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))
120 (uri (cran-uri "ape" version))
123 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
124 (build-system r-build-system)
126 `(("r-lattice" ,r-lattice)
129 (home-page "http://ape-package.ird.fr/")
130 (synopsis "Analyses of phylogenetics and evolution")
132 "This package provides functions for reading, writing, plotting, and
133 manipulating phylogenetic trees, analyses of comparative data in a
134 phylogenetic framework, ancestral character analyses, analyses of
135 diversification and macroevolution, computing distances from DNA sequences,
136 and several other tools.")
137 (license license:gpl2+)))
139 (define-public aragorn
146 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
150 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
151 (build-system gnu-build-system)
153 `(#:tests? #f ; there are no tests
155 (modify-phases %standard-phases
159 (zero? (system* "gcc"
165 (string-append "aragorn" ,version ".c")))))
167 (lambda* (#:key outputs #:allow-other-keys)
168 (let* ((out (assoc-ref outputs "out"))
169 (bin (string-append out "/bin"))
170 (man (string-append out "/share/man/man1")))
172 (install-file "aragorn" bin)
174 (install-file "aragorn.1" man))
176 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
177 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
179 "Aragorn identifies transfer RNA, mitochondrial RNA and
180 transfer-messenger RNA from nucleotide sequences, based on homology to known
181 tRNA consensus sequences and RNA structure. It also outputs the secondary
182 structure of the predicted RNA.")
183 (license license:gpl2)))
191 ;; BamM is not available on pypi.
193 "https://github.com/Ecogenomics/BamM/archive/"
195 (file-name (string-append name "-" version ".tar.gz"))
198 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
199 (modules '((guix build utils)))
202 ;; Delete bundled htslib.
203 (delete-file-recursively "c/htslib-1.3.1")
205 (build-system python-build-system)
207 `(#:python ,python-2 ; BamM is Python 2 only.
208 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
209 ;; been modified from its original form.
211 (let ((htslib (assoc-ref %build-inputs "htslib")))
212 (list "--with-libhts-lib" (string-append htslib "/lib")
213 "--with-libhts-inc" (string-append htslib "/include/htslib")))
215 (modify-phases %standard-phases
216 (add-after 'unpack 'autogen
218 (with-directory-excursion "c"
219 (let ((sh (which "sh")))
220 ;; Use autogen so that 'configure' works.
221 (substitute* "autogen.sh" (("/bin/sh") sh))
222 (setenv "CONFIG_SHELL" sh)
223 (substitute* "configure" (("/bin/sh") sh))
224 (zero? (system* "./autogen.sh"))))))
226 ;; Run tests after installation so compilation only happens once.
228 (add-after 'install 'wrap-executable
229 (lambda* (#:key outputs #:allow-other-keys)
230 (let* ((out (assoc-ref outputs "out"))
231 (path (getenv "PATH")))
232 (wrap-program (string-append out "/bin/bamm")
233 `("PATH" ":" prefix (,path))))
235 (add-after 'wrap-executable 'post-install-check
236 (lambda* (#:key inputs outputs #:allow-other-keys)
238 (string-append (assoc-ref outputs "out")
243 (assoc-ref outputs "out")
245 (string-take (string-take-right
246 (assoc-ref inputs "python") 5) 3)
248 (getenv "PYTHONPATH")))
249 ;; There are 2 errors printed, but they are safe to ignore:
250 ;; 1) [E::hts_open_format] fail to open file ...
251 ;; 2) samtools view: failed to open ...
252 (zero? (system* "nosetests")))))))
254 `(("autoconf" ,autoconf)
255 ("automake" ,automake)
258 ("python-nose" ,python2-nose)
259 ("python-pysam" ,python2-pysam)))
261 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
262 ("samtools" ,samtools)
266 ("coreutils" ,coreutils)))
268 `(("python-numpy" ,python2-numpy)))
269 (home-page "http://ecogenomics.github.io/BamM/")
270 (synopsis "Metagenomics-focused BAM file manipulator")
272 "BamM is a C library, wrapped in python, to efficiently generate and
273 parse BAM files, specifically for the analysis of metagenomic data. For
274 instance, it implements several methods to assess contig-wise read coverage.")
275 (license license:lgpl3+)))
277 (define-public bamtools
284 "https://github.com/pezmaster31/bamtools/archive/v"
286 (file-name (string-append name "-" version ".tar.gz"))
289 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
290 (build-system cmake-build-system)
292 `(#:tests? #f ;no "check" target
294 (modify-phases %standard-phases
296 'configure 'set-ldflags
297 (lambda* (#:key outputs #:allow-other-keys)
301 (assoc-ref outputs "out") "/lib/bamtools")))))))
302 (inputs `(("zlib" ,zlib)))
303 (home-page "https://github.com/pezmaster31/bamtools")
304 (synopsis "C++ API and command-line toolkit for working with BAM data")
306 "BamTools provides both a C++ API and a command-line toolkit for handling
308 (license license:expat)))
310 (define-public bcftools
317 "https://github.com/samtools/bcftools/releases/download/"
318 version "/bcftools-" version ".tar.bz2"))
321 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
322 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
323 (modules '((guix build utils)))
325 ;; Delete bundled htslib.
326 '(delete-file-recursively "htslib-1.5"))))
327 (build-system gnu-build-system)
329 `(#:test-target "test"
330 #:configure-flags (list "--with-htslib=system")
334 "LIBS=-lgsl -lgslcblas"
335 (string-append "prefix=" (assoc-ref %outputs "out"))
336 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
337 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
338 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
339 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
340 (string-append "PACKAGE_VERSION=" ,version))
342 (modify-phases %standard-phases
343 (add-before 'check 'patch-tests
345 (substitute* "test/test.pl"
346 (("/bin/bash") (which "bash")))
354 (home-page "https://samtools.github.io/bcftools/")
355 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
357 "BCFtools is a set of utilities that manipulate variant calls in the
358 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
359 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
360 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
361 (license (list license:gpl3+ license:expat))))
363 (define-public bedops
369 (uri (string-append "https://github.com/bedops/bedops/archive/v"
371 (file-name (string-append name "-" version ".tar.gz"))
374 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
375 (build-system gnu-build-system)
378 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
380 (modify-phases %standard-phases
381 (add-after 'unpack 'unpack-tarballs
383 ;; FIXME: Bedops includes tarballs of minimally patched upstream
384 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
385 ;; libraries because at least one of the libraries (zlib) is
386 ;; patched to add a C++ function definition (deflateInit2cpp).
387 ;; Until the Bedops developers offer a way to link against system
388 ;; libraries we have to build the in-tree copies of these three
391 ;; See upstream discussion:
392 ;; https://github.com/bedops/bedops/issues/124
394 ;; Unpack the tarballs to benefit from shebang patching.
395 (with-directory-excursion "third-party"
396 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
397 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
398 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
399 ;; Disable unpacking of tarballs in Makefile.
400 (substitute* "system.mk/Makefile.linux"
401 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
402 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
403 (substitute* "third-party/zlib-1.2.7/Makefile.in"
404 (("^SHELL=.*$") "SHELL=bash\n"))
406 (delete 'configure))))
407 (home-page "https://github.com/bedops/bedops")
408 (synopsis "Tools for high-performance genomic feature operations")
410 "BEDOPS is a suite of tools to address common questions raised in genomic
411 studies---mostly with regard to overlap and proximity relationships between
412 data sets. It aims to be scalable and flexible, facilitating the efficient
413 and accurate analysis and management of large-scale genomic data.
415 BEDOPS provides tools that perform highly efficient and scalable Boolean and
416 other set operations, statistical calculations, archiving, conversion and
417 other management of genomic data of arbitrary scale. Tasks can be easily
418 split by chromosome for distributing whole-genome analyses across a
419 computational cluster.")
420 (license license:gpl2+)))
422 (define-public bedtools
428 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
429 "download/v" version "/"
430 "bedtools-" version ".tar.gz"))
433 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
434 (build-system gnu-build-system)
436 '(#:test-target "test"
438 (list (string-append "prefix=" (assoc-ref %outputs "out")))
440 (modify-phases %standard-phases
441 (delete 'configure))))
442 (native-inputs `(("python" ,python-2)))
444 `(("samtools" ,samtools)
446 (home-page "https://github.com/arq5x/bedtools2")
447 (synopsis "Tools for genome analysis and arithmetic")
449 "Collectively, the bedtools utilities are a swiss-army knife of tools for
450 a wide-range of genomics analysis tasks. The most widely-used tools enable
451 genome arithmetic: that is, set theory on the genome. For example, bedtools
452 allows one to intersect, merge, count, complement, and shuffle genomic
453 intervals from multiple files in widely-used genomic file formats such as BAM,
455 (license license:gpl2)))
457 ;; Later releases of bedtools produce files with more columns than
458 ;; what Ribotaper expects.
459 (define-public bedtools-2.18
460 (package (inherit bedtools)
465 (uri (string-append "https://github.com/arq5x/bedtools2/"
466 "archive/v" version ".tar.gz"))
467 (file-name (string-append name "-" version ".tar.gz"))
470 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
472 '(#:test-target "test"
474 (modify-phases %standard-phases
477 (lambda* (#:key outputs #:allow-other-keys)
478 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
479 (for-each (lambda (file)
480 (install-file file bin))
481 (find-files "bin" ".*")))
484 (define-public ribotaper
490 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
491 "files/RiboTaper/RiboTaper_Version_"
495 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
496 (build-system gnu-build-system)
499 (modify-phases %standard-phases
500 (add-after 'install 'wrap-executables
501 (lambda* (#:key inputs outputs #:allow-other-keys)
502 (let* ((out (assoc-ref outputs "out")))
505 (wrap-program (string-append out "/bin/" script)
506 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
507 '("create_annotations_files.bash"
508 "create_metaplots.bash"
509 "Ribotaper_ORF_find.sh"
510 "Ribotaper.sh"))))))))
512 `(("bedtools" ,bedtools-2.18)
513 ("samtools" ,samtools-0.1)
514 ("r-minimal" ,r-minimal)
515 ("r-foreach" ,r-foreach)
516 ("r-xnomial" ,r-xnomial)
518 ("r-multitaper" ,r-multitaper)
519 ("r-seqinr" ,r-seqinr)))
520 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
521 (synopsis "Define translated ORFs using ribosome profiling data")
523 "Ribotaper is a method for defining translated @dfn{open reading
524 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
525 provides the Ribotaper pipeline.")
526 (license license:gpl3+)))
528 (define-public ribodiff
535 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
536 "archive/v" version ".tar.gz"))
537 (file-name (string-append name "-" version ".tar.gz"))
540 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
541 (build-system python-build-system)
545 (modify-phases %standard-phases
546 ;; Generate an installable executable script wrapper.
547 (add-after 'unpack 'patch-setup.py
549 (substitute* "setup.py"
550 (("^(.*)packages=.*" line prefix)
551 (string-append line "\n"
552 prefix "scripts=['scripts/TE.py'],\n")))
555 `(("python-numpy" ,python2-numpy)
556 ("python-matplotlib" ,python2-matplotlib)
557 ("python-scipy" ,python2-scipy)
558 ("python-statsmodels" ,python2-statsmodels)))
560 `(("python-mock" ,python2-mock)
561 ("python-nose" ,python2-nose)))
562 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
563 (synopsis "Detect translation efficiency changes from ribosome footprints")
564 (description "RiboDiff is a statistical tool that detects the protein
565 translational efficiency change from Ribo-Seq (ribosome footprinting) and
566 RNA-Seq data. It uses a generalized linear model to detect genes showing
567 difference in translational profile taking mRNA abundance into account. It
568 facilitates us to decipher the translational regulation that behave
569 independently with transcriptional regulation.")
570 (license license:gpl3+)))
572 (define-public bioawk
578 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
580 (file-name (string-append name "-" version ".tar.gz"))
582 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
583 (build-system gnu-build-system)
589 `(#:tests? #f ; There are no tests to run.
590 ;; Bison must generate files, before other targets can build.
593 (modify-phases %standard-phases
594 (delete 'configure) ; There is no configure phase.
596 (lambda* (#:key outputs #:allow-other-keys)
597 (let* ((out (assoc-ref outputs "out"))
598 (bin (string-append out "/bin"))
599 (man (string-append out "/share/man/man1")))
601 (copy-file "awk.1" (string-append man "/bioawk.1"))
602 (install-file "bioawk" bin)))))))
603 (home-page "https://github.com/lh3/bioawk")
604 (synopsis "AWK with bioinformatics extensions")
605 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
606 support of several common biological data formats, including optionally gzip'ed
607 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
608 also adds a few built-in functions and a command line option to use TAB as the
609 input/output delimiter. When the new functionality is not used, bioawk is
610 intended to behave exactly the same as the original BWK awk.")
611 (license license:x11)))
613 (define-public python2-pybedtools
615 (name "python2-pybedtools")
620 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
624 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
625 (build-system python-build-system)
626 (arguments `(#:python ,python-2)) ; no Python 3 support
628 `(("python-matplotlib" ,python2-matplotlib)))
630 `(("bedtools" ,bedtools)
631 ("samtools" ,samtools)))
633 `(("python-cython" ,python2-cython)
634 ("python-pyyaml" ,python2-pyyaml)
635 ("python-nose" ,python2-nose)))
636 (home-page "https://pythonhosted.org/pybedtools/")
637 (synopsis "Python wrapper for BEDtools programs")
639 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
640 which are widely used for genomic interval manipulation or \"genome algebra\".
641 pybedtools extends BEDTools by offering feature-level manipulations from with
643 (license license:gpl2+)))
645 (define-public python-biom-format
647 (name "python-biom-format")
652 ;; Use GitHub as source because PyPI distribution does not contain
653 ;; test data: https://github.com/biocore/biom-format/issues/693
654 (uri (string-append "https://github.com/biocore/biom-format/archive/"
656 (file-name (string-append name "-" version ".tar.gz"))
659 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
660 (build-system python-build-system)
662 `(("python-numpy" ,python-numpy)
663 ("python-scipy" ,python-scipy)
664 ("python-future" ,python-future)
665 ("python-click" ,python-click)
666 ("python-h5py" ,python-h5py)
667 ("python-pandas" ,python-pandas)))
669 `(("python-nose" ,python-nose)))
670 (home-page "http://www.biom-format.org")
671 (synopsis "Biological Observation Matrix (BIOM) format utilities")
673 "The BIOM file format is designed to be a general-use format for
674 representing counts of observations e.g. operational taxonomic units, KEGG
675 orthology groups or lipid types, in one or more biological samples
676 e.g. microbiome samples, genomes, metagenomes.")
677 (license license:bsd-3)
678 (properties `((python2-variant . ,(delay python2-biom-format))))))
680 (define-public python2-biom-format
681 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
686 (modify-phases %standard-phases
687 ;; Do not require the unmaintained pyqi library.
688 (add-after 'unpack 'remove-pyqi
690 (substitute* "setup.py"
691 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
693 ,@(package-arguments base))))))
695 (define-public bioperl-minimal
696 (let* ((inputs `(("perl-module-build" ,perl-module-build)
697 ("perl-data-stag" ,perl-data-stag)
698 ("perl-libwww" ,perl-libwww)
699 ("perl-uri" ,perl-uri)))
701 (map (compose package-name cadr)
704 (map (compose package-transitive-target-inputs cadr) inputs))))))
706 (name "bioperl-minimal")
711 (uri (string-append "https://github.com/bioperl/bioperl-live/"
713 (string-map (lambda (c)
719 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
720 (build-system perl-build-system)
723 (modify-phases %standard-phases
725 'install 'wrap-programs
726 (lambda* (#:key outputs #:allow-other-keys)
727 ;; Make sure all executables in "bin" find the required Perl
728 ;; modules at runtime. As the PERL5LIB variable contains also
729 ;; the paths of native inputs, we pick the transitive target
730 ;; inputs from %build-inputs.
731 (let* ((out (assoc-ref outputs "out"))
732 (bin (string-append out "/bin/"))
734 (cons (string-append out "/lib/perl5/site_perl")
736 (assoc-ref %build-inputs name))
737 ',transitive-inputs))
739 (for-each (lambda (file)
741 `("PERL5LIB" ":" prefix (,path))))
742 (find-files bin "\\.pl$"))
746 `(("perl-test-most" ,perl-test-most)))
747 (home-page "http://search.cpan.org/dist/BioPerl")
748 (synopsis "Bioinformatics toolkit")
750 "BioPerl is the product of a community effort to produce Perl code which
751 is useful in biology. Examples include Sequence objects, Alignment objects
752 and database searching objects. These objects not only do what they are
753 advertised to do in the documentation, but they also interact - Alignment
754 objects are made from the Sequence objects, Sequence objects have access to
755 Annotation and SeqFeature objects and databases, Blast objects can be
756 converted to Alignment objects, and so on. This means that the objects
757 provide a coordinated and extensible framework to do computational biology.")
758 (license license:perl-license))))
760 (define-public python-biopython
762 (name "python-biopython")
766 ;; use PyPi rather than biopython.org to ease updating
767 (uri (pypi-uri "biopython" version))
770 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
771 (build-system python-build-system)
774 (modify-phases %standard-phases
775 (add-before 'check 'set-home
776 ;; Some tests require a home directory to be set.
777 (lambda _ (setenv "HOME" "/tmp") #t)))))
779 `(("python-numpy" ,python-numpy)))
780 (home-page "http://biopython.org/")
781 (synopsis "Tools for biological computation in Python")
783 "Biopython is a set of tools for biological computation including parsers
784 for bioinformatics files into Python data structures; interfaces to common
785 bioinformatics programs; a standard sequence class and tools for performing
786 common operations on them; code to perform data classification; code for
787 dealing with alignments; code making it easy to split up parallelizable tasks
788 into separate processes; and more.")
789 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
791 (define-public python2-biopython
792 (package-with-python2 python-biopython))
794 (define-public bpp-core
795 ;; The last release was in 2014 and the recommended way to install from source
796 ;; is to clone the git repository, so we do this.
797 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
798 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
801 (version (string-append "2.2.0-1." (string-take commit 7)))
805 (url "http://biopp.univ-montp2.fr/git/bpp-core")
807 (file-name (string-append name "-" version "-checkout"))
810 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
811 (build-system cmake-build-system)
813 `(#:parallel-build? #f))
815 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
816 ; compile all of the bpp packages with GCC 5.
817 (home-page "http://biopp.univ-montp2.fr")
818 (synopsis "C++ libraries for Bioinformatics")
820 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
821 analysis, phylogenetics, molecular evolution and population genetics. It is
822 Object Oriented and is designed to be both easy to use and computer efficient.
823 Bio++ intends to help programmers to write computer expensive programs, by
824 providing them a set of re-usable tools.")
825 (license license:cecill-c))))
827 (define-public bpp-phyl
828 ;; The last release was in 2014 and the recommended way to install from source
829 ;; is to clone the git repository, so we do this.
830 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
831 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
834 (version (string-append "2.2.0-1." (string-take commit 7)))
838 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
840 (file-name (string-append name "-" version "-checkout"))
843 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
844 (build-system cmake-build-system)
846 `(#:parallel-build? #f
847 ;; If out-of-source, test data is not copied into the build directory
848 ;; so the tests fail.
849 #:out-of-source? #f))
851 `(("bpp-core" ,bpp-core)
853 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
856 (home-page "http://biopp.univ-montp2.fr")
857 (synopsis "Bio++ phylogenetic Library")
859 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
860 analysis, phylogenetics, molecular evolution and population genetics. This
861 library provides phylogenetics-related modules.")
862 (license license:cecill-c))))
864 (define-public bpp-popgen
865 ;; The last release was in 2014 and the recommended way to install from source
866 ;; is to clone the git repository, so we do this.
867 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
868 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
871 (version (string-append "2.2.0-1." (string-take commit 7)))
875 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
877 (file-name (string-append name "-" version "-checkout"))
880 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
881 (build-system cmake-build-system)
883 `(#:parallel-build? #f
884 #:tests? #f)) ; There are no tests.
886 `(("bpp-core" ,bpp-core)
889 (home-page "http://biopp.univ-montp2.fr")
890 (synopsis "Bio++ population genetics library")
892 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
893 analysis, phylogenetics, molecular evolution and population genetics. This
894 library provides population genetics-related modules.")
895 (license license:cecill-c))))
897 (define-public bpp-seq
898 ;; The last release was in 2014 and the recommended way to install from source
899 ;; is to clone the git repository, so we do this.
900 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
901 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
904 (version (string-append "2.2.0-1." (string-take commit 7)))
908 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
910 (file-name (string-append name "-" version "-checkout"))
913 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
914 (build-system cmake-build-system)
916 `(#:parallel-build? #f
917 ;; If out-of-source, test data is not copied into the build directory
918 ;; so the tests fail.
919 #:out-of-source? #f))
921 `(("bpp-core" ,bpp-core)
922 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
923 (home-page "http://biopp.univ-montp2.fr")
924 (synopsis "Bio++ sequence library")
926 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
927 analysis, phylogenetics, molecular evolution and population genetics. This
928 library provides sequence-related modules.")
929 (license license:cecill-c))))
931 (define-public bppsuite
932 ;; The last release was in 2014 and the recommended way to install from source
933 ;; is to clone the git repository, so we do this.
934 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
935 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
938 (version (string-append "2.2.0-1." (string-take commit 7)))
942 (url "http://biopp.univ-montp2.fr/git/bppsuite")
944 (file-name (string-append name "-" version "-checkout"))
947 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
948 (build-system cmake-build-system)
950 `(#:parallel-build? #f
951 #:tests? #f)) ; There are no tests.
955 ("texinfo" ,texinfo)))
957 `(("bpp-core" ,bpp-core)
959 ("bpp-phyl" ,bpp-phyl)
960 ("bpp-phyl" ,bpp-popgen)
962 (home-page "http://biopp.univ-montp2.fr")
963 (synopsis "Bioinformatics tools written with the Bio++ libraries")
965 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
966 analysis, phylogenetics, molecular evolution and population genetics. This
967 package provides command line tools using the Bio++ library.")
968 (license license:cecill-c))))
970 (define-public blast+
977 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
978 version "/ncbi-blast-" version "+-src.tar.gz"))
981 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
982 (patches (search-patches "blast+-fix-makefile.patch"))
983 (modules '((guix build utils)))
986 ;; Remove bundled bzip2, zlib and pcre.
987 (delete-file-recursively "c++/src/util/compress/bzip2")
988 (delete-file-recursively "c++/src/util/compress/zlib")
989 (delete-file-recursively "c++/src/util/regexp")
990 (substitute* "c++/src/util/compress/Makefile.in"
991 (("bzip2 zlib api") "api"))
992 ;; Remove useless msbuild directory
993 (delete-file-recursively
994 "c++/src/build-system/project_tree_builder/msbuild")
996 (build-system gnu-build-system)
998 `(;; There are two(!) tests for this massive library, and both fail with
999 ;; "unparsable timing stats".
1000 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1001 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1004 #:parallel-build? #f ; not supported
1006 (modify-phases %standard-phases
1008 'configure 'set-HOME
1009 ;; $HOME needs to be set at some point during the configure phase
1010 (lambda _ (setenv "HOME" "/tmp") #t))
1013 (lambda _ (chdir "c++") #t))
1015 'enter-dir 'fix-build-system
1017 (define (which* cmd)
1018 (cond ((string=? cmd "date")
1019 ;; make call to "date" deterministic
1024 (format (current-error-port)
1025 "WARNING: Unable to find absolute path for ~s~%"
1029 ;; Rewrite hardcoded paths to various tools
1030 (substitute* (append '("src/build-system/configure.ac"
1031 "src/build-system/configure"
1032 "src/build-system/helpers/run_with_lock.c"
1033 "scripts/common/impl/if_diff.sh"
1034 "scripts/common/impl/run_with_lock.sh"
1035 "src/build-system/Makefile.configurables.real"
1036 "src/build-system/Makefile.in.top"
1037 "src/build-system/Makefile.meta.gmake=no"
1038 "src/build-system/Makefile.meta.in"
1039 "src/build-system/Makefile.meta_l"
1040 "src/build-system/Makefile.meta_p"
1041 "src/build-system/Makefile.meta_r"
1042 "src/build-system/Makefile.mk.in"
1043 "src/build-system/Makefile.requirements"
1044 "src/build-system/Makefile.rules_with_autodep.in")
1045 (find-files "scripts/common/check" "\\.sh$"))
1046 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1047 (or (which* cmd) all)))
1049 (substitute* (find-files "src/build-system" "^config.*")
1050 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1053 ;; rewrite "/var/tmp" in check script
1054 (substitute* "scripts/common/check/check_make_unix.sh"
1055 (("/var/tmp") "/tmp"))
1057 ;; do not reset PATH
1058 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1060 (("action=/bin/") "action=")
1061 (("export PATH") ":"))
1065 (lambda* (#:key inputs outputs #:allow-other-keys)
1066 (let ((out (assoc-ref outputs "out"))
1067 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1068 (include (string-append (assoc-ref outputs "include")
1069 "/include/ncbi-tools++")))
1070 ;; The 'configure' script doesn't recognize things like
1071 ;; '--enable-fast-install'.
1072 (zero? (system* "./configure.orig"
1073 (string-append "--with-build-root=" (getcwd) "/build")
1074 (string-append "--prefix=" out)
1075 (string-append "--libdir=" lib)
1076 (string-append "--includedir=" include)
1077 (string-append "--with-bz2="
1078 (assoc-ref inputs "bzip2"))
1079 (string-append "--with-z="
1080 (assoc-ref inputs "zlib"))
1081 (string-append "--with-pcre="
1082 (assoc-ref inputs "pcre"))
1083 ;; Each library is built twice by default, once
1084 ;; with "-static" in its name, and again
1087 "--with-dll"))))))))
1088 (outputs '("out" ; 21 MB
1096 ("python" ,python-wrapper)))
1099 (home-page "http://blast.ncbi.nlm.nih.gov")
1100 (synopsis "Basic local alignment search tool")
1102 "BLAST is a popular method of performing a DNA or protein sequence
1103 similarity search, using heuristics to produce results quickly. It also
1104 calculates an “expect value” that estimates how many matches would have
1105 occurred at a given score by chance, which can aid a user in judging how much
1106 confidence to have in an alignment.")
1107 ;; Most of the sources are in the public domain, with the following
1110 ;; * ./c++/include/util/bitset/
1111 ;; * ./c++/src/html/ncbi_menu*.js
1113 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1115 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1117 ;; * ./c++/src/corelib/teamcity_*
1118 (license (list license:public-domain
1124 (define-public bless
1130 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1134 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1135 (modules '((guix build utils)))
1138 ;; Remove bundled boost, pigz, zlib, and .git directory
1139 ;; FIXME: also remove bundled sources for murmurhash3 and
1140 ;; kmc once packaged.
1141 (delete-file-recursively "boost")
1142 (delete-file-recursively "pigz")
1143 (delete-file-recursively "google-sparsehash")
1144 (delete-file-recursively "zlib")
1145 (delete-file-recursively ".git")
1147 (build-system gnu-build-system)
1149 '(#:tests? #f ;no "check" target
1151 (list (string-append "ZLIB="
1152 (assoc-ref %build-inputs "zlib")
1154 (string-append "LDFLAGS="
1155 (string-join '("-lboost_filesystem"
1162 (modify-phases %standard-phases
1163 (add-after 'unpack 'do-not-build-bundled-pigz
1164 (lambda* (#:key inputs outputs #:allow-other-keys)
1165 (substitute* "Makefile"
1166 (("cd pigz/pigz-2.3.3; make") ""))
1168 (add-after 'unpack 'patch-paths-to-executables
1169 (lambda* (#:key inputs outputs #:allow-other-keys)
1170 (substitute* "parse_args.cpp"
1171 (("kmc_binary = .*")
1172 (string-append "kmc_binary = \""
1173 (assoc-ref outputs "out")
1175 (("pigz_binary = .*")
1176 (string-append "pigz_binary = \""
1177 (assoc-ref inputs "pigz")
1181 (lambda* (#:key outputs #:allow-other-keys)
1182 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1183 (for-each (lambda (file)
1184 (install-file file bin))
1185 '("bless" "kmc/bin/kmc"))
1187 (delete 'configure))))
1191 `(("openmpi" ,openmpi)
1193 ("sparsehash" ,sparsehash)
1196 (supported-systems '("x86_64-linux"))
1197 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1198 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1200 "@dfn{Bloom-filter-based error correction solution for high-throughput
1201 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1202 correction tool for genomic reads produced by @dfn{Next-generation
1203 sequencing} (NGS). BLESS produces accurate correction results with much less
1204 memory compared with previous solutions and is also able to tolerate a higher
1205 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1206 errors at the end of reads.")
1207 (license license:gpl3+)))
1209 (define-public bowtie
1215 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1217 (file-name (string-append name "-" version ".tar.gz"))
1220 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1221 (modules '((guix build utils)))
1223 '(substitute* "Makefile"
1224 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1225 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1226 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1227 (build-system gnu-build-system)
1230 ("perl-clone" ,perl-clone)
1231 ("perl-test-deep" ,perl-test-deep)
1232 ("perl-test-simple" ,perl-test-simple)
1233 ("python" ,python-2)
1240 (string-append "prefix=" (assoc-ref %outputs "out")))
1242 (modify-phases %standard-phases
1245 (lambda* (#:key outputs #:allow-other-keys)
1246 (zero? (system* "perl"
1247 "scripts/test/simple_tests.pl"
1248 "--bowtie2=./bowtie2"
1249 "--bowtie2-build=./bowtie2-build")))))))
1250 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1251 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1253 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1254 reads to long reference sequences. It is particularly good at aligning reads
1255 of about 50 up to 100s or 1,000s of characters, and particularly good at
1256 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1257 genome with an FM Index to keep its memory footprint small: for the human
1258 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1259 gapped, local, and paired-end alignment modes.")
1260 (supported-systems '("x86_64-linux"))
1261 (license license:gpl3+)))
1263 (define-public tophat
1270 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1274 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1275 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1276 (modules '((guix build utils)))
1279 ;; Remove bundled SeqAn and samtools
1280 (delete-file-recursively "src/SeqAn-1.3")
1281 (delete-file-recursively "src/samtools-0.1.18")
1283 (build-system gnu-build-system)
1285 '(#:parallel-build? #f ; not supported
1287 (modify-phases %standard-phases
1288 (add-after 'unpack 'use-system-samtools
1289 (lambda* (#:key inputs #:allow-other-keys)
1290 (substitute* "src/Makefile.in"
1291 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1292 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1293 (("SAMPROG = samtools_0\\.1\\.18") "")
1294 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1295 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1296 (substitute* '("src/common.cpp"
1298 (("samtools_0.1.18") (which "samtools")))
1299 (substitute* '("src/common.h"
1300 "src/bam2fastx.cpp")
1301 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1302 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1303 (substitute* '("src/bwt_map.h"
1305 "src/align_status.h")
1306 (("#include <bam.h>") "#include <samtools/bam.h>")
1307 (("#include <sam.h>") "#include <samtools/sam.h>"))
1312 ("samtools" ,samtools-0.1)
1313 ("ncurses" ,ncurses)
1314 ("python" ,python-2)
1318 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1319 (synopsis "Spliced read mapper for RNA-Seq data")
1321 "TopHat is a fast splice junction mapper for nucleotide sequence
1322 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1323 mammalian-sized genomes using the ultra high-throughput short read
1324 aligner Bowtie, and then analyzes the mapping results to identify
1325 splice junctions between exons.")
1326 ;; TopHat is released under the Boost Software License, Version 1.0
1327 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1328 (license license:boost1.0)))
1337 "https://github.com/lh3/bwa/releases/download/v"
1338 version "/bwa-" version ".tar.bz2"))
1341 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1342 (build-system gnu-build-system)
1344 '(#:tests? #f ;no "check" target
1346 (modify-phases %standard-phases
1348 (lambda* (#:key outputs #:allow-other-keys)
1349 (let ((bin (string-append
1350 (assoc-ref outputs "out") "/bin"))
1352 (assoc-ref outputs "out") "/share/doc/bwa"))
1354 (assoc-ref outputs "out") "/share/man/man1")))
1355 (install-file "bwa" bin)
1356 (install-file "README.md" doc)
1357 (install-file "bwa.1" man))
1359 ;; no "configure" script
1360 (delete 'configure))))
1361 (inputs `(("zlib" ,zlib)))
1362 ;; Non-portable SSE instructions are used so building fails on platforms
1363 ;; other than x86_64.
1364 (supported-systems '("x86_64-linux"))
1365 (home-page "http://bio-bwa.sourceforge.net/")
1366 (synopsis "Burrows-Wheeler sequence aligner")
1368 "BWA is a software package for mapping low-divergent sequences against a
1369 large reference genome, such as the human genome. It consists of three
1370 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1371 designed for Illumina sequence reads up to 100bp, while the rest two for
1372 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1373 features such as long-read support and split alignment, but BWA-MEM, which is
1374 the latest, is generally recommended for high-quality queries as it is faster
1375 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1376 70-100bp Illumina reads.")
1377 (license license:gpl3+)))
1379 (define-public bwa-pssm
1380 (package (inherit bwa)
1385 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1386 "archive/" version ".tar.gz"))
1387 (file-name (string-append name "-" version ".tar.gz"))
1390 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1391 (build-system gnu-build-system)
1396 (home-page "http://bwa-pssm.binf.ku.dk/")
1397 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1399 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1400 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1401 existing aligners it is fast and sensitive. Unlike most other aligners,
1402 however, it is also adaptible in the sense that one can direct the alignment
1403 based on known biases within the data set. It is coded as a modification of
1404 the original BWA alignment program and shares the genome index structure as
1405 well as many of the command line options.")
1406 (license license:gpl3+)))
1408 (define-public python2-bx-python
1410 (name "python2-bx-python")
1414 (uri (pypi-uri "bx-python" version))
1417 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1418 (modules '((guix build utils)))
1420 '(substitute* "setup.py"
1421 ;; remove dependency on outdated "distribute" module
1422 (("^from distribute_setup import use_setuptools") "")
1423 (("^use_setuptools\\(\\)") "")))))
1424 (build-system python-build-system)
1426 `(#:tests? #f ;tests fail because test data are not included
1427 #:python ,python-2))
1429 `(("python-numpy" ,python2-numpy)
1432 `(("python-nose" ,python2-nose)))
1433 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1434 (synopsis "Tools for manipulating biological data")
1436 "bx-python provides tools for manipulating biological data, particularly
1437 multiple sequence alignments.")
1438 (license license:expat)))
1440 (define-public python-pysam
1442 (name "python-pysam")
1446 ;; Test data is missing on PyPi.
1448 "https://github.com/pysam-developers/pysam/archive/v"
1450 (file-name (string-append name "-" version ".tar.gz"))
1453 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1454 (modules '((guix build utils)))
1456 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1457 '(delete-file-recursively "htslib"))))
1458 (build-system python-build-system)
1460 `(#:modules ((ice-9 ftw)
1462 (guix build python-build-system)
1465 (modify-phases %standard-phases
1466 (add-before 'build 'set-flags
1467 (lambda* (#:key inputs #:allow-other-keys)
1468 (setenv "HTSLIB_MODE" "external")
1469 (setenv "HTSLIB_LIBRARY_DIR"
1470 (string-append (assoc-ref inputs "htslib") "/lib"))
1471 (setenv "HTSLIB_INCLUDE_DIR"
1472 (string-append (assoc-ref inputs "htslib") "/include"))
1473 (setenv "LDFLAGS" "-lncurses")
1474 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1477 (lambda* (#:key inputs outputs #:allow-other-keys)
1478 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1479 (setenv "PYTHONPATH"
1481 (getenv "PYTHONPATH")
1482 ":" (getcwd) "/build/"
1483 (car (scandir "build"
1484 (negate (cut string-prefix? "." <>))))))
1485 ;; Step out of source dir so python does not import from CWD.
1486 (with-directory-excursion "tests"
1487 (setenv "HOME" "/tmp")
1488 (and (zero? (system* "make" "-C" "pysam_data"))
1489 (zero? (system* "make" "-C" "cbcf_data"))
1490 ;; Running nosetests without explicitly asking for a
1491 ;; single process leads to a crash. Running with multiple
1492 ;; processes fails because the tests are not designed to
1495 ;; FIXME: tests keep timing out on some systems.
1496 ;; (zero? (system* "nosetests" "-v"
1497 ;; "--processes" "1"))
1500 `(("htslib" ,htslib))) ; Included from installed header files.
1502 `(("ncurses" ,ncurses)
1505 `(("python-cython" ,python-cython)
1506 ;; Dependencies below are are for tests only.
1507 ("samtools" ,samtools)
1508 ("bcftools" ,bcftools)
1509 ("python-nose" ,python-nose)))
1510 (home-page "https://github.com/pysam-developers/pysam")
1511 (synopsis "Python bindings to the SAMtools C API")
1513 "Pysam is a Python module for reading and manipulating files in the
1514 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1515 also includes an interface for tabix.")
1516 (license license:expat)))
1518 (define-public python2-pysam
1519 (package-with-python2 python-pysam))
1521 (define-public python-twobitreader
1523 (name "python-twobitreader")
1527 (uri (pypi-uri "twobitreader" version))
1530 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1531 (build-system python-build-system)
1533 '(;; Tests are not distributed in the PyPi release.
1534 ;; TODO Try building from the Git repo or asking the upstream maintainer
1535 ;; to distribute the tests on PyPi.
1538 `(("python-sphinx" ,python-sphinx)))
1539 (home-page "https://github.com/benjschiller/twobitreader")
1540 (synopsis "Python library for reading .2bit files")
1542 "twobitreader is a Python library for reading .2bit files as used by the
1543 UCSC genome browser.")
1544 (license license:artistic2.0)))
1546 (define-public python2-twobitreader
1547 (package-with-python2 python-twobitreader))
1549 (define-public python-plastid
1551 (name "python-plastid")
1555 (uri (pypi-uri "plastid" version))
1558 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1559 (build-system python-build-system)
1561 ;; Some test files are not included.
1564 `(("python-numpy" ,python-numpy)
1565 ("python-scipy" ,python-scipy)
1566 ("python-pandas" ,python-pandas)
1567 ("python-pysam" ,python-pysam)
1568 ("python-matplotlib" ,python-matplotlib)
1569 ("python-biopython" ,python-biopython)
1570 ("python-twobitreader" ,python-twobitreader)
1571 ("python-termcolor" ,python-termcolor)))
1573 `(("python-cython" ,python-cython)
1574 ("python-nose" ,python-nose)))
1575 (home-page "https://github.com/joshuagryphon/plastid")
1576 (synopsis "Python library for genomic analysis")
1578 "plastid is a Python library for genomic analysis – in particular,
1579 high-throughput sequencing data – with an emphasis on simplicity.")
1580 (license license:bsd-3)))
1582 (define-public python2-plastid
1583 (package-with-python2 python-plastid))
1585 (define-public cd-hit
1591 (uri (string-append "https://github.com/weizhongli/cdhit"
1592 "/releases/download/V" version
1594 "-2017-0621-source.tar.gz"))
1597 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1598 (build-system gnu-build-system)
1600 `(#:tests? #f ; there are no tests
1602 ;; Executables are copied directly to the PREFIX.
1603 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1605 (modify-phases %standard-phases
1606 ;; No "configure" script
1608 ;; Remove sources of non-determinism
1609 (add-after 'unpack 'be-timeless
1611 (substitute* "cdhit-utility.c++"
1612 ((" \\(built on \" __DATE__ \"\\)") ""))
1613 (substitute* "cdhit-common.c++"
1614 (("__DATE__") "\"0\"")
1615 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1617 ;; The "install" target does not create the target directory.
1618 (add-before 'install 'create-target-dir
1619 (lambda* (#:key outputs #:allow-other-keys)
1620 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1624 (home-page "http://weizhongli-lab.org/cd-hit/")
1625 (synopsis "Cluster and compare protein or nucleotide sequences")
1627 "CD-HIT is a program for clustering and comparing protein or nucleotide
1628 sequences. CD-HIT is designed to be fast and handle extremely large
1630 ;; The manual says: "It can be copied under the GNU General Public License
1631 ;; version 2 (GPLv2)."
1632 (license license:gpl2)))
1634 (define-public clipper
1641 "https://github.com/YeoLab/clipper/archive/"
1643 (file-name (string-append name "-" version ".tar.gz"))
1646 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1647 (modules '((guix build utils)))
1650 ;; remove unnecessary setup dependency
1651 (substitute* "setup.py"
1652 (("setup_requires = .*") ""))
1653 (for-each delete-file
1654 '("clipper/src/peaks.so"
1655 "clipper/src/readsToWiggle.so"))
1656 (delete-file-recursively "dist/")
1658 (build-system python-build-system)
1659 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1661 `(("htseq" ,python2-htseq)
1662 ("python-pybedtools" ,python2-pybedtools)
1663 ("python-cython" ,python2-cython)
1664 ("python-scikit-learn" ,python2-scikit-learn)
1665 ("python-matplotlib" ,python2-matplotlib)
1666 ("python-pandas" ,python2-pandas)
1667 ("python-pysam" ,python2-pysam)
1668 ("python-numpy" ,python2-numpy)
1669 ("python-scipy" ,python2-scipy)))
1671 `(("python-mock" ,python2-mock) ; for tests
1672 ("python-nose" ,python2-nose) ; for tests
1673 ("python-pytz" ,python2-pytz))) ; for tests
1674 (home-page "https://github.com/YeoLab/clipper")
1675 (synopsis "CLIP peak enrichment recognition")
1677 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1678 (license license:gpl2)))
1680 (define-public codingquarry
1682 (name "codingquarry")
1687 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1691 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1692 (build-system gnu-build-system)
1694 '(#:tests? #f ; no "check" target
1696 (modify-phases %standard-phases
1699 (lambda* (#:key outputs #:allow-other-keys)
1700 (let* ((out (assoc-ref outputs "out"))
1701 (bin (string-append out "/bin"))
1702 (doc (string-append out "/share/doc/codingquarry")))
1703 (install-file "INSTRUCTIONS.pdf" doc)
1704 (copy-recursively "QuarryFiles"
1705 (string-append out "/QuarryFiles"))
1706 (install-file "CodingQuarry" bin)
1707 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1708 (inputs `(("openmpi" ,openmpi)))
1709 (native-search-paths
1710 (list (search-path-specification
1711 (variable "QUARRY_PATH")
1712 (files '("QuarryFiles")))))
1713 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1714 (synopsis "Fungal gene predictor")
1715 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1716 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1717 (home-page "https://sourceforge.net/projects/codingquarry/")
1718 (license license:gpl3+)))
1720 (define-public couger
1727 "http://couger.oit.duke.edu/static/assets/COUGER"
1731 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1732 (build-system gnu-build-system)
1736 (modify-phases %standard-phases
1741 (lambda* (#:key outputs #:allow-other-keys)
1742 (let* ((out (assoc-ref outputs "out"))
1743 (bin (string-append out "/bin")))
1744 (copy-recursively "src" (string-append out "/src"))
1746 ;; Add "src" directory to module lookup path.
