; Make the configure script look for the "ilib" directory of
5457 ;; "ncbi-vdb" without first checking for the existence of a
5458 ;; matching library in its "lib" directory.
5459 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5460 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5461 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5462 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5463 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5466 (substitute* "tools/copycat/Makefile"
5467 (("smagic-static") "lmagic"))
5469 ;; The 'configure' script doesn't recognize things like
5470 ;; '--enable-fast-install'.
5473 (string-append "--build-prefix=" (getcwd) "/build")
5474 (string-append "--prefix=" (assoc-ref outputs "out"))
5475 (string-append "--debug")
5476 (string-append "--with-fuse-prefix="
5477 (assoc-ref inputs "fuse"))
5478 (string-append "--with-magic-prefix="
5479 (assoc-ref inputs "libmagic"))
5480 ;; TODO: building with libxml2 fails with linker errors
5481 ;; (string-append "--with-xml2-prefix="
5482 ;; (assoc-ref inputs "libxml2"))
5483 (string-append "--with-ncbi-vdb-sources="
5484 (assoc-ref inputs "ncbi-vdb"))
5485 (string-append "--with-ncbi-vdb-build="
5486 (assoc-ref inputs "ncbi-vdb"))
5487 (string-append "--with-ngs-sdk-prefix="
5488 (assoc-ref inputs "ngs-sdk"))
5489 (string-append "--with-hdf5-prefix="
5490 (assoc-ref inputs "hdf5"))))))
5491 ;; This version of sra-tools fails to build with glibc because of a
5492 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5493 ;; contains a definition of "canonicalize", so we rename it.
5495 ;; See upstream bug report:
5496 ;; https://github.com/ncbi/sra-tools/issues/67
5497 (add-after 'unpack 'patch-away-glibc-conflict
5499 (substitute* "tools/bam-loader/bam.c"
5500 (("canonicalize\\(" line)
5501 (string-append "sra_tools_" line)))
5503 (native-inputs `(("perl" ,perl)))
5505 `(("ngs-sdk" ,ngs-sdk)
5506 ("ncbi-vdb" ,ncbi-vdb)
5511 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5512 (synopsis "Tools and libraries for reading and writing sequencing data")
5514 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5515 reading of sequencing files from the Sequence Read Archive (SRA) database and
5516 writing files into the .sra format.")
5517 (license license:public-domain)))
5519 (define-public seqan
5525 (uri (string-append "http://packages.seqan.de/seqan-library/"
5526 "seqan-library-" version ".tar.bz2"))
5529 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5530 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5531 ;; makes sense to split the outputs.
5532 (outputs '("out" "doc"))
5533 (build-system trivial-build-system)
5535 `(#:modules ((guix build utils))
5538 (use-modules (guix build utils))
5539 (let ((tar (assoc-ref %build-inputs "tar"))
5540 (bzip (assoc-ref %build-inputs "bzip2"))
5541 (out (assoc-ref %outputs "out"))
5542 (doc (assoc-ref %outputs "doc")))
5543 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5544 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5545 (chdir (string-append "seqan-library-" ,version))
5546 (copy-recursively "include" (string-append out "/include"))
5547 (copy-recursively "share" (string-append doc "/share"))))))
5549 `(("source" ,source)
5552 (home-page "http://www.seqan.de")
5553 (synopsis "Library for nucleotide sequence analysis")
5555 "SeqAn is a C++ library of efficient algorithms and data structures for
5556 the analysis of sequences with the focus on biological data. It contains
5557 algorithms and data structures for string representation and their
5558 manipulation, online and indexed string search, efficient I/O of
5559 bioinformatics file formats, sequence alignment, and more.")
5560 (license license:bsd-3)))
5562 (define-public seqmagick
5569 (uri (pypi-uri "seqmagick" version))
5572 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5573 (build-system python-build-system)
5575 `(("python-biopython" ,python-biopython)))
5577 `(("python-nose" ,python-nose)))
5578 (home-page "https://github.com/fhcrc/seqmagick")
5579 (synopsis "Tools for converting and modifying sequence files")
5581 "Bioinformaticians often have to convert sequence files between formats
5582 and do little manipulations on them, and it's not worth writing scripts for
5583 that. Seqmagick is a utility to expose the file format conversion in
5584 BioPython in a convenient way. Instead of having a big mess of scripts, there
5585 is one that takes arguments.")
5586 (license license:gpl3)))
5588 (define-public seqtk
5595 "https://github.com/lh3/seqtk/archive/v"
5597 (file-name (string-append name "-" version ".tar.gz"))
5600 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5601 (modules '((guix build utils)))
5604 ;; Remove extraneous header files, as is done in the seqtk
5606 (for-each (lambda (file) (delete-file file))
5607 (list "ksort.h" "kstring.h" "kvec.h"))
5609 (build-system gnu-build-system)
5612 (modify-phases %standard-phases
5615 ;; There are no tests, so we just run a sanity check.
5616 (lambda _ (zero? (system* "./seqtk" "seq"))))
5618 (lambda* (#:key outputs #:allow-other-keys)
5619 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5620 (install-file "seqtk" bin)))))))
5623 (home-page "https://github.com/lh3/seqtk")
5624 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5626 "Seqtk is a fast and lightweight tool for processing sequences in the
5627 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5628 optionally compressed by gzip.")
5629 (license license:expat)))
5631 (define-public snap-aligner
5633 (name "snap-aligner")
5634 (version "1.0beta.18")
5638 "https://github.com/amplab/snap/archive/v"
5640 (file-name (string-append name "-" version ".tar.gz"))
5643 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5644 (build-system gnu-build-system)
5647 (modify-phases %standard-phases
5649 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5651 (lambda* (#:key outputs #:allow-other-keys)
5652 (let* ((out (assoc-ref outputs "out"))
5653 (bin (string-append out "/bin")))
5654 (install-file "snap-aligner" bin)
5655 (install-file "SNAPCommand" bin)
5659 (home-page "http://snap.cs.berkeley.edu/")
5660 (synopsis "Short read DNA sequence aligner")
5662 "SNAP is a fast and accurate aligner for short DNA reads. It is
5663 optimized for modern read lengths of 100 bases or higher, and takes advantage
5664 of these reads to align data quickly through a hash-based indexing scheme.")
5665 ;; 32-bit systems are not supported by the unpatched code.
5666 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5667 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5668 ;; systems without a lot of memory cannot make good use of this program.
5669 (supported-systems '("x86_64-linux"))
5670 (license license:asl2.0)))
5672 (define-public sortmerna
5680 "https://github.com/biocore/sortmerna/archive/"
5682 (file-name (string-append name "-" version ".tar.gz"))
5685 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5686 (build-system gnu-build-system)
5687 (outputs '("out" ;for binaries
5688 "db")) ;for sequence databases
5691 (modify-phases %standard-phases
5693 (lambda* (#:key outputs #:allow-other-keys)
5694 (let* ((out (assoc-ref outputs "out"))
5695 (bin (string-append out "/bin"))
5696 (db (assoc-ref outputs "db"))
5698 (string-append db "/share/sortmerna/rRNA_databases")))
5699 (install-file "sortmerna" bin)
5700 (install-file "indexdb_rna" bin)
5701 (for-each (lambda (file)
5702 (install-file file share))
5703 (find-files "rRNA_databases" ".*fasta"))
5707 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5708 (synopsis "Biological sequence analysis tool for NGS reads")
5710 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5711 and operational taxonomic unit (OTU) picking of next generation
5712 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5713 allows for fast and sensitive analyses of nucleotide sequences. The main
5714 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5715 ;; The source includes x86 specific code
5716 (supported-systems '("x86_64-linux" "i686-linux"))
5717 (license license:lgpl3)))
5725 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5727 (file-name (string-append name "-" version ".tar.gz"))
5730 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5731 (modules '((guix build utils)))
5734 (substitute* "source/Makefile"
5736 ;; Remove pre-built binaries and bundled htslib sources.
5737 (delete-file-recursively "bin/MacOSX_x86_64")
5738 (delete-file-recursively "bin/Linux_x86_64")
5739 (delete-file-recursively "bin/Linux_x86_64_static")
5740 (delete-file-recursively "source/htslib")
5742 (build-system gnu-build-system)
5744 '(#:tests? #f ;no check target
5745 #:make-flags '("STAR")
5747 (modify-phases %standard-phases
5748 (add-after 'unpack 'enter-source-dir
5749 (lambda _ (chdir "source") #t))
5750 (add-after 'enter-source-dir 'make-reproducible
5752 (substitute* "Makefile"
5753 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5754 (string-append pre "Built with Guix" post)))))
5755 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5757 (substitute* "Makefile"
5758 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5760 (substitute* '("BAMfunctions.cpp"
5765 "bamRemoveDuplicates.cpp")
5766 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5767 (string-append "#include <" header ">")))
5768 (substitute* "IncludeDefine.h"
5769 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5770 (string-append "<" header ">")))
5773 (lambda* (#:key outputs #:allow-other-keys)
5774 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5775 (install-file "STAR" bin))
5777 (delete 'configure))))
5781 `(("htslib" ,htslib)
5783 (home-page "https://github.com/alexdobin/STAR")
5784 (synopsis "Universal RNA-seq aligner")
5786 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5787 based on a previously undescribed RNA-seq alignment algorithm that uses
5788 sequential maximum mappable seed search in uncompressed suffix arrays followed
5789 by seed clustering and stitching procedure. In addition to unbiased de novo
5790 detection of canonical junctions, STAR can discover non-canonical splices and
5791 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5793 ;; Only 64-bit systems are supported according to the README.
5794 (supported-systems '("x86_64-linux" "mips64el-linux"))
5795 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5796 (license license:gpl3+)))
5798 (define-public subread
5804 (uri (string-append "mirror://sourceforge/subread/subread-"
5805 version "/subread-" version "-source.tar.gz"))
5808 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5809 (build-system gnu-build-system)
5811 `(#:tests? #f ;no "check" target
5812 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5813 ;; optimizations by default, so we override these flags such that x86_64
5814 ;; flags are only added when the build target is an x86_64 system.
5816 (list (let ((system ,(or (%current-target-system)
5818 (flags '("-ggdb" "-fomit-frame-pointer"
5819 "-ffast-math" "-funroll-loops"
5820 "-fmessage-length=0"
5821 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5823 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5824 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5825 (if (string-prefix? "x86_64" system)
5826 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5827 (string-append "CCFLAGS=" (string-join flags))))
5828 "-f" "Makefile.Linux"
5829 "CC=gcc ${CCFLAGS}")
5831 (modify-phases %standard-phases
5832 (add-after 'unpack 'enter-dir
5833 (lambda _ (chdir "src") #t))
5835 (lambda* (#:key outputs #:allow-other-keys)
5836 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5838 (copy-recursively "../bin" bin))))
5839 ;; no "configure" script
5840 (delete 'configure))))
5841 (inputs `(("zlib" ,zlib)))
5842 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5843 (synopsis "Tool kit for processing next-gen sequencing data")
5845 "The subread package contains the following tools: subread aligner, a
5846 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5847 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5848 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5849 against local background noises.")
5850 (license license:gpl3+)))
5852 (define-public stringtie
5858 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5859 "stringtie-" version ".tar.gz"))
5862 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5863 (modules '((guix build utils)))
5866 (delete-file-recursively "samtools-0.1.18")
5868 (build-system gnu-build-system)
5870 `(#:tests? #f ;no test suite
5872 (modify-phases %standard-phases
5873 ;; no configure script
5875 (add-before 'build 'use-system-samtools
5877 (substitute* "Makefile"
5878 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5880 (substitute* '("gclib/GBam.h"
5882 (("#include \"(bam|sam|kstring).h\"" _ header)
5883 (string-append "#include <samtools/" header ".h>")))
5885 (add-after 'unpack 'remove-duplicate-typedef
5887 ;; This typedef conflicts with the typedef in
5888 ;; glibc-2.25/include/bits/types.h
5889 (substitute* "gclib/GThreads.h"
5890 (("typedef long long __intmax_t;") ""))
5893 (lambda* (#:key outputs #:allow-other-keys)
5894 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5895 (install-file "stringtie" bin)
5898 `(("samtools" ,samtools-0.1)
5900 (home-page "http://ccb.jhu.edu/software/stringtie/")
5901 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5903 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5904 alignments into potential transcripts. It uses a novel network flow algorithm
5905 as well as an optional de novo assembly step to assemble and quantitate
5906 full-length transcripts representing multiple splice variants for each gene
5907 locus. Its input can include not only the alignments of raw reads used by
5908 other transcript assemblers, but also alignments of longer sequences that have
5909 been assembled from those reads. To identify differentially expressed genes
5910 between experiments, StringTie's output can be processed either by the
5911 Cuffdiff or Ballgown programs.")
5912 (license license:artistic2.0)))
5914 (define-public taxtastic
5920 (uri (pypi-uri "taxtastic" version))
5923 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5924 (build-system python-build-system)
5926 `(#:python ,python-2
5928 (modify-phases %standard-phases
5931 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5933 `(("python-sqlalchemy" ,python2-sqlalchemy)
5934 ("python-decorator" ,python2-decorator)
5935 ("python-biopython" ,python2-biopython)
5936 ("python-pandas" ,python2-pandas)))
5937 (home-page "https://github.com/fhcrc/taxtastic")
5938 (synopsis "Tools for taxonomic naming and annotation")
5940 "Taxtastic is software written in python used to build and maintain
5941 reference packages i.e. collections of reference trees, reference alignments,
5942 profiles, and associated taxonomic information.")
5943 (license license:gpl3+)))
5945 (define-public vcftools
5952 "https://github.com/vcftools/vcftools/releases/download/v"
5953 version "/vcftools-" version ".tar.gz"))
5956 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5957 (build-system gnu-build-system)
5959 `(#:tests? #f ; no "check" target
5961 "CFLAGS=-O2" ; override "-m64" flag
5962 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5963 (string-append "MANDIR=" (assoc-ref %outputs "out")
5964 "/share/man/man1"))))
5966 `(("pkg-config" ,pkg-config)))
5970 (home-page "https://vcftools.github.io/")
5971 (synopsis "Tools for working with VCF files")
5973 "VCFtools is a program package designed for working with VCF files, such
5974 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5975 provide easily accessible methods for working with complex genetic variation
5976 data in the form of VCF files.")
5977 ;; The license is declared as LGPLv3 in the README and
5978 ;; at https://vcftools.github.io/license.html
5979 (license license:lgpl3)))
5981 (define-public infernal
5987 (uri (string-append "http://eddylab.org/software/infernal/"
5988 "infernal-" version ".tar.gz"))
5991 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5992 (build-system gnu-build-system)
5994 `(("perl" ,perl))) ; for tests
5995 (home-page "http://eddylab.org/infernal/")
5996 (synopsis "Inference of RNA alignments")
5997 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5998 searching DNA sequence databases for RNA structure and sequence similarities.
5999 It is an implementation of a special case of profile stochastic context-free
6000 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6001 profile, but it scores a combination of sequence consensus and RNA secondary
6002 structure consensus, so in many cases, it is more capable of identifying RNA
6003 homologs that conserve their secondary structure more than their primary
6005 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6006 (supported-systems '("i686-linux" "x86_64-linux"))
6007 (license license:bsd-3)))
6009 (define-public r-centipede
6011 (name "r-centipede")
6015 (uri (string-append "http://download.r-forge.r-project.org/"
6016 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6019 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6020 (build-system r-build-system)
6021 (home-page "http://centipede.uchicago.edu/")
6022 (synopsis "Predict transcription factor binding sites")
6024 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6025 of the genome that are bound by particular transcription factors. It starts
6026 by identifying a set of candidate binding sites, and then aims to classify the
6027 sites according to whether each site is bound or not bound by a transcription
6028 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6029 between two different types of motif instances using as much relevant
6030 information as possible.")
6031 (license (list license:gpl2+ license:gpl3+))))
6033 (define-public r-vegan
6040 (uri (cran-uri "vegan" version))
6043 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
6044 (build-system r-build-system)
6046 `(("gfortran" ,gfortran)))
6048 `(("r-cluster" ,r-cluster)
6049 ("r-lattice" ,r-lattice)
6052 ("r-permute" ,r-permute)))
6053 (home-page "https://cran.r-project.org/web/packages/vegan")
6054 (synopsis "Functions for community ecology")
6056 "The vegan package provides tools for descriptive community ecology. It
6057 has most basic functions of diversity analysis, community ordination and
6058 dissimilarity analysis. Most of its multivariate tools can be used for other
6059 data types as well.")
6060 (license license:gpl2+)))
6062 (define-public r-annotate
6069 (uri (bioconductor-uri "annotate" version))
6072 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
6073 (build-system r-build-system)
6075 `(("r-annotationdbi" ,r-annotationdbi)
6076 ("r-biobase" ,r-biobase)
6077 ("r-biocgenerics" ,r-biocgenerics)
6079 ("r-rcurl" ,r-rcurl)
6081 ("r-xtable" ,r-xtable)))
6083 "https://bioconductor.org/packages/annotate")
6084 (synopsis "Annotation for microarrays")
6085 (description "This package provides R environments for the annotation of
6087 (license license:artistic2.0)))
6089 (define-public r-copynumber
6091 (name "r-copynumber")
6095 (uri (bioconductor-uri "copynumber" version))
6098 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6099 (build-system r-build-system)
6101 `(("r-s4vectors" ,r-s4vectors)
6102 ("r-iranges" ,r-iranges)
6103 ("r-genomicranges" ,r-genomicranges)
6104 ("r-biocgenerics" ,r-biocgenerics)))
6105 (home-page "https://bioconductor.org/packages/copynumber")
6106 (synopsis "Segmentation of single- and multi-track copy number data")
6108 "This package segments single- and multi-track copy number data by a
6109 penalized least squares regression method.")
6110 (license license:artistic2.0)))
6112 (define-public r-geneplotter
6114 (name "r-geneplotter")
6119 (uri (bioconductor-uri "geneplotter" version))
6122 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6123 (build-system r-build-system)
6125 `(("r-annotate" ,r-annotate)
6126 ("r-annotationdbi" ,r-annotationdbi)
6127 ("r-biobase" ,r-biobase)
6128 ("r-biocgenerics" ,r-biocgenerics)
6129 ("r-lattice" ,r-lattice)
6130 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6131 (home-page "https://bioconductor.org/packages/geneplotter")
6132 (synopsis "Graphics functions for genomic data")
6134 "This package provides functions for plotting genomic data.")
6135 (license license:artistic2.0)))
6137 (define-public r-genefilter
6139 (name "r-genefilter")
6144 (uri (bioconductor-uri "genefilter" version))
6147 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6148 (build-system r-build-system)
6150 `(("gfortran" ,gfortran)))
6152 `(("r-annotate" ,r-annotate)
6153 ("r-annotationdbi" ,r-annotationdbi)
6154 ("r-biobase" ,r-biobase)
6155 ("r-s4vectors" ,r-s4vectors)
6156 ("r-survival" ,r-survival)))
6157 (home-page "https://bioconductor.org/packages/genefilter")
6158 (synopsis "Filter genes from high-throughput experiments")
6160 "This package provides basic functions for filtering genes from
6161 high-throughput sequencing experiments.")
6162 (license license:artistic2.0)))
6164 (define-public r-deseq2
6171 (uri (bioconductor-uri "DESeq2" version))
6174 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6175 (properties `((upstream-name . "DESeq2")))
6176 (build-system r-build-system)
6178 `(("r-biobase" ,r-biobase)
6179 ("r-biocgenerics" ,r-biocgenerics)
6180 ("r-biocparallel" ,r-biocparallel)
6181 ("r-genefilter" ,r-genefilter)
6182 ("r-geneplotter" ,r-geneplotter)
6183 ("r-genomicranges" ,r-genomicranges)
6184 ("r-ggplot2" ,r-ggplot2)
6185 ("r-hmisc" ,r-hmisc)
6186 ("r-iranges" ,r-iranges)
6187 ("r-locfit" ,r-locfit)
6189 ("r-rcpparmadillo" ,r-rcpparmadillo)
6190 ("r-s4vectors" ,r-s4vectors)
6191 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6192 (home-page "https://bioconductor.org/packages/DESeq2")
6193 (synopsis "Differential gene expression analysis")
6195 "This package provides functions to estimate variance-mean dependence in
6196 count data from high-throughput nucleotide sequencing assays and test for
6197 differential expression based on a model using the negative binomial
6199 (license license:lgpl3+)))
6201 (define-public r-dexseq
6208 (uri (bioconductor-uri "DEXSeq" version))
6211 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6212 (properties `((upstream-name . "DEXSeq")))
6213 (build-system r-build-system)
6215 `(("r-annotationdbi" ,r-annotationdbi)
6216 ("r-biobase" ,r-biobase)
6217 ("r-biocgenerics" ,r-biocgenerics)
6218 ("r-biocparallel" ,r-biocparallel)
6219 ("r-biomart" ,r-biomart)
6220 ("r-deseq2" ,r-deseq2)
6221 ("r-genefilter" ,r-genefilter)
6222 ("r-geneplotter" ,r-geneplotter)
6223 ("r-genomicranges" ,r-genomicranges)
6224 ("r-hwriter" ,r-hwriter)
6225 ("r-iranges" ,r-iranges)
6226 ("r-rcolorbrewer" ,r-rcolorbrewer)
6227 ("r-rsamtools" ,r-rsamtools)
6228 ("r-s4vectors" ,r-s4vectors)
6229 ("r-statmod" ,r-statmod)
6230 ("r-stringr" ,r-stringr)
6231 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6232 (home-page "https://bioconductor.org/packages/DEXSeq")
6233 (synopsis "Inference of differential exon usage in RNA-Seq")
6235 "This package is focused on finding differential exon usage using RNA-seq
6236 exon counts between samples with different experimental designs. It provides
6237 functions that allows the user to make the necessary statistical tests based
6238 on a model that uses the negative binomial distribution to estimate the
6239 variance between biological replicates and generalized linear models for
6240 testing. The package also provides functions for the visualization and
6241 exploration of the results.")
6242 (license license:gpl3+)))
6244 (define-public r-annotationforge
6246 (name "r-annotationforge")
6251 (uri (bioconductor-uri "AnnotationForge" version))
6254 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6256 `((upstream-name . "AnnotationForge")))
6257 (build-system r-build-system)
6259 `(("r-annotationdbi" ,r-annotationdbi)
6260 ("r-biobase" ,r-biobase)
6261 ("r-biocgenerics" ,r-biocgenerics)
6263 ("r-rcurl" ,r-rcurl)
6264 ("r-rsqlite" ,r-rsqlite)
6265 ("r-s4vectors" ,r-s4vectors)
6267 (home-page "https://bioconductor.org/packages/AnnotationForge")
6268 (synopsis "Code for building annotation database packages")
6270 "This package provides code for generating Annotation packages and their
6271 databases. Packages produced are intended to be used with AnnotationDbi.")
6272 (license license:artistic2.0)))
6274 (define-public r-rbgl
6281 (uri (bioconductor-uri "RBGL" version))
6284 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6285 (properties `((upstream-name . "RBGL")))
6286 (build-system r-build-system)
6287 (propagated-inputs `(("r-graph" ,r-graph)))
6288 (home-page "https://www.bioconductor.org/packages/RBGL")
6289 (synopsis "Interface to the Boost graph library")
6291 "This package provides a fairly extensive and comprehensive interface to
6292 the graph algorithms contained in the Boost library.")
6293 (license license:artistic2.0)))
6295 (define-public r-gseabase
6302 (uri (bioconductor-uri "GSEABase" version))
6305 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6306 (properties `((upstream-name . "GSEABase")))
6307 (build-system r-build-system)
6309 `(("r-annotate" ,r-annotate)
6310 ("r-annotationdbi" ,r-annotationdbi)
6311 ("r-biobase" ,r-biobase)
6312 ("r-biocgenerics" ,r-biocgenerics)
6313 ("r-graph" ,r-graph)
6315 (home-page "https://bioconductor.org/packages/GSEABase")
6316 (synopsis "Gene set enrichment data structures and methods")
6318 "This package provides classes and methods to support @dfn{Gene Set
6319 Enrichment Analysis} (GSEA).")
6320 (license license:artistic2.0)))
6322 (define-public r-category
6329 (uri (bioconductor-uri "Category" version))
6332 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6333 (properties `((upstream-name . "Category")))
6334 (build-system r-build-system)
6336 `(("r-annotate" ,r-annotate)
6337 ("r-annotationdbi" ,r-annotationdbi)
6338 ("r-biobase" ,r-biobase)
6339 ("r-biocgenerics" ,r-biocgenerics)
6340 ("r-genefilter" ,r-genefilter)
6341 ("r-graph" ,r-graph)
6342 ("r-gseabase" ,r-gseabase)
6343 ("r-matrix" ,r-matrix)
6346 (home-page "https://bioconductor.org/packages/Category")
6347 (synopsis "Category analysis")
6349 "This package provides a collection of tools for performing category
6351 (license license:artistic2.0)))
6353 (define-public r-gostats
6360 (uri (bioconductor-uri "GOstats" version))
6363 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6364 (properties `((upstream-name . "GOstats")))
6365 (build-system r-build-system)
6367 `(("r-annotate" ,r-annotate)
6368 ("r-annotationdbi" ,r-annotationdbi)
6369 ("r-annotationforge" ,r-annotationforge)
6370 ("r-biobase" ,r-biobase)
6371 ("r-category" ,r-category)
6372 ("r-go-db" ,r-go-db)
6373 ("r-graph" ,r-graph)
6374 ("r-rgraphviz" ,r-rgraphviz)
6375 ("r-rbgl" ,r-rbgl)))
6376 (home-page "https://bioconductor.org/packages/GOstats")
6377 (synopsis "Tools for manipulating GO and microarrays")
6379 "This package provides a set of tools for interacting with GO and
6380 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6381 testing and other simple calculations.")
6382 (license license:artistic2.0)))
6384 (define-public r-shortread
6386 (name "r-shortread")
6391 (uri (bioconductor-uri "ShortRead" version))
6394 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6395 (properties `((upstream-name . "ShortRead")))
6396 (build-system r-build-system)
6400 `(("r-biobase" ,r-biobase)
6401 ("r-biocgenerics" ,r-biocgenerics)
6402 ("r-biocparallel" ,r-biocparallel)
6403 ("r-biostrings" ,r-biostrings)
6404 ("r-genomeinfodb" ,r-genomeinfodb)
6405 ("r-genomicalignments" ,r-genomicalignments)
6406 ("r-genomicranges" ,r-genomicranges)
6407 ("r-hwriter" ,r-hwriter)
6408 ("r-iranges" ,r-iranges)
6409 ("r-lattice" ,r-lattice)
6410 ("r-latticeextra" ,r-latticeextra)
6411 ("r-rsamtools" ,r-rsamtools)
6412 ("r-s4vectors" ,r-s4vectors)
6413 ("r-xvector" ,r-xvector)
6414 ("r-zlibbioc" ,r-zlibbioc)))
6415 (home-page "https://bioconductor.org/packages/ShortRead")
6416 (synopsis "FASTQ input and manipulation tools")
6418 "This package implements sampling, iteration, and input of FASTQ files.
6419 It includes functions for filtering and trimming reads, and for generating a
6420 quality assessment report. Data are represented as
6421 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6422 purposes. The package also contains legacy support for early single-end,
6423 ungapped alignment formats.")
