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>
13 ;;; This file is part of GNU Guix.
15 ;;; GNU Guix is free software; you can redistribute it and/or modify it
16 ;;; under the terms of the GNU General Public License as published by
17 ;;; the Free Software Foundation; either version 3 of the License, or (at
18 ;;; your option) any later version.
20 ;;; GNU Guix is distributed in the hope that it will be useful, but
21 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
22 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23 ;;; GNU General Public License for more details.
25 ;;; You should have received a copy of the GNU General Public License
26 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
28 (define-module (gnu packages bioinformatics)
29 #:use-module ((guix licenses) #:prefix license:)
30 #:use-module (guix packages)
31 #:use-module (guix utils)
32 #:use-module (guix download)
33 #:use-module (guix git-download)
34 #:use-module (guix hg-download)
35 #:use-module (guix build-system ant)
36 #:use-module (guix build-system gnu)
37 #:use-module (guix build-system cmake)
38 #:use-module (guix build-system ocaml)
39 #:use-module (guix build-system perl)
40 #:use-module (guix build-system python)
41 #:use-module (guix build-system r)
42 #:use-module (guix build-system ruby)
43 #:use-module (guix build-system scons)
44 #:use-module (guix build-system trivial)
45 #:use-module (gnu packages)
46 #:use-module (gnu packages autotools)
47 #:use-module (gnu packages algebra)
48 #:use-module (gnu packages base)
49 #:use-module (gnu packages bash)
50 #:use-module (gnu packages bison)
51 #:use-module (gnu packages boost)
52 #:use-module (gnu packages check)
53 #:use-module (gnu packages compression)
54 #:use-module (gnu packages cpio)
55 #:use-module (gnu packages cran)
56 #:use-module (gnu packages curl)
57 #:use-module (gnu packages documentation)
58 #:use-module (gnu packages databases)
59 #:use-module (gnu packages datastructures)
60 #:use-module (gnu packages file)
61 #:use-module (gnu packages flex)
62 #:use-module (gnu packages gawk)
63 #:use-module (gnu packages gcc)
64 #:use-module (gnu packages gd)
65 #:use-module (gnu packages gtk)
66 #:use-module (gnu packages glib)
67 #:use-module (gnu packages graph)
68 #:use-module (gnu packages groff)
69 #:use-module (gnu packages guile)
70 #:use-module (gnu packages haskell)
71 #:use-module (gnu packages image)
72 #:use-module (gnu packages imagemagick)
73 #:use-module (gnu packages java)
74 #:use-module (gnu packages jemalloc)
75 #:use-module (gnu packages ldc)
76 #:use-module (gnu packages linux)
77 #:use-module (gnu packages logging)
78 #:use-module (gnu packages machine-learning)
79 #:use-module (gnu packages man)
80 #:use-module (gnu packages maths)
81 #:use-module (gnu packages mpi)
82 #:use-module (gnu packages ncurses)
83 #:use-module (gnu packages ocaml)
84 #:use-module (gnu packages pcre)
85 #:use-module (gnu packages parallel)
86 #:use-module (gnu packages pdf)
87 #:use-module (gnu packages perl)
88 #:use-module (gnu packages perl-check)
89 #:use-module (gnu packages pkg-config)
90 #:use-module (gnu packages popt)
91 #:use-module (gnu packages protobuf)
92 #:use-module (gnu packages python)
93 #:use-module (gnu packages python-web)
94 #:use-module (gnu packages readline)
95 #:use-module (gnu packages ruby)
96 #:use-module (gnu packages serialization)
97 #:use-module (gnu packages shells)
98 #:use-module (gnu packages statistics)
99 #:use-module (gnu packages swig)
100 #:use-module (gnu packages tbb)
101 #:use-module (gnu packages tex)
102 #:use-module (gnu packages texinfo)
103 #:use-module (gnu packages textutils)
104 #:use-module (gnu packages time)
105 #:use-module (gnu packages tls)
106 #:use-module (gnu packages vim)
107 #:use-module (gnu packages web)
108 #:use-module (gnu packages xml)
109 #:use-module (gnu packages xorg)
110 #:use-module (srfi srfi-1)
111 #:use-module (ice-9 match))
113 (define-public aragorn
120 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
124 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
125 (build-system gnu-build-system)
127 `(#:tests? #f ; there are no tests
129 (modify-phases %standard-phases
133 (zero? (system* "gcc"
139 (string-append "aragorn" ,version ".c")))))
141 (lambda* (#:key outputs #:allow-other-keys)
142 (let* ((out (assoc-ref outputs "out"))
143 (bin (string-append out "/bin"))
144 (man (string-append out "/share/man/man1")))
146 (install-file "aragorn" bin)
148 (install-file "aragorn.1" man))
150 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
151 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
153 "Aragorn identifies transfer RNA, mitochondrial RNA and
154 transfer-messenger RNA from nucleotide sequences, based on homology to known
155 tRNA consensus sequences and RNA structure. It also outputs the secondary
156 structure of the predicted RNA.")
157 (license license:gpl2)))
165 ;; BamM is not available on pypi.
167 "https://github.com/Ecogenomics/BamM/archive/"
169 (file-name (string-append name "-" version ".tar.gz"))
172 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
173 (modules '((guix build utils)))
176 ;; Delete bundled htslib.
177 (delete-file-recursively "c/htslib-1.3.1")
179 (build-system python-build-system)
181 `(#:python ,python-2 ; BamM is Python 2 only.
182 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
183 ;; been modified from its original form.
185 (let ((htslib (assoc-ref %build-inputs "htslib")))
186 (list "--with-libhts-lib" (string-append htslib "/lib")
187 "--with-libhts-inc" (string-append htslib "/include/htslib")))
189 (modify-phases %standard-phases
190 (add-after 'unpack 'autogen
192 (with-directory-excursion "c"
193 (let ((sh (which "sh")))
194 ;; Use autogen so that 'configure' works.
195 (substitute* "autogen.sh" (("/bin/sh") sh))
196 (setenv "CONFIG_SHELL" sh)
197 (substitute* "configure" (("/bin/sh") sh))
198 (zero? (system* "./autogen.sh"))))))
200 ;; Run tests after installation so compilation only happens once.
202 (add-after 'install 'wrap-executable
203 (lambda* (#:key outputs #:allow-other-keys)
204 (let* ((out (assoc-ref outputs "out"))
205 (path (getenv "PATH")))
206 (wrap-program (string-append out "/bin/bamm")
207 `("PATH" ":" prefix (,path))))
209 (add-after 'wrap-executable 'post-install-check
210 (lambda* (#:key inputs outputs #:allow-other-keys)
212 (string-append (assoc-ref outputs "out")
217 (assoc-ref outputs "out")
219 (string-take (string-take-right
220 (assoc-ref inputs "python") 5) 3)
222 (getenv "PYTHONPATH")))
223 ;; There are 2 errors printed, but they are safe to ignore:
224 ;; 1) [E::hts_open_format] fail to open file ...
225 ;; 2) samtools view: failed to open ...
226 (zero? (system* "nosetests")))))))
228 `(("autoconf" ,autoconf)
229 ("automake" ,automake)
232 ("python-nose" ,python2-nose)
233 ("python-pysam" ,python2-pysam)))
235 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
236 ("samtools" ,samtools)
240 ("coreutils" ,coreutils)))
242 `(("python-numpy" ,python2-numpy)))
243 (home-page "http://ecogenomics.github.io/BamM/")
244 (synopsis "Metagenomics-focused BAM file manipulator")
246 "BamM is a C library, wrapped in python, to efficiently generate and
247 parse BAM files, specifically for the analysis of metagenomic data. For
248 instance, it implements several methods to assess contig-wise read coverage.")
249 (license license:lgpl3+)))
251 (define-public bamtools
258 "https://github.com/pezmaster31/bamtools/archive/v"
260 (file-name (string-append name "-" version ".tar.gz"))
263 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
264 (build-system cmake-build-system)
266 `(#:tests? #f ;no "check" target
268 (modify-phases %standard-phases
270 'configure 'set-ldflags
271 (lambda* (#:key outputs #:allow-other-keys)
275 (assoc-ref outputs "out") "/lib/bamtools")))))))
276 (inputs `(("zlib" ,zlib)))
277 (home-page "https://github.com/pezmaster31/bamtools")
278 (synopsis "C++ API and command-line toolkit for working with BAM data")
280 "BamTools provides both a C++ API and a command-line toolkit for handling
282 (license license:expat)))
284 (define-public bcftools
291 "https://github.com/samtools/bcftools/releases/download/"
292 version "/bcftools-" version ".tar.bz2"))
295 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
296 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
297 (modules '((guix build utils)))
299 ;; Delete bundled htslib.
300 '(delete-file-recursively "htslib-1.5"))))
301 (build-system gnu-build-system)
303 `(#:test-target "test"
304 #:configure-flags (list "--with-htslib=system")
308 "LIBS=-lgsl -lgslcblas"
309 (string-append "prefix=" (assoc-ref %outputs "out"))
310 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
311 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
312 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
313 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
314 (string-append "PACKAGE_VERSION=" ,version))
316 (modify-phases %standard-phases
317 (add-before 'check 'patch-tests
319 (substitute* "test/test.pl"
320 (("/bin/bash") (which "bash")))
328 (home-page "https://samtools.github.io/bcftools/")
329 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
331 "BCFtools is a set of utilities that manipulate variant calls in the
332 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
333 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
334 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
335 (license (list license:gpl3+ license:expat))))
337 (define-public bedops
343 (uri (string-append "https://github.com/bedops/bedops/archive/v"
345 (file-name (string-append name "-" version ".tar.gz"))
348 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
349 (build-system gnu-build-system)
352 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
354 (modify-phases %standard-phases
355 (add-after 'unpack 'unpack-tarballs
357 ;; FIXME: Bedops includes tarballs of minimally patched upstream
358 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
359 ;; libraries because at least one of the libraries (zlib) is
360 ;; patched to add a C++ function definition (deflateInit2cpp).
361 ;; Until the Bedops developers offer a way to link against system
362 ;; libraries we have to build the in-tree copies of these three
365 ;; See upstream discussion:
366 ;; https://github.com/bedops/bedops/issues/124
368 ;; Unpack the tarballs to benefit from shebang patching.
369 (with-directory-excursion "third-party"
370 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
371 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
372 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
373 ;; Disable unpacking of tarballs in Makefile.
374 (substitute* "system.mk/Makefile.linux"
375 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
376 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
377 (substitute* "third-party/zlib-1.2.7/Makefile.in"
378 (("^SHELL=.*$") "SHELL=bash\n"))
380 (delete 'configure))))
381 (home-page "https://github.com/bedops/bedops")
382 (synopsis "Tools for high-performance genomic feature operations")
384 "BEDOPS is a suite of tools to address common questions raised in genomic
385 studies---mostly with regard to overlap and proximity relationships between
386 data sets. It aims to be scalable and flexible, facilitating the efficient
387 and accurate analysis and management of large-scale genomic data.
389 BEDOPS provides tools that perform highly efficient and scalable Boolean and
390 other set operations, statistical calculations, archiving, conversion and
391 other management of genomic data of arbitrary scale. Tasks can be easily
392 split by chromosome for distributing whole-genome analyses across a
393 computational cluster.")
394 (license license:gpl2+)))
396 (define-public bedtools
402 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
403 "download/v" version "/"
404 "bedtools-" version ".tar.gz"))
407 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
408 (build-system gnu-build-system)
410 '(#:test-target "test"
412 (list (string-append "prefix=" (assoc-ref %outputs "out")))
414 (modify-phases %standard-phases
415 (delete 'configure))))
416 (native-inputs `(("python" ,python-2)))
418 `(("samtools" ,samtools)
420 (home-page "https://github.com/arq5x/bedtools2")
421 (synopsis "Tools for genome analysis and arithmetic")
423 "Collectively, the bedtools utilities are a swiss-army knife of tools for
424 a wide-range of genomics analysis tasks. The most widely-used tools enable
425 genome arithmetic: that is, set theory on the genome. For example, bedtools
426 allows one to intersect, merge, count, complement, and shuffle genomic
427 intervals from multiple files in widely-used genomic file formats such as BAM,
429 (license license:gpl2)))
431 ;; Later releases of bedtools produce files with more columns than
432 ;; what Ribotaper expects.
433 (define-public bedtools-2.18
434 (package (inherit bedtools)
439 (uri (string-append "https://github.com/arq5x/bedtools2/"
440 "archive/v" version ".tar.gz"))
441 (file-name (string-append name "-" version ".tar.gz"))
444 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
446 '(#:test-target "test"
448 (modify-phases %standard-phases
451 (lambda* (#:key outputs #:allow-other-keys)
452 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
453 (for-each (lambda (file)
454 (install-file file bin))
455 (find-files "bin" ".*")))
458 (define-public ribotaper
464 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
465 "files/RiboTaper/RiboTaper_Version_"
469 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
470 (build-system gnu-build-system)
473 (modify-phases %standard-phases
474 (add-after 'install 'wrap-executables
475 (lambda* (#:key inputs outputs #:allow-other-keys)
476 (let* ((out (assoc-ref outputs "out")))
479 (wrap-program (string-append out "/bin/" script)
480 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
481 '("create_annotations_files.bash"
482 "create_metaplots.bash"
483 "Ribotaper_ORF_find.sh"
484 "Ribotaper.sh"))))))))
486 `(("bedtools" ,bedtools-2.18)
487 ("samtools" ,samtools-0.1)
488 ("r-minimal" ,r-minimal)
489 ("r-foreach" ,r-foreach)
490 ("r-xnomial" ,r-xnomial)
492 ("r-multitaper" ,r-multitaper)
493 ("r-seqinr" ,r-seqinr)))
494 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
495 (synopsis "Define translated ORFs using ribosome profiling data")
497 "Ribotaper is a method for defining translated @dfn{open reading
498 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
499 provides the Ribotaper pipeline.")
500 (license license:gpl3+)))
502 (define-public ribodiff
509 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
510 "archive/v" version ".tar.gz"))
511 (file-name (string-append name "-" version ".tar.gz"))
514 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
515 (build-system python-build-system)
519 (modify-phases %standard-phases
520 ;; Generate an installable executable script wrapper.
521 (add-after 'unpack 'patch-setup.py
523 (substitute* "setup.py"
524 (("^(.*)packages=.*" line prefix)
525 (string-append line "\n"
526 prefix "scripts=['scripts/TE.py'],\n")))
529 `(("python-numpy" ,python2-numpy)
530 ("python-matplotlib" ,python2-matplotlib)
531 ("python-scipy" ,python2-scipy)
532 ("python-statsmodels" ,python2-statsmodels)))
534 `(("python-mock" ,python2-mock)
535 ("python-nose" ,python2-nose)))
536 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
537 (synopsis "Detect translation efficiency changes from ribosome footprints")
538 (description "RiboDiff is a statistical tool that detects the protein
539 translational efficiency change from Ribo-Seq (ribosome footprinting) and
540 RNA-Seq data. It uses a generalized linear model to detect genes showing
541 difference in translational profile taking mRNA abundance into account. It
542 facilitates us to decipher the translational regulation that behave
543 independently with transcriptional regulation.")
544 (license license:gpl3+)))
546 (define-public bioawk
552 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
554 (file-name (string-append name "-" version ".tar.gz"))
556 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
557 (build-system gnu-build-system)
563 `(#:tests? #f ; There are no tests to run.
564 ;; Bison must generate files, before other targets can build.
567 (modify-phases %standard-phases
568 (delete 'configure) ; There is no configure phase.
570 (lambda* (#:key outputs #:allow-other-keys)
571 (let* ((out (assoc-ref outputs "out"))
572 (bin (string-append out "/bin"))
573 (man (string-append out "/share/man/man1")))
575 (copy-file "awk.1" (string-append man "/bioawk.1"))
576 (install-file "bioawk" bin)))))))
577 (home-page "https://github.com/lh3/bioawk")
578 (synopsis "AWK with bioinformatics extensions")
579 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
580 support of several common biological data formats, including optionally gzip'ed
581 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
582 also adds a few built-in functions and a command line option to use TAB as the
583 input/output delimiter. When the new functionality is not used, bioawk is
584 intended to behave exactly the same as the original BWK awk.")
585 (license license:x11)))
587 (define-public python2-pybedtools
589 (name "python2-pybedtools")
594 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
598 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
599 (build-system python-build-system)
600 (arguments `(#:python ,python-2)) ; no Python 3 support
602 `(("python-matplotlib" ,python2-matplotlib)))
604 `(("bedtools" ,bedtools)
605 ("samtools" ,samtools)))
607 `(("python-cython" ,python2-cython)
608 ("python-pyyaml" ,python2-pyyaml)
609 ("python-nose" ,python2-nose)))
610 (home-page "https://pythonhosted.org/pybedtools/")
611 (synopsis "Python wrapper for BEDtools programs")
613 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
614 which are widely used for genomic interval manipulation or \"genome algebra\".
615 pybedtools extends BEDTools by offering feature-level manipulations from with
617 (license license:gpl2+)))
619 (define-public python-biom-format
621 (name "python-biom-format")
626 ;; Use GitHub as source because PyPI distribution does not contain
627 ;; test data: https://github.com/biocore/biom-format/issues/693
628 (uri (string-append "https://github.com/biocore/biom-format/archive/"
630 (file-name (string-append name "-" version ".tar.gz"))
633 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
634 (build-system python-build-system)
636 `(("python-numpy" ,python-numpy)
637 ("python-scipy" ,python-scipy)
638 ("python-future" ,python-future)
639 ("python-click" ,python-click)
640 ("python-h5py" ,python-h5py)
641 ("python-pandas" ,python-pandas)))
643 `(("python-nose" ,python-nose)))
644 (home-page "http://www.biom-format.org")
645 (synopsis "Biological Observation Matrix (BIOM) format utilities")
647 "The BIOM file format is designed to be a general-use format for
648 representing counts of observations e.g. operational taxonomic units, KEGG
649 orthology groups or lipid types, in one or more biological samples
650 e.g. microbiome samples, genomes, metagenomes.")
651 (license license:bsd-3)
652 (properties `((python2-variant . ,(delay python2-biom-format))))))
654 (define-public python2-biom-format
655 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
660 (modify-phases %standard-phases
661 ;; Do not require the unmaintained pyqi library.
662 (add-after 'unpack 'remove-pyqi
664 (substitute* "setup.py"
665 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
667 ,@(package-arguments base))))))
669 (define-public bioperl-minimal
670 (let* ((inputs `(("perl-module-build" ,perl-module-build)
671 ("perl-data-stag" ,perl-data-stag)
672 ("perl-libwww" ,perl-libwww)
673 ("perl-uri" ,perl-uri)))
675 (map (compose package-name cadr)
678 (map (compose package-transitive-target-inputs cadr) inputs))))))
680 (name "bioperl-minimal")
685 (uri (string-append "https://github.com/bioperl/bioperl-live/"
687 (string-map (lambda (c)
693 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
694 (build-system perl-build-system)
697 (modify-phases %standard-phases
699 'install 'wrap-programs
700 (lambda* (#:key outputs #:allow-other-keys)
701 ;; Make sure all executables in "bin" find the required Perl
702 ;; modules at runtime. As the PERL5LIB variable contains also
703 ;; the paths of native inputs, we pick the transitive target
704 ;; inputs from %build-inputs.
705 (let* ((out (assoc-ref outputs "out"))
706 (bin (string-append out "/bin/"))
708 (cons (string-append out "/lib/perl5/site_perl")
710 (assoc-ref %build-inputs name))
711 ',transitive-inputs))
713 (for-each (lambda (file)
715 `("PERL5LIB" ":" prefix (,path))))
716 (find-files bin "\\.pl$"))
720 `(("perl-test-most" ,perl-test-most)))
721 (home-page "http://search.cpan.org/dist/BioPerl")
722 (synopsis "Bioinformatics toolkit")
724 "BioPerl is the product of a community effort to produce Perl code which
725 is useful in biology. Examples include Sequence objects, Alignment objects
726 and database searching objects. These objects not only do what they are
727 advertised to do in the documentation, but they also interact - Alignment
728 objects are made from the Sequence objects, Sequence objects have access to
729 Annotation and SeqFeature objects and databases, Blast objects can be
730 converted to Alignment objects, and so on. This means that the objects
731 provide a coordinated and extensible framework to do computational biology.")
732 (license license:perl-license))))
734 (define-public python-biopython
736 (name "python-biopython")
740 ;; use PyPi rather than biopython.org to ease updating
741 (uri (pypi-uri "biopython" version))
744 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
745 (build-system python-build-system)
748 (modify-phases %standard-phases
749 (add-before 'check 'set-home
750 ;; Some tests require a home directory to be set.
751 (lambda _ (setenv "HOME" "/tmp") #t)))))
753 `(("python-numpy" ,python-numpy)))
754 (home-page "http://biopython.org/")
755 (synopsis "Tools for biological computation in Python")
757 "Biopython is a set of tools for biological computation including parsers
758 for bioinformatics files into Python data structures; interfaces to common
759 bioinformatics programs; a standard sequence class and tools for performing
760 common operations on them; code to perform data classification; code for
761 dealing with alignments; code making it easy to split up parallelizable tasks
762 into separate processes; and more.")
763 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
765 (define-public python2-biopython
766 (package-with-python2 python-biopython))
768 (define-public bpp-core
769 ;; The last release was in 2014 and the recommended way to install from source
770 ;; is to clone the git repository, so we do this.
771 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
772 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
775 (version (string-append "2.2.0-1." (string-take commit 7)))
779 (url "http://biopp.univ-montp2.fr/git/bpp-core")
781 (file-name (string-append name "-" version "-checkout"))
784 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
785 (build-system cmake-build-system)
787 `(#:parallel-build? #f))
789 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
790 ; compile all of the bpp packages with GCC 5.
791 (home-page "http://biopp.univ-montp2.fr")
792 (synopsis "C++ libraries for Bioinformatics")
794 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
795 analysis, phylogenetics, molecular evolution and population genetics. It is
796 Object Oriented and is designed to be both easy to use and computer efficient.
797 Bio++ intends to help programmers to write computer expensive programs, by
798 providing them a set of re-usable tools.")
799 (license license:cecill-c))))
801 (define-public bpp-phyl
802 ;; The last release was in 2014 and the recommended way to install from source
803 ;; is to clone the git repository, so we do this.
804 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
805 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
808 (version (string-append "2.2.0-1." (string-take commit 7)))
812 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
814 (file-name (string-append name "-" version "-checkout"))
817 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
818 (build-system cmake-build-system)
820 `(#:parallel-build? #f
821 ;; If out-of-source, test data is not copied into the build directory
822 ;; so the tests fail.
823 #:out-of-source? #f))
825 `(("bpp-core" ,bpp-core)
827 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
830 (home-page "http://biopp.univ-montp2.fr")
831 (synopsis "Bio++ phylogenetic Library")
833 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
834 analysis, phylogenetics, molecular evolution and population genetics. This
835 library provides phylogenetics-related modules.")
836 (license license:cecill-c))))
838 (define-public bpp-popgen
839 ;; The last release was in 2014 and the recommended way to install from source
840 ;; is to clone the git repository, so we do this.
841 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
842 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
845 (version (string-append "2.2.0-1." (string-take commit 7)))
849 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
851 (file-name (string-append name "-" version "-checkout"))
854 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
855 (build-system cmake-build-system)
857 `(#:parallel-build? #f
858 #:tests? #f)) ; There are no tests.
860 `(("bpp-core" ,bpp-core)
863 (home-page "http://biopp.univ-montp2.fr")
864 (synopsis "Bio++ population genetics library")
866 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
867 analysis, phylogenetics, molecular evolution and population genetics. This
868 library provides population genetics-related modules.")
869 (license license:cecill-c))))
871 (define-public bpp-seq
872 ;; The last release was in 2014 and the recommended way to install from source
873 ;; is to clone the git repository, so we do this.
874 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
875 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
878 (version (string-append "2.2.0-1." (string-take commit 7)))
882 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
884 (file-name (string-append name "-" version "-checkout"))
887 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
888 (build-system cmake-build-system)
890 `(#:parallel-build? #f
891 ;; If out-of-source, test data is not copied into the build directory
892 ;; so the tests fail.
893 #:out-of-source? #f))
895 `(("bpp-core" ,bpp-core)
896 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
897 (home-page "http://biopp.univ-montp2.fr")
898 (synopsis "Bio++ sequence library")
900 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
901 analysis, phylogenetics, molecular evolution and population genetics. This
902 library provides sequence-related modules.")
903 (license license:cecill-c))))
905 (define-public bppsuite
906 ;; The last release was in 2014 and the recommended way to install from source
907 ;; is to clone the git repository, so we do this.
908 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
909 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
912 (version (string-append "2.2.0-1." (string-take commit 7)))
916 (url "http://biopp.univ-montp2.fr/git/bppsuite")
918 (file-name (string-append name "-" version "-checkout"))
921 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
922 (build-system cmake-build-system)
924 `(#:parallel-build? #f
925 #:tests? #f)) ; There are no tests.
929 ("texinfo" ,texinfo)))
931 `(("bpp-core" ,bpp-core)
933 ("bpp-phyl" ,bpp-phyl)
934 ("bpp-phyl" ,bpp-popgen)
936 (home-page "http://biopp.univ-montp2.fr")
937 (synopsis "Bioinformatics tools written with the Bio++ libraries")
939 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
940 analysis, phylogenetics, molecular evolution and population genetics. This
941 package provides command line tools using the Bio++ library.")
942 (license license:cecill-c))))
944 (define-public blast+
951 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
952 version "/ncbi-blast-" version "+-src.tar.gz"))
955 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
956 (patches (search-patches "blast+-fix-makefile.patch"))
957 (modules '((guix build utils)))
960 ;; Remove bundled bzip2, zlib and pcre.
961 (delete-file-recursively "c++/src/util/compress/bzip2")
962 (delete-file-recursively "c++/src/util/compress/zlib")
963 (delete-file-recursively "c++/src/util/regexp")
964 (substitute* "c++/src/util/compress/Makefile.in"
965 (("bzip2 zlib api") "api"))
966 ;; Remove useless msbuild directory
967 (delete-file-recursively
968 "c++/src/build-system/project_tree_builder/msbuild")
970 (build-system gnu-build-system)
972 `(;; There are two(!) tests for this massive library, and both fail with
973 ;; "unparsable timing stats".
974 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
975 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
978 #:parallel-build? #f ; not supported
980 (modify-phases %standard-phases
983 ;; $HOME needs to be set at some point during the configure phase
984 (lambda _ (setenv "HOME" "/tmp") #t))
987 (lambda _ (chdir "c++") #t))
989 'enter-dir 'fix-build-system
992 (cond ((string=? cmd "date")
993 ;; make call to "date" deterministic
998 (format (current-error-port)
999 "WARNING: Unable to find absolute path for ~s~%"
1003 ;; Rewrite hardcoded paths to various tools
1004 (substitute* (append '("src/build-system/configure.ac"
1005 "src/build-system/configure"
1006 "src/build-system/helpers/run_with_lock.c"
1007 "scripts/common/impl/if_diff.sh"
1008 "scripts/common/impl/run_with_lock.sh"
1009 "src/build-system/Makefile.configurables.real"
1010 "src/build-system/Makefile.in.top"
1011 "src/build-system/Makefile.meta.gmake=no"
1012 "src/build-system/Makefile.meta.in"
1013 "src/build-system/Makefile.meta_l"
1014 "src/build-system/Makefile.meta_p"
1015 "src/build-system/Makefile.meta_r"
1016 "src/build-system/Makefile.mk.in"
1017 "src/build-system/Makefile.requirements"
1018 "src/build-system/Makefile.rules_with_autodep.in")
1019 (find-files "scripts/common/check" "\\.sh$"))
1020 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1021 (or (which* cmd) all)))
1023 (substitute* (find-files "src/build-system" "^config.*")
1024 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1027 ;; rewrite "/var/tmp" in check script
1028 (substitute* "scripts/common/check/check_make_unix.sh"
1029 (("/var/tmp") "/tmp"))
1031 ;; do not reset PATH
1032 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1034 (("action=/bin/") "action=")
1035 (("export PATH") ":"))
1039 (lambda* (#:key inputs outputs #:allow-other-keys)
1040 (let ((out (assoc-ref outputs "out"))
1041 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1042 (include (string-append (assoc-ref outputs "include")
1043 "/include/ncbi-tools++")))
1044 ;; The 'configure' script doesn't recognize things like
1045 ;; '--enable-fast-install'.
1046 (zero? (system* "./configure.orig"
1047 (string-append "--with-build-root=" (getcwd) "/build")
1048 (string-append "--prefix=" out)
1049 (string-append "--libdir=" lib)
1050 (string-append "--includedir=" include)
1051 (string-append "--with-bz2="
1052 (assoc-ref inputs "bzip2"))
1053 (string-append "--with-z="
1054 (assoc-ref inputs "zlib"))
1055 (string-append "--with-pcre="
1056 (assoc-ref inputs "pcre"))
1057 ;; Each library is built twice by default, once
1058 ;; with "-static" in its name, and again
1061 "--with-dll"))))))))
1062 (outputs '("out" ; 21 MB
1070 ("python" ,python-wrapper)))
1073 (home-page "http://blast.ncbi.nlm.nih.gov")
1074 (synopsis "Basic local alignment search tool")
1076 "BLAST is a popular method of performing a DNA or protein sequence
1077 similarity search, using heuristics to produce results quickly. It also
1078 calculates an “expect value” that estimates how many matches would have
1079 occurred at a given score by chance, which can aid a user in judging how much
1080 confidence to have in an alignment.")
1081 ;; Most of the sources are in the public domain, with the following
1084 ;; * ./c++/include/util/bitset/
1085 ;; * ./c++/src/html/ncbi_menu*.js
1087 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1089 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1091 ;; * ./c++/src/corelib/teamcity_*
1092 (license (list license:public-domain
1098 (define-public bless
1104 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1108 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1109 (modules '((guix build utils)))
1112 ;; Remove bundled boost, pigz, zlib, and .git directory
1113 ;; FIXME: also remove bundled sources for murmurhash3 and
1114 ;; kmc once packaged.
1115 (delete-file-recursively "boost")
1116 (delete-file-recursively "pigz")
1117 (delete-file-recursively "google-sparsehash")
1118 (delete-file-recursively "zlib")
1119 (delete-file-recursively ".git")
1121 (build-system gnu-build-system)
1123 '(#:tests? #f ;no "check" target
1125 (list (string-append "ZLIB="
1126 (assoc-ref %build-inputs "zlib")
1128 (string-append "LDFLAGS="
1129 (string-join '("-lboost_filesystem"
1136 (modify-phases %standard-phases
1137 (add-after 'unpack 'do-not-build-bundled-pigz
1138 (lambda* (#:key inputs outputs #:allow-other-keys)
1139 (substitute* "Makefile"
1140 (("cd pigz/pigz-2.3.3; make") ""))
1142 (add-after 'unpack 'patch-paths-to-executables
1143 (lambda* (#:key inputs outputs #:allow-other-keys)
1144 (substitute* "parse_args.cpp"
1145 (("kmc_binary = .*")
1146 (string-append "kmc_binary = \""
1147 (assoc-ref outputs "out")
1149 (("pigz_binary = .*")
1150 (string-append "pigz_binary = \""
1151 (assoc-ref inputs "pigz")
1155 (lambda* (#:key outputs #:allow-other-keys)
1156 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1157 (for-each (lambda (file)
1158 (install-file file bin))
1159 '("bless" "kmc/bin/kmc"))
1161 (delete 'configure))))
1165 `(("openmpi" ,openmpi)
1167 ("sparsehash" ,sparsehash)
1170 (supported-systems '("x86_64-linux"))
1171 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1172 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1174 "@dfn{Bloom-filter-based error correction solution for high-throughput
1175 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1176 correction tool for genomic reads produced by @dfn{Next-generation
1177 sequencing} (NGS). BLESS produces accurate correction results with much less
1178 memory compared with previous solutions and is also able to tolerate a higher
1179 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1180 errors at the end of reads.")
1181 (license license:gpl3+)))
1183 (define-public bowtie
1189 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1191 (file-name (string-append name "-" version ".tar.gz"))
1194 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1195 (modules '((guix build utils)))
1197 '(substitute* "Makefile"
1198 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1199 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1200 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1201 (build-system gnu-build-system)
1204 ("perl-clone" ,perl-clone)
1205 ("perl-test-deep" ,perl-test-deep)
1206 ("perl-test-simple" ,perl-test-simple)
1207 ("python" ,python-2)
1214 (string-append "prefix=" (assoc-ref %outputs "out")))
1216 (modify-phases %standard-phases
1219 (lambda* (#:key outputs #:allow-other-keys)
1220 (zero? (system* "perl"
1221 "scripts/test/simple_tests.pl"
1222 "--bowtie2=./bowtie2"
1223 "--bowtie2-build=./bowtie2-build")))))))
1224 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1225 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1227 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1228 reads to long reference sequences. It is particularly good at aligning reads
1229 of about 50 up to 100s or 1,000s of characters, and particularly good at
1230 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1231 genome with an FM Index to keep its memory footprint small: for the human
1232 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1233 gapped, local, and paired-end alignment modes.")
1234 (supported-systems '("x86_64-linux"))
1235 (license license:gpl3+)))
1237 (define-public tophat
1244 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1248 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1249 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1250 (modules '((guix build utils)))
1253 ;; Remove bundled SeqAn and samtools
1254 (delete-file-recursively "src/SeqAn-1.3")
1255 (delete-file-recursively "src/samtools-0.1.18")
1257 (build-system gnu-build-system)
1259 '(#:parallel-build? #f ; not supported
1261 (modify-phases %standard-phases
1262 (add-after 'unpack 'use-system-samtools
1263 (lambda* (#:key inputs #:allow-other-keys)
1264 (substitute* "src/Makefile.in"
1265 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1266 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1267 (("SAMPROG = samtools_0\\.1\\.18") "")
1268 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1269 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1270 (substitute* '("src/common.cpp"
1272 (("samtools_0.1.18") (which "samtools")))
1273 (substitute* '("src/common.h"
1274 "src/bam2fastx.cpp")
1275 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1276 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1277 (substitute* '("src/bwt_map.h"
1279 "src/align_status.h")
1280 (("#include <bam.h>") "#include <samtools/bam.h>")
1281 (("#include <sam.h>") "#include <samtools/sam.h>"))
1286 ("samtools" ,samtools-0.1)
1287 ("ncurses" ,ncurses)
1288 ("python" ,python-2)
1292 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1293 (synopsis "Spliced read mapper for RNA-Seq data")
1295 "TopHat is a fast splice junction mapper for nucleotide sequence
1296 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1297 mammalian-sized genomes using the ultra high-throughput short read
1298 aligner Bowtie, and then analyzes the mapping results to identify
1299 splice junctions between exons.")
1300 ;; TopHat is released under the Boost Software License, Version 1.0
1301 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1302 (license license:boost1.0)))
1311 "https://github.com/lh3/bwa/releases/download/v"
1312 version "/bwa-" version ".tar.bz2"))
1315 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1316 (build-system gnu-build-system)
1318 '(#:tests? #f ;no "check" target
1320 (modify-phases %standard-phases
1322 (lambda* (#:key outputs #:allow-other-keys)
1323 (let ((bin (string-append
1324 (assoc-ref outputs "out") "/bin"))
1326 (assoc-ref outputs "out") "/share/doc/bwa"))
1328 (assoc-ref outputs "out") "/share/man/man1")))
1329 (install-file "bwa" bin)
1330 (install-file "README.md" doc)
1331 (install-file "bwa.1" man))
1333 ;; no "configure" script
1334 (delete 'configure))))
1335 (inputs `(("zlib" ,zlib)))
1336 ;; Non-portable SSE instructions are used so building fails on platforms
1337 ;; other than x86_64.
1338 (supported-systems '("x86_64-linux"))
1339 (home-page "http://bio-bwa.sourceforge.net/")
1340 (synopsis "Burrows-Wheeler sequence aligner")
1342 "BWA is a software package for mapping low-divergent sequences against a
1343 large reference genome, such as the human genome. It consists of three
1344 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1345 designed for Illumina sequence reads up to 100bp, while the rest two for
1346 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1347 features such as long-read support and split alignment, but BWA-MEM, which is
1348 the latest, is generally recommended for high-quality queries as it is faster
1349 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1350 70-100bp Illumina reads.")
1351 (license license:gpl3+)))
1353 (define-public bwa-pssm
1354 (package (inherit bwa)
1359 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1360 "archive/" version ".tar.gz"))
1361 (file-name (string-append name "-" version ".tar.gz"))
1364 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1365 (build-system gnu-build-system)
1370 (home-page "http://bwa-pssm.binf.ku.dk/")
1371 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1373 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1374 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1375 existing aligners it is fast and sensitive. Unlike most other aligners,
1376 however, it is also adaptible in the sense that one can direct the alignment
1377 based on known biases within the data set. It is coded as a modification of
1378 the original BWA alignment program and shares the genome index structure as
1379 well as many of the command line options.")
1380 (license license:gpl3+)))
1382 (define-public python2-bx-python
1384 (name "python2-bx-python")
1388 (uri (pypi-uri "bx-python" version))
1391 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1392 (modules '((guix build utils)))
1394 '(substitute* "setup.py"
1395 ;; remove dependency on outdated "distribute" module
1396 (("^from distribute_setup import use_setuptools") "")
1397 (("^use_setuptools\\(\\)") "")))))
1398 (build-system python-build-system)
1400 `(#:tests? #f ;tests fail because test data are not included
1401 #:python ,python-2))
1403 `(("python-numpy" ,python2-numpy)
1406 `(("python-nose" ,python2-nose)))
1407 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1408 (synopsis "Tools for manipulating biological data")
1410 "bx-python provides tools for manipulating biological data, particularly
1411 multiple sequence alignments.")
1412 (license license:expat)))
1414 (define-public python-pysam
1416 (name "python-pysam")
1420 ;; Test data is missing on PyPi.
1422 "https://github.com/pysam-developers/pysam/archive/v"
1424 (file-name (string-append name "-" version ".tar.gz"))
1427 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1428 (modules '((guix build utils)))
1430 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1431 '(delete-file-recursively "htslib"))))
1432 (build-system python-build-system)
1434 `(#:modules ((ice-9 ftw)
1436 (guix build python-build-system)
1439 (modify-phases %standard-phases
1440 (add-before 'build 'set-flags
1441 (lambda* (#:key inputs #:allow-other-keys)
1442 (setenv "HTSLIB_MODE" "external")
1443 (setenv "HTSLIB_LIBRARY_DIR"
1444 (string-append (assoc-ref inputs "htslib") "/lib"))
1445 (setenv "HTSLIB_INCLUDE_DIR"
1446 (string-append (assoc-ref inputs "htslib") "/include"))
1447 (setenv "LDFLAGS" "-lncurses")
1448 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1451 (lambda* (#:key inputs outputs #:allow-other-keys)
1452 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1453 (setenv "PYTHONPATH"
1455 (getenv "PYTHONPATH")
1456 ":" (getcwd) "/build/"
1457 (car (scandir "build"
1458 (negate (cut string-prefix? "." <>))))))
1459 ;; Step out of source dir so python does not import from CWD.
1460 (with-directory-excursion "tests"
1461 (setenv "HOME" "/tmp")
1462 (and (zero? (system* "make" "-C" "pysam_data"))
1463 (zero? (system* "make" "-C" "cbcf_data"))
1464 ;; Running nosetests without explicitly asking for a
1465 ;; single process leads to a crash. Running with multiple
1466 ;; processes fails because the tests are not designed to
1469 ;; FIXME: tests keep timing out on some systems.
1470 ;; (zero? (system* "nosetests" "-v"
1471 ;; "--processes" "1"))
1474 `(("htslib" ,htslib))) ; Included from installed header files.
1476 `(("ncurses" ,ncurses)
1479 `(("python-cython" ,python-cython)
1480 ;; Dependencies below are are for tests only.
1481 ("samtools" ,samtools)
1482 ("bcftools" ,bcftools)
1483 ("python-nose" ,python-nose)))
1484 (home-page "https://github.com/pysam-developers/pysam")
1485 (synopsis "Python bindings to the SAMtools C API")
1487 "Pysam is a Python module for reading and manipulating files in the
1488 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1489 also includes an interface for tabix.")
1490 (license license:expat)))
1492 (define-public python2-pysam
1493 (package-with-python2 python-pysam))
1495 (define-public python-twobitreader
1497 (name "python-twobitreader")
1501 (uri (pypi-uri "twobitreader" version))
1504 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1505 (build-system python-build-system)
1507 '(;; Tests are not distributed in the PyPi release.
1508 ;; TODO Try building from the Git repo or asking the upstream maintainer
1509 ;; to distribute the tests on PyPi.
1512 `(("python-sphinx" ,python-sphinx)))
1513 (home-page "https://github.com/benjschiller/twobitreader")
1514 (synopsis "Python library for reading .2bit files")
1516 "twobitreader is a Python library for reading .2bit files as used by the
1517 UCSC genome browser.")
1518 (license license:artistic2.0)))
1520 (define-public python2-twobitreader
1521 (package-with-python2 python-twobitreader))
1523 (define-public python-plastid
1525 (name "python-plastid")
1529 (uri (pypi-uri "plastid" version))
1532 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1533 (build-system python-build-system)
1535 ;; Some test files are not included.
1538 `(("python-numpy" ,python-numpy)
1539 ("python-scipy" ,python-scipy)
1540 ("python-pandas" ,python-pandas)
1541 ("python-pysam" ,python-pysam)
1542 ("python-matplotlib" ,python-matplotlib)
1543 ("python-biopython" ,python-biopython)
1544 ("python-twobitreader" ,python-twobitreader)
1545 ("python-termcolor" ,python-termcolor)))
1547 `(("python-cython" ,python-cython)
1548 ("python-nose" ,python-nose)))
1549 (home-page "https://github.com/joshuagryphon/plastid")
1550 (synopsis "Python library for genomic analysis")
1552 "plastid is a Python library for genomic analysis – in particular,
1553 high-throughput sequencing data – with an emphasis on simplicity.")
1554 (license license:bsd-3)))
1556 (define-public python2-plastid
1557 (package-with-python2 python-plastid))
1559 (define-public cd-hit
1565 (uri (string-append "https://github.com/weizhongli/cdhit"
1566 "/releases/download/V" version
1568 "-2017-0621-source.tar.gz"))
1571 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1572 (build-system gnu-build-system)
1574 `(#:tests? #f ; there are no tests
1576 ;; Executables are copied directly to the PREFIX.
1577 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1579 (modify-phases %standard-phases
1580 ;; No "configure" script
1582 ;; Remove sources of non-determinism
1583 (add-after 'unpack 'be-timeless
1585 (substitute* "cdhit-utility.c++"
1586 ((" \\(built on \" __DATE__ \"\\)") ""))
1587 (substitute* "cdhit-common.c++"
1588 (("__DATE__") "\"0\"")
1589 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1591 ;; The "install" target does not create the target directory.
1592 (add-before 'install 'create-target-dir
1593 (lambda* (#:key outputs #:allow-other-keys)
1594 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1598 (home-page "http://weizhongli-lab.org/cd-hit/")
1599 (synopsis "Cluster and compare protein or nucleotide sequences")
1601 "CD-HIT is a program for clustering and comparing protein or nucleotide
1602 sequences. CD-HIT is designed to be fast and handle extremely large
1604 ;; The manual says: "It can be copied under the GNU General Public License
1605 ;; version 2 (GPLv2)."
1606 (license license:gpl2)))
1608 (define-public clipper
1615 "https://github.com/YeoLab/clipper/archive/"
1617 (file-name (string-append name "-" version ".tar.gz"))
1620 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1621 (modules '((guix build utils)))
1624 ;; remove unnecessary setup dependency
1625 (substitute* "setup.py"
1626 (("setup_requires = .*") ""))
1627 (for-each delete-file
1628 '("clipper/src/peaks.so"
1629 "clipper/src/readsToWiggle.so"))
1630 (delete-file-recursively "dist/")
1632 (build-system python-build-system)
1633 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1635 `(("htseq" ,python2-htseq)
1636 ("python-pybedtools" ,python2-pybedtools)
1637 ("python-cython" ,python2-cython)
1638 ("python-scikit-learn" ,python2-scikit-learn)
1639 ("python-matplotlib" ,python2-matplotlib)
1640 ("python-pandas" ,python2-pandas)
1641 ("python-pysam" ,python2-pysam)
1642 ("python-numpy" ,python2-numpy)
1643 ("python-scipy" ,python2-scipy)))
1645 `(("python-mock" ,python2-mock) ; for tests
1646 ("python-nose" ,python2-nose) ; for tests
1647 ("python-pytz" ,python2-pytz))) ; for tests
1648 (home-page "https://github.com/YeoLab/clipper")
1649 (synopsis "CLIP peak enrichment recognition")
1651 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1652 (license license:gpl2)))
1654 (define-public codingquarry
1656 (name "codingquarry")
1661 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1665 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1666 (build-system gnu-build-system)
1668 '(#:tests? #f ; no "check" target
1670 (modify-phases %standard-phases
1673 (lambda* (#:key outputs #:allow-other-keys)
1674 (let* ((out (assoc-ref outputs "out"))
1675 (bin (string-append out "/bin"))
1676 (doc (string-append out "/share/doc/codingquarry")))
1677 (install-file "INSTRUCTIONS.pdf" doc)
1678 (copy-recursively "QuarryFiles"
1679 (string-append out "/QuarryFiles"))
1680 (install-file "CodingQuarry" bin)
1681 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1682 (inputs `(("openmpi" ,openmpi)))
1683 (native-search-paths
1684 (list (search-path-specification
1685 (variable "QUARRY_PATH")
1686 (files '("QuarryFiles")))))
1687 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1688 (synopsis "Fungal gene predictor")
1689 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1690 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1691 (home-page "https://sourceforge.net/projects/codingquarry/")
1692 (license license:gpl3+)))
1694 (define-public couger
1701 "http://couger.oit.duke.edu/static/assets/COUGER"
1705 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1706 (build-system gnu-build-system)
1710 (modify-phases %standard-phases
1715 (lambda* (#:key outputs #:allow-other-keys)
1716 (let* ((out (assoc-ref outputs "out"))
1717 (bin (string-append out "/bin")))
1718 (copy-recursively "src" (string-append out "/src"))
1720 ;; Add "src" directory to module lookup path.