1747 (substitute* "couger"
1749 (string-append "import sys\nsys.path.append(\""
1750 out "\")\nfrom argparse")))
1751 (install-file "couger" bin))
1754 'install 'wrap-program
1755 (lambda* (#:key inputs outputs #:allow-other-keys)
1756 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1757 (let* ((out (assoc-ref outputs "out"))
1758 (path (getenv "PYTHONPATH")))
1759 (wrap-program (string-append out "/bin/couger")
1760 `("PYTHONPATH" ":" prefix (,path))))
1763 `(("python" ,python-2)
1764 ("python2-pillow" ,python2-pillow)
1765 ("python2-numpy" ,python2-numpy)
1766 ("python2-scipy" ,python2-scipy)
1767 ("python2-matplotlib" ,python2-matplotlib)))
1769 `(("r-minimal" ,r-minimal)
1771 ("randomjungle" ,randomjungle)))
1773 `(("unzip" ,unzip)))
1774 (home-page "http://couger.oit.duke.edu")
1775 (synopsis "Identify co-factors in sets of genomic regions")
1777 "COUGER can be applied to any two sets of genomic regions bound by
1778 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1779 putative co-factors that provide specificity to each TF. The framework
1780 determines the genomic targets uniquely-bound by each TF, and identifies a
1781 small set of co-factors that best explain the in vivo binding differences
1782 between the two TFs.
1784 COUGER uses classification algorithms (support vector machines and random
1785 forests) with features that reflect the DNA binding specificities of putative
1786 co-factors. The features are generated either from high-throughput TF-DNA
1787 binding data (from protein binding microarray experiments), or from large
1788 collections of DNA motifs.")
1789 (license license:gpl3+)))
1791 (define-public clustal-omega
1793 (name "clustal-omega")
1797 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1801 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1802 (build-system gnu-build-system)
1804 `(("argtable" ,argtable)))
1805 (home-page "http://www.clustal.org/omega/")
1806 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1808 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1809 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1810 of handling data-sets of hundreds of thousands of sequences in reasonable
1812 (license license:gpl2+)))
1814 (define-public crossmap
1820 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1824 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1825 ;; This patch has been sent upstream already and is available
1826 ;; for download from Sourceforge, but it has not been merged.
1827 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1828 (modules '((guix build utils)))
1829 ;; remove bundled copy of pysam
1831 '(delete-file-recursively "lib/pysam"))))
1832 (build-system python-build-system)
1834 `(#:python ,python-2
1836 (modify-phases %standard-phases
1837 (add-after 'unpack 'set-env
1838 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1840 `(("python-numpy" ,python2-numpy)
1841 ("python-pysam" ,python2-pysam)
1844 `(("python-cython" ,python2-cython)
1845 ("python-nose" ,python2-nose)))
1846 (home-page "http://crossmap.sourceforge.net/")
1847 (synopsis "Convert genome coordinates between assemblies")
1849 "CrossMap is a program for conversion of genome coordinates or annotation
1850 files between different genome assemblies. It supports most commonly used
1851 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1852 (license license:gpl2+)))
1854 (define-public cutadapt
1861 (url "https://github.com/marcelm/cutadapt.git")
1862 (commit (string-append "v" version))))
1863 (file-name (string-append name "-" version "-checkout"))
1866 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1867 (build-system python-build-system)
1869 `(("python-xopen" ,python-xopen)))
1871 `(("python-cython" ,python-cython)
1872 ("python-pytest" ,python-pytest)))
1873 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1874 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1876 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1877 other types of unwanted sequence from high-throughput sequencing reads.")
1878 (license license:expat)))
1880 (define-public libbigwig
1886 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1887 "archive/" version ".tar.gz"))
1888 (file-name (string-append name "-" version ".tar.gz"))
1891 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1892 (build-system gnu-build-system)
1894 `(#:test-target "test"
1897 (string-append "prefix=" (assoc-ref %outputs "out")))
1899 (modify-phases %standard-phases
1901 (add-before 'check 'disable-curl-test
1903 (substitute* "Makefile"
1904 (("./test/testRemote.*") ""))
1906 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1907 ;; there has not yet been a release containing this change.
1908 (add-before 'install 'create-target-dirs
1909 (lambda* (#:key outputs #:allow-other-keys)
1910 (let ((out (assoc-ref outputs "out")))
1911 (mkdir-p (string-append out "/lib"))
1912 (mkdir-p (string-append out "/include"))
1918 `(("doxygen" ,doxygen)))
1919 (home-page "https://github.com/dpryan79/libBigWig")
1920 (synopsis "C library for handling bigWig files")
1922 "This package provides a C library for parsing local and remote BigWig
1924 (license license:expat)))
1926 (define-public python-pybigwig
1928 (name "python-pybigwig")
1932 (uri (pypi-uri "pyBigWig" version))
1935 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1936 (modules '((guix build utils)))
1939 ;; Delete bundled libBigWig sources
1940 (delete-file-recursively "libBigWig")))))
1941 (build-system python-build-system)
1944 (modify-phases %standard-phases
1945 (add-after 'unpack 'link-with-libBigWig
1946 (lambda* (#:key inputs #:allow-other-keys)
1947 (substitute* "setup.py"
1948 (("libs=\\[") "libs=[\"BigWig\", "))
1951 `(("libbigwig" ,libbigwig)
1954 (home-page "https://github.com/dpryan79/pyBigWig")
1955 (synopsis "Access bigWig files in Python using libBigWig")
1957 "This package provides Python bindings to the libBigWig library for
1958 accessing bigWig files.")
1959 (license license:expat)))
1961 (define-public python2-pybigwig
1962 (package-with-python2 python-pybigwig))
1964 (define-public python-dendropy
1966 (name "python-dendropy")
1971 (uri (pypi-uri "DendroPy" version))
1974 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1975 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1976 (build-system python-build-system)
1977 (home-page "http://packages.python.org/DendroPy/")
1978 (synopsis "Library for phylogenetics and phylogenetic computing")
1980 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1981 writing, simulation, processing and manipulation of phylogenetic
1982 trees (phylogenies) and characters.")
1983 (license license:bsd-3)
1984 (properties `((python2-variant . ,(delay python2-dendropy))))))
1986 (define-public python2-dendropy
1987 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1991 `(#:python ,python-2
1993 (modify-phases %standard-phases
1995 ;; There is currently a test failure that only happens on some
1996 ;; systems, and only using "setup.py test"
1997 (lambda _ (zero? (system* "nosetests")))))))
1998 (native-inputs `(("python2-nose" ,python2-nose)
1999 ,@(package-native-inputs base))))))
2001 (define-public python-py2bit
2003 (name "python-py2bit")
2008 (uri (pypi-uri "py2bit" version))
2011 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2012 (build-system python-build-system)
2013 (home-page "https://github.com/dpryan79/py2bit")
2014 (synopsis "Access 2bit files using lib2bit")
2016 "This package provides Python bindings for lib2bit to access 2bit files
2018 (license license:expat)))
2020 (define-public deeptools
2026 (uri (string-append "https://github.com/deeptools/deepTools/"
2027 "archive/" version ".tar.gz"))
2028 (file-name (string-append name "-" version ".tar.gz"))
2031 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2032 (build-system python-build-system)
2034 `(("python-scipy" ,python-scipy)
2035 ("python-numpy" ,python-numpy)
2036 ("python-numpydoc" ,python-numpydoc)
2037 ("python-matplotlib" ,python-matplotlib)
2038 ("python-pysam" ,python-pysam)
2039 ("python-py2bit" ,python-py2bit)
2040 ("python-pybigwig" ,python-pybigwig)))
2042 `(("python-mock" ,python-mock) ;for tests
2043 ("python-nose" ,python-nose) ;for tests
2044 ("python-pytz" ,python-pytz))) ;for tests
2045 (home-page "https://github.com/deeptools/deepTools")
2046 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2048 "DeepTools addresses the challenge of handling the large amounts of data
2049 that are now routinely generated from DNA sequencing centers. To do so,
2050 deepTools contains useful modules to process the mapped reads data to create
2051 coverage files in standard bedGraph and bigWig file formats. By doing so,
2052 deepTools allows the creation of normalized coverage files or the comparison
2053 between two files (for example, treatment and control). Finally, using such
2054 normalized and standardized files, multiple visualizations can be created to
2055 identify enrichments with functional annotations of the genome.")
2056 (license license:gpl3+)))
2058 (define-public diamond
2065 "https://github.com/bbuchfink/diamond/archive/v"
2067 (file-name (string-append name "-" version ".tar.gz"))
2070 "1vi2nddmy7knrv8gsprwqp6a40k63n3f2dfvx22ipjhrg9xir96f"))))
2071 (build-system cmake-build-system)
2073 '(#:tests? #f ; no "check" target
2075 (modify-phases %standard-phases
2076 (add-after 'unpack 'remove-native-compilation
2078 (substitute* "CMakeLists.txt" (("-march=native") ""))
2082 (home-page "https://github.com/bbuchfink/diamond")
2083 (synopsis "Accelerated BLAST compatible local sequence aligner")
2085 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2086 translated DNA query sequences against a protein reference database (BLASTP
2087 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2088 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2089 data and settings.")
2090 (license license:agpl3+)))
2092 (define-public discrover
2099 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2101 (file-name (string-append name "-" version ".tar.gz"))
2104 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2105 (build-system cmake-build-system)
2107 `(#:tests? #f ; there are no tests
2109 (modify-phases %standard-phases
2110 (add-after 'unpack 'add-missing-includes
2112 (substitute* "src/executioninformation.hpp"
2113 (("#define EXECUTIONINFORMATION_HPP" line)
2114 (string-append line "\n#include <random>")))
2115 (substitute* "src/plasma/fasta.hpp"
2116 (("#define FASTA_HPP" line)
2117 (string-append line "\n#include <random>")))
2123 `(("texlive" ,texlive)
2124 ("imagemagick" ,imagemagick)))
2125 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2126 (synopsis "Discover discriminative nucleotide sequence motifs")
2127 (description "Discrover is a motif discovery method to find binding sites
2128 of nucleic acid binding proteins.")
2129 (license license:gpl3+)))
2131 (define-public eigensoft
2132 (let ((revision "1")
2133 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2136 (version (string-append "6.1.2-"
2138 (string-take commit 9)))
2143 (url "https://github.com/DReichLab/EIG.git")
2145 (file-name (string-append "eigensoft-" commit "-checkout"))
2148 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2149 (modules '((guix build utils)))
2150 ;; Remove pre-built binaries.
2152 (delete-file-recursively "bin")
2155 (build-system gnu-build-system)
2157 `(#:tests? #f ; There are no tests.
2158 #:make-flags '("CC=gcc")
2160 (modify-phases %standard-phases
2161 ;; There is no configure phase, but the Makefile is in a
2166 ;; The link flags are incomplete.
2167 (substitute* "Makefile"
2168 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2170 ;; The provided install target only copies executables to
2171 ;; the "bin" directory in the build root.
2172 (add-after 'install 'actually-install
2173 (lambda* (#:key outputs #:allow-other-keys)
2174 (let* ((out (assoc-ref outputs "out"))
2175 (bin (string-append out "/bin")))
2176 (for-each (lambda (file)
2177 (install-file file bin))
2178 (find-files "../bin" ".*"))
2183 ("openblas" ,openblas)
2185 ("gfortran" ,gfortran "lib")))
2186 (home-page "https://github.com/DReichLab/EIG")
2187 (synopsis "Tools for population genetics")
2188 (description "The EIGENSOFT package provides tools for population
2189 genetics and stratification correction. EIGENSOFT implements methods commonly
2190 used in population genetics analyses such as PCA, computation of Tracy-Widom
2191 statistics, and finding related individuals in structured populations. It
2192 comes with a built-in plotting script and supports multiple file formats and
2193 quantitative phenotypes.")
2194 ;; The license of the eigensoft tools is Expat, but since it's
2195 ;; linking with the GNU Scientific Library (GSL) the effective
2196 ;; license is the GPL.
2197 (license license:gpl3+))))
2199 (define-public edirect
2205 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2206 "versions/2016-05-03/edirect.tar.gz"))
2209 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2210 (build-system perl-build-system)
2212 `(#:tests? #f ;no "check" target
2214 (modify-phases %standard-phases
2218 (lambda* (#:key outputs #:allow-other-keys)
2219 (let ((target (string-append (assoc-ref outputs "out")
2222 (install-file "edirect.pl" target)
2225 'install 'wrap-program
2226 (lambda* (#:key inputs outputs #:allow-other-keys)
2227 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2228 (let* ((out (assoc-ref outputs "out"))
2229 (path (getenv "PERL5LIB")))
2230 (wrap-program (string-append out "/bin/edirect.pl")
2231 `("PERL5LIB" ":" prefix (,path)))))))))
2233 `(("perl-html-parser" ,perl-html-parser)
2234 ("perl-encode-locale" ,perl-encode-locale)
2235 ("perl-file-listing" ,perl-file-listing)
2236 ("perl-html-tagset" ,perl-html-tagset)
2237 ("perl-html-tree" ,perl-html-tree)
2238 ("perl-http-cookies" ,perl-http-cookies)
2239 ("perl-http-date" ,perl-http-date)
2240 ("perl-http-message" ,perl-http-message)
2241 ("perl-http-negotiate" ,perl-http-negotiate)
2242 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2243 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2244 ("perl-net-http" ,perl-net-http)
2245 ("perl-uri" ,perl-uri)
2246 ("perl-www-robotrules" ,perl-www-robotrules)
2248 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2249 (synopsis "Tools for accessing the NCBI's set of databases")
2251 "Entrez Direct (EDirect) is a method for accessing the National Center
2252 for Biotechnology Information's (NCBI) set of interconnected
2253 databases (publication, sequence, structure, gene, variation, expression,
2254 etc.) from a terminal. Functions take search terms from command-line
2255 arguments. Individual operations are combined to build multi-step queries.
2256 Record retrieval and formatting normally complete the process.
2258 EDirect also provides an argument-driven function that simplifies the
2259 extraction of data from document summaries or other results that are returned
2260 in structured XML format. This can eliminate the need for writing custom
2261 software to answer ad hoc questions.")
2262 (license license:public-domain)))
2264 (define-public exonerate
2273 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2274 "exonerate-" version ".tar.gz"))
2277 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2278 (build-system gnu-build-system)
2280 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2282 `(("pkg-config" ,pkg-config)))
2286 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2287 (synopsis "Generic tool for biological sequence alignment")
2289 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2290 the alignment of sequences using a many alignment models, either exhaustive
2291 dynamic programming or a variety of heuristics.")
2292 (license license:gpl3)))
2294 (define-public express
2302 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2303 version "/express-" version "-src.tgz"))
2306 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2307 (build-system cmake-build-system)
2309 `(#:tests? #f ;no "check" target
2311 (modify-phases %standard-phases
2312 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2313 (lambda* (#:key inputs #:allow-other-keys)
2314 (substitute* "CMakeLists.txt"
2315 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2316 "set(Boost_USE_STATIC_LIBS OFF)")
2317 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2318 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2319 (substitute* "src/CMakeLists.txt"
2320 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2321 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2325 ("bamtools" ,bamtools)
2326 ("protobuf" ,protobuf)
2328 (home-page "http://bio.math.berkeley.edu/eXpress")
2329 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2331 "eXpress is a streaming tool for quantifying the abundances of a set of
2332 target sequences from sampled subsequences. Example applications include
2333 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2334 analysis (from RNA-Seq), transcription factor binding quantification in
2335 ChIP-Seq, and analysis of metagenomic data.")
2336 (license license:artistic2.0)))
2338 (define-public express-beta-diversity
2340 (name "express-beta-diversity")
2346 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2348 (file-name (string-append name "-" version ".tar.gz"))
2351 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2352 (build-system gnu-build-system)
2355 (modify-phases %standard-phases
2357 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2359 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2361 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2363 (lambda* (#:key outputs #:allow-other-keys)
2364 (let ((bin (string-append (assoc-ref outputs "out")
2367 (install-file "scripts/convertToEBD.py" bin)
2368 (install-file "bin/ExpressBetaDiversity" bin)
2371 `(("python" ,python-2)))
2372 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2373 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2375 "Express Beta Diversity (EBD) calculates ecological beta diversity
2376 (dissimilarity) measures between biological communities. EBD implements a
2377 variety of diversity measures including those that make use of phylogenetic
2378 similarity of community members.")
2379 (license license:gpl3+)))
2381 (define-public fasttree
2388 "http://www.microbesonline.org/fasttree/FastTree-"
2392 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2393 (build-system gnu-build-system)
2395 `(#:tests? #f ; no "check" target
2397 (modify-phases %standard-phases
2401 (lambda* (#:key source #:allow-other-keys)
2402 (and (zero? (system* "gcc"
2404 "-finline-functions"
2411 (zero? (system* "gcc"
2415 "-finline-functions"
2423 (lambda* (#:key outputs #:allow-other-keys)
2424 (let ((bin (string-append (assoc-ref outputs "out")
2427 (install-file "FastTree" bin)
2428 (install-file "FastTreeMP" bin)
2430 (home-page "http://www.microbesonline.org/fasttree")
2431 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2433 "FastTree can handle alignments with up to a million of sequences in a
2434 reasonable amount of time and memory. For large alignments, FastTree is
2435 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2436 (license license:gpl2+)))
2438 (define-public fastx-toolkit
2440 (name "fastx-toolkit")
2446 "https://github.com/agordon/fastx_toolkit/releases/download/"
2447 version "/fastx_toolkit-" version ".tar.bz2"))
2450 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2451 (build-system gnu-build-system)
2453 `(("libgtextutils" ,libgtextutils)))
2455 `(("pkg-config" ,pkg-config)))
2456 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2457 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2459 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2460 FASTA/FASTQ files preprocessing.
2462 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2463 containing multiple short-reads sequences. The main processing of such
2464 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2465 is sometimes more productive to preprocess the files before mapping the
2466 sequences to the genome---manipulating the sequences to produce better mapping
2467 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2468 (license license:agpl3+)))
2470 (define-public flexbar
2477 (string-append "mirror://sourceforge/flexbar/"
2478 version "/flexbar_v" version "_src.tgz"))
2481 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2482 (build-system cmake-build-system)
2484 `(#:configure-flags (list
2485 (string-append "-DFLEXBAR_BINARY_DIR="
2486 (assoc-ref %outputs "out")
2489 (modify-phases %standard-phases
2491 (lambda* (#:key outputs #:allow-other-keys)
2492 (setenv "PATH" (string-append
2493 (assoc-ref outputs "out") "/bin:"
2495 (chdir "../flexbar_v2.5_src/test")
2496 (zero? (system* "bash" "flexbar_validate.sh"))))
2497 (delete 'install))))
2502 `(("pkg-config" ,pkg-config)
2504 (home-page "http://flexbar.sourceforge.net")
2505 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2507 "Flexbar preprocesses high-throughput nucleotide sequencing data
2508 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2509 Moreover, trimming and filtering features are provided. Flexbar increases
2510 read mapping rates and improves genome and transcriptome assemblies. It
2511 supports next-generation sequencing data in fasta/q and csfasta/q format from
2512 Illumina, Roche 454, and the SOLiD platform.")
2513 (license license:gpl3)))
2515 (define-public fraggenescan
2517 (name "fraggenescan")
2523 (string-append "mirror://sourceforge/fraggenescan/"
2524 "FragGeneScan" version ".tar.gz"))
2526 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2527 (build-system gnu-build-system)
2530 (modify-phases %standard-phases
2532 (add-before 'build 'patch-paths
2533 (lambda* (#:key outputs #:allow-other-keys)
2534 (let* ((out (string-append (assoc-ref outputs "out")))
2535 (share (string-append out "/share/fraggenescan/")))
2536 (substitute* "run_FragGeneScan.pl"
2538 (string-append "system(\"" (which "rm")))
2540 (string-append "system(\"" (which "mv")))
2541 (("\\\"awk") (string-append "\"" (which "awk")))
2542 ;; This script and other programs expect the training files
2543 ;; to be in the non-standard location bin/train/XXX. Change
2544 ;; this to be share/fraggenescan/train/XXX instead.
2545 (("^\\$train.file = \\$dir.*")
2546 (string-append "$train_file = \""
2548 "train/\".$FGS_train_file;")))
2549 (substitute* "run_hmm.c"
2550 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2551 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2554 (lambda _ (and (zero? (system* "make" "clean"))
2555 (zero? (system* "make" "fgs")))))
2557 (lambda* (#:key outputs #:allow-other-keys)
2558 (let* ((out (string-append (assoc-ref outputs "out")))
2559 (bin (string-append out "/bin/"))
2560 (share (string-append out "/share/fraggenescan/train")))
2561 (install-file "run_FragGeneScan.pl" bin)
2562 (install-file "FragGeneScan" bin)
2563 (copy-recursively "train" share))))
2565 (add-after 'install 'post-install-check
2566 ;; In lieu of 'make check', run one of the examples and check the
2567 ;; output files gets created.
2568 (lambda* (#:key outputs #:allow-other-keys)
2569 (let* ((out (string-append (assoc-ref outputs "out")))
2570 (bin (string-append out "/bin/"))
2571 (frag (string-append bin "run_FragGeneScan.pl")))
2572 (and (zero? (system* frag ; Test complete genome.
2573 "-genome=./example/NC_000913.fna"
2577 (file-exists? "test2.faa")
2578 (file-exists? "test2.ffn")
2579 (file-exists? "test2.gff")
2580 (file-exists? "test2.out")
2581 (zero? (system* ; Test incomplete sequences.
2583 "-genome=./example/NC_000913-fgs.ffn"
2586 "-train=454_30")))))))))
2589 ("python" ,python-2))) ;not compatible with python 3.
2590 (home-page "https://sourceforge.net/projects/fraggenescan/")
2591 (synopsis "Finds potentially fragmented genes in short reads")
2593 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2594 short and error-prone DNA sequencing reads. It can also be applied to predict
2595 genes in incomplete assemblies or complete genomes.")
2596 ;; GPL3+ according to private correspondense with the authors.
2597 (license license:gpl3+)))
2599 (define-public fxtract
2600 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2608 "https://github.com/ctSkennerton/fxtract/archive/"
2610 (file-name (string-append "ctstennerton-util-"
2611 (string-take util-commit 7)
2615 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2616 (build-system gnu-build-system)
2618 `(#:make-flags (list
2619 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2621 #:test-target "fxtract_test"
2623 (modify-phases %standard-phases
2625 (add-before 'build 'copy-util
2626 (lambda* (#:key inputs #:allow-other-keys)
2628 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2630 ;; Do not use make install as this requires additional dependencies.
2632 (lambda* (#:key outputs #:allow-other-keys)
2633 (let* ((out (assoc-ref outputs "out"))
2634 (bin (string-append out"/bin")))
2635 (install-file "fxtract" bin)
2641 ;; ctskennerton-util is licensed under GPL2.
2642 `(("ctskennerton-util"
2646 (url "https://github.com/ctSkennerton/util.git")
2647 (commit util-commit)))
2648 (file-name (string-append
2649 "ctstennerton-util-" util-commit "-checkout"))
2652 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2653 (home-page "https://github.com/ctSkennerton/fxtract")
2654 (synopsis "Extract sequences from FASTA and FASTQ files")
2656 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2657 or FASTQ) file given a subsequence. It uses a simple substring search for
2658 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2659 lookups or multi-pattern searching as required. By default fxtract looks in
2660 the sequence of each record but can also be told to look in the header,
2661 comment or quality sections.")
2662 ;; 'util' requires SSE instructions.
2663 (supported-systems '("x86_64-linux"))
2664 (license license:expat))))
2666 (define-public gemma
2672 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2674 (file-name (string-append name "-" version ".tar.gz"))
2677 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2678 (patches (search-patches "gemma-intel-compat.patch"))))
2683 (build-system gnu-build-system)
2686 '(,@(match (%current-system)
2688 '("FORCE_DYNAMIC=1"))
2690 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2692 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2694 (modify-phases %standard-phases
2696 (add-before 'build 'bin-mkdir
2701 (lambda* (#:key outputs #:allow-other-keys)
2702 (let ((out (assoc-ref outputs "out")))
2703 (install-file "bin/gemma"
2707 #:tests? #f)) ; no tests included yet
2708 (home-page "https://github.com/xiangzhou/GEMMA")
2709 (synopsis "Tool for genome-wide efficient mixed model association")
2711 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2712 standard linear mixed model resolver with application in genome-wide
2713 association studies (GWAS).")
2714 (license license:gpl3)))
2723 "https://github.com/nboley/grit/archive/"
2725 (file-name (string-append name "-" version ".tar.gz"))
2728 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2729 (build-system python-build-system)
2731 `(#:python ,python-2
2733 (modify-phases %standard-phases
2734 (add-after 'unpack 'generate-from-cython-sources
2735 (lambda* (#:key inputs outputs #:allow-other-keys)
2736 ;; Delete these C files to force fresh generation from pyx sources.
2737 (delete-file "grit/sparsify_support_fns.c")
2738 (delete-file "grit/call_peaks_support_fns.c")
2739 (substitute* "setup.py"
2740 (("Cython.Setup") "Cython.Build")
2741 ;; Add numpy include path to fix compilation
2743 (string-append "pyx\", ], include_dirs = ['"
2744 (assoc-ref inputs "python-numpy")
2745 "/lib/python2.7/site-packages/numpy/core/include/"
2749 `(("python-scipy" ,python2-scipy)
2750 ("python-numpy" ,python2-numpy)
2751 ("python-pysam" ,python2-pysam)
2752 ("python-networkx" ,python2-networkx)))
2754 `(("python-cython" ,python2-cython)))
2755 (home-page "http://grit-bio.org")
2756 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2758 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2759 full length transcript models. When none of these data sources are available,
2760 GRIT can be run by providing a candidate set of TES or TSS sites. In
2761 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2762 also be run in quantification mode, where it uses a provided GTF file and just
2763 estimates transcript expression.")
2764 (license license:gpl3+)))
2766 (define-public hisat
2773 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2774 version "-beta-source.zip"))
2777 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2778 (build-system gnu-build-system)
2780 `(#:tests? #f ;no check target
2781 #:make-flags '("allall"
2782 ;; Disable unsupported `popcnt' instructions on
2783 ;; architectures other than x86_64
2784 ,@(if (string-prefix? "x86_64"
2785 (or (%current-target-system)
2788 '("POPCNT_CAPABILITY=0")))
2790 (modify-phases %standard-phases
2791 (add-after 'unpack 'patch-sources
2793 ;; XXX Cannot use snippet because zip files are not supported
2794 (substitute* "Makefile"
2795 (("^CC = .*$") "CC = gcc")
2796 (("^CPP = .*$") "CPP = g++")
2797 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2798 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2799 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2800 (substitute* '("hisat-build" "hisat-inspect")
2801 (("/usr/bin/env") (which "env")))
2804 (lambda* (#:key outputs #:allow-other-keys)
2805 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2806 (for-each (lambda (file)
2807 (install-file file bin))
2810 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2812 (delete 'configure))))
2814 `(("unzip" ,unzip)))
2819 ;; Non-portable SSE instructions are used so building fails on platforms
2820 ;; other than x86_64.
2821 (supported-systems '("x86_64-linux"))
2822 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2823 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2825 "HISAT is a fast and sensitive spliced alignment program for mapping
2826 RNA-seq reads. In addition to one global FM index that represents a whole
2827 genome, HISAT uses a large set of small FM indexes that collectively cover the
2828 whole genome. These small indexes (called local indexes) combined with
2829 several alignment strategies enable effective alignment of RNA-seq reads, in
2830 particular, reads spanning multiple exons.")
2831 (license license:gpl3+)))
2833 (define-public hisat2
2840 ;; FIXME: a better source URL is
2841 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2842 ;; "/downloads/hisat2-" version "-source.zip")
2843 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2844 ;; but it is currently unavailable.
2845 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2846 (file-name (string-append name "-" version ".tar.gz"))
2849 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2850 (build-system gnu-build-system)
2852 `(#:tests? #f ; no check target
2853 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2854 #:modules ((guix build gnu-build-system)
2858 (modify-phases %standard-phases
2859 (add-after 'unpack 'make-deterministic
2861 (substitute* "Makefile"
2866 (lambda* (#:key outputs #:allow-other-keys)
2867 (let* ((out (assoc-ref outputs "out"))
2868 (bin (string-append out "/bin/"))
2869 (doc (string-append out "/share/doc/hisat2/")))
2871 (cut install-file <> bin)
2873 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2875 (install-file "doc/manual.inc.html" doc))
2878 `(("unzip" ,unzip) ; needed for archive from ftp
2880 ("pandoc" ,ghc-pandoc))) ; for documentation
2881 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2882 (synopsis "Graph-based alignment of genomic sequencing reads")
2883 (description "HISAT2 is a fast and sensitive alignment program for mapping
2884 next-generation sequencing reads (both DNA and RNA) to a population of human
2885 genomes (as well as to a single reference genome). In addition to using one
2886 global @dfn{graph FM} (GFM) index that represents a population of human
2887 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2888 the whole genome. These small indexes, combined with several alignment
2889 strategies, enable rapid and accurate alignment of sequencing reads. This new
2890 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2891 ;; HISAT2 contains files from Bowtie2, which is released under
2892 ;; GPLv2 or later. The HISAT2 source files are released under
2894 (license license:gpl3+)))
2896 (define-public hmmer
2904 "http://eddylab.org/software/hmmer"
2905 (version-major version) "/"
2906 version "/hmmer-" version ".tar.gz"))
2909 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2910 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2911 (build-system gnu-build-system)
2912 (native-inputs `(("perl" ,perl)))
2913 (home-page "http://hmmer.org/")
2914 (synopsis "Biosequence analysis using profile hidden Markov models")
2916 "HMMER is used for searching sequence databases for homologs of protein
2917 sequences, and for making protein sequence alignments. It implements methods
2918 using probabilistic models called profile hidden Markov models (profile
2920 (license (list license:gpl3+
2921 ;; The bundled library 'easel' is distributed
2922 ;; under The Janelia Farm Software License.
2923 (license:non-copyleft
2924 "file://easel/LICENSE"
2925 "See easel/LICENSE in the distribution.")))))
2927 (define-public htseq
2933 (uri (pypi-uri "HTSeq" version))
2936 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2937 (build-system python-build-system)
2939 `(("python-cython" ,python-cython)))
2940 ;; Numpy needs to be propagated when htseq is used as a Python library.
2942 `(("python-numpy" ,python-numpy)))
2944 `(("python-pysam" ,python-pysam)
2945 ("python-matplotlib" ,python-matplotlib)))
2946 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2947 (synopsis "Analysing high-throughput sequencing data with Python")
2949 "HTSeq is a Python package that provides infrastructure to process data
2950 from high-throughput sequencing assays.")
2951 (license license:gpl3+)))
2953 (define-public python2-htseq
2954 (package-with-python2 htseq))
2956 (define-public java-htsjdk
2958 (name "java-htsjdk")
2959 (version "2.3.0") ; last version without build dependency on gradle
2963 "https://github.com/samtools/htsjdk/archive/"
2965 (file-name (string-append name "-" version ".tar.gz"))
2968 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2969 (modules '((guix build utils)))
2971 ;; Delete pre-built binaries
2973 (delete-file-recursively "lib")
2976 (build-system ant-build-system)
2978 `(#:tests? #f ; test require Internet access
2981 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2982 "/share/java/htsjdk/"))
2983 #:build-target "all"
2985 (modify-phases %standard-phases
2986 ;; The build phase also installs the jars
2987 (delete 'install))))
2989 `(("java-ngs" ,java-ngs)
2990 ("java-snappy-1" ,java-snappy-1)
2991 ("java-commons-compress" ,java-commons-compress)
2992 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
2993 ("java-commons-jexl-2" ,java-commons-jexl-2)
2994 ("java-xz" ,java-xz)))
2996 `(("java-testng" ,java-testng)))
2997 (home-page "http://samtools.github.io/htsjdk/")
2998 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3000 "HTSJDK is an implementation of a unified Java library for accessing
3001 common file formats, such as SAM and VCF, used for high-throughput
3002 sequencing (HTS) data. There are also an number of useful utilities for
3003 manipulating HTS data.")
3004 (license license:expat)))
3006 (define-public java-htsjdk-latest
3008 (name "java-htsjdk")
3013 (url "https://github.com/samtools/htsjdk.git")
3015 (file-name (string-append name "-" version "-checkout"))
3018 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3019 (build-system ant-build-system)
3021 `(#:tests? #f ; test require Scala
3023 #:jar-name "htsjdk.jar"
3025 (modify-phases %standard-phases
3026 (add-after 'unpack 'remove-useless-build.xml
3027 (lambda _ (delete-file "build.xml") #t))
3028 ;; The tests require the scalatest package.
3029 (add-after 'unpack 'remove-tests
3030 (lambda _ (delete-file-recursively "src/test") #t)))))
3032 `(("java-ngs" ,java-ngs)
3033 ("java-snappy-1" ,java-snappy-1)
3034 ("java-commons-compress" ,java-commons-compress)
3035 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3036 ("java-commons-jexl-2" ,java-commons-jexl-2)
3037 ("java-xz" ,java-xz)))
3039 `(("java-junit" ,java-junit)))
3040 (home-page "http://samtools.github.io/htsjdk/")
3041 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3043 "HTSJDK is an implementation of a unified Java library for accessing
3044 common file formats, such as SAM and VCF, used for high-throughput
3045 sequencing (HTS) data. There are also an number of useful utilities for
3046 manipulating HTS data.")
3047 (license license:expat)))
3049 ;; This is needed for picard 2.10.3
3050 (define-public java-htsjdk-2.10.1
3051 (package (inherit java-htsjdk-latest)
3052 (name "java-htsjdk")
3057 (url "https://github.com/samtools/htsjdk.git")
3059 (file-name (string-append name "-" version "-checkout"))
3062 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3063 (build-system ant-build-system)
3065 `(#:tests? #f ; tests require Scala
3067 #:jar-name "htsjdk.jar"
3069 (modify-phases %standard-phases
3070 (add-after 'unpack 'remove-useless-build.xml
3071 (lambda _ (delete-file "build.xml") #t))
3072 ;; The tests require the scalatest package.
3073 (add-after 'unpack 'remove-tests
3074 (lambda _ (delete-file-recursively "src/test") #t)))))))
3076 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3077 ;; recent version of java-htsjdk, which depends on gradle.
3078 (define-public java-picard
3080 (name "java-picard")
3085 (url "https://github.com/broadinstitute/picard.git")
3087 (file-name (string-append "java-picard-" version "-checkout"))
3090 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3091 (modules '((guix build utils)))
3094 ;; Delete pre-built binaries.
3095 (delete-file-recursively "lib")
3097 (substitute* "build.xml"
3098 ;; Remove build-time dependency on git.
3099 (("failifexecutionfails=\"true\"")
3100 "failifexecutionfails=\"false\"")
3102 (("depends=\"compile-htsjdk, ")
3104 (("depends=\"compile-htsjdk-tests, ")
3106 ;; Build picard-lib.jar before building picard.jar
3107 (("name=\"picard-jar\" depends=\"" line)
3108 (string-append line "picard-lib-jar, ")))
3110 (build-system ant-build-system)
3112 `(#:build-target "picard-jar"
3113 #:test-target "test"
3114 ;; Tests require jacoco:coverage.
3117 (list (string-append "-Dhtsjdk_lib_dir="
3118 (assoc-ref %build-inputs "java-htsjdk")
3119 "/share/java/htsjdk/")
3120 "-Dhtsjdk-classes=dist/tmp"
3121 (string-append "-Dhtsjdk-version="
3122 ,(package-version java-htsjdk)))
3125 (modify-phases %standard-phases
3126 (add-after 'unpack 'use-our-htsjdk
3127 (lambda* (#:key inputs #:allow-other-keys)
3128 (substitute* "build.xml"
3129 (("\\$\\{htsjdk\\}/lib")
3130 (string-append (assoc-ref inputs "java-htsjdk")
3131 "/share/java/htsjdk/")))
3133 (add-after 'unpack 'make-test-target-independent
3134 (lambda* (#:key inputs #:allow-other-keys)
3135 (substitute* "build.xml"
3136 (("name=\"test\" depends=\"compile, ")
3137 "name=\"test\" depends=\""))
3139 (replace 'install (install-jars "dist")))))
3141 `(("java-htsjdk" ,java-htsjdk)
3142 ("java-guava" ,java-guava)))
3144 `(("java-testng" ,java-testng)))
3145 (home-page "http://broadinstitute.github.io/picard/")
3146 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3147 (description "Picard is a set of Java command line tools for manipulating
3148 high-throughput sequencing (HTS) data and formats. Picard is implemented
3149 using the HTSJDK Java library to support accessing file formats that are
3150 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3152 (license license:expat)))
3154 ;; This is the last version of Picard to provide net.sf.samtools
3155 (define-public java-picard-1.113
3156 (package (inherit java-picard)
3157 (name "java-picard")
3162 (url "https://github.com/broadinstitute/picard.git")
3164 (file-name (string-append "java-picard-" version "-checkout"))
3167 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3168 (modules '((guix build utils)))
3171 ;; Delete pre-built binaries.
3172 (delete-file-recursively "lib")
3175 (build-system ant-build-system)
3177 `(#:build-target "picard-jar"
3178 #:test-target "test"
3179 ;; FIXME: the class path at test time is wrong.
3180 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3181 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3184 ;; This is only used for tests.
3186 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3188 (modify-phases %standard-phases
3189 ;; Do not use bundled ant bzip2.
3190 (add-after 'unpack 'use-ant-bzip
3191 (lambda* (#:key inputs #:allow-other-keys)
3192 (substitute* "build.xml"
3193 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3194 (string-append (assoc-ref inputs "ant")
3197 (add-after 'unpack 'make-test-target-independent
3198 (lambda* (#:key inputs #:allow-other-keys)
3199 (substitute* "build.xml"
3200 (("name=\"test\" depends=\"compile, ")
3201 "name=\"test\" depends=\"compile-tests, ")
3202 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3203 "name=\"compile\" depends=\"compile-src\""))
3205 (add-after 'unpack 'fix-deflater-path
3206 (lambda* (#:key outputs #:allow-other-keys)
3207 (substitute* "src/java/net/sf/samtools/Defaults.java"
3208 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3209 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3210 (assoc-ref outputs "out")
3211 "/lib/jni/libIntelDeflater.so"
3214 ;; Build the deflater library, because we've previously deleted the
3215 ;; pre-built one. This can only be built with access to the JDK
3217 (add-after 'build 'build-jni
3218 (lambda* (#:key inputs #:allow-other-keys)
3221 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3222 "-xf" (assoc-ref inputs "jdk-src")))
3223 (zero? (system* "javah" "-jni"
3224 "-classpath" "classes"
3226 "net.sf.samtools.util.zip.IntelDeflater"))
3227 (with-directory-excursion "src/c/inteldeflater"
3228 (zero? (system* "gcc" "-I../../../lib" "-I."
3229 (string-append "-I" (assoc-ref inputs "jdk")
3231 "-I../../../jdk-src/src/share/native/common/"
3232 "-I../../../jdk-src/src/solaris/native/common/"
3233 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3234 (zero? (system* "gcc" "-shared"
3235 "-o" "../../../lib/jni/libIntelDeflater.so"
3236 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3237 ;; We can only build everything else after building the JNI library.
3238 (add-after 'build-jni 'build-rest
3239 (lambda* (#:key make-flags #:allow-other-keys)
3240 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3241 (add-before 'build 'set-JAVA6_HOME
3243 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3245 (replace 'install (install-jars "dist"))
3246 (add-after 'install 'install-jni-lib
3247 (lambda* (#:key outputs #:allow-other-keys)
3248 (let ((jni (string-append (assoc-ref outputs "out")
3251 (install-file "lib/jni/libIntelDeflater.so" jni)
3254 `(("java-snappy-1" ,java-snappy-1)
3255 ("java-commons-jexl-2" ,java-commons-jexl-2)
3256 ("java-cofoja" ,java-cofoja)
3257 ("ant" ,ant) ; for bzip2 support at runtime
3260 `(("ant-apache-bcel" ,ant-apache-bcel)
3261 ("ant-junit" ,ant-junit)
3262 ("java-testng" ,java-testng)
3263 ("java-commons-bcel" ,java-commons-bcel)
3264 ("java-jcommander" ,java-jcommander)
3265 ("jdk" ,icedtea-8 "jdk")
3266 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3268 (define-public fastqc
3275 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3276 "projects/fastqc/fastqc_v"
3277 version "_source.zip"))
3280 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3281 (build-system ant-build-system)
3283 `(#:tests? #f ; there are no tests
3284 #:build-target "build"
3286 (modify-phases %standard-phases
3287 (add-after 'unpack 'fix-dependencies
3288 (lambda* (#:key inputs #:allow-other-keys)
3289 (substitute* "build.xml"
3291 (string-append (assoc-ref inputs "java-jbzip2")
3292 "/share/java/jbzip2.jar"))
3294 (string-append (assoc-ref inputs "java-picard-1.113")
3295 "/share/java/sam-1.112.jar"))
3297 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3298 "/share/java/sis-jhdf5.jar")))
3300 ;; There is no installation target
3302 (lambda* (#:key inputs outputs #:allow-other-keys)
3303 (let* ((out (assoc-ref outputs "out"))
3304 (bin (string-append out "/bin"))
3305 (share (string-append out "/share/fastqc/"))
3306 (exe (string-append share "/fastqc")))
3307 (for-each mkdir-p (list bin share))
3308 (copy-recursively "bin" share)
3310 (("my \\$java_bin = 'java';")
3311 (string-append "my $java_bin = '"
3312 (assoc-ref inputs "java")
3315 (symlink exe (string-append bin "/fastqc"))
3319 ("perl" ,perl) ; needed for the wrapper script
3320 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3321 ("java-picard-1.113" ,java-picard-1.113)
3322 ("java-jbzip2" ,java-jbzip2)))
3324 `(("unzip" ,unzip)))
3325 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3326 (synopsis "Quality control tool for high throughput sequence data")
3328 "FastQC aims to provide a simple way to do some quality control
3329 checks on raw sequence data coming from high throughput sequencing
3330 pipelines. It provides a modular set of analyses which you can use to
3331 give a quick impression of whether your data has any problems of which
3332 you should be aware before doing any further analysis.
3334 The main functions of FastQC are:
3337 @item Import of data from BAM, SAM or FastQ files (any variant);
3338 @item Providing a quick overview to tell you in which areas there may
3340 @item Summary graphs and tables to quickly assess your data;
3341 @item Export of results to an HTML based permanent report;
3342 @item Offline operation to allow automated generation of reports
3343 without running the interactive application.
3345 (license license:gpl3+)))
3347 (define-public htslib
3354 "https://github.com/samtools/htslib/releases/download/"
3355 version "/htslib-" version ".tar.bz2"))
3358 "1jsca3hg4rbr6iqq6imkj4lsvgl8g9768bcmny3hlff2w25vx24m"))))
3359 (build-system gnu-build-system)
3362 (modify-phases %standard-phases
3364 'unpack 'patch-tests
3366 (substitute* "test/test.pl"
3367 (("/bin/bash") (which "bash")))
3370 `(("openssl" ,openssl)
3375 (home-page "http://www.htslib.org")
3376 (synopsis "C library for reading/writing high-throughput sequencing data")
3378 "HTSlib is a C library for reading/writing high-throughput sequencing
3379 data. It also provides the @command{bgzip}, @command{htsfile}, and
3380 @command{tabix} utilities.")
3381 ;; Files under cram/ are released under the modified BSD license;
3382 ;; the rest is released under the Expat license
3383 (license (list license:expat license:bsd-3))))
3385 ;; This package should be removed once no packages rely upon it.
3393 "https://github.com/samtools/htslib/releases/download/"
3394 version "/htslib-" version ".tar.bz2"))
3397 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3406 "https://github.com/nboley/idr/archive/"
3408 (file-name (string-append name "-" version ".tar.gz"))
3411 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3412 ;; Delete generated C code.