6424 (license license:artistic2.0)))
6426 (define-public r-systempiper
6428 (name "r-systempiper")
6433 (uri (bioconductor-uri "systemPipeR" version))
6436 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6437 (properties `((upstream-name . "systemPipeR")))
6438 (build-system r-build-system)
6440 `(("r-annotate" ,r-annotate)
6441 ("r-batchjobs" ,r-batchjobs)
6442 ("r-biocgenerics" ,r-biocgenerics)
6443 ("r-biostrings" ,r-biostrings)
6444 ("r-deseq2" ,r-deseq2)
6445 ("r-edger" ,r-edger)
6446 ("r-genomicfeatures" ,r-genomicfeatures)
6447 ("r-genomicranges" ,r-genomicranges)
6448 ("r-ggplot2" ,r-ggplot2)
6449 ("r-go-db" ,r-go-db)
6450 ("r-gostats" ,r-gostats)
6451 ("r-limma" ,r-limma)
6452 ("r-pheatmap" ,r-pheatmap)
6453 ("r-rjson" ,r-rjson)
6454 ("r-rsamtools" ,r-rsamtools)
6455 ("r-shortread" ,r-shortread)
6456 ("r-summarizedexperiment" ,r-summarizedexperiment)
6457 ("r-variantannotation" ,r-variantannotation)))
6458 (home-page "https://github.com/tgirke/systemPipeR")
6459 (synopsis "Next generation sequencing workflow and reporting environment")
6461 "This R package provides tools for building and running automated
6462 end-to-end analysis workflows for a wide range of @dfn{next generation
6463 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6464 Important features include a uniform workflow interface across different NGS
6465 applications, automated report generation, and support for running both R and
6466 command-line software, such as NGS aligners or peak/variant callers, on local
6467 computers or compute clusters. Efficient handling of complex sample sets and
6468 experimental designs is facilitated by a consistently implemented sample
6469 annotation infrastructure.")
6470 (license license:artistic2.0)))
6472 (define-public r-grohmm
6479 (uri (bioconductor-uri "groHMM" version))
6482 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6483 (properties `((upstream-name . "groHMM")))
6484 (build-system r-build-system)
6486 `(("r-genomeinfodb" ,r-genomeinfodb)
6487 ("r-genomicalignments" ,r-genomicalignments)
6488 ("r-genomicranges" ,r-genomicranges)
6489 ("r-iranges" ,r-iranges)
6491 ("r-rtracklayer" ,r-rtracklayer)
6492 ("r-s4vectors" ,r-s4vectors)))
6493 (home-page "https://github.com/Kraus-Lab/groHMM")
6494 (synopsis "GRO-seq analysis pipeline")
6496 "This package provides a pipeline for the analysis of GRO-seq data.")
6497 (license license:gpl3+)))
6499 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6501 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6505 ;; We cannot use bioconductor-uri here because this tarball is
6506 ;; located under "data/annotation/" instead of "bioc/".
6507 (uri (string-append "https://bioconductor.org/packages/"
6508 "release/data/annotation/src/contrib"
6509 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6513 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6515 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6516 (build-system r-build-system)
6517 ;; As this package provides little more than a very large data file it
6518 ;; doesn't make sense to build substitutes.
6519 (arguments `(#:substitutable? #f))
6521 `(("r-genomicfeatures" ,r-genomicfeatures)))
6523 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6524 (synopsis "Annotation package for human genome in TxDb format")
6526 "This package provides an annotation database of Homo sapiens genome
6527 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6528 track. The database is exposed as a @code{TxDb} object.")
6529 (license license:artistic2.0)))
6531 (define-public r-sparql
6537 (uri (cran-uri "SPARQL" version))
6540 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6541 (properties `((upstream-name . "SPARQL")))
6542 (build-system r-build-system)
6544 `(("r-rcurl" ,r-rcurl)
6546 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6547 (synopsis "SPARQL client for R")
6548 (description "This package provides an interface to use SPARQL to pose
6549 SELECT or UPDATE queries to an end-point.")
6550 ;; The only license indication is found in the DESCRIPTION file,
6551 ;; which states GPL-3. So we cannot assume GPLv3+.
6552 (license license:gpl3)))
6554 (define-public vsearch
6562 "https://github.com/torognes/vsearch/archive/v"
6564 (file-name (string-append name "-" version ".tar.gz"))
6567 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6568 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6571 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6572 ;; for this in the patch.
6573 (delete-file "src/city.h")
6574 (delete-file "src/citycrc.h")
6575 (delete-file "src/city.cc")
6577 (build-system gnu-build-system)
6580 (modify-phases %standard-phases
6581 (add-after 'unpack 'autogen
6582 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6586 ("cityhash" ,cityhash)))
6588 `(("autoconf" ,autoconf)
6589 ("automake" ,automake)))
6590 (synopsis "Sequence search tools for metagenomics")
6592 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6593 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6594 masking. The tool takes advantage of parallelism in the form of SIMD
6595 vectorization as well as multiple threads to perform accurate alignments at
6596 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6597 Needleman-Wunsch).")
6598 (home-page "https://github.com/torognes/vsearch")
6599 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6601 (supported-systems '("x86_64-linux"))
6602 ;; Dual licensed; also includes public domain source.
6603 (license (list license:gpl3 license:bsd-2))))
6605 (define-public pardre
6608 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6613 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6617 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6618 (build-system gnu-build-system)
6620 `(#:tests? #f ; no tests included
6622 (modify-phases %standard-phases
6625 (lambda* (#:key outputs #:allow-other-keys)
6626 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6627 (install-file "ParDRe" bin)
6630 `(("openmpi" ,openmpi)
6632 (synopsis "Parallel tool to remove duplicate DNA reads")
6634 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6635 Duplicate reads can be seen as identical or nearly identical sequences with
6636 some mismatches. This tool lets users avoid the analysis of unnecessary
6637 reads, reducing the time of subsequent procedures with the
6638 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6639 in order to exploit the parallel capabilities of multicore clusters. It is
6640 faster than multithreaded counterparts (end of 2015) for the same number of
6641 cores and, thanks to the message-passing technology, it can be executed on
6643 (home-page "https://sourceforge.net/projects/pardre/")
6644 (license license:gpl3+)))
6646 (define-public ruby-bio-kseq
6648 (name "ruby-bio-kseq")
6653 (uri (rubygems-uri "bio-kseq" version))
6656 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6657 (build-system ruby-build-system)
6659 `(#:test-target "spec"))
6661 `(("bundler" ,bundler)
6662 ("ruby-rspec" ,ruby-rspec)
6663 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6666 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6668 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6669 FASTQ parsing code. It provides a fast iterator over sequences and their
6671 (home-page "https://github.com/gusevfe/bio-kseq")
6672 (license license:expat)))
6674 (define-public bio-locus
6681 (uri (rubygems-uri "bio-locus" version))
6684 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6685 (build-system ruby-build-system)
6687 `(("ruby-rspec" ,ruby-rspec)))
6688 (synopsis "Tool for fast querying of genome locations")
6690 "Bio-locus is a tabix-like tool for fast querying of genome
6691 locations. Many file formats in bioinformatics contain records that
6692 start with a chromosome name and a position for a SNP, or a start-end
6693 position for indels. Bio-locus allows users to store this chr+pos or
6694 chr+pos+alt information in a database.")
6695 (home-page "https://github.com/pjotrp/bio-locus")
6696 (license license:expat)))
6698 (define-public bio-blastxmlparser
6700 (name "bio-blastxmlparser")
6704 (uri (rubygems-uri "bio-blastxmlparser" version))
6707 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6708 (build-system ruby-build-system)
6710 `(("ruby-bio-logger" ,ruby-bio-logger)
6711 ("ruby-nokogiri" ,ruby-nokogiri)))
6713 `(("ruby-rspec" ,ruby-rspec)))
6714 (synopsis "Fast big data BLAST XML parser and library")
6716 "Very fast parallel big-data BLAST XML file parser which can be used as
6717 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6718 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6719 (home-page "https://github.com/pjotrp/blastxmlparser")
6720 (license license:expat)))
6722 (define-public bioruby
6729 (uri (rubygems-uri "bio" version))
6732 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6733 (build-system ruby-build-system)
6735 `(("ruby-libxml" ,ruby-libxml)))
6737 `(("which" ,which))) ; required for test phase
6740 (modify-phases %standard-phases
6741 (add-before 'build 'patch-test-command
6743 (substitute* '("test/functional/bio/test_command.rb")
6744 (("/bin/sh") (which "sh")))
6745 (substitute* '("test/functional/bio/test_command.rb")
6746 (("/bin/ls") (which "ls")))
6747 (substitute* '("test/functional/bio/test_command.rb")
6748 (("which") (which "which")))
6749 (substitute* '("test/functional/bio/test_command.rb",
6750 "test/data/command/echoarg2.sh")
6751 (("/bin/echo") (which "echo")))
6753 (synopsis "Ruby library, shell and utilities for bioinformatics")
6754 (description "BioRuby comes with a comprehensive set of Ruby development
6755 tools and libraries for bioinformatics and molecular biology. BioRuby has
6756 components for sequence analysis, pathway analysis, protein modelling and
6757 phylogenetic analysis; it supports many widely used data formats and provides
6758 easy access to databases, external programs and public web services, including
6759 BLAST, KEGG, GenBank, MEDLINE and GO.")
6760 (home-page "http://bioruby.org/")
6761 ;; Code is released under Ruby license, except for setup
6762 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6763 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6765 (define-public r-acsnminer
6767 (name "r-acsnminer")
6768 (version "0.16.8.25")
6771 (uri (cran-uri "ACSNMineR" version))
6774 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6775 (properties `((upstream-name . "ACSNMineR")))
6776 (build-system r-build-system)
6778 `(("r-ggplot2" ,r-ggplot2)
6779 ("r-gridextra" ,r-gridextra)))
6780 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6781 (synopsis "Gene enrichment analysis")
6783 "This package provides tools to compute and represent gene set enrichment
6784 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6785 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6786 enrichment can be run with hypergeometric test or Fisher exact test, and can
6787 use multiple corrections. Visualization of data can be done either by
6788 barplots or heatmaps.")
6789 (license license:gpl2+)))
6791 (define-public r-biocgenerics
6793 (name "r-biocgenerics")
6797 (uri (bioconductor-uri "BiocGenerics" version))
6800 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6802 `((upstream-name . "BiocGenerics")))
6803 (build-system r-build-system)
6804 (home-page "https://bioconductor.org/packages/BiocGenerics")
6805 (synopsis "S4 generic functions for Bioconductor")
6807 "This package provides S4 generic functions needed by many Bioconductor
6809 (license license:artistic2.0)))
6811 (define-public r-biocinstaller
6813 (name "r-biocinstaller")
6817 (uri (bioconductor-uri "BiocInstaller" version))
6820 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6822 `((upstream-name . "BiocInstaller")))
6823 (build-system r-build-system)
6824 (home-page "https://bioconductor.org/packages/BiocInstaller")
6825 (synopsis "Install Bioconductor packages")
6826 (description "This package is used to install and update R packages from
6827 Bioconductor, CRAN, and Github.")
6828 (license license:artistic2.0)))
6830 (define-public r-biocviews
6832 (name "r-biocviews")
6836 (uri (bioconductor-uri "biocViews" version))
6839 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6841 `((upstream-name . "biocViews")))
6842 (build-system r-build-system)
6844 `(("r-biobase" ,r-biobase)
6845 ("r-graph" ,r-graph)
6847 ("r-rcurl" ,r-rcurl)
6849 ("r-runit" ,r-runit)))
6850 (home-page "https://bioconductor.org/packages/biocViews")
6851 (synopsis "Bioconductor package categorization helper")
6852 (description "The purpose of biocViews is to create HTML pages that
6853 categorize packages in a Bioconductor package repository according to keywords,
6854 also known as views, in a controlled vocabulary.")
6855 (license license:artistic2.0)))
6857 (define-public r-bookdown
6863 (uri (cran-uri "bookdown" version))
6866 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6867 (build-system r-build-system)
6869 `(("r-htmltools" ,r-htmltools)
6870 ("r-knitr" ,r-knitr)
6871 ("r-rmarkdown" ,r-rmarkdown)
6872 ("r-tinytex" ,r-tinytex)
6875 ("ghc-pandoc" ,ghc-pandoc)))
6876 (home-page "https://github.com/rstudio/bookdown")
6877 (synopsis "Authoring books and technical documents with R markdown")
6878 (description "This package provides output formats and utilities for
6879 authoring books and technical documents with R Markdown.")
6880 (license license:gpl3)))
6882 (define-public r-biocstyle
6884 (name "r-biocstyle")
6888 (uri (bioconductor-uri "BiocStyle" version))
6891 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6893 `((upstream-name . "BiocStyle")))
6894 (build-system r-build-system)
6896 `(("r-bookdown" ,r-bookdown)
6897 ("r-knitr" ,r-knitr)
6898 ("r-rmarkdown" ,r-rmarkdown)
6899 ("r-yaml" ,r-yaml)))
6900 (home-page "https://bioconductor.org/packages/BiocStyle")
6901 (synopsis "Bioconductor formatting styles")
6902 (description "This package provides standard formatting styles for
6903 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6905 (license license:artistic2.0)))
6907 (define-public r-bioccheck
6909 (name "r-bioccheck")
6913 (uri (bioconductor-uri "BiocCheck" version))
6916 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6918 `((upstream-name . "BiocCheck")))
6919 (build-system r-build-system)
6922 (modify-phases %standard-phases
6923 ;; This package can be used by calling BiocCheck(<package>) from
6924 ;; within R, or by running R CMD BiocCheck <package>. This phase
6925 ;; makes sure the latter works. For this to work, the BiocCheck
6926 ;; script must be somewhere on the PATH (not the R bin directory).
6927 (add-after 'install 'install-bioccheck-subcommand
6928 (lambda* (#:key outputs #:allow-other-keys)
6929 (let* ((out (assoc-ref outputs "out"))
6930 (dest-dir (string-append out "/bin"))
6932 (string-append out "/site-library/BiocCheck/script/")))
6934 (symlink (string-append script-dir "/checkBadDeps.R")
6935 (string-append dest-dir "/checkBadDeps.R"))
6936 (symlink (string-append script-dir "/BiocCheck")
6937 (string-append dest-dir "/BiocCheck")))
6940 `(("r-codetools" ,r-codetools)
6941 ("r-graph" ,r-graph)
6943 ("r-optparse" ,r-optparse)
6944 ("r-biocinstaller" ,r-biocinstaller)
6945 ("r-biocviews" ,r-biocviews)
6946 ("r-stringdist" ,r-stringdist)))
6947 (home-page "https://bioconductor.org/packages/BiocCheck")
6948 (synopsis "Executes Bioconductor-specific package checks")
6949 (description "This package contains tools to perform additional quality
6950 checks on R packages that are to be submitted to the Bioconductor repository.")
6951 (license license:artistic2.0)))
6953 (define-public r-getopt
6960 (uri (cran-uri "getopt" version))
6963 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
6964 (build-system r-build-system)
6965 (home-page "https://github.com/trevorld/getopt")
6966 (synopsis "Command-line option processor for R")
6968 "This package is designed to be used with Rscript to write shebang
6969 scripts that accept short and long options. Many users will prefer to
6970 use the packages @code{optparse} or @code{argparse} which add extra
6971 features like automatically generated help options and usage texts,
6972 support for default values, positional argument support, etc.")
6973 (license license:gpl2+)))
6975 (define-public r-optparse
6982 (uri (cran-uri "optparse" version))
6985 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6986 (build-system r-build-system)
6988 `(("r-getopt" ,r-getopt)))
6990 "https://github.com/trevorld/optparse")
6991 (synopsis "Command line option parser")
6993 "This package provides a command line parser inspired by Python's
6994 @code{optparse} library to be used with Rscript to write shebang scripts
6995 that accept short and long options.")
6996 (license license:gpl2+)))
6998 (define-public r-dnacopy
7004 (uri (bioconductor-uri "DNAcopy" version))
7007 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
7009 `((upstream-name . "DNAcopy")))
7010 (build-system r-build-system)
7012 `(("gfortran" ,gfortran)))
7013 (home-page "https://bioconductor.org/packages/DNAcopy")
7014 (synopsis "Implementation of a circular binary segmentation algorithm")
7015 (description "This package implements the circular binary segmentation (CBS)
7016 algorithm to segment DNA copy number data and identify genomic regions with
7017 abnormal copy number.")
7018 (license license:gpl2+)))
7020 (define-public r-s4vectors
7022 (name "r-s4vectors")
7026 (uri (bioconductor-uri "S4Vectors" version))
7029 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7031 `((upstream-name . "S4Vectors")))
7032 (build-system r-build-system)
7034 `(("r-biocgenerics" ,r-biocgenerics)))
7035 (home-page "https://bioconductor.org/packages/S4Vectors")
7036 (synopsis "S4 implementation of vectors and lists")
7038 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7039 classes and a set of generic functions that extend the semantic of ordinary
7040 vectors and lists in R. Package developers can easily implement vector-like
7041 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7042 In addition, a few low-level concrete subclasses of general interest (e.g.
7043 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7044 S4Vectors package itself.")
7045 (license license:artistic2.0)))
7047 (define-public r-seqinr
7054 (uri (cran-uri "seqinr" version))
7057 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7058 (build-system r-build-system)
7060 `(("r-ade4" ,r-ade4)
7061 ("r-segmented" ,r-segmented)))
7064 (home-page "http://seqinr.r-forge.r-project.org/")
7065 (synopsis "Biological sequences retrieval and analysis")
7067 "This package provides tools for exploratory data analysis and data
7068 visualization of biological sequence (DNA and protein) data. It also includes
7069 utilities for sequence data management under the ACNUC system.")
7070 (license license:gpl2+)))
7072 (define-public r-iranges
7078 (uri (bioconductor-uri "IRanges" version))
7081 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7083 `((upstream-name . "IRanges")))
7084 (build-system r-build-system)
7086 `(("r-biocgenerics" ,r-biocgenerics)
7087 ("r-s4vectors" ,r-s4vectors)))
7088 (home-page "https://bioconductor.org/packages/IRanges")
7089 (synopsis "Infrastructure for manipulating intervals on sequences")
7091 "This package provides efficient low-level and highly reusable S4 classes
7092 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7093 generally, data that can be organized sequentially (formally defined as
7094 @code{Vector} objects), as well as views on these @code{Vector} objects.
7095 Efficient list-like classes are also provided for storing big collections of
7096 instances of the basic classes. All classes in the package use consistent
7097 naming and share the same rich and consistent \"Vector API\" as much as
7099 (license license:artistic2.0)))
7101 (define-public r-genomeinfodbdata
7103 (name "r-genomeinfodbdata")
7107 ;; We cannot use bioconductor-uri here because this tarball is
7108 ;; located under "data/annotation/" instead of "bioc/".
7109 (uri (string-append "https://bioconductor.org/packages/release/"
7110 "data/annotation/src/contrib/GenomeInfoDbData_"
7114 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7116 `((upstream-name . "GenomeInfoDbData")))
7117 (build-system r-build-system)
7118 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7119 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7120 (description "This package contains data for mapping between NCBI taxonomy
7121 ID and species. It is used by functions in the GenomeInfoDb package.")
7122 (license license:artistic2.0)))
7124 (define-public r-genomeinfodb
7126 (name "r-genomeinfodb")
7130 (uri (bioconductor-uri "GenomeInfoDb" version))
7133 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7135 `((upstream-name . "GenomeInfoDb")))
7136 (build-system r-build-system)
7138 `(("r-biocgenerics" ,r-biocgenerics)
7139 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7140 ("r-iranges" ,r-iranges)
7141 ("r-rcurl" ,r-rcurl)
7142 ("r-s4vectors" ,r-s4vectors)))
7143 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7144 (synopsis "Utilities for manipulating chromosome identifiers")
7146 "This package contains data and functions that define and allow
7147 translation between different chromosome sequence naming conventions (e.g.,
7148 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7149 names in their natural, rather than lexicographic, order.")
7150 (license license:artistic2.0)))
7152 (define-public r-edger
7158 (uri (bioconductor-uri "edgeR" version))
7161 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7162 (properties `((upstream-name . "edgeR")))
7163 (build-system r-build-system)
7165 `(("r-limma" ,r-limma)
7166 ("r-locfit" ,r-locfit)
7168 ("r-statmod" ,r-statmod))) ;for estimateDisp
7169 (home-page "http://bioinf.wehi.edu.au/edgeR")
7170 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7171 (description "This package can do differential expression analysis of
7172 RNA-seq expression profiles with biological replication. It implements a range
7173 of statistical methodology based on the negative binomial distributions,
7174 including empirical Bayes estimation, exact tests, generalized linear models
7175 and quasi-likelihood tests. It be applied to differential signal analysis of
7176 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7178 (license license:gpl2+)))
7180 (define-public r-variantannotation
7182 (name "r-variantannotation")
7186 (uri (bioconductor-uri "VariantAnnotation" version))
7189 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7191 `((upstream-name . "VariantAnnotation")))
7195 `(("r-annotationdbi" ,r-annotationdbi)
7196 ("r-biobase" ,r-biobase)
7197 ("r-biocgenerics" ,r-biocgenerics)
7198 ("r-biostrings" ,r-biostrings)
7199 ("r-bsgenome" ,r-bsgenome)
7201 ("r-genomeinfodb" ,r-genomeinfodb)
7202 ("r-genomicfeatures" ,r-genomicfeatures)
7203 ("r-genomicranges" ,r-genomicranges)
7204 ("r-iranges" ,r-iranges)
7205 ("r-summarizedexperiment" ,r-summarizedexperiment)
7206 ("r-rsamtools" ,r-rsamtools)
7207 ("r-rtracklayer" ,r-rtracklayer)
7208 ("r-s4vectors" ,r-s4vectors)
7209 ("r-xvector" ,r-xvector)
7210 ("r-zlibbioc" ,r-zlibbioc)))
7211 (build-system r-build-system)
7212 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7213 (synopsis "Package for annotation of genetic variants")
7214 (description "This R package can annotate variants, compute amino acid
7215 coding changes and predict coding outcomes.")
7216 (license license:artistic2.0)))
7218 (define-public r-limma
7224 (uri (bioconductor-uri "limma" version))
7227 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7228 (build-system r-build-system)
7229 (home-page "http://bioinf.wehi.edu.au/limma")
7230 (synopsis "Package for linear models for microarray and RNA-seq data")
7231 (description "This package can be used for the analysis of gene expression
7232 studies, especially the use of linear models for analysing designed experiments
7233 and the assessment of differential expression. The analysis methods apply to
7234 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7235 (license license:gpl2+)))
7237 (define-public r-xvector
7243 (uri (bioconductor-uri "XVector" version))
7246 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7248 `((upstream-name . "XVector")))
7249 (build-system r-build-system)
7252 (modify-phases %standard-phases
7253 (add-after 'unpack 'use-system-zlib
7255 (substitute* "DESCRIPTION"
7256 (("zlibbioc, ") ""))
7257 (substitute* "NAMESPACE"
7258 (("import\\(zlibbioc\\)") ""))
7263 `(("r-biocgenerics" ,r-biocgenerics)
7264 ("r-iranges" ,r-iranges)
7265 ("r-s4vectors" ,r-s4vectors)))
7266 (home-page "https://bioconductor.org/packages/XVector")
7267 (synopsis "Representation and manpulation of external sequences")
7269 "This package provides memory efficient S4 classes for storing sequences
7270 \"externally\" (behind an R external pointer, or on disk).")
7271 (license license:artistic2.0)))
7273 (define-public r-genomicranges
7275 (name "r-genomicranges")
7279 (uri (bioconductor-uri "GenomicRanges" version))
7282 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7284 `((upstream-name . "GenomicRanges")))
7285 (build-system r-build-system)
7287 `(("r-biocgenerics" ,r-biocgenerics)
7288 ("r-genomeinfodb" ,r-genomeinfodb)
7289 ("r-iranges" ,r-iranges)
7290 ("r-s4vectors" ,r-s4vectors)
7291 ("r-xvector" ,r-xvector)))
7292 (home-page "https://bioconductor.org/packages/GenomicRanges")
7293 (synopsis "Representation and manipulation of genomic intervals")
7295 "This package provides tools to efficiently represent and manipulate
7296 genomic annotations and alignments is playing a central role when it comes to
7297 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7298 GenomicRanges package defines general purpose containers for storing and
7299 manipulating genomic intervals and variables defined along a genome.")
7300 (license license:artistic2.0)))
7302 (define-public r-biobase
7308 (uri (bioconductor-uri "Biobase" version))
7311 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7313 `((upstream-name . "Biobase")))
7314 (build-system r-build-system)
7316 `(("r-biocgenerics" ,r-biocgenerics)))
7317 (home-page "https://bioconductor.org/packages/Biobase")
7318 (synopsis "Base functions for Bioconductor")
7320 "This package provides functions that are needed by many other packages
7321 on Bioconductor or which replace R functions.")
7322 (license license:artistic2.0)))
7324 (define-public r-annotationdbi
7326 (name "r-annotationdbi")
7330 (uri (bioconductor-uri "AnnotationDbi" version))
7333 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7335 `((upstream-name . "AnnotationDbi")))
7336 (build-system r-build-system)
7338 `(("r-biobase" ,r-biobase)
7339 ("r-biocgenerics" ,r-biocgenerics)
7341 ("r-iranges" ,r-iranges)
7342 ("r-rsqlite" ,r-rsqlite)
7343 ("r-s4vectors" ,r-s4vectors)))
7344 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7345 (synopsis "Annotation database interface")
7347 "This package provides user interface and database connection code for
7348 annotation data packages using SQLite data storage.")
7349 (license license:artistic2.0)))
7351 (define-public r-biomart
7357 (uri (bioconductor-uri "biomaRt" version))
7360 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7362 `((upstream-name . "biomaRt")))
7363 (build-system r-build-system)
7365 `(("r-annotationdbi" ,r-annotationdbi)
7367 ("r-progress" ,r-progress)
7368 ("r-rcurl" ,r-rcurl)
7369 ("r-stringr" ,r-stringr)
7371 (home-page "https://bioconductor.org/packages/biomaRt")
7372 (synopsis "Interface to BioMart databases")
7374 "biomaRt provides an interface to a growing collection of databases
7375 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7376 package enables retrieval of large amounts of data in a uniform way without
7377 the need to know the underlying database schemas or write complex SQL queries.
7378 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7379 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7380 users direct access to a diverse set of data and enable a wide range of
7381 powerful online queries from gene annotation to database mining.")
7382 (license license:artistic2.0)))
7384 (define-public r-biocparallel
7386 (name "r-biocparallel")
7390 (uri (bioconductor-uri "BiocParallel" version))
7393 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7395 `((upstream-name . "BiocParallel")))
7396 (build-system r-build-system)
7398 `(("r-futile-logger" ,r-futile-logger)
7401 (home-page "https://bioconductor.org/packages/BiocParallel")
7402 (synopsis "Bioconductor facilities for parallel evaluation")
7404 "This package provides modified versions and novel implementation of
7405 functions for parallel evaluation, tailored to use with Bioconductor
7407 (license (list license:gpl2+ license:gpl3+))))
7409 (define-public r-biostrings
7411 (name "r-biostrings")
7415 (uri (bioconductor-uri "Biostrings" version))
7418 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7420 `((upstream-name . "Biostrings")))
7421 (build-system r-build-system)
7423 `(("r-biocgenerics" ,r-biocgenerics)
7424 ("r-iranges" ,r-iranges)
7425 ("r-s4vectors" ,r-s4vectors)
7426 ("r-xvector" ,r-xvector)))
7427 (home-page "https://bioconductor.org/packages/Biostrings")
7428 (synopsis "String objects and algorithms for biological sequences")
7430 "This package provides memory efficient string containers, string
7431 matching algorithms, and other utilities, for fast manipulation of large
7432 biological sequences or sets of sequences.")
