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 needed for dropseq-tools
3155 (define-public java-picard-2.10.3
3157 (name "java-picard")
3162 (url "https://github.com/broadinstitute/picard.git")
3164 (file-name (string-append "java-picard-" version "-checkout"))
3167 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3168 (build-system ant-build-system)
3170 `(#:jar-name "picard.jar"
3171 ;; Tests require jacoco:coverage.
3174 #:main-class "picard.cmdline.PicardCommandLine"
3175 #:modules ((guix build ant-build-system)
3177 (guix build java-utils)
3182 (modify-phases %standard-phases
3183 (add-after 'unpack 'remove-useless-build.xml
3184 (lambda _ (delete-file "build.xml") #t))
3185 ;; This is necessary to ensure that htsjdk is found when using
3186 ;; picard.jar as an executable.
3187 (add-before 'build 'edit-classpath-in-manifest
3188 (lambda* (#:key inputs #:allow-other-keys)
3189 (chmod "build.xml" #o664)
3190 (call-with-output-file "build.xml.new"
3194 (with-input-from-file "build.xml"
3195 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3196 `((target . ,(lambda (tag . kids)
3197 (let ((name ((sxpath '(name *text*))
3199 ;; FIXME: We're breaking the line
3200 ;; early with a dummy path to
3201 ;; ensure that the store reference
3202 ;; isn't broken apart and can still
3203 ;; be found by the reference
3208 ~a/share/java/htsjdk.jar${line.separator}"
3209 ;; maximum line length is 70
3210 (string-tabulate (const #\b) 57)
3211 (assoc-ref inputs "java-htsjdk"))))
3212 (if (member "manifest" name)
3216 (file "${manifest.file}")
3219 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3220 (*text* . ,(lambda (_ txt) txt))))
3222 (rename-file "build.xml.new" "build.xml")
3225 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3227 `(("java-testng" ,java-testng)
3228 ("java-guava" ,java-guava)))
3229 (home-page "http://broadinstitute.github.io/picard/")
3230 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3231 (description "Picard is a set of Java command line tools for manipulating
3232 high-throughput sequencing (HTS) data and formats. Picard is implemented
3233 using the HTSJDK Java library to support accessing file formats that are
3234 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3236 (license license:expat)))
3238 ;; This is the last version of Picard to provide net.sf.samtools
3239 (define-public java-picard-1.113
3240 (package (inherit java-picard)
3241 (name "java-picard")
3246 (url "https://github.com/broadinstitute/picard.git")
3248 (file-name (string-append "java-picard-" version "-checkout"))
3251 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3252 (modules '((guix build utils)))
3255 ;; Delete pre-built binaries.
3256 (delete-file-recursively "lib")
3259 (build-system ant-build-system)
3261 `(#:build-target "picard-jar"
3262 #:test-target "test"
3263 ;; FIXME: the class path at test time is wrong.
3264 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3265 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3268 ;; This is only used for tests.
3270 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3272 (modify-phases %standard-phases
3273 ;; Do not use bundled ant bzip2.
3274 (add-after 'unpack 'use-ant-bzip
3275 (lambda* (#:key inputs #:allow-other-keys)
3276 (substitute* "build.xml"
3277 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3278 (string-append (assoc-ref inputs "ant")
3281 (add-after 'unpack 'make-test-target-independent
3282 (lambda* (#:key inputs #:allow-other-keys)
3283 (substitute* "build.xml"
3284 (("name=\"test\" depends=\"compile, ")
3285 "name=\"test\" depends=\"compile-tests, ")
3286 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3287 "name=\"compile\" depends=\"compile-src\""))
3289 (add-after 'unpack 'fix-deflater-path
3290 (lambda* (#:key outputs #:allow-other-keys)
3291 (substitute* "src/java/net/sf/samtools/Defaults.java"
3292 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3293 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3294 (assoc-ref outputs "out")
3295 "/lib/jni/libIntelDeflater.so"
3298 ;; Build the deflater library, because we've previously deleted the
3299 ;; pre-built one. This can only be built with access to the JDK
3301 (add-after 'build 'build-jni
3302 (lambda* (#:key inputs #:allow-other-keys)
3305 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3306 "-xf" (assoc-ref inputs "jdk-src")))
3307 (zero? (system* "javah" "-jni"
3308 "-classpath" "classes"
3310 "net.sf.samtools.util.zip.IntelDeflater"))
3311 (with-directory-excursion "src/c/inteldeflater"
3312 (zero? (system* "gcc" "-I../../../lib" "-I."
3313 (string-append "-I" (assoc-ref inputs "jdk")
3315 "-I../../../jdk-src/src/share/native/common/"
3316 "-I../../../jdk-src/src/solaris/native/common/"
3317 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3318 (zero? (system* "gcc" "-shared"
3319 "-o" "../../../lib/jni/libIntelDeflater.so"
3320 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3321 ;; We can only build everything else after building the JNI library.
3322 (add-after 'build-jni 'build-rest
3323 (lambda* (#:key make-flags #:allow-other-keys)
3324 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3325 (add-before 'build 'set-JAVA6_HOME
3327 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3329 (replace 'install (install-jars "dist"))
3330 (add-after 'install 'install-jni-lib
3331 (lambda* (#:key outputs #:allow-other-keys)
3332 (let ((jni (string-append (assoc-ref outputs "out")
3335 (install-file "lib/jni/libIntelDeflater.so" jni)
3338 `(("java-snappy-1" ,java-snappy-1)
3339 ("java-commons-jexl-2" ,java-commons-jexl-2)
3340 ("java-cofoja" ,java-cofoja)
3341 ("ant" ,ant) ; for bzip2 support at runtime
3344 `(("ant-apache-bcel" ,ant-apache-bcel)
3345 ("ant-junit" ,ant-junit)
3346 ("java-testng" ,java-testng)
3347 ("java-commons-bcel" ,java-commons-bcel)
3348 ("java-jcommander" ,java-jcommander)
3349 ("jdk" ,icedtea-8 "jdk")
3350 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3352 (define-public fastqc
3359 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3360 "projects/fastqc/fastqc_v"
3361 version "_source.zip"))
3364 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3365 (build-system ant-build-system)
3367 `(#:tests? #f ; there are no tests
3368 #:build-target "build"
3370 (modify-phases %standard-phases
3371 (add-after 'unpack 'fix-dependencies
3372 (lambda* (#:key inputs #:allow-other-keys)
3373 (substitute* "build.xml"
3375 (string-append (assoc-ref inputs "java-jbzip2")
3376 "/share/java/jbzip2.jar"))
3378 (string-append (assoc-ref inputs "java-picard-1.113")
3379 "/share/java/sam-1.112.jar"))
3381 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3382 "/share/java/sis-jhdf5.jar")))
3384 ;; There is no installation target
3386 (lambda* (#:key inputs outputs #:allow-other-keys)
3387 (let* ((out (assoc-ref outputs "out"))
3388 (bin (string-append out "/bin"))
3389 (share (string-append out "/share/fastqc/"))
3390 (exe (string-append share "/fastqc")))
3391 (for-each mkdir-p (list bin share))
3392 (copy-recursively "bin" share)
3394 (("my \\$java_bin = 'java';")
3395 (string-append "my $java_bin = '"
3396 (assoc-ref inputs "java")
3399 (symlink exe (string-append bin "/fastqc"))
3403 ("perl" ,perl) ; needed for the wrapper script
3404 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3405 ("java-picard-1.113" ,java-picard-1.113)
3406 ("java-jbzip2" ,java-jbzip2)))
3408 `(("unzip" ,unzip)))
3409 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3410 (synopsis "Quality control tool for high throughput sequence data")
3412 "FastQC aims to provide a simple way to do some quality control
3413 checks on raw sequence data coming from high throughput sequencing
3414 pipelines. It provides a modular set of analyses which you can use to
3415 give a quick impression of whether your data has any problems of which
3416 you should be aware before doing any further analysis.
3418 The main functions of FastQC are:
3421 @item Import of data from BAM, SAM or FastQ files (any variant);
3422 @item Providing a quick overview to tell you in which areas there may
3424 @item Summary graphs and tables to quickly assess your data;
3425 @item Export of results to an HTML based permanent report;
3426 @item Offline operation to allow automated generation of reports
3427 without running the interactive application.
3429 (license license:gpl3+)))
3431 (define-public htslib
3438 "https://github.com/samtools/htslib/releases/download/"
3439 version "/htslib-" version ".tar.bz2"))
3442 "1il6i2p84b0y9c93dhvzzki1ifw9bvapm2mvpr0xvb2nq8jlwgdy"))))
3443 (build-system gnu-build-system)
3445 `(("openssl" ,openssl)
3450 (home-page "http://www.htslib.org")
3451 (synopsis "C library for reading/writing high-throughput sequencing data")
3453 "HTSlib is a C library for reading/writing high-throughput sequencing
3454 data. It also provides the @command{bgzip}, @command{htsfile}, and
3455 @command{tabix} utilities.")
3456 ;; Files under cram/ are released under the modified BSD license;
3457 ;; the rest is released under the Expat license
3458 (license (list license:expat license:bsd-3))))
3460 ;; This package should be removed once no packages rely upon it.
3468 "https://github.com/samtools/htslib/releases/download/"
3469 version "/htslib-" version ".tar.bz2"))
3472 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3481 "https://github.com/nboley/idr/archive/"
3483 (file-name (string-append name "-" version ".tar.gz"))
3486 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3487 ;; Delete generated C code.
3489 '(begin (delete-file "idr/inv_cdf.c") #t))))
3490 (build-system python-build-system)
3491 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3492 ;; are no longer part of this package. It also asserts False, which
3493 ;; causes the tests to always fail.
3494 (arguments `(#:tests? #f))
3496 `(("python-scipy" ,python-scipy)
3497 ("python-sympy" ,python-sympy)
3498 ("python-numpy" ,python-numpy)
3499 ("python-matplotlib" ,python-matplotlib)))
3501 `(("python-cython" ,python-cython)))
3502 (home-page "https://github.com/nboley/idr")
3503 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3505 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3506 to measure the reproducibility of findings identified from replicate
3507 experiments and provide highly stable thresholds based on reproducibility.")
3508 (license license:gpl2+)))
3510 (define-public jellyfish
3516 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3517 "releases/download/v" version
3518 "/jellyfish-" version ".tar.gz"))
3521 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3522 (build-system gnu-build-system)
3523 (outputs '("out" ;for library
3524 "ruby" ;for Ruby bindings
3525 "python")) ;for Python bindings
3528 (list (string-append "--enable-ruby-binding="
3529 (assoc-ref %outputs "ruby"))
3530 (string-append "--enable-python-binding="
3531 (assoc-ref %outputs "python")))
3533 (modify-phases %standard-phases
3534 (add-before 'check 'set-SHELL-variable
3536 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3538 (setenv "SHELL" (which "bash"))
3544 ("python" ,python-2)
3545 ("pkg-config" ,pkg-config)))
3547 `(("htslib" ,htslib)))
3548 (synopsis "Tool for fast counting of k-mers in DNA")
3550 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3551 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3552 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3553 is a command-line program that reads FASTA and multi-FASTA files containing
3554 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3555 translated into a human-readable text format using the @code{jellyfish dump}
3556 command, or queried for specific k-mers with @code{jellyfish query}.")
3557 (home-page "http://www.genome.umd.edu/jellyfish.html")
3558 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3559 (supported-systems '("x86_64-linux"))
3560 ;; The combined work is published under the GPLv3 or later. Individual
3561 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3562 (license (list license:gpl3+ license:expat))))
3564 (define-public khmer
3571 (uri (pypi-uri "khmer" version))
3574 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3575 (patches (search-patches "khmer-use-libraries.patch"))))
3576 (build-system python-build-system)
3579 (modify-phases %standard-phases
3580 (add-after 'unpack 'set-paths
3581 (lambda* (#:key inputs outputs #:allow-other-keys)
3582 ;; Delete bundled libraries.
3583 (delete-file-recursively "third-party/zlib")
3584 (delete-file-recursively "third-party/bzip2")
3585 ;; Replace bundled seqan.
3586 (let* ((seqan-all "third-party/seqan")
3587 (seqan-include (string-append
3588 seqan-all "/core/include")))
3589 (delete-file-recursively seqan-all)
3590 (copy-recursively (string-append (assoc-ref inputs "seqan")
3592 (string-append seqan-include "/seqan")))
3593 ;; We do not replace the bundled MurmurHash as the canonical
3594 ;; repository for this code 'SMHasher' is unsuitable for
3595 ;; providing a library. See
3596 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3598 (add-after 'unpack 'set-cc
3602 ;; It is simpler to test after installation.
3604 (add-after 'install 'post-install-check
3605 (lambda* (#:key inputs outputs #:allow-other-keys)
3606 (let ((out (assoc-ref outputs "out")))
3611 (assoc-ref outputs "out")
3613 (setenv "PYTHONPATH"
3615 (getenv "PYTHONPATH")
3619 (string-take (string-take-right
3620 (assoc-ref inputs "python") 5) 3)
3622 (with-directory-excursion "build"
3623 (zero? (system* "nosetests" "khmer" "--attr"
3624 "!known_failing")))))))))
3627 ("python-nose" ,python-nose)))
3631 ("python-screed" ,python-screed)
3632 ("python-bz2file" ,python-bz2file)
3633 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3634 ;; until the next version of khmer (likely 2.1) is released.
3636 (home-page "https://khmer.readthedocs.org/")
3637 (synopsis "K-mer counting, filtering and graph traversal library")
3638 (description "The khmer software is a set of command-line tools for
3639 working with DNA shotgun sequencing data from genomes, transcriptomes,
3640 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3641 sometimes better. Khmer can also identify and fix problems with shotgun
3643 ;; When building on i686, armhf and mips64el, we get the following error:
3644 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3645 (supported-systems '("x86_64-linux" "aarch64-linux"))
3646 (license license:bsd-3)))
3648 (define-public kaiju
3655 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3657 (file-name (string-append name "-" version ".tar.gz"))
3660 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3661 (build-system gnu-build-system)
3663 `(#:tests? #f ; There are no tests.
3665 (modify-phases %standard-phases
3667 (add-before 'build 'move-to-src-dir
3668 (lambda _ (chdir "src") #t))
3670 (lambda* (#:key inputs outputs #:allow-other-keys)
3671 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3674 (copy-recursively "bin" bin)
3675 (copy-recursively "util" bin))
3679 (home-page "http://kaiju.binf.ku.dk/")
3680 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3681 (description "Kaiju is a program for sensitive taxonomic classification
3682 of high-throughput sequencing reads from metagenomic whole genome sequencing
3684 (license license:gpl3+)))
3689 (version "2.1.0.20151222")
3692 (uri (pypi-uri "MACS2" version))
3695 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3696 (build-system python-build-system)
3698 `(#:python ,python-2 ; only compatible with Python 2.7
3699 #:tests? #f)) ; no test target
3701 `(("python-numpy" ,python2-numpy)))
3702 (home-page "https://github.com/taoliu/MACS/")
3703 (synopsis "Model based analysis for ChIP-Seq data")
3705 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3706 identifying transcript factor binding sites named Model-based Analysis of
3707 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3708 the significance of enriched ChIP regions and it improves the spatial
3709 resolution of binding sites through combining the information of both
3710 sequencing tag position and orientation.")
3711 (license license:bsd-3)))
3713 (define-public mafft
3720 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3721 "-without-extensions-src.tgz"))
3722 (file-name (string-append name "-" version ".tgz"))
3725 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3726 (build-system gnu-build-system)
3728 `(#:tests? #f ; no automated tests, though there are tests in the read me
3729 #:make-flags (let ((out (assoc-ref %outputs "out")))
3730 (list (string-append "PREFIX=" out)
3731 (string-append "BINDIR="
3732 (string-append out "/bin"))))
3734 (modify-phases %standard-phases
3735 (add-after 'unpack 'enter-dir
3736 (lambda _ (chdir "core") #t))
3737 (add-after 'enter-dir 'patch-makefile
3739 ;; on advice from the MAFFT authors, there is no need to
3740 ;; distribute mafft-profile, mafft-distance, or
3741 ;; mafft-homologs.rb as they are too "specialised".
3742 (substitute* "Makefile"
3743 ;; remove mafft-homologs.rb from SCRIPTS
3744 (("^SCRIPTS = mafft mafft-homologs.rb")
3746 ;; remove mafft-homologs from MANPAGES
3747 (("^MANPAGES = mafft.1 mafft-homologs.1")
3748 "MANPAGES = mafft.1")
3749 ;; remove mafft-distance from PROGS
3750 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3751 "PROGS = dvtditr dndfast7 dndblast sextet5")
3752 ;; remove mafft-profile from PROGS
3753 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3754 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3755 (("^rm -f mafft-profile mafft-profile.exe") "#")
3756 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3757 ;; do not install MAN pages in libexec folder
3758 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3759 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3761 (add-after 'enter-dir 'patch-paths
3762 (lambda* (#:key inputs #:allow-other-keys)
3763 (substitute* '("pairash.c"
3765 (("perl") (which "perl"))
3766 (("([\"`| ])awk" _ prefix)
3767 (string-append prefix (which "awk")))
3768 (("grep") (which "grep")))
3771 (add-after 'install 'wrap-programs
3772 (lambda* (#:key outputs #:allow-other-keys)
3773 (let* ((out (assoc-ref outputs "out"))
3774 (bin (string-append out "/bin"))
3775 (path (string-append
3776 (assoc-ref %build-inputs "coreutils") "/bin:")))
3777 (for-each (lambda (file)
3779 `("PATH" ":" prefix (,path))))
3787 ("coreutils" ,coreutils)))
3788 (home-page "http://mafft.cbrc.jp/alignment/software/")
3789 (synopsis "Multiple sequence alignment program")
3791 "MAFFT offers a range of multiple alignment methods for nucleotide and
3792 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3793 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3795 (license (license:non-copyleft
3796 "http://mafft.cbrc.jp/alignment/software/license.txt"
3797 "BSD-3 with different formatting"))))
3806 "https://github.com/marbl/mash/archive/v"
3808 (file-name (string-append name "-" version ".tar.gz"))
3811 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3812 (modules '((guix build utils)))
3814 ;; Delete bundled kseq.
3815 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3816 '(delete-file "src/mash/kseq.h"))))
3817 (build-system gnu-build-system)
3819 `(#:tests? #f ; No tests.
3822 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3823 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3824 #:make-flags (list "CC=gcc")
3826 (modify-phases %standard-phases
3827 (add-after 'unpack 'fix-includes
3829 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3830 (("^#include \"kseq\\.h\"")
3831 "#include \"htslib/kseq.h\""))
3833 (add-after 'fix-includes 'autoconf
3834 (lambda _ (zero? (system* "autoconf")))))))
3836 `(("autoconf" ,autoconf)
3837 ;; Capnproto and htslib are statically embedded in the final
3838 ;; application. Therefore we also list their licenses, below.
3839 ("capnproto" ,capnproto)
3840 ("htslib" ,htslib)))
3844 (supported-systems '("x86_64-linux"))
3845 (home-page "https://mash.readthedocs.io")
3846 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3847 (description "Mash is a fast sequence distance estimator that uses the
3848 MinHash algorithm and is designed to work with genomes and metagenomes in the
3849 form of assemblies or reads.")
3850 (license (list license:bsd-3 ; Mash
3851 license:expat ; HTSlib and capnproto
3852 license:public-domain ; MurmurHash 3
3853 license:cpl1.0)))) ; Open Bloom Filter
3855 (define-public metabat
3862 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3864 (file-name (string-append name "-" version ".tar.gz"))
3867 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3868 (patches (search-patches "metabat-fix-compilation.patch"))))
3869 (build-system scons-build-system)
3871 `(#:scons ,scons-python2
3873 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3874 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3875 #:tests? #f ;; Tests are run during the build phase.
3877 (modify-phases %standard-phases
3878 (add-after 'unpack 'fix-includes
3880 (substitute* "src/BamUtils.h"
3881 (("^#include \"bam/bam\\.h\"")
3882 "#include \"samtools/bam.h\"")
3883 (("^#include \"bam/sam\\.h\"")
3884 "#include \"samtools/sam.h\""))
3885 (substitute* "src/KseqReader.h"
3886 (("^#include \"bam/kseq\\.h\"")
3887 "#include \"htslib/kseq.h\""))
3889 (add-after 'unpack 'fix-scons
3890 (lambda* (#:key inputs #:allow-other-keys)
3891 (substitute* "SConstruct"
3892 (("^htslib_dir += 'samtools'")
3893 (string-append "htslib_dir = '"
3894 (assoc-ref inputs "htslib")
3896 (("^samtools_dir = 'samtools'")
3897 (string-append "samtools_dir = '"
3898 (assoc-ref inputs "samtools")
3900 (("^findStaticOrShared\\('bam', hts_lib")
3901 (string-append "findStaticOrShared('bam', '"
3902 (assoc-ref inputs "samtools")
3904 ;; Do not distribute README.
3905 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3910 ("samtools" ,samtools)
3913 (home-page "https://bitbucket.org/berkeleylab/metabat")
3915 "Reconstruction of single genomes from complex microbial communities")
3917 "Grouping large genomic fragments assembled from shotgun metagenomic
3918 sequences to deconvolute complex microbial communities, or metagenome binning,
3919 enables the study of individual organisms and their interactions. MetaBAT is
3920 an automated metagenome binning software, which integrates empirical
3921 probabilistic distances of genome abundance and tetranucleotide frequency.")
3922 ;; The source code contains inline assembly.
3923 (supported-systems '("x86_64-linux" "i686-linux"))
3924 (license (license:non-copyleft "file://license.txt"
3925 "See license.txt in the distribution."))))
3927 (define-public minced
3934 "https://github.com/ctSkennerton/minced/archive/"
3936 (file-name (string-append name "-" version ".tar.gz"))
3939 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3940 (build-system gnu-build-system)
3942 `(#:test-target "test"
3944 (modify-phases %standard-phases
3946 (add-before 'check 'fix-test
3948 ;; Fix test for latest version.
3949 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3950 (("minced:0.1.6") "minced:0.2.0"))
3952 (replace 'install ; No install target.
3953 (lambda* (#:key inputs outputs #:allow-other-keys)
3954 (let* ((out (assoc-ref outputs "out"))
3955 (bin (string-append out "/bin"))
3956 (wrapper (string-append bin "/minced")))
3957 ;; Minced comes with a wrapper script that tries to figure out where
3958 ;; it is located before running the JAR. Since these paths are known
3959 ;; to us, we build our own wrapper to avoid coreutils dependency.
3960 (install-file "minced.jar" bin)
3961 (with-output-to-file wrapper
3965 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3966 (assoc-ref inputs "jre") "/bin/java -jar "
3967 bin "/minced.jar \"$@\"\n"))))
3968 (chmod wrapper #o555)))))))
3970 `(("jdk" ,icedtea "jdk")))
3973 ("jre" ,icedtea "out")))
3974 (home-page "https://github.com/ctSkennerton/minced")
3975 (synopsis "Mining CRISPRs in Environmental Datasets")
3977 "MinCED is a program to find Clustered Regularly Interspaced Short
3978 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3979 unassembled metagenomic reads, but is mainly designed for full genomes and
3980 assembled metagenomic sequence.")
3981 (license license:gpl3+)))
3989 (uri (pypi-uri "misopy" version))
3992 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3993 (modules '((guix build utils)))
3995 '(substitute* "setup.py"
3996 ;; Use setuptools, or else the executables are not
3998 (("distutils.core") "setuptools")
3999 ;; use "gcc" instead of "cc" for compilation
4001 "cc.set_executables(
4005 linker_so='gcc -shared'); defines")))))
4006 (build-system python-build-system)
4008 `(#:python ,python-2 ; only Python 2 is supported
4009 #:tests? #f)) ; no "test" target
4011 `(("samtools" ,samtools)
4012 ("python-numpy" ,python2-numpy)
4013 ("python-pysam" ,python2-pysam)
4014 ("python-scipy" ,python2-scipy)
4015 ("python-matplotlib" ,python2-matplotlib)))
4017 `(("python-mock" ,python2-mock) ;for tests
4018 ("python-pytz" ,python2-pytz))) ;for tests
4019 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4020 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4022 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4023 the expression level of alternatively spliced genes from RNA-Seq data, and
4024 identifies differentially regulated isoforms or exons across samples. By
4025 modeling the generative process by which reads are produced from isoforms in
4026 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4027 that a read originated from a particular isoform.")
4028 (license license:gpl2)))
4030 (define-public muscle
4033 (version "3.8.1551")
4035 (method url-fetch/tarbomb)
4037 "http://www.drive5.com/muscle/muscle_src_"
4041 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4042 (build-system gnu-build-system)
4044 `(#:make-flags (list "LDLIBS = -lm")
4046 (modify-phases %standard-phases
4049 ;; There are no tests, so just test if it runs.
4050 (lambda _ (zero? (system* "./muscle" "-version"))))
4052 (lambda* (#:key outputs #:allow-other-keys)
4053 (let* ((out (assoc-ref outputs "out"))
4054 (bin (string-append out "/bin")))
4055 (install-file "muscle" bin)))))))
4056 (home-page "http://www.drive5.com/muscle")
4057 (synopsis "Multiple sequence alignment program")
4059 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4060 program for nucleotide and protein sequences.")
4061 ;; License information found in 'muscle -h' and usage.cpp.
4062 (license license:public-domain)))
4064 (define-public newick-utils
4065 ;; There are no recent releases so we package from git.
4066 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4068 (name "newick-utils")
4069 (version (string-append "1.6-1." (string-take commit 8)))
4073 (url "https://github.com/tjunier/newick_utils.git")
4075 (file-name (string-append name "-" version "-checkout"))
4078 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4079 (build-system gnu-build-system)
4082 (modify-phases %standard-phases
4083 (add-after 'unpack 'autoconf
4084 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4086 ;; XXX: TODO: Enable Lua and Guile bindings.
4087 ;; https://github.com/tjunier/newick_utils/issues/13
4088 `(("libxml2" ,libxml2)
4092 `(("autoconf" ,autoconf)
4093 ("automake" ,automake)
4094 ("libtool" ,libtool)))
4095 (synopsis "Programs for working with newick format phylogenetic trees")
4097 "Newick-utils is a suite of utilities for processing phylogenetic trees
4098 in Newick format. Functions include re-rooting, extracting subtrees,
4099 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4100 (home-page "https://github.com/tjunier/newick_utils")
4101 (license license:bsd-3))))
4110 "https://github.com/wwood/OrfM/releases/download/v"
4111 version "/orfm-" version ".tar.gz"))
4114 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4115 (build-system gnu-build-system)
4116 (inputs `(("zlib" ,zlib)))
4118 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4119 ("ruby-rspec" ,ruby-rspec)
4121 (synopsis "Simple and not slow open reading frame (ORF) caller")
4123 "An ORF caller finds stretches of DNA that, when translated, are not
4124 interrupted by stop codons. OrfM finds and prints these ORFs.")
4125 (home-page "https://github.com/wwood/OrfM")
4126 (license license:lgpl3+)))
4128 (define-public pplacer
4129 (let ((commit "g807f6f3"))
4132 ;; The commit should be updated with each version change.
4133 (version "1.1.alpha19")
4137 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4139 (file-name (string-append name "-" version ".tar.gz"))
4141 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4142 (build-system ocaml-build-system)
4144 `(#:ocaml ,ocaml-4.01
4145 #:findlib ,ocaml4.01-findlib
4146 #:modules ((guix build ocaml-build-system)
4150 (modify-phases %standard-phases
4152 (add-after 'unpack 'replace-bundled-cddlib
4153 (lambda* (#:key inputs #:allow-other-keys)
4154 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4155 (local-dir "cddlib_guix"))
4157 (with-directory-excursion local-dir
4158 (system* "tar" "xvf" cddlib-src))
4159 (let ((cddlib-src-folder
4160 (string-append local-dir "/"
4161 (list-ref (scandir local-dir) 2)
4166 (string-append "cdd_src/" (basename file))))
4167 (find-files cddlib-src-folder ".*[ch]$")))
4169 (add-after 'unpack 'fix-makefile
4171 ;; Remove system calls to 'git'.
4172 (substitute* "Makefile"
4173 (("^DESCRIPT:=pplacer-.*")
4175 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4176 (substitute* "myocamlbuild.ml"
4177 (("git describe --tags --long .*\\\" with")
4179 "echo -n v" ,version "-" ,commit "\" with")))
4182 (lambda* (#:key outputs #:allow-other-keys)
4183 (let* ((out (assoc-ref outputs "out"))
4184 (bin (string-append out "/bin")))
4185 (copy-recursively "bin" bin))
4190 ("ocaml-ounit" ,ocaml4.01-ounit)
4191 ("ocaml-batteries" ,ocaml4.01-batteries)
4192 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4193 ("ocaml-csv" ,ocaml4.01-csv)
4194 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4195 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4196 ("ocaml-mcl" ,ocaml4.01-mcl)
4197 ("ocaml-gsl" ,ocaml4.01-gsl)
4198 ("cddlib-src" ,(package-source cddlib))))
4200 `(("pplacer-scripts" ,pplacer-scripts)))
4201 (synopsis "Phylogenetic placement of biological sequences")
4203 "Pplacer places query sequences on a fixed reference phylogenetic tree
4204 to maximize phylogenetic likelihood or posterior probability according to a
4205 reference alignment. Pplacer is designed to be fast, to give useful
4206 information about uncertainty, and to offer advanced visualization and
4207 downstream analysis.")
4208 (home-page "http://matsen.fhcrc.org/pplacer")
4209 (license license:gpl3))))
4211 ;; This package is installed alongside 'pplacer'. It is a separate package so
4212 ;; that it can use the python-build-system for the scripts that are
4213 ;; distributed alongside the main OCaml binaries.
4214 (define pplacer-scripts
4217 (name "pplacer-scripts")
4218 (build-system python-build-system)
4220 `(#:python ,python-2
4222 (modify-phases %standard-phases
4223 (add-after 'unpack 'enter-scripts-dir
4224 (lambda _ (chdir "scripts")))
4227 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4228 (add-after 'install 'wrap-executables
4229 (lambda* (#:key inputs outputs #:allow-other-keys)
4230 (let* ((out (assoc-ref outputs "out"))
4231 (bin (string-append out "/bin")))
4232 (let ((path (string-append
4233 (assoc-ref inputs "hmmer") "/bin:"
4234 (assoc-ref inputs "infernal") "/bin")))
4236 (wrap-program (string-append bin "/refpkg_align.py")
4237 `("PATH" ":" prefix (,path))))
4238 (let ((path (string-append
4239 (assoc-ref inputs "hmmer") "/bin")))
4240 (wrap-program (string-append bin "/hrefpkg_query.py")
4241 `("PATH" ":" prefix (,path)))))
4244 `(("infernal" ,infernal)
4247 `(("python-biopython" ,python2-biopython)
4248 ("taxtastic" ,taxtastic)))
4249 (synopsis "Pplacer Python scripts")))
4251 (define-public python2-pbcore
4253 (name "python2-pbcore")
4257 (uri (pypi-uri "pbcore" version))
4260 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4261 (build-system python-build-system)
4262 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4264 `(("python-cython" ,python2-cython)
4265 ("python-numpy" ,python2-numpy)
4266 ("python-pysam" ,python2-pysam)
4267 ("python-h5py" ,python2-h5py)))
4269 `(("python-nose" ,python2-nose)
4270 ("python-sphinx" ,python2-sphinx)
4271 ("python-pyxb" ,python2-pyxb)))
4272 (home-page "http://pacificbiosciences.github.io/pbcore/")
4273 (synopsis "Library for reading and writing PacBio data files")
4275 "The pbcore package provides Python APIs for interacting with PacBio data
4276 files and writing bioinformatics applications.")
4277 (license license:bsd-3)))
4279 (define-public python2-warpedlmm
4281 (name "python2-warpedlmm")
4287 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4291 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4292 (build-system python-build-system)
4294 `(#:python ,python-2)) ; requires Python 2.7
4296 `(("python-scipy" ,python2-scipy)
4297 ("python-numpy" ,python2-numpy)
4298 ("python-matplotlib" ,python2-matplotlib)
4299 ("python-fastlmm" ,python2-fastlmm)
4300 ("python-pandas" ,python2-pandas)
4301 ("python-pysnptools" ,python2-pysnptools)))
4303 `(("python-mock" ,python2-mock)
4304 ("python-nose" ,python2-nose)
4306 (home-page "https://github.com/PMBio/warpedLMM")
4307 (synopsis "Implementation of warped linear mixed models")
4309 "WarpedLMM is a Python implementation of the warped linear mixed model,
4310 which automatically learns an optimal warping function (or transformation) for
4311 the phenotype as it models the data.")
4312 (license license:asl2.0)))
4314 (define-public pbtranscript-tofu
4315 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4317 (name "pbtranscript-tofu")
4318 (version (string-append "2.2.3." (string-take commit 7)))
4322 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4324 (file-name (string-append name "-" version "-checkout"))
4327 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4328 (modules '((guix build utils)))
4331 ;; remove bundled Cython sources
4332 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4334 (build-system python-build-system)
4336 `(#:python ,python-2
4337 ;; FIXME: Tests fail with "No such file or directory:
4338 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4341 (modify-phases %standard-phases
4342 (add-after 'unpack 'enter-directory
4344 (chdir "pbtranscript-tofu/pbtranscript/")
4346 ;; With setuptools version 18.0 and later this setup.py hack causes
4347 ;; a build error, so we disable it.
4348 (add-after 'enter-directory 'patch-setuppy
4350 (substitute* "setup.py"
4351 (("if 'setuptools.extension' in sys.modules:")
4355 `(("python-numpy" ,python2-numpy)
4356 ("python-bx-python" ,python2-bx-python)
4357 ("python-networkx" ,python2-networkx)
4358 ("python-scipy" ,python2-scipy)
4359 ("python-pbcore" ,python2-pbcore)
4360 ("python-h5py" ,python2-h5py)))
4362 `(("python-cython" ,python2-cython)
4363 ("python-nose" ,python2-nose)))
4364 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4365 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4367 "pbtranscript-tofu contains scripts to analyze transcriptome data
4368 generated using the PacBio Iso-Seq protocol.")
4369 (license license:bsd-3))))
4371 (define-public prank
4378 "http://wasabiapp.org/download/prank/prank.source."
4382 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4383 (build-system gnu-build-system)
4386 (modify-phases %standard-phases
4387 (add-after 'unpack 'enter-src-dir
4391 (add-after 'unpack 'remove-m64-flag
4392 ;; Prank will build with the correct 'bit-ness' without this flag
4393 ;; and this allows building on 32-bit machines.
