1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017 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 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017 Tobias Geerinckx-Rice <me@tobias.gr>
12 ;;; This file is part of GNU Guix.
14 ;;; GNU Guix is free software; you can redistribute it and/or modify it
15 ;;; under the terms of the GNU General Public License as published by
16 ;;; the Free Software Foundation; either version 3 of the License, or (at
17 ;;; your option) any later version.
19 ;;; GNU Guix is distributed in the hope that it will be useful, but
20 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
21 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 ;;; GNU General Public License for more details.
24 ;;; You should have received a copy of the GNU General Public License
25 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
27 (define-module (gnu packages bioinformatics)
28 #:use-module ((guix licenses) #:prefix license:)
29 #:use-module (guix packages)
30 #:use-module (guix utils)
31 #:use-module (guix download)
32 #:use-module (guix git-download)
33 #:use-module (guix hg-download)
34 #:use-module (guix build-system ant)
35 #:use-module (guix build-system gnu)
36 #:use-module (guix build-system cmake)
37 #:use-module (guix build-system ocaml)
38 #:use-module (guix build-system perl)
39 #:use-module (guix build-system python)
40 #:use-module (guix build-system r)
41 #:use-module (guix build-system ruby)
42 #:use-module (guix build-system trivial)
43 #:use-module (gnu packages)
44 #:use-module (gnu packages autotools)
45 #:use-module (gnu packages algebra)
46 #:use-module (gnu packages base)
47 #:use-module (gnu packages bash)
48 #:use-module (gnu packages bison)
49 #:use-module (gnu packages boost)
50 #:use-module (gnu packages compression)
51 #:use-module (gnu packages cpio)
52 #:use-module (gnu packages cran)
53 #:use-module (gnu packages curl)
54 #:use-module (gnu packages documentation)
55 #:use-module (gnu packages databases)
56 #:use-module (gnu packages datastructures)
57 #:use-module (gnu packages file)
58 #:use-module (gnu packages flex)
59 #:use-module (gnu packages gawk)
60 #:use-module (gnu packages gcc)
61 #:use-module (gnu packages gd)
62 #:use-module (gnu packages gtk)
63 #:use-module (gnu packages glib)
64 #:use-module (gnu packages graph)
65 #:use-module (gnu packages groff)
66 #:use-module (gnu packages guile)
67 #:use-module (gnu packages haskell)
68 #:use-module (gnu packages image)
69 #:use-module (gnu packages imagemagick)
70 #:use-module (gnu packages java)
71 #:use-module (gnu packages ldc)
72 #:use-module (gnu packages linux)
73 #:use-module (gnu packages logging)
74 #:use-module (gnu packages machine-learning)
75 #:use-module (gnu packages man)
76 #:use-module (gnu packages maths)
77 #:use-module (gnu packages mpi)
78 #:use-module (gnu packages ncurses)
79 #:use-module (gnu packages ocaml)
80 #:use-module (gnu packages pcre)
81 #:use-module (gnu packages parallel)
82 #:use-module (gnu packages pdf)
83 #:use-module (gnu packages perl)
84 #:use-module (gnu packages perl-check)
85 #:use-module (gnu packages pkg-config)
86 #:use-module (gnu packages popt)
87 #:use-module (gnu packages protobuf)
88 #:use-module (gnu packages python)
89 #:use-module (gnu packages python-web)
90 #:use-module (gnu packages readline)
91 #:use-module (gnu packages ruby)
92 #:use-module (gnu packages serialization)
93 #:use-module (gnu packages shells)
94 #:use-module (gnu packages statistics)
95 #:use-module (gnu packages swig)
96 #:use-module (gnu packages tbb)
97 #:use-module (gnu packages tex)
98 #:use-module (gnu packages texinfo)
99 #:use-module (gnu packages textutils)
100 #:use-module (gnu packages time)
101 #:use-module (gnu packages tls)
102 #:use-module (gnu packages vim)
103 #:use-module (gnu packages web)
104 #:use-module (gnu packages xml)
105 #:use-module (gnu packages xorg)
106 #:use-module (srfi srfi-1)
107 #:use-module (ice-9 match))
116 (uri (cran-uri "ape" version))
119 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
120 (build-system r-build-system)
122 `(("r-lattice" ,r-lattice)
125 (home-page "http://ape-package.ird.fr/")
126 (synopsis "Analyses of phylogenetics and evolution")
128 "This package provides functions for reading, writing, plotting, and
129 manipulating phylogenetic trees, analyses of comparative data in a
130 phylogenetic framework, ancestral character analyses, analyses of
131 diversification and macroevolution, computing distances from DNA sequences,
132 and several other tools.")
133 (license license:gpl2+)))
135 (define-public aragorn
142 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
146 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
147 (build-system gnu-build-system)
149 `(#:tests? #f ; there are no tests
151 (modify-phases %standard-phases
155 (zero? (system* "gcc"
161 (string-append "aragorn" ,version ".c")))))
163 (lambda* (#:key outputs #:allow-other-keys)
164 (let* ((out (assoc-ref outputs "out"))
165 (bin (string-append out "/bin"))
166 (man (string-append out "/share/man/man1")))
168 (install-file "aragorn" bin)
170 (install-file "aragorn.1" man))
172 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
173 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
175 "Aragorn identifies transfer RNA, mitochondrial RNA and
176 transfer-messenger RNA from nucleotide sequences, based on homology to known
177 tRNA consensus sequences and RNA structure. It also outputs the secondary
178 structure of the predicted RNA.")
179 (license license:gpl2)))
187 ;; BamM is not available on pypi.
189 "https://github.com/Ecogenomics/BamM/archive/"
191 (file-name (string-append name "-" version ".tar.gz"))
194 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
195 (modules '((guix build utils)))
198 ;; Delete bundled htslib.
199 (delete-file-recursively "c/htslib-1.3.1")
201 (build-system python-build-system)
203 `(#:python ,python-2 ; BamM is Python 2 only.
204 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
205 ;; been modified from its original form.
207 (let ((htslib (assoc-ref %build-inputs "htslib")))
208 (list "--with-libhts-lib" (string-append htslib "/lib")
209 "--with-libhts-inc" (string-append htslib "/include/htslib")))
211 (modify-phases %standard-phases
212 (add-after 'unpack 'autogen
214 (with-directory-excursion "c"
215 (let ((sh (which "sh")))
216 ;; Use autogen so that 'configure' works.
217 (substitute* "autogen.sh" (("/bin/sh") sh))
218 (setenv "CONFIG_SHELL" sh)
219 (substitute* "configure" (("/bin/sh") sh))
220 (zero? (system* "./autogen.sh"))))))
222 ;; Run tests after installation so compilation only happens once.
224 (add-after 'install 'wrap-executable
225 (lambda* (#:key outputs #:allow-other-keys)
226 (let* ((out (assoc-ref outputs "out"))
227 (path (getenv "PATH")))
228 (wrap-program (string-append out "/bin/bamm")
229 `("PATH" ":" prefix (,path))))
231 (add-after 'wrap-executable 'post-install-check
232 (lambda* (#:key inputs outputs #:allow-other-keys)
234 (string-append (assoc-ref outputs "out")
239 (assoc-ref outputs "out")
241 (string-take (string-take-right
242 (assoc-ref inputs "python") 5) 3)
244 (getenv "PYTHONPATH")))
245 ;; There are 2 errors printed, but they are safe to ignore:
246 ;; 1) [E::hts_open_format] fail to open file ...
247 ;; 2) samtools view: failed to open ...
248 (zero? (system* "nosetests")))))))
250 `(("autoconf" ,autoconf)
251 ("automake" ,automake)
254 ("python-nose" ,python2-nose)
255 ("python-pysam" ,python2-pysam)))
257 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
258 ("samtools" ,samtools)
262 ("coreutils" ,coreutils)))
264 `(("python-numpy" ,python2-numpy)))
265 (home-page "http://ecogenomics.github.io/BamM/")
266 (synopsis "Metagenomics-focused BAM file manipulator")
268 "BamM is a C library, wrapped in python, to efficiently generate and
269 parse BAM files, specifically for the analysis of metagenomic data. For
270 instance, it implements several methods to assess contig-wise read coverage.")
271 (license license:lgpl3+)))
273 (define-public bamtools
280 "https://github.com/pezmaster31/bamtools/archive/v"
282 (file-name (string-append name "-" version ".tar.gz"))
285 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
286 (build-system cmake-build-system)
288 `(#:tests? #f ;no "check" target
290 (modify-phases %standard-phases
292 'configure 'set-ldflags
293 (lambda* (#:key outputs #:allow-other-keys)
297 (assoc-ref outputs "out") "/lib/bamtools")))))))
298 (inputs `(("zlib" ,zlib)))
299 (home-page "https://github.com/pezmaster31/bamtools")
300 (synopsis "C++ API and command-line toolkit for working with BAM data")
302 "BamTools provides both a C++ API and a command-line toolkit for handling
304 (license license:expat)))
306 (define-public bcftools
313 "https://github.com/samtools/bcftools/releases/download/"
314 version "/bcftools-" version ".tar.bz2"))
317 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
318 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
319 (modules '((guix build utils)))
321 ;; Delete bundled htslib.
322 '(delete-file-recursively "htslib-1.5"))))
323 (build-system gnu-build-system)
325 `(#:test-target "test"
326 #:configure-flags (list "--with-htslib=system")
330 "LIBS=-lgsl -lgslcblas"
331 (string-append "prefix=" (assoc-ref %outputs "out"))
332 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
333 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
334 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
335 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
336 (string-append "PACKAGE_VERSION=" ,version))
338 (modify-phases %standard-phases
339 (add-before 'check 'patch-tests
341 (substitute* "test/test.pl"
342 (("/bin/bash") (which "bash")))
350 (home-page "https://samtools.github.io/bcftools/")
351 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
353 "BCFtools is a set of utilities that manipulate variant calls in the
354 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
355 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
356 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
357 (license (list license:gpl3+ license:expat))))
359 (define-public bedops
365 (uri (string-append "https://github.com/bedops/bedops/archive/v"
367 (file-name (string-append name "-" version ".tar.gz"))
370 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
371 (build-system gnu-build-system)
374 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
376 (modify-phases %standard-phases
377 (add-after 'unpack 'unpack-tarballs
379 ;; FIXME: Bedops includes tarballs of minimally patched upstream
380 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
381 ;; libraries because at least one of the libraries (zlib) is
382 ;; patched to add a C++ function definition (deflateInit2cpp).
383 ;; Until the Bedops developers offer a way to link against system
384 ;; libraries we have to build the in-tree copies of these three
387 ;; See upstream discussion:
388 ;; https://github.com/bedops/bedops/issues/124
390 ;; Unpack the tarballs to benefit from shebang patching.
391 (with-directory-excursion "third-party"
392 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
393 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
394 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
395 ;; Disable unpacking of tarballs in Makefile.
396 (substitute* "system.mk/Makefile.linux"
397 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
398 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
399 (substitute* "third-party/zlib-1.2.7/Makefile.in"
400 (("^SHELL=.*$") "SHELL=bash\n"))
402 (delete 'configure))))
403 (home-page "https://github.com/bedops/bedops")
404 (synopsis "Tools for high-performance genomic feature operations")
406 "BEDOPS is a suite of tools to address common questions raised in genomic
407 studies---mostly with regard to overlap and proximity relationships between
408 data sets. It aims to be scalable and flexible, facilitating the efficient
409 and accurate analysis and management of large-scale genomic data.
411 BEDOPS provides tools that perform highly efficient and scalable Boolean and
412 other set operations, statistical calculations, archiving, conversion and
413 other management of genomic data of arbitrary scale. Tasks can be easily
414 split by chromosome for distributing whole-genome analyses across a
415 computational cluster.")
416 (license license:gpl2+)))
418 (define-public bedtools
424 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
426 (file-name (string-append name "-" version ".tar.gz"))
429 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
430 (build-system gnu-build-system)
431 (native-inputs `(("python" ,python-2)))
432 (inputs `(("samtools" ,samtools)
435 '(#:test-target "test"
437 (modify-phases %standard-phases
440 (lambda* (#:key outputs #:allow-other-keys)
441 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
442 (for-each (lambda (file)
443 (install-file file bin))
444 (find-files "bin" ".*")))
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 (define-public ribotaper
478 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
479 "files/RiboTaper/RiboTaper_Version_"
483 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
484 (build-system gnu-build-system)
486 `(("bedtools" ,bedtools-2.18)
487 ("samtools" ,samtools-0.1)
488 ("r-minimal" ,r-minimal)
489 ("r-foreach" ,r-foreach)
490 ("r-xnomial" ,r-xnomial)
492 ("r-multitaper" ,r-multitaper)
493 ("r-seqinr" ,r-seqinr)))
494 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
495 (synopsis "Define translated ORFs using ribosome profiling data")
497 "Ribotaper is a method for defining translated @dfn{open reading
498 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
499 provides the Ribotaper pipeline.")
500 (license license:gpl3+)))
502 (define-public ribodiff
509 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
510 "archive/v" version ".tar.gz"))
511 (file-name (string-append name "-" version ".tar.gz"))
514 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
515 (build-system python-build-system)
519 (modify-phases %standard-phases
520 ;; Generate an installable executable script wrapper.
521 (add-after 'unpack 'patch-setup.py
523 (substitute* "setup.py"
524 (("^(.*)packages=.*" line prefix)
525 (string-append line "\n"
526 prefix "scripts=['scripts/TE.py'],\n")))
529 `(("python-numpy" ,python2-numpy)
530 ("python-matplotlib" ,python2-matplotlib)
531 ("python-scipy" ,python2-scipy)
532 ("python-statsmodels" ,python2-statsmodels)))
534 `(("python-mock" ,python2-mock)
535 ("python-nose" ,python2-nose)))
536 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
537 (synopsis "Detect translation efficiency changes from ribosome footprints")
538 (description "RiboDiff is a statistical tool that detects the protein
539 translational efficiency change from Ribo-Seq (ribosome footprinting) and
540 RNA-Seq data. It uses a generalized linear model to detect genes showing
541 difference in translational profile taking mRNA abundance into account. It
542 facilitates us to decipher the translational regulation that behave
543 independently with transcriptional regulation.")
544 (license license:gpl3+)))
546 (define-public bioawk
552 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
554 (file-name (string-append name "-" version ".tar.gz"))
556 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
557 (build-system gnu-build-system)
563 `(#:tests? #f ; There are no tests to run.
564 ;; Bison must generate files, before other targets can build.
567 (modify-phases %standard-phases
568 (delete 'configure) ; There is no configure phase.
570 (lambda* (#:key outputs #:allow-other-keys)
571 (let* ((out (assoc-ref outputs "out"))
572 (bin (string-append out "/bin"))
573 (man (string-append out "/share/man/man1")))
575 (copy-file "awk.1" (string-append man "/bioawk.1"))
576 (install-file "bioawk" bin)))))))
577 (home-page "https://github.com/lh3/bioawk")
578 (synopsis "AWK with bioinformatics extensions")
579 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
580 support of several common biological data formats, including optionally gzip'ed
581 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
582 also adds a few built-in functions and a command line option to use TAB as the
583 input/output delimiter. When the new functionality is not used, bioawk is
584 intended to behave exactly the same as the original BWK awk.")
585 (license license:x11)))
587 (define-public python2-pybedtools
589 (name "python2-pybedtools")
594 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
598 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
599 (build-system python-build-system)
600 (arguments `(#:python ,python-2)) ; no Python 3 support
602 `(("python-matplotlib" ,python2-matplotlib)))
604 `(("bedtools" ,bedtools)
605 ("samtools" ,samtools)))
607 `(("python-cython" ,python2-cython)
608 ("python-pyyaml" ,python2-pyyaml)
609 ("python-nose" ,python2-nose)))
610 (home-page "https://pythonhosted.org/pybedtools/")
611 (synopsis "Python wrapper for BEDtools programs")
613 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
614 which are widely used for genomic interval manipulation or \"genome algebra\".
615 pybedtools extends BEDTools by offering feature-level manipulations from with
617 (license license:gpl2+)))
619 (define-public python-biom-format
621 (name "python-biom-format")
626 ;; Use GitHub as source because PyPI distribution does not contain
627 ;; test data: https://github.com/biocore/biom-format/issues/693
628 (uri (string-append "https://github.com/biocore/biom-format/archive/"
630 (file-name (string-append name "-" version ".tar.gz"))
633 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
634 (build-system python-build-system)
636 `(("python-numpy" ,python-numpy)
637 ("python-scipy" ,python-scipy)
638 ("python-future" ,python-future)
639 ("python-click" ,python-click)
640 ("python-h5py" ,python-h5py)
641 ("python-pandas" ,python-pandas)))
643 `(("python-nose" ,python-nose)))
644 (home-page "http://www.biom-format.org")
645 (synopsis "Biological Observation Matrix (BIOM) format utilities")
647 "The BIOM file format is designed to be a general-use format for
648 representing counts of observations e.g. operational taxonomic units, KEGG
649 orthology groups or lipid types, in one or more biological samples
650 e.g. microbiome samples, genomes, metagenomes.")
651 (license license:bsd-3)
652 (properties `((python2-variant . ,(delay python2-biom-format))))))
654 (define-public python2-biom-format
655 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
660 (modify-phases %standard-phases
661 ;; Do not require the unmaintained pyqi library.
662 (add-after 'unpack 'remove-pyqi
664 (substitute* "setup.py"
665 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
667 ,@(package-arguments base))))))
669 (define-public bioperl-minimal
670 (let* ((inputs `(("perl-module-build" ,perl-module-build)
671 ("perl-data-stag" ,perl-data-stag)
672 ("perl-libwww" ,perl-libwww)
673 ("perl-uri" ,perl-uri)))
675 (map (compose package-name cadr)
678 (map (compose package-transitive-target-inputs cadr) inputs))))))
680 (name "bioperl-minimal")
685 (uri (string-append "https://github.com/bioperl/bioperl-live/"
687 (string-map (lambda (c)
693 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
694 (build-system perl-build-system)
697 (modify-phases %standard-phases
699 'install 'wrap-programs
700 (lambda* (#:key outputs #:allow-other-keys)
701 ;; Make sure all executables in "bin" find the required Perl
702 ;; modules at runtime. As the PERL5LIB variable contains also
703 ;; the paths of native inputs, we pick the transitive target
704 ;; inputs from %build-inputs.
705 (let* ((out (assoc-ref outputs "out"))
706 (bin (string-append out "/bin/"))
708 (cons (string-append out "/lib/perl5/site_perl")
710 (assoc-ref %build-inputs name))
711 ',transitive-inputs))
713 (for-each (lambda (file)
715 `("PERL5LIB" ":" prefix (,path))))
716 (find-files bin "\\.pl$"))
720 `(("perl-test-most" ,perl-test-most)))
721 (home-page "http://search.cpan.org/dist/BioPerl")
722 (synopsis "Bioinformatics toolkit")
724 "BioPerl is the product of a community effort to produce Perl code which
725 is useful in biology. Examples include Sequence objects, Alignment objects
726 and database searching objects. These objects not only do what they are
727 advertised to do in the documentation, but they also interact - Alignment
728 objects are made from the Sequence objects, Sequence objects have access to
729 Annotation and SeqFeature objects and databases, Blast objects can be
730 converted to Alignment objects, and so on. This means that the objects
731 provide a coordinated and extensible framework to do computational biology.")
732 (license license:perl-license))))
734 (define-public python-biopython
736 (name "python-biopython")
740 ;; use PyPi rather than biopython.org to ease updating
741 (uri (pypi-uri "biopython" version))
744 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
745 (build-system python-build-system)
748 (modify-phases %standard-phases
749 (add-before 'check 'set-home
750 ;; Some tests require a home directory to be set.
751 (lambda _ (setenv "HOME" "/tmp") #t)))))
753 `(("python-numpy" ,python-numpy)))
754 (home-page "http://biopython.org/")
755 (synopsis "Tools for biological computation in Python")
757 "Biopython is a set of tools for biological computation including parsers
758 for bioinformatics files into Python data structures; interfaces to common
759 bioinformatics programs; a standard sequence class and tools for performing
760 common operations on them; code to perform data classification; code for
761 dealing with alignments; code making it easy to split up parallelizable tasks
762 into separate processes; and more.")
763 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
765 (define-public python2-biopython
766 (package-with-python2 python-biopython))
768 ;; An outdated version of biopython is required for seqmagick, see
769 ;; https://github.com/fhcrc/seqmagick/issues/59
770 ;; When that issue has been resolved this package should be removed.
771 (define python2-biopython-1.66
773 (inherit python2-biopython)
777 (uri (pypi-uri "biopython" version))
780 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
782 (define-public bpp-core
783 ;; The last release was in 2014 and the recommended way to install from source
784 ;; is to clone the git repository, so we do this.
785 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
786 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
789 (version (string-append "2.2.0-1." (string-take commit 7)))
793 (url "http://biopp.univ-montp2.fr/git/bpp-core")
795 (file-name (string-append name "-" version "-checkout"))
798 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
799 (build-system cmake-build-system)
801 `(#:parallel-build? #f))
803 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
804 ; compile all of the bpp packages with GCC 5.
805 (home-page "http://biopp.univ-montp2.fr")
806 (synopsis "C++ libraries for Bioinformatics")
808 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
809 analysis, phylogenetics, molecular evolution and population genetics. It is
810 Object Oriented and is designed to be both easy to use and computer efficient.
811 Bio++ intends to help programmers to write computer expensive programs, by
812 providing them a set of re-usable tools.")
813 (license license:cecill-c))))
815 (define-public bpp-phyl
816 ;; The last release was in 2014 and the recommended way to install from source
817 ;; is to clone the git repository, so we do this.
818 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
819 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
822 (version (string-append "2.2.0-1." (string-take commit 7)))
826 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
828 (file-name (string-append name "-" version "-checkout"))
831 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
832 (build-system cmake-build-system)
834 `(#:parallel-build? #f
835 ;; If out-of-source, test data is not copied into the build directory
836 ;; so the tests fail.
837 #:out-of-source? #f))
839 `(("bpp-core" ,bpp-core)
841 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
844 (home-page "http://biopp.univ-montp2.fr")
845 (synopsis "Bio++ phylogenetic Library")
847 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
848 analysis, phylogenetics, molecular evolution and population genetics. This
849 library provides phylogenetics-related modules.")
850 (license license:cecill-c))))
852 (define-public bpp-popgen
853 ;; The last release was in 2014 and the recommended way to install from source
854 ;; is to clone the git repository, so we do this.
855 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
856 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
859 (version (string-append "2.2.0-1." (string-take commit 7)))
863 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
865 (file-name (string-append name "-" version "-checkout"))
868 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
869 (build-system cmake-build-system)
871 `(#:parallel-build? #f
872 #:tests? #f)) ; There are no tests.
874 `(("bpp-core" ,bpp-core)
877 (home-page "http://biopp.univ-montp2.fr")
878 (synopsis "Bio++ population genetics library")
880 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
881 analysis, phylogenetics, molecular evolution and population genetics. This
882 library provides population genetics-related modules.")
883 (license license:cecill-c))))
885 (define-public bpp-seq
886 ;; The last release was in 2014 and the recommended way to install from source
887 ;; is to clone the git repository, so we do this.
888 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
889 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
892 (version (string-append "2.2.0-1." (string-take commit 7)))
896 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
898 (file-name (string-append name "-" version "-checkout"))
901 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
902 (build-system cmake-build-system)
904 `(#:parallel-build? #f
905 ;; If out-of-source, test data is not copied into the build directory
906 ;; so the tests fail.
907 #:out-of-source? #f))
909 `(("bpp-core" ,bpp-core)
910 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
911 (home-page "http://biopp.univ-montp2.fr")
912 (synopsis "Bio++ sequence library")
914 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
915 analysis, phylogenetics, molecular evolution and population genetics. This
916 library provides sequence-related modules.")
917 (license license:cecill-c))))
919 (define-public bppsuite
920 ;; The last release was in 2014 and the recommended way to install from source
921 ;; is to clone the git repository, so we do this.
922 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
923 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
926 (version (string-append "2.2.0-1." (string-take commit 7)))
930 (url "http://biopp.univ-montp2.fr/git/bppsuite")
932 (file-name (string-append name "-" version "-checkout"))
935 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
936 (build-system cmake-build-system)
938 `(#:parallel-build? #f
939 #:tests? #f)) ; There are no tests.
943 ("texinfo" ,texinfo)))
945 `(("bpp-core" ,bpp-core)
947 ("bpp-phyl" ,bpp-phyl)
948 ("bpp-phyl" ,bpp-popgen)
950 (home-page "http://biopp.univ-montp2.fr")
951 (synopsis "Bioinformatics tools written with the Bio++ libraries")
953 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
954 analysis, phylogenetics, molecular evolution and population genetics. This
955 package provides command line tools using the Bio++ library.")
956 (license license:cecill-c))))
958 (define-public blast+
965 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
966 version "/ncbi-blast-" version "+-src.tar.gz"))
969 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
970 (patches (search-patches "blast+-fix-makefile.patch"))
971 (modules '((guix build utils)))
974 ;; Remove bundled bzip2, zlib and pcre.
975 (delete-file-recursively "c++/src/util/compress/bzip2")
976 (delete-file-recursively "c++/src/util/compress/zlib")
977 (delete-file-recursively "c++/src/util/regexp")
978 (substitute* "c++/src/util/compress/Makefile.in"
979 (("bzip2 zlib api") "api"))
980 ;; Remove useless msbuild directory
981 (delete-file-recursively
982 "c++/src/build-system/project_tree_builder/msbuild")
984 (build-system gnu-build-system)
986 `(;; There are two(!) tests for this massive library, and both fail with
987 ;; "unparsable timing stats".
988 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
989 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
992 #:parallel-build? #f ; not supported
994 (modify-phases %standard-phases
997 ;; $HOME needs to be set at some point during the configure phase
998 (lambda _ (setenv "HOME" "/tmp") #t))
1001 (lambda _ (chdir "c++") #t))
1003 'enter-dir 'fix-build-system
1005 (define (which* cmd)
1006 (cond ((string=? cmd "date")
1007 ;; make call to "date" deterministic
1012 (format (current-error-port)
1013 "WARNING: Unable to find absolute path for ~s~%"
1017 ;; Rewrite hardcoded paths to various tools
1018 (substitute* (append '("src/build-system/configure.ac"
1019 "src/build-system/configure"
1020 "src/build-system/helpers/run_with_lock.c"
1021 "scripts/common/impl/if_diff.sh"
1022 "scripts/common/impl/run_with_lock.sh"
1023 "src/build-system/Makefile.configurables.real"
1024 "src/build-system/Makefile.in.top"
1025 "src/build-system/Makefile.meta.gmake=no"
1026 "src/build-system/Makefile.meta.in"
1027 "src/build-system/Makefile.meta_l"
1028 "src/build-system/Makefile.meta_p"
1029 "src/build-system/Makefile.meta_r"
1030 "src/build-system/Makefile.mk.in"
1031 "src/build-system/Makefile.requirements"
1032 "src/build-system/Makefile.rules_with_autodep.in")
1033 (find-files "scripts/common/check" "\\.sh$"))
1034 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1035 (or (which* cmd) all)))
1037 (substitute* (find-files "src/build-system" "^config.*")
1038 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1041 ;; rewrite "/var/tmp" in check script
1042 (substitute* "scripts/common/check/check_make_unix.sh"
1043 (("/var/tmp") "/tmp"))
1045 ;; do not reset PATH
1046 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1048 (("action=/bin/") "action=")
1049 (("export PATH") ":"))
1053 (lambda* (#:key inputs outputs #:allow-other-keys)
1054 (let ((out (assoc-ref outputs "out"))
1055 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1056 (include (string-append (assoc-ref outputs "include")
1057 "/include/ncbi-tools++")))
1058 ;; The 'configure' script doesn't recognize things like
1059 ;; '--enable-fast-install'.
1060 (zero? (system* "./configure.orig"
1061 (string-append "--with-build-root=" (getcwd) "/build")
1062 (string-append "--prefix=" out)
1063 (string-append "--libdir=" lib)
1064 (string-append "--includedir=" include)
1065 (string-append "--with-bz2="
1066 (assoc-ref inputs "bzip2"))
1067 (string-append "--with-z="
1068 (assoc-ref inputs "zlib"))
1069 (string-append "--with-pcre="
1070 (assoc-ref inputs "pcre"))
1071 ;; Each library is built twice by default, once
1072 ;; with "-static" in its name, and again
1075 "--with-dll"))))))))
1076 (outputs '("out" ; 21 MB
1084 ("python" ,python-wrapper)))
1087 (home-page "http://blast.ncbi.nlm.nih.gov")
1088 (synopsis "Basic local alignment search tool")
1090 "BLAST is a popular method of performing a DNA or protein sequence
1091 similarity search, using heuristics to produce results quickly. It also
1092 calculates an “expect value” that estimates how many matches would have
1093 occurred at a given score by chance, which can aid a user in judging how much
1094 confidence to have in an alignment.")