7433 (license license:artistic2.0)))
7435 (define-public r-rsamtools
7437 (name "r-rsamtools")
7441 (uri (bioconductor-uri "Rsamtools" version))
7444 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7446 `((upstream-name . "Rsamtools")))
7447 (build-system r-build-system)
7450 (modify-phases %standard-phases
7451 (add-after 'unpack 'use-system-zlib
7453 (substitute* "DESCRIPTION"
7454 (("zlibbioc, ") ""))
7455 (substitute* "NAMESPACE"
7456 (("import\\(zlibbioc\\)") ""))
7461 `(("r-biocgenerics" ,r-biocgenerics)
7462 ("r-biocparallel" ,r-biocparallel)
7463 ("r-biostrings" ,r-biostrings)
7464 ("r-bitops" ,r-bitops)
7465 ("r-genomeinfodb" ,r-genomeinfodb)
7466 ("r-genomicranges" ,r-genomicranges)
7467 ("r-iranges" ,r-iranges)
7468 ("r-s4vectors" ,r-s4vectors)
7469 ("r-xvector" ,r-xvector)))
7470 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7471 (synopsis "Interface to samtools, bcftools, and tabix")
7473 "This package provides an interface to the 'samtools', 'bcftools', and
7474 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7475 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7477 (license license:expat)))
7479 (define-public r-delayedarray
7481 (name "r-delayedarray")
7485 (uri (bioconductor-uri "DelayedArray" version))
7488 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7490 `((upstream-name . "DelayedArray")))
7491 (build-system r-build-system)
7493 `(("r-biocgenerics" ,r-biocgenerics)
7494 ("r-s4vectors" ,r-s4vectors)
7495 ("r-iranges" ,r-iranges)
7496 ("r-matrixstats" ,r-matrixstats)))
7497 (home-page "https://bioconductor.org/packages/DelayedArray")
7498 (synopsis "Delayed operations on array-like objects")
7500 "Wrapping an array-like object (typically an on-disk object) in a
7501 @code{DelayedArray} object allows one to perform common array operations on it
7502 without loading the object in memory. In order to reduce memory usage and
7503 optimize performance, operations on the object are either delayed or executed
7504 using a block processing mechanism. Note that this also works on in-memory
7505 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7506 @code{Matrix} objects, and ordinary arrays and data frames.")
7507 (license license:artistic2.0)))
7509 (define-public r-summarizedexperiment
7511 (name "r-summarizedexperiment")
7515 (uri (bioconductor-uri "SummarizedExperiment" version))
7518 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7520 `((upstream-name . "SummarizedExperiment")))
7521 (build-system r-build-system)
7523 `(("r-biobase" ,r-biobase)
7524 ("r-biocgenerics" ,r-biocgenerics)
7525 ("r-delayedarray" ,r-delayedarray)
7526 ("r-genomeinfodb" ,r-genomeinfodb)
7527 ("r-genomicranges" ,r-genomicranges)
7528 ("r-iranges" ,r-iranges)
7529 ("r-matrix" ,r-matrix)
7530 ("r-s4vectors" ,r-s4vectors)))
7531 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7532 (synopsis "Container for representing genomic ranges by sample")
7534 "The SummarizedExperiment container contains one or more assays, each
7535 represented by a matrix-like object of numeric or other mode. The rows
7536 typically represent genomic ranges of interest and the columns represent
7538 (license license:artistic2.0)))
7540 (define-public r-genomicalignments
7542 (name "r-genomicalignments")
7546 (uri (bioconductor-uri "GenomicAlignments" version))
7549 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7551 `((upstream-name . "GenomicAlignments")))
7552 (build-system r-build-system)
7554 `(("r-biocgenerics" ,r-biocgenerics)
7555 ("r-biocparallel" ,r-biocparallel)
7556 ("r-biostrings" ,r-biostrings)
7557 ("r-genomeinfodb" ,r-genomeinfodb)
7558 ("r-genomicranges" ,r-genomicranges)
7559 ("r-iranges" ,r-iranges)
7560 ("r-rsamtools" ,r-rsamtools)
7561 ("r-s4vectors" ,r-s4vectors)
7562 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7563 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7564 (synopsis "Representation and manipulation of short genomic alignments")
7566 "This package provides efficient containers for storing and manipulating
7567 short genomic alignments (typically obtained by aligning short reads to a
7568 reference genome). This includes read counting, computing the coverage,
7569 junction detection, and working with the nucleotide content of the
7571 (license license:artistic2.0)))
7573 (define-public r-rtracklayer
7575 (name "r-rtracklayer")
7579 (uri (bioconductor-uri "rtracklayer" version))
7582 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7583 (build-system r-build-system)
7586 (modify-phases %standard-phases
7587 (add-after 'unpack 'use-system-zlib
7589 (substitute* "DESCRIPTION"
7590 ((" zlibbioc,") ""))
7591 (substitute* "NAMESPACE"
7592 (("import\\(zlibbioc\\)") ""))
7597 `(("r-biocgenerics" ,r-biocgenerics)
7598 ("r-biostrings" ,r-biostrings)
7599 ("r-genomeinfodb" ,r-genomeinfodb)
7600 ("r-genomicalignments" ,r-genomicalignments)
7601 ("r-genomicranges" ,r-genomicranges)
7602 ("r-iranges" ,r-iranges)
7603 ("r-rcurl" ,r-rcurl)
7604 ("r-rsamtools" ,r-rsamtools)
7605 ("r-s4vectors" ,r-s4vectors)
7607 ("r-xvector" ,r-xvector)))
7608 (home-page "https://bioconductor.org/packages/rtracklayer")
7609 (synopsis "R interface to genome browsers and their annotation tracks")
7611 "rtracklayer is an extensible framework for interacting with multiple
7612 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7613 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7614 built-in). The user may export/import tracks to/from the supported browsers,
7615 as well as query and modify the browser state, such as the current viewport.")
7616 (license license:artistic2.0)))
7618 (define-public r-genomicfeatures
7620 (name "r-genomicfeatures")
7624 (uri (bioconductor-uri "GenomicFeatures" version))
7627 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7629 `((upstream-name . "GenomicFeatures")))
7630 (build-system r-build-system)
7632 `(("r-annotationdbi" ,r-annotationdbi)
7633 ("r-biobase" ,r-biobase)
7634 ("r-biocgenerics" ,r-biocgenerics)
7635 ("r-biomart" ,r-biomart)
7636 ("r-biostrings" ,r-biostrings)
7638 ("r-genomeinfodb" ,r-genomeinfodb)
7639 ("r-genomicranges" ,r-genomicranges)
7640 ("r-iranges" ,r-iranges)
7641 ("r-rcurl" ,r-rcurl)
7642 ("r-rsqlite" ,r-rsqlite)
7643 ("r-rmysql" ,r-rmysql)
7644 ("r-rtracklayer" ,r-rtracklayer)
7645 ("r-s4vectors" ,r-s4vectors)
7646 ("r-xvector" ,r-xvector)))
7647 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7648 (synopsis "Tools for working with transcript centric annotations")
7650 "This package provides a set of tools and methods for making and
7651 manipulating transcript centric annotations. With these tools the user can
7652 easily download the genomic locations of the transcripts, exons and cds of a
7653 given organism, from either the UCSC Genome Browser or a BioMart
7654 database (more sources will be supported in the future). This information is
7655 then stored in a local database that keeps track of the relationship between
7656 transcripts, exons, cds and genes. Flexible methods are provided for
7657 extracting the desired features in a convenient format.")
7658 (license license:artistic2.0)))
7660 (define-public r-go-db
7666 (uri (string-append "https://www.bioconductor.org/packages/"
7667 "release/data/annotation/src/contrib/GO.db_"
7671 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7673 `((upstream-name . "GO.db")))
7674 (build-system r-build-system)
7676 `(("r-annotationdbi" ,r-annotationdbi)))
7677 (home-page "https://bioconductor.org/packages/GO.db")
7678 (synopsis "Annotation maps describing the entire Gene Ontology")
7680 "The purpose of this GO.db annotation package is to provide detailed
7681 information about the latest version of the Gene Ontologies.")
7682 (license license:artistic2.0)))
7684 (define-public r-graph
7690 (uri (bioconductor-uri "graph" version))
7693 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7694 (build-system r-build-system)
7696 `(("r-biocgenerics" ,r-biocgenerics)))
7697 (home-page "https://bioconductor.org/packages/graph")
7698 (synopsis "Handle graph data structures in R")
7700 "This package implements some simple graph handling capabilities for R.")
7701 (license license:artistic2.0)))
7703 (define-public r-topgo
7709 (uri (bioconductor-uri "topGO" version))
7712 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7714 `((upstream-name . "topGO")))
7715 (build-system r-build-system)
7717 `(("r-annotationdbi" ,r-annotationdbi)
7719 ("r-biobase" ,r-biobase)
7720 ("r-biocgenerics" ,r-biocgenerics)
7721 ("r-go-db" ,r-go-db)
7722 ("r-graph" ,r-graph)
7723 ("r-lattice" ,r-lattice)
7724 ("r-matrixstats" ,r-matrixstats)
7725 ("r-sparsem" ,r-sparsem)))
7726 (home-page "https://bioconductor.org/packages/topGO")
7727 (synopsis "Enrichment analysis for gene ontology")
7729 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7730 terms while accounting for the topology of the GO graph. Different test
7731 statistics and different methods for eliminating local similarities and
7732 dependencies between GO terms can be implemented and applied.")
7733 ;; Any version of the LGPL applies.
7734 (license license:lgpl2.1+)))
7736 (define-public r-bsgenome
7742 (uri (bioconductor-uri "BSgenome" version))
7745 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7747 `((upstream-name . "BSgenome")))
7748 (build-system r-build-system)
7750 `(("r-biocgenerics" ,r-biocgenerics)
7751 ("r-biostrings" ,r-biostrings)
7752 ("r-genomeinfodb" ,r-genomeinfodb)
7753 ("r-genomicranges" ,r-genomicranges)
7754 ("r-iranges" ,r-iranges)
7755 ("r-rsamtools" ,r-rsamtools)
7756 ("r-rtracklayer" ,r-rtracklayer)
7757 ("r-s4vectors" ,r-s4vectors)
7758 ("r-xvector" ,r-xvector)))
7759 (home-page "https://bioconductor.org/packages/BSgenome")
7760 (synopsis "Infrastructure for Biostrings-based genome data packages")
7762 "This package provides infrastructure shared by all Biostrings-based
7763 genome data packages and support for efficient SNP representation.")
7764 (license license:artistic2.0)))
7766 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7768 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7772 ;; We cannot use bioconductor-uri here because this tarball is
7773 ;; located under "data/annotation/" instead of "bioc/".
7774 (uri (string-append "https://www.bioconductor.org/packages/"
7775 "release/data/annotation/src/contrib/"
7776 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7780 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7782 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7783 (build-system r-build-system)
7784 ;; As this package provides little more than a very large data file it
7785 ;; doesn't make sense to build substitutes.
7786 (arguments `(#:substitutable? #f))
7788 `(("r-bsgenome" ,r-bsgenome)))
7790 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7791 (synopsis "Full genome sequences for Homo sapiens")
7793 "This package provides full genome sequences for Homo sapiens from
7794 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7795 (license license:artistic2.0)))
7797 (define-public r-impute
7803 (uri (bioconductor-uri "impute" version))
7806 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7808 `(("gfortran" ,gfortran)))
7809 (build-system r-build-system)
7810 (home-page "https://bioconductor.org/packages/impute")
7811 (synopsis "Imputation for microarray data")
7813 "This package provides a function to impute missing gene expression
7814 microarray data, using nearest neighbor averaging.")
7815 (license license:gpl2+)))
7817 (define-public r-seqpattern
7819 (name "r-seqpattern")
7823 (uri (bioconductor-uri "seqPattern" version))
7826 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7828 `((upstream-name . "seqPattern")))
7829 (build-system r-build-system)
7831 `(("r-biostrings" ,r-biostrings)
7832 ("r-genomicranges" ,r-genomicranges)
7833 ("r-iranges" ,r-iranges)
7834 ("r-kernsmooth" ,r-kernsmooth)
7835 ("r-plotrix" ,r-plotrix)))
7836 (home-page "https://bioconductor.org/packages/seqPattern")
7837 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7839 "This package provides tools to visualize oligonucleotide patterns and
7840 sequence motif occurrences across a large set of sequences centred at a common
7841 reference point and sorted by a user defined feature.")
7842 (license license:gpl3+)))
7844 (define-public r-genomation
7846 (name "r-genomation")
7850 (uri (bioconductor-uri "genomation" version))
7853 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7854 (build-system r-build-system)
7856 `(("r-biostrings" ,r-biostrings)
7857 ("r-bsgenome" ,r-bsgenome)
7858 ("r-data-table" ,r-data-table)
7859 ("r-genomeinfodb" ,r-genomeinfodb)
7860 ("r-genomicalignments" ,r-genomicalignments)
7861 ("r-genomicranges" ,r-genomicranges)
7862 ("r-ggplot2" ,r-ggplot2)
7863 ("r-gridbase" ,r-gridbase)
7864 ("r-impute" ,r-impute)
7865 ("r-iranges" ,r-iranges)
7866 ("r-matrixstats" ,r-matrixstats)
7867 ("r-plotrix" ,r-plotrix)
7870 ("r-readr" ,r-readr)
7871 ("r-reshape2" ,r-reshape2)
7872 ("r-rsamtools" ,r-rsamtools)
7873 ("r-rtracklayer" ,r-rtracklayer)
7874 ("r-runit" ,r-runit)
7875 ("r-s4vectors" ,r-s4vectors)
7876 ("r-seqpattern" ,r-seqpattern)))
7877 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7878 (synopsis "Summary, annotation and visualization of genomic data")
7880 "This package provides a package for summary and annotation of genomic
7881 intervals. Users can visualize and quantify genomic intervals over
7882 pre-defined functional regions, such as promoters, exons, introns, etc. The
7883 genomic intervals represent regions with a defined chromosome position, which
7884 may be associated with a score, such as aligned reads from HT-seq experiments,
7885 TF binding sites, methylation scores, etc. The package can use any tabular
7886 genomic feature data as long as it has minimal information on the locations of
7887 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7888 (license license:artistic2.0)))
7890 (define-public r-genomationdata
7892 (name "r-genomationdata")
7896 ;; We cannot use bioconductor-uri here because this tarball is
7897 ;; located under "data/annotation/" instead of "bioc/".
7898 (uri (string-append "https://bioconductor.org/packages/"
7899 "release/data/experiment/src/contrib/"
7900 "genomationData_" version ".tar.gz"))
7903 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7904 (build-system r-build-system)
7905 ;; As this package provides little more than large data files, it doesn't
7906 ;; make sense to build substitutes.
7907 (arguments `(#:substitutable? #f))
7909 `(("r-knitr" ,r-knitr)))
7910 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7911 (synopsis "Experimental data for use with the genomation package")
7913 "This package contains experimental genetic data for use with the
7914 genomation package. Included are Chip Seq, Methylation and Cage data,
7915 downloaded from Encode.")
7916 (license license:gpl3+)))
7918 (define-public r-org-hs-eg-db
7920 (name "r-org-hs-eg-db")
7924 ;; We cannot use bioconductor-uri here because this tarball is
7925 ;; located under "data/annotation/" instead of "bioc/".
7926 (uri (string-append "https://www.bioconductor.org/packages/"
7927 "release/data/annotation/src/contrib/"
7928 "org.Hs.eg.db_" version ".tar.gz"))
7931 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7933 `((upstream-name . "org.Hs.eg.db")))
7934 (build-system r-build-system)
7936 `(("r-annotationdbi" ,r-annotationdbi)))
7937 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7938 (synopsis "Genome wide annotation for Human")
7940 "This package contains genome-wide annotations for Human, primarily based
7941 on mapping using Entrez Gene identifiers.")
7942 (license license:artistic2.0)))
7944 (define-public r-org-ce-eg-db
7946 (name "r-org-ce-eg-db")
7950 ;; We cannot use bioconductor-uri here because this tarball is
7951 ;; located under "data/annotation/" instead of "bioc/".
7952 (uri (string-append "https://www.bioconductor.org/packages/"
7953 "release/data/annotation/src/contrib/"
7954 "org.Ce.eg.db_" version ".tar.gz"))
7957 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7959 `((upstream-name . "org.Ce.eg.db")))
7960 (build-system r-build-system)
7962 `(("r-annotationdbi" ,r-annotationdbi)))
7963 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7964 (synopsis "Genome wide annotation for Worm")
7966 "This package provides mappings from Entrez gene identifiers to various
7967 annotations for the genome of the model worm Caenorhabditis elegans.")
7968 (license license:artistic2.0)))
7970 (define-public r-org-dm-eg-db
7972 (name "r-org-dm-eg-db")
7976 ;; We cannot use bioconductor-uri here because this tarball is
7977 ;; located under "data/annotation/" instead of "bioc/".
7978 (uri (string-append "https://www.bioconductor.org/packages/"
7979 "release/data/annotation/src/contrib/"
7980 "org.Dm.eg.db_" version ".tar.gz"))
7983 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
7985 `((upstream-name . "org.Dm.eg.db")))
7986 (build-system r-build-system)
7988 `(("r-annotationdbi" ,r-annotationdbi)))
7989 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7990 (synopsis "Genome wide annotation for Fly")
7992 "This package provides mappings from Entrez gene identifiers to various
7993 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7994 (license license:artistic2.0)))
7996 (define-public r-org-mm-eg-db
7998 (name "r-org-mm-eg-db")
8002 ;; We cannot use bioconductor-uri here because this tarball is
8003 ;; located under "data/annotation/" instead of "bioc/".
8004 (uri (string-append "https://www.bioconductor.org/packages/"
8005 "release/data/annotation/src/contrib/"
8006 "org.Mm.eg.db_" version ".tar.gz"))
8009 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8011 `((upstream-name . "org.Mm.eg.db")))
8012 (build-system r-build-system)
8014 `(("r-annotationdbi" ,r-annotationdbi)))
8015 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8016 (synopsis "Genome wide annotation for Mouse")
8018 "This package provides mappings from Entrez gene identifiers to various
8019 annotations for the genome of the model mouse Mus musculus.")
8020 (license license:artistic2.0)))
8022 (define-public r-seqlogo
8029 (uri (bioconductor-uri "seqLogo" version))
8032 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
8033 (properties `((upstream-name . "seqLogo")))
8034 (build-system r-build-system)
8035 (home-page "https://bioconductor.org/packages/seqLogo")
8036 (synopsis "Sequence logos for DNA sequence alignments")
8038 "seqLogo takes the position weight matrix of a DNA sequence motif and
8039 plots the corresponding sequence logo as introduced by Schneider and
8041 (license license:lgpl2.0+)))
8043 (define-public r-bsgenome-hsapiens-ucsc-hg19
8045 (name "r-bsgenome-hsapiens-ucsc-hg19")
8049 ;; We cannot use bioconductor-uri here because this tarball is
8050 ;; located under "data/annotation/" instead of "bioc/".
8051 (uri (string-append "https://www.bioconductor.org/packages/"
8052 "release/data/annotation/src/contrib/"
8053 "BSgenome.Hsapiens.UCSC.hg19_"
8057 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8059 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8060 (build-system r-build-system)
8061 ;; As this package provides little more than a very large data file it
8062 ;; doesn't make sense to build substitutes.
8063 (arguments `(#:substitutable? #f))
8065 `(("r-bsgenome" ,r-bsgenome)))
8067 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8068 (synopsis "Full genome sequences for Homo sapiens")
8070 "This package provides full genome sequences for Homo sapiens as provided
8071 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8072 (license license:artistic2.0)))
8074 (define-public r-bsgenome-mmusculus-ucsc-mm9
8076 (name "r-bsgenome-mmusculus-ucsc-mm9")
8080 ;; We cannot use bioconductor-uri here because this tarball is
8081 ;; located under "data/annotation/" instead of "bioc/".
8082 (uri (string-append "https://www.bioconductor.org/packages/"
8083 "release/data/annotation/src/contrib/"
8084 "BSgenome.Mmusculus.UCSC.mm9_"
8088 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8090 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8091 (build-system r-build-system)
8092 ;; As this package provides little more than a very large data file it
8093 ;; doesn't make sense to build substitutes.
8094 (arguments `(#:substitutable? #f))
8096 `(("r-bsgenome" ,r-bsgenome)))
8098 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8099 (synopsis "Full genome sequences for Mouse")
8101 "This package provides full genome sequences for Mus musculus (Mouse) as
8102 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8103 (license license:artistic2.0)))
8105 (define-public r-bsgenome-mmusculus-ucsc-mm10
8107 (name "r-bsgenome-mmusculus-ucsc-mm10")
8111 ;; We cannot use bioconductor-uri here because this tarball is
8112 ;; located under "data/annotation/" instead of "bioc/".
8113 (uri (string-append "https://www.bioconductor.org/packages/"
8114 "release/data/annotation/src/contrib/"
8115 "BSgenome.Mmusculus.UCSC.mm10_"
8119 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8121 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8122 (build-system r-build-system)
8123 ;; As this package provides little more than a very large data file it
8124 ;; doesn't make sense to build substitutes.
8125 (arguments `(#:substitutable? #f))
8127 `(("r-bsgenome" ,r-bsgenome)))
8129 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8130 (synopsis "Full genome sequences for Mouse")
8132 "This package provides full genome sequences for Mus
8133 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8134 in Biostrings objects.")
8135 (license license:artistic2.0)))
8137 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8139 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8143 ;; We cannot use bioconductor-uri here because this tarball is
8144 ;; located under "data/annotation/" instead of "bioc/".
8145 (uri (string-append "https://www.bioconductor.org/packages/"
8146 "release/data/annotation/src/contrib/"
8147 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8151 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8153 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8154 (build-system r-build-system)
8155 ;; As this package provides little more than a very large data file it
8156 ;; doesn't make sense to build substitutes.
8157 (arguments `(#:substitutable? #f))
8159 `(("r-bsgenome" ,r-bsgenome)
8160 ("r-genomicfeatures" ,r-genomicfeatures)
8161 ("r-annotationdbi" ,r-annotationdbi)))
8163 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8164 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8166 "This package loads a TxDb object, which is an R interface to
8167 prefabricated databases contained in this package. This package provides
8168 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8169 based on the knownGene track.")
8170 (license license:artistic2.0)))
8172 (define-public r-bsgenome-celegans-ucsc-ce6
8174 (name "r-bsgenome-celegans-ucsc-ce6")
8178 ;; We cannot use bioconductor-uri here because this tarball is
8179 ;; located under "data/annotation/" instead of "bioc/".
8180 (uri (string-append "https://www.bioconductor.org/packages/"
8181 "release/data/annotation/src/contrib/"
8182 "BSgenome.Celegans.UCSC.ce6_"
8186 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8188 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8189 (build-system r-build-system)
8190 ;; As this package provides little more than a very large data file it
8191 ;; doesn't make sense to build substitutes.
8192 (arguments `(#:substitutable? #f))
8194 `(("r-bsgenome" ,r-bsgenome)))
8196 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8197 (synopsis "Full genome sequences for Worm")
8199 "This package provides full genome sequences for Caenorhabditis
8200 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8202 (license license:artistic2.0)))
8204 (define-public r-bsgenome-celegans-ucsc-ce10
8206 (name "r-bsgenome-celegans-ucsc-ce10")
8210 ;; We cannot use bioconductor-uri here because this tarball is
8211 ;; located under "data/annotation/" instead of "bioc/".
8212 (uri (string-append "https://www.bioconductor.org/packages/"
8213 "release/data/annotation/src/contrib/"
8214 "BSgenome.Celegans.UCSC.ce10_"
8218 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8220 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8221 (build-system r-build-system)
8222 ;; As this package provides little more than a very large data file it
8223 ;; doesn't make sense to build substitutes.
8224 (arguments `(#:substitutable? #f))
8226 `(("r-bsgenome" ,r-bsgenome)))
8228 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8229 (synopsis "Full genome sequences for Worm")
8231 "This package provides full genome sequences for Caenorhabditis
8232 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8234 (license license:artistic2.0)))
8236 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8238 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8242 ;; We cannot use bioconductor-uri here because this tarball is
8243 ;; located under "data/annotation/" instead of "bioc/".
8244 (uri (string-append "https://www.bioconductor.org/packages/"
8245 "release/data/annotation/src/contrib/"
8246 "BSgenome.Dmelanogaster.UCSC.dm3_"
8250 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8252 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8253 (build-system r-build-system)
8254 ;; As this package provides little more than a very large data file it
8255 ;; doesn't make sense to build substitutes.
8256 (arguments `(#:substitutable? #f))
8258 `(("r-bsgenome" ,r-bsgenome)))
8260 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8261 (synopsis "Full genome sequences for Fly")
8263 "This package provides full genome sequences for Drosophila
8264 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8265 Biostrings objects.")
8266 (license license:artistic2.0)))
8268 (define-public r-motifrg
8275 (uri (bioconductor-uri "motifRG" version))
8278 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8279 (properties `((upstream-name . "motifRG")))
8280 (build-system r-build-system)
8282 `(("r-biostrings" ,r-biostrings)
8283 ("r-bsgenome" ,r-bsgenome)
8284 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8285 ("r-iranges" ,r-iranges)
8286 ("r-seqlogo" ,r-seqlogo)
8287 ("r-xvector" ,r-xvector)))
8288 (home-page "https://bioconductor.org/packages/motifRG")
8289 (synopsis "Discover motifs in high throughput sequencing data")
8291 "This package provides tools for discriminative motif discovery in high
8292 throughput genetic sequencing data sets using regression methods.")
8293 (license license:artistic2.0)))
8295 (define-public r-qtl
8302 (uri (string-append "mirror://cran/src/contrib/qtl_"
8306 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8307 (build-system r-build-system)
8308 (home-page "http://rqtl.org/")
8309 (synopsis "R package for analyzing QTL experiments in genetics")
8310 (description "R/qtl is an extension library for the R statistics
8311 system. It is used to analyze experimental crosses for identifying
8312 genes contributing to variation in quantitative traits (so-called
8313 quantitative trait loci, QTLs).
8315 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8316 identify genotyping errors, and to perform single-QTL and two-QTL,
8317 two-dimensional genome scans.")
8318 (license license:gpl3)))
8320 (define-public r-zlibbioc
8326 (uri (bioconductor-uri "zlibbioc" version))
8329 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8331 `((upstream-name . "zlibbioc")))
8332 (build-system r-build-system)
8333 (home-page "https://bioconductor.org/packages/zlibbioc")
8334 (synopsis "Provider for zlib-1.2.5 to R packages")
8335 (description "This package uses the source code of zlib-1.2.5 to create
8336 libraries for systems that do not have these available via other means.")
8337 (license license:artistic2.0)))
8339 (define-public r-r4rna
8346 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8350 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8351 (build-system r-build-system)
8353 `(("r-optparse" ,r-optparse)
8354 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8355 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8356 (synopsis "Analysis framework for RNA secondary structure")
8358 "The R4RNA package aims to be a general framework for the analysis of RNA
8359 secondary structure and comparative analysis in R.")
8360 (license license:gpl3+)))
8362 (define-public r-rhtslib
8369 (uri (bioconductor-uri "Rhtslib" version))
8372 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8373 (properties `((upstream-name . "Rhtslib")))
8374 (build-system r-build-system)
8376 `(("r-zlibbioc" ,r-zlibbioc)))
8380 `(("autoconf" ,autoconf)))
8381 (home-page "https://github.com/nhayden/Rhtslib")
8382 (synopsis "High-throughput sequencing library as an R package")
8384 "This package provides the HTSlib C library for high-throughput
8385 nucleotide sequence analysis. The package is primarily useful to developers
8386 of other R packages who wish to make use of HTSlib.")
8387 (license license:lgpl2.0+)))
8389 (define-public r-bamsignals
8391 (name "r-bamsignals")
8396 (uri (bioconductor-uri "bamsignals" version))
8399 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8400 (build-system r-build-system)
8402 `(("r-biocgenerics" ,r-biocgenerics)
8403 ("r-genomicranges" ,r-genomicranges)
8404 ("r-iranges" ,r-iranges)
8406 ("r-rhtslib" ,r-rhtslib)
8407 ("r-zlibbioc" ,r-zlibbioc)))
8410 (home-page "https://bioconductor.org/packages/bamsignals")
8411 (synopsis "Extract read count signals from bam files")
8413 "This package allows to efficiently obtain count vectors from indexed bam
8414 files. It counts the number of nucleotide sequence reads in given genomic
8415 ranges and it computes reads profiles and coverage profiles. It also handles
8417 (license license:gpl2+)))
8419 (define-public r-rcas
8425 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8427 (file-name (string-append name "-" version ".tar.gz"))
8430 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8431 (build-system r-build-system)
8433 `(("r-knitr" ,r-knitr)
8434 ("r-testthat" ,r-testthat)
8435 ;; During vignette building knitr checks that "pandoc-citeproc"
8437 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)))
8439 `(("r-data-table" ,r-data-table)
8440 ("r-biomart" ,r-biomart)
8441 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8442 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8443 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8444 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8445 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8446 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8447 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8448 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8449 ("r-topgo" ,r-topgo)
8451 ("r-pbapply" ,r-pbapply)
8452 ("r-plotly" ,r-plotly)
8453 ("r-plotrix" ,r-plotrix)
8454 ("r-motifrg" ,r-motifrg)
8455 ("r-genomation" ,r-genomation)
8456 ("r-genomicfeatures" ,r-genomicfeatures)
8457 ("r-rtracklayer" ,r-rtracklayer)
8458 ("r-rmarkdown" ,r-rmarkdown)))
8459 (synopsis "RNA-centric annotation system")
8461 "RCAS aims to be a standalone RNA-centric annotation system that provides
8462 intuitive reports and publication-ready graphics. This package provides the R
8463 library implementing most of the pipeline's features.")