4394 (lambda _ (substitute* "src/Makefile"
4399 (lambda* (#:key outputs #:allow-other-keys)
4400 (let* ((out (assoc-ref outputs "out"))
4401 (bin (string-append out "/bin"))
4402 (man (string-append out "/share/man/man1"))
4403 (path (string-append
4404 (assoc-ref %build-inputs "mafft") "/bin:"
4405 (assoc-ref %build-inputs "exonerate") "/bin:"
4406 (assoc-ref %build-inputs "bppsuite") "/bin")))
4407 (install-file "prank" bin)
4408 (wrap-program (string-append bin "/prank")
4409 `("PATH" ":" prefix (,path)))
4410 (install-file "prank.1" man))
4414 ("exonerate" ,exonerate)
4415 ("bppsuite" ,bppsuite)))
4416 (home-page "http://wasabiapp.org/software/prank/")
4417 (synopsis "Probabilistic multiple sequence alignment program")
4419 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4420 codon and amino-acid sequences. It is based on a novel algorithm that treats
4421 insertions correctly and avoids over-estimation of the number of deletion
4422 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4423 in phylogenetics and correctly takes into account the evolutionary distances
4424 between sequences. Lastly, PRANK allows for defining a potential structure
4425 for sequences to be aligned and then, simultaneously with the alignment,
4426 predicts the locations of structural units in the sequences.")
4427 (license license:gpl2+)))
4429 (define-public proteinortho
4431 (name "proteinortho")
4438 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4439 version "_src.tar.gz"))
4442 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4443 (build-system gnu-build-system)
4445 `(#:test-target "test"
4447 (modify-phases %standard-phases
4449 ;; There is no configure script, so we modify the Makefile directly.
4450 (lambda* (#:key outputs #:allow-other-keys)
4451 (substitute* "Makefile"
4454 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4456 (add-before 'install 'make-install-directory
4457 ;; The install directory is not created during 'make install'.
4458 (lambda* (#:key outputs #:allow-other-keys)
4459 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4461 (add-after 'install 'wrap-programs
4462 (lambda* (#:key inputs outputs #:allow-other-keys)
4463 (let* ((path (getenv "PATH"))
4464 (out (assoc-ref outputs "out"))
4465 (binary (string-append out "/bin/proteinortho5.pl")))
4466 (wrap-program binary `("PATH" ":" prefix (,path))))
4470 ("python" ,python-2)
4471 ("blast+" ,blast+)))
4472 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4473 (synopsis "Detect orthologous genes across species")
4475 "Proteinortho is a tool to detect orthologous genes across different
4476 species. For doing so, it compares similarities of given gene sequences and
4477 clusters them to find significant groups. The algorithm was designed to handle
4478 large-scale data and can be applied to hundreds of species at once.")
4479 (license license:gpl2+)))
4481 (define-public pyicoteo
4488 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4489 "pyicoteo/get/v" version ".tar.bz2"))
4490 (file-name (string-append name "-" version ".tar.bz2"))
4493 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4494 (build-system python-build-system)
4496 `(#:python ,python-2 ; does not work with Python 3
4497 #:tests? #f)) ; there are no tests
4499 `(("python2-matplotlib" ,python2-matplotlib)))
4500 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4501 (synopsis "Analyze high-throughput genetic sequencing data")
4503 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4504 sequencing data. It works with genomic coordinates. There are currently six
4505 different command-line tools:
4508 @item pyicoregion: for generating exploratory regions automatically;
4509 @item pyicoenrich: for differential enrichment between two conditions;
4510 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4511 @item pyicos: for genomic coordinates manipulation;
4512 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4513 @item pyicount: to count how many reads from N experiment files overlap in a
4515 @item pyicotrocol: to combine operations from pyicoteo.
4517 (license license:gpl3+)))
4519 (define-public prodigal
4526 "https://github.com/hyattpd/Prodigal/archive/v"
4528 (file-name (string-append name "-" version ".tar.gz"))
4531 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4532 (build-system gnu-build-system)
4534 `(#:tests? #f ;no check target
4535 #:make-flags (list (string-append "INSTALLDIR="
4536 (assoc-ref %outputs "out")
4539 (modify-phases %standard-phases
4540 (delete 'configure))))
4541 (home-page "http://prodigal.ornl.gov")
4542 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4544 "Prodigal runs smoothly on finished genomes, draft genomes, and
4545 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4546 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4547 partial genes, and identifies translation initiation sites.")
4548 (license license:gpl3+)))
4550 (define-public roary
4558 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4562 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4563 (build-system perl-build-system)
4566 (modify-phases %standard-phases
4571 ;; The tests are not run by default, so we run each test file
4573 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4575 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4576 (getenv "PERL5LIB")))
4577 (zero? (length (filter (lambda (file)
4578 (display file)(display "\n")
4579 (not (zero? (system* "perl" file))))
4580 (find-files "t" ".*\\.t$"))))))
4582 ;; There is no 'install' target in the Makefile.
4583 (lambda* (#:key outputs #:allow-other-keys)
4584 (let* ((out (assoc-ref outputs "out"))
4585 (bin (string-append out "/bin"))
4586 (perl (string-append out "/lib/perl5/site_perl"))
4587 (roary-plots "contrib/roary_plots"))
4590 (copy-recursively "bin" bin)
4591 (copy-recursively "lib" perl)
4593 (add-after 'install 'wrap-programs
4594 (lambda* (#:key inputs outputs #:allow-other-keys)
4595 (let* ((out (assoc-ref outputs "out"))
4596 (perl5lib (getenv "PERL5LIB"))
4597 (path (getenv "PATH")))
4598 (for-each (lambda (prog)
4599 (let ((binary (string-append out "/" prog)))
4600 (wrap-program binary
4601 `("PERL5LIB" ":" prefix
4602 (,(string-append perl5lib ":" out
4603 "/lib/perl5/site_perl"))))
4604 (wrap-program binary
4606 (,(string-append path ":" out "/bin"))))))
4607 (find-files "bin" ".*[^R]$"))
4609 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4610 (r-site-lib (getenv "R_LIBS_SITE"))
4612 (string-append (assoc-ref inputs "coreutils") "/bin")))
4614 `("R_LIBS_SITE" ":" prefix
4615 (,(string-append r-site-lib ":" out "/site-library/"))))
4618 (,(string-append coreutils-path ":" out "/bin"))))))
4621 `(("perl-env-path" ,perl-env-path)
4622 ("perl-test-files" ,perl-test-files)
4623 ("perl-test-most" ,perl-test-most)
4624 ("perl-test-output" ,perl-test-output)))
4626 `(("perl-array-utils" ,perl-array-utils)
4627 ("bioperl" ,bioperl-minimal)
4628 ("perl-digest-md5-file" ,perl-digest-md5-file)
4629 ("perl-exception-class" ,perl-exception-class)
4630 ("perl-file-find-rule" ,perl-file-find-rule)
4631 ("perl-file-grep" ,perl-file-grep)
4632 ("perl-file-slurper" ,perl-file-slurper)
4633 ("perl-file-which" ,perl-file-which)
4634 ("perl-graph" ,perl-graph)
4635 ("perl-graph-readwrite" ,perl-graph-readwrite)
4636 ("perl-log-log4perl" ,perl-log-log4perl)
4637 ("perl-moose" ,perl-moose)
4638 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4639 ("perl-text-csv" ,perl-text-csv)
4640 ("bedtools" ,bedtools)
4644 ("parallel" ,parallel)
4647 ("fasttree" ,fasttree)
4651 ("r-minimal" ,r-minimal)
4652 ("r-ggplot2" ,r-ggplot2)
4653 ("coreutils" ,coreutils)))
4654 (home-page "http://sanger-pathogens.github.io/Roary")
4655 (synopsis "High speed stand-alone pan genome pipeline")
4657 "Roary is a high speed stand alone pan genome pipeline, which takes
4658 annotated assemblies in GFF3 format (produced by the Prokka program) and
4659 calculates the pan genome. Using a standard desktop PC, it can analyse
4660 datasets with thousands of samples, without compromising the quality of the
4661 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4662 single processor. Roary is not intended for metagenomics or for comparing
4663 extremely diverse sets of genomes.")
4664 (license license:gpl3)))
4666 (define-public raxml
4675 "https://github.com/stamatak/standard-RAxML/archive/v"
4677 (file-name (string-append name "-" version ".tar.gz"))
4680 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4681 (build-system gnu-build-system)
4683 `(#:tests? #f ; There are no tests.
4684 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4685 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4687 (modify-phases %standard-phases
4690 (lambda* (#:key outputs #:allow-other-keys)
4691 (let* ((out (assoc-ref outputs "out"))
4692 (bin (string-append out "/bin"))
4693 (executable "raxmlHPC-HYBRID"))
4694 (install-file executable bin)
4695 (symlink (string-append bin "/" executable) "raxml"))
4698 `(("openmpi" ,openmpi)))
4699 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4700 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4702 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4704 ;; The source includes x86 specific code
4705 (supported-systems '("x86_64-linux" "i686-linux"))
4706 (license license:gpl2+)))
4716 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4719 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4720 (patches (search-patches "rsem-makefile.patch"))
4721 (modules '((guix build utils)))
4724 ;; remove bundled copy of boost
4725 (delete-file-recursively "boost")
4727 (build-system gnu-build-system)
4729 `(#:tests? #f ;no "check" target
4731 (modify-phases %standard-phases
4732 ;; No "configure" script.
4733 ;; Do not build bundled samtools library.
4736 (substitute* "Makefile"
4737 (("^all : sam/libbam.a") "all : "))
4740 (lambda* (#:key outputs #:allow-other-keys)
4741 (let* ((out (string-append (assoc-ref outputs "out")))
4742 (bin (string-append out "/bin/"))
4743 (perl (string-append out "/lib/perl5/site_perl")))
4746 (for-each (lambda (file)
4747 (install-file file bin))
4748 (find-files "." "rsem-.*"))
4749 (install-file "rsem_perl_utils.pm" perl))
4752 'install 'wrap-program
4753 (lambda* (#:key outputs #:allow-other-keys)
4754 (let ((out (assoc-ref outputs "out")))
4755 (for-each (lambda (prog)
4756 (wrap-program (string-append out "/bin/" prog)
4757 `("PERL5LIB" ":" prefix
4758 (,(string-append out "/lib/perl5/site_perl")))))
4759 '("rsem-plot-transcript-wiggles"
4760 "rsem-calculate-expression"
4761 "rsem-generate-ngvector"
4763 "rsem-prepare-reference")))
4767 ("ncurses" ,ncurses)
4768 ("r-minimal" ,r-minimal)
4770 ("samtools" ,samtools-0.1)
4772 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4773 (synopsis "Estimate gene expression levels from RNA-Seq data")
4775 "RSEM is a software package for estimating gene and isoform expression
4776 levels from RNA-Seq data. The RSEM package provides a user-friendly
4777 interface, supports threads for parallel computation of the EM algorithm,
4778 single-end and paired-end read data, quality scores, variable-length reads and
4779 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4780 interval estimates for expression levels. For visualization, it can generate
4781 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4782 (license license:gpl3+)))
4784 (define-public rseqc
4792 (string-append "mirror://sourceforge/rseqc/"
4793 "RSeQC-" version ".tar.gz"))
4795 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4796 (modules '((guix build utils)))
4799 ;; remove bundled copy of pysam
4800 (delete-file-recursively "lib/pysam")
4801 (substitute* "setup.py"
4802 ;; remove dependency on outdated "distribute" module
4803 (("^from distribute_setup import use_setuptools") "")
4804 (("^use_setuptools\\(\\)") "")
4805 ;; do not use bundled copy of pysam
4806 (("^have_pysam = False") "have_pysam = True"))))))
4807 (build-system python-build-system)
4808 (arguments `(#:python ,python-2))
4810 `(("python-cython" ,python2-cython)
4811 ("python-pysam" ,python2-pysam)
4812 ("python-numpy" ,python2-numpy)
4815 `(("python-nose" ,python2-nose)))
4816 (home-page "http://rseqc.sourceforge.net/")
4817 (synopsis "RNA-seq quality control package")
4819 "RSeQC provides a number of modules that can comprehensively evaluate
4820 high throughput sequence data, especially RNA-seq data. Some basic modules
4821 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4822 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4823 distribution, coverage uniformity, strand specificity, etc.")
4824 (license license:gpl3+)))
4827 ;; There are no release tarballs. According to the installation
4828 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4829 ;; stable release is identified by this changeset ID.
4830 (let ((changeset "2329130")
4834 (version (string-append "0-" revision "." changeset))
4838 (url "https://bitbucket.org/libsleipnir/sleipnir")
4839 (changeset changeset)))
4840 (file-name (string-append name "-" version "-checkout"))
4843 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4844 (build-system gnu-build-system)
4846 `(#:modules ((srfi srfi-1)
4847 (guix build gnu-build-system)
4850 (let ((dirs '("SeekMiner"
4856 (modify-phases %standard-phases
4857 (add-before 'configure 'bootstrap
4859 (zero? (system* "bash" "gen_auto"))))
4860 (add-after 'build 'build-additional-tools
4861 (lambda* (#:key make-flags #:allow-other-keys)
4862 (every (lambda (dir)
4863 (with-directory-excursion (string-append "tools/" dir)
4864 (zero? (apply system* "make" make-flags))))
4866 (add-after 'install 'install-additional-tools
4867 (lambda* (#:key make-flags #:allow-other-keys)
4868 (fold (lambda (dir result)
4869 (with-directory-excursion (string-append "tools/" dir)
4871 (zero? (apply system*
4872 `("make" ,@make-flags "install"))))))
4878 ("readline" ,readline)
4879 ("gengetopt" ,gengetopt)
4880 ("log4cpp" ,log4cpp)))
4882 `(("autoconf" ,autoconf)
4883 ("automake" ,automake)
4885 (home-page "http://seek.princeton.edu")
4886 (synopsis "Gene co-expression search engine")
4888 "SEEK is a computational gene co-expression search engine. SEEK provides
4889 biologists with a way to navigate the massive human expression compendium that
4890 now contains thousands of expression datasets. SEEK returns a robust ranking
4891 of co-expressed genes in the biological area of interest defined by the user's
4892 query genes. It also prioritizes thousands of expression datasets according
4893 to the user's query of interest.")
4894 (license license:cc-by3.0))))
4896 (define-public samtools
4904 (string-append "mirror://sourceforge/samtools/samtools/"
4905 version "/samtools-" version ".tar.bz2"))
4908 "18acyqysbxpydlc44lqv2hpp57l06bs9a3yqmcvjk8va2xrrdc77"))))
4909 (build-system gnu-build-system)
4911 `(#:modules ((ice-9 ftw)
4913 (guix build gnu-build-system)
4915 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4916 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4918 (modify-phases %standard-phases
4919 (add-after 'unpack 'patch-tests
4921 (substitute* "test/test.pl"
4922 ;; The test script calls out to /bin/bash
4923 (("/bin/bash") (which "bash")))
4925 (add-after 'install 'install-library
4926 (lambda* (#:key outputs #:allow-other-keys)
4927 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4928 (install-file "libbam.a" lib)
4930 (add-after 'install 'install-headers
4931 (lambda* (#:key outputs #:allow-other-keys)
4932 (let ((include (string-append (assoc-ref outputs "out")
4933 "/include/samtools/")))
4934 (for-each (lambda (file)
4935 (install-file file include))
4936 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4938 (native-inputs `(("pkg-config" ,pkg-config)))
4940 `(("htslib" ,htslib)
4941 ("ncurses" ,ncurses)
4945 (home-page "http://samtools.sourceforge.net")
4946 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4948 "Samtools implements various utilities for post-processing nucleotide
4949 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4950 variant calling (in conjunction with bcftools), and a simple alignment
4952 (license license:expat)))
4954 (define-public samtools-0.1
4955 ;; This is the most recent version of the 0.1 line of samtools. The input
4956 ;; and output formats differ greatly from that used and produced by samtools
4957 ;; 1.x and is still used in many bioinformatics pipelines.
4958 (package (inherit samtools)
4964 (string-append "mirror://sourceforge/samtools/samtools/"
4965 version "/samtools-" version ".tar.bz2"))
4967 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4969 `(#:tests? #f ;no "check" target
4970 ,@(substitute-keyword-arguments (package-arguments samtools)
4971 ((#:make-flags flags)
4972 `(cons "LIBCURSES=-lncurses" ,flags))
4974 `(modify-phases ,phases
4976 (lambda* (#:key outputs #:allow-other-keys)
4977 (let ((bin (string-append
4978 (assoc-ref outputs "out") "/bin")))
4980 (install-file "samtools" bin)
4982 (delete 'patch-tests)
4983 (delete 'configure))))))))
4985 (define-public mosaik
4986 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4991 ;; There are no release tarballs nor tags.
4994 (url "https://github.com/wanpinglee/MOSAIK.git")
4996 (file-name (string-append name "-" version))
4999 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5000 (build-system gnu-build-system)
5002 `(#:tests? #f ; no tests
5003 #:make-flags (list "CC=gcc")
5005 (modify-phases %standard-phases
5007 (lambda _ (chdir "src") #t))
5009 (lambda* (#:key outputs #:allow-other-keys)
5010 (let ((bin (string-append (assoc-ref outputs "out")
5013 (copy-recursively "../bin" bin)
5018 (supported-systems '("x86_64-linux"))
5019 (home-page "https://github.com/wanpinglee/MOSAIK")
5020 (synopsis "Map nucleotide sequence reads to reference genomes")
5022 "MOSAIK is a program for mapping second and third-generation sequencing
5023 reads to a reference genome. MOSAIK can align reads generated by all the
5024 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5025 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5026 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5027 ;; code released into the public domain:
5028 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5029 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5030 (license (list license:gpl2+ license:public-domain)))))
5032 (define-public ngs-sdk
5040 (string-append "https://github.com/ncbi/ngs/archive/"
5042 (file-name (string-append name "-" version ".tar.gz"))
5045 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5046 (build-system gnu-build-system)
5048 `(#:parallel-build? #f ; not supported
5049 #:tests? #f ; no "check" target
5051 (modify-phases %standard-phases
5053 (lambda* (#:key outputs #:allow-other-keys)
5054 (let ((out (assoc-ref outputs "out")))
5055 ;; Allow 'konfigure.perl' to find 'package.prl'.
5057 (string-append ".:" (getenv "PERL5LIB")))
5059 ;; The 'configure' script doesn't recognize things like
5060 ;; '--enable-fast-install'.
5061 (zero? (system* "./configure"
5062 (string-append "--build-prefix=" (getcwd) "/build")
5063 (string-append "--prefix=" out))))))
5064 (add-after 'unpack 'enter-dir
5065 (lambda _ (chdir "ngs-sdk") #t)))))
5066 (native-inputs `(("perl" ,perl)))
5067 ;; According to the test
5068 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5069 ;; in ngs-sdk/setup/konfigure.perl
5070 (supported-systems '("i686-linux" "x86_64-linux"))
5071 (home-page "https://github.com/ncbi/ngs")
5072 (synopsis "API for accessing Next Generation Sequencing data")
5074 "NGS is a domain-specific API for accessing reads, alignments and pileups
5075 produced from Next Generation Sequencing. The API itself is independent from
5076 any particular back-end implementation, and supports use of multiple back-ends
5078 (license license:public-domain)))
5080 (define-public java-ngs
5081 (package (inherit ngs-sdk)
5084 `(,@(substitute-keyword-arguments
5085 `(#:modules ((guix build gnu-build-system)
5089 ,@(package-arguments ngs-sdk))
5091 `(modify-phases ,phases
5092 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5094 `(("jdk" ,icedtea "jdk")
5095 ("ngs-sdk" ,ngs-sdk)))
5096 (synopsis "Java bindings for NGS SDK")))
5098 (define-public ncbi-vdb
5106 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5108 (file-name (string-append name "-" version ".tar.gz"))
5111 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5112 (build-system gnu-build-system)
5114 `(#:parallel-build? #f ; not supported
5115 #:tests? #f ; no "check" target
5117 (modify-phases %standard-phases
5118 (add-before 'configure 'set-perl-search-path
5120 ;; Work around "dotless @INC" build failure.
5122 (string-append (getcwd) "/setup:"
5123 (getenv "PERL5LIB")))
5126 (lambda* (#:key inputs outputs #:allow-other-keys)
5127 (let ((out (assoc-ref outputs "out")))
5128 ;; Override include path for libmagic
5129 (substitute* "setup/package.prl"
5130 (("name => 'magic', Include => '/usr/include'")
5131 (string-append "name=> 'magic', Include => '"
5132 (assoc-ref inputs "libmagic")
5135 ;; Install kdf5 library (needed by sra-tools)
5136 (substitute* "build/Makefile.install"
5137 (("LIBRARIES_TO_INSTALL =")
5138 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5140 (substitute* "build/Makefile.env"
5141 (("CFLAGS =" prefix)
5142 (string-append prefix "-msse2 ")))
5144 ;; Override search path for ngs-java
5145 (substitute* "setup/package.prl"
5146 (("/usr/local/ngs/ngs-java")
5147 (assoc-ref inputs "java-ngs")))
5149 ;; The 'configure' script doesn't recognize things like
5150 ;; '--enable-fast-install'.
5153 (string-append "--build-prefix=" (getcwd) "/build")
5154 (string-append "--prefix=" (assoc-ref outputs "out"))
5155 (string-append "--debug")
5156 (string-append "--with-xml2-prefix="
5157 (assoc-ref inputs "libxml2"))
5158 (string-append "--with-ngs-sdk-prefix="
5159 (assoc-ref inputs "ngs-sdk"))
5160 (string-append "--with-hdf5-prefix="
5161 (assoc-ref inputs "hdf5")))))))
5162 (add-after 'install 'install-interfaces
5163 (lambda* (#:key outputs #:allow-other-keys)
5164 ;; Install interface libraries. On i686 the interface libraries
5165 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5166 ;; architecture name ("i386") instead of the target system prefix
5168 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5169 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5170 ,(system->linux-architecture
5171 (or (%current-target-system)
5174 (string-append (assoc-ref outputs "out")
5176 ;; Install interface headers
5177 (copy-recursively "interfaces"
5178 (string-append (assoc-ref outputs "out")
5181 ;; These files are needed by sra-tools.
5182 (add-after 'install 'install-configuration-files
5183 (lambda* (#:key outputs #:allow-other-keys)
5184 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5186 (install-file "libs/kfg/default.kfg" target)
5187 (install-file "libs/kfg/certs.kfg" target))
5190 `(("libxml2" ,libxml2)
5191 ("ngs-sdk" ,ngs-sdk)
5192 ("java-ngs" ,java-ngs)
5195 (native-inputs `(("perl" ,perl)))
5196 ;; NCBI-VDB requires SSE capability.
5197 (supported-systems '("i686-linux" "x86_64-linux"))
5198 (home-page "https://github.com/ncbi/ncbi-vdb")
5199 (synopsis "Database engine for genetic information")
5201 "The NCBI-VDB library implements a highly compressed columnar data
5202 warehousing engine that is most often used to store genetic information.
5203 Databases are stored in a portable image within the file system, and can be
5204 accessed/downloaded on demand across HTTP.")
5205 (license license:public-domain)))
5207 (define-public plink
5215 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5216 version "-src.zip"))
5218 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5219 (patches (search-patches "plink-1.07-unclobber-i.patch"
5220 "plink-endian-detection.patch"))))
5221 (build-system gnu-build-system)
5223 '(#:tests? #f ;no "check" target
5224 #:make-flags (list (string-append "LIB_LAPACK="
5225 (assoc-ref %build-inputs "lapack")
5226 "/lib/liblapack.so")
5229 ;; disable phoning home
5232 (modify-phases %standard-phases
5233 ;; no "configure" script
5236 (lambda* (#:key outputs #:allow-other-keys)
5237 (let ((bin (string-append (assoc-ref outputs "out")
5239 (install-file "plink" bin)
5243 ("lapack" ,lapack)))
5245 `(("unzip" ,unzip)))
5246 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5247 (synopsis "Whole genome association analysis toolset")
5249 "PLINK is a whole genome association analysis toolset, designed to
5250 perform a range of basic, large-scale analyses in a computationally efficient
5251 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5252 so there is no support for steps prior to this (e.g. study design and
5253 planning, generating genotype or CNV calls from raw data). Through
5254 integration with gPLINK and Haploview, there is some support for the
5255 subsequent visualization, annotation and storage of results.")
5256 ;; Code is released under GPLv2, except for fisher.h, which is under
5258 (license (list license:gpl2 license:lgpl2.1+))))
5260 (define-public plink-ng
5261 (package (inherit plink)
5267 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5269 (file-name (string-append name "-" version ".tar.gz"))
5271 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5272 (build-system gnu-build-system)
5274 '(#:tests? #f ;no "check" target
5275 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5276 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5278 "-f" "Makefile.std")
5280 (modify-phases %standard-phases
5281 (add-after 'unpack 'chdir
5282 (lambda _ (chdir "1.9") #t))
5283 (delete 'configure) ; no "configure" script
5285 (lambda* (#:key outputs #:allow-other-keys)
5286 (let ((bin (string-append (assoc-ref outputs "out")
5288 (install-file "plink" bin)
5293 ("openblas" ,openblas)))
5294 (home-page "https://www.cog-genomics.org/plink/")
5295 (license license:gpl3+)))
5297 (define-public smithlab-cpp
5298 (let ((revision "1")
5299 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5301 (name "smithlab-cpp")
5302 (version (string-append "0." revision "." (string-take commit 7)))
5306 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5308 (file-name (string-append name "-" version "-checkout"))
5311 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5312 (build-system gnu-build-system)
5314 `(#:modules ((guix build gnu-build-system)
5317 #:tests? #f ;no "check" target
5319 (modify-phases %standard-phases
5320 (add-after 'unpack 'use-samtools-headers
5322 (substitute* '("SAM.cpp"
5324 (("sam.h") "samtools/sam.h"))
5327 (lambda* (#:key outputs #:allow-other-keys)
5328 (let* ((out (assoc-ref outputs "out"))
5329 (lib (string-append out "/lib"))
5330 (include (string-append out "/include/smithlab-cpp")))
5333 (for-each (cut install-file <> lib)
5334 (find-files "." "\\.o$"))
5335 (for-each (cut install-file <> include)
5336 (find-files "." "\\.hpp$")))
5338 (delete 'configure))))
5340 `(("samtools" ,samtools-0.1)
5342 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5343 (synopsis "C++ helper library for functions used in Smith lab projects")
5345 "Smithlab CPP is a C++ library that includes functions used in many of
5346 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5347 structures, classes for genomic regions, mapped sequencing reads, etc.")
5348 (license license:gpl3+))))
5350 (define-public preseq
5356 (uri (string-append "https://github.com/smithlabcode/"
5357 "preseq/archive/v" version ".tar.gz"))
5358 (file-name (string-append name "-" version ".tar.gz"))
5360 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5361 (modules '((guix build utils)))
5363 ;; Remove bundled samtools.
5364 '(delete-file-recursively "samtools"))))
5365 (build-system gnu-build-system)
5367 `(#:tests? #f ;no "check" target
5369 (modify-phases %standard-phases
5370 (delete 'configure))
5372 (list (string-append "PREFIX="
5373 (assoc-ref %outputs "out"))
5374 (string-append "LIBBAM="
5375 (assoc-ref %build-inputs "samtools")
5377 (string-append "SMITHLAB_CPP="
5378 (assoc-ref %build-inputs "smithlab-cpp")
5381 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5384 ("samtools" ,samtools-0.1)
5385 ("smithlab-cpp" ,smithlab-cpp)
5387 (home-page "http://smithlabresearch.org/software/preseq/")
5388 (synopsis "Program for analyzing library complexity")
5390 "The preseq package is aimed at predicting and estimating the complexity
5391 of a genomic sequencing library, equivalent to predicting and estimating the
5392 number of redundant reads from a given sequencing depth and how many will be
5393 expected from additional sequencing using an initial sequencing experiment.
5394 The estimates can then be used to examine the utility of further sequencing,
5395 optimize the sequencing depth, or to screen multiple libraries to avoid low
5396 complexity samples.")
5397 (license license:gpl3+)))
5399 (define-public python-screed
5401 (name "python-screed")
5406 (uri (pypi-uri "screed" version))
5409 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5410 (build-system python-build-system)
5413 (modify-phases %standard-phases
5416 (setenv "PYTHONPATH"
5417 (string-append (getenv "PYTHONPATH") ":."))
5418 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5420 `(("python-nose" ,python-nose)))
5422 `(("python-bz2file" ,python-bz2file)))
5423 (home-page "https://github.com/dib-lab/screed/")
5424 (synopsis "Short read sequence database utilities")
5425 (description "Screed parses FASTA and FASTQ files and generates databases.
5426 Values such as sequence name, sequence description, sequence quality and the
5427 sequence itself can be retrieved from these databases.")
5428 (license license:bsd-3)))
5430 (define-public python2-screed
5431 (package-with-python2 python-screed))
5433 (define-public sra-tools
5441 (string-append "https://github.com/ncbi/sra-tools/archive/"
5443 (file-name (string-append name "-" version ".tar.gz"))
5446 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5447 (build-system gnu-build-system)
5449 `(#:parallel-build? #f ; not supported
5450 #:tests? #f ; no "check" target
5452 (list (string-append "DEFAULT_CRT="
5453 (assoc-ref %build-inputs "ncbi-vdb")
5455 (string-append "DEFAULT_KFG="
5456 (assoc-ref %build-inputs "ncbi-vdb")
5458 (string-append "VDB_LIBDIR="
5459 (assoc-ref %build-inputs "ncbi-vdb")
5460 ,(if (string-prefix? "x86_64"
5461 (or (%current-target-system)
5466 (modify-phases %standard-phases
5467 (add-before 'configure 'set-perl-search-path
5469 ;; Work around "dotless @INC" build failure.
5471 (string-append (getcwd) "/setup:"
5472 (getenv "PERL5LIB")))
5475 (lambda* (#:key inputs outputs #:allow-other-keys)
5476 ;; The build system expects a directory containing the sources and
5477 ;; raw build output of ncbi-vdb, including files that are not
5478 ;; installed. Since we are building against an installed version of
5479 ;; ncbi-vdb, the following modifications are needed.
5480 (substitute* "setup/konfigure.perl"
5481 ;; Make the configure script look for the "ilib" directory of
5482 ;; "ncbi-vdb" without first checking for the existence of a
5483 ;; matching library in its "lib" directory.
5484 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5485 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5486 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5487 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5488 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5491 (substitute* "tools/copycat/Makefile"
5492 (("smagic-static") "lmagic"))
5494 ;; The 'configure' script doesn't recognize things like
5495 ;; '--enable-fast-install'.
5498 (string-append "--build-prefix=" (getcwd) "/build")
5499 (string-append "--prefix=" (assoc-ref outputs "out"))
5500 (string-append "--debug")
5501 (string-append "--with-fuse-prefix="
5502 (assoc-ref inputs "fuse"))
5503 (string-append "--with-magic-prefix="
5504 (assoc-ref inputs "libmagic"))
5505 ;; TODO: building with libxml2 fails with linker errors
5506 ;; (string-append "--with-xml2-prefix="
5507 ;; (assoc-ref inputs "libxml2"))
5508 (string-append "--with-ncbi-vdb-sources="
5509 (assoc-ref inputs "ncbi-vdb"))
5510 (string-append "--with-ncbi-vdb-build="
5511 (assoc-ref inputs "ncbi-vdb"))
5512 (string-append "--with-ngs-sdk-prefix="
5513 (assoc-ref inputs "ngs-sdk"))
5514 (string-append "--with-hdf5-prefix="
5515 (assoc-ref inputs "hdf5"))))))
5516 ;; This version of sra-tools fails to build with glibc because of a
5517 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5518 ;; contains a definition of "canonicalize", so we rename it.
5520 ;; See upstream bug report:
5521 ;; https://github.com/ncbi/sra-tools/issues/67
5522 (add-after 'unpack 'patch-away-glibc-conflict
5524 (substitute* "tools/bam-loader/bam.c"
5525 (("canonicalize\\(" line)
5526 (string-append "sra_tools_" line)))
5528 (native-inputs `(("perl" ,perl)))
5530 `(("ngs-sdk" ,ngs-sdk)
5531 ("ncbi-vdb" ,ncbi-vdb)
5536 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5537 (synopsis "Tools and libraries for reading and writing sequencing data")
5539 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5540 reading of sequencing files from the Sequence Read Archive (SRA) database and
5541 writing files into the .sra format.")
5542 (license license:public-domain)))
5544 (define-public seqan
5550 (uri (string-append "http://packages.seqan.de/seqan-library/"
5551 "seqan-library-" version ".tar.bz2"))
5554 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5555 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5556 ;; makes sense to split the outputs.
5557 (outputs '("out" "doc"))
5558 (build-system trivial-build-system)
5560 `(#:modules ((guix build utils))
5563 (use-modules (guix build utils))
5564 (let ((tar (assoc-ref %build-inputs "tar"))
5565 (bzip (assoc-ref %build-inputs "bzip2"))
5566 (out (assoc-ref %outputs "out"))
5567 (doc (assoc-ref %outputs "doc")))
5568 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5569 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5570 (chdir (string-append "seqan-library-" ,version))
5571 (copy-recursively "include" (string-append out "/include"))
5572 (copy-recursively "share" (string-append doc "/share"))))))
5574 `(("source" ,source)
5577 (home-page "http://www.seqan.de")
5578 (synopsis "Library for nucleotide sequence analysis")
5580 "SeqAn is a C++ library of efficient algorithms and data structures for
5581 the analysis of sequences with the focus on biological data. It contains
5582 algorithms and data structures for string representation and their
5583 manipulation, online and indexed string search, efficient I/O of
5584 bioinformatics file formats, sequence alignment, and more.")
5585 (license license:bsd-3)))
5587 (define-public seqmagick
5594 (uri (pypi-uri "seqmagick" version))
5597 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5598 (build-system python-build-system)
5600 `(("python-biopython" ,python-biopython)))
5602 `(("python-nose" ,python-nose)))
5603 (home-page "https://github.com/fhcrc/seqmagick")
5604 (synopsis "Tools for converting and modifying sequence files")
5606 "Bioinformaticians often have to convert sequence files between formats
5607 and do little manipulations on them, and it's not worth writing scripts for
5608 that. Seqmagick is a utility to expose the file format conversion in
5609 BioPython in a convenient way. Instead of having a big mess of scripts, there
5610 is one that takes arguments.")
5611 (license license:gpl3)))
5613 (define-public seqtk
5620 "https://github.com/lh3/seqtk/archive/v"
5622 (file-name (string-append name "-" version ".tar.gz"))
5625 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5626 (modules '((guix build utils)))
5629 ;; Remove extraneous header files, as is done in the seqtk
5631 (for-each (lambda (file) (delete-file file))
5632 (list "ksort.h" "kstring.h" "kvec.h"))
5634 (build-system gnu-build-system)
5637 (modify-phases %standard-phases
5640 ;; There are no tests, so we just run a sanity check.