1095 ;; Most of the sources are in the public domain, with the following
1098 ;; * ./c++/include/util/bitset/
1099 ;; * ./c++/src/html/ncbi_menu*.js
1101 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1103 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1105 ;; * ./c++/src/corelib/teamcity_*
1106 (license (list license:public-domain
1112 (define-public bless
1118 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1122 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1123 (modules '((guix build utils)))
1126 ;; Remove bundled boost, pigz, zlib, and .git directory
1127 ;; FIXME: also remove bundled sources for murmurhash3 and
1128 ;; kmc once packaged.
1129 (delete-file-recursively "boost")
1130 (delete-file-recursively "pigz")
1131 (delete-file-recursively "google-sparsehash")
1132 (delete-file-recursively "zlib")
1133 (delete-file-recursively ".git")
1135 (build-system gnu-build-system)
1137 '(#:tests? #f ;no "check" target
1139 (list (string-append "ZLIB="
1140 (assoc-ref %build-inputs "zlib")
1142 (string-append "LDFLAGS="
1143 (string-join '("-lboost_filesystem"
1150 (modify-phases %standard-phases
1151 (add-after 'unpack 'do-not-build-bundled-pigz
1152 (lambda* (#:key inputs outputs #:allow-other-keys)
1153 (substitute* "Makefile"
1154 (("cd pigz/pigz-2.3.3; make") ""))
1156 (add-after 'unpack 'patch-paths-to-executables
1157 (lambda* (#:key inputs outputs #:allow-other-keys)
1158 (substitute* "parse_args.cpp"
1159 (("kmc_binary = .*")
1160 (string-append "kmc_binary = \""
1161 (assoc-ref outputs "out")
1163 (("pigz_binary = .*")
1164 (string-append "pigz_binary = \""
1165 (assoc-ref inputs "pigz")
1169 (lambda* (#:key outputs #:allow-other-keys)
1170 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1171 (for-each (lambda (file)
1172 (install-file file bin))
1173 '("bless" "kmc/bin/kmc"))
1175 (delete 'configure))))
1179 `(("openmpi" ,openmpi)
1181 ("sparsehash" ,sparsehash)
1184 (supported-systems '("x86_64-linux"))
1185 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1186 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1188 "@dfn{Bloom-filter-based error correction solution for high-throughput
1189 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1190 correction tool for genomic reads produced by @dfn{Next-generation
1191 sequencing} (NGS). BLESS produces accurate correction results with much less
1192 memory compared with previous solutions and is also able to tolerate a higher
1193 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1194 errors at the end of reads.")
1195 (license license:gpl3+)))
1197 (define-public bowtie
1203 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1205 (file-name (string-append name "-" version ".tar.gz"))
1208 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1209 (modules '((guix build utils)))
1211 '(substitute* "Makefile"
1212 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1213 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1214 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1215 (build-system gnu-build-system)
1218 ("perl-clone" ,perl-clone)
1219 ("perl-test-deep" ,perl-test-deep)
1220 ("perl-test-simple" ,perl-test-simple)
1221 ("python" ,python-2)
1228 (string-append "prefix=" (assoc-ref %outputs "out")))
1230 (modify-phases %standard-phases
1233 (lambda* (#:key outputs #:allow-other-keys)
1234 (zero? (system* "perl"
1235 "scripts/test/simple_tests.pl"
1236 "--bowtie2=./bowtie2"
1237 "--bowtie2-build=./bowtie2-build")))))))
1238 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1239 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1241 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1242 reads to long reference sequences. It is particularly good at aligning reads
1243 of about 50 up to 100s or 1,000s of characters, and particularly good at
1244 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1245 genome with an FM Index to keep its memory footprint small: for the human
1246 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1247 gapped, local, and paired-end alignment modes.")
1248 (supported-systems '("x86_64-linux"))
1249 (license license:gpl3+)))
1251 (define-public tophat
1258 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1262 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1263 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1264 (modules '((guix build utils)))
1267 ;; Remove bundled SeqAn and samtools
1268 (delete-file-recursively "src/SeqAn-1.3")
1269 (delete-file-recursively "src/samtools-0.1.18")
1271 (build-system gnu-build-system)
1273 '(#:parallel-build? #f ; not supported
1275 (modify-phases %standard-phases
1276 (add-after 'unpack 'use-system-samtools
1277 (lambda* (#:key inputs #:allow-other-keys)
1278 (substitute* "src/Makefile.in"
1279 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1280 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1281 (("SAMPROG = samtools_0\\.1\\.18") "")
1282 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1283 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1284 (substitute* '("src/common.cpp"
1286 (("samtools_0.1.18") (which "samtools")))
1287 (substitute* '("src/common.h"
1288 "src/bam2fastx.cpp")
1289 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1290 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1291 (substitute* '("src/bwt_map.h"
1293 "src/align_status.h")
1294 (("#include <bam.h>") "#include <samtools/bam.h>")
1295 (("#include <sam.h>") "#include <samtools/sam.h>"))
1300 ("samtools" ,samtools-0.1)
1301 ("ncurses" ,ncurses)
1302 ("python" ,python-2)
1306 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1307 (synopsis "Spliced read mapper for RNA-Seq data")
1309 "TopHat is a fast splice junction mapper for nucleotide sequence
1310 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1311 mammalian-sized genomes using the ultra high-throughput short read
1312 aligner Bowtie, and then analyzes the mapping results to identify
1313 splice junctions between exons.")
1314 ;; TopHat is released under the Boost Software License, Version 1.0
1315 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1316 (license license:boost1.0)))
1325 "https://github.com/lh3/bwa/releases/download/v"
1326 version "/bwa-" version ".tar.bz2"))
1329 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1330 (build-system gnu-build-system)
1332 '(#:tests? #f ;no "check" target
1334 (modify-phases %standard-phases
1336 (lambda* (#:key outputs #:allow-other-keys)
1337 (let ((bin (string-append
1338 (assoc-ref outputs "out") "/bin"))
1340 (assoc-ref outputs "out") "/share/doc/bwa"))
1342 (assoc-ref outputs "out") "/share/man/man1")))
1343 (install-file "bwa" bin)
1344 (install-file "README.md" doc)
1345 (install-file "bwa.1" man))
1347 ;; no "configure" script
1348 (delete 'configure))))
1349 (inputs `(("zlib" ,zlib)))
1350 ;; Non-portable SSE instructions are used so building fails on platforms
1351 ;; other than x86_64.
1352 (supported-systems '("x86_64-linux"))
1353 (home-page "http://bio-bwa.sourceforge.net/")
1354 (synopsis "Burrows-Wheeler sequence aligner")
1356 "BWA is a software package for mapping low-divergent sequences against a
1357 large reference genome, such as the human genome. It consists of three
1358 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1359 designed for Illumina sequence reads up to 100bp, while the rest two for
1360 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1361 features such as long-read support and split alignment, but BWA-MEM, which is
1362 the latest, is generally recommended for high-quality queries as it is faster
1363 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1364 70-100bp Illumina reads.")
1365 (license license:gpl3+)))
1367 (define-public bwa-pssm
1368 (package (inherit bwa)
1373 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1374 "archive/" version ".tar.gz"))
1375 (file-name (string-append name "-" version ".tar.gz"))
1378 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1379 (build-system gnu-build-system)
1384 (home-page "http://bwa-pssm.binf.ku.dk/")
1385 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1387 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1388 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1389 existing aligners it is fast and sensitive. Unlike most other aligners,
1390 however, it is also adaptible in the sense that one can direct the alignment
1391 based on known biases within the data set. It is coded as a modification of
1392 the original BWA alignment program and shares the genome index structure as
1393 well as many of the command line options.")
1394 (license license:gpl3+)))
1396 (define-public python2-bx-python
1398 (name "python2-bx-python")
1402 (uri (pypi-uri "bx-python" version))
1405 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1406 (modules '((guix build utils)))
1408 '(substitute* "setup.py"
1409 ;; remove dependency on outdated "distribute" module
1410 (("^from distribute_setup import use_setuptools") "")
1411 (("^use_setuptools\\(\\)") "")))))
1412 (build-system python-build-system)
1414 `(#:tests? #f ;tests fail because test data are not included
1415 #:python ,python-2))
1417 `(("python-numpy" ,python2-numpy)
1420 `(("python-nose" ,python2-nose)))
1421 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1422 (synopsis "Tools for manipulating biological data")
1424 "bx-python provides tools for manipulating biological data, particularly
1425 multiple sequence alignments.")
1426 (license license:expat)))
1428 (define-public python-pysam
1430 (name "python-pysam")
1431 (version "0.11.2.2")
1434 ;; Test data is missing on PyPi.
1436 "https://github.com/pysam-developers/pysam/archive/v"
1438 (file-name (string-append name "-" version ".tar.gz"))
1441 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1442 (modules '((guix build utils)))
1444 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1445 '(delete-file-recursively "htslib"))))
1446 (build-system python-build-system)
1448 `(#:modules ((ice-9 ftw)
1450 (guix build python-build-system)
1453 (modify-phases %standard-phases
1454 (add-before 'build 'set-flags
1455 (lambda* (#:key inputs #:allow-other-keys)
1456 (setenv "HTSLIB_MODE" "external")
1457 (setenv "HTSLIB_LIBRARY_DIR"
1458 (string-append (assoc-ref inputs "htslib") "/lib"))
1459 (setenv "HTSLIB_INCLUDE_DIR"
1460 (string-append (assoc-ref inputs "htslib") "/include"))
1461 (setenv "LDFLAGS" "-lncurses")
1462 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1465 (lambda* (#:key inputs outputs #:allow-other-keys)
1466 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1467 (setenv "PYTHONPATH"
1469 (getenv "PYTHONPATH")
1470 ":" (getcwd) "/build/"
1471 (car (scandir "build"
1472 (negate (cut string-prefix? "." <>))))))
1473 ;; Step out of source dir so python does not import from CWD.
1474 (with-directory-excursion "tests"
1475 (setenv "HOME" "/tmp")
1476 (and (zero? (system* "make" "-C" "pysam_data"))
1477 (zero? (system* "make" "-C" "cbcf_data"))
1478 ;; Running nosetests without explicitly asking for a
1479 ;; single process leads to a crash. Running with multiple
1480 ;; processes fails because the tests are not designed to
1483 ;; FIXME: tests keep timing out on some systems.
1484 ;; (zero? (system* "nosetests" "-v"
1485 ;; "--processes" "1"))
1488 `(("htslib" ,htslib))) ; Included from installed header files.
1490 `(("ncurses" ,ncurses)
1493 `(("python-cython" ,python-cython)
1494 ;; Dependencies below are are for tests only.
1495 ("samtools" ,samtools)
1496 ("bcftools" ,bcftools)
1497 ("python-nose" ,python-nose)))
1498 (home-page "https://github.com/pysam-developers/pysam")
1499 (synopsis "Python bindings to the SAMtools C API")
1501 "Pysam is a Python module for reading and manipulating files in the
1502 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1503 also includes an interface for tabix.")
1504 (license license:expat)))
1506 (define-public python2-pysam
1507 (package-with-python2 python-pysam))
1509 (define-public python-twobitreader
1511 (name "python-twobitreader")
1515 (uri (pypi-uri "twobitreader" version))
1518 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1519 (build-system python-build-system)
1521 '(;; Tests are not distributed in the PyPi release.
1522 ;; TODO Try building from the Git repo or asking the upstream maintainer
1523 ;; to distribute the tests on PyPi.
1526 `(("python-sphinx" ,python-sphinx)))
1527 (home-page "https://github.com/benjschiller/twobitreader")
1528 (synopsis "Python library for reading .2bit files")
1530 "twobitreader is a Python library for reading .2bit files as used by the
1531 UCSC genome browser.")
1532 (license license:artistic2.0)))
1534 (define-public python2-twobitreader
1535 (package-with-python2 python-twobitreader))
1537 (define-public python-plastid
1539 (name "python-plastid")
1543 (uri (pypi-uri "plastid" version))
1546 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1547 (build-system python-build-system)
1549 ;; Some test files are not included.
1552 `(("python-numpy" ,python-numpy)
1553 ("python-scipy" ,python-scipy)
1554 ("python-pandas" ,python-pandas)
1555 ("python-pysam" ,python-pysam)
1556 ("python-matplotlib" ,python-matplotlib)
1557 ("python-biopython" ,python-biopython)
1558 ("python-twobitreader" ,python-twobitreader)
1559 ("python-termcolor" ,python-termcolor)))
1561 `(("python-cython" ,python-cython)
1562 ("python-nose" ,python-nose)))
1563 (home-page "https://github.com/joshuagryphon/plastid")
1564 (synopsis "Python library for genomic analysis")
1566 "plastid is a Python library for genomic analysis – in particular,
1567 high-throughput sequencing data – with an emphasis on simplicity.")
1568 (license license:bsd-3)))
1570 (define-public python2-plastid
1571 (package-with-python2 python-plastid))
1573 (define-public cd-hit
1579 (uri (string-append "https://github.com/weizhongli/cdhit"
1580 "/releases/download/V" version
1582 "-2017-0621-source.tar.gz"))
1585 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1586 (build-system gnu-build-system)
1588 `(#:tests? #f ; there are no tests
1590 ;; Executables are copied directly to the PREFIX.
1591 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1593 (modify-phases %standard-phases
1594 ;; No "configure" script
1596 ;; Remove sources of non-determinism
1597 (add-after 'unpack 'be-timeless
1599 (substitute* "cdhit-utility.c++"
1600 ((" \\(built on \" __DATE__ \"\\)") ""))
1601 (substitute* "cdhit-common.c++"
1602 (("__DATE__") "\"0\"")
1603 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1605 ;; The "install" target does not create the target directory.
1606 (add-before 'install 'create-target-dir
1607 (lambda* (#:key outputs #:allow-other-keys)
1608 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1612 (home-page "http://weizhongli-lab.org/cd-hit/")
1613 (synopsis "Cluster and compare protein or nucleotide sequences")
1615 "CD-HIT is a program for clustering and comparing protein or nucleotide
1616 sequences. CD-HIT is designed to be fast and handle extremely large
1618 ;; The manual says: "It can be copied under the GNU General Public License
1619 ;; version 2 (GPLv2)."
1620 (license license:gpl2)))
1622 (define-public clipper
1629 "https://github.com/YeoLab/clipper/archive/"
1631 (file-name (string-append name "-" version ".tar.gz"))
1634 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1635 (modules '((guix build utils)))
1638 ;; remove unnecessary setup dependency
1639 (substitute* "setup.py"
1640 (("setup_requires = .*") ""))
1641 (for-each delete-file
1642 '("clipper/src/peaks.so"
1643 "clipper/src/readsToWiggle.so"))
1644 (delete-file-recursively "dist/")
1646 (build-system python-build-system)
1647 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1649 `(("htseq" ,python2-htseq)
1650 ("python-pybedtools" ,python2-pybedtools)
1651 ("python-cython" ,python2-cython)
1652 ("python-scikit-learn" ,python2-scikit-learn)
1653 ("python-matplotlib" ,python2-matplotlib)
1654 ("python-pandas" ,python2-pandas)
1655 ("python-pysam" ,python2-pysam)
1656 ("python-numpy" ,python2-numpy)
1657 ("python-scipy" ,python2-scipy)))
1659 `(("python-mock" ,python2-mock) ; for tests
1660 ("python-nose" ,python2-nose) ; for tests
1661 ("python-pytz" ,python2-pytz))) ; for tests
1662 (home-page "https://github.com/YeoLab/clipper")
1663 (synopsis "CLIP peak enrichment recognition")
1665 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1666 (license license:gpl2)))
1668 (define-public codingquarry
1670 (name "codingquarry")
1675 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1679 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1680 (build-system gnu-build-system)
1682 '(#:tests? #f ; no "check" target
1684 (modify-phases %standard-phases
1687 (lambda* (#:key outputs #:allow-other-keys)
1688 (let* ((out (assoc-ref outputs "out"))
1689 (bin (string-append out "/bin"))
1690 (doc (string-append out "/share/doc/codingquarry")))
1691 (install-file "INSTRUCTIONS.pdf" doc)
1692 (copy-recursively "QuarryFiles"
1693 (string-append out "/QuarryFiles"))
1694 (install-file "CodingQuarry" bin)
1695 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1696 (inputs `(("openmpi" ,openmpi)))
1697 (native-search-paths
1698 (list (search-path-specification
1699 (variable "QUARRY_PATH")
1700 (files '("QuarryFiles")))))
1701 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1702 (synopsis "Fungal gene predictor")
1703 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1704 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1705 (home-page "https://sourceforge.net/projects/codingquarry/")
1706 (license license:gpl3+)))
1708 (define-public couger
1715 "http://couger.oit.duke.edu/static/assets/COUGER"
1719 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1720 (build-system gnu-build-system)
1724 (modify-phases %standard-phases
1729 (lambda* (#:key outputs #:allow-other-keys)
1730 (let* ((out (assoc-ref outputs "out"))
1731 (bin (string-append out "/bin")))
1732 (copy-recursively "src" (string-append out "/src"))
1734 ;; Add "src" directory to module lookup path.
1735 (substitute* "couger"
1737 (string-append "import sys\nsys.path.append(\""
1738 out "\")\nfrom argparse")))
1739 (install-file "couger" bin))
1742 'install 'wrap-program
1743 (lambda* (#:key inputs outputs #:allow-other-keys)
1744 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1745 (let* ((out (assoc-ref outputs "out"))
1746 (path (getenv "PYTHONPATH")))
1747 (wrap-program (string-append out "/bin/couger")
1748 `("PYTHONPATH" ":" prefix (,path))))
1751 `(("python" ,python-2)
1752 ("python2-pillow" ,python2-pillow)
1753 ("python2-numpy" ,python2-numpy)
1754 ("python2-scipy" ,python2-scipy)
1755 ("python2-matplotlib" ,python2-matplotlib)))
1757 `(("r-minimal" ,r-minimal)
1759 ("randomjungle" ,randomjungle)))
1761 `(("unzip" ,unzip)))
1762 (home-page "http://couger.oit.duke.edu")
1763 (synopsis "Identify co-factors in sets of genomic regions")
1765 "COUGER can be applied to any two sets of genomic regions bound by
1766 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1767 putative co-factors that provide specificity to each TF. The framework
1768 determines the genomic targets uniquely-bound by each TF, and identifies a
1769 small set of co-factors that best explain the in vivo binding differences
1770 between the two TFs.
1772 COUGER uses classification algorithms (support vector machines and random
1773 forests) with features that reflect the DNA binding specificities of putative
1774 co-factors. The features are generated either from high-throughput TF-DNA
1775 binding data (from protein binding microarray experiments), or from large
1776 collections of DNA motifs.")
1777 (license license:gpl3+)))
1779 (define-public clustal-omega
1781 (name "clustal-omega")
1785 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1789 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1790 (build-system gnu-build-system)
1792 `(("argtable" ,argtable)))
1793 (home-page "http://www.clustal.org/omega/")
1794 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1796 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1797 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1798 of handling data-sets of hundreds of thousands of sequences in reasonable
1800 (license license:gpl2+)))
1802 (define-public crossmap
1808 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1812 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1813 ;; This patch has been sent upstream already and is available
1814 ;; for download from Sourceforge, but it has not been merged.
1815 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1816 (modules '((guix build utils)))
1817 ;; remove bundled copy of pysam
1819 '(delete-file-recursively "lib/pysam"))))
1820 (build-system python-build-system)
1822 `(#:python ,python-2
1824 (modify-phases %standard-phases
1825 (add-after 'unpack 'set-env
1826 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1828 `(("python-numpy" ,python2-numpy)
1829 ("python-pysam" ,python2-pysam)
1832 `(("python-cython" ,python2-cython)
1833 ("python-nose" ,python2-nose)))
1834 (home-page "http://crossmap.sourceforge.net/")
1835 (synopsis "Convert genome coordinates between assemblies")
1837 "CrossMap is a program for conversion of genome coordinates or annotation
1838 files between different genome assemblies. It supports most commonly used
1839 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1840 (license license:gpl2+)))
1842 (define-public cutadapt
1849 "https://github.com/marcelm/cutadapt/archive/v"
1851 (file-name (string-append name "-" version ".tar.gz"))
1854 "16gbpiwy4m48vq2h5wqar3i8vr6vcj9gcl2qvqim19x6ya9dp8kd"))))
1855 (build-system python-build-system)
1858 (modify-phases %standard-phases
1859 ;; The tests must be run after installation.
1861 (add-after 'install 'check
1862 (lambda* (#:key inputs outputs #:allow-other-keys)
1863 (setenv "PYTHONPATH"
1865 (getenv "PYTHONPATH")
1866 ":" (assoc-ref outputs "out")
1868 (string-take (string-take-right
1869 (assoc-ref inputs "python") 5) 3)
1871 (zero? (system* "nosetests" "-P" "tests")))))))
1873 `(("python-xopen" ,python-xopen)))
1875 `(("python-cython" ,python-cython)
1876 ("python-nose" ,python-nose)))
1877 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1878 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1880 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1881 other types of unwanted sequence from high-throughput sequencing reads.")
1882 (license license:expat)))
1884 (define-public libbigwig
1890 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1891 "archive/" version ".tar.gz"))
1892 (file-name (string-append name "-" version ".tar.gz"))
1895 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1896 (build-system gnu-build-system)
1898 `(#:test-target "test"
1901 (string-append "prefix=" (assoc-ref %outputs "out")))
1903 (modify-phases %standard-phases
1905 (add-before 'check 'disable-curl-test
1907 (substitute* "Makefile"
1908 (("./test/testRemote.*") ""))
1910 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1911 ;; there has not yet been a release containing this change.
1912 (add-before 'install 'create-target-dirs
1913 (lambda* (#:key outputs #:allow-other-keys)
1914 (let ((out (assoc-ref outputs "out")))
1915 (mkdir-p (string-append out "/lib"))
1916 (mkdir-p (string-append out "/include"))
1922 `(("doxygen" ,doxygen)))
1923 (home-page "https://github.com/dpryan79/libBigWig")
1924 (synopsis "C library for handling bigWig files")
1926 "This package provides a C library for parsing local and remote BigWig
1928 (license license:expat)))
1930 (define-public python-pybigwig
1932 (name "python-pybigwig")
1936 (uri (pypi-uri "pyBigWig" version))
1939 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1940 (modules '((guix build utils)))
1943 ;; Delete bundled libBigWig sources
1944 (delete-file-recursively "libBigWig")))))
1945 (build-system python-build-system)
1948 (modify-phases %standard-phases
1949 (add-after 'unpack 'link-with-libBigWig
1950 (lambda* (#:key inputs #:allow-other-keys)
1951 (substitute* "setup.py"
1952 (("libs=\\[") "libs=[\"BigWig\", "))
1955 `(("libbigwig" ,libbigwig)
1958 (home-page "https://github.com/dpryan79/pyBigWig")
1959 (synopsis "Access bigWig files in Python using libBigWig")
1961 "This package provides Python bindings to the libBigWig library for
1962 accessing bigWig files.")
1963 (license license:expat)))
1965 (define-public python2-pybigwig
1966 (package-with-python2 python-pybigwig))
1968 (define-public python-dendropy
1970 (name "python-dendropy")
1975 (uri (pypi-uri "DendroPy" version))
1978 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1979 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1980 (build-system python-build-system)
1981 (home-page "http://packages.python.org/DendroPy/")
1982 (synopsis "Library for phylogenetics and phylogenetic computing")
1984 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1985 writing, simulation, processing and manipulation of phylogenetic
1986 trees (phylogenies) and characters.")
1987 (license license:bsd-3)
1988 (properties `((python2-variant . ,(delay python2-dendropy))))))
1990 (define-public python2-dendropy
1991 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1995 `(#:python ,python-2
1997 (modify-phases %standard-phases
1999 ;; There is currently a test failure that only happens on some
2000 ;; systems, and only using "setup.py test"
2001 (lambda _ (zero? (system* "nosetests")))))))
2002 (native-inputs `(("python2-nose" ,python2-nose)
2003 ,@(package-native-inputs base))))))
2005 (define-public python-py2bit
2007 (name "python-py2bit")
2012 (uri (pypi-uri "py2bit" version))
2015 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2016 (build-system python-build-system)
2017 (home-page "https://github.com/dpryan79/py2bit")
2018 (synopsis "Access 2bit files using lib2bit")
2020 "This package provides Python bindings for lib2bit to access 2bit files
2022 (license license:expat)))
2024 (define-public deeptools
2030 (uri (string-append "https://github.com/fidelram/deepTools/"
2031 "archive/" version ".tar.gz"))
2032 (file-name (string-append name "-" version ".tar.gz"))
2035 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2036 (build-system python-build-system)
2038 `(("python-scipy" ,python-scipy)
2039 ("python-numpy" ,python-numpy)
2040 ("python-numpydoc" ,python-numpydoc)
2041 ("python-matplotlib" ,python-matplotlib)
2042 ("python-pysam" ,python-pysam)
2043 ("python-py2bit" ,python-py2bit)
2044 ("python-pybigwig" ,python-pybigwig)))
2046 `(("python-mock" ,python-mock) ;for tests
2047 ("python-nose" ,python-nose) ;for tests
2048 ("python-pytz" ,python-pytz))) ;for tests
2049 (home-page "https://github.com/fidelram/deepTools")
2050 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2052 "DeepTools addresses the challenge of handling the large amounts of data
2053 that are now routinely generated from DNA sequencing centers. To do so,
2054 deepTools contains useful modules to process the mapped reads data to create
2055 coverage files in standard bedGraph and bigWig file formats. By doing so,
2056 deepTools allows the creation of normalized coverage files or the comparison
2057 between two files (for example, treatment and control). Finally, using such
2058 normalized and standardized files, multiple visualizations can be created to
2059 identify enrichments with functional annotations of the genome.")
2060 (license license:gpl3+)))
2062 (define-public diamond
2069 "https://github.com/bbuchfink/diamond/archive/v"
2071 (file-name (string-append name "-" version ".tar.gz"))
2074 "1pi5ncqwmynqpmmp3j3lhnqrjhj34sr6wpmsgrpkv3wyxx22fv86"))))
2075 (build-system cmake-build-system)
2077 '(#:tests? #f ; no "check" target
2079 (modify-phases %standard-phases
2080 (add-after 'unpack 'remove-native-compilation
2082 (substitute* "CMakeLists.txt" (("-march=native") ""))
2086 (home-page "https://github.com/bbuchfink/diamond")
2087 (synopsis "Accelerated BLAST compatible local sequence aligner")
2089 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2090 translated DNA query sequences against a protein reference database (BLASTP
2091 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2092 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2093 data and settings.")
2094 (license license:agpl3+)))
2096 (define-public discrover
2103 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2105 (file-name (string-append name "-" version ".tar.gz"))
2108 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2109 (build-system cmake-build-system)
2111 `(#:tests? #f ; there are no tests
2113 (modify-phases %standard-phases
2114 (add-after 'unpack 'add-missing-includes
2116 (substitute* "src/executioninformation.hpp"
2117 (("#define EXECUTIONINFORMATION_HPP" line)
2118 (string-append line "\n#include <random>")))
2119 (substitute* "src/plasma/fasta.hpp"
2120 (("#define FASTA_HPP" line)
2121 (string-append line "\n#include <random>")))
2127 `(("texlive" ,texlive)
2128 ("imagemagick" ,imagemagick)))
2129 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2130 (synopsis "Discover discriminative nucleotide sequence motifs")
2131 (description "Discrover is a motif discovery method to find binding sites
2132 of nucleic acid binding proteins.")
2133 (license license:gpl3+)))
2135 (define-public eigensoft
2136 (let ((revision "1")
2137 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2140 (version (string-append "6.1.2-"
2142 (string-take commit 9)))
2147 (url "https://github.com/DReichLab/EIG.git")
2149 (file-name (string-append "eigensoft-" commit "-checkout"))
2152 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2153 (modules '((guix build utils)))
2154 ;; Remove pre-built binaries.
2156 (delete-file-recursively "bin")
2159 (build-system gnu-build-system)
2161 `(#:tests? #f ; There are no tests.