8464 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8465 (license license:artistic2.0)))
8467 (define-public rcas-web
8474 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8475 "releases/download/v" version
8476 "/rcas-web-" version ".tar.gz"))
8479 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8480 (build-system gnu-build-system)
8483 (modify-phases %standard-phases
8484 (add-after 'install 'wrap-executable
8485 (lambda* (#:key inputs outputs #:allow-other-keys)
8486 (let* ((out (assoc-ref outputs "out"))
8487 (json (assoc-ref inputs "guile-json"))
8488 (redis (assoc-ref inputs "guile-redis"))
8489 (path (string-append
8490 json "/share/guile/site/2.2:"
8491 redis "/share/guile/site/2.2")))
8492 (wrap-program (string-append out "/bin/rcas-web")
8493 `("GUILE_LOAD_PATH" ":" = (,path))
8494 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8495 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8498 `(("r-minimal" ,r-minimal)
8500 ("guile-next" ,guile-2.2)
8501 ("guile-json" ,guile-json)
8502 ("guile-redis" ,guile2.2-redis)))
8504 `(("pkg-config" ,pkg-config)))
8505 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8506 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8507 (description "This package provides a simple web interface for the
8508 @dfn{RNA-centric annotation system} (RCAS).")
8509 (license license:agpl3+)))
8511 (define-public r-mutationalpatterns
8513 (name "r-mutationalpatterns")
8518 (uri (bioconductor-uri "MutationalPatterns" version))
8521 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8522 (build-system r-build-system)
8524 `(("r-biocgenerics" ,r-biocgenerics)
8525 ("r-biostrings" ,r-biostrings)
8526 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8527 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8528 ("r-genomicranges" ,r-genomicranges)
8529 ("r-genomeinfodb" ,r-genomeinfodb)
8530 ("r-ggplot2" ,r-ggplot2)
8531 ("r-gridextra" ,r-gridextra)
8532 ("r-iranges" ,r-iranges)
8535 ("r-pracma" ,r-pracma)
8536 ("r-reshape2" ,r-reshape2)
8537 ("r-cowplot" ,r-cowplot)
8538 ("r-ggdendro" ,r-ggdendro)
8539 ("r-s4vectors" ,r-s4vectors)
8540 ("r-summarizedexperiment" ,r-summarizedexperiment)
8541 ("r-variantannotation" ,r-variantannotation)))
8542 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8543 (synopsis "Extract and visualize mutational patterns in genomic data")
8544 (description "This package provides an extensive toolset for the
8545 characterization and visualization of a wide range of mutational patterns
8546 in SNV base substitution data.")
8547 (license license:expat)))
8549 (define-public r-wgcna
8556 (uri (cran-uri "WGCNA" version))
8559 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8560 (properties `((upstream-name . "WGCNA")))
8561 (build-system r-build-system)
8563 `(("r-annotationdbi" ,r-annotationdbi)
8564 ("r-doparallel" ,r-doparallel)
8565 ("r-dynamictreecut" ,r-dynamictreecut)
8566 ("r-fastcluster" ,r-fastcluster)
8567 ("r-foreach" ,r-foreach)
8568 ("r-go-db" ,r-go-db)
8569 ("r-hmisc" ,r-hmisc)
8570 ("r-impute" ,r-impute)
8572 ("r-robust" ,r-robust)
8573 ("r-survival" ,r-survival)
8574 ("r-matrixstats" ,r-matrixstats)
8575 ("r-preprocesscore" ,r-preprocesscore)))
8577 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8578 (synopsis "Weighted correlation network analysis")
8580 "This package provides functions necessary to perform Weighted
8581 Correlation Network Analysis on high-dimensional data. It includes functions
8582 for rudimentary data cleaning, construction and summarization of correlation
8583 networks, module identification and functions for relating both variables and
8584 modules to sample traits. It also includes a number of utility functions for
8585 data manipulation and visualization.")
8586 (license license:gpl2+)))
8588 (define-public r-chipkernels
8589 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8592 (name "r-chipkernels")
8593 (version (string-append "1.1-" revision "." (string-take commit 9)))
8598 (url "https://github.com/ManuSetty/ChIPKernels.git")
8600 (file-name (string-append name "-" version))
8603 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8604 (build-system r-build-system)
8606 `(("r-iranges" ,r-iranges)
8607 ("r-xvector" ,r-xvector)
8608 ("r-biostrings" ,r-biostrings)
8609 ("r-bsgenome" ,r-bsgenome)
8610 ("r-gtools" ,r-gtools)
8611 ("r-genomicranges" ,r-genomicranges)
8612 ("r-sfsmisc" ,r-sfsmisc)
8613 ("r-kernlab" ,r-kernlab)
8614 ("r-s4vectors" ,r-s4vectors)
8615 ("r-biocgenerics" ,r-biocgenerics)))
8616 (home-page "https://github.com/ManuSetty/ChIPKernels")
8617 (synopsis "Build string kernels for DNA Sequence analysis")
8618 (description "ChIPKernels is an R package for building different string
8619 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8620 must be built and this dictionary can be used for determining kernels for DNA
8622 (license license:gpl2+))))
8624 (define-public r-seqgl
8631 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8632 "archive/" version ".tar.gz"))
8633 (file-name (string-append name "-" version ".tar.gz"))
8636 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8637 (build-system r-build-system)
8639 `(("r-biostrings" ,r-biostrings)
8640 ("r-chipkernels" ,r-chipkernels)
8641 ("r-genomicranges" ,r-genomicranges)
8642 ("r-spams" ,r-spams)
8643 ("r-wgcna" ,r-wgcna)
8644 ("r-fastcluster" ,r-fastcluster)))
8645 (home-page "https://github.com/ManuSetty/SeqGL")
8646 (synopsis "Group lasso for Dnase/ChIP-seq data")
8647 (description "SeqGL is a group lasso based algorithm to extract
8648 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8649 This package presents a method which uses group lasso to discriminate between
8650 bound and non bound genomic regions to accurately identify transcription
8651 factors bound at the specific regions.")
8652 (license license:gpl2+)))
8654 (define-public r-gkmsvm
8661 (uri (cran-uri "gkmSVM" version))
8664 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8665 (properties `((upstream-name . "gkmSVM")))
8666 (build-system r-build-system)
8668 `(("r-biocgenerics" ,r-biocgenerics)
8669 ("r-biostrings" ,r-biostrings)
8670 ("r-genomeinfodb" ,r-genomeinfodb)
8671 ("r-genomicranges" ,r-genomicranges)
8672 ("r-iranges" ,r-iranges)
8673 ("r-kernlab" ,r-kernlab)
8676 ("r-rtracklayer" ,r-rtracklayer)
8677 ("r-s4vectors" ,r-s4vectors)
8678 ("r-seqinr" ,r-seqinr)))
8679 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8680 (synopsis "Gapped-kmer support vector machine")
8682 "This R package provides tools for training gapped-kmer SVM classifiers
8683 for DNA and protein sequences. This package supports several sequence
8684 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8685 (license license:gpl2+)))
8687 (define-public r-tximport
8693 (uri (bioconductor-uri "tximport" version))
8696 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8697 (build-system r-build-system)
8698 (home-page "https://bioconductor.org/packages/tximport")
8699 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8701 "This package provides tools to import transcript-level abundance,
8702 estimated counts and transcript lengths, and to summarize them into matrices
8703 for use with downstream gene-level analysis packages. Average transcript
8704 length, weighted by sample-specific transcript abundance estimates, is
8705 provided as a matrix which can be used as an offset for different expression
8706 of gene-level counts.")
8707 (license license:gpl2+)))
8709 (define-public r-rhdf5
8715 (uri (bioconductor-uri "rhdf5" version))
8718 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8719 (build-system r-build-system)
8722 (modify-phases %standard-phases
8723 (add-after 'unpack 'unpack-smallhdf5
8724 (lambda* (#:key outputs #:allow-other-keys)
8725 (system* "tar" "-xzvf"
8726 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8727 (substitute* "src/hdf5/configure"
8729 ;; Remove timestamp and host system information to make
8730 ;; the build reproducible.
8731 (substitute* "src/hdf5/src/libhdf5.settings.in"
8732 (("Configured on: @CONFIG_DATE@")
8733 "Configured on: Guix")
8734 (("Uname information:.*")
8735 "Uname information: Linux\n")
8736 ;; Remove unnecessary store reference.
8738 "C Compiler: GCC\n"))
8741 `(("r-zlibbioc" ,r-zlibbioc)))
8745 (home-page "https://bioconductor.org/packages/rhdf5")
8746 (synopsis "HDF5 interface to R")
8748 "This R/Bioconductor package provides an interface between HDF5 and R.
8749 HDF5's main features are the ability to store and access very large and/or
8750 complex datasets and a wide variety of metadata on mass storage (disk) through
8751 a completely portable file format. The rhdf5 package is thus suited for the
8752 exchange of large and/or complex datasets between R and other software
8753 package, and for letting R applications work on datasets that are larger than
8754 the available RAM.")
8755 (license license:artistic2.0)))
8757 (define-public r-annotationfilter
8759 (name "r-annotationfilter")
8763 (uri (bioconductor-uri "AnnotationFilter" version))
8766 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8768 `((upstream-name . "AnnotationFilter")))
8769 (build-system r-build-system)
8771 `(("r-genomicranges" ,r-genomicranges)
8772 ("r-lazyeval" ,r-lazyeval)))
8773 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8774 (synopsis "Facilities for filtering Bioconductor annotation resources")
8776 "This package provides classes and other infrastructure to implement
8777 filters for manipulating Bioconductor annotation resources. The filters are
8778 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8779 (license license:artistic2.0)))
8781 (define-public emboss
8787 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8788 (version-major+minor version) ".0/"
8789 "EMBOSS-" version ".tar.gz"))
8792 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8793 (build-system gnu-build-system)
8796 (list (string-append "--with-hpdf="
8797 (assoc-ref %build-inputs "libharu")))
8799 (modify-phases %standard-phases
8800 (add-after 'unpack 'fix-checks
8802 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8803 ;; and zlib, but assume that they are all found at the same
8805 (substitute* "configure.in"
8806 (("CHECK_PNGDRIVER")
8807 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8808 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8809 AM_CONDITIONAL(AMPNG, true)"))
8811 (add-after 'fix-checks 'disable-update-check
8813 ;; At build time there is no connection to the Internet, so
8814 ;; looking for updates will not work.
8815 (substitute* "Makefile.am"
8816 (("\\$\\(bindir\\)/embossupdate") ""))
8818 (add-after 'disable-update-check 'autogen
8819 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8825 ("libharu" ,libharu)
8828 `(("autoconf" ,autoconf)
8829 ("automake" ,automake)
8830 ("libtool" ,libtool)
8831 ("pkg-config" ,pkg-config)))
8832 (home-page "http://emboss.sourceforge.net")
8833 (synopsis "Molecular biology analysis suite")
8834 (description "EMBOSS is the \"European Molecular Biology Open Software
8835 Suite\". EMBOSS is an analysis package specially developed for the needs of
8836 the molecular biology (e.g. EMBnet) user community. The software
8837 automatically copes with data in a variety of formats and even allows
8838 transparent retrieval of sequence data from the web. It also provides a
8839 number of libraries for the development of software in the field of molecular
8840 biology. EMBOSS also integrates a range of currently available packages and
8841 tools for sequence analysis into a seamless whole.")
8842 (license license:gpl2+)))
8845 (let ((revision "1")
8846 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8849 ;; The version is 2.13.0 even though no release archives have been
8850 ;; published as yet.
8851 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8855 (url "https://github.com/arq5x/bits.git")
8857 (file-name (string-append name "-" version "-checkout"))
8860 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8861 (build-system gnu-build-system)
8863 `(#:tests? #f ;no tests included
8865 (modify-phases %standard-phases
8867 (add-after 'unpack 'remove-cuda
8869 (substitute* "Makefile"
8871 (("(bits_test_intersections) \\\\" _ match) match))
8874 (lambda* (#:key outputs #:allow-other-keys)
8876 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8881 (home-page "https://github.com/arq5x/bits")
8882 (synopsis "Implementation of binary interval search algorithm")
8883 (description "This package provides an implementation of the
8884 BITS (Binary Interval Search) algorithm, an approach to interval set
8885 intersection. It is especially suited for the comparison of diverse genomic
8886 datasets and the exploration of large datasets of genome
8887 intervals (e.g. genes, sequence alignments).")
8888 (license license:gpl2))))
8890 (define-public piranha
8891 ;; There is no release tarball for the latest version. The latest commit is
8892 ;; older than one year at the time of this writing.
8893 (let ((revision "1")
8894 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8897 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8901 (url "https://github.com/smithlabcode/piranha.git")
8903 (file-name (git-file-name name version))
8906 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8907 (build-system gnu-build-system)
8909 `(#:test-target "test"
8911 (modify-phases %standard-phases
8912 (add-after 'unpack 'copy-smithlab-cpp
8913 (lambda* (#:key inputs #:allow-other-keys)
8914 (for-each (lambda (file)
8915 (install-file file "./src/smithlab_cpp/"))
8916 (find-files (assoc-ref inputs "smithlab-cpp")))
8918 (add-after 'install 'install-to-store
8919 (lambda* (#:key outputs #:allow-other-keys)
8920 (let* ((out (assoc-ref outputs "out"))
8921 (bin (string-append out "/bin")))
8922 (for-each (lambda (file)
8923 (install-file file bin))
8924 (find-files "bin" ".*")))
8927 (list (string-append "--with-bam_tools_headers="
8928 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8929 (string-append "--with-bam_tools_library="
8930 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8932 `(("bamtools" ,bamtools)
8933 ("samtools" ,samtools-0.1)
8936 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8940 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8942 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8945 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8947 `(("python" ,python-2)))
8948 (home-page "https://github.com/smithlabcode/piranha")
8949 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8951 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8952 RIP-seq experiments. It takes input in BED or BAM format and identifies
8953 regions of statistically significant read enrichment. Additional covariates
8954 may optionally be provided to further inform the peak-calling process.")
8955 (license license:gpl3+))))
8963 (uri (string-append "https://pypi.python.org/packages/source/P"
8964 "/PePr/PePr-" version ".tar.gz"))
8967 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8968 (build-system python-build-system)
8970 `(#:python ,python-2 ; python2 only
8971 #:tests? #f)) ; no tests included
8973 `(("python2-numpy" ,python2-numpy)
8974 ("python2-scipy" ,python2-scipy)
8975 ("python2-pysam" ,python2-pysam)))
8976 (home-page "https://github.com/shawnzhangyx/PePr")
8977 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8979 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8980 that is primarily designed for data with biological replicates. It uses a
8981 negative binomial distribution to model the read counts among the samples in
8982 the same group, and look for consistent differences between ChIP and control
8983 group or two ChIP groups run under different conditions.")
8984 (license license:gpl3+)))
8986 (define-public filevercmp
8987 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8990 (version (string-append "0-1." (string-take commit 7)))
8993 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8995 (file-name (string-append name "-" version ".tar.gz"))
8997 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8998 (build-system gnu-build-system)
9000 `(#:tests? #f ; There are no tests to run.
9002 (modify-phases %standard-phases
9003 (delete 'configure) ; There is no configure phase.
9005 (lambda* (#:key outputs #:allow-other-keys)
9006 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9007 (install-file "filevercmp" bin)))))))
9008 (home-page "https://github.com/ekg/filevercmp")
9009 (synopsis "This program compares version strings")
9010 (description "This program compares version strings. It intends to be a
9011 replacement for strverscmp.")
9012 (license license:gpl3+))))
9014 (define-public multiqc
9021 (uri (pypi-uri "multiqc" version))
9024 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
9025 (build-system python-build-system)
9027 `(("python-jinja2" ,python-jinja2)
9028 ("python-simplejson" ,python-simplejson)
9029 ("python-pyyaml" ,python-pyyaml)
9030 ("python-click" ,python-click)
9031 ("python-spectra" ,python-spectra)
9032 ("python-requests" ,python-requests)
9033 ("python-markdown" ,python-markdown)
9034 ("python-lzstring" ,python-lzstring)
9035 ("python-matplotlib" ,python-matplotlib)
9036 ("python-numpy" ,python-numpy)
9037 ;; MultQC checks for the presence of nose at runtime.
9038 ("python-nose" ,python-nose)))
9039 (home-page "http://multiqc.info")
9040 (synopsis "Aggregate bioinformatics analysis reports")
9042 "MultiQC is a tool to aggregate bioinformatics results across many
9043 samples into a single report. It contains modules for a large number of
9044 common bioinformatics tools.")
9045 (license license:gpl3+)))
9047 (define-public r-chipseq
9054 (uri (bioconductor-uri "chipseq" version))
9057 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
9058 (build-system r-build-system)
9060 `(("r-biocgenerics" ,r-biocgenerics)
9061 ("r-genomicranges" ,r-genomicranges)
9062 ("r-iranges" ,r-iranges)
9063 ("r-lattice" ,r-lattice)
9064 ("r-s4vectors" ,r-s4vectors)
9065 ("r-shortread" ,r-shortread)))
9066 (home-page "https://bioconductor.org/packages/chipseq")
9067 (synopsis "Package for analyzing ChIPseq data")
9069 "This package provides tools for processing short read data from ChIPseq
9071 (license license:artistic2.0)))
9073 (define-public r-copyhelper
9075 (name "r-copyhelper")
9080 (uri (string-append "https://bioconductor.org/packages/release/"
9081 "data/experiment/src/contrib/CopyhelpeR_"
9085 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9086 (properties `((upstream-name . "CopyhelpeR")))
9087 (build-system r-build-system)
9088 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9089 (synopsis "Helper files for CopywriteR")
9091 "This package contains the helper files that are required to run the
9092 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9093 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9094 mm10. In addition, it contains a blacklist filter to remove regions that
9095 display copy number variation. Files are stored as GRanges objects from the
9096 GenomicRanges Bioconductor package.")
9097 (license license:gpl2)))
9099 (define-public r-copywriter
9101 (name "r-copywriter")
9106 (uri (bioconductor-uri "CopywriteR" version))
9109 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9110 (properties `((upstream-name . "CopywriteR")))
9111 (build-system r-build-system)
9113 `(("r-biocparallel" ,r-biocparallel)
9114 ("r-chipseq" ,r-chipseq)
9115 ("r-copyhelper" ,r-copyhelper)
9116 ("r-data-table" ,r-data-table)
9117 ("r-dnacopy" ,r-dnacopy)
9118 ("r-futile-logger" ,r-futile-logger)
9119 ("r-genomeinfodb" ,r-genomeinfodb)
9120 ("r-genomicalignments" ,r-genomicalignments)
9121 ("r-genomicranges" ,r-genomicranges)
9122 ("r-gtools" ,r-gtools)
9123 ("r-iranges" ,r-iranges)
9124 ("r-matrixstats" ,r-matrixstats)
9125 ("r-rsamtools" ,r-rsamtools)
9126 ("r-s4vectors" ,r-s4vectors)))
9127 (home-page "https://github.com/PeeperLab/CopywriteR")
9128 (synopsis "Copy number information from targeted sequencing")
9130 "CopywriteR extracts DNA copy number information from targeted sequencing
9131 by utilizing off-target reads. It allows for extracting uniformly distributed
9132 copy number information, can be used without reference, and can be applied to
9133 sequencing data obtained from various techniques including chromatin
9134 immunoprecipitation and target enrichment on small gene panels. Thereby,
9135 CopywriteR constitutes a widely applicable alternative to available copy
9136 number detection tools.")
9137 (license license:gpl2)))
9139 (define-public r-methylkit
9141 (name "r-methylkit")
9145 (uri (bioconductor-uri "methylKit" version))
9148 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9149 (properties `((upstream-name . "methylKit")))
9150 (build-system r-build-system)
9152 `(("r-data-table" ,r-data-table)
9153 ("r-emdbook" ,r-emdbook)
9154 ("r-fastseg" ,r-fastseg)
9155 ("r-genomeinfodb" ,r-genomeinfodb)
9156 ("r-genomicranges" ,r-genomicranges)
9157 ("r-gtools" ,r-gtools)
9158 ("r-iranges" ,r-iranges)
9159 ("r-kernsmooth" ,r-kernsmooth)
9160 ("r-limma" ,r-limma)
9161 ("r-mclust" ,r-mclust)
9162 ("r-qvalue" ,r-qvalue)
9163 ("r-r-utils" ,r-r-utils)
9165 ("r-rhtslib" ,r-rhtslib)
9166 ("r-rsamtools" ,r-rsamtools)
9167 ("r-rtracklayer" ,r-rtracklayer)
9168 ("r-s4vectors" ,r-s4vectors)
9169 ("r-zlibbioc" ,r-zlibbioc)))
9172 (home-page "https://github.com/al2na/methylKit")
9174 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9176 "MethylKit is an R package for DNA methylation analysis and annotation
9177 from high-throughput bisulfite sequencing. The package is designed to deal
9178 with sequencing data from @dfn{Reduced representation bisulfite
9179 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9180 genome bisulfite sequencing. It also has functions to analyze base-pair
9181 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9183 (license license:artistic2.0)))
9185 (define-public r-sva
9192 (uri (bioconductor-uri "sva" version))
9195 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9196 (build-system r-build-system)
9198 `(("r-genefilter" ,r-genefilter)
9200 ("r-biocparallel" ,r-biocparallel)
9201 ("r-matrixstats" ,r-matrixstats)
9202 ("r-limma" ,r-limma)))
9203 (home-page "https://bioconductor.org/packages/sva")
9204 (synopsis "Surrogate variable analysis")
9206 "This package contains functions for removing batch effects and other
9207 unwanted variation in high-throughput experiment. It also contains functions
9208 for identifying and building surrogate variables for high-dimensional data
9209 sets. Surrogate variables are covariates constructed directly from
9210 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9211 imaging data that can be used in subsequent analyses to adjust for unknown,
9212 unmodeled, or latent sources of noise.")
9213 (license license:artistic2.0)))
9215 (define-public r-seqminer
9222 (uri (cran-uri "seqminer" version))
9225 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9226 (build-system r-build-system)
9229 (home-page "http://seqminer.genomic.codes")
9230 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9232 "This package provides tools to integrate nucleotide sequencing
9233 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9234 ;; Any version of the GPL is acceptable
9235 (license (list license:gpl2+ license:gpl3+))))
9237 (define-public r-raremetals2
9239 (name "r-raremetals2")
9244 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9245 "b/b7/RareMETALS2_" version ".tar.gz"))
9248 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9249 (properties `((upstream-name . "RareMETALS2")))
9250 (build-system r-build-system)
9252 `(("r-seqminer" ,r-seqminer)
9253 ("r-mvtnorm" ,r-mvtnorm)
9255 ("r-compquadform" ,r-compquadform)
9256 ("r-getopt" ,r-getopt)))
9257 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9258 (synopsis "Analyze gene-level association tests for binary trait")
9260 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9261 It was designed to meta-analyze gene-level association tests for binary trait.
9262 While rareMETALS offers a near-complete solution for meta-analysis of
9263 gene-level tests for quantitative trait, it does not offer the optimal
9264 solution for binary trait. The package rareMETALS2 offers improved features
9265 for analyzing gene-level association tests in meta-analyses for binary
9267 (license license:gpl3)))
9269 (define-public r-maldiquant
9271 (name "r-maldiquant")
9276 (uri (cran-uri "MALDIquant" version))
9279 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9280 (properties `((upstream-name . "MALDIquant")))
9281 (build-system r-build-system)
9282 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9283 (synopsis "Quantitative analysis of mass spectrometry data")
9285 "This package provides a complete analysis pipeline for matrix-assisted
9286 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9287 two-dimensional mass spectrometry data. In addition to commonly used plotting
9288 and processing methods it includes distinctive features, namely baseline
9289 subtraction methods such as morphological filters (TopHat) or the
9290 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9291 alignment using warping functions, handling of replicated measurements as well
9292 as allowing spectra with different resolutions.")
9293 (license license:gpl3+)))
9295 (define-public r-protgenerics
9297 (name "r-protgenerics")
9302 (uri (bioconductor-uri "ProtGenerics" version))
9305 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9306 (properties `((upstream-name . "ProtGenerics")))
9307 (build-system r-build-system)
9308 (home-page "https://github.com/lgatto/ProtGenerics")
9309 (synopsis "S4 generic functions for proteomics infrastructure")
9311 "This package provides S4 generic functions needed by Bioconductor
9312 proteomics packages.")
9313 (license license:artistic2.0)))
9315 (define-public r-mzr
9322 (uri (bioconductor-uri "mzR" version))
9325 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9326 (modules '((guix build utils)))
9329 (delete-file-recursively "src/boost")
9331 (properties `((upstream-name . "mzR")))
9332 (build-system r-build-system)
9335 (modify-phases %standard-phases
9336 (add-after 'unpack 'use-system-boost
9338 (substitute* "src/Makevars"
9339 (("\\./boost/libs.*") "")
9340 (("ARCH_OBJS=" line)
9342 "\nARCH_LIBS=-lboost_system -lboost_regex \
9343 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9346 `(("boost" ,boost) ; use this instead of the bundled boost sources
9347 ("netcdf" ,netcdf)))
9349 `(("r-biobase" ,r-biobase)
9350 ("r-biocgenerics" ,r-biocgenerics)
9351 ("r-protgenerics" ,r-protgenerics)
9353 ("r-zlibbioc" ,r-zlibbioc)))
9354 (home-page "https://github.com/sneumann/mzR/")
9355 (synopsis "Parser for mass spectrometry data files")
9357 "The mzR package provides a unified API to the common file formats and
9358 parsers available for mass spectrometry data. It comes with a wrapper for the
9359 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9360 The package contains the original code written by the ISB, and a subset of the
9361 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9362 previously been used in XCMS.")
9363 (license license:artistic2.0)))
9365 (define-public r-affyio
9372 (uri (bioconductor-uri "affyio" version))
9375 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9376 (build-system r-build-system)
9378 `(("r-zlibbioc" ,r-zlibbioc)))
9381 (home-page "https://github.com/bmbolstad/affyio")
9382 (synopsis "Tools for parsing Affymetrix data files")
9384 "This package provides routines for parsing Affymetrix data files based
9385 upon file format information. The primary focus is on accessing the CEL and
9387 (license license:lgpl2.0+)))
9389 (define-public r-affy
9396 (uri (bioconductor-uri "affy" version))
9399 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9400 (build-system r-build-system)
9402 `(("r-affyio" ,r-affyio)
9403 ("r-biobase" ,r-biobase)
9404 ("r-biocgenerics" ,r-biocgenerics)
9405 ("r-biocinstaller" ,r-biocinstaller)
9406 ("r-preprocesscore" ,r-preprocesscore)
9407 ("r-zlibbioc" ,r-zlibbioc)))
9408 (home-page "https://bioconductor.org/packages/affy")
9409 (synopsis "Methods for affymetrix oligonucleotide arrays")
9411 "This package contains functions for exploratory oligonucleotide array
9413 (license license:lgpl2.0+)))
9415 (define-public r-vsn
9422 (uri (bioconductor-uri "vsn" version))
9425 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9426 (build-system r-build-system)
9428 `(("r-affy" ,r-affy)
9429 ("r-biobase" ,r-biobase)
9430 ("r-ggplot2" ,r-ggplot2)
9431 ("r-lattice" ,r-lattice)
9432 ("r-limma" ,r-limma)))
9433 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9434 (synopsis "Variance stabilization and calibration for microarray data")
9436 "The package implements a method for normalising microarray intensities,
9437 and works for single- and multiple-color arrays. It can also be used for data
9438 from other technologies, as long as they have similar format. The method uses
9439 a robust variant of the maximum-likelihood estimator for an
9440 additive-multiplicative error model and affine calibration. The model
9441 incorporates data calibration step (a.k.a. normalization), a model for the
9442 dependence of the variance on the mean intensity and a variance stabilizing
9443 data transformation. Differences between transformed intensities are
9444 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9445 their variance is independent of the mean, and they are usually more sensitive
9446 and specific in detecting differential transcription.")