5641 (lambda _ (zero? (system* "./seqtk" "seq"))))
5643 (lambda* (#:key outputs #:allow-other-keys)
5644 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5645 (install-file "seqtk" bin)))))))
5648 (home-page "https://github.com/lh3/seqtk")
5649 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5651 "Seqtk is a fast and lightweight tool for processing sequences in the
5652 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5653 optionally compressed by gzip.")
5654 (license license:expat)))
5656 (define-public snap-aligner
5658 (name "snap-aligner")
5659 (version "1.0beta.18")
5663 "https://github.com/amplab/snap/archive/v"
5665 (file-name (string-append name "-" version ".tar.gz"))
5668 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5669 (build-system gnu-build-system)
5672 (modify-phases %standard-phases
5674 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5676 (lambda* (#:key outputs #:allow-other-keys)
5677 (let* ((out (assoc-ref outputs "out"))
5678 (bin (string-append out "/bin")))
5679 (install-file "snap-aligner" bin)
5680 (install-file "SNAPCommand" bin)
5684 (home-page "http://snap.cs.berkeley.edu/")
5685 (synopsis "Short read DNA sequence aligner")
5687 "SNAP is a fast and accurate aligner for short DNA reads. It is
5688 optimized for modern read lengths of 100 bases or higher, and takes advantage
5689 of these reads to align data quickly through a hash-based indexing scheme.")
5690 ;; 32-bit systems are not supported by the unpatched code.
5691 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5692 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5693 ;; systems without a lot of memory cannot make good use of this program.
5694 (supported-systems '("x86_64-linux"))
5695 (license license:asl2.0)))
5697 (define-public sortmerna
5705 "https://github.com/biocore/sortmerna/archive/"
5707 (file-name (string-append name "-" version ".tar.gz"))
5710 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5711 (build-system gnu-build-system)
5712 (outputs '("out" ;for binaries
5713 "db")) ;for sequence databases
5716 (modify-phases %standard-phases
5718 (lambda* (#:key outputs #:allow-other-keys)
5719 (let* ((out (assoc-ref outputs "out"))
5720 (bin (string-append out "/bin"))
5721 (db (assoc-ref outputs "db"))
5723 (string-append db "/share/sortmerna/rRNA_databases")))
5724 (install-file "sortmerna" bin)
5725 (install-file "indexdb_rna" bin)
5726 (for-each (lambda (file)
5727 (install-file file share))
5728 (find-files "rRNA_databases" ".*fasta"))
5732 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5733 (synopsis "Biological sequence analysis tool for NGS reads")
5735 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5736 and operational taxonomic unit (OTU) picking of next generation
5737 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5738 allows for fast and sensitive analyses of nucleotide sequences. The main
5739 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5740 ;; The source includes x86 specific code
5741 (supported-systems '("x86_64-linux" "i686-linux"))
5742 (license license:lgpl3)))
5750 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5752 (file-name (string-append name "-" version ".tar.gz"))
5755 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5756 (modules '((guix build utils)))
5759 (substitute* "source/Makefile"
5761 ;; Remove pre-built binaries and bundled htslib sources.
5762 (delete-file-recursively "bin/MacOSX_x86_64")
5763 (delete-file-recursively "bin/Linux_x86_64")
5764 (delete-file-recursively "bin/Linux_x86_64_static")
5765 (delete-file-recursively "source/htslib")
5767 (build-system gnu-build-system)
5769 '(#:tests? #f ;no check target
5770 #:make-flags '("STAR")
5772 (modify-phases %standard-phases
5773 (add-after 'unpack 'enter-source-dir
5774 (lambda _ (chdir "source") #t))
5775 (add-after 'enter-source-dir 'make-reproducible
5777 (substitute* "Makefile"
5778 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5779 (string-append pre "Built with Guix" post)))))
5780 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5782 (substitute* "Makefile"
5783 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5785 (substitute* '("BAMfunctions.cpp"
5790 "bamRemoveDuplicates.cpp")
5791 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5792 (string-append "#include <" header ">")))
5793 (substitute* "IncludeDefine.h"
5794 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5795 (string-append "<" header ">")))
5798 (lambda* (#:key outputs #:allow-other-keys)
5799 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5800 (install-file "STAR" bin))
5802 (delete 'configure))))
5806 `(("htslib" ,htslib)
5808 (home-page "https://github.com/alexdobin/STAR")
5809 (synopsis "Universal RNA-seq aligner")
5811 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5812 based on a previously undescribed RNA-seq alignment algorithm that uses
5813 sequential maximum mappable seed search in uncompressed suffix arrays followed
5814 by seed clustering and stitching procedure. In addition to unbiased de novo
5815 detection of canonical junctions, STAR can discover non-canonical splices and
5816 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5818 ;; Only 64-bit systems are supported according to the README.
5819 (supported-systems '("x86_64-linux" "mips64el-linux"))
5820 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5821 (license license:gpl3+)))
5823 (define-public subread
5829 (uri (string-append "mirror://sourceforge/subread/subread-"
5830 version "/subread-" version "-source.tar.gz"))
5833 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5834 (build-system gnu-build-system)
5836 `(#:tests? #f ;no "check" target
5837 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5838 ;; optimizations by default, so we override these flags such that x86_64
5839 ;; flags are only added when the build target is an x86_64 system.
5841 (list (let ((system ,(or (%current-target-system)
5843 (flags '("-ggdb" "-fomit-frame-pointer"
5844 "-ffast-math" "-funroll-loops"
5845 "-fmessage-length=0"
5846 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5848 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5849 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5850 (if (string-prefix? "x86_64" system)
5851 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5852 (string-append "CCFLAGS=" (string-join flags))))
5853 "-f" "Makefile.Linux"
5854 "CC=gcc ${CCFLAGS}")
5856 (modify-phases %standard-phases
5857 (add-after 'unpack 'enter-dir
5858 (lambda _ (chdir "src") #t))
5860 (lambda* (#:key outputs #:allow-other-keys)
5861 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5863 (copy-recursively "../bin" bin))))
5864 ;; no "configure" script
5865 (delete 'configure))))
5866 (inputs `(("zlib" ,zlib)))
5867 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5868 (synopsis "Tool kit for processing next-gen sequencing data")
5870 "The subread package contains the following tools: subread aligner, a
5871 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5872 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5873 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5874 against local background noises.")
5875 (license license:gpl3+)))
5877 (define-public stringtie
5883 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5884 "stringtie-" version ".tar.gz"))
5887 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5888 (modules '((guix build utils)))
5891 (delete-file-recursively "samtools-0.1.18")
5893 (build-system gnu-build-system)
5895 `(#:tests? #f ;no test suite
5897 (modify-phases %standard-phases
5898 ;; no configure script
5900 (add-before 'build 'use-system-samtools
5902 (substitute* "Makefile"
5903 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5905 (substitute* '("gclib/GBam.h"
5907 (("#include \"(bam|sam|kstring).h\"" _ header)
5908 (string-append "#include <samtools/" header ".h>")))
5910 (add-after 'unpack 'remove-duplicate-typedef
5912 ;; This typedef conflicts with the typedef in
5913 ;; glibc-2.25/include/bits/types.h
5914 (substitute* "gclib/GThreads.h"
5915 (("typedef long long __intmax_t;") ""))
5918 (lambda* (#:key outputs #:allow-other-keys)
5919 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5920 (install-file "stringtie" bin)
5923 `(("samtools" ,samtools-0.1)
5925 (home-page "http://ccb.jhu.edu/software/stringtie/")
5926 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5928 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5929 alignments into potential transcripts. It uses a novel network flow algorithm
5930 as well as an optional de novo assembly step to assemble and quantitate
5931 full-length transcripts representing multiple splice variants for each gene
5932 locus. Its input can include not only the alignments of raw reads used by
5933 other transcript assemblers, but also alignments of longer sequences that have
5934 been assembled from those reads. To identify differentially expressed genes
5935 between experiments, StringTie's output can be processed either by the
5936 Cuffdiff or Ballgown programs.")
5937 (license license:artistic2.0)))
5939 (define-public taxtastic
5945 (uri (pypi-uri "taxtastic" version))
5948 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5949 (build-system python-build-system)
5951 `(#:python ,python-2
5953 (modify-phases %standard-phases
5956 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5958 `(("python-sqlalchemy" ,python2-sqlalchemy)
5959 ("python-decorator" ,python2-decorator)
5960 ("python-biopython" ,python2-biopython)
5961 ("python-pandas" ,python2-pandas)))
5962 (home-page "https://github.com/fhcrc/taxtastic")
5963 (synopsis "Tools for taxonomic naming and annotation")
5965 "Taxtastic is software written in python used to build and maintain
5966 reference packages i.e. collections of reference trees, reference alignments,
5967 profiles, and associated taxonomic information.")
5968 (license license:gpl3+)))
5970 (define-public vcftools
5977 "https://github.com/vcftools/vcftools/releases/download/v"
5978 version "/vcftools-" version ".tar.gz"))
5981 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5982 (build-system gnu-build-system)
5984 `(#:tests? #f ; no "check" target
5986 "CFLAGS=-O2" ; override "-m64" flag
5987 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5988 (string-append "MANDIR=" (assoc-ref %outputs "out")
5989 "/share/man/man1"))))
5991 `(("pkg-config" ,pkg-config)))
5995 (home-page "https://vcftools.github.io/")
5996 (synopsis "Tools for working with VCF files")
5998 "VCFtools is a program package designed for working with VCF files, such
5999 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6000 provide easily accessible methods for working with complex genetic variation
6001 data in the form of VCF files.")
6002 ;; The license is declared as LGPLv3 in the README and
6003 ;; at https://vcftools.github.io/license.html
6004 (license license:lgpl3)))
6006 (define-public infernal
6012 (uri (string-append "http://eddylab.org/software/infernal/"
6013 "infernal-" version ".tar.gz"))
6016 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6017 (build-system gnu-build-system)
6019 `(("perl" ,perl))) ; for tests
6020 (home-page "http://eddylab.org/infernal/")
6021 (synopsis "Inference of RNA alignments")
6022 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6023 searching DNA sequence databases for RNA structure and sequence similarities.
6024 It is an implementation of a special case of profile stochastic context-free
6025 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6026 profile, but it scores a combination of sequence consensus and RNA secondary
6027 structure consensus, so in many cases, it is more capable of identifying RNA
6028 homologs that conserve their secondary structure more than their primary
6030 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6031 (supported-systems '("i686-linux" "x86_64-linux"))
6032 (license license:bsd-3)))
6034 (define-public r-centipede
6036 (name "r-centipede")
6040 (uri (string-append "http://download.r-forge.r-project.org/"
6041 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6044 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6045 (build-system r-build-system)
6046 (home-page "http://centipede.uchicago.edu/")
6047 (synopsis "Predict transcription factor binding sites")
6049 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6050 of the genome that are bound by particular transcription factors. It starts
6051 by identifying a set of candidate binding sites, and then aims to classify the
6052 sites according to whether each site is bound or not bound by a transcription
6053 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6054 between two different types of motif instances using as much relevant
6055 information as possible.")
6056 (license (list license:gpl2+ license:gpl3+))))
6058 (define-public r-vegan
6065 (uri (cran-uri "vegan" version))
6068 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
6069 (build-system r-build-system)
6071 `(("gfortran" ,gfortran)))
6073 `(("r-cluster" ,r-cluster)
6074 ("r-lattice" ,r-lattice)
6077 ("r-permute" ,r-permute)))
6078 (home-page "https://cran.r-project.org/web/packages/vegan")
6079 (synopsis "Functions for community ecology")
6081 "The vegan package provides tools for descriptive community ecology. It
6082 has most basic functions of diversity analysis, community ordination and
6083 dissimilarity analysis. Most of its multivariate tools can be used for other
6084 data types as well.")
6085 (license license:gpl2+)))
6087 (define-public r-annotate
6094 (uri (bioconductor-uri "annotate" version))
6097 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
6098 (build-system r-build-system)
6100 `(("r-annotationdbi" ,r-annotationdbi)
6101 ("r-biobase" ,r-biobase)
6102 ("r-biocgenerics" ,r-biocgenerics)
6104 ("r-rcurl" ,r-rcurl)
6106 ("r-xtable" ,r-xtable)))
6108 "https://bioconductor.org/packages/annotate")
6109 (synopsis "Annotation for microarrays")
6110 (description "This package provides R environments for the annotation of
6112 (license license:artistic2.0)))
6114 (define-public r-copynumber
6116 (name "r-copynumber")
6120 (uri (bioconductor-uri "copynumber" version))
6123 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6124 (build-system r-build-system)
6126 `(("r-s4vectors" ,r-s4vectors)
6127 ("r-iranges" ,r-iranges)
6128 ("r-genomicranges" ,r-genomicranges)
6129 ("r-biocgenerics" ,r-biocgenerics)))
6130 (home-page "https://bioconductor.org/packages/copynumber")
6131 (synopsis "Segmentation of single- and multi-track copy number data")
6133 "This package segments single- and multi-track copy number data by a
6134 penalized least squares regression method.")
6135 (license license:artistic2.0)))
6137 (define-public r-geneplotter
6139 (name "r-geneplotter")
6144 (uri (bioconductor-uri "geneplotter" version))
6147 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6148 (build-system r-build-system)
6150 `(("r-annotate" ,r-annotate)
6151 ("r-annotationdbi" ,r-annotationdbi)
6152 ("r-biobase" ,r-biobase)
6153 ("r-biocgenerics" ,r-biocgenerics)
6154 ("r-lattice" ,r-lattice)
6155 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6156 (home-page "https://bioconductor.org/packages/geneplotter")
6157 (synopsis "Graphics functions for genomic data")
6159 "This package provides functions for plotting genomic data.")
6160 (license license:artistic2.0)))
6162 (define-public r-genefilter
6164 (name "r-genefilter")
6169 (uri (bioconductor-uri "genefilter" version))
6172 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6173 (build-system r-build-system)
6175 `(("gfortran" ,gfortran)))
6177 `(("r-annotate" ,r-annotate)
6178 ("r-annotationdbi" ,r-annotationdbi)
6179 ("r-biobase" ,r-biobase)
6180 ("r-s4vectors" ,r-s4vectors)
6181 ("r-survival" ,r-survival)))
6182 (home-page "https://bioconductor.org/packages/genefilter")
6183 (synopsis "Filter genes from high-throughput experiments")
6185 "This package provides basic functions for filtering genes from
6186 high-throughput sequencing experiments.")
6187 (license license:artistic2.0)))
6189 (define-public r-deseq2
6196 (uri (bioconductor-uri "DESeq2" version))
6199 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6200 (properties `((upstream-name . "DESeq2")))
6201 (build-system r-build-system)
6203 `(("r-biobase" ,r-biobase)
6204 ("r-biocgenerics" ,r-biocgenerics)
6205 ("r-biocparallel" ,r-biocparallel)
6206 ("r-genefilter" ,r-genefilter)
6207 ("r-geneplotter" ,r-geneplotter)
6208 ("r-genomicranges" ,r-genomicranges)
6209 ("r-ggplot2" ,r-ggplot2)
6210 ("r-hmisc" ,r-hmisc)
6211 ("r-iranges" ,r-iranges)
6212 ("r-locfit" ,r-locfit)
6214 ("r-rcpparmadillo" ,r-rcpparmadillo)
6215 ("r-s4vectors" ,r-s4vectors)
6216 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6217 (home-page "https://bioconductor.org/packages/DESeq2")
6218 (synopsis "Differential gene expression analysis")
6220 "This package provides functions to estimate variance-mean dependence in
6221 count data from high-throughput nucleotide sequencing assays and test for
6222 differential expression based on a model using the negative binomial
6224 (license license:lgpl3+)))
6226 (define-public r-dexseq
6233 (uri (bioconductor-uri "DEXSeq" version))
6236 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6237 (properties `((upstream-name . "DEXSeq")))
6238 (build-system r-build-system)
6240 `(("r-annotationdbi" ,r-annotationdbi)
6241 ("r-biobase" ,r-biobase)
6242 ("r-biocgenerics" ,r-biocgenerics)
6243 ("r-biocparallel" ,r-biocparallel)
6244 ("r-biomart" ,r-biomart)
6245 ("r-deseq2" ,r-deseq2)
6246 ("r-genefilter" ,r-genefilter)
6247 ("r-geneplotter" ,r-geneplotter)
6248 ("r-genomicranges" ,r-genomicranges)
6249 ("r-hwriter" ,r-hwriter)
6250 ("r-iranges" ,r-iranges)
6251 ("r-rcolorbrewer" ,r-rcolorbrewer)
6252 ("r-rsamtools" ,r-rsamtools)
6253 ("r-s4vectors" ,r-s4vectors)
6254 ("r-statmod" ,r-statmod)
6255 ("r-stringr" ,r-stringr)
6256 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6257 (home-page "https://bioconductor.org/packages/DEXSeq")
6258 (synopsis "Inference of differential exon usage in RNA-Seq")
6260 "This package is focused on finding differential exon usage using RNA-seq
6261 exon counts between samples with different experimental designs. It provides
6262 functions that allows the user to make the necessary statistical tests based
6263 on a model that uses the negative binomial distribution to estimate the
6264 variance between biological replicates and generalized linear models for
6265 testing. The package also provides functions for the visualization and
6266 exploration of the results.")
6267 (license license:gpl3+)))
6269 (define-public r-annotationforge
6271 (name "r-annotationforge")
6276 (uri (bioconductor-uri "AnnotationForge" version))
6279 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6281 `((upstream-name . "AnnotationForge")))
6282 (build-system r-build-system)
6284 `(("r-annotationdbi" ,r-annotationdbi)
6285 ("r-biobase" ,r-biobase)
6286 ("r-biocgenerics" ,r-biocgenerics)
6288 ("r-rcurl" ,r-rcurl)
6289 ("r-rsqlite" ,r-rsqlite)
6290 ("r-s4vectors" ,r-s4vectors)
6292 (home-page "https://bioconductor.org/packages/AnnotationForge")
6293 (synopsis "Code for building annotation database packages")
6295 "This package provides code for generating Annotation packages and their
6296 databases. Packages produced are intended to be used with AnnotationDbi.")
6297 (license license:artistic2.0)))
6299 (define-public r-rbgl
6306 (uri (bioconductor-uri "RBGL" version))
6309 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6310 (properties `((upstream-name . "RBGL")))
6311 (build-system r-build-system)
6312 (propagated-inputs `(("r-graph" ,r-graph)))
6313 (home-page "https://www.bioconductor.org/packages/RBGL")
6314 (synopsis "Interface to the Boost graph library")
6316 "This package provides a fairly extensive and comprehensive interface to
6317 the graph algorithms contained in the Boost library.")
6318 (license license:artistic2.0)))
6320 (define-public r-gseabase
6327 (uri (bioconductor-uri "GSEABase" version))
6330 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6331 (properties `((upstream-name . "GSEABase")))
6332 (build-system r-build-system)
6334 `(("r-annotate" ,r-annotate)
6335 ("r-annotationdbi" ,r-annotationdbi)
6336 ("r-biobase" ,r-biobase)
6337 ("r-biocgenerics" ,r-biocgenerics)
6338 ("r-graph" ,r-graph)
6340 (home-page "https://bioconductor.org/packages/GSEABase")
6341 (synopsis "Gene set enrichment data structures and methods")
6343 "This package provides classes and methods to support @dfn{Gene Set
6344 Enrichment Analysis} (GSEA).")
6345 (license license:artistic2.0)))
6347 (define-public r-category
6354 (uri (bioconductor-uri "Category" version))
6357 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6358 (properties `((upstream-name . "Category")))
6359 (build-system r-build-system)
6361 `(("r-annotate" ,r-annotate)
6362 ("r-annotationdbi" ,r-annotationdbi)
6363 ("r-biobase" ,r-biobase)
6364 ("r-biocgenerics" ,r-biocgenerics)
6365 ("r-genefilter" ,r-genefilter)
6366 ("r-graph" ,r-graph)
6367 ("r-gseabase" ,r-gseabase)
6368 ("r-matrix" ,r-matrix)
6371 (home-page "https://bioconductor.org/packages/Category")
6372 (synopsis "Category analysis")
6374 "This package provides a collection of tools for performing category
6376 (license license:artistic2.0)))
6378 (define-public r-gostats
6385 (uri (bioconductor-uri "GOstats" version))
6388 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6389 (properties `((upstream-name . "GOstats")))
6390 (build-system r-build-system)
6392 `(("r-annotate" ,r-annotate)
6393 ("r-annotationdbi" ,r-annotationdbi)
6394 ("r-annotationforge" ,r-annotationforge)
6395 ("r-biobase" ,r-biobase)
6396 ("r-category" ,r-category)
6397 ("r-go-db" ,r-go-db)
6398 ("r-graph" ,r-graph)
6399 ("r-rgraphviz" ,r-rgraphviz)
6400 ("r-rbgl" ,r-rbgl)))
6401 (home-page "https://bioconductor.org/packages/GOstats")
6402 (synopsis "Tools for manipulating GO and microarrays")
6404 "This package provides a set of tools for interacting with GO and
6405 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6406 testing and other simple calculations.")
6407 (license license:artistic2.0)))
6409 (define-public r-shortread
6411 (name "r-shortread")
6416 (uri (bioconductor-uri "ShortRead" version))
6419 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6420 (properties `((upstream-name . "ShortRead")))
6421 (build-system r-build-system)
6425 `(("r-biobase" ,r-biobase)
6426 ("r-biocgenerics" ,r-biocgenerics)
6427 ("r-biocparallel" ,r-biocparallel)
6428 ("r-biostrings" ,r-biostrings)
6429 ("r-genomeinfodb" ,r-genomeinfodb)
6430 ("r-genomicalignments" ,r-genomicalignments)
6431 ("r-genomicranges" ,r-genomicranges)
6432 ("r-hwriter" ,r-hwriter)
6433 ("r-iranges" ,r-iranges)
6434 ("r-lattice" ,r-lattice)
6435 ("r-latticeextra" ,r-latticeextra)
6436 ("r-rsamtools" ,r-rsamtools)
6437 ("r-s4vectors" ,r-s4vectors)
6438 ("r-xvector" ,r-xvector)
6439 ("r-zlibbioc" ,r-zlibbioc)))
6440 (home-page "https://bioconductor.org/packages/ShortRead")
6441 (synopsis "FASTQ input and manipulation tools")
6443 "This package implements sampling, iteration, and input of FASTQ files.
6444 It includes functions for filtering and trimming reads, and for generating a
6445 quality assessment report. Data are represented as
6446 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6447 purposes. The package also contains legacy support for early single-end,
6448 ungapped alignment formats.")
6449 (license license:artistic2.0)))
6451 (define-public r-systempiper
6453 (name "r-systempiper")
6458 (uri (bioconductor-uri "systemPipeR" version))
6461 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6462 (properties `((upstream-name . "systemPipeR")))
6463 (build-system r-build-system)
6465 `(("r-annotate" ,r-annotate)
6466 ("r-batchjobs" ,r-batchjobs)
6467 ("r-biocgenerics" ,r-biocgenerics)
6468 ("r-biostrings" ,r-biostrings)
6469 ("r-deseq2" ,r-deseq2)
6470 ("r-edger" ,r-edger)
6471 ("r-genomicfeatures" ,r-genomicfeatures)
6472 ("r-genomicranges" ,r-genomicranges)
6473 ("r-ggplot2" ,r-ggplot2)
6474 ("r-go-db" ,r-go-db)
6475 ("r-gostats" ,r-gostats)
6476 ("r-limma" ,r-limma)
6477 ("r-pheatmap" ,r-pheatmap)
6478 ("r-rjson" ,r-rjson)
6479 ("r-rsamtools" ,r-rsamtools)
6480 ("r-shortread" ,r-shortread)
6481 ("r-summarizedexperiment" ,r-summarizedexperiment)
6482 ("r-variantannotation" ,r-variantannotation)))
6483 (home-page "https://github.com/tgirke/systemPipeR")
6484 (synopsis "Next generation sequencing workflow and reporting environment")
6486 "This R package provides tools for building and running automated
6487 end-to-end analysis workflows for a wide range of @dfn{next generation
6488 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6489 Important features include a uniform workflow interface across different NGS
6490 applications, automated report generation, and support for running both R and
6491 command-line software, such as NGS aligners or peak/variant callers, on local
6492 computers or compute clusters. Efficient handling of complex sample sets and
6493 experimental designs is facilitated by a consistently implemented sample
6494 annotation infrastructure.")
6495 (license license:artistic2.0)))
6497 (define-public r-grohmm
6504 (uri (bioconductor-uri "groHMM" version))
6507 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6508 (properties `((upstream-name . "groHMM")))
6509 (build-system r-build-system)
6511 `(("r-genomeinfodb" ,r-genomeinfodb)
6512 ("r-genomicalignments" ,r-genomicalignments)
6513 ("r-genomicranges" ,r-genomicranges)
6514 ("r-iranges" ,r-iranges)
6516 ("r-rtracklayer" ,r-rtracklayer)
6517 ("r-s4vectors" ,r-s4vectors)))
6518 (home-page "https://github.com/Kraus-Lab/groHMM")
6519 (synopsis "GRO-seq analysis pipeline")
6521 "This package provides a pipeline for the analysis of GRO-seq data.")
6522 (license license:gpl3+)))
6524 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6526 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6530 ;; We cannot use bioconductor-uri here because this tarball is
6531 ;; located under "data/annotation/" instead of "bioc/".
6532 (uri (string-append "https://bioconductor.org/packages/"
6533 "release/data/annotation/src/contrib"
6534 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6538 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6540 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6541 (build-system r-build-system)
6542 ;; As this package provides little more than a very large data file it
6543 ;; doesn't make sense to build substitutes.
6544 (arguments `(#:substitutable? #f))
6546 `(("r-genomicfeatures" ,r-genomicfeatures)))
6548 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6549 (synopsis "Annotation package for human genome in TxDb format")
6551 "This package provides an annotation database of Homo sapiens genome
6552 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6553 track. The database is exposed as a @code{TxDb} object.")
6554 (license license:artistic2.0)))
6556 (define-public r-sparql
6562 (uri (cran-uri "SPARQL" version))
6565 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6566 (properties `((upstream-name . "SPARQL")))
6567 (build-system r-build-system)
6569 `(("r-rcurl" ,r-rcurl)
6571 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6572 (synopsis "SPARQL client for R")
6573 (description "This package provides an interface to use SPARQL to pose
6574 SELECT or UPDATE queries to an end-point.")
6575 ;; The only license indication is found in the DESCRIPTION file,
6576 ;; which states GPL-3. So we cannot assume GPLv3+.
6577 (license license:gpl3)))
6579 (define-public vsearch
6587 "https://github.com/torognes/vsearch/archive/v"
6589 (file-name (string-append name "-" version ".tar.gz"))
6592 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6593 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6596 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6597 ;; for this in the patch.
6598 (delete-file "src/city.h")
6599 (delete-file "src/citycrc.h")
6600 (delete-file "src/city.cc")
6602 (build-system gnu-build-system)
6605 (modify-phases %standard-phases
6606 (add-after 'unpack 'autogen
6607 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6611 ("cityhash" ,cityhash)))
6613 `(("autoconf" ,autoconf)
6614 ("automake" ,automake)))
6615 (synopsis "Sequence search tools for metagenomics")
6617 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6618 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6619 masking. The tool takes advantage of parallelism in the form of SIMD
6620 vectorization as well as multiple threads to perform accurate alignments at
6621 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6622 Needleman-Wunsch).")
6623 (home-page "https://github.com/torognes/vsearch")
6624 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6626 (supported-systems '("x86_64-linux"))
6627 ;; Dual licensed; also includes public domain source.
6628 (license (list license:gpl3 license:bsd-2))))
6630 (define-public pardre
6633 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6638 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6642 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6643 (build-system gnu-build-system)
6645 `(#:tests? #f ; no tests included
6647 (modify-phases %standard-phases
6650 (lambda* (#:key outputs #:allow-other-keys)
6651 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6652 (install-file "ParDRe" bin)
6655 `(("openmpi" ,openmpi)
6657 (synopsis "Parallel tool to remove duplicate DNA reads")
6659 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6660 Duplicate reads can be seen as identical or nearly identical sequences with
6661 some mismatches. This tool lets users avoid the analysis of unnecessary
6662 reads, reducing the time of subsequent procedures with the
6663 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6664 in order to exploit the parallel capabilities of multicore clusters. It is
6665 faster than multithreaded counterparts (end of 2015) for the same number of
6666 cores and, thanks to the message-passing technology, it can be executed on
6668 (home-page "https://sourceforge.net/projects/pardre/")
6669 (license license:gpl3+)))
6671 (define-public ruby-bio-kseq
6673 (name "ruby-bio-kseq")
6678 (uri (rubygems-uri "bio-kseq" version))
6681 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6682 (build-system ruby-build-system)
6684 `(#:test-target "spec"))
6686 `(("bundler" ,bundler)
6687 ("ruby-rspec" ,ruby-rspec)
6688 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6691 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6693 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6694 FASTQ parsing code. It provides a fast iterator over sequences and their
6696 (home-page "https://github.com/gusevfe/bio-kseq")
6697 (license license:expat)))
6699 (define-public bio-locus
6706 (uri (rubygems-uri "bio-locus" version))
6709 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6710 (build-system ruby-build-system)
6712 `(("ruby-rspec" ,ruby-rspec)))
6713 (synopsis "Tool for fast querying of genome locations")
6715 "Bio-locus is a tabix-like tool for fast querying of genome
6716 locations. Many file formats in bioinformatics contain records that
6717 start with a chromosome name and a position for a SNP, or a start-end
6718 position for indels. Bio-locus allows users to store this chr+pos or
6719 chr+pos+alt information in a database.")
6720 (home-page "https://github.com/pjotrp/bio-locus")
6721 (license license:expat)))
6723 (define-public bio-blastxmlparser
6725 (name "bio-blastxmlparser")
6729 (uri (rubygems-uri "bio-blastxmlparser" version))
6732 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6733 (build-system ruby-build-system)
6735 `(("ruby-bio-logger" ,ruby-bio-logger)
6736 ("ruby-nokogiri" ,ruby-nokogiri)))
6738 `(("ruby-rspec" ,ruby-rspec)))
6739 (synopsis "Fast big data BLAST XML parser and library")
6741 "Very fast parallel big-data BLAST XML file parser which can be used as
6742 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6743 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6744 (home-page "https://github.com/pjotrp/blastxmlparser")
6745 (license license:expat)))
6747 (define-public bioruby
6754 (uri (rubygems-uri "bio" version))
6757 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6758 (build-system ruby-build-system)
6760 `(("ruby-libxml" ,ruby-libxml)))
6762 `(("which" ,which))) ; required for test phase
6765 (modify-phases %standard-phases
6766 (add-before 'build 'patch-test-command
6768 (substitute* '("test/functional/bio/test_command.rb")
6769 (("/bin/sh") (which "sh")))
6770 (substitute* '("test/functional/bio/test_command.rb")
6771 (("/bin/ls") (which "ls")))
6772 (substitute* '("test/functional/bio/test_command.rb")
6773 (("which") (which "which")))
6774 (substitute* '("test/functional/bio/test_command.rb",
6775 "test/data/command/echoarg2.sh")
6776 (("/bin/echo") (which "echo")))
6778 (synopsis "Ruby library, shell and utilities for bioinformatics")
6779 (description "BioRuby comes with a comprehensive set of Ruby development
6780 tools and libraries for bioinformatics and molecular biology. BioRuby has
6781 components for sequence analysis, pathway analysis, protein modelling and
6782 phylogenetic analysis; it supports many widely used data formats and provides
6783 easy access to databases, external programs and public web services, including
6784 BLAST, KEGG, GenBank, MEDLINE and GO.")
6785 (home-page "http://bioruby.org/")
6786 ;; Code is released under Ruby license, except for setup
6787 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6788 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6790 (define-public r-acsnminer
6792 (name "r-acsnminer")
6793 (version "0.16.8.25")
6796 (uri (cran-uri "ACSNMineR" version))
6799 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6800 (properties `((upstream-name . "ACSNMineR")))
6801 (build-system r-build-system)
6803 `(("r-ggplot2" ,r-ggplot2)
6804 ("r-gridextra" ,r-gridextra)))
6805 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6806 (synopsis "Gene enrichment analysis")
6808 "This package provides tools to compute and represent gene set enrichment
6809 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6810 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6811 enrichment can be run with hypergeometric test or Fisher exact test, and can
6812 use multiple corrections. Visualization of data can be done either by
6813 barplots or heatmaps.")
6814 (license license:gpl2+)))
6816 (define-public r-biocgenerics
6818 (name "r-biocgenerics")
6822 (uri (bioconductor-uri "BiocGenerics" version))
6825 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6827 `((upstream-name . "BiocGenerics")))
6828 (build-system r-build-system)
6829 (home-page "https://bioconductor.org/packages/BiocGenerics")
6830 (synopsis "S4 generic functions for Bioconductor")
6832 "This package provides S4 generic functions needed by many Bioconductor
6834 (license license:artistic2.0)))
6836 (define-public r-biocinstaller
6838 (name "r-biocinstaller")
6842 (uri (bioconductor-uri "BiocInstaller" version))
6845 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6847 `((upstream-name . "BiocInstaller")))
6848 (build-system r-build-system)
6849 (home-page "https://bioconductor.org/packages/BiocInstaller")
6850 (synopsis "Install Bioconductor packages")
6851 (description "This package is used to install and update R packages from
6852 Bioconductor, CRAN, and Github.")
6853 (license license:artistic2.0)))
6855 (define-public r-biocviews
6857 (name "r-biocviews")
6861 (uri (bioconductor-uri "biocViews" version))
6864 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6866 `((upstream-name . "biocViews")))
6867 (build-system r-build-system)
6869 `(("r-biobase" ,r-biobase)
6870 ("r-graph" ,r-graph)
6872 ("r-rcurl" ,r-rcurl)
6874 ("r-runit" ,r-runit)))
6875 (home-page "https://bioconductor.org/packages/biocViews")
6876 (synopsis "Bioconductor package categorization helper")
6877 (description "The purpose of biocViews is to create HTML pages that
6878 categorize packages in a Bioconductor package repository according to keywords,
6879 also known as views, in a controlled vocabulary.")
6880 (license license:artistic2.0)))
6882 (define-public r-bookdown
6888 (uri (cran-uri "bookdown" version))
6891 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6892 (build-system r-build-system)
6894 `(("r-htmltools" ,r-htmltools)
6895 ("r-knitr" ,r-knitr)
6896 ("r-rmarkdown" ,r-rmarkdown)
6897 ("r-tinytex" ,r-tinytex)
6900 ("ghc-pandoc" ,ghc-pandoc)))
6901 (home-page "https://github.com/rstudio/bookdown")
6902 (synopsis "Authoring books and technical documents with R markdown")
6903 (description "This package provides output formats and utilities for
6904 authoring books and technical documents with R Markdown.")