2162 #:make-flags '("CC=gcc")
2164 (modify-phases %standard-phases
2165 ;; There is no configure phase, but the Makefile is in a
2170 ;; The link flags are incomplete.
2171 (substitute* "Makefile"
2172 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2174 ;; The provided install target only copies executables to
2175 ;; the "bin" directory in the build root.
2176 (add-after 'install 'actually-install
2177 (lambda* (#:key outputs #:allow-other-keys)
2178 (let* ((out (assoc-ref outputs "out"))
2179 (bin (string-append out "/bin")))
2180 (for-each (lambda (file)
2181 (install-file file bin))
2182 (find-files "../bin" ".*"))
2187 ("openblas" ,openblas)
2189 ("gfortran" ,gfortran "lib")))
2190 (home-page "https://github.com/DReichLab/EIG")
2191 (synopsis "Tools for population genetics")
2192 (description "The EIGENSOFT package provides tools for population
2193 genetics and stratification correction. EIGENSOFT implements methods commonly
2194 used in population genetics analyses such as PCA, computation of Tracy-Widom
2195 statistics, and finding related individuals in structured populations. It
2196 comes with a built-in plotting script and supports multiple file formats and
2197 quantitative phenotypes.")
2198 ;; The license of the eigensoft tools is Expat, but since it's
2199 ;; linking with the GNU Scientific Library (GSL) the effective
2200 ;; license is the GPL.
2201 (license license:gpl3+))))
2203 (define-public edirect
2209 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2210 "versions/2016-05-03/edirect.tar.gz"))
2213 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2214 (build-system perl-build-system)
2216 `(#:tests? #f ;no "check" target
2218 (modify-phases %standard-phases
2222 (lambda* (#:key outputs #:allow-other-keys)
2223 (let ((target (string-append (assoc-ref outputs "out")
2226 (install-file "edirect.pl" target)
2229 'install 'wrap-program
2230 (lambda* (#:key inputs outputs #:allow-other-keys)
2231 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2232 (let* ((out (assoc-ref outputs "out"))
2233 (path (getenv "PERL5LIB")))
2234 (wrap-program (string-append out "/bin/edirect.pl")
2235 `("PERL5LIB" ":" prefix (,path)))))))))
2237 `(("perl-html-parser" ,perl-html-parser)
2238 ("perl-encode-locale" ,perl-encode-locale)
2239 ("perl-file-listing" ,perl-file-listing)
2240 ("perl-html-tagset" ,perl-html-tagset)
2241 ("perl-html-tree" ,perl-html-tree)
2242 ("perl-http-cookies" ,perl-http-cookies)
2243 ("perl-http-date" ,perl-http-date)
2244 ("perl-http-message" ,perl-http-message)
2245 ("perl-http-negotiate" ,perl-http-negotiate)
2246 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2247 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2248 ("perl-net-http" ,perl-net-http)
2249 ("perl-uri" ,perl-uri)
2250 ("perl-www-robotrules" ,perl-www-robotrules)
2252 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2253 (synopsis "Tools for accessing the NCBI's set of databases")
2255 "Entrez Direct (EDirect) is a method for accessing the National Center
2256 for Biotechnology Information's (NCBI) set of interconnected
2257 databases (publication, sequence, structure, gene, variation, expression,
2258 etc.) from a terminal. Functions take search terms from command-line
2259 arguments. Individual operations are combined to build multi-step queries.
2260 Record retrieval and formatting normally complete the process.
2262 EDirect also provides an argument-driven function that simplifies the
2263 extraction of data from document summaries or other results that are returned
2264 in structured XML format. This can eliminate the need for writing custom
2265 software to answer ad hoc questions.")
2266 (license license:public-domain)))
2268 (define-public exonerate
2277 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2278 "exonerate-" version ".tar.gz"))
2281 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2282 (build-system gnu-build-system)
2284 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2286 `(("pkg-config" ,pkg-config)))
2290 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2291 (synopsis "Generic tool for biological sequence alignment")
2293 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2294 the alignment of sequences using a many alignment models, either exhaustive
2295 dynamic programming or a variety of heuristics.")
2296 (license license:gpl3)))
2298 (define-public express
2306 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2307 version "/express-" version "-src.tgz"))
2310 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2311 (build-system cmake-build-system)
2313 `(#:tests? #f ;no "check" target
2315 (modify-phases %standard-phases
2316 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2317 (lambda* (#:key inputs #:allow-other-keys)
2318 (substitute* "CMakeLists.txt"
2319 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2320 "set(Boost_USE_STATIC_LIBS OFF)")
2321 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2322 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2323 (substitute* "src/CMakeLists.txt"
2324 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2325 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2329 ("bamtools" ,bamtools)
2330 ("protobuf" ,protobuf)
2332 (home-page "http://bio.math.berkeley.edu/eXpress")
2333 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2335 "eXpress is a streaming tool for quantifying the abundances of a set of
2336 target sequences from sampled subsequences. Example applications include
2337 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2338 analysis (from RNA-Seq), transcription factor binding quantification in
2339 ChIP-Seq, and analysis of metagenomic data.")
2340 (license license:artistic2.0)))
2342 (define-public express-beta-diversity
2344 (name "express-beta-diversity")
2350 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2352 (file-name (string-append name "-" version ".tar.gz"))
2355 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2356 (build-system gnu-build-system)
2359 (modify-phases %standard-phases
2361 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2363 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2365 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2367 (lambda* (#:key outputs #:allow-other-keys)
2368 (let ((bin (string-append (assoc-ref outputs "out")
2371 (install-file "scripts/convertToEBD.py" bin)
2372 (install-file "bin/ExpressBetaDiversity" bin)
2375 `(("python" ,python-2)))
2376 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2377 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2379 "Express Beta Diversity (EBD) calculates ecological beta diversity
2380 (dissimilarity) measures between biological communities. EBD implements a
2381 variety of diversity measures including those that make use of phylogenetic
2382 similarity of community members.")
2383 (license license:gpl3+)))
2385 (define-public fasttree
2392 "http://www.microbesonline.org/fasttree/FastTree-"
2396 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2397 (build-system gnu-build-system)
2399 `(#:tests? #f ; no "check" target
2401 (modify-phases %standard-phases
2405 (lambda* (#:key source #:allow-other-keys)
2406 (and (zero? (system* "gcc"
2408 "-finline-functions"
2415 (zero? (system* "gcc"
2419 "-finline-functions"
2427 (lambda* (#:key outputs #:allow-other-keys)
2428 (let ((bin (string-append (assoc-ref outputs "out")
2431 (install-file "FastTree" bin)
2432 (install-file "FastTreeMP" bin)
2434 (home-page "http://www.microbesonline.org/fasttree")
2435 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2437 "FastTree can handle alignments with up to a million of sequences in a
2438 reasonable amount of time and memory. For large alignments, FastTree is
2439 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2440 (license license:gpl2+)))
2442 (define-public fastx-toolkit
2444 (name "fastx-toolkit")
2450 "https://github.com/agordon/fastx_toolkit/releases/download/"
2451 version "/fastx_toolkit-" version ".tar.bz2"))
2454 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2455 (build-system gnu-build-system)
2457 `(("libgtextutils" ,libgtextutils)))
2459 `(("pkg-config" ,pkg-config)))
2460 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2461 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2463 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2464 FASTA/FASTQ files preprocessing.
2466 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2467 containing multiple short-reads sequences. The main processing of such
2468 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2469 is sometimes more productive to preprocess the files before mapping the
2470 sequences to the genome---manipulating the sequences to produce better mapping
2471 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2472 (license license:agpl3+)))
2474 (define-public flexbar
2481 (string-append "mirror://sourceforge/flexbar/"
2482 version "/flexbar_v" version "_src.tgz"))
2485 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2486 (build-system cmake-build-system)
2488 `(#:configure-flags (list
2489 (string-append "-DFLEXBAR_BINARY_DIR="
2490 (assoc-ref %outputs "out")
2493 (modify-phases %standard-phases
2495 (lambda* (#:key outputs #:allow-other-keys)
2496 (setenv "PATH" (string-append
2497 (assoc-ref outputs "out") "/bin:"
2499 (chdir "../flexbar_v2.5_src/test")
2500 (zero? (system* "bash" "flexbar_validate.sh"))))
2501 (delete 'install))))
2506 `(("pkg-config" ,pkg-config)
2508 (home-page "http://flexbar.sourceforge.net")
2509 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2511 "Flexbar preprocesses high-throughput nucleotide sequencing data
2512 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2513 Moreover, trimming and filtering features are provided. Flexbar increases
2514 read mapping rates and improves genome and transcriptome assemblies. It
2515 supports next-generation sequencing data in fasta/q and csfasta/q format from
2516 Illumina, Roche 454, and the SOLiD platform.")
2517 (license license:gpl3)))
2519 (define-public fraggenescan
2521 (name "fraggenescan")
2527 (string-append "mirror://sourceforge/fraggenescan/"
2528 "FragGeneScan" version ".tar.gz"))
2530 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2531 (build-system gnu-build-system)
2534 (modify-phases %standard-phases
2536 (add-before 'build 'patch-paths
2537 (lambda* (#:key outputs #:allow-other-keys)
2538 (let* ((out (string-append (assoc-ref outputs "out")))
2539 (share (string-append out "/share/fraggenescan/")))
2540 (substitute* "run_FragGeneScan.pl"
2542 (string-append "system(\"" (which "rm")))
2544 (string-append "system(\"" (which "mv")))
2545 (("\\\"awk") (string-append "\"" (which "awk")))
2546 ;; This script and other programs expect the training files
2547 ;; to be in the non-standard location bin/train/XXX. Change
2548 ;; this to be share/fraggenescan/train/XXX instead.
2549 (("^\\$train.file = \\$dir.*")
2550 (string-append "$train_file = \""
2552 "train/\".$FGS_train_file;")))
2553 (substitute* "run_hmm.c"
2554 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2555 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2558 (lambda _ (and (zero? (system* "make" "clean"))
2559 (zero? (system* "make" "fgs")))))
2561 (lambda* (#:key outputs #:allow-other-keys)
2562 (let* ((out (string-append (assoc-ref outputs "out")))
2563 (bin (string-append out "/bin/"))
2564 (share (string-append out "/share/fraggenescan/train")))
2565 (install-file "run_FragGeneScan.pl" bin)
2566 (install-file "FragGeneScan" bin)
2567 (copy-recursively "train" share))))
2569 (add-after 'install 'post-install-check
2570 ;; In lieu of 'make check', run one of the examples and check the
2571 ;; output files gets created.
2572 (lambda* (#:key outputs #:allow-other-keys)
2573 (let* ((out (string-append (assoc-ref outputs "out")))
2574 (bin (string-append out "/bin/"))
2575 (frag (string-append bin "run_FragGeneScan.pl")))
2576 (and (zero? (system* frag ; Test complete genome.
2577 "-genome=./example/NC_000913.fna"
2581 (file-exists? "test2.faa")
2582 (file-exists? "test2.ffn")
2583 (file-exists? "test2.gff")
2584 (file-exists? "test2.out")
2585 (zero? (system* ; Test incomplete sequences.
2587 "-genome=./example/NC_000913-fgs.ffn"
2590 "-train=454_30")))))))))
2593 ("python" ,python-2))) ;not compatible with python 3.
2594 (home-page "https://sourceforge.net/projects/fraggenescan/")
2595 (synopsis "Finds potentially fragmented genes in short reads")
2597 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2598 short and error-prone DNA sequencing reads. It can also be applied to predict
2599 genes in incomplete assemblies or complete genomes.")
2600 ;; GPL3+ according to private correspondense with the authors.
2601 (license license:gpl3+)))
2603 (define-public fxtract
2604 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2612 "https://github.com/ctSkennerton/fxtract/archive/"
2614 (file-name (string-append "ctstennerton-util-"
2615 (string-take util-commit 7)
2619 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2620 (build-system gnu-build-system)
2622 `(#:make-flags (list
2623 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2625 #:test-target "fxtract_test"
2627 (modify-phases %standard-phases
2629 (add-before 'build 'copy-util
2630 (lambda* (#:key inputs #:allow-other-keys)
2632 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2634 ;; Do not use make install as this requires additional dependencies.
2636 (lambda* (#:key outputs #:allow-other-keys)
2637 (let* ((out (assoc-ref outputs "out"))
2638 (bin (string-append out"/bin")))
2639 (install-file "fxtract" bin)
2645 ;; ctskennerton-util is licensed under GPL2.
2646 `(("ctskennerton-util"
2650 (url "https://github.com/ctSkennerton/util.git")
2651 (commit util-commit)))
2652 (file-name (string-append
2653 "ctstennerton-util-" util-commit "-checkout"))
2656 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2657 (home-page "https://github.com/ctSkennerton/fxtract")
2658 (synopsis "Extract sequences from FASTA and FASTQ files")
2660 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2661 or FASTQ) file given a subsequence. It uses a simple substring search for
2662 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2663 lookups or multi-pattern searching as required. By default fxtract looks in
2664 the sequence of each record but can also be told to look in the header,
2665 comment or quality sections.")
2666 ;; 'util' requires SSE instructions.
2667 (supported-systems '("x86_64-linux"))
2668 (license license:expat))))
2670 (define-public gemma
2676 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2678 (file-name (string-append name "-" version ".tar.gz"))
2681 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2682 (patches (search-patches "gemma-intel-compat.patch"))))
2687 (build-system gnu-build-system)
2690 '(,@(match (%current-system)
2692 '("FORCE_DYNAMIC=1"))
2694 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2696 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2698 (modify-phases %standard-phases
2700 (add-before 'build 'bin-mkdir
2705 (lambda* (#:key outputs #:allow-other-keys)
2706 (let ((out (assoc-ref outputs "out")))
2707 (install-file "bin/gemma"
2711 #:tests? #f)) ; no tests included yet
2712 (home-page "https://github.com/xiangzhou/GEMMA")
2713 (synopsis "Tool for genome-wide efficient mixed model association")
2715 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2716 standard linear mixed model resolver with application in genome-wide
2717 association studies (GWAS).")
2718 (license license:gpl3)))
2727 "https://github.com/nboley/grit/archive/"
2729 (file-name (string-append name "-" version ".tar.gz"))
2732 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2733 (build-system python-build-system)
2735 `(#:python ,python-2
2737 (modify-phases %standard-phases
2738 (add-after 'unpack 'generate-from-cython-sources
2739 (lambda* (#:key inputs outputs #:allow-other-keys)
2740 ;; Delete these C files to force fresh generation from pyx sources.
2741 (delete-file "grit/sparsify_support_fns.c")
2742 (delete-file "grit/call_peaks_support_fns.c")
2743 (substitute* "setup.py"
2744 (("Cython.Setup") "Cython.Build")
2745 ;; Add numpy include path to fix compilation
2747 (string-append "pyx\", ], include_dirs = ['"
2748 (assoc-ref inputs "python-numpy")
2749 "/lib/python2.7/site-packages/numpy/core/include/"
2753 `(("python-scipy" ,python2-scipy)
2754 ("python-numpy" ,python2-numpy)
2755 ("python-pysam" ,python2-pysam)
2756 ("python-networkx" ,python2-networkx)))
2758 `(("python-cython" ,python2-cython)))
2759 (home-page "http://grit-bio.org")
2760 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2762 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2763 full length transcript models. When none of these data sources are available,
2764 GRIT can be run by providing a candidate set of TES or TSS sites. In
2765 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2766 also be run in quantification mode, where it uses a provided GTF file and just
2767 estimates transcript expression.")
2768 (license license:gpl3+)))
2770 (define-public hisat
2777 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2778 version "-beta-source.zip"))
2781 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2782 (build-system gnu-build-system)
2784 `(#:tests? #f ;no check target
2785 #:make-flags '("allall"
2786 ;; Disable unsupported `popcnt' instructions on
2787 ;; architectures other than x86_64
2788 ,@(if (string-prefix? "x86_64"
2789 (or (%current-target-system)
2792 '("POPCNT_CAPABILITY=0")))
2794 (modify-phases %standard-phases
2795 (add-after 'unpack 'patch-sources
2797 ;; XXX Cannot use snippet because zip files are not supported
2798 (substitute* "Makefile"
2799 (("^CC = .*$") "CC = gcc")
2800 (("^CPP = .*$") "CPP = g++")
2801 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2802 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2803 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2804 (substitute* '("hisat-build" "hisat-inspect")
2805 (("/usr/bin/env") (which "env")))
2808 (lambda* (#:key outputs #:allow-other-keys)
2809 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2810 (for-each (lambda (file)
2811 (install-file file bin))
2814 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2816 (delete 'configure))))
2818 `(("unzip" ,unzip)))
2823 ;; Non-portable SSE instructions are used so building fails on platforms
2824 ;; other than x86_64.
2825 (supported-systems '("x86_64-linux"))
2826 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2827 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2829 "HISAT is a fast and sensitive spliced alignment program for mapping
2830 RNA-seq reads. In addition to one global FM index that represents a whole
2831 genome, HISAT uses a large set of small FM indexes that collectively cover the
2832 whole genome. These small indexes (called local indexes) combined with
2833 several alignment strategies enable effective alignment of RNA-seq reads, in
2834 particular, reads spanning multiple exons.")
2835 (license license:gpl3+)))
2837 (define-public hisat2
2844 ;; FIXME: a better source URL is
2845 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2846 ;; "/downloads/hisat2-" version "-source.zip")
2847 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2848 ;; but it is currently unavailable.
2849 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2850 (file-name (string-append name "-" version ".tar.gz"))
2853 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2854 (build-system gnu-build-system)
2856 `(#:tests? #f ; no check target
2857 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2858 #:modules ((guix build gnu-build-system)
2862 (modify-phases %standard-phases
2863 (add-after 'unpack 'make-deterministic
2865 (substitute* "Makefile"
2870 (lambda* (#:key outputs #:allow-other-keys)
2871 (let* ((out (assoc-ref outputs "out"))
2872 (bin (string-append out "/bin/"))
2873 (doc (string-append out "/share/doc/hisat2/")))
2875 (cut install-file <> bin)
2877 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2879 (install-file "doc/manual.inc.html" doc))
2882 `(("unzip" ,unzip) ; needed for archive from ftp
2884 ("pandoc" ,ghc-pandoc))) ; for documentation
2885 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2886 (synopsis "Graph-based alignment of genomic sequencing reads")
2887 (description "HISAT2 is a fast and sensitive alignment program for mapping
2888 next-generation sequencing reads (both DNA and RNA) to a population of human
2889 genomes (as well as to a single reference genome). In addition to using one
2890 global @dfn{graph FM} (GFM) index that represents a population of human
2891 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2892 the whole genome. These small indexes, combined with several alignment
2893 strategies, enable rapid and accurate alignment of sequencing reads. This new
2894 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2895 ;; HISAT2 contains files from Bowtie2, which is released under
2896 ;; GPLv2 or later. The HISAT2 source files are released under
2898 (license license:gpl3+)))
2900 (define-public hmmer
2908 "http://eddylab.org/software/hmmer"
2909 (version-prefix version 1) "/"
2910 version "/hmmer-" version ".tar.gz"))
2913 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2914 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2915 (build-system gnu-build-system)
2916 (native-inputs `(("perl" ,perl)))
2917 (home-page "http://hmmer.org/")
2918 (synopsis "Biosequence analysis using profile hidden Markov models")
2920 "HMMER is used for searching sequence databases for homologs of protein
2921 sequences, and for making protein sequence alignments. It implements methods
2922 using probabilistic models called profile hidden Markov models (profile
2924 (license (list license:gpl3+
2925 ;; The bundled library 'easel' is distributed
2926 ;; under The Janelia Farm Software License.
2927 (license:non-copyleft
2928 "file://easel/LICENSE"
2929 "See easel/LICENSE in the distribution.")))))
2931 (define-public htseq
2937 (uri (pypi-uri "HTSeq" version))
2940 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2941 (build-system python-build-system)
2943 `(("python-cython" ,python-cython)))
2944 ;; Numpy needs to be propagated when htseq is used as a Python library.
2946 `(("python-numpy" ,python-numpy)))
2948 `(("python-pysam" ,python-pysam)
2949 ("python-matplotlib" ,python-matplotlib)))
2950 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2951 (synopsis "Analysing high-throughput sequencing data with Python")
2953 "HTSeq is a Python package that provides infrastructure to process data
2954 from high-throughput sequencing assays.")
2955 (license license:gpl3+)))
2957 (define-public python2-htseq
2958 (package-with-python2 htseq))
2960 (define-public java-htsjdk
2962 (name "java-htsjdk")
2967 "https://github.com/samtools/htsjdk/archive/"
2969 (file-name (string-append name "-" version ".tar.gz"))
2972 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2973 (modules '((guix build utils)))
2974 ;; remove build dependency on git
2975 (snippet '(substitute* "build.xml"
2976 (("failifexecutionfails=\"true\"")
2977 "failifexecutionfails=\"false\"")))))
2978 (build-system ant-build-system)
2980 `(#:tests? #f ; test require Internet access
2982 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2983 "/share/java/htsjdk/"))
2984 #:build-target "all"
2986 (modify-phases %standard-phases
2987 ;; The build phase also installs the jars
2988 (delete 'install))))
2989 (home-page "http://samtools.github.io/htsjdk/")
2990 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2992 "HTSJDK is an implementation of a unified Java library for accessing
2993 common file formats, such as SAM and VCF, used for high-throughput
2994 sequencing (HTS) data. There are also an number of useful utilities for
2995 manipulating HTS data.")
2996 (license license:expat)))
2998 (define-public htslib
3005 "https://github.com/samtools/htslib/releases/download/"
3006 version "/htslib-" version ".tar.bz2"))
3009 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3010 (build-system gnu-build-system)
3013 (modify-phases %standard-phases
3015 'unpack 'patch-tests
3017 (substitute* "test/test.pl"
3018 (("/bin/bash") (which "bash")))
3021 `(("openssl" ,openssl)
3026 (home-page "http://www.htslib.org")
3027 (synopsis "C library for reading/writing high-throughput sequencing data")
3029 "HTSlib is a C library for reading/writing high-throughput sequencing
3030 data. It also provides the bgzip, htsfile, and tabix utilities.")
3031 ;; Files under cram/ are released under the modified BSD license;
3032 ;; the rest is released under the Expat license
3033 (license (list license:expat license:bsd-3))))
3035 ;; This package should be removed once no packages rely upon it.
3043 "https://github.com/samtools/htslib/releases/download/"
3044 version "/htslib-" version ".tar.bz2"))
3047 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3056 "https://github.com/nboley/idr/archive/"
3058 (file-name (string-append name "-" version ".tar.gz"))
3061 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3062 (build-system python-build-system)
3064 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3066 `(("python-scipy" ,python-scipy)
3067 ("python-sympy" ,python-sympy)
3068 ("python-numpy" ,python-numpy)
3069 ("python-matplotlib" ,python-matplotlib)))
3071 `(("python-cython" ,python-cython)))
3072 (home-page "https://github.com/nboley/idr")
3073 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3075 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3076 to measure the reproducibility of findings identified from replicate
3077 experiments and provide highly stable thresholds based on reproducibility.")
3078 (license license:gpl3+)))
3080 (define-public jellyfish
3086 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3087 "releases/download/v" version
3088 "/jellyfish-" version ".tar.gz"))
3091 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3092 (build-system gnu-build-system)
3093 (outputs '("out" ;for library
3094 "ruby" ;for Ruby bindings
3095 "python")) ;for Python bindings
3098 (list (string-append "--enable-ruby-binding="
3099 (assoc-ref %outputs "ruby"))
3100 (string-append "--enable-python-binding="
3101 (assoc-ref %outputs "python")))
3103 (modify-phases %standard-phases
3104 (add-before 'check 'set-SHELL-variable
3106 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3108 (setenv "SHELL" (which "bash"))
3114 ("python" ,python-2)))
3115 (synopsis "Tool for fast counting of k-mers in DNA")
3117 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3118 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3119 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3120 is a command-line program that reads FASTA and multi-FASTA files containing
3121 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3122 translated into a human-readable text format using the @code{jellyfish dump}
3123 command, or queried for specific k-mers with @code{jellyfish query}.")
3124 (home-page "http://www.genome.umd.edu/jellyfish.html")
3125 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3126 (supported-systems '("x86_64-linux"))
3127 ;; The combined work is published under the GPLv3 or later. Individual
3128 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3129 (license (list license:gpl3+ license:expat))))
3131 (define-public khmer
3138 (uri (pypi-uri "khmer" version))
3141 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3142 (patches (search-patches "khmer-use-libraries.patch"))))
3143 (build-system python-build-system)
3146 (modify-phases %standard-phases
3147 (add-after 'unpack 'set-paths
3148 (lambda* (#:key inputs outputs #:allow-other-keys)
3149 ;; Delete bundled libraries.
3150 (delete-file-recursively "third-party/zlib")
3151 (delete-file-recursively "third-party/bzip2")
3152 ;; Replace bundled seqan.
3153 (let* ((seqan-all "third-party/seqan")
3154 (seqan-include (string-append
3155 seqan-all "/core/include")))
3156 (delete-file-recursively seqan-all)
3157 (copy-recursively (string-append (assoc-ref inputs "seqan")
3159 (string-append seqan-include "/seqan")))
3160 ;; We do not replace the bundled MurmurHash as the canonical
3161 ;; repository for this code 'SMHasher' is unsuitable for
3162 ;; providing a library. See
3163 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3165 (add-after 'unpack 'set-cc
3169 ;; It is simpler to test after installation.
3171 (add-after 'install 'post-install-check
3172 (lambda* (#:key inputs outputs #:allow-other-keys)
3173 (let ((out (assoc-ref outputs "out")))
3178 (assoc-ref outputs "out")
3180 (setenv "PYTHONPATH"
3182 (getenv "PYTHONPATH")
3186 (string-take (string-take-right
3187 (assoc-ref inputs "python") 5) 3)
3189 (with-directory-excursion "build"
3190 (zero? (system* "nosetests" "khmer" "--attr"
3191 "!known_failing")))))))))
3194 ("python-nose" ,python-nose)))
3198 ("python-screed" ,python-screed)
3199 ("python-bz2file" ,python-bz2file)
3200 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3201 ;; until the next version of khmer (likely 2.1) is released.
3203 (home-page "https://khmer.readthedocs.org/")
3204 (synopsis "K-mer counting, filtering and graph traversal library")
3205 (description "The khmer software is a set of command-line tools for
3206 working with DNA shotgun sequencing data from genomes, transcriptomes,
3207 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3208 sometimes better. Khmer can also identify and fix problems with shotgun
3210 ;; When building on i686, armhf and mips64el, we get the following error:
3211 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3212 (supported-systems '("x86_64-linux"))
3213 (license license:bsd-3)))
3215 (define-public kaiju
3222 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3224 (file-name (string-append name "-" version ".tar.gz"))
3227 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3228 (build-system gnu-build-system)
3230 `(#:tests? #f ; There are no tests.
3232 (modify-phases %standard-phases
3234 (add-before 'build 'move-to-src-dir
3235 (lambda _ (chdir "src") #t))
3237 (lambda* (#:key inputs outputs #:allow-other-keys)
3238 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3241 (copy-recursively "bin" bin)
3242 (copy-recursively "util" bin))
3246 (home-page "http://kaiju.binf.ku.dk/")
3247 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3248 (description "Kaiju is a program for sensitive taxonomic classification
3249 of high-throughput sequencing reads from metagenomic whole genome sequencing
3251 (license license:gpl3+)))
3256 (version "2.1.0.20151222")
3259 (uri (pypi-uri "MACS2" version))
3262 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3263 (build-system python-build-system)
3265 `(#:python ,python-2 ; only compatible with Python 2.7
3266 #:tests? #f)) ; no test target
3268 `(("python-numpy" ,python2-numpy)))
3269 (home-page "https://github.com/taoliu/MACS/")
3270 (synopsis "Model based analysis for ChIP-Seq data")
3272 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3273 identifying transcript factor binding sites named Model-based Analysis of
3274 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3275 the significance of enriched ChIP regions and it improves the spatial
3276 resolution of binding sites through combining the information of both
3277 sequencing tag position and orientation.")