9447 (license license:artistic2.0)))
9449 (define-public r-mzid
9456 (uri (bioconductor-uri "mzID" version))
9459 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9460 (properties `((upstream-name . "mzID")))
9461 (build-system r-build-system)
9463 `(("r-doparallel" ,r-doparallel)
9464 ("r-foreach" ,r-foreach)
9465 ("r-iterators" ,r-iterators)
9467 ("r-protgenerics" ,r-protgenerics)
9470 (home-page "https://bioconductor.org/packages/mzID")
9471 (synopsis "Parser for mzIdentML files")
9473 "This package provides a parser for mzIdentML files implemented using the
9474 XML package. The parser tries to be general and able to handle all types of
9475 mzIdentML files with the drawback of having less pretty output than a vendor
9477 (license license:gpl2+)))
9479 (define-public r-pcamethods
9481 (name "r-pcamethods")
9486 (uri (bioconductor-uri "pcaMethods" version))
9489 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9490 (properties `((upstream-name . "pcaMethods")))
9491 (build-system r-build-system)
9493 `(("r-biobase" ,r-biobase)
9494 ("r-biocgenerics" ,r-biocgenerics)
9496 ("r-rcpp" ,r-rcpp)))
9497 (home-page "https://github.com/hredestig/pcamethods")
9498 (synopsis "Collection of PCA methods")
9500 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9501 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9502 for missing value estimation is included for comparison. BPCA, PPCA and
9503 NipalsPCA may be used to perform PCA on incomplete data as well as for
9504 accurate missing value estimation. A set of methods for printing and plotting
9505 the results is also provided. All PCA methods make use of the same data
9506 structure (pcaRes) to provide a common interface to the PCA results.")
9507 (license license:gpl3+)))
9509 (define-public r-msnbase
9516 (uri (bioconductor-uri "MSnbase" version))
9519 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9520 (properties `((upstream-name . "MSnbase")))
9521 (build-system r-build-system)
9523 `(("r-affy" ,r-affy)
9524 ("r-biobase" ,r-biobase)
9525 ("r-biocgenerics" ,r-biocgenerics)
9526 ("r-biocparallel" ,r-biocparallel)
9527 ("r-digest" ,r-digest)
9528 ("r-ggplot2" ,r-ggplot2)
9529 ("r-impute" ,r-impute)
9530 ("r-iranges" ,r-iranges)
9531 ("r-lattice" ,r-lattice)
9532 ("r-maldiquant" ,r-maldiquant)
9535 ("r-pcamethods" ,r-pcamethods)
9537 ("r-preprocesscore" ,r-preprocesscore)
9538 ("r-protgenerics" ,r-protgenerics)
9540 ("r-s4vectors" ,r-s4vectors)
9543 (home-page "https://github.com/lgatto/MSnbase")
9544 (synopsis "Base functions and classes for MS-based proteomics")
9546 "This package provides basic plotting, data manipulation and processing
9547 of mass spectrometry based proteomics data.")
9548 (license license:artistic2.0)))
9550 (define-public r-msnid
9557 (uri (bioconductor-uri "MSnID" version))
9560 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9561 (properties `((upstream-name . "MSnID")))
9562 (build-system r-build-system)
9564 `(("r-biobase" ,r-biobase)
9565 ("r-data-table" ,r-data-table)
9566 ("r-doparallel" ,r-doparallel)
9567 ("r-dplyr" ,r-dplyr)
9568 ("r-foreach" ,r-foreach)
9569 ("r-iterators" ,r-iterators)
9570 ("r-msnbase" ,r-msnbase)
9573 ("r-protgenerics" ,r-protgenerics)
9574 ("r-r-cache" ,r-r-cache)
9576 ("r-reshape2" ,r-reshape2)))
9577 (home-page "https://bioconductor.org/packages/MSnID")
9578 (synopsis "Utilities for LC-MSn proteomics identifications")
9580 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9581 from mzIdentML (leveraging the mzID package) or text files. After collating
9582 the search results from multiple datasets it assesses their identification
9583 quality and optimize filtering criteria to achieve the maximum number of
9584 identifications while not exceeding a specified false discovery rate. It also
9585 contains a number of utilities to explore the MS/MS results and assess missed
9586 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9587 (license license:artistic2.0)))
9589 (define-public r-seurat
9595 (uri (cran-uri "Seurat" version))
9598 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9599 ;; Delete pre-built jar.
9601 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9603 (properties `((upstream-name . "Seurat")))
9604 (build-system r-build-system)
9607 (modify-phases %standard-phases
9608 (add-after 'unpack 'build-jar
9609 (lambda* (#:key inputs #:allow-other-keys)
9610 (let ((classesdir "tmp-classes"))
9611 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9613 (with-output-to-file "manifest"
9615 (display "Manifest-Version: 1.0
9616 Main-Class: ModularityOptimizer\n")))
9617 (and (zero? (apply system* `("javac" "-d" ,classesdir
9618 ,@(find-files "java" "\\.java$"))))
9619 (zero? (system* "jar"
9621 "inst/java/ModularityOptimizer.jar"
9622 "-C" classesdir ".")))))))))
9624 `(("jdk" ,icedtea "jdk")))
9627 ("r-caret" ,r-caret)
9628 ("r-cowplot" ,r-cowplot)
9629 ("r-diffusionmap" ,r-diffusionmap)
9630 ("r-dplyr" ,r-dplyr)
9634 ("r-gdata" ,r-gdata)
9635 ("r-ggplot2" ,r-ggplot2)
9636 ("r-ggridges" ,r-ggridges)
9637 ("r-gplots" ,r-gplots)
9638 ("r-gridextra" ,r-gridextra)
9639 ("r-hmisc" ,r-hmisc)
9641 ("r-igraph" ,r-igraph)
9642 ("r-irlba" ,r-irlba)
9645 ("r-matrix" ,r-matrix)
9646 ("r-metap" ,r-metap)
9647 ("r-mixtools" ,r-mixtools)
9648 ("r-pbapply" ,r-pbapply)
9649 ("r-plotly" ,r-plotly)
9650 ("r-ranger" ,r-ranger)
9651 ("r-rcolorbrewer" ,r-rcolorbrewer)
9653 ("r-rcppeigen" ,r-rcppeigen)
9654 ("r-rcppprogress" ,r-rcppprogress)
9655 ("r-reshape2" ,r-reshape2)
9657 ("r-rtsne" ,r-rtsne)
9658 ("r-sdmtools" ,r-sdmtools)
9659 ("r-stringr" ,r-stringr)
9660 ("r-tclust" ,r-tclust)
9661 ("r-tidyr" ,r-tidyr)
9663 ("r-vgam" ,r-vgam)))
9664 (home-page "http://www.satijalab.org/seurat")
9665 (synopsis "Seurat is an R toolkit for single cell genomics")
9667 "This package is an R package designed for QC, analysis, and
9668 exploration of single cell RNA-seq data. It easily enables widely-used
9669 analytical techniques, including the identification of highly variable genes,
9670 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9671 algorithms; density clustering, hierarchical clustering, k-means, and the
9672 discovery of differentially expressed genes and markers.")
9673 (license license:gpl3)))
9675 (define-public r-aroma-light
9677 (name "r-aroma-light")
9682 (uri (bioconductor-uri "aroma.light" version))
9685 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9686 (properties `((upstream-name . "aroma.light")))
9687 (build-system r-build-system)
9689 `(("r-matrixstats" ,r-matrixstats)
9690 ("r-r-methodss3" ,r-r-methodss3)
9692 ("r-r-utils" ,r-r-utils)))
9693 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9694 (synopsis "Methods for normalization and visualization of microarray data")
9696 "This package provides methods for microarray analysis that take basic
9697 data types such as matrices and lists of vectors. These methods can be used
9698 standalone, be utilized in other packages, or be wrapped up in higher-level
9700 (license license:gpl2+)))
9702 (define-public r-deseq
9709 (uri (bioconductor-uri "DESeq" version))
9712 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9713 (properties `((upstream-name . "DESeq")))
9714 (build-system r-build-system)
9716 `(("r-biobase" ,r-biobase)
9717 ("r-biocgenerics" ,r-biocgenerics)
9718 ("r-genefilter" ,r-genefilter)
9719 ("r-geneplotter" ,r-geneplotter)
9720 ("r-lattice" ,r-lattice)
9721 ("r-locfit" ,r-locfit)
9723 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9724 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9725 (synopsis "Differential gene expression analysis")
9727 "This package provides tools for estimating variance-mean dependence in
9728 count data from high-throughput genetic sequencing assays and for testing for
9729 differential expression based on a model using the negative binomial
9731 (license license:gpl3+)))
9733 (define-public r-edaseq
9740 (uri (bioconductor-uri "EDASeq" version))
9743 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9744 (properties `((upstream-name . "EDASeq")))
9745 (build-system r-build-system)
9747 `(("r-annotationdbi" ,r-annotationdbi)
9748 ("r-aroma-light" ,r-aroma-light)
9749 ("r-biobase" ,r-biobase)
9750 ("r-biocgenerics" ,r-biocgenerics)
9751 ("r-biomart" ,r-biomart)
9752 ("r-biostrings" ,r-biostrings)
9753 ("r-deseq" ,r-deseq)
9754 ("r-genomicfeatures" ,r-genomicfeatures)
9755 ("r-genomicranges" ,r-genomicranges)
9756 ("r-iranges" ,r-iranges)
9757 ("r-rsamtools" ,r-rsamtools)
9758 ("r-shortread" ,r-shortread)))
9759 (home-page "https://github.com/drisso/EDASeq")
9760 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9762 "This package provides support for numerical and graphical summaries of
9763 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9764 adjust for GC-content effect (or other gene-level effects) on read counts:
9765 loess robust local regression, global-scaling, and full-quantile
9766 normalization. Between-lane normalization procedures to adjust for
9767 distributional differences between lanes (e.g., sequencing depth):
9768 global-scaling and full-quantile normalization.")
9769 (license license:artistic2.0)))
9771 (define-public r-interactivedisplaybase
9773 (name "r-interactivedisplaybase")
9778 (uri (bioconductor-uri "interactiveDisplayBase" version))
9781 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9783 `((upstream-name . "interactiveDisplayBase")))
9784 (build-system r-build-system)
9786 `(("r-biocgenerics" ,r-biocgenerics)
9787 ("r-shiny" ,r-shiny)))
9788 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9789 (synopsis "Base package for web displays of Bioconductor objects")
9791 "This package contains the basic methods needed to generate interactive
9792 Shiny-based display methods for Bioconductor objects.")
9793 (license license:artistic2.0)))
9795 (define-public r-annotationhub
9797 (name "r-annotationhub")
9802 (uri (bioconductor-uri "AnnotationHub" version))
9805 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9806 (properties `((upstream-name . "AnnotationHub")))
9807 (build-system r-build-system)
9809 `(("r-annotationdbi" ,r-annotationdbi)
9810 ("r-biocgenerics" ,r-biocgenerics)
9811 ("r-biocinstaller" ,r-biocinstaller)
9814 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9815 ("r-rsqlite" ,r-rsqlite)
9816 ("r-s4vectors" ,r-s4vectors)
9817 ("r-yaml" ,r-yaml)))
9818 (home-page "https://bioconductor.org/packages/AnnotationHub")
9819 (synopsis "Client to access AnnotationHub resources")
9821 "This package provides a client for the Bioconductor AnnotationHub web
9822 resource. The AnnotationHub web resource provides a central location where
9823 genomic files (e.g. VCF, bed, wig) and other resources from standard
9824 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9825 metadata about each resource, e.g., a textual description, tags, and date of
9826 modification. The client creates and manages a local cache of files retrieved
9827 by the user, helping with quick and reproducible access.")
9828 (license license:artistic2.0)))
9830 (define-public r-fastseg
9837 (uri (bioconductor-uri "fastseg" version))
9840 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9841 (build-system r-build-system)
9843 `(("r-biobase" ,r-biobase)
9844 ("r-biocgenerics" ,r-biocgenerics)
9845 ("r-genomicranges" ,r-genomicranges)
9846 ("r-iranges" ,r-iranges)
9847 ("r-s4vectors" ,r-s4vectors)))
9848 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9849 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9851 "Fastseg implements a very fast and efficient segmentation algorithm.
9852 It can segment data from DNA microarrays and data from next generation
9853 sequencing for example to detect copy number segments. Further it can segment
9854 data from RNA microarrays like tiling arrays to identify transcripts. Most
9855 generally, it can segment data given as a matrix or as a vector. Various data
9856 formats can be used as input to fastseg like expression set objects for
9857 microarrays or GRanges for sequencing data.")
9858 (license license:lgpl2.0+)))
9860 (define-public r-keggrest
9867 (uri (bioconductor-uri "KEGGREST" version))
9870 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9871 (properties `((upstream-name . "KEGGREST")))
9872 (build-system r-build-system)
9874 `(("r-biostrings" ,r-biostrings)
9877 (home-page "https://bioconductor.org/packages/KEGGREST")
9878 (synopsis "Client-side REST access to KEGG")
9880 "This package provides a package that provides a client interface to the
9881 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9882 (license license:artistic2.0)))
9884 (define-public r-gage
9891 (uri (bioconductor-uri "gage" version))
9894 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9895 (build-system r-build-system)
9897 `(("r-annotationdbi" ,r-annotationdbi)
9898 ("r-graph" ,r-graph)
9899 ("r-keggrest" ,r-keggrest)))
9900 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9901 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9903 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9904 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9905 data attributes including sample sizes, experimental designs, assay platforms,
9906 and other types of heterogeneity. The gage package provides functions for
9907 basic GAGE analysis, result processing and presentation. In addition, it
9908 provides demo microarray data and commonly used gene set data based on KEGG
9909 pathways and GO terms. These funtions and data are also useful for gene set
9910 analysis using other methods.")
9911 (license license:gpl2+)))
9913 (define-public r-genomicfiles
9915 (name "r-genomicfiles")
9920 (uri (bioconductor-uri "GenomicFiles" version))
9923 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9924 (properties `((upstream-name . "GenomicFiles")))
9925 (build-system r-build-system)
9927 `(("r-biocgenerics" ,r-biocgenerics)
9928 ("r-biocparallel" ,r-biocparallel)
9929 ("r-genomeinfodb" ,r-genomeinfodb)
9930 ("r-genomicalignments" ,r-genomicalignments)
9931 ("r-genomicranges" ,r-genomicranges)
9932 ("r-iranges" ,r-iranges)
9933 ("r-rsamtools" ,r-rsamtools)
9934 ("r-rtracklayer" ,r-rtracklayer)
9935 ("r-s4vectors" ,r-s4vectors)
9936 ("r-summarizedexperiment" ,r-summarizedexperiment)
9937 ("r-variantannotation" ,r-variantannotation)))
9938 (home-page "https://bioconductor.org/packages/GenomicFiles")
9939 (synopsis "Distributed computing by file or by range")
9941 "This package provides infrastructure for parallel computations
9942 distributed by file or by range. User defined mapper and reducer functions
9943 provide added flexibility for data combination and manipulation.")
9944 (license license:artistic2.0)))
9946 (define-public r-complexheatmap
9948 (name "r-complexheatmap")
9953 (uri (bioconductor-uri "ComplexHeatmap" version))
9956 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9958 `((upstream-name . "ComplexHeatmap")))
9959 (build-system r-build-system)
9961 `(("r-circlize" ,r-circlize)
9962 ("r-colorspace" ,r-colorspace)
9963 ("r-getoptlong" ,r-getoptlong)
9964 ("r-globaloptions" ,r-globaloptions)
9965 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9967 "https://github.com/jokergoo/ComplexHeatmap")
9968 (synopsis "Making Complex Heatmaps")
9970 "Complex heatmaps are efficient to visualize associations between
9971 different sources of data sets and reveal potential structures. This package
9972 provides a highly flexible way to arrange multiple heatmaps and supports
9973 self-defined annotation graphics.")
9974 (license license:gpl2+)))
9976 (define-public r-dirichletmultinomial
9978 (name "r-dirichletmultinomial")
9983 (uri (bioconductor-uri "DirichletMultinomial" version))
9986 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9988 `((upstream-name . "DirichletMultinomial")))
9989 (build-system r-build-system)
9993 `(("r-biocgenerics" ,r-biocgenerics)
9994 ("r-iranges" ,r-iranges)
9995 ("r-s4vectors" ,r-s4vectors)))
9996 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9997 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9999 "Dirichlet-multinomial mixture models can be used to describe variability
10000 in microbial metagenomic data. This package is an interface to code
10001 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10003 (license license:lgpl3)))
10005 (define-public r-ensembldb
10007 (name "r-ensembldb")
10012 (uri (bioconductor-uri "ensembldb" version))
10015 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
10016 (build-system r-build-system)
10018 `(("r-annotationdbi" ,r-annotationdbi)
10019 ("r-annotationfilter" ,r-annotationfilter)
10020 ("r-annotationhub" ,r-annotationhub)
10021 ("r-biobase" ,r-biobase)
10022 ("r-biocgenerics" ,r-biocgenerics)
10023 ("r-biostrings" ,r-biostrings)
10026 ("r-genomeinfodb" ,r-genomeinfodb)
10027 ("r-genomicfeatures" ,r-genomicfeatures)
10028 ("r-genomicranges" ,r-genomicranges)
10029 ("r-iranges" ,r-iranges)
10030 ("r-protgenerics" ,r-protgenerics)
10031 ("r-rsamtools" ,r-rsamtools)
10032 ("r-rsqlite" ,r-rsqlite)
10033 ("r-rtracklayer" ,r-rtracklayer)
10034 ("r-s4vectors" ,r-s4vectors)))
10035 (home-page "https://github.com/jotsetung/ensembldb")
10036 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10038 "The package provides functions to create and use transcript-centric
10039 annotation databases/packages. The annotation for the databases are directly
10040 fetched from Ensembl using their Perl API. The functionality and data is
10041 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10042 but, in addition to retrieve all gene/transcript models and annotations from
10043 the database, the @code{ensembldb} package also provides a filter framework
10044 allowing to retrieve annotations for specific entries like genes encoded on a
10045 chromosome region or transcript models of lincRNA genes.")
10046 ;; No version specified
10047 (license license:lgpl3+)))
10049 (define-public r-organismdbi
10051 (name "r-organismdbi")
10056 (uri (bioconductor-uri "OrganismDbi" version))
10059 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
10060 (properties `((upstream-name . "OrganismDbi")))
10061 (build-system r-build-system)
10063 `(("r-annotationdbi" ,r-annotationdbi)
10064 ("r-biobase" ,r-biobase)
10065 ("r-biocgenerics" ,r-biocgenerics)
10066 ("r-biocinstaller" ,r-biocinstaller)
10068 ("r-genomicfeatures" ,r-genomicfeatures)
10069 ("r-genomicranges" ,r-genomicranges)
10070 ("r-graph" ,r-graph)
10071 ("r-iranges" ,r-iranges)
10073 ("r-s4vectors" ,r-s4vectors)))
10074 (home-page "https://bioconductor.org/packages/OrganismDbi")
10075 (synopsis "Software to enable the smooth interfacing of database packages")
10076 (description "The package enables a simple unified interface to several
10077 annotation packages each of which has its own schema by taking advantage of
10078 the fact that each of these packages implements a select methods.")
10079 (license license:artistic2.0)))
10081 (define-public r-biovizbase
10083 (name "r-biovizbase")
10088 (uri (bioconductor-uri "biovizBase" version))
10091 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10092 (properties `((upstream-name . "biovizBase")))
10093 (build-system r-build-system)
10095 `(("r-annotationdbi" ,r-annotationdbi)
10096 ("r-annotationfilter" ,r-annotationfilter)
10097 ("r-biocgenerics" ,r-biocgenerics)
10098 ("r-biostrings" ,r-biostrings)
10099 ("r-dichromat" ,r-dichromat)
10100 ("r-ensembldb" ,r-ensembldb)
10101 ("r-genomeinfodb" ,r-genomeinfodb)
10102 ("r-genomicalignments" ,r-genomicalignments)
10103 ("r-genomicfeatures" ,r-genomicfeatures)
10104 ("r-genomicranges" ,r-genomicranges)
10105 ("r-hmisc" ,r-hmisc)
10106 ("r-iranges" ,r-iranges)
10107 ("r-rcolorbrewer" ,r-rcolorbrewer)
10108 ("r-rsamtools" ,r-rsamtools)
10109 ("r-s4vectors" ,r-s4vectors)
10110 ("r-scales" ,r-scales)
10111 ("r-summarizedexperiment" ,r-summarizedexperiment)
10112 ("r-variantannotation" ,r-variantannotation)))
10113 (home-page "https://bioconductor.org/packages/biovizBase")
10114 (synopsis "Basic graphic utilities for visualization of genomic data")
10116 "The biovizBase package is designed to provide a set of utilities, color
10117 schemes and conventions for genomic data. It serves as the base for various
10118 high-level packages for biological data visualization. This saves development
10119 effort and encourages consistency.")
10120 (license license:artistic2.0)))
10122 (define-public r-ggbio
10129 (uri (bioconductor-uri "ggbio" version))
10132 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10133 (build-system r-build-system)
10135 `(("r-annotationdbi" ,r-annotationdbi)
10136 ("r-annotationfilter" ,r-annotationfilter)
10137 ("r-biobase" ,r-biobase)
10138 ("r-biocgenerics" ,r-biocgenerics)
10139 ("r-biostrings" ,r-biostrings)
10140 ("r-biovizbase" ,r-biovizbase)
10141 ("r-bsgenome" ,r-bsgenome)
10142 ("r-ensembldb" ,r-ensembldb)
10143 ("r-genomeinfodb" ,r-genomeinfodb)
10144 ("r-genomicalignments" ,r-genomicalignments)
10145 ("r-genomicfeatures" ,r-genomicfeatures)
10146 ("r-genomicranges" ,r-genomicranges)
10147 ("r-ggally" ,r-ggally)
10148 ("r-ggplot2" ,r-ggplot2)
10149 ("r-gridextra" ,r-gridextra)
10150 ("r-gtable" ,r-gtable)
10151 ("r-hmisc" ,r-hmisc)
10152 ("r-iranges" ,r-iranges)
10153 ("r-organismdbi" ,r-organismdbi)
10154 ("r-reshape2" ,r-reshape2)
10155 ("r-rsamtools" ,r-rsamtools)
10156 ("r-rtracklayer" ,r-rtracklayer)
10157 ("r-s4vectors" ,r-s4vectors)
10158 ("r-scales" ,r-scales)
10159 ("r-summarizedexperiment" ,r-summarizedexperiment)
10160 ("r-variantannotation" ,r-variantannotation)))
10161 (home-page "http://www.tengfei.name/ggbio/")
10162 (synopsis "Visualization tools for genomic data")
10164 "The ggbio package extends and specializes the grammar of graphics for
10165 biological data. The graphics are designed to answer common scientific
10166 questions, in particular those often asked of high throughput genomics data.
10167 All core Bioconductor data structures are supported, where appropriate. The
10168 package supports detailed views of particular genomic regions, as well as
10169 genome-wide overviews. Supported overviews include ideograms and grand linear
10170 views. High-level plots include sequence fragment length, edge-linked
10171 interval to data view, mismatch pileup, and several splicing summaries.")
10172 (license license:artistic2.0)))
10174 (define-public r-gprofiler
10176 (name "r-gprofiler")
10181 (uri (cran-uri "gProfileR" version))
10184 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10185 (properties `((upstream-name . "gProfileR")))
10186 (build-system r-build-system)
10188 `(("r-plyr" ,r-plyr)
10189 ("r-rcurl" ,r-rcurl)))
10190 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10191 (synopsis "Interface to the g:Profiler toolkit")
10193 "This package provides tools for functional enrichment analysis,
10194 gene identifier conversion and mapping homologous genes across related
10195 organisms via the @code{g:Profiler} toolkit.")
10196 (license license:gpl2+)))
10198 (define-public r-gqtlbase
10200 (name "r-gqtlbase")
10205 (uri (bioconductor-uri "gQTLBase" version))
10208 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10209 (properties `((upstream-name . "gQTLBase")))
10210 (build-system r-build-system)
10212 `(("r-batchjobs" ,r-batchjobs)
10213 ("r-bbmisc" ,r-bbmisc)
10214 ("r-biocgenerics" ,r-biocgenerics)
10216 ("r-doparallel" ,r-doparallel)
10218 ("r-ffbase" ,r-ffbase)
10219 ("r-foreach" ,r-foreach)
10220 ("r-genomicfiles" ,r-genomicfiles)
10221 ("r-genomicranges" ,r-genomicranges)
10222 ("r-rtracklayer" ,r-rtracklayer)
10223 ("r-s4vectors" ,r-s4vectors)
10224 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10225 (home-page "https://bioconductor.org/packages/gQTLBase")
10226 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10228 "The purpose of this package is to simplify the storage and interrogation
10229 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10231 (license license:artistic2.0)))
10233 (define-public r-snpstats
10235 (name "r-snpstats")
10240 (uri (bioconductor-uri "snpStats" version))
10243 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10244 (properties `((upstream-name . "snpStats")))
10245 (build-system r-build-system)
10246 (inputs `(("zlib" ,zlib)))
10248 `(("r-biocgenerics" ,r-biocgenerics)
10249 ("r-matrix" ,r-matrix)
10250 ("r-survival" ,r-survival)
10251 ("r-zlibbioc" ,r-zlibbioc)))
10252 (home-page "https://bioconductor.org/packages/snpStats")
10253 (synopsis "Methods for SNP association studies")
10255 "This package provides classes and statistical methods for large
10256 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10257 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10258 (license license:gpl3)))
10260 (define-public r-homo-sapiens
10262 (name "r-homo-sapiens")
10266 ;; We cannot use bioconductor-uri here because this tarball is
10267 ;; located under "data/annotation/" instead of "bioc/".
10268 (uri (string-append "http://www.bioconductor.org/packages/"
10269 "release/data/annotation/src/contrib/"
10271 version ".tar.gz"))
10274 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10276 `((upstream-name . "Homo.sapiens")))
10277 (build-system r-build-system)
10279 `(("r-genomicfeatures" ,r-genomicfeatures)
10280 ("r-go-db" ,r-go-db)
10281 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10282 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10283 ("r-organismdbi" ,r-organismdbi)
10284 ("r-annotationdbi" ,r-annotationdbi)))
10285 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10286 (synopsis "Annotation package for the Homo.sapiens object")
10288 "This package contains the Homo.sapiens object to access data from
10289 several related annotation packages.")
10290 (license license:artistic2.0)))
10292 (define-public r-erma
10299 (uri (bioconductor-uri "erma" version))
10302 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10303 (build-system r-build-system)
10305 `(("r-annotationdbi" ,r-annotationdbi)
10306 ("r-biobase" ,r-biobase)
10307 ("r-biocgenerics" ,r-biocgenerics)
10308 ("r-foreach" ,r-foreach)
10309 ("r-genomicfiles" ,r-genomicfiles)
10310 ("r-genomicranges" ,r-genomicranges)
10311 ("r-ggplot2" ,r-ggplot2)
10312 ("r-homo-sapiens" ,r-homo-sapiens)
10313 ("r-rtracklayer" ,r-rtracklayer)
10314 ("r-s4vectors" ,r-s4vectors)
10315 ("r-shiny" ,r-shiny)
10316 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10317 (home-page "https://bioconductor.org/packages/erma")
10318 (synopsis "Epigenomic road map adventures")
10320 "The epigenomics road map describes locations of epigenetic marks in DNA
10321 from a variety of cell types. Of interest are locations of histone
10322 modifications, sites of DNA methylation, and regions of accessible chromatin.