6905 (license license:gpl3)))
6907 (define-public r-biocstyle
6909 (name "r-biocstyle")
6913 (uri (bioconductor-uri "BiocStyle" version))
6916 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6918 `((upstream-name . "BiocStyle")))
6919 (build-system r-build-system)
6921 `(("r-bookdown" ,r-bookdown)
6922 ("r-knitr" ,r-knitr)
6923 ("r-rmarkdown" ,r-rmarkdown)
6924 ("r-yaml" ,r-yaml)))
6925 (home-page "https://bioconductor.org/packages/BiocStyle")
6926 (synopsis "Bioconductor formatting styles")
6927 (description "This package provides standard formatting styles for
6928 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6930 (license license:artistic2.0)))
6932 (define-public r-bioccheck
6934 (name "r-bioccheck")
6938 (uri (bioconductor-uri "BiocCheck" version))
6941 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6943 `((upstream-name . "BiocCheck")))
6944 (build-system r-build-system)
6947 (modify-phases %standard-phases
6948 ;; This package can be used by calling BiocCheck(<package>) from
6949 ;; within R, or by running R CMD BiocCheck <package>. This phase
6950 ;; makes sure the latter works. For this to work, the BiocCheck
6951 ;; script must be somewhere on the PATH (not the R bin directory).
6952 (add-after 'install 'install-bioccheck-subcommand
6953 (lambda* (#:key outputs #:allow-other-keys)
6954 (let* ((out (assoc-ref outputs "out"))
6955 (dest-dir (string-append out "/bin"))
6957 (string-append out "/site-library/BiocCheck/script/")))
6959 (symlink (string-append script-dir "/checkBadDeps.R")
6960 (string-append dest-dir "/checkBadDeps.R"))
6961 (symlink (string-append script-dir "/BiocCheck")
6962 (string-append dest-dir "/BiocCheck")))
6965 `(("r-codetools" ,r-codetools)
6966 ("r-graph" ,r-graph)
6968 ("r-optparse" ,r-optparse)
6969 ("r-biocinstaller" ,r-biocinstaller)
6970 ("r-biocviews" ,r-biocviews)
6971 ("r-stringdist" ,r-stringdist)))
6972 (home-page "https://bioconductor.org/packages/BiocCheck")
6973 (synopsis "Executes Bioconductor-specific package checks")
6974 (description "This package contains tools to perform additional quality
6975 checks on R packages that are to be submitted to the Bioconductor repository.")
6976 (license license:artistic2.0)))
6978 (define-public r-getopt
6985 (uri (cran-uri "getopt" version))
6988 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
6989 (build-system r-build-system)
6990 (home-page "https://github.com/trevorld/getopt")
6991 (synopsis "Command-line option processor for R")
6993 "This package is designed to be used with Rscript to write shebang
6994 scripts that accept short and long options. Many users will prefer to
6995 use the packages @code{optparse} or @code{argparse} which add extra
6996 features like automatically generated help options and usage texts,
6997 support for default values, positional argument support, etc.")
6998 (license license:gpl2+)))
7000 (define-public r-optparse
7007 (uri (cran-uri "optparse" version))
7010 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
7011 (build-system r-build-system)
7013 `(("r-getopt" ,r-getopt)))
7015 "https://github.com/trevorld/optparse")
7016 (synopsis "Command line option parser")
7018 "This package provides a command line parser inspired by Python's
7019 @code{optparse} library to be used with Rscript to write shebang scripts
7020 that accept short and long options.")
7021 (license license:gpl2+)))
7023 (define-public r-dnacopy
7029 (uri (bioconductor-uri "DNAcopy" version))
7032 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
7034 `((upstream-name . "DNAcopy")))
7035 (build-system r-build-system)
7037 `(("gfortran" ,gfortran)))
7038 (home-page "https://bioconductor.org/packages/DNAcopy")
7039 (synopsis "Implementation of a circular binary segmentation algorithm")
7040 (description "This package implements the circular binary segmentation (CBS)
7041 algorithm to segment DNA copy number data and identify genomic regions with
7042 abnormal copy number.")
7043 (license license:gpl2+)))
7045 (define-public r-s4vectors
7047 (name "r-s4vectors")
7051 (uri (bioconductor-uri "S4Vectors" version))
7054 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7056 `((upstream-name . "S4Vectors")))
7057 (build-system r-build-system)
7059 `(("r-biocgenerics" ,r-biocgenerics)))
7060 (home-page "https://bioconductor.org/packages/S4Vectors")
7061 (synopsis "S4 implementation of vectors and lists")
7063 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7064 classes and a set of generic functions that extend the semantic of ordinary
7065 vectors and lists in R. Package developers can easily implement vector-like
7066 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7067 In addition, a few low-level concrete subclasses of general interest (e.g.
7068 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7069 S4Vectors package itself.")
7070 (license license:artistic2.0)))
7072 (define-public r-seqinr
7079 (uri (cran-uri "seqinr" version))
7082 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7083 (build-system r-build-system)
7085 `(("r-ade4" ,r-ade4)
7086 ("r-segmented" ,r-segmented)))
7089 (home-page "http://seqinr.r-forge.r-project.org/")
7090 (synopsis "Biological sequences retrieval and analysis")
7092 "This package provides tools for exploratory data analysis and data
7093 visualization of biological sequence (DNA and protein) data. It also includes
7094 utilities for sequence data management under the ACNUC system.")
7095 (license license:gpl2+)))
7097 (define-public r-iranges
7103 (uri (bioconductor-uri "IRanges" version))
7106 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7108 `((upstream-name . "IRanges")))
7109 (build-system r-build-system)
7111 `(("r-biocgenerics" ,r-biocgenerics)
7112 ("r-s4vectors" ,r-s4vectors)))
7113 (home-page "https://bioconductor.org/packages/IRanges")
7114 (synopsis "Infrastructure for manipulating intervals on sequences")
7116 "This package provides efficient low-level and highly reusable S4 classes
7117 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7118 generally, data that can be organized sequentially (formally defined as
7119 @code{Vector} objects), as well as views on these @code{Vector} objects.
7120 Efficient list-like classes are also provided for storing big collections of
7121 instances of the basic classes. All classes in the package use consistent
7122 naming and share the same rich and consistent \"Vector API\" as much as
7124 (license license:artistic2.0)))
7126 (define-public r-genomeinfodbdata
7128 (name "r-genomeinfodbdata")
7132 ;; We cannot use bioconductor-uri here because this tarball is
7133 ;; located under "data/annotation/" instead of "bioc/".
7134 (uri (string-append "https://bioconductor.org/packages/release/"
7135 "data/annotation/src/contrib/GenomeInfoDbData_"
7139 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7141 `((upstream-name . "GenomeInfoDbData")))
7142 (build-system r-build-system)
7143 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7144 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7145 (description "This package contains data for mapping between NCBI taxonomy
7146 ID and species. It is used by functions in the GenomeInfoDb package.")
7147 (license license:artistic2.0)))
7149 (define-public r-genomeinfodb
7151 (name "r-genomeinfodb")
7155 (uri (bioconductor-uri "GenomeInfoDb" version))
7158 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7160 `((upstream-name . "GenomeInfoDb")))
7161 (build-system r-build-system)
7163 `(("r-biocgenerics" ,r-biocgenerics)
7164 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7165 ("r-iranges" ,r-iranges)
7166 ("r-rcurl" ,r-rcurl)
7167 ("r-s4vectors" ,r-s4vectors)))
7168 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7169 (synopsis "Utilities for manipulating chromosome identifiers")
7171 "This package contains data and functions that define and allow
7172 translation between different chromosome sequence naming conventions (e.g.,
7173 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7174 names in their natural, rather than lexicographic, order.")
7175 (license license:artistic2.0)))
7177 (define-public r-edger
7183 (uri (bioconductor-uri "edgeR" version))
7186 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7187 (properties `((upstream-name . "edgeR")))
7188 (build-system r-build-system)
7190 `(("r-limma" ,r-limma)
7191 ("r-locfit" ,r-locfit)
7193 ("r-statmod" ,r-statmod))) ;for estimateDisp
7194 (home-page "http://bioinf.wehi.edu.au/edgeR")
7195 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7196 (description "This package can do differential expression analysis of
7197 RNA-seq expression profiles with biological replication. It implements a range
7198 of statistical methodology based on the negative binomial distributions,
7199 including empirical Bayes estimation, exact tests, generalized linear models
7200 and quasi-likelihood tests. It be applied to differential signal analysis of
7201 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7203 (license license:gpl2+)))
7205 (define-public r-variantannotation
7207 (name "r-variantannotation")
7211 (uri (bioconductor-uri "VariantAnnotation" version))
7214 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7216 `((upstream-name . "VariantAnnotation")))
7220 `(("r-annotationdbi" ,r-annotationdbi)
7221 ("r-biobase" ,r-biobase)
7222 ("r-biocgenerics" ,r-biocgenerics)
7223 ("r-biostrings" ,r-biostrings)
7224 ("r-bsgenome" ,r-bsgenome)
7226 ("r-genomeinfodb" ,r-genomeinfodb)
7227 ("r-genomicfeatures" ,r-genomicfeatures)
7228 ("r-genomicranges" ,r-genomicranges)
7229 ("r-iranges" ,r-iranges)
7230 ("r-summarizedexperiment" ,r-summarizedexperiment)
7231 ("r-rsamtools" ,r-rsamtools)
7232 ("r-rtracklayer" ,r-rtracklayer)
7233 ("r-s4vectors" ,r-s4vectors)
7234 ("r-xvector" ,r-xvector)
7235 ("r-zlibbioc" ,r-zlibbioc)))
7236 (build-system r-build-system)
7237 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7238 (synopsis "Package for annotation of genetic variants")
7239 (description "This R package can annotate variants, compute amino acid
7240 coding changes and predict coding outcomes.")
7241 (license license:artistic2.0)))
7243 (define-public r-limma
7249 (uri (bioconductor-uri "limma" version))
7252 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7253 (build-system r-build-system)
7254 (home-page "http://bioinf.wehi.edu.au/limma")
7255 (synopsis "Package for linear models for microarray and RNA-seq data")
7256 (description "This package can be used for the analysis of gene expression
7257 studies, especially the use of linear models for analysing designed experiments
7258 and the assessment of differential expression. The analysis methods apply to
7259 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7260 (license license:gpl2+)))
7262 (define-public r-xvector
7268 (uri (bioconductor-uri "XVector" version))
7271 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7273 `((upstream-name . "XVector")))
7274 (build-system r-build-system)
7277 (modify-phases %standard-phases
7278 (add-after 'unpack 'use-system-zlib
7280 (substitute* "DESCRIPTION"
7281 (("zlibbioc, ") ""))
7282 (substitute* "NAMESPACE"
7283 (("import\\(zlibbioc\\)") ""))
7288 `(("r-biocgenerics" ,r-biocgenerics)
7289 ("r-iranges" ,r-iranges)
7290 ("r-s4vectors" ,r-s4vectors)))
7291 (home-page "https://bioconductor.org/packages/XVector")
7292 (synopsis "Representation and manpulation of external sequences")
7294 "This package provides memory efficient S4 classes for storing sequences
7295 \"externally\" (behind an R external pointer, or on disk).")
7296 (license license:artistic2.0)))
7298 (define-public r-genomicranges
7300 (name "r-genomicranges")
7304 (uri (bioconductor-uri "GenomicRanges" version))
7307 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7309 `((upstream-name . "GenomicRanges")))
7310 (build-system r-build-system)
7312 `(("r-biocgenerics" ,r-biocgenerics)
7313 ("r-genomeinfodb" ,r-genomeinfodb)
7314 ("r-iranges" ,r-iranges)
7315 ("r-s4vectors" ,r-s4vectors)
7316 ("r-xvector" ,r-xvector)))
7317 (home-page "https://bioconductor.org/packages/GenomicRanges")
7318 (synopsis "Representation and manipulation of genomic intervals")
7320 "This package provides tools to efficiently represent and manipulate
7321 genomic annotations and alignments is playing a central role when it comes to
7322 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7323 GenomicRanges package defines general purpose containers for storing and
7324 manipulating genomic intervals and variables defined along a genome.")
7325 (license license:artistic2.0)))
7327 (define-public r-biobase
7333 (uri (bioconductor-uri "Biobase" version))
7336 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7338 `((upstream-name . "Biobase")))
7339 (build-system r-build-system)
7341 `(("r-biocgenerics" ,r-biocgenerics)))
7342 (home-page "https://bioconductor.org/packages/Biobase")
7343 (synopsis "Base functions for Bioconductor")
7345 "This package provides functions that are needed by many other packages
7346 on Bioconductor or which replace R functions.")
7347 (license license:artistic2.0)))
7349 (define-public r-annotationdbi
7351 (name "r-annotationdbi")
7355 (uri (bioconductor-uri "AnnotationDbi" version))
7358 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7360 `((upstream-name . "AnnotationDbi")))
7361 (build-system r-build-system)
7363 `(("r-biobase" ,r-biobase)
7364 ("r-biocgenerics" ,r-biocgenerics)
7366 ("r-iranges" ,r-iranges)
7367 ("r-rsqlite" ,r-rsqlite)
7368 ("r-s4vectors" ,r-s4vectors)))
7369 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7370 (synopsis "Annotation database interface")
7372 "This package provides user interface and database connection code for
7373 annotation data packages using SQLite data storage.")
7374 (license license:artistic2.0)))
7376 (define-public r-biomart
7382 (uri (bioconductor-uri "biomaRt" version))
7385 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7387 `((upstream-name . "biomaRt")))
7388 (build-system r-build-system)
7390 `(("r-annotationdbi" ,r-annotationdbi)
7392 ("r-progress" ,r-progress)
7393 ("r-rcurl" ,r-rcurl)
7394 ("r-stringr" ,r-stringr)
7396 (home-page "https://bioconductor.org/packages/biomaRt")
7397 (synopsis "Interface to BioMart databases")
7399 "biomaRt provides an interface to a growing collection of databases
7400 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7401 package enables retrieval of large amounts of data in a uniform way without
7402 the need to know the underlying database schemas or write complex SQL queries.
7403 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7404 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7405 users direct access to a diverse set of data and enable a wide range of
7406 powerful online queries from gene annotation to database mining.")
7407 (license license:artistic2.0)))
7409 (define-public r-biocparallel
7411 (name "r-biocparallel")
7415 (uri (bioconductor-uri "BiocParallel" version))
7418 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7420 `((upstream-name . "BiocParallel")))
7421 (build-system r-build-system)
7423 `(("r-futile-logger" ,r-futile-logger)
7426 (home-page "https://bioconductor.org/packages/BiocParallel")
7427 (synopsis "Bioconductor facilities for parallel evaluation")
7429 "This package provides modified versions and novel implementation of
7430 functions for parallel evaluation, tailored to use with Bioconductor
7432 (license (list license:gpl2+ license:gpl3+))))
7434 (define-public r-biostrings
7436 (name "r-biostrings")
7440 (uri (bioconductor-uri "Biostrings" version))
7443 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7445 `((upstream-name . "Biostrings")))
7446 (build-system r-build-system)
7448 `(("r-biocgenerics" ,r-biocgenerics)
7449 ("r-iranges" ,r-iranges)
7450 ("r-s4vectors" ,r-s4vectors)
7451 ("r-xvector" ,r-xvector)))
7452 (home-page "https://bioconductor.org/packages/Biostrings")
7453 (synopsis "String objects and algorithms for biological sequences")
7455 "This package provides memory efficient string containers, string
7456 matching algorithms, and other utilities, for fast manipulation of large
7457 biological sequences or sets of sequences.")
7458 (license license:artistic2.0)))
7460 (define-public r-rsamtools
7462 (name "r-rsamtools")
7466 (uri (bioconductor-uri "Rsamtools" version))
7469 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7471 `((upstream-name . "Rsamtools")))
7472 (build-system r-build-system)
7475 (modify-phases %standard-phases
7476 (add-after 'unpack 'use-system-zlib
7478 (substitute* "DESCRIPTION"
7479 (("zlibbioc, ") ""))
7480 (substitute* "NAMESPACE"
7481 (("import\\(zlibbioc\\)") ""))
7486 `(("r-biocgenerics" ,r-biocgenerics)
7487 ("r-biocparallel" ,r-biocparallel)
7488 ("r-biostrings" ,r-biostrings)
7489 ("r-bitops" ,r-bitops)
7490 ("r-genomeinfodb" ,r-genomeinfodb)
7491 ("r-genomicranges" ,r-genomicranges)
7492 ("r-iranges" ,r-iranges)
7493 ("r-s4vectors" ,r-s4vectors)
7494 ("r-xvector" ,r-xvector)))
7495 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7496 (synopsis "Interface to samtools, bcftools, and tabix")
7498 "This package provides an interface to the 'samtools', 'bcftools', and
7499 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7500 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7502 (license license:expat)))
7504 (define-public r-delayedarray
7506 (name "r-delayedarray")
7510 (uri (bioconductor-uri "DelayedArray" version))
7513 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7515 `((upstream-name . "DelayedArray")))
7516 (build-system r-build-system)
7518 `(("r-biocgenerics" ,r-biocgenerics)
7519 ("r-s4vectors" ,r-s4vectors)
7520 ("r-iranges" ,r-iranges)
7521 ("r-matrixstats" ,r-matrixstats)))
7522 (home-page "https://bioconductor.org/packages/DelayedArray")
7523 (synopsis "Delayed operations on array-like objects")
7525 "Wrapping an array-like object (typically an on-disk object) in a
7526 @code{DelayedArray} object allows one to perform common array operations on it
7527 without loading the object in memory. In order to reduce memory usage and
7528 optimize performance, operations on the object are either delayed or executed
7529 using a block processing mechanism. Note that this also works on in-memory
7530 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7531 @code{Matrix} objects, and ordinary arrays and data frames.")
7532 (license license:artistic2.0)))
7534 (define-public r-summarizedexperiment
7536 (name "r-summarizedexperiment")
7540 (uri (bioconductor-uri "SummarizedExperiment" version))
7543 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7545 `((upstream-name . "SummarizedExperiment")))
7546 (build-system r-build-system)
7548 `(("r-biobase" ,r-biobase)
7549 ("r-biocgenerics" ,r-biocgenerics)
7550 ("r-delayedarray" ,r-delayedarray)
7551 ("r-genomeinfodb" ,r-genomeinfodb)
7552 ("r-genomicranges" ,r-genomicranges)
7553 ("r-iranges" ,r-iranges)
7554 ("r-matrix" ,r-matrix)
7555 ("r-s4vectors" ,r-s4vectors)))
7556 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7557 (synopsis "Container for representing genomic ranges by sample")
7559 "The SummarizedExperiment container contains one or more assays, each
7560 represented by a matrix-like object of numeric or other mode. The rows
7561 typically represent genomic ranges of interest and the columns represent
7563 (license license:artistic2.0)))
7565 (define-public r-genomicalignments
7567 (name "r-genomicalignments")
7571 (uri (bioconductor-uri "GenomicAlignments" version))
7574 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7576 `((upstream-name . "GenomicAlignments")))
7577 (build-system r-build-system)
7579 `(("r-biocgenerics" ,r-biocgenerics)
7580 ("r-biocparallel" ,r-biocparallel)
7581 ("r-biostrings" ,r-biostrings)
7582 ("r-genomeinfodb" ,r-genomeinfodb)
7583 ("r-genomicranges" ,r-genomicranges)
7584 ("r-iranges" ,r-iranges)
7585 ("r-rsamtools" ,r-rsamtools)
7586 ("r-s4vectors" ,r-s4vectors)
7587 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7588 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7589 (synopsis "Representation and manipulation of short genomic alignments")
7591 "This package provides efficient containers for storing and manipulating
7592 short genomic alignments (typically obtained by aligning short reads to a
7593 reference genome). This includes read counting, computing the coverage,
7594 junction detection, and working with the nucleotide content of the
7596 (license license:artistic2.0)))
7598 (define-public r-rtracklayer
7600 (name "r-rtracklayer")
7604 (uri (bioconductor-uri "rtracklayer" version))
7607 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7608 (build-system r-build-system)
7611 (modify-phases %standard-phases
7612 (add-after 'unpack 'use-system-zlib
7614 (substitute* "DESCRIPTION"
7615 ((" zlibbioc,") ""))
7616 (substitute* "NAMESPACE"
7617 (("import\\(zlibbioc\\)") ""))
7622 `(("r-biocgenerics" ,r-biocgenerics)
7623 ("r-biostrings" ,r-biostrings)
7624 ("r-genomeinfodb" ,r-genomeinfodb)
7625 ("r-genomicalignments" ,r-genomicalignments)
7626 ("r-genomicranges" ,r-genomicranges)
7627 ("r-iranges" ,r-iranges)
7628 ("r-rcurl" ,r-rcurl)
7629 ("r-rsamtools" ,r-rsamtools)
7630 ("r-s4vectors" ,r-s4vectors)
7632 ("r-xvector" ,r-xvector)))
7633 (home-page "https://bioconductor.org/packages/rtracklayer")
7634 (synopsis "R interface to genome browsers and their annotation tracks")
7636 "rtracklayer is an extensible framework for interacting with multiple
7637 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7638 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7639 built-in). The user may export/import tracks to/from the supported browsers,
7640 as well as query and modify the browser state, such as the current viewport.")
7641 (license license:artistic2.0)))
7643 (define-public r-genomicfeatures
7645 (name "r-genomicfeatures")
7649 (uri (bioconductor-uri "GenomicFeatures" version))
7652 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7654 `((upstream-name . "GenomicFeatures")))
7655 (build-system r-build-system)
7657 `(("r-annotationdbi" ,r-annotationdbi)
7658 ("r-biobase" ,r-biobase)
7659 ("r-biocgenerics" ,r-biocgenerics)
7660 ("r-biomart" ,r-biomart)
7661 ("r-biostrings" ,r-biostrings)
7663 ("r-genomeinfodb" ,r-genomeinfodb)
7664 ("r-genomicranges" ,r-genomicranges)
7665 ("r-iranges" ,r-iranges)
7666 ("r-rcurl" ,r-rcurl)
7667 ("r-rsqlite" ,r-rsqlite)
7668 ("r-rmysql" ,r-rmysql)
7669 ("r-rtracklayer" ,r-rtracklayer)
7670 ("r-s4vectors" ,r-s4vectors)
7671 ("r-xvector" ,r-xvector)))
7672 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7673 (synopsis "Tools for working with transcript centric annotations")
7675 "This package provides a set of tools and methods for making and
7676 manipulating transcript centric annotations. With these tools the user can
7677 easily download the genomic locations of the transcripts, exons and cds of a
7678 given organism, from either the UCSC Genome Browser or a BioMart
7679 database (more sources will be supported in the future). This information is
7680 then stored in a local database that keeps track of the relationship between
7681 transcripts, exons, cds and genes. Flexible methods are provided for
7682 extracting the desired features in a convenient format.")
7683 (license license:artistic2.0)))
7685 (define-public r-go-db
7691 (uri (string-append "https://www.bioconductor.org/packages/"
7692 "release/data/annotation/src/contrib/GO.db_"
7696 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7698 `((upstream-name . "GO.db")))
7699 (build-system r-build-system)
7701 `(("r-annotationdbi" ,r-annotationdbi)))
7702 (home-page "https://bioconductor.org/packages/GO.db")
7703 (synopsis "Annotation maps describing the entire Gene Ontology")
7705 "The purpose of this GO.db annotation package is to provide detailed
7706 information about the latest version of the Gene Ontologies.")
7707 (license license:artistic2.0)))
7709 (define-public r-graph
7715 (uri (bioconductor-uri "graph" version))
7718 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7719 (build-system r-build-system)
7721 `(("r-biocgenerics" ,r-biocgenerics)))
7722 (home-page "https://bioconductor.org/packages/graph")
7723 (synopsis "Handle graph data structures in R")
7725 "This package implements some simple graph handling capabilities for R.")
7726 (license license:artistic2.0)))
7728 (define-public r-topgo
7734 (uri (bioconductor-uri "topGO" version))
7737 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7739 `((upstream-name . "topGO")))
7740 (build-system r-build-system)
7742 `(("r-annotationdbi" ,r-annotationdbi)
7744 ("r-biobase" ,r-biobase)
7745 ("r-biocgenerics" ,r-biocgenerics)
7746 ("r-go-db" ,r-go-db)
7747 ("r-graph" ,r-graph)
7748 ("r-lattice" ,r-lattice)
7749 ("r-matrixstats" ,r-matrixstats)
7750 ("r-sparsem" ,r-sparsem)))
7751 (home-page "https://bioconductor.org/packages/topGO")
7752 (synopsis "Enrichment analysis for gene ontology")
7754 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7755 terms while accounting for the topology of the GO graph. Different test
7756 statistics and different methods for eliminating local similarities and
7757 dependencies between GO terms can be implemented and applied.")
7758 ;; Any version of the LGPL applies.
7759 (license license:lgpl2.1+)))
7761 (define-public r-bsgenome
7767 (uri (bioconductor-uri "BSgenome" version))
7770 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7772 `((upstream-name . "BSgenome")))
7773 (build-system r-build-system)
7775 `(("r-biocgenerics" ,r-biocgenerics)
7776 ("r-biostrings" ,r-biostrings)
7777 ("r-genomeinfodb" ,r-genomeinfodb)
7778 ("r-genomicranges" ,r-genomicranges)
7779 ("r-iranges" ,r-iranges)
7780 ("r-rsamtools" ,r-rsamtools)
7781 ("r-rtracklayer" ,r-rtracklayer)
7782 ("r-s4vectors" ,r-s4vectors)
7783 ("r-xvector" ,r-xvector)))
7784 (home-page "https://bioconductor.org/packages/BSgenome")
7785 (synopsis "Infrastructure for Biostrings-based genome data packages")
7787 "This package provides infrastructure shared by all Biostrings-based
7788 genome data packages and support for efficient SNP representation.")
7789 (license license:artistic2.0)))
7791 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7793 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7797 ;; We cannot use bioconductor-uri here because this tarball is
7798 ;; located under "data/annotation/" instead of "bioc/".
7799 (uri (string-append "https://www.bioconductor.org/packages/"
7800 "release/data/annotation/src/contrib/"
7801 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7805 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7807 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7808 (build-system r-build-system)
7809 ;; As this package provides little more than a very large data file it
7810 ;; doesn't make sense to build substitutes.
7811 (arguments `(#:substitutable? #f))
7813 `(("r-bsgenome" ,r-bsgenome)))
7815 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7816 (synopsis "Full genome sequences for Homo sapiens")
7818 "This package provides full genome sequences for Homo sapiens from
7819 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7820 (license license:artistic2.0)))
7822 (define-public r-impute
7828 (uri (bioconductor-uri "impute" version))
7831 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7833 `(("gfortran" ,gfortran)))
7834 (build-system r-build-system)
7835 (home-page "https://bioconductor.org/packages/impute")
7836 (synopsis "Imputation for microarray data")
7838 "This package provides a function to impute missing gene expression
7839 microarray data, using nearest neighbor averaging.")
7840 (license license:gpl2+)))
7842 (define-public r-seqpattern
7844 (name "r-seqpattern")
7848 (uri (bioconductor-uri "seqPattern" version))
7851 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7853 `((upstream-name . "seqPattern")))
7854 (build-system r-build-system)
7856 `(("r-biostrings" ,r-biostrings)
7857 ("r-genomicranges" ,r-genomicranges)
7858 ("r-iranges" ,r-iranges)
7859 ("r-kernsmooth" ,r-kernsmooth)
7860 ("r-plotrix" ,r-plotrix)))
7861 (home-page "https://bioconductor.org/packages/seqPattern")
7862 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7864 "This package provides tools to visualize oligonucleotide patterns and
7865 sequence motif occurrences across a large set of sequences centred at a common
7866 reference point and sorted by a user defined feature.")
7867 (license license:gpl3+)))
7869 (define-public r-genomation
7871 (name "r-genomation")
7875 (uri (bioconductor-uri "genomation" version))
7878 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7879 (build-system r-build-system)
7881 `(("r-biostrings" ,r-biostrings)
7882 ("r-bsgenome" ,r-bsgenome)
7883 ("r-data-table" ,r-data-table)
7884 ("r-genomeinfodb" ,r-genomeinfodb)
7885 ("r-genomicalignments" ,r-genomicalignments)
7886 ("r-genomicranges" ,r-genomicranges)
7887 ("r-ggplot2" ,r-ggplot2)
7888 ("r-gridbase" ,r-gridbase)
7889 ("r-impute" ,r-impute)
7890 ("r-iranges" ,r-iranges)
7891 ("r-matrixstats" ,r-matrixstats)
7892 ("r-plotrix" ,r-plotrix)
7895 ("r-readr" ,r-readr)
7896 ("r-reshape2" ,r-reshape2)
7897 ("r-rsamtools" ,r-rsamtools)
7898 ("r-rtracklayer" ,r-rtracklayer)
7899 ("r-runit" ,r-runit)
7900 ("r-s4vectors" ,r-s4vectors)
7901 ("r-seqpattern" ,r-seqpattern)))
7902 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7903 (synopsis "Summary, annotation and visualization of genomic data")
7905 "This package provides a package for summary and annotation of genomic
7906 intervals. Users can visualize and quantify genomic intervals over
7907 pre-defined functional regions, such as promoters, exons, introns, etc. The
7908 genomic intervals represent regions with a defined chromosome position, which
7909 may be associated with a score, such as aligned reads from HT-seq experiments,
7910 TF binding sites, methylation scores, etc. The package can use any tabular
7911 genomic feature data as long as it has minimal information on the locations of
7912 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7913 (license license:artistic2.0)))
7915 (define-public r-genomationdata
7917 (name "r-genomationdata")
7921 ;; We cannot use bioconductor-uri here because this tarball is
7922 ;; located under "data/annotation/" instead of "bioc/".
7923 (uri (string-append "https://bioconductor.org/packages/"
7924 "release/data/experiment/src/contrib/"
7925 "genomationData_" version ".tar.gz"))
7928 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7929 (build-system r-build-system)
7930 ;; As this package provides little more than large data files, it doesn't
7931 ;; make sense to build substitutes.
7932 (arguments `(#:substitutable? #f))
7934 `(("r-knitr" ,r-knitr)))
7935 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7936 (synopsis "Experimental data for use with the genomation package")
7938 "This package contains experimental genetic data for use with the
7939 genomation package. Included are Chip Seq, Methylation and Cage data,
7940 downloaded from Encode.")
7941 (license license:gpl3+)))
7943 (define-public r-org-hs-eg-db
7945 (name "r-org-hs-eg-db")
7949 ;; We cannot use bioconductor-uri here because this tarball is
7950 ;; located under "data/annotation/" instead of "bioc/".
7951 (uri (string-append "https://www.bioconductor.org/packages/"
7952 "release/data/annotation/src/contrib/"
7953 "org.Hs.eg.db_" version ".tar.gz"))
7956 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7958 `((upstream-name . "org.Hs.eg.db")))
7959 (build-system r-build-system)
7961 `(("r-annotationdbi" ,r-annotationdbi)))
7962 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7963 (synopsis "Genome wide annotation for Human")
7965 "This package contains genome-wide annotations for Human, primarily based
7966 on mapping using Entrez Gene identifiers.")
7967 (license license:artistic2.0)))
7969 (define-public r-org-ce-eg-db
7971 (name "r-org-ce-eg-db")
7975 ;; We cannot use bioconductor-uri here because this tarball is
7976 ;; located under "data/annotation/" instead of "bioc/".
7977 (uri (string-append "https://www.bioconductor.org/packages/"
7978 "release/data/annotation/src/contrib/"
7979 "org.Ce.eg.db_" version ".tar.gz"))
7982 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7984 `((upstream-name . "org.Ce.eg.db")))
7985 (build-system r-build-system)
7987 `(("r-annotationdbi" ,r-annotationdbi)))
7988 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7989 (synopsis "Genome wide annotation for Worm")
7991 "This package provides mappings from Entrez gene identifiers to various
7992 annotations for the genome of the model worm Caenorhabditis elegans.")
7993 (license license:artistic2.0)))
7995 (define-public r-org-dm-eg-db
7997 (name "r-org-dm-eg-db")
8001 ;; We cannot use bioconductor-uri here because this tarball is
8002 ;; located under "data/annotation/" instead of "bioc/".
8003 (uri (string-append "https://www.bioconductor.org/packages/"
8004 "release/data/annotation/src/contrib/"
8005 "org.Dm.eg.db_" version ".tar.gz"))
8008 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8010 `((upstream-name . "org.Dm.eg.db")))
8011 (build-system r-build-system)
8013 `(("r-annotationdbi" ,r-annotationdbi)))
8014 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8015 (synopsis "Genome wide annotation for Fly")
8017 "This package provides mappings from Entrez gene identifiers to various
8018 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8019 (license license:artistic2.0)))
8021 (define-public r-org-mm-eg-db
8023 (name "r-org-mm-eg-db")
8027 ;; We cannot use bioconductor-uri here because this tarball is
8028 ;; located under "data/annotation/" instead of "bioc/".
8029 (uri (string-append "https://www.bioconductor.org/packages/"
8030 "release/data/annotation/src/contrib/"
8031 "org.Mm.eg.db_" version ".tar.gz"))
8034 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8036 `((upstream-name . "org.Mm.eg.db")))
8037 (build-system r-build-system)
8039 `(("r-annotationdbi" ,r-annotationdbi)))
8040 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8041 (synopsis "Genome wide annotation for Mouse")
8043 "This package provides mappings from Entrez gene identifiers to various
8044 annotations for the genome of the model mouse Mus musculus.")
8045 (license license:artistic2.0)))
8047 (define-public r-seqlogo
8054 (uri (bioconductor-uri "seqLogo" version))
8057 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
8058 (properties `((upstream-name . "seqLogo")))
8059 (build-system r-build-system)
8060 (home-page "https://bioconductor.org/packages/seqLogo")
8061 (synopsis "Sequence logos for DNA sequence alignments")
8063 "seqLogo takes the position weight matrix of a DNA sequence motif and
8064 plots the corresponding sequence logo as introduced by Schneider and
8066 (license license:lgpl2.0+)))
8068 (define-public r-bsgenome-hsapiens-ucsc-hg19
8070 (name "r-bsgenome-hsapiens-ucsc-hg19")
8074 ;; We cannot use bioconductor-uri here because this tarball is
8075 ;; located under "data/annotation/" instead of "bioc/".