1721 (substitute* "couger"
1723 (string-append "import sys\nsys.path.append(\""
1724 out "\")\nfrom argparse")))
1725 (install-file "couger" bin))
1728 'install 'wrap-program
1729 (lambda* (#:key inputs outputs #:allow-other-keys)
1730 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1731 (let* ((out (assoc-ref outputs "out"))
1732 (path (getenv "PYTHONPATH")))
1733 (wrap-program (string-append out "/bin/couger")
1734 `("PYTHONPATH" ":" prefix (,path))))
1737 `(("python" ,python-2)
1738 ("python2-pillow" ,python2-pillow)
1739 ("python2-numpy" ,python2-numpy)
1740 ("python2-scipy" ,python2-scipy)
1741 ("python2-matplotlib" ,python2-matplotlib)))
1743 `(("r-minimal" ,r-minimal)
1745 ("randomjungle" ,randomjungle)))
1747 `(("unzip" ,unzip)))
1748 (home-page "http://couger.oit.duke.edu")
1749 (synopsis "Identify co-factors in sets of genomic regions")
1751 "COUGER can be applied to any two sets of genomic regions bound by
1752 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1753 putative co-factors that provide specificity to each TF. The framework
1754 determines the genomic targets uniquely-bound by each TF, and identifies a
1755 small set of co-factors that best explain the in vivo binding differences
1756 between the two TFs.
1758 COUGER uses classification algorithms (support vector machines and random
1759 forests) with features that reflect the DNA binding specificities of putative
1760 co-factors. The features are generated either from high-throughput TF-DNA
1761 binding data (from protein binding microarray experiments), or from large
1762 collections of DNA motifs.")
1763 (license license:gpl3+)))
1765 (define-public clustal-omega
1767 (name "clustal-omega")
1771 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1775 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1776 (build-system gnu-build-system)
1778 `(("argtable" ,argtable)))
1779 (home-page "http://www.clustal.org/omega/")
1780 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1782 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1783 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1784 of handling data-sets of hundreds of thousands of sequences in reasonable
1786 (license license:gpl2+)))
1788 (define-public crossmap
1794 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1798 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1799 ;; This patch has been sent upstream already and is available
1800 ;; for download from Sourceforge, but it has not been merged.
1801 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1802 (modules '((guix build utils)))
1803 ;; remove bundled copy of pysam
1805 '(delete-file-recursively "lib/pysam"))))
1806 (build-system python-build-system)
1808 `(#:python ,python-2
1810 (modify-phases %standard-phases
1811 (add-after 'unpack 'set-env
1812 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1814 `(("python-numpy" ,python2-numpy)
1815 ("python-pysam" ,python2-pysam)
1818 `(("python-cython" ,python2-cython)
1819 ("python-nose" ,python2-nose)))
1820 (home-page "http://crossmap.sourceforge.net/")
1821 (synopsis "Convert genome coordinates between assemblies")
1823 "CrossMap is a program for conversion of genome coordinates or annotation
1824 files between different genome assemblies. It supports most commonly used
1825 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1826 (license license:gpl2+)))
1828 (define-public cutadapt
1835 (url "https://github.com/marcelm/cutadapt.git")
1836 (commit (string-append "v" version))))
1837 (file-name (string-append name "-" version "-checkout"))
1840 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1841 (build-system python-build-system)
1843 `(("python-xopen" ,python-xopen)))
1845 `(("python-cython" ,python-cython)
1846 ("python-pytest" ,python-pytest)))
1847 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1848 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1850 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1851 other types of unwanted sequence from high-throughput sequencing reads.")
1852 (license license:expat)))
1854 (define-public libbigwig
1860 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1861 "archive/" version ".tar.gz"))
1862 (file-name (string-append name "-" version ".tar.gz"))
1865 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1866 (build-system gnu-build-system)
1868 `(#:test-target "test"
1871 (string-append "prefix=" (assoc-ref %outputs "out")))
1873 (modify-phases %standard-phases
1875 (add-before 'check 'disable-curl-test
1877 (substitute* "Makefile"
1878 (("./test/testRemote.*") ""))
1880 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1881 ;; there has not yet been a release containing this change.
1882 (add-before 'install 'create-target-dirs
1883 (lambda* (#:key outputs #:allow-other-keys)
1884 (let ((out (assoc-ref outputs "out")))
1885 (mkdir-p (string-append out "/lib"))
1886 (mkdir-p (string-append out "/include"))
1892 `(("doxygen" ,doxygen)))
1893 (home-page "https://github.com/dpryan79/libBigWig")
1894 (synopsis "C library for handling bigWig files")
1896 "This package provides a C library for parsing local and remote BigWig
1898 (license license:expat)))
1900 (define-public python-pybigwig
1902 (name "python-pybigwig")
1906 (uri (pypi-uri "pyBigWig" version))
1909 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1910 (modules '((guix build utils)))
1913 ;; Delete bundled libBigWig sources
1914 (delete-file-recursively "libBigWig")))))
1915 (build-system python-build-system)
1918 (modify-phases %standard-phases
1919 (add-after 'unpack 'link-with-libBigWig
1920 (lambda* (#:key inputs #:allow-other-keys)
1921 (substitute* "setup.py"
1922 (("libs=\\[") "libs=[\"BigWig\", "))
1925 `(("libbigwig" ,libbigwig)
1928 (home-page "https://github.com/dpryan79/pyBigWig")
1929 (synopsis "Access bigWig files in Python using libBigWig")
1931 "This package provides Python bindings to the libBigWig library for
1932 accessing bigWig files.")
1933 (license license:expat)))
1935 (define-public python2-pybigwig
1936 (package-with-python2 python-pybigwig))
1938 (define-public python-dendropy
1940 (name "python-dendropy")
1945 (uri (pypi-uri "DendroPy" version))
1948 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1949 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1950 (build-system python-build-system)
1951 (home-page "http://packages.python.org/DendroPy/")
1952 (synopsis "Library for phylogenetics and phylogenetic computing")
1954 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1955 writing, simulation, processing and manipulation of phylogenetic
1956 trees (phylogenies) and characters.")
1957 (license license:bsd-3)
1958 (properties `((python2-variant . ,(delay python2-dendropy))))))
1960 (define-public python2-dendropy
1961 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1965 `(#:python ,python-2
1967 (modify-phases %standard-phases
1969 ;; There is currently a test failure that only happens on some
1970 ;; systems, and only using "setup.py test"
1971 (lambda _ (zero? (system* "nosetests")))))))
1972 (native-inputs `(("python2-nose" ,python2-nose)
1973 ,@(package-native-inputs base))))))
1975 (define-public python-py2bit
1977 (name "python-py2bit")
1982 (uri (pypi-uri "py2bit" version))
1985 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
1986 (build-system python-build-system)
1987 (home-page "https://github.com/dpryan79/py2bit")
1988 (synopsis "Access 2bit files using lib2bit")
1990 "This package provides Python bindings for lib2bit to access 2bit files
1992 (license license:expat)))
1994 (define-public deeptools
2000 (uri (string-append "https://github.com/deeptools/deepTools/"
2001 "archive/" version ".tar.gz"))
2002 (file-name (string-append name "-" version ".tar.gz"))
2005 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2006 (build-system python-build-system)
2008 `(("python-scipy" ,python-scipy)
2009 ("python-numpy" ,python-numpy)
2010 ("python-numpydoc" ,python-numpydoc)
2011 ("python-matplotlib" ,python-matplotlib)
2012 ("python-pysam" ,python-pysam)
2013 ("python-py2bit" ,python-py2bit)
2014 ("python-pybigwig" ,python-pybigwig)))
2016 `(("python-mock" ,python-mock) ;for tests
2017 ("python-nose" ,python-nose) ;for tests
2018 ("python-pytz" ,python-pytz))) ;for tests
2019 (home-page "https://github.com/deeptools/deepTools")
2020 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2022 "DeepTools addresses the challenge of handling the large amounts of data
2023 that are now routinely generated from DNA sequencing centers. To do so,
2024 deepTools contains useful modules to process the mapped reads data to create
2025 coverage files in standard bedGraph and bigWig file formats. By doing so,
2026 deepTools allows the creation of normalized coverage files or the comparison
2027 between two files (for example, treatment and control). Finally, using such
2028 normalized and standardized files, multiple visualizations can be created to
2029 identify enrichments with functional annotations of the genome.")
2030 (license license:gpl3+)))
2032 (define-public diamond
2039 "https://github.com/bbuchfink/diamond/archive/v"
2041 (file-name (string-append name "-" version ".tar.gz"))
2044 "1vi2nddmy7knrv8gsprwqp6a40k63n3f2dfvx22ipjhrg9xir96f"))))
2045 (build-system cmake-build-system)
2047 '(#:tests? #f ; no "check" target
2049 (modify-phases %standard-phases
2050 (add-after 'unpack 'remove-native-compilation
2052 (substitute* "CMakeLists.txt" (("-march=native") ""))
2056 (home-page "https://github.com/bbuchfink/diamond")
2057 (synopsis "Accelerated BLAST compatible local sequence aligner")
2059 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2060 translated DNA query sequences against a protein reference database (BLASTP
2061 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2062 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2063 data and settings.")
2064 (license license:agpl3+)))
2066 (define-public discrover
2073 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2075 (file-name (string-append name "-" version ".tar.gz"))
2078 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2079 (build-system cmake-build-system)
2081 `(#:tests? #f ; there are no tests
2083 (modify-phases %standard-phases
2084 (add-after 'unpack 'add-missing-includes
2086 (substitute* "src/executioninformation.hpp"
2087 (("#define EXECUTIONINFORMATION_HPP" line)
2088 (string-append line "\n#include <random>")))
2089 (substitute* "src/plasma/fasta.hpp"
2090 (("#define FASTA_HPP" line)
2091 (string-append line "\n#include <random>")))
2097 `(("texlive" ,texlive)
2098 ("imagemagick" ,imagemagick)))
2099 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2100 (synopsis "Discover discriminative nucleotide sequence motifs")
2101 (description "Discrover is a motif discovery method to find binding sites
2102 of nucleic acid binding proteins.")
2103 (license license:gpl3+)))
2105 (define-public eigensoft
2106 (let ((revision "1")
2107 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2110 (version (string-append "6.1.2-"
2112 (string-take commit 9)))
2117 (url "https://github.com/DReichLab/EIG.git")
2119 (file-name (string-append "eigensoft-" commit "-checkout"))
2122 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2123 (modules '((guix build utils)))
2124 ;; Remove pre-built binaries.
2126 (delete-file-recursively "bin")
2129 (build-system gnu-build-system)
2131 `(#:tests? #f ; There are no tests.
2132 #:make-flags '("CC=gcc")
2134 (modify-phases %standard-phases
2135 ;; There is no configure phase, but the Makefile is in a
2140 ;; The link flags are incomplete.
2141 (substitute* "Makefile"
2142 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2144 ;; The provided install target only copies executables to
2145 ;; the "bin" directory in the build root.
2146 (add-after 'install 'actually-install
2147 (lambda* (#:key outputs #:allow-other-keys)
2148 (let* ((out (assoc-ref outputs "out"))
2149 (bin (string-append out "/bin")))
2150 (for-each (lambda (file)
2151 (install-file file bin))
2152 (find-files "../bin" ".*"))
2157 ("openblas" ,openblas)
2159 ("gfortran" ,gfortran "lib")))
2160 (home-page "https://github.com/DReichLab/EIG")
2161 (synopsis "Tools for population genetics")
2162 (description "The EIGENSOFT package provides tools for population
2163 genetics and stratification correction. EIGENSOFT implements methods commonly
2164 used in population genetics analyses such as PCA, computation of Tracy-Widom
2165 statistics, and finding related individuals in structured populations. It
2166 comes with a built-in plotting script and supports multiple file formats and
2167 quantitative phenotypes.")
2168 ;; The license of the eigensoft tools is Expat, but since it's
2169 ;; linking with the GNU Scientific Library (GSL) the effective
2170 ;; license is the GPL.
2171 (license license:gpl3+))))
2173 (define-public edirect
2179 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2180 "versions/2016-05-03/edirect.tar.gz"))
2183 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2184 (build-system perl-build-system)
2186 `(#:tests? #f ;no "check" target
2188 (modify-phases %standard-phases
2192 (lambda* (#:key outputs #:allow-other-keys)
2193 (let ((target (string-append (assoc-ref outputs "out")
2196 (install-file "edirect.pl" target)
2199 'install 'wrap-program
2200 (lambda* (#:key inputs outputs #:allow-other-keys)
2201 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2202 (let* ((out (assoc-ref outputs "out"))
2203 (path (getenv "PERL5LIB")))
2204 (wrap-program (string-append out "/bin/edirect.pl")
2205 `("PERL5LIB" ":" prefix (,path)))))))))
2207 `(("perl-html-parser" ,perl-html-parser)
2208 ("perl-encode-locale" ,perl-encode-locale)
2209 ("perl-file-listing" ,perl-file-listing)
2210 ("perl-html-tagset" ,perl-html-tagset)
2211 ("perl-html-tree" ,perl-html-tree)
2212 ("perl-http-cookies" ,perl-http-cookies)
2213 ("perl-http-date" ,perl-http-date)
2214 ("perl-http-message" ,perl-http-message)
2215 ("perl-http-negotiate" ,perl-http-negotiate)
2216 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2217 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2218 ("perl-net-http" ,perl-net-http)
2219 ("perl-uri" ,perl-uri)
2220 ("perl-www-robotrules" ,perl-www-robotrules)
2222 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2223 (synopsis "Tools for accessing the NCBI's set of databases")
2225 "Entrez Direct (EDirect) is a method for accessing the National Center
2226 for Biotechnology Information's (NCBI) set of interconnected
2227 databases (publication, sequence, structure, gene, variation, expression,
2228 etc.) from a terminal. Functions take search terms from command-line
2229 arguments. Individual operations are combined to build multi-step queries.
2230 Record retrieval and formatting normally complete the process.
2232 EDirect also provides an argument-driven function that simplifies the
2233 extraction of data from document summaries or other results that are returned
2234 in structured XML format. This can eliminate the need for writing custom
2235 software to answer ad hoc questions.")
2236 (license license:public-domain)))
2238 (define-public exonerate
2247 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2248 "exonerate-" version ".tar.gz"))
2251 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2252 (build-system gnu-build-system)
2254 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2256 `(("pkg-config" ,pkg-config)))
2260 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2261 (synopsis "Generic tool for biological sequence alignment")
2263 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2264 the alignment of sequences using a many alignment models, either exhaustive
2265 dynamic programming or a variety of heuristics.")
2266 (license license:gpl3)))
2268 (define-public express
2276 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2277 version "/express-" version "-src.tgz"))
2280 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2281 (build-system cmake-build-system)
2283 `(#:tests? #f ;no "check" target
2285 (modify-phases %standard-phases
2286 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2287 (lambda* (#:key inputs #:allow-other-keys)
2288 (substitute* "CMakeLists.txt"
2289 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2290 "set(Boost_USE_STATIC_LIBS OFF)")
2291 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2292 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2293 (substitute* "src/CMakeLists.txt"
2294 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2295 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2299 ("bamtools" ,bamtools)
2300 ("protobuf" ,protobuf)
2302 (home-page "http://bio.math.berkeley.edu/eXpress")
2303 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2305 "eXpress is a streaming tool for quantifying the abundances of a set of
2306 target sequences from sampled subsequences. Example applications include
2307 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2308 analysis (from RNA-Seq), transcription factor binding quantification in
2309 ChIP-Seq, and analysis of metagenomic data.")
2310 (license license:artistic2.0)))
2312 (define-public express-beta-diversity
2314 (name "express-beta-diversity")
2320 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2322 (file-name (string-append name "-" version ".tar.gz"))
2325 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2326 (build-system gnu-build-system)
2329 (modify-phases %standard-phases
2331 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2333 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2335 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2337 (lambda* (#:key outputs #:allow-other-keys)
2338 (let ((bin (string-append (assoc-ref outputs "out")
2341 (install-file "scripts/convertToEBD.py" bin)
2342 (install-file "bin/ExpressBetaDiversity" bin)
2345 `(("python" ,python-2)))
2346 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2347 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2349 "Express Beta Diversity (EBD) calculates ecological beta diversity
2350 (dissimilarity) measures between biological communities. EBD implements a
2351 variety of diversity measures including those that make use of phylogenetic
2352 similarity of community members.")
2353 (license license:gpl3+)))
2355 (define-public fasttree
2362 "http://www.microbesonline.org/fasttree/FastTree-"
2366 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2367 (build-system gnu-build-system)
2369 `(#:tests? #f ; no "check" target
2371 (modify-phases %standard-phases
2375 (lambda* (#:key source #:allow-other-keys)
2376 (and (zero? (system* "gcc"
2378 "-finline-functions"
2385 (zero? (system* "gcc"
2389 "-finline-functions"
2397 (lambda* (#:key outputs #:allow-other-keys)
2398 (let ((bin (string-append (assoc-ref outputs "out")
2401 (install-file "FastTree" bin)
2402 (install-file "FastTreeMP" bin)
2404 (home-page "http://www.microbesonline.org/fasttree")
2405 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2407 "FastTree can handle alignments with up to a million of sequences in a
2408 reasonable amount of time and memory. For large alignments, FastTree is
2409 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2410 (license license:gpl2+)))
2412 (define-public fastx-toolkit
2414 (name "fastx-toolkit")
2420 "https://github.com/agordon/fastx_toolkit/releases/download/"
2421 version "/fastx_toolkit-" version ".tar.bz2"))
2424 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2425 (build-system gnu-build-system)
2427 `(("libgtextutils" ,libgtextutils)))
2429 `(("pkg-config" ,pkg-config)))
2430 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2431 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2433 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2434 FASTA/FASTQ files preprocessing.
2436 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2437 containing multiple short-reads sequences. The main processing of such
2438 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2439 is sometimes more productive to preprocess the files before mapping the
2440 sequences to the genome---manipulating the sequences to produce better mapping
2441 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2442 (license license:agpl3+)))
2444 (define-public flexbar
2451 (string-append "mirror://sourceforge/flexbar/"
2452 version "/flexbar_v" version "_src.tgz"))
2455 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2456 (build-system cmake-build-system)
2458 `(#:configure-flags (list
2459 (string-append "-DFLEXBAR_BINARY_DIR="
2460 (assoc-ref %outputs "out")
2463 (modify-phases %standard-phases
2465 (lambda* (#:key outputs #:allow-other-keys)
2466 (setenv "PATH" (string-append
2467 (assoc-ref outputs "out") "/bin:"
2469 (chdir "../flexbar_v2.5_src/test")
2470 (zero? (system* "bash" "flexbar_validate.sh"))))
2471 (delete 'install))))
2476 `(("pkg-config" ,pkg-config)
2478 (home-page "http://flexbar.sourceforge.net")
2479 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2481 "Flexbar preprocesses high-throughput nucleotide sequencing data
2482 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2483 Moreover, trimming and filtering features are provided. Flexbar increases
2484 read mapping rates and improves genome and transcriptome assemblies. It
2485 supports next-generation sequencing data in fasta/q and csfasta/q format from
2486 Illumina, Roche 454, and the SOLiD platform.")
2487 (license license:gpl3)))
2489 (define-public fraggenescan
2491 (name "fraggenescan")
2497 (string-append "mirror://sourceforge/fraggenescan/"
2498 "FragGeneScan" version ".tar.gz"))
2500 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2501 (build-system gnu-build-system)
2504 (modify-phases %standard-phases
2506 (add-before 'build 'patch-paths
2507 (lambda* (#:key outputs #:allow-other-keys)
2508 (let* ((out (string-append (assoc-ref outputs "out")))
2509 (share (string-append out "/share/fraggenescan/")))
2510 (substitute* "run_FragGeneScan.pl"
2512 (string-append "system(\"" (which "rm")))
2514 (string-append "system(\"" (which "mv")))
2515 (("\\\"awk") (string-append "\"" (which "awk")))
2516 ;; This script and other programs expect the training files
2517 ;; to be in the non-standard location bin/train/XXX. Change
2518 ;; this to be share/fraggenescan/train/XXX instead.
2519 (("^\\$train.file = \\$dir.*")
2520 (string-append "$train_file = \""
2522 "train/\".$FGS_train_file;")))
2523 (substitute* "run_hmm.c"
2524 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2525 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2528 (lambda _ (and (zero? (system* "make" "clean"))
2529 (zero? (system* "make" "fgs")))))
2531 (lambda* (#:key outputs #:allow-other-keys)
2532 (let* ((out (string-append (assoc-ref outputs "out")))
2533 (bin (string-append out "/bin/"))
2534 (share (string-append out "/share/fraggenescan/train")))
2535 (install-file "run_FragGeneScan.pl" bin)
2536 (install-file "FragGeneScan" bin)
2537 (copy-recursively "train" share))))
2539 (add-after 'install 'post-install-check
2540 ;; In lieu of 'make check', run one of the examples and check the
2541 ;; output files gets created.
2542 (lambda* (#:key outputs #:allow-other-keys)
2543 (let* ((out (string-append (assoc-ref outputs "out")))
2544 (bin (string-append out "/bin/"))
2545 (frag (string-append bin "run_FragGeneScan.pl")))
2546 (and (zero? (system* frag ; Test complete genome.
2547 "-genome=./example/NC_000913.fna"
2551 (file-exists? "test2.faa")
2552 (file-exists? "test2.ffn")
2553 (file-exists? "test2.gff")
2554 (file-exists? "test2.out")
2555 (zero? (system* ; Test incomplete sequences.
2557 "-genome=./example/NC_000913-fgs.ffn"
2560 "-train=454_30")))))))))
2563 ("python" ,python-2))) ;not compatible with python 3.
2564 (home-page "https://sourceforge.net/projects/fraggenescan/")
2565 (synopsis "Finds potentially fragmented genes in short reads")
2567 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2568 short and error-prone DNA sequencing reads. It can also be applied to predict
2569 genes in incomplete assemblies or complete genomes.")
2570 ;; GPL3+ according to private correspondense with the authors.
2571 (license license:gpl3+)))
2573 (define-public fxtract
2574 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2582 "https://github.com/ctSkennerton/fxtract/archive/"
2584 (file-name (string-append "ctstennerton-util-"
2585 (string-take util-commit 7)
2589 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2590 (build-system gnu-build-system)
2592 `(#:make-flags (list
2593 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2595 #:test-target "fxtract_test"
2597 (modify-phases %standard-phases
2599 (add-before 'build 'copy-util
2600 (lambda* (#:key inputs #:allow-other-keys)
2602 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2604 ;; Do not use make install as this requires additional dependencies.
2606 (lambda* (#:key outputs #:allow-other-keys)
2607 (let* ((out (assoc-ref outputs "out"))
2608 (bin (string-append out"/bin")))
2609 (install-file "fxtract" bin)
2615 ;; ctskennerton-util is licensed under GPL2.
2616 `(("ctskennerton-util"
2620 (url "https://github.com/ctSkennerton/util.git")
2621 (commit util-commit)))
2622 (file-name (string-append
2623 "ctstennerton-util-" util-commit "-checkout"))
2626 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2627 (home-page "https://github.com/ctSkennerton/fxtract")
2628 (synopsis "Extract sequences from FASTA and FASTQ files")
2630 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2631 or FASTQ) file given a subsequence. It uses a simple substring search for
2632 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2633 lookups or multi-pattern searching as required. By default fxtract looks in
2634 the sequence of each record but can also be told to look in the header,
2635 comment or quality sections.")
2636 ;; 'util' requires SSE instructions.
2637 (supported-systems '("x86_64-linux"))
2638 (license license:expat))))
2640 (define-public gemma
2646 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2648 (file-name (string-append name "-" version ".tar.gz"))
2651 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2652 (patches (search-patches "gemma-intel-compat.patch"))))
2657 (build-system gnu-build-system)
2660 '(,@(match (%current-system)
2662 '("FORCE_DYNAMIC=1"))
2664 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2666 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2668 (modify-phases %standard-phases
2670 (add-before 'build 'bin-mkdir
2675 (lambda* (#:key outputs #:allow-other-keys)
2676 (let ((out (assoc-ref outputs "out")))
2677 (install-file "bin/gemma"
2681 #:tests? #f)) ; no tests included yet
2682 (home-page "https://github.com/xiangzhou/GEMMA")
2683 (synopsis "Tool for genome-wide efficient mixed model association")
2685 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2686 standard linear mixed model resolver with application in genome-wide
2687 association studies (GWAS).")
2688 (license license:gpl3)))
2697 "https://github.com/nboley/grit/archive/"
2699 (file-name (string-append name "-" version ".tar.gz"))
2702 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2703 (build-system python-build-system)
2705 `(#:python ,python-2
2707 (modify-phases %standard-phases
2708 (add-after 'unpack 'generate-from-cython-sources
2709 (lambda* (#:key inputs outputs #:allow-other-keys)
2710 ;; Delete these C files to force fresh generation from pyx sources.
2711 (delete-file "grit/sparsify_support_fns.c")
2712 (delete-file "grit/call_peaks_support_fns.c")
2713 (substitute* "setup.py"
2714 (("Cython.Setup") "Cython.Build")
2715 ;; Add numpy include path to fix compilation
2717 (string-append "pyx\", ], include_dirs = ['"
2718 (assoc-ref inputs "python-numpy")
2719 "/lib/python2.7/site-packages/numpy/core/include/"
2723 `(("python-scipy" ,python2-scipy)
2724 ("python-numpy" ,python2-numpy)
2725 ("python-pysam" ,python2-pysam)
2726 ("python-networkx" ,python2-networkx)))
2728 `(("python-cython" ,python2-cython)))
2729 (home-page "http://grit-bio.org")
2730 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2732 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2733 full length transcript models. When none of these data sources are available,
2734 GRIT can be run by providing a candidate set of TES or TSS sites. In
2735 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2736 also be run in quantification mode, where it uses a provided GTF file and just
2737 estimates transcript expression.")
2738 (license license:gpl3+)))
2740 (define-public hisat
2747 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2748 version "-beta-source.zip"))
2751 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2752 (build-system gnu-build-system)
2754 `(#:tests? #f ;no check target
2755 #:make-flags '("allall"
2756 ;; Disable unsupported `popcnt' instructions on
2757 ;; architectures other than x86_64
2758 ,@(if (string-prefix? "x86_64"
2759 (or (%current-target-system)
2762 '("POPCNT_CAPABILITY=0")))
2764 (modify-phases %standard-phases
2765 (add-after 'unpack 'patch-sources
2767 ;; XXX Cannot use snippet because zip files are not supported
2768 (substitute* "Makefile"
2769 (("^CC = .*$") "CC = gcc")
2770 (("^CPP = .*$") "CPP = g++")
2771 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2772 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2773 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2774 (substitute* '("hisat-build" "hisat-inspect")
2775 (("/usr/bin/env") (which "env")))
2778 (lambda* (#:key outputs #:allow-other-keys)
2779 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2780 (for-each (lambda (file)
2781 (install-file file bin))
2784 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2786 (delete 'configure))))
2788 `(("unzip" ,unzip)))
2793 ;; Non-portable SSE instructions are used so building fails on platforms
2794 ;; other than x86_64.
2795 (supported-systems '("x86_64-linux"))
2796 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2797 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2799 "HISAT is a fast and sensitive spliced alignment program for mapping
2800 RNA-seq reads. In addition to one global FM index that represents a whole
2801 genome, HISAT uses a large set of small FM indexes that collectively cover the
2802 whole genome. These small indexes (called local indexes) combined with
2803 several alignment strategies enable effective alignment of RNA-seq reads, in
2804 particular, reads spanning multiple exons.")
2805 (license license:gpl3+)))
2807 (define-public hisat2
2814 ;; FIXME: a better source URL is
2815 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2816 ;; "/downloads/hisat2-" version "-source.zip")
2817 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2818 ;; but it is currently unavailable.
2819 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2820 (file-name (string-append name "-" version ".tar.gz"))
2823 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2824 (build-system gnu-build-system)
2826 `(#:tests? #f ; no check target
2827 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2828 #:modules ((guix build gnu-build-system)
2832 (modify-phases %standard-phases
2833 (add-after 'unpack 'make-deterministic
2835 (substitute* "Makefile"
2840 (lambda* (#:key outputs #:allow-other-keys)
2841 (let* ((out (assoc-ref outputs "out"))
2842 (bin (string-append out "/bin/"))
2843 (doc (string-append out "/share/doc/hisat2/")))
2845 (cut install-file <> bin)
2847 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2849 (install-file "doc/manual.inc.html" doc))
2852 `(("unzip" ,unzip) ; needed for archive from ftp
2854 ("pandoc" ,ghc-pandoc))) ; for documentation
2855 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2856 (synopsis "Graph-based alignment of genomic sequencing reads")
2857 (description "HISAT2 is a fast and sensitive alignment program for mapping
2858 next-generation sequencing reads (both DNA and RNA) to a population of human
2859 genomes (as well as to a single reference genome). In addition to using one
2860 global @dfn{graph FM} (GFM) index that represents a population of human
2861 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2862 the whole genome. These small indexes, combined with several alignment
2863 strategies, enable rapid and accurate alignment of sequencing reads. This new
2864 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2865 ;; HISAT2 contains files from Bowtie2, which is released under
2866 ;; GPLv2 or later. The HISAT2 source files are released under
2868 (license license:gpl3+)))
2870 (define-public hmmer
2878 "http://eddylab.org/software/hmmer"
2879 (version-major version) "/"
2880 version "/hmmer-" version ".tar.gz"))
2883 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2884 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2885 (build-system gnu-build-system)
2886 (native-inputs `(("perl" ,perl)))
2887 (home-page "http://hmmer.org/")
2888 (synopsis "Biosequence analysis using profile hidden Markov models")
2890 "HMMER is used for searching sequence databases for homologs of protein
2891 sequences, and for making protein sequence alignments. It implements methods
2892 using probabilistic models called profile hidden Markov models (profile
2894 (license (list license:gpl3+
2895 ;; The bundled library 'easel' is distributed
2896 ;; under The Janelia Farm Software License.
2897 (license:non-copyleft
2898 "file://easel/LICENSE"
2899 "See easel/LICENSE in the distribution.")))))
2901 (define-public htseq
2907 (uri (pypi-uri "HTSeq" version))
2910 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2911 (build-system python-build-system)
2913 `(("python-cython" ,python-cython)))
2914 ;; Numpy needs to be propagated when htseq is used as a Python library.
2916 `(("python-numpy" ,python-numpy)))
2918 `(("python-pysam" ,python-pysam)
2919 ("python-matplotlib" ,python-matplotlib)))
2920 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2921 (synopsis "Analysing high-throughput sequencing data with Python")
2923 "HTSeq is a Python package that provides infrastructure to process data
2924 from high-throughput sequencing assays.")
2925 (license license:gpl3+)))
2927 (define-public python2-htseq
2928 (package-with-python2 htseq))
2930 (define-public java-htsjdk
2932 (name "java-htsjdk")
2933 (version "2.3.0") ; last version without build dependency on gradle
2937 "https://github.com/samtools/htsjdk/archive/"
2939 (file-name (string-append name "-" version ".tar.gz"))
2942 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2943 (modules '((guix build utils)))
2945 ;; Delete pre-built binaries
2947 (delete-file-recursively "lib")
2950 (build-system ant-build-system)
2952 `(#:tests? #f ; test require Internet access
2955 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2956 "/share/java/htsjdk/"))
2957 #:build-target "all"
2959 (modify-phases %standard-phases
2960 ;; The build phase also installs the jars
2961 (delete 'install))))
2963 `(("java-ngs" ,java-ngs)
2964 ("java-snappy-1" ,java-snappy-1)
2965 ("java-commons-compress" ,java-commons-compress)
2966 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
2967 ("java-commons-jexl-2" ,java-commons-jexl-2)
2968 ("java-xz" ,java-xz)))
2970 `(("java-testng" ,java-testng)))
2971 (home-page "http://samtools.github.io/htsjdk/")
2972 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2974 "HTSJDK is an implementation of a unified Java library for accessing
2975 common file formats, such as SAM and VCF, used for high-throughput
2976 sequencing (HTS) data. There are also an number of useful utilities for
2977 manipulating HTS data.")
2978 (license license:expat)))
2980 (define-public java-htsjdk-latest
2982 (name "java-htsjdk")
2987 (url "https://github.com/samtools/htsjdk.git")
2989 (file-name (string-append name "-" version "-checkout"))
2992 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
2993 (build-system ant-build-system)
2995 `(#:tests? #f ; test require Scala
2997 #:jar-name "htsjdk.jar"
2999 (modify-phases %standard-phases
3000 (add-after 'unpack 'remove-useless-build.xml
3001 (lambda _ (delete-file "build.xml") #t))
3002 ;; The tests require the scalatest package.
3003 (add-after 'unpack 'remove-tests
3004 (lambda _ (delete-file-recursively "src/test") #t)))))
3006 `(("java-ngs" ,java-ngs)
3007 ("java-snappy-1" ,java-snappy-1)
3008 ("java-commons-compress" ,java-commons-compress)
3009 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3010 ("java-commons-jexl-2" ,java-commons-jexl-2)
3011 ("java-xz" ,java-xz)))
3013 `(("java-junit" ,java-junit)))
3014 (home-page "http://samtools.github.io/htsjdk/")
3015 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3017 "HTSJDK is an implementation of a unified Java library for accessing
3018 common file formats, such as SAM and VCF, used for high-throughput
3019 sequencing (HTS) data. There are also an number of useful utilities for
3020 manipulating HTS data.")
3021 (license license:expat)))
3023 ;; This is needed for picard 2.10.3
3024 (define-public java-htsjdk-2.10.1
3025 (package (inherit java-htsjdk-latest)
3026 (name "java-htsjdk")
3031 (url "https://github.com/samtools/htsjdk.git")
3033 (file-name (string-append name "-" version "-checkout"))
3036 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3037 (build-system ant-build-system)
3039 `(#:tests? #f ; tests require Scala
3041 #:jar-name "htsjdk.jar"
3043 (modify-phases %standard-phases
3044 (add-after 'unpack 'remove-useless-build.xml
3045 (lambda _ (delete-file "build.xml") #t))
3046 ;; The tests require the scalatest package.
3047 (add-after 'unpack 'remove-tests
3048 (lambda _ (delete-file-recursively "src/test") #t)))))))
3050 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3051 ;; recent version of java-htsjdk, which depends on gradle.
3052 (define-public java-picard
3054 (name "java-picard")
3059 (url "https://github.com/broadinstitute/picard.git")
3061 (file-name (string-append "java-picard-" version "-checkout"))
3064 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3065 (modules '((guix build utils)))
3068 ;; Delete pre-built binaries.
3069 (delete-file-recursively "lib")
3071 (substitute* "build.xml"
3072 ;; Remove build-time dependency on git.
3073 (("failifexecutionfails=\"true\"")
3074 "failifexecutionfails=\"false\"")
3076 (("depends=\"compile-htsjdk, ")
3078 (("depends=\"compile-htsjdk-tests, ")
3080 ;; Build picard-lib.jar before building picard.jar
3081 (("name=\"picard-jar\" depends=\"" line)
3082 (string-append line "picard-lib-jar, ")))
3084 (build-system ant-build-system)
3086 `(#:build-target "picard-jar"
3087 #:test-target "test"
3088 ;; Tests require jacoco:coverage.
3091 (list (string-append "-Dhtsjdk_lib_dir="
3092 (assoc-ref %build-inputs "java-htsjdk")
3093 "/share/java/htsjdk/")
3094 "-Dhtsjdk-classes=dist/tmp"
3095 (string-append "-Dhtsjdk-version="
3096 ,(package-version java-htsjdk)))
3099 (modify-phases %standard-phases
3100 (add-after 'unpack 'use-our-htsjdk
3101 (lambda* (#:key inputs #:allow-other-keys)
3102 (substitute* "build.xml"
3103 (("\\$\\{htsjdk\\}/lib")
3104 (string-append (assoc-ref inputs "java-htsjdk")
3105 "/share/java/htsjdk/")))
3107 (add-after 'unpack 'make-test-target-independent
3108 (lambda* (#:key inputs #:allow-other-keys)
3109 (substitute* "build.xml"
3110 (("name=\"test\" depends=\"compile, ")
3111 "name=\"test\" depends=\""))
3113 (replace 'install (install-jars "dist")))))
3115 `(("java-htsjdk" ,java-htsjdk)
3116 ("java-guava" ,java-guava)))
3118 `(("java-testng" ,java-testng)))
3119 (home-page "http://broadinstitute.github.io/picard/")
3120 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3121 (description "Picard is a set of Java command line tools for manipulating
3122 high-throughput sequencing (HTS) data and formats. Picard is implemented
3123 using the HTSJDK Java library to support accessing file formats that are
3124 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3126 (license license:expat)))
3128 ;; This is needed for dropseq-tools
3129 (define-public java-picard-2.10.3
3131 (name "java-picard")
3136 (url "https://github.com/broadinstitute/picard.git")
3138 (file-name (string-append "java-picard-" version "-checkout"))
3141 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3142 (build-system ant-build-system)
3144 `(#:jar-name "picard.jar"
3145 ;; Tests require jacoco:coverage.
3148 #:main-class "picard.cmdline.PicardCommandLine"
3149 #:modules ((guix build ant-build-system)
3151 (guix build java-utils)
3156 (modify-phases %standard-phases
3157 (add-after 'unpack 'remove-useless-build.xml
3158 (lambda _ (delete-file "build.xml") #t))
3159 ;; This is necessary to ensure that htsjdk is found when using
3160 ;; picard.jar as an executable.
3161 (add-before 'build 'edit-classpath-in-manifest
3162 (lambda* (#:key inputs #:allow-other-keys)
3163 (chmod "build.xml" #o664)
3164 (call-with-output-file "build.xml.new"
3168 (with-input-from-file "build.xml"
3169 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3170 `((target . ,(lambda (tag . kids)
3171 (let ((name ((sxpath '(name *text*))
3173 ;; FIXME: We're breaking the line
3174 ;; early with a dummy path to
3175 ;; ensure that the store reference
3176 ;; isn't broken apart and can still
3177 ;; be found by the reference
3182 ~a/share/java/htsjdk.jar${line.separator}"
3183 ;; maximum line length is 70
3184 (string-tabulate (const #\b) 57)
3185 (assoc-ref inputs "java-htsjdk"))))
3186 (if (member "manifest" name)
3190 (file "${manifest.file}")
3193 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3194 (*text* . ,(lambda (_ txt) txt))))
3196 (rename-file "build.xml.new" "build.xml")
3199 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3201 `(("java-testng" ,java-testng)
3202 ("java-guava" ,java-guava)))
3203 (home-page "http://broadinstitute.github.io/picard/")
3204 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3205 (description "Picard is a set of Java command line tools for manipulating
3206 high-throughput sequencing (HTS) data and formats. Picard is implemented
3207 using the HTSJDK Java library to support accessing file formats that are
3208 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3210 (license license:expat)))
3212 ;; This is the last version of Picard to provide net.sf.samtools
3213 (define-public java-picard-1.113
3214 (package (inherit java-picard)
3215 (name "java-picard")
3220 (url "https://github.com/broadinstitute/picard.git")
3222 (file-name (string-append "java-picard-" version "-checkout"))
3225 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3226 (modules '((guix build utils)))
3229 ;; Delete pre-built binaries.
3230 (delete-file-recursively "lib")
3233 (build-system ant-build-system)
3235 `(#:build-target "picard-jar"
3236 #:test-target "test"
3237 ;; FIXME: the class path at test time is wrong.
3238 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3239 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3242 ;; This is only used for tests.
3244 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3246 (modify-phases %standard-phases
3247 ;; Do not use bundled ant bzip2.
3248 (add-after 'unpack 'use-ant-bzip
3249 (lambda* (#:key inputs #:allow-other-keys)
3250 (substitute* "build.xml"
3251 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3252 (string-append (assoc-ref inputs "ant")
3255 (add-after 'unpack 'make-test-target-independent
3256 (lambda* (#:key inputs #:allow-other-keys)
3257 (substitute* "build.xml"
3258 (("name=\"test\" depends=\"compile, ")
3259 "name=\"test\" depends=\"compile-tests, ")
3260 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3261 "name=\"compile\" depends=\"compile-src\""))
3263 (add-after 'unpack 'fix-deflater-path
3264 (lambda* (#:key outputs #:allow-other-keys)
3265 (substitute* "src/java/net/sf/samtools/Defaults.java"
3266 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3267 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3268 (assoc-ref outputs "out")
3269 "/lib/jni/libIntelDeflater.so"
3272 ;; Build the deflater library, because we've previously deleted the
3273 ;; pre-built one. This can only be built with access to the JDK
3275 (add-after 'build 'build-jni
3276 (lambda* (#:key inputs #:allow-other-keys)
3279 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3280 "-xf" (assoc-ref inputs "jdk-src")))
3281 (zero? (system* "javah" "-jni"
3282 "-classpath" "classes"
3284 "net.sf.samtools.util.zip.IntelDeflater"))
3285 (with-directory-excursion "src/c/inteldeflater"
3286 (zero? (system* "gcc" "-I../../../lib" "-I."
3287 (string-append "-I" (assoc-ref inputs "jdk")
3289 "-I../../../jdk-src/src/share/native/common/"
3290 "-I../../../jdk-src/src/solaris/native/common/"
3291 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3292 (zero? (system* "gcc" "-shared"
3293 "-o" "../../../lib/jni/libIntelDeflater.so"
3294 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3295 ;; We can only build everything else after building the JNI library.
3296 (add-after 'build-jni 'build-rest
3297 (lambda* (#:key make-flags #:allow-other-keys)
3298 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3299 (add-before 'build 'set-JAVA6_HOME
3301 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3303 (replace 'install (install-jars "dist"))
3304 (add-after 'install 'install-jni-lib
3305 (lambda* (#:key outputs #:allow-other-keys)
3306 (let ((jni (string-append (assoc-ref outputs "out")
3309 (install-file "lib/jni/libIntelDeflater.so" jni)
3312 `(("java-snappy-1" ,java-snappy-1)
3313 ("java-commons-jexl-2" ,java-commons-jexl-2)
3314 ("java-cofoja" ,java-cofoja)
3315 ("ant" ,ant) ; for bzip2 support at runtime
3318 `(("ant-apache-bcel" ,ant-apache-bcel)
3319 ("ant-junit" ,ant-junit)
3320 ("java-testng" ,java-testng)
3321 ("java-commons-bcel" ,java-commons-bcel)
3322 ("java-jcommander" ,java-jcommander)
3323 ("jdk" ,icedtea-8 "jdk")
3324 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3326 (define-public fastqc
3333 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3334 "projects/fastqc/fastqc_v"
3335 version "_source.zip"))
3338 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3339 (build-system ant-build-system)
3341 `(#:tests? #f ; there are no tests
3342 #:build-target "build"
3344 (modify-phases %standard-phases
3345 (add-after 'unpack 'fix-dependencies
3346 (lambda* (#:key inputs #:allow-other-keys)
3347 (substitute* "build.xml"
3349 (string-append (assoc-ref inputs "java-jbzip2")
3350 "/share/java/jbzip2.jar"))
3352 (string-append (assoc-ref inputs "java-picard-1.113")
3353 "/share/java/sam-1.112.jar"))
3355 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3356 "/share/java/sis-jhdf5.jar")))
3358 ;; There is no installation target
3360 (lambda* (#:key inputs outputs #:allow-other-keys)
3361 (let* ((out (assoc-ref outputs "out"))
3362 (bin (string-append out "/bin"))
3363 (share (string-append out "/share/fastqc/"))
3364 (exe (string-append share "/fastqc")))
3365 (for-each mkdir-p (list bin share))
3366 (copy-recursively "bin" share)
3368 (("my \\$java_bin = 'java';")
3369 (string-append "my $java_bin = '"
3370 (assoc-ref inputs "java")
3373 (symlink exe (string-append bin "/fastqc"))
3377 ("perl" ,perl) ; needed for the wrapper script
3378 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3379 ("java-picard-1.113" ,java-picard-1.113)
3380 ("java-jbzip2" ,java-jbzip2)))
3382 `(("unzip" ,unzip)))
3383 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3384 (synopsis "Quality control tool for high throughput sequence data")
3386 "FastQC aims to provide a simple way to do some quality control
3387 checks on raw sequence data coming from high throughput sequencing
3388 pipelines. It provides a modular set of analyses which you can use to
3389 give a quick impression of whether your data has any problems of which
3390 you should be aware before doing any further analysis.
3392 The main functions of FastQC are:
3395 @item Import of data from BAM, SAM or FastQ files (any variant);
3396 @item Providing a quick overview to tell you in which areas there may
3398 @item Summary graphs and tables to quickly assess your data;
3399 @item Export of results to an HTML based permanent report;
3400 @item Offline operation to allow automated generation of reports
3401 without running the interactive application.
3403 (license license:gpl3+)))
3405 (define-public htslib
3412 "https://github.com/samtools/htslib/releases/download/"
3413 version "/htslib-" version ".tar.bz2"))
3416 "1il6i2p84b0y9c93dhvzzki1ifw9bvapm2mvpr0xvb2nq8jlwgdy"))))
3417 (build-system gnu-build-system)
3419 `(("openssl" ,openssl)
3424 (home-page "http://www.htslib.org")
3425 (synopsis "C library for reading/writing high-throughput sequencing data")
3427 "HTSlib is a C library for reading/writing high-throughput sequencing
3428 data. It also provides the @command{bgzip}, @command{htsfile}, and
3429 @command{tabix} utilities.")