10323 This package presents a selection of elements of the road map including
10324 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10325 by Ernst and Kellis.")
10326 (license license:artistic2.0)))
10328 (define-public r-ldblock
10335 (uri (bioconductor-uri "ldblock" version))
10338 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10339 (build-system r-build-system)
10341 `(("r-erma" ,r-erma)
10342 ("r-genomeinfodb" ,r-genomeinfodb)
10343 ("r-genomicfiles" ,r-genomicfiles)
10344 ("r-go-db" ,r-go-db)
10345 ("r-homo-sapiens" ,r-homo-sapiens)
10346 ("r-matrix" ,r-matrix)
10347 ("r-rsamtools" ,r-rsamtools)
10348 ("r-snpstats" ,r-snpstats)
10349 ("r-variantannotation" ,r-variantannotation)))
10350 (home-page "https://bioconductor.org/packages/ldblock")
10351 (synopsis "Data structures for linkage disequilibrium measures in populations")
10353 "This package defines data structures for @dfn{linkage
10354 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10355 handling of existing population-level data for the purpose of flexibly
10356 defining LD blocks.")
10357 (license license:artistic2.0)))
10359 (define-public r-gqtlstats
10361 (name "r-gqtlstats")
10366 (uri (bioconductor-uri "gQTLstats" version))
10369 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10370 (properties `((upstream-name . "gQTLstats")))
10371 (build-system r-build-system)
10373 `(("r-annotationdbi" ,r-annotationdbi)
10374 ("r-batchjobs" ,r-batchjobs)
10375 ("r-bbmisc" ,r-bbmisc)
10376 ("r-beeswarm" ,r-beeswarm)
10377 ("r-biobase" ,r-biobase)
10378 ("r-biocgenerics" ,r-biocgenerics)
10379 ("r-doparallel" ,r-doparallel)
10380 ("r-dplyr" ,r-dplyr)
10382 ("r-ffbase" ,r-ffbase)
10383 ("r-foreach" ,r-foreach)
10384 ("r-genomeinfodb" ,r-genomeinfodb)
10385 ("r-genomicfeatures" ,r-genomicfeatures)
10386 ("r-genomicfiles" ,r-genomicfiles)
10387 ("r-genomicranges" ,r-genomicranges)
10388 ("r-ggbeeswarm" ,r-ggbeeswarm)
10389 ("r-ggplot2" ,r-ggplot2)
10390 ("r-gqtlbase" ,r-gqtlbase)
10391 ("r-hardyweinberg" ,r-hardyweinberg)
10392 ("r-iranges" ,r-iranges)
10393 ("r-ldblock" ,r-ldblock)
10394 ("r-limma" ,r-limma)
10396 ("r-plotly" ,r-plotly)
10397 ("r-reshape2" ,r-reshape2)
10398 ("r-s4vectors" ,r-s4vectors)
10399 ("r-shiny" ,r-shiny)
10400 ("r-snpstats" ,r-snpstats)
10401 ("r-summarizedexperiment" ,r-summarizedexperiment)
10402 ("r-variantannotation" ,r-variantannotation)))
10403 (home-page "https://bioconductor.org/packages/gQTLstats")
10404 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10406 "This package provides tools for the computationally efficient analysis
10407 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10408 The software in this package aims to support refinements and functional
10409 interpretation of members of a collection of association statistics on a
10410 family of feature/genome hypotheses.")
10411 (license license:artistic2.0)))
10413 (define-public r-gviz
10420 (uri (bioconductor-uri "Gviz" version))
10423 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10424 (properties `((upstream-name . "Gviz")))
10425 (build-system r-build-system)
10427 `(("r-annotationdbi" ,r-annotationdbi)
10428 ("r-biobase" ,r-biobase)
10429 ("r-biocgenerics" ,r-biocgenerics)
10430 ("r-biomart" ,r-biomart)
10431 ("r-biostrings" ,r-biostrings)
10432 ("r-biovizbase" ,r-biovizbase)
10433 ("r-bsgenome" ,r-bsgenome)
10434 ("r-digest" ,r-digest)
10435 ("r-genomeinfodb" ,r-genomeinfodb)
10436 ("r-genomicalignments" ,r-genomicalignments)
10437 ("r-genomicfeatures" ,r-genomicfeatures)
10438 ("r-genomicranges" ,r-genomicranges)
10439 ("r-iranges" ,r-iranges)
10440 ("r-lattice" ,r-lattice)
10441 ("r-latticeextra" ,r-latticeextra)
10442 ("r-matrixstats" ,r-matrixstats)
10443 ("r-rcolorbrewer" ,r-rcolorbrewer)
10444 ("r-rsamtools" ,r-rsamtools)
10445 ("r-rtracklayer" ,r-rtracklayer)
10446 ("r-s4vectors" ,r-s4vectors)
10447 ("r-xvector" ,r-xvector)))
10448 (home-page "https://bioconductor.org/packages/Gviz")
10449 (synopsis "Plotting data and annotation information along genomic coordinates")
10451 "Genomic data analyses requires integrated visualization of known genomic
10452 information and new experimental data. Gviz uses the biomaRt and the
10453 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10454 and translates this to e.g. gene/transcript structures in viewports of the
10455 grid graphics package. This results in genomic information plotted together
10457 (license license:artistic2.0)))
10459 (define-public r-gwascat
10466 (uri (bioconductor-uri "gwascat" version))
10469 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10470 (build-system r-build-system)
10472 `(("r-annotationdbi" ,r-annotationdbi)
10473 ("r-annotationhub" ,r-annotationhub)
10474 ("r-biocgenerics" ,r-biocgenerics)
10475 ("r-biostrings" ,r-biostrings)
10476 ("r-genomeinfodb" ,r-genomeinfodb)
10477 ("r-genomicfeatures" ,r-genomicfeatures)
10478 ("r-genomicranges" ,r-genomicranges)
10479 ("r-ggbio" ,r-ggbio)
10480 ("r-ggplot2" ,r-ggplot2)
10481 ("r-gqtlstats" ,r-gqtlstats)
10482 ("r-graph" ,r-graph)
10484 ("r-homo-sapiens" ,r-homo-sapiens)
10485 ("r-iranges" ,r-iranges)
10486 ("r-rsamtools" ,r-rsamtools)
10487 ("r-rtracklayer" ,r-rtracklayer)
10488 ("r-s4vectors" ,r-s4vectors)
10489 ("r-snpstats" ,r-snpstats)
10490 ("r-summarizedexperiment" ,r-summarizedexperiment)
10491 ("r-variantannotation" ,r-variantannotation)))
10492 (home-page "https://bioconductor.org/packages/gwascat")
10493 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10495 "This package provides tools for representing and modeling data in the
10496 EMBL-EBI GWAS catalog.")
10497 (license license:artistic2.0)))
10499 (define-public r-sushi
10505 (uri (bioconductor-uri "Sushi" version))
10508 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10509 (properties `((upstream-name . "Sushi")))
10510 (build-system r-build-system)
10512 `(("r-biomart" ,r-biomart)
10514 (home-page "https://bioconductor.org/packages/Sushi")
10515 (synopsis "Tools for visualizing genomics data")
10517 "This package provides flexible, quantitative, and integrative genomic
10518 visualizations for publication-quality multi-panel figures.")
10519 (license license:gpl2+)))
10521 (define-public r-fithic
10527 (uri (bioconductor-uri "FitHiC" version))
10530 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10531 (properties `((upstream-name . "FitHiC")))
10532 (build-system r-build-system)
10534 `(("r-data-table" ,r-data-table)
10535 ("r-fdrtool" ,r-fdrtool)
10536 ("r-rcpp" ,r-rcpp)))
10537 (home-page "https://bioconductor.org/packages/FitHiC")
10538 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10540 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10541 intra-chromosomal contact maps produced by genome-wide genome architecture
10542 assays such as Hi-C.")
10543 (license license:gpl2+)))
10545 (define-public r-hitc
10551 (uri (bioconductor-uri "HiTC" version))
10554 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10555 (properties `((upstream-name . "HiTC")))
10556 (build-system r-build-system)
10558 `(("r-biostrings" ,r-biostrings)
10559 ("r-genomeinfodb" ,r-genomeinfodb)
10560 ("r-genomicranges" ,r-genomicranges)
10561 ("r-iranges" ,r-iranges)
10562 ("r-matrix" ,r-matrix)
10563 ("r-rcolorbrewer" ,r-rcolorbrewer)
10564 ("r-rtracklayer" ,r-rtracklayer)))
10565 (home-page "https://bioconductor.org/packages/HiTC")
10566 (synopsis "High throughput chromosome conformation capture analysis")
10568 "The HiTC package was developed to explore high-throughput \"C\" data
10569 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10570 quality controls, normalization, visualization, and further analysis are also
10572 (license license:artistic2.0)))
10574 (define-public r-qvalue
10581 (uri (bioconductor-uri "qvalue" version))
10584 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10585 (build-system r-build-system)
10587 `(("r-ggplot2" ,r-ggplot2)
10588 ("r-reshape2" ,r-reshape2)))
10589 (home-page "http://github.com/jdstorey/qvalue")
10590 (synopsis "Q-value estimation for false discovery rate control")
10592 "This package takes a list of p-values resulting from the simultaneous
10593 testing of many hypotheses and estimates their q-values and local @dfn{false
10594 discovery rate} (FDR) values. The q-value of a test measures the proportion
10595 of false positives incurred when that particular test is called significant.
10596 The local FDR measures the posterior probability the null hypothesis is true
10597 given the test's p-value. Various plots are automatically generated, allowing
10598 one to make sensible significance cut-offs. The software can be applied to
10599 problems in genomics, brain imaging, astrophysics, and data mining.")
10600 ;; Any version of the LGPL.
10601 (license license:lgpl3+)))
10603 (define-public r-hdf5array
10605 (name "r-hdf5array")
10610 (uri (bioconductor-uri "HDF5Array" version))
10613 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10614 (properties `((upstream-name . "HDF5Array")))
10615 (build-system r-build-system)
10617 `(("r-biocgenerics" ,r-biocgenerics)
10618 ("r-delayedarray" ,r-delayedarray)
10619 ("r-iranges" ,r-iranges)
10620 ("r-rhdf5" ,r-rhdf5)
10621 ("r-s4vectors" ,r-s4vectors)))
10622 (home-page "https://bioconductor.org/packages/HDF5Array")
10623 (synopsis "HDF5 back end for DelayedArray objects")
10624 (description "This package provides an array-like container for convenient
10625 access and manipulation of HDF5 datasets. It supports delayed operations and
10626 block processing.")
10627 (license license:artistic2.0)))
10629 (define-public r-rhdf5lib
10631 (name "r-rhdf5lib")
10636 (uri (bioconductor-uri "Rhdf5lib" version))
10639 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10640 (properties `((upstream-name . "Rhdf5lib")))
10641 (build-system r-build-system)
10644 (modify-phases %standard-phases
10645 (add-after 'unpack 'do-not-use-bundled-hdf5
10646 (lambda* (#:key inputs #:allow-other-keys)
10647 (for-each delete-file '("configure" "configure.ac"))
10648 ;; Do not make other packages link with the proprietary libsz.
10649 (substitute* "R/zzz.R"
10650 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10651 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10652 (("'%s/libhdf5.a %s/libsz.a'")
10653 "'%s/libhdf5.a %s/libhdf5.a'"))
10654 (with-directory-excursion "src"
10655 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10656 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10658 ;; Remove timestamp and host system information to make
10659 ;; the build reproducible.
10660 (substitute* "hdf5/src/libhdf5.settings.in"
10661 (("Configured on: @CONFIG_DATE@")
10662 "Configured on: Guix")
10663 (("Uname information:.*")
10664 "Uname information: Linux\n")
10665 ;; Remove unnecessary store reference.
10667 "C Compiler: GCC\n"))
10668 (rename-file "Makevars.in" "Makevars")
10669 (substitute* "Makevars"
10670 (("HDF5_CXX_LIB=.*")
10671 (string-append "HDF5_CXX_LIB="
10672 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10674 (string-append "HDF5_LIB="
10675 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10676 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10677 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10678 ;; szip is non-free software
10679 (("cp \\$\\{SZIP_LIB\\}.*") "")
10680 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10681 "PKG_LIBS = ${HDF5_LIB}\n")))
10688 `(("hdf5-source" ,(package-source hdf5))))
10689 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10690 (synopsis "HDF5 library as an R package")
10691 (description "This package provides C and C++ HDF5 libraries for use in R
10693 (license license:artistic2.0)))
10695 (define-public r-beachmat
10697 (name "r-beachmat")
10702 (uri (bioconductor-uri "beachmat" version))
10705 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10706 (build-system r-build-system)
10710 `(("r-delayedarray" ,r-delayedarray)
10711 ("r-hdf5array" ,r-hdf5array)
10713 ("r-rhdf5" ,r-rhdf5)
10714 ("r-rhdf5lib" ,r-rhdf5lib)))
10715 (home-page "https://bioconductor.org/packages/beachmat")
10716 (synopsis "Compiling Bioconductor to handle each matrix type")
10717 (description "This package provides a consistent C++ class interface for a
10718 variety of commonly used matrix types, including sparse and HDF5-backed
10720 (license license:gpl3)))
10722 (define-public r-singlecellexperiment
10724 (name "r-singlecellexperiment")
10729 (uri (bioconductor-uri "SingleCellExperiment" version))
10732 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10734 `((upstream-name . "SingleCellExperiment")))
10735 (build-system r-build-system)
10737 `(("r-biocgenerics" ,r-biocgenerics)
10738 ("r-s4vectors" ,r-s4vectors)
10739 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10740 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10741 (synopsis "S4 classes for single cell data")
10742 (description "This package defines an S4 class for storing data from
10743 single-cell experiments. This includes specialized methods to store and
10744 retrieve spike-in information, dimensionality reduction coordinates and size
10745 factors for each cell, along with the usual metadata for genes and
10747 (license license:gpl3)))
10749 (define-public r-scater
10755 (uri (bioconductor-uri "scater" version))
10758 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10759 (build-system r-build-system)
10761 `(("r-beachmat" ,r-beachmat)
10762 ("r-biobase" ,r-biobase)
10763 ("r-biocgenerics" ,r-biocgenerics)
10764 ("r-biomart" ,r-biomart)
10765 ("r-data-table" ,r-data-table)
10766 ("r-dplyr" ,r-dplyr)
10767 ("r-edger" ,r-edger)
10768 ("r-ggbeeswarm" ,r-ggbeeswarm)
10769 ("r-ggplot2" ,r-ggplot2)
10770 ("r-limma" ,r-limma)
10771 ("r-matrix" ,r-matrix)
10772 ("r-matrixstats" ,r-matrixstats)
10775 ("r-reshape2" ,r-reshape2)
10776 ("r-rhdf5" ,r-rhdf5)
10777 ("r-rhdf5lib" ,r-rhdf5lib)
10778 ("r-rjson" ,r-rjson)
10779 ("r-s4vectors" ,r-s4vectors)
10780 ("r-shiny" ,r-shiny)
10781 ("r-shinydashboard" ,r-shinydashboard)
10782 ("r-singlecellexperiment" ,r-singlecellexperiment)
10783 ("r-summarizedexperiment" ,r-summarizedexperiment)
10784 ("r-tximport" ,r-tximport)
10785 ("r-viridis" ,r-viridis)))
10786 (home-page "https://github.com/davismcc/scater")
10787 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10788 (description "This package provides a collection of tools for doing
10789 various analyses of single-cell RNA-seq gene expression data, with a focus on
10791 (license license:gpl2+)))
10793 (define-public r-scran
10800 (uri (bioconductor-uri "scran" version))
10803 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10804 (build-system r-build-system)
10806 `(("r-beachmat" ,r-beachmat)
10807 ("r-biocgenerics" ,r-biocgenerics)
10808 ("r-biocparallel" ,r-biocparallel)
10810 ("r-dynamictreecut" ,r-dynamictreecut)
10811 ("r-edger" ,r-edger)
10813 ("r-ggplot2" ,r-ggplot2)
10814 ("r-igraph" ,r-igraph)
10815 ("r-limma" ,r-limma)
10816 ("r-matrix" ,r-matrix)
10818 ("r-rhdf5lib" ,r-rhdf5lib)
10819 ("r-s4vectors" ,r-s4vectors)
10820 ("r-scater" ,r-scater)
10821 ("r-shiny" ,r-shiny)
10822 ("r-singlecellexperiment" ,r-singlecellexperiment)
10823 ("r-statmod" ,r-statmod)
10824 ("r-summarizedexperiment" ,r-summarizedexperiment)
10825 ("r-viridis" ,r-viridis)
10827 (home-page "https://bioconductor.org/packages/scran")
10828 (synopsis "Methods for single-cell RNA-Seq data analysis")
10829 (description "This package implements a variety of low-level analyses of
10830 single-cell RNA-seq data. Methods are provided for normalization of
10831 cell-specific biases, assignment of cell cycle phase, and detection of highly
10832 variable and significantly correlated genes.")
10833 (license license:gpl3)))
10835 (define-public r-delayedmatrixstats
10837 (name "r-delayedmatrixstats")
10842 (uri (bioconductor-uri "DelayedMatrixStats" version))
10845 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10847 `((upstream-name . "DelayedMatrixStats")))
10848 (build-system r-build-system)
10850 `(("r-delayedarray" ,r-delayedarray)
10851 ("r-iranges" ,r-iranges)
10852 ("r-matrix" ,r-matrix)
10853 ("r-matrixstats" ,r-matrixstats)
10854 ("r-s4vectors" ,r-s4vectors)))
10855 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10856 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10858 "This package provides a port of the @code{matrixStats} API for use with
10859 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10860 contains high-performing functions operating on rows and columns of
10861 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10862 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10863 are optimized per data type and for subsetted calculations such that both
10864 memory usage and processing time is minimized.")
10865 (license license:expat)))
10867 (define-public r-phangorn
10869 (name "r-phangorn")
10874 (uri (cran-uri "phangorn" version))
10877 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10878 (build-system r-build-system)
10881 ("r-fastmatch" ,r-fastmatch)
10882 ("r-igraph" ,r-igraph)
10883 ("r-magrittr" ,r-magrittr)
10884 ("r-matrix" ,r-matrix)
10885 ("r-quadprog" ,r-quadprog)
10886 ("r-rcpp" ,r-rcpp)))
10887 (home-page "https://github.com/KlausVigo/phangorn")
10888 (synopsis "Phylogenetic analysis in R")
10890 "Phangorn is a package for phylogenetic analysis in R. It supports
10891 estimation of phylogenetic trees and networks using Maximum Likelihood,
10892 Maximum Parsimony, distance methods and Hadamard conjugation.")
10893 (license license:gpl2+)))
10895 (define-public r-dropbead
10896 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10899 (name "r-dropbead")
10900 (version (string-append "0-" revision "." (string-take commit 7)))
10904 (uri (git-reference
10905 (url "https://github.com/rajewsky-lab/dropbead.git")
10907 (file-name (git-file-name name version))
10910 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10911 (build-system r-build-system)
10913 `(("r-ggplot2" ,r-ggplot2)
10914 ("r-rcolorbrewer" ,r-rcolorbrewer)
10915 ("r-gridextra" ,r-gridextra)
10916 ("r-gplots" ,r-gplots)
10917 ("r-plyr" ,r-plyr)))
10918 (home-page "https://github.com/rajewsky-lab/dropbead")
10919 (synopsis "Basic exploration and analysis of Drop-seq data")
10920 (description "This package offers a quick and straight-forward way to
10921 explore and perform basic analysis of single cell sequencing data coming from
10922 droplet sequencing. It has been particularly tailored for Drop-seq.")
10923 (license license:gpl3))))
10925 (define htslib-for-sambamba
10926 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10929 (name "htslib-for-sambamba")
10930 (version (string-append "1.3.1-1." (string-take commit 9)))
10934 (uri (git-reference
10935 (url "https://github.com/lomereiter/htslib.git")
10937 (file-name (string-append "htslib-" version "-checkout"))
10940 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10942 (substitute-keyword-arguments (package-arguments htslib)
10944 `(modify-phases ,phases
10945 (add-after 'unpack 'bootstrap
10947 (zero? (system* "autoreconf" "-vif"))))))))
10949 `(("autoconf" ,autoconf)
10950 ("automake" ,automake)
10951 ,@(package-native-inputs htslib))))))
10953 (define-public sambamba
10960 (uri (string-append "https://github.com/lomereiter/sambamba/"
10961 "archive/v" version ".tar.gz"))
10962 (file-name (string-append name "-" version ".tar.gz"))
10965 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10966 (build-system gnu-build-system)
10968 `(#:tests? #f ; there is no test target
10970 '("D_COMPILER=ldc2"
10971 ;; Override "--compiler" flag only.
10972 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10973 "sambamba-ldmd2-64")
10975 (modify-phases %standard-phases
10976 (delete 'configure)
10977 (add-after 'unpack 'place-biod
10978 (lambda* (#:key inputs #:allow-other-keys)
10979 (copy-recursively (assoc-ref inputs "biod") "BioD")
10981 (add-after 'unpack 'unbundle-prerequisites
10983 (substitute* "Makefile"
10984 ((" htslib-static lz4-static") ""))
10987 (lambda* (#:key outputs #:allow-other-keys)
10988 (let* ((out (assoc-ref outputs "out"))
10989 (bin (string-append out "/bin")))
10991 (install-file "build/sambamba" bin)
10997 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
11000 (uri (git-reference
11001 (url "https://github.com/biod/BioD.git")
11003 (file-name (string-append "biod-"
11004 (string-take commit 9)
11008 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
11011 ("htslib" ,htslib-for-sambamba)))
11012 (home-page "http://lomereiter.github.io/sambamba")
11013 (synopsis "Tools for working with SAM/BAM data")
11014 (description "Sambamba is a high performance modern robust and
11015 fast tool (and library), written in the D programming language, for
11016 working with SAM and BAM files. Current parallelised functionality is
11017 an important subset of samtools functionality, including view, index,
11018 sort, markdup, and depth.")
11019 (license license:gpl2+)))
11021 (define-public ritornello
11023 (name "ritornello")
11027 (uri (string-append "https://github.com/KlugerLab/"
11028 "Ritornello/archive/v"
11029 version ".tar.gz"))
11030 (file-name (string-append name "-" version ".tar.gz"))
11033 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11034 (build-system gnu-build-system)
11036 `(#:tests? #f ; there are no tests
11038 (modify-phases %standard-phases
11039 (add-after 'unpack 'patch-samtools-references
11040 (lambda* (#:key inputs #:allow-other-keys)
11041 (substitute* '("src/SamStream.h"
11042 "src/BufferedGenomeReader.h")
11043 (("<sam.h>") "<samtools/sam.h>"))
11045 (delete 'configure)
11047 (lambda* (#:key inputs outputs #:allow-other-keys)
11048 (let* ((out (assoc-ref outputs "out"))
11049 (bin (string-append out "/bin/")))
11051 (install-file "bin/Ritornello" bin)
11054 `(("samtools" ,samtools-0.1)
11058 (home-page "https://github.com/KlugerLab/Ritornello")
11059 (synopsis "Control-free peak caller for ChIP-seq data")
11060 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11061 signal processing that can accurately call binding events without the need to
11062 do a pair total DNA input or IgG control sample. It has been tested for use
11063 with narrow binding events such as transcription factor ChIP-seq.")
11064 (license license:gpl3+)))
11066 (define-public trim-galore
11068 (name "trim-galore")
11073 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
11074 "projects/trim_galore/trim_galore_v"
11078 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
11079 (build-system gnu-build-system)
11081 `(#:tests? #f ; no tests
11083 (modify-phases %standard-phases
11084 ;; The archive contains plain files.
11086 (lambda* (#:key source #:allow-other-keys)
11087 (zero? (system* "unzip" source))))
11088 (delete 'configure)
11090 (add-after 'unpack 'hardcode-tool-references
11091 (lambda* (#:key inputs #:allow-other-keys)
11092 (substitute* "trim_galore"
11093 (("\\$path_to_cutadapt = 'cutadapt'")
11094 (string-append "$path_to_cutadapt = '"
11095 (assoc-ref inputs "cutadapt")
11098 (string-append "| "
11099 (assoc-ref inputs "gzip")
11102 (string-append "\""
11103 (assoc-ref inputs "gzip")
11107 (lambda* (#:key outputs #:allow-other-keys)
11108 (let ((bin (string-append (assoc-ref outputs "out")
11111 (install-file "trim_galore" bin)
11116 ("cutadapt" ,cutadapt)))
11118 `(("unzip" ,unzip)))
11119 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11120 (synopsis "Wrapper around Cutadapt and FastQC")
11121 (description "Trim Galore! is a wrapper script to automate quality and
11122 adapter trimming as well as quality control, with some added functionality to
11123 remove biased methylation positions for RRBS sequence files.")
11124 (license license:gpl3+)))
11126 (define-public gess
11132 (uri (string-append "http://compbio.uthscsa.edu/"
11134 "gess-" version ".src.tar.gz"))
11137 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11138 (build-system gnu-build-system)
11140 `(#:tests? #f ; no tests
11142 (modify-phases %standard-phases
11143 (delete 'configure)
11146 (lambda* (#:key inputs outputs #:allow-other-keys)
11147 (let* ((python (assoc-ref inputs "python"))
11148 (out (assoc-ref outputs "out"))
11149 (bin (string-append out "/bin/"))
11150 (target (string-append
11151 out "/lib/python2.7/site-packages/gess/")))
11153 (copy-recursively "." target)
11154 ;; Make GESS.py executable
11155 (chmod (string-append target "GESS.py") #o555)
11156 ;; Add Python shebang to the top and make Matplotlib
11158 (substitute* (string-append target "GESS.py")
11159 (("\"\"\"Description:" line)
11160 (string-append "#!" (which "python") "
11162 matplotlib.use('Agg')
11164 ;; Make sure GESS has all modules in its path
11165 (wrap-program (string-append target "GESS.py")
11166 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11168 (symlink (string-append target "GESS.py")
11169 (string-append bin "GESS.py"))
11172 `(("python" ,python-2)
11173 ("python2-pysam" ,python2-pysam)
11174 ("python2-scipy" ,python2-scipy)
11175 ("python2-numpy" ,python2-numpy)
11176 ("python2-networkx" ,python2-networkx)
11177 ("python2-biopython" ,python2-biopython)))
11178 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11179 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11181 "GESS is an implementation of a novel computational method to detect de
11182 novo exon-skipping events directly from raw RNA-seq data without the prior
11183 knowledge of gene annotation information. GESS stands for the graph-based
11184 exon-skipping scanner detection scheme.")
11185 (license license:bsd-3)))
11187 (define-public phylip
11194 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11195 "download/phylip-" version ".tar.gz"))
11198 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11199 (build-system gnu-build-system)
11201 `(#:tests? #f ; no check target
11202 #:make-flags (list "-f" "Makefile.unx" "install")
11203 #:parallel-build? #f ; not supported
11205 (modify-phases %standard-phases
11206 (add-after 'unpack 'enter-dir
11207 (lambda _ (chdir "src") #t))
11208 (delete 'configure)
11210 (lambda* (#:key inputs outputs #:allow-other-keys)
11211 (let ((target (string-append (assoc-ref outputs "out")
11214 (for-each (lambda (file)
11215 (install-file file target))
11216 (find-files "../exe" ".*")))
11218 (home-page "http://evolution.genetics.washington.edu/phylip/")
11219 (synopsis "Tools for inferring phylogenies")
11220 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11221 programs for inferring phylogenies (evolutionary trees).")