8076 (uri (string-append "https://www.bioconductor.org/packages/"
8077 "release/data/annotation/src/contrib/"
8078 "BSgenome.Hsapiens.UCSC.hg19_"
8082 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8084 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8085 (build-system r-build-system)
8086 ;; As this package provides little more than a very large data file it
8087 ;; doesn't make sense to build substitutes.
8088 (arguments `(#:substitutable? #f))
8090 `(("r-bsgenome" ,r-bsgenome)))
8092 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8093 (synopsis "Full genome sequences for Homo sapiens")
8095 "This package provides full genome sequences for Homo sapiens as provided
8096 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8097 (license license:artistic2.0)))
8099 (define-public r-bsgenome-mmusculus-ucsc-mm9
8101 (name "r-bsgenome-mmusculus-ucsc-mm9")
8105 ;; We cannot use bioconductor-uri here because this tarball is
8106 ;; located under "data/annotation/" instead of "bioc/".
8107 (uri (string-append "https://www.bioconductor.org/packages/"
8108 "release/data/annotation/src/contrib/"
8109 "BSgenome.Mmusculus.UCSC.mm9_"
8113 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8115 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8116 (build-system r-build-system)
8117 ;; As this package provides little more than a very large data file it
8118 ;; doesn't make sense to build substitutes.
8119 (arguments `(#:substitutable? #f))
8121 `(("r-bsgenome" ,r-bsgenome)))
8123 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8124 (synopsis "Full genome sequences for Mouse")
8126 "This package provides full genome sequences for Mus musculus (Mouse) as
8127 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8128 (license license:artistic2.0)))
8130 (define-public r-bsgenome-mmusculus-ucsc-mm10
8132 (name "r-bsgenome-mmusculus-ucsc-mm10")
8136 ;; We cannot use bioconductor-uri here because this tarball is
8137 ;; located under "data/annotation/" instead of "bioc/".
8138 (uri (string-append "https://www.bioconductor.org/packages/"
8139 "release/data/annotation/src/contrib/"
8140 "BSgenome.Mmusculus.UCSC.mm10_"
8144 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8146 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8147 (build-system r-build-system)
8148 ;; As this package provides little more than a very large data file it
8149 ;; doesn't make sense to build substitutes.
8150 (arguments `(#:substitutable? #f))
8152 `(("r-bsgenome" ,r-bsgenome)))
8154 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8155 (synopsis "Full genome sequences for Mouse")
8157 "This package provides full genome sequences for Mus
8158 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8159 in Biostrings objects.")
8160 (license license:artistic2.0)))
8162 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8164 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8168 ;; We cannot use bioconductor-uri here because this tarball is
8169 ;; located under "data/annotation/" instead of "bioc/".
8170 (uri (string-append "https://www.bioconductor.org/packages/"
8171 "release/data/annotation/src/contrib/"
8172 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8176 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8178 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8179 (build-system r-build-system)
8180 ;; As this package provides little more than a very large data file it
8181 ;; doesn't make sense to build substitutes.
8182 (arguments `(#:substitutable? #f))
8184 `(("r-bsgenome" ,r-bsgenome)
8185 ("r-genomicfeatures" ,r-genomicfeatures)
8186 ("r-annotationdbi" ,r-annotationdbi)))
8188 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8189 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8191 "This package loads a TxDb object, which is an R interface to
8192 prefabricated databases contained in this package. This package provides
8193 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8194 based on the knownGene track.")
8195 (license license:artistic2.0)))
8197 (define-public r-bsgenome-celegans-ucsc-ce6
8199 (name "r-bsgenome-celegans-ucsc-ce6")
8203 ;; We cannot use bioconductor-uri here because this tarball is
8204 ;; located under "data/annotation/" instead of "bioc/".
8205 (uri (string-append "https://www.bioconductor.org/packages/"
8206 "release/data/annotation/src/contrib/"
8207 "BSgenome.Celegans.UCSC.ce6_"
8211 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8213 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8214 (build-system r-build-system)
8215 ;; As this package provides little more than a very large data file it
8216 ;; doesn't make sense to build substitutes.
8217 (arguments `(#:substitutable? #f))
8219 `(("r-bsgenome" ,r-bsgenome)))
8221 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8222 (synopsis "Full genome sequences for Worm")
8224 "This package provides full genome sequences for Caenorhabditis
8225 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8227 (license license:artistic2.0)))
8229 (define-public r-bsgenome-celegans-ucsc-ce10
8231 (name "r-bsgenome-celegans-ucsc-ce10")
8235 ;; We cannot use bioconductor-uri here because this tarball is
8236 ;; located under "data/annotation/" instead of "bioc/".
8237 (uri (string-append "https://www.bioconductor.org/packages/"
8238 "release/data/annotation/src/contrib/"
8239 "BSgenome.Celegans.UCSC.ce10_"
8243 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8245 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8246 (build-system r-build-system)
8247 ;; As this package provides little more than a very large data file it
8248 ;; doesn't make sense to build substitutes.
8249 (arguments `(#:substitutable? #f))
8251 `(("r-bsgenome" ,r-bsgenome)))
8253 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8254 (synopsis "Full genome sequences for Worm")
8256 "This package provides full genome sequences for Caenorhabditis
8257 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8259 (license license:artistic2.0)))
8261 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8263 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8267 ;; We cannot use bioconductor-uri here because this tarball is
8268 ;; located under "data/annotation/" instead of "bioc/".
8269 (uri (string-append "https://www.bioconductor.org/packages/"
8270 "release/data/annotation/src/contrib/"
8271 "BSgenome.Dmelanogaster.UCSC.dm3_"
8275 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8277 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8278 (build-system r-build-system)
8279 ;; As this package provides little more than a very large data file it
8280 ;; doesn't make sense to build substitutes.
8281 (arguments `(#:substitutable? #f))
8283 `(("r-bsgenome" ,r-bsgenome)))
8285 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8286 (synopsis "Full genome sequences for Fly")
8288 "This package provides full genome sequences for Drosophila
8289 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8290 Biostrings objects.")
8291 (license license:artistic2.0)))
8293 (define-public r-motifrg
8300 (uri (bioconductor-uri "motifRG" version))
8303 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8304 (properties `((upstream-name . "motifRG")))
8305 (build-system r-build-system)
8307 `(("r-biostrings" ,r-biostrings)
8308 ("r-bsgenome" ,r-bsgenome)
8309 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8310 ("r-iranges" ,r-iranges)
8311 ("r-seqlogo" ,r-seqlogo)
8312 ("r-xvector" ,r-xvector)))
8313 (home-page "https://bioconductor.org/packages/motifRG")
8314 (synopsis "Discover motifs in high throughput sequencing data")
8316 "This package provides tools for discriminative motif discovery in high
8317 throughput genetic sequencing data sets using regression methods.")
8318 (license license:artistic2.0)))
8320 (define-public r-qtl
8327 (uri (string-append "mirror://cran/src/contrib/qtl_"
8331 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8332 (build-system r-build-system)
8333 (home-page "http://rqtl.org/")
8334 (synopsis "R package for analyzing QTL experiments in genetics")
8335 (description "R/qtl is an extension library for the R statistics
8336 system. It is used to analyze experimental crosses for identifying
8337 genes contributing to variation in quantitative traits (so-called
8338 quantitative trait loci, QTLs).
8340 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8341 identify genotyping errors, and to perform single-QTL and two-QTL,
8342 two-dimensional genome scans.")
8343 (license license:gpl3)))
8345 (define-public r-zlibbioc
8351 (uri (bioconductor-uri "zlibbioc" version))
8354 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8356 `((upstream-name . "zlibbioc")))
8357 (build-system r-build-system)
8358 (home-page "https://bioconductor.org/packages/zlibbioc")
8359 (synopsis "Provider for zlib-1.2.5 to R packages")
8360 (description "This package uses the source code of zlib-1.2.5 to create
8361 libraries for systems that do not have these available via other means.")
8362 (license license:artistic2.0)))
8364 (define-public r-r4rna
8371 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8375 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8376 (build-system r-build-system)
8378 `(("r-optparse" ,r-optparse)
8379 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8380 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8381 (synopsis "Analysis framework for RNA secondary structure")
8383 "The R4RNA package aims to be a general framework for the analysis of RNA
8384 secondary structure and comparative analysis in R.")
8385 (license license:gpl3+)))
8387 (define-public r-rhtslib
8394 (uri (bioconductor-uri "Rhtslib" version))
8397 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8398 (properties `((upstream-name . "Rhtslib")))
8399 (build-system r-build-system)
8401 `(("r-zlibbioc" ,r-zlibbioc)))
8405 `(("autoconf" ,autoconf)))
8406 (home-page "https://github.com/nhayden/Rhtslib")
8407 (synopsis "High-throughput sequencing library as an R package")
8409 "This package provides the HTSlib C library for high-throughput
8410 nucleotide sequence analysis. The package is primarily useful to developers
8411 of other R packages who wish to make use of HTSlib.")
8412 (license license:lgpl2.0+)))
8414 (define-public r-bamsignals
8416 (name "r-bamsignals")
8421 (uri (bioconductor-uri "bamsignals" version))
8424 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8425 (build-system r-build-system)
8427 `(("r-biocgenerics" ,r-biocgenerics)
8428 ("r-genomicranges" ,r-genomicranges)
8429 ("r-iranges" ,r-iranges)
8431 ("r-rhtslib" ,r-rhtslib)
8432 ("r-zlibbioc" ,r-zlibbioc)))
8435 (home-page "https://bioconductor.org/packages/bamsignals")
8436 (synopsis "Extract read count signals from bam files")
8438 "This package allows to efficiently obtain count vectors from indexed bam
8439 files. It counts the number of nucleotide sequence reads in given genomic
8440 ranges and it computes reads profiles and coverage profiles. It also handles
8442 (license license:gpl2+)))
8444 (define-public r-rcas
8450 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8452 (file-name (string-append name "-" version ".tar.gz"))
8455 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8456 (build-system r-build-system)
8458 `(("r-knitr" ,r-knitr)
8459 ("r-testthat" ,r-testthat)
8460 ;; During vignette building knitr checks that "pandoc-citeproc"
8462 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8464 `(("r-data-table" ,r-data-table)
8465 ("r-biomart" ,r-biomart)
8466 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8467 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8468 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8469 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8470 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8471 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8472 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8473 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8474 ("r-topgo" ,r-topgo)
8476 ("r-pbapply" ,r-pbapply)
8477 ("r-plotly" ,r-plotly)
8478 ("r-plotrix" ,r-plotrix)
8479 ("r-motifrg" ,r-motifrg)
8480 ("r-genomation" ,r-genomation)
8481 ("r-genomicfeatures" ,r-genomicfeatures)
8482 ("r-rtracklayer" ,r-rtracklayer)
8483 ("r-rmarkdown" ,r-rmarkdown)))
8484 (synopsis "RNA-centric annotation system")
8486 "RCAS aims to be a standalone RNA-centric annotation system that provides
8487 intuitive reports and publication-ready graphics. This package provides the R
8488 library implementing most of the pipeline's features.")
8489 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8490 (license license:artistic2.0)))
8492 (define-public rcas-web
8499 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8500 "releases/download/v" version
8501 "/rcas-web-" version ".tar.gz"))
8504 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8505 (build-system gnu-build-system)
8508 (modify-phases %standard-phases
8509 (add-after 'install 'wrap-executable
8510 (lambda* (#:key inputs outputs #:allow-other-keys)
8511 (let* ((out (assoc-ref outputs "out"))
8512 (json (assoc-ref inputs "guile-json"))
8513 (redis (assoc-ref inputs "guile-redis"))
8514 (path (string-append
8515 json "/share/guile/site/2.2:"
8516 redis "/share/guile/site/2.2")))
8517 (wrap-program (string-append out "/bin/rcas-web")
8518 `("GUILE_LOAD_PATH" ":" = (,path))
8519 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8520 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8523 `(("r-minimal" ,r-minimal)
8525 ("guile-next" ,guile-2.2)
8526 ("guile-json" ,guile-json)
8527 ("guile-redis" ,guile2.2-redis)))
8529 `(("pkg-config" ,pkg-config)))
8530 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8531 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8532 (description "This package provides a simple web interface for the
8533 @dfn{RNA-centric annotation system} (RCAS).")
8534 (license license:agpl3+)))
8536 (define-public r-mutationalpatterns
8538 (name "r-mutationalpatterns")
8543 (uri (bioconductor-uri "MutationalPatterns" version))
8546 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8547 (build-system r-build-system)
8549 `(("r-biocgenerics" ,r-biocgenerics)
8550 ("r-biostrings" ,r-biostrings)
8551 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8552 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8553 ("r-genomicranges" ,r-genomicranges)
8554 ("r-genomeinfodb" ,r-genomeinfodb)
8555 ("r-ggplot2" ,r-ggplot2)
8556 ("r-gridextra" ,r-gridextra)
8557 ("r-iranges" ,r-iranges)
8560 ("r-pracma" ,r-pracma)
8561 ("r-reshape2" ,r-reshape2)
8562 ("r-cowplot" ,r-cowplot)
8563 ("r-ggdendro" ,r-ggdendro)
8564 ("r-s4vectors" ,r-s4vectors)
8565 ("r-summarizedexperiment" ,r-summarizedexperiment)
8566 ("r-variantannotation" ,r-variantannotation)))
8567 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8568 (synopsis "Extract and visualize mutational patterns in genomic data")
8569 (description "This package provides an extensive toolset for the
8570 characterization and visualization of a wide range of mutational patterns
8571 in SNV base substitution data.")
8572 (license license:expat)))
8574 (define-public r-wgcna
8581 (uri (cran-uri "WGCNA" version))
8584 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8585 (properties `((upstream-name . "WGCNA")))
8586 (build-system r-build-system)
8588 `(("r-annotationdbi" ,r-annotationdbi)
8589 ("r-doparallel" ,r-doparallel)
8590 ("r-dynamictreecut" ,r-dynamictreecut)
8591 ("r-fastcluster" ,r-fastcluster)
8592 ("r-foreach" ,r-foreach)
8593 ("r-go-db" ,r-go-db)
8594 ("r-hmisc" ,r-hmisc)
8595 ("r-impute" ,r-impute)
8597 ("r-robust" ,r-robust)
8598 ("r-survival" ,r-survival)
8599 ("r-matrixstats" ,r-matrixstats)
8600 ("r-preprocesscore" ,r-preprocesscore)))
8602 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8603 (synopsis "Weighted correlation network analysis")
8605 "This package provides functions necessary to perform Weighted
8606 Correlation Network Analysis on high-dimensional data. It includes functions
8607 for rudimentary data cleaning, construction and summarization of correlation
8608 networks, module identification and functions for relating both variables and
8609 modules to sample traits. It also includes a number of utility functions for
8610 data manipulation and visualization.")
8611 (license license:gpl2+)))
8613 (define-public r-chipkernels
8614 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8617 (name "r-chipkernels")
8618 (version (string-append "1.1-" revision "." (string-take commit 9)))
8623 (url "https://github.com/ManuSetty/ChIPKernels.git")
8625 (file-name (string-append name "-" version))
8628 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8629 (build-system r-build-system)
8631 `(("r-iranges" ,r-iranges)
8632 ("r-xvector" ,r-xvector)
8633 ("r-biostrings" ,r-biostrings)
8634 ("r-bsgenome" ,r-bsgenome)
8635 ("r-gtools" ,r-gtools)
8636 ("r-genomicranges" ,r-genomicranges)
8637 ("r-sfsmisc" ,r-sfsmisc)
8638 ("r-kernlab" ,r-kernlab)
8639 ("r-s4vectors" ,r-s4vectors)
8640 ("r-biocgenerics" ,r-biocgenerics)))
8641 (home-page "https://github.com/ManuSetty/ChIPKernels")
8642 (synopsis "Build string kernels for DNA Sequence analysis")
8643 (description "ChIPKernels is an R package for building different string
8644 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8645 must be built and this dictionary can be used for determining kernels for DNA
8647 (license license:gpl2+))))
8649 (define-public r-seqgl
8656 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8657 "archive/" version ".tar.gz"))
8658 (file-name (string-append name "-" version ".tar.gz"))
8661 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8662 (build-system r-build-system)
8664 `(("r-biostrings" ,r-biostrings)
8665 ("r-chipkernels" ,r-chipkernels)
8666 ("r-genomicranges" ,r-genomicranges)
8667 ("r-spams" ,r-spams)
8668 ("r-wgcna" ,r-wgcna)
8669 ("r-fastcluster" ,r-fastcluster)))
8670 (home-page "https://github.com/ManuSetty/SeqGL")
8671 (synopsis "Group lasso for Dnase/ChIP-seq data")
8672 (description "SeqGL is a group lasso based algorithm to extract
8673 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8674 This package presents a method which uses group lasso to discriminate between
8675 bound and non bound genomic regions to accurately identify transcription
8676 factors bound at the specific regions.")
8677 (license license:gpl2+)))
8679 (define-public r-gkmsvm
8686 (uri (cran-uri "gkmSVM" version))
8689 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8690 (properties `((upstream-name . "gkmSVM")))
8691 (build-system r-build-system)
8693 `(("r-biocgenerics" ,r-biocgenerics)
8694 ("r-biostrings" ,r-biostrings)
8695 ("r-genomeinfodb" ,r-genomeinfodb)
8696 ("r-genomicranges" ,r-genomicranges)
8697 ("r-iranges" ,r-iranges)
8698 ("r-kernlab" ,r-kernlab)
8701 ("r-rtracklayer" ,r-rtracklayer)
8702 ("r-s4vectors" ,r-s4vectors)
8703 ("r-seqinr" ,r-seqinr)))
8704 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8705 (synopsis "Gapped-kmer support vector machine")
8707 "This R package provides tools for training gapped-kmer SVM classifiers
8708 for DNA and protein sequences. This package supports several sequence
8709 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8710 (license license:gpl2+)))
8712 (define-public r-tximport
8718 (uri (bioconductor-uri "tximport" version))
8721 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8722 (build-system r-build-system)
8723 (home-page "https://bioconductor.org/packages/tximport")
8724 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8726 "This package provides tools to import transcript-level abundance,
8727 estimated counts and transcript lengths, and to summarize them into matrices
8728 for use with downstream gene-level analysis packages. Average transcript
8729 length, weighted by sample-specific transcript abundance estimates, is
8730 provided as a matrix which can be used as an offset for different expression
8731 of gene-level counts.")
8732 (license license:gpl2+)))
8734 (define-public r-rhdf5
8740 (uri (bioconductor-uri "rhdf5" version))
8743 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8744 (build-system r-build-system)
8747 (modify-phases %standard-phases
8748 (add-after 'unpack 'unpack-smallhdf5
8749 (lambda* (#:key outputs #:allow-other-keys)
8750 (system* "tar" "-xzvf"
8751 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8752 (substitute* "src/hdf5/configure"
8754 ;; Remove timestamp and host system information to make
8755 ;; the build reproducible.
8756 (substitute* "src/hdf5/src/libhdf5.settings.in"
8757 (("Configured on: @CONFIG_DATE@")
8758 "Configured on: Guix")
8759 (("Uname information:.*")
8760 "Uname information: Linux\n")
8761 ;; Remove unnecessary store reference.
8763 "C Compiler: GCC\n"))
8766 `(("r-zlibbioc" ,r-zlibbioc)))
8770 (home-page "https://bioconductor.org/packages/rhdf5")
8771 (synopsis "HDF5 interface to R")
8773 "This R/Bioconductor package provides an interface between HDF5 and R.
8774 HDF5's main features are the ability to store and access very large and/or
8775 complex datasets and a wide variety of metadata on mass storage (disk) through
8776 a completely portable file format. The rhdf5 package is thus suited for the
8777 exchange of large and/or complex datasets between R and other software
8778 package, and for letting R applications work on datasets that are larger than
8779 the available RAM.")
8780 (license license:artistic2.0)))
8782 (define-public r-annotationfilter
8784 (name "r-annotationfilter")
8788 (uri (bioconductor-uri "AnnotationFilter" version))
8791 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8793 `((upstream-name . "AnnotationFilter")))
8794 (build-system r-build-system)
8796 `(("r-genomicranges" ,r-genomicranges)
8797 ("r-lazyeval" ,r-lazyeval)))
8798 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8799 (synopsis "Facilities for filtering Bioconductor annotation resources")
8801 "This package provides classes and other infrastructure to implement
8802 filters for manipulating Bioconductor annotation resources. The filters are
8803 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8804 (license license:artistic2.0)))
8806 (define-public emboss
8812 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8813 (version-major+minor version) ".0/"
8814 "EMBOSS-" version ".tar.gz"))
8817 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8818 (build-system gnu-build-system)
8821 (list (string-append "--with-hpdf="
8822 (assoc-ref %build-inputs "libharu")))
8824 (modify-phases %standard-phases
8825 (add-after 'unpack 'fix-checks
8827 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8828 ;; and zlib, but assume that they are all found at the same
8830 (substitute* "configure.in"
8831 (("CHECK_PNGDRIVER")
8832 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8833 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8834 AM_CONDITIONAL(AMPNG, true)"))
8836 (add-after 'fix-checks 'disable-update-check
8838 ;; At build time there is no connection to the Internet, so
8839 ;; looking for updates will not work.
8840 (substitute* "Makefile.am"
8841 (("\\$\\(bindir\\)/embossupdate") ""))
8843 (add-after 'disable-update-check 'autogen
8844 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8850 ("libharu" ,libharu)
8853 `(("autoconf" ,autoconf)
8854 ("automake" ,automake)
8855 ("libtool" ,libtool)
8856 ("pkg-config" ,pkg-config)))
8857 (home-page "http://emboss.sourceforge.net")
8858 (synopsis "Molecular biology analysis suite")
8859 (description "EMBOSS is the \"European Molecular Biology Open Software
8860 Suite\". EMBOSS is an analysis package specially developed for the needs of
8861 the molecular biology (e.g. EMBnet) user community. The software
8862 automatically copes with data in a variety of formats and even allows
8863 transparent retrieval of sequence data from the web. It also provides a
8864 number of libraries for the development of software in the field of molecular
8865 biology. EMBOSS also integrates a range of currently available packages and
8866 tools for sequence analysis into a seamless whole.")
8867 (license license:gpl2+)))
8870 (let ((revision "1")
8871 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8874 ;; The version is 2.13.0 even though no release archives have been
8875 ;; published as yet.
8876 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8880 (url "https://github.com/arq5x/bits.git")
8882 (file-name (string-append name "-" version "-checkout"))
8885 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8886 (build-system gnu-build-system)
8888 `(#:tests? #f ;no tests included
8890 (modify-phases %standard-phases
8892 (add-after 'unpack 'remove-cuda
8894 (substitute* "Makefile"
8896 (("(bits_test_intersections) \\\\" _ match) match))
8899 (lambda* (#:key outputs #:allow-other-keys)
8901 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8906 (home-page "https://github.com/arq5x/bits")
8907 (synopsis "Implementation of binary interval search algorithm")
8908 (description "This package provides an implementation of the
8909 BITS (Binary Interval Search) algorithm, an approach to interval set
8910 intersection. It is especially suited for the comparison of diverse genomic
8911 datasets and the exploration of large datasets of genome
8912 intervals (e.g. genes, sequence alignments).")
8913 (license license:gpl2))))
8915 (define-public piranha
8916 ;; There is no release tarball for the latest version. The latest commit is
8917 ;; older than one year at the time of this writing.
8918 (let ((revision "1")
8919 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8922 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8926 (url "https://github.com/smithlabcode/piranha.git")
8928 (file-name (git-file-name name version))
8931 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8932 (build-system gnu-build-system)
8934 `(#:test-target "test"
8936 (modify-phases %standard-phases
8937 (add-after 'unpack 'copy-smithlab-cpp
8938 (lambda* (#:key inputs #:allow-other-keys)
8939 (for-each (lambda (file)
8940 (install-file file "./src/smithlab_cpp/"))
8941 (find-files (assoc-ref inputs "smithlab-cpp")))
8943 (add-after 'install 'install-to-store
8944 (lambda* (#:key outputs #:allow-other-keys)
8945 (let* ((out (assoc-ref outputs "out"))
8946 (bin (string-append out "/bin")))
8947 (for-each (lambda (file)
8948 (install-file file bin))
8949 (find-files "bin" ".*")))
8952 (list (string-append "--with-bam_tools_headers="
8953 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8954 (string-append "--with-bam_tools_library="
8955 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8957 `(("bamtools" ,bamtools)
8958 ("samtools" ,samtools-0.1)
8961 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8965 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8967 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8970 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8972 `(("python" ,python-2)))
8973 (home-page "https://github.com/smithlabcode/piranha")
8974 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8976 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8977 RIP-seq experiments. It takes input in BED or BAM format and identifies
8978 regions of statistically significant read enrichment. Additional covariates
8979 may optionally be provided to further inform the peak-calling process.")
8980 (license license:gpl3+))))
8988 (uri (string-append "https://pypi.python.org/packages/source/P"
8989 "/PePr/PePr-" version ".tar.gz"))
8992 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8993 (build-system python-build-system)
8995 `(#:python ,python-2 ; python2 only
8996 #:tests? #f)) ; no tests included
8998 `(("python2-numpy" ,python2-numpy)
8999 ("python2-scipy" ,python2-scipy)
9000 ("python2-pysam" ,python2-pysam)))
9001 (home-page "https://github.com/shawnzhangyx/PePr")
9002 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9004 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9005 that is primarily designed for data with biological replicates. It uses a
9006 negative binomial distribution to model the read counts among the samples in
9007 the same group, and look for consistent differences between ChIP and control
9008 group or two ChIP groups run under different conditions.")
9009 (license license:gpl3+)))
9011 (define-public filevercmp
9012 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9015 (version (string-append "0-1." (string-take commit 7)))
9018 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9020 (file-name (string-append name "-" version ".tar.gz"))
9022 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9023 (build-system gnu-build-system)
9025 `(#:tests? #f ; There are no tests to run.
9027 (modify-phases %standard-phases
9028 (delete 'configure) ; There is no configure phase.
9030 (lambda* (#:key outputs #:allow-other-keys)
9031 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9032 (install-file "filevercmp" bin)))))))
9033 (home-page "https://github.com/ekg/filevercmp")
9034 (synopsis "This program compares version strings")
9035 (description "This program compares version strings. It intends to be a
9036 replacement for strverscmp.")
9037 (license license:gpl3+))))
9039 (define-public multiqc
9046 (uri (pypi-uri "multiqc" version))
9049 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
9050 (build-system python-build-system)
9052 `(("python-jinja2" ,python-jinja2)
9053 ("python-simplejson" ,python-simplejson)
9054 ("python-pyyaml" ,python-pyyaml)
9055 ("python-click" ,python-click)
9056 ("python-spectra" ,python-spectra)
9057 ("python-requests" ,python-requests)
9058 ("python-markdown" ,python-markdown)
9059 ("python-lzstring" ,python-lzstring)
9060 ("python-matplotlib" ,python-matplotlib)
9061 ("python-numpy" ,python-numpy)
9062 ;; MultQC checks for the presence of nose at runtime.
9063 ("python-nose" ,python-nose)))
9064 (home-page "http://multiqc.info")
9065 (synopsis "Aggregate bioinformatics analysis reports")
9067 "MultiQC is a tool to aggregate bioinformatics results across many
9068 samples into a single report. It contains modules for a large number of
9069 common bioinformatics tools.")
9070 (license license:gpl3+)))
9072 (define-public r-chipseq
9079 (uri (bioconductor-uri "chipseq" version))
9082 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
9083 (build-system r-build-system)
9085 `(("r-biocgenerics" ,r-biocgenerics)
9086 ("r-genomicranges" ,r-genomicranges)
9087 ("r-iranges" ,r-iranges)
9088 ("r-lattice" ,r-lattice)
9089 ("r-s4vectors" ,r-s4vectors)
9090 ("r-shortread" ,r-shortread)))
9091 (home-page "https://bioconductor.org/packages/chipseq")
9092 (synopsis "Package for analyzing ChIPseq data")
9094 "This package provides tools for processing short read data from ChIPseq
9096 (license license:artistic2.0)))
9098 (define-public r-copyhelper
9100 (name "r-copyhelper")
9105 (uri (string-append "https://bioconductor.org/packages/release/"
9106 "data/experiment/src/contrib/CopyhelpeR_"
9110 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9111 (properties `((upstream-name . "CopyhelpeR")))
9112 (build-system r-build-system)
9113 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9114 (synopsis "Helper files for CopywriteR")
9116 "This package contains the helper files that are required to run the
9117 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9118 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9119 mm10. In addition, it contains a blacklist filter to remove regions that
9120 display copy number variation. Files are stored as GRanges objects from the
9121 GenomicRanges Bioconductor package.")
9122 (license license:gpl2)))
9124 (define-public r-copywriter
9126 (name "r-copywriter")
9131 (uri (bioconductor-uri "CopywriteR" version))
9134 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9135 (properties `((upstream-name . "CopywriteR")))
9136 (build-system r-build-system)
9138 `(("r-biocparallel" ,r-biocparallel)
9139 ("r-chipseq" ,r-chipseq)
9140 ("r-copyhelper" ,r-copyhelper)
9141 ("r-data-table" ,r-data-table)
9142 ("r-dnacopy" ,r-dnacopy)
9143 ("r-futile-logger" ,r-futile-logger)
9144 ("r-genomeinfodb" ,r-genomeinfodb)
9145 ("r-genomicalignments" ,r-genomicalignments)
9146 ("r-genomicranges" ,r-genomicranges)
9147 ("r-gtools" ,r-gtools)
9148 ("r-iranges" ,r-iranges)
9149 ("r-matrixstats" ,r-matrixstats)
9150 ("r-rsamtools" ,r-rsamtools)
9151 ("r-s4vectors" ,r-s4vectors)))
9152 (home-page "https://github.com/PeeperLab/CopywriteR")
9153 (synopsis "Copy number information from targeted sequencing")
9155 "CopywriteR extracts DNA copy number information from targeted sequencing
9156 by utilizing off-target reads. It allows for extracting uniformly distributed
9157 copy number information, can be used without reference, and can be applied to
9158 sequencing data obtained from various techniques including chromatin
9159 immunoprecipitation and target enrichment on small gene panels. Thereby,
9160 CopywriteR constitutes a widely applicable alternative to available copy
9161 number detection tools.")
9162 (license license:gpl2)))
9164 (define-public r-methylkit
9166 (name "r-methylkit")
9170 (uri (bioconductor-uri "methylKit" version))
9173 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9174 (properties `((upstream-name . "methylKit")))
9175 (build-system r-build-system)
9177 `(("r-data-table" ,r-data-table)
9178 ("r-emdbook" ,r-emdbook)
9179 ("r-fastseg" ,r-fastseg)
9180 ("r-genomeinfodb" ,r-genomeinfodb)
9181 ("r-genomicranges" ,r-genomicranges)
9182 ("r-gtools" ,r-gtools)
9183 ("r-iranges" ,r-iranges)
9184 ("r-kernsmooth" ,r-kernsmooth)
9185 ("r-limma" ,r-limma)
9186 ("r-mclust" ,r-mclust)
9187 ("r-qvalue" ,r-qvalue)
9188 ("r-r-utils" ,r-r-utils)
9190 ("r-rhtslib" ,r-rhtslib)
9191 ("r-rsamtools" ,r-rsamtools)
9192 ("r-rtracklayer" ,r-rtracklayer)
9193 ("r-s4vectors" ,r-s4vectors)
9194 ("r-zlibbioc" ,r-zlibbioc)))
9197 (home-page "https://github.com/al2na/methylKit")
9199 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9201 "MethylKit is an R package for DNA methylation analysis and annotation
9202 from high-throughput bisulfite sequencing. The package is designed to deal
9203 with sequencing data from @dfn{Reduced representation bisulfite
9204 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9205 genome bisulfite sequencing. It also has functions to analyze base-pair
9206 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9208 (license license:artistic2.0)))
9210 (define-public r-sva
9217 (uri (bioconductor-uri "sva" version))
9220 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9221 (build-system r-build-system)
9223 `(("r-genefilter" ,r-genefilter)
9225 ("r-biocparallel" ,r-biocparallel)
9226 ("r-matrixstats" ,r-matrixstats)
9227 ("r-limma" ,r-limma)))
9228 (home-page "https://bioconductor.org/packages/sva")
9229 (synopsis "Surrogate variable analysis")
9231 "This package contains functions for removing batch effects and other
9232 unwanted variation in high-throughput experiment. It also contains functions
9233 for identifying and building surrogate variables for high-dimensional data
9234 sets. Surrogate variables are covariates constructed directly from
9235 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9236 imaging data that can be used in subsequent analyses to adjust for unknown,
9237 unmodeled, or latent sources of noise.")
9238 (license license:artistic2.0)))
9240 (define-public r-seqminer
9247 (uri (cran-uri "seqminer" version))
9250 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9251 (build-system r-build-system)
9254 (home-page "http://seqminer.genomic.codes")
9255 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9257 "This package provides tools to integrate nucleotide sequencing
9258 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9259 ;; Any version of the GPL is acceptable
9260 (license (list license:gpl2+ license:gpl3+))))
9262 (define-public r-raremetals2
9264 (name "r-raremetals2")
9269 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9270 "b/b7/RareMETALS2_" version ".tar.gz"))
9273 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9274 (properties `((upstream-name . "RareMETALS2")))
9275 (build-system r-build-system)
9277 `(("r-seqminer" ,r-seqminer)
9278 ("r-mvtnorm" ,r-mvtnorm)
9280 ("r-compquadform" ,r-compquadform)
9281 ("r-getopt" ,r-getopt)))
9282 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9283 (synopsis "Analyze gene-level association tests for binary trait")
9285 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9286 It was designed to meta-analyze gene-level association tests for binary trait.
9287 While rareMETALS offers a near-complete solution for meta-analysis of
9288 gene-level tests for quantitative trait, it does not offer the optimal
9289 solution for binary trait. The package rareMETALS2 offers improved features
9290 for analyzing gene-level association tests in meta-analyses for binary
9292 (license license:gpl3)))
9294 (define-public r-maldiquant
9296 (name "r-maldiquant")
9301 (uri (cran-uri "MALDIquant" version))
9304 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9305 (properties `((upstream-name . "MALDIquant")))
9306 (build-system r-build-system)
9307 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9308 (synopsis "Quantitative analysis of mass spectrometry data")
9310 "This package provides a complete analysis pipeline for matrix-assisted
9311 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9312 two-dimensional mass spectrometry data. In addition to commonly used plotting
9313 and processing methods it includes distinctive features, namely baseline
9314 subtraction methods such as morphological filters (TopHat) or the
9315 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9316 alignment using warping functions, handling of replicated measurements as well
9317 as allowing spectra with different resolutions.")