3278 (license license:bsd-3)))
3280 (define-public mafft
3287 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3288 "-without-extensions-src.tgz"))
3289 (file-name (string-append name "-" version ".tgz"))
3292 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3293 (build-system gnu-build-system)
3295 `(#:tests? #f ; no automated tests, though there are tests in the read me
3296 #:make-flags (let ((out (assoc-ref %outputs "out")))
3297 (list (string-append "PREFIX=" out)
3298 (string-append "BINDIR="
3299 (string-append out "/bin"))))
3301 (modify-phases %standard-phases
3302 (add-after 'unpack 'enter-dir
3303 (lambda _ (chdir "core") #t))
3304 (add-after 'enter-dir 'patch-makefile
3306 ;; on advice from the MAFFT authors, there is no need to
3307 ;; distribute mafft-profile, mafft-distance, or
3308 ;; mafft-homologs.rb as they are too "specialised".
3309 (substitute* "Makefile"
3310 ;; remove mafft-homologs.rb from SCRIPTS
3311 (("^SCRIPTS = mafft mafft-homologs.rb")
3313 ;; remove mafft-homologs from MANPAGES
3314 (("^MANPAGES = mafft.1 mafft-homologs.1")
3315 "MANPAGES = mafft.1")
3316 ;; remove mafft-distance from PROGS
3317 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3318 "PROGS = dvtditr dndfast7 dndblast sextet5")
3319 ;; remove mafft-profile from PROGS
3320 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3321 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3322 (("^rm -f mafft-profile mafft-profile.exe") "#")
3323 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3324 ;; do not install MAN pages in libexec folder
3325 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3326 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3328 (add-after 'enter-dir 'patch-paths
3329 (lambda* (#:key inputs #:allow-other-keys)
3330 (substitute* '("pairash.c"
3332 (("perl") (which "perl"))
3333 (("([\"`| ])awk" _ prefix)
3334 (string-append prefix (which "awk")))
3335 (("grep") (which "grep")))
3338 (add-after 'install 'wrap-programs
3339 (lambda* (#:key outputs #:allow-other-keys)
3340 (let* ((out (assoc-ref outputs "out"))
3341 (bin (string-append out "/bin"))
3342 (path (string-append
3343 (assoc-ref %build-inputs "coreutils") "/bin:")))
3344 (for-each (lambda (file)
3346 `("PATH" ":" prefix (,path))))
3354 ("coreutils" ,coreutils)))
3355 (home-page "http://mafft.cbrc.jp/alignment/software/")
3356 (synopsis "Multiple sequence alignment program")
3358 "MAFFT offers a range of multiple alignment methods for nucleotide and
3359 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3360 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3362 (license (license:non-copyleft
3363 "http://mafft.cbrc.jp/alignment/software/license.txt"
3364 "BSD-3 with different formatting"))))
3373 "https://github.com/marbl/mash/archive/v"
3375 (file-name (string-append name "-" version ".tar.gz"))
3378 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3379 (modules '((guix build utils)))
3381 ;; Delete bundled kseq.
3382 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3383 '(delete-file "src/mash/kseq.h"))))
3384 (build-system gnu-build-system)
3386 `(#:tests? #f ; No tests.
3389 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3390 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3391 #:make-flags (list "CC=gcc")
3393 (modify-phases %standard-phases
3394 (add-after 'unpack 'fix-includes
3396 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3397 (("^#include \"kseq\\.h\"")
3398 "#include \"htslib/kseq.h\""))
3400 (add-after 'fix-includes 'autoconf
3401 (lambda _ (zero? (system* "autoconf")))))))
3403 `(("autoconf" ,autoconf)
3404 ;; Capnproto and htslib are statically embedded in the final
3405 ;; application. Therefore we also list their licenses, below.
3406 ("capnproto" ,capnproto)
3407 ("htslib" ,htslib)))
3411 (supported-systems '("x86_64-linux"))
3412 (home-page "https://mash.readthedocs.io")
3413 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3414 (description "Mash is a fast sequence distance estimator that uses the
3415 MinHash algorithm and is designed to work with genomes and metagenomes in the
3416 form of assemblies or reads.")
3417 (license (list license:bsd-3 ; Mash
3418 license:expat ; HTSlib and capnproto
3419 license:public-domain ; MurmurHash 3
3420 license:cpl1.0)))) ; Open Bloom Filter
3422 (define-public metabat
3429 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3431 (file-name (string-append name "-" version ".tar.gz"))
3434 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3435 (patches (search-patches "metabat-fix-compilation.patch"))))
3436 (build-system gnu-build-system)
3439 (modify-phases %standard-phases
3440 (add-after 'unpack 'fix-includes
3442 (substitute* "src/BamUtils.h"
3443 (("^#include \"bam/bam\\.h\"")
3444 "#include \"samtools/bam.h\"")
3445 (("^#include \"bam/sam\\.h\"")
3446 "#include \"samtools/sam.h\""))
3447 (substitute* "src/KseqReader.h"
3448 (("^#include \"bam/kseq\\.h\"")
3449 "#include \"htslib/kseq.h\""))
3451 (add-after 'unpack 'fix-scons
3452 (lambda* (#:key inputs #:allow-other-keys)
3453 (substitute* "SConstruct"
3454 (("^htslib_dir += 'samtools'")
3455 (string-append "htslib_dir = '"
3456 (assoc-ref inputs "htslib")
3458 (("^samtools_dir = 'samtools'")
3459 (string-append "samtools_dir = '"
3460 (assoc-ref inputs "samtools")
3462 (("^findStaticOrShared\\('bam', hts_lib")
3463 (string-append "findStaticOrShared('bam', '"
3464 (assoc-ref inputs "samtools")
3466 ;; Do not distribute README.
3467 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3471 (lambda* (#:key inputs outputs #:allow-other-keys)
3472 (mkdir (assoc-ref outputs "out"))
3473 (zero? (system* "scons"
3476 (assoc-ref outputs "out"))
3479 (assoc-ref inputs "boost"))
3481 ;; Check and install are carried out during build phase.
3483 (delete 'install))))
3487 ("samtools" ,samtools)
3491 `(("scons" ,scons)))
3492 (home-page "https://bitbucket.org/berkeleylab/metabat")
3494 "Reconstruction of single genomes from complex microbial communities")
3496 "Grouping large genomic fragments assembled from shotgun metagenomic
3497 sequences to deconvolute complex microbial communities, or metagenome binning,
3498 enables the study of individual organisms and their interactions. MetaBAT is
3499 an automated metagenome binning software, which integrates empirical
3500 probabilistic distances of genome abundance and tetranucleotide frequency.")
3501 ;; The source code contains inline assembly.
3502 (supported-systems '("x86_64-linux" "i686-linux"))
3503 (license (license:non-copyleft "file://license.txt"
3504 "See license.txt in the distribution."))))
3506 (define-public minced
3513 "https://github.com/ctSkennerton/minced/archive/"
3515 (file-name (string-append name "-" version ".tar.gz"))
3518 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3519 (build-system gnu-build-system)
3521 `(#:test-target "test"
3523 (modify-phases %standard-phases
3525 (add-before 'check 'fix-test
3527 ;; Fix test for latest version.
3528 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3529 (("minced:0.1.6") "minced:0.2.0"))
3531 (replace 'install ; No install target.
3532 (lambda* (#:key inputs outputs #:allow-other-keys)
3533 (let* ((out (assoc-ref outputs "out"))
3534 (bin (string-append out "/bin"))
3535 (wrapper (string-append bin "/minced")))
3536 ;; Minced comes with a wrapper script that tries to figure out where
3537 ;; it is located before running the JAR. Since these paths are known
3538 ;; to us, we build our own wrapper to avoid coreutils dependency.
3539 (install-file "minced.jar" bin)
3540 (with-output-to-file wrapper
3544 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3545 (assoc-ref inputs "jre") "/bin/java -jar "
3546 bin "/minced.jar \"$@\"\n"))))
3547 (chmod wrapper #o555)))))))
3549 `(("jdk" ,icedtea "jdk")))
3552 ("jre" ,icedtea "out")))
3553 (home-page "https://github.com/ctSkennerton/minced")
3554 (synopsis "Mining CRISPRs in Environmental Datasets")
3556 "MinCED is a program to find Clustered Regularly Interspaced Short
3557 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3558 unassembled metagenomic reads, but is mainly designed for full genomes and
3559 assembled metagenomic sequence.")
3560 (license license:gpl3+)))
3568 (uri (pypi-uri "misopy" version))
3571 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3572 (modules '((guix build utils)))
3574 '(substitute* "setup.py"
3575 ;; Use setuptools, or else the executables are not
3577 (("distutils.core") "setuptools")
3578 ;; use "gcc" instead of "cc" for compilation
3580 "cc.set_executables(
3584 linker_so='gcc -shared'); defines")))))
3585 (build-system python-build-system)
3587 `(#:python ,python-2 ; only Python 2 is supported
3588 #:tests? #f)) ; no "test" target
3590 `(("samtools" ,samtools)
3591 ("python-numpy" ,python2-numpy)
3592 ("python-pysam" ,python2-pysam)
3593 ("python-scipy" ,python2-scipy)
3594 ("python-matplotlib" ,python2-matplotlib)))
3596 `(("python-mock" ,python2-mock) ;for tests
3597 ("python-pytz" ,python2-pytz))) ;for tests
3598 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3599 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3601 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3602 the expression level of alternatively spliced genes from RNA-Seq data, and
3603 identifies differentially regulated isoforms or exons across samples. By
3604 modeling the generative process by which reads are produced from isoforms in
3605 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3606 that a read originated from a particular isoform.")
3607 (license license:gpl2)))
3609 (define-public muscle
3612 (version "3.8.1551")
3614 (method url-fetch/tarbomb)
3616 "http://www.drive5.com/muscle/muscle_src_"
3620 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3621 (build-system gnu-build-system)
3623 `(#:make-flags (list "LDLIBS = -lm")
3625 (modify-phases %standard-phases
3628 ;; There are no tests, so just test if it runs.
3629 (lambda _ (zero? (system* "./muscle" "-version"))))
3631 (lambda* (#:key outputs #:allow-other-keys)
3632 (let* ((out (assoc-ref outputs "out"))
3633 (bin (string-append out "/bin")))
3634 (install-file "muscle" bin)))))))
3635 (home-page "http://www.drive5.com/muscle")
3636 (synopsis "Multiple sequence alignment program")
3638 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3639 program for nucleotide and protein sequences.")
3640 ;; License information found in 'muscle -h' and usage.cpp.
3641 (license license:public-domain)))
3643 (define-public newick-utils
3644 ;; There are no recent releases so we package from git.
3645 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3647 (name "newick-utils")
3648 (version (string-append "1.6-1." (string-take commit 8)))
3652 (url "https://github.com/tjunier/newick_utils.git")
3654 (file-name (string-append name "-" version "-checkout"))
3657 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3658 (build-system gnu-build-system)
3661 (modify-phases %standard-phases
3662 (add-after 'unpack 'autoconf
3663 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3665 ;; XXX: TODO: Enable Lua and Guile bindings.
3666 ;; https://github.com/tjunier/newick_utils/issues/13
3667 `(("libxml2" ,libxml2)
3671 `(("autoconf" ,autoconf)
3672 ("automake" ,automake)
3673 ("libtool" ,libtool)))
3674 (synopsis "Programs for working with newick format phylogenetic trees")
3676 "Newick-utils is a suite of utilities for processing phylogenetic trees
3677 in Newick format. Functions include re-rooting, extracting subtrees,
3678 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3679 (home-page "https://github.com/tjunier/newick_utils")
3680 (license license:bsd-3))))
3689 "https://github.com/wwood/OrfM/releases/download/v"
3690 version "/orfm-" version ".tar.gz"))
3693 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3694 (build-system gnu-build-system)
3695 (inputs `(("zlib" ,zlib)))
3697 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3698 ("ruby-rspec" ,ruby-rspec)
3700 (synopsis "Simple and not slow open reading frame (ORF) caller")
3702 "An ORF caller finds stretches of DNA that, when translated, are not
3703 interrupted by stop codons. OrfM finds and prints these ORFs.")
3704 (home-page "https://github.com/wwood/OrfM")
3705 (license license:lgpl3+)))
3707 (define-public pplacer
3708 (let ((commit "g807f6f3"))
3711 ;; The commit should be updated with each version change.
3712 (version "1.1.alpha19")
3716 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3718 (file-name (string-append name "-" version ".tar.gz"))
3720 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3721 (build-system ocaml-build-system)
3723 `(#:ocaml ,ocaml-4.01
3724 #:findlib ,ocaml4.01-findlib
3725 #:modules ((guix build ocaml-build-system)
3729 (modify-phases %standard-phases
3731 (add-after 'unpack 'replace-bundled-cddlib
3732 (lambda* (#:key inputs #:allow-other-keys)
3733 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3734 (local-dir "cddlib_guix"))
3736 (with-directory-excursion local-dir
3737 (system* "tar" "xvf" cddlib-src))
3738 (let ((cddlib-src-folder
3739 (string-append local-dir "/"
3740 (list-ref (scandir local-dir) 2)
3745 (string-append "cdd_src/" (basename file))))
3746 (find-files cddlib-src-folder ".*[ch]$")))
3748 (add-after 'unpack 'fix-makefile
3750 ;; Remove system calls to 'git'.
3751 (substitute* "Makefile"
3752 (("^DESCRIPT:=pplacer-.*")
3754 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3755 (substitute* "myocamlbuild.ml"
3756 (("git describe --tags --long .*\\\" with")
3758 "echo -n v" ,version "-" ,commit "\" with")))
3761 (lambda* (#:key outputs #:allow-other-keys)
3762 (let* ((out (assoc-ref outputs "out"))
3763 (bin (string-append out "/bin")))
3764 (copy-recursively "bin" bin))
3769 ("ocaml-ounit" ,ocaml4.01-ounit)
3770 ("ocaml-batteries" ,ocaml4.01-batteries)
3771 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3772 ("ocaml-csv" ,ocaml4.01-csv)
3773 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3774 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3775 ("ocaml-mcl" ,ocaml4.01-mcl)
3776 ("ocaml-gsl" ,ocaml4.01-gsl)
3777 ("cddlib-src" ,(package-source cddlib))))
3779 `(("pplacer-scripts" ,pplacer-scripts)))
3780 (synopsis "Phylogenetic placement of biological sequences")
3782 "Pplacer places query sequences on a fixed reference phylogenetic tree
3783 to maximize phylogenetic likelihood or posterior probability according to a
3784 reference alignment. Pplacer is designed to be fast, to give useful
3785 information about uncertainty, and to offer advanced visualization and
3786 downstream analysis.")
3787 (home-page "http://matsen.fhcrc.org/pplacer")
3788 (license license:gpl3))))
3790 ;; This package is installed alongside 'pplacer'. It is a separate package so
3791 ;; that it can use the python-build-system for the scripts that are
3792 ;; distributed alongside the main OCaml binaries.
3793 (define pplacer-scripts
3796 (name "pplacer-scripts")
3797 (build-system python-build-system)
3799 `(#:python ,python-2
3801 (modify-phases %standard-phases
3802 (add-after 'unpack 'enter-scripts-dir
3803 (lambda _ (chdir "scripts")))
3806 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3807 (add-after 'install 'wrap-executables
3808 (lambda* (#:key inputs outputs #:allow-other-keys)
3809 (let* ((out (assoc-ref outputs "out"))
3810 (bin (string-append out "/bin")))
3811 (let ((path (string-append
3812 (assoc-ref inputs "hmmer") "/bin:"
3813 (assoc-ref inputs "infernal") "/bin")))
3815 (wrap-program (string-append bin "/refpkg_align.py")
3816 `("PATH" ":" prefix (,path))))
3817 (let ((path (string-append
3818 (assoc-ref inputs "hmmer") "/bin")))
3819 (wrap-program (string-append bin "/hrefpkg_query.py")
3820 `("PATH" ":" prefix (,path)))))
3823 `(("infernal" ,infernal)
3826 `(("python-biopython" ,python2-biopython)
3827 ("taxtastic" ,taxtastic)))
3828 (synopsis "Pplacer Python scripts")))
3830 (define-public python2-pbcore
3832 (name "python2-pbcore")
3836 (uri (pypi-uri "pbcore" version))
3839 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3840 (build-system python-build-system)
3841 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3843 `(("python-cython" ,python2-cython)
3844 ("python-numpy" ,python2-numpy)
3845 ("python-pysam" ,python2-pysam)
3846 ("python-h5py" ,python2-h5py)))
3848 `(("python-nose" ,python2-nose)
3849 ("python-sphinx" ,python2-sphinx)
3850 ("python-pyxb" ,python2-pyxb)))
3851 (home-page "http://pacificbiosciences.github.io/pbcore/")
3852 (synopsis "Library for reading and writing PacBio data files")
3854 "The pbcore package provides Python APIs for interacting with PacBio data
3855 files and writing bioinformatics applications.")
3856 (license license:bsd-3)))
3858 (define-public python2-warpedlmm
3860 (name "python2-warpedlmm")
3866 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3870 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3871 (build-system python-build-system)
3873 `(#:python ,python-2)) ; requires Python 2.7
3875 `(("python-scipy" ,python2-scipy)
3876 ("python-numpy" ,python2-numpy)
3877 ("python-matplotlib" ,python2-matplotlib)
3878 ("python-fastlmm" ,python2-fastlmm)
3879 ("python-pandas" ,python2-pandas)
3880 ("python-pysnptools" ,python2-pysnptools)))
3882 `(("python-mock" ,python2-mock)
3883 ("python-nose" ,python2-nose)
3885 (home-page "https://github.com/PMBio/warpedLMM")
3886 (synopsis "Implementation of warped linear mixed models")
3888 "WarpedLMM is a Python implementation of the warped linear mixed model,
3889 which automatically learns an optimal warping function (or transformation) for
3890 the phenotype as it models the data.")
3891 (license license:asl2.0)))
3893 (define-public pbtranscript-tofu
3894 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3896 (name "pbtranscript-tofu")
3897 (version (string-append "2.2.3." (string-take commit 7)))
3901 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3903 (file-name (string-append name "-" version "-checkout"))
3906 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3907 (modules '((guix build utils)))
3910 ;; remove bundled Cython sources
3911 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3913 (build-system python-build-system)
3915 `(#:python ,python-2
3916 ;; FIXME: Tests fail with "No such file or directory:
3917 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3920 (modify-phases %standard-phases
3921 (add-after 'unpack 'enter-directory
3923 (chdir "pbtranscript-tofu/pbtranscript/")
3925 ;; With setuptools version 18.0 and later this setup.py hack causes
3926 ;; a build error, so we disable it.
3927 (add-after 'enter-directory 'patch-setuppy
3929 (substitute* "setup.py"
3930 (("if 'setuptools.extension' in sys.modules:")
3934 `(("python-numpy" ,python2-numpy)
3935 ("python-bx-python" ,python2-bx-python)
3936 ("python-networkx" ,python2-networkx)
3937 ("python-scipy" ,python2-scipy)
3938 ("python-pbcore" ,python2-pbcore)
3939 ("python-h5py" ,python2-h5py)))
3941 `(("python-cython" ,python2-cython)
3942 ("python-nose" ,python2-nose)))
3943 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3944 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3946 "pbtranscript-tofu contains scripts to analyze transcriptome data
3947 generated using the PacBio Iso-Seq protocol.")
3948 (license license:bsd-3))))
3950 (define-public prank
3957 "http://wasabiapp.org/download/prank/prank.source."
3961 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3962 (build-system gnu-build-system)
3965 (modify-phases %standard-phases
3966 (add-after 'unpack 'enter-src-dir
3970 (add-after 'unpack 'remove-m64-flag
3971 ;; Prank will build with the correct 'bit-ness' without this flag
3972 ;; and this allows building on 32-bit machines.
3973 (lambda _ (substitute* "src/Makefile"
3978 (lambda* (#:key outputs #:allow-other-keys)
3979 (let* ((out (assoc-ref outputs "out"))
3980 (bin (string-append out "/bin"))
3981 (man (string-append out "/share/man/man1"))
3982 (path (string-append
3983 (assoc-ref %build-inputs "mafft") "/bin:"
3984 (assoc-ref %build-inputs "exonerate") "/bin:"
3985 (assoc-ref %build-inputs "bppsuite") "/bin")))
3986 (install-file "prank" bin)
3987 (wrap-program (string-append bin "/prank")
3988 `("PATH" ":" prefix (,path)))
3989 (install-file "prank.1" man))
3993 ("exonerate" ,exonerate)
3994 ("bppsuite" ,bppsuite)))
3995 (home-page "http://wasabiapp.org/software/prank/")
3996 (synopsis "Probabilistic multiple sequence alignment program")
3998 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3999 codon and amino-acid sequences. It is based on a novel algorithm that treats
4000 insertions correctly and avoids over-estimation of the number of deletion
4001 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4002 in phylogenetics and correctly takes into account the evolutionary distances
4003 between sequences. Lastly, PRANK allows for defining a potential structure
4004 for sequences to be aligned and then, simultaneously with the alignment,
4005 predicts the locations of structural units in the sequences.")
4006 (license license:gpl2+)))
4008 (define-public proteinortho
4010 (name "proteinortho")
4017 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4018 version "_src.tar.gz"))
4021 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4022 (build-system gnu-build-system)
4024 `(#:test-target "test"
4026 (modify-phases %standard-phases
4028 ;; There is no configure script, so we modify the Makefile directly.
4029 (lambda* (#:key outputs #:allow-other-keys)
4030 (substitute* "Makefile"
4033 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4035 (add-before 'install 'make-install-directory
4036 ;; The install directory is not created during 'make install'.
4037 (lambda* (#:key outputs #:allow-other-keys)
4038 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4040 (add-after 'install 'wrap-programs
4041 (lambda* (#:key inputs outputs #:allow-other-keys)
4042 (let* ((path (getenv "PATH"))
4043 (out (assoc-ref outputs "out"))
4044 (binary (string-append out "/bin/proteinortho5.pl")))
4045 (wrap-program binary `("PATH" ":" prefix (,path))))
4049 ("python" ,python-2)
4050 ("blast+" ,blast+)))
4051 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4052 (synopsis "Detect orthologous genes across species")
4054 "Proteinortho is a tool to detect orthologous genes across different
4055 species. For doing so, it compares similarities of given gene sequences and
4056 clusters them to find significant groups. The algorithm was designed to handle
4057 large-scale data and can be applied to hundreds of species at once.")
4058 (license license:gpl2+)))
4060 (define-public pyicoteo
4067 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4068 "pyicoteo/get/v" version ".tar.bz2"))
4069 (file-name (string-append name "-" version ".tar.bz2"))
4072 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4073 (build-system python-build-system)
4075 `(#:python ,python-2 ; does not work with Python 3
4076 #:tests? #f)) ; there are no tests
4078 `(("python2-matplotlib" ,python2-matplotlib)))
4079 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4080 (synopsis "Analyze high-throughput genetic sequencing data")
4082 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4083 sequencing data. It works with genomic coordinates. There are currently six
4084 different command-line tools:
4087 @item pyicoregion: for generating exploratory regions automatically;
4088 @item pyicoenrich: for differential enrichment between two conditions;
4089 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4090 @item pyicos: for genomic coordinates manipulation;
4091 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4092 @item pyicount: to count how many reads from N experiment files overlap in a
4094 @item pyicotrocol: to combine operations from pyicoteo.
4096 (license license:gpl3+)))
4098 (define-public prodigal
4105 "https://github.com/hyattpd/Prodigal/archive/v"
4107 (file-name (string-append name "-" version ".tar.gz"))
4110 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4111 (build-system gnu-build-system)
4113 `(#:tests? #f ;no check target
4114 #:make-flags (list (string-append "INSTALLDIR="
4115 (assoc-ref %outputs "out")
4118 (modify-phases %standard-phases
4119 (delete 'configure))))
4120 (home-page "http://prodigal.ornl.gov")
4121 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4123 "Prodigal runs smoothly on finished genomes, draft genomes, and
4124 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4125 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4126 partial genes, and identifies translation initiation sites.")
4127 (license license:gpl3+)))
4129 (define-public roary
4137 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4141 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4142 (build-system perl-build-system)
4145 (modify-phases %standard-phases
4150 ;; The tests are not run by default, so we run each test file
4152 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4154 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4155 (getenv "PERL5LIB")))
4156 (zero? (length (filter (lambda (file)
4157 (display file)(display "\n")
4158 (not (zero? (system* "perl" file))))
4159 (find-files "t" ".*\\.t$"))))))
4161 ;; There is no 'install' target in the Makefile.
4162 (lambda* (#:key outputs #:allow-other-keys)
4163 (let* ((out (assoc-ref outputs "out"))
4164 (bin (string-append out "/bin"))
4165 (perl (string-append out "/lib/perl5/site_perl"))
4166 (roary-plots "contrib/roary_plots"))
4169 (copy-recursively "bin" bin)
4170 (copy-recursively "lib" perl)
4172 (add-after 'install 'wrap-programs
4173 (lambda* (#:key inputs outputs #:allow-other-keys)
4174 (let* ((out (assoc-ref outputs "out"))
4175 (perl5lib (getenv "PERL5LIB"))
4176 (path (getenv "PATH")))
4177 (for-each (lambda (prog)
4178 (let ((binary (string-append out "/" prog)))
4179 (wrap-program binary
4180 `("PERL5LIB" ":" prefix
4181 (,(string-append perl5lib ":" out
4182 "/lib/perl5/site_perl"))))
4183 (wrap-program binary
4185 (,(string-append path ":" out "/bin"))))))
4186 (find-files "bin" ".*[^R]$"))
4188 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4189 (r-site-lib (getenv "R_LIBS_SITE"))
4191 (string-append (assoc-ref inputs "coreutils") "/bin")))
4193 `("R_LIBS_SITE" ":" prefix
4194 (,(string-append r-site-lib ":" out "/site-library/"))))
4197 (,(string-append coreutils-path ":" out "/bin"))))))
4200 `(("perl-env-path" ,perl-env-path)
4201 ("perl-test-files" ,perl-test-files)
4202 ("perl-test-most" ,perl-test-most)
4203 ("perl-test-output" ,perl-test-output)))
4205 `(("perl-array-utils" ,perl-array-utils)
4206 ("bioperl" ,bioperl-minimal)
4207 ("perl-digest-md5-file" ,perl-digest-md5-file)
4208 ("perl-exception-class" ,perl-exception-class)
4209 ("perl-file-find-rule" ,perl-file-find-rule)
4210 ("perl-file-grep" ,perl-file-grep)
4211 ("perl-file-slurper" ,perl-file-slurper)
4212 ("perl-file-which" ,perl-file-which)
4213 ("perl-graph" ,perl-graph)
4214 ("perl-graph-readwrite" ,perl-graph-readwrite)
4215 ("perl-log-log4perl" ,perl-log-log4perl)
4216 ("perl-moose" ,perl-moose)
4217 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4218 ("perl-text-csv" ,perl-text-csv)
4219 ("bedtools" ,bedtools)
4223 ("parallel" ,parallel)
4226 ("fasttree" ,fasttree)
4230 ("r-minimal" ,r-minimal)
4231 ("r-ggplot2" ,r-ggplot2)
4232 ("coreutils" ,coreutils)))
4233 (home-page "http://sanger-pathogens.github.io/Roary")
4234 (synopsis "High speed stand-alone pan genome pipeline")
4236 "Roary is a high speed stand alone pan genome pipeline, which takes
4237 annotated assemblies in GFF3 format (produced by the Prokka program) and
4238 calculates the pan genome. Using a standard desktop PC, it can analyse
4239 datasets with thousands of samples, without compromising the quality of the
4240 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4241 single processor. Roary is not intended for metagenomics or for comparing
4242 extremely diverse sets of genomes.")
4243 (license license:gpl3)))
4245 (define-public raxml
4254 "https://github.com/stamatak/standard-RAxML/archive/v"
4256 (file-name (string-append name "-" version ".tar.gz"))
4259 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4260 (build-system gnu-build-system)
4262 `(#:tests? #f ; There are no tests.
4263 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4264 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4266 (modify-phases %standard-phases
4269 (lambda* (#:key outputs #:allow-other-keys)
4270 (let* ((out (assoc-ref outputs "out"))
4271 (bin (string-append out "/bin"))
4272 (executable "raxmlHPC-HYBRID"))
4273 (install-file executable bin)
4274 (symlink (string-append bin "/" executable) "raxml"))
4277 `(("openmpi" ,openmpi)))
4278 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4279 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4281 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4283 ;; The source includes x86 specific code
4284 (supported-systems '("x86_64-linux" "i686-linux"))
4285 (license license:gpl2+)))
4295 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4298 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4299 (patches (search-patches "rsem-makefile.patch"))
4300 (modules '((guix build utils)))
4303 ;; remove bundled copy of boost
4304 (delete-file-recursively "boost")
4306 (build-system gnu-build-system)
4308 `(#:tests? #f ;no "check" target
4310 (modify-phases %standard-phases
4311 ;; No "configure" script.