3414 '(begin (delete-file "idr/inv_cdf.c") #t))))
3415 (build-system python-build-system)
3416 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3417 ;; are no longer part of this package. It also asserts False, which
3418 ;; causes the tests to always fail.
3419 (arguments `(#:tests? #f))
3421 `(("python-scipy" ,python-scipy)
3422 ("python-sympy" ,python-sympy)
3423 ("python-numpy" ,python-numpy)
3424 ("python-matplotlib" ,python-matplotlib)))
3426 `(("python-cython" ,python-cython)))
3427 (home-page "https://github.com/nboley/idr")
3428 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3430 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3431 to measure the reproducibility of findings identified from replicate
3432 experiments and provide highly stable thresholds based on reproducibility.")
3433 (license license:gpl2+)))
3435 (define-public jellyfish
3441 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3442 "releases/download/v" version
3443 "/jellyfish-" version ".tar.gz"))
3446 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3447 (build-system gnu-build-system)
3448 (outputs '("out" ;for library
3449 "ruby" ;for Ruby bindings
3450 "python")) ;for Python bindings
3453 (list (string-append "--enable-ruby-binding="
3454 (assoc-ref %outputs "ruby"))
3455 (string-append "--enable-python-binding="
3456 (assoc-ref %outputs "python")))
3458 (modify-phases %standard-phases
3459 (add-before 'check 'set-SHELL-variable
3461 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3463 (setenv "SHELL" (which "bash"))
3469 ("python" ,python-2)
3470 ("pkg-config" ,pkg-config)))
3472 `(("htslib" ,htslib)))
3473 (synopsis "Tool for fast counting of k-mers in DNA")
3475 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3476 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3477 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3478 is a command-line program that reads FASTA and multi-FASTA files containing
3479 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3480 translated into a human-readable text format using the @code{jellyfish dump}
3481 command, or queried for specific k-mers with @code{jellyfish query}.")
3482 (home-page "http://www.genome.umd.edu/jellyfish.html")
3483 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3484 (supported-systems '("x86_64-linux"))
3485 ;; The combined work is published under the GPLv3 or later. Individual
3486 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3487 (license (list license:gpl3+ license:expat))))
3489 (define-public khmer
3496 (uri (pypi-uri "khmer" version))
3499 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3500 (patches (search-patches "khmer-use-libraries.patch"))))
3501 (build-system python-build-system)
3504 (modify-phases %standard-phases
3505 (add-after 'unpack 'set-paths
3506 (lambda* (#:key inputs outputs #:allow-other-keys)
3507 ;; Delete bundled libraries.
3508 (delete-file-recursively "third-party/zlib")
3509 (delete-file-recursively "third-party/bzip2")
3510 ;; Replace bundled seqan.
3511 (let* ((seqan-all "third-party/seqan")
3512 (seqan-include (string-append
3513 seqan-all "/core/include")))
3514 (delete-file-recursively seqan-all)
3515 (copy-recursively (string-append (assoc-ref inputs "seqan")
3517 (string-append seqan-include "/seqan")))
3518 ;; We do not replace the bundled MurmurHash as the canonical
3519 ;; repository for this code 'SMHasher' is unsuitable for
3520 ;; providing a library. See
3521 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3523 (add-after 'unpack 'set-cc
3527 ;; It is simpler to test after installation.
3529 (add-after 'install 'post-install-check
3530 (lambda* (#:key inputs outputs #:allow-other-keys)
3531 (let ((out (assoc-ref outputs "out")))
3536 (assoc-ref outputs "out")
3538 (setenv "PYTHONPATH"
3540 (getenv "PYTHONPATH")
3544 (string-take (string-take-right
3545 (assoc-ref inputs "python") 5) 3)
3547 (with-directory-excursion "build"
3548 (zero? (system* "nosetests" "khmer" "--attr"
3549 "!known_failing")))))))))
3552 ("python-nose" ,python-nose)))
3556 ("python-screed" ,python-screed)
3557 ("python-bz2file" ,python-bz2file)
3558 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3559 ;; until the next version of khmer (likely 2.1) is released.
3561 (home-page "https://khmer.readthedocs.org/")
3562 (synopsis "K-mer counting, filtering and graph traversal library")
3563 (description "The khmer software is a set of command-line tools for
3564 working with DNA shotgun sequencing data from genomes, transcriptomes,
3565 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3566 sometimes better. Khmer can also identify and fix problems with shotgun
3568 ;; When building on i686, armhf and mips64el, we get the following error:
3569 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3570 (supported-systems '("x86_64-linux" "aarch64-linux"))
3571 (license license:bsd-3)))
3573 (define-public kaiju
3580 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3582 (file-name (string-append name "-" version ".tar.gz"))
3585 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3586 (build-system gnu-build-system)
3588 `(#:tests? #f ; There are no tests.
3590 (modify-phases %standard-phases
3592 (add-before 'build 'move-to-src-dir
3593 (lambda _ (chdir "src") #t))
3595 (lambda* (#:key inputs outputs #:allow-other-keys)
3596 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3599 (copy-recursively "bin" bin)
3600 (copy-recursively "util" bin))
3604 (home-page "http://kaiju.binf.ku.dk/")
3605 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3606 (description "Kaiju is a program for sensitive taxonomic classification
3607 of high-throughput sequencing reads from metagenomic whole genome sequencing
3609 (license license:gpl3+)))
3614 (version "2.1.0.20151222")
3617 (uri (pypi-uri "MACS2" version))
3620 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3621 (build-system python-build-system)
3623 `(#:python ,python-2 ; only compatible with Python 2.7
3624 #:tests? #f)) ; no test target
3626 `(("python-numpy" ,python2-numpy)))
3627 (home-page "https://github.com/taoliu/MACS/")
3628 (synopsis "Model based analysis for ChIP-Seq data")
3630 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3631 identifying transcript factor binding sites named Model-based Analysis of
3632 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3633 the significance of enriched ChIP regions and it improves the spatial
3634 resolution of binding sites through combining the information of both
3635 sequencing tag position and orientation.")
3636 (license license:bsd-3)))
3638 (define-public mafft
3645 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3646 "-without-extensions-src.tgz"))
3647 (file-name (string-append name "-" version ".tgz"))
3650 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3651 (build-system gnu-build-system)
3653 `(#:tests? #f ; no automated tests, though there are tests in the read me
3654 #:make-flags (let ((out (assoc-ref %outputs "out")))
3655 (list (string-append "PREFIX=" out)
3656 (string-append "BINDIR="
3657 (string-append out "/bin"))))
3659 (modify-phases %standard-phases
3660 (add-after 'unpack 'enter-dir
3661 (lambda _ (chdir "core") #t))
3662 (add-after 'enter-dir 'patch-makefile
3664 ;; on advice from the MAFFT authors, there is no need to
3665 ;; distribute mafft-profile, mafft-distance, or
3666 ;; mafft-homologs.rb as they are too "specialised".
3667 (substitute* "Makefile"
3668 ;; remove mafft-homologs.rb from SCRIPTS
3669 (("^SCRIPTS = mafft mafft-homologs.rb")
3671 ;; remove mafft-homologs from MANPAGES
3672 (("^MANPAGES = mafft.1 mafft-homologs.1")
3673 "MANPAGES = mafft.1")
3674 ;; remove mafft-distance from PROGS
3675 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3676 "PROGS = dvtditr dndfast7 dndblast sextet5")
3677 ;; remove mafft-profile from PROGS
3678 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3679 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3680 (("^rm -f mafft-profile mafft-profile.exe") "#")
3681 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3682 ;; do not install MAN pages in libexec folder
3683 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3684 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3686 (add-after 'enter-dir 'patch-paths
3687 (lambda* (#:key inputs #:allow-other-keys)
3688 (substitute* '("pairash.c"
3690 (("perl") (which "perl"))
3691 (("([\"`| ])awk" _ prefix)
3692 (string-append prefix (which "awk")))
3693 (("grep") (which "grep")))
3696 (add-after 'install 'wrap-programs
3697 (lambda* (#:key outputs #:allow-other-keys)
3698 (let* ((out (assoc-ref outputs "out"))
3699 (bin (string-append out "/bin"))
3700 (path (string-append
3701 (assoc-ref %build-inputs "coreutils") "/bin:")))
3702 (for-each (lambda (file)
3704 `("PATH" ":" prefix (,path))))
3712 ("coreutils" ,coreutils)))
3713 (home-page "http://mafft.cbrc.jp/alignment/software/")
3714 (synopsis "Multiple sequence alignment program")
3716 "MAFFT offers a range of multiple alignment methods for nucleotide and
3717 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3718 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3720 (license (license:non-copyleft
3721 "http://mafft.cbrc.jp/alignment/software/license.txt"
3722 "BSD-3 with different formatting"))))
3731 "https://github.com/marbl/mash/archive/v"
3733 (file-name (string-append name "-" version ".tar.gz"))
3736 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3737 (modules '((guix build utils)))
3739 ;; Delete bundled kseq.
3740 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3741 '(delete-file "src/mash/kseq.h"))))
3742 (build-system gnu-build-system)
3744 `(#:tests? #f ; No tests.
3747 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3748 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3749 #:make-flags (list "CC=gcc")
3751 (modify-phases %standard-phases
3752 (add-after 'unpack 'fix-includes
3754 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3755 (("^#include \"kseq\\.h\"")
3756 "#include \"htslib/kseq.h\""))
3758 (add-after 'fix-includes 'autoconf
3759 (lambda _ (zero? (system* "autoconf")))))))
3761 `(("autoconf" ,autoconf)
3762 ;; Capnproto and htslib are statically embedded in the final
3763 ;; application. Therefore we also list their licenses, below.
3764 ("capnproto" ,capnproto)
3765 ("htslib" ,htslib)))
3769 (supported-systems '("x86_64-linux"))
3770 (home-page "https://mash.readthedocs.io")
3771 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3772 (description "Mash is a fast sequence distance estimator that uses the
3773 MinHash algorithm and is designed to work with genomes and metagenomes in the
3774 form of assemblies or reads.")
3775 (license (list license:bsd-3 ; Mash
3776 license:expat ; HTSlib and capnproto
3777 license:public-domain ; MurmurHash 3
3778 license:cpl1.0)))) ; Open Bloom Filter
3780 (define-public metabat
3787 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3789 (file-name (string-append name "-" version ".tar.gz"))
3792 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3793 (patches (search-patches "metabat-fix-compilation.patch"))))
3794 (build-system scons-build-system)
3796 `(#:scons ,scons-python2
3798 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3799 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3800 #:tests? #f ;; Tests are run during the build phase.
3802 (modify-phases %standard-phases
3803 (add-after 'unpack 'fix-includes
3805 (substitute* "src/BamUtils.h"
3806 (("^#include \"bam/bam\\.h\"")
3807 "#include \"samtools/bam.h\"")
3808 (("^#include \"bam/sam\\.h\"")
3809 "#include \"samtools/sam.h\""))
3810 (substitute* "src/KseqReader.h"
3811 (("^#include \"bam/kseq\\.h\"")
3812 "#include \"htslib/kseq.h\""))
3814 (add-after 'unpack 'fix-scons
3815 (lambda* (#:key inputs #:allow-other-keys)
3816 (substitute* "SConstruct"
3817 (("^htslib_dir += 'samtools'")
3818 (string-append "htslib_dir = '"
3819 (assoc-ref inputs "htslib")
3821 (("^samtools_dir = 'samtools'")
3822 (string-append "samtools_dir = '"
3823 (assoc-ref inputs "samtools")
3825 (("^findStaticOrShared\\('bam', hts_lib")
3826 (string-append "findStaticOrShared('bam', '"
3827 (assoc-ref inputs "samtools")
3829 ;; Do not distribute README.
3830 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3835 ("samtools" ,samtools)
3838 (home-page "https://bitbucket.org/berkeleylab/metabat")
3840 "Reconstruction of single genomes from complex microbial communities")
3842 "Grouping large genomic fragments assembled from shotgun metagenomic
3843 sequences to deconvolute complex microbial communities, or metagenome binning,
3844 enables the study of individual organisms and their interactions. MetaBAT is
3845 an automated metagenome binning software, which integrates empirical
3846 probabilistic distances of genome abundance and tetranucleotide frequency.")
3847 ;; The source code contains inline assembly.
3848 (supported-systems '("x86_64-linux" "i686-linux"))
3849 (license (license:non-copyleft "file://license.txt"
3850 "See license.txt in the distribution."))))
3852 (define-public minced
3859 "https://github.com/ctSkennerton/minced/archive/"
3861 (file-name (string-append name "-" version ".tar.gz"))
3864 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3865 (build-system gnu-build-system)
3867 `(#:test-target "test"
3869 (modify-phases %standard-phases
3871 (add-before 'check 'fix-test
3873 ;; Fix test for latest version.
3874 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3875 (("minced:0.1.6") "minced:0.2.0"))
3877 (replace 'install ; No install target.
3878 (lambda* (#:key inputs outputs #:allow-other-keys)
3879 (let* ((out (assoc-ref outputs "out"))
3880 (bin (string-append out "/bin"))
3881 (wrapper (string-append bin "/minced")))
3882 ;; Minced comes with a wrapper script that tries to figure out where
3883 ;; it is located before running the JAR. Since these paths are known
3884 ;; to us, we build our own wrapper to avoid coreutils dependency.
3885 (install-file "minced.jar" bin)
3886 (with-output-to-file wrapper
3890 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3891 (assoc-ref inputs "jre") "/bin/java -jar "
3892 bin "/minced.jar \"$@\"\n"))))
3893 (chmod wrapper #o555)))))))
3895 `(("jdk" ,icedtea "jdk")))
3898 ("jre" ,icedtea "out")))
3899 (home-page "https://github.com/ctSkennerton/minced")
3900 (synopsis "Mining CRISPRs in Environmental Datasets")
3902 "MinCED is a program to find Clustered Regularly Interspaced Short
3903 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3904 unassembled metagenomic reads, but is mainly designed for full genomes and
3905 assembled metagenomic sequence.")
3906 (license license:gpl3+)))
3914 (uri (pypi-uri "misopy" version))
3917 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3918 (modules '((guix build utils)))
3920 '(substitute* "setup.py"
3921 ;; Use setuptools, or else the executables are not
3923 (("distutils.core") "setuptools")
3924 ;; use "gcc" instead of "cc" for compilation
3926 "cc.set_executables(
3930 linker_so='gcc -shared'); defines")))))
3931 (build-system python-build-system)
3933 `(#:python ,python-2 ; only Python 2 is supported
3934 #:tests? #f)) ; no "test" target
3936 `(("samtools" ,samtools)
3937 ("python-numpy" ,python2-numpy)
3938 ("python-pysam" ,python2-pysam)
3939 ("python-scipy" ,python2-scipy)
3940 ("python-matplotlib" ,python2-matplotlib)))
3942 `(("python-mock" ,python2-mock) ;for tests
3943 ("python-pytz" ,python2-pytz))) ;for tests
3944 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3945 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3947 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3948 the expression level of alternatively spliced genes from RNA-Seq data, and
3949 identifies differentially regulated isoforms or exons across samples. By
3950 modeling the generative process by which reads are produced from isoforms in
3951 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3952 that a read originated from a particular isoform.")
3953 (license license:gpl2)))
3955 (define-public muscle
3958 (version "3.8.1551")
3960 (method url-fetch/tarbomb)
3962 "http://www.drive5.com/muscle/muscle_src_"
3966 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3967 (build-system gnu-build-system)
3969 `(#:make-flags (list "LDLIBS = -lm")
3971 (modify-phases %standard-phases
3974 ;; There are no tests, so just test if it runs.
3975 (lambda _ (zero? (system* "./muscle" "-version"))))
3977 (lambda* (#:key outputs #:allow-other-keys)
3978 (let* ((out (assoc-ref outputs "out"))
3979 (bin (string-append out "/bin")))
3980 (install-file "muscle" bin)))))))
3981 (home-page "http://www.drive5.com/muscle")
3982 (synopsis "Multiple sequence alignment program")
3984 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3985 program for nucleotide and protein sequences.")
3986 ;; License information found in 'muscle -h' and usage.cpp.
3987 (license license:public-domain)))
3989 (define-public newick-utils
3990 ;; There are no recent releases so we package from git.
3991 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3993 (name "newick-utils")
3994 (version (string-append "1.6-1." (string-take commit 8)))
3998 (url "https://github.com/tjunier/newick_utils.git")
4000 (file-name (string-append name "-" version "-checkout"))
4003 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4004 (build-system gnu-build-system)
4007 (modify-phases %standard-phases
4008 (add-after 'unpack 'autoconf
4009 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4011 ;; XXX: TODO: Enable Lua and Guile bindings.
4012 ;; https://github.com/tjunier/newick_utils/issues/13
4013 `(("libxml2" ,libxml2)
4017 `(("autoconf" ,autoconf)
4018 ("automake" ,automake)
4019 ("libtool" ,libtool)))
4020 (synopsis "Programs for working with newick format phylogenetic trees")
4022 "Newick-utils is a suite of utilities for processing phylogenetic trees
4023 in Newick format. Functions include re-rooting, extracting subtrees,
4024 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4025 (home-page "https://github.com/tjunier/newick_utils")
4026 (license license:bsd-3))))
4035 "https://github.com/wwood/OrfM/releases/download/v"
4036 version "/orfm-" version ".tar.gz"))
4039 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4040 (build-system gnu-build-system)
4041 (inputs `(("zlib" ,zlib)))
4043 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4044 ("ruby-rspec" ,ruby-rspec)
4046 (synopsis "Simple and not slow open reading frame (ORF) caller")
4048 "An ORF caller finds stretches of DNA that, when translated, are not
4049 interrupted by stop codons. OrfM finds and prints these ORFs.")
4050 (home-page "https://github.com/wwood/OrfM")
4051 (license license:lgpl3+)))
4053 (define-public pplacer
4054 (let ((commit "g807f6f3"))
4057 ;; The commit should be updated with each version change.
4058 (version "1.1.alpha19")
4062 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4064 (file-name (string-append name "-" version ".tar.gz"))
4066 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4067 (build-system ocaml-build-system)
4069 `(#:ocaml ,ocaml-4.01
4070 #:findlib ,ocaml4.01-findlib
4071 #:modules ((guix build ocaml-build-system)
4075 (modify-phases %standard-phases
4077 (add-after 'unpack 'replace-bundled-cddlib
4078 (lambda* (#:key inputs #:allow-other-keys)
4079 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4080 (local-dir "cddlib_guix"))
4082 (with-directory-excursion local-dir
4083 (system* "tar" "xvf" cddlib-src))
4084 (let ((cddlib-src-folder
4085 (string-append local-dir "/"
4086 (list-ref (scandir local-dir) 2)
4091 (string-append "cdd_src/" (basename file))))
4092 (find-files cddlib-src-folder ".*[ch]$")))
4094 (add-after 'unpack 'fix-makefile
4096 ;; Remove system calls to 'git'.
4097 (substitute* "Makefile"
4098 (("^DESCRIPT:=pplacer-.*")
4100 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4101 (substitute* "myocamlbuild.ml"
4102 (("git describe --tags --long .*\\\" with")
4104 "echo -n v" ,version "-" ,commit "\" with")))
4107 (lambda* (#:key outputs #:allow-other-keys)
4108 (let* ((out (assoc-ref outputs "out"))
4109 (bin (string-append out "/bin")))
4110 (copy-recursively "bin" bin))
4115 ("ocaml-ounit" ,ocaml4.01-ounit)
4116 ("ocaml-batteries" ,ocaml4.01-batteries)
4117 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4118 ("ocaml-csv" ,ocaml4.01-csv)
4119 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4120 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4121 ("ocaml-mcl" ,ocaml4.01-mcl)
4122 ("ocaml-gsl" ,ocaml4.01-gsl)
4123 ("cddlib-src" ,(package-source cddlib))))
4125 `(("pplacer-scripts" ,pplacer-scripts)))
4126 (synopsis "Phylogenetic placement of biological sequences")
4128 "Pplacer places query sequences on a fixed reference phylogenetic tree
4129 to maximize phylogenetic likelihood or posterior probability according to a
4130 reference alignment. Pplacer is designed to be fast, to give useful
4131 information about uncertainty, and to offer advanced visualization and
4132 downstream analysis.")
4133 (home-page "http://matsen.fhcrc.org/pplacer")
4134 (license license:gpl3))))
4136 ;; This package is installed alongside 'pplacer'. It is a separate package so
4137 ;; that it can use the python-build-system for the scripts that are
4138 ;; distributed alongside the main OCaml binaries.
4139 (define pplacer-scripts
4142 (name "pplacer-scripts")
4143 (build-system python-build-system)
4145 `(#:python ,python-2
4147 (modify-phases %standard-phases
4148 (add-after 'unpack 'enter-scripts-dir
4149 (lambda _ (chdir "scripts")))
4152 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4153 (add-after 'install 'wrap-executables
4154 (lambda* (#:key inputs outputs #:allow-other-keys)
4155 (let* ((out (assoc-ref outputs "out"))
4156 (bin (string-append out "/bin")))
4157 (let ((path (string-append
4158 (assoc-ref inputs "hmmer") "/bin:"
4159 (assoc-ref inputs "infernal") "/bin")))
4161 (wrap-program (string-append bin "/refpkg_align.py")
4162 `("PATH" ":" prefix (,path))))
4163 (let ((path (string-append
4164 (assoc-ref inputs "hmmer") "/bin")))
4165 (wrap-program (string-append bin "/hrefpkg_query.py")
4166 `("PATH" ":" prefix (,path)))))
4169 `(("infernal" ,infernal)
4172 `(("python-biopython" ,python2-biopython)
4173 ("taxtastic" ,taxtastic)))
4174 (synopsis "Pplacer Python scripts")))
4176 (define-public python2-pbcore
4178 (name "python2-pbcore")
4182 (uri (pypi-uri "pbcore" version))
4185 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4186 (build-system python-build-system)
4187 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4189 `(("python-cython" ,python2-cython)
4190 ("python-numpy" ,python2-numpy)
4191 ("python-pysam" ,python2-pysam)
4192 ("python-h5py" ,python2-h5py)))
4194 `(("python-nose" ,python2-nose)
4195 ("python-sphinx" ,python2-sphinx)
4196 ("python-pyxb" ,python2-pyxb)))
4197 (home-page "http://pacificbiosciences.github.io/pbcore/")
4198 (synopsis "Library for reading and writing PacBio data files")
4200 "The pbcore package provides Python APIs for interacting with PacBio data
4201 files and writing bioinformatics applications.")
4202 (license license:bsd-3)))
4204 (define-public python2-warpedlmm
4206 (name "python2-warpedlmm")
4212 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4216 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4217 (build-system python-build-system)
4219 `(#:python ,python-2)) ; requires Python 2.7
4221 `(("python-scipy" ,python2-scipy)
4222 ("python-numpy" ,python2-numpy)
4223 ("python-matplotlib" ,python2-matplotlib)
4224 ("python-fastlmm" ,python2-fastlmm)
4225 ("python-pandas" ,python2-pandas)
4226 ("python-pysnptools" ,python2-pysnptools)))
4228 `(("python-mock" ,python2-mock)
4229 ("python-nose" ,python2-nose)
4231 (home-page "https://github.com/PMBio/warpedLMM")
4232 (synopsis "Implementation of warped linear mixed models")
4234 "WarpedLMM is a Python implementation of the warped linear mixed model,
4235 which automatically learns an optimal warping function (or transformation) for
4236 the phenotype as it models the data.")
4237 (license license:asl2.0)))
4239 (define-public pbtranscript-tofu
4240 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4242 (name "pbtranscript-tofu")
4243 (version (string-append "2.2.3." (string-take commit 7)))
4247 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4249 (file-name (string-append name "-" version "-checkout"))
4252 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4253 (modules '((guix build utils)))
4256 ;; remove bundled Cython sources
4257 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4259 (build-system python-build-system)
4261 `(#:python ,python-2
4262 ;; FIXME: Tests fail with "No such file or directory:
4263 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4266 (modify-phases %standard-phases
4267 (add-after 'unpack 'enter-directory
4269 (chdir "pbtranscript-tofu/pbtranscript/")
4271 ;; With setuptools version 18.0 and later this setup.py hack causes
4272 ;; a build error, so we disable it.
4273 (add-after 'enter-directory 'patch-setuppy
4275 (substitute* "setup.py"
4276 (("if 'setuptools.extension' in sys.modules:")
4280 `(("python-numpy" ,python2-numpy)
4281 ("python-bx-python" ,python2-bx-python)
4282 ("python-networkx" ,python2-networkx)
4283 ("python-scipy" ,python2-scipy)
4284 ("python-pbcore" ,python2-pbcore)
4285 ("python-h5py" ,python2-h5py)))
4287 `(("python-cython" ,python2-cython)
4288 ("python-nose" ,python2-nose)))
4289 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4290 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4292 "pbtranscript-tofu contains scripts to analyze transcriptome data
4293 generated using the PacBio Iso-Seq protocol.")
4294 (license license:bsd-3))))
4296 (define-public prank
4303 "http://wasabiapp.org/download/prank/prank.source."
4307 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4308 (build-system gnu-build-system)
4311 (modify-phases %standard-phases
4312 (add-after 'unpack 'enter-src-dir
4316 (add-after 'unpack 'remove-m64-flag
4317 ;; Prank will build with the correct 'bit-ness' without this flag
4318 ;; and this allows building on 32-bit machines.
4319 (lambda _ (substitute* "src/Makefile"
4324 (lambda* (#:key outputs #:allow-other-keys)
4325 (let* ((out (assoc-ref outputs "out"))
4326 (bin (string-append out "/bin"))
4327 (man (string-append out "/share/man/man1"))
4328 (path (string-append
4329 (assoc-ref %build-inputs "mafft") "/bin:"
4330 (assoc-ref %build-inputs "exonerate") "/bin:"
4331 (assoc-ref %build-inputs "bppsuite") "/bin")))
4332 (install-file "prank" bin)
4333 (wrap-program (string-append bin "/prank")
4334 `("PATH" ":" prefix (,path)))
4335 (install-file "prank.1" man))
4339 ("exonerate" ,exonerate)
4340 ("bppsuite" ,bppsuite)))
4341 (home-page "http://wasabiapp.org/software/prank/")
4342 (synopsis "Probabilistic multiple sequence alignment program")
4344 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4345 codon and amino-acid sequences. It is based on a novel algorithm that treats
4346 insertions correctly and avoids over-estimation of the number of deletion
4347 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4348 in phylogenetics and correctly takes into account the evolutionary distances
4349 between sequences. Lastly, PRANK allows for defining a potential structure
4350 for sequences to be aligned and then, simultaneously with the alignment,
4351 predicts the locations of structural units in the sequences.")
4352 (license license:gpl2+)))
4354 (define-public proteinortho
4356 (name "proteinortho")
4363 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4364 version "_src.tar.gz"))
4367 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4368 (build-system gnu-build-system)
4370 `(#:test-target "test"
4372 (modify-phases %standard-phases
4374 ;; There is no configure script, so we modify the Makefile directly.
4375 (lambda* (#:key outputs #:allow-other-keys)
4376 (substitute* "Makefile"
4379 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4381 (add-before 'install 'make-install-directory
4382 ;; The install directory is not created during 'make install'.
4383 (lambda* (#:key outputs #:allow-other-keys)
4384 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4386 (add-after 'install 'wrap-programs
4387 (lambda* (#:key inputs outputs #:allow-other-keys)
4388 (let* ((path (getenv "PATH"))
4389 (out (assoc-ref outputs "out"))
4390 (binary (string-append out "/bin/proteinortho5.pl")))
4391 (wrap-program binary `("PATH" ":" prefix (,path))))
4395 ("python" ,python-2)
4396 ("blast+" ,blast+)))
4397 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4398 (synopsis "Detect orthologous genes across species")
4400 "Proteinortho is a tool to detect orthologous genes across different
4401 species. For doing so, it compares similarities of given gene sequences and
4402 clusters them to find significant groups. The algorithm was designed to handle
4403 large-scale data and can be applied to hundreds of species at once.")
4404 (license license:gpl2+)))
4406 (define-public pyicoteo
4413 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4414 "pyicoteo/get/v" version ".tar.bz2"))
4415 (file-name (string-append name "-" version ".tar.bz2"))
4418 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4419 (build-system python-build-system)
4421 `(#:python ,python-2 ; does not work with Python 3
4422 #:tests? #f)) ; there are no tests
4424 `(("python2-matplotlib" ,python2-matplotlib)))
4425 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4426 (synopsis "Analyze high-throughput genetic sequencing data")
4428 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4429 sequencing data. It works with genomic coordinates. There are currently six
4430 different command-line tools:
4433 @item pyicoregion: for generating exploratory regions automatically;
4434 @item pyicoenrich: for differential enrichment between two conditions;
4435 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4436 @item pyicos: for genomic coordinates manipulation;
4437 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4438 @item pyicount: to count how many reads from N experiment files overlap in a
4440 @item pyicotrocol: to combine operations from pyicoteo.
4442 (license license:gpl3+)))
4444 (define-public prodigal
4451 "https://github.com/hyattpd/Prodigal/archive/v"
4453 (file-name (string-append name "-" version ".tar.gz"))
4456 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4457 (build-system gnu-build-system)
4459 `(#:tests? #f ;no check target
4460 #:make-flags (list (string-append "INSTALLDIR="
4461 (assoc-ref %outputs "out")
4464 (modify-phases %standard-phases
4465 (delete 'configure))))
4466 (home-page "http://prodigal.ornl.gov")
4467 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4469 "Prodigal runs smoothly on finished genomes, draft genomes, and
4470 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4471 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4472 partial genes, and identifies translation initiation sites.")
4473 (license license:gpl3+)))
4475 (define-public roary
4483 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4487 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4488 (build-system perl-build-system)
4491 (modify-phases %standard-phases
4496 ;; The tests are not run by default, so we run each test file
4498 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4500 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4501 (getenv "PERL5LIB")))
4502 (zero? (length (filter (lambda (file)
4503 (display file)(display "\n")
4504 (not (zero? (system* "perl" file))))
4505 (find-files "t" ".*\\.t$"))))))
4507 ;; There is no 'install' target in the Makefile.
4508 (lambda* (#:key outputs #:allow-other-keys)
4509 (let* ((out (assoc-ref outputs "out"))
4510 (bin (string-append out "/bin"))
4511 (perl (string-append out "/lib/perl5/site_perl"))
4512 (roary-plots "contrib/roary_plots"))
4515 (copy-recursively "bin" bin)
4516 (copy-recursively "lib" perl)
4518 (add-after 'install 'wrap-programs
4519 (lambda* (#:key inputs outputs #:allow-other-keys)
4520 (let* ((out (assoc-ref outputs "out"))
4521 (perl5lib (getenv "PERL5LIB"))
4522 (path (getenv "PATH")))
4523 (for-each (lambda (prog)
4524 (let ((binary (string-append out "/" prog)))
4525 (wrap-program binary
4526 `("PERL5LIB" ":" prefix
4527 (,(string-append perl5lib ":" out
4528 "/lib/perl5/site_perl"))))
4529 (wrap-program binary
4531 (,(string-append path ":" out "/bin"))))))
4532 (find-files "bin" ".*[^R]$"))
4534 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4535 (r-site-lib (getenv "R_LIBS_SITE"))
4537 (string-append (assoc-ref inputs "coreutils") "/bin")))
4539 `("R_LIBS_SITE" ":" prefix
4540 (,(string-append r-site-lib ":" out "/site-library/"))))
4543 (,(string-append coreutils-path ":" out "/bin"))))))
4546 `(("perl-env-path" ,perl-env-path)
4547 ("perl-test-files" ,perl-test-files)
4548 ("perl-test-most" ,perl-test-most)
4549 ("perl-test-output" ,perl-test-output)))
4551 `(("perl-array-utils" ,perl-array-utils)
4552 ("bioperl" ,bioperl-minimal)
4553 ("perl-digest-md5-file" ,perl-digest-md5-file)
4554 ("perl-exception-class" ,perl-exception-class)
4555 ("perl-file-find-rule" ,perl-file-find-rule)
4556 ("perl-file-grep" ,perl-file-grep)
4557 ("perl-file-slurper" ,perl-file-slurper)
4558 ("perl-file-which" ,perl-file-which)
4559 ("perl-graph" ,perl-graph)
4560 ("perl-graph-readwrite" ,perl-graph-readwrite)
4561 ("perl-log-log4perl" ,perl-log-log4perl)
4562 ("perl-moose" ,perl-moose)
4563 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4564 ("perl-text-csv" ,perl-text-csv)
4565 ("bedtools" ,bedtools)
4569 ("parallel" ,parallel)
4572 ("fasttree" ,fasttree)
4576 ("r-minimal" ,r-minimal)
4577 ("r-ggplot2" ,r-ggplot2)
4578 ("coreutils" ,coreutils)))
4579 (home-page "http://sanger-pathogens.github.io/Roary")
4580 (synopsis "High speed stand-alone pan genome pipeline")
4582 "Roary is a high speed stand alone pan genome pipeline, which takes
4583 annotated assemblies in GFF3 format (produced by the Prokka program) and
4584 calculates the pan genome. Using a standard desktop PC, it can analyse
4585 datasets with thousands of samples, without compromising the quality of the
4586 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4587 single processor. Roary is not intended for metagenomics or for comparing
4588 extremely diverse sets of genomes.")
4589 (license license:gpl3)))
4591 (define-public raxml
4600 "https://github.com/stamatak/standard-RAxML/archive/v"
4602 (file-name (string-append name "-" version ".tar.gz"))
4605 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4606 (build-system gnu-build-system)
4608 `(#:tests? #f ; There are no tests.
4609 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4610 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4612 (modify-phases %standard-phases
4615 (lambda* (#:key outputs #:allow-other-keys)
4616 (let* ((out (assoc-ref outputs "out"))
4617 (bin (string-append out "/bin"))
4618 (executable "raxmlHPC-HYBRID"))
4619 (install-file executable bin)
4620 (symlink (string-append bin "/" executable) "raxml"))
4623 `(("openmpi" ,openmpi)))
4624 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4625 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4627 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4629 ;; The source includes x86 specific code
4630 (supported-systems '("x86_64-linux" "i686-linux"))
4631 (license license:gpl2+)))
4641 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4644 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4645 (patches (search-patches "rsem-makefile.patch"))
4646 (modules '((guix build utils)))
4649 ;; remove bundled copy of boost
4650 (delete-file-recursively "boost")
4652 (build-system gnu-build-system)
4654 `(#:tests? #f ;no "check" target
4656 (modify-phases %standard-phases
4657 ;; No "configure" script.
4658 ;; Do not build bundled samtools library.
4661 (substitute* "Makefile"
4662 (("^all : sam/libbam.a") "all : "))
4665 (lambda* (#:key outputs #:allow-other-keys)
4666 (let* ((out (string-append (assoc-ref outputs "out")))
4667 (bin (string-append out "/bin/"))
4668 (perl (string-append out "/lib/perl5/site_perl")))
4671 (for-each (lambda (file)
4672 (install-file file bin))
4673 (find-files "." "rsem-.*"))
4674 (install-file "rsem_perl_utils.pm" perl))
4677 'install 'wrap-program
4678 (lambda* (#:key outputs #:allow-other-keys)
4679 (let ((out (assoc-ref outputs "out")))
4680 (for-each (lambda (prog)
4681 (wrap-program (string-append out "/bin/" prog)
4682 `("PERL5LIB" ":" prefix
4683 (,(string-append out "/lib/perl5/site_perl")))))
4684 '("rsem-plot-transcript-wiggles"
4685 "rsem-calculate-expression"
4686 "rsem-generate-ngvector"
4688 "rsem-prepare-reference")))
4692 ("ncurses" ,ncurses)
4693 ("r-minimal" ,r-minimal)
4695 ("samtools" ,samtools-0.1)
4697 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4698 (synopsis "Estimate gene expression levels from RNA-Seq data")
4700 "RSEM is a software package for estimating gene and isoform expression
4701 levels from RNA-Seq data. The RSEM package provides a user-friendly
4702 interface, supports threads for parallel computation of the EM algorithm,
4703 single-end and paired-end read data, quality scores, variable-length reads and
4704 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4705 interval estimates for expression levels. For visualization, it can generate
4706 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4707 (license license:gpl3+)))
4709 (define-public rseqc
4717 (string-append "mirror://sourceforge/rseqc/"
4718 "RSeQC-" version ".tar.gz"))
4720 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4721 (modules '((guix build utils)))
4724 ;; remove bundled copy of pysam
4725 (delete-file-recursively "lib/pysam")
4726 (substitute* "setup.py"
4727 ;; remove dependency on outdated "distribute" module
4728 (("^from distribute_setup import use_setuptools") "")
4729 (("^use_setuptools\\(\\)") "")
4730 ;; do not use bundled copy of pysam
4731 (("^have_pysam = False") "have_pysam = True"))))))
4732 (build-system python-build-system)
4733 (arguments `(#:python ,python-2))
4735 `(("python-cython" ,python2-cython)
4736 ("python-pysam" ,python2-pysam)
4737 ("python-numpy" ,python2-numpy)
4740 `(("python-nose" ,python2-nose)))
4741 (home-page "http://rseqc.sourceforge.net/")
4742 (synopsis "RNA-seq quality control package")
4744 "RSeQC provides a number of modules that can comprehensively evaluate
4745 high throughput sequence data, especially RNA-seq data. Some basic modules
4746 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4747 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4748 distribution, coverage uniformity, strand specificity, etc.")
4749 (license license:gpl3+)))
4752 ;; There are no release tarballs. According to the installation
4753 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4754 ;; stable release is identified by this changeset ID.
4755 (let ((changeset "2329130")
4759 (version (string-append "0-" revision "." changeset))
4763 (url "https://bitbucket.org/libsleipnir/sleipnir")
4764 (changeset changeset)))
4767 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4768 (build-system gnu-build-system)
4770 `(#:modules ((srfi srfi-1)
4771 (guix build gnu-build-system)
4774 (let ((dirs '("SeekMiner"
4780 (modify-phases %standard-phases
4781 (add-before 'configure 'bootstrap
4783 (zero? (system* "bash" "gen_auto"))))
4784 (add-after 'build 'build-additional-tools
4785 (lambda* (#:key make-flags #:allow-other-keys)
4786 (every (lambda (dir)
4787 (with-directory-excursion (string-append "tools/" dir)
4788 (zero? (apply system* "make" make-flags))))
4790 (add-after 'install 'install-additional-tools
4791 (lambda* (#:key make-flags #:allow-other-keys)
4792 (fold (lambda (dir result)
4793 (with-directory-excursion (string-append "tools/" dir)
4795 (zero? (apply system*
4796 `("make" ,@make-flags "install"))))))
4802 ("readline" ,readline)
4803 ("gengetopt" ,gengetopt)
4804 ("log4cpp" ,log4cpp)))
4806 `(("autoconf" ,autoconf)
4807 ("automake" ,automake)
4809 (home-page "http://seek.princeton.edu")
4810 (synopsis "Gene co-expression search engine")
4812 "SEEK is a computational gene co-expression search engine. SEEK provides
4813 biologists with a way to navigate the massive human expression compendium that
4814 now contains thousands of expression datasets. SEEK returns a robust ranking
4815 of co-expressed genes in the biological area of interest defined by the user's
4816 query genes. It also prioritizes thousands of expression datasets according
4817 to the user's query of interest.")
4818 (license license:cc-by3.0))))
4820 (define-public samtools
4828 (string-append "mirror://sourceforge/samtools/samtools/"
4829 version "/samtools-" version ".tar.bz2"))
4832 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4833 (build-system gnu-build-system)
4835 `(#:modules ((ice-9 ftw)
4837 (guix build gnu-build-system)
4839 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4840 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4842 (modify-phases %standard-phases
4843 (add-after 'unpack 'patch-tests
4845 (substitute* "test/test.pl"
4846 ;; The test script calls out to /bin/bash
4847 (("/bin/bash") (which "bash")))
4849 (add-after 'install 'install-library
4850 (lambda* (#:key outputs #:allow-other-keys)
4851 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4852 (install-file "libbam.a" lib)
4854 (add-after 'install 'install-headers
4855 (lambda* (#:key outputs #:allow-other-keys)
4856 (let ((include (string-append (assoc-ref outputs "out")
4857 "/include/samtools/")))
4858 (for-each (lambda (file)
4859 (install-file file include))
4860 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4862 (native-inputs `(("pkg-config" ,pkg-config)))
4864 `(("htslib" ,htslib)
4865 ("ncurses" ,ncurses)
4869 (home-page "http://samtools.sourceforge.net")
4870 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4872 "Samtools implements various utilities for post-processing nucleotide
4873 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4874 variant calling (in conjunction with bcftools), and a simple alignment
4876 (license license:expat)))
4878 (define-public samtools-0.1
4879 ;; This is the most recent version of the 0.1 line of samtools. The input
4880 ;; and output formats differ greatly from that used and produced by samtools
4881 ;; 1.x and is still used in many bioinformatics pipelines.
4882 (package (inherit samtools)
4888 (string-append "mirror://sourceforge/samtools/samtools/"
4889 version "/samtools-" version ".tar.bz2"))
4891 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4893 `(#:tests? #f ;no "check" target
4894 ,@(substitute-keyword-arguments (package-arguments samtools)
4895 ((#:make-flags flags)
4896 `(cons "LIBCURSES=-lncurses" ,flags))
4898 `(modify-phases ,phases
4900 (lambda* (#:key outputs #:allow-other-keys)
4901 (let ((bin (string-append
4902 (assoc-ref outputs "out") "/bin")))
4904 (install-file "samtools" bin)
4906 (delete 'patch-tests)
4907 (delete 'configure))))))))
4909 (define-public mosaik
4910 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4915 ;; There are no release tarballs nor tags.
4918 (url "https://github.com/wanpinglee/MOSAIK.git")
4920 (file-name (string-append name "-" version))
4923 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4924 (build-system gnu-build-system)
4926 `(#:tests? #f ; no tests
4927 #:make-flags (list "CC=gcc")
4929 (modify-phases %standard-phases
4931 (lambda _ (chdir "src") #t))
4933 (lambda* (#:key outputs #:allow-other-keys)
4934 (let ((bin (string-append (assoc-ref outputs "out")
4937 (copy-recursively "../bin" bin)
4942 (supported-systems '("x86_64-linux"))
4943 (home-page "https://github.com/wanpinglee/MOSAIK")
4944 (synopsis "Map nucleotide sequence reads to reference genomes")
4946 "MOSAIK is a program for mapping second and third-generation sequencing
4947 reads to a reference genome. MOSAIK can align reads generated by all the
4948 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4949 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4950 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4951 ;; code released into the public domain:
4952 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4953 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4954 (license (list license:gpl2+ license:public-domain)))))
4956 (define-public ngs-sdk
4964 (string-append "https://github.com/ncbi/ngs/archive/"
4966 (file-name (string-append name "-" version ".tar.gz"))
4969 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4970 (build-system gnu-build-system)
4972 `(#:parallel-build? #f ; not supported
4973 #:tests? #f ; no "check" target
4975 (modify-phases %standard-phases
4977 (lambda* (#:key outputs #:allow-other-keys)
4978 (let ((out (assoc-ref outputs "out")))
4979 ;; Allow 'konfigure.perl' to find 'package.prl'.