9318 (license license:gpl3+)))
9320 (define-public r-protgenerics
9322 (name "r-protgenerics")
9327 (uri (bioconductor-uri "ProtGenerics" version))
9330 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9331 (properties `((upstream-name . "ProtGenerics")))
9332 (build-system r-build-system)
9333 (home-page "https://github.com/lgatto/ProtGenerics")
9334 (synopsis "S4 generic functions for proteomics infrastructure")
9336 "This package provides S4 generic functions needed by Bioconductor
9337 proteomics packages.")
9338 (license license:artistic2.0)))
9340 (define-public r-mzr
9347 (uri (bioconductor-uri "mzR" version))
9350 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9351 (modules '((guix build utils)))
9354 (delete-file-recursively "src/boost")
9356 (properties `((upstream-name . "mzR")))
9357 (build-system r-build-system)
9360 (modify-phases %standard-phases
9361 (add-after 'unpack 'use-system-boost
9363 (substitute* "src/Makevars"
9364 (("\\./boost/libs.*") "")
9365 (("ARCH_OBJS=" line)
9367 "\nARCH_LIBS=-lboost_system -lboost_regex \
9368 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9371 `(("boost" ,boost) ; use this instead of the bundled boost sources
9372 ("netcdf" ,netcdf)))
9374 `(("r-biobase" ,r-biobase)
9375 ("r-biocgenerics" ,r-biocgenerics)
9376 ("r-protgenerics" ,r-protgenerics)
9378 ("r-zlibbioc" ,r-zlibbioc)))
9379 (home-page "https://github.com/sneumann/mzR/")
9380 (synopsis "Parser for mass spectrometry data files")
9382 "The mzR package provides a unified API to the common file formats and
9383 parsers available for mass spectrometry data. It comes with a wrapper for the
9384 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9385 The package contains the original code written by the ISB, and a subset of the
9386 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9387 previously been used in XCMS.")
9388 (license license:artistic2.0)))
9390 (define-public r-affyio
9397 (uri (bioconductor-uri "affyio" version))
9400 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9401 (build-system r-build-system)
9403 `(("r-zlibbioc" ,r-zlibbioc)))
9406 (home-page "https://github.com/bmbolstad/affyio")
9407 (synopsis "Tools for parsing Affymetrix data files")
9409 "This package provides routines for parsing Affymetrix data files based
9410 upon file format information. The primary focus is on accessing the CEL and
9412 (license license:lgpl2.0+)))
9414 (define-public r-affy
9421 (uri (bioconductor-uri "affy" version))
9424 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9425 (build-system r-build-system)
9427 `(("r-affyio" ,r-affyio)
9428 ("r-biobase" ,r-biobase)
9429 ("r-biocgenerics" ,r-biocgenerics)
9430 ("r-biocinstaller" ,r-biocinstaller)
9431 ("r-preprocesscore" ,r-preprocesscore)
9432 ("r-zlibbioc" ,r-zlibbioc)))
9433 (home-page "https://bioconductor.org/packages/affy")
9434 (synopsis "Methods for affymetrix oligonucleotide arrays")
9436 "This package contains functions for exploratory oligonucleotide array
9438 (license license:lgpl2.0+)))
9440 (define-public r-vsn
9447 (uri (bioconductor-uri "vsn" version))
9450 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9451 (build-system r-build-system)
9453 `(("r-affy" ,r-affy)
9454 ("r-biobase" ,r-biobase)
9455 ("r-ggplot2" ,r-ggplot2)
9456 ("r-lattice" ,r-lattice)
9457 ("r-limma" ,r-limma)))
9458 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9459 (synopsis "Variance stabilization and calibration for microarray data")
9461 "The package implements a method for normalising microarray intensities,
9462 and works for single- and multiple-color arrays. It can also be used for data
9463 from other technologies, as long as they have similar format. The method uses
9464 a robust variant of the maximum-likelihood estimator for an
9465 additive-multiplicative error model and affine calibration. The model
9466 incorporates data calibration step (a.k.a. normalization), a model for the
9467 dependence of the variance on the mean intensity and a variance stabilizing
9468 data transformation. Differences between transformed intensities are
9469 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9470 their variance is independent of the mean, and they are usually more sensitive
9471 and specific in detecting differential transcription.")
9472 (license license:artistic2.0)))
9474 (define-public r-mzid
9481 (uri (bioconductor-uri "mzID" version))
9484 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9485 (properties `((upstream-name . "mzID")))
9486 (build-system r-build-system)
9488 `(("r-doparallel" ,r-doparallel)
9489 ("r-foreach" ,r-foreach)
9490 ("r-iterators" ,r-iterators)
9492 ("r-protgenerics" ,r-protgenerics)
9495 (home-page "https://bioconductor.org/packages/mzID")
9496 (synopsis "Parser for mzIdentML files")
9498 "This package provides a parser for mzIdentML files implemented using the
9499 XML package. The parser tries to be general and able to handle all types of
9500 mzIdentML files with the drawback of having less pretty output than a vendor
9502 (license license:gpl2+)))
9504 (define-public r-pcamethods
9506 (name "r-pcamethods")
9511 (uri (bioconductor-uri "pcaMethods" version))
9514 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9515 (properties `((upstream-name . "pcaMethods")))
9516 (build-system r-build-system)
9518 `(("r-biobase" ,r-biobase)
9519 ("r-biocgenerics" ,r-biocgenerics)
9521 ("r-rcpp" ,r-rcpp)))
9522 (home-page "https://github.com/hredestig/pcamethods")
9523 (synopsis "Collection of PCA methods")
9525 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9526 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9527 for missing value estimation is included for comparison. BPCA, PPCA and
9528 NipalsPCA may be used to perform PCA on incomplete data as well as for
9529 accurate missing value estimation. A set of methods for printing and plotting
9530 the results is also provided. All PCA methods make use of the same data
9531 structure (pcaRes) to provide a common interface to the PCA results.")
9532 (license license:gpl3+)))
9534 (define-public r-msnbase
9541 (uri (bioconductor-uri "MSnbase" version))
9544 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9545 (properties `((upstream-name . "MSnbase")))
9546 (build-system r-build-system)
9548 `(("r-affy" ,r-affy)
9549 ("r-biobase" ,r-biobase)
9550 ("r-biocgenerics" ,r-biocgenerics)
9551 ("r-biocparallel" ,r-biocparallel)
9552 ("r-digest" ,r-digest)
9553 ("r-ggplot2" ,r-ggplot2)
9554 ("r-impute" ,r-impute)
9555 ("r-iranges" ,r-iranges)
9556 ("r-lattice" ,r-lattice)
9557 ("r-maldiquant" ,r-maldiquant)
9560 ("r-pcamethods" ,r-pcamethods)
9562 ("r-preprocesscore" ,r-preprocesscore)
9563 ("r-protgenerics" ,r-protgenerics)
9565 ("r-s4vectors" ,r-s4vectors)
9568 (home-page "https://github.com/lgatto/MSnbase")
9569 (synopsis "Base functions and classes for MS-based proteomics")
9571 "This package provides basic plotting, data manipulation and processing
9572 of mass spectrometry based proteomics data.")
9573 (license license:artistic2.0)))
9575 (define-public r-msnid
9582 (uri (bioconductor-uri "MSnID" version))
9585 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9586 (properties `((upstream-name . "MSnID")))
9587 (build-system r-build-system)
9589 `(("r-biobase" ,r-biobase)
9590 ("r-data-table" ,r-data-table)
9591 ("r-doparallel" ,r-doparallel)
9592 ("r-dplyr" ,r-dplyr)
9593 ("r-foreach" ,r-foreach)
9594 ("r-iterators" ,r-iterators)
9595 ("r-msnbase" ,r-msnbase)
9598 ("r-protgenerics" ,r-protgenerics)
9599 ("r-r-cache" ,r-r-cache)
9601 ("r-reshape2" ,r-reshape2)))
9602 (home-page "https://bioconductor.org/packages/MSnID")
9603 (synopsis "Utilities for LC-MSn proteomics identifications")
9605 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9606 from mzIdentML (leveraging the mzID package) or text files. After collating
9607 the search results from multiple datasets it assesses their identification
9608 quality and optimize filtering criteria to achieve the maximum number of
9609 identifications while not exceeding a specified false discovery rate. It also
9610 contains a number of utilities to explore the MS/MS results and assess missed
9611 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9612 (license license:artistic2.0)))
9614 (define-public r-seurat
9620 (uri (cran-uri "Seurat" version))
9623 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9624 ;; Delete pre-built jar.
9626 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9628 (properties `((upstream-name . "Seurat")))
9629 (build-system r-build-system)
9632 (modify-phases %standard-phases
9633 (add-after 'unpack 'build-jar
9634 (lambda* (#:key inputs #:allow-other-keys)
9635 (let ((classesdir "tmp-classes"))
9636 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9638 (with-output-to-file "manifest"
9640 (display "Manifest-Version: 1.0
9641 Main-Class: ModularityOptimizer\n")))
9642 (and (zero? (apply system* `("javac" "-d" ,classesdir
9643 ,@(find-files "java" "\\.java$"))))
9644 (zero? (system* "jar"
9646 "inst/java/ModularityOptimizer.jar"
9647 "-C" classesdir ".")))))))))
9649 `(("jdk" ,icedtea "jdk")))
9652 ("r-caret" ,r-caret)
9653 ("r-cowplot" ,r-cowplot)
9654 ("r-diffusionmap" ,r-diffusionmap)
9655 ("r-dplyr" ,r-dplyr)
9659 ("r-gdata" ,r-gdata)
9660 ("r-ggplot2" ,r-ggplot2)
9661 ("r-ggridges" ,r-ggridges)
9662 ("r-gplots" ,r-gplots)
9663 ("r-gridextra" ,r-gridextra)
9664 ("r-hmisc" ,r-hmisc)
9666 ("r-igraph" ,r-igraph)
9667 ("r-irlba" ,r-irlba)
9670 ("r-matrix" ,r-matrix)
9671 ("r-metap" ,r-metap)
9672 ("r-mixtools" ,r-mixtools)
9673 ("r-pbapply" ,r-pbapply)
9674 ("r-plotly" ,r-plotly)
9675 ("r-ranger" ,r-ranger)
9676 ("r-rcolorbrewer" ,r-rcolorbrewer)
9678 ("r-rcppeigen" ,r-rcppeigen)
9679 ("r-rcppprogress" ,r-rcppprogress)
9680 ("r-reshape2" ,r-reshape2)
9682 ("r-rtsne" ,r-rtsne)
9683 ("r-sdmtools" ,r-sdmtools)
9684 ("r-stringr" ,r-stringr)
9685 ("r-tclust" ,r-tclust)
9686 ("r-tidyr" ,r-tidyr)
9688 ("r-vgam" ,r-vgam)))
9689 (home-page "http://www.satijalab.org/seurat")
9690 (synopsis "Seurat is an R toolkit for single cell genomics")
9692 "This package is an R package designed for QC, analysis, and
9693 exploration of single cell RNA-seq data. It easily enables widely-used
9694 analytical techniques, including the identification of highly variable genes,
9695 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9696 algorithms; density clustering, hierarchical clustering, k-means, and the
9697 discovery of differentially expressed genes and markers.")
9698 (license license:gpl3)))
9700 (define-public r-aroma-light
9702 (name "r-aroma-light")
9707 (uri (bioconductor-uri "aroma.light" version))
9710 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9711 (properties `((upstream-name . "aroma.light")))
9712 (build-system r-build-system)
9714 `(("r-matrixstats" ,r-matrixstats)
9715 ("r-r-methodss3" ,r-r-methodss3)
9717 ("r-r-utils" ,r-r-utils)))
9718 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9719 (synopsis "Methods for normalization and visualization of microarray data")
9721 "This package provides methods for microarray analysis that take basic
9722 data types such as matrices and lists of vectors. These methods can be used
9723 standalone, be utilized in other packages, or be wrapped up in higher-level
9725 (license license:gpl2+)))
9727 (define-public r-deseq
9734 (uri (bioconductor-uri "DESeq" version))
9737 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9738 (properties `((upstream-name . "DESeq")))
9739 (build-system r-build-system)
9741 `(("r-biobase" ,r-biobase)
9742 ("r-biocgenerics" ,r-biocgenerics)
9743 ("r-genefilter" ,r-genefilter)
9744 ("r-geneplotter" ,r-geneplotter)
9745 ("r-lattice" ,r-lattice)
9746 ("r-locfit" ,r-locfit)
9748 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9749 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9750 (synopsis "Differential gene expression analysis")
9752 "This package provides tools for estimating variance-mean dependence in
9753 count data from high-throughput genetic sequencing assays and for testing for
9754 differential expression based on a model using the negative binomial
9756 (license license:gpl3+)))
9758 (define-public r-edaseq
9765 (uri (bioconductor-uri "EDASeq" version))
9768 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9769 (properties `((upstream-name . "EDASeq")))
9770 (build-system r-build-system)
9772 `(("r-annotationdbi" ,r-annotationdbi)
9773 ("r-aroma-light" ,r-aroma-light)
9774 ("r-biobase" ,r-biobase)
9775 ("r-biocgenerics" ,r-biocgenerics)
9776 ("r-biomart" ,r-biomart)
9777 ("r-biostrings" ,r-biostrings)
9778 ("r-deseq" ,r-deseq)
9779 ("r-genomicfeatures" ,r-genomicfeatures)
9780 ("r-genomicranges" ,r-genomicranges)
9781 ("r-iranges" ,r-iranges)
9782 ("r-rsamtools" ,r-rsamtools)
9783 ("r-shortread" ,r-shortread)))
9784 (home-page "https://github.com/drisso/EDASeq")
9785 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9787 "This package provides support for numerical and graphical summaries of
9788 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9789 adjust for GC-content effect (or other gene-level effects) on read counts:
9790 loess robust local regression, global-scaling, and full-quantile
9791 normalization. Between-lane normalization procedures to adjust for
9792 distributional differences between lanes (e.g., sequencing depth):
9793 global-scaling and full-quantile normalization.")
9794 (license license:artistic2.0)))
9796 (define-public r-interactivedisplaybase
9798 (name "r-interactivedisplaybase")
9803 (uri (bioconductor-uri "interactiveDisplayBase" version))
9806 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9808 `((upstream-name . "interactiveDisplayBase")))
9809 (build-system r-build-system)
9811 `(("r-biocgenerics" ,r-biocgenerics)
9812 ("r-shiny" ,r-shiny)))
9813 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9814 (synopsis "Base package for web displays of Bioconductor objects")
9816 "This package contains the basic methods needed to generate interactive
9817 Shiny-based display methods for Bioconductor objects.")
9818 (license license:artistic2.0)))
9820 (define-public r-annotationhub
9822 (name "r-annotationhub")
9827 (uri (bioconductor-uri "AnnotationHub" version))
9830 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9831 (properties `((upstream-name . "AnnotationHub")))
9832 (build-system r-build-system)
9834 `(("r-annotationdbi" ,r-annotationdbi)
9835 ("r-biocgenerics" ,r-biocgenerics)
9836 ("r-biocinstaller" ,r-biocinstaller)
9839 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9840 ("r-rsqlite" ,r-rsqlite)
9841 ("r-s4vectors" ,r-s4vectors)
9842 ("r-yaml" ,r-yaml)))
9843 (home-page "https://bioconductor.org/packages/AnnotationHub")
9844 (synopsis "Client to access AnnotationHub resources")
9846 "This package provides a client for the Bioconductor AnnotationHub web
9847 resource. The AnnotationHub web resource provides a central location where
9848 genomic files (e.g. VCF, bed, wig) and other resources from standard
9849 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9850 metadata about each resource, e.g., a textual description, tags, and date of
9851 modification. The client creates and manages a local cache of files retrieved
9852 by the user, helping with quick and reproducible access.")
9853 (license license:artistic2.0)))
9855 (define-public r-fastseg
9862 (uri (bioconductor-uri "fastseg" version))
9865 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9866 (build-system r-build-system)
9868 `(("r-biobase" ,r-biobase)
9869 ("r-biocgenerics" ,r-biocgenerics)
9870 ("r-genomicranges" ,r-genomicranges)
9871 ("r-iranges" ,r-iranges)
9872 ("r-s4vectors" ,r-s4vectors)))
9873 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9874 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9876 "Fastseg implements a very fast and efficient segmentation algorithm.
9877 It can segment data from DNA microarrays and data from next generation
9878 sequencing for example to detect copy number segments. Further it can segment
9879 data from RNA microarrays like tiling arrays to identify transcripts. Most
9880 generally, it can segment data given as a matrix or as a vector. Various data
9881 formats can be used as input to fastseg like expression set objects for
9882 microarrays or GRanges for sequencing data.")
9883 (license license:lgpl2.0+)))
9885 (define-public r-keggrest
9892 (uri (bioconductor-uri "KEGGREST" version))
9895 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9896 (properties `((upstream-name . "KEGGREST")))
9897 (build-system r-build-system)
9899 `(("r-biostrings" ,r-biostrings)
9902 (home-page "https://bioconductor.org/packages/KEGGREST")
9903 (synopsis "Client-side REST access to KEGG")
9905 "This package provides a package that provides a client interface to the
9906 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9907 (license license:artistic2.0)))
9909 (define-public r-gage
9916 (uri (bioconductor-uri "gage" version))
9919 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9920 (build-system r-build-system)
9922 `(("r-annotationdbi" ,r-annotationdbi)
9923 ("r-graph" ,r-graph)
9924 ("r-keggrest" ,r-keggrest)))
9925 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9926 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9928 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9929 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9930 data attributes including sample sizes, experimental designs, assay platforms,
9931 and other types of heterogeneity. The gage package provides functions for
9932 basic GAGE analysis, result processing and presentation. In addition, it
9933 provides demo microarray data and commonly used gene set data based on KEGG
9934 pathways and GO terms. These funtions and data are also useful for gene set
9935 analysis using other methods.")
9936 (license license:gpl2+)))
9938 (define-public r-genomicfiles
9940 (name "r-genomicfiles")
9945 (uri (bioconductor-uri "GenomicFiles" version))
9948 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9949 (properties `((upstream-name . "GenomicFiles")))
9950 (build-system r-build-system)
9952 `(("r-biocgenerics" ,r-biocgenerics)
9953 ("r-biocparallel" ,r-biocparallel)
9954 ("r-genomeinfodb" ,r-genomeinfodb)
9955 ("r-genomicalignments" ,r-genomicalignments)
9956 ("r-genomicranges" ,r-genomicranges)
9957 ("r-iranges" ,r-iranges)
9958 ("r-rsamtools" ,r-rsamtools)
9959 ("r-rtracklayer" ,r-rtracklayer)
9960 ("r-s4vectors" ,r-s4vectors)
9961 ("r-summarizedexperiment" ,r-summarizedexperiment)
9962 ("r-variantannotation" ,r-variantannotation)))
9963 (home-page "https://bioconductor.org/packages/GenomicFiles")
9964 (synopsis "Distributed computing by file or by range")
9966 "This package provides infrastructure for parallel computations
9967 distributed by file or by range. User defined mapper and reducer functions
9968 provide added flexibility for data combination and manipulation.")
9969 (license license:artistic2.0)))
9971 (define-public r-complexheatmap
9973 (name "r-complexheatmap")
9978 (uri (bioconductor-uri "ComplexHeatmap" version))
9981 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9983 `((upstream-name . "ComplexHeatmap")))
9984 (build-system r-build-system)
9986 `(("r-circlize" ,r-circlize)
9987 ("r-colorspace" ,r-colorspace)
9988 ("r-getoptlong" ,r-getoptlong)
9989 ("r-globaloptions" ,r-globaloptions)
9990 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9992 "https://github.com/jokergoo/ComplexHeatmap")
9993 (synopsis "Making Complex Heatmaps")
9995 "Complex heatmaps are efficient to visualize associations between
9996 different sources of data sets and reveal potential structures. This package
9997 provides a highly flexible way to arrange multiple heatmaps and supports
9998 self-defined annotation graphics.")
9999 (license license:gpl2+)))
10001 (define-public r-dirichletmultinomial
10003 (name "r-dirichletmultinomial")
10008 (uri (bioconductor-uri "DirichletMultinomial" version))
10011 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
10013 `((upstream-name . "DirichletMultinomial")))
10014 (build-system r-build-system)
10018 `(("r-biocgenerics" ,r-biocgenerics)
10019 ("r-iranges" ,r-iranges)
10020 ("r-s4vectors" ,r-s4vectors)))
10021 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10022 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10024 "Dirichlet-multinomial mixture models can be used to describe variability
10025 in microbial metagenomic data. This package is an interface to code
10026 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10028 (license license:lgpl3)))
10030 (define-public r-ensembldb
10032 (name "r-ensembldb")
10037 (uri (bioconductor-uri "ensembldb" version))
10040 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
10041 (build-system r-build-system)
10043 `(("r-annotationdbi" ,r-annotationdbi)
10044 ("r-annotationfilter" ,r-annotationfilter)
10045 ("r-annotationhub" ,r-annotationhub)
10046 ("r-biobase" ,r-biobase)
10047 ("r-biocgenerics" ,r-biocgenerics)
10048 ("r-biostrings" ,r-biostrings)
10051 ("r-genomeinfodb" ,r-genomeinfodb)
10052 ("r-genomicfeatures" ,r-genomicfeatures)
10053 ("r-genomicranges" ,r-genomicranges)
10054 ("r-iranges" ,r-iranges)
10055 ("r-protgenerics" ,r-protgenerics)
10056 ("r-rsamtools" ,r-rsamtools)
10057 ("r-rsqlite" ,r-rsqlite)
10058 ("r-rtracklayer" ,r-rtracklayer)
10059 ("r-s4vectors" ,r-s4vectors)))
10060 (home-page "https://github.com/jotsetung/ensembldb")
10061 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10063 "The package provides functions to create and use transcript-centric
10064 annotation databases/packages. The annotation for the databases are directly
10065 fetched from Ensembl using their Perl API. The functionality and data is
10066 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10067 but, in addition to retrieve all gene/transcript models and annotations from
10068 the database, the @code{ensembldb} package also provides a filter framework
10069 allowing to retrieve annotations for specific entries like genes encoded on a
10070 chromosome region or transcript models of lincRNA genes.")
10071 ;; No version specified
10072 (license license:lgpl3+)))
10074 (define-public r-organismdbi
10076 (name "r-organismdbi")
10081 (uri (bioconductor-uri "OrganismDbi" version))
10084 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
10085 (properties `((upstream-name . "OrganismDbi")))
10086 (build-system r-build-system)
10088 `(("r-annotationdbi" ,r-annotationdbi)
10089 ("r-biobase" ,r-biobase)
10090 ("r-biocgenerics" ,r-biocgenerics)
10091 ("r-biocinstaller" ,r-biocinstaller)
10093 ("r-genomicfeatures" ,r-genomicfeatures)
10094 ("r-genomicranges" ,r-genomicranges)
10095 ("r-graph" ,r-graph)
10096 ("r-iranges" ,r-iranges)
10098 ("r-s4vectors" ,r-s4vectors)))
10099 (home-page "https://bioconductor.org/packages/OrganismDbi")
10100 (synopsis "Software to enable the smooth interfacing of database packages")
10101 (description "The package enables a simple unified interface to several
10102 annotation packages each of which has its own schema by taking advantage of
10103 the fact that each of these packages implements a select methods.")
10104 (license license:artistic2.0)))
10106 (define-public r-biovizbase
10108 (name "r-biovizbase")
10113 (uri (bioconductor-uri "biovizBase" version))
10116 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10117 (properties `((upstream-name . "biovizBase")))
10118 (build-system r-build-system)
10120 `(("r-annotationdbi" ,r-annotationdbi)
10121 ("r-annotationfilter" ,r-annotationfilter)
10122 ("r-biocgenerics" ,r-biocgenerics)
10123 ("r-biostrings" ,r-biostrings)
10124 ("r-dichromat" ,r-dichromat)
10125 ("r-ensembldb" ,r-ensembldb)
10126 ("r-genomeinfodb" ,r-genomeinfodb)
10127 ("r-genomicalignments" ,r-genomicalignments)
10128 ("r-genomicfeatures" ,r-genomicfeatures)
10129 ("r-genomicranges" ,r-genomicranges)
10130 ("r-hmisc" ,r-hmisc)
10131 ("r-iranges" ,r-iranges)
10132 ("r-rcolorbrewer" ,r-rcolorbrewer)
10133 ("r-rsamtools" ,r-rsamtools)
10134 ("r-s4vectors" ,r-s4vectors)
10135 ("r-scales" ,r-scales)
10136 ("r-summarizedexperiment" ,r-summarizedexperiment)
10137 ("r-variantannotation" ,r-variantannotation)))
10138 (home-page "https://bioconductor.org/packages/biovizBase")
10139 (synopsis "Basic graphic utilities for visualization of genomic data")
10141 "The biovizBase package is designed to provide a set of utilities, color
10142 schemes and conventions for genomic data. It serves as the base for various
10143 high-level packages for biological data visualization. This saves development
10144 effort and encourages consistency.")
10145 (license license:artistic2.0)))
10147 (define-public r-ggbio
10154 (uri (bioconductor-uri "ggbio" version))
10157 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10158 (build-system r-build-system)
10160 `(("r-annotationdbi" ,r-annotationdbi)
10161 ("r-annotationfilter" ,r-annotationfilter)
10162 ("r-biobase" ,r-biobase)
10163 ("r-biocgenerics" ,r-biocgenerics)
10164 ("r-biostrings" ,r-biostrings)
10165 ("r-biovizbase" ,r-biovizbase)
10166 ("r-bsgenome" ,r-bsgenome)
10167 ("r-ensembldb" ,r-ensembldb)
10168 ("r-genomeinfodb" ,r-genomeinfodb)
10169 ("r-genomicalignments" ,r-genomicalignments)
10170 ("r-genomicfeatures" ,r-genomicfeatures)
10171 ("r-genomicranges" ,r-genomicranges)
10172 ("r-ggally" ,r-ggally)
10173 ("r-ggplot2" ,r-ggplot2)
10174 ("r-gridextra" ,r-gridextra)
10175 ("r-gtable" ,r-gtable)
10176 ("r-hmisc" ,r-hmisc)
10177 ("r-iranges" ,r-iranges)
10178 ("r-organismdbi" ,r-organismdbi)
10179 ("r-reshape2" ,r-reshape2)
10180 ("r-rsamtools" ,r-rsamtools)
10181 ("r-rtracklayer" ,r-rtracklayer)
10182 ("r-s4vectors" ,r-s4vectors)
10183 ("r-scales" ,r-scales)
10184 ("r-summarizedexperiment" ,r-summarizedexperiment)
10185 ("r-variantannotation" ,r-variantannotation)))
10186 (home-page "http://www.tengfei.name/ggbio/")
10187 (synopsis "Visualization tools for genomic data")
10189 "The ggbio package extends and specializes the grammar of graphics for
10190 biological data. The graphics are designed to answer common scientific
10191 questions, in particular those often asked of high throughput genomics data.
10192 All core Bioconductor data structures are supported, where appropriate. The
10193 package supports detailed views of particular genomic regions, as well as
10194 genome-wide overviews. Supported overviews include ideograms and grand linear
10195 views. High-level plots include sequence fragment length, edge-linked
10196 interval to data view, mismatch pileup, and several splicing summaries.")
10197 (license license:artistic2.0)))
10199 (define-public r-gprofiler
10201 (name "r-gprofiler")
10206 (uri (cran-uri "gProfileR" version))
10209 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10210 (properties `((upstream-name . "gProfileR")))
10211 (build-system r-build-system)
10213 `(("r-plyr" ,r-plyr)
10214 ("r-rcurl" ,r-rcurl)))
10215 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10216 (synopsis "Interface to the g:Profiler toolkit")
10218 "This package provides tools for functional enrichment analysis,
10219 gene identifier conversion and mapping homologous genes across related
10220 organisms via the @code{g:Profiler} toolkit.")
10221 (license license:gpl2+)))
10223 (define-public r-gqtlbase
10225 (name "r-gqtlbase")
10230 (uri (bioconductor-uri "gQTLBase" version))
10233 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10234 (properties `((upstream-name . "gQTLBase")))
10235 (build-system r-build-system)
10237 `(("r-batchjobs" ,r-batchjobs)
10238 ("r-bbmisc" ,r-bbmisc)
10239 ("r-biocgenerics" ,r-biocgenerics)
10241 ("r-doparallel" ,r-doparallel)
10243 ("r-ffbase" ,r-ffbase)
10244 ("r-foreach" ,r-foreach)
10245 ("r-genomicfiles" ,r-genomicfiles)
10246 ("r-genomicranges" ,r-genomicranges)
10247 ("r-rtracklayer" ,r-rtracklayer)
10248 ("r-s4vectors" ,r-s4vectors)
10249 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10250 (home-page "https://bioconductor.org/packages/gQTLBase")
10251 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10253 "The purpose of this package is to simplify the storage and interrogation
10254 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10256 (license license:artistic2.0)))
10258 (define-public r-snpstats
10260 (name "r-snpstats")
10265 (uri (bioconductor-uri "snpStats" version))
10268 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10269 (properties `((upstream-name . "snpStats")))
10270 (build-system r-build-system)
10271 (inputs `(("zlib" ,zlib)))
10273 `(("r-biocgenerics" ,r-biocgenerics)
10274 ("r-matrix" ,r-matrix)
10275 ("r-survival" ,r-survival)
10276 ("r-zlibbioc" ,r-zlibbioc)))
10277 (home-page "https://bioconductor.org/packages/snpStats")
10278 (synopsis "Methods for SNP association studies")
10280 "This package provides classes and statistical methods for large
10281 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10282 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10283 (license license:gpl3)))
10285 (define-public r-homo-sapiens
10287 (name "r-homo-sapiens")
10291 ;; We cannot use bioconductor-uri here because this tarball is
10292 ;; located under "data/annotation/" instead of "bioc/".
10293 (uri (string-append "http://www.bioconductor.org/packages/"
10294 "release/data/annotation/src/contrib/"
10296 version ".tar.gz"))
10299 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10301 `((upstream-name . "Homo.sapiens")))
10302 (build-system r-build-system)
10304 `(("r-genomicfeatures" ,r-genomicfeatures)
10305 ("r-go-db" ,r-go-db)
10306 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10307 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10308 ("r-organismdbi" ,r-organismdbi)
10309 ("r-annotationdbi" ,r-annotationdbi)))
10310 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10311 (synopsis "Annotation package for the Homo.sapiens object")
10313 "This package contains the Homo.sapiens object to access data from
10314 several related annotation packages.")
10315 (license license:artistic2.0)))
10317 (define-public r-erma
10324 (uri (bioconductor-uri "erma" version))
10327 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10328 (build-system r-build-system)
10330 `(("r-annotationdbi" ,r-annotationdbi)
10331 ("r-biobase" ,r-biobase)
10332 ("r-biocgenerics" ,r-biocgenerics)
10333 ("r-foreach" ,r-foreach)
10334 ("r-genomicfiles" ,r-genomicfiles)
10335 ("r-genomicranges" ,r-genomicranges)
10336 ("r-ggplot2" ,r-ggplot2)
10337 ("r-homo-sapiens" ,r-homo-sapiens)
10338 ("r-rtracklayer" ,r-rtracklayer)
10339 ("r-s4vectors" ,r-s4vectors)
10340 ("r-shiny" ,r-shiny)
10341 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10342 (home-page "https://bioconductor.org/packages/erma")
10343 (synopsis "Epigenomic road map adventures")
10345 "The epigenomics road map describes locations of epigenetic marks in DNA
10346 from a variety of cell types. Of interest are locations of histone
10347 modifications, sites of DNA methylation, and regions of accessible chromatin.
10348 This package presents a selection of elements of the road map including
10349 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10350 by Ernst and Kellis.")
10351 (license license:artistic2.0)))
10353 (define-public r-ldblock
10360 (uri (bioconductor-uri "ldblock" version))
10363 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10364 (build-system r-build-system)
10366 `(("r-erma" ,r-erma)
10367 ("r-genomeinfodb" ,r-genomeinfodb)
10368 ("r-genomicfiles" ,r-genomicfiles)
10369 ("r-go-db" ,r-go-db)
10370 ("r-homo-sapiens" ,r-homo-sapiens)
10371 ("r-matrix" ,r-matrix)
10372 ("r-rsamtools" ,r-rsamtools)
10373 ("r-snpstats" ,r-snpstats)
10374 ("r-variantannotation" ,r-variantannotation)))
10375 (home-page "https://bioconductor.org/packages/ldblock")
10376 (synopsis "Data structures for linkage disequilibrium measures in populations")
10378 "This package defines data structures for @dfn{linkage
10379 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10380 handling of existing population-level data for the purpose of flexibly
10381 defining LD blocks.")
10382 (license license:artistic2.0)))
10384 (define-public r-gqtlstats
10386 (name "r-gqtlstats")
10391 (uri (bioconductor-uri "gQTLstats" version))
10394 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10395 (properties `((upstream-name . "gQTLstats")))
10396 (build-system r-build-system)
10398 `(("r-annotationdbi" ,r-annotationdbi)
10399 ("r-batchjobs" ,r-batchjobs)
10400 ("r-bbmisc" ,r-bbmisc)
10401 ("r-beeswarm" ,r-beeswarm)
10402 ("r-biobase" ,r-biobase)
10403 ("r-biocgenerics" ,r-biocgenerics)
10404 ("r-doparallel" ,r-doparallel)
10405 ("r-dplyr" ,r-dplyr)
10407 ("r-ffbase" ,r-ffbase)
10408 ("r-foreach" ,r-foreach)
10409 ("r-genomeinfodb" ,r-genomeinfodb)
10410 ("r-genomicfeatures" ,r-genomicfeatures)
10411 ("r-genomicfiles" ,r-genomicfiles)
10412 ("r-genomicranges" ,r-genomicranges)
10413 ("r-ggbeeswarm" ,r-ggbeeswarm)
10414 ("r-ggplot2" ,r-ggplot2)
10415 ("r-gqtlbase" ,r-gqtlbase)
10416 ("r-hardyweinberg" ,r-hardyweinberg)
10417 ("r-iranges" ,r-iranges)
10418 ("r-ldblock" ,r-ldblock)
10419 ("r-limma" ,r-limma)
10421 ("r-plotly" ,r-plotly)
10422 ("r-reshape2" ,r-reshape2)
10423 ("r-s4vectors" ,r-s4vectors)
10424 ("r-shiny" ,r-shiny)
10425 ("r-snpstats" ,r-snpstats)
10426 ("r-summarizedexperiment" ,r-summarizedexperiment)
10427 ("r-variantannotation" ,r-variantannotation)))
10428 (home-page "https://bioconductor.org/packages/gQTLstats")
10429 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10431 "This package provides tools for the computationally efficient analysis
10432 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10433 The software in this package aims to support refinements and functional
10434 interpretation of members of a collection of association statistics on a
10435 family of feature/genome hypotheses.")