4312 ;; Do not build bundled samtools library.
4315 (substitute* "Makefile"
4316 (("^all : sam/libbam.a") "all : "))
4319 (lambda* (#:key outputs #:allow-other-keys)
4320 (let* ((out (string-append (assoc-ref outputs "out")))
4321 (bin (string-append out "/bin/"))
4322 (perl (string-append out "/lib/perl5/site_perl")))
4325 (for-each (lambda (file)
4326 (install-file file bin))
4327 (find-files "." "rsem-.*"))
4328 (install-file "rsem_perl_utils.pm" perl))
4331 'install 'wrap-program
4332 (lambda* (#:key outputs #:allow-other-keys)
4333 (let ((out (assoc-ref outputs "out")))
4334 (for-each (lambda (prog)
4335 (wrap-program (string-append out "/bin/" prog)
4336 `("PERL5LIB" ":" prefix
4337 (,(string-append out "/lib/perl5/site_perl")))))
4338 '("rsem-plot-transcript-wiggles"
4339 "rsem-calculate-expression"
4340 "rsem-generate-ngvector"
4342 "rsem-prepare-reference")))
4346 ("ncurses" ,ncurses)
4347 ("r-minimal" ,r-minimal)
4349 ("samtools" ,samtools-0.1)
4351 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4352 (synopsis "Estimate gene expression levels from RNA-Seq data")
4354 "RSEM is a software package for estimating gene and isoform expression
4355 levels from RNA-Seq data. The RSEM package provides a user-friendly
4356 interface, supports threads for parallel computation of the EM algorithm,
4357 single-end and paired-end read data, quality scores, variable-length reads and
4358 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4359 interval estimates for expression levels. For visualization, it can generate
4360 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4361 (license license:gpl3+)))
4363 (define-public rseqc
4371 (string-append "mirror://sourceforge/rseqc/"
4372 "RSeQC-" version ".tar.gz"))
4374 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4375 (modules '((guix build utils)))
4378 ;; remove bundled copy of pysam
4379 (delete-file-recursively "lib/pysam")
4380 (substitute* "setup.py"
4381 ;; remove dependency on outdated "distribute" module
4382 (("^from distribute_setup import use_setuptools") "")
4383 (("^use_setuptools\\(\\)") "")
4384 ;; do not use bundled copy of pysam
4385 (("^have_pysam = False") "have_pysam = True"))))))
4386 (build-system python-build-system)
4387 (arguments `(#:python ,python-2))
4389 `(("python-cython" ,python2-cython)
4390 ("python-pysam" ,python2-pysam)
4391 ("python-numpy" ,python2-numpy)
4394 `(("python-nose" ,python2-nose)))
4395 (home-page "http://rseqc.sourceforge.net/")
4396 (synopsis "RNA-seq quality control package")
4398 "RSeQC provides a number of modules that can comprehensively evaluate
4399 high throughput sequence data, especially RNA-seq data. Some basic modules
4400 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4401 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4402 distribution, coverage uniformity, strand specificity, etc.")
4403 (license license:gpl3+)))
4406 ;; There are no release tarballs. According to the installation
4407 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4408 ;; stable release is identified by this changeset ID.
4409 (let ((changeset "2329130")
4413 (version (string-append "0-" revision "." changeset))
4417 (url "https://bitbucket.org/libsleipnir/sleipnir")
4418 (changeset changeset)))
4421 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4422 (build-system gnu-build-system)
4424 `(#:modules ((srfi srfi-1)
4425 (guix build gnu-build-system)
4428 (let ((dirs '("SeekMiner"
4434 (modify-phases %standard-phases
4435 (add-before 'configure 'bootstrap
4437 (zero? (system* "bash" "gen_auto"))))
4438 (add-after 'build 'build-additional-tools
4439 (lambda* (#:key make-flags #:allow-other-keys)
4440 (every (lambda (dir)
4441 (with-directory-excursion (string-append "tools/" dir)
4442 (zero? (apply system* "make" make-flags))))
4444 (add-after 'install 'install-additional-tools
4445 (lambda* (#:key make-flags #:allow-other-keys)
4446 (fold (lambda (dir result)
4447 (with-directory-excursion (string-append "tools/" dir)
4449 (zero? (apply system*
4450 `("make" ,@make-flags "install"))))))
4456 ("readline" ,readline)
4457 ("gengetopt" ,gengetopt)
4458 ("log4cpp" ,log4cpp)))
4460 `(("autoconf" ,autoconf)
4461 ("automake" ,automake)
4463 (home-page "http://seek.princeton.edu")
4464 (synopsis "Gene co-expression search engine")
4466 "SEEK is a computational gene co-expression search engine. SEEK provides
4467 biologists with a way to navigate the massive human expression compendium that
4468 now contains thousands of expression datasets. SEEK returns a robust ranking
4469 of co-expressed genes in the biological area of interest defined by the user's
4470 query genes. It also prioritizes thousands of expression datasets according
4471 to the user's query of interest.")
4472 (license license:cc-by3.0))))
4474 (define-public samtools
4482 (string-append "mirror://sourceforge/samtools/samtools/"
4483 version "/samtools-" version ".tar.bz2"))
4486 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4487 (build-system gnu-build-system)
4489 `(#:modules ((ice-9 ftw)
4491 (guix build gnu-build-system)
4493 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4494 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4496 (modify-phases %standard-phases
4497 (add-after 'unpack 'patch-tests
4499 (substitute* "test/test.pl"
4500 ;; The test script calls out to /bin/bash
4501 (("/bin/bash") (which "bash")))
4503 (add-after 'install 'install-library
4504 (lambda* (#:key outputs #:allow-other-keys)
4505 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4506 (install-file "libbam.a" lib)
4508 (add-after 'install 'install-headers
4509 (lambda* (#:key outputs #:allow-other-keys)
4510 (let ((include (string-append (assoc-ref outputs "out")
4511 "/include/samtools/")))
4512 (for-each (lambda (file)
4513 (install-file file include))
4514 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4516 (native-inputs `(("pkg-config" ,pkg-config)))
4518 `(("htslib" ,htslib)
4519 ("ncurses" ,ncurses)
4523 (home-page "http://samtools.sourceforge.net")
4524 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4526 "Samtools implements various utilities for post-processing nucleotide
4527 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4528 variant calling (in conjunction with bcftools), and a simple alignment
4530 (license license:expat)))
4532 (define-public samtools-0.1
4533 ;; This is the most recent version of the 0.1 line of samtools. The input
4534 ;; and output formats differ greatly from that used and produced by samtools
4535 ;; 1.x and is still used in many bioinformatics pipelines.
4536 (package (inherit samtools)
4542 (string-append "mirror://sourceforge/samtools/samtools/"
4543 version "/samtools-" version ".tar.bz2"))
4545 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4547 `(#:tests? #f ;no "check" target
4548 ,@(substitute-keyword-arguments (package-arguments samtools)
4549 ((#:make-flags flags)
4550 `(cons "LIBCURSES=-lncurses" ,flags))
4552 `(modify-phases ,phases
4554 (lambda* (#:key outputs #:allow-other-keys)
4555 (let ((bin (string-append
4556 (assoc-ref outputs "out") "/bin")))
4558 (install-file "samtools" bin)
4560 (delete 'patch-tests)
4561 (delete 'configure))))))))
4563 (define-public mosaik
4564 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4569 ;; There are no release tarballs nor tags.
4572 (url "https://github.com/wanpinglee/MOSAIK.git")
4574 (file-name (string-append name "-" version))
4577 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4578 (build-system gnu-build-system)
4580 `(#:tests? #f ; no tests
4581 #:make-flags (list "CC=gcc")
4583 (modify-phases %standard-phases
4585 (lambda _ (chdir "src") #t))
4587 (lambda* (#:key outputs #:allow-other-keys)
4588 (let ((bin (string-append (assoc-ref outputs "out")
4591 (copy-recursively "../bin" bin)
4596 (supported-systems '("x86_64-linux"))
4597 (home-page "https://github.com/wanpinglee/MOSAIK")
4598 (synopsis "Map nucleotide sequence reads to reference genomes")
4600 "MOSAIK is a program for mapping second and third-generation sequencing
4601 reads to a reference genome. MOSAIK can align reads generated by all the
4602 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4603 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4604 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4605 ;; code released into the public domain:
4606 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4607 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4608 (license (list license:gpl2+ license:public-domain)))))
4610 (define-public ngs-sdk
4618 (string-append "https://github.com/ncbi/ngs/archive/"
4620 (file-name (string-append name "-" version ".tar.gz"))
4623 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4624 (build-system gnu-build-system)
4626 `(#:parallel-build? #f ; not supported
4627 #:tests? #f ; no "check" target
4629 (modify-phases %standard-phases
4631 (lambda* (#:key outputs #:allow-other-keys)
4632 (let ((out (assoc-ref outputs "out")))
4633 ;; Allow 'konfigure.perl' to find 'package.prl'.
4635 (string-append ".:" (getenv "PERL5LIB")))
4637 ;; The 'configure' script doesn't recognize things like
4638 ;; '--enable-fast-install'.
4639 (zero? (system* "./configure"
4640 (string-append "--build-prefix=" (getcwd) "/build")
4641 (string-append "--prefix=" out))))))
4642 (add-after 'unpack 'enter-dir
4643 (lambda _ (chdir "ngs-sdk") #t)))))
4644 (native-inputs `(("perl" ,perl)))
4645 ;; According to the test
4646 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4647 ;; in ngs-sdk/setup/konfigure.perl
4648 (supported-systems '("i686-linux" "x86_64-linux"))
4649 (home-page "https://github.com/ncbi/ngs")
4650 (synopsis "API for accessing Next Generation Sequencing data")
4652 "NGS is a domain-specific API for accessing reads, alignments and pileups
4653 produced from Next Generation Sequencing. The API itself is independent from
4654 any particular back-end implementation, and supports use of multiple back-ends
4656 (license license:public-domain)))
4658 (define-public java-ngs
4659 (package (inherit ngs-sdk)
4662 `(,@(substitute-keyword-arguments
4663 `(#:modules ((guix build gnu-build-system)
4667 ,@(package-arguments ngs-sdk))
4669 `(modify-phases ,phases
4670 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4672 `(("jdk" ,icedtea "jdk")
4673 ("ngs-sdk" ,ngs-sdk)))
4674 (synopsis "Java bindings for NGS SDK")))
4676 (define-public ncbi-vdb
4684 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4686 (file-name (string-append name "-" version ".tar.gz"))
4689 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4690 (build-system gnu-build-system)
4692 `(#:parallel-build? #f ; not supported
4693 #:tests? #f ; no "check" target
4695 (modify-phases %standard-phases
4696 (add-before 'configure 'set-perl-search-path
4698 ;; Work around "dotless @INC" build failure.
4700 (string-append (getcwd) "/setup:"
4701 (getenv "PERL5LIB")))
4704 (lambda* (#:key inputs outputs #:allow-other-keys)
4705 (let ((out (assoc-ref outputs "out")))
4706 ;; Override include path for libmagic
4707 (substitute* "setup/package.prl"
4708 (("name => 'magic', Include => '/usr/include'")
4709 (string-append "name=> 'magic', Include => '"
4710 (assoc-ref inputs "libmagic")
4713 ;; Install kdf5 library (needed by sra-tools)
4714 (substitute* "build/Makefile.install"
4715 (("LIBRARIES_TO_INSTALL =")
4716 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4718 (substitute* "build/Makefile.env"
4719 (("CFLAGS =" prefix)
4720 (string-append prefix "-msse2 ")))
4722 ;; Override search path for ngs-java
4723 (substitute* "setup/package.prl"
4724 (("/usr/local/ngs/ngs-java")
4725 (assoc-ref inputs "java-ngs")))
4727 ;; The 'configure' script doesn't recognize things like
4728 ;; '--enable-fast-install'.
4731 (string-append "--build-prefix=" (getcwd) "/build")
4732 (string-append "--prefix=" (assoc-ref outputs "out"))
4733 (string-append "--debug")
4734 (string-append "--with-xml2-prefix="
4735 (assoc-ref inputs "libxml2"))
4736 (string-append "--with-ngs-sdk-prefix="
4737 (assoc-ref inputs "ngs-sdk"))
4738 (string-append "--with-hdf5-prefix="
4739 (assoc-ref inputs "hdf5")))))))
4740 (add-after 'install 'install-interfaces
4741 (lambda* (#:key outputs #:allow-other-keys)
4742 ;; Install interface libraries. On i686 the interface libraries
4743 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4744 ;; architecture name ("i386") instead of the target system prefix
4746 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4747 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4748 ,(system->linux-architecture
4749 (or (%current-target-system)
4752 (string-append (assoc-ref outputs "out")
4754 ;; Install interface headers
4755 (copy-recursively "interfaces"
4756 (string-append (assoc-ref outputs "out")
4759 ;; These files are needed by sra-tools.
4760 (add-after 'install 'install-configuration-files
4761 (lambda* (#:key outputs #:allow-other-keys)
4762 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4764 (install-file "libs/kfg/default.kfg" target)
4765 (install-file "libs/kfg/certs.kfg" target))
4768 `(("libxml2" ,libxml2)
4769 ("ngs-sdk" ,ngs-sdk)
4770 ("java-ngs" ,java-ngs)
4773 (native-inputs `(("perl" ,perl)))
4774 ;; NCBI-VDB requires SSE capability.
4775 (supported-systems '("i686-linux" "x86_64-linux"))
4776 (home-page "https://github.com/ncbi/ncbi-vdb")
4777 (synopsis "Database engine for genetic information")
4779 "The NCBI-VDB library implements a highly compressed columnar data
4780 warehousing engine that is most often used to store genetic information.
4781 Databases are stored in a portable image within the file system, and can be
4782 accessed/downloaded on demand across HTTP.")
4783 (license license:public-domain)))
4785 (define-public plink
4793 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4794 version "-src.zip"))
4796 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4797 (patches (search-patches "plink-1.07-unclobber-i.patch"
4798 "plink-endian-detection.patch"))))
4799 (build-system gnu-build-system)
4801 '(#:tests? #f ;no "check" target
4802 #:make-flags (list (string-append "LIB_LAPACK="
4803 (assoc-ref %build-inputs "lapack")
4804 "/lib/liblapack.so")
4807 ;; disable phoning home
4810 (modify-phases %standard-phases
4811 ;; no "configure" script
4814 (lambda* (#:key outputs #:allow-other-keys)
4815 (let ((bin (string-append (assoc-ref outputs "out")
4817 (install-file "plink" bin)
4821 ("lapack" ,lapack)))
4823 `(("unzip" ,unzip)))
4824 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4825 (synopsis "Whole genome association analysis toolset")
4827 "PLINK is a whole genome association analysis toolset, designed to
4828 perform a range of basic, large-scale analyses in a computationally efficient
4829 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4830 so there is no support for steps prior to this (e.g. study design and
4831 planning, generating genotype or CNV calls from raw data). Through
4832 integration with gPLINK and Haploview, there is some support for the
4833 subsequent visualization, annotation and storage of results.")
4834 ;; Code is released under GPLv2, except for fisher.h, which is under
4836 (license (list license:gpl2 license:lgpl2.1+))))
4838 (define-public plink-ng
4839 (package (inherit plink)
4845 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
4847 (file-name (string-append name "-" version ".tar.gz"))
4849 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
4850 (build-system gnu-build-system)
4852 '(#:tests? #f ;no "check" target
4853 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
4854 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
4856 "-f" "Makefile.std")
4858 (modify-phases %standard-phases
4859 (add-after 'unpack 'chdir
4860 (lambda _ (chdir "1.9") #t))
4861 (delete 'configure) ; no "configure" script
4863 (lambda* (#:key outputs #:allow-other-keys)
4864 (let ((bin (string-append (assoc-ref outputs "out")
4866 (install-file "plink" bin)
4871 ("openblas" ,openblas)))
4872 (home-page "https://www.cog-genomics.org/plink/")
4873 (license license:gpl3+)))
4875 (define-public smithlab-cpp
4876 (let ((revision "1")
4877 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4879 (name "smithlab-cpp")
4880 (version (string-append "0." revision "." (string-take commit 7)))
4884 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4886 (file-name (string-append name "-" version "-checkout"))
4889 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4890 (build-system gnu-build-system)
4892 `(#:modules ((guix build gnu-build-system)
4895 #:tests? #f ;no "check" target
4897 (modify-phases %standard-phases
4898 (add-after 'unpack 'use-samtools-headers
4900 (substitute* '("SAM.cpp"
4902 (("sam.h") "samtools/sam.h"))
4905 (lambda* (#:key outputs #:allow-other-keys)
4906 (let* ((out (assoc-ref outputs "out"))
4907 (lib (string-append out "/lib"))
4908 (include (string-append out "/include/smithlab-cpp")))
4911 (for-each (cut install-file <> lib)
4912 (find-files "." "\\.o$"))
4913 (for-each (cut install-file <> include)
4914 (find-files "." "\\.hpp$")))
4916 (delete 'configure))))
4918 `(("samtools" ,samtools-0.1)
4920 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4921 (synopsis "C++ helper library for functions used in Smith lab projects")
4923 "Smithlab CPP is a C++ library that includes functions used in many of
4924 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4925 structures, classes for genomic regions, mapped sequencing reads, etc.")
4926 (license license:gpl3+))))
4928 (define-public preseq
4934 (uri (string-append "https://github.com/smithlabcode/"
4935 "preseq/archive/v" version ".tar.gz"))
4936 (file-name (string-append name "-" version ".tar.gz"))
4938 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4939 (modules '((guix build utils)))
4941 ;; Remove bundled samtools.
4942 '(delete-file-recursively "samtools"))))
4943 (build-system gnu-build-system)
4945 `(#:tests? #f ;no "check" target
4947 (modify-phases %standard-phases
4948 (delete 'configure))
4950 (list (string-append "PREFIX="
4951 (assoc-ref %outputs "out"))
4952 (string-append "LIBBAM="
4953 (assoc-ref %build-inputs "samtools")
4955 (string-append "SMITHLAB_CPP="
4956 (assoc-ref %build-inputs "smithlab-cpp")
4959 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4962 ("samtools" ,samtools-0.1)
4963 ("smithlab-cpp" ,smithlab-cpp)
4965 (home-page "http://smithlabresearch.org/software/preseq/")
4966 (synopsis "Program for analyzing library complexity")
4968 "The preseq package is aimed at predicting and estimating the complexity
4969 of a genomic sequencing library, equivalent to predicting and estimating the
4970 number of redundant reads from a given sequencing depth and how many will be
4971 expected from additional sequencing using an initial sequencing experiment.
4972 The estimates can then be used to examine the utility of further sequencing,
4973 optimize the sequencing depth, or to screen multiple libraries to avoid low
4974 complexity samples.")
4975 (license license:gpl3+)))
4977 (define-public python-screed
4979 (name "python-screed")
4984 (uri (pypi-uri "screed" version))
4987 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4988 (build-system python-build-system)
4991 (modify-phases %standard-phases
4994 (setenv "PYTHONPATH"
4995 (string-append (getenv "PYTHONPATH") ":."))
4996 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4998 `(("python-nose" ,python-nose)))
5000 `(("python-bz2file" ,python-bz2file)))
5001 (home-page "https://github.com/dib-lab/screed/")
5002 (synopsis "Short read sequence database utilities")
5003 (description "Screed parses FASTA and FASTQ files and generates databases.
5004 Values such as sequence name, sequence description, sequence quality and the
5005 sequence itself can be retrieved from these databases.")
5006 (license license:bsd-3)))
5008 (define-public python2-screed
5009 (package-with-python2 python-screed))
5011 (define-public sra-tools
5019 (string-append "https://github.com/ncbi/sra-tools/archive/"
5021 (file-name (string-append name "-" version ".tar.gz"))
5024 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5025 (build-system gnu-build-system)
5027 `(#:parallel-build? #f ; not supported
5028 #:tests? #f ; no "check" target
5030 (list (string-append "DEFAULT_CRT="
5031 (assoc-ref %build-inputs "ncbi-vdb")
5033 (string-append "DEFAULT_KFG="
5034 (assoc-ref %build-inputs "ncbi-vdb")
5036 (string-append "VDB_LIBDIR="
5037 (assoc-ref %build-inputs "ncbi-vdb")
5038 ,(if (string-prefix? "x86_64"
5039 (or (%current-target-system)
5044 (modify-phases %standard-phases
5045 (add-before 'configure 'set-perl-search-path
5047 ;; Work around "dotless @INC" build failure.
5049 (string-append (getcwd) "/setup:"
5050 (getenv "PERL5LIB")))
5053 (lambda* (#:key inputs outputs #:allow-other-keys)
5054 ;; The build system expects a directory containing the sources and
5055 ;; raw build output of ncbi-vdb, including files that are not
5056 ;; installed. Since we are building against an installed version of
5057 ;; ncbi-vdb, the following modifications are needed.
5058 (substitute* "setup/konfigure.perl"
5059 ;; Make the configure script look for the "ilib" directory of
5060 ;; "ncbi-vdb" without first checking for the existence of a
5061 ;; matching library in its "lib" directory.
5062 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5063 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5064 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5065 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5066 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5069 (substitute* "tools/copycat/Makefile"
5070 (("smagic-static") "lmagic"))
5072 ;; The 'configure' script doesn't recognize things like
5073 ;; '--enable-fast-install'.
5076 (string-append "--build-prefix=" (getcwd) "/build")
5077 (string-append "--prefix=" (assoc-ref outputs "out"))
5078 (string-append "--debug")
5079 (string-append "--with-fuse-prefix="
5080 (assoc-ref inputs "fuse"))
5081 (string-append "--with-magic-prefix="
5082 (assoc-ref inputs "libmagic"))
5083 ;; TODO: building with libxml2 fails with linker errors
5084 ;; (string-append "--with-xml2-prefix="
5085 ;; (assoc-ref inputs "libxml2"))
5086 (string-append "--with-ncbi-vdb-sources="
5087 (assoc-ref inputs "ncbi-vdb"))
5088 (string-append "--with-ncbi-vdb-build="
5089 (assoc-ref inputs "ncbi-vdb"))
5090 (string-append "--with-ngs-sdk-prefix="
5091 (assoc-ref inputs "ngs-sdk"))
5092 (string-append "--with-hdf5-prefix="
5093 (assoc-ref inputs "hdf5"))))))
5094 ;; This version of sra-tools fails to build with glibc because of a
5095 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5096 ;; contains a definition of "canonicalize", so we rename it.
5098 ;; See upstream bug report:
5099 ;; https://github.com/ncbi/sra-tools/issues/67
5100 (add-after 'unpack 'patch-away-glibc-conflict
5102 (substitute* "tools/bam-loader/bam.c"
5103 (("canonicalize\\(" line)
5104 (string-append "sra_tools_" line)))
5106 (native-inputs `(("perl" ,perl)))
5108 `(("ngs-sdk" ,ngs-sdk)
5109 ("ncbi-vdb" ,ncbi-vdb)
5114 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5115 (synopsis "Tools and libraries for reading and writing sequencing data")
5117 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5118 reading of sequencing files from the Sequence Read Archive (SRA) database and
5119 writing files into the .sra format.")
5120 (license license:public-domain)))
5122 (define-public seqan
5128 (uri (string-append "http://packages.seqan.de/seqan-library/"
5129 "seqan-library-" version ".tar.bz2"))
5132 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5133 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5134 ;; makes sense to split the outputs.
5135 (outputs '("out" "doc"))
5136 (build-system trivial-build-system)
5138 `(#:modules ((guix build utils))
5141 (use-modules (guix build utils))
5142 (let ((tar (assoc-ref %build-inputs "tar"))
5143 (bzip (assoc-ref %build-inputs "bzip2"))
5144 (out (assoc-ref %outputs "out"))
5145 (doc (assoc-ref %outputs "doc")))
5146 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5147 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5148 (chdir (string-append "seqan-library-" ,version))
5149 (copy-recursively "include" (string-append out "/include"))
5150 (copy-recursively "share" (string-append doc "/share"))))))
5152 `(("source" ,source)
5155 (home-page "http://www.seqan.de")
5156 (synopsis "Library for nucleotide sequence analysis")
5158 "SeqAn is a C++ library of efficient algorithms and data structures for
5159 the analysis of sequences with the focus on biological data. It contains
5160 algorithms and data structures for string representation and their
5161 manipulation, online and indexed string search, efficient I/O of
5162 bioinformatics file formats, sequence alignment, and more.")
5163 (license license:bsd-3)))
5165 (define-public seqmagick
5173 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5177 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5178 (build-system python-build-system)
5180 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5181 `(#:python ,python-2
5183 (modify-phases %standard-phases
5184 ;; Current test in setup.py does not work as of 0.6.1,
5185 ;; so use nose to run tests instead for now. See
5186 ;; https://github.com/fhcrc/seqmagick/issues/55
5187 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5189 ;; biopython-1.66 is required due to
5190 ;; https://github.com/fhcrc/seqmagick/issues/59
5191 ;; When that issue is resolved the 'python2-biopython-1.66' package
5192 ;; should be removed.
5193 `(("python-biopython" ,python2-biopython-1.66)))
5195 `(("python-nose" ,python2-nose)))
5196 (home-page "https://github.com/fhcrc/seqmagick")
5197 (synopsis "Tools for converting and modifying sequence files")
5199 "Bioinformaticians often have to convert sequence files between formats
5200 and do little manipulations on them, and it's not worth writing scripts for
5201 that. Seqmagick is a utility to expose the file format conversion in
5202 BioPython in a convenient way. Instead of having a big mess of scripts, there
5203 is one that takes arguments.")
5204 (license license:gpl3)))
5206 (define-public seqtk
5213 "https://github.com/lh3/seqtk/archive/v"
5215 (file-name (string-append name "-" version ".tar.gz"))
5218 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5219 (modules '((guix build utils)))
5222 ;; Remove extraneous header files, as is done in the seqtk
5224 (for-each (lambda (file) (delete-file file))
5225 (list "ksort.h" "kstring.h" "kvec.h"))
5227 (build-system gnu-build-system)
5230 (modify-phases %standard-phases
5233 ;; There are no tests, so we just run a sanity check.
5234 (lambda _ (zero? (system* "./seqtk" "seq"))))
5236 (lambda* (#:key outputs #:allow-other-keys)
5237 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5238 (install-file "seqtk" bin)))))))
5241 (home-page "https://github.com/lh3/seqtk")
5242 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5244 "Seqtk is a fast and lightweight tool for processing sequences in the
5245 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5246 optionally compressed by gzip.")
5247 (license license:expat)))
5249 (define-public snap-aligner
5251 (name "snap-aligner")
5252 (version "1.0beta.18")
5256 "https://github.com/amplab/snap/archive/v"
5258 (file-name (string-append name "-" version ".tar.gz"))
5261 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5262 (build-system gnu-build-system)
5265 (modify-phases %standard-phases
5267 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5269 (lambda* (#:key outputs #:allow-other-keys)
5270 (let* ((out (assoc-ref outputs "out"))
5271 (bin (string-append out "/bin")))
5272 (install-file "snap-aligner" bin)
5273 (install-file "SNAPCommand" bin)
5277 (home-page "http://snap.cs.berkeley.edu/")
5278 (synopsis "Short read DNA sequence aligner")
5280 "SNAP is a fast and accurate aligner for short DNA reads. It is
5281 optimized for modern read lengths of 100 bases or higher, and takes advantage
5282 of these reads to align data quickly through a hash-based indexing scheme.")
5283 ;; 32-bit systems are not supported by the unpatched code.
5284 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5285 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5286 ;; systems without a lot of memory cannot make good use of this program.
5287 (supported-systems '("x86_64-linux"))
5288 (license license:asl2.0)))
5290 (define-public sortmerna
5298 "https://github.com/biocore/sortmerna/archive/"
5300 (file-name (string-append name "-" version ".tar.gz"))
5303 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5304 (build-system gnu-build-system)
5305 (outputs '("out" ;for binaries
5306 "db")) ;for sequence databases
5309 (modify-phases %standard-phases
5311 (lambda* (#:key outputs #:allow-other-keys)
5312 (let* ((out (assoc-ref outputs "out"))
5313 (bin (string-append out "/bin"))
5314 (db (assoc-ref outputs "db"))
5316 (string-append db "/share/sortmerna/rRNA_databases")))
5317 (install-file "sortmerna" bin)
5318 (install-file "indexdb_rna" bin)
5319 (for-each (lambda (file)
5320 (install-file file share))
5321 (find-files "rRNA_databases" ".*fasta"))
5325 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5326 (synopsis "Biological sequence analysis tool for NGS reads")
5328 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5329 and operational taxonomic unit (OTU) picking of next generation
5330 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5331 allows for fast and sensitive analyses of nucleotide sequences. The main
5332 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5333 ;; The source includes x86 specific code
5334 (supported-systems '("x86_64-linux" "i686-linux"))
5335 (license license:lgpl3)))
5343 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5345 (file-name (string-append name "-" version ".tar.gz"))
5348 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5349 (modules '((guix build utils)))
5352 (substitute* "source/Makefile"
5354 ;; Remove pre-built binaries and bundled htslib sources.