4981 (string-append ".:" (getenv "PERL5LIB")))
4983 ;; The 'configure' script doesn't recognize things like
4984 ;; '--enable-fast-install'.
4985 (zero? (system* "./configure"
4986 (string-append "--build-prefix=" (getcwd) "/build")
4987 (string-append "--prefix=" out))))))
4988 (add-after 'unpack 'enter-dir
4989 (lambda _ (chdir "ngs-sdk") #t)))))
4990 (native-inputs `(("perl" ,perl)))
4991 ;; According to the test
4992 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4993 ;; in ngs-sdk/setup/konfigure.perl
4994 (supported-systems '("i686-linux" "x86_64-linux"))
4995 (home-page "https://github.com/ncbi/ngs")
4996 (synopsis "API for accessing Next Generation Sequencing data")
4998 "NGS is a domain-specific API for accessing reads, alignments and pileups
4999 produced from Next Generation Sequencing. The API itself is independent from
5000 any particular back-end implementation, and supports use of multiple back-ends
5002 (license license:public-domain)))
5004 (define-public java-ngs
5005 (package (inherit ngs-sdk)
5008 `(,@(substitute-keyword-arguments
5009 `(#:modules ((guix build gnu-build-system)
5013 ,@(package-arguments ngs-sdk))
5015 `(modify-phases ,phases
5016 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5018 `(("jdk" ,icedtea "jdk")
5019 ("ngs-sdk" ,ngs-sdk)))
5020 (synopsis "Java bindings for NGS SDK")))
5022 (define-public ncbi-vdb
5030 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5032 (file-name (string-append name "-" version ".tar.gz"))
5035 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5036 (build-system gnu-build-system)
5038 `(#:parallel-build? #f ; not supported
5039 #:tests? #f ; no "check" target
5041 (modify-phases %standard-phases
5042 (add-before 'configure 'set-perl-search-path
5044 ;; Work around "dotless @INC" build failure.
5046 (string-append (getcwd) "/setup:"
5047 (getenv "PERL5LIB")))
5050 (lambda* (#:key inputs outputs #:allow-other-keys)
5051 (let ((out (assoc-ref outputs "out")))
5052 ;; Override include path for libmagic
5053 (substitute* "setup/package.prl"
5054 (("name => 'magic', Include => '/usr/include'")
5055 (string-append "name=> 'magic', Include => '"
5056 (assoc-ref inputs "libmagic")
5059 ;; Install kdf5 library (needed by sra-tools)
5060 (substitute* "build/Makefile.install"
5061 (("LIBRARIES_TO_INSTALL =")
5062 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5064 (substitute* "build/Makefile.env"
5065 (("CFLAGS =" prefix)
5066 (string-append prefix "-msse2 ")))
5068 ;; Override search path for ngs-java
5069 (substitute* "setup/package.prl"
5070 (("/usr/local/ngs/ngs-java")
5071 (assoc-ref inputs "java-ngs")))
5073 ;; The 'configure' script doesn't recognize things like
5074 ;; '--enable-fast-install'.
5077 (string-append "--build-prefix=" (getcwd) "/build")
5078 (string-append "--prefix=" (assoc-ref outputs "out"))
5079 (string-append "--debug")
5080 (string-append "--with-xml2-prefix="
5081 (assoc-ref inputs "libxml2"))
5082 (string-append "--with-ngs-sdk-prefix="
5083 (assoc-ref inputs "ngs-sdk"))
5084 (string-append "--with-hdf5-prefix="
5085 (assoc-ref inputs "hdf5")))))))
5086 (add-after 'install 'install-interfaces
5087 (lambda* (#:key outputs #:allow-other-keys)
5088 ;; Install interface libraries. On i686 the interface libraries
5089 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5090 ;; architecture name ("i386") instead of the target system prefix
5092 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5093 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5094 ,(system->linux-architecture
5095 (or (%current-target-system)
5098 (string-append (assoc-ref outputs "out")
5100 ;; Install interface headers
5101 (copy-recursively "interfaces"
5102 (string-append (assoc-ref outputs "out")
5105 ;; These files are needed by sra-tools.
5106 (add-after 'install 'install-configuration-files
5107 (lambda* (#:key outputs #:allow-other-keys)
5108 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5110 (install-file "libs/kfg/default.kfg" target)
5111 (install-file "libs/kfg/certs.kfg" target))
5114 `(("libxml2" ,libxml2)
5115 ("ngs-sdk" ,ngs-sdk)
5116 ("java-ngs" ,java-ngs)
5119 (native-inputs `(("perl" ,perl)))
5120 ;; NCBI-VDB requires SSE capability.
5121 (supported-systems '("i686-linux" "x86_64-linux"))
5122 (home-page "https://github.com/ncbi/ncbi-vdb")
5123 (synopsis "Database engine for genetic information")
5125 "The NCBI-VDB library implements a highly compressed columnar data
5126 warehousing engine that is most often used to store genetic information.
5127 Databases are stored in a portable image within the file system, and can be
5128 accessed/downloaded on demand across HTTP.")
5129 (license license:public-domain)))
5131 (define-public plink
5139 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5140 version "-src.zip"))
5142 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5143 (patches (search-patches "plink-1.07-unclobber-i.patch"
5144 "plink-endian-detection.patch"))))
5145 (build-system gnu-build-system)
5147 '(#:tests? #f ;no "check" target
5148 #:make-flags (list (string-append "LIB_LAPACK="
5149 (assoc-ref %build-inputs "lapack")
5150 "/lib/liblapack.so")
5153 ;; disable phoning home
5156 (modify-phases %standard-phases
5157 ;; no "configure" script
5160 (lambda* (#:key outputs #:allow-other-keys)
5161 (let ((bin (string-append (assoc-ref outputs "out")
5163 (install-file "plink" bin)
5167 ("lapack" ,lapack)))
5169 `(("unzip" ,unzip)))
5170 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5171 (synopsis "Whole genome association analysis toolset")
5173 "PLINK is a whole genome association analysis toolset, designed to
5174 perform a range of basic, large-scale analyses in a computationally efficient
5175 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5176 so there is no support for steps prior to this (e.g. study design and
5177 planning, generating genotype or CNV calls from raw data). Through
5178 integration with gPLINK and Haploview, there is some support for the
5179 subsequent visualization, annotation and storage of results.")
5180 ;; Code is released under GPLv2, except for fisher.h, which is under
5182 (license (list license:gpl2 license:lgpl2.1+))))
5184 (define-public plink-ng
5185 (package (inherit plink)
5191 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5193 (file-name (string-append name "-" version ".tar.gz"))
5195 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5196 (build-system gnu-build-system)
5198 '(#:tests? #f ;no "check" target
5199 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5200 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5202 "-f" "Makefile.std")
5204 (modify-phases %standard-phases
5205 (add-after 'unpack 'chdir
5206 (lambda _ (chdir "1.9") #t))
5207 (delete 'configure) ; no "configure" script
5209 (lambda* (#:key outputs #:allow-other-keys)
5210 (let ((bin (string-append (assoc-ref outputs "out")
5212 (install-file "plink" bin)
5217 ("openblas" ,openblas)))
5218 (home-page "https://www.cog-genomics.org/plink/")
5219 (license license:gpl3+)))
5221 (define-public smithlab-cpp
5222 (let ((revision "1")
5223 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5225 (name "smithlab-cpp")
5226 (version (string-append "0." revision "." (string-take commit 7)))
5230 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5232 (file-name (string-append name "-" version "-checkout"))
5235 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5236 (build-system gnu-build-system)
5238 `(#:modules ((guix build gnu-build-system)
5241 #:tests? #f ;no "check" target
5243 (modify-phases %standard-phases
5244 (add-after 'unpack 'use-samtools-headers
5246 (substitute* '("SAM.cpp"
5248 (("sam.h") "samtools/sam.h"))
5251 (lambda* (#:key outputs #:allow-other-keys)
5252 (let* ((out (assoc-ref outputs "out"))
5253 (lib (string-append out "/lib"))
5254 (include (string-append out "/include/smithlab-cpp")))
5257 (for-each (cut install-file <> lib)
5258 (find-files "." "\\.o$"))
5259 (for-each (cut install-file <> include)
5260 (find-files "." "\\.hpp$")))
5262 (delete 'configure))))
5264 `(("samtools" ,samtools-0.1)
5266 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5267 (synopsis "C++ helper library for functions used in Smith lab projects")
5269 "Smithlab CPP is a C++ library that includes functions used in many of
5270 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5271 structures, classes for genomic regions, mapped sequencing reads, etc.")
5272 (license license:gpl3+))))
5274 (define-public preseq
5280 (uri (string-append "https://github.com/smithlabcode/"
5281 "preseq/archive/v" version ".tar.gz"))
5282 (file-name (string-append name "-" version ".tar.gz"))
5284 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5285 (modules '((guix build utils)))
5287 ;; Remove bundled samtools.
5288 '(delete-file-recursively "samtools"))))
5289 (build-system gnu-build-system)
5291 `(#:tests? #f ;no "check" target
5293 (modify-phases %standard-phases
5294 (delete 'configure))
5296 (list (string-append "PREFIX="
5297 (assoc-ref %outputs "out"))
5298 (string-append "LIBBAM="
5299 (assoc-ref %build-inputs "samtools")
5301 (string-append "SMITHLAB_CPP="
5302 (assoc-ref %build-inputs "smithlab-cpp")
5305 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5308 ("samtools" ,samtools-0.1)
5309 ("smithlab-cpp" ,smithlab-cpp)
5311 (home-page "http://smithlabresearch.org/software/preseq/")
5312 (synopsis "Program for analyzing library complexity")
5314 "The preseq package is aimed at predicting and estimating the complexity
5315 of a genomic sequencing library, equivalent to predicting and estimating the
5316 number of redundant reads from a given sequencing depth and how many will be
5317 expected from additional sequencing using an initial sequencing experiment.
5318 The estimates can then be used to examine the utility of further sequencing,
5319 optimize the sequencing depth, or to screen multiple libraries to avoid low
5320 complexity samples.")
5321 (license license:gpl3+)))
5323 (define-public python-screed
5325 (name "python-screed")
5330 (uri (pypi-uri "screed" version))
5333 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5334 (build-system python-build-system)
5337 (modify-phases %standard-phases
5340 (setenv "PYTHONPATH"
5341 (string-append (getenv "PYTHONPATH") ":."))
5342 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5344 `(("python-nose" ,python-nose)))
5346 `(("python-bz2file" ,python-bz2file)))
5347 (home-page "https://github.com/dib-lab/screed/")
5348 (synopsis "Short read sequence database utilities")
5349 (description "Screed parses FASTA and FASTQ files and generates databases.
5350 Values such as sequence name, sequence description, sequence quality and the
5351 sequence itself can be retrieved from these databases.")
5352 (license license:bsd-3)))
5354 (define-public python2-screed
5355 (package-with-python2 python-screed))
5357 (define-public sra-tools
5365 (string-append "https://github.com/ncbi/sra-tools/archive/"
5367 (file-name (string-append name "-" version ".tar.gz"))
5370 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5371 (build-system gnu-build-system)
5373 `(#:parallel-build? #f ; not supported
5374 #:tests? #f ; no "check" target
5376 (list (string-append "DEFAULT_CRT="
5377 (assoc-ref %build-inputs "ncbi-vdb")
5379 (string-append "DEFAULT_KFG="
5380 (assoc-ref %build-inputs "ncbi-vdb")
5382 (string-append "VDB_LIBDIR="
5383 (assoc-ref %build-inputs "ncbi-vdb")
5384 ,(if (string-prefix? "x86_64"
5385 (or (%current-target-system)
5390 (modify-phases %standard-phases
5391 (add-before 'configure 'set-perl-search-path
5393 ;; Work around "dotless @INC" build failure.
5395 (string-append (getcwd) "/setup:"
5396 (getenv "PERL5LIB")))
5399 (lambda* (#:key inputs outputs #:allow-other-keys)
5400 ;; The build system expects a directory containing the sources and
5401 ;; raw build output of ncbi-vdb, including files that are not
5402 ;; installed. Since we are building against an installed version of
5403 ;; ncbi-vdb, the following modifications are needed.
5404 (substitute* "setup/konfigure.perl"
5405 ;; Make the configure script look for the "ilib" directory of
5406 ;; "ncbi-vdb" without first checking for the existence of a
5407 ;; matching library in its "lib" directory.
5408 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5409 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5410 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5411 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5412 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5415 (substitute* "tools/copycat/Makefile"
5416 (("smagic-static") "lmagic"))
5418 ;; The 'configure' script doesn't recognize things like
5419 ;; '--enable-fast-install'.
5422 (string-append "--build-prefix=" (getcwd) "/build")
5423 (string-append "--prefix=" (assoc-ref outputs "out"))
5424 (string-append "--debug")
5425 (string-append "--with-fuse-prefix="
5426 (assoc-ref inputs "fuse"))
5427 (string-append "--with-magic-prefix="
5428 (assoc-ref inputs "libmagic"))
5429 ;; TODO: building with libxml2 fails with linker errors
5430 ;; (string-append "--with-xml2-prefix="
5431 ;; (assoc-ref inputs "libxml2"))
5432 (string-append "--with-ncbi-vdb-sources="
5433 (assoc-ref inputs "ncbi-vdb"))
5434 (string-append "--with-ncbi-vdb-build="
5435 (assoc-ref inputs "ncbi-vdb"))
5436 (string-append "--with-ngs-sdk-prefix="
5437 (assoc-ref inputs "ngs-sdk"))
5438 (string-append "--with-hdf5-prefix="
5439 (assoc-ref inputs "hdf5"))))))
5440 ;; This version of sra-tools fails to build with glibc because of a
5441 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5442 ;; contains a definition of "canonicalize", so we rename it.
5444 ;; See upstream bug report:
5445 ;; https://github.com/ncbi/sra-tools/issues/67
5446 (add-after 'unpack 'patch-away-glibc-conflict
5448 (substitute* "tools/bam-loader/bam.c"
5449 (("canonicalize\\(" line)
5450 (string-append "sra_tools_" line)))
5452 (native-inputs `(("perl" ,perl)))
5454 `(("ngs-sdk" ,ngs-sdk)
5455 ("ncbi-vdb" ,ncbi-vdb)
5460 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5461 (synopsis "Tools and libraries for reading and writing sequencing data")
5463 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5464 reading of sequencing files from the Sequence Read Archive (SRA) database and
5465 writing files into the .sra format.")
5466 (license license:public-domain)))
5468 (define-public seqan
5474 (uri (string-append "http://packages.seqan.de/seqan-library/"
5475 "seqan-library-" version ".tar.bz2"))
5478 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5479 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5480 ;; makes sense to split the outputs.
5481 (outputs '("out" "doc"))
5482 (build-system trivial-build-system)
5484 `(#:modules ((guix build utils))
5487 (use-modules (guix build utils))
5488 (let ((tar (assoc-ref %build-inputs "tar"))
5489 (bzip (assoc-ref %build-inputs "bzip2"))
5490 (out (assoc-ref %outputs "out"))
5491 (doc (assoc-ref %outputs "doc")))
5492 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5493 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5494 (chdir (string-append "seqan-library-" ,version))
5495 (copy-recursively "include" (string-append out "/include"))
5496 (copy-recursively "share" (string-append doc "/share"))))))
5498 `(("source" ,source)
5501 (home-page "http://www.seqan.de")
5502 (synopsis "Library for nucleotide sequence analysis")
5504 "SeqAn is a C++ library of efficient algorithms and data structures for
5505 the analysis of sequences with the focus on biological data. It contains
5506 algorithms and data structures for string representation and their
5507 manipulation, online and indexed string search, efficient I/O of
5508 bioinformatics file formats, sequence alignment, and more.")
5509 (license license:bsd-3)))
5511 (define-public seqmagick
5518 (uri (pypi-uri "seqmagick" version))
5521 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5522 (build-system python-build-system)
5524 `(("python-biopython" ,python-biopython)))
5526 `(("python-nose" ,python-nose)))
5527 (home-page "https://github.com/fhcrc/seqmagick")
5528 (synopsis "Tools for converting and modifying sequence files")
5530 "Bioinformaticians often have to convert sequence files between formats
5531 and do little manipulations on them, and it's not worth writing scripts for
5532 that. Seqmagick is a utility to expose the file format conversion in
5533 BioPython in a convenient way. Instead of having a big mess of scripts, there
5534 is one that takes arguments.")
5535 (license license:gpl3)))
5537 (define-public seqtk
5544 "https://github.com/lh3/seqtk/archive/v"
5546 (file-name (string-append name "-" version ".tar.gz"))
5549 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5550 (modules '((guix build utils)))
5553 ;; Remove extraneous header files, as is done in the seqtk
5555 (for-each (lambda (file) (delete-file file))
5556 (list "ksort.h" "kstring.h" "kvec.h"))
5558 (build-system gnu-build-system)
5561 (modify-phases %standard-phases
5564 ;; There are no tests, so we just run a sanity check.
5565 (lambda _ (zero? (system* "./seqtk" "seq"))))
5567 (lambda* (#:key outputs #:allow-other-keys)
5568 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5569 (install-file "seqtk" bin)))))))
5572 (home-page "https://github.com/lh3/seqtk")
5573 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5575 "Seqtk is a fast and lightweight tool for processing sequences in the
5576 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5577 optionally compressed by gzip.")
5578 (license license:expat)))
5580 (define-public snap-aligner
5582 (name "snap-aligner")
5583 (version "1.0beta.18")
5587 "https://github.com/amplab/snap/archive/v"
5589 (file-name (string-append name "-" version ".tar.gz"))
5592 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5593 (build-system gnu-build-system)
5596 (modify-phases %standard-phases
5598 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5600 (lambda* (#:key outputs #:allow-other-keys)
5601 (let* ((out (assoc-ref outputs "out"))
5602 (bin (string-append out "/bin")))
5603 (install-file "snap-aligner" bin)
5604 (install-file "SNAPCommand" bin)
5608 (home-page "http://snap.cs.berkeley.edu/")
5609 (synopsis "Short read DNA sequence aligner")
5611 "SNAP is a fast and accurate aligner for short DNA reads. It is
5612 optimized for modern read lengths of 100 bases or higher, and takes advantage
5613 of these reads to align data quickly through a hash-based indexing scheme.")
5614 ;; 32-bit systems are not supported by the unpatched code.
5615 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5616 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5617 ;; systems without a lot of memory cannot make good use of this program.
5618 (supported-systems '("x86_64-linux"))
5619 (license license:asl2.0)))
5621 (define-public sortmerna
5629 "https://github.com/biocore/sortmerna/archive/"
5631 (file-name (string-append name "-" version ".tar.gz"))
5634 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5635 (build-system gnu-build-system)
5636 (outputs '("out" ;for binaries
5637 "db")) ;for sequence databases
5640 (modify-phases %standard-phases
5642 (lambda* (#:key outputs #:allow-other-keys)
5643 (let* ((out (assoc-ref outputs "out"))
5644 (bin (string-append out "/bin"))
5645 (db (assoc-ref outputs "db"))
5647 (string-append db "/share/sortmerna/rRNA_databases")))
5648 (install-file "sortmerna" bin)
5649 (install-file "indexdb_rna" bin)
5650 (for-each (lambda (file)
5651 (install-file file share))
5652 (find-files "rRNA_databases" ".*fasta"))
5656 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5657 (synopsis "Biological sequence analysis tool for NGS reads")
5659 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5660 and operational taxonomic unit (OTU) picking of next generation
5661 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5662 allows for fast and sensitive analyses of nucleotide sequences. The main
5663 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5664 ;; The source includes x86 specific code
5665 (supported-systems '("x86_64-linux" "i686-linux"))
5666 (license license:lgpl3)))
5674 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5676 (file-name (string-append name "-" version ".tar.gz"))
5679 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5680 (modules '((guix build utils)))
5683 (substitute* "source/Makefile"
5685 ;; Remove pre-built binaries and bundled htslib sources.
5686 (delete-file-recursively "bin/MacOSX_x86_64")
5687 (delete-file-recursively "bin/Linux_x86_64")
5688 (delete-file-recursively "bin/Linux_x86_64_static")
5689 (delete-file-recursively "source/htslib")
5691 (build-system gnu-build-system)
5693 '(#:tests? #f ;no check target
5694 #:make-flags '("STAR")
5696 (modify-phases %standard-phases
5697 (add-after 'unpack 'enter-source-dir
5698 (lambda _ (chdir "source") #t))
5699 (add-after 'enter-source-dir 'make-reproducible
5701 (substitute* "Makefile"
5702 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5703 (string-append pre "Built with Guix" post)))))
5704 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5706 (substitute* "Makefile"
5707 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5709 (substitute* '("BAMfunctions.cpp"
5714 "bamRemoveDuplicates.cpp")
5715 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5716 (string-append "#include <" header ">")))
5717 (substitute* "IncludeDefine.h"
5718 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5719 (string-append "<" header ">")))
5722 (lambda* (#:key outputs #:allow-other-keys)
5723 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5724 (install-file "STAR" bin))
5726 (delete 'configure))))
5730 `(("htslib" ,htslib)
5732 (home-page "https://github.com/alexdobin/STAR")
5733 (synopsis "Universal RNA-seq aligner")
5735 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5736 based on a previously undescribed RNA-seq alignment algorithm that uses
5737 sequential maximum mappable seed search in uncompressed suffix arrays followed
5738 by seed clustering and stitching procedure. In addition to unbiased de novo
5739 detection of canonical junctions, STAR can discover non-canonical splices and
5740 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5742 ;; Only 64-bit systems are supported according to the README.
5743 (supported-systems '("x86_64-linux" "mips64el-linux"))
5744 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5745 (license license:gpl3+)))
5747 (define-public subread
5753 (uri (string-append "mirror://sourceforge/subread/subread-"
5754 version "/subread-" version "-source.tar.gz"))
5757 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5758 (build-system gnu-build-system)
5760 `(#:tests? #f ;no "check" target
5761 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5762 ;; optimizations by default, so we override these flags such that x86_64
5763 ;; flags are only added when the build target is an x86_64 system.
5765 (list (let ((system ,(or (%current-target-system)
5767 (flags '("-ggdb" "-fomit-frame-pointer"
5768 "-ffast-math" "-funroll-loops"
5769 "-fmessage-length=0"
5770 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5772 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5773 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5774 (if (string-prefix? "x86_64" system)
5775 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5776 (string-append "CCFLAGS=" (string-join flags))))
5777 "-f" "Makefile.Linux"
5778 "CC=gcc ${CCFLAGS}")
5780 (modify-phases %standard-phases
5781 (add-after 'unpack 'enter-dir
5782 (lambda _ (chdir "src") #t))
5784 (lambda* (#:key outputs #:allow-other-keys)
5785 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5787 (copy-recursively "../bin" bin))))
5788 ;; no "configure" script
5789 (delete 'configure))))
5790 (inputs `(("zlib" ,zlib)))
5791 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5792 (synopsis "Tool kit for processing next-gen sequencing data")
5794 "The subread package contains the following tools: subread aligner, a
5795 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5796 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5797 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5798 against local background noises.")
5799 (license license:gpl3+)))
5801 (define-public stringtie
5807 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5808 "stringtie-" version ".tar.gz"))
5811 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5812 (modules '((guix build utils)))
5815 (delete-file-recursively "samtools-0.1.18")
5817 (build-system gnu-build-system)
5819 `(#:tests? #f ;no test suite
5821 (modify-phases %standard-phases
5822 ;; no configure script
5824 (add-before 'build 'use-system-samtools
5826 (substitute* "Makefile"
5827 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5829 (substitute* '("gclib/GBam.h"
5831 (("#include \"(bam|sam|kstring).h\"" _ header)
5832 (string-append "#include <samtools/" header ".h>")))
5834 (add-after 'unpack 'remove-duplicate-typedef
5836 ;; This typedef conflicts with the typedef in
5837 ;; glibc-2.25/include/bits/types.h
5838 (substitute* "gclib/GThreads.h"
5839 (("typedef long long __intmax_t;") ""))
5842 (lambda* (#:key outputs #:allow-other-keys)
5843 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5844 (install-file "stringtie" bin)
5847 `(("samtools" ,samtools-0.1)
5849 (home-page "http://ccb.jhu.edu/software/stringtie/")
5850 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5852 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5853 alignments into potential transcripts. It uses a novel network flow algorithm
5854 as well as an optional de novo assembly step to assemble and quantitate
5855 full-length transcripts representing multiple splice variants for each gene
5856 locus. Its input can include not only the alignments of raw reads used by
5857 other transcript assemblers, but also alignments of longer sequences that have
5858 been assembled from those reads. To identify differentially expressed genes
5859 between experiments, StringTie's output can be processed either by the
5860 Cuffdiff or Ballgown programs.")
5861 (license license:artistic2.0)))
5863 (define-public taxtastic
5869 (uri (pypi-uri "taxtastic" version))
5872 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5873 (build-system python-build-system)
5875 `(#:python ,python-2
5877 (modify-phases %standard-phases
5880 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5882 `(("python-sqlalchemy" ,python2-sqlalchemy)
5883 ("python-decorator" ,python2-decorator)
5884 ("python-biopython" ,python2-biopython)
5885 ("python-pandas" ,python2-pandas)))
5886 (home-page "https://github.com/fhcrc/taxtastic")
5887 (synopsis "Tools for taxonomic naming and annotation")
5889 "Taxtastic is software written in python used to build and maintain
5890 reference packages i.e. collections of reference trees, reference alignments,
5891 profiles, and associated taxonomic information.")
5892 (license license:gpl3+)))
5894 (define-public vcftools
5901 "https://github.com/vcftools/vcftools/releases/download/v"
5902 version "/vcftools-" version ".tar.gz"))
5905 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5906 (build-system gnu-build-system)
5908 `(#:tests? #f ; no "check" target
5910 "CFLAGS=-O2" ; override "-m64" flag
5911 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5912 (string-append "MANDIR=" (assoc-ref %outputs "out")
5913 "/share/man/man1"))))
5915 `(("pkg-config" ,pkg-config)))
5919 (home-page "https://vcftools.github.io/")
5920 (synopsis "Tools for working with VCF files")
5922 "VCFtools is a program package designed for working with VCF files, such
5923 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5924 provide easily accessible methods for working with complex genetic variation
5925 data in the form of VCF files.")
5926 ;; The license is declared as LGPLv3 in the README and
5927 ;; at https://vcftools.github.io/license.html
5928 (license license:lgpl3)))
5930 (define-public infernal
5936 (uri (string-append "http://eddylab.org/software/infernal/"
5937 "infernal-" version ".tar.gz"))
5940 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5941 (build-system gnu-build-system)
5943 `(("perl" ,perl))) ; for tests
5944 (home-page "http://eddylab.org/infernal/")
5945 (synopsis "Inference of RNA alignments")
5946 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5947 searching DNA sequence databases for RNA structure and sequence similarities.
5948 It is an implementation of a special case of profile stochastic context-free
5949 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5950 profile, but it scores a combination of sequence consensus and RNA secondary
5951 structure consensus, so in many cases, it is more capable of identifying RNA
5952 homologs that conserve their secondary structure more than their primary
5954 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5955 (supported-systems '("i686-linux" "x86_64-linux"))
5956 (license license:bsd-3)))
5958 (define-public r-centipede
5960 (name "r-centipede")
5964 (uri (string-append "http://download.r-forge.r-project.org/"
5965 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5968 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5969 (build-system r-build-system)
5970 (home-page "http://centipede.uchicago.edu/")
5971 (synopsis "Predict transcription factor binding sites")
5973 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5974 of the genome that are bound by particular transcription factors. It starts
5975 by identifying a set of candidate binding sites, and then aims to classify the
5976 sites according to whether each site is bound or not bound by a transcription
5977 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5978 between two different types of motif instances using as much relevant
5979 information as possible.")
5980 (license (list license:gpl2+ license:gpl3+))))
5982 (define-public r-vegan
5989 (uri (cran-uri "vegan" version))
5992 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
5993 (build-system r-build-system)
5995 `(("gfortran" ,gfortran)))
5997 `(("r-cluster" ,r-cluster)
5998 ("r-lattice" ,r-lattice)
6001 ("r-permute" ,r-permute)))
6002 (home-page "https://cran.r-project.org/web/packages/vegan")
6003 (synopsis "Functions for community ecology")
6005 "The vegan package provides tools for descriptive community ecology. It
6006 has most basic functions of diversity analysis, community ordination and
6007 dissimilarity analysis. Most of its multivariate tools can be used for other
6008 data types as well.")
6009 (license license:gpl2+)))
6011 (define-public r-annotate
6018 (uri (bioconductor-uri "annotate" version))
6021 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
6022 (build-system r-build-system)
6024 `(("r-annotationdbi" ,r-annotationdbi)
6025 ("r-biobase" ,r-biobase)
6026 ("r-biocgenerics" ,r-biocgenerics)
6028 ("r-rcurl" ,r-rcurl)
6030 ("r-xtable" ,r-xtable)))
6032 "https://bioconductor.org/packages/annotate")
6033 (synopsis "Annotation for microarrays")
6034 (description "This package provides R environments for the annotation of
6036 (license license:artistic2.0)))
6038 (define-public r-copynumber
6040 (name "r-copynumber")
6044 (uri (bioconductor-uri "copynumber" version))
6047 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6048 (build-system r-build-system)
6050 `(("r-s4vectors" ,r-s4vectors)
6051 ("r-iranges" ,r-iranges)
6052 ("r-genomicranges" ,r-genomicranges)
6053 ("r-biocgenerics" ,r-biocgenerics)))
6054 (home-page "https://bioconductor.org/packages/copynumber")
6055 (synopsis "Segmentation of single- and multi-track copy number data")
6057 "This package segments single- and multi-track copy number data by a
6058 penalized least squares regression method.")
6059 (license license:artistic2.0)))
6061 (define-public r-geneplotter
6063 (name "r-geneplotter")
6068 (uri (bioconductor-uri "geneplotter" version))
6071 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6072 (build-system r-build-system)
6074 `(("r-annotate" ,r-annotate)
6075 ("r-annotationdbi" ,r-annotationdbi)
6076 ("r-biobase" ,r-biobase)
6077 ("r-biocgenerics" ,r-biocgenerics)
6078 ("r-lattice" ,r-lattice)
6079 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6080 (home-page "https://bioconductor.org/packages/geneplotter")
6081 (synopsis "Graphics functions for genomic data")
6083 "This package provides functions for plotting genomic data.")
6084 (license license:artistic2.0)))
6086 (define-public r-genefilter
6088 (name "r-genefilter")
6093 (uri (bioconductor-uri "genefilter" version))
6096 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6097 (build-system r-build-system)
6099 `(("gfortran" ,gfortran)))
6101 `(("r-annotate" ,r-annotate)
6102 ("r-annotationdbi" ,r-annotationdbi)
6103 ("r-biobase" ,r-biobase)
6104 ("r-s4vectors" ,r-s4vectors)
6105 ("r-survival" ,r-survival)))
6106 (home-page "https://bioconductor.org/packages/genefilter")
6107 (synopsis "Filter genes from high-throughput experiments")
6109 "This package provides basic functions for filtering genes from
6110 high-throughput sequencing experiments.")
6111 (license license:artistic2.0)))
6113 (define-public r-deseq2
6120 (uri (bioconductor-uri "DESeq2" version))
6123 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6124 (properties `((upstream-name . "DESeq2")))
6125 (build-system r-build-system)
6127 `(("r-biobase" ,r-biobase)
6128 ("r-biocgenerics" ,r-biocgenerics)
6129 ("r-biocparallel" ,r-biocparallel)
6130 ("r-genefilter" ,r-genefilter)
6131 ("r-geneplotter" ,r-geneplotter)
6132 ("r-genomicranges" ,r-genomicranges)
6133 ("r-ggplot2" ,r-ggplot2)
6134 ("r-hmisc" ,r-hmisc)
6135 ("r-iranges" ,r-iranges)
6136 ("r-locfit" ,r-locfit)
6138 ("r-rcpparmadillo" ,r-rcpparmadillo)
6139 ("r-s4vectors" ,r-s4vectors)
6140 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6141 (home-page "https://bioconductor.org/packages/DESeq2")
6142 (synopsis "Differential gene expression analysis")
6144 "This package provides functions to estimate variance-mean dependence in
6145 count data from high-throughput nucleotide sequencing assays and test for
6146 differential expression based on a model using the negative binomial
6148 (license license:lgpl3+)))
6150 (define-public r-dexseq
6157 (uri (bioconductor-uri "DEXSeq" version))
6160 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6161 (properties `((upstream-name . "DEXSeq")))
6162 (build-system r-build-system)
6164 `(("r-annotationdbi" ,r-annotationdbi)
6165 ("r-biobase" ,r-biobase)
6166 ("r-biocgenerics" ,r-biocgenerics)
6167 ("r-biocparallel" ,r-biocparallel)
6168 ("r-biomart" ,r-biomart)
6169 ("r-deseq2" ,r-deseq2)
6170 ("r-genefilter" ,r-genefilter)
6171 ("r-geneplotter" ,r-geneplotter)
6172 ("r-genomicranges" ,r-genomicranges)
6173 ("r-hwriter" ,r-hwriter)
6174 ("r-iranges" ,r-iranges)
6175 ("r-rcolorbrewer" ,r-rcolorbrewer)
6176 ("r-rsamtools" ,r-rsamtools)
6177 ("r-s4vectors" ,r-s4vectors)
6178 ("r-statmod" ,r-statmod)
6179 ("r-stringr" ,r-stringr)
6180 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6181 (home-page "https://bioconductor.org/packages/DEXSeq")
6182 (synopsis "Inference of differential exon usage in RNA-Seq")
6184 "This package is focused on finding differential exon usage using RNA-seq
6185 exon counts between samples with different experimental designs. It provides
6186 functions that allows the user to make the necessary statistical tests based
6187 on a model that uses the negative binomial distribution to estimate the
6188 variance between biological replicates and generalized linear models for
6189 testing. The package also provides functions for the visualization and
6190 exploration of the results.")
6191 (license license:gpl3+)))
6193 (define-public r-annotationforge
6195 (name "r-annotationforge")
6200 (uri (bioconductor-uri "AnnotationForge" version))
6203 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6205 `((upstream-name . "AnnotationForge")))
6206 (build-system r-build-system)
6208 `(("r-annotationdbi" ,r-annotationdbi)
6209 ("r-biobase" ,r-biobase)
6210 ("r-biocgenerics" ,r-biocgenerics)
6212 ("r-rcurl" ,r-rcurl)
6213 ("r-rsqlite" ,r-rsqlite)
6214 ("r-s4vectors" ,r-s4vectors)
6216 (home-page "https://bioconductor.org/packages/AnnotationForge")
6217 (synopsis "Code for building annotation database packages")
6219 "This package provides code for generating Annotation packages and their
6220 databases. Packages produced are intended to be used with AnnotationDbi.")
6221 (license license:artistic2.0)))
6223 (define-public r-rbgl
6230 (uri (bioconductor-uri "RBGL" version))
6233 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6234 (properties `((upstream-name . "RBGL")))
6235 (build-system r-build-system)
6236 (propagated-inputs `(("r-graph" ,r-graph)))
6237 (home-page "https://www.bioconductor.org/packages/RBGL")
6238 (synopsis "Interface to the Boost graph library")
6240 "This package provides a fairly extensive and comprehensive interface to
6241 the graph algorithms contained in the Boost library.")
6242 (license license:artistic2.0)))
6244 (define-public r-gseabase
6251 (uri (bioconductor-uri "GSEABase" version))
6254 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6255 (properties `((upstream-name . "GSEABase")))
6256 (build-system r-build-system)
6258 `(("r-annotate" ,r-annotate)
6259 ("r-annotationdbi" ,r-annotationdbi)
6260 ("r-biobase" ,r-biobase)
6261 ("r-biocgenerics" ,r-biocgenerics)
6262 ("r-graph" ,r-graph)
6264 (home-page "https://bioconductor.org/packages/GSEABase")
6265 (synopsis "Gene set enrichment data structures and methods")
6267 "This package provides classes and methods to support @dfn{Gene Set
6268 Enrichment Analysis} (GSEA).")
6269 (license license:artistic2.0)))
6271 (define-public r-category
6278 (uri (bioconductor-uri "Category" version))
6281 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6282 (properties `((upstream-name . "Category")))
6283 (build-system r-build-system)
6285 `(("r-annotate" ,r-annotate)
6286 ("r-annotationdbi" ,r-annotationdbi)
6287 ("r-biobase" ,r-biobase)
6288 ("r-biocgenerics" ,r-biocgenerics)
6289 ("r-genefilter" ,r-genefilter)
6290 ("r-graph" ,r-graph)
6291 ("r-gseabase" ,r-gseabase)
6292 ("r-matrix" ,r-matrix)
6295 (home-page "https://bioconductor.org/packages/Category")
6296 (synopsis "Category analysis")
6298 "This package provides a collection of tools for performing category
6300 (license license:artistic2.0)))
6302 (define-public r-gostats
6309 (uri (bioconductor-uri "GOstats" version))
6312 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6313 (properties `((upstream-name . "GOstats")))
6314 (build-system r-build-system)
6316 `(("r-annotate" ,r-annotate)
6317 ("r-annotationdbi" ,r-annotationdbi)
6318 ("r-annotationforge" ,r-annotationforge)
6319 ("r-biobase" ,r-biobase)
6320 ("r-category" ,r-category)
6321 ("r-go-db" ,r-go-db)
6322 ("r-graph" ,r-graph)
6323 ("r-rgraphviz" ,r-rgraphviz)
6324 ("r-rbgl" ,r-rbgl)))
6325 (home-page "https://bioconductor.org/packages/GOstats")
6326 (synopsis "Tools for manipulating GO and microarrays")
6328 "This package provides a set of tools for interacting with GO and
6329 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6330 testing and other simple calculations.")
6331 (license license:artistic2.0)))
6333 (define-public r-shortread
6335 (name "r-shortread")
6340 (uri (bioconductor-uri "ShortRead" version))
6343 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6344 (properties `((upstream-name . "ShortRead")))
6345 (build-system r-build-system)
6349 `(("r-biobase" ,r-biobase)
6350 ("r-biocgenerics" ,r-biocgenerics)
6351 ("r-biocparallel" ,r-biocparallel)
6352 ("r-biostrings" ,r-biostrings)
6353 ("r-genomeinfodb" ,r-genomeinfodb)
6354 ("r-genomicalignments" ,r-genomicalignments)
6355 ("r-genomicranges" ,r-genomicranges)
6356 ("r-hwriter" ,r-hwriter)
6357 ("r-iranges" ,r-iranges)
6358 ("r-lattice" ,r-lattice)
6359 ("r-latticeextra" ,r-latticeextra)
6360 ("r-rsamtools" ,r-rsamtools)
6361 ("r-s4vectors" ,r-s4vectors)
6362 ("r-xvector" ,r-xvector)
6363 ("r-zlibbioc" ,r-zlibbioc)))
6364 (home-page "https://bioconductor.org/packages/ShortRead")
6365 (synopsis "FASTQ input and manipulation tools")
6367 "This package implements sampling, iteration, and input of FASTQ files.
6368 It includes functions for filtering and trimming reads, and for generating a
6369 quality assessment report. Data are represented as
6370 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6371 purposes. The package also contains legacy support for early single-end,
6372 ungapped alignment formats.")
6373 (license license:artistic2.0)))
6375 (define-public r-systempiper
6377 (name "r-systempiper")
6382 (uri (bioconductor-uri "systemPipeR" version))
6385 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6386 (properties `((upstream-name . "systemPipeR")))
6387 (build-system r-build-system)
6389 `(("r-annotate" ,r-annotate)
6390 ("r-batchjobs" ,r-batchjobs)
6391 ("r-biocgenerics" ,r-biocgenerics)
6392 ("r-biostrings" ,r-biostrings)
6393 ("r-deseq2" ,r-deseq2)
6394 ("r-edger" ,r-edger)
6395 ("r-genomicfeatures" ,r-genomicfeatures)
6396 ("r-genomicranges" ,r-genomicranges)
6397 ("r-ggplot2" ,r-ggplot2)
6398 ("r-go-db" ,r-go-db)
6399 ("r-gostats" ,r-gostats)
6400 ("r-limma" ,r-limma)
6401 ("r-pheatmap" ,r-pheatmap)
6402 ("r-rjson" ,r-rjson)
6403 ("r-rsamtools" ,r-rsamtools)
6404 ("r-shortread" ,r-shortread)
6405 ("r-summarizedexperiment" ,r-summarizedexperiment)
6406 ("r-variantannotation" ,r-variantannotation)))
6407 (home-page "https://github.com/tgirke/systemPipeR")
6408 (synopsis "Next generation sequencing workflow and reporting environment")
6410 "This R package provides tools for building and running automated
6411 end-to-end analysis workflows for a wide range of @dfn{next generation
6412 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6413 Important features include a uniform workflow interface across different NGS
6414 applications, automated report generation, and support for running both R and
6415 command-line software, such as NGS aligners or peak/variant callers, on local
6416 computers or compute clusters. Efficient handling of complex sample sets and
6417 experimental designs is facilitated by a consistently implemented sample
6418 annotation infrastructure.")
6419 (license license:artistic2.0)))
6421 (define-public r-grohmm
6428 (uri (bioconductor-uri "groHMM" version))
6431 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6432 (properties `((upstream-name . "groHMM")))
6433 (build-system r-build-system)
6435 `(("r-genomeinfodb" ,r-genomeinfodb)
6436 ("r-genomicalignments" ,r-genomicalignments)
6437 ("r-genomicranges" ,r-genomicranges)
6438 ("r-iranges" ,r-iranges)
6440 ("r-rtracklayer" ,r-rtracklayer)
6441 ("r-s4vectors" ,r-s4vectors)))
6442 (home-page "https://github.com/Kraus-Lab/groHMM")
6443 (synopsis "GRO-seq analysis pipeline")
6445 "This package provides a pipeline for the analysis of GRO-seq data.")
6446 (license license:gpl3+)))
6448 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6450 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6454 ;; We cannot use bioconductor-uri here because this tarball is
6455 ;; located under "data/annotation/" instead of "bioc/".
6456 (uri (string-append "https://bioconductor.org/packages/"
6457 "release/data/annotation/src/contrib"
6458 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6462 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6464 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6465 (build-system r-build-system)
6466 ;; As this package provides little more than a very large data file it
6467 ;; doesn't make sense to build substitutes.
6468 (arguments `(#:substitutable? #f))
6470 `(("r-genomicfeatures" ,r-genomicfeatures)))
6472 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6473 (synopsis "Annotation package for human genome in TxDb format")
6475 "This package provides an annotation database of Homo sapiens genome
6476 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6477 track. The database is exposed as a @code{TxDb} object.")
6478 (license license:artistic2.0)))
6480 (define-public r-sparql
6486 (uri (cran-uri "SPARQL" version))
6489 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6490 (properties `((upstream-name . "SPARQL")))
6491 (build-system r-build-system)
6493 `(("r-rcurl" ,r-rcurl)
6495 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6496 (synopsis "SPARQL client for R")
6497 (description "This package provides an interface to use SPARQL to pose
6498 SELECT or UPDATE queries to an end-point.")
6499 ;; The only license indication is found in the DESCRIPTION file,
6500 ;; which states GPL-3. So we cannot assume GPLv3+.
6501 (license license:gpl3)))
6503 (define-public vsearch
6511 "https://github.com/torognes/vsearch/archive/v"
6513 (file-name (string-append name "-" version ".tar.gz"))
6516 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6517 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6520 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6521 ;; for this in the patch.