3430 ;; Files under cram/ are released under the modified BSD license;
3431 ;; the rest is released under the Expat license
3432 (license (list license:expat license:bsd-3))))
3434 ;; This package should be removed once no packages rely upon it.
3442 "https://github.com/samtools/htslib/releases/download/"
3443 version "/htslib-" version ".tar.bz2"))
3446 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3455 "https://github.com/nboley/idr/archive/"
3457 (file-name (string-append name "-" version ".tar.gz"))
3460 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3461 ;; Delete generated C code.
3463 '(begin (delete-file "idr/inv_cdf.c") #t))))
3464 (build-system python-build-system)
3465 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3466 ;; are no longer part of this package. It also asserts False, which
3467 ;; causes the tests to always fail.
3468 (arguments `(#:tests? #f))
3470 `(("python-scipy" ,python-scipy)
3471 ("python-sympy" ,python-sympy)
3472 ("python-numpy" ,python-numpy)
3473 ("python-matplotlib" ,python-matplotlib)))
3475 `(("python-cython" ,python-cython)))
3476 (home-page "https://github.com/nboley/idr")
3477 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3479 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3480 to measure the reproducibility of findings identified from replicate
3481 experiments and provide highly stable thresholds based on reproducibility.")
3482 (license license:gpl2+)))
3484 (define-public jellyfish
3490 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3491 "releases/download/v" version
3492 "/jellyfish-" version ".tar.gz"))
3495 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3496 (build-system gnu-build-system)
3497 (outputs '("out" ;for library
3498 "ruby" ;for Ruby bindings
3499 "python")) ;for Python bindings
3502 (list (string-append "--enable-ruby-binding="
3503 (assoc-ref %outputs "ruby"))
3504 (string-append "--enable-python-binding="
3505 (assoc-ref %outputs "python")))
3507 (modify-phases %standard-phases
3508 (add-before 'check 'set-SHELL-variable
3510 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3512 (setenv "SHELL" (which "bash"))
3518 ("python" ,python-2)
3519 ("pkg-config" ,pkg-config)))
3521 `(("htslib" ,htslib)))
3522 (synopsis "Tool for fast counting of k-mers in DNA")
3524 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3525 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3526 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3527 is a command-line program that reads FASTA and multi-FASTA files containing
3528 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3529 translated into a human-readable text format using the @code{jellyfish dump}
3530 command, or queried for specific k-mers with @code{jellyfish query}.")
3531 (home-page "http://www.genome.umd.edu/jellyfish.html")
3532 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3533 (supported-systems '("x86_64-linux"))
3534 ;; The combined work is published under the GPLv3 or later. Individual
3535 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3536 (license (list license:gpl3+ license:expat))))
3538 (define-public khmer
3545 (uri (pypi-uri "khmer" version))
3548 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3549 (patches (search-patches "khmer-use-libraries.patch"))))
3550 (build-system python-build-system)
3553 (modify-phases %standard-phases
3554 (add-after 'unpack 'set-paths
3555 (lambda* (#:key inputs outputs #:allow-other-keys)
3556 ;; Delete bundled libraries.
3557 (delete-file-recursively "third-party/zlib")
3558 (delete-file-recursively "third-party/bzip2")
3559 ;; Replace bundled seqan.
3560 (let* ((seqan-all "third-party/seqan")
3561 (seqan-include (string-append
3562 seqan-all "/core/include")))
3563 (delete-file-recursively seqan-all)
3564 (copy-recursively (string-append (assoc-ref inputs "seqan")
3566 (string-append seqan-include "/seqan")))
3567 ;; We do not replace the bundled MurmurHash as the canonical
3568 ;; repository for this code 'SMHasher' is unsuitable for
3569 ;; providing a library. See
3570 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3572 (add-after 'unpack 'set-cc
3576 ;; It is simpler to test after installation.
3578 (add-after 'install 'post-install-check
3579 (lambda* (#:key inputs outputs #:allow-other-keys)
3580 (let ((out (assoc-ref outputs "out")))
3585 (assoc-ref outputs "out")
3587 (setenv "PYTHONPATH"
3589 (getenv "PYTHONPATH")
3593 (string-take (string-take-right
3594 (assoc-ref inputs "python") 5) 3)
3596 (with-directory-excursion "build"
3597 (zero? (system* "nosetests" "khmer" "--attr"
3598 "!known_failing")))))))))
3601 ("python-nose" ,python-nose)))
3605 ("python-screed" ,python-screed)
3606 ("python-bz2file" ,python-bz2file)
3607 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3608 ;; until the next version of khmer (likely 2.1) is released.
3610 (home-page "https://khmer.readthedocs.org/")
3611 (synopsis "K-mer counting, filtering and graph traversal library")
3612 (description "The khmer software is a set of command-line tools for
3613 working with DNA shotgun sequencing data from genomes, transcriptomes,
3614 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3615 sometimes better. Khmer can also identify and fix problems with shotgun
3617 ;; When building on i686, armhf and mips64el, we get the following error:
3618 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3619 (supported-systems '("x86_64-linux" "aarch64-linux"))
3620 (license license:bsd-3)))
3622 (define-public kaiju
3629 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3631 (file-name (string-append name "-" version ".tar.gz"))
3634 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3635 (build-system gnu-build-system)
3637 `(#:tests? #f ; There are no tests.
3639 (modify-phases %standard-phases
3641 (add-before 'build 'move-to-src-dir
3642 (lambda _ (chdir "src") #t))
3644 (lambda* (#:key inputs outputs #:allow-other-keys)
3645 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3648 (copy-recursively "bin" bin)
3649 (copy-recursively "util" bin))
3653 (home-page "http://kaiju.binf.ku.dk/")
3654 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3655 (description "Kaiju is a program for sensitive taxonomic classification
3656 of high-throughput sequencing reads from metagenomic whole genome sequencing
3658 (license license:gpl3+)))
3663 (version "2.1.0.20151222")
3666 (uri (pypi-uri "MACS2" version))
3669 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3670 (build-system python-build-system)
3672 `(#:python ,python-2 ; only compatible with Python 2.7
3673 #:tests? #f)) ; no test target
3675 `(("python-numpy" ,python2-numpy)))
3676 (home-page "https://github.com/taoliu/MACS/")
3677 (synopsis "Model based analysis for ChIP-Seq data")
3679 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3680 identifying transcript factor binding sites named Model-based Analysis of
3681 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3682 the significance of enriched ChIP regions and it improves the spatial
3683 resolution of binding sites through combining the information of both
3684 sequencing tag position and orientation.")
3685 (license license:bsd-3)))
3687 (define-public mafft
3694 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3695 "-without-extensions-src.tgz"))
3696 (file-name (string-append name "-" version ".tgz"))
3699 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3700 (build-system gnu-build-system)
3702 `(#:tests? #f ; no automated tests, though there are tests in the read me
3703 #:make-flags (let ((out (assoc-ref %outputs "out")))
3704 (list (string-append "PREFIX=" out)
3705 (string-append "BINDIR="
3706 (string-append out "/bin"))))
3708 (modify-phases %standard-phases
3709 (add-after 'unpack 'enter-dir
3710 (lambda _ (chdir "core") #t))
3711 (add-after 'enter-dir 'patch-makefile
3713 ;; on advice from the MAFFT authors, there is no need to
3714 ;; distribute mafft-profile, mafft-distance, or
3715 ;; mafft-homologs.rb as they are too "specialised".
3716 (substitute* "Makefile"
3717 ;; remove mafft-homologs.rb from SCRIPTS
3718 (("^SCRIPTS = mafft mafft-homologs.rb")
3720 ;; remove mafft-homologs from MANPAGES
3721 (("^MANPAGES = mafft.1 mafft-homologs.1")
3722 "MANPAGES = mafft.1")
3723 ;; remove mafft-distance from PROGS
3724 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3725 "PROGS = dvtditr dndfast7 dndblast sextet5")
3726 ;; remove mafft-profile from PROGS
3727 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3728 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3729 (("^rm -f mafft-profile mafft-profile.exe") "#")
3730 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3731 ;; do not install MAN pages in libexec folder
3732 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3733 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3735 (add-after 'enter-dir 'patch-paths
3736 (lambda* (#:key inputs #:allow-other-keys)
3737 (substitute* '("pairash.c"
3739 (("perl") (which "perl"))
3740 (("([\"`| ])awk" _ prefix)
3741 (string-append prefix (which "awk")))
3742 (("grep") (which "grep")))
3745 (add-after 'install 'wrap-programs
3746 (lambda* (#:key outputs #:allow-other-keys)
3747 (let* ((out (assoc-ref outputs "out"))
3748 (bin (string-append out "/bin"))
3749 (path (string-append
3750 (assoc-ref %build-inputs "coreutils") "/bin:")))
3751 (for-each (lambda (file)
3753 `("PATH" ":" prefix (,path))))
3761 ("coreutils" ,coreutils)))
3762 (home-page "http://mafft.cbrc.jp/alignment/software/")
3763 (synopsis "Multiple sequence alignment program")
3765 "MAFFT offers a range of multiple alignment methods for nucleotide and
3766 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3767 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3769 (license (license:non-copyleft
3770 "http://mafft.cbrc.jp/alignment/software/license.txt"
3771 "BSD-3 with different formatting"))))
3780 "https://github.com/marbl/mash/archive/v"
3782 (file-name (string-append name "-" version ".tar.gz"))
3785 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3786 (modules '((guix build utils)))
3788 ;; Delete bundled kseq.
3789 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3790 '(delete-file "src/mash/kseq.h"))))
3791 (build-system gnu-build-system)
3793 `(#:tests? #f ; No tests.
3796 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3797 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3798 #:make-flags (list "CC=gcc")
3800 (modify-phases %standard-phases
3801 (add-after 'unpack 'fix-includes
3803 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3804 (("^#include \"kseq\\.h\"")
3805 "#include \"htslib/kseq.h\""))
3807 (add-after 'fix-includes 'autoconf
3808 (lambda _ (zero? (system* "autoconf")))))))
3810 `(("autoconf" ,autoconf)
3811 ;; Capnproto and htslib are statically embedded in the final
3812 ;; application. Therefore we also list their licenses, below.
3813 ("capnproto" ,capnproto)
3814 ("htslib" ,htslib)))
3818 (supported-systems '("x86_64-linux"))
3819 (home-page "https://mash.readthedocs.io")
3820 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3821 (description "Mash is a fast sequence distance estimator that uses the
3822 MinHash algorithm and is designed to work with genomes and metagenomes in the
3823 form of assemblies or reads.")
3824 (license (list license:bsd-3 ; Mash
3825 license:expat ; HTSlib and capnproto
3826 license:public-domain ; MurmurHash 3
3827 license:cpl1.0)))) ; Open Bloom Filter
3829 (define-public metabat
3836 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3838 (file-name (string-append name "-" version ".tar.gz"))
3841 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3842 (patches (search-patches "metabat-fix-compilation.patch"))))
3843 (build-system scons-build-system)
3845 `(#:scons ,scons-python2
3847 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3848 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3849 #:tests? #f ;; Tests are run during the build phase.
3851 (modify-phases %standard-phases
3852 (add-after 'unpack 'fix-includes
3854 (substitute* "src/BamUtils.h"
3855 (("^#include \"bam/bam\\.h\"")
3856 "#include \"samtools/bam.h\"")
3857 (("^#include \"bam/sam\\.h\"")
3858 "#include \"samtools/sam.h\""))
3859 (substitute* "src/KseqReader.h"
3860 (("^#include \"bam/kseq\\.h\"")
3861 "#include \"htslib/kseq.h\""))
3863 (add-after 'unpack 'fix-scons
3864 (lambda* (#:key inputs #:allow-other-keys)
3865 (substitute* "SConstruct"
3866 (("^htslib_dir += 'samtools'")
3867 (string-append "htslib_dir = '"
3868 (assoc-ref inputs "htslib")
3870 (("^samtools_dir = 'samtools'")
3871 (string-append "samtools_dir = '"
3872 (assoc-ref inputs "samtools")
3874 (("^findStaticOrShared\\('bam', hts_lib")
3875 (string-append "findStaticOrShared('bam', '"
3876 (assoc-ref inputs "samtools")
3878 ;; Do not distribute README.
3879 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3884 ("samtools" ,samtools)
3887 (home-page "https://bitbucket.org/berkeleylab/metabat")
3889 "Reconstruction of single genomes from complex microbial communities")
3891 "Grouping large genomic fragments assembled from shotgun metagenomic
3892 sequences to deconvolute complex microbial communities, or metagenome binning,
3893 enables the study of individual organisms and their interactions. MetaBAT is
3894 an automated metagenome binning software, which integrates empirical
3895 probabilistic distances of genome abundance and tetranucleotide frequency.")
3896 ;; The source code contains inline assembly.
3897 (supported-systems '("x86_64-linux" "i686-linux"))
3898 (license (license:non-copyleft "file://license.txt"
3899 "See license.txt in the distribution."))))
3901 (define-public minced
3908 "https://github.com/ctSkennerton/minced/archive/"
3910 (file-name (string-append name "-" version ".tar.gz"))
3913 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3914 (build-system gnu-build-system)
3916 `(#:test-target "test"
3918 (modify-phases %standard-phases
3920 (add-before 'check 'fix-test
3922 ;; Fix test for latest version.
3923 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3924 (("minced:0.1.6") "minced:0.2.0"))
3926 (replace 'install ; No install target.
3927 (lambda* (#:key inputs outputs #:allow-other-keys)
3928 (let* ((out (assoc-ref outputs "out"))
3929 (bin (string-append out "/bin"))
3930 (wrapper (string-append bin "/minced")))
3931 ;; Minced comes with a wrapper script that tries to figure out where
3932 ;; it is located before running the JAR. Since these paths are known
3933 ;; to us, we build our own wrapper to avoid coreutils dependency.
3934 (install-file "minced.jar" bin)
3935 (with-output-to-file wrapper
3939 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3940 (assoc-ref inputs "jre") "/bin/java -jar "
3941 bin "/minced.jar \"$@\"\n"))))
3942 (chmod wrapper #o555)))))))
3944 `(("jdk" ,icedtea "jdk")))
3947 ("jre" ,icedtea "out")))
3948 (home-page "https://github.com/ctSkennerton/minced")
3949 (synopsis "Mining CRISPRs in Environmental Datasets")
3951 "MinCED is a program to find Clustered Regularly Interspaced Short
3952 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3953 unassembled metagenomic reads, but is mainly designed for full genomes and
3954 assembled metagenomic sequence.")
3955 (license license:gpl3+)))
3963 (uri (pypi-uri "misopy" version))
3966 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3967 (modules '((guix build utils)))
3969 '(substitute* "setup.py"
3970 ;; Use setuptools, or else the executables are not
3972 (("distutils.core") "setuptools")
3973 ;; use "gcc" instead of "cc" for compilation
3975 "cc.set_executables(
3979 linker_so='gcc -shared'); defines")))))
3980 (build-system python-build-system)
3982 `(#:python ,python-2 ; only Python 2 is supported
3983 #:tests? #f)) ; no "test" target
3985 `(("samtools" ,samtools)
3986 ("python-numpy" ,python2-numpy)
3987 ("python-pysam" ,python2-pysam)
3988 ("python-scipy" ,python2-scipy)
3989 ("python-matplotlib" ,python2-matplotlib)))
3991 `(("python-mock" ,python2-mock) ;for tests
3992 ("python-pytz" ,python2-pytz))) ;for tests
3993 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3994 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3996 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3997 the expression level of alternatively spliced genes from RNA-Seq data, and
3998 identifies differentially regulated isoforms or exons across samples. By
3999 modeling the generative process by which reads are produced from isoforms in
4000 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4001 that a read originated from a particular isoform.")
4002 (license license:gpl2)))
4004 (define-public muscle
4007 (version "3.8.1551")
4009 (method url-fetch/tarbomb)
4011 "http://www.drive5.com/muscle/muscle_src_"
4015 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4016 (build-system gnu-build-system)
4018 `(#:make-flags (list "LDLIBS = -lm")
4020 (modify-phases %standard-phases
4023 ;; There are no tests, so just test if it runs.
4024 (lambda _ (zero? (system* "./muscle" "-version"))))
4026 (lambda* (#:key outputs #:allow-other-keys)
4027 (let* ((out (assoc-ref outputs "out"))
4028 (bin (string-append out "/bin")))
4029 (install-file "muscle" bin)))))))
4030 (home-page "http://www.drive5.com/muscle")
4031 (synopsis "Multiple sequence alignment program")
4033 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4034 program for nucleotide and protein sequences.")
4035 ;; License information found in 'muscle -h' and usage.cpp.
4036 (license license:public-domain)))
4038 (define-public newick-utils
4039 ;; There are no recent releases so we package from git.
4040 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4042 (name "newick-utils")
4043 (version (string-append "1.6-1." (string-take commit 8)))
4047 (url "https://github.com/tjunier/newick_utils.git")
4049 (file-name (string-append name "-" version "-checkout"))
4052 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4053 (build-system gnu-build-system)
4056 (modify-phases %standard-phases
4057 (add-after 'unpack 'autoconf
4058 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4060 ;; XXX: TODO: Enable Lua and Guile bindings.
4061 ;; https://github.com/tjunier/newick_utils/issues/13
4062 `(("libxml2" ,libxml2)
4066 `(("autoconf" ,autoconf)
4067 ("automake" ,automake)
4068 ("libtool" ,libtool)))
4069 (synopsis "Programs for working with newick format phylogenetic trees")
4071 "Newick-utils is a suite of utilities for processing phylogenetic trees
4072 in Newick format. Functions include re-rooting, extracting subtrees,
4073 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4074 (home-page "https://github.com/tjunier/newick_utils")
4075 (license license:bsd-3))))
4084 "https://github.com/wwood/OrfM/releases/download/v"
4085 version "/orfm-" version ".tar.gz"))
4088 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4089 (build-system gnu-build-system)
4090 (inputs `(("zlib" ,zlib)))
4092 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4093 ("ruby-rspec" ,ruby-rspec)
4095 (synopsis "Simple and not slow open reading frame (ORF) caller")
4097 "An ORF caller finds stretches of DNA that, when translated, are not
4098 interrupted by stop codons. OrfM finds and prints these ORFs.")
4099 (home-page "https://github.com/wwood/OrfM")
4100 (license license:lgpl3+)))
4102 (define-public pplacer
4103 (let ((commit "g807f6f3"))
4106 ;; The commit should be updated with each version change.
4107 (version "1.1.alpha19")
4111 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4113 (file-name (string-append name "-" version ".tar.gz"))
4115 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4116 (build-system ocaml-build-system)
4118 `(#:ocaml ,ocaml-4.01
4119 #:findlib ,ocaml4.01-findlib
4120 #:modules ((guix build ocaml-build-system)
4124 (modify-phases %standard-phases
4126 (add-after 'unpack 'replace-bundled-cddlib
4127 (lambda* (#:key inputs #:allow-other-keys)
4128 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4129 (local-dir "cddlib_guix"))
4131 (with-directory-excursion local-dir
4132 (system* "tar" "xvf" cddlib-src))
4133 (let ((cddlib-src-folder
4134 (string-append local-dir "/"
4135 (list-ref (scandir local-dir) 2)
4140 (string-append "cdd_src/" (basename file))))
4141 (find-files cddlib-src-folder ".*[ch]$")))
4143 (add-after 'unpack 'fix-makefile
4145 ;; Remove system calls to 'git'.
4146 (substitute* "Makefile"
4147 (("^DESCRIPT:=pplacer-.*")
4149 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4150 (substitute* "myocamlbuild.ml"
4151 (("git describe --tags --long .*\\\" with")
4153 "echo -n v" ,version "-" ,commit "\" with")))
4156 (lambda* (#:key outputs #:allow-other-keys)
4157 (let* ((out (assoc-ref outputs "out"))
4158 (bin (string-append out "/bin")))
4159 (copy-recursively "bin" bin))
4164 ("ocaml-ounit" ,ocaml4.01-ounit)
4165 ("ocaml-batteries" ,ocaml4.01-batteries)
4166 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4167 ("ocaml-csv" ,ocaml4.01-csv)
4168 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4169 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4170 ("ocaml-mcl" ,ocaml4.01-mcl)
4171 ("ocaml-gsl" ,ocaml4.01-gsl)
4172 ("cddlib-src" ,(package-source cddlib))))
4174 `(("pplacer-scripts" ,pplacer-scripts)))
4175 (synopsis "Phylogenetic placement of biological sequences")
4177 "Pplacer places query sequences on a fixed reference phylogenetic tree
4178 to maximize phylogenetic likelihood or posterior probability according to a
4179 reference alignment. Pplacer is designed to be fast, to give useful
4180 information about uncertainty, and to offer advanced visualization and
4181 downstream analysis.")
4182 (home-page "http://matsen.fhcrc.org/pplacer")
4183 (license license:gpl3))))
4185 ;; This package is installed alongside 'pplacer'. It is a separate package so
4186 ;; that it can use the python-build-system for the scripts that are
4187 ;; distributed alongside the main OCaml binaries.
4188 (define pplacer-scripts
4191 (name "pplacer-scripts")
4192 (build-system python-build-system)
4194 `(#:python ,python-2
4196 (modify-phases %standard-phases
4197 (add-after 'unpack 'enter-scripts-dir
4198 (lambda _ (chdir "scripts")))
4201 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4202 (add-after 'install 'wrap-executables
4203 (lambda* (#:key inputs outputs #:allow-other-keys)
4204 (let* ((out (assoc-ref outputs "out"))
4205 (bin (string-append out "/bin")))
4206 (let ((path (string-append
4207 (assoc-ref inputs "hmmer") "/bin:"
4208 (assoc-ref inputs "infernal") "/bin")))
4210 (wrap-program (string-append bin "/refpkg_align.py")
4211 `("PATH" ":" prefix (,path))))
4212 (let ((path (string-append
4213 (assoc-ref inputs "hmmer") "/bin")))
4214 (wrap-program (string-append bin "/hrefpkg_query.py")
4215 `("PATH" ":" prefix (,path)))))
4218 `(("infernal" ,infernal)
4221 `(("python-biopython" ,python2-biopython)
4222 ("taxtastic" ,taxtastic)))
4223 (synopsis "Pplacer Python scripts")))
4225 (define-public python2-pbcore
4227 (name "python2-pbcore")
4231 (uri (pypi-uri "pbcore" version))
4234 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4235 (build-system python-build-system)
4236 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4238 `(("python-cython" ,python2-cython)
4239 ("python-numpy" ,python2-numpy)
4240 ("python-pysam" ,python2-pysam)
4241 ("python-h5py" ,python2-h5py)))
4243 `(("python-nose" ,python2-nose)
4244 ("python-sphinx" ,python2-sphinx)
4245 ("python-pyxb" ,python2-pyxb)))
4246 (home-page "http://pacificbiosciences.github.io/pbcore/")
4247 (synopsis "Library for reading and writing PacBio data files")
4249 "The pbcore package provides Python APIs for interacting with PacBio data
4250 files and writing bioinformatics applications.")
4251 (license license:bsd-3)))
4253 (define-public python2-warpedlmm
4255 (name "python2-warpedlmm")
4261 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4265 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4266 (build-system python-build-system)
4268 `(#:python ,python-2)) ; requires Python 2.7
4270 `(("python-scipy" ,python2-scipy)
4271 ("python-numpy" ,python2-numpy)
4272 ("python-matplotlib" ,python2-matplotlib)
4273 ("python-fastlmm" ,python2-fastlmm)
4274 ("python-pandas" ,python2-pandas)
4275 ("python-pysnptools" ,python2-pysnptools)))
4277 `(("python-mock" ,python2-mock)
4278 ("python-nose" ,python2-nose)
4280 (home-page "https://github.com/PMBio/warpedLMM")
4281 (synopsis "Implementation of warped linear mixed models")
4283 "WarpedLMM is a Python implementation of the warped linear mixed model,
4284 which automatically learns an optimal warping function (or transformation) for
4285 the phenotype as it models the data.")
4286 (license license:asl2.0)))
4288 (define-public pbtranscript-tofu
4289 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4291 (name "pbtranscript-tofu")
4292 (version (string-append "2.2.3." (string-take commit 7)))
4296 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4298 (file-name (string-append name "-" version "-checkout"))
4301 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4302 (modules '((guix build utils)))
4305 ;; remove bundled Cython sources
4306 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4308 (build-system python-build-system)
4310 `(#:python ,python-2
4311 ;; FIXME: Tests fail with "No such file or directory:
4312 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4315 (modify-phases %standard-phases
4316 (add-after 'unpack 'enter-directory
4318 (chdir "pbtranscript-tofu/pbtranscript/")
4320 ;; With setuptools version 18.0 and later this setup.py hack causes
4321 ;; a build error, so we disable it.
4322 (add-after 'enter-directory 'patch-setuppy
4324 (substitute* "setup.py"
4325 (("if 'setuptools.extension' in sys.modules:")
4329 `(("python-numpy" ,python2-numpy)
4330 ("python-bx-python" ,python2-bx-python)
4331 ("python-networkx" ,python2-networkx)
4332 ("python-scipy" ,python2-scipy)
4333 ("python-pbcore" ,python2-pbcore)
4334 ("python-h5py" ,python2-h5py)))
4336 `(("python-cython" ,python2-cython)
4337 ("python-nose" ,python2-nose)))
4338 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4339 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4341 "pbtranscript-tofu contains scripts to analyze transcriptome data
4342 generated using the PacBio Iso-Seq protocol.")
4343 (license license:bsd-3))))
4345 (define-public prank
4352 "http://wasabiapp.org/download/prank/prank.source."
4356 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4357 (build-system gnu-build-system)
4360 (modify-phases %standard-phases
4361 (add-after 'unpack 'enter-src-dir
4365 (add-after 'unpack 'remove-m64-flag
4366 ;; Prank will build with the correct 'bit-ness' without this flag
4367 ;; and this allows building on 32-bit machines.
4368 (lambda _ (substitute* "src/Makefile"
4373 (lambda* (#:key outputs #:allow-other-keys)
4374 (let* ((out (assoc-ref outputs "out"))
4375 (bin (string-append out "/bin"))
4376 (man (string-append out "/share/man/man1"))
4377 (path (string-append
4378 (assoc-ref %build-inputs "mafft") "/bin:"
4379 (assoc-ref %build-inputs "exonerate") "/bin:"
4380 (assoc-ref %build-inputs "bppsuite") "/bin")))
4381 (install-file "prank" bin)
4382 (wrap-program (string-append bin "/prank")
4383 `("PATH" ":" prefix (,path)))
4384 (install-file "prank.1" man))
4388 ("exonerate" ,exonerate)
4389 ("bppsuite" ,bppsuite)))
4390 (home-page "http://wasabiapp.org/software/prank/")
4391 (synopsis "Probabilistic multiple sequence alignment program")
4393 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4394 codon and amino-acid sequences. It is based on a novel algorithm that treats
4395 insertions correctly and avoids over-estimation of the number of deletion
4396 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4397 in phylogenetics and correctly takes into account the evolutionary distances
4398 between sequences. Lastly, PRANK allows for defining a potential structure
4399 for sequences to be aligned and then, simultaneously with the alignment,
4400 predicts the locations of structural units in the sequences.")
4401 (license license:gpl2+)))
4403 (define-public proteinortho
4405 (name "proteinortho")
4412 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4413 version "_src.tar.gz"))
4416 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4417 (build-system gnu-build-system)
4419 `(#:test-target "test"
4421 (modify-phases %standard-phases
4423 ;; There is no configure script, so we modify the Makefile directly.
4424 (lambda* (#:key outputs #:allow-other-keys)
4425 (substitute* "Makefile"
4428 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4430 (add-before 'install 'make-install-directory
4431 ;; The install directory is not created during 'make install'.
4432 (lambda* (#:key outputs #:allow-other-keys)
4433 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4435 (add-after 'install 'wrap-programs
4436 (lambda* (#:key inputs outputs #:allow-other-keys)
4437 (let* ((path (getenv "PATH"))
4438 (out (assoc-ref outputs "out"))
4439 (binary (string-append out "/bin/proteinortho5.pl")))
4440 (wrap-program binary `("PATH" ":" prefix (,path))))
4444 ("python" ,python-2)
4445 ("blast+" ,blast+)))
4446 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4447 (synopsis "Detect orthologous genes across species")
4449 "Proteinortho is a tool to detect orthologous genes across different
4450 species. For doing so, it compares similarities of given gene sequences and
4451 clusters them to find significant groups. The algorithm was designed to handle
4452 large-scale data and can be applied to hundreds of species at once.")
4453 (license license:gpl2+)))
4455 (define-public pyicoteo
4462 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4463 "pyicoteo/get/v" version ".tar.bz2"))
4464 (file-name (string-append name "-" version ".tar.bz2"))
4467 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4468 (build-system python-build-system)
4470 `(#:python ,python-2 ; does not work with Python 3
4471 #:tests? #f)) ; there are no tests
4473 `(("python2-matplotlib" ,python2-matplotlib)))
4474 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4475 (synopsis "Analyze high-throughput genetic sequencing data")
4477 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4478 sequencing data. It works with genomic coordinates. There are currently six
4479 different command-line tools:
4482 @item pyicoregion: for generating exploratory regions automatically;
4483 @item pyicoenrich: for differential enrichment between two conditions;
4484 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4485 @item pyicos: for genomic coordinates manipulation;
4486 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4487 @item pyicount: to count how many reads from N experiment files overlap in a
4489 @item pyicotrocol: to combine operations from pyicoteo.
4491 (license license:gpl3+)))
4493 (define-public prodigal
4500 "https://github.com/hyattpd/Prodigal/archive/v"
4502 (file-name (string-append name "-" version ".tar.gz"))
4505 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4506 (build-system gnu-build-system)
4508 `(#:tests? #f ;no check target
4509 #:make-flags (list (string-append "INSTALLDIR="
4510 (assoc-ref %outputs "out")
4513 (modify-phases %standard-phases
4514 (delete 'configure))))
4515 (home-page "http://prodigal.ornl.gov")
4516 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4518 "Prodigal runs smoothly on finished genomes, draft genomes, and
4519 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4520 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4521 partial genes, and identifies translation initiation sites.")
4522 (license license:gpl3+)))
4524 (define-public roary
4532 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4536 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4537 (build-system perl-build-system)
4540 (modify-phases %standard-phases
4545 ;; The tests are not run by default, so we run each test file
4547 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4549 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4550 (getenv "PERL5LIB")))
4551 (zero? (length (filter (lambda (file)
4552 (display file)(display "\n")
4553 (not (zero? (system* "perl" file))))
4554 (find-files "t" ".*\\.t$"))))))
4556 ;; There is no 'install' target in the Makefile.
4557 (lambda* (#:key outputs #:allow-other-keys)
4558 (let* ((out (assoc-ref outputs "out"))
4559 (bin (string-append out "/bin"))
4560 (perl (string-append out "/lib/perl5/site_perl"))
4561 (roary-plots "contrib/roary_plots"))
4564 (copy-recursively "bin" bin)
4565 (copy-recursively "lib" perl)
4567 (add-after 'install 'wrap-programs
4568 (lambda* (#:key inputs outputs #:allow-other-keys)
4569 (let* ((out (assoc-ref outputs "out"))
4570 (perl5lib (getenv "PERL5LIB"))
4571 (path (getenv "PATH")))
4572 (for-each (lambda (prog)
4573 (let ((binary (string-append out "/" prog)))
4574 (wrap-program binary
4575 `("PERL5LIB" ":" prefix
4576 (,(string-append perl5lib ":" out
4577 "/lib/perl5/site_perl"))))
4578 (wrap-program binary
4580 (,(string-append path ":" out "/bin"))))))
4581 (find-files "bin" ".*[^R]$"))
4583 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4584 (r-site-lib (getenv "R_LIBS_SITE"))
4586 (string-append (assoc-ref inputs "coreutils") "/bin")))
4588 `("R_LIBS_SITE" ":" prefix
4589 (,(string-append r-site-lib ":" out "/site-library/"))))
4592 (,(string-append coreutils-path ":" out "/bin"))))))
4595 `(("perl-env-path" ,perl-env-path)
4596 ("perl-test-files" ,perl-test-files)
4597 ("perl-test-most" ,perl-test-most)
4598 ("perl-test-output" ,perl-test-output)))
4600 `(("perl-array-utils" ,perl-array-utils)
4601 ("bioperl" ,bioperl-minimal)
4602 ("perl-digest-md5-file" ,perl-digest-md5-file)
4603 ("perl-exception-class" ,perl-exception-class)
4604 ("perl-file-find-rule" ,perl-file-find-rule)
4605 ("perl-file-grep" ,perl-file-grep)
4606 ("perl-file-slurper" ,perl-file-slurper)
4607 ("perl-file-which" ,perl-file-which)
4608 ("perl-graph" ,perl-graph)
4609 ("perl-graph-readwrite" ,perl-graph-readwrite)
4610 ("perl-log-log4perl" ,perl-log-log4perl)
4611 ("perl-moose" ,perl-moose)
4612 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4613 ("perl-text-csv" ,perl-text-csv)
4614 ("bedtools" ,bedtools)
4618 ("parallel" ,parallel)
4621 ("fasttree" ,fasttree)
4625 ("r-minimal" ,r-minimal)
4626 ("r-ggplot2" ,r-ggplot2)
4627 ("coreutils" ,coreutils)))
4628 (home-page "http://sanger-pathogens.github.io/Roary")
4629 (synopsis "High speed stand-alone pan genome pipeline")
4631 "Roary is a high speed stand alone pan genome pipeline, which takes
4632 annotated assemblies in GFF3 format (produced by the Prokka program) and
4633 calculates the pan genome. Using a standard desktop PC, it can analyse
4634 datasets with thousands of samples, without compromising the quality of the
4635 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4636 single processor. Roary is not intended for metagenomics or for comparing
4637 extremely diverse sets of genomes.")
4638 (license license:gpl3)))
4640 (define-public raxml
4649 "https://github.com/stamatak/standard-RAxML/archive/v"
4651 (file-name (string-append name "-" version ".tar.gz"))
4654 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4655 (build-system gnu-build-system)
4657 `(#:tests? #f ; There are no tests.
4658 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4659 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4661 (modify-phases %standard-phases
4664 (lambda* (#:key outputs #:allow-other-keys)
4665 (let* ((out (assoc-ref outputs "out"))
4666 (bin (string-append out "/bin"))
4667 (executable "raxmlHPC-HYBRID"))
4668 (install-file executable bin)
4669 (symlink (string-append bin "/" executable) "raxml"))
4672 `(("openmpi" ,openmpi)))
4673 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4674 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4676 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4678 ;; The source includes x86 specific code
4679 (supported-systems '("x86_64-linux" "i686-linux"))
4680 (license license:gpl2+)))
4690 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4693 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4694 (patches (search-patches "rsem-makefile.patch"))
4695 (modules '((guix build utils)))
4698 ;; remove bundled copy of boost
4699 (delete-file-recursively "boost")
4701 (build-system gnu-build-system)
4703 `(#:tests? #f ;no "check" target
4705 (modify-phases %standard-phases
4706 ;; No "configure" script.
4707 ;; Do not build bundled samtools library.
4710 (substitute* "Makefile"
4711 (("^all : sam/libbam.a") "all : "))
4714 (lambda* (#:key outputs #:allow-other-keys)
4715 (let* ((out (string-append (assoc-ref outputs "out")))
4716 (bin (string-append out "/bin/"))
4717 (perl (string-append out "/lib/perl5/site_perl")))
4720 (for-each (lambda (file)
4721 (install-file file bin))
4722 (find-files "." "rsem-.*"))
4723 (install-file "rsem_perl_utils.pm" perl))
4726 'install 'wrap-program
4727 (lambda* (#:key outputs #:allow-other-keys)
4728 (let ((out (assoc-ref outputs "out")))
4729 (for-each (lambda (prog)
4730 (wrap-program (string-append out "/bin/" prog)
4731 `("PERL5LIB" ":" prefix
4732 (,(string-append out "/lib/perl5/site_perl")))))
4733 '("rsem-plot-transcript-wiggles"
4734 "rsem-calculate-expression"
4735 "rsem-generate-ngvector"
4737 "rsem-prepare-reference")))
4741 ("ncurses" ,ncurses)
4742 ("r-minimal" ,r-minimal)
4744 ("samtools" ,samtools-0.1)
4746 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4747 (synopsis "Estimate gene expression levels from RNA-Seq data")
4749 "RSEM is a software package for estimating gene and isoform expression
4750 levels from RNA-Seq data. The RSEM package provides a user-friendly
4751 interface, supports threads for parallel computation of the EM algorithm,
4752 single-end and paired-end read data, quality scores, variable-length reads and
4753 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4754 interval estimates for expression levels. For visualization, it can generate
4755 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4756 (license license:gpl3+)))
4758 (define-public rseqc
4766 (string-append "mirror://sourceforge/rseqc/"
4767 "RSeQC-" version ".tar.gz"))
4769 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4770 (modules '((guix build utils)))
4773 ;; remove bundled copy of pysam
4774 (delete-file-recursively "lib/pysam")
4775 (substitute* "setup.py"
4776 ;; remove dependency on outdated "distribute" module
4777 (("^from distribute_setup import use_setuptools") "")
4778 (("^use_setuptools\\(\\)") "")
4779 ;; do not use bundled copy of pysam
4780 (("^have_pysam = False") "have_pysam = True"))))))
4781 (build-system python-build-system)
4782 (arguments `(#:python ,python-2))
4784 `(("python-cython" ,python2-cython)
4785 ("python-pysam" ,python2-pysam)
4786 ("python-numpy" ,python2-numpy)
4789 `(("python-nose" ,python2-nose)))
4790 (home-page "http://rseqc.sourceforge.net/")
4791 (synopsis "RNA-seq quality control package")
4793 "RSeQC provides a number of modules that can comprehensively evaluate
4794 high throughput sequence data, especially RNA-seq data. Some basic modules
4795 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4796 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4797 distribution, coverage uniformity, strand specificity, etc.")
4798 (license license:gpl3+)))
4801 ;; There are no release tarballs. According to the installation
4802 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4803 ;; stable release is identified by this changeset ID.
4804 (let ((changeset "2329130")
4808 (version (string-append "0-" revision "." changeset))
4812 (url "https://bitbucket.org/libsleipnir/sleipnir")
4813 (changeset changeset)))
4814 (file-name (string-append name "-" version "-checkout"))
4817 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4818 (build-system gnu-build-system)
4820 `(#:modules ((srfi srfi-1)
4821 (guix build gnu-build-system)
4824 (let ((dirs '("SeekMiner"
4830 (modify-phases %standard-phases
4831 (add-before 'configure 'bootstrap
4833 (zero? (system* "bash" "gen_auto"))))
4834 (add-after 'build 'build-additional-tools
4835 (lambda* (#:key make-flags #:allow-other-keys)
4836 (every (lambda (dir)
4837 (with-directory-excursion (string-append "tools/" dir)
4838 (zero? (apply system* "make" make-flags))))
4840 (add-after 'install 'install-additional-tools
4841 (lambda* (#:key make-flags #:allow-other-keys)
4842 (fold (lambda (dir result)
4843 (with-directory-excursion (string-append "tools/" dir)
4845 (zero? (apply system*
4846 `("make" ,@make-flags "install"))))))
4852 ("readline" ,readline)
4853 ("gengetopt" ,gengetopt)
4854 ("log4cpp" ,log4cpp)))
4856 `(("autoconf" ,autoconf)
4857 ("automake" ,automake)
4859 (home-page "http://seek.princeton.edu")
4860 (synopsis "Gene co-expression search engine")
4862 "SEEK is a computational gene co-expression search engine. SEEK provides
4863 biologists with a way to navigate the massive human expression compendium that
4864 now contains thousands of expression datasets. SEEK returns a robust ranking
4865 of co-expressed genes in the biological area of interest defined by the user's
4866 query genes. It also prioritizes thousands of expression datasets according
4867 to the user's query of interest.")
4868 (license license:cc-by3.0))))
4870 (define-public samtools
4878 (string-append "mirror://sourceforge/samtools/samtools/"
4879 version "/samtools-" version ".tar.bz2"))
4882 "18acyqysbxpydlc44lqv2hpp57l06bs9a3yqmcvjk8va2xrrdc77"))))
4883 (build-system gnu-build-system)
4885 `(#:modules ((ice-9 ftw)
4887 (guix build gnu-build-system)
4889 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4890 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4892 (modify-phases %standard-phases
4893 (add-after 'unpack 'patch-tests
4895 (substitute* "test/test.pl"
4896 ;; The test script calls out to /bin/bash
4897 (("/bin/bash") (which "bash")))
4899 (add-after 'install 'install-library
4900 (lambda* (#:key outputs #:allow-other-keys)
4901 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4902 (install-file "libbam.a" lib)
4904 (add-after 'install 'install-headers
4905 (lambda* (#:key outputs #:allow-other-keys)
4906 (let ((include (string-append (assoc-ref outputs "out")
4907 "/include/samtools/")))
4908 (for-each (lambda (file)
4909 (install-file file include))
4910 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4912 (native-inputs `(("pkg-config" ,pkg-config)))
4914 `(("htslib" ,htslib)
4915 ("ncurses" ,ncurses)
4919 (home-page "http://samtools.sourceforge.net")
4920 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4922 "Samtools implements various utilities for post-processing nucleotide
4923 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4924 variant calling (in conjunction with bcftools), and a simple alignment
4926 (license license:expat)))
4928 (define-public samtools-0.1
4929 ;; This is the most recent version of the 0.1 line of samtools. The input
4930 ;; and output formats differ greatly from that used and produced by samtools
4931 ;; 1.x and is still used in many bioinformatics pipelines.
4932 (package (inherit samtools)
4938 (string-append "mirror://sourceforge/samtools/samtools/"
4939 version "/samtools-" version ".tar.bz2"))
4941 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4943 `(#:tests? #f ;no "check" target
4944 ,@(substitute-keyword-arguments (package-arguments samtools)
4945 ((#:make-flags flags)
4946 `(cons "LIBCURSES=-lncurses" ,flags))
4948 `(modify-phases ,phases
4950 (lambda* (#:key outputs #:allow-other-keys)
4951 (let ((bin (string-append
4952 (assoc-ref outputs "out") "/bin")))
4954 (install-file "samtools" bin)
4956 (delete 'patch-tests)
4957 (delete 'configure))))))))
4959 (define-public mosaik
4960 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4965 ;; There are no release tarballs nor tags.
4968 (url "https://github.com/wanpinglee/MOSAIK.git")
4970 (file-name (string-append name "-" version))
4973 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4974 (build-system gnu-build-system)
4976 `(#:tests? #f ; no tests
4977 #:make-flags (list "CC=gcc")
4979 (modify-phases %standard-phases
4981 (lambda _ (chdir "src") #t))
4983 (lambda* (#:key outputs #:allow-other-keys)
4984 (let ((bin (string-append (assoc-ref outputs "out")
4987 (copy-recursively "../bin" bin)
4992 (supported-systems '("x86_64-linux"))
4993 (home-page "https://github.com/wanpinglee/MOSAIK")
4994 (synopsis "Map nucleotide sequence reads to reference genomes")
4996 "MOSAIK is a program for mapping second and third-generation sequencing
4997 reads to a reference genome. MOSAIK can align reads generated by all the
4998 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4999 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5000 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5001 ;; code released into the public domain:
5002 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5003 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5004 (license (list license:gpl2+ license:public-domain)))))
5006 (define-public ngs-sdk
5014 (string-append "https://github.com/ncbi/ngs/archive/"
5016 (file-name (string-append name "-" version ".tar.gz"))
5019 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5020 (build-system gnu-build-system)
5022 `(#:parallel-build? #f ; not supported
5023 #:tests? #f ; no "check" target
5025 (modify-phases %standard-phases
5027 (lambda* (#:key outputs #:allow-other-keys)
5028 (let ((out (assoc-ref outputs "out")))
5029 ;; Allow 'konfigure.perl' to find 'package.prl'.
5031 (string-append ".:" (getenv "PERL5LIB")))
5033 ;; The 'configure' script doesn't recognize things like
5034 ;; '--enable-fast-install'.
5035 (zero? (system* "./configure"
5036 (string-append "--build-prefix=" (getcwd) "/build")
5037 (string-append "--prefix=" out))))))
5038 (add-after 'unpack 'enter-dir
5039 (lambda _ (chdir "ngs-sdk") #t)))))
5040 (native-inputs `(("perl" ,perl)))
5041 ;; According to the test
5042 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5043 ;; in ngs-sdk/setup/konfigure.perl
5044 (supported-systems '("i686-linux" "x86_64-linux"))
5045 (home-page "https://github.com/ncbi/ngs")
5046 (synopsis "API for accessing Next Generation Sequencing data")
5048 "NGS is a domain-specific API for accessing reads, alignments and pileups
5049 produced from Next Generation Sequencing. The API itself is independent from
5050 any particular back-end implementation, and supports use of multiple back-ends
5052 (license license:public-domain)))
5054 (define-public java-ngs
5055 (package (inherit ngs-sdk)
5058 `(,@(substitute-keyword-arguments
5059 `(#:modules ((guix build gnu-build-system)
5063 ,@(package-arguments ngs-sdk))
5065 `(modify-phases ,phases
5066 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5068 `(("jdk" ,icedtea "jdk")
5069 ("ngs-sdk" ,ngs-sdk)))
5070 (synopsis "Java bindings for NGS SDK")))
5072 (define-public ncbi-vdb
5080 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5082 (file-name (string-append name "-" version ".tar.gz"))
5085 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5086 (build-system gnu-build-system)
5088 `(#:parallel-build? #f ; not supported
5089 #:tests? #f ; no "check" target
5091 (modify-phases %standard-phases
5092 (add-before 'configure 'set-perl-search-path
5094 ;; Work around "dotless @INC" build failure.