5355 (delete-file-recursively "bin/MacOSX_x86_64")
5356 (delete-file-recursively "bin/Linux_x86_64")
5357 (delete-file-recursively "bin/Linux_x86_64_static")
5358 (delete-file-recursively "source/htslib")
5360 (build-system gnu-build-system)
5362 '(#:tests? #f ;no check target
5363 #:make-flags '("STAR")
5365 (modify-phases %standard-phases
5366 (add-after 'unpack 'enter-source-dir
5367 (lambda _ (chdir "source") #t))
5368 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5370 (substitute* "Makefile"
5371 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5373 (substitute* '("BAMfunctions.cpp"
5378 "bamRemoveDuplicates.cpp")
5379 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5380 (string-append "#include <" header ">")))
5381 (substitute* "IncludeDefine.h"
5382 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5383 (string-append "<" header ">")))
5386 (lambda* (#:key outputs #:allow-other-keys)
5387 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5388 (install-file "STAR" bin))
5390 (delete 'configure))))
5394 `(("htslib" ,htslib)
5396 (home-page "https://github.com/alexdobin/STAR")
5397 (synopsis "Universal RNA-seq aligner")
5399 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5400 based on a previously undescribed RNA-seq alignment algorithm that uses
5401 sequential maximum mappable seed search in uncompressed suffix arrays followed
5402 by seed clustering and stitching procedure. In addition to unbiased de novo
5403 detection of canonical junctions, STAR can discover non-canonical splices and
5404 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5406 ;; Only 64-bit systems are supported according to the README.
5407 (supported-systems '("x86_64-linux" "mips64el-linux"))
5408 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5409 (license license:gpl3+)))
5411 (define-public subread
5417 (uri (string-append "mirror://sourceforge/subread/subread-"
5418 version "/subread-" version "-source.tar.gz"))
5421 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5422 (build-system gnu-build-system)
5424 `(#:tests? #f ;no "check" target
5425 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5426 ;; optimizations by default, so we override these flags such that x86_64
5427 ;; flags are only added when the build target is an x86_64 system.
5429 (list (let ((system ,(or (%current-target-system)
5431 (flags '("-ggdb" "-fomit-frame-pointer"
5432 "-ffast-math" "-funroll-loops"
5433 "-fmessage-length=0"
5434 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5436 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5437 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5438 (if (string-prefix? "x86_64" system)
5439 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5440 (string-append "CCFLAGS=" (string-join flags))))
5441 "-f" "Makefile.Linux"
5442 "CC=gcc ${CCFLAGS}")
5444 (modify-phases %standard-phases
5445 (add-after 'unpack 'enter-dir
5446 (lambda _ (chdir "src") #t))
5448 (lambda* (#:key outputs #:allow-other-keys)
5449 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5451 (copy-recursively "../bin" bin))))
5452 ;; no "configure" script
5453 (delete 'configure))))
5454 (inputs `(("zlib" ,zlib)))
5455 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5456 (synopsis "Tool kit for processing next-gen sequencing data")
5458 "The subread package contains the following tools: subread aligner, a
5459 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5460 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5461 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5462 against local background noises.")
5463 (license license:gpl3+)))
5465 (define-public stringtie
5471 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5472 "stringtie-" version ".tar.gz"))
5475 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5476 (modules '((guix build utils)))
5479 (delete-file-recursively "samtools-0.1.18")
5481 (build-system gnu-build-system)
5483 `(#:tests? #f ;no test suite
5485 (modify-phases %standard-phases
5486 ;; no configure script
5488 (add-before 'build 'use-system-samtools
5490 (substitute* "Makefile"
5491 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5493 (substitute* '("gclib/GBam.h"
5495 (("#include \"(bam|sam|kstring).h\"" _ header)
5496 (string-append "#include <samtools/" header ".h>")))
5498 (add-after 'unpack 'remove-duplicate-typedef
5500 ;; This typedef conflicts with the typedef in
5501 ;; glibc-2.25/include/bits/types.h
5502 (substitute* "gclib/GThreads.h"
5503 (("typedef long long __intmax_t;") ""))
5506 (lambda* (#:key outputs #:allow-other-keys)
5507 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5508 (install-file "stringtie" bin)
5511 `(("samtools" ,samtools-0.1)
5513 (home-page "http://ccb.jhu.edu/software/stringtie/")
5514 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5516 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5517 alignments into potential transcripts. It uses a novel network flow algorithm
5518 as well as an optional de novo assembly step to assemble and quantitate
5519 full-length transcripts representing multiple splice variants for each gene
5520 locus. Its input can include not only the alignments of raw reads used by
5521 other transcript assemblers, but also alignments of longer sequences that have
5522 been assembled from those reads. To identify differentially expressed genes
5523 between experiments, StringTie's output can be processed either by the
5524 Cuffdiff or Ballgown programs.")
5525 (license license:artistic2.0)))
5527 (define-public taxtastic
5533 (uri (pypi-uri "taxtastic" version))
5536 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5537 (build-system python-build-system)
5539 `(#:python ,python-2
5541 (modify-phases %standard-phases
5544 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5546 `(("python-sqlalchemy" ,python2-sqlalchemy)
5547 ("python-decorator" ,python2-decorator)
5548 ("python-biopython" ,python2-biopython)
5549 ("python-pandas" ,python2-pandas)))
5550 (home-page "https://github.com/fhcrc/taxtastic")
5551 (synopsis "Tools for taxonomic naming and annotation")
5553 "Taxtastic is software written in python used to build and maintain
5554 reference packages i.e. collections of reference trees, reference alignments,
5555 profiles, and associated taxonomic information.")
5556 (license license:gpl3+)))
5558 (define-public vcftools
5565 "https://github.com/vcftools/vcftools/releases/download/v"
5566 version "/vcftools-" version ".tar.gz"))
5569 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5570 (build-system gnu-build-system)
5572 `(#:tests? #f ; no "check" target
5574 "CFLAGS=-O2" ; override "-m64" flag
5575 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5576 (string-append "MANDIR=" (assoc-ref %outputs "out")
5577 "/share/man/man1"))))
5579 `(("pkg-config" ,pkg-config)))
5583 (home-page "https://vcftools.github.io/")
5584 (synopsis "Tools for working with VCF files")
5586 "VCFtools is a program package designed for working with VCF files, such
5587 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5588 provide easily accessible methods for working with complex genetic variation
5589 data in the form of VCF files.")
5590 ;; The license is declared as LGPLv3 in the README and
5591 ;; at https://vcftools.github.io/license.html
5592 (license license:lgpl3)))
5594 (define-public infernal
5600 (uri (string-append "http://eddylab.org/software/infernal/"
5601 "infernal-" version ".tar.gz"))
5604 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5605 (build-system gnu-build-system)
5607 `(("perl" ,perl))) ; for tests
5608 (home-page "http://eddylab.org/infernal/")
5609 (synopsis "Inference of RNA alignments")
5610 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5611 searching DNA sequence databases for RNA structure and sequence similarities.
5612 It is an implementation of a special case of profile stochastic context-free
5613 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5614 profile, but it scores a combination of sequence consensus and RNA secondary
5615 structure consensus, so in many cases, it is more capable of identifying RNA
5616 homologs that conserve their secondary structure more than their primary
5618 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5619 (supported-systems '("i686-linux" "x86_64-linux"))
5620 (license license:bsd-3)))
5622 (define-public r-centipede
5624 (name "r-centipede")
5628 (uri (string-append "http://download.r-forge.r-project.org/"
5629 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5632 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5633 (build-system r-build-system)
5634 (home-page "http://centipede.uchicago.edu/")
5635 (synopsis "Predict transcription factor binding sites")
5637 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5638 of the genome that are bound by particular transcription factors. It starts
5639 by identifying a set of candidate binding sites, and then aims to classify the
5640 sites according to whether each site is bound or not bound by a transcription
5641 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5642 between two different types of motif instances using as much relevant
5643 information as possible.")
5644 (license (list license:gpl2+ license:gpl3+))))
5646 (define-public r-vegan
5653 (uri (cran-uri "vegan" version))
5656 "1n57dzv2aid6iqd9fkqik401sidqanhzsawyak94qbiyh6dbd1x9"))))
5657 (build-system r-build-system)
5659 `(("gfortran" ,gfortran)))
5661 `(("r-cluster" ,r-cluster)
5662 ("r-lattice" ,r-lattice)
5665 ("r-permute" ,r-permute)))
5666 (home-page "https://cran.r-project.org/web/packages/vegan")
5667 (synopsis "Functions for community ecology")
5669 "The vegan package provides tools for descriptive community ecology. It
5670 has most basic functions of diversity analysis, community ordination and
5671 dissimilarity analysis. Most of its multivariate tools can be used for other
5672 data types as well.")
5673 (license license:gpl2+)))
5675 (define-public r-annotate
5682 (uri (bioconductor-uri "annotate" version))
5685 "0wlrp3v2jxw9is98ap39dfi7z97kmw1wv1xi4h7yfh12zpj2r8l0"))))
5686 (build-system r-build-system)
5688 `(("r-annotationdbi" ,r-annotationdbi)
5689 ("r-biobase" ,r-biobase)
5690 ("r-biocgenerics" ,r-biocgenerics)
5692 ("r-rcurl" ,r-rcurl)
5694 ("r-xtable" ,r-xtable)))
5696 "https://bioconductor.org/packages/annotate")
5697 (synopsis "Annotation for microarrays")
5698 (description "This package provides R environments for the annotation of
5700 (license license:artistic2.0)))
5702 (define-public r-geneplotter
5704 (name "r-geneplotter")
5709 (uri (bioconductor-uri "geneplotter" version))
5712 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
5713 (build-system r-build-system)
5715 `(("r-annotate" ,r-annotate)
5716 ("r-annotationdbi" ,r-annotationdbi)
5717 ("r-biobase" ,r-biobase)
5718 ("r-biocgenerics" ,r-biocgenerics)
5719 ("r-lattice" ,r-lattice)
5720 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5721 (home-page "https://bioconductor.org/packages/geneplotter")
5722 (synopsis "Graphics functions for genomic data")
5724 "This package provides functions for plotting genomic data.")
5725 (license license:artistic2.0)))
5727 (define-public r-genefilter
5729 (name "r-genefilter")
5734 (uri (bioconductor-uri "genefilter" version))
5737 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
5738 (build-system r-build-system)
5740 `(("gfortran" ,gfortran)))
5742 `(("r-annotate" ,r-annotate)
5743 ("r-annotationdbi" ,r-annotationdbi)
5744 ("r-biobase" ,r-biobase)
5745 ("r-s4vectors" ,r-s4vectors)
5746 ("r-survival" ,r-survival)))
5747 (home-page "https://bioconductor.org/packages/genefilter")
5748 (synopsis "Filter genes from high-throughput experiments")
5750 "This package provides basic functions for filtering genes from
5751 high-throughput sequencing experiments.")
5752 (license license:artistic2.0)))
5754 (define-public r-deseq2
5761 (uri (bioconductor-uri "DESeq2" version))
5764 "1hcxnkkjfvz4hj8iqidshwsjq7jnl1z7wj63dvcwlx1zx5aichyh"))))
5765 (properties `((upstream-name . "DESeq2")))
5766 (build-system r-build-system)
5768 `(("r-biobase" ,r-biobase)
5769 ("r-biocgenerics" ,r-biocgenerics)
5770 ("r-biocparallel" ,r-biocparallel)
5771 ("r-genefilter" ,r-genefilter)
5772 ("r-geneplotter" ,r-geneplotter)
5773 ("r-genomicranges" ,r-genomicranges)
5774 ("r-ggplot2" ,r-ggplot2)
5775 ("r-hmisc" ,r-hmisc)
5776 ("r-iranges" ,r-iranges)
5777 ("r-locfit" ,r-locfit)
5779 ("r-rcpparmadillo" ,r-rcpparmadillo)
5780 ("r-s4vectors" ,r-s4vectors)
5781 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5782 (home-page "https://bioconductor.org/packages/DESeq2")
5783 (synopsis "Differential gene expression analysis")
5785 "This package provides functions to estimate variance-mean dependence in
5786 count data from high-throughput nucleotide sequencing assays and test for
5787 differential expression based on a model using the negative binomial
5789 (license license:lgpl3+)))
5791 (define-public r-dexseq
5798 (uri (bioconductor-uri "DEXSeq" version))
5801 "0qxwnz2ffhav9slcn095k206cfza9i3i5l7w1154plf08gpy1d1d"))))
5802 (properties `((upstream-name . "DEXSeq")))
5803 (build-system r-build-system)
5805 `(("r-annotationdbi" ,r-annotationdbi)
5806 ("r-biobase" ,r-biobase)
5807 ("r-biocgenerics" ,r-biocgenerics)
5808 ("r-biocparallel" ,r-biocparallel)
5809 ("r-biomart" ,r-biomart)
5810 ("r-deseq2" ,r-deseq2)
5811 ("r-genefilter" ,r-genefilter)
5812 ("r-geneplotter" ,r-geneplotter)
5813 ("r-genomicranges" ,r-genomicranges)
5814 ("r-hwriter" ,r-hwriter)
5815 ("r-iranges" ,r-iranges)
5816 ("r-rcolorbrewer" ,r-rcolorbrewer)
5817 ("r-rsamtools" ,r-rsamtools)
5818 ("r-s4vectors" ,r-s4vectors)
5819 ("r-statmod" ,r-statmod)
5820 ("r-stringr" ,r-stringr)
5821 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5822 (home-page "https://bioconductor.org/packages/DEXSeq")
5823 (synopsis "Inference of differential exon usage in RNA-Seq")
5825 "This package is focused on finding differential exon usage using RNA-seq
5826 exon counts between samples with different experimental designs. It provides
5827 functions that allows the user to make the necessary statistical tests based
5828 on a model that uses the negative binomial distribution to estimate the
5829 variance between biological replicates and generalized linear models for
5830 testing. The package also provides functions for the visualization and
5831 exploration of the results.")
5832 (license license:gpl3+)))
5834 (define-public r-annotationforge
5836 (name "r-annotationforge")
5841 (uri (bioconductor-uri "AnnotationForge" version))
5844 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
5846 `((upstream-name . "AnnotationForge")))
5847 (build-system r-build-system)
5849 `(("r-annotationdbi" ,r-annotationdbi)
5850 ("r-biobase" ,r-biobase)
5851 ("r-biocgenerics" ,r-biocgenerics)
5853 ("r-rcurl" ,r-rcurl)
5854 ("r-rsqlite" ,r-rsqlite)
5855 ("r-s4vectors" ,r-s4vectors)
5857 (home-page "https://bioconductor.org/packages/AnnotationForge")
5858 (synopsis "Code for building annotation database packages")
5860 "This package provides code for generating Annotation packages and their
5861 databases. Packages produced are intended to be used with AnnotationDbi.")
5862 (license license:artistic2.0)))
5864 (define-public r-rbgl
5871 (uri (bioconductor-uri "RBGL" version))
5874 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
5875 (properties `((upstream-name . "RBGL")))
5876 (build-system r-build-system)
5877 (propagated-inputs `(("r-graph" ,r-graph)))
5878 (home-page "https://www.bioconductor.org/packages/RBGL")
5879 (synopsis "Interface to the Boost graph library")
5881 "This package provides a fairly extensive and comprehensive interface to
5882 the graph algorithms contained in the Boost library.")
5883 (license license:artistic2.0)))
5885 (define-public r-gseabase
5892 (uri (bioconductor-uri "GSEABase" version))
5895 "0kpkl6c5lrar6ip7wlhvd5axqlb9lb5l3lgbdb3dlih32c3nz0yq"))))
5896 (properties `((upstream-name . "GSEABase")))
5897 (build-system r-build-system)
5899 `(("r-annotate" ,r-annotate)
5900 ("r-annotationdbi" ,r-annotationdbi)
5901 ("r-biobase" ,r-biobase)
5902 ("r-biocgenerics" ,r-biocgenerics)
5903 ("r-graph" ,r-graph)
5905 (home-page "https://bioconductor.org/packages/GSEABase")
5906 (synopsis "Gene set enrichment data structures and methods")
5908 "This package provides classes and methods to support @dfn{Gene Set
5909 Enrichment Analysis} (GSEA).")
5910 (license license:artistic2.0)))
5912 (define-public r-category
5919 (uri (bioconductor-uri "Category" version))
5922 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
5923 (properties `((upstream-name . "Category")))
5924 (build-system r-build-system)
5926 `(("r-annotate" ,r-annotate)
5927 ("r-annotationdbi" ,r-annotationdbi)
5928 ("r-biobase" ,r-biobase)
5929 ("r-biocgenerics" ,r-biocgenerics)
5930 ("r-genefilter" ,r-genefilter)
5931 ("r-graph" ,r-graph)
5932 ("r-gseabase" ,r-gseabase)
5933 ("r-matrix" ,r-matrix)
5936 (home-page "https://bioconductor.org/packages/Category")
5937 (synopsis "Category analysis")
5939 "This package provides a collection of tools for performing category
5941 (license license:artistic2.0)))
5943 (define-public r-gostats
5950 (uri (bioconductor-uri "GOstats" version))
5953 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
5954 (properties `((upstream-name . "GOstats")))
5955 (build-system r-build-system)
5957 `(("r-annotate" ,r-annotate)
5958 ("r-annotationdbi" ,r-annotationdbi)
5959 ("r-annotationforge" ,r-annotationforge)
5960 ("r-biobase" ,r-biobase)
5961 ("r-category" ,r-category)
5962 ("r-go-db" ,r-go-db)
5963 ("r-graph" ,r-graph)
5964 ("r-rgraphviz" ,r-rgraphviz)
5965 ("r-rbgl" ,r-rbgl)))
5966 (home-page "https://bioconductor.org/packages/GOstats")
5967 (synopsis "Tools for manipulating GO and microarrays")
5969 "This package provides a set of tools for interacting with GO and
5970 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5971 testing and other simple calculations.")
5972 (license license:artistic2.0)))
5974 (define-public r-shortread
5976 (name "r-shortread")
5981 (uri (bioconductor-uri "ShortRead" version))
5984 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
5985 (properties `((upstream-name . "ShortRead")))
5986 (build-system r-build-system)
5990 `(("r-biobase" ,r-biobase)
5991 ("r-biocgenerics" ,r-biocgenerics)
5992 ("r-biocparallel" ,r-biocparallel)
5993 ("r-biostrings" ,r-biostrings)
5994 ("r-genomeinfodb" ,r-genomeinfodb)
5995 ("r-genomicalignments" ,r-genomicalignments)
5996 ("r-genomicranges" ,r-genomicranges)
5997 ("r-hwriter" ,r-hwriter)
5998 ("r-iranges" ,r-iranges)
5999 ("r-lattice" ,r-lattice)
6000 ("r-latticeextra" ,r-latticeextra)
6001 ("r-rsamtools" ,r-rsamtools)
6002 ("r-s4vectors" ,r-s4vectors)
6003 ("r-xvector" ,r-xvector)
6004 ("r-zlibbioc" ,r-zlibbioc)))
6005 (home-page "https://bioconductor.org/packages/ShortRead")
6006 (synopsis "FASTQ input and manipulation tools")
6008 "This package implements sampling, iteration, and input of FASTQ files.
6009 It includes functions for filtering and trimming reads, and for generating a
6010 quality assessment report. Data are represented as
6011 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6012 purposes. The package also contains legacy support for early single-end,
6013 ungapped alignment formats.")
6014 (license license:artistic2.0)))
6016 (define-public r-systempiper
6018 (name "r-systempiper")
6023 (uri (bioconductor-uri "systemPipeR" version))
6026 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6027 (properties `((upstream-name . "systemPipeR")))
6028 (build-system r-build-system)
6030 `(("r-annotate" ,r-annotate)
6031 ("r-batchjobs" ,r-batchjobs)
6032 ("r-biocgenerics" ,r-biocgenerics)
6033 ("r-biostrings" ,r-biostrings)
6034 ("r-deseq2" ,r-deseq2)
6035 ("r-edger" ,r-edger)
6036 ("r-genomicfeatures" ,r-genomicfeatures)
6037 ("r-genomicranges" ,r-genomicranges)
6038 ("r-ggplot2" ,r-ggplot2)
6039 ("r-go-db" ,r-go-db)
6040 ("r-gostats" ,r-gostats)
6041 ("r-limma" ,r-limma)
6042 ("r-pheatmap" ,r-pheatmap)
6043 ("r-rjson" ,r-rjson)
6044 ("r-rsamtools" ,r-rsamtools)
6045 ("r-shortread" ,r-shortread)
6046 ("r-summarizedexperiment" ,r-summarizedexperiment)
6047 ("r-variantannotation" ,r-variantannotation)))
6048 (home-page "https://github.com/tgirke/systemPipeR")
6049 (synopsis "Next generation sequencing workflow and reporting environment")
6051 "This R package provides tools for building and running automated
6052 end-to-end analysis workflows for a wide range of @dfn{next generation
6053 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6054 Important features include a uniform workflow interface across different NGS
6055 applications, automated report generation, and support for running both R and
6056 command-line software, such as NGS aligners or peak/variant callers, on local
6057 computers or compute clusters. Efficient handling of complex sample sets and
6058 experimental designs is facilitated by a consistently implemented sample
6059 annotation infrastructure.")
6060 (license license:artistic2.0)))
6062 (define-public r-grohmm
6069 (uri (bioconductor-uri "groHMM" version))
6072 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6073 (properties `((upstream-name . "groHMM")))
6074 (build-system r-build-system)
6076 `(("r-genomeinfodb" ,r-genomeinfodb)
6077 ("r-genomicalignments" ,r-genomicalignments)
6078 ("r-genomicranges" ,r-genomicranges)
6079 ("r-iranges" ,r-iranges)
6081 ("r-rtracklayer" ,r-rtracklayer)
6082 ("r-s4vectors" ,r-s4vectors)))
6083 (home-page "https://github.com/Kraus-Lab/groHMM")
6084 (synopsis "GRO-seq analysis pipeline")
6086 "This package provides a pipeline for the analysis of GRO-seq data.")
6087 (license license:gpl3+)))
6089 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6091 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6095 ;; We cannot use bioconductor-uri here because this tarball is
6096 ;; located under "data/annotation/" instead of "bioc/".
6097 (uri (string-append "https://bioconductor.org/packages/"
6098 "release/data/annotation/src/contrib"
6099 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6103 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6105 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6106 (build-system r-build-system)
6107 ;; As this package provides little more than a very large data file it
6108 ;; doesn't make sense to build substitutes.
6109 (arguments `(#:substitutable? #f))
6111 `(("r-genomicfeatures" ,r-genomicfeatures)))
6113 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6114 (synopsis "Annotation package for human genome in TxDb format")
6116 "This package provides an annotation database of Homo sapiens genome
6117 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6118 track. The database is exposed as a @code{TxDb} object.")
6119 (license license:artistic2.0)))
6121 (define-public r-sparql
6127 (uri (cran-uri "SPARQL" version))
6130 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6131 (properties `((upstream-name . "SPARQL")))
6132 (build-system r-build-system)
6134 `(("r-rcurl" ,r-rcurl)
6136 (home-page "http://cran.r-project.org/web/packages/SPARQL")
6137 (synopsis "SPARQL client for R")
6138 (description "This package provides an interface to use SPARQL to pose
6139 SELECT or UPDATE queries to an end-point.")
6140 ;; The only license indication is found in the DESCRIPTION file,
6141 ;; which states GPL-3. So we cannot assume GPLv3+.
6142 (license license:gpl3)))
6144 (define-public vsearch
6152 "https://github.com/torognes/vsearch/archive/v"
6154 (file-name (string-append name "-" version ".tar.gz"))
6157 "0rplgpvsdkxw0k371ckxrp6i77jn93ckhslaazwbyd85m83nkynr"))
6158 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6161 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6162 ;; for this in the patch.
6163 (delete-file "src/city.h")
6164 (delete-file "src/citycrc.h")
6165 (delete-file "src/city.cc")
6167 (build-system gnu-build-system)
6170 (modify-phases %standard-phases
6171 (add-after 'unpack 'autogen
6172 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6176 ("cityhash" ,cityhash)))
6178 `(("autoconf" ,autoconf)
6179 ("automake" ,automake)))
6180 (synopsis "Sequence search tools for metagenomics")
6182 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6183 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6184 masking. The tool takes advantage of parallelism in the form of SIMD
6185 vectorization as well as multiple threads to perform accurate alignments at
6186 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6187 Needleman-Wunsch).")
6188 (home-page "https://github.com/torognes/vsearch")
6189 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6191 (supported-systems '("x86_64-linux"))
6192 ;; Dual licensed; also includes public domain source.
6193 (license (list license:gpl3 license:bsd-2))))
6195 (define-public pardre
6198 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6203 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6207 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6208 (build-system gnu-build-system)
6210 `(#:tests? #f ; no tests included
6212 (modify-phases %standard-phases
6215 (lambda* (#:key outputs #:allow-other-keys)
6216 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6217 (install-file "ParDRe" bin)
6220 `(("openmpi" ,openmpi)
6222 (synopsis "Parallel tool to remove duplicate DNA reads")
6224 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6225 Duplicate reads can be seen as identical or nearly identical sequences with
6226 some mismatches. This tool lets users avoid the analysis of unnecessary
6227 reads, reducing the time of subsequent procedures with the
6228 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6229 in order to exploit the parallel capabilities of multicore clusters. It is
6230 faster than multithreaded counterparts (end of 2015) for the same number of
6231 cores and, thanks to the message-passing technology, it can be executed on
6233 (home-page "https://sourceforge.net/projects/pardre/")
6234 (license license:gpl3+)))
6236 (define-public ruby-bio-kseq
6238 (name "ruby-bio-kseq")
6243 (uri (rubygems-uri "bio-kseq" version))
6246 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6247 (build-system ruby-build-system)
6249 `(#:test-target "spec"))
6251 `(("bundler" ,bundler)
6252 ("ruby-rspec" ,ruby-rspec)
6253 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6256 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6258 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6259 FASTQ parsing code. It provides a fast iterator over sequences and their
6261 (home-page "https://github.com/gusevfe/bio-kseq")
6262 (license license:expat)))
6264 (define-public bio-locus
6271 (uri (rubygems-uri "bio-locus" version))
6274 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6275 (build-system ruby-build-system)
6277 `(("ruby-rspec" ,ruby-rspec)))
6278 (synopsis "Tool for fast querying of genome locations")
6280 "Bio-locus is a tabix-like tool for fast querying of genome
6281 locations. Many file formats in bioinformatics contain records that
6282 start with a chromosome name and a position for a SNP, or a start-end
6283 position for indels. Bio-locus allows users to store this chr+pos or
6284 chr+pos+alt information in a database.")