6522 (delete-file "src/city.h")
6523 (delete-file "src/citycrc.h")
6524 (delete-file "src/city.cc")
6526 (build-system gnu-build-system)
6529 (modify-phases %standard-phases
6530 (add-after 'unpack 'autogen
6531 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6535 ("cityhash" ,cityhash)))
6537 `(("autoconf" ,autoconf)
6538 ("automake" ,automake)))
6539 (synopsis "Sequence search tools for metagenomics")
6541 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6542 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6543 masking. The tool takes advantage of parallelism in the form of SIMD
6544 vectorization as well as multiple threads to perform accurate alignments at
6545 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6546 Needleman-Wunsch).")
6547 (home-page "https://github.com/torognes/vsearch")
6548 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6550 (supported-systems '("x86_64-linux"))
6551 ;; Dual licensed; also includes public domain source.
6552 (license (list license:gpl3 license:bsd-2))))
6554 (define-public pardre
6557 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6562 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6566 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6567 (build-system gnu-build-system)
6569 `(#:tests? #f ; no tests included
6571 (modify-phases %standard-phases
6574 (lambda* (#:key outputs #:allow-other-keys)
6575 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6576 (install-file "ParDRe" bin)
6579 `(("openmpi" ,openmpi)
6581 (synopsis "Parallel tool to remove duplicate DNA reads")
6583 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6584 Duplicate reads can be seen as identical or nearly identical sequences with
6585 some mismatches. This tool lets users avoid the analysis of unnecessary
6586 reads, reducing the time of subsequent procedures with the
6587 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6588 in order to exploit the parallel capabilities of multicore clusters. It is
6589 faster than multithreaded counterparts (end of 2015) for the same number of
6590 cores and, thanks to the message-passing technology, it can be executed on
6592 (home-page "https://sourceforge.net/projects/pardre/")
6593 (license license:gpl3+)))
6595 (define-public ruby-bio-kseq
6597 (name "ruby-bio-kseq")
6602 (uri (rubygems-uri "bio-kseq" version))
6605 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6606 (build-system ruby-build-system)
6608 `(#:test-target "spec"))
6610 `(("bundler" ,bundler)
6611 ("ruby-rspec" ,ruby-rspec)
6612 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6615 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6617 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6618 FASTQ parsing code. It provides a fast iterator over sequences and their
6620 (home-page "https://github.com/gusevfe/bio-kseq")
6621 (license license:expat)))
6623 (define-public bio-locus
6630 (uri (rubygems-uri "bio-locus" version))
6633 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6634 (build-system ruby-build-system)
6636 `(("ruby-rspec" ,ruby-rspec)))
6637 (synopsis "Tool for fast querying of genome locations")
6639 "Bio-locus is a tabix-like tool for fast querying of genome
6640 locations. Many file formats in bioinformatics contain records that
6641 start with a chromosome name and a position for a SNP, or a start-end
6642 position for indels. Bio-locus allows users to store this chr+pos or
6643 chr+pos+alt information in a database.")
6644 (home-page "https://github.com/pjotrp/bio-locus")
6645 (license license:expat)))
6647 (define-public bio-blastxmlparser
6649 (name "bio-blastxmlparser")
6653 (uri (rubygems-uri "bio-blastxmlparser" version))
6656 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6657 (build-system ruby-build-system)
6659 `(("ruby-bio-logger" ,ruby-bio-logger)
6660 ("ruby-nokogiri" ,ruby-nokogiri)))
6662 `(("ruby-rspec" ,ruby-rspec)))
6663 (synopsis "Fast big data BLAST XML parser and library")
6665 "Very fast parallel big-data BLAST XML file parser which can be used as
6666 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6667 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6668 (home-page "https://github.com/pjotrp/blastxmlparser")
6669 (license license:expat)))
6671 (define-public bioruby
6678 (uri (rubygems-uri "bio" version))
6681 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6682 (build-system ruby-build-system)
6684 `(("ruby-libxml" ,ruby-libxml)))
6686 `(("which" ,which))) ; required for test phase
6689 (modify-phases %standard-phases
6690 (add-before 'build 'patch-test-command
6692 (substitute* '("test/functional/bio/test_command.rb")
6693 (("/bin/sh") (which "sh")))
6694 (substitute* '("test/functional/bio/test_command.rb")
6695 (("/bin/ls") (which "ls")))
6696 (substitute* '("test/functional/bio/test_command.rb")
6697 (("which") (which "which")))
6698 (substitute* '("test/functional/bio/test_command.rb",
6699 "test/data/command/echoarg2.sh")
6700 (("/bin/echo") (which "echo")))
6702 (synopsis "Ruby library, shell and utilities for bioinformatics")
6703 (description "BioRuby comes with a comprehensive set of Ruby development
6704 tools and libraries for bioinformatics and molecular biology. BioRuby has
6705 components for sequence analysis, pathway analysis, protein modelling and
6706 phylogenetic analysis; it supports many widely used data formats and provides
6707 easy access to databases, external programs and public web services, including
6708 BLAST, KEGG, GenBank, MEDLINE and GO.")
6709 (home-page "http://bioruby.org/")
6710 ;; Code is released under Ruby license, except for setup
6711 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6712 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6714 (define-public r-acsnminer
6716 (name "r-acsnminer")
6717 (version "0.16.8.25")
6720 (uri (cran-uri "ACSNMineR" version))
6723 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6724 (properties `((upstream-name . "ACSNMineR")))
6725 (build-system r-build-system)
6727 `(("r-ggplot2" ,r-ggplot2)
6728 ("r-gridextra" ,r-gridextra)))
6729 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6730 (synopsis "Gene enrichment analysis")
6732 "This package provides tools to compute and represent gene set enrichment
6733 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6734 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6735 enrichment can be run with hypergeometric test or Fisher exact test, and can
6736 use multiple corrections. Visualization of data can be done either by
6737 barplots or heatmaps.")
6738 (license license:gpl2+)))
6740 (define-public r-biocgenerics
6742 (name "r-biocgenerics")
6746 (uri (bioconductor-uri "BiocGenerics" version))
6749 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6751 `((upstream-name . "BiocGenerics")))
6752 (build-system r-build-system)
6753 (home-page "https://bioconductor.org/packages/BiocGenerics")
6754 (synopsis "S4 generic functions for Bioconductor")
6756 "This package provides S4 generic functions needed by many Bioconductor
6758 (license license:artistic2.0)))
6760 (define-public r-biocinstaller
6762 (name "r-biocinstaller")
6766 (uri (bioconductor-uri "BiocInstaller" version))
6769 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6771 `((upstream-name . "BiocInstaller")))
6772 (build-system r-build-system)
6773 (home-page "https://bioconductor.org/packages/BiocInstaller")
6774 (synopsis "Install Bioconductor packages")
6775 (description "This package is used to install and update R packages from
6776 Bioconductor, CRAN, and Github.")
6777 (license license:artistic2.0)))
6779 (define-public r-biocviews
6781 (name "r-biocviews")
6785 (uri (bioconductor-uri "biocViews" version))
6788 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6790 `((upstream-name . "biocViews")))
6791 (build-system r-build-system)
6793 `(("r-biobase" ,r-biobase)
6794 ("r-graph" ,r-graph)
6796 ("r-rcurl" ,r-rcurl)
6798 ("r-runit" ,r-runit)))
6799 (home-page "https://bioconductor.org/packages/biocViews")
6800 (synopsis "Bioconductor package categorization helper")
6801 (description "The purpose of biocViews is to create HTML pages that
6802 categorize packages in a Bioconductor package repository according to keywords,
6803 also known as views, in a controlled vocabulary.")
6804 (license license:artistic2.0)))
6806 (define-public r-bookdown
6812 (uri (cran-uri "bookdown" version))
6815 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6816 (build-system r-build-system)
6818 `(("r-htmltools" ,r-htmltools)
6819 ("r-knitr" ,r-knitr)
6820 ("r-rmarkdown" ,r-rmarkdown)
6821 ("r-tinytex" ,r-tinytex)
6824 ("ghc-pandoc" ,ghc-pandoc)))
6825 (home-page "https://github.com/rstudio/bookdown")
6826 (synopsis "Authoring books and technical documents with R markdown")
6827 (description "This package provides output formats and utilities for
6828 authoring books and technical documents with R Markdown.")
6829 (license license:gpl3)))
6831 (define-public r-biocstyle
6833 (name "r-biocstyle")
6837 (uri (bioconductor-uri "BiocStyle" version))
6840 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6842 `((upstream-name . "BiocStyle")))
6843 (build-system r-build-system)
6845 `(("r-bookdown" ,r-bookdown)
6846 ("r-knitr" ,r-knitr)
6847 ("r-rmarkdown" ,r-rmarkdown)
6848 ("r-yaml" ,r-yaml)))
6849 (home-page "https://bioconductor.org/packages/BiocStyle")
6850 (synopsis "Bioconductor formatting styles")
6851 (description "This package provides standard formatting styles for
6852 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6854 (license license:artistic2.0)))
6856 (define-public r-bioccheck
6858 (name "r-bioccheck")
6862 (uri (bioconductor-uri "BiocCheck" version))
6865 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6867 `((upstream-name . "BiocCheck")))
6868 (build-system r-build-system)
6871 (modify-phases %standard-phases
6872 ;; This package can be used by calling BiocCheck(<package>) from
6873 ;; within R, or by running R CMD BiocCheck <package>. This phase
6874 ;; makes sure the latter works. For this to work, the BiocCheck
6875 ;; script must be somewhere on the PATH (not the R bin directory).
6876 (add-after 'install 'install-bioccheck-subcommand
6877 (lambda* (#:key outputs #:allow-other-keys)
6878 (let* ((out (assoc-ref outputs "out"))
6879 (dest-dir (string-append out "/bin"))
6881 (string-append out "/site-library/BiocCheck/script/")))
6883 (symlink (string-append script-dir "/checkBadDeps.R")
6884 (string-append dest-dir "/checkBadDeps.R"))
6885 (symlink (string-append script-dir "/BiocCheck")
6886 (string-append dest-dir "/BiocCheck")))
6889 `(("r-codetools" ,r-codetools)
6890 ("r-graph" ,r-graph)
6892 ("r-optparse" ,r-optparse)
6893 ("r-biocinstaller" ,r-biocinstaller)
6894 ("r-biocviews" ,r-biocviews)
6895 ("r-stringdist" ,r-stringdist)))
6896 (home-page "https://bioconductor.org/packages/BiocCheck")
6897 (synopsis "Executes Bioconductor-specific package checks")
6898 (description "This package contains tools to perform additional quality
6899 checks on R packages that are to be submitted to the Bioconductor repository.")
6900 (license license:artistic2.0)))
6902 (define-public r-getopt
6909 (uri (cran-uri "getopt" version))
6912 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
6913 (build-system r-build-system)
6914 (home-page "https://github.com/trevorld/getopt")
6915 (synopsis "Command-line option processor for R")
6917 "This package is designed to be used with Rscript to write shebang
6918 scripts that accept short and long options. Many users will prefer to
6919 use the packages @code{optparse} or @code{argparse} which add extra
6920 features like automatically generated help options and usage texts,
6921 support for default values, positional argument support, etc.")
6922 (license license:gpl2+)))
6924 (define-public r-optparse
6931 (uri (cran-uri "optparse" version))
6934 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6935 (build-system r-build-system)
6937 `(("r-getopt" ,r-getopt)))
6939 "https://github.com/trevorld/optparse")
6940 (synopsis "Command line option parser")
6942 "This package provides a command line parser inspired by Python's
6943 @code{optparse} library to be used with Rscript to write shebang scripts
6944 that accept short and long options.")
6945 (license license:gpl2+)))
6947 (define-public r-dnacopy
6953 (uri (bioconductor-uri "DNAcopy" version))
6956 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6958 `((upstream-name . "DNAcopy")))
6959 (build-system r-build-system)
6961 `(("gfortran" ,gfortran)))
6962 (home-page "https://bioconductor.org/packages/DNAcopy")
6963 (synopsis "Implementation of a circular binary segmentation algorithm")
6964 (description "This package implements the circular binary segmentation (CBS)
6965 algorithm to segment DNA copy number data and identify genomic regions with
6966 abnormal copy number.")
6967 (license license:gpl2+)))
6969 (define-public r-s4vectors
6971 (name "r-s4vectors")
6975 (uri (bioconductor-uri "S4Vectors" version))
6978 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6980 `((upstream-name . "S4Vectors")))
6981 (build-system r-build-system)
6983 `(("r-biocgenerics" ,r-biocgenerics)))
6984 (home-page "https://bioconductor.org/packages/S4Vectors")
6985 (synopsis "S4 implementation of vectors and lists")
6987 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6988 classes and a set of generic functions that extend the semantic of ordinary
6989 vectors and lists in R. Package developers can easily implement vector-like
6990 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6991 In addition, a few low-level concrete subclasses of general interest (e.g.
6992 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6993 S4Vectors package itself.")
6994 (license license:artistic2.0)))
6996 (define-public r-seqinr
7003 (uri (cran-uri "seqinr" version))
7006 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7007 (build-system r-build-system)
7009 `(("r-ade4" ,r-ade4)
7010 ("r-segmented" ,r-segmented)))
7013 (home-page "http://seqinr.r-forge.r-project.org/")
7014 (synopsis "Biological sequences retrieval and analysis")
7016 "This package provides tools for exploratory data analysis and data
7017 visualization of biological sequence (DNA and protein) data. It also includes
7018 utilities for sequence data management under the ACNUC system.")
7019 (license license:gpl2+)))
7021 (define-public r-iranges
7027 (uri (bioconductor-uri "IRanges" version))
7030 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7032 `((upstream-name . "IRanges")))
7033 (build-system r-build-system)
7035 `(("r-biocgenerics" ,r-biocgenerics)
7036 ("r-s4vectors" ,r-s4vectors)))
7037 (home-page "https://bioconductor.org/packages/IRanges")
7038 (synopsis "Infrastructure for manipulating intervals on sequences")
7040 "This package provides efficient low-level and highly reusable S4 classes
7041 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7042 generally, data that can be organized sequentially (formally defined as
7043 @code{Vector} objects), as well as views on these @code{Vector} objects.
7044 Efficient list-like classes are also provided for storing big collections of
7045 instances of the basic classes. All classes in the package use consistent
7046 naming and share the same rich and consistent \"Vector API\" as much as
7048 (license license:artistic2.0)))
7050 (define-public r-genomeinfodbdata
7052 (name "r-genomeinfodbdata")
7056 ;; We cannot use bioconductor-uri here because this tarball is
7057 ;; located under "data/annotation/" instead of "bioc/".
7058 (uri (string-append "https://bioconductor.org/packages/release/"
7059 "data/annotation/src/contrib/GenomeInfoDbData_"
7063 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7065 `((upstream-name . "GenomeInfoDbData")))
7066 (build-system r-build-system)
7067 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7068 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7069 (description "This package contains data for mapping between NCBI taxonomy
7070 ID and species. It is used by functions in the GenomeInfoDb package.")
7071 (license license:artistic2.0)))
7073 (define-public r-genomeinfodb
7075 (name "r-genomeinfodb")
7079 (uri (bioconductor-uri "GenomeInfoDb" version))
7082 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7084 `((upstream-name . "GenomeInfoDb")))
7085 (build-system r-build-system)
7087 `(("r-biocgenerics" ,r-biocgenerics)
7088 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7089 ("r-iranges" ,r-iranges)
7090 ("r-rcurl" ,r-rcurl)
7091 ("r-s4vectors" ,r-s4vectors)))
7092 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7093 (synopsis "Utilities for manipulating chromosome identifiers")
7095 "This package contains data and functions that define and allow
7096 translation between different chromosome sequence naming conventions (e.g.,
7097 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7098 names in their natural, rather than lexicographic, order.")
7099 (license license:artistic2.0)))
7101 (define-public r-edger
7107 (uri (bioconductor-uri "edgeR" version))
7110 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7111 (properties `((upstream-name . "edgeR")))
7112 (build-system r-build-system)
7114 `(("r-limma" ,r-limma)
7115 ("r-locfit" ,r-locfit)
7117 ("r-statmod" ,r-statmod))) ;for estimateDisp
7118 (home-page "http://bioinf.wehi.edu.au/edgeR")
7119 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7120 (description "This package can do differential expression analysis of
7121 RNA-seq expression profiles with biological replication. It implements a range
7122 of statistical methodology based on the negative binomial distributions,
7123 including empirical Bayes estimation, exact tests, generalized linear models
7124 and quasi-likelihood tests. It be applied to differential signal analysis of
7125 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7127 (license license:gpl2+)))
7129 (define-public r-variantannotation
7131 (name "r-variantannotation")
7135 (uri (bioconductor-uri "VariantAnnotation" version))
7138 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7140 `((upstream-name . "VariantAnnotation")))
7144 `(("r-annotationdbi" ,r-annotationdbi)
7145 ("r-biobase" ,r-biobase)
7146 ("r-biocgenerics" ,r-biocgenerics)
7147 ("r-biostrings" ,r-biostrings)
7148 ("r-bsgenome" ,r-bsgenome)
7150 ("r-genomeinfodb" ,r-genomeinfodb)
7151 ("r-genomicfeatures" ,r-genomicfeatures)
7152 ("r-genomicranges" ,r-genomicranges)
7153 ("r-iranges" ,r-iranges)
7154 ("r-summarizedexperiment" ,r-summarizedexperiment)
7155 ("r-rsamtools" ,r-rsamtools)
7156 ("r-rtracklayer" ,r-rtracklayer)
7157 ("r-s4vectors" ,r-s4vectors)
7158 ("r-xvector" ,r-xvector)
7159 ("r-zlibbioc" ,r-zlibbioc)))
7160 (build-system r-build-system)
7161 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7162 (synopsis "Package for annotation of genetic variants")
7163 (description "This R package can annotate variants, compute amino acid
7164 coding changes and predict coding outcomes.")
7165 (license license:artistic2.0)))
7167 (define-public r-limma
7173 (uri (bioconductor-uri "limma" version))
7176 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7177 (build-system r-build-system)
7178 (home-page "http://bioinf.wehi.edu.au/limma")
7179 (synopsis "Package for linear models for microarray and RNA-seq data")
7180 (description "This package can be used for the analysis of gene expression
7181 studies, especially the use of linear models for analysing designed experiments
7182 and the assessment of differential expression. The analysis methods apply to
7183 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7184 (license license:gpl2+)))
7186 (define-public r-xvector
7192 (uri (bioconductor-uri "XVector" version))
7195 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7197 `((upstream-name . "XVector")))
7198 (build-system r-build-system)
7201 (modify-phases %standard-phases
7202 (add-after 'unpack 'use-system-zlib
7204 (substitute* "DESCRIPTION"
7205 (("zlibbioc, ") ""))
7206 (substitute* "NAMESPACE"
7207 (("import\\(zlibbioc\\)") ""))
7212 `(("r-biocgenerics" ,r-biocgenerics)
7213 ("r-iranges" ,r-iranges)
7214 ("r-s4vectors" ,r-s4vectors)))
7215 (home-page "https://bioconductor.org/packages/XVector")
7216 (synopsis "Representation and manpulation of external sequences")
7218 "This package provides memory efficient S4 classes for storing sequences
7219 \"externally\" (behind an R external pointer, or on disk).")
7220 (license license:artistic2.0)))
7222 (define-public r-genomicranges
7224 (name "r-genomicranges")
7228 (uri (bioconductor-uri "GenomicRanges" version))
7231 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7233 `((upstream-name . "GenomicRanges")))
7234 (build-system r-build-system)
7236 `(("r-biocgenerics" ,r-biocgenerics)
7237 ("r-genomeinfodb" ,r-genomeinfodb)
7238 ("r-iranges" ,r-iranges)
7239 ("r-s4vectors" ,r-s4vectors)
7240 ("r-xvector" ,r-xvector)))
7241 (home-page "https://bioconductor.org/packages/GenomicRanges")
7242 (synopsis "Representation and manipulation of genomic intervals")
7244 "This package provides tools to efficiently represent and manipulate
7245 genomic annotations and alignments is playing a central role when it comes to
7246 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7247 GenomicRanges package defines general purpose containers for storing and
7248 manipulating genomic intervals and variables defined along a genome.")
7249 (license license:artistic2.0)))
7251 (define-public r-biobase
7257 (uri (bioconductor-uri "Biobase" version))
7260 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7262 `((upstream-name . "Biobase")))
7263 (build-system r-build-system)
7265 `(("r-biocgenerics" ,r-biocgenerics)))
7266 (home-page "https://bioconductor.org/packages/Biobase")
7267 (synopsis "Base functions for Bioconductor")
7269 "This package provides functions that are needed by many other packages
7270 on Bioconductor or which replace R functions.")
7271 (license license:artistic2.0)))
7273 (define-public r-annotationdbi
7275 (name "r-annotationdbi")
7279 (uri (bioconductor-uri "AnnotationDbi" version))
7282 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7284 `((upstream-name . "AnnotationDbi")))
7285 (build-system r-build-system)
7287 `(("r-biobase" ,r-biobase)
7288 ("r-biocgenerics" ,r-biocgenerics)
7290 ("r-iranges" ,r-iranges)
7291 ("r-rsqlite" ,r-rsqlite)
7292 ("r-s4vectors" ,r-s4vectors)))
7293 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7294 (synopsis "Annotation database interface")
7296 "This package provides user interface and database connection code for
7297 annotation data packages using SQLite data storage.")
7298 (license license:artistic2.0)))
7300 (define-public r-biomart
7306 (uri (bioconductor-uri "biomaRt" version))
7309 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7311 `((upstream-name . "biomaRt")))
7312 (build-system r-build-system)
7314 `(("r-annotationdbi" ,r-annotationdbi)
7316 ("r-progress" ,r-progress)
7317 ("r-rcurl" ,r-rcurl)
7318 ("r-stringr" ,r-stringr)
7320 (home-page "https://bioconductor.org/packages/biomaRt")
7321 (synopsis "Interface to BioMart databases")
7323 "biomaRt provides an interface to a growing collection of databases
7324 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7325 package enables retrieval of large amounts of data in a uniform way without
7326 the need to know the underlying database schemas or write complex SQL queries.
7327 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7328 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7329 users direct access to a diverse set of data and enable a wide range of
7330 powerful online queries from gene annotation to database mining.")
7331 (license license:artistic2.0)))
7333 (define-public r-biocparallel
7335 (name "r-biocparallel")
7339 (uri (bioconductor-uri "BiocParallel" version))
7342 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7344 `((upstream-name . "BiocParallel")))
7345 (build-system r-build-system)
7347 `(("r-futile-logger" ,r-futile-logger)
7350 (home-page "https://bioconductor.org/packages/BiocParallel")
7351 (synopsis "Bioconductor facilities for parallel evaluation")
7353 "This package provides modified versions and novel implementation of
7354 functions for parallel evaluation, tailored to use with Bioconductor
7356 (license (list license:gpl2+ license:gpl3+))))
7358 (define-public r-biostrings
7360 (name "r-biostrings")
7364 (uri (bioconductor-uri "Biostrings" version))
7367 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7369 `((upstream-name . "Biostrings")))
7370 (build-system r-build-system)
7372 `(("r-biocgenerics" ,r-biocgenerics)
7373 ("r-iranges" ,r-iranges)
7374 ("r-s4vectors" ,r-s4vectors)
7375 ("r-xvector" ,r-xvector)))
7376 (home-page "https://bioconductor.org/packages/Biostrings")
7377 (synopsis "String objects and algorithms for biological sequences")
7379 "This package provides memory efficient string containers, string
7380 matching algorithms, and other utilities, for fast manipulation of large
7381 biological sequences or sets of sequences.")
7382 (license license:artistic2.0)))
7384 (define-public r-rsamtools
7386 (name "r-rsamtools")
7390 (uri (bioconductor-uri "Rsamtools" version))
7393 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7395 `((upstream-name . "Rsamtools")))
7396 (build-system r-build-system)
7399 (modify-phases %standard-phases
7400 (add-after 'unpack 'use-system-zlib
7402 (substitute* "DESCRIPTION"
7403 (("zlibbioc, ") ""))
7404 (substitute* "NAMESPACE"
7405 (("import\\(zlibbioc\\)") ""))
7410 `(("r-biocgenerics" ,r-biocgenerics)
7411 ("r-biocparallel" ,r-biocparallel)
7412 ("r-biostrings" ,r-biostrings)
7413 ("r-bitops" ,r-bitops)
7414 ("r-genomeinfodb" ,r-genomeinfodb)
7415 ("r-genomicranges" ,r-genomicranges)
7416 ("r-iranges" ,r-iranges)
7417 ("r-s4vectors" ,r-s4vectors)
7418 ("r-xvector" ,r-xvector)))
7419 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7420 (synopsis "Interface to samtools, bcftools, and tabix")
7422 "This package provides an interface to the 'samtools', 'bcftools', and
7423 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7424 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7426 (license license:expat)))
7428 (define-public r-delayedarray
7430 (name "r-delayedarray")
7434 (uri (bioconductor-uri "DelayedArray" version))
7437 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7439 `((upstream-name . "DelayedArray")))
7440 (build-system r-build-system)
7442 `(("r-biocgenerics" ,r-biocgenerics)
7443 ("r-s4vectors" ,r-s4vectors)
7444 ("r-iranges" ,r-iranges)
7445 ("r-matrixstats" ,r-matrixstats)))
7446 (home-page "https://bioconductor.org/packages/DelayedArray")
7447 (synopsis "Delayed operations on array-like objects")
7449 "Wrapping an array-like object (typically an on-disk object) in a
7450 @code{DelayedArray} object allows one to perform common array operations on it
7451 without loading the object in memory. In order to reduce memory usage and
7452 optimize performance, operations on the object are either delayed or executed
7453 using a block processing mechanism. Note that this also works on in-memory
7454 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7455 @code{Matrix} objects, and ordinary arrays and data frames.")
7456 (license license:artistic2.0)))
7458 (define-public r-summarizedexperiment
7460 (name "r-summarizedexperiment")
7464 (uri (bioconductor-uri "SummarizedExperiment" version))
7467 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7469 `((upstream-name . "SummarizedExperiment")))
7470 (build-system r-build-system)
7472 `(("r-biobase" ,r-biobase)
7473 ("r-biocgenerics" ,r-biocgenerics)
7474 ("r-delayedarray" ,r-delayedarray)
7475 ("r-genomeinfodb" ,r-genomeinfodb)
7476 ("r-genomicranges" ,r-genomicranges)
7477 ("r-iranges" ,r-iranges)
7478 ("r-matrix" ,r-matrix)
7479 ("r-s4vectors" ,r-s4vectors)))
7480 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7481 (synopsis "Container for representing genomic ranges by sample")
7483 "The SummarizedExperiment container contains one or more assays, each
7484 represented by a matrix-like object of numeric or other mode. The rows
7485 typically represent genomic ranges of interest and the columns represent
7487 (license license:artistic2.0)))
7489 (define-public r-genomicalignments
7491 (name "r-genomicalignments")
7495 (uri (bioconductor-uri "GenomicAlignments" version))
7498 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7500 `((upstream-name . "GenomicAlignments")))
7501 (build-system r-build-system)
7503 `(("r-biocgenerics" ,r-biocgenerics)
7504 ("r-biocparallel" ,r-biocparallel)
7505 ("r-biostrings" ,r-biostrings)
7506 ("r-genomeinfodb" ,r-genomeinfodb)
7507 ("r-genomicranges" ,r-genomicranges)
7508 ("r-iranges" ,r-iranges)
7509 ("r-rsamtools" ,r-rsamtools)
7510 ("r-s4vectors" ,r-s4vectors)
7511 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7512 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7513 (synopsis "Representation and manipulation of short genomic alignments")
7515 "This package provides efficient containers for storing and manipulating
7516 short genomic alignments (typically obtained by aligning short reads to a
7517 reference genome). This includes read counting, computing the coverage,
7518 junction detection, and working with the nucleotide content of the
7520 (license license:artistic2.0)))
7522 (define-public r-rtracklayer
7524 (name "r-rtracklayer")
7528 (uri (bioconductor-uri "rtracklayer" version))
7531 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7532 (build-system r-build-system)
7535 (modify-phases %standard-phases
7536 (add-after 'unpack 'use-system-zlib
7538 (substitute* "DESCRIPTION"
7539 ((" zlibbioc,") ""))
7540 (substitute* "NAMESPACE"
7541 (("import\\(zlibbioc\\)") ""))
7546 `(("r-biocgenerics" ,r-biocgenerics)
7547 ("r-biostrings" ,r-biostrings)
7548 ("r-genomeinfodb" ,r-genomeinfodb)
7549 ("r-genomicalignments" ,r-genomicalignments)
7550 ("r-genomicranges" ,r-genomicranges)
7551 ("r-iranges" ,r-iranges)
7552 ("r-rcurl" ,r-rcurl)
7553 ("r-rsamtools" ,r-rsamtools)
7554 ("r-s4vectors" ,r-s4vectors)
7556 ("r-xvector" ,r-xvector)))
7557 (home-page "https://bioconductor.org/packages/rtracklayer")
7558 (synopsis "R interface to genome browsers and their annotation tracks")
7560 "rtracklayer is an extensible framework for interacting with multiple
7561 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7562 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7563 built-in). The user may export/import tracks to/from the supported browsers,
7564 as well as query and modify the browser state, such as the current viewport.")
7565 (license license:artistic2.0)))
7567 (define-public r-genomicfeatures
7569 (name "r-genomicfeatures")
7573 (uri (bioconductor-uri "GenomicFeatures" version))
7576 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7578 `((upstream-name . "GenomicFeatures")))
7579 (build-system r-build-system)
7581 `(("r-annotationdbi" ,r-annotationdbi)
7582 ("r-biobase" ,r-biobase)
7583 ("r-biocgenerics" ,r-biocgenerics)
7584 ("r-biomart" ,r-biomart)
7585 ("r-biostrings" ,r-biostrings)
7587 ("r-genomeinfodb" ,r-genomeinfodb)
7588 ("r-genomicranges" ,r-genomicranges)
7589 ("r-iranges" ,r-iranges)
7590 ("r-rcurl" ,r-rcurl)
7591 ("r-rsqlite" ,r-rsqlite)
7592 ("r-rmysql" ,r-rmysql)
7593 ("r-rtracklayer" ,r-rtracklayer)
7594 ("r-s4vectors" ,r-s4vectors)
7595 ("r-xvector" ,r-xvector)))
7596 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7597 (synopsis "Tools for working with transcript centric annotations")
7599 "This package provides a set of tools and methods for making and
7600 manipulating transcript centric annotations. With these tools the user can
7601 easily download the genomic locations of the transcripts, exons and cds of a
7602 given organism, from either the UCSC Genome Browser or a BioMart
7603 database (more sources will be supported in the future). This information is
7604 then stored in a local database that keeps track of the relationship between
7605 transcripts, exons, cds and genes. Flexible methods are provided for
7606 extracting the desired features in a convenient format.")
7607 (license license:artistic2.0)))
7609 (define-public r-go-db
7615 (uri (string-append "https://www.bioconductor.org/packages/"
7616 "release/data/annotation/src/contrib/GO.db_"
7620 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7622 `((upstream-name . "GO.db")))
7623 (build-system r-build-system)
7625 `(("r-annotationdbi" ,r-annotationdbi)))
7626 (home-page "https://bioconductor.org/packages/GO.db")
7627 (synopsis "Annotation maps describing the entire Gene Ontology")
7629 "The purpose of this GO.db annotation package is to provide detailed
7630 information about the latest version of the Gene Ontologies.")
7631 (license license:artistic2.0)))
7633 (define-public r-graph
7639 (uri (bioconductor-uri "graph" version))
7642 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7643 (build-system r-build-system)
7645 `(("r-biocgenerics" ,r-biocgenerics)))
7646 (home-page "https://bioconductor.org/packages/graph")
7647 (synopsis "Handle graph data structures in R")
7649 "This package implements some simple graph handling capabilities for R.")
7650 (license license:artistic2.0)))
7652 (define-public r-topgo
7658 (uri (bioconductor-uri "topGO" version))
7661 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7663 `((upstream-name . "topGO")))
7664 (build-system r-build-system)
7666 `(("r-annotationdbi" ,r-annotationdbi)
7668 ("r-biobase" ,r-biobase)
7669 ("r-biocgenerics" ,r-biocgenerics)
7670 ("r-go-db" ,r-go-db)
7671 ("r-graph" ,r-graph)
7672 ("r-lattice" ,r-lattice)
7673 ("r-matrixstats" ,r-matrixstats)
7674 ("r-sparsem" ,r-sparsem)))
7675 (home-page "https://bioconductor.org/packages/topGO")
7676 (synopsis "Enrichment analysis for gene ontology")
7678 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7679 terms while accounting for the topology of the GO graph. Different test
7680 statistics and different methods for eliminating local similarities and
7681 dependencies between GO terms can be implemented and applied.")
7682 ;; Any version of the LGPL applies.
7683 (license license:lgpl2.1+)))
7685 (define-public r-bsgenome
7691 (uri (bioconductor-uri "BSgenome" version))
7694 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7696 `((upstream-name . "BSgenome")))
7697 (build-system r-build-system)
7699 `(("r-biocgenerics" ,r-biocgenerics)
7700 ("r-biostrings" ,r-biostrings)
7701 ("r-genomeinfodb" ,r-genomeinfodb)
7702 ("r-genomicranges" ,r-genomicranges)
7703 ("r-iranges" ,r-iranges)
7704 ("r-rsamtools" ,r-rsamtools)
7705 ("r-rtracklayer" ,r-rtracklayer)
7706 ("r-s4vectors" ,r-s4vectors)
7707 ("r-xvector" ,r-xvector)))
7708 (home-page "https://bioconductor.org/packages/BSgenome")
7709 (synopsis "Infrastructure for Biostrings-based genome data packages")
7711 "This package provides infrastructure shared by all Biostrings-based
7712 genome data packages and support for efficient SNP representation.")
7713 (license license:artistic2.0)))
7715 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7717 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7721 ;; We cannot use bioconductor-uri here because this tarball is
7722 ;; located under "data/annotation/" instead of "bioc/".
7723 (uri (string-append "https://www.bioconductor.org/packages/"
7724 "release/data/annotation/src/contrib/"
7725 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7729 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7731 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7732 (build-system r-build-system)
7733 ;; As this package provides little more than a very large data file it
7734 ;; doesn't make sense to build substitutes.
7735 (arguments `(#:substitutable? #f))
7737 `(("r-bsgenome" ,r-bsgenome)))
7739 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7740 (synopsis "Full genome sequences for Homo sapiens")
7742 "This package provides full genome sequences for Homo sapiens from
7743 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7744 (license license:artistic2.0)))
7746 (define-public r-impute
7752 (uri (bioconductor-uri "impute" version))
7755 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7757 `(("gfortran" ,gfortran)))
7758 (build-system r-build-system)
7759 (home-page "https://bioconductor.org/packages/impute")
7760 (synopsis "Imputation for microarray data")
7762 "This package provides a function to impute missing gene expression
7763 microarray data, using nearest neighbor averaging.")
7764 (license license:gpl2+)))
7766 (define-public r-seqpattern
7768 (name "r-seqpattern")
7772 (uri (bioconductor-uri "seqPattern" version))
7775 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7777 `((upstream-name . "seqPattern")))
7778 (build-system r-build-system)
7780 `(("r-biostrings" ,r-biostrings)
7781 ("r-genomicranges" ,r-genomicranges)
7782 ("r-iranges" ,r-iranges)
7783 ("r-kernsmooth" ,r-kernsmooth)
7784 ("r-plotrix" ,r-plotrix)))
7785 (home-page "https://bioconductor.org/packages/seqPattern")
7786 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7788 "This package provides tools to visualize oligonucleotide patterns and
7789 sequence motif occurrences across a large set of sequences centred at a common
7790 reference point and sorted by a user defined feature.")
7791 (license license:gpl3+)))
7793 (define-public r-genomation
7795 (name "r-genomation")
7799 (uri (bioconductor-uri "genomation" version))
7802 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7803 (build-system r-build-system)
7805 `(("r-biostrings" ,r-biostrings)
7806 ("r-bsgenome" ,r-bsgenome)
7807 ("r-data-table" ,r-data-table)
7808 ("r-genomeinfodb" ,r-genomeinfodb)
7809 ("r-genomicalignments" ,r-genomicalignments)
7810 ("r-genomicranges" ,r-genomicranges)
7811 ("r-ggplot2" ,r-ggplot2)
7812 ("r-gridbase" ,r-gridbase)
7813 ("r-impute" ,r-impute)
7814 ("r-iranges" ,r-iranges)
7815 ("r-matrixstats" ,r-matrixstats)
7816 ("r-plotrix" ,r-plotrix)
7819 ("r-readr" ,r-readr)
7820 ("r-reshape2" ,r-reshape2)
7821 ("r-rsamtools" ,r-rsamtools)
7822 ("r-rtracklayer" ,r-rtracklayer)
7823 ("r-runit" ,r-runit)
7824 ("r-s4vectors" ,r-s4vectors)
7825 ("r-seqpattern" ,r-seqpattern)))
7826 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7827 (synopsis "Summary, annotation and visualization of genomic data")
7829 "This package provides a package for summary and annotation of genomic
7830 intervals. Users can visualize and quantify genomic intervals over
7831 pre-defined functional regions, such as promoters, exons, introns, etc. The
7832 genomic intervals represent regions with a defined chromosome position, which
7833 may be associated with a score, such as aligned reads from HT-seq experiments,
7834 TF binding sites, methylation scores, etc. The package can use any tabular
7835 genomic feature data as long as it has minimal information on the locations of
7836 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7837 (license license:artistic2.0)))
7839 (define-public r-genomationdata
7841 (name "r-genomationdata")
7845 ;; We cannot use bioconductor-uri here because this tarball is
7846 ;; located under "data/annotation/" instead of "bioc/".
7847 (uri (string-append "https://bioconductor.org/packages/"
7848 "release/data/experiment/src/contrib/"
7849 "genomationData_" version ".tar.gz"))
7852 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7853 (build-system r-build-system)
7854 ;; As this package provides little more than large data files, it doesn't
7855 ;; make sense to build substitutes.
7856 (arguments `(#:substitutable? #f))
7858 `(("r-knitr" ,r-knitr)))
7859 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7860 (synopsis "Experimental data for use with the genomation package")
7862 "This package contains experimental genetic data for use with the
7863 genomation package. Included are Chip Seq, Methylation and Cage data,
7864 downloaded from Encode.")
7865 (license license:gpl3+)))
7867 (define-public r-org-hs-eg-db
7869 (name "r-org-hs-eg-db")
7873 ;; We cannot use bioconductor-uri here because this tarball is
7874 ;; located under "data/annotation/" instead of "bioc/".
7875 (uri (string-append "https://www.bioconductor.org/packages/"
7876 "release/data/annotation/src/contrib/"
7877 "org.Hs.eg.db_" version ".tar.gz"))
7880 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7882 `((upstream-name . "org.Hs.eg.db")))
7883 (build-system r-build-system)
7885 `(("r-annotationdbi" ,r-annotationdbi)))
7886 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7887 (synopsis "Genome wide annotation for Human")
7889 "This package contains genome-wide annotations for Human, primarily based
7890 on mapping using Entrez Gene identifiers.")
7891 (license license:artistic2.0)))
7893 (define-public r-org-ce-eg-db
7895 (name "r-org-ce-eg-db")
7899 ;; We cannot use bioconductor-uri here because this tarball is
7900 ;; located under "data/annotation/" instead of "bioc/".
7901 (uri (string-append "https://www.bioconductor.org/packages/"
7902 "release/data/annotation/src/contrib/"
7903 "org.Ce.eg.db_" version ".tar.gz"))
7906 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7908 `((upstream-name . "org.Ce.eg.db")))
7909 (build-system r-build-system)
7911 `(("r-annotationdbi" ,r-annotationdbi)))
7912 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7913 (synopsis "Genome wide annotation for Worm")
7915 "This package provides mappings from Entrez gene identifiers to various
7916 annotations for the genome of the model worm Caenorhabditis elegans.")
7917 (license license:artistic2.0)))
7919 (define-public r-org-dm-eg-db
7921 (name "r-org-dm-eg-db")
7925 ;; We cannot use bioconductor-uri here because this tarball is
7926 ;; located under "data/annotation/" instead of "bioc/".
7927 (uri (string-append "https://www.bioconductor.org/packages/"
7928 "release/data/annotation/src/contrib/"
7929 "org.Dm.eg.db_" version ".tar.gz"))
7932 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
7934 `((upstream-name . "org.Dm.eg.db")))
7935 (build-system r-build-system)
7937 `(("r-annotationdbi" ,r-annotationdbi)))
7938 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7939 (synopsis "Genome wide annotation for Fly")
7941 "This package provides mappings from Entrez gene identifiers to various
7942 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7943 (license license:artistic2.0)))
7945 (define-public r-org-mm-eg-db
7947 (name "r-org-mm-eg-db")
7951 ;; We cannot use bioconductor-uri here because this tarball is
7952 ;; located under "data/annotation/" instead of "bioc/".
7953 (uri (string-append "https://www.bioconductor.org/packages/"
7954 "release/data/annotation/src/contrib/"
7955 "org.Mm.eg.db_" version ".tar.gz"))
7958 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
7960 `((upstream-name . "org.Mm.eg.db")))
7961 (build-system r-build-system)
7963 `(("r-annotationdbi" ,r-annotationdbi)))
7964 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7965 (synopsis "Genome wide annotation for Mouse")
7967 "This package provides mappings from Entrez gene identifiers to various
7968 annotations for the genome of the model mouse Mus musculus.")
7969 (license license:artistic2.0)))
7971 (define-public r-seqlogo
7978 (uri (bioconductor-uri "seqLogo" version))
7981 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7982 (properties `((upstream-name . "seqLogo")))
7983 (build-system r-build-system)
7984 (home-page "https://bioconductor.org/packages/seqLogo")
7985 (synopsis "Sequence logos for DNA sequence alignments")
7987 "seqLogo takes the position weight matrix of a DNA sequence motif and
7988 plots the corresponding sequence logo as introduced by Schneider and
7990 (license license:lgpl2.0+)))
7992 (define-public r-bsgenome-hsapiens-ucsc-hg19
7994 (name "r-bsgenome-hsapiens-ucsc-hg19")
7998 ;; We cannot use bioconductor-uri here because this tarball is
7999 ;; located under "data/annotation/" instead of "bioc/".
8000 (uri (string-append "https://www.bioconductor.org/packages/"
8001 "release/data/annotation/src/contrib/"
8002 "BSgenome.Hsapiens.UCSC.hg19_"
8006 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8008 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8009 (build-system r-build-system)
8010 ;; As this package provides little more than a very large data file it
8011 ;; doesn't make sense to build substitutes.
8012 (arguments `(#:substitutable? #f))
8014 `(("r-bsgenome" ,r-bsgenome)))
8016 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8017 (synopsis "Full genome sequences for Homo sapiens")
8019 "This package provides full genome sequences for Homo sapiens as provided
8020 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8021 (license license:artistic2.0)))
8023 (define-public r-bsgenome-mmusculus-ucsc-mm9
8025 (name "r-bsgenome-mmusculus-ucsc-mm9")
8029 ;; We cannot use bioconductor-uri here because this tarball is
8030 ;; located under "data/annotation/" instead of "bioc/".