5096 (string-append (getcwd) "/setup:"
5097 (getenv "PERL5LIB")))
5100 (lambda* (#:key inputs outputs #:allow-other-keys)
5101 (let ((out (assoc-ref outputs "out")))
5102 ;; Override include path for libmagic
5103 (substitute* "setup/package.prl"
5104 (("name => 'magic', Include => '/usr/include'")
5105 (string-append "name=> 'magic', Include => '"
5106 (assoc-ref inputs "libmagic")
5109 ;; Install kdf5 library (needed by sra-tools)
5110 (substitute* "build/Makefile.install"
5111 (("LIBRARIES_TO_INSTALL =")
5112 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5114 (substitute* "build/Makefile.env"
5115 (("CFLAGS =" prefix)
5116 (string-append prefix "-msse2 ")))
5118 ;; Override search path for ngs-java
5119 (substitute* "setup/package.prl"
5120 (("/usr/local/ngs/ngs-java")
5121 (assoc-ref inputs "java-ngs")))
5123 ;; The 'configure' script doesn't recognize things like
5124 ;; '--enable-fast-install'.
5127 (string-append "--build-prefix=" (getcwd) "/build")
5128 (string-append "--prefix=" (assoc-ref outputs "out"))
5129 (string-append "--debug")
5130 (string-append "--with-xml2-prefix="
5131 (assoc-ref inputs "libxml2"))
5132 (string-append "--with-ngs-sdk-prefix="
5133 (assoc-ref inputs "ngs-sdk"))
5134 (string-append "--with-hdf5-prefix="
5135 (assoc-ref inputs "hdf5")))))))
5136 (add-after 'install 'install-interfaces
5137 (lambda* (#:key outputs #:allow-other-keys)
5138 ;; Install interface libraries. On i686 the interface libraries
5139 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5140 ;; architecture name ("i386") instead of the target system prefix
5142 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5143 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5144 ,(system->linux-architecture
5145 (or (%current-target-system)
5148 (string-append (assoc-ref outputs "out")
5150 ;; Install interface headers
5151 (copy-recursively "interfaces"
5152 (string-append (assoc-ref outputs "out")
5155 ;; These files are needed by sra-tools.
5156 (add-after 'install 'install-configuration-files
5157 (lambda* (#:key outputs #:allow-other-keys)
5158 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5160 (install-file "libs/kfg/default.kfg" target)
5161 (install-file "libs/kfg/certs.kfg" target))
5164 `(("libxml2" ,libxml2)
5165 ("ngs-sdk" ,ngs-sdk)
5166 ("java-ngs" ,java-ngs)
5169 (native-inputs `(("perl" ,perl)))
5170 ;; NCBI-VDB requires SSE capability.
5171 (supported-systems '("i686-linux" "x86_64-linux"))
5172 (home-page "https://github.com/ncbi/ncbi-vdb")
5173 (synopsis "Database engine for genetic information")
5175 "The NCBI-VDB library implements a highly compressed columnar data
5176 warehousing engine that is most often used to store genetic information.
5177 Databases are stored in a portable image within the file system, and can be
5178 accessed/downloaded on demand across HTTP.")
5179 (license license:public-domain)))
5181 (define-public plink
5189 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5190 version "-src.zip"))
5192 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5193 (patches (search-patches "plink-1.07-unclobber-i.patch"
5194 "plink-endian-detection.patch"))))
5195 (build-system gnu-build-system)
5197 '(#:tests? #f ;no "check" target
5198 #:make-flags (list (string-append "LIB_LAPACK="
5199 (assoc-ref %build-inputs "lapack")
5200 "/lib/liblapack.so")
5203 ;; disable phoning home
5206 (modify-phases %standard-phases
5207 ;; no "configure" script
5210 (lambda* (#:key outputs #:allow-other-keys)
5211 (let ((bin (string-append (assoc-ref outputs "out")
5213 (install-file "plink" bin)
5217 ("lapack" ,lapack)))
5219 `(("unzip" ,unzip)))
5220 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5221 (synopsis "Whole genome association analysis toolset")
5223 "PLINK is a whole genome association analysis toolset, designed to
5224 perform a range of basic, large-scale analyses in a computationally efficient
5225 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5226 so there is no support for steps prior to this (e.g. study design and
5227 planning, generating genotype or CNV calls from raw data). Through
5228 integration with gPLINK and Haploview, there is some support for the
5229 subsequent visualization, annotation and storage of results.")
5230 ;; Code is released under GPLv2, except for fisher.h, which is under
5232 (license (list license:gpl2 license:lgpl2.1+))))
5234 (define-public plink-ng
5235 (package (inherit plink)
5241 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5243 (file-name (string-append name "-" version ".tar.gz"))
5245 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5246 (build-system gnu-build-system)
5248 '(#:tests? #f ;no "check" target
5249 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5250 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5252 "-f" "Makefile.std")
5254 (modify-phases %standard-phases
5255 (add-after 'unpack 'chdir
5256 (lambda _ (chdir "1.9") #t))
5257 (delete 'configure) ; no "configure" script
5259 (lambda* (#:key outputs #:allow-other-keys)
5260 (let ((bin (string-append (assoc-ref outputs "out")
5262 (install-file "plink" bin)
5267 ("openblas" ,openblas)))
5268 (home-page "https://www.cog-genomics.org/plink/")
5269 (license license:gpl3+)))
5271 (define-public smithlab-cpp
5272 (let ((revision "1")
5273 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5275 (name "smithlab-cpp")
5276 (version (string-append "0." revision "." (string-take commit 7)))
5280 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5282 (file-name (string-append name "-" version "-checkout"))
5285 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5286 (build-system gnu-build-system)
5288 `(#:modules ((guix build gnu-build-system)
5291 #:tests? #f ;no "check" target
5293 (modify-phases %standard-phases
5294 (add-after 'unpack 'use-samtools-headers
5296 (substitute* '("SAM.cpp"
5298 (("sam.h") "samtools/sam.h"))
5301 (lambda* (#:key outputs #:allow-other-keys)
5302 (let* ((out (assoc-ref outputs "out"))
5303 (lib (string-append out "/lib"))
5304 (include (string-append out "/include/smithlab-cpp")))
5307 (for-each (cut install-file <> lib)
5308 (find-files "." "\\.o$"))
5309 (for-each (cut install-file <> include)
5310 (find-files "." "\\.hpp$")))
5312 (delete 'configure))))
5314 `(("samtools" ,samtools-0.1)
5316 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5317 (synopsis "C++ helper library for functions used in Smith lab projects")
5319 "Smithlab CPP is a C++ library that includes functions used in many of
5320 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5321 structures, classes for genomic regions, mapped sequencing reads, etc.")
5322 (license license:gpl3+))))
5324 (define-public preseq
5330 (uri (string-append "https://github.com/smithlabcode/"
5331 "preseq/archive/v" version ".tar.gz"))
5332 (file-name (string-append name "-" version ".tar.gz"))
5334 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5335 (modules '((guix build utils)))
5337 ;; Remove bundled samtools.
5338 '(delete-file-recursively "samtools"))))
5339 (build-system gnu-build-system)
5341 `(#:tests? #f ;no "check" target
5343 (modify-phases %standard-phases
5344 (delete 'configure))
5346 (list (string-append "PREFIX="
5347 (assoc-ref %outputs "out"))
5348 (string-append "LIBBAM="
5349 (assoc-ref %build-inputs "samtools")
5351 (string-append "SMITHLAB_CPP="
5352 (assoc-ref %build-inputs "smithlab-cpp")
5355 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5358 ("samtools" ,samtools-0.1)
5359 ("smithlab-cpp" ,smithlab-cpp)
5361 (home-page "http://smithlabresearch.org/software/preseq/")
5362 (synopsis "Program for analyzing library complexity")
5364 "The preseq package is aimed at predicting and estimating the complexity
5365 of a genomic sequencing library, equivalent to predicting and estimating the
5366 number of redundant reads from a given sequencing depth and how many will be
5367 expected from additional sequencing using an initial sequencing experiment.
5368 The estimates can then be used to examine the utility of further sequencing,
5369 optimize the sequencing depth, or to screen multiple libraries to avoid low
5370 complexity samples.")
5371 (license license:gpl3+)))
5373 (define-public python-screed
5375 (name "python-screed")
5380 (uri (pypi-uri "screed" version))
5383 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5384 (build-system python-build-system)
5387 (modify-phases %standard-phases
5390 (setenv "PYTHONPATH"
5391 (string-append (getenv "PYTHONPATH") ":."))
5392 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5394 `(("python-nose" ,python-nose)))
5396 `(("python-bz2file" ,python-bz2file)))
5397 (home-page "https://github.com/dib-lab/screed/")
5398 (synopsis "Short read sequence database utilities")
5399 (description "Screed parses FASTA and FASTQ files and generates databases.
5400 Values such as sequence name, sequence description, sequence quality and the
5401 sequence itself can be retrieved from these databases.")
5402 (license license:bsd-3)))
5404 (define-public python2-screed
5405 (package-with-python2 python-screed))
5407 (define-public sra-tools
5415 (string-append "https://github.com/ncbi/sra-tools/archive/"
5417 (file-name (string-append name "-" version ".tar.gz"))
5420 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5421 (build-system gnu-build-system)
5423 `(#:parallel-build? #f ; not supported
5424 #:tests? #f ; no "check" target
5426 (list (string-append "DEFAULT_CRT="
5427 (assoc-ref %build-inputs "ncbi-vdb")
5429 (string-append "DEFAULT_KFG="
5430 (assoc-ref %build-inputs "ncbi-vdb")
5432 (string-append "VDB_LIBDIR="
5433 (assoc-ref %build-inputs "ncbi-vdb")
5434 ,(if (string-prefix? "x86_64"
5435 (or (%current-target-system)
5440 (modify-phases %standard-phases
5441 (add-before 'configure 'set-perl-search-path
5443 ;; Work around "dotless @INC" build failure.
5445 (string-append (getcwd) "/setup:"
5446 (getenv "PERL5LIB")))
5449 (lambda* (#:key inputs outputs #:allow-other-keys)
5450 ;; The build system expects a directory containing the sources and
5451 ;; raw build output of ncbi-vdb, including files that are not
5452 ;; installed. Since we are building against an installed version of
5453 ;; ncbi-vdb, the following modifications are needed.
5454 (substitute* "setup/konfigure.perl"
5455 ;; Make the configure script look for the "ilib" directory of
5456 ;; "ncbi-vdb" without first checking for the existence of a
5457 ;; matching library in its "lib" directory.
5458 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5459 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5460 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5461 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5462 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5465 (substitute* "tools/copycat/Makefile"
5466 (("smagic-static") "lmagic"))
5468 ;; The 'configure' script doesn't recognize things like
5469 ;; '--enable-fast-install'.
5472 (string-append "--build-prefix=" (getcwd) "/build")
5473 (string-append "--prefix=" (assoc-ref outputs "out"))
5474 (string-append "--debug")
5475 (string-append "--with-fuse-prefix="
5476 (assoc-ref inputs "fuse"))
5477 (string-append "--with-magic-prefix="
5478 (assoc-ref inputs "libmagic"))
5479 ;; TODO: building with libxml2 fails with linker errors
5480 ;; (string-append "--with-xml2-prefix="
5481 ;; (assoc-ref inputs "libxml2"))
5482 (string-append "--with-ncbi-vdb-sources="
5483 (assoc-ref inputs "ncbi-vdb"))
5484 (string-append "--with-ncbi-vdb-build="
5485 (assoc-ref inputs "ncbi-vdb"))
5486 (string-append "--with-ngs-sdk-prefix="
5487 (assoc-ref inputs "ngs-sdk"))
5488 (string-append "--with-hdf5-prefix="
5489 (assoc-ref inputs "hdf5"))))))
5490 ;; This version of sra-tools fails to build with glibc because of a
5491 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5492 ;; contains a definition of "canonicalize", so we rename it.
5494 ;; See upstream bug report:
5495 ;; https://github.com/ncbi/sra-tools/issues/67
5496 (add-after 'unpack 'patch-away-glibc-conflict
5498 (substitute* "tools/bam-loader/bam.c"
5499 (("canonicalize\\(" line)
5500 (string-append "sra_tools_" line)))
5502 (native-inputs `(("perl" ,perl)))
5504 `(("ngs-sdk" ,ngs-sdk)
5505 ("ncbi-vdb" ,ncbi-vdb)
5510 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5511 (synopsis "Tools and libraries for reading and writing sequencing data")
5513 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5514 reading of sequencing files from the Sequence Read Archive (SRA) database and
5515 writing files into the .sra format.")
5516 (license license:public-domain)))
5518 (define-public seqan
5524 (uri (string-append "http://packages.seqan.de/seqan-library/"
5525 "seqan-library-" version ".tar.bz2"))
5528 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5529 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5530 ;; makes sense to split the outputs.
5531 (outputs '("out" "doc"))
5532 (build-system trivial-build-system)
5534 `(#:modules ((guix build utils))
5537 (use-modules (guix build utils))
5538 (let ((tar (assoc-ref %build-inputs "tar"))
5539 (bzip (assoc-ref %build-inputs "bzip2"))
5540 (out (assoc-ref %outputs "out"))
5541 (doc (assoc-ref %outputs "doc")))
5542 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5543 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5544 (chdir (string-append "seqan-library-" ,version))
5545 (copy-recursively "include" (string-append out "/include"))
5546 (copy-recursively "share" (string-append doc "/share"))))))
5548 `(("source" ,source)
5551 (home-page "http://www.seqan.de")
5552 (synopsis "Library for nucleotide sequence analysis")
5554 "SeqAn is a C++ library of efficient algorithms and data structures for
5555 the analysis of sequences with the focus on biological data. It contains
5556 algorithms and data structures for string representation and their
5557 manipulation, online and indexed string search, efficient I/O of
5558 bioinformatics file formats, sequence alignment, and more.")
5559 (license license:bsd-3)))
5561 (define-public seqmagick
5568 (uri (pypi-uri "seqmagick" version))
5571 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5572 (build-system python-build-system)
5574 `(("python-biopython" ,python-biopython)))
5576 `(("python-nose" ,python-nose)))
5577 (home-page "https://github.com/fhcrc/seqmagick")
5578 (synopsis "Tools for converting and modifying sequence files")
5580 "Bioinformaticians often have to convert sequence files between formats
5581 and do little manipulations on them, and it's not worth writing scripts for
5582 that. Seqmagick is a utility to expose the file format conversion in
5583 BioPython in a convenient way. Instead of having a big mess of scripts, there
5584 is one that takes arguments.")
5585 (license license:gpl3)))
5587 (define-public seqtk
5594 "https://github.com/lh3/seqtk/archive/v"
5596 (file-name (string-append name "-" version ".tar.gz"))
5599 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5600 (modules '((guix build utils)))
5603 ;; Remove extraneous header files, as is done in the seqtk
5605 (for-each (lambda (file) (delete-file file))
5606 (list "ksort.h" "kstring.h" "kvec.h"))
5608 (build-system gnu-build-system)
5611 (modify-phases %standard-phases
5614 ;; There are no tests, so we just run a sanity check.
5615 (lambda _ (zero? (system* "./seqtk" "seq"))))
5617 (lambda* (#:key outputs #:allow-other-keys)
5618 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5619 (install-file "seqtk" bin)))))))
5622 (home-page "https://github.com/lh3/seqtk")
5623 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5625 "Seqtk is a fast and lightweight tool for processing sequences in the
5626 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5627 optionally compressed by gzip.")
5628 (license license:expat)))
5630 (define-public snap-aligner
5632 (name "snap-aligner")
5633 (version "1.0beta.18")
5637 "https://github.com/amplab/snap/archive/v"
5639 (file-name (string-append name "-" version ".tar.gz"))
5642 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5643 (build-system gnu-build-system)
5646 (modify-phases %standard-phases
5648 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5650 (lambda* (#:key outputs #:allow-other-keys)
5651 (let* ((out (assoc-ref outputs "out"))
5652 (bin (string-append out "/bin")))
5653 (install-file "snap-aligner" bin)
5654 (install-file "SNAPCommand" bin)
5658 (home-page "http://snap.cs.berkeley.edu/")
5659 (synopsis "Short read DNA sequence aligner")
5661 "SNAP is a fast and accurate aligner for short DNA reads. It is
5662 optimized for modern read lengths of 100 bases or higher, and takes advantage
5663 of these reads to align data quickly through a hash-based indexing scheme.")
5664 ;; 32-bit systems are not supported by the unpatched code.
5665 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5666 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5667 ;; systems without a lot of memory cannot make good use of this program.
5668 (supported-systems '("x86_64-linux"))
5669 (license license:asl2.0)))
5671 (define-public sortmerna
5679 "https://github.com/biocore/sortmerna/archive/"
5681 (file-name (string-append name "-" version ".tar.gz"))
5684 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5685 (build-system gnu-build-system)
5686 (outputs '("out" ;for binaries
5687 "db")) ;for sequence databases
5690 (modify-phases %standard-phases
5692 (lambda* (#:key outputs #:allow-other-keys)
5693 (let* ((out (assoc-ref outputs "out"))
5694 (bin (string-append out "/bin"))
5695 (db (assoc-ref outputs "db"))
5697 (string-append db "/share/sortmerna/rRNA_databases")))
5698 (install-file "sortmerna" bin)
5699 (install-file "indexdb_rna" bin)
5700 (for-each (lambda (file)
5701 (install-file file share))
5702 (find-files "rRNA_databases" ".*fasta"))
5706 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5707 (synopsis "Biological sequence analysis tool for NGS reads")
5709 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5710 and operational taxonomic unit (OTU) picking of next generation
5711 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5712 allows for fast and sensitive analyses of nucleotide sequences. The main
5713 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5714 ;; The source includes x86 specific code
5715 (supported-systems '("x86_64-linux" "i686-linux"))
5716 (license license:lgpl3)))
5724 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5726 (file-name (string-append name "-" version ".tar.gz"))
5729 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5730 (modules '((guix build utils)))
5733 (substitute* "source/Makefile"
5735 ;; Remove pre-built binaries and bundled htslib sources.
5736 (delete-file-recursively "bin/MacOSX_x86_64")
5737 (delete-file-recursively "bin/Linux_x86_64")
5738 (delete-file-recursively "bin/Linux_x86_64_static")
5739 (delete-file-recursively "source/htslib")
5741 (build-system gnu-build-system)
5743 '(#:tests? #f ;no check target
5744 #:make-flags '("STAR")
5746 (modify-phases %standard-phases
5747 (add-after 'unpack 'enter-source-dir
5748 (lambda _ (chdir "source") #t))
5749 (add-after 'enter-source-dir 'make-reproducible
5751 (substitute* "Makefile"
5752 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5753 (string-append pre "Built with Guix" post)))))
5754 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5756 (substitute* "Makefile"
5757 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5759 (substitute* '("BAMfunctions.cpp"
5764 "bamRemoveDuplicates.cpp")
5765 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5766 (string-append "#include <" header ">")))
5767 (substitute* "IncludeDefine.h"
5768 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5769 (string-append "<" header ">")))
5772 (lambda* (#:key outputs #:allow-other-keys)
5773 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5774 (install-file "STAR" bin))
5776 (delete 'configure))))
5780 `(("htslib" ,htslib)
5782 (home-page "https://github.com/alexdobin/STAR")
5783 (synopsis "Universal RNA-seq aligner")
5785 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5786 based on a previously undescribed RNA-seq alignment algorithm that uses
5787 sequential maximum mappable seed search in uncompressed suffix arrays followed
5788 by seed clustering and stitching procedure. In addition to unbiased de novo
5789 detection of canonical junctions, STAR can discover non-canonical splices and
5790 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5792 ;; Only 64-bit systems are supported according to the README.
5793 (supported-systems '("x86_64-linux" "mips64el-linux"))
5794 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5795 (license license:gpl3+)))
5797 (define-public subread
5803 (uri (string-append "mirror://sourceforge/subread/subread-"
5804 version "/subread-" version "-source.tar.gz"))
5807 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5808 (build-system gnu-build-system)
5810 `(#:tests? #f ;no "check" target
5811 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5812 ;; optimizations by default, so we override these flags such that x86_64
5813 ;; flags are only added when the build target is an x86_64 system.
5815 (list (let ((system ,(or (%current-target-system)
5817 (flags '("-ggdb" "-fomit-frame-pointer"
5818 "-ffast-math" "-funroll-loops"
5819 "-fmessage-length=0"
5820 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5822 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5823 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5824 (if (string-prefix? "x86_64" system)
5825 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5826 (string-append "CCFLAGS=" (string-join flags))))
5827 "-f" "Makefile.Linux"
5828 "CC=gcc ${CCFLAGS}")
5830 (modify-phases %standard-phases
5831 (add-after 'unpack 'enter-dir
5832 (lambda _ (chdir "src") #t))
5834 (lambda* (#:key outputs #:allow-other-keys)
5835 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5837 (copy-recursively "../bin" bin))))
5838 ;; no "configure" script
5839 (delete 'configure))))
5840 (inputs `(("zlib" ,zlib)))
5841 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5842 (synopsis "Tool kit for processing next-gen sequencing data")
5844 "The subread package contains the following tools: subread aligner, a
5845 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5846 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5847 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5848 against local background noises.")
5849 (license license:gpl3+)))
5851 (define-public stringtie
5857 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5858 "stringtie-" version ".tar.gz"))
5861 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5862 (modules '((guix build utils)))
5865 (delete-file-recursively "samtools-0.1.18")
5867 (build-system gnu-build-system)
5869 `(#:tests? #f ;no test suite
5871 (modify-phases %standard-phases
5872 ;; no configure script
5874 (add-before 'build 'use-system-samtools
5876 (substitute* "Makefile"
5877 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5879 (substitute* '("gclib/GBam.h"
5881 (("#include \"(bam|sam|kstring).h\"" _ header)
5882 (string-append "#include <samtools/" header ".h>")))
5884 (add-after 'unpack 'remove-duplicate-typedef
5886 ;; This typedef conflicts with the typedef in
5887 ;; glibc-2.25/include/bits/types.h
5888 (substitute* "gclib/GThreads.h"
5889 (("typedef long long __intmax_t;") ""))
5892 (lambda* (#:key outputs #:allow-other-keys)
5893 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5894 (install-file "stringtie" bin)
5897 `(("samtools" ,samtools-0.1)
5899 (home-page "http://ccb.jhu.edu/software/stringtie/")
5900 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5902 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5903 alignments into potential transcripts. It uses a novel network flow algorithm
5904 as well as an optional de novo assembly step to assemble and quantitate
5905 full-length transcripts representing multiple splice variants for each gene
5906 locus. Its input can include not only the alignments of raw reads used by
5907 other transcript assemblers, but also alignments of longer sequences that have
5908 been assembled from those reads. To identify differentially expressed genes
5909 between experiments, StringTie's output can be processed either by the
5910 Cuffdiff or Ballgown programs.")
5911 (license license:artistic2.0)))
5913 (define-public taxtastic
5919 (uri (pypi-uri "taxtastic" version))
5922 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5923 (build-system python-build-system)
5925 `(#:python ,python-2
5927 (modify-phases %standard-phases
5930 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5932 `(("python-sqlalchemy" ,python2-sqlalchemy)
5933 ("python-decorator" ,python2-decorator)
5934 ("python-biopython" ,python2-biopython)
5935 ("python-pandas" ,python2-pandas)))
5936 (home-page "https://github.com/fhcrc/taxtastic")
5937 (synopsis "Tools for taxonomic naming and annotation")
5939 "Taxtastic is software written in python used to build and maintain
5940 reference packages i.e. collections of reference trees, reference alignments,
5941 profiles, and associated taxonomic information.")
5942 (license license:gpl3+)))
5944 (define-public vcftools
5951 "https://github.com/vcftools/vcftools/releases/download/v"
5952 version "/vcftools-" version ".tar.gz"))
5955 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5956 (build-system gnu-build-system)
5958 `(#:tests? #f ; no "check" target
5960 "CFLAGS=-O2" ; override "-m64" flag
5961 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5962 (string-append "MANDIR=" (assoc-ref %outputs "out")
5963 "/share/man/man1"))))
5965 `(("pkg-config" ,pkg-config)))
5969 (home-page "https://vcftools.github.io/")
5970 (synopsis "Tools for working with VCF files")
5972 "VCFtools is a program package designed for working with VCF files, such
5973 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5974 provide easily accessible methods for working with complex genetic variation
5975 data in the form of VCF files.")
5976 ;; The license is declared as LGPLv3 in the README and
5977 ;; at https://vcftools.github.io/license.html
5978 (license license:lgpl3)))
5980 (define-public infernal
5986 (uri (string-append "http://eddylab.org/software/infernal/"
5987 "infernal-" version ".tar.gz"))
5990 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5991 (build-system gnu-build-system)
5993 `(("perl" ,perl))) ; for tests
5994 (home-page "http://eddylab.org/infernal/")
5995 (synopsis "Inference of RNA alignments")
5996 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5997 searching DNA sequence databases for RNA structure and sequence similarities.
5998 It is an implementation of a special case of profile stochastic context-free
5999 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6000 profile, but it scores a combination of sequence consensus and RNA secondary
6001 structure consensus, so in many cases, it is more capable of identifying RNA
6002 homologs that conserve their secondary structure more than their primary
6004 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6005 (supported-systems '("i686-linux" "x86_64-linux"))
6006 (license license:bsd-3)))
6008 (define-public r-centipede
6010 (name "r-centipede")
6014 (uri (string-append "http://download.r-forge.r-project.org/"
6015 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6018 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6019 (build-system r-build-system)
6020 (home-page "http://centipede.uchicago.edu/")
6021 (synopsis "Predict transcription factor binding sites")
6023 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6024 of the genome that are bound by particular transcription factors. It starts
6025 by identifying a set of candidate binding sites, and then aims to classify the
6026 sites according to whether each site is bound or not bound by a transcription
6027 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6028 between two different types of motif instances using as much relevant
6029 information as possible.")
6030 (license (list license:gpl2+ license:gpl3+))))
6032 (define-public r-vegan
6039 (uri (cran-uri "vegan" version))
6042 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
6043 (build-system r-build-system)
6045 `(("gfortran" ,gfortran)))
6047 `(("r-cluster" ,r-cluster)
6048 ("r-lattice" ,r-lattice)
6051 ("r-permute" ,r-permute)))
6052 (home-page "https://cran.r-project.org/web/packages/vegan")
6053 (synopsis "Functions for community ecology")
6055 "The vegan package provides tools for descriptive community ecology. It
6056 has most basic functions of diversity analysis, community ordination and
6057 dissimilarity analysis. Most of its multivariate tools can be used for other
6058 data types as well.")
6059 (license license:gpl2+)))
6061 (define-public r-annotate
6068 (uri (bioconductor-uri "annotate" version))
6071 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
6072 (build-system r-build-system)
6074 `(("r-annotationdbi" ,r-annotationdbi)
6075 ("r-biobase" ,r-biobase)
6076 ("r-biocgenerics" ,r-biocgenerics)
6078 ("r-rcurl" ,r-rcurl)
6080 ("r-xtable" ,r-xtable)))
6082 "https://bioconductor.org/packages/annotate")
6083 (synopsis "Annotation for microarrays")
6084 (description "This package provides R environments for the annotation of
6086 (license license:artistic2.0)))
6088 (define-public r-copynumber
6090 (name "r-copynumber")
6094 (uri (bioconductor-uri "copynumber" version))
6097 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6098 (build-system r-build-system)
6100 `(("r-s4vectors" ,r-s4vectors)
6101 ("r-iranges" ,r-iranges)
6102 ("r-genomicranges" ,r-genomicranges)
6103 ("r-biocgenerics" ,r-biocgenerics)))
6104 (home-page "https://bioconductor.org/packages/copynumber")
6105 (synopsis "Segmentation of single- and multi-track copy number data")
6107 "This package segments single- and multi-track copy number data by a
6108 penalized least squares regression method.")
6109 (license license:artistic2.0)))
6111 (define-public r-geneplotter
6113 (name "r-geneplotter")
6118 (uri (bioconductor-uri "geneplotter" version))
6121 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6122 (build-system r-build-system)
6124 `(("r-annotate" ,r-annotate)
6125 ("r-annotationdbi" ,r-annotationdbi)
6126 ("r-biobase" ,r-biobase)
6127 ("r-biocgenerics" ,r-biocgenerics)
6128 ("r-lattice" ,r-lattice)
6129 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6130 (home-page "https://bioconductor.org/packages/geneplotter")
6131 (synopsis "Graphics functions for genomic data")
6133 "This package provides functions for plotting genomic data.")
6134 (license license:artistic2.0)))
6136 (define-public r-genefilter
6138 (name "r-genefilter")
6143 (uri (bioconductor-uri "genefilter" version))
6146 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6147 (build-system r-build-system)
6149 `(("gfortran" ,gfortran)))
6151 `(("r-annotate" ,r-annotate)
6152 ("r-annotationdbi" ,r-annotationdbi)
6153 ("r-biobase" ,r-biobase)
6154 ("r-s4vectors" ,r-s4vectors)
6155 ("r-survival" ,r-survival)))
6156 (home-page "https://bioconductor.org/packages/genefilter")
6157 (synopsis "Filter genes from high-throughput experiments")
6159 "This package provides basic functions for filtering genes from
6160 high-throughput sequencing experiments.")
6161 (license license:artistic2.0)))
6163 (define-public r-deseq2
6170 (uri (bioconductor-uri "DESeq2" version))
6173 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6174 (properties `((upstream-name . "DESeq2")))
6175 (build-system r-build-system)
6177 `(("r-biobase" ,r-biobase)
6178 ("r-biocgenerics" ,r-biocgenerics)
6179 ("r-biocparallel" ,r-biocparallel)
6180 ("r-genefilter" ,r-genefilter)
6181 ("r-geneplotter" ,r-geneplotter)
6182 ("r-genomicranges" ,r-genomicranges)
6183 ("r-ggplot2" ,r-ggplot2)
6184 ("r-hmisc" ,r-hmisc)
6185 ("r-iranges" ,r-iranges)
6186 ("r-locfit" ,r-locfit)
6188 ("r-rcpparmadillo" ,r-rcpparmadillo)
6189 ("r-s4vectors" ,r-s4vectors)
6190 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6191 (home-page "https://bioconductor.org/packages/DESeq2")
6192 (synopsis "Differential gene expression analysis")
6194 "This package provides functions to estimate variance-mean dependence in
6195 count data from high-throughput nucleotide sequencing assays and test for
6196 differential expression based on a model using the negative binomial
6198 (license license:lgpl3+)))
6200 (define-public r-dexseq
6207 (uri (bioconductor-uri "DEXSeq" version))
6210 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6211 (properties `((upstream-name . "DEXSeq")))
6212 (build-system r-build-system)
6214 `(("r-annotationdbi" ,r-annotationdbi)
6215 ("r-biobase" ,r-biobase)
6216 ("r-biocgenerics" ,r-biocgenerics)
6217 ("r-biocparallel" ,r-biocparallel)
6218 ("r-biomart" ,r-biomart)
6219 ("r-deseq2" ,r-deseq2)
6220 ("r-genefilter" ,r-genefilter)
6221 ("r-geneplotter" ,r-geneplotter)
6222 ("r-genomicranges" ,r-genomicranges)
6223 ("r-hwriter" ,r-hwriter)
6224 ("r-iranges" ,r-iranges)
6225 ("r-rcolorbrewer" ,r-rcolorbrewer)
6226 ("r-rsamtools" ,r-rsamtools)
6227 ("r-s4vectors" ,r-s4vectors)
6228 ("r-statmod" ,r-statmod)
6229 ("r-stringr" ,r-stringr)
6230 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6231 (home-page "https://bioconductor.org/packages/DEXSeq")
6232 (synopsis "Inference of differential exon usage in RNA-Seq")
6234 "This package is focused on finding differential exon usage using RNA-seq
6235 exon counts between samples with different experimental designs. It provides
6236 functions that allows the user to make the necessary statistical tests based
6237 on a model that uses the negative binomial distribution to estimate the
6238 variance between biological replicates and generalized linear models for
6239 testing. The package also provides functions for the visualization and
6240 exploration of the results.")
6241 (license license:gpl3+)))
6243 (define-public r-annotationforge
6245 (name "r-annotationforge")
6250 (uri (bioconductor-uri "AnnotationForge" version))
6253 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6255 `((upstream-name . "AnnotationForge")))
6256 (build-system r-build-system)
6258 `(("r-annotationdbi" ,r-annotationdbi)
6259 ("r-biobase" ,r-biobase)
6260 ("r-biocgenerics" ,r-biocgenerics)
6262 ("r-rcurl" ,r-rcurl)
6263 ("r-rsqlite" ,r-rsqlite)
6264 ("r-s4vectors" ,r-s4vectors)
6266 (home-page "https://bioconductor.org/packages/AnnotationForge")
6267 (synopsis "Code for building annotation database packages")
6269 "This package provides code for generating Annotation packages and their
6270 databases. Packages produced are intended to be used with AnnotationDbi.")
6271 (license license:artistic2.0)))
6273 (define-public r-rbgl
6280 (uri (bioconductor-uri "RBGL" version))
6283 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6284 (properties `((upstream-name . "RBGL")))
6285 (build-system r-build-system)
6286 (propagated-inputs `(("r-graph" ,r-graph)))
6287 (home-page "https://www.bioconductor.org/packages/RBGL")
6288 (synopsis "Interface to the Boost graph library")
6290 "This package provides a fairly extensive and comprehensive interface to
6291 the graph algorithms contained in the Boost library.")
6292 (license license:artistic2.0)))
6294 (define-public r-gseabase
6301 (uri (bioconductor-uri "GSEABase" version))
6304 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6305 (properties `((upstream-name . "GSEABase")))
6306 (build-system r-build-system)
6308 `(("r-annotate" ,r-annotate)
6309 ("r-annotationdbi" ,r-annotationdbi)
6310 ("r-biobase" ,r-biobase)
6311 ("r-biocgenerics" ,r-biocgenerics)
6312 ("r-graph" ,r-graph)
6314 (home-page "https://bioconductor.org/packages/GSEABase")
6315 (synopsis "Gene set enrichment data structures and methods")
6317 "This package provides classes and methods to support @dfn{Gene Set
6318 Enrichment Analysis} (GSEA).")
6319 (license license:artistic2.0)))
6321 (define-public r-category
6328 (uri (bioconductor-uri "Category" version))
6331 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6332 (properties `((upstream-name . "Category")))
6333 (build-system r-build-system)
6335 `(("r-annotate" ,r-annotate)
6336 ("r-annotationdbi" ,r-annotationdbi)
6337 ("r-biobase" ,r-biobase)
6338 ("r-biocgenerics" ,r-biocgenerics)
6339 ("r-genefilter" ,r-genefilter)
6340 ("r-graph" ,r-graph)
6341 ("r-gseabase" ,r-gseabase)
6342 ("r-matrix" ,r-matrix)
6345 (home-page "https://bioconductor.org/packages/Category")
6346 (synopsis "Category analysis")
6348 "This package provides a collection of tools for performing category
6350 (license license:artistic2.0)))
6352 (define-public r-gostats
6359 (uri (bioconductor-uri "GOstats" version))
6362 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6363 (properties `((upstream-name . "GOstats")))
6364 (build-system r-build-system)
6366 `(("r-annotate" ,r-annotate)
6367 ("r-annotationdbi" ,r-annotationdbi)
6368 ("r-annotationforge" ,r-annotationforge)
6369 ("r-biobase" ,r-biobase)
6370 ("r-category" ,r-category)
6371 ("r-go-db" ,r-go-db)
6372 ("r-graph" ,r-graph)
6373 ("r-rgraphviz" ,r-rgraphviz)
6374 ("r-rbgl" ,r-rbgl)))
6375 (home-page "https://bioconductor.org/packages/GOstats")
6376 (synopsis "Tools for manipulating GO and microarrays")
6378 "This package provides a set of tools for interacting with GO and
6379 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6380 testing and other simple calculations.")
6381 (license license:artistic2.0)))
6383 (define-public r-shortread
6385 (name "r-shortread")
6390 (uri (bioconductor-uri "ShortRead" version))
6393 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6394 (properties `((upstream-name . "ShortRead")))
6395 (build-system r-build-system)
6399 `(("r-biobase" ,r-biobase)
6400 ("r-biocgenerics" ,r-biocgenerics)
6401 ("r-biocparallel" ,r-biocparallel)
6402 ("r-biostrings" ,r-biostrings)
6403 ("r-genomeinfodb" ,r-genomeinfodb)
6404 ("r-genomicalignments" ,r-genomicalignments)
6405 ("r-genomicranges" ,r-genomicranges)
6406 ("r-hwriter" ,r-hwriter)
6407 ("r-iranges" ,r-iranges)
6408 ("r-lattice" ,r-lattice)
6409 ("r-latticeextra" ,r-latticeextra)
6410 ("r-rsamtools" ,r-rsamtools)
6411 ("r-s4vectors" ,r-s4vectors)
6412 ("r-xvector" ,r-xvector)
6413 ("r-zlibbioc" ,r-zlibbioc)))
6414 (home-page "https://bioconductor.org/packages/ShortRead")
6415 (synopsis "FASTQ input and manipulation tools")
6417 "This package implements sampling, iteration, and input of FASTQ files.
6418 It includes functions for filtering and trimming reads, and for generating a
6419 quality assessment report. Data are represented as
6420 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6421 purposes. The package also contains legacy support for early single-end,
6422 ungapped alignment formats.")
6423 (license license:artistic2.0)))
6425 (define-public r-systempiper
6427 (name "r-systempiper")
6432 (uri (bioconductor-uri "systemPipeR" version))
6435 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6436 (properties `((upstream-name . "systemPipeR")))
6437 (build-system r-build-system)
6439 `(("r-annotate" ,r-annotate)
6440 ("r-batchjobs" ,r-batchjobs)
6441 ("r-biocgenerics" ,r-biocgenerics)
6442 ("r-biostrings" ,r-biostrings)
6443 ("r-deseq2" ,r-deseq2)
6444 ("r-edger" ,r-edger)
6445 ("r-genomicfeatures" ,r-genomicfeatures)
6446 ("r-genomicranges" ,r-genomicranges)
6447 ("r-ggplot2" ,r-ggplot2)
6448 ("r-go-db" ,r-go-db)
6449 ("r-gostats" ,r-gostats)
6450 ("r-limma" ,r-limma)
6451 ("r-pheatmap" ,r-pheatmap)
6452 ("r-rjson" ,r-rjson)
6453 ("r-rsamtools" ,r-rsamtools)
6454 ("r-shortread" ,r-shortread)
6455 ("r-summarizedexperiment" ,r-summarizedexperiment)
6456 ("r-variantannotation" ,r-variantannotation)))
6457 (home-page "https://github.com/tgirke/systemPipeR")
6458 (synopsis "Next generation sequencing workflow and reporting environment")
6460 "This R package provides tools for building and running automated
6461 end-to-end analysis workflows for a wide range of @dfn{next generation
6462 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6463 Important features include a uniform workflow interface across different NGS
6464 applications, automated report generation, and support for running both R and
6465 command-line software, such as NGS aligners or peak/variant callers, on local
6466 computers or compute clusters. Efficient handling of complex sample sets and
6467 experimental designs is facilitated by a consistently implemented sample
6468 annotation infrastructure.")
6469 (license license:artistic2.0)))
6471 (define-public r-grohmm
6478 (uri (bioconductor-uri "groHMM" version))
6481 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6482 (properties `((upstream-name . "groHMM")))
6483 (build-system r-build-system)
6485 `(("r-genomeinfodb" ,r-genomeinfodb)
6486 ("r-genomicalignments" ,r-genomicalignments)
6487 ("r-genomicranges" ,r-genomicranges)
6488 ("r-iranges" ,r-iranges)
6490 ("r-rtracklayer" ,r-rtracklayer)
6491 ("r-s4vectors" ,r-s4vectors)))
6492 (home-page "https://github.com/Kraus-Lab/groHMM")
6493 (synopsis "GRO-seq analysis pipeline")
6495 "This package provides a pipeline for the analysis of GRO-seq data.")
6496 (license license:gpl3+)))
6498 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6500 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6504 ;; We cannot use bioconductor-uri here because this tarball is
6505 ;; located under "data/annotation/" instead of "bioc/".
6506 (uri (string-append "https://bioconductor.org/packages/"
6507 "release/data/annotation/src/contrib"
6508 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6512 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6514 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6515 (build-system r-build-system)
6516 ;; As this package provides little more than a very large data file it
6517 ;; doesn't make sense to build substitutes.
6518 (arguments `(#:substitutable? #f))
6520 `(("r-genomicfeatures" ,r-genomicfeatures)))
6522 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6523 (synopsis "Annotation package for human genome in TxDb format")
6525 "This package provides an annotation database of Homo sapiens genome
6526 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6527 track. The database is exposed as a @code{TxDb} object.")
6528 (license license:artistic2.0)))
6530 (define-public r-sparql
6536 (uri (cran-uri "SPARQL" version))
6539 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6540 (properties `((upstream-name . "SPARQL")))
6541 (build-system r-build-system)
6543 `(("r-rcurl" ,r-rcurl)
6545 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6546 (synopsis "SPARQL client for R")
6547 (description "This package provides an interface to use SPARQL to pose
6548 SELECT or UPDATE queries to an end-point.")
6549 ;; The only license indication is found in the DESCRIPTION file,
6550 ;; which states GPL-3. So we cannot assume GPLv3+.
6551 (license license:gpl3)))
6553 (define-public vsearch
6561 "https://github.com/torognes/vsearch/archive/v"
6563 (file-name (string-append name "-" version ".tar.gz"))
6566 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6567 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6570 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6571 ;; for this in the patch.
6572 (delete-file "src/city.h")
6573 (delete-file "src/citycrc.h")
6574 (delete-file "src/city.cc")
6576 (build-system gnu-build-system)
6579 (modify-phases %standard-phases
6580 (add-after 'unpack 'autogen
6581 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6585 ("cityhash" ,cityhash)))
6587 `(("autoconf" ,autoconf)
6588 ("automake" ,automake)))
6589 (synopsis "Sequence search tools for metagenomics")
6591 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6592 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6593 masking. The tool takes advantage of parallelism in the form of SIMD
6594 vectorization as well as multiple threads to perform accurate alignments at
6595 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6596 Needleman-Wunsch).")
6597 (home-page "https://github.com/torognes/vsearch")
6598 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6600 (supported-systems '("x86_64-linux"))
6601 ;; Dual licensed; also includes public domain source.
6602 (license (list license:gpl3 license:bsd-2))))
6604 (define-public pardre
6607 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6612 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6616 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6617 (build-system gnu-build-system)
6619 `(#:tests? #f ; no tests included
6621 (modify-phases %standard-phases
6624 (lambda* (#:key outputs #:allow-other-keys)
6625 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6626 (install-file "ParDRe" bin)
6629 `(("openmpi" ,openmpi)
6631 (synopsis "Parallel tool to remove duplicate DNA reads")
6633 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6634 Duplicate reads can be seen as identical or nearly identical sequences with
6635 some mismatches. This tool lets users avoid the analysis of unnecessary
6636 reads, reducing the time of subsequent procedures with the
6637 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6638 in order to exploit the parallel capabilities of multicore clusters. It is
6639 faster than multithreaded counterparts (end of 2015) for the same number of
6640 cores and, thanks to the message-passing technology, it can be executed on
6642 (home-page "https://sourceforge.net/projects/pardre/")
6643 (license license:gpl3+)))
6645 (define-public ruby-bio-kseq
6647 (name "ruby-bio-kseq")
6652 (uri (rubygems-uri "bio-kseq" version))
6655 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6656 (build-system ruby-build-system)
6658 `(#:test-target "spec"))
6660 `(("bundler" ,bundler)
6661 ("ruby-rspec" ,ruby-rspec)
6662 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6665 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6667 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6668 FASTQ parsing code. It provides a fast iterator over sequences and their
6670 (home-page "https://github.com/gusevfe/bio-kseq")
6671 (license license:expat)))
6673 (define-public bio-locus
6680 (uri (rubygems-uri "bio-locus" version))
6683 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6684 (build-system ruby-build-system)
6686 `(("ruby-rspec" ,ruby-rspec)))
6687 (synopsis "Tool for fast querying of genome locations")
6689 "Bio-locus is a tabix-like tool for fast querying of genome
6690 locations. Many file formats in bioinformatics contain records that
6691 start with a chromosome name and a position for a SNP, or a start-end
6692 position for indels. Bio-locus allows users to store this chr+pos or
6693 chr+pos+alt information in a database.")