6285 (home-page "https://github.com/pjotrp/bio-locus")
6286 (license license:expat)))
6288 (define-public bio-blastxmlparser
6290 (name "bio-blastxmlparser")
6294 (uri (rubygems-uri "bio-blastxmlparser" version))
6297 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6298 (build-system ruby-build-system)
6300 `(("ruby-bio-logger" ,ruby-bio-logger)
6301 ("ruby-nokogiri" ,ruby-nokogiri)))
6303 `(("ruby-rspec" ,ruby-rspec)))
6304 (synopsis "Fast big data BLAST XML parser and library")
6306 "Very fast parallel big-data BLAST XML file parser which can be used as
6307 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6308 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6309 (home-page "https://github.com/pjotrp/blastxmlparser")
6310 (license license:expat)))
6312 (define-public bioruby
6319 (uri (rubygems-uri "bio" version))
6322 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6323 (build-system ruby-build-system)
6325 `(("ruby-libxml" ,ruby-libxml)))
6327 `(("which" ,which))) ; required for test phase
6330 (modify-phases %standard-phases
6331 (add-before 'build 'patch-test-command
6333 (substitute* '("test/functional/bio/test_command.rb")
6334 (("/bin/sh") (which "sh")))
6335 (substitute* '("test/functional/bio/test_command.rb")
6336 (("/bin/ls") (which "ls")))
6337 (substitute* '("test/functional/bio/test_command.rb")
6338 (("which") (which "which")))
6339 (substitute* '("test/functional/bio/test_command.rb",
6340 "test/data/command/echoarg2.sh")
6341 (("/bin/echo") (which "echo")))
6343 (synopsis "Ruby library, shell and utilities for bioinformatics")
6344 (description "BioRuby comes with a comprehensive set of Ruby development
6345 tools and libraries for bioinformatics and molecular biology. BioRuby has
6346 components for sequence analysis, pathway analysis, protein modelling and
6347 phylogenetic analysis; it supports many widely used data formats and provides
6348 easy access to databases, external programs and public web services, including
6349 BLAST, KEGG, GenBank, MEDLINE and GO.")
6350 (home-page "http://bioruby.org/")
6351 ;; Code is released under Ruby license, except for setup
6352 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6353 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6355 (define-public r-acsnminer
6357 (name "r-acsnminer")
6358 (version "0.16.8.25")
6361 (uri (cran-uri "ACSNMineR" version))
6364 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6365 (properties `((upstream-name . "ACSNMineR")))
6366 (build-system r-build-system)
6368 `(("r-ggplot2" ,r-ggplot2)
6369 ("r-gridextra" ,r-gridextra)))
6370 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6371 (synopsis "Gene enrichment analysis")
6373 "This package provides tools to compute and represent gene set enrichment
6374 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6375 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6376 enrichment can be run with hypergeometric test or Fisher exact test, and can
6377 use multiple corrections. Visualization of data can be done either by
6378 barplots or heatmaps.")
6379 (license license:gpl2+)))
6381 (define-public r-biocgenerics
6383 (name "r-biocgenerics")
6387 (uri (bioconductor-uri "BiocGenerics" version))
6390 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6392 `((upstream-name . "BiocGenerics")))
6393 (build-system r-build-system)
6394 (home-page "https://bioconductor.org/packages/BiocGenerics")
6395 (synopsis "S4 generic functions for Bioconductor")
6397 "This package provides S4 generic functions needed by many Bioconductor
6399 (license license:artistic2.0)))
6401 (define-public r-biocinstaller
6403 (name "r-biocinstaller")
6407 (uri (bioconductor-uri "BiocInstaller" version))
6410 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6412 `((upstream-name . "BiocInstaller")))
6413 (build-system r-build-system)
6414 (home-page "https://bioconductor.org/packages/BiocInstaller")
6415 (synopsis "Install Bioconductor packages")
6416 (description "This package is used to install and update R packages from
6417 Bioconductor, CRAN, and Github.")
6418 (license license:artistic2.0)))
6420 (define-public r-biocviews
6422 (name "r-biocviews")
6426 (uri (bioconductor-uri "biocViews" version))
6429 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6431 `((upstream-name . "biocViews")))
6432 (build-system r-build-system)
6434 `(("r-biobase" ,r-biobase)
6435 ("r-graph" ,r-graph)
6437 ("r-rcurl" ,r-rcurl)
6439 ("r-runit" ,r-runit)))
6440 (home-page "https://bioconductor.org/packages/biocViews")
6441 (synopsis "Bioconductor package categorization helper")
6442 (description "The purpose of biocViews is to create HTML pages that
6443 categorize packages in a Bioconductor package repository according to keywords,
6444 also known as views, in a controlled vocabulary.")
6445 (license license:artistic2.0)))
6447 (define-public r-bookdown
6453 (uri (cran-uri "bookdown" version))
6456 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
6457 (build-system r-build-system)
6459 `(("r-htmltools" ,r-htmltools)
6460 ("r-knitr" ,r-knitr)
6461 ("r-rmarkdown" ,r-rmarkdown)
6462 ("r-yaml" ,r-yaml)))
6463 (home-page "https://github.com/rstudio/bookdown")
6464 (synopsis "Authoring books and technical documents with R markdown")
6465 (description "This package provides output formats and utilities for
6466 authoring books and technical documents with R Markdown.")
6467 (license license:gpl3)))
6469 (define-public r-biocstyle
6471 (name "r-biocstyle")
6475 (uri (bioconductor-uri "BiocStyle" version))
6478 "05f2j9fx8s5gh4f8qkl6wcz32ghz04wxhqb3xxcn1bj24qd7x1x8"))))
6480 `((upstream-name . "BiocStyle")))
6481 (build-system r-build-system)
6483 `(("r-bookdown" ,r-bookdown)
6484 ("r-knitr" ,r-knitr)
6485 ("r-rmarkdown" ,r-rmarkdown)
6486 ("r-yaml" ,r-yaml)))
6487 (home-page "https://bioconductor.org/packages/BiocStyle")
6488 (synopsis "Bioconductor formatting styles")
6489 (description "This package provides standard formatting styles for
6490 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6492 (license license:artistic2.0)))
6494 (define-public r-bioccheck
6496 (name "r-bioccheck")
6500 (uri (bioconductor-uri "BiocCheck" version))
6503 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6505 `((upstream-name . "BiocCheck")))
6506 (build-system r-build-system)
6509 (modify-phases %standard-phases
6510 ;; This package can be used by calling BiocCheck(<package>) from
6511 ;; within R, or by running R CMD BiocCheck <package>. This phase
6512 ;; makes sure the latter works. For this to work, the BiocCheck
6513 ;; script must be somewhere on the PATH (not the R bin directory).
6514 (add-after 'install 'install-bioccheck-subcommand
6515 (lambda* (#:key outputs #:allow-other-keys)
6516 (let* ((out (assoc-ref outputs "out"))
6517 (dest-dir (string-append out "/bin"))
6519 (string-append out "/site-library/BiocCheck/script/")))
6521 (symlink (string-append script-dir "/checkBadDeps.R")
6522 (string-append dest-dir "/checkBadDeps.R"))
6523 (symlink (string-append script-dir "/BiocCheck")
6524 (string-append dest-dir "/BiocCheck")))
6527 `(("r-codetools" ,r-codetools)
6528 ("r-graph" ,r-graph)
6530 ("r-optparse" ,r-optparse)
6531 ("r-biocinstaller" ,r-biocinstaller)
6532 ("r-biocviews" ,r-biocviews)
6533 ("r-stringdist" ,r-stringdist)))
6534 (home-page "https://bioconductor.org/packages/BiocCheck")
6535 (synopsis "Executes Bioconductor-specific package checks")
6536 (description "This package contains tools to perform additional quality
6537 checks on R packages that are to be submitted to the Bioconductor repository.")
6538 (license license:artistic2.0)))
6540 (define-public r-getopt
6547 (uri (cran-uri "getopt" version))
6550 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6551 (build-system r-build-system)
6552 (home-page "https://github.com/trevorld/getopt")
6553 (synopsis "Command-line option processor for R")
6555 "This package is designed to be used with Rscript to write shebang
6556 scripts that accept short and long options. Many users will prefer to
6557 use the packages @code{optparse} or @code{argparse} which add extra
6558 features like automatically generated help options and usage texts,
6559 support for default values, positional argument support, etc.")
6560 (license license:gpl2+)))
6562 (define-public r-optparse
6569 (uri (cran-uri "optparse" version))
6572 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6573 (build-system r-build-system)
6575 `(("r-getopt" ,r-getopt)))
6577 "https://github.com/trevorld/optparse")
6578 (synopsis "Command line option parser")
6580 "This package provides a command line parser inspired by Python's
6581 @code{optparse} library to be used with Rscript to write shebang scripts
6582 that accept short and long options.")
6583 (license license:gpl2+)))
6585 (define-public r-dnacopy
6591 (uri (bioconductor-uri "DNAcopy" version))
6594 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6596 `((upstream-name . "DNAcopy")))
6597 (build-system r-build-system)
6599 `(("gfortran" ,gfortran)))
6600 (home-page "https://bioconductor.org/packages/DNAcopy")
6601 (synopsis "Implementation of a circular binary segmentation algorithm")
6602 (description "This package implements the circular binary segmentation (CBS)
6603 algorithm to segment DNA copy number data and identify genomic regions with
6604 abnormal copy number.")
6605 (license license:gpl2+)))
6607 (define-public r-s4vectors
6609 (name "r-s4vectors")
6613 (uri (bioconductor-uri "S4Vectors" version))
6616 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6618 `((upstream-name . "S4Vectors")))
6619 (build-system r-build-system)
6621 `(("r-biocgenerics" ,r-biocgenerics)))
6622 (home-page "https://bioconductor.org/packages/S4Vectors")
6623 (synopsis "S4 implementation of vectors and lists")
6625 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6626 classes and a set of generic functions that extend the semantic of ordinary
6627 vectors and lists in R. Package developers can easily implement vector-like
6628 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6629 In addition, a few low-level concrete subclasses of general interest (e.g.
6630 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6631 S4Vectors package itself.")
6632 (license license:artistic2.0)))
6634 (define-public r-seqinr
6641 (uri (cran-uri "seqinr" version))
6644 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6645 (build-system r-build-system)
6647 `(("r-ade4" ,r-ade4)
6648 ("r-segmented" ,r-segmented)))
6651 (home-page "http://seqinr.r-forge.r-project.org/")
6652 (synopsis "Biological sequences retrieval and analysis")
6654 "This package provides tools for exploratory data analysis and data
6655 visualization of biological sequence (DNA and protein) data. It also includes
6656 utilities for sequence data management under the ACNUC system.")
6657 (license license:gpl2+)))
6659 (define-public r-iranges
6665 (uri (bioconductor-uri "IRanges" version))
6668 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
6670 `((upstream-name . "IRanges")))
6671 (build-system r-build-system)
6673 `(("r-biocgenerics" ,r-biocgenerics)
6674 ("r-s4vectors" ,r-s4vectors)))
6675 (home-page "https://bioconductor.org/packages/IRanges")
6676 (synopsis "Infrastructure for manipulating intervals on sequences")
6678 "This package provides efficient low-level and highly reusable S4 classes
6679 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6680 generally, data that can be organized sequentially (formally defined as
6681 @code{Vector} objects), as well as views on these @code{Vector} objects.
6682 Efficient list-like classes are also provided for storing big collections of
6683 instances of the basic classes. All classes in the package use consistent
6684 naming and share the same rich and consistent \"Vector API\" as much as
6686 (license license:artistic2.0)))
6688 (define-public r-genomeinfodbdata
6690 (name "r-genomeinfodbdata")
6694 ;; We cannot use bioconductor-uri here because this tarball is
6695 ;; located under "data/annotation/" instead of "bioc/".
6696 (uri (string-append "https://bioconductor.org/packages/release/"
6697 "data/annotation/src/contrib/GenomeInfoDbData_"
6701 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6703 `((upstream-name . "GenomeInfoDbData")))
6704 (build-system r-build-system)
6705 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
6706 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6707 (description "This package contains data for mapping between NCBI taxonomy
6708 ID and species. It is used by functions in the GenomeInfoDb package.")
6709 (license license:artistic2.0)))
6711 (define-public r-genomeinfodb
6713 (name "r-genomeinfodb")
6717 (uri (bioconductor-uri "GenomeInfoDb" version))
6720 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
6722 `((upstream-name . "GenomeInfoDb")))
6723 (build-system r-build-system)
6725 `(("r-biocgenerics" ,r-biocgenerics)
6726 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6727 ("r-iranges" ,r-iranges)
6728 ("r-rcurl" ,r-rcurl)
6729 ("r-s4vectors" ,r-s4vectors)))
6730 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
6731 (synopsis "Utilities for manipulating chromosome identifiers")
6733 "This package contains data and functions that define and allow
6734 translation between different chromosome sequence naming conventions (e.g.,
6735 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6736 names in their natural, rather than lexicographic, order.")
6737 (license license:artistic2.0)))
6739 (define-public r-edger
6745 (uri (bioconductor-uri "edgeR" version))
6748 "01qnxwr9rmz8r5ga3hvjk632365ga2aygx71mxkk7jiad2pjznsp"))))
6749 (properties `((upstream-name . "edgeR")))
6750 (build-system r-build-system)
6752 `(("r-limma" ,r-limma)
6753 ("r-locfit" ,r-locfit)
6755 ("r-statmod" ,r-statmod))) ;for estimateDisp
6756 (home-page "http://bioinf.wehi.edu.au/edgeR")
6757 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6758 (description "This package can do differential expression analysis of
6759 RNA-seq expression profiles with biological replication. It implements a range
6760 of statistical methodology based on the negative binomial distributions,
6761 including empirical Bayes estimation, exact tests, generalized linear models
6762 and quasi-likelihood tests. It be applied to differential signal analysis of
6763 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6765 (license license:gpl2+)))
6767 (define-public r-variantannotation
6769 (name "r-variantannotation")
6773 (uri (bioconductor-uri "VariantAnnotation" version))
6776 "1lllp2vgyfbrar1yg28ji7am470hfzrzxm1bgdk68xpnrwcgcl25"))))
6778 `((upstream-name . "VariantAnnotation")))
6782 `(("r-annotationdbi" ,r-annotationdbi)
6783 ("r-biobase" ,r-biobase)
6784 ("r-biocgenerics" ,r-biocgenerics)
6785 ("r-biostrings" ,r-biostrings)
6786 ("r-bsgenome" ,r-bsgenome)
6788 ("r-genomeinfodb" ,r-genomeinfodb)
6789 ("r-genomicfeatures" ,r-genomicfeatures)
6790 ("r-genomicranges" ,r-genomicranges)
6791 ("r-iranges" ,r-iranges)
6792 ("r-summarizedexperiment" ,r-summarizedexperiment)
6793 ("r-rsamtools" ,r-rsamtools)
6794 ("r-rtracklayer" ,r-rtracklayer)
6795 ("r-s4vectors" ,r-s4vectors)
6796 ("r-xvector" ,r-xvector)
6797 ("r-zlibbioc" ,r-zlibbioc)))
6798 (build-system r-build-system)
6799 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6800 (synopsis "Package for annotation of genetic variants")
6801 (description "This R package can annotate variants, compute amino acid
6802 coding changes and predict coding outcomes.")
6803 (license license:artistic2.0)))
6805 (define-public r-limma
6811 (uri (bioconductor-uri "limma" version))
6814 "0a15gsaky0hfrkx8wrrmp0labzxpq6m2hrd33zl206wyas8bqzcs"))))
6815 (build-system r-build-system)
6816 (home-page "http://bioinf.wehi.edu.au/limma")
6817 (synopsis "Package for linear models for microarray and RNA-seq data")
6818 (description "This package can be used for the analysis of gene expression
6819 studies, especially the use of linear models for analysing designed experiments
6820 and the assessment of differential expression. The analysis methods apply to
6821 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6822 (license license:gpl2+)))
6824 (define-public r-xvector
6830 (uri (bioconductor-uri "XVector" version))
6833 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
6835 `((upstream-name . "XVector")))
6836 (build-system r-build-system)
6839 (modify-phases %standard-phases
6840 (add-after 'unpack 'use-system-zlib
6842 (substitute* "DESCRIPTION"
6843 (("zlibbioc, ") ""))
6844 (substitute* "NAMESPACE"
6845 (("import\\(zlibbioc\\)") ""))
6850 `(("r-biocgenerics" ,r-biocgenerics)
6851 ("r-iranges" ,r-iranges)
6852 ("r-s4vectors" ,r-s4vectors)))
6853 (home-page "https://bioconductor.org/packages/XVector")
6854 (synopsis "Representation and manpulation of external sequences")
6856 "This package provides memory efficient S4 classes for storing sequences
6857 \"externally\" (behind an R external pointer, or on disk).")
6858 (license license:artistic2.0)))
6860 (define-public r-genomicranges
6862 (name "r-genomicranges")
6866 (uri (bioconductor-uri "GenomicRanges" version))
6869 "10ra2sjn17h6gilm9iz0cygp9ijpgbirljlc4drwrnivnw9cmi2a"))))
6871 `((upstream-name . "GenomicRanges")))
6872 (build-system r-build-system)
6874 `(("r-biocgenerics" ,r-biocgenerics)
6875 ("r-genomeinfodb" ,r-genomeinfodb)
6876 ("r-iranges" ,r-iranges)
6877 ("r-s4vectors" ,r-s4vectors)
6878 ("r-xvector" ,r-xvector)))
6879 (home-page "https://bioconductor.org/packages/GenomicRanges")
6880 (synopsis "Representation and manipulation of genomic intervals")
6882 "This package provides tools to efficiently represent and manipulate
6883 genomic annotations and alignments is playing a central role when it comes to
6884 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6885 GenomicRanges package defines general purpose containers for storing and
6886 manipulating genomic intervals and variables defined along a genome.")
6887 (license license:artistic2.0)))
6889 (define-public r-biobase
6895 (uri (bioconductor-uri "Biobase" version))
6898 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
6900 `((upstream-name . "Biobase")))
6901 (build-system r-build-system)
6903 `(("r-biocgenerics" ,r-biocgenerics)))
6904 (home-page "https://bioconductor.org/packages/Biobase")
6905 (synopsis "Base functions for Bioconductor")
6907 "This package provides functions that are needed by many other packages
6908 on Bioconductor or which replace R functions.")
6909 (license license:artistic2.0)))
6911 (define-public r-annotationdbi
6913 (name "r-annotationdbi")
6917 (uri (bioconductor-uri "AnnotationDbi" version))
6920 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
6922 `((upstream-name . "AnnotationDbi")))
6923 (build-system r-build-system)
6925 `(("r-biobase" ,r-biobase)
6926 ("r-biocgenerics" ,r-biocgenerics)
6928 ("r-iranges" ,r-iranges)
6929 ("r-rsqlite" ,r-rsqlite)
6930 ("r-s4vectors" ,r-s4vectors)))
6931 (home-page "https://bioconductor.org/packages/AnnotationDbi")
6932 (synopsis "Annotation database interface")
6934 "This package provides user interface and database connection code for
6935 annotation data packages using SQLite data storage.")
6936 (license license:artistic2.0)))
6938 (define-public r-biomart
6944 (uri (bioconductor-uri "biomaRt" version))
6947 "1dn3ysf0vb3mmg2b3380g0j1ajf88x4rh7fddfp990h2xlnsy2cx"))))
6949 `((upstream-name . "biomaRt")))
6950 (build-system r-build-system)
6952 `(("r-annotationdbi" ,r-annotationdbi)
6953 ("r-progress" ,r-progress)
6954 ("r-rcurl" ,r-rcurl)
6955 ("r-stringr" ,r-stringr)
6957 (home-page "https://bioconductor.org/packages/biomaRt")
6958 (synopsis "Interface to BioMart databases")
6960 "biomaRt provides an interface to a growing collection of databases
6961 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6962 package enables retrieval of large amounts of data in a uniform way without
6963 the need to know the underlying database schemas or write complex SQL queries.
6964 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6965 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6966 users direct access to a diverse set of data and enable a wide range of
6967 powerful online queries from gene annotation to database mining.")
6968 (license license:artistic2.0)))
6970 (define-public r-biocparallel
6972 (name "r-biocparallel")
6976 (uri (bioconductor-uri "BiocParallel" version))
6979 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
6981 `((upstream-name . "BiocParallel")))
6982 (build-system r-build-system)
6984 `(("r-futile-logger" ,r-futile-logger)
6987 (home-page "https://bioconductor.org/packages/BiocParallel")
6988 (synopsis "Bioconductor facilities for parallel evaluation")
6990 "This package provides modified versions and novel implementation of
6991 functions for parallel evaluation, tailored to use with Bioconductor
6993 (license (list license:gpl2+ license:gpl3+))))
6995 (define-public r-biostrings
6997 (name "r-biostrings")
7001 (uri (bioconductor-uri "Biostrings" version))
7004 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7006 `((upstream-name . "Biostrings")))
7007 (build-system r-build-system)
7009 `(("r-biocgenerics" ,r-biocgenerics)
7010 ("r-iranges" ,r-iranges)
7011 ("r-s4vectors" ,r-s4vectors)
7012 ("r-xvector" ,r-xvector)))
7013 (home-page "https://bioconductor.org/packages/Biostrings")
7014 (synopsis "String objects and algorithms for biological sequences")
7016 "This package provides memory efficient string containers, string
7017 matching algorithms, and other utilities, for fast manipulation of large
7018 biological sequences or sets of sequences.")
7019 (license license:artistic2.0)))
7021 (define-public r-rsamtools
7023 (name "r-rsamtools")
7027 (uri (bioconductor-uri "Rsamtools" version))
7030 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7032 `((upstream-name . "Rsamtools")))
7033 (build-system r-build-system)
7036 (modify-phases %standard-phases
7037 (add-after 'unpack 'use-system-zlib
7039 (substitute* "DESCRIPTION"
7040 (("zlibbioc, ") ""))
7041 (substitute* "NAMESPACE"
7042 (("import\\(zlibbioc\\)") ""))
7047 `(("r-biocgenerics" ,r-biocgenerics)
7048 ("r-biocparallel" ,r-biocparallel)
7049 ("r-biostrings" ,r-biostrings)
7050 ("r-bitops" ,r-bitops)
7051 ("r-genomeinfodb" ,r-genomeinfodb)
7052 ("r-genomicranges" ,r-genomicranges)
7053 ("r-iranges" ,r-iranges)
7054 ("r-s4vectors" ,r-s4vectors)
7055 ("r-xvector" ,r-xvector)))
7056 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7057 (synopsis "Interface to samtools, bcftools, and tabix")
7059 "This package provides an interface to the 'samtools', 'bcftools', and
7060 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7061 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7063 (license license:expat)))
7065 (define-public r-delayedarray
7067 (name "r-delayedarray")
7071 (uri (bioconductor-uri "DelayedArray" version))
7074 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7076 `((upstream-name . "DelayedArray")))
7077 (build-system r-build-system)
7079 `(("r-biocgenerics" ,r-biocgenerics)
7080 ("r-s4vectors" ,r-s4vectors)
7081 ("r-iranges" ,r-iranges)
7082 ("r-matrixstats" ,r-matrixstats)))
7083 (home-page "https://bioconductor.org/packages/DelayedArray")
7084 (synopsis "Delayed operations on array-like objects")
7086 "Wrapping an array-like object (typically an on-disk object) in a
7087 @code{DelayedArray} object allows one to perform common array operations on it
7088 without loading the object in memory. In order to reduce memory usage and
7089 optimize performance, operations on the object are either delayed or executed
7090 using a block processing mechanism. Note that this also works on in-memory
7091 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7092 @code{Matrix} objects, and ordinary arrays and data frames.")
7093 (license license:artistic2.0)))
7095 (define-public r-summarizedexperiment
7097 (name "r-summarizedexperiment")
7101 (uri (bioconductor-uri "SummarizedExperiment" version))
7104 "1011r8l0k8420j31bmh4xdcp6ka5bzf4bqhip84v5b6alpkcbvmf"))))
7106 `((upstream-name . "SummarizedExperiment")))
7107 (build-system r-build-system)
7109 `(("r-biobase" ,r-biobase)
7110 ("r-biocgenerics" ,r-biocgenerics)
7111 ("r-delayedarray" ,r-delayedarray)
7112 ("r-genomeinfodb" ,r-genomeinfodb)
7113 ("r-genomicranges" ,r-genomicranges)
7114 ("r-iranges" ,r-iranges)
7115 ("r-matrix" ,r-matrix)
7116 ("r-s4vectors" ,r-s4vectors)))
7117 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7118 (synopsis "Container for representing genomic ranges by sample")
7120 "The SummarizedExperiment container contains one or more assays, each
7121 represented by a matrix-like object of numeric or other mode. The rows
7122 typically represent genomic ranges of interest and the columns represent
7124 (license license:artistic2.0)))
7126 (define-public r-genomicalignments
7128 (name "r-genomicalignments")
7132 (uri (bioconductor-uri "GenomicAlignments" version))
7135 "0sw30lj11wv7ifzypqm04lcah987crqwvj48wz3flaw3biw41zfi"))))
7137 `((upstream-name . "GenomicAlignments")))
7138 (build-system r-build-system)
7140 `(("r-biocgenerics" ,r-biocgenerics)
7141 ("r-biocparallel" ,r-biocparallel)
7142 ("r-biostrings" ,r-biostrings)
7143 ("r-genomeinfodb" ,r-genomeinfodb)
7144 ("r-genomicranges" ,r-genomicranges)
7145 ("r-iranges" ,r-iranges)
7146 ("r-rsamtools" ,r-rsamtools)
7147 ("r-s4vectors" ,r-s4vectors)
7148 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7149 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7150 (synopsis "Representation and manipulation of short genomic alignments")
7152 "This package provides efficient containers for storing and manipulating
7153 short genomic alignments (typically obtained by aligning short reads to a
7154 reference genome). This includes read counting, computing the coverage,
7155 junction detection, and working with the nucleotide content of the
7157 (license license:artistic2.0)))
7159 (define-public r-rtracklayer
7161 (name "r-rtracklayer")
7165 (uri (bioconductor-uri "rtracklayer" version))
7168 "12al1ygzy9p4myxa1fd817m28x2fj6f863znk9bw3hp7knbi98dh"))))
7169 (build-system r-build-system)
7172 (modify-phases %standard-phases
7173 (add-after 'unpack 'use-system-zlib
7175 (substitute* "DESCRIPTION"
7176 ((" zlibbioc,") ""))
7177 (substitute* "NAMESPACE"
7178 (("import\\(zlibbioc\\)") ""))
7183 `(("r-biocgenerics" ,r-biocgenerics)
7184 ("r-biostrings" ,r-biostrings)
7185 ("r-genomeinfodb" ,r-genomeinfodb)
7186 ("r-genomicalignments" ,r-genomicalignments)
7187 ("r-genomicranges" ,r-genomicranges)
7188 ("r-iranges" ,r-iranges)
7189 ("r-rcurl" ,r-rcurl)
7190 ("r-rsamtools" ,r-rsamtools)
7191 ("r-s4vectors" ,r-s4vectors)
7193 ("r-xvector" ,r-xvector)))
7194 (home-page "https://bioconductor.org/packages/rtracklayer")
7195 (synopsis "R interface to genome browsers and their annotation tracks")
7197 "rtracklayer is an extensible framework for interacting with multiple
7198 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7199 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7200 built-in). The user may export/import tracks to/from the supported browsers,
7201 as well as query and modify the browser state, such as the current viewport.")
7202 (license license:artistic2.0)))
7204 (define-public r-genomicfeatures
7206 (name "r-genomicfeatures")
7210 (uri (bioconductor-uri "GenomicFeatures" version))
7213 "1khjvq1ffhqavkwf8n7bilknci60lxbg52icrcf2vnb9k8rlpghs"))))
7215 `((upstream-name . "GenomicFeatures")))
7216 (build-system r-build-system)
7218 `(("r-annotationdbi" ,r-annotationdbi)
7219 ("r-biobase" ,r-biobase)
7220 ("r-biocgenerics" ,r-biocgenerics)
7221 ("r-biomart" ,r-biomart)
7222 ("r-biostrings" ,r-biostrings)
7224 ("r-genomeinfodb" ,r-genomeinfodb)
7225 ("r-genomicranges" ,r-genomicranges)
7226 ("r-iranges" ,r-iranges)
7227 ("r-rcurl" ,r-rcurl)
7228 ("r-rsqlite" ,r-rsqlite)
7229 ("r-rmysql" ,r-rmysql)
7230 ("r-rtracklayer" ,r-rtracklayer)
7231 ("r-s4vectors" ,r-s4vectors)
7232 ("r-xvector" ,r-xvector)))
7233 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7234 (synopsis "Tools for working with transcript centric annotations")
7236 "This package provides a set of tools and methods for making and
7237 manipulating transcript centric annotations. With these tools the user can
7238 easily download the genomic locations of the transcripts, exons and cds of a
7239 given organism, from either the UCSC Genome Browser or a BioMart
7240 database (more sources will be supported in the future). This information is
7241 then stored in a local database that keeps track of the relationship between
7242 transcripts, exons, cds and genes. Flexible methods are provided for
7243 extracting the desired features in a convenient format.")
7244 (license license:artistic2.0)))
7246 (define-public r-go-db
7252 (uri (string-append "https://www.bioconductor.org/packages/"
7253 "release/data/annotation/src/contrib/GO.db_"
7257 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7259 `((upstream-name . "GO.db")))
7260 (build-system r-build-system)
7262 `(("r-annotationdbi" ,r-annotationdbi)))
7263 (home-page "https://bioconductor.org/packages/GO.db")
7264 (synopsis "Annotation maps describing the entire Gene Ontology")
7266 "The purpose of this GO.db annotation package is to provide detailed
7267 information about the latest version of the Gene Ontologies.")