8031 (uri (string-append "https://www.bioconductor.org/packages/"
8032 "release/data/annotation/src/contrib/"
8033 "BSgenome.Mmusculus.UCSC.mm9_"
8037 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8039 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8040 (build-system r-build-system)
8041 ;; As this package provides little more than a very large data file it
8042 ;; doesn't make sense to build substitutes.
8043 (arguments `(#:substitutable? #f))
8045 `(("r-bsgenome" ,r-bsgenome)))
8047 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8048 (synopsis "Full genome sequences for Mouse")
8050 "This package provides full genome sequences for Mus musculus (Mouse) as
8051 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8052 (license license:artistic2.0)))
8054 (define-public r-bsgenome-mmusculus-ucsc-mm10
8056 (name "r-bsgenome-mmusculus-ucsc-mm10")
8060 ;; We cannot use bioconductor-uri here because this tarball is
8061 ;; located under "data/annotation/" instead of "bioc/".
8062 (uri (string-append "https://www.bioconductor.org/packages/"
8063 "release/data/annotation/src/contrib/"
8064 "BSgenome.Mmusculus.UCSC.mm10_"
8068 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8070 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8071 (build-system r-build-system)
8072 ;; As this package provides little more than a very large data file it
8073 ;; doesn't make sense to build substitutes.
8074 (arguments `(#:substitutable? #f))
8076 `(("r-bsgenome" ,r-bsgenome)))
8078 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8079 (synopsis "Full genome sequences for Mouse")
8081 "This package provides full genome sequences for Mus
8082 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8083 in Biostrings objects.")
8084 (license license:artistic2.0)))
8086 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8088 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8092 ;; We cannot use bioconductor-uri here because this tarball is
8093 ;; located under "data/annotation/" instead of "bioc/".
8094 (uri (string-append "https://www.bioconductor.org/packages/"
8095 "release/data/annotation/src/contrib/"
8096 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8100 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8102 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8103 (build-system r-build-system)
8104 ;; As this package provides little more than a very large data file it
8105 ;; doesn't make sense to build substitutes.
8106 (arguments `(#:substitutable? #f))
8108 `(("r-bsgenome" ,r-bsgenome)
8109 ("r-genomicfeatures" ,r-genomicfeatures)
8110 ("r-annotationdbi" ,r-annotationdbi)))
8112 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8113 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8115 "This package loads a TxDb object, which is an R interface to
8116 prefabricated databases contained in this package. This package provides
8117 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8118 based on the knownGene track.")
8119 (license license:artistic2.0)))
8121 (define-public r-bsgenome-celegans-ucsc-ce6
8123 (name "r-bsgenome-celegans-ucsc-ce6")
8127 ;; We cannot use bioconductor-uri here because this tarball is
8128 ;; located under "data/annotation/" instead of "bioc/".
8129 (uri (string-append "https://www.bioconductor.org/packages/"
8130 "release/data/annotation/src/contrib/"
8131 "BSgenome.Celegans.UCSC.ce6_"
8135 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8137 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8138 (build-system r-build-system)
8139 ;; As this package provides little more than a very large data file it
8140 ;; doesn't make sense to build substitutes.
8141 (arguments `(#:substitutable? #f))
8143 `(("r-bsgenome" ,r-bsgenome)))
8145 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8146 (synopsis "Full genome sequences for Worm")
8148 "This package provides full genome sequences for Caenorhabditis
8149 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8151 (license license:artistic2.0)))
8153 (define-public r-bsgenome-celegans-ucsc-ce10
8155 (name "r-bsgenome-celegans-ucsc-ce10")
8159 ;; We cannot use bioconductor-uri here because this tarball is
8160 ;; located under "data/annotation/" instead of "bioc/".
8161 (uri (string-append "https://www.bioconductor.org/packages/"
8162 "release/data/annotation/src/contrib/"
8163 "BSgenome.Celegans.UCSC.ce10_"
8167 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8169 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8170 (build-system r-build-system)
8171 ;; As this package provides little more than a very large data file it
8172 ;; doesn't make sense to build substitutes.
8173 (arguments `(#:substitutable? #f))
8175 `(("r-bsgenome" ,r-bsgenome)))
8177 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8178 (synopsis "Full genome sequences for Worm")
8180 "This package provides full genome sequences for Caenorhabditis
8181 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8183 (license license:artistic2.0)))
8185 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8187 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8191 ;; We cannot use bioconductor-uri here because this tarball is
8192 ;; located under "data/annotation/" instead of "bioc/".
8193 (uri (string-append "https://www.bioconductor.org/packages/"
8194 "release/data/annotation/src/contrib/"
8195 "BSgenome.Dmelanogaster.UCSC.dm3_"
8199 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8201 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8202 (build-system r-build-system)
8203 ;; As this package provides little more than a very large data file it
8204 ;; doesn't make sense to build substitutes.
8205 (arguments `(#:substitutable? #f))
8207 `(("r-bsgenome" ,r-bsgenome)))
8209 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8210 (synopsis "Full genome sequences for Fly")
8212 "This package provides full genome sequences for Drosophila
8213 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8214 Biostrings objects.")
8215 (license license:artistic2.0)))
8217 (define-public r-motifrg
8224 (uri (bioconductor-uri "motifRG" version))
8227 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8228 (properties `((upstream-name . "motifRG")))
8229 (build-system r-build-system)
8231 `(("r-biostrings" ,r-biostrings)
8232 ("r-bsgenome" ,r-bsgenome)
8233 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8234 ("r-iranges" ,r-iranges)
8235 ("r-seqlogo" ,r-seqlogo)
8236 ("r-xvector" ,r-xvector)))
8237 (home-page "https://bioconductor.org/packages/motifRG")
8238 (synopsis "Discover motifs in high throughput sequencing data")
8240 "This package provides tools for discriminative motif discovery in high
8241 throughput genetic sequencing data sets using regression methods.")
8242 (license license:artistic2.0)))
8244 (define-public r-qtl
8251 (uri (string-append "mirror://cran/src/contrib/qtl_"
8255 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8256 (build-system r-build-system)
8257 (home-page "http://rqtl.org/")
8258 (synopsis "R package for analyzing QTL experiments in genetics")
8259 (description "R/qtl is an extension library for the R statistics
8260 system. It is used to analyze experimental crosses for identifying
8261 genes contributing to variation in quantitative traits (so-called
8262 quantitative trait loci, QTLs).
8264 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8265 identify genotyping errors, and to perform single-QTL and two-QTL,
8266 two-dimensional genome scans.")
8267 (license license:gpl3)))
8269 (define-public r-zlibbioc
8275 (uri (bioconductor-uri "zlibbioc" version))
8278 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8280 `((upstream-name . "zlibbioc")))
8281 (build-system r-build-system)
8282 (home-page "https://bioconductor.org/packages/zlibbioc")
8283 (synopsis "Provider for zlib-1.2.5 to R packages")
8284 (description "This package uses the source code of zlib-1.2.5 to create
8285 libraries for systems that do not have these available via other means.")
8286 (license license:artistic2.0)))
8288 (define-public r-r4rna
8295 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8299 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8300 (build-system r-build-system)
8302 `(("r-optparse" ,r-optparse)
8303 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8304 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8305 (synopsis "Analysis framework for RNA secondary structure")
8307 "The R4RNA package aims to be a general framework for the analysis of RNA
8308 secondary structure and comparative analysis in R.")
8309 (license license:gpl3+)))
8311 (define-public r-rhtslib
8318 (uri (bioconductor-uri "Rhtslib" version))
8321 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8322 (properties `((upstream-name . "Rhtslib")))
8323 (build-system r-build-system)
8325 `(("r-zlibbioc" ,r-zlibbioc)))
8329 `(("autoconf" ,autoconf)))
8330 (home-page "https://github.com/nhayden/Rhtslib")
8331 (synopsis "High-throughput sequencing library as an R package")
8333 "This package provides the HTSlib C library for high-throughput
8334 nucleotide sequence analysis. The package is primarily useful to developers
8335 of other R packages who wish to make use of HTSlib.")
8336 (license license:lgpl2.0+)))
8338 (define-public r-bamsignals
8340 (name "r-bamsignals")
8345 (uri (bioconductor-uri "bamsignals" version))
8348 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8349 (build-system r-build-system)
8351 `(("r-biocgenerics" ,r-biocgenerics)
8352 ("r-genomicranges" ,r-genomicranges)
8353 ("r-iranges" ,r-iranges)
8355 ("r-rhtslib" ,r-rhtslib)
8356 ("r-zlibbioc" ,r-zlibbioc)))
8359 (home-page "https://bioconductor.org/packages/bamsignals")
8360 (synopsis "Extract read count signals from bam files")
8362 "This package allows to efficiently obtain count vectors from indexed bam
8363 files. It counts the number of nucleotide sequence reads in given genomic
8364 ranges and it computes reads profiles and coverage profiles. It also handles
8366 (license license:gpl2+)))
8368 (define-public r-rcas
8374 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8376 (file-name (string-append name "-" version ".tar.gz"))
8379 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8380 (build-system r-build-system)
8382 `(("r-knitr" ,r-knitr)
8383 ("r-testthat" ,r-testthat)
8384 ;; During vignette building knitr checks that "pandoc-citeproc"
8386 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8388 `(("r-data-table" ,r-data-table)
8389 ("r-biomart" ,r-biomart)
8390 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8391 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8392 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8393 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8394 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8395 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8396 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8397 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8398 ("r-topgo" ,r-topgo)
8400 ("r-pbapply" ,r-pbapply)
8401 ("r-plotly" ,r-plotly)
8402 ("r-plotrix" ,r-plotrix)
8403 ("r-motifrg" ,r-motifrg)
8404 ("r-genomation" ,r-genomation)
8405 ("r-genomicfeatures" ,r-genomicfeatures)
8406 ("r-rtracklayer" ,r-rtracklayer)
8407 ("r-rmarkdown" ,r-rmarkdown)))
8408 (synopsis "RNA-centric annotation system")
8410 "RCAS aims to be a standalone RNA-centric annotation system that provides
8411 intuitive reports and publication-ready graphics. This package provides the R
8412 library implementing most of the pipeline's features.")
8413 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8414 (license license:artistic2.0)))
8416 (define-public rcas-web
8423 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8424 "releases/download/v" version
8425 "/rcas-web-" version ".tar.gz"))
8428 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8429 (build-system gnu-build-system)
8432 (modify-phases %standard-phases
8433 (add-after 'install 'wrap-executable
8434 (lambda* (#:key inputs outputs #:allow-other-keys)
8435 (let* ((out (assoc-ref outputs "out"))
8436 (json (assoc-ref inputs "guile-json"))
8437 (redis (assoc-ref inputs "guile-redis"))
8438 (path (string-append
8439 json "/share/guile/site/2.2:"
8440 redis "/share/guile/site/2.2")))
8441 (wrap-program (string-append out "/bin/rcas-web")
8442 `("GUILE_LOAD_PATH" ":" = (,path))
8443 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8444 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8447 `(("r-minimal" ,r-minimal)
8449 ("guile-next" ,guile-2.2)
8450 ("guile-json" ,guile-json)
8451 ("guile-redis" ,guile2.2-redis)))
8453 `(("pkg-config" ,pkg-config)))
8454 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8455 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8456 (description "This package provides a simple web interface for the
8457 @dfn{RNA-centric annotation system} (RCAS).")
8458 (license license:agpl3+)))
8460 (define-public r-mutationalpatterns
8462 (name "r-mutationalpatterns")
8467 (uri (bioconductor-uri "MutationalPatterns" version))
8470 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8471 (build-system r-build-system)
8473 `(("r-biocgenerics" ,r-biocgenerics)
8474 ("r-biostrings" ,r-biostrings)
8475 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8476 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8477 ("r-genomicranges" ,r-genomicranges)
8478 ("r-genomeinfodb" ,r-genomeinfodb)
8479 ("r-ggplot2" ,r-ggplot2)
8480 ("r-gridextra" ,r-gridextra)
8481 ("r-iranges" ,r-iranges)
8484 ("r-pracma" ,r-pracma)
8485 ("r-reshape2" ,r-reshape2)
8486 ("r-cowplot" ,r-cowplot)
8487 ("r-ggdendro" ,r-ggdendro)
8488 ("r-s4vectors" ,r-s4vectors)
8489 ("r-summarizedexperiment" ,r-summarizedexperiment)
8490 ("r-variantannotation" ,r-variantannotation)))
8491 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8492 (synopsis "Extract and visualize mutational patterns in genomic data")
8493 (description "This package provides an extensive toolset for the
8494 characterization and visualization of a wide range of mutational patterns
8495 in SNV base substitution data.")
8496 (license license:expat)))
8498 (define-public r-wgcna
8505 (uri (cran-uri "WGCNA" version))
8508 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8509 (properties `((upstream-name . "WGCNA")))
8510 (build-system r-build-system)
8512 `(("r-annotationdbi" ,r-annotationdbi)
8513 ("r-doparallel" ,r-doparallel)
8514 ("r-dynamictreecut" ,r-dynamictreecut)
8515 ("r-fastcluster" ,r-fastcluster)
8516 ("r-foreach" ,r-foreach)
8517 ("r-go-db" ,r-go-db)
8518 ("r-hmisc" ,r-hmisc)
8519 ("r-impute" ,r-impute)
8521 ("r-robust" ,r-robust)
8522 ("r-survival" ,r-survival)
8523 ("r-matrixstats" ,r-matrixstats)
8524 ("r-preprocesscore" ,r-preprocesscore)))
8526 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8527 (synopsis "Weighted correlation network analysis")
8529 "This package provides functions necessary to perform Weighted
8530 Correlation Network Analysis on high-dimensional data. It includes functions
8531 for rudimentary data cleaning, construction and summarization of correlation
8532 networks, module identification and functions for relating both variables and
8533 modules to sample traits. It also includes a number of utility functions for
8534 data manipulation and visualization.")
8535 (license license:gpl2+)))
8537 (define-public r-chipkernels
8538 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8541 (name "r-chipkernels")
8542 (version (string-append "1.1-" revision "." (string-take commit 9)))
8547 (url "https://github.com/ManuSetty/ChIPKernels.git")
8549 (file-name (string-append name "-" version))
8552 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8553 (build-system r-build-system)
8555 `(("r-iranges" ,r-iranges)
8556 ("r-xvector" ,r-xvector)
8557 ("r-biostrings" ,r-biostrings)
8558 ("r-bsgenome" ,r-bsgenome)
8559 ("r-gtools" ,r-gtools)
8560 ("r-genomicranges" ,r-genomicranges)
8561 ("r-sfsmisc" ,r-sfsmisc)
8562 ("r-kernlab" ,r-kernlab)
8563 ("r-s4vectors" ,r-s4vectors)
8564 ("r-biocgenerics" ,r-biocgenerics)))
8565 (home-page "https://github.com/ManuSetty/ChIPKernels")
8566 (synopsis "Build string kernels for DNA Sequence analysis")
8567 (description "ChIPKernels is an R package for building different string
8568 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8569 must be built and this dictionary can be used for determining kernels for DNA
8571 (license license:gpl2+))))
8573 (define-public r-seqgl
8580 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8581 "archive/" version ".tar.gz"))
8582 (file-name (string-append name "-" version ".tar.gz"))
8585 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8586 (build-system r-build-system)
8588 `(("r-biostrings" ,r-biostrings)
8589 ("r-chipkernels" ,r-chipkernels)
8590 ("r-genomicranges" ,r-genomicranges)
8591 ("r-spams" ,r-spams)
8592 ("r-wgcna" ,r-wgcna)
8593 ("r-fastcluster" ,r-fastcluster)))
8594 (home-page "https://github.com/ManuSetty/SeqGL")
8595 (synopsis "Group lasso for Dnase/ChIP-seq data")
8596 (description "SeqGL is a group lasso based algorithm to extract
8597 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8598 This package presents a method which uses group lasso to discriminate between
8599 bound and non bound genomic regions to accurately identify transcription
8600 factors bound at the specific regions.")
8601 (license license:gpl2+)))
8603 (define-public r-gkmsvm
8610 (uri (cran-uri "gkmSVM" version))
8613 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8614 (properties `((upstream-name . "gkmSVM")))
8615 (build-system r-build-system)
8617 `(("r-biocgenerics" ,r-biocgenerics)
8618 ("r-biostrings" ,r-biostrings)
8619 ("r-genomeinfodb" ,r-genomeinfodb)
8620 ("r-genomicranges" ,r-genomicranges)
8621 ("r-iranges" ,r-iranges)
8622 ("r-kernlab" ,r-kernlab)
8625 ("r-rtracklayer" ,r-rtracklayer)
8626 ("r-s4vectors" ,r-s4vectors)
8627 ("r-seqinr" ,r-seqinr)))
8628 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8629 (synopsis "Gapped-kmer support vector machine")
8631 "This R package provides tools for training gapped-kmer SVM classifiers
8632 for DNA and protein sequences. This package supports several sequence
8633 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8634 (license license:gpl2+)))
8636 (define-public r-tximport
8642 (uri (bioconductor-uri "tximport" version))
8645 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8646 (build-system r-build-system)
8647 (home-page "https://bioconductor.org/packages/tximport")
8648 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8650 "This package provides tools to import transcript-level abundance,
8651 estimated counts and transcript lengths, and to summarize them into matrices
8652 for use with downstream gene-level analysis packages. Average transcript
8653 length, weighted by sample-specific transcript abundance estimates, is
8654 provided as a matrix which can be used as an offset for different expression
8655 of gene-level counts.")
8656 (license license:gpl2+)))
8658 (define-public r-rhdf5
8664 (uri (bioconductor-uri "rhdf5" version))
8667 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8668 (build-system r-build-system)
8671 (modify-phases %standard-phases
8672 (add-after 'unpack 'unpack-smallhdf5
8673 (lambda* (#:key outputs #:allow-other-keys)
8674 (system* "tar" "-xzvf"
8675 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8676 (substitute* "src/hdf5/configure"
8680 `(("r-zlibbioc" ,r-zlibbioc)))
8684 (home-page "https://bioconductor.org/packages/rhdf5")
8685 (synopsis "HDF5 interface to R")
8687 "This R/Bioconductor package provides an interface between HDF5 and R.
8688 HDF5's main features are the ability to store and access very large and/or
8689 complex datasets and a wide variety of metadata on mass storage (disk) through
8690 a completely portable file format. The rhdf5 package is thus suited for the
8691 exchange of large and/or complex datasets between R and other software
8692 package, and for letting R applications work on datasets that are larger than
8693 the available RAM.")
8694 (license license:artistic2.0)))
8696 (define-public r-annotationfilter
8698 (name "r-annotationfilter")
8702 (uri (bioconductor-uri "AnnotationFilter" version))
8705 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8707 `((upstream-name . "AnnotationFilter")))
8708 (build-system r-build-system)
8710 `(("r-genomicranges" ,r-genomicranges)
8711 ("r-lazyeval" ,r-lazyeval)))
8712 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8713 (synopsis "Facilities for filtering Bioconductor annotation resources")
8715 "This package provides classes and other infrastructure to implement
8716 filters for manipulating Bioconductor annotation resources. The filters are
8717 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8718 (license license:artistic2.0)))
8720 (define-public emboss
8726 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8727 (version-major+minor version) ".0/"
8728 "EMBOSS-" version ".tar.gz"))
8731 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8732 (build-system gnu-build-system)
8735 (list (string-append "--with-hpdf="
8736 (assoc-ref %build-inputs "libharu")))
8738 (modify-phases %standard-phases
8739 (add-after 'unpack 'fix-checks
8741 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8742 ;; and zlib, but assume that they are all found at the same
8744 (substitute* "configure.in"
8745 (("CHECK_PNGDRIVER")
8746 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8747 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8748 AM_CONDITIONAL(AMPNG, true)"))
8750 (add-after 'fix-checks 'disable-update-check
8752 ;; At build time there is no connection to the Internet, so
8753 ;; looking for updates will not work.
8754 (substitute* "Makefile.am"
8755 (("\\$\\(bindir\\)/embossupdate") ""))
8757 (add-after 'disable-update-check 'autogen
8758 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8764 ("libharu" ,libharu)
8767 `(("autoconf" ,autoconf)
8768 ("automake" ,automake)
8769 ("libtool" ,libtool)
8770 ("pkg-config" ,pkg-config)))
8771 (home-page "http://emboss.sourceforge.net")
8772 (synopsis "Molecular biology analysis suite")
8773 (description "EMBOSS is the \"European Molecular Biology Open Software
8774 Suite\". EMBOSS is an analysis package specially developed for the needs of
8775 the molecular biology (e.g. EMBnet) user community. The software
8776 automatically copes with data in a variety of formats and even allows
8777 transparent retrieval of sequence data from the web. It also provides a
8778 number of libraries for the development of software in the field of molecular
8779 biology. EMBOSS also integrates a range of currently available packages and
8780 tools for sequence analysis into a seamless whole.")
8781 (license license:gpl2+)))
8784 (let ((revision "1")
8785 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8788 ;; The version is 2.13.0 even though no release archives have been
8789 ;; published as yet.
8790 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8794 (url "https://github.com/arq5x/bits.git")
8796 (file-name (string-append name "-" version "-checkout"))
8799 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8800 (build-system gnu-build-system)
8802 `(#:tests? #f ;no tests included
8804 (modify-phases %standard-phases
8806 (add-after 'unpack 'remove-cuda
8808 (substitute* "Makefile"
8810 (("(bits_test_intersections) \\\\" _ match) match))
8813 (lambda* (#:key outputs #:allow-other-keys)
8815 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8820 (home-page "https://github.com/arq5x/bits")
8821 (synopsis "Implementation of binary interval search algorithm")
8822 (description "This package provides an implementation of the
8823 BITS (Binary Interval Search) algorithm, an approach to interval set
8824 intersection. It is especially suited for the comparison of diverse genomic
8825 datasets and the exploration of large datasets of genome
8826 intervals (e.g. genes, sequence alignments).")
8827 (license license:gpl2))))
8829 (define-public piranha
8830 ;; There is no release tarball for the latest version. The latest commit is
8831 ;; older than one year at the time of this writing.
8832 (let ((revision "1")
8833 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8836 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8840 (url "https://github.com/smithlabcode/piranha.git")
8844 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8845 (build-system gnu-build-system)
8847 `(#:test-target "test"
8849 (modify-phases %standard-phases
8850 (add-after 'unpack 'copy-smithlab-cpp
8851 (lambda* (#:key inputs #:allow-other-keys)
8852 (for-each (lambda (file)
8853 (install-file file "./src/smithlab_cpp/"))
8854 (find-files (assoc-ref inputs "smithlab-cpp")))
8856 (add-after 'install 'install-to-store
8857 (lambda* (#:key outputs #:allow-other-keys)
8858 (let* ((out (assoc-ref outputs "out"))
8859 (bin (string-append out "/bin")))
8860 (for-each (lambda (file)
8861 (install-file file bin))
8862 (find-files "bin" ".*")))
8865 (list (string-append "--with-bam_tools_headers="
8866 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8867 (string-append "--with-bam_tools_library="
8868 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8870 `(("bamtools" ,bamtools)
8871 ("samtools" ,samtools-0.1)
8874 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8878 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8880 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8883 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8885 `(("python" ,python-2)))
8886 (home-page "https://github.com/smithlabcode/piranha")
8887 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8889 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8890 RIP-seq experiments. It takes input in BED or BAM format and identifies
8891 regions of statistically significant read enrichment. Additional covariates
8892 may optionally be provided to further inform the peak-calling process.")
8893 (license license:gpl3+))))
8901 (uri (string-append "https://pypi.python.org/packages/source/P"
8902 "/PePr/PePr-" version ".tar.gz"))
8905 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8906 (build-system python-build-system)
8908 `(#:python ,python-2 ; python2 only
8909 #:tests? #f)) ; no tests included
8911 `(("python2-numpy" ,python2-numpy)
8912 ("python2-scipy" ,python2-scipy)
8913 ("python2-pysam" ,python2-pysam)))
8914 (home-page "https://github.com/shawnzhangyx/PePr")
8915 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8917 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8918 that is primarily designed for data with biological replicates. It uses a
8919 negative binomial distribution to model the read counts among the samples in
8920 the same group, and look for consistent differences between ChIP and control
8921 group or two ChIP groups run under different conditions.")
8922 (license license:gpl3+)))
8924 (define-public filevercmp
8925 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8928 (version (string-append "0-1." (string-take commit 7)))
8931 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8933 (file-name (string-append name "-" version ".tar.gz"))
8935 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8936 (build-system gnu-build-system)
8938 `(#:tests? #f ; There are no tests to run.
8940 (modify-phases %standard-phases
8941 (delete 'configure) ; There is no configure phase.
8943 (lambda* (#:key outputs #:allow-other-keys)
8944 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8945 (install-file "filevercmp" bin)))))))
8946 (home-page "https://github.com/ekg/filevercmp")
8947 (synopsis "This program compares version strings")
8948 (description "This program compares version strings. It intends to be a
8949 replacement for strverscmp.")
8950 (license license:gpl3+))))
8952 (define-public multiqc
8959 (uri (pypi-uri "multiqc" version))
8962 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
8963 (build-system python-build-system)
8965 `(("python-jinja2" ,python-jinja2)
8966 ("python-simplejson" ,python-simplejson)
8967 ("python-pyyaml" ,python-pyyaml)
8968 ("python-click" ,python-click)
8969 ("python-spectra" ,python-spectra)
8970 ("python-requests" ,python-requests)
8971 ("python-markdown" ,python-markdown)
8972 ("python-lzstring" ,python-lzstring)
8973 ("python-matplotlib" ,python-matplotlib)
8974 ("python-numpy" ,python-numpy)
8975 ;; MultQC checks for the presence of nose at runtime.
8976 ("python-nose" ,python-nose)))
8977 (home-page "http://multiqc.info")
8978 (synopsis "Aggregate bioinformatics analysis reports")
8980 "MultiQC is a tool to aggregate bioinformatics results across many
8981 samples into a single report. It contains modules for a large number of
8982 common bioinformatics tools.")
8983 (license license:gpl3+)))
8985 (define-public r-chipseq
8992 (uri (bioconductor-uri "chipseq" version))
8995 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8996 (build-system r-build-system)
8998 `(("r-biocgenerics" ,r-biocgenerics)
8999 ("r-genomicranges" ,r-genomicranges)
9000 ("r-iranges" ,r-iranges)
9001 ("r-lattice" ,r-lattice)
9002 ("r-s4vectors" ,r-s4vectors)
9003 ("r-shortread" ,r-shortread)))
9004 (home-page "https://bioconductor.org/packages/chipseq")
9005 (synopsis "Package for analyzing ChIPseq data")
9007 "This package provides tools for processing short read data from ChIPseq
9009 (license license:artistic2.0)))
9011 (define-public r-copyhelper
9013 (name "r-copyhelper")
9018 (uri (string-append "https://bioconductor.org/packages/release/"
9019 "data/experiment/src/contrib/CopyhelpeR_"
9023 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9024 (properties `((upstream-name . "CopyhelpeR")))
9025 (build-system r-build-system)
9026 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9027 (synopsis "Helper files for CopywriteR")
9029 "This package contains the helper files that are required to run the
9030 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9031 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9032 mm10. In addition, it contains a blacklist filter to remove regions that
9033 display copy number variation. Files are stored as GRanges objects from the
9034 GenomicRanges Bioconductor package.")
9035 (license license:gpl2)))
9037 (define-public r-copywriter
9039 (name "r-copywriter")
9044 (uri (bioconductor-uri "CopywriteR" version))
9047 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9048 (properties `((upstream-name . "CopywriteR")))
9049 (build-system r-build-system)
9051 `(("r-biocparallel" ,r-biocparallel)
9052 ("r-chipseq" ,r-chipseq)
9053 ("r-copyhelper" ,r-copyhelper)
9054 ("r-data-table" ,r-data-table)
9055 ("r-dnacopy" ,r-dnacopy)
9056 ("r-futile-logger" ,r-futile-logger)
9057 ("r-genomeinfodb" ,r-genomeinfodb)
9058 ("r-genomicalignments" ,r-genomicalignments)
9059 ("r-genomicranges" ,r-genomicranges)
9060 ("r-gtools" ,r-gtools)
9061 ("r-iranges" ,r-iranges)
9062 ("r-matrixstats" ,r-matrixstats)
9063 ("r-rsamtools" ,r-rsamtools)
9064 ("r-s4vectors" ,r-s4vectors)))
9065 (home-page "https://github.com/PeeperLab/CopywriteR")
9066 (synopsis "Copy number information from targeted sequencing")
9068 "CopywriteR extracts DNA copy number information from targeted sequencing
9069 by utilizing off-target reads. It allows for extracting uniformly distributed
9070 copy number information, can be used without reference, and can be applied to
9071 sequencing data obtained from various techniques including chromatin
9072 immunoprecipitation and target enrichment on small gene panels. Thereby,
9073 CopywriteR constitutes a widely applicable alternative to available copy
9074 number detection tools.")
9075 (license license:gpl2)))
9077 (define-public r-methylkit
9079 (name "r-methylkit")
9083 (uri (bioconductor-uri "methylKit" version))
9086 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9087 (properties `((upstream-name . "methylKit")))
9088 (build-system r-build-system)
9090 `(("r-data-table" ,r-data-table)
9091 ("r-emdbook" ,r-emdbook)
9092 ("r-fastseg" ,r-fastseg)
9093 ("r-genomeinfodb" ,r-genomeinfodb)
9094 ("r-genomicranges" ,r-genomicranges)
9095 ("r-gtools" ,r-gtools)
9096 ("r-iranges" ,r-iranges)
9097 ("r-kernsmooth" ,r-kernsmooth)
9098 ("r-limma" ,r-limma)
9099 ("r-mclust" ,r-mclust)
9100 ("r-qvalue" ,r-qvalue)
9101 ("r-r-utils" ,r-r-utils)
9103 ("r-rhtslib" ,r-rhtslib)
9104 ("r-rsamtools" ,r-rsamtools)
9105 ("r-rtracklayer" ,r-rtracklayer)
9106 ("r-s4vectors" ,r-s4vectors)
9107 ("r-zlibbioc" ,r-zlibbioc)))
9110 (home-page "https://github.com/al2na/methylKit")
9112 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9114 "MethylKit is an R package for DNA methylation analysis and annotation
9115 from high-throughput bisulfite sequencing. The package is designed to deal
9116 with sequencing data from @dfn{Reduced representation bisulfite
9117 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9118 genome bisulfite sequencing. It also has functions to analyze base-pair
9119 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9121 (license license:artistic2.0)))
9123 (define-public r-sva
9130 (uri (bioconductor-uri "sva" version))
9133 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9134 (build-system r-build-system)
9136 `(("r-genefilter" ,r-genefilter)
9138 ("r-biocparallel" ,r-biocparallel)
9139 ("r-matrixstats" ,r-matrixstats)
9140 ("r-limma" ,r-limma)))
9141 (home-page "https://bioconductor.org/packages/sva")
9142 (synopsis "Surrogate variable analysis")
9144 "This package contains functions for removing batch effects and other
9145 unwanted variation in high-throughput experiment. It also contains functions
9146 for identifying and building surrogate variables for high-dimensional data
9147 sets. Surrogate variables are covariates constructed directly from
9148 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9149 imaging data that can be used in subsequent analyses to adjust for unknown,
9150 unmodeled, or latent sources of noise.")
9151 (license license:artistic2.0)))
9153 (define-public r-seqminer
9160 (uri (cran-uri "seqminer" version))
9163 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9164 (build-system r-build-system)
9167 (home-page "http://seqminer.genomic.codes")
9168 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9170 "This package provides tools to integrate nucleotide sequencing
9171 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9172 ;; Any version of the GPL is acceptable
9173 (license (list license:gpl2+ license:gpl3+))))
9175 (define-public r-raremetals2
9177 (name "r-raremetals2")
9182 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9183 "b/b7/RareMETALS2_" version ".tar.gz"))
9186 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9187 (properties `((upstream-name . "RareMETALS2")))
9188 (build-system r-build-system)
9190 `(("r-seqminer" ,r-seqminer)
9191 ("r-mvtnorm" ,r-mvtnorm)
9193 ("r-compquadform" ,r-compquadform)
9194 ("r-getopt" ,r-getopt)))
9195 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9196 (synopsis "Analyze gene-level association tests for binary trait")
9198 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9199 It was designed to meta-analyze gene-level association tests for binary trait.
9200 While rareMETALS offers a near-complete solution for meta-analysis of
9201 gene-level tests for quantitative trait, it does not offer the optimal
9202 solution for binary trait. The package rareMETALS2 offers improved features
9203 for analyzing gene-level association tests in meta-analyses for binary
9205 (license license:gpl3)))
9207 (define-public r-maldiquant
9209 (name "r-maldiquant")
9214 (uri (cran-uri "MALDIquant" version))
9217 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9218 (properties `((upstream-name . "MALDIquant")))
9219 (build-system r-build-system)
9220 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9221 (synopsis "Quantitative analysis of mass spectrometry data")
9223 "This package provides a complete analysis pipeline for matrix-assisted
9224 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9225 two-dimensional mass spectrometry data. In addition to commonly used plotting
9226 and processing methods it includes distinctive features, namely baseline
9227 subtraction methods such as morphological filters (TopHat) or the
9228 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9229 alignment using warping functions, handling of replicated measurements as well
9230 as allowing spectra with different resolutions.")
9231 (license license:gpl3+)))
9233 (define-public r-protgenerics
9235 (name "r-protgenerics")
9240 (uri (bioconductor-uri "ProtGenerics" version))
9243 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9244 (properties `((upstream-name . "ProtGenerics")))
9245 (build-system r-build-system)
9246 (home-page "https://github.com/lgatto/ProtGenerics")
9247 (synopsis "S4 generic functions for proteomics infrastructure")
9249 "This package provides S4 generic functions needed by Bioconductor
9250 proteomics packages.")
9251 (license license:artistic2.0)))
9253 (define-public r-mzr
9260 (uri (bioconductor-uri "mzR" version))
9263 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9264 (modules '((guix build utils)))
9267 (delete-file-recursively "src/boost")
9269 (properties `((upstream-name . "mzR")))
9270 (build-system r-build-system)
9273 (modify-phases %standard-phases
9274 (add-after 'unpack 'use-system-boost
9276 (substitute* "src/Makevars"
9277 (("\\./boost/libs.*") "")
9278 (("ARCH_OBJS=" line)
9280 "\nARCH_LIBS=-lboost_system -lboost_regex \
9281 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9284 `(("boost" ,boost) ; use this instead of the bundled boost sources
9285 ("netcdf" ,netcdf)))
9287 `(("r-biobase" ,r-biobase)
9288 ("r-biocgenerics" ,r-biocgenerics)
9289 ("r-protgenerics" ,r-protgenerics)
9291 ("r-zlibbioc" ,r-zlibbioc)))
9292 (home-page "https://github.com/sneumann/mzR/")
9293 (synopsis "Parser for mass spectrometry data files")
9295 "The mzR package provides a unified API to the common file formats and
9296 parsers available for mass spectrometry data. It comes with a wrapper for the
9297 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9298 The package contains the original code written by the ISB, and a subset of the
9299 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9300 previously been used in XCMS.")
9301 (license license:artistic2.0)))
9303 (define-public r-affyio
9310 (uri (bioconductor-uri "affyio" version))
9313 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9314 (build-system r-build-system)
9316 `(("r-zlibbioc" ,r-zlibbioc)))
9319 (home-page "https://github.com/bmbolstad/affyio")
9320 (synopsis "Tools for parsing Affymetrix data files")
9322 "This package provides routines for parsing Affymetrix data files based
9323 upon file format information. The primary focus is on accessing the CEL and
9325 (license license:lgpl2.0+)))
9327 (define-public r-affy
9334 (uri (bioconductor-uri "affy" version))
9337 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9338 (build-system r-build-system)
9340 `(("r-affyio" ,r-affyio)
9341 ("r-biobase" ,r-biobase)
9342 ("r-biocgenerics" ,r-biocgenerics)
9343 ("r-biocinstaller" ,r-biocinstaller)
9344 ("r-preprocesscore" ,r-preprocesscore)
9345 ("r-zlibbioc" ,r-zlibbioc)))
9346 (home-page "https://bioconductor.org/packages/affy")
9347 (synopsis "Methods for affymetrix oligonucleotide arrays")
9349 "This package contains functions for exploratory oligonucleotide array
9351 (license license:lgpl2.0+)))
9353 (define-public r-vsn
9360 (uri (bioconductor-uri "vsn" version))
9363 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9364 (build-system r-build-system)
9366 `(("r-affy" ,r-affy)
9367 ("r-biobase" ,r-biobase)
9368 ("r-ggplot2" ,r-ggplot2)
9369 ("r-lattice" ,r-lattice)
9370 ("r-limma" ,r-limma)))
9371 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9372 (synopsis "Variance stabilization and calibration for microarray data")
9374 "The package implements a method for normalising microarray intensities,
9375 and works for single- and multiple-color arrays. It can also be used for data
9376 from other technologies, as long as they have similar format. The method uses
9377 a robust variant of the maximum-likelihood estimator for an
9378 additive-multiplicative error model and affine calibration. The model
9379 incorporates data calibration step (a.k.a. normalization), a model for the
9380 dependence of the variance on the mean intensity and a variance stabilizing
9381 data transformation. Differences between transformed intensities are
9382 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9383 their variance is independent of the mean, and they are usually more sensitive
9384 and specific in detecting differential transcription.")
9385 (license license:artistic2.0)))
9387 (define-public r-mzid
9394 (uri (bioconductor-uri "mzID" version))
9397 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9398 (properties `((upstream-name . "mzID")))
9399 (build-system r-build-system)
9401 `(("r-doparallel" ,r-doparallel)
9402 ("r-foreach" ,r-foreach)
9403 ("r-iterators" ,r-iterators)
9405 ("r-protgenerics" ,r-protgenerics)
9408 (home-page "https://bioconductor.org/packages/mzID")
9409 (synopsis "Parser for mzIdentML files")
9411 "This package provides a parser for mzIdentML files implemented using the
9412 XML package. The parser tries to be general and able to handle all types of
9413 mzIdentML files with the drawback of having less pretty output than a vendor
9415 (license license:gpl2+)))
9417 (define-public r-pcamethods
9419 (name "r-pcamethods")
9424 (uri (bioconductor-uri "pcaMethods" version))
9427 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9428 (properties `((upstream-name . "pcaMethods")))
9429 (build-system r-build-system)
9431 `(("r-biobase" ,r-biobase)
9432 ("r-biocgenerics" ,r-biocgenerics)
9434 ("r-rcpp" ,r-rcpp)))
9435 (home-page "https://github.com/hredestig/pcamethods")
9436 (synopsis "Collection of PCA methods")
9438 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9439 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9440 for missing value estimation is included for comparison. BPCA, PPCA and
9441 NipalsPCA may be used to perform PCA on incomplete data as well as for
9442 accurate missing value estimation. A set of methods for printing and plotting
9443 the results is also provided. All PCA methods make use of the same data
9444 structure (pcaRes) to provide a common interface to the PCA results.")
9445 (license license:gpl3+)))
9447 (define-public r-msnbase
9454 (uri (bioconductor-uri "MSnbase" version))
9457 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9458 (properties `((upstream-name . "MSnbase")))
9459 (build-system r-build-system)
9461 `(("r-affy" ,r-affy)
9462 ("r-biobase" ,r-biobase)
9463 ("r-biocgenerics" ,r-biocgenerics)
9464 ("r-biocparallel" ,r-biocparallel)
9465 ("r-digest" ,r-digest)
9466 ("r-ggplot2" ,r-ggplot2)
9467 ("r-impute" ,r-impute)
9468 ("r-iranges" ,r-iranges)
9469 ("r-lattice" ,r-lattice)
9470 ("r-maldiquant" ,r-maldiquant)
9473 ("r-pcamethods" ,r-pcamethods)
9475 ("r-preprocesscore" ,r-preprocesscore)
9476 ("r-protgenerics" ,r-protgenerics)
9478 ("r-s4vectors" ,r-s4vectors)
9481 (home-page "https://github.com/lgatto/MSnbase")
9482 (synopsis "Base functions and classes for MS-based proteomics")
9484 "This package provides basic plotting, data manipulation and processing
9485 of mass spectrometry based proteomics data.")
9486 (license license:artistic2.0)))
9488 (define-public r-msnid
9495 (uri (bioconductor-uri "MSnID" version))
9498 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9499 (properties `((upstream-name . "MSnID")))
9500 (build-system r-build-system)
9502 `(("r-biobase" ,r-biobase)
9503 ("r-data-table" ,r-data-table)
9504 ("r-doparallel" ,r-doparallel)
9505 ("r-dplyr" ,r-dplyr)
9506 ("r-foreach" ,r-foreach)
9507 ("r-iterators" ,r-iterators)
9508 ("r-msnbase" ,r-msnbase)
9511 ("r-protgenerics" ,r-protgenerics)
9512 ("r-r-cache" ,r-r-cache)
9514 ("r-reshape2" ,r-reshape2)))
9515 (home-page "https://bioconductor.org/packages/MSnID")
9516 (synopsis "Utilities for LC-MSn proteomics identifications")
9518 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9519 from mzIdentML (leveraging the mzID package) or text files. After collating
9520 the search results from multiple datasets it assesses their identification
9521 quality and optimize filtering criteria to achieve the maximum number of
9522 identifications while not exceeding a specified false discovery rate. It also
9523 contains a number of utilities to explore the MS/MS results and assess missed
9524 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9525 (license license:artistic2.0)))
9527 (define-public r-seurat
9533 (uri (cran-uri "Seurat" version))
9536 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9537 ;; Delete pre-built jar.
9539 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9541 (properties `((upstream-name . "Seurat")))
9542 (build-system r-build-system)
9545 (modify-phases %standard-phases
9546 (add-after 'unpack 'build-jar
9547 (lambda* (#:key inputs #:allow-other-keys)
9548 (let ((classesdir "tmp-classes"))
9549 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9551 (with-output-to-file "manifest"
9553 (display "Manifest-Version: 1.0
9554 Main-Class: ModularityOptimizer\n")))
9555 (and (zero? (apply system* `("javac" "-d" ,classesdir
9556 ,@(find-files "java" "\\.java$"))))
9557 (zero? (system* "jar"
9559 "inst/java/ModularityOptimizer.jar"
9560 "-C" classesdir ".")))))))))
9562 `(("jdk" ,icedtea "jdk")))
9565 ("r-caret" ,r-caret)
9566 ("r-cowplot" ,r-cowplot)
9567 ("r-diffusionmap" ,r-diffusionmap)
9568 ("r-dplyr" ,r-dplyr)
9572 ("r-gdata" ,r-gdata)
9573 ("r-ggplot2" ,r-ggplot2)
9574 ("r-ggridges" ,r-ggridges)
9575 ("r-gplots" ,r-gplots)
9576 ("r-gridextra" ,r-gridextra)
9577 ("r-hmisc" ,r-hmisc)
9579 ("r-igraph" ,r-igraph)
9580 ("r-irlba" ,r-irlba)
9583 ("r-matrix" ,r-matrix)
9584 ("r-metap" ,r-metap)
9585 ("r-mixtools" ,r-mixtools)
9586 ("r-pbapply" ,r-pbapply)
9587 ("r-plotly" ,r-plotly)
9588 ("r-ranger" ,r-ranger)
9589 ("r-rcolorbrewer" ,r-rcolorbrewer)
9591 ("r-rcppeigen" ,r-rcppeigen)
9592 ("r-rcppprogress" ,r-rcppprogress)
9593 ("r-reshape2" ,r-reshape2)
9595 ("r-rtsne" ,r-rtsne)
9596 ("r-sdmtools" ,r-sdmtools)
9597 ("r-stringr" ,r-stringr)
9598 ("r-tclust" ,r-tclust)
9599 ("r-tidyr" ,r-tidyr)
9601 ("r-vgam" ,r-vgam)))
9602 (home-page "http://www.satijalab.org/seurat")
9603 (synopsis "Seurat is an R toolkit for single cell genomics")
9605 "This package is an R package designed for QC, analysis, and
9606 exploration of single cell RNA-seq data. It easily enables widely-used
9607 analytical techniques, including the identification of highly variable genes,
9608 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9609 algorithms; density clustering, hierarchical clustering, k-means, and the
9610 discovery of differentially expressed genes and markers.")