11222 (license license:bsd-2)))
11231 (uri (string-append "https://integrativemodeling.org/"
11232 version "/download/imp-" version ".tar.gz"))
11235 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11236 (build-system cmake-build-system)
11238 `(;; FIXME: Some tests fail because they produce warnings, others fail
11239 ;; because the PYTHONPATH does not include the modeller's directory.
11247 ("python" ,python-2)))
11249 `(("python2-numpy" ,python2-numpy)
11250 ("python2-scipy" ,python2-scipy)
11251 ("python2-pandas" ,python2-pandas)
11252 ("python2-scikit-learn" ,python2-scikit-learn)
11253 ("python2-networkx" ,python2-networkx)))
11254 (home-page "https://integrativemodeling.org")
11255 (synopsis "Integrative modeling platform")
11256 (description "IMP's broad goal is to contribute to a comprehensive
11257 structural characterization of biomolecules ranging in size and complexity
11258 from small peptides to large macromolecular assemblies, by integrating data
11259 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11260 Python toolbox for solving complex modeling problems, and a number of
11261 applications for tackling some common problems in a user-friendly way.")
11262 ;; IMP is largely available under the GNU Lesser GPL; see the file
11263 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11264 ;; available under the GNU GPL (see the file COPYING.GPL).
11265 (license (list license:lgpl2.1+
11268 (define-public tadbit
11274 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11275 "archive/v" version ".tar.gz"))
11276 (file-name (string-append name "-" version ".tar.gz"))
11279 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11280 (build-system python-build-system)
11282 `(;; Tests are included and must be run after installation, but
11283 ;; they are incomplete and thus cannot be run.
11287 (modify-phases %standard-phases
11288 (add-after 'unpack 'fix-problems-with-setup.py
11289 (lambda* (#:key outputs #:allow-other-keys)
11290 ;; setup.py opens these files for writing
11291 (chmod "_pytadbit/_version.py" #o664)
11292 (chmod "README.rst" #o664)
11294 ;; Don't attempt to install the bash completions to
11295 ;; the home directory.
11296 (rename-file "extras/.bash_completion"
11298 (substitute* "setup.py"
11299 (("\\(path.expanduser\\('~'\\)")
11300 (string-append "(\""
11301 (assoc-ref outputs "out")
11302 "/etc/bash_completion.d\""))
11303 (("extras/\\.bash_completion")
11307 ;; TODO: add Chimera for visualization
11310 ("python2-scipy" ,python2-scipy)
11311 ("python2-numpy" ,python2-numpy)
11312 ("python2-matplotlib" ,python2-matplotlib)
11313 ("python2-pysam" ,python2-pysam)))
11314 (home-page "http://3dgenomes.github.io/TADbit/")
11315 (synopsis "Analyze, model, and explore 3C-based data")
11317 "TADbit is a complete Python library to deal with all steps to analyze,
11318 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11319 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11320 correct interaction matrices, identify and compare the so-called
11321 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11322 interaction matrices, and finally, extract structural properties from the
11323 models. TADbit is complemented by TADkit for visualizing 3D models.")
11324 (license license:gpl3+)))
11326 (define-public kentutils
11329 ;; 302.1.0 is out, but the only difference is the inclusion of
11330 ;; pre-built binaries.
11331 (version "302.0.0")
11335 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11336 "archive/v" version ".tar.gz"))
11337 (file-name (string-append name "-" version ".tar.gz"))
11340 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11341 (modules '((guix build utils)
11346 ;; Only the contents of the specified directories are free
11347 ;; for all uses, so we remove the rest. "hg/autoSql" and
11348 ;; "hg/autoXml" are nominally free, but they depend on a
11349 ;; library that is built from the sources in "hg/lib",
11350 ;; which is nonfree.
11351 (let ((free (list "." ".."
11352 "utils" "lib" "inc" "tagStorm"
11353 "parasol" "htslib"))
11354 (directory? (lambda (file)
11355 (eq? 'directory (stat:type (stat file))))))
11356 (for-each (lambda (file)
11357 (and (directory? file)
11358 (delete-file-recursively file)))
11359 (map (cut string-append "src/" <>)
11362 (not (member file free)))))))
11363 ;; Only make the utils target, not the userApps target,
11364 ;; because that requires libraries we won't build.
11365 (substitute* "Makefile"
11366 ((" userApps") " utils"))
11367 ;; Only build libraries that are free.
11368 (substitute* "src/makefile"
11369 (("DIRS =.*") "DIRS =\n")
11370 (("cd jkOwnLib.*") "")
11373 (substitute* "src/utils/makefile"
11374 ;; These tools depend on "jkhgap.a", which is part of the
11375 ;; nonfree "src/hg/lib" directory.
11376 (("raSqlQuery") "")
11377 (("pslLiftSubrangeBlat") "")
11379 ;; Do not build UCSC tools, which may require nonfree
11381 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11383 (build-system gnu-build-system)
11385 `( ;; There is no global test target and the test target for
11386 ;; individual tools depends on input files that are not
11390 (modify-phases %standard-phases
11391 (add-after 'unpack 'fix-paths
11393 (substitute* "Makefile"
11394 (("/bin/echo") (which "echo")))
11396 (add-after 'unpack 'prepare-samtabix
11397 (lambda* (#:key inputs #:allow-other-keys)
11398 (copy-recursively (assoc-ref inputs "samtabix")
11401 (delete 'configure)
11403 (lambda* (#:key outputs #:allow-other-keys)
11404 (let ((bin (string-append (assoc-ref outputs "out")
11406 (copy-recursively "bin" bin))
11412 (uri (git-reference
11413 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11414 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11417 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11423 ("mariadb" ,mariadb)
11424 ("openssl" ,openssl)))
11425 (home-page "http://genome.cse.ucsc.edu/index.html")
11426 (synopsis "Assorted bioinformatics utilities")
11427 (description "This package provides the kentUtils, a selection of
11428 bioinformatics utilities used in combination with the UCSC genome
11430 ;; Only a subset of the sources are released under a non-copyleft
11431 ;; free software license. All other sources are removed in a
11432 ;; snippet. See this bug report for an explanation of how the
11433 ;; license statements apply:
11434 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11435 (license (license:non-copyleft
11436 "http://genome.ucsc.edu/license/"
11437 "The contents of this package are free for all uses."))))
11439 (define-public f-seq
11440 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11444 (version (string-append "1.1-" revision "." (string-take commit 7)))
11447 (uri (git-reference
11448 (url "https://github.com/aboyle/F-seq.git")
11450 (file-name (string-append name "-" version))
11453 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11454 (modules '((guix build utils)))
11455 ;; Remove bundled Java library archives.
11458 (for-each delete-file (find-files "lib" ".*"))
11460 (build-system ant-build-system)
11462 `(#:tests? #f ; no tests included
11464 (modify-phases %standard-phases
11466 (lambda* (#:key inputs outputs #:allow-other-keys)
11467 (let* ((target (assoc-ref outputs "out"))
11468 (doc (string-append target "/share/doc/f-seq/")))
11471 (substitute* "bin/linux/fseq"
11472 (("java") (which "java"))
11473 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11474 (string-append (assoc-ref inputs "java-commons-cli")
11475 "/share/java/commons-cli.jar"))
11477 (string-append "REALDIR=" target "/bin\n")))
11478 (install-file "README.txt" doc)
11479 (install-file "bin/linux/fseq" (string-append target "/bin"))
11480 (install-file "build~/fseq.jar" (string-append target "/lib"))
11481 (copy-recursively "lib" (string-append target "/lib"))
11485 ("java-commons-cli" ,java-commons-cli)))
11486 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11487 (synopsis "Feature density estimator for high-throughput sequence tags")
11489 "F-Seq is a software package that generates a continuous tag sequence
11490 density estimation allowing identification of biologically meaningful sites
11491 such as transcription factor binding sites (ChIP-seq) or regions of open
11492 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11494 (license license:gpl3+))))
11496 (define-public bismark
11503 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11504 "archive/" version ".tar.gz"))
11505 (file-name (string-append name "-" version ".tar.gz"))
11508 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11509 (build-system perl-build-system)
11511 `(#:tests? #f ; there are no tests
11513 (modify-phases %standard-phases
11514 (delete 'configure)
11517 (lambda* (#:key outputs #:allow-other-keys)
11518 (let ((bin (string-append (assoc-ref outputs "out")
11520 (docdir (string-append (assoc-ref outputs "out")
11521 "/share/doc/bismark"))
11522 (docs '("Bismark_User_Guide.pdf"
11523 "RELEASE_NOTES.txt"))
11524 (scripts '("bismark"
11525 "bismark_genome_preparation"
11526 "bismark_methylation_extractor"
11529 "coverage2cytosine"
11530 "deduplicate_bismark"
11531 "bismark_sitrep.tpl"
11533 "bismark2summary")))
11536 (for-each (lambda (file) (install-file file bin))
11538 (for-each (lambda (file) (install-file file docdir))
11541 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11542 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11543 (description "Bismark is a program to map bisulfite treated sequencing
11544 reads to a genome of interest and perform methylation calls in a single step.
11545 The output can be easily imported into a genome viewer, such as SeqMonk, and
11546 enables a researcher to analyse the methylation levels of their samples
11547 straight away. Its main features are:
11550 @item Bisulfite mapping and methylation calling in one single step
11551 @item Supports single-end and paired-end read alignments
11552 @item Supports ungapped and gapped alignments
11553 @item Alignment seed length, number of mismatches etc are adjustable
11554 @item Output discriminates between cytosine methylation in CpG, CHG
11557 (license license:gpl3+)))
11559 (define-public paml
11565 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11566 "paml" version ".tgz"))
11569 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11570 (modules '((guix build utils)))
11571 ;; Remove Windows binaries
11574 (for-each delete-file (find-files "." "\\.exe$"))
11576 (build-system gnu-build-system)
11578 `(#:tests? #f ; there are no tests
11579 #:make-flags '("CC=gcc")
11581 (modify-phases %standard-phases
11582 (replace 'configure
11584 (substitute* "src/BFdriver.c"
11585 (("/bin/bash") (which "bash")))
11589 (lambda* (#:key outputs #:allow-other-keys)
11590 (let ((tools '("baseml" "basemlg" "codeml"
11591 "pamp" "evolver" "yn00" "chi2"))
11592 (bin (string-append (assoc-ref outputs "out") "/bin"))
11593 (docdir (string-append (assoc-ref outputs "out")
11594 "/share/doc/paml")))
11596 (for-each (lambda (file) (install-file file bin)) tools)
11597 (copy-recursively "../doc" docdir)
11599 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11600 (synopsis "Phylogentic analysis by maximum likelihood")
11601 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11602 contains a few programs for model fitting and phylogenetic tree reconstruction
11603 using nucleotide or amino-acid sequence data.")
11605 (license license:gpl3)))
11607 (define-public kallisto
11613 (uri (string-append "https://github.com/pachterlab/"
11614 "kallisto/archive/v" version ".tar.gz"))
11615 (file-name (string-append name "-" version ".tar.gz"))
11618 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11619 (build-system cmake-build-system)
11620 (arguments `(#:tests? #f)) ; no "check" target
11624 (home-page "http://pachterlab.github.io/kallisto/")
11625 (synopsis "Near-optimal RNA-Seq quantification")
11627 "Kallisto is a program for quantifying abundances of transcripts from
11628 RNA-Seq data, or more generally of target sequences using high-throughput
11629 sequencing reads. It is based on the novel idea of pseudoalignment for
11630 rapidly determining the compatibility of reads with targets, without the need
11631 for alignment. Pseudoalignment of reads preserves the key information needed
11632 for quantification, and kallisto is therefore not only fast, but also as
11633 accurate as existing quantification tools.")
11634 (license license:bsd-2)))
11636 (define-public libgff
11642 (uri (string-append
11643 "https://github.com/Kingsford-Group/"
11644 "libgff/archive/v" version ".tar.gz"))
11645 (file-name (string-append name "-" version ".tar.gz"))
11648 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11649 (build-system cmake-build-system)
11650 (arguments `(#:tests? #f)) ; no tests included
11651 (home-page "https://github.com/Kingsford-Group/libgff")
11652 (synopsis "Parser library for reading/writing GFF files")
11653 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11654 code that is used in the Cufflinks codebase. The goal of this library is to
11655 provide this functionality without the necessity of drawing in a heavy-weight
11656 dependency like SeqAn.")
11657 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11659 (define-public libdivsufsort
11661 (name "libdivsufsort")
11665 (uri (git-reference
11666 (url "https://github.com/y-256/libdivsufsort.git")
11668 (file-name (git-file-name name version))
11671 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11672 (build-system cmake-build-system)
11674 '(#:tests? #f ; there are no tests
11676 ;; Needed for rapmap and sailfish.
11677 '("-DBUILD_DIVSUFSORT64=ON")))
11678 (home-page "https://github.com/y-256/libdivsufsort")
11679 (synopsis "Lightweight suffix-sorting library")
11680 (description "libdivsufsort is a software library that implements a
11681 lightweight suffix array construction algorithm. This library provides a
11682 simple and an efficient C API to construct a suffix array and a
11683 Burrows-Wheeler transformed string from a given string over a constant-size
11684 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11685 bytes of memory space, where n is the length of the string.")
11686 (license license:expat)))
11688 (define-public sailfish
11695 (string-append "https://github.com/kingsfordgroup/"
11696 "sailfish/archive/v" version ".tar.gz"))
11697 (file-name (string-append name "-" version ".tar.gz"))
11700 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11701 (modules '((guix build utils)))
11704 ;; Delete bundled headers for eigen3.
11705 (delete-file-recursively "include/eigen3/")
11707 (build-system cmake-build-system)
11709 `(#:configure-flags
11710 (list (string-append "-DBOOST_INCLUDEDIR="
11711 (assoc-ref %build-inputs "boost")
11713 (string-append "-DBOOST_LIBRARYDIR="
11714 (assoc-ref %build-inputs "boost")
11716 (string-append "-DBoost_LIBRARIES="
11717 "-lboost_iostreams "
11718 "-lboost_filesystem "
11723 "-lboost_program_options")
11724 "-DBoost_FOUND=TRUE"
11725 ;; Don't download RapMap---we already have it!
11726 "-DFETCHED_RAPMAP=1")
11727 ;; Tests must be run after installation and the location of the test
11728 ;; data file must be overridden. But the tests fail. It looks like
11729 ;; they are not really meant to be run.
11732 (modify-phases %standard-phases
11733 ;; Boost cannot be found, even though it's right there.
11734 (add-after 'unpack 'do-not-look-for-boost
11735 (lambda* (#:key inputs #:allow-other-keys)
11736 (substitute* "CMakeLists.txt"
11737 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11738 (add-after 'unpack 'do-not-assign-to-macro
11740 (substitute* "include/spdlog/details/format.cc"
11741 (("const unsigned CHAR_WIDTH = 1;") ""))))
11742 (add-after 'unpack 'prepare-rapmap
11743 (lambda* (#:key inputs #:allow-other-keys)
11744 (let ((src "external/install/src/rapmap/")
11745 (include "external/install/include/rapmap/")
11746 (rapmap (assoc-ref inputs "rapmap")))
11747 (mkdir-p "/tmp/rapmap")
11748 (system* "tar" "xf"
11749 (assoc-ref inputs "rapmap")
11751 "--strip-components=1")
11754 (for-each (lambda (file)
11755 (install-file file src))
11756 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11757 (copy-recursively "/tmp/rapmap/include" include))))
11758 (add-after 'unpack 'use-system-libraries
11759 (lambda* (#:key inputs #:allow-other-keys)
11760 (substitute* '("src/SailfishIndexer.cpp"
11761 "src/SailfishUtils.cpp"
11762 "src/SailfishQuantify.cpp"
11763 "src/FASTAParser.cpp"
11765 "include/SailfishUtils.hpp"
11766 "include/SailfishIndex.hpp"
11767 "include/CollapsedEMOptimizer.hpp"
11768 "src/CollapsedEMOptimizer.cpp")
11769 (("#include \"jellyfish/config.h\"") ""))
11770 (substitute* "src/CMakeLists.txt"
11771 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11772 (string-append (assoc-ref inputs "jellyfish")
11773 "/include/jellyfish-" ,(package-version jellyfish)))
11774 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11775 (string-append (assoc-ref inputs "jellyfish")
11776 "/lib/libjellyfish-2.0.a"))
11777 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11778 (string-append (assoc-ref inputs "libdivsufsort")
11779 "/lib/libdivsufsort.so"))
11780 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11781 (string-append (assoc-ref inputs "libdivsufsort")
11782 "/lib/libdivsufsort64.so")))
11783 (substitute* "CMakeLists.txt"
11784 ;; Don't prefer static libs
11785 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11786 (("find_package\\(Jellyfish.*") "")
11787 (("ExternalProject_Add\\(libjellyfish") "message(")
11788 (("ExternalProject_Add\\(libgff") "message(")
11789 (("ExternalProject_Add\\(libsparsehash") "message(")
11790 (("ExternalProject_Add\\(libdivsufsort") "message("))
11792 ;; Ensure that Eigen headers can be found
11793 (setenv "CPLUS_INCLUDE_PATH"
11794 (string-append (getenv "CPLUS_INCLUDE_PATH")
11796 (assoc-ref inputs "eigen")
11797 "/include/eigen3")))))))
11801 ("jemalloc" ,jemalloc)
11802 ("jellyfish" ,jellyfish)
11803 ("sparsehash" ,sparsehash)
11806 (uri (git-reference
11807 (url "https://github.com/COMBINE-lab/RapMap.git")
11808 (commit (string-append "sf-v" version))))
11809 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11812 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11813 (modules '((guix build utils)))
11814 ;; These files are expected to be excluded.
11816 '(begin (delete-file-recursively "include/spdlog")
11817 (for-each delete-file '("include/xxhash.h"
11818 "src/xxhash.c"))))))
11819 ("libdivsufsort" ,libdivsufsort)
11824 `(("pkg-config" ,pkg-config)))
11825 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11826 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11827 (description "Sailfish is a tool for genomic transcript quantification
11828 from RNA-seq data. It requires a set of target transcripts (either from a
11829 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11830 fasta file containing your reference transcripts and a (set of) fasta/fastq
11831 file(s) containing your reads.")
11832 (license license:gpl3+)))
11834 (define libstadenio-for-salmon
11836 (name "libstadenio")
11840 (uri (git-reference
11841 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11842 (commit (string-append "v" version))))
11843 (file-name (string-append name "-" version "-checkout"))
11846 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11847 (build-system gnu-build-system)
11848 (arguments '(#:parallel-tests? #f)) ; not supported
11852 `(("perl" ,perl))) ; for tests
11853 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11854 (synopsis "General purpose trace and experiment file library")
11855 (description "This package provides a library of file reading and writing
11856 code to provide a general purpose Trace file (and Experiment File) reading
11859 The following file formats are supported:
11862 @item SCF trace files
11863 @item ABI trace files
11864 @item ALF trace files
11865 @item ZTR trace files
11866 @item SFF trace archives
11867 @item SRF trace archives
11868 @item Experiment files
11869 @item Plain text files
11870 @item SAM/BAM sequence files
11871 @item CRAM sequence files
11873 (license license:bsd-3)))
11875 (define spdlog-for-salmon
11881 (uri (git-reference
11882 (url "https://github.com/COMBINE-lab/spdlog.git")
11883 (commit (string-append "v" version))))
11884 (file-name (string-append name "-" version "-checkout"))
11887 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11888 (build-system cmake-build-system)
11889 (home-page "https://github.com/COMBINE-lab/spdlog")
11890 (synopsis "Very fast C++ logging library")
11891 (description "Spdlog is a very fast header-only C++ logging library with
11892 performance as its primary goal.")
11893 (license license:expat)))
11895 ;; This is a modified variant of bwa for use with Salmon. It installs a
11896 ;; library to avoid having to build this as part of Salmon.
11897 (define bwa-for-salmon
11898 (package (inherit bwa)
11900 (version "0.7.12.5")
11903 (uri (git-reference
11904 (url "https://github.com/COMBINE-lab/bwa.git")
11905 (commit (string-append "v" version))))
11906 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11909 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11910 (build-system gnu-build-system)
11912 '(#:tests? #f ;no "check" target
11914 (modify-phases %standard-phases
11916 (lambda* (#:key outputs #:allow-other-keys)
11917 (let* ((out (assoc-ref outputs "out"))
11918 (bin (string-append out "/bin"))
11919 (lib (string-append out "/lib"))
11920 (doc (string-append out "/share/doc/bwa"))
11921 (man (string-append out "/share/man/man1"))
11922 (inc (string-append out "/include/bwa")))
11923 (install-file "bwa" bin)
11924 (install-file "README.md" doc)
11925 (install-file "bwa.1" man)
11926 (install-file "libbwa.a" lib)
11929 (for-each (lambda (file)
11930 (install-file file inc))
11931 (find-files "." "\\.h$")))
11933 ;; no "configure" script
11934 (delete 'configure))))))
11936 (define-public salmon
11942 (uri (git-reference
11943 (url "https://github.com/COMBINE-lab/salmon.git")
11944 (commit (string-append "v" version))))
11945 (file-name (string-append name "-" version "-checkout"))
11948 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11949 (modules '((guix build utils)))
11952 ;; Delete bundled headers for eigen3.
11953 (delete-file-recursively "include/eigen3/")
11955 (build-system cmake-build-system)
11957 `(#:configure-flags
11958 (list (string-append "-DBOOST_INCLUDEDIR="
11959 (assoc-ref %build-inputs "boost")
11961 (string-append "-DBOOST_LIBRARYDIR="
11962 (assoc-ref %build-inputs "boost")
11964 (string-append "-DBoost_LIBRARIES="
11965 "-lboost_iostreams "
11966 "-lboost_filesystem "
11971 "-lboost_program_options")
11972 "-DBoost_FOUND=TRUE"
11973 "-DTBB_LIBRARIES=tbb tbbmalloc"
11974 ;; Don't download RapMap---we already have it!
11975 "-DFETCHED_RAPMAP=1")
11977 (modify-phases %standard-phases
11978 ;; Boost cannot be found, even though it's right there.
11979 (add-after 'unpack 'do-not-look-for-boost
11980 (lambda* (#:key inputs #:allow-other-keys)
11981 (substitute* "CMakeLists.txt"
11982 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11983 (add-after 'unpack 'do-not-phone-home
11985 (substitute* "src/Salmon.cpp"
11986 (("getVersionMessage\\(\\)") "\"\""))))
11987 (add-after 'unpack 'prepare-rapmap
11988 (lambda* (#:key inputs #:allow-other-keys)
11989 (let ((src "external/install/src/rapmap/")
11990 (include "external/install/include/rapmap/")
11991 (rapmap (assoc-ref inputs "rapmap")))
11994 (for-each (lambda (file)
11995 (install-file file src))
11996 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11997 (copy-recursively (string-append rapmap "/include") include)
11998 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11999 "external/install/include/rapmap/FastxParser.hpp"
12000 "external/install/include/rapmap/concurrentqueue.h"
12001 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12002 "external/install/src/rapmap/FastxParser.cpp"
12003 "external/install/src/rapmap/xxhash.c")))))
12004 (add-after 'unpack 'use-system-libraries
12005 (lambda* (#:key inputs #:allow-other-keys)
12006 (substitute* "src/CMakeLists.txt"
12007 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12008 (string-append (assoc-ref inputs "jellyfish")
12009 "/include/jellyfish-" ,(package-version jellyfish)))
12010 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12011 (string-append (assoc-ref inputs "jellyfish")
12012 "/lib/libjellyfish-2.0.a"))
12013 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12014 (string-append (assoc-ref inputs "libdivsufsort")
12015 "/lib/libdivsufsort.so"))
12016 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12017 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12018 "/lib/libstaden-read.a"))
12019 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12020 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12021 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12022 (string-append (assoc-ref inputs "libdivsufsort")
12023 "/lib/libdivsufsort64.so")))
12024 (substitute* "CMakeLists.txt"
12025 ;; Don't prefer static libs
12026 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12027 (("set\\(TBB_LIBRARIES") "message(")
12028 (("find_package\\(Jellyfish.*") "")
12029 (("ExternalProject_Add\\(libcereal") "message(")
12030 (("ExternalProject_Add\\(libbwa") "message(")
12031 (("ExternalProject_Add\\(libjellyfish") "message(")
12032 (("ExternalProject_Add\\(libgff") "message(")
12033 (("ExternalProject_Add\\(libtbb") "message(")
12034 (("ExternalProject_Add\\(libspdlog") "message(")
12035 (("ExternalProject_Add\\(libdivsufsort") "message(")
12036 (("ExternalProject_Add\\(libstadenio") "message(")
12037 (("ExternalProject_Add_Step\\(") "message("))
12039 ;; Ensure that all headers can be found
12040 (setenv "CPLUS_INCLUDE_PATH"
12041 (string-append (getenv "CPLUS_INCLUDE_PATH")
12043 (assoc-ref inputs "bwa")
12046 (assoc-ref inputs "eigen")
12047 "/include/eigen3"))
12049 (string-append (assoc-ref inputs "bwa")
12052 (assoc-ref inputs "eigen")
12053 "/include/eigen3"))
12055 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12056 ;; run. It only exists after the install phase.
12057 (add-after 'unpack 'fix-tests
12059 (substitute* "src/CMakeLists.txt"
12060 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12061 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12065 ("bwa" ,bwa-for-salmon)
12071 (uri (git-reference
12072 (url "https://github.com/COMBINE-lab/RapMap.git")
12073 (commit (string-append "salmon-v" version))))
12074 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12077 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12078 ("jemalloc" ,jemalloc)
12079 ("jellyfish" ,jellyfish)
12082 ("libdivsufsort" ,libdivsufsort)
12083 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12084 ("spdlog-for-salmon" ,spdlog-for-salmon)
12087 (home-page "https://github.com/COMBINE-lab/salmon")
12088 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12089 (description "Salmon is a program to produce highly-accurate,
12090 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12091 its accuracy and speed via a number of different innovations, including the
12092 use of lightweight alignments (accurate but fast-to-compute proxies for
12093 traditional read alignments) and massively-parallel stochastic collapsed
12094 variational inference.")
12095 (license license:gpl3+)))
12097 (define-public python-loompy
12099 (name "python-loompy")
12104 (uri (pypi-uri "loompy" version))
12107 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12108 (build-system python-build-system)
12109 ;; There are no tests
12110 (arguments '(#:tests? #f))
12112 `(("python-h5py" ,python-h5py)
12113 ("python-numpy" ,python-numpy)
12114 ("python-scipy" ,python-scipy)
12115 ("python-typing" ,python-typing)))
12116 (home-page "https://github.com/linnarsson-lab/loompy")
12117 (synopsis "Work with .loom files for single-cell RNA-seq data")
12118 (description "The loom file format is an efficient format for very large
12119 omics datasets, consisting of a main matrix, optional additional layers, a
12120 variable number of row and column annotations. Loom also supports sparse
12121 graphs. This library makes it easy to work with @file{.loom} files for
12122 single-cell RNA-seq data.")
12123 (license license:bsd-3)))
12125 ;; We cannot use the latest commit because it requires Java 9.
12126 (define-public java-forester
12127 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12130 (name "java-forester")
12131 (version (string-append "0-" revision "." (string-take commit 7)))
12134 (uri (git-reference
12135 (url "https://github.com/cmzmasek/forester.git")
12137 (file-name (string-append name "-" version "-checkout"))
12140 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12141 (modules '((guix build utils)))
12144 ;; Delete bundled jars and pre-built classes
12145 (delete-file-recursively "forester/java/resources")
12146 (delete-file-recursively "forester/java/classes")
12147 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12148 ;; Delete bundled applications
12149 (delete-file-recursively "forester_applications")
12151 (build-system ant-build-system)
12153 `(#:tests? #f ; there are none
12155 #:modules ((guix build ant-build-system)
12157 (guix build java-utils)
12161 (modify-phases %standard-phases
12162 (add-after 'unpack 'chdir
12163 (lambda _ (chdir "forester/java") #t))
12164 (add-after 'chdir 'fix-dependencies
12166 (chmod "build.xml" #o664)
12167 (call-with-output-file "build.xml.new"
12171 (with-input-from-file "build.xml"
12172 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12173 `(;; Remove all unjar tags to avoid repacking classes.