6694 (home-page "https://github.com/pjotrp/bio-locus")
6695 (license license:expat)))
6697 (define-public bio-blastxmlparser
6699 (name "bio-blastxmlparser")
6703 (uri (rubygems-uri "bio-blastxmlparser" version))
6706 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6707 (build-system ruby-build-system)
6709 `(("ruby-bio-logger" ,ruby-bio-logger)
6710 ("ruby-nokogiri" ,ruby-nokogiri)))
6712 `(("ruby-rspec" ,ruby-rspec)))
6713 (synopsis "Fast big data BLAST XML parser and library")
6715 "Very fast parallel big-data BLAST XML file parser which can be used as
6716 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6717 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6718 (home-page "https://github.com/pjotrp/blastxmlparser")
6719 (license license:expat)))
6721 (define-public bioruby
6728 (uri (rubygems-uri "bio" version))
6731 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6732 (build-system ruby-build-system)
6734 `(("ruby-libxml" ,ruby-libxml)))
6736 `(("which" ,which))) ; required for test phase
6739 (modify-phases %standard-phases
6740 (add-before 'build 'patch-test-command
6742 (substitute* '("test/functional/bio/test_command.rb")
6743 (("/bin/sh") (which "sh")))
6744 (substitute* '("test/functional/bio/test_command.rb")
6745 (("/bin/ls") (which "ls")))
6746 (substitute* '("test/functional/bio/test_command.rb")
6747 (("which") (which "which")))
6748 (substitute* '("test/functional/bio/test_command.rb",
6749 "test/data/command/echoarg2.sh")
6750 (("/bin/echo") (which "echo")))
6752 (synopsis "Ruby library, shell and utilities for bioinformatics")
6753 (description "BioRuby comes with a comprehensive set of Ruby development
6754 tools and libraries for bioinformatics and molecular biology. BioRuby has
6755 components for sequence analysis, pathway analysis, protein modelling and
6756 phylogenetic analysis; it supports many widely used data formats and provides
6757 easy access to databases, external programs and public web services, including
6758 BLAST, KEGG, GenBank, MEDLINE and GO.")
6759 (home-page "http://bioruby.org/")
6760 ;; Code is released under Ruby license, except for setup
6761 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6762 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6764 (define-public r-acsnminer
6766 (name "r-acsnminer")
6767 (version "0.16.8.25")
6770 (uri (cran-uri "ACSNMineR" version))
6773 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6774 (properties `((upstream-name . "ACSNMineR")))
6775 (build-system r-build-system)
6777 `(("r-ggplot2" ,r-ggplot2)
6778 ("r-gridextra" ,r-gridextra)))
6779 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6780 (synopsis "Gene enrichment analysis")
6782 "This package provides tools to compute and represent gene set enrichment
6783 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6784 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6785 enrichment can be run with hypergeometric test or Fisher exact test, and can
6786 use multiple corrections. Visualization of data can be done either by
6787 barplots or heatmaps.")
6788 (license license:gpl2+)))
6790 (define-public r-biocgenerics
6792 (name "r-biocgenerics")
6796 (uri (bioconductor-uri "BiocGenerics" version))
6799 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6801 `((upstream-name . "BiocGenerics")))
6802 (build-system r-build-system)
6803 (home-page "https://bioconductor.org/packages/BiocGenerics")
6804 (synopsis "S4 generic functions for Bioconductor")
6806 "This package provides S4 generic functions needed by many Bioconductor
6808 (license license:artistic2.0)))
6810 (define-public r-biocinstaller
6812 (name "r-biocinstaller")
6816 (uri (bioconductor-uri "BiocInstaller" version))
6819 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6821 `((upstream-name . "BiocInstaller")))
6822 (build-system r-build-system)
6823 (home-page "https://bioconductor.org/packages/BiocInstaller")
6824 (synopsis "Install Bioconductor packages")
6825 (description "This package is used to install and update R packages from
6826 Bioconductor, CRAN, and Github.")
6827 (license license:artistic2.0)))
6829 (define-public r-biocviews
6831 (name "r-biocviews")
6835 (uri (bioconductor-uri "biocViews" version))
6838 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6840 `((upstream-name . "biocViews")))
6841 (build-system r-build-system)
6843 `(("r-biobase" ,r-biobase)
6844 ("r-graph" ,r-graph)
6846 ("r-rcurl" ,r-rcurl)
6848 ("r-runit" ,r-runit)))
6849 (home-page "https://bioconductor.org/packages/biocViews")
6850 (synopsis "Bioconductor package categorization helper")
6851 (description "The purpose of biocViews is to create HTML pages that
6852 categorize packages in a Bioconductor package repository according to keywords,
6853 also known as views, in a controlled vocabulary.")
6854 (license license:artistic2.0)))
6856 (define-public r-bookdown
6862 (uri (cran-uri "bookdown" version))
6865 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6866 (build-system r-build-system)
6868 `(("r-htmltools" ,r-htmltools)
6869 ("r-knitr" ,r-knitr)
6870 ("r-rmarkdown" ,r-rmarkdown)
6871 ("r-tinytex" ,r-tinytex)
6874 ("ghc-pandoc" ,ghc-pandoc)))
6875 (home-page "https://github.com/rstudio/bookdown")
6876 (synopsis "Authoring books and technical documents with R markdown")
6877 (description "This package provides output formats and utilities for
6878 authoring books and technical documents with R Markdown.")
6879 (license license:gpl3)))
6881 (define-public r-biocstyle
6883 (name "r-biocstyle")
6887 (uri (bioconductor-uri "BiocStyle" version))
6890 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6892 `((upstream-name . "BiocStyle")))
6893 (build-system r-build-system)
6895 `(("r-bookdown" ,r-bookdown)
6896 ("r-knitr" ,r-knitr)
6897 ("r-rmarkdown" ,r-rmarkdown)
6898 ("r-yaml" ,r-yaml)))
6899 (home-page "https://bioconductor.org/packages/BiocStyle")
6900 (synopsis "Bioconductor formatting styles")
6901 (description "This package provides standard formatting styles for
6902 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6904 (license license:artistic2.0)))
6906 (define-public r-bioccheck
6908 (name "r-bioccheck")
6912 (uri (bioconductor-uri "BiocCheck" version))
6915 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6917 `((upstream-name . "BiocCheck")))
6918 (build-system r-build-system)
6921 (modify-phases %standard-phases
6922 ;; This package can be used by calling BiocCheck(<package>) from
6923 ;; within R, or by running R CMD BiocCheck <package>. This phase
6924 ;; makes sure the latter works. For this to work, the BiocCheck
6925 ;; script must be somewhere on the PATH (not the R bin directory).
6926 (add-after 'install 'install-bioccheck-subcommand
6927 (lambda* (#:key outputs #:allow-other-keys)
6928 (let* ((out (assoc-ref outputs "out"))
6929 (dest-dir (string-append out "/bin"))
6931 (string-append out "/site-library/BiocCheck/script/")))
6933 (symlink (string-append script-dir "/checkBadDeps.R")
6934 (string-append dest-dir "/checkBadDeps.R"))
6935 (symlink (string-append script-dir "/BiocCheck")
6936 (string-append dest-dir "/BiocCheck")))
6939 `(("r-codetools" ,r-codetools)
6940 ("r-graph" ,r-graph)
6942 ("r-optparse" ,r-optparse)
6943 ("r-biocinstaller" ,r-biocinstaller)
6944 ("r-biocviews" ,r-biocviews)
6945 ("r-stringdist" ,r-stringdist)))
6946 (home-page "https://bioconductor.org/packages/BiocCheck")
6947 (synopsis "Executes Bioconductor-specific package checks")
6948 (description "This package contains tools to perform additional quality
6949 checks on R packages that are to be submitted to the Bioconductor repository.")
6950 (license license:artistic2.0)))
6952 (define-public r-getopt
6959 (uri (cran-uri "getopt" version))
6962 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
6963 (build-system r-build-system)
6964 (home-page "https://github.com/trevorld/getopt")
6965 (synopsis "Command-line option processor for R")
6967 "This package is designed to be used with Rscript to write shebang
6968 scripts that accept short and long options. Many users will prefer to
6969 use the packages @code{optparse} or @code{argparse} which add extra
6970 features like automatically generated help options and usage texts,
6971 support for default values, positional argument support, etc.")
6972 (license license:gpl2+)))
6974 (define-public r-optparse
6981 (uri (cran-uri "optparse" version))
6984 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6985 (build-system r-build-system)
6987 `(("r-getopt" ,r-getopt)))
6989 "https://github.com/trevorld/optparse")
6990 (synopsis "Command line option parser")
6992 "This package provides a command line parser inspired by Python's
6993 @code{optparse} library to be used with Rscript to write shebang scripts
6994 that accept short and long options.")
6995 (license license:gpl2+)))
6997 (define-public r-dnacopy
7003 (uri (bioconductor-uri "DNAcopy" version))
7006 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
7008 `((upstream-name . "DNAcopy")))
7009 (build-system r-build-system)
7011 `(("gfortran" ,gfortran)))
7012 (home-page "https://bioconductor.org/packages/DNAcopy")
7013 (synopsis "Implementation of a circular binary segmentation algorithm")
7014 (description "This package implements the circular binary segmentation (CBS)
7015 algorithm to segment DNA copy number data and identify genomic regions with
7016 abnormal copy number.")
7017 (license license:gpl2+)))
7019 (define-public r-s4vectors
7021 (name "r-s4vectors")
7025 (uri (bioconductor-uri "S4Vectors" version))
7028 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7030 `((upstream-name . "S4Vectors")))
7031 (build-system r-build-system)
7033 `(("r-biocgenerics" ,r-biocgenerics)))
7034 (home-page "https://bioconductor.org/packages/S4Vectors")
7035 (synopsis "S4 implementation of vectors and lists")
7037 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7038 classes and a set of generic functions that extend the semantic of ordinary
7039 vectors and lists in R. Package developers can easily implement vector-like
7040 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7041 In addition, a few low-level concrete subclasses of general interest (e.g.
7042 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7043 S4Vectors package itself.")
7044 (license license:artistic2.0)))
7046 (define-public r-seqinr
7053 (uri (cran-uri "seqinr" version))
7056 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7057 (build-system r-build-system)
7059 `(("r-ade4" ,r-ade4)
7060 ("r-segmented" ,r-segmented)))
7063 (home-page "http://seqinr.r-forge.r-project.org/")
7064 (synopsis "Biological sequences retrieval and analysis")
7066 "This package provides tools for exploratory data analysis and data
7067 visualization of biological sequence (DNA and protein) data. It also includes
7068 utilities for sequence data management under the ACNUC system.")
7069 (license license:gpl2+)))
7071 (define-public r-iranges
7077 (uri (bioconductor-uri "IRanges" version))
7080 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7082 `((upstream-name . "IRanges")))
7083 (build-system r-build-system)
7085 `(("r-biocgenerics" ,r-biocgenerics)
7086 ("r-s4vectors" ,r-s4vectors)))
7087 (home-page "https://bioconductor.org/packages/IRanges")
7088 (synopsis "Infrastructure for manipulating intervals on sequences")
7090 "This package provides efficient low-level and highly reusable S4 classes
7091 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7092 generally, data that can be organized sequentially (formally defined as
7093 @code{Vector} objects), as well as views on these @code{Vector} objects.
7094 Efficient list-like classes are also provided for storing big collections of
7095 instances of the basic classes. All classes in the package use consistent
7096 naming and share the same rich and consistent \"Vector API\" as much as
7098 (license license:artistic2.0)))
7100 (define-public r-genomeinfodbdata
7102 (name "r-genomeinfodbdata")
7106 ;; We cannot use bioconductor-uri here because this tarball is
7107 ;; located under "data/annotation/" instead of "bioc/".
7108 (uri (string-append "https://bioconductor.org/packages/release/"
7109 "data/annotation/src/contrib/GenomeInfoDbData_"
7113 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7115 `((upstream-name . "GenomeInfoDbData")))
7116 (build-system r-build-system)
7117 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7118 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7119 (description "This package contains data for mapping between NCBI taxonomy
7120 ID and species. It is used by functions in the GenomeInfoDb package.")
7121 (license license:artistic2.0)))
7123 (define-public r-genomeinfodb
7125 (name "r-genomeinfodb")
7129 (uri (bioconductor-uri "GenomeInfoDb" version))
7132 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7134 `((upstream-name . "GenomeInfoDb")))
7135 (build-system r-build-system)
7137 `(("r-biocgenerics" ,r-biocgenerics)
7138 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7139 ("r-iranges" ,r-iranges)
7140 ("r-rcurl" ,r-rcurl)
7141 ("r-s4vectors" ,r-s4vectors)))
7142 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7143 (synopsis "Utilities for manipulating chromosome identifiers")
7145 "This package contains data and functions that define and allow
7146 translation between different chromosome sequence naming conventions (e.g.,
7147 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7148 names in their natural, rather than lexicographic, order.")
7149 (license license:artistic2.0)))
7151 (define-public r-edger
7157 (uri (bioconductor-uri "edgeR" version))
7160 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7161 (properties `((upstream-name . "edgeR")))
7162 (build-system r-build-system)
7164 `(("r-limma" ,r-limma)
7165 ("r-locfit" ,r-locfit)
7167 ("r-statmod" ,r-statmod))) ;for estimateDisp
7168 (home-page "http://bioinf.wehi.edu.au/edgeR")
7169 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7170 (description "This package can do differential expression analysis of
7171 RNA-seq expression profiles with biological replication. It implements a range
7172 of statistical methodology based on the negative binomial distributions,
7173 including empirical Bayes estimation, exact tests, generalized linear models
7174 and quasi-likelihood tests. It be applied to differential signal analysis of
7175 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7177 (license license:gpl2+)))
7179 (define-public r-variantannotation
7181 (name "r-variantannotation")
7185 (uri (bioconductor-uri "VariantAnnotation" version))
7188 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7190 `((upstream-name . "VariantAnnotation")))
7194 `(("r-annotationdbi" ,r-annotationdbi)
7195 ("r-biobase" ,r-biobase)
7196 ("r-biocgenerics" ,r-biocgenerics)
7197 ("r-biostrings" ,r-biostrings)
7198 ("r-bsgenome" ,r-bsgenome)
7200 ("r-genomeinfodb" ,r-genomeinfodb)
7201 ("r-genomicfeatures" ,r-genomicfeatures)
7202 ("r-genomicranges" ,r-genomicranges)
7203 ("r-iranges" ,r-iranges)
7204 ("r-summarizedexperiment" ,r-summarizedexperiment)
7205 ("r-rsamtools" ,r-rsamtools)
7206 ("r-rtracklayer" ,r-rtracklayer)
7207 ("r-s4vectors" ,r-s4vectors)
7208 ("r-xvector" ,r-xvector)
7209 ("r-zlibbioc" ,r-zlibbioc)))
7210 (build-system r-build-system)
7211 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7212 (synopsis "Package for annotation of genetic variants")
7213 (description "This R package can annotate variants, compute amino acid
7214 coding changes and predict coding outcomes.")
7215 (license license:artistic2.0)))
7217 (define-public r-limma
7223 (uri (bioconductor-uri "limma" version))
7226 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7227 (build-system r-build-system)
7228 (home-page "http://bioinf.wehi.edu.au/limma")
7229 (synopsis "Package for linear models for microarray and RNA-seq data")
7230 (description "This package can be used for the analysis of gene expression
7231 studies, especially the use of linear models for analysing designed experiments
7232 and the assessment of differential expression. The analysis methods apply to
7233 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7234 (license license:gpl2+)))
7236 (define-public r-xvector
7242 (uri (bioconductor-uri "XVector" version))
7245 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7247 `((upstream-name . "XVector")))
7248 (build-system r-build-system)
7251 (modify-phases %standard-phases
7252 (add-after 'unpack 'use-system-zlib
7254 (substitute* "DESCRIPTION"
7255 (("zlibbioc, ") ""))
7256 (substitute* "NAMESPACE"
7257 (("import\\(zlibbioc\\)") ""))
7262 `(("r-biocgenerics" ,r-biocgenerics)
7263 ("r-iranges" ,r-iranges)
7264 ("r-s4vectors" ,r-s4vectors)))
7265 (home-page "https://bioconductor.org/packages/XVector")
7266 (synopsis "Representation and manpulation of external sequences")
7268 "This package provides memory efficient S4 classes for storing sequences
7269 \"externally\" (behind an R external pointer, or on disk).")
7270 (license license:artistic2.0)))
7272 (define-public r-genomicranges
7274 (name "r-genomicranges")
7278 (uri (bioconductor-uri "GenomicRanges" version))
7281 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7283 `((upstream-name . "GenomicRanges")))
7284 (build-system r-build-system)
7286 `(("r-biocgenerics" ,r-biocgenerics)
7287 ("r-genomeinfodb" ,r-genomeinfodb)
7288 ("r-iranges" ,r-iranges)
7289 ("r-s4vectors" ,r-s4vectors)
7290 ("r-xvector" ,r-xvector)))
7291 (home-page "https://bioconductor.org/packages/GenomicRanges")
7292 (synopsis "Representation and manipulation of genomic intervals")
7294 "This package provides tools to efficiently represent and manipulate
7295 genomic annotations and alignments is playing a central role when it comes to
7296 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7297 GenomicRanges package defines general purpose containers for storing and
7298 manipulating genomic intervals and variables defined along a genome.")
7299 (license license:artistic2.0)))
7301 (define-public r-biobase
7307 (uri (bioconductor-uri "Biobase" version))
7310 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7312 `((upstream-name . "Biobase")))
7313 (build-system r-build-system)
7315 `(("r-biocgenerics" ,r-biocgenerics)))
7316 (home-page "https://bioconductor.org/packages/Biobase")
7317 (synopsis "Base functions for Bioconductor")
7319 "This package provides functions that are needed by many other packages
7320 on Bioconductor or which replace R functions.")
7321 (license license:artistic2.0)))
7323 (define-public r-annotationdbi
7325 (name "r-annotationdbi")
7329 (uri (bioconductor-uri "AnnotationDbi" version))
7332 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7334 `((upstream-name . "AnnotationDbi")))
7335 (build-system r-build-system)
7337 `(("r-biobase" ,r-biobase)
7338 ("r-biocgenerics" ,r-biocgenerics)
7340 ("r-iranges" ,r-iranges)
7341 ("r-rsqlite" ,r-rsqlite)
7342 ("r-s4vectors" ,r-s4vectors)))
7343 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7344 (synopsis "Annotation database interface")
7346 "This package provides user interface and database connection code for
7347 annotation data packages using SQLite data storage.")
7348 (license license:artistic2.0)))
7350 (define-public r-biomart
7356 (uri (bioconductor-uri "biomaRt" version))
7359 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7361 `((upstream-name . "biomaRt")))
7362 (build-system r-build-system)
7364 `(("r-annotationdbi" ,r-annotationdbi)
7366 ("r-progress" ,r-progress)
7367 ("r-rcurl" ,r-rcurl)
7368 ("r-stringr" ,r-stringr)
7370 (home-page "https://bioconductor.org/packages/biomaRt")
7371 (synopsis "Interface to BioMart databases")
7373 "biomaRt provides an interface to a growing collection of databases
7374 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7375 package enables retrieval of large amounts of data in a uniform way without
7376 the need to know the underlying database schemas or write complex SQL queries.
7377 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7378 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7379 users direct access to a diverse set of data and enable a wide range of
7380 powerful online queries from gene annotation to database mining.")
7381 (license license:artistic2.0)))
7383 (define-public r-biocparallel
7385 (name "r-biocparallel")
7389 (uri (bioconductor-uri "BiocParallel" version))
7392 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7394 `((upstream-name . "BiocParallel")))
7395 (build-system r-build-system)
7397 `(("r-futile-logger" ,r-futile-logger)
7400 (home-page "https://bioconductor.org/packages/BiocParallel")
7401 (synopsis "Bioconductor facilities for parallel evaluation")
7403 "This package provides modified versions and novel implementation of
7404 functions for parallel evaluation, tailored to use with Bioconductor
7406 (license (list license:gpl2+ license:gpl3+))))
7408 (define-public r-biostrings
7410 (name "r-biostrings")
7414 (uri (bioconductor-uri "Biostrings" version))
7417 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7419 `((upstream-name . "Biostrings")))
7420 (build-system r-build-system)
7422 `(("r-biocgenerics" ,r-biocgenerics)
7423 ("r-iranges" ,r-iranges)
7424 ("r-s4vectors" ,r-s4vectors)
7425 ("r-xvector" ,r-xvector)))
7426 (home-page "https://bioconductor.org/packages/Biostrings")
7427 (synopsis "String objects and algorithms for biological sequences")
7429 "This package provides memory efficient string containers, string
7430 matching algorithms, and other utilities, for fast manipulation of large
7431 biological sequences or sets of sequences.")
7432 (license license:artistic2.0)))
7434 (define-public r-rsamtools
7436 (name "r-rsamtools")
7440 (uri (bioconductor-uri "Rsamtools" version))
7443 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7445 `((upstream-name . "Rsamtools")))
7446 (build-system r-build-system)
7449 (modify-phases %standard-phases
7450 (add-after 'unpack 'use-system-zlib
7452 (substitute* "DESCRIPTION"
7453 (("zlibbioc, ") ""))
7454 (substitute* "NAMESPACE"
7455 (("import\\(zlibbioc\\)") ""))
7460 `(("r-biocgenerics" ,r-biocgenerics)
7461 ("r-biocparallel" ,r-biocparallel)
7462 ("r-biostrings" ,r-biostrings)
7463 ("r-bitops" ,r-bitops)
7464 ("r-genomeinfodb" ,r-genomeinfodb)
7465 ("r-genomicranges" ,r-genomicranges)
7466 ("r-iranges" ,r-iranges)
7467 ("r-s4vectors" ,r-s4vectors)
7468 ("r-xvector" ,r-xvector)))
7469 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7470 (synopsis "Interface to samtools, bcftools, and tabix")
7472 "This package provides an interface to the 'samtools', 'bcftools', and
7473 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7474 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7476 (license license:expat)))
7478 (define-public r-delayedarray
7480 (name "r-delayedarray")
7484 (uri (bioconductor-uri "DelayedArray" version))
7487 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7489 `((upstream-name . "DelayedArray")))
7490 (build-system r-build-system)
7492 `(("r-biocgenerics" ,r-biocgenerics)
7493 ("r-s4vectors" ,r-s4vectors)
7494 ("r-iranges" ,r-iranges)
7495 ("r-matrixstats" ,r-matrixstats)))
7496 (home-page "https://bioconductor.org/packages/DelayedArray")
7497 (synopsis "Delayed operations on array-like objects")
7499 "Wrapping an array-like object (typically an on-disk object) in a
7500 @code{DelayedArray} object allows one to perform common array operations on it
7501 without loading the object in memory. In order to reduce memory usage and
7502 optimize performance, operations on the object are either delayed or executed
7503 using a block processing mechanism. Note that this also works on in-memory
7504 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7505 @code{Matrix} objects, and ordinary arrays and data frames.")
7506 (license license:artistic2.0)))
7508 (define-public r-summarizedexperiment
7510 (name "r-summarizedexperiment")
7514 (uri (bioconductor-uri "SummarizedExperiment" version))
7517 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7519 `((upstream-name . "SummarizedExperiment")))
7520 (build-system r-build-system)
7522 `(("r-biobase" ,r-biobase)
7523 ("r-biocgenerics" ,r-biocgenerics)
7524 ("r-delayedarray" ,r-delayedarray)
7525 ("r-genomeinfodb" ,r-genomeinfodb)
7526 ("r-genomicranges" ,r-genomicranges)
7527 ("r-iranges" ,r-iranges)
7528 ("r-matrix" ,r-matrix)
7529 ("r-s4vectors" ,r-s4vectors)))
7530 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7531 (synopsis "Container for representing genomic ranges by sample")
7533 "The SummarizedExperiment container contains one or more assays, each
7534 represented by a matrix-like object of numeric or other mode. The rows
7535 typically represent genomic ranges of interest and the columns represent
7537 (license license:artistic2.0)))
7539 (define-public r-genomicalignments
7541 (name "r-genomicalignments")
7545 (uri (bioconductor-uri "GenomicAlignments" version))
7548 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7550 `((upstream-name . "GenomicAlignments")))
7551 (build-system r-build-system)
7553 `(("r-biocgenerics" ,r-biocgenerics)
7554 ("r-biocparallel" ,r-biocparallel)
7555 ("r-biostrings" ,r-biostrings)
7556 ("r-genomeinfodb" ,r-genomeinfodb)
7557 ("r-genomicranges" ,r-genomicranges)
7558 ("r-iranges" ,r-iranges)
7559 ("r-rsamtools" ,r-rsamtools)
7560 ("r-s4vectors" ,r-s4vectors)
7561 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7562 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7563 (synopsis "Representation and manipulation of short genomic alignments")
7565 "This package provides efficient containers for storing and manipulating
7566 short genomic alignments (typically obtained by aligning short reads to a
7567 reference genome). This includes read counting, computing the coverage,
7568 junction detection, and working with the nucleotide content of the
7570 (license license:artistic2.0)))
7572 (define-public r-rtracklayer
7574 (name "r-rtracklayer")
7578 (uri (bioconductor-uri "rtracklayer" version))
7581 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7582 (build-system r-build-system)
7585 (modify-phases %standard-phases
7586 (add-after 'unpack 'use-system-zlib
7588 (substitute* "DESCRIPTION"
7589 ((" zlibbioc,") ""))
7590 (substitute* "NAMESPACE"
7591 (("import\\(zlibbioc\\)") ""))
7596 `(("r-biocgenerics" ,r-biocgenerics)
7597 ("r-biostrings" ,r-biostrings)
7598 ("r-genomeinfodb" ,r-genomeinfodb)
7599 ("r-genomicalignments" ,r-genomicalignments)
7600 ("r-genomicranges" ,r-genomicranges)
7601 ("r-iranges" ,r-iranges)
7602 ("r-rcurl" ,r-rcurl)
7603 ("r-rsamtools" ,r-rsamtools)
7604 ("r-s4vectors" ,r-s4vectors)
7606 ("r-xvector" ,r-xvector)))
7607 (home-page "https://bioconductor.org/packages/rtracklayer")
7608 (synopsis "R interface to genome browsers and their annotation tracks")
7610 "rtracklayer is an extensible framework for interacting with multiple
7611 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7612 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7613 built-in). The user may export/import tracks to/from the supported browsers,
7614 as well as query and modify the browser state, such as the current viewport.")
7615 (license license:artistic2.0)))
7617 (define-public r-genomicfeatures
7619 (name "r-genomicfeatures")
7623 (uri (bioconductor-uri "GenomicFeatures" version))
7626 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7628 `((upstream-name . "GenomicFeatures")))
7629 (build-system r-build-system)
7631 `(("r-annotationdbi" ,r-annotationdbi)
7632 ("r-biobase" ,r-biobase)
7633 ("r-biocgenerics" ,r-biocgenerics)
7634 ("r-biomart" ,r-biomart)
7635 ("r-biostrings" ,r-biostrings)
7637 ("r-genomeinfodb" ,r-genomeinfodb)
7638 ("r-genomicranges" ,r-genomicranges)
7639 ("r-iranges" ,r-iranges)
7640 ("r-rcurl" ,r-rcurl)
7641 ("r-rsqlite" ,r-rsqlite)
7642 ("r-rmysql" ,r-rmysql)
7643 ("r-rtracklayer" ,r-rtracklayer)
7644 ("r-s4vectors" ,r-s4vectors)
7645 ("r-xvector" ,r-xvector)))
7646 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7647 (synopsis "Tools for working with transcript centric annotations")
7649 "This package provides a set of tools and methods for making and
7650 manipulating transcript centric annotations. With these tools the user can
7651 easily download the genomic locations of the transcripts, exons and cds of a
7652 given organism, from either the UCSC Genome Browser or a BioMart
7653 database (more sources will be supported in the future). This information is
7654 then stored in a local database that keeps track of the relationship between
7655 transcripts, exons, cds and genes. Flexible methods are provided for
7656 extracting the desired features in a convenient format.")
7657 (license license:artistic2.0)))
7659 (define-public r-go-db
7665 (uri (string-append "https://www.bioconductor.org/packages/"
7666 "release/data/annotation/src/contrib/GO.db_"
7670 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7672 `((upstream-name . "GO.db")))
7673 (build-system r-build-system)
7675 `(("r-annotationdbi" ,r-annotationdbi)))
7676 (home-page "https://bioconductor.org/packages/GO.db")
7677 (synopsis "Annotation maps describing the entire Gene Ontology")
7679 "The purpose of this GO.db annotation package is to provide detailed
7680 information about the latest version of the Gene Ontologies.")
7681 (license license:artistic2.0)))
7683 (define-public r-graph
7689 (uri (bioconductor-uri "graph" version))
7692 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7693 (build-system r-build-system)
7695 `(("r-biocgenerics" ,r-biocgenerics)))
7696 (home-page "https://bioconductor.org/packages/graph")
7697 (synopsis "Handle graph data structures in R")
7699 "This package implements some simple graph handling capabilities for R.")
7700 (license license:artistic2.0)))
7702 (define-public r-topgo
7708 (uri (bioconductor-uri "topGO" version))
7711 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7713 `((upstream-name . "topGO")))
7714 (build-system r-build-system)
7716 `(("r-annotationdbi" ,r-annotationdbi)
7718 ("r-biobase" ,r-biobase)
7719 ("r-biocgenerics" ,r-biocgenerics)
7720 ("r-go-db" ,r-go-db)
7721 ("r-graph" ,r-graph)
7722 ("r-lattice" ,r-lattice)
7723 ("r-matrixstats" ,r-matrixstats)
7724 ("r-sparsem" ,r-sparsem)))
7725 (home-page "https://bioconductor.org/packages/topGO")
7726 (synopsis "Enrichment analysis for gene ontology")
7728 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7729 terms while accounting for the topology of the GO graph. Different test
7730 statistics and different methods for eliminating local similarities and
7731 dependencies between GO terms can be implemented and applied.")
7732 ;; Any version of the LGPL applies.
7733 (license license:lgpl2.1+)))
7735 (define-public r-bsgenome
7741 (uri (bioconductor-uri "BSgenome" version))
7744 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7746 `((upstream-name . "BSgenome")))
7747 (build-system r-build-system)
7749 `(("r-biocgenerics" ,r-biocgenerics)
7750 ("r-biostrings" ,r-biostrings)
7751 ("r-genomeinfodb" ,r-genomeinfodb)
7752 ("r-genomicranges" ,r-genomicranges)
7753 ("r-iranges" ,r-iranges)
7754 ("r-rsamtools" ,r-rsamtools)
7755 ("r-rtracklayer" ,r-rtracklayer)
7756 ("r-s4vectors" ,r-s4vectors)
7757 ("r-xvector" ,r-xvector)))
7758 (home-page "https://bioconductor.org/packages/BSgenome")
7759 (synopsis "Infrastructure for Biostrings-based genome data packages")
7761 "This package provides infrastructure shared by all Biostrings-based
7762 genome data packages and support for efficient SNP representation.")
7763 (license license:artistic2.0)))
7765 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7767 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7771 ;; We cannot use bioconductor-uri here because this tarball is
7772 ;; located under "data/annotation/" instead of "bioc/".
7773 (uri (string-append "https://www.bioconductor.org/packages/"
7774 "release/data/annotation/src/contrib/"
7775 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7779 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7781 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7782 (build-system r-build-system)
7783 ;; As this package provides little more than a very large data file it
7784 ;; doesn't make sense to build substitutes.
7785 (arguments `(#:substitutable? #f))
7787 `(("r-bsgenome" ,r-bsgenome)))
7789 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7790 (synopsis "Full genome sequences for Homo sapiens")
7792 "This package provides full genome sequences for Homo sapiens from
7793 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7794 (license license:artistic2.0)))
7796 (define-public r-impute
7802 (uri (bioconductor-uri "impute" version))
7805 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7807 `(("gfortran" ,gfortran)))
7808 (build-system r-build-system)
7809 (home-page "https://bioconductor.org/packages/impute")
7810 (synopsis "Imputation for microarray data")
7812 "This package provides a function to impute missing gene expression
7813 microarray data, using nearest neighbor averaging.")
7814 (license license:gpl2+)))
7816 (define-public r-seqpattern
7818 (name "r-seqpattern")
7822 (uri (bioconductor-uri "seqPattern" version))
7825 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7827 `((upstream-name . "seqPattern")))
7828 (build-system r-build-system)
7830 `(("r-biostrings" ,r-biostrings)
7831 ("r-genomicranges" ,r-genomicranges)
7832 ("r-iranges" ,r-iranges)
7833 ("r-kernsmooth" ,r-kernsmooth)
7834 ("r-plotrix" ,r-plotrix)))
7835 (home-page "https://bioconductor.org/packages/seqPattern")
7836 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7838 "This package provides tools to visualize oligonucleotide patterns and
7839 sequence motif occurrences across a large set of sequences centred at a common
7840 reference point and sorted by a user defined feature.")
7841 (license license:gpl3+)))
7843 (define-public r-genomation
7845 (name "r-genomation")
7849 (uri (bioconductor-uri "genomation" version))
7852 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7853 (build-system r-build-system)
7855 `(("r-biostrings" ,r-biostrings)
7856 ("r-bsgenome" ,r-bsgenome)
7857 ("r-data-table" ,r-data-table)
7858 ("r-genomeinfodb" ,r-genomeinfodb)
7859 ("r-genomicalignments" ,r-genomicalignments)
7860 ("r-genomicranges" ,r-genomicranges)
7861 ("r-ggplot2" ,r-ggplot2)
7862 ("r-gridbase" ,r-gridbase)
7863 ("r-impute" ,r-impute)
7864 ("r-iranges" ,r-iranges)
7865 ("r-matrixstats" ,r-matrixstats)
7866 ("r-plotrix" ,r-plotrix)
7869 ("r-readr" ,r-readr)
7870 ("r-reshape2" ,r-reshape2)
7871 ("r-rsamtools" ,r-rsamtools)
7872 ("r-rtracklayer" ,r-rtracklayer)
7873 ("r-runit" ,r-runit)
7874 ("r-s4vectors" ,r-s4vectors)
7875 ("r-seqpattern" ,r-seqpattern)))
7876 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7877 (synopsis "Summary, annotation and visualization of genomic data")
7879 "This package provides a package for summary and annotation of genomic
7880 intervals. Users can visualize and quantify genomic intervals over
7881 pre-defined functional regions, such as promoters, exons, introns, etc. The
7882 genomic intervals represent regions with a defined chromosome position, which
7883 may be associated with a score, such as aligned reads from HT-seq experiments,
7884 TF binding sites, methylation scores, etc. The package can use any tabular
7885 genomic feature data as long as it has minimal information on the locations of
7886 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7887 (license license:artistic2.0)))
7889 (define-public r-genomationdata
7891 (name "r-genomationdata")
7895 ;; We cannot use bioconductor-uri here because this tarball is
7896 ;; located under "data/annotation/" instead of "bioc/".
7897 (uri (string-append "https://bioconductor.org/packages/"
7898 "release/data/experiment/src/contrib/"
7899 "genomationData_" version ".tar.gz"))
7902 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7903 (build-system r-build-system)
7904 ;; As this package provides little more than large data files, it doesn't
7905 ;; make sense to build substitutes.
7906 (arguments `(#:substitutable? #f))
7908 `(("r-knitr" ,r-knitr)))
7909 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7910 (synopsis "Experimental data for use with the genomation package")
7912 "This package contains experimental genetic data for use with the
7913 genomation package. Included are Chip Seq, Methylation and Cage data,
7914 downloaded from Encode.")
7915 (license license:gpl3+)))
7917 (define-public r-org-hs-eg-db
7919 (name "r-org-hs-eg-db")
7923 ;; We cannot use bioconductor-uri here because this tarball is
7924 ;; located under "data/annotation/" instead of "bioc/".
7925 (uri (string-append "https://www.bioconductor.org/packages/"
7926 "release/data/annotation/src/contrib/"
7927 "org.Hs.eg.db_" version ".tar.gz"))
7930 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7932 `((upstream-name . "org.Hs.eg.db")))
7933 (build-system r-build-system)
7935 `(("r-annotationdbi" ,r-annotationdbi)))
7936 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7937 (synopsis "Genome wide annotation for Human")
7939 "This package contains genome-wide annotations for Human, primarily based
7940 on mapping using Entrez Gene identifiers.")
7941 (license license:artistic2.0)))
7943 (define-public r-org-ce-eg-db
7945 (name "r-org-ce-eg-db")
7949 ;; We cannot use bioconductor-uri here because this tarball is
7950 ;; located under "data/annotation/" instead of "bioc/".
7951 (uri (string-append "https://www.bioconductor.org/packages/"
7952 "release/data/annotation/src/contrib/"
7953 "org.Ce.eg.db_" version ".tar.gz"))
7956 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7958 `((upstream-name . "org.Ce.eg.db")))
7959 (build-system r-build-system)
7961 `(("r-annotationdbi" ,r-annotationdbi)))
7962 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7963 (synopsis "Genome wide annotation for Worm")
7965 "This package provides mappings from Entrez gene identifiers to various
7966 annotations for the genome of the model worm Caenorhabditis elegans.")
7967 (license license:artistic2.0)))
7969 (define-public r-org-dm-eg-db
7971 (name "r-org-dm-eg-db")
7975 ;; We cannot use bioconductor-uri here because this tarball is
7976 ;; located under "data/annotation/" instead of "bioc/".
7977 (uri (string-append "https://www.bioconductor.org/packages/"
7978 "release/data/annotation/src/contrib/"
7979 "org.Dm.eg.db_" version ".tar.gz"))
7982 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
7984 `((upstream-name . "org.Dm.eg.db")))
7985 (build-system r-build-system)
7987 `(("r-annotationdbi" ,r-annotationdbi)))
7988 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7989 (synopsis "Genome wide annotation for Fly")
7991 "This package provides mappings from Entrez gene identifiers to various
7992 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7993 (license license:artistic2.0)))
7995 (define-public r-org-mm-eg-db
7997 (name "r-org-mm-eg-db")
8001 ;; We cannot use bioconductor-uri here because this tarball is
8002 ;; located under "data/annotation/" instead of "bioc/".
8003 (uri (string-append "https://www.bioconductor.org/packages/"
8004 "release/data/annotation/src/contrib/"
8005 "org.Mm.eg.db_" version ".tar.gz"))
8008 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8010 `((upstream-name . "org.Mm.eg.db")))
8011 (build-system r-build-system)
8013 `(("r-annotationdbi" ,r-annotationdbi)))
8014 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8015 (synopsis "Genome wide annotation for Mouse")
8017 "This package provides mappings from Entrez gene identifiers to various
8018 annotations for the genome of the model mouse Mus musculus.")
8019 (license license:artistic2.0)))
8021 (define-public r-seqlogo
8028 (uri (bioconductor-uri "seqLogo" version))
8031 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
8032 (properties `((upstream-name . "seqLogo")))
8033 (build-system r-build-system)
8034 (home-page "https://bioconductor.org/packages/seqLogo")
8035 (synopsis "Sequence logos for DNA sequence alignments")
8037 "seqLogo takes the position weight matrix of a DNA sequence motif and
8038 plots the corresponding sequence logo as introduced by Schneider and
8040 (license license:lgpl2.0+)))
8042 (define-public r-bsgenome-hsapiens-ucsc-hg19
8044 (name "r-bsgenome-hsapiens-ucsc-hg19")
8048 ;; We cannot use bioconductor-uri here because this tarball is
8049 ;; located under "data/annotation/" instead of "bioc/".
8050 (uri (string-append "https://www.bioconductor.org/packages/"
8051 "release/data/annotation/src/contrib/"
8052 "BSgenome.Hsapiens.UCSC.hg19_"
8056 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8058 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8059 (build-system r-build-system)
8060 ;; As this package provides little more than a very large data file it
8061 ;; doesn't make sense to build substitutes.
8062 (arguments `(#:substitutable? #f))
8064 `(("r-bsgenome" ,r-bsgenome)))
8066 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8067 (synopsis "Full genome sequences for Homo sapiens")
8069 "This package provides full genome sequences for Homo sapiens as provided
8070 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8071 (license license:artistic2.0)))
8073 (define-public r-bsgenome-mmusculus-ucsc-mm9
8075 (name "r-bsgenome-mmusculus-ucsc-mm9")
8079 ;; We cannot use bioconductor-uri here because this tarball is
8080 ;; located under "data/annotation/" instead of "bioc/".
8081 (uri (string-append "https://www.bioconductor.org/packages/"
8082 "release/data/annotation/src/contrib/"
8083 "BSgenome.Mmusculus.UCSC.mm9_"
8087 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8089 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8090 (build-system r-build-system)
8091 ;; As this package provides little more than a very large data file it
8092 ;; doesn't make sense to build substitutes.
8093 (arguments `(#:substitutable? #f))
8095 `(("r-bsgenome" ,r-bsgenome)))
8097 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8098 (synopsis "Full genome sequences for Mouse")
8100 "This package provides full genome sequences for Mus musculus (Mouse) as
8101 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8102 (license license:artistic2.0)))
8104 (define-public r-bsgenome-mmusculus-ucsc-mm10
8106 (name "r-bsgenome-mmusculus-ucsc-mm10")
8110 ;; We cannot use bioconductor-uri here because this tarball is
8111 ;; located under "data/annotation/" instead of "bioc/".
8112 (uri (string-append "https://www.bioconductor.org/packages/"
8113 "release/data/annotation/src/contrib/"
8114 "BSgenome.Mmusculus.UCSC.mm10_"
8118 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8120 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8121 (build-system r-build-system)
8122 ;; As this package provides little more than a very large data file it
8123 ;; doesn't make sense to build substitutes.
8124 (arguments `(#:substitutable? #f))
8126 `(("r-bsgenome" ,r-bsgenome)))
8128 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8129 (synopsis "Full genome sequences for Mouse")
8131 "This package provides full genome sequences for Mus
8132 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8133 in Biostrings objects.")
8134 (license license:artistic2.0)))
8136 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8138 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8142 ;; We cannot use bioconductor-uri here because this tarball is
8143 ;; located under "data/annotation/" instead of "bioc/".
8144 (uri (string-append "https://www.bioconductor.org/packages/"
8145 "release/data/annotation/src/contrib/"
8146 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8150 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8152 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8153 (build-system r-build-system)
8154 ;; As this package provides little more than a very large data file it
8155 ;; doesn't make sense to build substitutes.
8156 (arguments `(#:substitutable? #f))
8158 `(("r-bsgenome" ,r-bsgenome)
8159 ("r-genomicfeatures" ,r-genomicfeatures)
8160 ("r-annotationdbi" ,r-annotationdbi)))
8162 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8163 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8165 "This package loads a TxDb object, which is an R interface to
8166 prefabricated databases contained in this package. This package provides
8167 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8168 based on the knownGene track.")
8169 (license license:artistic2.0)))
8171 (define-public r-bsgenome-celegans-ucsc-ce6
8173 (name "r-bsgenome-celegans-ucsc-ce6")
8177 ;; We cannot use bioconductor-uri here because this tarball is
8178 ;; located under "data/annotation/" instead of "bioc/".
8179 (uri (string-append "https://www.bioconductor.org/packages/"
8180 "release/data/annotation/src/contrib/"
8181 "BSgenome.Celegans.UCSC.ce6_"
8185 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8187 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8188 (build-system r-build-system)
8189 ;; As this package provides little more than a very large data file it
8190 ;; doesn't make sense to build substitutes.
8191 (arguments `(#:substitutable? #f))
8193 `(("r-bsgenome" ,r-bsgenome)))
8195 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8196 (synopsis "Full genome sequences for Worm")
8198 "This package provides full genome sequences for Caenorhabditis
8199 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8201 (license license:artistic2.0)))
8203 (define-public r-bsgenome-celegans-ucsc-ce10
8205 (name "r-bsgenome-celegans-ucsc-ce10")
8209 ;; We cannot use bioconductor-uri here because this tarball is
8210 ;; located under "data/annotation/" instead of "bioc/".
8211 (uri (string-append "https://www.bioconductor.org/packages/"
8212 "release/data/annotation/src/contrib/"
8213 "BSgenome.Celegans.UCSC.ce10_"
8217 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8219 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8220 (build-system r-build-system)
8221 ;; As this package provides little more than a very large data file it
8222 ;; doesn't make sense to build substitutes.
8223 (arguments `(#:substitutable? #f))
8225 `(("r-bsgenome" ,r-bsgenome)))
8227 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8228 (synopsis "Full genome sequences for Worm")
8230 "This package provides full genome sequences for Caenorhabditis
8231 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8233 (license license:artistic2.0)))
8235 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8237 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8241 ;; We cannot use bioconductor-uri here because this tarball is
8242 ;; located under "data/annotation/" instead of "bioc/".
8243 (uri (string-append "https://www.bioconductor.org/packages/"
8244 "release/data/annotation/src/contrib/"
8245 "BSgenome.Dmelanogaster.UCSC.dm3_"
8249 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8251 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8252 (build-system r-build-system)
8253 ;; As this package provides little more than a very large data file it
8254 ;; doesn't make sense to build substitutes.
8255 (arguments `(#:substitutable? #f))
8257 `(("r-bsgenome" ,r-bsgenome)))
8259 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8260 (synopsis "Full genome sequences for Fly")
8262 "This package provides full genome sequences for Drosophila
8263 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8264 Biostrings objects.")
8265 (license license:artistic2.0)))
8267 (define-public r-motifrg
8274 (uri (bioconductor-uri "motifRG" version))
8277 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8278 (properties `((upstream-name . "motifRG")))
8279 (build-system r-build-system)
8281 `(("r-biostrings" ,r-biostrings)
8282 ("r-bsgenome" ,r-bsgenome)
8283 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8284 ("r-iranges" ,r-iranges)
8285 ("r-seqlogo" ,r-seqlogo)
8286 ("r-xvector" ,r-xvector)))
8287 (home-page "https://bioconductor.org/packages/motifRG")
8288 (synopsis "Discover motifs in high throughput sequencing data")
8290 "This package provides tools for discriminative motif discovery in high
8291 throughput genetic sequencing data sets using regression methods.")
8292 (license license:artistic2.0)))
8294 (define-public r-qtl
8301 (uri (string-append "mirror://cran/src/contrib/qtl_"
8305 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8306 (build-system r-build-system)
8307 (home-page "http://rqtl.org/")
8308 (synopsis "R package for analyzing QTL experiments in genetics")
8309 (description "R/qtl is an extension library for the R statistics
8310 system. It is used to analyze experimental crosses for identifying
8311 genes contributing to variation in quantitative traits (so-called
8312 quantitative trait loci, QTLs).
8314 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8315 identify genotyping errors, and to perform single-QTL and two-QTL,
8316 two-dimensional genome scans.")