9611 (license license:gpl3)))
9613 (define-public r-aroma-light
9615 (name "r-aroma-light")
9620 (uri (bioconductor-uri "aroma.light" version))
9623 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9624 (properties `((upstream-name . "aroma.light")))
9625 (build-system r-build-system)
9627 `(("r-matrixstats" ,r-matrixstats)
9628 ("r-r-methodss3" ,r-r-methodss3)
9630 ("r-r-utils" ,r-r-utils)))
9631 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9632 (synopsis "Methods for normalization and visualization of microarray data")
9634 "This package provides methods for microarray analysis that take basic
9635 data types such as matrices and lists of vectors. These methods can be used
9636 standalone, be utilized in other packages, or be wrapped up in higher-level
9638 (license license:gpl2+)))
9640 (define-public r-deseq
9647 (uri (bioconductor-uri "DESeq" version))
9650 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9651 (properties `((upstream-name . "DESeq")))
9652 (build-system r-build-system)
9654 `(("r-biobase" ,r-biobase)
9655 ("r-biocgenerics" ,r-biocgenerics)
9656 ("r-genefilter" ,r-genefilter)
9657 ("r-geneplotter" ,r-geneplotter)
9658 ("r-lattice" ,r-lattice)
9659 ("r-locfit" ,r-locfit)
9661 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9662 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9663 (synopsis "Differential gene expression analysis")
9665 "This package provides tools for estimating variance-mean dependence in
9666 count data from high-throughput genetic sequencing assays and for testing for
9667 differential expression based on a model using the negative binomial
9669 (license license:gpl3+)))
9671 (define-public r-edaseq
9678 (uri (bioconductor-uri "EDASeq" version))
9681 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9682 (properties `((upstream-name . "EDASeq")))
9683 (build-system r-build-system)
9685 `(("r-annotationdbi" ,r-annotationdbi)
9686 ("r-aroma-light" ,r-aroma-light)
9687 ("r-biobase" ,r-biobase)
9688 ("r-biocgenerics" ,r-biocgenerics)
9689 ("r-biomart" ,r-biomart)
9690 ("r-biostrings" ,r-biostrings)
9691 ("r-deseq" ,r-deseq)
9692 ("r-genomicfeatures" ,r-genomicfeatures)
9693 ("r-genomicranges" ,r-genomicranges)
9694 ("r-iranges" ,r-iranges)
9695 ("r-rsamtools" ,r-rsamtools)
9696 ("r-shortread" ,r-shortread)))
9697 (home-page "https://github.com/drisso/EDASeq")
9698 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9700 "This package provides support for numerical and graphical summaries of
9701 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9702 adjust for GC-content effect (or other gene-level effects) on read counts:
9703 loess robust local regression, global-scaling, and full-quantile
9704 normalization. Between-lane normalization procedures to adjust for
9705 distributional differences between lanes (e.g., sequencing depth):
9706 global-scaling and full-quantile normalization.")
9707 (license license:artistic2.0)))
9709 (define-public r-interactivedisplaybase
9711 (name "r-interactivedisplaybase")
9716 (uri (bioconductor-uri "interactiveDisplayBase" version))
9719 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9721 `((upstream-name . "interactiveDisplayBase")))
9722 (build-system r-build-system)
9724 `(("r-biocgenerics" ,r-biocgenerics)
9725 ("r-shiny" ,r-shiny)))
9726 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9727 (synopsis "Base package for web displays of Bioconductor objects")
9729 "This package contains the basic methods needed to generate interactive
9730 Shiny-based display methods for Bioconductor objects.")
9731 (license license:artistic2.0)))
9733 (define-public r-annotationhub
9735 (name "r-annotationhub")
9740 (uri (bioconductor-uri "AnnotationHub" version))
9743 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9744 (properties `((upstream-name . "AnnotationHub")))
9745 (build-system r-build-system)
9747 `(("r-annotationdbi" ,r-annotationdbi)
9748 ("r-biocgenerics" ,r-biocgenerics)
9749 ("r-biocinstaller" ,r-biocinstaller)
9752 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9753 ("r-rsqlite" ,r-rsqlite)
9754 ("r-s4vectors" ,r-s4vectors)
9755 ("r-yaml" ,r-yaml)))
9756 (home-page "https://bioconductor.org/packages/AnnotationHub")
9757 (synopsis "Client to access AnnotationHub resources")
9759 "This package provides a client for the Bioconductor AnnotationHub web
9760 resource. The AnnotationHub web resource provides a central location where
9761 genomic files (e.g. VCF, bed, wig) and other resources from standard
9762 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9763 metadata about each resource, e.g., a textual description, tags, and date of
9764 modification. The client creates and manages a local cache of files retrieved
9765 by the user, helping with quick and reproducible access.")
9766 (license license:artistic2.0)))
9768 (define-public r-fastseg
9775 (uri (bioconductor-uri "fastseg" version))
9778 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9779 (build-system r-build-system)
9781 `(("r-biobase" ,r-biobase)
9782 ("r-biocgenerics" ,r-biocgenerics)
9783 ("r-genomicranges" ,r-genomicranges)
9784 ("r-iranges" ,r-iranges)
9785 ("r-s4vectors" ,r-s4vectors)))
9786 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9787 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9789 "Fastseg implements a very fast and efficient segmentation algorithm.
9790 It can segment data from DNA microarrays and data from next generation
9791 sequencing for example to detect copy number segments. Further it can segment
9792 data from RNA microarrays like tiling arrays to identify transcripts. Most
9793 generally, it can segment data given as a matrix or as a vector. Various data
9794 formats can be used as input to fastseg like expression set objects for
9795 microarrays or GRanges for sequencing data.")
9796 (license license:lgpl2.0+)))
9798 (define-public r-keggrest
9805 (uri (bioconductor-uri "KEGGREST" version))
9808 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9809 (properties `((upstream-name . "KEGGREST")))
9810 (build-system r-build-system)
9812 `(("r-biostrings" ,r-biostrings)
9815 (home-page "https://bioconductor.org/packages/KEGGREST")
9816 (synopsis "Client-side REST access to KEGG")
9818 "This package provides a package that provides a client interface to the
9819 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9820 (license license:artistic2.0)))
9822 (define-public r-gage
9829 (uri (bioconductor-uri "gage" version))
9832 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9833 (build-system r-build-system)
9835 `(("r-annotationdbi" ,r-annotationdbi)
9836 ("r-graph" ,r-graph)
9837 ("r-keggrest" ,r-keggrest)))
9838 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9839 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9841 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9842 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9843 data attributes including sample sizes, experimental designs, assay platforms,
9844 and other types of heterogeneity. The gage package provides functions for
9845 basic GAGE analysis, result processing and presentation. In addition, it
9846 provides demo microarray data and commonly used gene set data based on KEGG
9847 pathways and GO terms. These funtions and data are also useful for gene set
9848 analysis using other methods.")
9849 (license license:gpl2+)))
9851 (define-public r-genomicfiles
9853 (name "r-genomicfiles")
9858 (uri (bioconductor-uri "GenomicFiles" version))
9861 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9862 (properties `((upstream-name . "GenomicFiles")))
9863 (build-system r-build-system)
9865 `(("r-biocgenerics" ,r-biocgenerics)
9866 ("r-biocparallel" ,r-biocparallel)
9867 ("r-genomeinfodb" ,r-genomeinfodb)
9868 ("r-genomicalignments" ,r-genomicalignments)
9869 ("r-genomicranges" ,r-genomicranges)
9870 ("r-iranges" ,r-iranges)
9871 ("r-rsamtools" ,r-rsamtools)
9872 ("r-rtracklayer" ,r-rtracklayer)
9873 ("r-s4vectors" ,r-s4vectors)
9874 ("r-summarizedexperiment" ,r-summarizedexperiment)
9875 ("r-variantannotation" ,r-variantannotation)))
9876 (home-page "https://bioconductor.org/packages/GenomicFiles")
9877 (synopsis "Distributed computing by file or by range")
9879 "This package provides infrastructure for parallel computations
9880 distributed by file or by range. User defined mapper and reducer functions
9881 provide added flexibility for data combination and manipulation.")
9882 (license license:artistic2.0)))
9884 (define-public r-complexheatmap
9886 (name "r-complexheatmap")
9891 (uri (bioconductor-uri "ComplexHeatmap" version))
9894 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9896 `((upstream-name . "ComplexHeatmap")))
9897 (build-system r-build-system)
9899 `(("r-circlize" ,r-circlize)
9900 ("r-colorspace" ,r-colorspace)
9901 ("r-getoptlong" ,r-getoptlong)
9902 ("r-globaloptions" ,r-globaloptions)
9903 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9905 "https://github.com/jokergoo/ComplexHeatmap")
9906 (synopsis "Making Complex Heatmaps")
9908 "Complex heatmaps are efficient to visualize associations between
9909 different sources of data sets and reveal potential structures. This package
9910 provides a highly flexible way to arrange multiple heatmaps and supports
9911 self-defined annotation graphics.")
9912 (license license:gpl2+)))
9914 (define-public r-dirichletmultinomial
9916 (name "r-dirichletmultinomial")
9921 (uri (bioconductor-uri "DirichletMultinomial" version))
9924 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9926 `((upstream-name . "DirichletMultinomial")))
9927 (build-system r-build-system)
9931 `(("r-biocgenerics" ,r-biocgenerics)
9932 ("r-iranges" ,r-iranges)
9933 ("r-s4vectors" ,r-s4vectors)))
9934 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9935 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9937 "Dirichlet-multinomial mixture models can be used to describe variability
9938 in microbial metagenomic data. This package is an interface to code
9939 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9941 (license license:lgpl3)))
9943 (define-public r-ensembldb
9945 (name "r-ensembldb")
9950 (uri (bioconductor-uri "ensembldb" version))
9953 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
9954 (build-system r-build-system)
9956 `(("r-annotationdbi" ,r-annotationdbi)
9957 ("r-annotationfilter" ,r-annotationfilter)
9958 ("r-annotationhub" ,r-annotationhub)
9959 ("r-biobase" ,r-biobase)
9960 ("r-biocgenerics" ,r-biocgenerics)
9961 ("r-biostrings" ,r-biostrings)
9964 ("r-genomeinfodb" ,r-genomeinfodb)
9965 ("r-genomicfeatures" ,r-genomicfeatures)
9966 ("r-genomicranges" ,r-genomicranges)
9967 ("r-iranges" ,r-iranges)
9968 ("r-protgenerics" ,r-protgenerics)
9969 ("r-rsamtools" ,r-rsamtools)
9970 ("r-rsqlite" ,r-rsqlite)
9971 ("r-rtracklayer" ,r-rtracklayer)
9972 ("r-s4vectors" ,r-s4vectors)))
9973 (home-page "https://github.com/jotsetung/ensembldb")
9974 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9976 "The package provides functions to create and use transcript-centric
9977 annotation databases/packages. The annotation for the databases are directly
9978 fetched from Ensembl using their Perl API. The functionality and data is
9979 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9980 but, in addition to retrieve all gene/transcript models and annotations from
9981 the database, the @code{ensembldb} package also provides a filter framework
9982 allowing to retrieve annotations for specific entries like genes encoded on a
9983 chromosome region or transcript models of lincRNA genes.")
9984 ;; No version specified
9985 (license license:lgpl3+)))
9987 (define-public r-organismdbi
9989 (name "r-organismdbi")
9994 (uri (bioconductor-uri "OrganismDbi" version))
9997 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9998 (properties `((upstream-name . "OrganismDbi")))
9999 (build-system r-build-system)
10001 `(("r-annotationdbi" ,r-annotationdbi)
10002 ("r-biobase" ,r-biobase)
10003 ("r-biocgenerics" ,r-biocgenerics)
10004 ("r-biocinstaller" ,r-biocinstaller)
10006 ("r-genomicfeatures" ,r-genomicfeatures)
10007 ("r-genomicranges" ,r-genomicranges)
10008 ("r-graph" ,r-graph)
10009 ("r-iranges" ,r-iranges)
10011 ("r-s4vectors" ,r-s4vectors)))
10012 (home-page "https://bioconductor.org/packages/OrganismDbi")
10013 (synopsis "Software to enable the smooth interfacing of database packages")
10014 (description "The package enables a simple unified interface to several
10015 annotation packages each of which has its own schema by taking advantage of
10016 the fact that each of these packages implements a select methods.")
10017 (license license:artistic2.0)))
10019 (define-public r-biovizbase
10021 (name "r-biovizbase")
10026 (uri (bioconductor-uri "biovizBase" version))
10029 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10030 (properties `((upstream-name . "biovizBase")))
10031 (build-system r-build-system)
10033 `(("r-annotationdbi" ,r-annotationdbi)
10034 ("r-annotationfilter" ,r-annotationfilter)
10035 ("r-biocgenerics" ,r-biocgenerics)
10036 ("r-biostrings" ,r-biostrings)
10037 ("r-dichromat" ,r-dichromat)
10038 ("r-ensembldb" ,r-ensembldb)
10039 ("r-genomeinfodb" ,r-genomeinfodb)
10040 ("r-genomicalignments" ,r-genomicalignments)
10041 ("r-genomicfeatures" ,r-genomicfeatures)
10042 ("r-genomicranges" ,r-genomicranges)
10043 ("r-hmisc" ,r-hmisc)
10044 ("r-iranges" ,r-iranges)
10045 ("r-rcolorbrewer" ,r-rcolorbrewer)
10046 ("r-rsamtools" ,r-rsamtools)
10047 ("r-s4vectors" ,r-s4vectors)
10048 ("r-scales" ,r-scales)
10049 ("r-summarizedexperiment" ,r-summarizedexperiment)
10050 ("r-variantannotation" ,r-variantannotation)))
10051 (home-page "https://bioconductor.org/packages/biovizBase")
10052 (synopsis "Basic graphic utilities for visualization of genomic data")
10054 "The biovizBase package is designed to provide a set of utilities, color
10055 schemes and conventions for genomic data. It serves as the base for various
10056 high-level packages for biological data visualization. This saves development
10057 effort and encourages consistency.")
10058 (license license:artistic2.0)))
10060 (define-public r-ggbio
10067 (uri (bioconductor-uri "ggbio" version))
10070 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10071 (build-system r-build-system)
10073 `(("r-annotationdbi" ,r-annotationdbi)
10074 ("r-annotationfilter" ,r-annotationfilter)
10075 ("r-biobase" ,r-biobase)
10076 ("r-biocgenerics" ,r-biocgenerics)
10077 ("r-biostrings" ,r-biostrings)
10078 ("r-biovizbase" ,r-biovizbase)
10079 ("r-bsgenome" ,r-bsgenome)
10080 ("r-ensembldb" ,r-ensembldb)
10081 ("r-genomeinfodb" ,r-genomeinfodb)
10082 ("r-genomicalignments" ,r-genomicalignments)
10083 ("r-genomicfeatures" ,r-genomicfeatures)
10084 ("r-genomicranges" ,r-genomicranges)
10085 ("r-ggally" ,r-ggally)
10086 ("r-ggplot2" ,r-ggplot2)
10087 ("r-gridextra" ,r-gridextra)
10088 ("r-gtable" ,r-gtable)
10089 ("r-hmisc" ,r-hmisc)
10090 ("r-iranges" ,r-iranges)
10091 ("r-organismdbi" ,r-organismdbi)
10092 ("r-reshape2" ,r-reshape2)
10093 ("r-rsamtools" ,r-rsamtools)
10094 ("r-rtracklayer" ,r-rtracklayer)
10095 ("r-s4vectors" ,r-s4vectors)
10096 ("r-scales" ,r-scales)
10097 ("r-summarizedexperiment" ,r-summarizedexperiment)
10098 ("r-variantannotation" ,r-variantannotation)))
10099 (home-page "http://www.tengfei.name/ggbio/")
10100 (synopsis "Visualization tools for genomic data")
10102 "The ggbio package extends and specializes the grammar of graphics for
10103 biological data. The graphics are designed to answer common scientific
10104 questions, in particular those often asked of high throughput genomics data.
10105 All core Bioconductor data structures are supported, where appropriate. The
10106 package supports detailed views of particular genomic regions, as well as
10107 genome-wide overviews. Supported overviews include ideograms and grand linear
10108 views. High-level plots include sequence fragment length, edge-linked
10109 interval to data view, mismatch pileup, and several splicing summaries.")
10110 (license license:artistic2.0)))
10112 (define-public r-gprofiler
10114 (name "r-gprofiler")
10119 (uri (cran-uri "gProfileR" version))
10122 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10123 (properties `((upstream-name . "gProfileR")))
10124 (build-system r-build-system)
10126 `(("r-plyr" ,r-plyr)
10127 ("r-rcurl" ,r-rcurl)))
10128 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10129 (synopsis "Interface to the g:Profiler toolkit")
10131 "This package provides tools for functional enrichment analysis,
10132 gene identifier conversion and mapping homologous genes across related
10133 organisms via the @code{g:Profiler} toolkit.")
10134 (license license:gpl2+)))
10136 (define-public r-gqtlbase
10138 (name "r-gqtlbase")
10143 (uri (bioconductor-uri "gQTLBase" version))
10146 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10147 (properties `((upstream-name . "gQTLBase")))
10148 (build-system r-build-system)
10150 `(("r-batchjobs" ,r-batchjobs)
10151 ("r-bbmisc" ,r-bbmisc)
10152 ("r-biocgenerics" ,r-biocgenerics)
10154 ("r-doparallel" ,r-doparallel)
10156 ("r-ffbase" ,r-ffbase)
10157 ("r-foreach" ,r-foreach)
10158 ("r-genomicfiles" ,r-genomicfiles)
10159 ("r-genomicranges" ,r-genomicranges)
10160 ("r-rtracklayer" ,r-rtracklayer)
10161 ("r-s4vectors" ,r-s4vectors)
10162 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10163 (home-page "https://bioconductor.org/packages/gQTLBase")
10164 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10166 "The purpose of this package is to simplify the storage and interrogation
10167 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10169 (license license:artistic2.0)))
10171 (define-public r-snpstats
10173 (name "r-snpstats")
10178 (uri (bioconductor-uri "snpStats" version))
10181 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10182 (properties `((upstream-name . "snpStats")))
10183 (build-system r-build-system)
10184 (inputs `(("zlib" ,zlib)))
10186 `(("r-biocgenerics" ,r-biocgenerics)
10187 ("r-matrix" ,r-matrix)
10188 ("r-survival" ,r-survival)
10189 ("r-zlibbioc" ,r-zlibbioc)))
10190 (home-page "https://bioconductor.org/packages/snpStats")
10191 (synopsis "Methods for SNP association studies")
10193 "This package provides classes and statistical methods for large
10194 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10195 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10196 (license license:gpl3)))
10198 (define-public r-homo-sapiens
10200 (name "r-homo-sapiens")
10204 ;; We cannot use bioconductor-uri here because this tarball is
10205 ;; located under "data/annotation/" instead of "bioc/".
10206 (uri (string-append "http://www.bioconductor.org/packages/"
10207 "release/data/annotation/src/contrib/"
10209 version ".tar.gz"))
10212 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10214 `((upstream-name . "Homo.sapiens")))
10215 (build-system r-build-system)
10217 `(("r-genomicfeatures" ,r-genomicfeatures)
10218 ("r-go-db" ,r-go-db)
10219 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10220 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10221 ("r-organismdbi" ,r-organismdbi)
10222 ("r-annotationdbi" ,r-annotationdbi)))
10223 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10224 (synopsis "Annotation package for the Homo.sapiens object")
10226 "This package contains the Homo.sapiens object to access data from
10227 several related annotation packages.")
10228 (license license:artistic2.0)))
10230 (define-public r-erma
10237 (uri (bioconductor-uri "erma" version))
10240 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10241 (build-system r-build-system)
10243 `(("r-annotationdbi" ,r-annotationdbi)
10244 ("r-biobase" ,r-biobase)
10245 ("r-biocgenerics" ,r-biocgenerics)
10246 ("r-foreach" ,r-foreach)
10247 ("r-genomicfiles" ,r-genomicfiles)
10248 ("r-genomicranges" ,r-genomicranges)
10249 ("r-ggplot2" ,r-ggplot2)
10250 ("r-homo-sapiens" ,r-homo-sapiens)
10251 ("r-rtracklayer" ,r-rtracklayer)
10252 ("r-s4vectors" ,r-s4vectors)
10253 ("r-shiny" ,r-shiny)
10254 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10255 (home-page "https://bioconductor.org/packages/erma")
10256 (synopsis "Epigenomic road map adventures")
10258 "The epigenomics road map describes locations of epigenetic marks in DNA
10259 from a variety of cell types. Of interest are locations of histone
10260 modifications, sites of DNA methylation, and regions of accessible chromatin.
10261 This package presents a selection of elements of the road map including
10262 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10263 by Ernst and Kellis.")
10264 (license license:artistic2.0)))
10266 (define-public r-ldblock
10273 (uri (bioconductor-uri "ldblock" version))
10276 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10277 (build-system r-build-system)
10279 `(("r-erma" ,r-erma)
10280 ("r-genomeinfodb" ,r-genomeinfodb)
10281 ("r-genomicfiles" ,r-genomicfiles)
10282 ("r-go-db" ,r-go-db)
10283 ("r-homo-sapiens" ,r-homo-sapiens)
10284 ("r-matrix" ,r-matrix)
10285 ("r-rsamtools" ,r-rsamtools)
10286 ("r-snpstats" ,r-snpstats)
10287 ("r-variantannotation" ,r-variantannotation)))
10288 (home-page "https://bioconductor.org/packages/ldblock")
10289 (synopsis "Data structures for linkage disequilibrium measures in populations")
10291 "This package defines data structures for @dfn{linkage
10292 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10293 handling of existing population-level data for the purpose of flexibly
10294 defining LD blocks.")
10295 (license license:artistic2.0)))
10297 (define-public r-gqtlstats
10299 (name "r-gqtlstats")
10304 (uri (bioconductor-uri "gQTLstats" version))
10307 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10308 (properties `((upstream-name . "gQTLstats")))
10309 (build-system r-build-system)
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-batchjobs" ,r-batchjobs)
10313 ("r-bbmisc" ,r-bbmisc)
10314 ("r-beeswarm" ,r-beeswarm)
10315 ("r-biobase" ,r-biobase)
10316 ("r-biocgenerics" ,r-biocgenerics)
10317 ("r-doparallel" ,r-doparallel)
10318 ("r-dplyr" ,r-dplyr)
10320 ("r-ffbase" ,r-ffbase)
10321 ("r-foreach" ,r-foreach)
10322 ("r-genomeinfodb" ,r-genomeinfodb)
10323 ("r-genomicfeatures" ,r-genomicfeatures)
10324 ("r-genomicfiles" ,r-genomicfiles)
10325 ("r-genomicranges" ,r-genomicranges)
10326 ("r-ggbeeswarm" ,r-ggbeeswarm)
10327 ("r-ggplot2" ,r-ggplot2)
10328 ("r-gqtlbase" ,r-gqtlbase)
10329 ("r-hardyweinberg" ,r-hardyweinberg)
10330 ("r-iranges" ,r-iranges)
10331 ("r-ldblock" ,r-ldblock)
10332 ("r-limma" ,r-limma)
10334 ("r-plotly" ,r-plotly)
10335 ("r-reshape2" ,r-reshape2)
10336 ("r-s4vectors" ,r-s4vectors)
10337 ("r-shiny" ,r-shiny)
10338 ("r-snpstats" ,r-snpstats)
10339 ("r-summarizedexperiment" ,r-summarizedexperiment)
10340 ("r-variantannotation" ,r-variantannotation)))
10341 (home-page "https://bioconductor.org/packages/gQTLstats")
10342 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10344 "This package provides tools for the computationally efficient analysis
10345 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10346 The software in this package aims to support refinements and functional
10347 interpretation of members of a collection of association statistics on a
10348 family of feature/genome hypotheses.")
10349 (license license:artistic2.0)))
10351 (define-public r-gviz
10358 (uri (bioconductor-uri "Gviz" version))
10361 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10362 (properties `((upstream-name . "Gviz")))
10363 (build-system r-build-system)
10365 `(("r-annotationdbi" ,r-annotationdbi)
10366 ("r-biobase" ,r-biobase)
10367 ("r-biocgenerics" ,r-biocgenerics)
10368 ("r-biomart" ,r-biomart)
10369 ("r-biostrings" ,r-biostrings)
10370 ("r-biovizbase" ,r-biovizbase)
10371 ("r-bsgenome" ,r-bsgenome)
10372 ("r-digest" ,r-digest)
10373 ("r-genomeinfodb" ,r-genomeinfodb)
10374 ("r-genomicalignments" ,r-genomicalignments)
10375 ("r-genomicfeatures" ,r-genomicfeatures)
10376 ("r-genomicranges" ,r-genomicranges)
10377 ("r-iranges" ,r-iranges)
10378 ("r-lattice" ,r-lattice)
10379 ("r-latticeextra" ,r-latticeextra)
10380 ("r-matrixstats" ,r-matrixstats)
10381 ("r-rcolorbrewer" ,r-rcolorbrewer)
10382 ("r-rsamtools" ,r-rsamtools)
10383 ("r-rtracklayer" ,r-rtracklayer)
10384 ("r-s4vectors" ,r-s4vectors)
10385 ("r-xvector" ,r-xvector)))
10386 (home-page "https://bioconductor.org/packages/Gviz")
10387 (synopsis "Plotting data and annotation information along genomic coordinates")
10389 "Genomic data analyses requires integrated visualization of known genomic
10390 information and new experimental data. Gviz uses the biomaRt and the
10391 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10392 and translates this to e.g. gene/transcript structures in viewports of the
10393 grid graphics package. This results in genomic information plotted together
10395 (license license:artistic2.0)))
10397 (define-public r-gwascat
10404 (uri (bioconductor-uri "gwascat" version))
10407 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10408 (build-system r-build-system)
10410 `(("r-annotationdbi" ,r-annotationdbi)
10411 ("r-annotationhub" ,r-annotationhub)
10412 ("r-biocgenerics" ,r-biocgenerics)
10413 ("r-biostrings" ,r-biostrings)
10414 ("r-genomeinfodb" ,r-genomeinfodb)
10415 ("r-genomicfeatures" ,r-genomicfeatures)
10416 ("r-genomicranges" ,r-genomicranges)
10417 ("r-ggbio" ,r-ggbio)
10418 ("r-ggplot2" ,r-ggplot2)
10419 ("r-gqtlstats" ,r-gqtlstats)
10420 ("r-graph" ,r-graph)
10422 ("r-homo-sapiens" ,r-homo-sapiens)
10423 ("r-iranges" ,r-iranges)
10424 ("r-rsamtools" ,r-rsamtools)
10425 ("r-rtracklayer" ,r-rtracklayer)
10426 ("r-s4vectors" ,r-s4vectors)
10427 ("r-snpstats" ,r-snpstats)
10428 ("r-summarizedexperiment" ,r-summarizedexperiment)
10429 ("r-variantannotation" ,r-variantannotation)))
10430 (home-page "https://bioconductor.org/packages/gwascat")
10431 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10433 "This package provides tools for representing and modeling data in the
10434 EMBL-EBI GWAS catalog.")
10435 (license license:artistic2.0)))
10437 (define-public r-sushi
10443 (uri (bioconductor-uri "Sushi" version))
10446 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10447 (properties `((upstream-name . "Sushi")))
10448 (build-system r-build-system)
10450 `(("r-biomart" ,r-biomart)
10452 (home-page "https://bioconductor.org/packages/Sushi")
10453 (synopsis "Tools for visualizing genomics data")
10455 "This package provides flexible, quantitative, and integrative genomic
10456 visualizations for publication-quality multi-panel figures.")
10457 (license license:gpl2+)))
10459 (define-public r-fithic
10465 (uri (bioconductor-uri "FitHiC" version))
10468 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10469 (properties `((upstream-name . "FitHiC")))
10470 (build-system r-build-system)
10472 `(("r-data-table" ,r-data-table)
10473 ("r-fdrtool" ,r-fdrtool)
10474 ("r-rcpp" ,r-rcpp)))
10475 (home-page "https://bioconductor.org/packages/FitHiC")
10476 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10478 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10479 intra-chromosomal contact maps produced by genome-wide genome architecture
10480 assays such as Hi-C.")
10481 (license license:gpl2+)))
10483 (define-public r-hitc
10489 (uri (bioconductor-uri "HiTC" version))
10492 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10493 (properties `((upstream-name . "HiTC")))
10494 (build-system r-build-system)
10496 `(("r-biostrings" ,r-biostrings)
10497 ("r-genomeinfodb" ,r-genomeinfodb)
10498 ("r-genomicranges" ,r-genomicranges)
10499 ("r-iranges" ,r-iranges)
10500 ("r-matrix" ,r-matrix)
10501 ("r-rcolorbrewer" ,r-rcolorbrewer)
10502 ("r-rtracklayer" ,r-rtracklayer)))
10503 (home-page "https://bioconductor.org/packages/HiTC")
10504 (synopsis "High throughput chromosome conformation capture analysis")
10506 "The HiTC package was developed to explore high-throughput \"C\" data
10507 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10508 quality controls, normalization, visualization, and further analysis are also
10510 (license license:artistic2.0)))
10512 (define-public r-qvalue
10519 (uri (bioconductor-uri "qvalue" version))
10522 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10523 (build-system r-build-system)
10525 `(("r-ggplot2" ,r-ggplot2)
10526 ("r-reshape2" ,r-reshape2)))
10527 (home-page "http://github.com/jdstorey/qvalue")
10528 (synopsis "Q-value estimation for false discovery rate control")
10530 "This package takes a list of p-values resulting from the simultaneous
10531 testing of many hypotheses and estimates their q-values and local @dfn{false
10532 discovery rate} (FDR) values. The q-value of a test measures the proportion
10533 of false positives incurred when that particular test is called significant.
10534 The local FDR measures the posterior probability the null hypothesis is true
10535 given the test's p-value. Various plots are automatically generated, allowing
10536 one to make sensible significance cut-offs. The software can be applied to
10537 problems in genomics, brain imaging, astrophysics, and data mining.")
10538 ;; Any version of the LGPL.
10539 (license license:lgpl3+)))
10541 (define-public r-hdf5array
10543 (name "r-hdf5array")
10548 (uri (bioconductor-uri "HDF5Array" version))
10551 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10552 (properties `((upstream-name . "HDF5Array")))
10553 (build-system r-build-system)
10555 `(("r-biocgenerics" ,r-biocgenerics)
10556 ("r-delayedarray" ,r-delayedarray)
10557 ("r-iranges" ,r-iranges)
10558 ("r-rhdf5" ,r-rhdf5)
10559 ("r-s4vectors" ,r-s4vectors)))
10560 (home-page "https://bioconductor.org/packages/HDF5Array")
10561 (synopsis "HDF5 back end for DelayedArray objects")
10562 (description "This package provides an array-like container for convenient
10563 access and manipulation of HDF5 datasets. It supports delayed operations and
10564 block processing.")
10565 (license license:artistic2.0)))
10567 (define-public r-rhdf5lib
10569 (name "r-rhdf5lib")
10574 (uri (bioconductor-uri "Rhdf5lib" version))
10577 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10578 (properties `((upstream-name . "Rhdf5lib")))
10579 (build-system r-build-system)
10582 (modify-phases %standard-phases
10583 (add-after 'unpack 'do-not-use-bundled-hdf5
10584 (lambda* (#:key inputs #:allow-other-keys)
10585 (for-each delete-file '("configure" "configure.ac"))
10586 ;; Do not make other packages link with the proprietary libsz.
10587 (substitute* "R/zzz.R"
10588 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10589 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10590 (("'%s/libhdf5.a %s/libsz.a'")
10591 "'%s/libhdf5.a %s/libhdf5.a'"))
10592 (with-directory-excursion "src"
10593 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10594 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10596 (rename-file "Makevars.in" "Makevars")
10597 (substitute* "Makevars"
10598 (("HDF5_CXX_LIB=.*")
10599 (string-append "HDF5_CXX_LIB="
10600 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10602 (string-append "HDF5_LIB="
10603 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10604 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10605 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10606 ;; szip is non-free software
10607 (("cp \\$\\{SZIP_LIB\\}.*") "")
10608 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10609 "PKG_LIBS = ${HDF5_LIB}\n")))
10616 `(("hdf5-source" ,(package-source hdf5))))
10617 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10618 (synopsis "HDF5 library as an R package")
10619 (description "This package provides C and C++ HDF5 libraries for use in R
10621 (license license:artistic2.0)))
10623 (define-public r-beachmat
10625 (name "r-beachmat")
10630 (uri (bioconductor-uri "beachmat" version))
10633 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10634 (build-system r-build-system)
10638 `(("r-delayedarray" ,r-delayedarray)
10639 ("r-hdf5array" ,r-hdf5array)
10641 ("r-rhdf5" ,r-rhdf5)
10642 ("r-rhdf5lib" ,r-rhdf5lib)))
10643 (home-page "https://bioconductor.org/packages/beachmat")
10644 (synopsis "Compiling Bioconductor to handle each matrix type")
10645 (description "This package provides a consistent C++ class interface for a
10646 variety of commonly used matrix types, including sparse and HDF5-backed
10648 (license license:gpl3)))
10650 (define-public r-singlecellexperiment
10652 (name "r-singlecellexperiment")
10657 (uri (bioconductor-uri "SingleCellExperiment" version))
10660 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10662 `((upstream-name . "SingleCellExperiment")))
10663 (build-system r-build-system)
10665 `(("r-biocgenerics" ,r-biocgenerics)
10666 ("r-s4vectors" ,r-s4vectors)
10667 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10668 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10669 (synopsis "S4 classes for single cell data")
10670 (description "This package defines an S4 class for storing data from
10671 single-cell experiments. This includes specialized methods to store and
10672 retrieve spike-in information, dimensionality reduction coordinates and size
10673 factors for each cell, along with the usual metadata for genes and
10675 (license license:gpl3)))
10677 (define-public r-scater
10683 (uri (bioconductor-uri "scater" version))
10686 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10687 (build-system r-build-system)
10689 `(("r-beachmat" ,r-beachmat)
10690 ("r-biobase" ,r-biobase)
10691 ("r-biocgenerics" ,r-biocgenerics)
10692 ("r-biomart" ,r-biomart)
10693 ("r-data-table" ,r-data-table)
10694 ("r-dplyr" ,r-dplyr)
10695 ("r-edger" ,r-edger)
10696 ("r-ggbeeswarm" ,r-ggbeeswarm)
10697 ("r-ggplot2" ,r-ggplot2)
10698 ("r-limma" ,r-limma)
10699 ("r-matrix" ,r-matrix)
10700 ("r-matrixstats" ,r-matrixstats)
10703 ("r-reshape2" ,r-reshape2)
10704 ("r-rhdf5" ,r-rhdf5)
10705 ("r-rhdf5lib" ,r-rhdf5lib)
10706 ("r-rjson" ,r-rjson)
10707 ("r-s4vectors" ,r-s4vectors)
10708 ("r-shiny" ,r-shiny)
10709 ("r-shinydashboard" ,r-shinydashboard)
10710 ("r-singlecellexperiment" ,r-singlecellexperiment)
10711 ("r-summarizedexperiment" ,r-summarizedexperiment)
10712 ("r-tximport" ,r-tximport)
10713 ("r-viridis" ,r-viridis)))
10714 (home-page "https://github.com/davismcc/scater")
10715 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10716 (description "This package provides a collection of tools for doing
10717 various analyses of single-cell RNA-seq gene expression data, with a focus on
10719 (license license:gpl2+)))
10721 (define-public r-scran
10728 (uri (bioconductor-uri "scran" version))
10731 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10732 (build-system r-build-system)
10734 `(("r-beachmat" ,r-beachmat)
10735 ("r-biocgenerics" ,r-biocgenerics)
10736 ("r-biocparallel" ,r-biocparallel)
10738 ("r-dynamictreecut" ,r-dynamictreecut)
10739 ("r-edger" ,r-edger)
10741 ("r-ggplot2" ,r-ggplot2)
10742 ("r-igraph" ,r-igraph)
10743 ("r-limma" ,r-limma)
10744 ("r-matrix" ,r-matrix)
10746 ("r-rhdf5lib" ,r-rhdf5lib)
10747 ("r-s4vectors" ,r-s4vectors)
10748 ("r-scater" ,r-scater)
10749 ("r-shiny" ,r-shiny)
10750 ("r-singlecellexperiment" ,r-singlecellexperiment)
10751 ("r-statmod" ,r-statmod)
10752 ("r-summarizedexperiment" ,r-summarizedexperiment)
10753 ("r-viridis" ,r-viridis)
10755 (home-page "https://bioconductor.org/packages/scran")
10756 (synopsis "Methods for single-cell RNA-Seq data analysis")
10757 (description "This package implements a variety of low-level analyses of
10758 single-cell RNA-seq data. Methods are provided for normalization of
10759 cell-specific biases, assignment of cell cycle phase, and detection of highly
10760 variable and significantly correlated genes.")
10761 (license license:gpl3)))
10763 (define-public r-delayedmatrixstats
10765 (name "r-delayedmatrixstats")
10770 (uri (bioconductor-uri "DelayedMatrixStats" version))
10773 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10775 `((upstream-name . "DelayedMatrixStats")))
10776 (build-system r-build-system)
10778 `(("r-delayedarray" ,r-delayedarray)
10779 ("r-iranges" ,r-iranges)
10780 ("r-matrix" ,r-matrix)
10781 ("r-matrixstats" ,r-matrixstats)
10782 ("r-s4vectors" ,r-s4vectors)))
10783 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10784 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10786 "This package provides a port of the @code{matrixStats} API for use with
10787 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10788 contains high-performing functions operating on rows and columns of
10789 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10790 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10791 are optimized per data type and for subsetted calculations such that both
10792 memory usage and processing time is minimized.")
10793 (license license:expat)))
10795 (define-public r-dropbead
10796 (let ((commit "cf0be5ae5302684bd03e78ab65b142900bbbb840")
10799 (name "r-dropbead")
10800 (version (string-append "0-" revision "." (string-take commit 7)))
10804 (uri (git-reference
10805 (url "https://github.com/rajewsky-lab/dropbead.git")
10809 "1b2lphsc236s1rdzlijxg8yl1jnqpwcvj4x938r89rqpj93jb780"))))
10810 (build-system r-build-system)
10812 `(("r-ggplot2" ,r-ggplot2)
10813 ("r-rcolorbrewer" ,r-rcolorbrewer)
10814 ("r-gridextra" ,r-gridextra)
10815 ("r-gplots" ,r-gplots)
10816 ("r-plyr" ,r-plyr)))
10817 (home-page "https://github.com/rajewsky-lab/dropbead")
10818 (synopsis "Basic exploration and analysis of Drop-seq data")
10819 (description "This package offers a quick and straight-forward way to
10820 explore and perform basic analysis of single cell sequencing data coming from
10821 droplet sequencing. It has been particularly tailored for Drop-seq.")
10822 (license license:gpl3))))
10824 (define htslib-for-sambamba
10825 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10828 (name "htslib-for-sambamba")
10829 (version (string-append "1.3.1-1." (string-take commit 9)))
10833 (uri (git-reference
10834 (url "https://github.com/lomereiter/htslib.git")
10836 (file-name (string-append "htslib-" version "-checkout"))
10839 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10841 (substitute-keyword-arguments (package-arguments htslib)
10843 `(modify-phases ,phases
10844 (add-after 'unpack 'bootstrap
10846 (zero? (system* "autoreconf" "-vif"))))))))
10848 `(("autoconf" ,autoconf)
10849 ("automake" ,automake)
10850 ,@(package-native-inputs htslib))))))
10852 (define-public sambamba
10859 (uri (string-append "https://github.com/lomereiter/sambamba/"
10860 "archive/v" version ".tar.gz"))
10861 (file-name (string-append name "-" version ".tar.gz"))
10864 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10865 (build-system gnu-build-system)
10867 `(#:tests? #f ; there is no test target
10869 '("D_COMPILER=ldc2"
10870 ;; Override "--compiler" flag only.
10871 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10872 "sambamba-ldmd2-64")
10874 (modify-phases %standard-phases
10875 (delete 'configure)
10876 (add-after 'unpack 'place-biod
10877 (lambda* (#:key inputs #:allow-other-keys)
10878 (copy-recursively (assoc-ref inputs "biod") "BioD")
10880 (add-after 'unpack 'unbundle-prerequisites
10882 (substitute* "Makefile"
10883 ((" htslib-static lz4-static") ""))
10886 (lambda* (#:key outputs #:allow-other-keys)
10887 (let* ((out (assoc-ref outputs "out"))
10888 (bin (string-append out "/bin")))
10890 (install-file "build/sambamba" bin)
10896 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10899 (uri (git-reference
10900 (url "https://github.com/biod/BioD.git")
10902 (file-name (string-append "biod-"
10903 (string-take commit 9)
10907 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10910 ("htslib" ,htslib-for-sambamba)))
10911 (home-page "http://lomereiter.github.io/sambamba")
10912 (synopsis "Tools for working with SAM/BAM data")
10913 (description "Sambamba is a high performance modern robust and
10914 fast tool (and library), written in the D programming language, for
10915 working with SAM and BAM files. Current parallelised functionality is
10916 an important subset of samtools functionality, including view, index,
10917 sort, markdup, and depth.")
10918 (license license:gpl2+)))
10920 (define-public ritornello
10922 (name "ritornello")
10926 (uri (string-append "https://github.com/KlugerLab/"
10927 "Ritornello/archive/v"
10928 version ".tar.gz"))
10929 (file-name (string-append name "-" version ".tar.gz"))
10932 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10933 (build-system gnu-build-system)
10935 `(#:tests? #f ; there are no tests
10937 (modify-phases %standard-phases
10938 (add-after 'unpack 'patch-samtools-references
10939 (lambda* (#:key inputs #:allow-other-keys)
10940 (substitute* '("src/SamStream.h"
10941 "src/BufferedGenomeReader.h")
10942 (("<sam.h>") "<samtools/sam.h>"))
10944 (delete 'configure)
10946 (lambda* (#:key inputs outputs #:allow-other-keys)
10947 (let* ((out (assoc-ref outputs "out"))
10948 (bin (string-append out "/bin/")))
10950 (install-file "bin/Ritornello" bin)
10953 `(("samtools" ,samtools-0.1)
10957 (home-page "https://github.com/KlugerLab/Ritornello")
10958 (synopsis "Control-free peak caller for ChIP-seq data")
10959 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10960 signal processing that can accurately call binding events without the need to
10961 do a pair total DNA input or IgG control sample. It has been tested for use
10962 with narrow binding events such as transcription factor ChIP-seq.")