10436 (license license:artistic2.0)))
10438 (define-public r-gviz
10445 (uri (bioconductor-uri "Gviz" version))
10448 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10449 (properties `((upstream-name . "Gviz")))
10450 (build-system r-build-system)
10452 `(("r-annotationdbi" ,r-annotationdbi)
10453 ("r-biobase" ,r-biobase)
10454 ("r-biocgenerics" ,r-biocgenerics)
10455 ("r-biomart" ,r-biomart)
10456 ("r-biostrings" ,r-biostrings)
10457 ("r-biovizbase" ,r-biovizbase)
10458 ("r-bsgenome" ,r-bsgenome)
10459 ("r-digest" ,r-digest)
10460 ("r-genomeinfodb" ,r-genomeinfodb)
10461 ("r-genomicalignments" ,r-genomicalignments)
10462 ("r-genomicfeatures" ,r-genomicfeatures)
10463 ("r-genomicranges" ,r-genomicranges)
10464 ("r-iranges" ,r-iranges)
10465 ("r-lattice" ,r-lattice)
10466 ("r-latticeextra" ,r-latticeextra)
10467 ("r-matrixstats" ,r-matrixstats)
10468 ("r-rcolorbrewer" ,r-rcolorbrewer)
10469 ("r-rsamtools" ,r-rsamtools)
10470 ("r-rtracklayer" ,r-rtracklayer)
10471 ("r-s4vectors" ,r-s4vectors)
10472 ("r-xvector" ,r-xvector)))
10473 (home-page "https://bioconductor.org/packages/Gviz")
10474 (synopsis "Plotting data and annotation information along genomic coordinates")
10476 "Genomic data analyses requires integrated visualization of known genomic
10477 information and new experimental data. Gviz uses the biomaRt and the
10478 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10479 and translates this to e.g. gene/transcript structures in viewports of the
10480 grid graphics package. This results in genomic information plotted together
10482 (license license:artistic2.0)))
10484 (define-public r-gwascat
10491 (uri (bioconductor-uri "gwascat" version))
10494 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10495 (build-system r-build-system)
10497 `(("r-annotationdbi" ,r-annotationdbi)
10498 ("r-annotationhub" ,r-annotationhub)
10499 ("r-biocgenerics" ,r-biocgenerics)
10500 ("r-biostrings" ,r-biostrings)
10501 ("r-genomeinfodb" ,r-genomeinfodb)
10502 ("r-genomicfeatures" ,r-genomicfeatures)
10503 ("r-genomicranges" ,r-genomicranges)
10504 ("r-ggbio" ,r-ggbio)
10505 ("r-ggplot2" ,r-ggplot2)
10506 ("r-gqtlstats" ,r-gqtlstats)
10507 ("r-graph" ,r-graph)
10509 ("r-homo-sapiens" ,r-homo-sapiens)
10510 ("r-iranges" ,r-iranges)
10511 ("r-rsamtools" ,r-rsamtools)
10512 ("r-rtracklayer" ,r-rtracklayer)
10513 ("r-s4vectors" ,r-s4vectors)
10514 ("r-snpstats" ,r-snpstats)
10515 ("r-summarizedexperiment" ,r-summarizedexperiment)
10516 ("r-variantannotation" ,r-variantannotation)))
10517 (home-page "https://bioconductor.org/packages/gwascat")
10518 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10520 "This package provides tools for representing and modeling data in the
10521 EMBL-EBI GWAS catalog.")
10522 (license license:artistic2.0)))
10524 (define-public r-sushi
10530 (uri (bioconductor-uri "Sushi" version))
10533 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10534 (properties `((upstream-name . "Sushi")))
10535 (build-system r-build-system)
10537 `(("r-biomart" ,r-biomart)
10539 (home-page "https://bioconductor.org/packages/Sushi")
10540 (synopsis "Tools for visualizing genomics data")
10542 "This package provides flexible, quantitative, and integrative genomic
10543 visualizations for publication-quality multi-panel figures.")
10544 (license license:gpl2+)))
10546 (define-public r-fithic
10552 (uri (bioconductor-uri "FitHiC" version))
10555 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10556 (properties `((upstream-name . "FitHiC")))
10557 (build-system r-build-system)
10559 `(("r-data-table" ,r-data-table)
10560 ("r-fdrtool" ,r-fdrtool)
10561 ("r-rcpp" ,r-rcpp)))
10562 (home-page "https://bioconductor.org/packages/FitHiC")
10563 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10565 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10566 intra-chromosomal contact maps produced by genome-wide genome architecture
10567 assays such as Hi-C.")
10568 (license license:gpl2+)))
10570 (define-public r-hitc
10576 (uri (bioconductor-uri "HiTC" version))
10579 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10580 (properties `((upstream-name . "HiTC")))
10581 (build-system r-build-system)
10583 `(("r-biostrings" ,r-biostrings)
10584 ("r-genomeinfodb" ,r-genomeinfodb)
10585 ("r-genomicranges" ,r-genomicranges)
10586 ("r-iranges" ,r-iranges)
10587 ("r-matrix" ,r-matrix)
10588 ("r-rcolorbrewer" ,r-rcolorbrewer)
10589 ("r-rtracklayer" ,r-rtracklayer)))
10590 (home-page "https://bioconductor.org/packages/HiTC")
10591 (synopsis "High throughput chromosome conformation capture analysis")
10593 "The HiTC package was developed to explore high-throughput \"C\" data
10594 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10595 quality controls, normalization, visualization, and further analysis are also
10597 (license license:artistic2.0)))
10599 (define-public r-qvalue
10606 (uri (bioconductor-uri "qvalue" version))
10609 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10610 (build-system r-build-system)
10612 `(("r-ggplot2" ,r-ggplot2)
10613 ("r-reshape2" ,r-reshape2)))
10614 (home-page "http://github.com/jdstorey/qvalue")
10615 (synopsis "Q-value estimation for false discovery rate control")
10617 "This package takes a list of p-values resulting from the simultaneous
10618 testing of many hypotheses and estimates their q-values and local @dfn{false
10619 discovery rate} (FDR) values. The q-value of a test measures the proportion
10620 of false positives incurred when that particular test is called significant.
10621 The local FDR measures the posterior probability the null hypothesis is true
10622 given the test's p-value. Various plots are automatically generated, allowing
10623 one to make sensible significance cut-offs. The software can be applied to
10624 problems in genomics, brain imaging, astrophysics, and data mining.")
10625 ;; Any version of the LGPL.
10626 (license license:lgpl3+)))
10628 (define-public r-hdf5array
10630 (name "r-hdf5array")
10635 (uri (bioconductor-uri "HDF5Array" version))
10638 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10639 (properties `((upstream-name . "HDF5Array")))
10640 (build-system r-build-system)
10642 `(("r-biocgenerics" ,r-biocgenerics)
10643 ("r-delayedarray" ,r-delayedarray)
10644 ("r-iranges" ,r-iranges)
10645 ("r-rhdf5" ,r-rhdf5)
10646 ("r-s4vectors" ,r-s4vectors)))
10647 (home-page "https://bioconductor.org/packages/HDF5Array")
10648 (synopsis "HDF5 back end for DelayedArray objects")
10649 (description "This package provides an array-like container for convenient
10650 access and manipulation of HDF5 datasets. It supports delayed operations and
10651 block processing.")
10652 (license license:artistic2.0)))
10654 (define-public r-rhdf5lib
10656 (name "r-rhdf5lib")
10661 (uri (bioconductor-uri "Rhdf5lib" version))
10664 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10665 (properties `((upstream-name . "Rhdf5lib")))
10666 (build-system r-build-system)
10669 (modify-phases %standard-phases
10670 (add-after 'unpack 'do-not-use-bundled-hdf5
10671 (lambda* (#:key inputs #:allow-other-keys)
10672 (for-each delete-file '("configure" "configure.ac"))
10673 ;; Do not make other packages link with the proprietary libsz.
10674 (substitute* "R/zzz.R"
10675 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10676 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10677 (("'%s/libhdf5.a %s/libsz.a'")
10678 "'%s/libhdf5.a %s/libhdf5.a'"))
10679 (with-directory-excursion "src"
10680 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10681 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10683 (rename-file "Makevars.in" "Makevars")
10684 (substitute* "Makevars"
10685 (("HDF5_CXX_LIB=.*")
10686 (string-append "HDF5_CXX_LIB="
10687 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10689 (string-append "HDF5_LIB="
10690 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10691 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10692 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10693 ;; szip is non-free software
10694 (("cp \\$\\{SZIP_LIB\\}.*") "")
10695 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10696 "PKG_LIBS = ${HDF5_LIB}\n")))
10703 `(("hdf5-source" ,(package-source hdf5))))
10704 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10705 (synopsis "HDF5 library as an R package")
10706 (description "This package provides C and C++ HDF5 libraries for use in R
10708 (license license:artistic2.0)))
10710 (define-public r-beachmat
10712 (name "r-beachmat")
10717 (uri (bioconductor-uri "beachmat" version))
10720 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10721 (build-system r-build-system)
10725 `(("r-delayedarray" ,r-delayedarray)
10726 ("r-hdf5array" ,r-hdf5array)
10728 ("r-rhdf5" ,r-rhdf5)
10729 ("r-rhdf5lib" ,r-rhdf5lib)))
10730 (home-page "https://bioconductor.org/packages/beachmat")
10731 (synopsis "Compiling Bioconductor to handle each matrix type")
10732 (description "This package provides a consistent C++ class interface for a
10733 variety of commonly used matrix types, including sparse and HDF5-backed
10735 (license license:gpl3)))
10737 (define-public r-singlecellexperiment
10739 (name "r-singlecellexperiment")
10744 (uri (bioconductor-uri "SingleCellExperiment" version))
10747 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10749 `((upstream-name . "SingleCellExperiment")))
10750 (build-system r-build-system)
10752 `(("r-biocgenerics" ,r-biocgenerics)
10753 ("r-s4vectors" ,r-s4vectors)
10754 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10755 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10756 (synopsis "S4 classes for single cell data")
10757 (description "This package defines an S4 class for storing data from
10758 single-cell experiments. This includes specialized methods to store and
10759 retrieve spike-in information, dimensionality reduction coordinates and size
10760 factors for each cell, along with the usual metadata for genes and
10762 (license license:gpl3)))
10764 (define-public r-scater
10770 (uri (bioconductor-uri "scater" version))
10773 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10774 (build-system r-build-system)
10776 `(("r-beachmat" ,r-beachmat)
10777 ("r-biobase" ,r-biobase)
10778 ("r-biocgenerics" ,r-biocgenerics)
10779 ("r-biomart" ,r-biomart)
10780 ("r-data-table" ,r-data-table)
10781 ("r-dplyr" ,r-dplyr)
10782 ("r-edger" ,r-edger)
10783 ("r-ggbeeswarm" ,r-ggbeeswarm)
10784 ("r-ggplot2" ,r-ggplot2)
10785 ("r-limma" ,r-limma)
10786 ("r-matrix" ,r-matrix)
10787 ("r-matrixstats" ,r-matrixstats)
10790 ("r-reshape2" ,r-reshape2)
10791 ("r-rhdf5" ,r-rhdf5)
10792 ("r-rhdf5lib" ,r-rhdf5lib)
10793 ("r-rjson" ,r-rjson)
10794 ("r-s4vectors" ,r-s4vectors)
10795 ("r-shiny" ,r-shiny)
10796 ("r-shinydashboard" ,r-shinydashboard)
10797 ("r-singlecellexperiment" ,r-singlecellexperiment)
10798 ("r-summarizedexperiment" ,r-summarizedexperiment)
10799 ("r-tximport" ,r-tximport)
10800 ("r-viridis" ,r-viridis)))
10801 (home-page "https://github.com/davismcc/scater")
10802 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10803 (description "This package provides a collection of tools for doing
10804 various analyses of single-cell RNA-seq gene expression data, with a focus on
10806 (license license:gpl2+)))
10808 (define-public r-scran
10815 (uri (bioconductor-uri "scran" version))
10818 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10819 (build-system r-build-system)
10821 `(("r-beachmat" ,r-beachmat)
10822 ("r-biocgenerics" ,r-biocgenerics)
10823 ("r-biocparallel" ,r-biocparallel)
10825 ("r-dynamictreecut" ,r-dynamictreecut)
10826 ("r-edger" ,r-edger)
10828 ("r-ggplot2" ,r-ggplot2)
10829 ("r-igraph" ,r-igraph)
10830 ("r-limma" ,r-limma)
10831 ("r-matrix" ,r-matrix)
10833 ("r-rhdf5lib" ,r-rhdf5lib)
10834 ("r-s4vectors" ,r-s4vectors)
10835 ("r-scater" ,r-scater)
10836 ("r-shiny" ,r-shiny)
10837 ("r-singlecellexperiment" ,r-singlecellexperiment)
10838 ("r-statmod" ,r-statmod)
10839 ("r-summarizedexperiment" ,r-summarizedexperiment)
10840 ("r-viridis" ,r-viridis)
10842 (home-page "https://bioconductor.org/packages/scran")
10843 (synopsis "Methods for single-cell RNA-Seq data analysis")
10844 (description "This package implements a variety of low-level analyses of
10845 single-cell RNA-seq data. Methods are provided for normalization of
10846 cell-specific biases, assignment of cell cycle phase, and detection of highly
10847 variable and significantly correlated genes.")
10848 (license license:gpl3)))
10850 (define-public r-delayedmatrixstats
10852 (name "r-delayedmatrixstats")
10857 (uri (bioconductor-uri "DelayedMatrixStats" version))
10860 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10862 `((upstream-name . "DelayedMatrixStats")))
10863 (build-system r-build-system)
10865 `(("r-delayedarray" ,r-delayedarray)
10866 ("r-iranges" ,r-iranges)
10867 ("r-matrix" ,r-matrix)
10868 ("r-matrixstats" ,r-matrixstats)
10869 ("r-s4vectors" ,r-s4vectors)))
10870 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10871 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10873 "This package provides a port of the @code{matrixStats} API for use with
10874 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10875 contains high-performing functions operating on rows and columns of
10876 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10877 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10878 are optimized per data type and for subsetted calculations such that both
10879 memory usage and processing time is minimized.")
10880 (license license:expat)))
10882 (define-public r-dropbead
10883 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10886 (name "r-dropbead")
10887 (version (string-append "0-" revision "." (string-take commit 7)))
10891 (uri (git-reference
10892 (url "https://github.com/rajewsky-lab/dropbead.git")
10894 (file-name (git-file-name name version))
10897 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10898 (build-system r-build-system)
10900 `(("r-ggplot2" ,r-ggplot2)
10901 ("r-rcolorbrewer" ,r-rcolorbrewer)
10902 ("r-gridextra" ,r-gridextra)
10903 ("r-gplots" ,r-gplots)
10904 ("r-plyr" ,r-plyr)))
10905 (home-page "https://github.com/rajewsky-lab/dropbead")
10906 (synopsis "Basic exploration and analysis of Drop-seq data")
10907 (description "This package offers a quick and straight-forward way to
10908 explore and perform basic analysis of single cell sequencing data coming from
10909 droplet sequencing. It has been particularly tailored for Drop-seq.")
10910 (license license:gpl3))))
10912 (define htslib-for-sambamba
10913 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10916 (name "htslib-for-sambamba")
10917 (version (string-append "1.3.1-1." (string-take commit 9)))
10921 (uri (git-reference
10922 (url "https://github.com/lomereiter/htslib.git")
10924 (file-name (string-append "htslib-" version "-checkout"))
10927 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10929 (substitute-keyword-arguments (package-arguments htslib)
10931 `(modify-phases ,phases
10932 (add-after 'unpack 'bootstrap
10934 (zero? (system* "autoreconf" "-vif"))))))))
10936 `(("autoconf" ,autoconf)
10937 ("automake" ,automake)
10938 ,@(package-native-inputs htslib))))))
10940 (define-public sambamba
10947 (uri (string-append "https://github.com/lomereiter/sambamba/"
10948 "archive/v" version ".tar.gz"))
10949 (file-name (string-append name "-" version ".tar.gz"))
10952 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10953 (build-system gnu-build-system)
10955 `(#:tests? #f ; there is no test target
10957 '("D_COMPILER=ldc2"
10958 ;; Override "--compiler" flag only.
10959 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10960 "sambamba-ldmd2-64")
10962 (modify-phases %standard-phases
10963 (delete 'configure)
10964 (add-after 'unpack 'place-biod
10965 (lambda* (#:key inputs #:allow-other-keys)
10966 (copy-recursively (assoc-ref inputs "biod") "BioD")
10968 (add-after 'unpack 'unbundle-prerequisites
10970 (substitute* "Makefile"
10971 ((" htslib-static lz4-static") ""))
10974 (lambda* (#:key outputs #:allow-other-keys)
10975 (let* ((out (assoc-ref outputs "out"))
10976 (bin (string-append out "/bin")))
10978 (install-file "build/sambamba" bin)
10984 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10987 (uri (git-reference
10988 (url "https://github.com/biod/BioD.git")
10990 (file-name (string-append "biod-"
10991 (string-take commit 9)
10995 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10998 ("htslib" ,htslib-for-sambamba)))
10999 (home-page "http://lomereiter.github.io/sambamba")
11000 (synopsis "Tools for working with SAM/BAM data")
11001 (description "Sambamba is a high performance modern robust and
11002 fast tool (and library), written in the D programming language, for
11003 working with SAM and BAM files. Current parallelised functionality is
11004 an important subset of samtools functionality, including view, index,
11005 sort, markdup, and depth.")
11006 (license license:gpl2+)))
11008 (define-public ritornello
11010 (name "ritornello")
11014 (uri (string-append "https://github.com/KlugerLab/"
11015 "Ritornello/archive/v"
11016 version ".tar.gz"))
11017 (file-name (string-append name "-" version ".tar.gz"))
11020 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11021 (build-system gnu-build-system)
11023 `(#:tests? #f ; there are no tests
11025 (modify-phases %standard-phases
11026 (add-after 'unpack 'patch-samtools-references
11027 (lambda* (#:key inputs #:allow-other-keys)
11028 (substitute* '("src/SamStream.h"
11029 "src/BufferedGenomeReader.h")
11030 (("<sam.h>") "<samtools/sam.h>"))
11032 (delete 'configure)
11034 (lambda* (#:key inputs outputs #:allow-other-keys)
11035 (let* ((out (assoc-ref outputs "out"))
11036 (bin (string-append out "/bin/")))
11038 (install-file "bin/Ritornello" bin)
11041 `(("samtools" ,samtools-0.1)
11045 (home-page "https://github.com/KlugerLab/Ritornello")
11046 (synopsis "Control-free peak caller for ChIP-seq data")
11047 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11048 signal processing that can accurately call binding events without the need to
11049 do a pair total DNA input or IgG control sample. It has been tested for use
11050 with narrow binding events such as transcription factor ChIP-seq.")
11051 (license license:gpl3+)))
11053 (define-public trim-galore
11055 (name "trim-galore")
11060 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
11061 "projects/trim_galore/trim_galore_v"
11065 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
11066 (build-system gnu-build-system)
11068 `(#:tests? #f ; no tests
11070 (modify-phases %standard-phases
11071 ;; The archive contains plain files.
11073 (lambda* (#:key source #:allow-other-keys)
11074 (zero? (system* "unzip" source))))
11075 (delete 'configure)
11077 (add-after 'unpack 'hardcode-tool-references
11078 (lambda* (#:key inputs #:allow-other-keys)
11079 (substitute* "trim_galore"
11080 (("\\$path_to_cutadapt = 'cutadapt'")
11081 (string-append "$path_to_cutadapt = '"
11082 (assoc-ref inputs "cutadapt")
11085 (string-append "| "
11086 (assoc-ref inputs "gzip")
11089 (string-append "\""
11090 (assoc-ref inputs "gzip")
11094 (lambda* (#:key outputs #:allow-other-keys)
11095 (let ((bin (string-append (assoc-ref outputs "out")
11098 (install-file "trim_galore" bin)
11103 ("cutadapt" ,cutadapt)))
11105 `(("unzip" ,unzip)))
11106 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11107 (synopsis "Wrapper around Cutadapt and FastQC")
11108 (description "Trim Galore! is a wrapper script to automate quality and
11109 adapter trimming as well as quality control, with some added functionality to
11110 remove biased methylation positions for RRBS sequence files.")
11111 (license license:gpl3+)))
11113 (define-public gess
11119 (uri (string-append "http://compbio.uthscsa.edu/"
11121 "gess-" version ".src.tar.gz"))
11124 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11125 (build-system gnu-build-system)
11127 `(#:tests? #f ; no tests
11129 (modify-phases %standard-phases
11130 (delete 'configure)
11133 (lambda* (#:key inputs outputs #:allow-other-keys)
11134 (let* ((python (assoc-ref inputs "python"))
11135 (out (assoc-ref outputs "out"))
11136 (bin (string-append out "/bin/"))
11137 (target (string-append
11138 out "/lib/python2.7/site-packages/gess/")))
11140 (copy-recursively "." target)
11141 ;; Make GESS.py executable
11142 (chmod (string-append target "GESS.py") #o555)
11143 ;; Add Python shebang to the top and make Matplotlib
11145 (substitute* (string-append target "GESS.py")
11146 (("\"\"\"Description:" line)
11147 (string-append "#!" (which "python") "
11149 matplotlib.use('Agg')
11151 ;; Make sure GESS has all modules in its path
11152 (wrap-program (string-append target "GESS.py")
11153 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11155 (symlink (string-append target "GESS.py")
11156 (string-append bin "GESS.py"))
11159 `(("python" ,python-2)
11160 ("python2-pysam" ,python2-pysam)
11161 ("python2-scipy" ,python2-scipy)
11162 ("python2-numpy" ,python2-numpy)
11163 ("python2-networkx" ,python2-networkx)
11164 ("python2-biopython" ,python2-biopython)))
11165 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11166 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11168 "GESS is an implementation of a novel computational method to detect de
11169 novo exon-skipping events directly from raw RNA-seq data without the prior
11170 knowledge of gene annotation information. GESS stands for the graph-based
11171 exon-skipping scanner detection scheme.")
11172 (license license:bsd-3)))
11174 (define-public phylip
11181 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11182 "download/phylip-" version ".tar.gz"))
11185 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11186 (build-system gnu-build-system)
11188 `(#:tests? #f ; no check target
11189 #:make-flags (list "-f" "Makefile.unx" "install")
11190 #:parallel-build? #f ; not supported
11192 (modify-phases %standard-phases
11193 (add-after 'unpack 'enter-dir
11194 (lambda _ (chdir "src") #t))
11195 (delete 'configure)
11197 (lambda* (#:key inputs outputs #:allow-other-keys)
11198 (let ((target (string-append (assoc-ref outputs "out")
11201 (for-each (lambda (file)
11202 (install-file file target))
11203 (find-files "../exe" ".*")))
11205 (home-page "http://evolution.genetics.washington.edu/phylip/")
11206 (synopsis "Tools for inferring phylogenies")
11207 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11208 programs for inferring phylogenies (evolutionary trees).")
11209 (license license:bsd-2)))
11218 (uri (string-append "https://integrativemodeling.org/"
11219 version "/download/imp-" version ".tar.gz"))
11222 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11223 (build-system cmake-build-system)
11225 `(;; FIXME: Some tests fail because they produce warnings, others fail
11226 ;; because the PYTHONPATH does not include the modeller's directory.
11234 ("python" ,python-2)))
11236 `(("python2-numpy" ,python2-numpy)
11237 ("python2-scipy" ,python2-scipy)
11238 ("python2-pandas" ,python2-pandas)
11239 ("python2-scikit-learn" ,python2-scikit-learn)
11240 ("python2-networkx" ,python2-networkx)))
11241 (home-page "https://integrativemodeling.org")
11242 (synopsis "Integrative modeling platform")
11243 (description "IMP's broad goal is to contribute to a comprehensive
11244 structural characterization of biomolecules ranging in size and complexity
11245 from small peptides to large macromolecular assemblies, by integrating data
11246 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11247 Python toolbox for solving complex modeling problems, and a number of
11248 applications for tackling some common problems in a user-friendly way.")
11249 ;; IMP is largely available under the GNU Lesser GPL; see the file
11250 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11251 ;; available under the GNU GPL (see the file COPYING.GPL).
11252 (license (list license:lgpl2.1+
11255 (define-public tadbit
11261 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11262 "archive/v" version ".tar.gz"))
11263 (file-name (string-append name "-" version ".tar.gz"))
11266 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11267 (build-system python-build-system)
11269 `(;; Tests are included and must be run after installation, but
11270 ;; they are incomplete and thus cannot be run.
11274 (modify-phases %standard-phases
11275 (add-after 'unpack 'fix-problems-with-setup.py
11276 (lambda* (#:key outputs #:allow-other-keys)
11277 ;; setup.py opens these files for writing
11278 (chmod "_pytadbit/_version.py" #o664)
11279 (chmod "README.rst" #o664)
11281 ;; Don't attempt to install the bash completions to
11282 ;; the home directory.
11283 (rename-file "extras/.bash_completion"
11285 (substitute* "setup.py"
11286 (("\\(path.expanduser\\('~'\\)")
11287 (string-append "(\""
11288 (assoc-ref outputs "out")
11289 "/etc/bash_completion.d\""))
11290 (("extras/\\.bash_completion")
11294 ;; TODO: add Chimera for visualization
11297 ("python2-scipy" ,python2-scipy)
11298 ("python2-numpy" ,python2-numpy)
11299 ("python2-matplotlib" ,python2-matplotlib)
11300 ("python2-pysam" ,python2-pysam)))
11301 (home-page "http://3dgenomes.github.io/TADbit/")
11302 (synopsis "Analyze, model, and explore 3C-based data")
11304 "TADbit is a complete Python library to deal with all steps to analyze,
11305 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11306 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11307 correct interaction matrices, identify and compare the so-called
11308 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11309 interaction matrices, and finally, extract structural properties from the
11310 models. TADbit is complemented by TADkit for visualizing 3D models.")
11311 (license license:gpl3+)))
11313 (define-public kentutils
11316 ;; 302.1.0 is out, but the only difference is the inclusion of
11317 ;; pre-built binaries.
11318 (version "302.0.0")
11322 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11323 "archive/v" version ".tar.gz"))
11324 (file-name (string-append name "-" version ".tar.gz"))
11327 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11328 (modules '((guix build utils)
11333 ;; Only the contents of the specified directories are free
11334 ;; for all uses, so we remove the rest. "hg/autoSql" and
11335 ;; "hg/autoXml" are nominally free, but they depend on a
11336 ;; library that is built from the sources in "hg/lib",
11337 ;; which is nonfree.
11338 (let ((free (list "." ".."
11339 "utils" "lib" "inc" "tagStorm"
11340 "parasol" "htslib"))
11341 (directory? (lambda (file)
11342 (eq? 'directory (stat:type (stat file))))))
11343 (for-each (lambda (file)
11344 (and (directory? file)
11345 (delete-file-recursively file)))
11346 (map (cut string-append "src/" <>)
11349 (not (member file free)))))))
11350 ;; Only make the utils target, not the userApps target,
11351 ;; because that requires libraries we won't build.
11352 (substitute* "Makefile"
11353 ((" userApps") " utils"))
11354 ;; Only build libraries that are free.
11355 (substitute* "src/makefile"
11356 (("DIRS =.*") "DIRS =\n")
11357 (("cd jkOwnLib.*") "")
11360 (substitute* "src/utils/makefile"
11361 ;; These tools depend on "jkhgap.a", which is part of the
11362 ;; nonfree "src/hg/lib" directory.
11363 (("raSqlQuery") "")
11364 (("pslLiftSubrangeBlat") "")
11366 ;; Do not build UCSC tools, which may require nonfree
11368 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11370 (build-system gnu-build-system)
11372 `( ;; There is no global test target and the test target for
11373 ;; individual tools depends on input files that are not
11377 (modify-phases %standard-phases
11378 (add-after 'unpack 'fix-paths
11380 (substitute* "Makefile"
11381 (("/bin/echo") (which "echo")))
11383 (add-after 'unpack 'prepare-samtabix
11384 (lambda* (#:key inputs #:allow-other-keys)
11385 (copy-recursively (assoc-ref inputs "samtabix")
11388 (delete 'configure)
11390 (lambda* (#:key outputs #:allow-other-keys)
11391 (let ((bin (string-append (assoc-ref outputs "out")
11393 (copy-recursively "bin" bin))
11399 (uri (git-reference
11400 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11401 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11404 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11411 ("openssl" ,openssl)))
11412 (home-page "http://genome.cse.ucsc.edu/index.html")
11413 (synopsis "Assorted bioinformatics utilities")
11414 (description "This package provides the kentUtils, a selection of
11415 bioinformatics utilities used in combination with the UCSC genome
11417 ;; Only a subset of the sources are released under a non-copyleft
11418 ;; free software license. All other sources are removed in a
11419 ;; snippet. See this bug report for an explanation of how the
11420 ;; license statements apply:
11421 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11422 (license (license:non-copyleft
11423 "http://genome.ucsc.edu/license/"
11424 "The contents of this package are free for all uses."))))
11426 (define-public f-seq
11427 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11431 (version (string-append "1.1-" revision "." (string-take commit 7)))
11434 (uri (git-reference
11435 (url "https://github.com/aboyle/F-seq.git")
11437 (file-name (string-append name "-" version))
11440 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11441 (modules '((guix build utils)))
11442 ;; Remove bundled Java library archives.
11445 (for-each delete-file (find-files "lib" ".*"))
11447 (build-system ant-build-system)
11449 `(#:tests? #f ; no tests included
11451 (modify-phases %standard-phases
11453 (lambda* (#:key inputs outputs #:allow-other-keys)
11454 (let* ((target (assoc-ref outputs "out"))
11455 (doc (string-append target "/share/doc/f-seq/")))
11458 (substitute* "bin/linux/fseq"
11459 (("java") (which "java"))
11460 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11461 (string-append (assoc-ref inputs "java-commons-cli")
11462 "/share/java/commons-cli.jar"))
11464 (string-append "REALDIR=" target "/bin\n")))
11465 (install-file "README.txt" doc)
11466 (install-file "bin/linux/fseq" (string-append target "/bin"))
11467 (install-file "build~/fseq.jar" (string-append target "/lib"))
11468 (copy-recursively "lib" (string-append target "/lib"))
11472 ("java-commons-cli" ,java-commons-cli)))
11473 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11474 (synopsis "Feature density estimator for high-throughput sequence tags")
11476 "F-Seq is a software package that generates a continuous tag sequence
11477 density estimation allowing identification of biologically meaningful sites
11478 such as transcription factor binding sites (ChIP-seq) or regions of open
11479 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11481 (license license:gpl3+))))
11483 (define-public bismark
11490 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11491 "archive/" version ".tar.gz"))
11492 (file-name (string-append name "-" version ".tar.gz"))
11495 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11496 (build-system perl-build-system)
11498 `(#:tests? #f ; there are no tests
11500 (modify-phases %standard-phases
11501 (delete 'configure)
11504 (lambda* (#:key outputs #:allow-other-keys)
11505 (let ((bin (string-append (assoc-ref outputs "out")
11507 (docdir (string-append (assoc-ref outputs "out")
11508 "/share/doc/bismark"))
11509 (docs '("Bismark_User_Guide.pdf"
11510 "RELEASE_NOTES.txt"))
11511 (scripts '("bismark"
11512 "bismark_genome_preparation"
11513 "bismark_methylation_extractor"
11516 "coverage2cytosine"
11517 "deduplicate_bismark"
11518 "bismark_sitrep.tpl"
11520 "bismark2summary")))
11523 (for-each (lambda (file) (install-file file bin))
11525 (for-each (lambda (file) (install-file file docdir))
11528 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11529 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11530 (description "Bismark is a program to map bisulfite treated sequencing
11531 reads to a genome of interest and perform methylation calls in a single step.
11532 The output can be easily imported into a genome viewer, such as SeqMonk, and
11533 enables a researcher to analyse the methylation levels of their samples
11534 straight away. Its main features are:
11537 @item Bisulfite mapping and methylation calling in one single step
11538 @item Supports single-end and paired-end read alignments
11539 @item Supports ungapped and gapped alignments
11540 @item Alignment seed length, number of mismatches etc are adjustable
11541 @item Output discriminates between cytosine methylation in CpG, CHG
11544 (license license:gpl3+)))
11546 (define-public paml
11552 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11553 "paml" version ".tgz"))
11556 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11557 (modules '((guix build utils)))
11558 ;; Remove Windows binaries
11561 (for-each delete-file (find-files "." "\\.exe$"))
11563 (build-system gnu-build-system)
11565 `(#:tests? #f ; there are no tests
11566 #:make-flags '("CC=gcc")
11568 (modify-phases %standard-phases
11569 (replace 'configure
11571 (substitute* "src/BFdriver.c"
11572 (("/bin/bash") (which "bash")))
11576 (lambda* (#:key outputs #:allow-other-keys)
11577 (let ((tools '("baseml" "basemlg" "codeml"
11578 "pamp" "evolver" "yn00" "chi2"))
11579 (bin (string-append (assoc-ref outputs "out") "/bin"))
11580 (docdir (string-append (assoc-ref outputs "out")
11581 "/share/doc/paml")))
11583 (for-each (lambda (file) (install-file file bin)) tools)
11584 (copy-recursively "../doc" docdir)
11586 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11587 (synopsis "Phylogentic analysis by maximum likelihood")
11588 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11589 contains a few programs for model fitting and phylogenetic tree reconstruction
11590 using nucleotide or amino-acid sequence data.")
11592 (license license:gpl3)))
11594 (define-public kallisto
11600 (uri (string-append "https://github.com/pachterlab/"
11601 "kallisto/archive/v" version ".tar.gz"))
11602 (file-name (string-append name "-" version ".tar.gz"))
11605 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11606 (build-system cmake-build-system)
11607 (arguments `(#:tests? #f)) ; no "check" target
11611 (home-page "http://pachterlab.github.io/kallisto/")
11612 (synopsis "Near-optimal RNA-Seq quantification")
11614 "Kallisto is a program for quantifying abundances of transcripts from
11615 RNA-Seq data, or more generally of target sequences using high-throughput
11616 sequencing reads. It is based on the novel idea of pseudoalignment for
11617 rapidly determining the compatibility of reads with targets, without the need
11618 for alignment. Pseudoalignment of reads preserves the key information needed
11619 for quantification, and kallisto is therefore not only fast, but also as
11620 accurate as existing quantification tools.")