8317 (license license:gpl3)))
8319 (define-public r-zlibbioc
8325 (uri (bioconductor-uri "zlibbioc" version))
8328 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8330 `((upstream-name . "zlibbioc")))
8331 (build-system r-build-system)
8332 (home-page "https://bioconductor.org/packages/zlibbioc")
8333 (synopsis "Provider for zlib-1.2.5 to R packages")
8334 (description "This package uses the source code of zlib-1.2.5 to create
8335 libraries for systems that do not have these available via other means.")
8336 (license license:artistic2.0)))
8338 (define-public r-r4rna
8345 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8349 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8350 (build-system r-build-system)
8352 `(("r-optparse" ,r-optparse)
8353 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8354 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8355 (synopsis "Analysis framework for RNA secondary structure")
8357 "The R4RNA package aims to be a general framework for the analysis of RNA
8358 secondary structure and comparative analysis in R.")
8359 (license license:gpl3+)))
8361 (define-public r-rhtslib
8368 (uri (bioconductor-uri "Rhtslib" version))
8371 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8372 (properties `((upstream-name . "Rhtslib")))
8373 (build-system r-build-system)
8375 `(("r-zlibbioc" ,r-zlibbioc)))
8379 `(("autoconf" ,autoconf)))
8380 (home-page "https://github.com/nhayden/Rhtslib")
8381 (synopsis "High-throughput sequencing library as an R package")
8383 "This package provides the HTSlib C library for high-throughput
8384 nucleotide sequence analysis. The package is primarily useful to developers
8385 of other R packages who wish to make use of HTSlib.")
8386 (license license:lgpl2.0+)))
8388 (define-public r-bamsignals
8390 (name "r-bamsignals")
8395 (uri (bioconductor-uri "bamsignals" version))
8398 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8399 (build-system r-build-system)
8401 `(("r-biocgenerics" ,r-biocgenerics)
8402 ("r-genomicranges" ,r-genomicranges)
8403 ("r-iranges" ,r-iranges)
8405 ("r-rhtslib" ,r-rhtslib)
8406 ("r-zlibbioc" ,r-zlibbioc)))
8409 (home-page "https://bioconductor.org/packages/bamsignals")
8410 (synopsis "Extract read count signals from bam files")
8412 "This package allows to efficiently obtain count vectors from indexed bam
8413 files. It counts the number of nucleotide sequence reads in given genomic
8414 ranges and it computes reads profiles and coverage profiles. It also handles
8416 (license license:gpl2+)))
8418 (define-public r-rcas
8424 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8426 (file-name (string-append name "-" version ".tar.gz"))
8429 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8430 (build-system r-build-system)
8432 `(("r-knitr" ,r-knitr)
8433 ("r-testthat" ,r-testthat)
8434 ;; During vignette building knitr checks that "pandoc-citeproc"
8436 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8438 `(("r-data-table" ,r-data-table)
8439 ("r-biomart" ,r-biomart)
8440 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8441 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8442 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8443 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8444 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8445 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8446 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8447 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8448 ("r-topgo" ,r-topgo)
8450 ("r-pbapply" ,r-pbapply)
8451 ("r-plotly" ,r-plotly)
8452 ("r-plotrix" ,r-plotrix)
8453 ("r-motifrg" ,r-motifrg)
8454 ("r-genomation" ,r-genomation)
8455 ("r-genomicfeatures" ,r-genomicfeatures)
8456 ("r-rtracklayer" ,r-rtracklayer)
8457 ("r-rmarkdown" ,r-rmarkdown)))
8458 (synopsis "RNA-centric annotation system")
8460 "RCAS aims to be a standalone RNA-centric annotation system that provides
8461 intuitive reports and publication-ready graphics. This package provides the R
8462 library implementing most of the pipeline's features.")
8463 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8464 (license license:artistic2.0)))
8466 (define-public rcas-web
8473 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8474 "releases/download/v" version
8475 "/rcas-web-" version ".tar.gz"))
8478 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8479 (build-system gnu-build-system)
8482 (modify-phases %standard-phases
8483 (add-after 'install 'wrap-executable
8484 (lambda* (#:key inputs outputs #:allow-other-keys)
8485 (let* ((out (assoc-ref outputs "out"))
8486 (json (assoc-ref inputs "guile-json"))
8487 (redis (assoc-ref inputs "guile-redis"))
8488 (path (string-append
8489 json "/share/guile/site/2.2:"
8490 redis "/share/guile/site/2.2")))
8491 (wrap-program (string-append out "/bin/rcas-web")
8492 `("GUILE_LOAD_PATH" ":" = (,path))
8493 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8494 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8497 `(("r-minimal" ,r-minimal)
8499 ("guile-next" ,guile-2.2)
8500 ("guile-json" ,guile-json)
8501 ("guile-redis" ,guile2.2-redis)))
8503 `(("pkg-config" ,pkg-config)))
8504 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8505 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8506 (description "This package provides a simple web interface for the
8507 @dfn{RNA-centric annotation system} (RCAS).")
8508 (license license:agpl3+)))
8510 (define-public r-mutationalpatterns
8512 (name "r-mutationalpatterns")
8517 (uri (bioconductor-uri "MutationalPatterns" version))
8520 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8521 (build-system r-build-system)
8523 `(("r-biocgenerics" ,r-biocgenerics)
8524 ("r-biostrings" ,r-biostrings)
8525 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8526 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8527 ("r-genomicranges" ,r-genomicranges)
8528 ("r-genomeinfodb" ,r-genomeinfodb)
8529 ("r-ggplot2" ,r-ggplot2)
8530 ("r-gridextra" ,r-gridextra)
8531 ("r-iranges" ,r-iranges)
8534 ("r-pracma" ,r-pracma)
8535 ("r-reshape2" ,r-reshape2)
8536 ("r-cowplot" ,r-cowplot)
8537 ("r-ggdendro" ,r-ggdendro)
8538 ("r-s4vectors" ,r-s4vectors)
8539 ("r-summarizedexperiment" ,r-summarizedexperiment)
8540 ("r-variantannotation" ,r-variantannotation)))
8541 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8542 (synopsis "Extract and visualize mutational patterns in genomic data")
8543 (description "This package provides an extensive toolset for the
8544 characterization and visualization of a wide range of mutational patterns
8545 in SNV base substitution data.")
8546 (license license:expat)))
8548 (define-public r-wgcna
8555 (uri (cran-uri "WGCNA" version))
8558 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8559 (properties `((upstream-name . "WGCNA")))
8560 (build-system r-build-system)
8562 `(("r-annotationdbi" ,r-annotationdbi)
8563 ("r-doparallel" ,r-doparallel)
8564 ("r-dynamictreecut" ,r-dynamictreecut)
8565 ("r-fastcluster" ,r-fastcluster)
8566 ("r-foreach" ,r-foreach)
8567 ("r-go-db" ,r-go-db)
8568 ("r-hmisc" ,r-hmisc)
8569 ("r-impute" ,r-impute)
8571 ("r-robust" ,r-robust)
8572 ("r-survival" ,r-survival)
8573 ("r-matrixstats" ,r-matrixstats)
8574 ("r-preprocesscore" ,r-preprocesscore)))
8576 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8577 (synopsis "Weighted correlation network analysis")
8579 "This package provides functions necessary to perform Weighted
8580 Correlation Network Analysis on high-dimensional data. It includes functions
8581 for rudimentary data cleaning, construction and summarization of correlation
8582 networks, module identification and functions for relating both variables and
8583 modules to sample traits. It also includes a number of utility functions for
8584 data manipulation and visualization.")
8585 (license license:gpl2+)))
8587 (define-public r-chipkernels
8588 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8591 (name "r-chipkernels")
8592 (version (string-append "1.1-" revision "." (string-take commit 9)))
8597 (url "https://github.com/ManuSetty/ChIPKernels.git")
8599 (file-name (string-append name "-" version))
8602 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8603 (build-system r-build-system)
8605 `(("r-iranges" ,r-iranges)
8606 ("r-xvector" ,r-xvector)
8607 ("r-biostrings" ,r-biostrings)
8608 ("r-bsgenome" ,r-bsgenome)
8609 ("r-gtools" ,r-gtools)
8610 ("r-genomicranges" ,r-genomicranges)
8611 ("r-sfsmisc" ,r-sfsmisc)
8612 ("r-kernlab" ,r-kernlab)
8613 ("r-s4vectors" ,r-s4vectors)
8614 ("r-biocgenerics" ,r-biocgenerics)))
8615 (home-page "https://github.com/ManuSetty/ChIPKernels")
8616 (synopsis "Build string kernels for DNA Sequence analysis")
8617 (description "ChIPKernels is an R package for building different string
8618 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8619 must be built and this dictionary can be used for determining kernels for DNA
8621 (license license:gpl2+))))
8623 (define-public r-seqgl
8630 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8631 "archive/" version ".tar.gz"))
8632 (file-name (string-append name "-" version ".tar.gz"))
8635 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8636 (build-system r-build-system)
8638 `(("r-biostrings" ,r-biostrings)
8639 ("r-chipkernels" ,r-chipkernels)
8640 ("r-genomicranges" ,r-genomicranges)
8641 ("r-spams" ,r-spams)
8642 ("r-wgcna" ,r-wgcna)
8643 ("r-fastcluster" ,r-fastcluster)))
8644 (home-page "https://github.com/ManuSetty/SeqGL")
8645 (synopsis "Group lasso for Dnase/ChIP-seq data")
8646 (description "SeqGL is a group lasso based algorithm to extract
8647 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8648 This package presents a method which uses group lasso to discriminate between
8649 bound and non bound genomic regions to accurately identify transcription
8650 factors bound at the specific regions.")
8651 (license license:gpl2+)))
8653 (define-public r-gkmsvm
8660 (uri (cran-uri "gkmSVM" version))
8663 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8664 (properties `((upstream-name . "gkmSVM")))
8665 (build-system r-build-system)
8667 `(("r-biocgenerics" ,r-biocgenerics)
8668 ("r-biostrings" ,r-biostrings)
8669 ("r-genomeinfodb" ,r-genomeinfodb)
8670 ("r-genomicranges" ,r-genomicranges)
8671 ("r-iranges" ,r-iranges)
8672 ("r-kernlab" ,r-kernlab)
8675 ("r-rtracklayer" ,r-rtracklayer)
8676 ("r-s4vectors" ,r-s4vectors)
8677 ("r-seqinr" ,r-seqinr)))
8678 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8679 (synopsis "Gapped-kmer support vector machine")
8681 "This R package provides tools for training gapped-kmer SVM classifiers
8682 for DNA and protein sequences. This package supports several sequence
8683 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8684 (license license:gpl2+)))
8686 (define-public r-tximport
8692 (uri (bioconductor-uri "tximport" version))
8695 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8696 (build-system r-build-system)
8697 (home-page "https://bioconductor.org/packages/tximport")
8698 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8700 "This package provides tools to import transcript-level abundance,
8701 estimated counts and transcript lengths, and to summarize them into matrices
8702 for use with downstream gene-level analysis packages. Average transcript
8703 length, weighted by sample-specific transcript abundance estimates, is
8704 provided as a matrix which can be used as an offset for different expression
8705 of gene-level counts.")
8706 (license license:gpl2+)))
8708 (define-public r-rhdf5
8714 (uri (bioconductor-uri "rhdf5" version))
8717 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8718 (build-system r-build-system)
8721 (modify-phases %standard-phases
8722 (add-after 'unpack 'unpack-smallhdf5
8723 (lambda* (#:key outputs #:allow-other-keys)
8724 (system* "tar" "-xzvf"
8725 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8726 (substitute* "src/hdf5/configure"
8728 ;; Remove timestamp and host system information to make
8729 ;; the build reproducible.
8730 (substitute* "src/hdf5/src/libhdf5.settings.in"
8731 (("Configured on: @CONFIG_DATE@")
8732 "Configured on: Guix")
8733 (("Uname information:.*")
8734 "Uname information: Linux\n")
8735 ;; Remove unnecessary store reference.
8737 "C Compiler: GCC\n"))
8740 `(("r-zlibbioc" ,r-zlibbioc)))
8744 (home-page "https://bioconductor.org/packages/rhdf5")
8745 (synopsis "HDF5 interface to R")
8747 "This R/Bioconductor package provides an interface between HDF5 and R.
8748 HDF5's main features are the ability to store and access very large and/or
8749 complex datasets and a wide variety of metadata on mass storage (disk) through
8750 a completely portable file format. The rhdf5 package is thus suited for the
8751 exchange of large and/or complex datasets between R and other software
8752 package, and for letting R applications work on datasets that are larger than
8753 the available RAM.")
8754 (license license:artistic2.0)))
8756 (define-public r-annotationfilter
8758 (name "r-annotationfilter")
8762 (uri (bioconductor-uri "AnnotationFilter" version))
8765 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8767 `((upstream-name . "AnnotationFilter")))
8768 (build-system r-build-system)
8770 `(("r-genomicranges" ,r-genomicranges)
8771 ("r-lazyeval" ,r-lazyeval)))
8772 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8773 (synopsis "Facilities for filtering Bioconductor annotation resources")
8775 "This package provides classes and other infrastructure to implement
8776 filters for manipulating Bioconductor annotation resources. The filters are
8777 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8778 (license license:artistic2.0)))
8780 (define-public emboss
8786 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8787 (version-major+minor version) ".0/"
8788 "EMBOSS-" version ".tar.gz"))
8791 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8792 (build-system gnu-build-system)
8795 (list (string-append "--with-hpdf="
8796 (assoc-ref %build-inputs "libharu")))
8798 (modify-phases %standard-phases
8799 (add-after 'unpack 'fix-checks
8801 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8802 ;; and zlib, but assume that they are all found at the same
8804 (substitute* "configure.in"
8805 (("CHECK_PNGDRIVER")
8806 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8807 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8808 AM_CONDITIONAL(AMPNG, true)"))
8810 (add-after 'fix-checks 'disable-update-check
8812 ;; At build time there is no connection to the Internet, so
8813 ;; looking for updates will not work.
8814 (substitute* "Makefile.am"
8815 (("\\$\\(bindir\\)/embossupdate") ""))
8817 (add-after 'disable-update-check 'autogen
8818 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8824 ("libharu" ,libharu)
8827 `(("autoconf" ,autoconf)
8828 ("automake" ,automake)
8829 ("libtool" ,libtool)
8830 ("pkg-config" ,pkg-config)))
8831 (home-page "http://emboss.sourceforge.net")
8832 (synopsis "Molecular biology analysis suite")
8833 (description "EMBOSS is the \"European Molecular Biology Open Software
8834 Suite\". EMBOSS is an analysis package specially developed for the needs of
8835 the molecular biology (e.g. EMBnet) user community. The software
8836 automatically copes with data in a variety of formats and even allows
8837 transparent retrieval of sequence data from the web. It also provides a
8838 number of libraries for the development of software in the field of molecular
8839 biology. EMBOSS also integrates a range of currently available packages and
8840 tools for sequence analysis into a seamless whole.")
8841 (license license:gpl2+)))
8844 (let ((revision "1")
8845 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8848 ;; The version is 2.13.0 even though no release archives have been
8849 ;; published as yet.
8850 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8854 (url "https://github.com/arq5x/bits.git")
8856 (file-name (string-append name "-" version "-checkout"))
8859 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8860 (build-system gnu-build-system)
8862 `(#:tests? #f ;no tests included
8864 (modify-phases %standard-phases
8866 (add-after 'unpack 'remove-cuda
8868 (substitute* "Makefile"
8870 (("(bits_test_intersections) \\\\" _ match) match))
8873 (lambda* (#:key outputs #:allow-other-keys)
8875 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8880 (home-page "https://github.com/arq5x/bits")
8881 (synopsis "Implementation of binary interval search algorithm")
8882 (description "This package provides an implementation of the
8883 BITS (Binary Interval Search) algorithm, an approach to interval set
8884 intersection. It is especially suited for the comparison of diverse genomic
8885 datasets and the exploration of large datasets of genome
8886 intervals (e.g. genes, sequence alignments).")
8887 (license license:gpl2))))
8889 (define-public piranha
8890 ;; There is no release tarball for the latest version. The latest commit is
8891 ;; older than one year at the time of this writing.
8892 (let ((revision "1")
8893 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8896 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8900 (url "https://github.com/smithlabcode/piranha.git")
8902 (file-name (git-file-name name version))
8905 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8906 (build-system gnu-build-system)
8908 `(#:test-target "test"
8910 (modify-phases %standard-phases
8911 (add-after 'unpack 'copy-smithlab-cpp
8912 (lambda* (#:key inputs #:allow-other-keys)
8913 (for-each (lambda (file)
8914 (install-file file "./src/smithlab_cpp/"))
8915 (find-files (assoc-ref inputs "smithlab-cpp")))
8917 (add-after 'install 'install-to-store
8918 (lambda* (#:key outputs #:allow-other-keys)
8919 (let* ((out (assoc-ref outputs "out"))
8920 (bin (string-append out "/bin")))
8921 (for-each (lambda (file)
8922 (install-file file bin))
8923 (find-files "bin" ".*")))
8926 (list (string-append "--with-bam_tools_headers="
8927 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8928 (string-append "--with-bam_tools_library="
8929 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8931 `(("bamtools" ,bamtools)
8932 ("samtools" ,samtools-0.1)
8935 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8939 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8941 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8944 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8946 `(("python" ,python-2)))
8947 (home-page "https://github.com/smithlabcode/piranha")
8948 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8950 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8951 RIP-seq experiments. It takes input in BED or BAM format and identifies
8952 regions of statistically significant read enrichment. Additional covariates
8953 may optionally be provided to further inform the peak-calling process.")
8954 (license license:gpl3+))))
8962 (uri (string-append "https://pypi.python.org/packages/source/P"
8963 "/PePr/PePr-" version ".tar.gz"))
8966 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8967 (build-system python-build-system)
8969 `(#:python ,python-2 ; python2 only
8970 #:tests? #f)) ; no tests included
8972 `(("python2-numpy" ,python2-numpy)
8973 ("python2-scipy" ,python2-scipy)
8974 ("python2-pysam" ,python2-pysam)))
8975 (home-page "https://github.com/shawnzhangyx/PePr")
8976 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8978 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8979 that is primarily designed for data with biological replicates. It uses a
8980 negative binomial distribution to model the read counts among the samples in
8981 the same group, and look for consistent differences between ChIP and control
8982 group or two ChIP groups run under different conditions.")
8983 (license license:gpl3+)))
8985 (define-public filevercmp
8986 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8989 (version (string-append "0-1." (string-take commit 7)))
8992 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8994 (file-name (string-append name "-" version ".tar.gz"))
8996 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8997 (build-system gnu-build-system)
8999 `(#:tests? #f ; There are no tests to run.
9001 (modify-phases %standard-phases
9002 (delete 'configure) ; There is no configure phase.
9004 (lambda* (#:key outputs #:allow-other-keys)
9005 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9006 (install-file "filevercmp" bin)))))))
9007 (home-page "https://github.com/ekg/filevercmp")
9008 (synopsis "This program compares version strings")
9009 (description "This program compares version strings. It intends to be a
9010 replacement for strverscmp.")
9011 (license license:gpl3+))))
9013 (define-public multiqc
9020 (uri (pypi-uri "multiqc" version))
9023 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
9024 (build-system python-build-system)
9026 `(("python-jinja2" ,python-jinja2)
9027 ("python-simplejson" ,python-simplejson)
9028 ("python-pyyaml" ,python-pyyaml)
9029 ("python-click" ,python-click)
9030 ("python-spectra" ,python-spectra)
9031 ("python-requests" ,python-requests)
9032 ("python-markdown" ,python-markdown)
9033 ("python-lzstring" ,python-lzstring)
9034 ("python-matplotlib" ,python-matplotlib)
9035 ("python-numpy" ,python-numpy)
9036 ;; MultQC checks for the presence of nose at runtime.
9037 ("python-nose" ,python-nose)))
9038 (home-page "http://multiqc.info")
9039 (synopsis "Aggregate bioinformatics analysis reports")
9041 "MultiQC is a tool to aggregate bioinformatics results across many
9042 samples into a single report. It contains modules for a large number of
9043 common bioinformatics tools.")
9044 (license license:gpl3+)))
9046 (define-public r-chipseq
9053 (uri (bioconductor-uri "chipseq" version))
9056 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
9057 (build-system r-build-system)
9059 `(("r-biocgenerics" ,r-biocgenerics)
9060 ("r-genomicranges" ,r-genomicranges)
9061 ("r-iranges" ,r-iranges)
9062 ("r-lattice" ,r-lattice)
9063 ("r-s4vectors" ,r-s4vectors)
9064 ("r-shortread" ,r-shortread)))
9065 (home-page "https://bioconductor.org/packages/chipseq")
9066 (synopsis "Package for analyzing ChIPseq data")
9068 "This package provides tools for processing short read data from ChIPseq
9070 (license license:artistic2.0)))
9072 (define-public r-copyhelper
9074 (name "r-copyhelper")
9079 (uri (string-append "https://bioconductor.org/packages/release/"
9080 "data/experiment/src/contrib/CopyhelpeR_"
9084 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9085 (properties `((upstream-name . "CopyhelpeR")))
9086 (build-system r-build-system)
9087 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9088 (synopsis "Helper files for CopywriteR")
9090 "This package contains the helper files that are required to run the
9091 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9092 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9093 mm10. In addition, it contains a blacklist filter to remove regions that
9094 display copy number variation. Files are stored as GRanges objects from the
9095 GenomicRanges Bioconductor package.")
9096 (license license:gpl2)))
9098 (define-public r-copywriter
9100 (name "r-copywriter")
9105 (uri (bioconductor-uri "CopywriteR" version))
9108 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9109 (properties `((upstream-name . "CopywriteR")))
9110 (build-system r-build-system)
9112 `(("r-biocparallel" ,r-biocparallel)
9113 ("r-chipseq" ,r-chipseq)
9114 ("r-copyhelper" ,r-copyhelper)
9115 ("r-data-table" ,r-data-table)
9116 ("r-dnacopy" ,r-dnacopy)
9117 ("r-futile-logger" ,r-futile-logger)
9118 ("r-genomeinfodb" ,r-genomeinfodb)
9119 ("r-genomicalignments" ,r-genomicalignments)
9120 ("r-genomicranges" ,r-genomicranges)
9121 ("r-gtools" ,r-gtools)
9122 ("r-iranges" ,r-iranges)
9123 ("r-matrixstats" ,r-matrixstats)
9124 ("r-rsamtools" ,r-rsamtools)
9125 ("r-s4vectors" ,r-s4vectors)))
9126 (home-page "https://github.com/PeeperLab/CopywriteR")
9127 (synopsis "Copy number information from targeted sequencing")
9129 "CopywriteR extracts DNA copy number information from targeted sequencing
9130 by utilizing off-target reads. It allows for extracting uniformly distributed
9131 copy number information, can be used without reference, and can be applied to
9132 sequencing data obtained from various techniques including chromatin
9133 immunoprecipitation and target enrichment on small gene panels. Thereby,
9134 CopywriteR constitutes a widely applicable alternative to available copy
9135 number detection tools.")
9136 (license license:gpl2)))
9138 (define-public r-methylkit
9140 (name "r-methylkit")
9144 (uri (bioconductor-uri "methylKit" version))
9147 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9148 (properties `((upstream-name . "methylKit")))
9149 (build-system r-build-system)
9151 `(("r-data-table" ,r-data-table)
9152 ("r-emdbook" ,r-emdbook)
9153 ("r-fastseg" ,r-fastseg)
9154 ("r-genomeinfodb" ,r-genomeinfodb)
9155 ("r-genomicranges" ,r-genomicranges)
9156 ("r-gtools" ,r-gtools)
9157 ("r-iranges" ,r-iranges)
9158 ("r-kernsmooth" ,r-kernsmooth)
9159 ("r-limma" ,r-limma)
9160 ("r-mclust" ,r-mclust)
9161 ("r-qvalue" ,r-qvalue)
9162 ("r-r-utils" ,r-r-utils)
9164 ("r-rhtslib" ,r-rhtslib)
9165 ("r-rsamtools" ,r-rsamtools)
9166 ("r-rtracklayer" ,r-rtracklayer)
9167 ("r-s4vectors" ,r-s4vectors)
9168 ("r-zlibbioc" ,r-zlibbioc)))
9171 (home-page "https://github.com/al2na/methylKit")
9173 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9175 "MethylKit is an R package for DNA methylation analysis and annotation
9176 from high-throughput bisulfite sequencing. The package is designed to deal
9177 with sequencing data from @dfn{Reduced representation bisulfite
9178 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9179 genome bisulfite sequencing. It also has functions to analyze base-pair
9180 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9182 (license license:artistic2.0)))
9184 (define-public r-sva
9191 (uri (bioconductor-uri "sva" version))
9194 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9195 (build-system r-build-system)
9197 `(("r-genefilter" ,r-genefilter)
9199 ("r-biocparallel" ,r-biocparallel)
9200 ("r-matrixstats" ,r-matrixstats)
9201 ("r-limma" ,r-limma)))
9202 (home-page "https://bioconductor.org/packages/sva")
9203 (synopsis "Surrogate variable analysis")
9205 "This package contains functions for removing batch effects and other
9206 unwanted variation in high-throughput experiment. It also contains functions
9207 for identifying and building surrogate variables for high-dimensional data
9208 sets. Surrogate variables are covariates constructed directly from
9209 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9210 imaging data that can be used in subsequent analyses to adjust for unknown,
9211 unmodeled, or latent sources of noise.")
9212 (license license:artistic2.0)))
9214 (define-public r-seqminer
9221 (uri (cran-uri "seqminer" version))
9224 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9225 (build-system r-build-system)
9228 (home-page "http://seqminer.genomic.codes")
9229 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9231 "This package provides tools to integrate nucleotide sequencing
9232 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9233 ;; Any version of the GPL is acceptable
9234 (license (list license:gpl2+ license:gpl3+))))
9236 (define-public r-raremetals2
9238 (name "r-raremetals2")
9243 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9244 "b/b7/RareMETALS2_" version ".tar.gz"))
9247 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9248 (properties `((upstream-name . "RareMETALS2")))
9249 (build-system r-build-system)
9251 `(("r-seqminer" ,r-seqminer)
9252 ("r-mvtnorm" ,r-mvtnorm)
9254 ("r-compquadform" ,r-compquadform)
9255 ("r-getopt" ,r-getopt)))
9256 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9257 (synopsis "Analyze gene-level association tests for binary trait")
9259 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9260 It was designed to meta-analyze gene-level association tests for binary trait.
9261 While rareMETALS offers a near-complete solution for meta-analysis of
9262 gene-level tests for quantitative trait, it does not offer the optimal
9263 solution for binary trait. The package rareMETALS2 offers improved features
9264 for analyzing gene-level association tests in meta-analyses for binary
9266 (license license:gpl3)))
9268 (define-public r-maldiquant
9270 (name "r-maldiquant")
9275 (uri (cran-uri "MALDIquant" version))
9278 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9279 (properties `((upstream-name . "MALDIquant")))
9280 (build-system r-build-system)
9281 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9282 (synopsis "Quantitative analysis of mass spectrometry data")
9284 "This package provides a complete analysis pipeline for matrix-assisted
9285 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9286 two-dimensional mass spectrometry data. In addition to commonly used plotting
9287 and processing methods it includes distinctive features, namely baseline
9288 subtraction methods such as morphological filters (TopHat) or the
9289 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9290 alignment using warping functions, handling of replicated measurements as well
9291 as allowing spectra with different resolutions.")
9292 (license license:gpl3+)))
9294 (define-public r-protgenerics
9296 (name "r-protgenerics")
9301 (uri (bioconductor-uri "ProtGenerics" version))
9304 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9305 (properties `((upstream-name . "ProtGenerics")))
9306 (build-system r-build-system)
9307 (home-page "https://github.com/lgatto/ProtGenerics")
9308 (synopsis "S4 generic functions for proteomics infrastructure")
9310 "This package provides S4 generic functions needed by Bioconductor
9311 proteomics packages.")
9312 (license license:artistic2.0)))
9314 (define-public r-mzr
9321 (uri (bioconductor-uri "mzR" version))
9324 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9325 (modules '((guix build utils)))
9328 (delete-file-recursively "src/boost")
9330 (properties `((upstream-name . "mzR")))
9331 (build-system r-build-system)
9334 (modify-phases %standard-phases
9335 (add-after 'unpack 'use-system-boost
9337 (substitute* "src/Makevars"
9338 (("\\./boost/libs.*") "")
9339 (("ARCH_OBJS=" line)
9341 "\nARCH_LIBS=-lboost_system -lboost_regex \
9342 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9345 `(("boost" ,boost) ; use this instead of the bundled boost sources
9346 ("netcdf" ,netcdf)))
9348 `(("r-biobase" ,r-biobase)
9349 ("r-biocgenerics" ,r-biocgenerics)
9350 ("r-protgenerics" ,r-protgenerics)
9352 ("r-zlibbioc" ,r-zlibbioc)))
9353 (home-page "https://github.com/sneumann/mzR/")
9354 (synopsis "Parser for mass spectrometry data files")
9356 "The mzR package provides a unified API to the common file formats and
9357 parsers available for mass spectrometry data. It comes with a wrapper for the
9358 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9359 The package contains the original code written by the ISB, and a subset of the
9360 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9361 previously been used in XCMS.")
9362 (license license:artistic2.0)))
9364 (define-public r-affyio
9371 (uri (bioconductor-uri "affyio" version))
9374 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9375 (build-system r-build-system)
9377 `(("r-zlibbioc" ,r-zlibbioc)))
9380 (home-page "https://github.com/bmbolstad/affyio")
9381 (synopsis "Tools for parsing Affymetrix data files")
9383 "This package provides routines for parsing Affymetrix data files based
9384 upon file format information. The primary focus is on accessing the CEL and
9386 (license license:lgpl2.0+)))
9388 (define-public r-affy
9395 (uri (bioconductor-uri "affy" version))
9398 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9399 (build-system r-build-system)
9401 `(("r-affyio" ,r-affyio)
9402 ("r-biobase" ,r-biobase)
9403 ("r-biocgenerics" ,r-biocgenerics)
9404 ("r-biocinstaller" ,r-biocinstaller)
9405 ("r-preprocesscore" ,r-preprocesscore)
9406 ("r-zlibbioc" ,r-zlibbioc)))
9407 (home-page "https://bioconductor.org/packages/affy")
9408 (synopsis "Methods for affymetrix oligonucleotide arrays")
9410 "This package contains functions for exploratory oligonucleotide array
9412 (license license:lgpl2.0+)))
9414 (define-public r-vsn
9421 (uri (bioconductor-uri "vsn" version))
9424 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9425 (build-system r-build-system)
9427 `(("r-affy" ,r-affy)
9428 ("r-biobase" ,r-biobase)
9429 ("r-ggplot2" ,r-ggplot2)
9430 ("r-lattice" ,r-lattice)
9431 ("r-limma" ,r-limma)))
9432 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9433 (synopsis "Variance stabilization and calibration for microarray data")
9435 "The package implements a method for normalising microarray intensities,
9436 and works for single- and multiple-color arrays. It can also be used for data
9437 from other technologies, as long as they have similar format. The method uses
9438 a robust variant of the maximum-likelihood estimator for an
9439 additive-multiplicative error model and affine calibration. The model
9440 incorporates data calibration step (a.k.a. normalization), a model for the
9441 dependence of the variance on the mean intensity and a variance stabilizing
9442 data transformation. Differences between transformed intensities are
9443 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9444 their variance is independent of the mean, and they are usually more sensitive
9445 and specific in detecting differential transcription.")
9446 (license license:artistic2.0)))
9448 (define-public r-mzid
9455 (uri (bioconductor-uri "mzID" version))
9458 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9459 (properties `((upstream-name . "mzID")))
9460 (build-system r-build-system)
9462 `(("r-doparallel" ,r-doparallel)
9463 ("r-foreach" ,r-foreach)
9464 ("r-iterators" ,r-iterators)
9466 ("r-protgenerics" ,r-protgenerics)
9469 (home-page "https://bioconductor.org/packages/mzID")
9470 (synopsis "Parser for mzIdentML files")
9472 "This package provides a parser for mzIdentML files implemented using the
9473 XML package. The parser tries to be general and able to handle all types of
9474 mzIdentML files with the drawback of having less pretty output than a vendor
9476 (license license:gpl2+)))
9478 (define-public r-pcamethods
9480 (name "r-pcamethods")
9485 (uri (bioconductor-uri "pcaMethods" version))
9488 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9489 (properties `((upstream-name . "pcaMethods")))
9490 (build-system r-build-system)
9492 `(("r-biobase" ,r-biobase)
9493 ("r-biocgenerics" ,r-biocgenerics)
9495 ("r-rcpp" ,r-rcpp)))
9496 (home-page "https://github.com/hredestig/pcamethods")
9497 (synopsis "Collection of PCA methods")
9499 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9500 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9501 for missing value estimation is included for comparison. BPCA, PPCA and
9502 NipalsPCA may be used to perform PCA on incomplete data as well as for
9503 accurate missing value estimation. A set of methods for printing and plotting
9504 the results is also provided. All PCA methods make use of the same data
9505 structure (pcaRes) to provide a common interface to the PCA results.")
9506 (license license:gpl3+)))
9508 (define-public r-msnbase
9515 (uri (bioconductor-uri "MSnbase" version))
9518 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9519 (properties `((upstream-name . "MSnbase")))
9520 (build-system r-build-system)
9522 `(("r-affy" ,r-affy)
9523 ("r-biobase" ,r-biobase)
9524 ("r-biocgenerics" ,r-biocgenerics)
9525 ("r-biocparallel" ,r-biocparallel)
9526 ("r-digest" ,r-digest)
9527 ("r-ggplot2" ,r-ggplot2)
9528 ("r-impute" ,r-impute)
9529 ("r-iranges" ,r-iranges)
9530 ("r-lattice" ,r-lattice)
9531 ("r-maldiquant" ,r-maldiquant)
9534 ("r-pcamethods" ,r-pcamethods)
9536 ("r-preprocesscore" ,r-preprocesscore)
9537 ("r-protgenerics" ,r-protgenerics)
9539 ("r-s4vectors" ,r-s4vectors)
9542 (home-page "https://github.com/lgatto/MSnbase")
9543 (synopsis "Base functions and classes for MS-based proteomics")
9545 "This package provides basic plotting, data manipulation and processing
9546 of mass spectrometry based proteomics data.")
9547 (license license:artistic2.0)))
9549 (define-public r-msnid
9556 (uri (bioconductor-uri "MSnID" version))
9559 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9560 (properties `((upstream-name . "MSnID")))
9561 (build-system r-build-system)
9563 `(("r-biobase" ,r-biobase)
9564 ("r-data-table" ,r-data-table)
9565 ("r-doparallel" ,r-doparallel)
9566 ("r-dplyr" ,r-dplyr)
9567 ("r-foreach" ,r-foreach)
9568 ("r-iterators" ,r-iterators)
9569 ("r-msnbase" ,r-msnbase)
9572 ("r-protgenerics" ,r-protgenerics)
9573 ("r-r-cache" ,r-r-cache)
9575 ("r-reshape2" ,r-reshape2)))
9576 (home-page "https://bioconductor.org/packages/MSnID")
9577 (synopsis "Utilities for LC-MSn proteomics identifications")
9579 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9580 from mzIdentML (leveraging the mzID package) or text files. After collating
9581 the search results from multiple datasets it assesses their identification
9582 quality and optimize filtering criteria to achieve the maximum number of
9583 identifications while not exceeding a specified false discovery rate. It also
9584 contains a number of utilities to explore the MS/MS results and assess missed
9585 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9586 (license license:artistic2.0)))
9588 (define-public r-seurat
9594 (uri (cran-uri "Seurat" version))
9597 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9598 ;; Delete pre-built jar.
9600 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9602 (properties `((upstream-name . "Seurat")))
9603 (build-system r-build-system)
9606 (modify-phases %standard-phases
9607 (add-after 'unpack 'build-jar
9608 (lambda* (#:key inputs #:allow-other-keys)
9609 (let ((classesdir "tmp-classes"))
9610 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9612 (with-output-to-file "manifest"
9614 (display "Manifest-Version: 1.0
9615 Main-Class: ModularityOptimizer\n")))
9616 (and (zero? (apply system* `("javac" "-d" ,classesdir
9617 ,@(find-files "java" "\\.java$"))))
9618 (zero? (system* "jar"
9620 "inst/java/ModularityOptimizer.jar"
9621 "-C" classesdir ".")))))))))
9623 `(("jdk" ,icedtea "jdk")))
9626 ("r-caret" ,r-caret)
9627 ("r-cowplot" ,r-cowplot)
9628 ("r-diffusionmap" ,r-diffusionmap)
9629 ("r-dplyr" ,r-dplyr)
9633 ("r-gdata" ,r-gdata)
9634 ("r-ggplot2" ,r-ggplot2)
9635 ("r-ggridges" ,r-ggridges)
9636 ("r-gplots" ,r-gplots)
9637 ("r-gridextra" ,r-gridextra)
9638 ("r-hmisc" ,r-hmisc)
9640 ("r-igraph" ,r-igraph)
9641 ("r-irlba" ,r-irlba)
9644 ("r-matrix" ,r-matrix)
9645 ("r-metap" ,r-metap)
9646 ("r-mixtools" ,r-mixtools)
9647 ("r-pbapply" ,r-pbapply)
9648 ("r-plotly" ,r-plotly)
9649 ("r-ranger" ,r-ranger)
9650 ("r-rcolorbrewer" ,r-rcolorbrewer)
9652 ("r-rcppeigen" ,r-rcppeigen)
9653 ("r-rcppprogress" ,r-rcppprogress)
9654 ("r-reshape2" ,r-reshape2)
9656 ("r-rtsne" ,r-rtsne)
9657 ("r-sdmtools" ,r-sdmtools)
9658 ("r-stringr" ,r-stringr)
9659 ("r-tclust" ,r-tclust)
9660 ("r-tidyr" ,r-tidyr)
9662 ("r-vgam" ,r-vgam)))
9663 (home-page "http://www.satijalab.org/seurat")
9664 (synopsis "Seurat is an R toolkit for single cell genomics")
9666 "This package is an R package designed for QC, analysis, and
9667 exploration of single cell RNA-seq data. It easily enables widely-used
9668 analytical techniques, including the identification of highly variable genes,
9669 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9670 algorithms; density clustering, hierarchical clustering, k-means, and the
9671 discovery of differentially expressed genes and markers.")
9672 (license license:gpl3)))
9674 (define-public r-aroma-light
9676 (name "r-aroma-light")
9681 (uri (bioconductor-uri "aroma.light" version))
9684 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9685 (properties `((upstream-name . "aroma.light")))
9686 (build-system r-build-system)
9688 `(("r-matrixstats" ,r-matrixstats)
9689 ("r-r-methodss3" ,r-r-methodss3)
9691 ("r-r-utils" ,r-r-utils)))
9692 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9693 (synopsis "Methods for normalization and visualization of microarray data")
9695 "This package provides methods for microarray analysis that take basic
9696 data types such as matrices and lists of vectors. These methods can be used
9697 standalone, be utilized in other packages, or be wrapped up in higher-level
9699 (license license:gpl2+)))
9701 (define-public r-deseq
9708 (uri (bioconductor-uri "DESeq" version))
9711 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9712 (properties `((upstream-name . "DESeq")))
9713 (build-system r-build-system)
9715 `(("r-biobase" ,r-biobase)
9716 ("r-biocgenerics" ,r-biocgenerics)
9717 ("r-genefilter" ,r-genefilter)
9718 ("r-geneplotter" ,r-geneplotter)
9719 ("r-lattice" ,r-lattice)
9720 ("r-locfit" ,r-locfit)
9722 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9723 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9724 (synopsis "Differential gene expression analysis")
9726 "This package provides tools for estimating variance-mean dependence in
9727 count data from high-throughput genetic sequencing assays and for testing for
9728 differential expression based on a model using the negative binomial
9730 (license license:gpl3+)))
9732 (define-public r-edaseq
9739 (uri (bioconductor-uri "EDASeq" version))
9742 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9743 (properties `((upstream-name . "EDASeq")))
9744 (build-system r-build-system)
9746 `(("r-annotationdbi" ,r-annotationdbi)
9747 ("r-aroma-light" ,r-aroma-light)
9748 ("r-biobase" ,r-biobase)
9749 ("r-biocgenerics" ,r-biocgenerics)
9750 ("r-biomart" ,r-biomart)
9751 ("r-biostrings" ,r-biostrings)
9752 ("r-deseq" ,r-deseq)
9753 ("r-genomicfeatures" ,r-genomicfeatures)
9754 ("r-genomicranges" ,r-genomicranges)
9755 ("r-iranges" ,r-iranges)
9756 ("r-rsamtools" ,r-rsamtools)
9757 ("r-shortread" ,r-shortread)))
9758 (home-page "https://github.com/drisso/EDASeq")
9759 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9761 "This package provides support for numerical and graphical summaries of
9762 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9763 adjust for GC-content effect (or other gene-level effects) on read counts:
9764 loess robust local regression, global-scaling, and full-quantile
9765 normalization. Between-lane normalization procedures to adjust for
9766 distributional differences between lanes (e.g., sequencing depth):
9767 global-scaling and full-quantile normalization.")
9768 (license license:artistic2.0)))
9770 (define-public r-interactivedisplaybase
9772 (name "r-interactivedisplaybase")
9777 (uri (bioconductor-uri "interactiveDisplayBase" version))
9780 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9782 `((upstream-name . "interactiveDisplayBase")))
9783 (build-system r-build-system)
9785 `(("r-biocgenerics" ,r-biocgenerics)
9786 ("r-shiny" ,r-shiny)))
9787 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9788 (synopsis "Base package for web displays of Bioconductor objects")
9790 "This package contains the basic methods needed to generate interactive
9791 Shiny-based display methods for Bioconductor objects.")
9792 (license license:artistic2.0)))
9794 (define-public r-annotationhub
9796 (name "r-annotationhub")
9801 (uri (bioconductor-uri "AnnotationHub" version))
9804 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9805 (properties `((upstream-name . "AnnotationHub")))
9806 (build-system r-build-system)
9808 `(("r-annotationdbi" ,r-annotationdbi)
9809 ("r-biocgenerics" ,r-biocgenerics)
9810 ("r-biocinstaller" ,r-biocinstaller)
9813 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9814 ("r-rsqlite" ,r-rsqlite)
9815 ("r-s4vectors" ,r-s4vectors)
9816 ("r-yaml" ,r-yaml)))
9817 (home-page "https://bioconductor.org/packages/AnnotationHub")
9818 (synopsis "Client to access AnnotationHub resources")
9820 "This package provides a client for the Bioconductor AnnotationHub web
9821 resource. The AnnotationHub web resource provides a central location where
9822 genomic files (e.g. VCF, bed, wig) and other resources from standard
9823 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9824 metadata about each resource, e.g., a textual description, tags, and date of
9825 modification. The client creates and manages a local cache of files retrieved
9826 by the user, helping with quick and reproducible access.")
9827 (license license:artistic2.0)))
9829 (define-public r-fastseg
9836 (uri (bioconductor-uri "fastseg" version))
9839 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9840 (build-system r-build-system)
9842 `(("r-biobase" ,r-biobase)
9843 ("r-biocgenerics" ,r-biocgenerics)
9844 ("r-genomicranges" ,r-genomicranges)
9845 ("r-iranges" ,r-iranges)
9846 ("r-s4vectors" ,r-s4vectors)))
9847 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9848 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9850 "Fastseg implements a very fast and efficient segmentation algorithm.
9851 It can segment data from DNA microarrays and data from next generation
9852 sequencing for example to detect copy number segments. Further it can segment
9853 data from RNA microarrays like tiling arrays to identify transcripts. Most
9854 generally, it can segment data given as a matrix or as a vector. Various data
9855 formats can be used as input to fastseg like expression set objects for
9856 microarrays or GRanges for sequencing data.")
9857 (license license:lgpl2.0+)))
9859 (define-public r-keggrest
9866 (uri (bioconductor-uri "KEGGREST" version))
9869 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9870 (properties `((upstream-name . "KEGGREST")))
9871 (build-system r-build-system)
9873 `(("r-biostrings" ,r-biostrings)
9876 (home-page "https://bioconductor.org/packages/KEGGREST")
9877 (synopsis "Client-side REST access to KEGG")
9879 "This package provides a package that provides a client interface to the
9880 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9881 (license license:artistic2.0)))
9883 (define-public r-gage
9890 (uri (bioconductor-uri "gage" version))
9893 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9894 (build-system r-build-system)
9896 `(("r-annotationdbi" ,r-annotationdbi)
9897 ("r-graph" ,r-graph)
9898 ("r-keggrest" ,r-keggrest)))
9899 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9900 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9902 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9903 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9904 data attributes including sample sizes, experimental designs, assay platforms,
9905 and other types of heterogeneity. The gage package provides functions for
9906 basic GAGE analysis, result processing and presentation. In addition, it
9907 provides demo microarray data and commonly used gene set data based on KEGG
9908 pathways and GO terms. These funtions and data are also useful for gene set
9909 analysis using other methods.")