10963 (license license:gpl3+)))
10965 (define-public trim-galore
10967 (name "trim-galore")
10972 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10973 "projects/trim_galore/trim_galore_v"
10977 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10978 (build-system gnu-build-system)
10980 `(#:tests? #f ; no tests
10982 (modify-phases %standard-phases
10983 ;; The archive contains plain files.
10985 (lambda* (#:key source #:allow-other-keys)
10986 (zero? (system* "unzip" source))))
10987 (delete 'configure)
10989 (add-after 'unpack 'hardcode-tool-references
10990 (lambda* (#:key inputs #:allow-other-keys)
10991 (substitute* "trim_galore"
10992 (("\\$path_to_cutadapt = 'cutadapt'")
10993 (string-append "$path_to_cutadapt = '"
10994 (assoc-ref inputs "cutadapt")
10997 (string-append "| "
10998 (assoc-ref inputs "gzip")
11001 (string-append "\""
11002 (assoc-ref inputs "gzip")
11006 (lambda* (#:key outputs #:allow-other-keys)
11007 (let ((bin (string-append (assoc-ref outputs "out")
11010 (install-file "trim_galore" bin)
11015 ("cutadapt" ,cutadapt)))
11017 `(("unzip" ,unzip)))
11018 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11019 (synopsis "Wrapper around Cutadapt and FastQC")
11020 (description "Trim Galore! is a wrapper script to automate quality and
11021 adapter trimming as well as quality control, with some added functionality to
11022 remove biased methylation positions for RRBS sequence files.")
11023 (license license:gpl3+)))
11025 (define-public gess
11031 (uri (string-append "http://compbio.uthscsa.edu/"
11033 "gess-" version ".src.tar.gz"))
11036 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11037 (build-system gnu-build-system)
11039 `(#:tests? #f ; no tests
11041 (modify-phases %standard-phases
11042 (delete 'configure)
11045 (lambda* (#:key inputs outputs #:allow-other-keys)
11046 (let* ((python (assoc-ref inputs "python"))
11047 (out (assoc-ref outputs "out"))
11048 (bin (string-append out "/bin/"))
11049 (target (string-append
11050 out "/lib/python2.7/site-packages/gess/")))
11052 (copy-recursively "." target)
11053 ;; Make GESS.py executable
11054 (chmod (string-append target "GESS.py") #o555)
11055 ;; Add Python shebang to the top and make Matplotlib
11057 (substitute* (string-append target "GESS.py")
11058 (("\"\"\"Description:" line)
11059 (string-append "#!" (which "python") "
11061 matplotlib.use('Agg')
11063 ;; Make sure GESS has all modules in its path
11064 (wrap-program (string-append target "GESS.py")
11065 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11067 (symlink (string-append target "GESS.py")
11068 (string-append bin "GESS.py"))
11071 `(("python" ,python-2)
11072 ("python2-pysam" ,python2-pysam)
11073 ("python2-scipy" ,python2-scipy)
11074 ("python2-numpy" ,python2-numpy)
11075 ("python2-networkx" ,python2-networkx)
11076 ("python2-biopython" ,python2-biopython)))
11077 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11078 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11080 "GESS is an implementation of a novel computational method to detect de
11081 novo exon-skipping events directly from raw RNA-seq data without the prior
11082 knowledge of gene annotation information. GESS stands for the graph-based
11083 exon-skipping scanner detection scheme.")
11084 (license license:bsd-3)))
11086 (define-public phylip
11093 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11094 "download/phylip-" version ".tar.gz"))
11097 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11098 (build-system gnu-build-system)
11100 `(#:tests? #f ; no check target
11101 #:make-flags (list "-f" "Makefile.unx" "install")
11102 #:parallel-build? #f ; not supported
11104 (modify-phases %standard-phases
11105 (add-after 'unpack 'enter-dir
11106 (lambda _ (chdir "src") #t))
11107 (delete 'configure)
11109 (lambda* (#:key inputs outputs #:allow-other-keys)
11110 (let ((target (string-append (assoc-ref outputs "out")
11113 (for-each (lambda (file)
11114 (install-file file target))
11115 (find-files "../exe" ".*")))
11117 (home-page "http://evolution.genetics.washington.edu/phylip/")
11118 (synopsis "Tools for inferring phylogenies")
11119 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11120 programs for inferring phylogenies (evolutionary trees).")
11121 (license license:bsd-2)))
11130 (uri (string-append "https://integrativemodeling.org/"
11131 version "/download/imp-" version ".tar.gz"))
11134 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11135 (build-system cmake-build-system)
11137 `(;; FIXME: Some tests fail because they produce warnings, others fail
11138 ;; because the PYTHONPATH does not include the modeller's directory.
11146 ("python" ,python-2)))
11148 `(("python2-numpy" ,python2-numpy)
11149 ("python2-scipy" ,python2-scipy)
11150 ("python2-pandas" ,python2-pandas)
11151 ("python2-scikit-learn" ,python2-scikit-learn)
11152 ("python2-networkx" ,python2-networkx)))
11153 (home-page "https://integrativemodeling.org")
11154 (synopsis "Integrative modeling platform")
11155 (description "IMP's broad goal is to contribute to a comprehensive
11156 structural characterization of biomolecules ranging in size and complexity
11157 from small peptides to large macromolecular assemblies, by integrating data
11158 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11159 Python toolbox for solving complex modeling problems, and a number of
11160 applications for tackling some common problems in a user-friendly way.")
11161 ;; IMP is largely available under the GNU Lesser GPL; see the file
11162 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11163 ;; available under the GNU GPL (see the file COPYING.GPL).
11164 (license (list license:lgpl2.1+
11167 (define-public tadbit
11173 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11174 "archive/v" version ".tar.gz"))
11175 (file-name (string-append name "-" version ".tar.gz"))
11178 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11179 (build-system python-build-system)
11181 `(;; Tests are included and must be run after installation, but
11182 ;; they are incomplete and thus cannot be run.
11186 (modify-phases %standard-phases
11187 (add-after 'unpack 'fix-problems-with-setup.py
11188 (lambda* (#:key outputs #:allow-other-keys)
11189 ;; setup.py opens these files for writing
11190 (chmod "_pytadbit/_version.py" #o664)
11191 (chmod "README.rst" #o664)
11193 ;; Don't attempt to install the bash completions to
11194 ;; the home directory.
11195 (rename-file "extras/.bash_completion"
11197 (substitute* "setup.py"
11198 (("\\(path.expanduser\\('~'\\)")
11199 (string-append "(\""
11200 (assoc-ref outputs "out")
11201 "/etc/bash_completion.d\""))
11202 (("extras/\\.bash_completion")
11206 ;; TODO: add Chimera for visualization
11209 ("python2-scipy" ,python2-scipy)
11210 ("python2-numpy" ,python2-numpy)
11211 ("python2-matplotlib" ,python2-matplotlib)
11212 ("python2-pysam" ,python2-pysam)))
11213 (home-page "http://3dgenomes.github.io/TADbit/")
11214 (synopsis "Analyze, model, and explore 3C-based data")
11216 "TADbit is a complete Python library to deal with all steps to analyze,
11217 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11218 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11219 correct interaction matrices, identify and compare the so-called
11220 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11221 interaction matrices, and finally, extract structural properties from the
11222 models. TADbit is complemented by TADkit for visualizing 3D models.")
11223 (license license:gpl3+)))
11225 (define-public kentutils
11228 ;; 302.1.0 is out, but the only difference is the inclusion of
11229 ;; pre-built binaries.
11230 (version "302.0.0")
11234 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11235 "archive/v" version ".tar.gz"))
11236 (file-name (string-append name "-" version ".tar.gz"))
11239 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11240 (modules '((guix build utils)
11245 ;; Only the contents of the specified directories are free
11246 ;; for all uses, so we remove the rest. "hg/autoSql" and
11247 ;; "hg/autoXml" are nominally free, but they depend on a
11248 ;; library that is built from the sources in "hg/lib",
11249 ;; which is nonfree.
11250 (let ((free (list "." ".."
11251 "utils" "lib" "inc" "tagStorm"
11252 "parasol" "htslib"))
11253 (directory? (lambda (file)
11254 (eq? 'directory (stat:type (stat file))))))
11255 (for-each (lambda (file)
11256 (and (directory? file)
11257 (delete-file-recursively file)))
11258 (map (cut string-append "src/" <>)
11261 (not (member file free)))))))
11262 ;; Only make the utils target, not the userApps target,
11263 ;; because that requires libraries we won't build.
11264 (substitute* "Makefile"
11265 ((" userApps") " utils"))
11266 ;; Only build libraries that are free.
11267 (substitute* "src/makefile"
11268 (("DIRS =.*") "DIRS =\n")
11269 (("cd jkOwnLib.*") "")
11272 (substitute* "src/utils/makefile"
11273 ;; These tools depend on "jkhgap.a", which is part of the
11274 ;; nonfree "src/hg/lib" directory.
11275 (("raSqlQuery") "")
11276 (("pslLiftSubrangeBlat") "")
11278 ;; Do not build UCSC tools, which may require nonfree
11280 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11282 (build-system gnu-build-system)
11284 `( ;; There is no global test target and the test target for
11285 ;; individual tools depends on input files that are not
11289 (modify-phases %standard-phases
11290 (add-after 'unpack 'fix-paths
11292 (substitute* "Makefile"
11293 (("/bin/echo") (which "echo")))
11295 (add-after 'unpack 'prepare-samtabix
11296 (lambda* (#:key inputs #:allow-other-keys)
11297 (copy-recursively (assoc-ref inputs "samtabix")
11300 (delete 'configure)
11302 (lambda* (#:key outputs #:allow-other-keys)
11303 (let ((bin (string-append (assoc-ref outputs "out")
11305 (copy-recursively "bin" bin))
11311 (uri (git-reference
11312 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11313 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11316 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11323 ("openssl" ,openssl)))
11324 (home-page "http://genome.cse.ucsc.edu/index.html")
11325 (synopsis "Assorted bioinformatics utilities")
11326 (description "This package provides the kentUtils, a selection of
11327 bioinformatics utilities used in combination with the UCSC genome
11329 ;; Only a subset of the sources are released under a non-copyleft
11330 ;; free software license. All other sources are removed in a
11331 ;; snippet. See this bug report for an explanation of how the
11332 ;; license statements apply:
11333 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11334 (license (license:non-copyleft
11335 "http://genome.ucsc.edu/license/"
11336 "The contents of this package are free for all uses."))))
11338 (define-public f-seq
11339 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11343 (version (string-append "1.1-" revision "." (string-take commit 7)))
11346 (uri (git-reference
11347 (url "https://github.com/aboyle/F-seq.git")
11349 (file-name (string-append name "-" version))
11352 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11353 (modules '((guix build utils)))
11354 ;; Remove bundled Java library archives.
11357 (for-each delete-file (find-files "lib" ".*"))
11359 (build-system ant-build-system)
11361 `(#:tests? #f ; no tests included
11363 (modify-phases %standard-phases
11365 (lambda* (#:key inputs outputs #:allow-other-keys)
11366 (let* ((target (assoc-ref outputs "out"))
11367 (doc (string-append target "/share/doc/f-seq/")))
11370 (substitute* "bin/linux/fseq"
11371 (("java") (which "java"))
11372 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11373 (string-append (assoc-ref inputs "java-commons-cli")
11374 "/share/java/commons-cli.jar"))
11376 (string-append "REALDIR=" target "/bin\n")))
11377 (install-file "README.txt" doc)
11378 (install-file "bin/linux/fseq" (string-append target "/bin"))
11379 (install-file "build~/fseq.jar" (string-append target "/lib"))
11380 (copy-recursively "lib" (string-append target "/lib"))
11384 ("java-commons-cli" ,java-commons-cli)))
11385 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11386 (synopsis "Feature density estimator for high-throughput sequence tags")
11388 "F-Seq is a software package that generates a continuous tag sequence
11389 density estimation allowing identification of biologically meaningful sites
11390 such as transcription factor binding sites (ChIP-seq) or regions of open
11391 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11393 (license license:gpl3+))))
11395 (define-public bismark
11402 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11403 "archive/" version ".tar.gz"))
11404 (file-name (string-append name "-" version ".tar.gz"))
11407 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11408 (build-system perl-build-system)
11410 `(#:tests? #f ; there are no tests
11412 (modify-phases %standard-phases
11413 (delete 'configure)
11416 (lambda* (#:key outputs #:allow-other-keys)
11417 (let ((bin (string-append (assoc-ref outputs "out")
11419 (docdir (string-append (assoc-ref outputs "out")
11420 "/share/doc/bismark"))
11421 (docs '("Bismark_User_Guide.pdf"
11422 "RELEASE_NOTES.txt"))
11423 (scripts '("bismark"
11424 "bismark_genome_preparation"
11425 "bismark_methylation_extractor"
11428 "coverage2cytosine"
11429 "deduplicate_bismark"
11430 "bismark_sitrep.tpl"
11432 "bismark2summary")))
11435 (for-each (lambda (file) (install-file file bin))
11437 (for-each (lambda (file) (install-file file docdir))
11440 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11441 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11442 (description "Bismark is a program to map bisulfite treated sequencing
11443 reads to a genome of interest and perform methylation calls in a single step.
11444 The output can be easily imported into a genome viewer, such as SeqMonk, and
11445 enables a researcher to analyse the methylation levels of their samples
11446 straight away. Its main features are:
11449 @item Bisulfite mapping and methylation calling in one single step
11450 @item Supports single-end and paired-end read alignments
11451 @item Supports ungapped and gapped alignments
11452 @item Alignment seed length, number of mismatches etc are adjustable
11453 @item Output discriminates between cytosine methylation in CpG, CHG
11456 (license license:gpl3+)))
11458 (define-public paml
11464 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11465 "paml" version ".tgz"))
11468 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11469 (modules '((guix build utils)))
11470 ;; Remove Windows binaries
11473 (for-each delete-file (find-files "." "\\.exe$"))
11475 (build-system gnu-build-system)
11477 `(#:tests? #f ; there are no tests
11478 #:make-flags '("CC=gcc")
11480 (modify-phases %standard-phases
11481 (replace 'configure
11483 (substitute* "src/BFdriver.c"
11484 (("/bin/bash") (which "bash")))
11488 (lambda* (#:key outputs #:allow-other-keys)
11489 (let ((tools '("baseml" "basemlg" "codeml"
11490 "pamp" "evolver" "yn00" "chi2"))
11491 (bin (string-append (assoc-ref outputs "out") "/bin"))
11492 (docdir (string-append (assoc-ref outputs "out")
11493 "/share/doc/paml")))
11495 (for-each (lambda (file) (install-file file bin)) tools)
11496 (copy-recursively "../doc" docdir)
11498 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11499 (synopsis "Phylogentic analysis by maximum likelihood")
11500 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11501 contains a few programs for model fitting and phylogenetic tree reconstruction
11502 using nucleotide or amino-acid sequence data.")
11504 (license license:gpl3)))
11506 (define-public kallisto
11512 (uri (string-append "https://github.com/pachterlab/"
11513 "kallisto/archive/v" version ".tar.gz"))
11514 (file-name (string-append name "-" version ".tar.gz"))
11517 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11518 (build-system cmake-build-system)
11519 (arguments `(#:tests? #f)) ; no "check" target
11523 (home-page "http://pachterlab.github.io/kallisto/")
11524 (synopsis "Near-optimal RNA-Seq quantification")
11526 "Kallisto is a program for quantifying abundances of transcripts from
11527 RNA-Seq data, or more generally of target sequences using high-throughput
11528 sequencing reads. It is based on the novel idea of pseudoalignment for
11529 rapidly determining the compatibility of reads with targets, without the need
11530 for alignment. Pseudoalignment of reads preserves the key information needed
11531 for quantification, and kallisto is therefore not only fast, but also as
11532 accurate as existing quantification tools.")
11533 (license license:bsd-2)))
11535 (define-public libgff
11541 (uri (string-append
11542 "https://github.com/Kingsford-Group/"
11543 "libgff/archive/v" version ".tar.gz"))
11544 (file-name (string-append name "-" version ".tar.gz"))
11547 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11548 (build-system cmake-build-system)
11549 (arguments `(#:tests? #f)) ; no tests included
11550 (home-page "https://github.com/Kingsford-Group/libgff")
11551 (synopsis "Parser library for reading/writing GFF files")
11552 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11553 code that is used in the Cufflinks codebase. The goal of this library is to
11554 provide this functionality without the necessity of drawing in a heavy-weight
11555 dependency like SeqAn.")
11556 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11558 (define-public libdivsufsort
11560 (name "libdivsufsort")
11564 (uri (git-reference
11565 (url "https://github.com/y-256/libdivsufsort.git")
11569 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11570 (build-system cmake-build-system)
11572 '(#:tests? #f ; there are no tests
11574 ;; Needed for rapmap and sailfish.
11575 '("-DBUILD_DIVSUFSORT64=ON")))
11576 (home-page "https://github.com/y-256/libdivsufsort")
11577 (synopsis "Lightweight suffix-sorting library")
11578 (description "libdivsufsort is a software library that implements a
11579 lightweight suffix array construction algorithm. This library provides a
11580 simple and an efficient C API to construct a suffix array and a
11581 Burrows-Wheeler transformed string from a given string over a constant-size
11582 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11583 bytes of memory space, where n is the length of the string.")
11584 (license license:expat)))
11586 (define-public sailfish
11593 (string-append "https://github.com/kingsfordgroup/"
11594 "sailfish/archive/v" version ".tar.gz"))
11595 (file-name (string-append name "-" version ".tar.gz"))
11598 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11599 (modules '((guix build utils)))
11602 ;; Delete bundled headers for eigen3.
11603 (delete-file-recursively "include/eigen3/")
11605 (build-system cmake-build-system)
11607 `(#:configure-flags
11608 (list (string-append "-DBOOST_INCLUDEDIR="
11609 (assoc-ref %build-inputs "boost")
11611 (string-append "-DBOOST_LIBRARYDIR="
11612 (assoc-ref %build-inputs "boost")
11614 (string-append "-DBoost_LIBRARIES="
11615 "-lboost_iostreams "
11616 "-lboost_filesystem "
11621 "-lboost_program_options")
11622 "-DBoost_FOUND=TRUE"
11623 ;; Don't download RapMap---we already have it!
11624 "-DFETCHED_RAPMAP=1")
11625 ;; Tests must be run after installation and the location of the test
11626 ;; data file must be overridden. But the tests fail. It looks like
11627 ;; they are not really meant to be run.
11630 (modify-phases %standard-phases
11631 ;; Boost cannot be found, even though it's right there.
11632 (add-after 'unpack 'do-not-look-for-boost
11633 (lambda* (#:key inputs #:allow-other-keys)
11634 (substitute* "CMakeLists.txt"
11635 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11636 (add-after 'unpack 'do-not-assign-to-macro
11638 (substitute* "include/spdlog/details/format.cc"
11639 (("const unsigned CHAR_WIDTH = 1;") ""))))
11640 (add-after 'unpack 'prepare-rapmap
11641 (lambda* (#:key inputs #:allow-other-keys)
11642 (let ((src "external/install/src/rapmap/")
11643 (include "external/install/include/rapmap/")
11644 (rapmap (assoc-ref inputs "rapmap")))
11645 (mkdir-p "/tmp/rapmap")
11646 (system* "tar" "xf"
11647 (assoc-ref inputs "rapmap")
11649 "--strip-components=1")
11652 (for-each (lambda (file)
11653 (install-file file src))
11654 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11655 (copy-recursively "/tmp/rapmap/include" include))))
11656 (add-after 'unpack 'use-system-libraries
11657 (lambda* (#:key inputs #:allow-other-keys)
11658 (substitute* '("src/SailfishIndexer.cpp"
11659 "src/SailfishUtils.cpp"
11660 "src/SailfishQuantify.cpp"
11661 "src/FASTAParser.cpp"
11663 "include/SailfishUtils.hpp"
11664 "include/SailfishIndex.hpp"
11665 "include/CollapsedEMOptimizer.hpp"
11666 "src/CollapsedEMOptimizer.cpp")
11667 (("#include \"jellyfish/config.h\"") ""))
11668 (substitute* "src/CMakeLists.txt"
11669 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11670 (string-append (assoc-ref inputs "jellyfish")
11671 "/include/jellyfish-" ,(package-version jellyfish)))
11672 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11673 (string-append (assoc-ref inputs "jellyfish")
11674 "/lib/libjellyfish-2.0.a"))
11675 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11676 (string-append (assoc-ref inputs "libdivsufsort")
11677 "/lib/libdivsufsort.so"))
11678 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11679 (string-append (assoc-ref inputs "libdivsufsort")
11680 "/lib/libdivsufsort64.so")))
11681 (substitute* "CMakeLists.txt"
11682 ;; Don't prefer static libs
11683 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11684 (("find_package\\(Jellyfish.*") "")
11685 (("ExternalProject_Add\\(libjellyfish") "message(")
11686 (("ExternalProject_Add\\(libgff") "message(")
11687 (("ExternalProject_Add\\(libsparsehash") "message(")
11688 (("ExternalProject_Add\\(libdivsufsort") "message("))
11690 ;; Ensure that Eigen headers can be found
11691 (setenv "CPLUS_INCLUDE_PATH"
11692 (string-append (getenv "CPLUS_INCLUDE_PATH")
11694 (assoc-ref inputs "eigen")
11695 "/include/eigen3")))))))
11699 ("jemalloc" ,jemalloc)
11700 ("jellyfish" ,jellyfish)
11701 ("sparsehash" ,sparsehash)
11704 (uri (git-reference
11705 (url "https://github.com/COMBINE-lab/RapMap.git")
11706 (commit (string-append "sf-v" version))))
11707 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11710 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11711 (modules '((guix build utils)))
11712 ;; These files are expected to be excluded.
11714 '(begin (delete-file-recursively "include/spdlog")
11715 (for-each delete-file '("include/xxhash.h"
11716 "src/xxhash.c"))))))
11717 ("libdivsufsort" ,libdivsufsort)
11722 `(("pkg-config" ,pkg-config)))
11723 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11724 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11725 (description "Sailfish is a tool for genomic transcript quantification
11726 from RNA-seq data. It requires a set of target transcripts (either from a
11727 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11728 fasta file containing your reference transcripts and a (set of) fasta/fastq
11729 file(s) containing your reads.")
11730 (license license:gpl3+)))
11732 (define libstadenio-for-salmon
11734 (name "libstadenio")
11738 (uri (git-reference
11739 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11740 (commit (string-append "v" version))))
11741 (file-name (string-append name "-" version "-checkout"))
11744 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11745 (build-system gnu-build-system)
11746 (arguments '(#:parallel-tests? #f)) ; not supported
11750 `(("perl" ,perl))) ; for tests
11751 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11752 (synopsis "General purpose trace and experiment file library")
11753 (description "This package provides a library of file reading and writing
11754 code to provide a general purpose Trace file (and Experiment File) reading
11757 The following file formats are supported:
11760 @item SCF trace files
11761 @item ABI trace files
11762 @item ALF trace files
11763 @item ZTR trace files
11764 @item SFF trace archives
11765 @item SRF trace archives
11766 @item Experiment files
11767 @item Plain text files
11768 @item SAM/BAM sequence files
11769 @item CRAM sequence files
11771 (license license:bsd-3)))
11773 (define spdlog-for-salmon
11779 (uri (git-reference
11780 (url "https://github.com/COMBINE-lab/spdlog.git")
11781 (commit (string-append "v" version))))
11782 (file-name (string-append name "-" version "-checkout"))
11785 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11786 (build-system cmake-build-system)
11787 (home-page "https://github.com/COMBINE-lab/spdlog")
11788 (synopsis "Very fast C++ logging library")
11789 (description "Spdlog is a very fast header-only C++ logging library with
11790 performance as its primary goal.")
11791 (license license:expat)))
11793 ;; This is a modified variant of bwa for use with Salmon. It installs a
11794 ;; library to avoid having to build this as part of Salmon.
11795 (define bwa-for-salmon
11796 (package (inherit bwa)
11798 (version "0.7.12.5")
11801 (uri (git-reference
11802 (url "https://github.com/COMBINE-lab/bwa.git")
11803 (commit (string-append "v" version))))
11804 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11807 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11808 (build-system gnu-build-system)
11810 '(#:tests? #f ;no "check" target
11812 (modify-phases %standard-phases
11814 (lambda* (#:key outputs #:allow-other-keys)
11815 (let* ((out (assoc-ref outputs "out"))
11816 (bin (string-append out "/bin"))
11817 (lib (string-append out "/lib"))
11818 (doc (string-append out "/share/doc/bwa"))
11819 (man (string-append out "/share/man/man1"))
11820 (inc (string-append out "/include/bwa")))
11821 (install-file "bwa" bin)
11822 (install-file "README.md" doc)
11823 (install-file "bwa.1" man)
11824 (install-file "libbwa.a" lib)
11827 (for-each (lambda (file)
11828 (install-file file inc))
11829 (find-files "." "\\.h$")))
11831 ;; no "configure" script
11832 (delete 'configure))))))
11834 (define-public salmon
11840 (uri (git-reference
11841 (url "https://github.com/COMBINE-lab/salmon.git")
11842 (commit (string-append "v" version))))
11843 (file-name (string-append name "-" version "-checkout"))
11846 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11847 (modules '((guix build utils)))
11850 ;; Delete bundled headers for eigen3.
11851 (delete-file-recursively "include/eigen3/")
11853 (build-system cmake-build-system)
11855 `(#:configure-flags
11856 (list (string-append "-DBOOST_INCLUDEDIR="
11857 (assoc-ref %build-inputs "boost")
11859 (string-append "-DBOOST_LIBRARYDIR="
11860 (assoc-ref %build-inputs "boost")
11862 (string-append "-DBoost_LIBRARIES="
11863 "-lboost_iostreams "
11864 "-lboost_filesystem "
11869 "-lboost_program_options")
11870 "-DBoost_FOUND=TRUE"
11871 "-DTBB_LIBRARIES=tbb tbbmalloc"
11872 ;; Don't download RapMap---we already have it!
11873 "-DFETCHED_RAPMAP=1")
11875 (modify-phases %standard-phases
11876 ;; Boost cannot be found, even though it's right there.
11877 (add-after 'unpack 'do-not-look-for-boost
11878 (lambda* (#:key inputs #:allow-other-keys)
11879 (substitute* "CMakeLists.txt"
11880 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11881 (add-after 'unpack 'do-not-phone-home
11883 (substitute* "src/Salmon.cpp"
11884 (("getVersionMessage\\(\\)") "\"\""))))
11885 (add-after 'unpack 'prepare-rapmap
11886 (lambda* (#:key inputs #:allow-other-keys)
11887 (let ((src "external/install/src/rapmap/")
11888 (include "external/install/include/rapmap/")
11889 (rapmap (assoc-ref inputs "rapmap")))
11892 (for-each (lambda (file)
11893 (install-file file src))
11894 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11895 (copy-recursively (string-append rapmap "/include") include)
11896 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11897 "external/install/include/rapmap/FastxParser.hpp"
11898 "external/install/include/rapmap/concurrentqueue.h"
11899 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11900 "external/install/src/rapmap/FastxParser.cpp"
11901 "external/install/src/rapmap/xxhash.c")))))
11902 (add-after 'unpack 'use-system-libraries
11903 (lambda* (#:key inputs #:allow-other-keys)
11904 (substitute* "src/CMakeLists.txt"
11905 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11906 (string-append (assoc-ref inputs "jellyfish")
11907 "/include/jellyfish-" ,(package-version jellyfish)))
11908 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11909 (string-append (assoc-ref inputs "jellyfish")
11910 "/lib/libjellyfish-2.0.a"))
11911 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11912 (string-append (assoc-ref inputs "libdivsufsort")
11913 "/lib/libdivsufsort.so"))
11914 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11915 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11916 "/lib/libstaden-read.a"))
11917 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
11918 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
11919 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11920 (string-append (assoc-ref inputs "libdivsufsort")
11921 "/lib/libdivsufsort64.so")))
11922 (substitute* "CMakeLists.txt"
11923 ;; Don't prefer static libs
11924 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11925 (("set\\(TBB_LIBRARIES") "message(")
11926 (("find_package\\(Jellyfish.*") "")
11927 (("ExternalProject_Add\\(libcereal") "message(")
11928 (("ExternalProject_Add\\(libbwa") "message(")
11929 (("ExternalProject_Add\\(libjellyfish") "message(")
11930 (("ExternalProject_Add\\(libgff") "message(")
11931 (("ExternalProject_Add\\(libtbb") "message(")
11932 (("ExternalProject_Add\\(libspdlog") "message(")
11933 (("ExternalProject_Add\\(libdivsufsort") "message(")
11934 (("ExternalProject_Add\\(libstadenio") "message(")
11935 (("ExternalProject_Add_Step\\(") "message("))
11937 ;; Ensure that all headers can be found
11938 (setenv "CPLUS_INCLUDE_PATH"
11939 (string-append (getenv "CPLUS_INCLUDE_PATH")
11941 (assoc-ref inputs "bwa")
11944 (assoc-ref inputs "eigen")
11945 "/include/eigen3"))
11947 (string-append (assoc-ref inputs "bwa")
11950 (assoc-ref inputs "eigen")
11951 "/include/eigen3"))
11953 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11954 ;; run. It only exists after the install phase.
11955 (add-after 'unpack 'fix-tests
11957 (substitute* "src/CMakeLists.txt"
11958 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11959 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11963 ("bwa" ,bwa-for-salmon)
11969 (uri (git-reference
11970 (url "https://github.com/COMBINE-lab/RapMap.git")
11971 (commit (string-append "salmon-v" version))))
11972 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11975 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
11976 ("jemalloc" ,jemalloc)
11977 ("jellyfish" ,jellyfish)
11980 ("libdivsufsort" ,libdivsufsort)
11981 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11982 ("spdlog-for-salmon" ,spdlog-for-salmon)
11985 (home-page "https://github.com/COMBINE-lab/salmon")
11986 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11987 (description "Salmon is a program to produce highly-accurate,
11988 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11989 its accuracy and speed via a number of different innovations, including the
11990 use of lightweight alignments (accurate but fast-to-compute proxies for
11991 traditional read alignments) and massively-parallel stochastic collapsed
11992 variational inference.")
11993 (license license:gpl3+)))
11995 (define-public python-loompy
11997 (name "python-loompy")
12002 (uri (pypi-uri "loompy" version))
12005 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12006 (build-system python-build-system)
12007 ;; There are no tests
12008 (arguments '(#:tests? #f))
12010 `(("python-h5py" ,python-h5py)
12011 ("python-numpy" ,python-numpy)
12012 ("python-scipy" ,python-scipy)
12013 ("python-typing" ,python-typing)))
12014 (home-page "https://github.com/linnarsson-lab/loompy")
12015 (synopsis "Work with .loom files for single-cell RNA-seq data")
12016 (description "The loom file format is an efficient format for very large
12017 omics datasets, consisting of a main matrix, optional additional layers, a
12018 variable number of row and column annotations. Loom also supports sparse
12019 graphs. This library makes it easy to work with @file{.loom} files for
12020 single-cell RNA-seq data.")
12021 (license license:bsd-3)))
12023 ;; We cannot use the latest commit because it requires Java 9.
12024 (define-public java-forester
12025 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12028 (name "java-forester")
12029 (version (string-append "0-" revision "." (string-take commit 7)))
12032 (uri (git-reference
12033 (url "https://github.com/cmzmasek/forester.git")
12035 (file-name (string-append name "-" version "-checkout"))
12038 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12039 (modules '((guix build utils)))
12042 ;; Delete bundled jars and pre-built classes
12043 (delete-file-recursively "forester/java/resources")
12044 (delete-file-recursively "forester/java/classes")
12045 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12046 ;; Delete bundled applications
12047 (delete-file-recursively "forester_applications")
12049 (build-system ant-build-system)
12051 `(#:tests? #f ; there are none
12053 #:modules ((guix build ant-build-system)
12055 (guix build java-utils)
12059 (modify-phases %standard-phases
12060 (add-after 'unpack 'chdir
12061 (lambda _ (chdir "forester/java") #t))
12062 (add-after 'chdir 'fix-dependencies
12064 (chmod "build.xml" #o664)
12065 (call-with-output-file "build.xml.new"
12069 (with-input-from-file "build.xml"
12070 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12071 `(;; Remove all unjar tags to avoid repacking classes.
12072 (unjar . ,(lambda _ '()))
12073 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12074 (*text* . ,(lambda (_ txt) txt))))
12076 (rename-file "build.xml.new" "build.xml")
12078 ;; FIXME: itext is difficult to package as it depends on a few
12079 ;; unpackaged libraries.
12080 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12082 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12083 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12084 (("pdf_written_to = PdfExporter.*")
12085 "throw new IOException(\"PDF export is not available.\");"))
12087 ;; There is no install target
12088 (replace 'install (install-jars ".")))))
12090 `(("java-commons-codec" ,java-commons-codec)
12091 ("java-openchart2" ,java-openchart2)))
12092 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12093 (synopsis "Phylogenomics libraries for Java")
12094 (description "Forester is a collection of Java libraries for
12095 phylogenomics and evolutionary biology research. It includes support for
12096 reading, writing, and exporting phylogenetic trees.")
12097 (license license:lgpl2.1+))))
12099 (define-public java-forester-1.005
12101 (name "java-forester")
12105 (uri (string-append "http://search.maven.org/remotecontent?"
12106 "filepath=org/biojava/thirdparty/forester/"
12107 version "/forester-" version "-sources.jar"))
12108 (file-name (string-append name "-" version ".jar"))
12111 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12112 (build-system ant-build-system)
12114 `(#:tests? #f ; there are none
12116 #:modules ((guix build ant-build-system)
12118 (guix build java-utils)
12122 (modify-phases %standard-phases
12123 (add-after 'unpack 'fix-dependencies
12124 (lambda* (#:key inputs #:allow-other-keys)
12125 (call-with-output-file "build.xml"
12129 (with-input-from-file "src/build.xml"
12130 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12131 `(;; Remove all unjar tags to avoid repacking classes.
12132 (unjar . ,(lambda _ '()))
12133 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12134 (*text* . ,(lambda (_ txt) txt))))
12136 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12137 "synth_look_and_feel_1.xml")
12138 (copy-file (assoc-ref inputs "phyloxml.xsd")
12140 (substitute* "build.xml"
12141 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12142 "synth_look_and_feel_1.xml")
12143 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12146 ;; FIXME: itext is difficult to package as it depends on a few
12147 ;; unpackaged libraries.
12148 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12150 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12151 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12152 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12153 (("pdf_written_to = PdfExporter.*")
12154 "throw new IOException(\"PDF export is not available.\"); /*")
12155 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12156 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12158 (add-after 'unpack 'delete-pre-built-classes
12159 (lambda _ (delete-file-recursively "src/classes") #t))
12160 ;; There is no install target
12161 (replace 'install (install-jars ".")))))
12163 `(("java-commons-codec" ,java-commons-codec)
12164 ("java-openchart2" ,java-openchart2)))
12165 ;; The source archive does not contain the resources.
12170 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12171 "b61cc2dcede0bede317db362472333115756b8c6/"
12172 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12173 (file-name (string-append name "-phyloxml-" version ".xsd"))
12176 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12177 ("synth_look_and_feel_1.xml"
12180 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12181 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12182 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12183 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12186 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12187 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12188 (synopsis "Phylogenomics libraries for Java")
12189 (description "Forester is a collection of Java libraries for
12190 phylogenomics and evolutionary biology research. It includes support for
12191 reading, writing, and exporting phylogenetic trees.")
12192 (license license:lgpl2.1+)))
12194 (define-public java-biojava-core
12196 (name "java-biojava-core")
12200 (uri (git-reference
12201 (url "https://github.com/biojava/biojava")
12202 (commit (string-append "biojava-" version))))
12203 (file-name (string-append name "-" version "-checkout"))
12206 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12207 (build-system ant-build-system)
12210 #:jar-name "biojava-core.jar"
12211 #:source-dir "biojava-core/src/main/java/"
12212 #:test-dir "biojava-core/src/test"
12213 ;; These tests seem to require internet access.
12214 #:test-exclude (list "**/SearchIOTest.java"
12215 "**/BlastXMLParserTest.java"
12216 "**/GenbankCookbookTest.java"
12217 "**/GenbankProxySequenceReaderTest.java")
12219 (modify-phases %standard-phases
12220 (add-before 'build 'copy-resources
12222 (copy-recursively "biojava-core/src/main/resources"
12225 (add-before 'check 'copy-test-resources
12227 (copy-recursively "biojava-core/src/test/resources"
12228 "build/test-classes")
12231 `(("java-log4j-api" ,java-log4j-api)
12232 ("java-log4j-core" ,java-log4j-core)
12233 ("java-slf4j-api" ,java-slf4j-api)
12234 ("java-slf4j-simple" ,java-slf4j-simple)))
12236 `(("java-junit" ,java-junit)
12237 ("java-hamcrest-core" ,java-hamcrest-core)))
12238 (home-page "http://biojava.org")
12239 (synopsis "Core libraries of Java framework for processing biological data")
12240 (description "BioJava is a project dedicated to providing a Java framework
12241 for processing biological data. It provides analytical and statistical
12242 routines, parsers for common file formats, reference implementations of
12243 popular algorithms, and allows the manipulation of sequences and 3D
12244 structures. The goal of the biojava project is to facilitate rapid
12245 application development for bioinformatics.
12247 This package provides the core libraries.")
12248 (license license:lgpl2.1+)))
12250 (define-public java-biojava-phylo
12251 (package (inherit java-biojava-core)
12252 (name "java-biojava-phylo")
12253 (build-system ant-build-system)
12256 #:jar-name "biojava-phylo.jar"
12257 #:source-dir "biojava-phylo/src/main/java/"
12258 #:test-dir "biojava-phylo/src/test"
12260 (modify-phases %standard-phases
12261 (add-before 'build 'copy-resources
12263 (copy-recursively "biojava-phylo/src/main/resources"
12266 (add-before 'check 'copy-test-resources
12268 (copy-recursively "biojava-phylo/src/test/resources"
12269 "build/test-classes")
12272 `(("java-log4j-api" ,java-log4j-api)
12273 ("java-log4j-core" ,java-log4j-core)
12274 ("java-slf4j-api" ,java-slf4j-api)
12275 ("java-slf4j-simple" ,java-slf4j-simple)
12276 ("java-biojava-core" ,java-biojava-core)
12277 ("java-forester" ,java-forester)))
12279 `(("java-junit" ,java-junit)
12280 ("java-hamcrest-core" ,java-hamcrest-core)))
12281 (home-page "http://biojava.org")
12282 (synopsis "Biojava interface to the forester phylogenomics library")
12283 (description "The phylo module provides a biojava interface layer to the
12284 forester phylogenomics library for constructing phylogenetic trees.")))
12286 (define-public java-biojava-alignment
12287 (package (inherit java-biojava-core)
12288 (name "java-biojava-alignment")
12289 (build-system ant-build-system)
12292 #:jar-name "biojava-alignment.jar"
12293 #:source-dir "biojava-alignment/src/main/java/"
12294 #:test-dir "biojava-alignment/src/test"
12296 (modify-phases %standard-phases
12297 (add-before 'build 'copy-resources
12299 (copy-recursively "biojava-alignment/src/main/resources"
12302 (add-before 'check 'copy-test-resources
12304 (copy-recursively "biojava-alignment/src/test/resources"
12305 "build/test-classes")
12308 `(("java-log4j-api" ,java-log4j-api)
12309 ("java-log4j-core" ,java-log4j-core)
12310 ("java-slf4j-api" ,java-slf4j-api)
12311 ("java-slf4j-simple" ,java-slf4j-simple)
12312 ("java-biojava-core" ,java-biojava-core)
12313 ("java-biojava-phylo" ,java-biojava-phylo)
12314 ("java-forester" ,java-forester)))
12316 `(("java-junit" ,java-junit)
12317 ("java-hamcrest-core" ,java-hamcrest-core)))
12318 (home-page "http://biojava.org")
12319 (synopsis "Biojava API for genetic sequence alignment")
12320 (description "The alignment module of BioJava provides an API that
12324 @item implementations of dynamic programming algorithms for sequence
12326 @item reading and writing of popular alignment file formats;
12327 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12330 (define-public java-biojava-core-4.0
12331 (package (inherit java-biojava-core)
12332 (name "java-biojava-core")
12336 (uri (git-reference
12337 (url "https://github.com/biojava/biojava")
12338 (commit (string-append "biojava-" version))))
12339 (file-name (string-append name "-" version "-checkout"))
12342 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12344 (define-public java-biojava-phylo-4.0
12345 (package (inherit java-biojava-core-4.0)
12346 (name "java-biojava-phylo")
12347 (build-system ant-build-system)
12350 #:jar-name "biojava-phylo.jar"
12351 #:source-dir "biojava-phylo/src/main/java/"
12352 #:test-dir "biojava-phylo/src/test"
12354 (modify-phases %standard-phases
12355 (add-before 'build 'copy-resources
12357 (copy-recursively "biojava-phylo/src/main/resources"
12360 (add-before 'check 'copy-test-resources
12362 (copy-recursively "biojava-phylo/src/test/resources"
12363 "build/test-classes")
12366 `(("java-log4j-api" ,java-log4j-api)
12367 ("java-log4j-core" ,java-log4j-core)
12368 ("java-slf4j-api" ,java-slf4j-api)
12369 ("java-slf4j-simple" ,java-slf4j-simple)
12370 ("java-biojava-core" ,java-biojava-core-4.0)
12371 ("java-forester" ,java-forester-1.005)))
12373 `(("java-junit" ,java-junit)
12374 ("java-hamcrest-core" ,java-hamcrest-core)))
12375 (home-page "http://biojava.org")
12376 (synopsis "Biojava interface to the forester phylogenomics library")
12377 (description "The phylo module provides a biojava interface layer to the
12378 forester phylogenomics library for constructing phylogenetic trees.")))
12380 (define-public java-biojava-alignment-4.0
12381 (package (inherit java-biojava-core-4.0)
12382 (name "java-biojava-alignment")
12383 (build-system ant-build-system)
12386 #:jar-name "biojava-alignment.jar"
12387 #:source-dir "biojava-alignment/src/main/java/"
12388 #:test-dir "biojava-alignment/src/test"
12390 (modify-phases %standard-phases
12391 (add-before 'build 'copy-resources
12393 (copy-recursively "biojava-alignment/src/main/resources"
12396 (add-before 'check 'copy-test-resources
12398 (copy-recursively "biojava-alignment/src/test/resources"
12399 "build/test-classes")
12402 `(("java-log4j-api" ,java-log4j-api)
12403 ("java-log4j-core" ,java-log4j-core)
12404 ("java-slf4j-api" ,java-slf4j-api)
12405 ("java-slf4j-simple" ,java-slf4j-simple)
12406 ("java-biojava-core" ,java-biojava-core-4.0)
12407 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12408 ("java-forester" ,java-forester-1.005)))
12410 `(("java-junit" ,java-junit)
12411 ("java-hamcrest-core" ,java-hamcrest-core)))
12412 (home-page "http://biojava.org")
12413 (synopsis "Biojava API for genetic sequence alignment")
12414 (description "The alignment module of BioJava provides an API that
12418 @item implementations of dynamic programming algorithms for sequence
12420 @item reading and writing of popular alignment file formats;
12421 @item a single-, or multi- threaded multiple sequence alignment algorithm.