11621 (license license:bsd-2)))
11623 (define-public libgff
11629 (uri (string-append
11630 "https://github.com/Kingsford-Group/"
11631 "libgff/archive/v" version ".tar.gz"))
11632 (file-name (string-append name "-" version ".tar.gz"))
11635 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11636 (build-system cmake-build-system)
11637 (arguments `(#:tests? #f)) ; no tests included
11638 (home-page "https://github.com/Kingsford-Group/libgff")
11639 (synopsis "Parser library for reading/writing GFF files")
11640 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11641 code that is used in the Cufflinks codebase. The goal of this library is to
11642 provide this functionality without the necessity of drawing in a heavy-weight
11643 dependency like SeqAn.")
11644 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11646 (define-public libdivsufsort
11648 (name "libdivsufsort")
11652 (uri (git-reference
11653 (url "https://github.com/y-256/libdivsufsort.git")
11655 (file-name (git-file-name name version))
11658 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11659 (build-system cmake-build-system)
11661 '(#:tests? #f ; there are no tests
11663 ;; Needed for rapmap and sailfish.
11664 '("-DBUILD_DIVSUFSORT64=ON")))
11665 (home-page "https://github.com/y-256/libdivsufsort")
11666 (synopsis "Lightweight suffix-sorting library")
11667 (description "libdivsufsort is a software library that implements a
11668 lightweight suffix array construction algorithm. This library provides a
11669 simple and an efficient C API to construct a suffix array and a
11670 Burrows-Wheeler transformed string from a given string over a constant-size
11671 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11672 bytes of memory space, where n is the length of the string.")
11673 (license license:expat)))
11675 (define-public sailfish
11682 (string-append "https://github.com/kingsfordgroup/"
11683 "sailfish/archive/v" version ".tar.gz"))
11684 (file-name (string-append name "-" version ".tar.gz"))
11687 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11688 (modules '((guix build utils)))
11691 ;; Delete bundled headers for eigen3.
11692 (delete-file-recursively "include/eigen3/")
11694 (build-system cmake-build-system)
11696 `(#:configure-flags
11697 (list (string-append "-DBOOST_INCLUDEDIR="
11698 (assoc-ref %build-inputs "boost")
11700 (string-append "-DBOOST_LIBRARYDIR="
11701 (assoc-ref %build-inputs "boost")
11703 (string-append "-DBoost_LIBRARIES="
11704 "-lboost_iostreams "
11705 "-lboost_filesystem "
11710 "-lboost_program_options")
11711 "-DBoost_FOUND=TRUE"
11712 ;; Don't download RapMap---we already have it!
11713 "-DFETCHED_RAPMAP=1")
11714 ;; Tests must be run after installation and the location of the test
11715 ;; data file must be overridden. But the tests fail. It looks like
11716 ;; they are not really meant to be run.
11719 (modify-phases %standard-phases
11720 ;; Boost cannot be found, even though it's right there.
11721 (add-after 'unpack 'do-not-look-for-boost
11722 (lambda* (#:key inputs #:allow-other-keys)
11723 (substitute* "CMakeLists.txt"
11724 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11725 (add-after 'unpack 'do-not-assign-to-macro
11727 (substitute* "include/spdlog/details/format.cc"
11728 (("const unsigned CHAR_WIDTH = 1;") ""))))
11729 (add-after 'unpack 'prepare-rapmap
11730 (lambda* (#:key inputs #:allow-other-keys)
11731 (let ((src "external/install/src/rapmap/")
11732 (include "external/install/include/rapmap/")
11733 (rapmap (assoc-ref inputs "rapmap")))
11734 (mkdir-p "/tmp/rapmap")
11735 (system* "tar" "xf"
11736 (assoc-ref inputs "rapmap")
11738 "--strip-components=1")
11741 (for-each (lambda (file)
11742 (install-file file src))
11743 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11744 (copy-recursively "/tmp/rapmap/include" include))))
11745 (add-after 'unpack 'use-system-libraries
11746 (lambda* (#:key inputs #:allow-other-keys)
11747 (substitute* '("src/SailfishIndexer.cpp"
11748 "src/SailfishUtils.cpp"
11749 "src/SailfishQuantify.cpp"
11750 "src/FASTAParser.cpp"
11752 "include/SailfishUtils.hpp"
11753 "include/SailfishIndex.hpp"
11754 "include/CollapsedEMOptimizer.hpp"
11755 "src/CollapsedEMOptimizer.cpp")
11756 (("#include \"jellyfish/config.h\"") ""))
11757 (substitute* "src/CMakeLists.txt"
11758 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11759 (string-append (assoc-ref inputs "jellyfish")
11760 "/include/jellyfish-" ,(package-version jellyfish)))
11761 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11762 (string-append (assoc-ref inputs "jellyfish")
11763 "/lib/libjellyfish-2.0.a"))
11764 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11765 (string-append (assoc-ref inputs "libdivsufsort")
11766 "/lib/libdivsufsort.so"))
11767 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11768 (string-append (assoc-ref inputs "libdivsufsort")
11769 "/lib/libdivsufsort64.so")))
11770 (substitute* "CMakeLists.txt"
11771 ;; Don't prefer static libs
11772 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11773 (("find_package\\(Jellyfish.*") "")
11774 (("ExternalProject_Add\\(libjellyfish") "message(")
11775 (("ExternalProject_Add\\(libgff") "message(")
11776 (("ExternalProject_Add\\(libsparsehash") "message(")
11777 (("ExternalProject_Add\\(libdivsufsort") "message("))
11779 ;; Ensure that Eigen headers can be found
11780 (setenv "CPLUS_INCLUDE_PATH"
11781 (string-append (getenv "CPLUS_INCLUDE_PATH")
11783 (assoc-ref inputs "eigen")
11784 "/include/eigen3")))))))
11788 ("jemalloc" ,jemalloc)
11789 ("jellyfish" ,jellyfish)
11790 ("sparsehash" ,sparsehash)
11793 (uri (git-reference
11794 (url "https://github.com/COMBINE-lab/RapMap.git")
11795 (commit (string-append "sf-v" version))))
11796 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11799 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11800 (modules '((guix build utils)))
11801 ;; These files are expected to be excluded.
11803 '(begin (delete-file-recursively "include/spdlog")
11804 (for-each delete-file '("include/xxhash.h"
11805 "src/xxhash.c"))))))
11806 ("libdivsufsort" ,libdivsufsort)
11811 `(("pkg-config" ,pkg-config)))
11812 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11813 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11814 (description "Sailfish is a tool for genomic transcript quantification
11815 from RNA-seq data. It requires a set of target transcripts (either from a
11816 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11817 fasta file containing your reference transcripts and a (set of) fasta/fastq
11818 file(s) containing your reads.")
11819 (license license:gpl3+)))
11821 (define libstadenio-for-salmon
11823 (name "libstadenio")
11827 (uri (git-reference
11828 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11829 (commit (string-append "v" version))))
11830 (file-name (string-append name "-" version "-checkout"))
11833 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11834 (build-system gnu-build-system)
11835 (arguments '(#:parallel-tests? #f)) ; not supported
11839 `(("perl" ,perl))) ; for tests
11840 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11841 (synopsis "General purpose trace and experiment file library")
11842 (description "This package provides a library of file reading and writing
11843 code to provide a general purpose Trace file (and Experiment File) reading
11846 The following file formats are supported:
11849 @item SCF trace files
11850 @item ABI trace files
11851 @item ALF trace files
11852 @item ZTR trace files
11853 @item SFF trace archives
11854 @item SRF trace archives
11855 @item Experiment files
11856 @item Plain text files
11857 @item SAM/BAM sequence files
11858 @item CRAM sequence files
11860 (license license:bsd-3)))
11862 (define spdlog-for-salmon
11868 (uri (git-reference
11869 (url "https://github.com/COMBINE-lab/spdlog.git")
11870 (commit (string-append "v" version))))
11871 (file-name (string-append name "-" version "-checkout"))
11874 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11875 (build-system cmake-build-system)
11876 (home-page "https://github.com/COMBINE-lab/spdlog")
11877 (synopsis "Very fast C++ logging library")
11878 (description "Spdlog is a very fast header-only C++ logging library with
11879 performance as its primary goal.")
11880 (license license:expat)))
11882 ;; This is a modified variant of bwa for use with Salmon. It installs a
11883 ;; library to avoid having to build this as part of Salmon.
11884 (define bwa-for-salmon
11885 (package (inherit bwa)
11887 (version "0.7.12.5")
11890 (uri (git-reference
11891 (url "https://github.com/COMBINE-lab/bwa.git")
11892 (commit (string-append "v" version))))
11893 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11896 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11897 (build-system gnu-build-system)
11899 '(#:tests? #f ;no "check" target
11901 (modify-phases %standard-phases
11903 (lambda* (#:key outputs #:allow-other-keys)
11904 (let* ((out (assoc-ref outputs "out"))
11905 (bin (string-append out "/bin"))
11906 (lib (string-append out "/lib"))
11907 (doc (string-append out "/share/doc/bwa"))
11908 (man (string-append out "/share/man/man1"))
11909 (inc (string-append out "/include/bwa")))
11910 (install-file "bwa" bin)
11911 (install-file "README.md" doc)
11912 (install-file "bwa.1" man)
11913 (install-file "libbwa.a" lib)
11916 (for-each (lambda (file)
11917 (install-file file inc))
11918 (find-files "." "\\.h$")))
11920 ;; no "configure" script
11921 (delete 'configure))))))
11923 (define-public salmon
11929 (uri (git-reference
11930 (url "https://github.com/COMBINE-lab/salmon.git")
11931 (commit (string-append "v" version))))
11932 (file-name (string-append name "-" version "-checkout"))
11935 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11936 (modules '((guix build utils)))
11939 ;; Delete bundled headers for eigen3.
11940 (delete-file-recursively "include/eigen3/")
11942 (build-system cmake-build-system)
11944 `(#:configure-flags
11945 (list (string-append "-DBOOST_INCLUDEDIR="
11946 (assoc-ref %build-inputs "boost")
11948 (string-append "-DBOOST_LIBRARYDIR="
11949 (assoc-ref %build-inputs "boost")
11951 (string-append "-DBoost_LIBRARIES="
11952 "-lboost_iostreams "
11953 "-lboost_filesystem "
11958 "-lboost_program_options")
11959 "-DBoost_FOUND=TRUE"
11960 "-DTBB_LIBRARIES=tbb tbbmalloc"
11961 ;; Don't download RapMap---we already have it!
11962 "-DFETCHED_RAPMAP=1")
11964 (modify-phases %standard-phases
11965 ;; Boost cannot be found, even though it's right there.
11966 (add-after 'unpack 'do-not-look-for-boost
11967 (lambda* (#:key inputs #:allow-other-keys)
11968 (substitute* "CMakeLists.txt"
11969 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11970 (add-after 'unpack 'do-not-phone-home
11972 (substitute* "src/Salmon.cpp"
11973 (("getVersionMessage\\(\\)") "\"\""))))
11974 (add-after 'unpack 'prepare-rapmap
11975 (lambda* (#:key inputs #:allow-other-keys)
11976 (let ((src "external/install/src/rapmap/")
11977 (include "external/install/include/rapmap/")
11978 (rapmap (assoc-ref inputs "rapmap")))
11981 (for-each (lambda (file)
11982 (install-file file src))
11983 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11984 (copy-recursively (string-append rapmap "/include") include)
11985 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11986 "external/install/include/rapmap/FastxParser.hpp"
11987 "external/install/include/rapmap/concurrentqueue.h"
11988 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11989 "external/install/src/rapmap/FastxParser.cpp"
11990 "external/install/src/rapmap/xxhash.c")))))
11991 (add-after 'unpack 'use-system-libraries
11992 (lambda* (#:key inputs #:allow-other-keys)
11993 (substitute* "src/CMakeLists.txt"
11994 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11995 (string-append (assoc-ref inputs "jellyfish")
11996 "/include/jellyfish-" ,(package-version jellyfish)))
11997 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11998 (string-append (assoc-ref inputs "jellyfish")
11999 "/lib/libjellyfish-2.0.a"))
12000 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12001 (string-append (assoc-ref inputs "libdivsufsort")
12002 "/lib/libdivsufsort.so"))
12003 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12004 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12005 "/lib/libstaden-read.a"))
12006 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12007 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12008 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12009 (string-append (assoc-ref inputs "libdivsufsort")
12010 "/lib/libdivsufsort64.so")))
12011 (substitute* "CMakeLists.txt"
12012 ;; Don't prefer static libs
12013 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12014 (("set\\(TBB_LIBRARIES") "message(")
12015 (("find_package\\(Jellyfish.*") "")
12016 (("ExternalProject_Add\\(libcereal") "message(")
12017 (("ExternalProject_Add\\(libbwa") "message(")
12018 (("ExternalProject_Add\\(libjellyfish") "message(")
12019 (("ExternalProject_Add\\(libgff") "message(")
12020 (("ExternalProject_Add\\(libtbb") "message(")
12021 (("ExternalProject_Add\\(libspdlog") "message(")
12022 (("ExternalProject_Add\\(libdivsufsort") "message(")
12023 (("ExternalProject_Add\\(libstadenio") "message(")
12024 (("ExternalProject_Add_Step\\(") "message("))
12026 ;; Ensure that all headers can be found
12027 (setenv "CPLUS_INCLUDE_PATH"
12028 (string-append (getenv "CPLUS_INCLUDE_PATH")
12030 (assoc-ref inputs "bwa")
12033 (assoc-ref inputs "eigen")
12034 "/include/eigen3"))
12036 (string-append (assoc-ref inputs "bwa")
12039 (assoc-ref inputs "eigen")
12040 "/include/eigen3"))
12042 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12043 ;; run. It only exists after the install phase.
12044 (add-after 'unpack 'fix-tests
12046 (substitute* "src/CMakeLists.txt"
12047 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12048 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12052 ("bwa" ,bwa-for-salmon)
12058 (uri (git-reference
12059 (url "https://github.com/COMBINE-lab/RapMap.git")
12060 (commit (string-append "salmon-v" version))))
12061 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12064 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12065 ("jemalloc" ,jemalloc)
12066 ("jellyfish" ,jellyfish)
12069 ("libdivsufsort" ,libdivsufsort)
12070 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12071 ("spdlog-for-salmon" ,spdlog-for-salmon)
12074 (home-page "https://github.com/COMBINE-lab/salmon")
12075 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12076 (description "Salmon is a program to produce highly-accurate,
12077 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12078 its accuracy and speed via a number of different innovations, including the
12079 use of lightweight alignments (accurate but fast-to-compute proxies for
12080 traditional read alignments) and massively-parallel stochastic collapsed
12081 variational inference.")
12082 (license license:gpl3+)))
12084 (define-public python-loompy
12086 (name "python-loompy")
12091 (uri (pypi-uri "loompy" version))
12094 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12095 (build-system python-build-system)
12096 ;; There are no tests
12097 (arguments '(#:tests? #f))
12099 `(("python-h5py" ,python-h5py)
12100 ("python-numpy" ,python-numpy)
12101 ("python-scipy" ,python-scipy)
12102 ("python-typing" ,python-typing)))
12103 (home-page "https://github.com/linnarsson-lab/loompy")
12104 (synopsis "Work with .loom files for single-cell RNA-seq data")
12105 (description "The loom file format is an efficient format for very large
12106 omics datasets, consisting of a main matrix, optional additional layers, a
12107 variable number of row and column annotations. Loom also supports sparse
12108 graphs. This library makes it easy to work with @file{.loom} files for
12109 single-cell RNA-seq data.")
12110 (license license:bsd-3)))
12112 ;; We cannot use the latest commit because it requires Java 9.
12113 (define-public java-forester
12114 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12117 (name "java-forester")
12118 (version (string-append "0-" revision "." (string-take commit 7)))
12121 (uri (git-reference
12122 (url "https://github.com/cmzmasek/forester.git")
12124 (file-name (string-append name "-" version "-checkout"))
12127 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12128 (modules '((guix build utils)))
12131 ;; Delete bundled jars and pre-built classes
12132 (delete-file-recursively "forester/java/resources")
12133 (delete-file-recursively "forester/java/classes")
12134 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12135 ;; Delete bundled applications
12136 (delete-file-recursively "forester_applications")
12138 (build-system ant-build-system)
12140 `(#:tests? #f ; there are none
12142 #:modules ((guix build ant-build-system)
12144 (guix build java-utils)
12148 (modify-phases %standard-phases
12149 (add-after 'unpack 'chdir
12150 (lambda _ (chdir "forester/java") #t))
12151 (add-after 'chdir 'fix-dependencies
12153 (chmod "build.xml" #o664)
12154 (call-with-output-file "build.xml.new"
12158 (with-input-from-file "build.xml"
12159 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12160 `(;; Remove all unjar tags to avoid repacking classes.
12161 (unjar . ,(lambda _ '()))
12162 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12163 (*text* . ,(lambda (_ txt) txt))))
12165 (rename-file "build.xml.new" "build.xml")
12167 ;; FIXME: itext is difficult to package as it depends on a few
12168 ;; unpackaged libraries.
12169 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12171 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12172 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12173 (("pdf_written_to = PdfExporter.*")
12174 "throw new IOException(\"PDF export is not available.\");"))
12176 ;; There is no install target
12177 (replace 'install (install-jars ".")))))
12179 `(("java-commons-codec" ,java-commons-codec)
12180 ("java-openchart2" ,java-openchart2)))
12181 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12182 (synopsis "Phylogenomics libraries for Java")
12183 (description "Forester is a collection of Java libraries for
12184 phylogenomics and evolutionary biology research. It includes support for
12185 reading, writing, and exporting phylogenetic trees.")
12186 (license license:lgpl2.1+))))
12188 (define-public java-forester-1.005
12190 (name "java-forester")
12194 (uri (string-append "http://search.maven.org/remotecontent?"
12195 "filepath=org/biojava/thirdparty/forester/"
12196 version "/forester-" version "-sources.jar"))
12197 (file-name (string-append name "-" version ".jar"))
12200 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12201 (build-system ant-build-system)
12203 `(#:tests? #f ; there are none
12205 #:modules ((guix build ant-build-system)
12207 (guix build java-utils)
12211 (modify-phases %standard-phases
12212 (add-after 'unpack 'fix-dependencies
12213 (lambda* (#:key inputs #:allow-other-keys)
12214 (call-with-output-file "build.xml"
12218 (with-input-from-file "src/build.xml"
12219 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12220 `(;; Remove all unjar tags to avoid repacking classes.
12221 (unjar . ,(lambda _ '()))
12222 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12223 (*text* . ,(lambda (_ txt) txt))))
12225 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12226 "synth_look_and_feel_1.xml")
12227 (copy-file (assoc-ref inputs "phyloxml.xsd")
12229 (substitute* "build.xml"
12230 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12231 "synth_look_and_feel_1.xml")
12232 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12235 ;; FIXME: itext is difficult to package as it depends on a few
12236 ;; unpackaged libraries.
12237 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12239 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12240 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12241 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12242 (("pdf_written_to = PdfExporter.*")
12243 "throw new IOException(\"PDF export is not available.\"); /*")
12244 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12245 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12247 (add-after 'unpack 'delete-pre-built-classes
12248 (lambda _ (delete-file-recursively "src/classes") #t))
12249 ;; There is no install target
12250 (replace 'install (install-jars ".")))))
12252 `(("java-commons-codec" ,java-commons-codec)
12253 ("java-openchart2" ,java-openchart2)))
12254 ;; The source archive does not contain the resources.
12259 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12260 "b61cc2dcede0bede317db362472333115756b8c6/"
12261 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12262 (file-name (string-append name "-phyloxml-" version ".xsd"))
12265 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12266 ("synth_look_and_feel_1.xml"
12269 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12270 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12271 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12272 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12275 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12276 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12277 (synopsis "Phylogenomics libraries for Java")
12278 (description "Forester is a collection of Java libraries for
12279 phylogenomics and evolutionary biology research. It includes support for
12280 reading, writing, and exporting phylogenetic trees.")
12281 (license license:lgpl2.1+)))
12283 (define-public java-biojava-core
12285 (name "java-biojava-core")
12289 (uri (git-reference
12290 (url "https://github.com/biojava/biojava")
12291 (commit (string-append "biojava-" version))))
12292 (file-name (string-append name "-" version "-checkout"))
12295 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12296 (build-system ant-build-system)
12299 #:jar-name "biojava-core.jar"
12300 #:source-dir "biojava-core/src/main/java/"
12301 #:test-dir "biojava-core/src/test"
12302 ;; These tests seem to require internet access.
12303 #:test-exclude (list "**/SearchIOTest.java"
12304 "**/BlastXMLParserTest.java"
12305 "**/GenbankCookbookTest.java"
12306 "**/GenbankProxySequenceReaderTest.java")
12308 (modify-phases %standard-phases
12309 (add-before 'build 'copy-resources
12311 (copy-recursively "biojava-core/src/main/resources"
12314 (add-before 'check 'copy-test-resources
12316 (copy-recursively "biojava-core/src/test/resources"
12317 "build/test-classes")
12320 `(("java-log4j-api" ,java-log4j-api)
12321 ("java-log4j-core" ,java-log4j-core)
12322 ("java-slf4j-api" ,java-slf4j-api)
12323 ("java-slf4j-simple" ,java-slf4j-simple)))
12325 `(("java-junit" ,java-junit)
12326 ("java-hamcrest-core" ,java-hamcrest-core)))
12327 (home-page "http://biojava.org")
12328 (synopsis "Core libraries of Java framework for processing biological data")
12329 (description "BioJava is a project dedicated to providing a Java framework
12330 for processing biological data. It provides analytical and statistical
12331 routines, parsers for common file formats, reference implementations of
12332 popular algorithms, and allows the manipulation of sequences and 3D
12333 structures. The goal of the biojava project is to facilitate rapid
12334 application development for bioinformatics.
12336 This package provides the core libraries.")
12337 (license license:lgpl2.1+)))
12339 (define-public java-biojava-phylo
12340 (package (inherit java-biojava-core)
12341 (name "java-biojava-phylo")
12342 (build-system ant-build-system)
12345 #:jar-name "biojava-phylo.jar"
12346 #:source-dir "biojava-phylo/src/main/java/"
12347 #:test-dir "biojava-phylo/src/test"
12349 (modify-phases %standard-phases
12350 (add-before 'build 'copy-resources
12352 (copy-recursively "biojava-phylo/src/main/resources"
12355 (add-before 'check 'copy-test-resources
12357 (copy-recursively "biojava-phylo/src/test/resources"
12358 "build/test-classes")
12361 `(("java-log4j-api" ,java-log4j-api)
12362 ("java-log4j-core" ,java-log4j-core)
12363 ("java-slf4j-api" ,java-slf4j-api)
12364 ("java-slf4j-simple" ,java-slf4j-simple)
12365 ("java-biojava-core" ,java-biojava-core)
12366 ("java-forester" ,java-forester)))
12368 `(("java-junit" ,java-junit)
12369 ("java-hamcrest-core" ,java-hamcrest-core)))
12370 (home-page "http://biojava.org")
12371 (synopsis "Biojava interface to the forester phylogenomics library")
12372 (description "The phylo module provides a biojava interface layer to the
12373 forester phylogenomics library for constructing phylogenetic trees.")))
12375 (define-public java-biojava-alignment
12376 (package (inherit java-biojava-core)
12377 (name "java-biojava-alignment")
12378 (build-system ant-build-system)
12381 #:jar-name "biojava-alignment.jar"
12382 #:source-dir "biojava-alignment/src/main/java/"
12383 #:test-dir "biojava-alignment/src/test"
12385 (modify-phases %standard-phases
12386 (add-before 'build 'copy-resources
12388 (copy-recursively "biojava-alignment/src/main/resources"
12391 (add-before 'check 'copy-test-resources
12393 (copy-recursively "biojava-alignment/src/test/resources"
12394 "build/test-classes")
12397 `(("java-log4j-api" ,java-log4j-api)
12398 ("java-log4j-core" ,java-log4j-core)
12399 ("java-slf4j-api" ,java-slf4j-api)
12400 ("java-slf4j-simple" ,java-slf4j-simple)
12401 ("java-biojava-core" ,java-biojava-core)
12402 ("java-biojava-phylo" ,java-biojava-phylo)
12403 ("java-forester" ,java-forester)))
12405 `(("java-junit" ,java-junit)
12406 ("java-hamcrest-core" ,java-hamcrest-core)))
12407 (home-page "http://biojava.org")
12408 (synopsis "Biojava API for genetic sequence alignment")
12409 (description "The alignment module of BioJava provides an API that
12413 @item implementations of dynamic programming algorithms for sequence
12415 @item reading and writing of popular alignment file formats;
12416 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12419 (define-public java-biojava-core-4.0
12420 (package (inherit java-biojava-core)
12421 (name "java-biojava-core")
12425 (uri (git-reference
12426 (url "https://github.com/biojava/biojava")
12427 (commit (string-append "biojava-" version))))
12428 (file-name (string-append name "-" version "-checkout"))
12431 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12433 (define-public java-biojava-phylo-4.0
12434 (package (inherit java-biojava-core-4.0)
12435 (name "java-biojava-phylo")
12436 (build-system ant-build-system)
12439 #:jar-name "biojava-phylo.jar"
12440 #:source-dir "biojava-phylo/src/main/java/"
12441 #:test-dir "biojava-phylo/src/test"
12443 (modify-phases %standard-phases
12444 (add-before 'build 'copy-resources
12446 (copy-recursively "biojava-phylo/src/main/resources"
12449 (add-before 'check 'copy-test-resources
12451 (copy-recursively "biojava-phylo/src/test/resources"
12452 "build/test-classes")
12455 `(("java-log4j-api" ,java-log4j-api)
12456 ("java-log4j-core" ,java-log4j-core)
12457 ("java-slf4j-api" ,java-slf4j-api)
12458 ("java-slf4j-simple" ,java-slf4j-simple)
12459 ("java-biojava-core" ,java-biojava-core-4.0)
12460 ("java-forester" ,java-forester-1.005)))
12462 `(("java-junit" ,java-junit)
12463 ("java-hamcrest-core" ,java-hamcrest-core)))
12464 (home-page "http://biojava.org")
12465 (synopsis "Biojava interface to the forester phylogenomics library")
12466 (description "The phylo module provides a biojava interface layer to the
12467 forester phylogenomics library for constructing phylogenetic trees.")))
12469 (define-public java-biojava-alignment-4.0
12470 (package (inherit java-biojava-core-4.0)
12471 (name "java-biojava-alignment")
12472 (build-system ant-build-system)
12475 #:jar-name "biojava-alignment.jar"
12476 #:source-dir "biojava-alignment/src/main/java/"
12477 #:test-dir "biojava-alignment/src/test"
12479 (modify-phases %standard-phases
12480 (add-before 'build 'copy-resources
12482 (copy-recursively "biojava-alignment/src/main/resources"
12485 (add-before 'check 'copy-test-resources
12487 (copy-recursively "biojava-alignment/src/test/resources"
12488 "build/test-classes")
12491 `(("java-log4j-api" ,java-log4j-api)
12492 ("java-log4j-core" ,java-log4j-core)
12493 ("java-slf4j-api" ,java-slf4j-api)
12494 ("java-slf4j-simple" ,java-slf4j-simple)
12495 ("java-biojava-core" ,java-biojava-core-4.0)
12496 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12497 ("java-forester" ,java-forester-1.005)))
12499 `(("java-junit" ,java-junit)
12500 ("java-hamcrest-core" ,java-hamcrest-core)))
12501 (home-page "http://biojava.org")
12502 (synopsis "Biojava API for genetic sequence alignment")
12503 (description "The alignment module of BioJava provides an API that
12507 @item implementations of dynamic programming algorithms for sequence
12509 @item reading and writing of popular alignment file formats;
12510 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12513 (define-public dropseq-tools
12515 (name "dropseq-tools")
12520 (uri "http://mccarrolllab.com/download/1276/")
12521 (file-name (string-append "dropseq-tools-" version ".zip"))
12524 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12525 ;; Delete bundled libraries
12526 (modules '((guix build utils)))
12529 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12530 (delete-file-recursively "3rdParty")))))
12531 (build-system ant-build-system)
12533 `(#:tests? #f ; test data are not included
12534 #:test-target "test"
12535 #:build-target "all"
12536 #:source-dir "public/src/"
12539 (list (string-append "-Dpicard.executable.dir="
12540 (assoc-ref %build-inputs "java-picard")
12542 #:modules ((ice-9 match)
12545 (guix build java-utils)
12546 (guix build ant-build-system))
12548 (modify-phases %standard-phases
12549 ;; All dependencies must be linked to "lib", because that's where
12550 ;; they will be searched for when the Class-Path property of the
12551 ;; manifest is computed.
12552 (add-after 'unpack 'record-references
12553 (lambda* (#:key inputs #:allow-other-keys)
12554 (mkdir-p "jar/lib")
12555 (let ((dirs (filter-map (match-lambda
12557 (if (and (string-prefix? "java-" name)
12558 (not (string=? name "java-testng")))
12561 (for-each (lambda (jar)
12562 (symlink jar (string-append "jar/lib/" (basename jar))))
12563 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12566 ;; There is no installation target
12568 (lambda* (#:key inputs outputs #:allow-other-keys)
12569 (let* ((out (assoc-ref outputs "out"))
12570 (bin (string-append out "/bin"))
12571 (share (string-append out "/share/java/"))
12572 (lib (string-append share "/lib/"))
12573 (scripts (list "BAMTagHistogram"
12574 "BAMTagofTagCounts"
12575 "BaseDistributionAtReadPosition"
12576 "CollapseBarcodesInPlace"
12577 "CollapseTagWithContext"
12579 "CreateIntervalsFiles"
12580 "DetectBeadSynthesisErrors"
12581 "DigitalExpression"
12582 "Drop-seq_alignment.sh"
12585 "GatherGeneGCLength"
12586 "GatherMolecularBarcodeDistributionByGene"
12587 "GatherReadQualityMetrics"
12590 "SelectCellsByNumTranscripts"
12591 "SingleCellRnaSeqMetricsCollector"
12592 "TagBamWithReadSequenceExtended"
12593 "TagReadWithGeneExon"
12594 "TagReadWithInterval"
12595 "TrimStartingSequence"
12596 "ValidateReference")))
12597 (for-each mkdir-p (list bin share lib))
12598 (install-file "dist/dropseq.jar" share)
12599 (for-each (lambda (script)
12600 (chmod script #o555)
12601 (install-file script bin))
12603 (substitute* (map (lambda (script)
12604 (string-append bin "/" script))
12606 (("^java") (which "java"))
12607 (("jar_deploy_dir=.*")
12608 (string-append "jar_deploy_dir=" share "\n"))))
12610 ;; FIXME: We do this after stripping jars because we don't want it to
12611 ;; copy all these jars and strip them. We only want to install
12612 ;; links. Arguably, this is a problem with the ant-build-system.
12613 (add-after 'strip-jar-timestamps 'install-links
12614 (lambda* (#:key outputs #:allow-other-keys)
12615 (let* ((out (assoc-ref outputs "out"))
12616 (share (string-append out "/share/java/"))
12617 (lib (string-append share "/lib/")))
12618 (for-each (lambda (jar)
12619 (symlink (readlink jar)
12620 (string-append lib (basename jar))))
12621 (find-files "jar/lib" "\\.jar$")))
12624 `(("jdk" ,icedtea-8)
12625 ("java-picard" ,java-picard-2.10.3)
12626 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12627 ("java-commons-math3" ,java-commons-math3)
12628 ("java-commons-jexl2" ,java-commons-jexl-2)
12629 ("java-commons-collections4" ,java-commons-collections4)
12630 ("java-commons-lang2" ,java-commons-lang)
12631 ("java-commons-io" ,java-commons-io)
12632 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12633 ("java-guava" ,java-guava)
12634 ("java-la4j" ,java-la4j)
12635 ("java-biojava-core" ,java-biojava-core-4.0)
12636 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12637 ("java-jdistlib" ,java-jdistlib)
12638 ("java-simple-xml" ,java-simple-xml)
12639 ("java-snakeyaml" ,java-snakeyaml)))
12642 ("java-testng" ,java-testng)))
12643 (home-page "http://mccarrolllab.com/dropseq/")
12644 (synopsis "Tools for Drop-seq analyses")
12645 (description "Drop-seq is a technology to enable biologists to
12646 analyze RNA expression genome-wide in thousands of individual cells at
12647 once. This package provides tools to perform Drop-seq analyses.")
12648 (license license:expat)))
12650 (define-public pigx-rnaseq
12652 (name "pigx-rnaseq")
12656 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12657 "releases/download/v" version
12658 "/pigx_rnaseq-" version ".tar.gz"))
12661 "168hx2ig3rarphx3l21ay9yyg8ipaakzixnrhpbdi0sknhyvrrk8"))))
12662 (build-system gnu-build-system)
12664 `(#:parallel-tests? #f ; not supported
12666 (modify-phases %standard-phases
12667 (add-after 'install 'wrap-executable
12668 ;; Make sure the executable finds all R modules.
12669 (lambda* (#:key inputs outputs #:allow-other-keys)
12670 (let ((out (assoc-ref outputs "out")))
12671 (wrap-program (string-append out "/bin/pigx-rnaseq")
12672 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))
12673 `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH")))))
12676 `(("snakemake" ,snakemake)
12678 ("multiqc" ,multiqc)
12680 ("trim-galore" ,trim-galore)
12682 ("samtools" ,samtools)
12683 ("bedtools" ,bedtools)
12684 ("r-minimal" ,r-minimal)
12685 ("r-rmarkdown" ,r-rmarkdown)
12686 ("r-ggplot2" ,r-ggplot2)
12687 ("r-ggrepel" ,r-ggrepel)
12688 ("r-gprofiler" ,r-gprofiler)
12689 ("r-deseq2" ,r-deseq2)
12691 ("r-knitr" ,r-knitr)
12692 ("r-pheatmap" ,r-pheatmap)
12693 ("r-corrplot" ,r-corrplot)
12694 ("r-reshape2" ,r-reshape2)
12695 ("r-plotly" ,r-plotly)
12696 ("r-scales" ,r-scales)
12697 ("r-summarizedexperiment" ,r-summarizedexperiment)
12698 ("r-crosstalk" ,r-crosstalk)
12699 ("r-tximport" ,r-tximport)
12700 ("r-rtracklayer" ,r-rtracklayer)
12701 ("r-rjson" ,r-rjson)
12703 ("ghc-pandoc" ,ghc-pandoc)
12704 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12705 ("python-wrapper" ,python-wrapper)
12706 ("python-pyyaml" ,python-pyyaml)))
12707 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12708 (synopsis "Analysis pipeline for RNA sequencing experiments")
12709 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12710 reporting for RNA sequencing experiments. It is easy to use and produces high
12711 quality reports. The inputs are reads files from the sequencing experiment,
12712 and a configuration file which describes the experiment. In addition to
12713 quality control of the experiment, the pipeline produces a differential
12714 expression report comparing samples in an easily configurable manner.")
12715 (license license:gpl3+)))