12174 (unjar . ,(lambda _ '()))
12175 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12176 (*text* . ,(lambda (_ txt) txt))))
12178 (rename-file "build.xml.new" "build.xml")
12180 ;; FIXME: itext is difficult to package as it depends on a few
12181 ;; unpackaged libraries.
12182 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12184 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12185 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12186 (("pdf_written_to = PdfExporter.*")
12187 "throw new IOException(\"PDF export is not available.\");"))
12189 ;; There is no install target
12190 (replace 'install (install-jars ".")))))
12192 `(("java-commons-codec" ,java-commons-codec)
12193 ("java-openchart2" ,java-openchart2)))
12194 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12195 (synopsis "Phylogenomics libraries for Java")
12196 (description "Forester is a collection of Java libraries for
12197 phylogenomics and evolutionary biology research. It includes support for
12198 reading, writing, and exporting phylogenetic trees.")
12199 (license license:lgpl2.1+))))
12201 (define-public java-forester-1.005
12203 (name "java-forester")
12207 (uri (string-append "http://search.maven.org/remotecontent?"
12208 "filepath=org/biojava/thirdparty/forester/"
12209 version "/forester-" version "-sources.jar"))
12210 (file-name (string-append name "-" version ".jar"))
12213 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12214 (build-system ant-build-system)
12216 `(#:tests? #f ; there are none
12218 #:modules ((guix build ant-build-system)
12220 (guix build java-utils)
12224 (modify-phases %standard-phases
12225 (add-after 'unpack 'fix-dependencies
12226 (lambda* (#:key inputs #:allow-other-keys)
12227 (call-with-output-file "build.xml"
12231 (with-input-from-file "src/build.xml"
12232 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12233 `(;; Remove all unjar tags to avoid repacking classes.
12234 (unjar . ,(lambda _ '()))
12235 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12236 (*text* . ,(lambda (_ txt) txt))))
12238 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12239 "synth_look_and_feel_1.xml")
12240 (copy-file (assoc-ref inputs "phyloxml.xsd")
12242 (substitute* "build.xml"
12243 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12244 "synth_look_and_feel_1.xml")
12245 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12248 ;; FIXME: itext is difficult to package as it depends on a few
12249 ;; unpackaged libraries.
12250 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12252 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12253 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12254 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12255 (("pdf_written_to = PdfExporter.*")
12256 "throw new IOException(\"PDF export is not available.\"); /*")
12257 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12258 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12260 (add-after 'unpack 'delete-pre-built-classes
12261 (lambda _ (delete-file-recursively "src/classes") #t))
12262 ;; There is no install target
12263 (replace 'install (install-jars ".")))))
12265 `(("java-commons-codec" ,java-commons-codec)
12266 ("java-openchart2" ,java-openchart2)))
12267 ;; The source archive does not contain the resources.
12272 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12273 "b61cc2dcede0bede317db362472333115756b8c6/"
12274 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12275 (file-name (string-append name "-phyloxml-" version ".xsd"))
12278 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12279 ("synth_look_and_feel_1.xml"
12282 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12283 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12284 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12285 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12288 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12289 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12290 (synopsis "Phylogenomics libraries for Java")
12291 (description "Forester is a collection of Java libraries for
12292 phylogenomics and evolutionary biology research. It includes support for
12293 reading, writing, and exporting phylogenetic trees.")
12294 (license license:lgpl2.1+)))
12296 (define-public java-biojava-core
12298 (name "java-biojava-core")
12302 (uri (git-reference
12303 (url "https://github.com/biojava/biojava")
12304 (commit (string-append "biojava-" version))))
12305 (file-name (string-append name "-" version "-checkout"))
12308 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12309 (build-system ant-build-system)
12312 #:jar-name "biojava-core.jar"
12313 #:source-dir "biojava-core/src/main/java/"
12314 #:test-dir "biojava-core/src/test"
12315 ;; These tests seem to require internet access.
12316 #:test-exclude (list "**/SearchIOTest.java"
12317 "**/BlastXMLParserTest.java"
12318 "**/GenbankCookbookTest.java"
12319 "**/GenbankProxySequenceReaderTest.java")
12321 (modify-phases %standard-phases
12322 (add-before 'build 'copy-resources
12324 (copy-recursively "biojava-core/src/main/resources"
12327 (add-before 'check 'copy-test-resources
12329 (copy-recursively "biojava-core/src/test/resources"
12330 "build/test-classes")
12333 `(("java-log4j-api" ,java-log4j-api)
12334 ("java-log4j-core" ,java-log4j-core)
12335 ("java-slf4j-api" ,java-slf4j-api)
12336 ("java-slf4j-simple" ,java-slf4j-simple)))
12338 `(("java-junit" ,java-junit)
12339 ("java-hamcrest-core" ,java-hamcrest-core)))
12340 (home-page "http://biojava.org")
12341 (synopsis "Core libraries of Java framework for processing biological data")
12342 (description "BioJava is a project dedicated to providing a Java framework
12343 for processing biological data. It provides analytical and statistical
12344 routines, parsers for common file formats, reference implementations of
12345 popular algorithms, and allows the manipulation of sequences and 3D
12346 structures. The goal of the biojava project is to facilitate rapid
12347 application development for bioinformatics.
12349 This package provides the core libraries.")
12350 (license license:lgpl2.1+)))
12352 (define-public java-biojava-phylo
12353 (package (inherit java-biojava-core)
12354 (name "java-biojava-phylo")
12355 (build-system ant-build-system)
12358 #:jar-name "biojava-phylo.jar"
12359 #:source-dir "biojava-phylo/src/main/java/"
12360 #:test-dir "biojava-phylo/src/test"
12362 (modify-phases %standard-phases
12363 (add-before 'build 'copy-resources
12365 (copy-recursively "biojava-phylo/src/main/resources"
12368 (add-before 'check 'copy-test-resources
12370 (copy-recursively "biojava-phylo/src/test/resources"
12371 "build/test-classes")
12374 `(("java-log4j-api" ,java-log4j-api)
12375 ("java-log4j-core" ,java-log4j-core)
12376 ("java-slf4j-api" ,java-slf4j-api)
12377 ("java-slf4j-simple" ,java-slf4j-simple)
12378 ("java-biojava-core" ,java-biojava-core)
12379 ("java-forester" ,java-forester)))
12381 `(("java-junit" ,java-junit)
12382 ("java-hamcrest-core" ,java-hamcrest-core)))
12383 (home-page "http://biojava.org")
12384 (synopsis "Biojava interface to the forester phylogenomics library")
12385 (description "The phylo module provides a biojava interface layer to the
12386 forester phylogenomics library for constructing phylogenetic trees.")))
12388 (define-public java-biojava-alignment
12389 (package (inherit java-biojava-core)
12390 (name "java-biojava-alignment")
12391 (build-system ant-build-system)
12394 #:jar-name "biojava-alignment.jar"
12395 #:source-dir "biojava-alignment/src/main/java/"
12396 #:test-dir "biojava-alignment/src/test"
12398 (modify-phases %standard-phases
12399 (add-before 'build 'copy-resources
12401 (copy-recursively "biojava-alignment/src/main/resources"
12404 (add-before 'check 'copy-test-resources
12406 (copy-recursively "biojava-alignment/src/test/resources"
12407 "build/test-classes")
12410 `(("java-log4j-api" ,java-log4j-api)
12411 ("java-log4j-core" ,java-log4j-core)
12412 ("java-slf4j-api" ,java-slf4j-api)
12413 ("java-slf4j-simple" ,java-slf4j-simple)
12414 ("java-biojava-core" ,java-biojava-core)
12415 ("java-biojava-phylo" ,java-biojava-phylo)
12416 ("java-forester" ,java-forester)))
12418 `(("java-junit" ,java-junit)
12419 ("java-hamcrest-core" ,java-hamcrest-core)))
12420 (home-page "http://biojava.org")
12421 (synopsis "Biojava API for genetic sequence alignment")
12422 (description "The alignment module of BioJava provides an API that
12426 @item implementations of dynamic programming algorithms for sequence
12428 @item reading and writing of popular alignment file formats;
12429 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12432 (define-public java-biojava-core-4.0
12433 (package (inherit java-biojava-core)
12434 (name "java-biojava-core")
12438 (uri (git-reference
12439 (url "https://github.com/biojava/biojava")
12440 (commit (string-append "biojava-" version))))
12441 (file-name (string-append name "-" version "-checkout"))
12444 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12446 (define-public java-biojava-phylo-4.0
12447 (package (inherit java-biojava-core-4.0)
12448 (name "java-biojava-phylo")
12449 (build-system ant-build-system)
12452 #:jar-name "biojava-phylo.jar"
12453 #:source-dir "biojava-phylo/src/main/java/"
12454 #:test-dir "biojava-phylo/src/test"
12456 (modify-phases %standard-phases
12457 (add-before 'build 'copy-resources
12459 (copy-recursively "biojava-phylo/src/main/resources"
12462 (add-before 'check 'copy-test-resources
12464 (copy-recursively "biojava-phylo/src/test/resources"
12465 "build/test-classes")
12468 `(("java-log4j-api" ,java-log4j-api)
12469 ("java-log4j-core" ,java-log4j-core)
12470 ("java-slf4j-api" ,java-slf4j-api)
12471 ("java-slf4j-simple" ,java-slf4j-simple)
12472 ("java-biojava-core" ,java-biojava-core-4.0)
12473 ("java-forester" ,java-forester-1.005)))
12475 `(("java-junit" ,java-junit)
12476 ("java-hamcrest-core" ,java-hamcrest-core)))
12477 (home-page "http://biojava.org")
12478 (synopsis "Biojava interface to the forester phylogenomics library")
12479 (description "The phylo module provides a biojava interface layer to the
12480 forester phylogenomics library for constructing phylogenetic trees.")))
12482 (define-public java-biojava-alignment-4.0
12483 (package (inherit java-biojava-core-4.0)
12484 (name "java-biojava-alignment")
12485 (build-system ant-build-system)
12488 #:jar-name "biojava-alignment.jar"
12489 #:source-dir "biojava-alignment/src/main/java/"
12490 #:test-dir "biojava-alignment/src/test"
12492 (modify-phases %standard-phases
12493 (add-before 'build 'copy-resources
12495 (copy-recursively "biojava-alignment/src/main/resources"
12498 (add-before 'check 'copy-test-resources
12500 (copy-recursively "biojava-alignment/src/test/resources"
12501 "build/test-classes")
12504 `(("java-log4j-api" ,java-log4j-api)
12505 ("java-log4j-core" ,java-log4j-core)
12506 ("java-slf4j-api" ,java-slf4j-api)
12507 ("java-slf4j-simple" ,java-slf4j-simple)
12508 ("java-biojava-core" ,java-biojava-core-4.0)
12509 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12510 ("java-forester" ,java-forester-1.005)))
12512 `(("java-junit" ,java-junit)
12513 ("java-hamcrest-core" ,java-hamcrest-core)))
12514 (home-page "http://biojava.org")
12515 (synopsis "Biojava API for genetic sequence alignment")
12516 (description "The alignment module of BioJava provides an API that
12520 @item implementations of dynamic programming algorithms for sequence
12522 @item reading and writing of popular alignment file formats;
12523 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12526 (define-public dropseq-tools
12528 (name "dropseq-tools")
12533 (uri "http://mccarrolllab.com/download/1276/")
12534 (file-name (string-append "dropseq-tools-" version ".zip"))
12537 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12538 ;; Delete bundled libraries
12539 (modules '((guix build utils)))
12542 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12543 (delete-file-recursively "3rdParty")))))
12544 (build-system ant-build-system)
12546 `(#:tests? #f ; test data are not included
12547 #:test-target "test"
12548 #:build-target "all"
12549 #:source-dir "public/src/"
12552 (list (string-append "-Dpicard.executable.dir="
12553 (assoc-ref %build-inputs "java-picard")
12555 #:modules ((ice-9 match)
12558 (guix build java-utils)
12559 (guix build ant-build-system))
12561 (modify-phases %standard-phases
12562 ;; All dependencies must be linked to "lib", because that's where
12563 ;; they will be searched for when the Class-Path property of the
12564 ;; manifest is computed.
12565 (add-after 'unpack 'record-references
12566 (lambda* (#:key inputs #:allow-other-keys)
12567 (mkdir-p "jar/lib")
12568 (let ((dirs (filter-map (match-lambda
12570 (if (and (string-prefix? "java-" name)
12571 (not (string=? name "java-testng")))
12574 (for-each (lambda (jar)
12575 (symlink jar (string-append "jar/lib/" (basename jar))))
12576 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12579 ;; There is no installation target
12581 (lambda* (#:key inputs outputs #:allow-other-keys)
12582 (let* ((out (assoc-ref outputs "out"))
12583 (bin (string-append out "/bin"))
12584 (share (string-append out "/share/java/"))
12585 (lib (string-append share "/lib/"))
12586 (scripts (list "BAMTagHistogram"
12587 "BAMTagofTagCounts"
12588 "BaseDistributionAtReadPosition"
12589 "CollapseBarcodesInPlace"
12590 "CollapseTagWithContext"
12592 "CreateIntervalsFiles"
12593 "DetectBeadSynthesisErrors"
12594 "DigitalExpression"
12595 "Drop-seq_alignment.sh"
12598 "GatherGeneGCLength"
12599 "GatherMolecularBarcodeDistributionByGene"
12600 "GatherReadQualityMetrics"
12603 "SelectCellsByNumTranscripts"
12604 "SingleCellRnaSeqMetricsCollector"
12605 "TagBamWithReadSequenceExtended"
12606 "TagReadWithGeneExon"
12607 "TagReadWithInterval"
12608 "TrimStartingSequence"
12609 "ValidateReference")))
12610 (for-each mkdir-p (list bin share lib))
12611 (install-file "dist/dropseq.jar" share)
12612 (for-each (lambda (script)
12613 (chmod script #o555)
12614 (install-file script bin))
12616 (substitute* (map (lambda (script)
12617 (string-append bin "/" script))
12619 (("^java") (which "java"))
12620 (("jar_deploy_dir=.*")
12621 (string-append "jar_deploy_dir=" share "\n"))))
12623 ;; FIXME: We do this after stripping jars because we don't want it to
12624 ;; copy all these jars and strip them. We only want to install
12625 ;; links. Arguably, this is a problem with the ant-build-system.
12626 (add-after 'strip-jar-timestamps 'install-links
12627 (lambda* (#:key outputs #:allow-other-keys)
12628 (let* ((out (assoc-ref outputs "out"))
12629 (share (string-append out "/share/java/"))
12630 (lib (string-append share "/lib/")))
12631 (for-each (lambda (jar)
12632 (symlink (readlink jar)
12633 (string-append lib (basename jar))))
12634 (find-files "jar/lib" "\\.jar$")))
12637 `(("jdk" ,icedtea-8)
12638 ("java-picard" ,java-picard-2.10.3)
12639 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12640 ("java-commons-math3" ,java-commons-math3)
12641 ("java-commons-jexl2" ,java-commons-jexl-2)
12642 ("java-commons-collections4" ,java-commons-collections4)
12643 ("java-commons-lang2" ,java-commons-lang)
12644 ("java-commons-io" ,java-commons-io)
12645 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12646 ("java-guava" ,java-guava)
12647 ("java-la4j" ,java-la4j)
12648 ("java-biojava-core" ,java-biojava-core-4.0)
12649 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12650 ("java-jdistlib" ,java-jdistlib)
12651 ("java-simple-xml" ,java-simple-xml)
12652 ("java-snakeyaml" ,java-snakeyaml)))
12655 ("java-testng" ,java-testng)))
12656 (home-page "http://mccarrolllab.com/dropseq/")
12657 (synopsis "Tools for Drop-seq analyses")
12658 (description "Drop-seq is a technology to enable biologists to
12659 analyze RNA expression genome-wide in thousands of individual cells at
12660 once. This package provides tools to perform Drop-seq analyses.")
12661 (license license:expat)))
12663 (define-public pigx-rnaseq
12665 (name "pigx-rnaseq")
12669 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12670 "releases/download/v" version
12671 "/pigx_rnaseq-" version ".tar.gz"))
12674 "168hx2ig3rarphx3l21ay9yyg8ipaakzixnrhpbdi0sknhyvrrk8"))))
12675 (build-system gnu-build-system)
12677 `(#:parallel-tests? #f ; not supported
12679 (modify-phases %standard-phases
12680 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12681 (add-after 'unpack 'disable-resource-intensive-test
12683 (substitute* "Makefile.in"
12684 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12685 (("^ test.sh") ""))
12687 (add-after 'install 'wrap-executable
12688 ;; Make sure the executable finds all R modules.
12689 (lambda* (#:key inputs outputs #:allow-other-keys)
12690 (let ((out (assoc-ref outputs "out")))
12691 (wrap-program (string-append out "/bin/pigx-rnaseq")
12692 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12693 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12696 `(("snakemake" ,snakemake)
12698 ("multiqc" ,multiqc)
12700 ("trim-galore" ,trim-galore)
12702 ("samtools" ,samtools)
12703 ("bedtools" ,bedtools)
12704 ("r-minimal" ,r-minimal)
12705 ("r-rmarkdown" ,r-rmarkdown)
12706 ("r-ggplot2" ,r-ggplot2)
12707 ("r-ggrepel" ,r-ggrepel)
12708 ("r-gprofiler" ,r-gprofiler)
12709 ("r-deseq2" ,r-deseq2)
12711 ("r-knitr" ,r-knitr)
12712 ("r-pheatmap" ,r-pheatmap)
12713 ("r-corrplot" ,r-corrplot)
12714 ("r-reshape2" ,r-reshape2)
12715 ("r-plotly" ,r-plotly)
12716 ("r-scales" ,r-scales)
12717 ("r-summarizedexperiment" ,r-summarizedexperiment)
12718 ("r-crosstalk" ,r-crosstalk)
12719 ("r-tximport" ,r-tximport)
12720 ("r-rtracklayer" ,r-rtracklayer)
12721 ("r-rjson" ,r-rjson)
12723 ("ghc-pandoc" ,ghc-pandoc-1)
12724 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12725 ("python-wrapper" ,python-wrapper)
12726 ("python-pyyaml" ,python-pyyaml)))
12727 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12728 (synopsis "Analysis pipeline for RNA sequencing experiments")
12729 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12730 reporting for RNA sequencing experiments. It is easy to use and produces high
12731 quality reports. The inputs are reads files from the sequencing experiment,
12732 and a configuration file which describes the experiment. In addition to
12733 quality control of the experiment, the pipeline produces a differential
12734 expression report comparing samples in an easily configurable manner.")
12735 (license license:gpl3+)))
12737 (define-public pigx-chipseq
12739 (name "pigx-chipseq")
12743 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12744 "releases/download/v" version
12745 "/pigx_chipseq-" version ".tar.gz"))
12748 "1plw0bz0b7flj0g9irbn8n520005lmajkiq5flpizzapsl0a0r9g"))))
12749 (build-system gnu-build-system)
12751 `(#:tests? #f ; parts of the tests rely on access to the network
12753 (modify-phases %standard-phases
12754 (add-after 'install 'wrap-executable
12755 ;; Make sure the executable finds all R modules.
12756 (lambda* (#:key inputs outputs #:allow-other-keys)
12757 (let ((out (assoc-ref outputs "out")))
12758 (wrap-program (string-append out "/bin/pigx-chipseq")
12759 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12760 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12763 `(("r-minimal" ,r-minimal)
12764 ("r-argparser" ,r-argparser)
12765 ("r-chipseq" ,r-chipseq)
12766 ("r-data-table" ,r-data-table)
12767 ("r-genomation" ,r-genomation)
12768 ("r-genomicranges" ,r-genomicranges)
12769 ("r-rtracklayer" ,r-rtracklayer)
12771 ("r-stringr" ,r-stringr)
12772 ("r-jsonlite" ,r-jsonlite)
12773 ("r-heatmaply" ,r-heatmaply)
12774 ("r-ggplot2" ,r-ggplot2)
12775 ("r-plotly" ,r-plotly)
12776 ("python-wrapper" ,python-wrapper)
12777 ("python-magic" ,python-magic)
12778 ("python-pyyaml" ,python-pyyaml)
12779 ("python-xlrd" ,python-xlrd)
12780 ("snakemake" ,snakemake)
12781 ("trim-galore" ,trim-galore)
12783 ("multiqc" ,multiqc)
12785 ("ghc-pandoc" ,ghc-pandoc-1)
12786 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12790 ("snakemake" ,snakemake)
12791 ("samtools" ,samtools)
12792 ("bedtools" ,bedtools)
12793 ("kentutils" ,kentutils)))
12795 `(("python-pytest" ,python-pytest)))
12796 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12797 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12798 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12799 calling and reporting for ChIP sequencing experiments. It is easy to use and
12800 produces high quality reports. The inputs are reads files from the sequencing
12801 experiment, and a configuration file which describes the experiment. In
12802 addition to quality control of the experiment, the pipeline enables to set up
12803 multiple peak calling analysis and allows the generation of a UCSC track hub
12804 in an easily configurable manner.")
12805 (license license:gpl3+)))
12807 (define-public pigx-bsseq
12809 (name "pigx-bsseq")
12813 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12814 "releases/download/v" version
12815 "/pigx_bsseq-" version ".tar.gz"))
12818 "1h8ma99vi7hs83nafvjpq8jmaq9977j3n11c4zd95hai0cf7zxmp"))))
12819 (build-system gnu-build-system)
12822 (modify-phases %standard-phases
12823 (add-before 'check 'set-timezone
12824 ;; The readr package is picky about timezones.
12825 (lambda* (#:key inputs #:allow-other-keys)
12826 (setenv "TZ" "UTC+1")
12828 (string-append (assoc-ref inputs "tzdata")
12829 "/share/zoneinfo"))
12831 (add-after 'install 'wrap-executable
12832 ;; Make sure the executable finds all R modules.
12833 (lambda* (#:key inputs outputs #:allow-other-keys)
12834 (let ((out (assoc-ref outputs "out")))
12835 (wrap-program (string-append out "/bin/pigx-bsseq")
12836 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12837 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12840 `(("tzdata" ,tzdata)))
12842 `(("r-minimal" ,r-minimal)
12843 ("r-annotationhub" ,r-annotationhub)
12845 ("r-genomation" ,r-genomation)
12846 ("r-methylkit" ,r-methylkit)
12847 ("r-rtracklayer" ,r-rtracklayer)
12848 ("r-rmarkdown" ,r-rmarkdown)
12849 ("r-bookdown" ,r-bookdown)
12850 ("r-ggplot2" ,r-ggplot2)
12851 ("r-ggbio" ,r-ggbio)
12852 ("ghc-pandoc" ,ghc-pandoc-1)
12853 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12854 ("python-wrapper" ,python-wrapper)
12855 ("python-pyyaml" ,python-pyyaml)
12856 ("snakemake" ,snakemake)
12857 ("bismark" ,bismark)
12860 ("trim-galore" ,trim-galore)
12861 ("cutadapt" ,cutadapt)
12862 ("samtools" ,samtools)))
12863 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12864 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12865 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12866 data of bisulfite experiments; it produces reports on aggregate methylation
12867 and coverage and can be used to produce information on differential
12868 methylation and segmentation.")
12869 (license license:gpl3+)))
12871 (define-public pigx-scrnaseq
12873 (name "pigx-scrnaseq")
12877 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12878 "releases/download/v" version
12879 "/pigx_scrnaseq-" version ".tar.gz"))
12882 "12qdq0nj1wdkyighdxj6924bmbpd1a0b3gam6w64l4hiqrv5sijz"))))
12883 (build-system gnu-build-system)
12885 `(#:configure-flags
12886 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12887 "/share/java/picard.jar")
12888 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12889 "/share/java/dropseq.jar"))
12891 (modify-phases %standard-phases
12892 (add-after 'install 'wrap-executable
12893 ;; Make sure the executable finds all R modules.
12894 (lambda* (#:key inputs outputs #:allow-other-keys)
12895 (let ((out (assoc-ref outputs "out")))
12896 (wrap-program (string-append out "/bin/pigx-scrnaseq")
12897 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12898 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12901 `(("coreutils" ,coreutils)
12903 ("dropseq-tools" ,dropseq-tools)
12905 ("java-picard" ,java-picard)
12906 ("java" ,icedtea-8)
12907 ("python-wrapper" ,python-wrapper)
12908 ("python-pyyaml" ,python-pyyaml)
12909 ("python-pandas" ,python-pandas)
12910 ("python-numpy" ,python-numpy)
12911 ("python-loompy" ,python-loompy)
12912 ("ghc-pandoc" ,ghc-pandoc-1)
12913 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1)
12914 ("snakemake" ,snakemake)
12916 ("r-minimal" ,r-minimal)
12917 ("r-argparser" ,r-argparser)
12918 ("r-cowplot" ,r-cowplot)
12919 ("r-data-table" ,r-data-table)
12920 ("r-delayedarray" ,r-delayedarray)
12921 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12922 ("r-dplyr" ,r-dplyr)
12923 ("r-dropbead" ,r-dropbead)
12925 ("r-genomicalignments" ,r-genomicalignments)
12926 ("r-genomicfiles" ,r-genomicfiles)
12927 ("r-genomicranges" ,r-genomicranges)
12928 ("r-ggplot2" ,r-ggplot2)
12929 ("r-hdf5array" ,r-hdf5array)
12930 ("r-pheatmap" ,r-pheatmap)
12931 ("r-rmarkdown" ,r-rmarkdown)
12932 ("r-rsamtools" ,r-rsamtools)
12933 ("r-rtracklayer" ,r-rtracklayer)
12934 ("r-rtsne" ,r-rtsne)
12935 ("r-scater" ,r-scater)
12936 ("r-scran" ,r-scran)
12937 ("r-singlecellexperiment" ,r-singlecellexperiment)
12938 ("r-stringr" ,r-stringr)
12939 ("r-yaml" ,r-yaml)))
12940 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12941 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12942 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12943 quality control for single cell RNA sequencing experiments. The inputs are
12944 read files from the sequencing experiment, and a configuration file which
12945 describes the experiment. It produces processed files for downstream analysis
12946 and interactive quality reports. The pipeline is designed to work with UMI
12948 (license license:gpl3+)))
12950 (define-public pigx
12956 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12957 "releases/download/v" version
12958 "/pigx-" version ".tar.gz"))
12961 "0sb708sl42h3s5z872jb1w70bbqplwapnsc1wm27zcsvi7li4gw8"))))
12962 (build-system gnu-build-system)
12964 `(("python" ,python)
12965 ("pigx-bsseq" ,pigx-bsseq)
12966 ("pigx-chipseq" ,pigx-chipseq)
12967 ("pigx-rnaseq" ,pigx-rnaseq)
12968 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12969 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12970 (synopsis "Analysis pipelines for genomics")
12971 (description "PiGx is a collection of genomics pipelines. It includes the
12972 following pipelines:
12975 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12976 @item PiGx RNAseq for RNAseq samples
12977 @item PiGx scRNAseq for single cell dropseq analysis
12978 @item PiGx ChIPseq for reads from ChIPseq experiments
12981 All pipelines are easily configured with a simple sample sheet and a
12982 descriptive settings file. The result is a set of comprehensive, interactive
12983 HTML reports with interesting findings about your samples.")
12984 (license license:gpl3+)))
12986 (define-public r-diversitree
12988 (name "r-diversitree")
12993 (uri (cran-uri "diversitree" version))
12996 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
12997 (build-system r-build-system)
12999 `(("gfortran" ,gfortran)))
13000 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13003 ("r-desolve" ,r-desolve)
13005 ("r-suplex" ,r-subplex)))
13006 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13007 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13008 (description "This package contains a number of comparative \"phylogenetic\"
13009 methods, mostly focusing on analysing diversification and character evolution.
13010 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13011 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13012 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13013 include Markov models of discrete and continuous trait evolution and constant
13014 rate speciation and extinction.")
13015 (license license:gpl2+)))