9910 (license license:gpl2+)))
9912 (define-public r-genomicfiles
9914 (name "r-genomicfiles")
9919 (uri (bioconductor-uri "GenomicFiles" version))
9922 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9923 (properties `((upstream-name . "GenomicFiles")))
9924 (build-system r-build-system)
9926 `(("r-biocgenerics" ,r-biocgenerics)
9927 ("r-biocparallel" ,r-biocparallel)
9928 ("r-genomeinfodb" ,r-genomeinfodb)
9929 ("r-genomicalignments" ,r-genomicalignments)
9930 ("r-genomicranges" ,r-genomicranges)
9931 ("r-iranges" ,r-iranges)
9932 ("r-rsamtools" ,r-rsamtools)
9933 ("r-rtracklayer" ,r-rtracklayer)
9934 ("r-s4vectors" ,r-s4vectors)
9935 ("r-summarizedexperiment" ,r-summarizedexperiment)
9936 ("r-variantannotation" ,r-variantannotation)))
9937 (home-page "https://bioconductor.org/packages/GenomicFiles")
9938 (synopsis "Distributed computing by file or by range")
9940 "This package provides infrastructure for parallel computations
9941 distributed by file or by range. User defined mapper and reducer functions
9942 provide added flexibility for data combination and manipulation.")
9943 (license license:artistic2.0)))
9945 (define-public r-complexheatmap
9947 (name "r-complexheatmap")
9952 (uri (bioconductor-uri "ComplexHeatmap" version))
9955 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9957 `((upstream-name . "ComplexHeatmap")))
9958 (build-system r-build-system)
9960 `(("r-circlize" ,r-circlize)
9961 ("r-colorspace" ,r-colorspace)
9962 ("r-getoptlong" ,r-getoptlong)
9963 ("r-globaloptions" ,r-globaloptions)
9964 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9966 "https://github.com/jokergoo/ComplexHeatmap")
9967 (synopsis "Making Complex Heatmaps")
9969 "Complex heatmaps are efficient to visualize associations between
9970 different sources of data sets and reveal potential structures. This package
9971 provides a highly flexible way to arrange multiple heatmaps and supports
9972 self-defined annotation graphics.")
9973 (license license:gpl2+)))
9975 (define-public r-dirichletmultinomial
9977 (name "r-dirichletmultinomial")
9982 (uri (bioconductor-uri "DirichletMultinomial" version))
9985 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9987 `((upstream-name . "DirichletMultinomial")))
9988 (build-system r-build-system)
9992 `(("r-biocgenerics" ,r-biocgenerics)
9993 ("r-iranges" ,r-iranges)
9994 ("r-s4vectors" ,r-s4vectors)))
9995 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9996 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9998 "Dirichlet-multinomial mixture models can be used to describe variability
9999 in microbial metagenomic data. This package is an interface to code
10000 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10002 (license license:lgpl3)))
10004 (define-public r-ensembldb
10006 (name "r-ensembldb")
10011 (uri (bioconductor-uri "ensembldb" version))
10014 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
10015 (build-system r-build-system)
10017 `(("r-annotationdbi" ,r-annotationdbi)
10018 ("r-annotationfilter" ,r-annotationfilter)
10019 ("r-annotationhub" ,r-annotationhub)
10020 ("r-biobase" ,r-biobase)
10021 ("r-biocgenerics" ,r-biocgenerics)
10022 ("r-biostrings" ,r-biostrings)
10025 ("r-genomeinfodb" ,r-genomeinfodb)
10026 ("r-genomicfeatures" ,r-genomicfeatures)
10027 ("r-genomicranges" ,r-genomicranges)
10028 ("r-iranges" ,r-iranges)
10029 ("r-protgenerics" ,r-protgenerics)
10030 ("r-rsamtools" ,r-rsamtools)
10031 ("r-rsqlite" ,r-rsqlite)
10032 ("r-rtracklayer" ,r-rtracklayer)
10033 ("r-s4vectors" ,r-s4vectors)))
10034 (home-page "https://github.com/jotsetung/ensembldb")
10035 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10037 "The package provides functions to create and use transcript-centric
10038 annotation databases/packages. The annotation for the databases are directly
10039 fetched from Ensembl using their Perl API. The functionality and data is
10040 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10041 but, in addition to retrieve all gene/transcript models and annotations from
10042 the database, the @code{ensembldb} package also provides a filter framework
10043 allowing to retrieve annotations for specific entries like genes encoded on a
10044 chromosome region or transcript models of lincRNA genes.")
10045 ;; No version specified
10046 (license license:lgpl3+)))
10048 (define-public r-organismdbi
10050 (name "r-organismdbi")
10055 (uri (bioconductor-uri "OrganismDbi" version))
10058 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
10059 (properties `((upstream-name . "OrganismDbi")))
10060 (build-system r-build-system)
10062 `(("r-annotationdbi" ,r-annotationdbi)
10063 ("r-biobase" ,r-biobase)
10064 ("r-biocgenerics" ,r-biocgenerics)
10065 ("r-biocinstaller" ,r-biocinstaller)
10067 ("r-genomicfeatures" ,r-genomicfeatures)
10068 ("r-genomicranges" ,r-genomicranges)
10069 ("r-graph" ,r-graph)
10070 ("r-iranges" ,r-iranges)
10072 ("r-s4vectors" ,r-s4vectors)))
10073 (home-page "https://bioconductor.org/packages/OrganismDbi")
10074 (synopsis "Software to enable the smooth interfacing of database packages")
10075 (description "The package enables a simple unified interface to several
10076 annotation packages each of which has its own schema by taking advantage of
10077 the fact that each of these packages implements a select methods.")
10078 (license license:artistic2.0)))
10080 (define-public r-biovizbase
10082 (name "r-biovizbase")
10087 (uri (bioconductor-uri "biovizBase" version))
10090 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10091 (properties `((upstream-name . "biovizBase")))
10092 (build-system r-build-system)
10094 `(("r-annotationdbi" ,r-annotationdbi)
10095 ("r-annotationfilter" ,r-annotationfilter)
10096 ("r-biocgenerics" ,r-biocgenerics)
10097 ("r-biostrings" ,r-biostrings)
10098 ("r-dichromat" ,r-dichromat)
10099 ("r-ensembldb" ,r-ensembldb)
10100 ("r-genomeinfodb" ,r-genomeinfodb)
10101 ("r-genomicalignments" ,r-genomicalignments)
10102 ("r-genomicfeatures" ,r-genomicfeatures)
10103 ("r-genomicranges" ,r-genomicranges)
10104 ("r-hmisc" ,r-hmisc)
10105 ("r-iranges" ,r-iranges)
10106 ("r-rcolorbrewer" ,r-rcolorbrewer)
10107 ("r-rsamtools" ,r-rsamtools)
10108 ("r-s4vectors" ,r-s4vectors)
10109 ("r-scales" ,r-scales)
10110 ("r-summarizedexperiment" ,r-summarizedexperiment)
10111 ("r-variantannotation" ,r-variantannotation)))
10112 (home-page "https://bioconductor.org/packages/biovizBase")
10113 (synopsis "Basic graphic utilities for visualization of genomic data")
10115 "The biovizBase package is designed to provide a set of utilities, color
10116 schemes and conventions for genomic data. It serves as the base for various
10117 high-level packages for biological data visualization. This saves development
10118 effort and encourages consistency.")
10119 (license license:artistic2.0)))
10121 (define-public r-ggbio
10128 (uri (bioconductor-uri "ggbio" version))
10131 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10132 (build-system r-build-system)
10134 `(("r-annotationdbi" ,r-annotationdbi)
10135 ("r-annotationfilter" ,r-annotationfilter)
10136 ("r-biobase" ,r-biobase)
10137 ("r-biocgenerics" ,r-biocgenerics)
10138 ("r-biostrings" ,r-biostrings)
10139 ("r-biovizbase" ,r-biovizbase)
10140 ("r-bsgenome" ,r-bsgenome)
10141 ("r-ensembldb" ,r-ensembldb)
10142 ("r-genomeinfodb" ,r-genomeinfodb)
10143 ("r-genomicalignments" ,r-genomicalignments)
10144 ("r-genomicfeatures" ,r-genomicfeatures)
10145 ("r-genomicranges" ,r-genomicranges)
10146 ("r-ggally" ,r-ggally)
10147 ("r-ggplot2" ,r-ggplot2)
10148 ("r-gridextra" ,r-gridextra)
10149 ("r-gtable" ,r-gtable)
10150 ("r-hmisc" ,r-hmisc)
10151 ("r-iranges" ,r-iranges)
10152 ("r-organismdbi" ,r-organismdbi)
10153 ("r-reshape2" ,r-reshape2)
10154 ("r-rsamtools" ,r-rsamtools)
10155 ("r-rtracklayer" ,r-rtracklayer)
10156 ("r-s4vectors" ,r-s4vectors)
10157 ("r-scales" ,r-scales)
10158 ("r-summarizedexperiment" ,r-summarizedexperiment)
10159 ("r-variantannotation" ,r-variantannotation)))
10160 (home-page "http://www.tengfei.name/ggbio/")
10161 (synopsis "Visualization tools for genomic data")
10163 "The ggbio package extends and specializes the grammar of graphics for
10164 biological data. The graphics are designed to answer common scientific
10165 questions, in particular those often asked of high throughput genomics data.
10166 All core Bioconductor data structures are supported, where appropriate. The
10167 package supports detailed views of particular genomic regions, as well as
10168 genome-wide overviews. Supported overviews include ideograms and grand linear
10169 views. High-level plots include sequence fragment length, edge-linked
10170 interval to data view, mismatch pileup, and several splicing summaries.")
10171 (license license:artistic2.0)))
10173 (define-public r-gprofiler
10175 (name "r-gprofiler")
10180 (uri (cran-uri "gProfileR" version))
10183 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10184 (properties `((upstream-name . "gProfileR")))
10185 (build-system r-build-system)
10187 `(("r-plyr" ,r-plyr)
10188 ("r-rcurl" ,r-rcurl)))
10189 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10190 (synopsis "Interface to the g:Profiler toolkit")
10192 "This package provides tools for functional enrichment analysis,
10193 gene identifier conversion and mapping homologous genes across related
10194 organisms via the @code{g:Profiler} toolkit.")
10195 (license license:gpl2+)))
10197 (define-public r-gqtlbase
10199 (name "r-gqtlbase")
10204 (uri (bioconductor-uri "gQTLBase" version))
10207 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10208 (properties `((upstream-name . "gQTLBase")))
10209 (build-system r-build-system)
10211 `(("r-batchjobs" ,r-batchjobs)
10212 ("r-bbmisc" ,r-bbmisc)
10213 ("r-biocgenerics" ,r-biocgenerics)
10215 ("r-doparallel" ,r-doparallel)
10217 ("r-ffbase" ,r-ffbase)
10218 ("r-foreach" ,r-foreach)
10219 ("r-genomicfiles" ,r-genomicfiles)
10220 ("r-genomicranges" ,r-genomicranges)
10221 ("r-rtracklayer" ,r-rtracklayer)
10222 ("r-s4vectors" ,r-s4vectors)
10223 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10224 (home-page "https://bioconductor.org/packages/gQTLBase")
10225 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10227 "The purpose of this package is to simplify the storage and interrogation
10228 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10230 (license license:artistic2.0)))
10232 (define-public r-snpstats
10234 (name "r-snpstats")
10239 (uri (bioconductor-uri "snpStats" version))
10242 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10243 (properties `((upstream-name . "snpStats")))
10244 (build-system r-build-system)
10245 (inputs `(("zlib" ,zlib)))
10247 `(("r-biocgenerics" ,r-biocgenerics)
10248 ("r-matrix" ,r-matrix)
10249 ("r-survival" ,r-survival)
10250 ("r-zlibbioc" ,r-zlibbioc)))
10251 (home-page "https://bioconductor.org/packages/snpStats")
10252 (synopsis "Methods for SNP association studies")
10254 "This package provides classes and statistical methods for large
10255 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10256 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10257 (license license:gpl3)))
10259 (define-public r-homo-sapiens
10261 (name "r-homo-sapiens")
10265 ;; We cannot use bioconductor-uri here because this tarball is
10266 ;; located under "data/annotation/" instead of "bioc/".
10267 (uri (string-append "http://www.bioconductor.org/packages/"
10268 "release/data/annotation/src/contrib/"
10270 version ".tar.gz"))
10273 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10275 `((upstream-name . "Homo.sapiens")))
10276 (build-system r-build-system)
10278 `(("r-genomicfeatures" ,r-genomicfeatures)
10279 ("r-go-db" ,r-go-db)
10280 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10281 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10282 ("r-organismdbi" ,r-organismdbi)
10283 ("r-annotationdbi" ,r-annotationdbi)))
10284 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10285 (synopsis "Annotation package for the Homo.sapiens object")
10287 "This package contains the Homo.sapiens object to access data from
10288 several related annotation packages.")
10289 (license license:artistic2.0)))
10291 (define-public r-erma
10298 (uri (bioconductor-uri "erma" version))
10301 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10302 (build-system r-build-system)
10304 `(("r-annotationdbi" ,r-annotationdbi)
10305 ("r-biobase" ,r-biobase)
10306 ("r-biocgenerics" ,r-biocgenerics)
10307 ("r-foreach" ,r-foreach)
10308 ("r-genomicfiles" ,r-genomicfiles)
10309 ("r-genomicranges" ,r-genomicranges)
10310 ("r-ggplot2" ,r-ggplot2)
10311 ("r-homo-sapiens" ,r-homo-sapiens)
10312 ("r-rtracklayer" ,r-rtracklayer)
10313 ("r-s4vectors" ,r-s4vectors)
10314 ("r-shiny" ,r-shiny)
10315 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10316 (home-page "https://bioconductor.org/packages/erma")
10317 (synopsis "Epigenomic road map adventures")
10319 "The epigenomics road map describes locations of epigenetic marks in DNA
10320 from a variety of cell types. Of interest are locations of histone
10321 modifications, sites of DNA methylation, and regions of accessible chromatin.
10322 This package presents a selection of elements of the road map including
10323 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10324 by Ernst and Kellis.")
10325 (license license:artistic2.0)))
10327 (define-public r-ldblock
10334 (uri (bioconductor-uri "ldblock" version))
10337 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10338 (build-system r-build-system)
10340 `(("r-erma" ,r-erma)
10341 ("r-genomeinfodb" ,r-genomeinfodb)
10342 ("r-genomicfiles" ,r-genomicfiles)
10343 ("r-go-db" ,r-go-db)
10344 ("r-homo-sapiens" ,r-homo-sapiens)
10345 ("r-matrix" ,r-matrix)
10346 ("r-rsamtools" ,r-rsamtools)
10347 ("r-snpstats" ,r-snpstats)
10348 ("r-variantannotation" ,r-variantannotation)))
10349 (home-page "https://bioconductor.org/packages/ldblock")
10350 (synopsis "Data structures for linkage disequilibrium measures in populations")
10352 "This package defines data structures for @dfn{linkage
10353 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10354 handling of existing population-level data for the purpose of flexibly
10355 defining LD blocks.")
10356 (license license:artistic2.0)))
10358 (define-public r-gqtlstats
10360 (name "r-gqtlstats")
10365 (uri (bioconductor-uri "gQTLstats" version))
10368 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10369 (properties `((upstream-name . "gQTLstats")))
10370 (build-system r-build-system)
10372 `(("r-annotationdbi" ,r-annotationdbi)
10373 ("r-batchjobs" ,r-batchjobs)
10374 ("r-bbmisc" ,r-bbmisc)
10375 ("r-beeswarm" ,r-beeswarm)
10376 ("r-biobase" ,r-biobase)
10377 ("r-biocgenerics" ,r-biocgenerics)
10378 ("r-doparallel" ,r-doparallel)
10379 ("r-dplyr" ,r-dplyr)
10381 ("r-ffbase" ,r-ffbase)
10382 ("r-foreach" ,r-foreach)
10383 ("r-genomeinfodb" ,r-genomeinfodb)
10384 ("r-genomicfeatures" ,r-genomicfeatures)
10385 ("r-genomicfiles" ,r-genomicfiles)
10386 ("r-genomicranges" ,r-genomicranges)
10387 ("r-ggbeeswarm" ,r-ggbeeswarm)
10388 ("r-ggplot2" ,r-ggplot2)
10389 ("r-gqtlbase" ,r-gqtlbase)
10390 ("r-hardyweinberg" ,r-hardyweinberg)
10391 ("r-iranges" ,r-iranges)
10392 ("r-ldblock" ,r-ldblock)
10393 ("r-limma" ,r-limma)
10395 ("r-plotly" ,r-plotly)
10396 ("r-reshape2" ,r-reshape2)
10397 ("r-s4vectors" ,r-s4vectors)
10398 ("r-shiny" ,r-shiny)
10399 ("r-snpstats" ,r-snpstats)
10400 ("r-summarizedexperiment" ,r-summarizedexperiment)
10401 ("r-variantannotation" ,r-variantannotation)))
10402 (home-page "https://bioconductor.org/packages/gQTLstats")
10403 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10405 "This package provides tools for the computationally efficient analysis
10406 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10407 The software in this package aims to support refinements and functional
10408 interpretation of members of a collection of association statistics on a
10409 family of feature/genome hypotheses.")
10410 (license license:artistic2.0)))
10412 (define-public r-gviz
10419 (uri (bioconductor-uri "Gviz" version))
10422 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10423 (properties `((upstream-name . "Gviz")))
10424 (build-system r-build-system)
10426 `(("r-annotationdbi" ,r-annotationdbi)
10427 ("r-biobase" ,r-biobase)
10428 ("r-biocgenerics" ,r-biocgenerics)
10429 ("r-biomart" ,r-biomart)
10430 ("r-biostrings" ,r-biostrings)
10431 ("r-biovizbase" ,r-biovizbase)
10432 ("r-bsgenome" ,r-bsgenome)
10433 ("r-digest" ,r-digest)
10434 ("r-genomeinfodb" ,r-genomeinfodb)
10435 ("r-genomicalignments" ,r-genomicalignments)
10436 ("r-genomicfeatures" ,r-genomicfeatures)
10437 ("r-genomicranges" ,r-genomicranges)
10438 ("r-iranges" ,r-iranges)
10439 ("r-lattice" ,r-lattice)
10440 ("r-latticeextra" ,r-latticeextra)
10441 ("r-matrixstats" ,r-matrixstats)
10442 ("r-rcolorbrewer" ,r-rcolorbrewer)
10443 ("r-rsamtools" ,r-rsamtools)
10444 ("r-rtracklayer" ,r-rtracklayer)
10445 ("r-s4vectors" ,r-s4vectors)
10446 ("r-xvector" ,r-xvector)))
10447 (home-page "https://bioconductor.org/packages/Gviz")
10448 (synopsis "Plotting data and annotation information along genomic coordinates")
10450 "Genomic data analyses requires integrated visualization of known genomic
10451 information and new experimental data. Gviz uses the biomaRt and the
10452 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10453 and translates this to e.g. gene/transcript structures in viewports of the
10454 grid graphics package. This results in genomic information plotted together
10456 (license license:artistic2.0)))
10458 (define-public r-gwascat
10465 (uri (bioconductor-uri "gwascat" version))
10468 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10469 (build-system r-build-system)
10471 `(("r-annotationdbi" ,r-annotationdbi)
10472 ("r-annotationhub" ,r-annotationhub)
10473 ("r-biocgenerics" ,r-biocgenerics)
10474 ("r-biostrings" ,r-biostrings)
10475 ("r-genomeinfodb" ,r-genomeinfodb)
10476 ("r-genomicfeatures" ,r-genomicfeatures)
10477 ("r-genomicranges" ,r-genomicranges)
10478 ("r-ggbio" ,r-ggbio)
10479 ("r-ggplot2" ,r-ggplot2)
10480 ("r-gqtlstats" ,r-gqtlstats)
10481 ("r-graph" ,r-graph)
10483 ("r-homo-sapiens" ,r-homo-sapiens)
10484 ("r-iranges" ,r-iranges)
10485 ("r-rsamtools" ,r-rsamtools)
10486 ("r-rtracklayer" ,r-rtracklayer)
10487 ("r-s4vectors" ,r-s4vectors)
10488 ("r-snpstats" ,r-snpstats)
10489 ("r-summarizedexperiment" ,r-summarizedexperiment)
10490 ("r-variantannotation" ,r-variantannotation)))
10491 (home-page "https://bioconductor.org/packages/gwascat")
10492 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10494 "This package provides tools for representing and modeling data in the
10495 EMBL-EBI GWAS catalog.")
10496 (license license:artistic2.0)))
10498 (define-public r-sushi
10504 (uri (bioconductor-uri "Sushi" version))
10507 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10508 (properties `((upstream-name . "Sushi")))
10509 (build-system r-build-system)
10511 `(("r-biomart" ,r-biomart)
10513 (home-page "https://bioconductor.org/packages/Sushi")
10514 (synopsis "Tools for visualizing genomics data")
10516 "This package provides flexible, quantitative, and integrative genomic
10517 visualizations for publication-quality multi-panel figures.")
10518 (license license:gpl2+)))
10520 (define-public r-fithic
10526 (uri (bioconductor-uri "FitHiC" version))
10529 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10530 (properties `((upstream-name . "FitHiC")))
10531 (build-system r-build-system)
10533 `(("r-data-table" ,r-data-table)
10534 ("r-fdrtool" ,r-fdrtool)
10535 ("r-rcpp" ,r-rcpp)))
10536 (home-page "https://bioconductor.org/packages/FitHiC")
10537 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10539 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10540 intra-chromosomal contact maps produced by genome-wide genome architecture
10541 assays such as Hi-C.")
10542 (license license:gpl2+)))
10544 (define-public r-hitc
10550 (uri (bioconductor-uri "HiTC" version))
10553 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10554 (properties `((upstream-name . "HiTC")))
10555 (build-system r-build-system)
10557 `(("r-biostrings" ,r-biostrings)
10558 ("r-genomeinfodb" ,r-genomeinfodb)
10559 ("r-genomicranges" ,r-genomicranges)
10560 ("r-iranges" ,r-iranges)
10561 ("r-matrix" ,r-matrix)
10562 ("r-rcolorbrewer" ,r-rcolorbrewer)
10563 ("r-rtracklayer" ,r-rtracklayer)))
10564 (home-page "https://bioconductor.org/packages/HiTC")
10565 (synopsis "High throughput chromosome conformation capture analysis")
10567 "The HiTC package was developed to explore high-throughput \"C\" data
10568 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10569 quality controls, normalization, visualization, and further analysis are also
10571 (license license:artistic2.0)))
10573 (define-public r-qvalue
10580 (uri (bioconductor-uri "qvalue" version))
10583 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10584 (build-system r-build-system)
10586 `(("r-ggplot2" ,r-ggplot2)
10587 ("r-reshape2" ,r-reshape2)))
10588 (home-page "http://github.com/jdstorey/qvalue")
10589 (synopsis "Q-value estimation for false discovery rate control")
10591 "This package takes a list of p-values resulting from the simultaneous
10592 testing of many hypotheses and estimates their q-values and local @dfn{false
10593 discovery rate} (FDR) values. The q-value of a test measures the proportion
10594 of false positives incurred when that particular test is called significant.
10595 The local FDR measures the posterior probability the null hypothesis is true
10596 given the test's p-value. Various plots are automatically generated, allowing
10597 one to make sensible significance cut-offs. The software can be applied to
10598 problems in genomics, brain imaging, astrophysics, and data mining.")
10599 ;; Any version of the LGPL.
10600 (license license:lgpl3+)))
10602 (define-public r-hdf5array
10604 (name "r-hdf5array")
10609 (uri (bioconductor-uri "HDF5Array" version))
10612 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10613 (properties `((upstream-name . "HDF5Array")))
10614 (build-system r-build-system)
10616 `(("r-biocgenerics" ,r-biocgenerics)
10617 ("r-delayedarray" ,r-delayedarray)
10618 ("r-iranges" ,r-iranges)
10619 ("r-rhdf5" ,r-rhdf5)
10620 ("r-s4vectors" ,r-s4vectors)))
10621 (home-page "https://bioconductor.org/packages/HDF5Array")
10622 (synopsis "HDF5 back end for DelayedArray objects")
10623 (description "This package provides an array-like container for convenient
10624 access and manipulation of HDF5 datasets. It supports delayed operations and
10625 block processing.")
10626 (license license:artistic2.0)))
10628 (define-public r-rhdf5lib
10630 (name "r-rhdf5lib")
10635 (uri (bioconductor-uri "Rhdf5lib" version))
10638 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10639 (properties `((upstream-name . "Rhdf5lib")))
10640 (build-system r-build-system)
10643 (modify-phases %standard-phases
10644 (add-after 'unpack 'do-not-use-bundled-hdf5
10645 (lambda* (#:key inputs #:allow-other-keys)
10646 (for-each delete-file '("configure" "configure.ac"))
10647 ;; Do not make other packages link with the proprietary libsz.
10648 (substitute* "R/zzz.R"
10649 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10650 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10651 (("'%s/libhdf5.a %s/libsz.a'")
10652 "'%s/libhdf5.a %s/libhdf5.a'"))
10653 (with-directory-excursion "src"
10654 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10655 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10657 ;; Remove timestamp and host system information to make
10658 ;; the build reproducible.
10659 (substitute* "hdf5/src/libhdf5.settings.in"
10660 (("Configured on: @CONFIG_DATE@")
10661 "Configured on: Guix")
10662 (("Uname information:.*")
10663 "Uname information: Linux\n")
10664 ;; Remove unnecessary store reference.
10666 "C Compiler: GCC\n"))
10667 (rename-file "Makevars.in" "Makevars")
10668 (substitute* "Makevars"
10669 (("HDF5_CXX_LIB=.*")
10670 (string-append "HDF5_CXX_LIB="
10671 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10673 (string-append "HDF5_LIB="
10674 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10675 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10676 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10677 ;; szip is non-free software
10678 (("cp \\$\\{SZIP_LIB\\}.*") "")
10679 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10680 "PKG_LIBS = ${HDF5_LIB}\n")))
10687 `(("hdf5-source" ,(package-source hdf5))))
10688 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10689 (synopsis "HDF5 library as an R package")
10690 (description "This package provides C and C++ HDF5 libraries for use in R
10692 (license license:artistic2.0)))
10694 (define-public r-beachmat
10696 (name "r-beachmat")
10701 (uri (bioconductor-uri "beachmat" version))
10704 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10705 (build-system r-build-system)
10709 `(("r-delayedarray" ,r-delayedarray)
10710 ("r-hdf5array" ,r-hdf5array)
10712 ("r-rhdf5" ,r-rhdf5)
10713 ("r-rhdf5lib" ,r-rhdf5lib)))
10714 (home-page "https://bioconductor.org/packages/beachmat")
10715 (synopsis "Compiling Bioconductor to handle each matrix type")
10716 (description "This package provides a consistent C++ class interface for a
10717 variety of commonly used matrix types, including sparse and HDF5-backed
10719 (license license:gpl3)))
10721 (define-public r-singlecellexperiment
10723 (name "r-singlecellexperiment")
10728 (uri (bioconductor-uri "SingleCellExperiment" version))
10731 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10733 `((upstream-name . "SingleCellExperiment")))
10734 (build-system r-build-system)
10736 `(("r-biocgenerics" ,r-biocgenerics)
10737 ("r-s4vectors" ,r-s4vectors)
10738 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10739 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10740 (synopsis "S4 classes for single cell data")
10741 (description "This package defines an S4 class for storing data from
10742 single-cell experiments. This includes specialized methods to store and
10743 retrieve spike-in information, dimensionality reduction coordinates and size
10744 factors for each cell, along with the usual metadata for genes and
10746 (license license:gpl3)))
10748 (define-public r-scater
10754 (uri (bioconductor-uri "scater" version))
10757 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10758 (build-system r-build-system)
10760 `(("r-beachmat" ,r-beachmat)
10761 ("r-biobase" ,r-biobase)
10762 ("r-biocgenerics" ,r-biocgenerics)
10763 ("r-biomart" ,r-biomart)
10764 ("r-data-table" ,r-data-table)
10765 ("r-dplyr" ,r-dplyr)
10766 ("r-edger" ,r-edger)
10767 ("r-ggbeeswarm" ,r-ggbeeswarm)
10768 ("r-ggplot2" ,r-ggplot2)
10769 ("r-limma" ,r-limma)
10770 ("r-matrix" ,r-matrix)
10771 ("r-matrixstats" ,r-matrixstats)
10774 ("r-reshape2" ,r-reshape2)
10775 ("r-rhdf5" ,r-rhdf5)
10776 ("r-rhdf5lib" ,r-rhdf5lib)
10777 ("r-rjson" ,r-rjson)
10778 ("r-s4vectors" ,r-s4vectors)
10779 ("r-shiny" ,r-shiny)
10780 ("r-shinydashboard" ,r-shinydashboard)
10781 ("r-singlecellexperiment" ,r-singlecellexperiment)
10782 ("r-summarizedexperiment" ,r-summarizedexperiment)
10783 ("r-tximport" ,r-tximport)
10784 ("r-viridis" ,r-viridis)))
10785 (home-page "https://github.com/davismcc/scater")
10786 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10787 (description "This package provides a collection of tools for doing
10788 various analyses of single-cell RNA-seq gene expression data, with a focus on
10790 (license license:gpl2+)))
10792 (define-public r-scran
10799 (uri (bioconductor-uri "scran" version))
10802 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10803 (build-system r-build-system)
10805 `(("r-beachmat" ,r-beachmat)
10806 ("r-biocgenerics" ,r-biocgenerics)
10807 ("r-biocparallel" ,r-biocparallel)
10809 ("r-dynamictreecut" ,r-dynamictreecut)
10810 ("r-edger" ,r-edger)
10812 ("r-ggplot2" ,r-ggplot2)
10813 ("r-igraph" ,r-igraph)
10814 ("r-limma" ,r-limma)
10815 ("r-matrix" ,r-matrix)
10817 ("r-rhdf5lib" ,r-rhdf5lib)
10818 ("r-s4vectors" ,r-s4vectors)
10819 ("r-scater" ,r-scater)
10820 ("r-shiny" ,r-shiny)
10821 ("r-singlecellexperiment" ,r-singlecellexperiment)
10822 ("r-statmod" ,r-statmod)
10823 ("r-summarizedexperiment" ,r-summarizedexperiment)
10824 ("r-viridis" ,r-viridis)
10826 (home-page "https://bioconductor.org/packages/scran")
10827 (synopsis "Methods for single-cell RNA-Seq data analysis")
10828 (description "This package implements a variety of low-level analyses of
10829 single-cell RNA-seq data. Methods are provided for normalization of
10830 cell-specific biases, assignment of cell cycle phase, and detection of highly
10831 variable and significantly correlated genes.")
10832 (license license:gpl3)))
10834 (define-public r-delayedmatrixstats
10836 (name "r-delayedmatrixstats")
10841 (uri (bioconductor-uri "DelayedMatrixStats" version))
10844 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10846 `((upstream-name . "DelayedMatrixStats")))
10847 (build-system r-build-system)
10849 `(("r-delayedarray" ,r-delayedarray)
10850 ("r-iranges" ,r-iranges)
10851 ("r-matrix" ,r-matrix)
10852 ("r-matrixstats" ,r-matrixstats)
10853 ("r-s4vectors" ,r-s4vectors)))
10854 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10855 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10857 "This package provides a port of the @code{matrixStats} API for use with
10858 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10859 contains high-performing functions operating on rows and columns of
10860 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10861 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10862 are optimized per data type and for subsetted calculations such that both
10863 memory usage and processing time is minimized.")
10864 (license license:expat)))
10866 (define-public r-phangorn
10868 (name "r-phangorn")
10873 (uri (cran-uri "phangorn" version))
10876 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10877 (build-system r-build-system)
10880 ("r-fastmatch" ,r-fastmatch)
10881 ("r-igraph" ,r-igraph)
10882 ("r-magrittr" ,r-magrittr)
10883 ("r-matrix" ,r-matrix)
10884 ("r-quadprog" ,r-quadprog)
10885 ("r-rcpp" ,r-rcpp)))
10886 (home-page "https://github.com/KlausVigo/phangorn")
10887 (synopsis "Phylogenetic analysis in R")
10889 "Phangorn is a package for phylogenetic analysis in R. It supports
10890 estimation of phylogenetic trees and networks using Maximum Likelihood,
10891 Maximum Parsimony, distance methods and Hadamard conjugation.")
10892 (license license:gpl2+)))
10894 (define-public r-dropbead
10895 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10898 (name "r-dropbead")
10899 (version (string-append "0-" revision "." (string-take commit 7)))
10903 (uri (git-reference
10904 (url "https://github.com/rajewsky-lab/dropbead.git")
10906 (file-name (git-file-name name version))
10909 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10910 (build-system r-build-system)
10912 `(("r-ggplot2" ,r-ggplot2)
10913 ("r-rcolorbrewer" ,r-rcolorbrewer)
10914 ("r-gridextra" ,r-gridextra)
10915 ("r-gplots" ,r-gplots)
10916 ("r-plyr" ,r-plyr)))
10917 (home-page "https://github.com/rajewsky-lab/dropbead")
10918 (synopsis "Basic exploration and analysis of Drop-seq data")
10919 (description "This package offers a quick and straight-forward way to
10920 explore and perform basic analysis of single cell sequencing data coming from
10921 droplet sequencing. It has been particularly tailored for Drop-seq.")
10922 (license license:gpl3))))
10924 (define htslib-for-sambamba
10925 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10928 (name "htslib-for-sambamba")
10929 (version (string-append "1.3.1-1." (string-take commit 9)))
10933 (uri (git-reference
10934 (url "https://github.com/lomereiter/htslib.git")
10936 (file-name (string-append "htslib-" version "-checkout"))
10939 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10941 (substitute-keyword-arguments (package-arguments htslib)
10943 `(modify-phases ,phases
10944 (add-after 'unpack 'bootstrap
10946 (zero? (system* "autoreconf" "-vif"))))))))
10948 `(("autoconf" ,autoconf)
10949 ("automake" ,automake)
10950 ,@(package-native-inputs htslib))))))
10952 (define-public sambamba
10959 (uri (string-append "https://github.com/lomereiter/sambamba/"
10960 "archive/v" version ".tar.gz"))
10961 (file-name (string-append name "-" version ".tar.gz"))
10964 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10965 (build-system gnu-build-system)
10967 `(#:tests? #f ; there is no test target
10969 '("D_COMPILER=ldc2"
10970 ;; Override "--compiler" flag only.
10971 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10972 "sambamba-ldmd2-64")
10974 (modify-phases %standard-phases
10975 (delete 'configure)
10976 (add-after 'unpack 'place-biod
10977 (lambda* (#:key inputs #:allow-other-keys)
10978 (copy-recursively (assoc-ref inputs "biod") "BioD")
10980 (add-after 'unpack 'unbundle-prerequisites
10982 (substitute* "Makefile"
10983 ((" htslib-static lz4-static") ""))
10986 (lambda* (#:key outputs #:allow-other-keys)
10987 (let* ((out (assoc-ref outputs "out"))
10988 (bin (string-append out "/bin")))
10990 (install-file "build/sambamba" bin)
10996 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10999 (uri (git-reference
11000 (url "https://github.com/biod/BioD.git")
11002 (file-name (string-append "biod-"
11003 (string-take commit 9)
11007 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
11010 ("htslib" ,htslib-for-sambamba)))
11011 (home-page "http://lomereiter.github.io/sambamba")
11012 (synopsis "Tools for working with SAM/BAM data")
11013 (description "Sambamba is a high performance modern robust and
11014 fast tool (and library), written in the D programming language, for
11015 working with SAM and BAM files. Current parallelised functionality is
11016 an important subset of samtools functionality, including view, index,
11017 sort, markdup, and depth.")
11018 (license license:gpl2+)))
11020 (define-public ritornello
11022 (name "ritornello")
11026 (uri (string-append "https://github.com/KlugerLab/"
11027 "Ritornello/archive/v"
11028 version ".tar.gz"))
11029 (file-name (string-append name "-" version ".tar.gz"))
11032 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11033 (build-system gnu-build-system)
11035 `(#:tests? #f ; there are no tests
11037 (modify-phases %standard-phases
11038 (add-after 'unpack 'patch-samtools-references
11039 (lambda* (#:key inputs #:allow-other-keys)
11040 (substitute* '("src/SamStream.h"
11041 "src/BufferedGenomeReader.h")
11042 (("<sam.h>") "<samtools/sam.h>"))
11044 (delete 'configure)
11046 (lambda* (#:key inputs outputs #:allow-other-keys)
11047 (let* ((out (assoc-ref outputs "out"))
11048 (bin (string-append out "/bin/")))
11050 (install-file "bin/Ritornello" bin)
11053 `(("samtools" ,samtools-0.1)
11057 (home-page "https://github.com/KlugerLab/Ritornello")
11058 (synopsis "Control-free peak caller for ChIP-seq data")
11059 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11060 signal processing that can accurately call binding events without the need to
11061 do a pair total DNA input or IgG control sample. It has been tested for use
11062 with narrow binding events such as transcription factor ChIP-seq.")
11063 (license license:gpl3+)))
11065 (define-public trim-galore
11067 (name "trim-galore")
11072 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
11073 "projects/trim_galore/trim_galore_v"
11077 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
11078 (build-system gnu-build-system)
11080 `(#:tests? #f ; no tests
11082 (modify-phases %standard-phases
11083 ;; The archive contains plain files.
11085 (lambda* (#:key source #:allow-other-keys)
11086 (zero? (system* "unzip" source))))
11087 (delete 'configure)
11089 (add-after 'unpack 'hardcode-tool-references
11090 (lambda* (#:key inputs #:allow-other-keys)
11091 (substitute* "trim_galore"
11092 (("\\$path_to_cutadapt = 'cutadapt'")
11093 (string-append "$path_to_cutadapt = '"
11094 (assoc-ref inputs "cutadapt")
11097 (string-append "| "
11098 (assoc-ref inputs "gzip")
11101 (string-append "\""
11102 (assoc-ref inputs "gzip")
11106 (lambda* (#:key outputs #:allow-other-keys)
11107 (let ((bin (string-append (assoc-ref outputs "out")
11110 (install-file "trim_galore" bin)
11115 ("cutadapt" ,cutadapt)))
11117 `(("unzip" ,unzip)))
11118 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11119 (synopsis "Wrapper around Cutadapt and FastQC")
11120 (description "Trim Galore! is a wrapper script to automate quality and
11121 adapter trimming as well as quality control, with some added functionality to
11122 remove biased methylation positions for RRBS sequence files.")
11123 (license license:gpl3+)))
11125 (define-public gess
11131 (uri (string-append "http://compbio.uthscsa.edu/"
11133 "gess-" version ".src.tar.gz"))
11136 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11137 (build-system gnu-build-system)
11139 `(#:tests? #f ; no tests
11141 (modify-phases %standard-phases
11142 (delete 'configure)
11145 (lambda* (#:key inputs outputs #:allow-other-keys)
11146 (let* ((python (assoc-ref inputs "python"))
11147 (out (assoc-ref outputs "out"))
11148 (bin (string-append out "/bin/"))
11149 (target (string-append
11150 out "/lib/python2.7/site-packages/gess/")))
11152 (copy-recursively "." target)
11153 ;; Make GESS.py executable
11154 (chmod (string-append target "GESS.py") #o555)
11155 ;; Add Python shebang to the top and make Matplotlib
11157 (substitute* (string-append target "GESS.py")
11158 (("\"\"\"Description:" line)
11159 (string-append "#!" (which "python") "
11161 matplotlib.use('Agg')
11163 ;; Make sure GESS has all modules in its path
11164 (wrap-program (string-append target "GESS.py")
11165 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11167 (symlink (string-append target "GESS.py")
11168 (string-append bin "GESS.py"))
11171 `(("python" ,python-2)
11172 ("python2-pysam" ,python2-pysam)
11173 ("python2-scipy" ,python2-scipy)
11174 ("python2-numpy" ,python2-numpy)
11175 ("python2-networkx" ,python2-networkx)
11176 ("python2-biopython" ,python2-biopython)))
11177 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11178 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11180 "GESS is an implementation of a novel computational method to detect de
11181 novo exon-skipping events directly from raw RNA-seq data without the prior
11182 knowledge of gene annotation information. GESS stands for the graph-based
11183 exon-skipping scanner detection scheme.")
11184 (license license:bsd-3)))
11186 (define-public phylip
11193 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11194 "download/phylip-" version ".tar.gz"))
11197 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11198 (build-system gnu-build-system)
11200 `(#:tests? #f ; no check target
11201 #:make-flags (list "-f" "Makefile.unx" "install")
11202 #:parallel-build? #f ; not supported
11204 (modify-phases %standard-phases
11205 (add-after 'unpack 'enter-dir
11206 (lambda _ (chdir "src") #t))
11207 (delete 'configure)
11209 (lambda* (#:key inputs outputs #:allow-other-keys)
11210 (let ((target (string-append (assoc-ref outputs "out")
11213 (for-each (lambda (file)
11214 (install-file file target))
11215 (find-files "../exe" ".*")))
11217 (home-page "http://evolution.genetics.washington.edu/phylip/")
11218 (synopsis "Tools for inferring phylogenies")
11219 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11220 programs for inferring phylogenies (evolutionary trees).")
11221 (license license:bsd-2)))
11230 (uri (string-append "https://integrativemodeling.org/"
11231 version "/download/imp-" version ".tar.gz"))
11234 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11235 (build-system cmake-build-system)
11237 `(;; FIXME: Some tests fail because they produce warnings, others fail
11238 ;; because the PYTHONPATH does not include the modeller's directory.
11246 ("python" ,python-2)))
11248 `(("python2-numpy" ,python2-numpy)
11249 ("python2-scipy" ,python2-scipy)
11250 ("python2-pandas" ,python2-pandas)
11251 ("python2-scikit-learn" ,python2-scikit-learn)
11252 ("python2-networkx" ,python2-networkx)))
11253 (home-page "https://integrativemodeling.org")
11254 (synopsis "Integrative modeling platform")
11255 (description "IMP's broad goal is to contribute to a comprehensive
11256 structural characterization of biomolecules ranging in size and complexity
11257 from small peptides to large macromolecular assemblies, by integrating data
11258 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11259 Python toolbox for solving complex modeling problems, and a number of
11260 applications for tackling some common problems in a user-friendly way.")
11261 ;; IMP is largely available under the GNU Lesser GPL; see the file
11262 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11263 ;; available under the GNU GPL (see the file COPYING.GPL).
11264 (license (list license:lgpl2.1+
11267 (define-public tadbit
11273 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11274 "archive/v" version ".tar.gz"))
11275 (file-name (string-append name "-" version ".tar.gz"))
11278 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11279 (build-system python-build-system)
11281 `(;; Tests are included and must be run after installation, but
11282 ;; they are incomplete and thus cannot be run.
11286 (modify-phases %standard-phases
11287 (add-after 'unpack 'fix-problems-with-setup.py
11288 (lambda* (#:key outputs #:allow-other-keys)
11289 ;; setup.py opens these files for writing
11290 (chmod "_pytadbit/_version.py" #o664)
11291 (chmod "README.rst" #o664)
11293 ;; Don't attempt to install the bash completions to
11294 ;; the home directory.
11295 (rename-file "extras/.bash_completion"
11297 (substitute* "setup.py"
11298 (("\\(path.expanduser\\('~'\\)")
11299 (string-append "(\""
11300 (assoc-ref outputs "out")
11301 "/etc/bash_completion.d\""))
11302 (("extras/\\.bash_completion")
11306 ;; TODO: add Chimera for visualization
11309 ("python2-scipy" ,python2-scipy)
11310 ("python2-numpy" ,python2-numpy)
11311 ("python2-matplotlib" ,python2-matplotlib)
11312 ("python2-pysam" ,python2-pysam)))
11313 (home-page "http://3dgenomes.github.io/TADbit/")
11314 (synopsis "Analyze, model, and explore 3C-based data")
11316 "TADbit is a complete Python library to deal with all steps to analyze,
11317 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11318 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11319 correct interaction matrices, identify and compare the so-called
11320 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11321 interaction matrices, and finally, extract structural properties from the
11322 models. TADbit is complemented by TADkit for visualizing 3D models.")
11323 (license license:gpl3+)))
11325 (define-public kentutils
11328 ;; 302.1.0 is out, but the only difference is the inclusion of
11329 ;; pre-built binaries.
11330 (version "302.0.0")
11334 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11335 "archive/v" version ".tar.gz"))
11336 (file-name (string-append name "-" version ".tar.gz"))
11339 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11340 (modules '((guix build utils)
11345 ;; Only the contents of the specified directories are free
11346 ;; for all uses, so we remove the rest. "hg/autoSql" and
11347 ;; "hg/autoXml" are nominally free, but they depend on a
11348 ;; library that is built from the sources in "hg/lib",
11349 ;; which is nonfree.
11350 (let ((free (list "." ".."
11351 "utils" "lib" "inc" "tagStorm"
11352 "parasol" "htslib"))
11353 (directory? (lambda (file)
11354 (eq? 'directory (stat:type (stat file))))))
11355 (for-each (lambda (file)
11356 (and (directory? file)
11357 (delete-file-recursively file)))
11358 (map (cut string-append "src/" <>)
11361 (not (member file free)))))))
11362 ;; Only make the utils target, not the userApps target,
11363 ;; because that requires libraries we won't build.
11364 (substitute* "Makefile"
11365 ((" userApps") " utils"))
11366 ;; Only build libraries that are free.
11367 (substitute* "src/makefile"
11368 (("DIRS =.*") "DIRS =\n")
11369 (("cd jkOwnLib.*") "")
11372 (substitute* "src/utils/makefile"
11373 ;; These tools depend on "jkhgap.a", which is part of the
11374 ;; nonfree "src/hg/lib" directory.
11375 (("raSqlQuery") "")
11376 (("pslLiftSubrangeBlat") "")
11378 ;; Do not build UCSC tools, which may require nonfree
11380 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11382 (build-system gnu-build-system)
11384 `( ;; There is no global test target and the test target for
11385 ;; individual tools depends on input files that are not
11389 (modify-phases %standard-phases
11390 (add-after 'unpack 'fix-paths
11392 (substitute* "Makefile"
11393 (("/bin/echo") (which "echo")))
11395 (add-after 'unpack 'prepare-samtabix
11396 (lambda* (#:key inputs #:allow-other-keys)
11397 (copy-recursively (assoc-ref inputs "samtabix")
11400 (delete 'configure)
11402 (lambda* (#:key outputs #:allow-other-keys)
11403 (let ((bin (string-append (assoc-ref outputs "out")
11405 (copy-recursively "bin" bin))
11411 (uri (git-reference
11412 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11413 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11416 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11423 ("openssl" ,openssl)))
11424 (home-page "http://genome.cse.ucsc.edu/index.html")
11425 (synopsis "Assorted bioinformatics utilities")
11426 (description "This package provides the kentUtils, a selection of
11427 bioinformatics utilities used in combination with the UCSC genome
11429 ;; Only a subset of the sources are released under a non-copyleft
11430 ;; free software license. All other sources are removed in a
11431 ;; snippet. See this bug report for an explanation of how the
11432 ;; license statements apply:
11433 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11434 (license (license:non-copyleft
11435 "http://genome.ucsc.edu/license/"
11436 "The contents of this package are free for all uses."))))
11438 (define-public f-seq
11439 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11443 (version (string-append "1.1-" revision "." (string-take commit 7)))
11446 (uri (git-reference
11447 (url "https://github.com/aboyle/F-seq.git")
11449 (file-name (string-append name "-" version))
11452 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11453 (modules '((guix build utils)))
11454 ;; Remove bundled Java library archives.
11457 (for-each delete-file (find-files "lib" ".*"))
11459 (build-system ant-build-system)
11461 `(#:tests? #f ; no tests included
11463 (modify-phases %standard-phases
11465 (lambda* (#:key inputs outputs #:allow-other-keys)
11466 (let* ((target (assoc-ref outputs "out"))
11467 (doc (string-append target "/share/doc/f-seq/")))
11470 (substitute* "bin/linux/fseq"
11471 (("java") (which "java"))
11472 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11473 (string-append (assoc-ref inputs "java-commons-cli")
11474 "/share/java/commons-cli.jar"))
11476 (string-append "REALDIR=" target "/bin\n")))
11477 (install-file "README.txt" doc)
11478 (install-file "bin/linux/fseq" (string-append target "/bin"))
11479 (install-file "build~/fseq.jar" (string-append target "/lib"))
11480 (copy-recursively "lib" (string-append target "/lib"))
11484 ("java-commons-cli" ,java-commons-cli)))
11485 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11486 (synopsis "Feature density estimator for high-throughput sequence tags")
11488 "F-Seq is a software package that generates a continuous tag sequence
11489 density estimation allowing identification of biologically meaningful sites
11490 such as transcription factor binding sites (ChIP-seq) or regions of open
11491 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11493 (license license:gpl3+))))
11495 (define-public bismark
11502 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11503 "archive/" version ".tar.gz"))
11504 (file-name (string-append name "-" version ".tar.gz"))
11507 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11508 (build-system perl-build-system)
11510 `(#:tests? #f ; there are no tests
11512 (modify-phases %standard-phases
11513 (delete 'configure)
11516 (lambda* (#:key outputs #:allow-other-keys)
11517 (let ((bin (string-append (assoc-ref outputs "out")
11519 (docdir (string-append (assoc-ref outputs "out")
11520 "/share/doc/bismark"))
11521 (docs '("Bismark_User_Guide.pdf"
11522 "RELEASE_NOTES.txt"))
11523 (scripts '("bismark"
11524 "bismark_genome_preparation"
11525 "bismark_methylation_extractor"
11528 "coverage2cytosine"
11529 "deduplicate_bismark"
11530 "bismark_sitrep.tpl"
11532 "bismark2summary")))
11535 (for-each (lambda (file) (install-file file bin))
11537 (for-each (lambda (file) (install-file file docdir))
11540 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11541 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11542 (description "Bismark is a program to map bisulfite treated sequencing
11543 reads to a genome of interest and perform methylation calls in a single step.
11544 The output can be easily imported into a genome viewer, such as SeqMonk, and
11545 enables a researcher to analyse the methylation levels of their samples
11546 straight away. Its main features are:
11549 @item Bisulfite mapping and methylation calling in one single step
11550 @item Supports single-end and paired-end read alignments
11551 @item Supports ungapped and gapped alignments
11552 @item Alignment seed length, number of mismatches etc are adjustable
11553 @item Output discriminates between cytosine methylation in CpG, CHG
11556 (license license:gpl3+)))
11558 (define-public paml
11564 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11565 "paml" version ".tgz"))
11568 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11569 (modules '((guix build utils)))
11570 ;; Remove Windows binaries
11573 (for-each delete-file (find-files "." "\\.exe$"))
11575 (build-system gnu-build-system)
11577 `(#:tests? #f ; there are no tests
11578 #:make-flags '("CC=gcc")
11580 (modify-phases %standard-phases
11581 (replace 'configure
11583 (substitute* "src/BFdriver.c"
11584 (("/bin/bash") (which "bash")))
11588 (lambda* (#:key outputs #:allow-other-keys)
11589 (let ((tools '("baseml" "basemlg" "codeml"
11590 "pamp" "evolver" "yn00" "chi2"))
11591 (bin (string-append (assoc-ref outputs "out") "/bin"))
11592 (docdir (string-append (assoc-ref outputs "out")
11593 "/share/doc/paml")))
11595 (for-each (lambda (file) (install-file file bin)) tools)
11596 (copy-recursively "../doc" docdir)
11598 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11599 (synopsis "Phylogentic analysis by maximum likelihood")
11600 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11601 contains a few programs for model fitting and phylogenetic tree reconstruction
11602 using nucleotide or amino-acid sequence data.")
11604 (license license:gpl3)))
11606 (define-public kallisto
11612 (uri (string-append "https://github.com/pachterlab/"
11613 "kallisto/archive/v" version ".tar.gz"))
11614 (file-name (string-append name "-" version ".tar.gz"))
11617 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11618 (build-system cmake-build-system)
11619 (arguments `(#:tests? #f)) ; no "check" target
11623 (home-page "http://pachterlab.github.io/kallisto/")
11624 (synopsis "Near-optimal RNA-Seq quantification")
11626 "Kallisto is a program for quantifying abundances of transcripts from
11627 RNA-Seq data, or more generally of target sequences using high-throughput
11628 sequencing reads. It is based on the novel idea of pseudoalignment for
11629 rapidly determining the compatibility of reads with targets, without the need
11630 for alignment. Pseudoalignment of reads preserves the key information needed
11631 for quantification, and kallisto is therefore not only fast, but also as
11632 accurate as existing quantification tools.")
11633 (license license:bsd-2)))
11635 (define-public libgff
11641 (uri (string-append
11642 "https://github.com/Kingsford-Group/"
11643 "libgff/archive/v" version ".tar.gz"))
11644 (file-name (string-append name "-" version ".tar.gz"))
11647 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11648 (build-system cmake-build-system)
11649 (arguments `(#:tests? #f)) ; no tests included
11650 (home-page "https://github.com/Kingsford-Group/libgff")
11651 (synopsis "Parser library for reading/writing GFF files")
11652 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11653 code that is used in the Cufflinks codebase. The goal of this library is to
11654 provide this functionality without the necessity of drawing in a heavy-weight
11655 dependency like SeqAn.")
11656 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11658 (define-public libdivsufsort
11660 (name "libdivsufsort")
11664 (uri (git-reference
11665 (url "https://github.com/y-256/libdivsufsort.git")
11667 (file-name (git-file-name name version))
11670 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11671 (build-system cmake-build-system)
11673 '(#:tests? #f ; there are no tests
11675 ;; Needed for rapmap and sailfish.
11676 '("-DBUILD_DIVSUFSORT64=ON")))
11677 (home-page "https://github.com/y-256/libdivsufsort")
11678 (synopsis "Lightweight suffix-sorting library")
11679 (description "libdivsufsort is a software library that implements a
11680 lightweight suffix array construction algorithm. This library provides a
11681 simple and an efficient C API to construct a suffix array and a
11682 Burrows-Wheeler transformed string from a given string over a constant-size
11683 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11684 bytes of memory space, where n is the length of the string.")
11685 (license license:expat)))
11687 (define-public sailfish
11694 (string-append "https://github.com/kingsfordgroup/"
11695 "sailfish/archive/v" version ".tar.gz"))
11696 (file-name (string-append name "-" version ".tar.gz"))
11699 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11700 (modules '((guix build utils)))
11703 ;; Delete bundled headers for eigen3.
11704 (delete-file-recursively "include/eigen3/")
11706 (build-system cmake-build-system)
11708 `(#:configure-flags
11709 (list (string-append "-DBOOST_INCLUDEDIR="
11710 (assoc-ref %build-inputs "boost")
11712 (string-append "-DBOOST_LIBRARYDIR="
11713 (assoc-ref %build-inputs "boost")
11715 (string-append "-DBoost_LIBRARIES="
11716 "-lboost_iostreams "
11717 "-lboost_filesystem "
11722 "-lboost_program_options")
11723 "-DBoost_FOUND=TRUE"
11724 ;; Don't download RapMap---we already have it!
11725 "-DFETCHED_RAPMAP=1")
11726 ;; Tests must be run after installation and the location of the test
11727 ;; data file must be overridden. But the tests fail. It looks like
11728 ;; they are not really meant to be run.
11731 (modify-phases %standard-phases
11732 ;; Boost cannot be found, even though it's right there.
11733 (add-after 'unpack 'do-not-look-for-boost
11734 (lambda* (#:key inputs #:allow-other-keys)
11735 (substitute* "CMakeLists.txt"
11736 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11737 (add-after 'unpack 'do-not-assign-to-macro
11739 (substitute* "include/spdlog/details/format.cc"
11740 (("const unsigned CHAR_WIDTH = 1;") ""))))
11741 (add-after 'unpack 'prepare-rapmap
11742 (lambda* (#:key inputs #:allow-other-keys)
11743 (let ((src "external/install/src/rapmap/")
11744 (include "external/install/include/rapmap/")
11745 (rapmap (assoc-ref inputs "rapmap")))
11746 (mkdir-p "/tmp/rapmap")
11747 (system* "tar" "xf"
11748 (assoc-ref inputs "rapmap")
11750 "--strip-components=1")
11753 (for-each (lambda (file)
11754 (install-file file src))
11755 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11756 (copy-recursively "/tmp/rapmap/include" include))))
11757 (add-after 'unpack 'use-system-libraries
11758 (lambda* (#:key inputs #:allow-other-keys)
11759 (substitute* '("src/SailfishIndexer.cpp"
11760 "src/SailfishUtils.cpp"
11761 "src/SailfishQuantify.cpp"
11762 "src/FASTAParser.cpp"
11764 "include/SailfishUtils.hpp"
11765 "include/SailfishIndex.hpp"
11766 "include/CollapsedEMOptimizer.hpp"
11767 "src/CollapsedEMOptimizer.cpp")
11768 (("#include \"jellyfish/config.h\"") ""))
11769 (substitute* "src/CMakeLists.txt"
11770 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11771 (string-append (assoc-ref inputs "jellyfish")
11772 "/include/jellyfish-" ,(package-version jellyfish)))
11773 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11774 (string-append (assoc-ref inputs "jellyfish")
11775 "/lib/libjellyfish-2.0.a"))
11776 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11777 (string-append (assoc-ref inputs "libdivsufsort")
11778 "/lib/libdivsufsort.so"))
11779 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11780 (string-append (assoc-ref inputs "libdivsufsort")
11781 "/lib/libdivsufsort64.so")))
11782 (substitute* "CMakeLists.txt"
11783 ;; Don't prefer static libs
11784 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11785 (("find_package\\(Jellyfish.*") "")
11786 (("ExternalProject_Add\\(libjellyfish") "message(")
11787 (("ExternalProject_Add\\(libgff") "message(")
11788 (("ExternalProject_Add\\(libsparsehash") "message(")
11789 (("ExternalProject_Add\\(libdivsufsort") "message("))
11791 ;; Ensure that Eigen headers can be found
11792 (setenv "CPLUS_INCLUDE_PATH"
11793 (string-append (getenv "CPLUS_INCLUDE_PATH")
11795 (assoc-ref inputs "eigen")
11796 "/include/eigen3")))))))
11800 ("jemalloc" ,jemalloc)
11801 ("jellyfish" ,jellyfish)
11802 ("sparsehash" ,sparsehash)
11805 (uri (git-reference
11806 (url "https://github.com/COMBINE-lab/RapMap.git")
11807 (commit (string-append "sf-v" version))))
11808 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11811 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11812 (modules '((guix build utils)))
11813 ;; These files are expected to be excluded.
11815 '(begin (delete-file-recursively "include/spdlog")
11816 (for-each delete-file '("include/xxhash.h"
11817 "src/xxhash.c"))))))
11818 ("libdivsufsort" ,libdivsufsort)
11823 `(("pkg-config" ,pkg-config)))
11824 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11825 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11826 (description "Sailfish is a tool for genomic transcript quantification
11827 from RNA-seq data. It requires a set of target transcripts (either from a
11828 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11829 fasta file containing your reference transcripts and a (set of) fasta/fastq
11830 file(s) containing your reads.")
11831 (license license:gpl3+)))
11833 (define libstadenio-for-salmon
11835 (name "libstadenio")
11839 (uri (git-reference
11840 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11841 (commit (string-append "v" version))))
11842 (file-name (string-append name "-" version "-checkout"))
11845 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11846 (build-system gnu-build-system)
11847 (arguments '(#:parallel-tests? #f)) ; not supported
11851 `(("perl" ,perl))) ; for tests
11852 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11853 (synopsis "General purpose trace and experiment file library")
11854 (description "This package provides a library of file reading and writing
11855 code to provide a general purpose Trace file (and Experiment File) reading
11858 The following file formats are supported:
11861 @item SCF trace files
11862 @item ABI trace files
11863 @item ALF trace files
11864 @item ZTR trace files
11865 @item SFF trace archives
11866 @item SRF trace archives
11867 @item Experiment files
11868 @item Plain text files
11869 @item SAM/BAM sequence files
11870 @item CRAM sequence files
11872 (license license:bsd-3)))
11874 (define spdlog-for-salmon
11880 (uri (git-reference
11881 (url "https://github.com/COMBINE-lab/spdlog.git")
11882 (commit (string-append "v" version))))
11883 (file-name (string-append name "-" version "-checkout"))
11886 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11887 (build-system cmake-build-system)
11888 (home-page "https://github.com/COMBINE-lab/spdlog")
11889 (synopsis "Very fast C++ logging library")
11890 (description "Spdlog is a very fast header-only C++ logging library with
11891 performance as its primary goal.")
11892 (license license:expat)))
11894 ;; This is a modified variant of bwa for use with Salmon. It installs a
11895 ;; library to avoid having to build this as part of Salmon.
11896 (define bwa-for-salmon
11897 (package (inherit bwa)
11899 (version "0.7.12.5")
11902 (uri (git-reference
11903 (url "https://github.com/COMBINE-lab/bwa.git")
11904 (commit (string-append "v" version))))
11905 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11908 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11909 (build-system gnu-build-system)
11911 '(#:tests? #f ;no "check" target
11913 (modify-phases %standard-phases
11915 (lambda* (#:key outputs #:allow-other-keys)
11916 (let* ((out (assoc-ref outputs "out"))
11917 (bin (string-append out "/bin"))
11918 (lib (string-append out "/lib"))
11919 (doc (string-append out "/share/doc/bwa"))
11920 (man (string-append out "/share/man/man1"))
11921 (inc (string-append out "/include/bwa")))
11922 (install-file "bwa" bin)
11923 (install-file "README.md" doc)
11924 (install-file "bwa.1" man)
11925 (install-file "libbwa.a" lib)
11928 (for-each (lambda (file)
11929 (install-file file inc))
11930 (find-files "." "\\.h$")))
11932 ;; no "configure" script
11933 (delete 'configure))))))
11935 (define-public salmon
11941 (uri (git-reference
11942 (url "https://github.com/COMBINE-lab/salmon.git")
11943 (commit (string-append "v" version))))
11944 (file-name (string-append name "-" version "-checkout"))
11947 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11948 (modules '((guix build utils)))
11951 ;; Delete bundled headers for eigen3.
11952 (delete-file-recursively "include/eigen3/")
11954 (build-system cmake-build-system)
11956 `(#:configure-flags
11957 (list (string-append "-DBOOST_INCLUDEDIR="
11958 (assoc-ref %build-inputs "boost")
11960 (string-append "-DBOOST_LIBRARYDIR="
11961 (assoc-ref %build-inputs "boost")
11963 (string-append "-DBoost_LIBRARIES="
11964 "-lboost_iostreams "
11965 "-lboost_filesystem "
11970 "-lboost_program_options")
11971 "-DBoost_FOUND=TRUE"
11972 "-DTBB_LIBRARIES=tbb tbbmalloc"
11973 ;; Don't download RapMap---we already have it!
11974 "-DFETCHED_RAPMAP=1")
11976 (modify-phases %standard-phases
11977 ;; Boost cannot be found, even though it's right there.
11978 (add-after 'unpack 'do-not-look-for-boost
11979 (lambda* (#:key inputs #:allow-other-keys)
11980 (substitute* "CMakeLists.txt"
11981 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11982 (add-after 'unpack 'do-not-phone-home
11984 (substitute* "src/Salmon.cpp"
11985 (("getVersionMessage\\(\\)") "\"\""))))
11986 (add-after 'unpack 'prepare-rapmap
11987 (lambda* (#:key inputs #:allow-other-keys)
11988 (let ((src "external/install/src/rapmap/")
11989 (include "external/install/include/rapmap/")
11990 (rapmap (assoc-ref inputs "rapmap")))
11993 (for-each (lambda (file)
11994 (install-file file src))
11995 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11996 (copy-recursively (string-append rapmap "/include") include)
11997 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11998 "external/install/include/rapmap/FastxParser.hpp"
11999 "external/install/include/rapmap/concurrentqueue.h"
12000 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12001 "external/install/src/rapmap/FastxParser.cpp"
12002 "external/install/src/rapmap/xxhash.c")))))
12003 (add-after 'unpack 'use-system-libraries
12004 (lambda* (#:key inputs #:allow-other-keys)
12005 (substitute* "src/CMakeLists.txt"
12006 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12007 (string-append (assoc-ref inputs "jellyfish")
12008 "/include/jellyfish-" ,(package-version jellyfish)))
12009 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12010 (string-append (assoc-ref inputs "jellyfish")
12011 "/lib/libjellyfish-2.0.a"))
12012 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12013 (string-append (assoc-ref inputs "libdivsufsort")
12014 "/lib/libdivsufsort.so"))
12015 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12016 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12017 "/lib/libstaden-read.a"))
12018 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12019 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12020 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12021 (string-append (assoc-ref inputs "libdivsufsort")
12022 "/lib/libdivsufsort64.so")))
12023 (substitute* "CMakeLists.txt"
12024 ;; Don't prefer static libs
12025 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12026 (("set\\(TBB_LIBRARIES") "message(")
12027 (("find_package\\(Jellyfish.*") "")
12028 (("ExternalProject_Add\\(libcereal") "message(")
12029 (("ExternalProject_Add\\(libbwa") "message(")
12030 (("ExternalProject_Add\\(libjellyfish") "message(")
12031 (("ExternalProject_Add\\(libgff") "message(")
12032 (("ExternalProject_Add\\(libtbb") "message(")
12033 (("ExternalProject_Add\\(libspdlog") "message(")
12034 (("ExternalProject_Add\\(libdivsufsort") "message(")
12035 (("ExternalProject_Add\\(libstadenio") "message(")
12036 (("ExternalProject_Add_Step\\(") "message("))
12038 ;; Ensure that all headers can be found
12039 (setenv "CPLUS_INCLUDE_PATH"
12040 (string-append (getenv "CPLUS_INCLUDE_PATH")
12042 (assoc-ref inputs "bwa")
12045 (assoc-ref inputs "eigen")
12046 "/include/eigen3"))
12048 (string-append (assoc-ref inputs "bwa")
12051 (assoc-ref inputs "eigen")
12052 "/include/eigen3"))
12054 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12055 ;; run. It only exists after the install phase.
12056 (add-after 'unpack 'fix-tests
12058 (substitute* "src/CMakeLists.txt"
12059 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12060 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12064 ("bwa" ,bwa-for-salmon)
12070 (uri (git-reference
12071 (url "https://github.com/COMBINE-lab/RapMap.git")
12072 (commit (string-append "salmon-v" version))))
12073 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12076 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12077 ("jemalloc" ,jemalloc)
12078 ("jellyfish" ,jellyfish)
12081 ("libdivsufsort" ,libdivsufsort)
12082 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12083 ("spdlog-for-salmon" ,spdlog-for-salmon)
12086 (home-page "https://github.com/COMBINE-lab/salmon")
12087 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12088 (description "Salmon is a program to produce highly-accurate,
12089 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12090 its accuracy and speed via a number of different innovations, including the
12091 use of lightweight alignments (accurate but fast-to-compute proxies for
12092 traditional read alignments) and massively-parallel stochastic collapsed
12093 variational inference.")
12094 (license license:gpl3+)))
12096 (define-public python-loompy
12098 (name "python-loompy")
12103 (uri (pypi-uri "loompy" version))
12106 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12107 (build-system python-build-system)
12108 ;; There are no tests
12109 (arguments '(#:tests? #f))
12111 `(("python-h5py" ,python-h5py)
12112 ("python-numpy" ,python-numpy)
12113 ("python-scipy" ,python-scipy)
12114 ("python-typing" ,python-typing)))
12115 (home-page "https://github.com/linnarsson-lab/loompy")
12116 (synopsis "Work with .loom files for single-cell RNA-seq data")
12117 (description "The loom file format is an efficient format for very large
12118 omics datasets, consisting of a main matrix, optional additional layers, a
12119 variable number of row and column annotations. Loom also supports sparse
12120 graphs. This library makes it easy to work with @file{.loom} files for
12121 single-cell RNA-seq data.")
12122 (license license:bsd-3)))
12124 ;; We cannot use the latest commit because it requires Java 9.
12125 (define-public java-forester
12126 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12129 (name "java-forester")
12130 (version (string-append "0-" revision "." (string-take commit 7)))
12133 (uri (git-reference
12134 (url "https://github.com/cmzmasek/forester.git")
12136 (file-name (string-append name "-" version "-checkout"))
12139 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12140 (modules '((guix build utils)))
12143 ;; Delete bundled jars and pre-built classes
12144 (delete-file-recursively "forester/java/resources")
12145 (delete-file-recursively "forester/java/classes")
12146 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12147 ;; Delete bundled applications
12148 (delete-file-recursively "forester_applications")
12150 (build-system ant-build-system)
12152 `(#:tests? #f ; there are none
12154 #:modules ((guix build ant-build-system)
12156 (guix build java-utils)
12160 (modify-phases %standard-phases
12161 (add-after 'unpack 'chdir
12162 (lambda _ (chdir "forester/java") #t))
12163 (add-after 'chdir 'fix-dependencies
12165 (chmod "build.xml" #o664)
12166 (call-with-output-file "build.xml.new"
12170 (with-input-from-file "build.xml"
12171 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12172 `(;; Remove all unjar tags to avoid repacking classes.
12173 (unjar . ,(lambda _ '()))
12174 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12175 (*text* . ,(lambda (_ txt) txt))))
12177 (rename-file "build.xml.new" "build.xml")
12179 ;; FIXME: itext is difficult to package as it depends on a few
12180 ;; unpackaged libraries.
12181 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12183 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12184 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12185 (("pdf_written_to = PdfExporter.*")
12186 "throw new IOException(\"PDF export is not available.\");"))
12188 ;; There is no install target
12189 (replace 'install (install-jars ".")))))
12191 `(("java-commons-codec" ,java-commons-codec)
12192 ("java-openchart2" ,java-openchart2)))
12193 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12194 (synopsis "Phylogenomics libraries for Java")
12195 (description "Forester is a collection of Java libraries for
12196 phylogenomics and evolutionary biology research. It includes support for
12197 reading, writing, and exporting phylogenetic trees.")
12198 (license license:lgpl2.1+))))
12200 (define-public java-forester-1.005
12202 (name "java-forester")
12206 (uri (string-append "http://search.maven.org/remotecontent?"
12207 "filepath=org/biojava/thirdparty/forester/"
12208 version "/forester-" version "-sources.jar"))
12209 (file-name (string-append name "-" version ".jar"))
12212 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12213 (build-system ant-build-system)
12215 `(#:tests? #f ; there are none
12217 #:modules ((guix build ant-build-system)
12219 (guix build java-utils)
12223 (modify-phases %standard-phases
12224 (add-after 'unpack 'fix-dependencies
12225 (lambda* (#:key inputs #:allow-other-keys)
12226 (call-with-output-file "build.xml"
12230 (with-input-from-file "src/build.xml"
12231 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12232 `(;; Remove all unjar tags to avoid repacking classes.
12233 (unjar . ,(lambda _ '()))
12234 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12235 (*text* . ,(lambda (_ txt) txt))))
12237 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12238 "synth_look_and_feel_1.xml")
12239 (copy-file (assoc-ref inputs "phyloxml.xsd")
12241 (substitute* "build.xml"
12242 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12243 "synth_look_and_feel_1.xml")
12244 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12247 ;; FIXME: itext is difficult to package as it depends on a few
12248 ;; unpackaged libraries.
12249 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12251 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12252 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12253 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12254 (("pdf_written_to = PdfExporter.*")
12255 "throw new IOException(\"PDF export is not available.\"); /*")
12256 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12257 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12259 (add-after 'unpack 'delete-pre-built-classes
12260 (lambda _ (delete-file-recursively "src/classes") #t))
12261 ;; There is no install target
12262 (replace 'install (install-jars ".")))))
12264 `(("java-commons-codec" ,java-commons-codec)
12265 ("java-openchart2" ,java-openchart2)))
12266 ;; The source archive does not contain the resources.
12271 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12272 "b61cc2dcede0bede317db362472333115756b8c6/"
12273 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12274 (file-name (string-append name "-phyloxml-" version ".xsd"))
12277 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12278 ("synth_look_and_feel_1.xml"
12281 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12282 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12283 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12284 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12287 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12288 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12289 (synopsis "Phylogenomics libraries for Java")
12290 (description "Forester is a collection of Java libraries for
12291 phylogenomics and evolutionary biology research. It includes support for
12292 reading, writing, and exporting phylogenetic trees.")
12293 (license license:lgpl2.1+)))
12295 (define-public java-biojava-core
12297 (name "java-biojava-core")
12301 (uri (git-reference
12302 (url "https://github.com/biojava/biojava")
12303 (commit (string-append "biojava-" version))))
12304 (file-name (string-append name "-" version "-checkout"))
12307 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12308 (build-system ant-build-system)
12311 #:jar-name "biojava-core.jar"
12312 #:source-dir "biojava-core/src/main/java/"
12313 #:test-dir "biojava-core/src/test"
12314 ;; These tests seem to require internet access.
12315 #:test-exclude (list "**/SearchIOTest.java"
12316 "**/BlastXMLParserTest.java"
12317 "**/GenbankCookbookTest.java"
12318 "**/GenbankProxySequenceReaderTest.java")
12320 (modify-phases %standard-phases
12321 (add-before 'build 'copy-resources
12323 (copy-recursively "biojava-core/src/main/resources"
12326 (add-before 'check 'copy-test-resources
12328 (copy-recursively "biojava-core/src/test/resources"
12329 "build/test-classes")
12332 `(("java-log4j-api" ,java-log4j-api)
12333 ("java-log4j-core" ,java-log4j-core)
12334 ("java-slf4j-api" ,java-slf4j-api)
12335 ("java-slf4j-simple" ,java-slf4j-simple)))
12337 `(("java-junit" ,java-junit)
12338 ("java-hamcrest-core" ,java-hamcrest-core)))
12339 (home-page "http://biojava.org")
12340 (synopsis "Core libraries of Java framework for processing biological data")
12341 (description "BioJava is a project dedicated to providing a Java framework
12342 for processing biological data. It provides analytical and statistical
12343 routines, parsers for common file formats, reference implementations of
12344 popular algorithms, and allows the manipulation of sequences and 3D
12345 structures. The goal of the biojava project is to facilitate rapid
12346 application development for bioinformatics.
12348 This package provides the core libraries.")
12349 (license license:lgpl2.1+)))
12351 (define-public java-biojava-phylo
12352 (package (inherit java-biojava-core)
12353 (name "java-biojava-phylo")
12354 (build-system ant-build-system)
12357 #:jar-name "biojava-phylo.jar"
12358 #:source-dir "biojava-phylo/src/main/java/"
12359 #:test-dir "biojava-phylo/src/test"
12361 (modify-phases %standard-phases
12362 (add-before 'build 'copy-resources
12364 (copy-recursively "biojava-phylo/src/main/resources"
12367 (add-before 'check 'copy-test-resources
12369 (copy-recursively "biojava-phylo/src/test/resources"
12370 "build/test-classes")
12373 `(("java-log4j-api" ,java-log4j-api)
12374 ("java-log4j-core" ,java-log4j-core)
12375 ("java-slf4j-api" ,java-slf4j-api)
12376 ("java-slf4j-simple" ,java-slf4j-simple)
12377 ("java-biojava-core" ,java-biojava-core)
12378 ("java-forester" ,java-forester)))
12380 `(("java-junit" ,java-junit)
12381 ("java-hamcrest-core" ,java-hamcrest-core)))
12382 (home-page "http://biojava.org")
12383 (synopsis "Biojava interface to the forester phylogenomics library")
12384 (description "The phylo module provides a biojava interface layer to the
12385 forester phylogenomics library for constructing phylogenetic trees.")))
12387 (define-public java-biojava-alignment
12388 (package (inherit java-biojava-core)
12389 (name "java-biojava-alignment")
12390 (build-system ant-build-system)
12393 #:jar-name "biojava-alignment.jar"
12394 #:source-dir "biojava-alignment/src/main/java/"
12395 #:test-dir "biojava-alignment/src/test"
12397 (modify-phases %standard-phases
12398 (add-before 'build 'copy-resources
12400 (copy-recursively "biojava-alignment/src/main/resources"
12403 (add-before 'check 'copy-test-resources
12405 (copy-recursively "biojava-alignment/src/test/resources"
12406 "build/test-classes")
12409 `(("java-log4j-api" ,java-log4j-api)
12410 ("java-log4j-core" ,java-log4j-core)
12411 ("java-slf4j-api" ,java-slf4j-api)
12412 ("java-slf4j-simple" ,java-slf4j-simple)
12413 ("java-biojava-core" ,java-biojava-core)
12414 ("java-biojava-phylo" ,java-biojava-phylo)
12415 ("java-forester" ,java-forester)))
12417 `(("java-junit" ,java-junit)
12418 ("java-hamcrest-core" ,java-hamcrest-core)))
12419 (home-page "http://biojava.org")
12420 (synopsis "Biojava API for genetic sequence alignment")
12421 (description "The alignment module of BioJava provides an API that
12425 @item implementations of dynamic programming algorithms for sequence
12427 @item reading and writing of popular alignment file formats;
12428 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12431 (define-public java-biojava-core-4.0
12432 (package (inherit java-biojava-core)
12433 (name "java-biojava-core")
12437 (uri (git-reference
12438 (url "https://github.com/biojava/biojava")
12439 (commit (string-append "biojava-" version))))
12440 (file-name (string-append name "-" version "-checkout"))
12443 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12445 (define-public java-biojava-phylo-4.0
12446 (package (inherit java-biojava-core-4.0)
12447 (name "java-biojava-phylo")
12448 (build-system ant-build-system)
12451 #:jar-name "biojava-phylo.jar"
12452 #:source-dir "biojava-phylo/src/main/java/"
12453 #:test-dir "biojava-phylo/src/test"
12455 (modify-phases %standard-phases
12456 (add-before 'build 'copy-resources
12458 (copy-recursively "biojava-phylo/src/main/resources"
12461 (add-before 'check 'copy-test-resources
12463 (copy-recursively "biojava-phylo/src/test/resources"
12464 "build/test-classes")
12467 `(("java-log4j-api" ,java-log4j-api)
12468 ("java-log4j-core" ,java-log4j-core)
12469 ("java-slf4j-api" ,java-slf4j-api)
12470 ("java-slf4j-simple" ,java-slf4j-simple)
12471 ("java-biojava-core" ,java-biojava-core-4.0)
12472 ("java-forester" ,java-forester-1.005)))
12474 `(("java-junit" ,java-junit)
12475 ("java-hamcrest-core" ,java-hamcrest-core)))
12476 (home-page "http://biojava.org")
12477 (synopsis "Biojava interface to the forester phylogenomics library")
12478 (description "The phylo module provides a biojava interface layer to the
12479 forester phylogenomics library for constructing phylogenetic trees.")))
12481 (define-public java-biojava-alignment-4.0
12482 (package (inherit java-biojava-core-4.0)
12483 (name "java-biojava-alignment")
12484 (build-system ant-build-system)
12487 #:jar-name "biojava-alignment.jar"
12488 #:source-dir "biojava-alignment/src/main/java/"
12489 #:test-dir "biojava-alignment/src/test"
12491 (modify-phases %standard-phases
12492 (add-before 'build 'copy-resources
12494 (copy-recursively "biojava-alignment/src/main/resources"
12497 (add-before 'check 'copy-test-resources
12499 (copy-recursively "biojava-alignment/src/test/resources"
12500 "build/test-classes")
12503 `(("java-log4j-api" ,java-log4j-api)
12504 ("java-log4j-core" ,java-log4j-core)
12505 ("java-slf4j-api" ,java-slf4j-api)
12506 ("java-slf4j-simple" ,java-slf4j-simple)
12507 ("java-biojava-core" ,java-biojava-core-4.0)
12508 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12509 ("java-forester" ,java-forester-1.005)))
12511 `(("java-junit" ,java-junit)
12512 ("java-hamcrest-core" ,java-hamcrest-core)))
12513 (home-page "http://biojava.org")
12514 (synopsis "Biojava API for genetic sequence alignment")
12515 (description "The alignment module of BioJava provides an API that
12519 @item implementations of dynamic programming algorithms for sequence
12521 @item reading and writing of popular alignment file formats;
12522 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12525 (define-public dropseq-tools
12527 (name "dropseq-tools")
12532 (uri "http://mccarrolllab.com/download/1276/")
12533 (file-name (string-append "dropseq-tools-" version ".zip"))
12536 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12537 ;; Delete bundled libraries
12538 (modules '((guix build utils)))
12541 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12542 (delete-file-recursively "3rdParty")))))
12543 (build-system ant-build-system)
12545 `(#:tests? #f ; test data are not included
12546 #:test-target "test"
12547 #:build-target "all"
12548 #:source-dir "public/src/"
12551 (list (string-append "-Dpicard.executable.dir="
12552 (assoc-ref %build-inputs "java-picard")
12554 #:modules ((ice-9 match)
12557 (guix build java-utils)
12558 (guix build ant-build-system))
12560 (modify-phases %standard-phases
12561 ;; All dependencies must be linked to "lib", because that's where
12562 ;; they will be searched for when the Class-Path property of the
12563 ;; manifest is computed.
12564 (add-after 'unpack 'record-references
12565 (lambda* (#:key inputs #:allow-other-keys)
12566 (mkdir-p "jar/lib")
12567 (let ((dirs (filter-map (match-lambda
12569 (if (and (string-prefix? "java-" name)
12570 (not (string=? name "java-testng")))
12573 (for-each (lambda (jar)
12574 (symlink jar (string-append "jar/lib/" (basename jar))))
12575 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12578 ;; There is no installation target
12580 (lambda* (#:key inputs outputs #:allow-other-keys)
12581 (let* ((out (assoc-ref outputs "out"))
12582 (bin (string-append out "/bin"))
12583 (share (string-append out "/share/java/"))
12584 (lib (string-append share "/lib/"))
12585 (scripts (list "BAMTagHistogram"
12586 "BAMTagofTagCounts"
12587 "BaseDistributionAtReadPosition"
12588 "CollapseBarcodesInPlace"
12589 "CollapseTagWithContext"
12591 "CreateIntervalsFiles"
12592 "DetectBeadSynthesisErrors"
12593 "DigitalExpression"
12594 "Drop-seq_alignment.sh"
12597 "GatherGeneGCLength"
12598 "GatherMolecularBarcodeDistributionByGene"
12599 "GatherReadQualityMetrics"
12602 "SelectCellsByNumTranscripts"
12603 "SingleCellRnaSeqMetricsCollector"
12604 "TagBamWithReadSequenceExtended"
12605 "TagReadWithGeneExon"
12606 "TagReadWithInterval"
12607 "TrimStartingSequence"
12608 "ValidateReference")))
12609 (for-each mkdir-p (list bin share lib))
12610 (install-file "dist/dropseq.jar" share)
12611 (for-each (lambda (script)
12612 (chmod script #o555)
12613 (install-file script bin))
12615 (substitute* (map (lambda (script)
12616 (string-append bin "/" script))
12618 (("^java") (which "java"))
12619 (("jar_deploy_dir=.*")
12620 (string-append "jar_deploy_dir=" share "\n"))))
12622 ;; FIXME: We do this after stripping jars because we don't want it to
12623 ;; copy all these jars and strip them. We only want to install
12624 ;; links. Arguably, this is a problem with the ant-build-system.
12625 (add-after 'strip-jar-timestamps 'install-links
12626 (lambda* (#:key outputs #:allow-other-keys)
12627 (let* ((out (assoc-ref outputs "out"))
12628 (share (string-append out "/share/java/"))
12629 (lib (string-append share "/lib/")))
12630 (for-each (lambda (jar)
12631 (symlink (readlink jar)
12632 (string-append lib (basename jar))))
12633 (find-files "jar/lib" "\\.jar$")))
12636 `(("jdk" ,icedtea-8)
12637 ("java-picard" ,java-picard-2.10.3)
12638 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12639 ("java-commons-math3" ,java-commons-math3)
12640 ("java-commons-jexl2" ,java-commons-jexl-2)
12641 ("java-commons-collections4" ,java-commons-collections4)
12642 ("java-commons-lang2" ,java-commons-lang)
12643 ("java-commons-io" ,java-commons-io)
12644 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12645 ("java-guava" ,java-guava)
12646 ("java-la4j" ,java-la4j)
12647 ("java-biojava-core" ,java-biojava-core-4.0)
12648 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12649 ("java-jdistlib" ,java-jdistlib)
12650 ("java-simple-xml" ,java-simple-xml)
12651 ("java-snakeyaml" ,java-snakeyaml)))
12654 ("java-testng" ,java-testng)))
12655 (home-page "http://mccarrolllab.com/dropseq/")
12656 (synopsis "Tools for Drop-seq analyses")
12657 (description "Drop-seq is a technology to enable biologists to
12658 analyze RNA expression genome-wide in thousands of individual cells at
12659 once. This package provides tools to perform Drop-seq analyses.")
12660 (license license:expat)))
12662 (define-public pigx-rnaseq
12664 (name "pigx-rnaseq")
12668 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12669 "releases/download/v" version
12670 "/pigx_rnaseq-" version ".tar.gz"))
12673 "168hx2ig3rarphx3l21ay9yyg8ipaakzixnrhpbdi0sknhyvrrk8"))))
12674 (build-system gnu-build-system)
12676 `(#:parallel-tests? #f ; not supported
12678 (modify-phases %standard-phases
12679 (add-after 'install 'wrap-executable
12680 ;; Make sure the executable finds all R modules.
12681 (lambda* (#:key inputs outputs #:allow-other-keys)
12682 (let ((out (assoc-ref outputs "out")))
12683 (wrap-program (string-append out "/bin/pigx-rnaseq")
12684 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12685 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12688 `(("snakemake" ,snakemake)
12690 ("multiqc" ,multiqc)
12692 ("trim-galore" ,trim-galore)
12694 ("samtools" ,samtools)
12695 ("bedtools" ,bedtools)
12696 ("r-minimal" ,r-minimal)
12697 ("r-rmarkdown" ,r-rmarkdown)
12698 ("r-ggplot2" ,r-ggplot2)
12699 ("r-ggrepel" ,r-ggrepel)
12700 ("r-gprofiler" ,r-gprofiler)
12701 ("r-deseq2" ,r-deseq2)
12703 ("r-knitr" ,r-knitr)
12704 ("r-pheatmap" ,r-pheatmap)
12705 ("r-corrplot" ,r-corrplot)
12706 ("r-reshape2" ,r-reshape2)
12707 ("r-plotly" ,r-plotly)
12708 ("r-scales" ,r-scales)
12709 ("r-summarizedexperiment" ,r-summarizedexperiment)
12710 ("r-crosstalk" ,r-crosstalk)
12711 ("r-tximport" ,r-tximport)
12712 ("r-rtracklayer" ,r-rtracklayer)
12713 ("r-rjson" ,r-rjson)
12715 ("ghc-pandoc" ,ghc-pandoc)
12716 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12717 ("python-wrapper" ,python-wrapper)
12718 ("python-pyyaml" ,python-pyyaml)))
12719 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12720 (synopsis "Analysis pipeline for RNA sequencing experiments")
12721 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12722 reporting for RNA sequencing experiments. It is easy to use and produces high
12723 quality reports. The inputs are reads files from the sequencing experiment,
12724 and a configuration file which describes the experiment. In addition to
12725 quality control of the experiment, the pipeline produces a differential
12726 expression report comparing samples in an easily configurable manner.")
12727 (license license:gpl3+)))
12729 (define-public pigx-chipseq
12731 (name "pigx-chipseq")
12735 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12736 "releases/download/v" version
12737 "/pigx_chipseq-" version ".tar.gz"))
12740 "1jliwhifnjgl9x0z730bzpxswi2s84fyg5y8cagbyzpw509452f5"))))
12741 (build-system gnu-build-system)
12744 (modify-phases %standard-phases
12745 (add-after 'install 'wrap-executable
12746 ;; Make sure the executable finds all R modules.
12747 (lambda* (#:key inputs outputs #:allow-other-keys)
12748 (let ((out (assoc-ref outputs "out")))
12749 (wrap-program (string-append out "/bin/pigx-chipseq")
12750 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12751 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12754 `(("r-minimal" ,r-minimal)
12755 ("r-argparser" ,r-argparser)
12756 ("r-chipseq" ,r-chipseq)
12757 ("r-data-table" ,r-data-table)
12758 ("r-genomation" ,r-genomation)
12759 ("r-genomicranges" ,r-genomicranges)
12760 ("r-rtracklayer" ,r-rtracklayer)
12762 ("r-stringr" ,r-stringr)
12763 ("r-jsonlite" ,r-jsonlite)
12764 ("r-heatmaply" ,r-heatmaply)
12765 ("r-ggplot2" ,r-ggplot2)
12766 ("r-plotly" ,r-plotly)
12767 ("python-wrapper" ,python-wrapper)
12768 ("python-pyyaml" ,python-pyyaml)
12769 ("snakemake" ,snakemake)
12771 ("multiqc" ,multiqc)
12773 ("ghc-pandoc" ,ghc-pandoc)
12774 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12778 ("snakemake" ,snakemake)
12779 ("samtools" ,samtools)
12780 ("bedtools" ,bedtools)
12781 ("kentutils" ,kentutils)))
12783 `(("python-pytest" ,python-pytest)))
12784 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12785 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12786 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12787 calling and reporting for ChIP sequencing experiments. It is easy to use and
12788 produces high quality reports. The inputs are reads files from the sequencing
12789 experiment, and a configuration file which describes the experiment. In
12790 addition to quality control of the experiment, the pipeline enables to set up
12791 multiple peak calling analysis and allows the generation of a UCSC track hub
12792 in an easily configurable manner.")
12793 (license license:gpl3+)))
12795 (define-public pigx-bsseq
12797 (name "pigx-bsseq")
12801 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12802 "releases/download/v" version
12803 "/pigx_bsseq-" version ".tar.gz"))
12806 "1h8ma99vi7hs83nafvjpq8jmaq9977j3n11c4zd95hai0cf7zxmp"))))
12807 (build-system gnu-build-system)
12810 (modify-phases %standard-phases
12811 (add-before 'check 'set-timezone
12812 ;; The readr package is picky about timezones.
12813 (lambda* (#:key inputs #:allow-other-keys)
12814 (setenv "TZ" "UTC+1")
12816 (string-append (assoc-ref inputs "tzdata")
12817 "/share/zoneinfo"))
12819 (add-after 'install 'wrap-executable
12820 ;; Make sure the executable finds all R modules.
12821 (lambda* (#:key inputs outputs #:allow-other-keys)
12822 (let ((out (assoc-ref outputs "out")))
12823 (wrap-program (string-append out "/bin/pigx-bsseq")
12824 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12825 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12828 `(("tzdata" ,tzdata)))
12830 `(("r-minimal" ,r-minimal)
12831 ("r-annotationhub" ,r-annotationhub)
12833 ("r-genomation" ,r-genomation)
12834 ("r-methylkit" ,r-methylkit)
12835 ("r-rtracklayer" ,r-rtracklayer)
12836 ("r-rmarkdown" ,r-rmarkdown)
12837 ("r-bookdown" ,r-bookdown)
12838 ("r-ggplot2" ,r-ggplot2)
12839 ("r-ggbio" ,r-ggbio)
12840 ("ghc-pandoc" ,ghc-pandoc)
12841 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12842 ("python-wrapper" ,python-wrapper)
12843 ("python-pyyaml" ,python-pyyaml)
12844 ("snakemake" ,snakemake)
12845 ("bismark" ,bismark)
12848 ("trim-galore" ,trim-galore)
12849 ("cutadapt" ,cutadapt)
12850 ("samtools" ,samtools)))
12851 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12852 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12853 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12854 data of bisulfite experiments; it produces reports on aggregate methylation
12855 and coverage and can be used to produce information on differential
12856 methylation and segmentation.")
12857 (license license:gpl3+)))