7268 (license license:artistic2.0)))
7270 (define-public r-graph
7276 (uri (bioconductor-uri "graph" version))
7279 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7280 (build-system r-build-system)
7282 `(("r-biocgenerics" ,r-biocgenerics)))
7283 (home-page "https://bioconductor.org/packages/graph")
7284 (synopsis "Handle graph data structures in R")
7286 "This package implements some simple graph handling capabilities for R.")
7287 (license license:artistic2.0)))
7289 (define-public r-topgo
7295 (uri (bioconductor-uri "topGO" version))
7298 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
7300 `((upstream-name . "topGO")))
7301 (build-system r-build-system)
7303 `(("r-annotationdbi" ,r-annotationdbi)
7305 ("r-biobase" ,r-biobase)
7306 ("r-biocgenerics" ,r-biocgenerics)
7307 ("r-go-db" ,r-go-db)
7308 ("r-graph" ,r-graph)
7309 ("r-lattice" ,r-lattice)
7310 ("r-matrixstats" ,r-matrixstats)
7311 ("r-sparsem" ,r-sparsem)))
7312 (home-page "https://bioconductor.org/packages/topGO")
7313 (synopsis "Enrichment analysis for gene ontology")
7315 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7316 terms while accounting for the topology of the GO graph. Different test
7317 statistics and different methods for eliminating local similarities and
7318 dependencies between GO terms can be implemented and applied.")
7319 ;; Any version of the LGPL applies.
7320 (license license:lgpl2.1+)))
7322 (define-public r-bsgenome
7328 (uri (bioconductor-uri "BSgenome" version))
7331 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7333 `((upstream-name . "BSgenome")))
7334 (build-system r-build-system)
7336 `(("r-biocgenerics" ,r-biocgenerics)
7337 ("r-biostrings" ,r-biostrings)
7338 ("r-genomeinfodb" ,r-genomeinfodb)
7339 ("r-genomicranges" ,r-genomicranges)
7340 ("r-iranges" ,r-iranges)
7341 ("r-rsamtools" ,r-rsamtools)
7342 ("r-rtracklayer" ,r-rtracklayer)
7343 ("r-s4vectors" ,r-s4vectors)
7344 ("r-xvector" ,r-xvector)))
7345 (home-page "https://bioconductor.org/packages/BSgenome")
7346 (synopsis "Infrastructure for Biostrings-based genome data packages")
7348 "This package provides infrastructure shared by all Biostrings-based
7349 genome data packages and support for efficient SNP representation.")
7350 (license license:artistic2.0)))
7352 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7354 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7358 ;; We cannot use bioconductor-uri here because this tarball is
7359 ;; located under "data/annotation/" instead of "bioc/".
7360 (uri (string-append "https://www.bioconductor.org/packages/"
7361 "release/data/annotation/src/contrib/"
7362 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7366 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7368 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7369 (build-system r-build-system)
7370 ;; As this package provides little more than a very large data file it
7371 ;; doesn't make sense to build substitutes.
7372 (arguments `(#:substitutable? #f))
7374 `(("r-bsgenome" ,r-bsgenome)))
7376 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7377 (synopsis "Full genome sequences for Homo sapiens")
7379 "This package provides full genome sequences for Homo sapiens from
7380 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7381 (license license:artistic2.0)))
7383 (define-public r-impute
7389 (uri (bioconductor-uri "impute" version))
7392 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7394 `(("gfortran" ,gfortran)))
7395 (build-system r-build-system)
7396 (home-page "https://bioconductor.org/packages/impute")
7397 (synopsis "Imputation for microarray data")
7399 "This package provides a function to impute missing gene expression
7400 microarray data, using nearest neighbor averaging.")
7401 (license license:gpl2+)))
7403 (define-public r-seqpattern
7405 (name "r-seqpattern")
7409 (uri (bioconductor-uri "seqPattern" version))
7412 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7414 `((upstream-name . "seqPattern")))
7415 (build-system r-build-system)
7417 `(("r-biostrings" ,r-biostrings)
7418 ("r-genomicranges" ,r-genomicranges)
7419 ("r-iranges" ,r-iranges)
7420 ("r-kernsmooth" ,r-kernsmooth)
7421 ("r-plotrix" ,r-plotrix)))
7422 (home-page "https://bioconductor.org/packages/seqPattern")
7423 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7425 "This package provides tools to visualize oligonucleotide patterns and
7426 sequence motif occurrences across a large set of sequences centred at a common
7427 reference point and sorted by a user defined feature.")
7428 (license license:gpl3+)))
7430 (define-public r-genomation
7432 (name "r-genomation")
7436 (uri (bioconductor-uri "genomation" version))
7439 "1ddd8c9w1f1i1ga9rpbwiic8rsaws1chdxx4j38bpyaiy4zhz1ca"))))
7440 (build-system r-build-system)
7442 `(("r-biostrings" ,r-biostrings)
7443 ("r-bsgenome" ,r-bsgenome)
7444 ("r-data-table" ,r-data-table)
7445 ("r-genomeinfodb" ,r-genomeinfodb)
7446 ("r-genomicalignments" ,r-genomicalignments)
7447 ("r-genomicranges" ,r-genomicranges)
7448 ("r-ggplot2" ,r-ggplot2)
7449 ("r-gridbase" ,r-gridbase)
7450 ("r-impute" ,r-impute)
7451 ("r-iranges" ,r-iranges)
7452 ("r-matrixstats" ,r-matrixstats)
7453 ("r-plotrix" ,r-plotrix)
7456 ("r-readr" ,r-readr)
7457 ("r-reshape2" ,r-reshape2)
7458 ("r-rsamtools" ,r-rsamtools)
7459 ("r-rtracklayer" ,r-rtracklayer)
7460 ("r-runit" ,r-runit)
7461 ("r-s4vectors" ,r-s4vectors)
7462 ("r-seqpattern" ,r-seqpattern)))
7463 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7464 (synopsis "Summary, annotation and visualization of genomic data")
7466 "This package provides a package for summary and annotation of genomic
7467 intervals. Users can visualize and quantify genomic intervals over
7468 pre-defined functional regions, such as promoters, exons, introns, etc. The
7469 genomic intervals represent regions with a defined chromosome position, which
7470 may be associated with a score, such as aligned reads from HT-seq experiments,
7471 TF binding sites, methylation scores, etc. The package can use any tabular
7472 genomic feature data as long as it has minimal information on the locations of
7473 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7474 (license license:artistic2.0)))
7476 (define-public r-genomationdata
7478 (name "r-genomationdata")
7482 ;; We cannot use bioconductor-uri here because this tarball is
7483 ;; located under "data/annotation/" instead of "bioc/".
7484 (uri (string-append "https://bioconductor.org/packages/"
7485 "release/data/experiment/src/contrib/"
7486 "genomationData_" version ".tar.gz"))
7489 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7490 (build-system r-build-system)
7491 ;; As this package provides little more than large data files, it doesn't
7492 ;; make sense to build substitutes.
7493 (arguments `(#:substitutable? #f))
7495 `(("r-knitr" ,r-knitr)))
7496 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7497 (synopsis "Experimental data for use with the genomation package")
7499 "This package contains experimental genetic data for use with the
7500 genomation package. Included are Chip Seq, Methylation and Cage data,
7501 downloaded from Encode.")
7502 (license license:gpl3+)))
7504 (define-public r-org-hs-eg-db
7506 (name "r-org-hs-eg-db")
7510 ;; We cannot use bioconductor-uri here because this tarball is
7511 ;; located under "data/annotation/" instead of "bioc/".
7512 (uri (string-append "https://www.bioconductor.org/packages/"
7513 "release/data/annotation/src/contrib/"
7514 "org.Hs.eg.db_" version ".tar.gz"))
7517 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7519 `((upstream-name . "org.Hs.eg.db")))
7520 (build-system r-build-system)
7522 `(("r-annotationdbi" ,r-annotationdbi)))
7523 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7524 (synopsis "Genome wide annotation for Human")
7526 "This package provides mappings from Entrez gene identifiers to various
7527 annotations for the human genome.")
7528 (license license:artistic2.0)))
7530 (define-public r-org-ce-eg-db
7532 (name "r-org-ce-eg-db")
7536 ;; We cannot use bioconductor-uri here because this tarball is
7537 ;; located under "data/annotation/" instead of "bioc/".
7538 (uri (string-append "https://www.bioconductor.org/packages/"
7539 "release/data/annotation/src/contrib/"
7540 "org.Ce.eg.db_" version ".tar.gz"))
7543 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7545 `((upstream-name . "org.Ce.eg.db")))
7546 (build-system r-build-system)
7548 `(("r-annotationdbi" ,r-annotationdbi)))
7549 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7550 (synopsis "Genome wide annotation for Worm")
7552 "This package provides mappings from Entrez gene identifiers to various
7553 annotations for the genome of the model worm Caenorhabditis elegans.")
7554 (license license:artistic2.0)))
7556 (define-public r-org-dm-eg-db
7558 (name "r-org-dm-eg-db")
7562 ;; We cannot use bioconductor-uri here because this tarball is
7563 ;; located under "data/annotation/" instead of "bioc/".
7564 (uri (string-append "https://www.bioconductor.org/packages/"
7565 "release/data/annotation/src/contrib/"
7566 "org.Dm.eg.db_" version ".tar.gz"))
7569 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7571 `((upstream-name . "org.Dm.eg.db")))
7572 (build-system r-build-system)
7574 `(("r-annotationdbi" ,r-annotationdbi)))
7575 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7576 (synopsis "Genome wide annotation for Fly")
7578 "This package provides mappings from Entrez gene identifiers to various
7579 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7580 (license license:artistic2.0)))
7582 (define-public r-org-mm-eg-db
7584 (name "r-org-mm-eg-db")
7588 ;; We cannot use bioconductor-uri here because this tarball is
7589 ;; located under "data/annotation/" instead of "bioc/".
7590 (uri (string-append "https://www.bioconductor.org/packages/"
7591 "release/data/annotation/src/contrib/"
7592 "org.Mm.eg.db_" version ".tar.gz"))
7595 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7597 `((upstream-name . "org.Mm.eg.db")))
7598 (build-system r-build-system)
7600 `(("r-annotationdbi" ,r-annotationdbi)))
7601 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7602 (synopsis "Genome wide annotation for Mouse")
7604 "This package provides mappings from Entrez gene identifiers to various
7605 annotations for the genome of the model mouse Mus musculus.")
7606 (license license:artistic2.0)))
7608 (define-public r-seqlogo
7615 (uri (bioconductor-uri "seqLogo" version))
7618 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7619 (properties `((upstream-name . "seqLogo")))
7620 (build-system r-build-system)
7621 (home-page "https://bioconductor.org/packages/seqLogo")
7622 (synopsis "Sequence logos for DNA sequence alignments")
7624 "seqLogo takes the position weight matrix of a DNA sequence motif and
7625 plots the corresponding sequence logo as introduced by Schneider and
7627 (license license:lgpl2.0+)))
7629 (define-public r-bsgenome-hsapiens-ucsc-hg19
7631 (name "r-bsgenome-hsapiens-ucsc-hg19")
7635 ;; We cannot use bioconductor-uri here because this tarball is
7636 ;; located under "data/annotation/" instead of "bioc/".
7637 (uri (string-append "https://www.bioconductor.org/packages/"
7638 "release/data/annotation/src/contrib/"
7639 "BSgenome.Hsapiens.UCSC.hg19_"
7643 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7645 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7646 (build-system r-build-system)
7647 ;; As this package provides little more than a very large data file it
7648 ;; doesn't make sense to build substitutes.
7649 (arguments `(#:substitutable? #f))
7651 `(("r-bsgenome" ,r-bsgenome)))
7653 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7654 (synopsis "Full genome sequences for Homo sapiens")
7656 "This package provides full genome sequences for Homo sapiens as provided
7657 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7658 (license license:artistic2.0)))
7660 (define-public r-bsgenome-mmusculus-ucsc-mm9
7662 (name "r-bsgenome-mmusculus-ucsc-mm9")
7666 ;; We cannot use bioconductor-uri here because this tarball is
7667 ;; located under "data/annotation/" instead of "bioc/".
7668 (uri (string-append "https://www.bioconductor.org/packages/"
7669 "release/data/annotation/src/contrib/"
7670 "BSgenome.Mmusculus.UCSC.mm9_"
7674 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7676 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7677 (build-system r-build-system)
7678 ;; As this package provides little more than a very large data file it
7679 ;; doesn't make sense to build substitutes.
7680 (arguments `(#:substitutable? #f))
7682 `(("r-bsgenome" ,r-bsgenome)))
7684 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7685 (synopsis "Full genome sequences for Mouse")
7687 "This package provides full genome sequences for Mus musculus (Mouse) as
7688 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7689 (license license:artistic2.0)))
7691 (define-public r-bsgenome-mmusculus-ucsc-mm10
7693 (name "r-bsgenome-mmusculus-ucsc-mm10")
7697 ;; We cannot use bioconductor-uri here because this tarball is
7698 ;; located under "data/annotation/" instead of "bioc/".
7699 (uri (string-append "https://www.bioconductor.org/packages/"
7700 "release/data/annotation/src/contrib/"
7701 "BSgenome.Mmusculus.UCSC.mm10_"
7705 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7707 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7708 (build-system r-build-system)
7709 ;; As this package provides little more than a very large data file it
7710 ;; doesn't make sense to build substitutes.
7711 (arguments `(#:substitutable? #f))
7713 `(("r-bsgenome" ,r-bsgenome)))
7715 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7716 (synopsis "Full genome sequences for Mouse")
7718 "This package provides full genome sequences for Mus
7719 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7720 in Biostrings objects.")
7721 (license license:artistic2.0)))
7723 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7725 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7729 ;; We cannot use bioconductor-uri here because this tarball is
7730 ;; located under "data/annotation/" instead of "bioc/".
7731 (uri (string-append "https://www.bioconductor.org/packages/"
7732 "release/data/annotation/src/contrib/"
7733 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7737 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7739 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7740 (build-system r-build-system)
7741 ;; As this package provides little more than a very large data file it
7742 ;; doesn't make sense to build substitutes.
7743 (arguments `(#:substitutable? #f))
7745 `(("r-bsgenome" ,r-bsgenome)
7746 ("r-genomicfeatures" ,r-genomicfeatures)
7747 ("r-annotationdbi" ,r-annotationdbi)))
7749 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7750 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7752 "This package loads a TxDb object, which is an R interface to
7753 prefabricated databases contained in this package. This package provides
7754 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7755 based on the knownGene track.")
7756 (license license:artistic2.0)))
7758 (define-public r-bsgenome-celegans-ucsc-ce6
7760 (name "r-bsgenome-celegans-ucsc-ce6")
7764 ;; We cannot use bioconductor-uri here because this tarball is
7765 ;; located under "data/annotation/" instead of "bioc/".
7766 (uri (string-append "https://www.bioconductor.org/packages/"
7767 "release/data/annotation/src/contrib/"
7768 "BSgenome.Celegans.UCSC.ce6_"
7772 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7774 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7775 (build-system r-build-system)
7776 ;; As this package provides little more than a very large data file it
7777 ;; doesn't make sense to build substitutes.
7778 (arguments `(#:substitutable? #f))
7780 `(("r-bsgenome" ,r-bsgenome)))
7782 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7783 (synopsis "Full genome sequences for Worm")
7785 "This package provides full genome sequences for Caenorhabditis
7786 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7788 (license license:artistic2.0)))
7790 (define-public r-bsgenome-celegans-ucsc-ce10
7792 (name "r-bsgenome-celegans-ucsc-ce10")
7796 ;; We cannot use bioconductor-uri here because this tarball is
7797 ;; located under "data/annotation/" instead of "bioc/".
7798 (uri (string-append "https://www.bioconductor.org/packages/"
7799 "release/data/annotation/src/contrib/"
7800 "BSgenome.Celegans.UCSC.ce10_"
7804 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7806 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7807 (build-system r-build-system)
7808 ;; As this package provides little more than a very large data file it
7809 ;; doesn't make sense to build substitutes.
7810 (arguments `(#:substitutable? #f))
7812 `(("r-bsgenome" ,r-bsgenome)))
7814 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7815 (synopsis "Full genome sequences for Worm")
7817 "This package provides full genome sequences for Caenorhabditis
7818 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7820 (license license:artistic2.0)))
7822 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7824 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7828 ;; We cannot use bioconductor-uri here because this tarball is
7829 ;; located under "data/annotation/" instead of "bioc/".
7830 (uri (string-append "https://www.bioconductor.org/packages/"
7831 "release/data/annotation/src/contrib/"
7832 "BSgenome.Dmelanogaster.UCSC.dm3_"
7836 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7838 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7839 (build-system r-build-system)
7840 ;; As this package provides little more than a very large data file it
7841 ;; doesn't make sense to build substitutes.
7842 (arguments `(#:substitutable? #f))
7844 `(("r-bsgenome" ,r-bsgenome)))
7846 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7847 (synopsis "Full genome sequences for Fly")
7849 "This package provides full genome sequences for Drosophila
7850 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7851 Biostrings objects.")
7852 (license license:artistic2.0)))
7854 (define-public r-motifrg
7861 (uri (bioconductor-uri "motifRG" version))
7864 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
7865 (properties `((upstream-name . "motifRG")))
7866 (build-system r-build-system)
7868 `(("r-biostrings" ,r-biostrings)
7869 ("r-bsgenome" ,r-bsgenome)
7870 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7871 ("r-iranges" ,r-iranges)
7872 ("r-seqlogo" ,r-seqlogo)
7873 ("r-xvector" ,r-xvector)))
7874 (home-page "https://bioconductor.org/packages/motifRG")
7875 (synopsis "Discover motifs in high throughput sequencing data")
7877 "This package provides tools for discriminative motif discovery in high
7878 throughput genetic sequencing data sets using regression methods.")
7879 (license license:artistic2.0)))
7881 (define-public r-qtl
7888 (uri (string-append "mirror://cran/src/contrib/qtl_"
7892 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
7893 (build-system r-build-system)
7894 (home-page "http://rqtl.org/")
7895 (synopsis "R package for analyzing QTL experiments in genetics")
7896 (description "R/qtl is an extension library for the R statistics
7897 system. It is used to analyze experimental crosses for identifying
7898 genes contributing to variation in quantitative traits (so-called
7899 quantitative trait loci, QTLs).
7901 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7902 identify genotyping errors, and to perform single-QTL and two-QTL,
7903 two-dimensional genome scans.")
7904 (license license:gpl3)))
7906 (define-public r-zlibbioc
7912 (uri (bioconductor-uri "zlibbioc" version))
7915 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
7917 `((upstream-name . "zlibbioc")))
7918 (build-system r-build-system)
7919 (home-page "https://bioconductor.org/packages/zlibbioc")
7920 (synopsis "Provider for zlib-1.2.5 to R packages")
7921 (description "This package uses the source code of zlib-1.2.5 to create
7922 libraries for systems that do not have these available via other means.")
7923 (license license:artistic2.0)))
7925 (define-public r-r4rna
7932 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7936 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7937 (build-system r-build-system)
7939 `(("r-optparse" ,r-optparse)
7940 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7941 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7942 (synopsis "Analysis framework for RNA secondary structure")
7944 "The R4RNA package aims to be a general framework for the analysis of RNA
7945 secondary structure and comparative analysis in R.")
7946 (license license:gpl3+)))
7948 (define-public r-rhtslib
7955 (uri (bioconductor-uri "Rhtslib" version))
7958 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
7959 (properties `((upstream-name . "Rhtslib")))
7960 (build-system r-build-system)
7962 `(("r-zlibbioc" ,r-zlibbioc)))
7966 `(("autoconf" ,autoconf)))
7967 (home-page "https://github.com/nhayden/Rhtslib")
7968 (synopsis "High-throughput sequencing library as an R package")
7970 "This package provides the HTSlib C library for high-throughput
7971 nucleotide sequence analysis. The package is primarily useful to developers
7972 of other R packages who wish to make use of HTSlib.")
7973 (license license:lgpl2.0+)))
7975 (define-public r-bamsignals
7977 (name "r-bamsignals")
7982 (uri (bioconductor-uri "bamsignals" version))
7985 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
7986 (build-system r-build-system)
7988 `(("r-biocgenerics" ,r-biocgenerics)
7989 ("r-genomicranges" ,r-genomicranges)
7990 ("r-iranges" ,r-iranges)
7992 ("r-rhtslib" ,r-rhtslib)
7993 ("r-zlibbioc" ,r-zlibbioc)))
7996 (home-page "https://bioconductor.org/packages/bamsignals")
7997 (synopsis "Extract read count signals from bam files")
7999 "This package allows to efficiently obtain count vectors from indexed bam
8000 files. It counts the number of nucleotide sequence reads in given genomic
8001 ranges and it computes reads profiles and coverage profiles. It also handles
8003 (license license:gpl2+)))
8005 (define-public r-rcas
8011 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8013 (file-name (string-append name "-" version ".tar.gz"))
8016 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8017 (build-system r-build-system)
8019 `(("r-knitr" ,r-knitr)
8020 ("r-testthat" ,r-testthat)
8021 ;; During vignette building knitr checks that "pandoc-citeproc"
8023 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8025 `(("r-data-table" ,r-data-table)
8026 ("r-biomart" ,r-biomart)
8027 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8028 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8029 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8030 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8031 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8032 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8033 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8034 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8035 ("r-topgo" ,r-topgo)
8037 ("r-pbapply" ,r-pbapply)
8038 ("r-plotly" ,r-plotly)
8039 ("r-plotrix" ,r-plotrix)
8040 ("r-motifrg" ,r-motifrg)
8041 ("r-genomation" ,r-genomation)
8042 ("r-genomicfeatures" ,r-genomicfeatures)
8043 ("r-rtracklayer" ,r-rtracklayer)
8044 ("r-rmarkdown" ,r-rmarkdown)))
8045 (synopsis "RNA-centric annotation system")
8047 "RCAS aims to be a standalone RNA-centric annotation system that provides
8048 intuitive reports and publication-ready graphics. This package provides the R
8049 library implementing most of the pipeline's features.")
8050 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8051 (license license:artistic2.0)))
8053 (define-public rcas-web
8060 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8061 "releases/download/v" version
8062 "/rcas-web-" version ".tar.gz"))
8065 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8066 (build-system gnu-build-system)
8069 (modify-phases %standard-phases
8070 (add-after 'install 'wrap-executable
8071 (lambda* (#:key inputs outputs #:allow-other-keys)
8072 (let* ((out (assoc-ref outputs "out"))
8073 (json (assoc-ref inputs "guile-json"))
8074 (redis (assoc-ref inputs "guile-redis"))
8075 (path (string-append
8076 json "/share/guile/site/2.2:"
8077 redis "/share/guile/site/2.2")))
8078 (wrap-program (string-append out "/bin/rcas-web")
8079 `("GUILE_LOAD_PATH" ":" = (,path))
8080 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8081 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8084 `(("r-minimal" ,r-minimal)
8086 ("guile-next" ,guile-2.2)
8087 ("guile-json" ,guile-json)
8088 ("guile-redis" ,guile2.2-redis)))
8090 `(("pkg-config" ,pkg-config)))
8091 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8092 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8093 (description "This package provides a simple web interface for the
8094 @dfn{RNA-centric annotation system} (RCAS).")
8095 (license license:agpl3+)))
8097 (define-public r-mutationalpatterns
8099 (name "r-mutationalpatterns")
8104 (uri (bioconductor-uri "MutationalPatterns" version))
8107 "0sqbrswg8ylkjb9q3vqcb5ggwixynwj6hyv2n4sk7snyk61z3fq9"))))
8108 (build-system r-build-system)
8110 `(("r-biocgenerics" ,r-biocgenerics)
8111 ("r-biostrings" ,r-biostrings)
8112 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8113 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8114 ("r-genomicranges" ,r-genomicranges)
8115 ("r-genomeinfodb" ,r-genomeinfodb)
8116 ("r-ggplot2" ,r-ggplot2)
8117 ("r-gridextra" ,r-gridextra)
8118 ("r-iranges" ,r-iranges)
8121 ("r-pracma" ,r-pracma)
8122 ("r-reshape2" ,r-reshape2)
8123 ("r-cowplot" ,r-cowplot)
8124 ("r-ggdendro" ,r-ggdendro)
8125 ("r-s4vectors" ,r-s4vectors)
8126 ("r-summarizedexperiment" ,r-summarizedexperiment)
8127 ("r-variantannotation" ,r-variantannotation)))
8128 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8129 (synopsis "Extract and visualize mutational patterns in genomic data")
8130 (description "This package provides an extensive toolset for the
8131 characterization and visualization of a wide range of mutational patterns
8132 in SNV base substitution data.")
8133 (license license:expat)))
8135 (define-public r-wgcna
8142 (uri (cran-uri "WGCNA" version))
8145 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
8146 (properties `((upstream-name . "WGCNA")))
8147 (build-system r-build-system)
8149 `(("r-annotationdbi" ,r-annotationdbi)
8150 ("r-doparallel" ,r-doparallel)
8151 ("r-dynamictreecut" ,r-dynamictreecut)
8152 ("r-fastcluster" ,r-fastcluster)
8153 ("r-foreach" ,r-foreach)
8154 ("r-go-db" ,r-go-db)
8155 ("r-hmisc" ,r-hmisc)
8156 ("r-impute" ,r-impute)
8158 ("r-robust" ,r-robust)
8159 ("r-survival" ,r-survival)
8160 ("r-matrixstats" ,r-matrixstats)
8161 ("r-preprocesscore" ,r-preprocesscore)))
8163 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8164 (synopsis "Weighted correlation network analysis")
8166 "This package provides functions necessary to perform Weighted
8167 Correlation Network Analysis on high-dimensional data. It includes functions
8168 for rudimentary data cleaning, construction and summarization of correlation
8169 networks, module identification and functions for relating both variables and
8170 modules to sample traits. It also includes a number of utility functions for
8171 data manipulation and visualization.")
8172 (license license:gpl2+)))
8174 (define-public r-chipkernels
8175 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8178 (name "r-chipkernels")
8179 (version (string-append "1.1-" revision "." (string-take commit 9)))
8184 (url "https://github.com/ManuSetty/ChIPKernels.git")
8186 (file-name (string-append name "-" version))
8189 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8190 (build-system r-build-system)
8192 `(("r-iranges" ,r-iranges)
8193 ("r-xvector" ,r-xvector)
8194 ("r-biostrings" ,r-biostrings)
8195 ("r-bsgenome" ,r-bsgenome)
8196 ("r-gtools" ,r-gtools)
8197 ("r-genomicranges" ,r-genomicranges)
8198 ("r-sfsmisc" ,r-sfsmisc)
8199 ("r-kernlab" ,r-kernlab)
8200 ("r-s4vectors" ,r-s4vectors)
8201 ("r-biocgenerics" ,r-biocgenerics)))
8202 (home-page "https://github.com/ManuSetty/ChIPKernels")
8203 (synopsis "Build string kernels for DNA Sequence analysis")
8204 (description "ChIPKernels is an R package for building different string
8205 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8206 must be built and this dictionary can be used for determining kernels for DNA
8208 (license license:gpl2+))))
8210 (define-public r-seqgl
8217 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8218 "archive/" version ".tar.gz"))
8219 (file-name (string-append name "-" version ".tar.gz"))
8222 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8223 (build-system r-build-system)
8225 `(("r-biostrings" ,r-biostrings)
8226 ("r-chipkernels" ,r-chipkernels)
8227 ("r-genomicranges" ,r-genomicranges)
8228 ("r-spams" ,r-spams)
8229 ("r-wgcna" ,r-wgcna)
8230 ("r-fastcluster" ,r-fastcluster)))
8231 (home-page "https://github.com/ManuSetty/SeqGL")
8232 (synopsis "Group lasso for Dnase/ChIP-seq data")
8233 (description "SeqGL is a group lasso based algorithm to extract
8234 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8235 This package presents a method which uses group lasso to discriminate between
8236 bound and non bound genomic regions to accurately identify transcription
8237 factors bound at the specific regions.")
8238 (license license:gpl2+)))
8240 (define-public r-gkmsvm
8247 (uri (cran-uri "gkmSVM" version))
8250 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8251 (properties `((upstream-name . "gkmSVM")))
8252 (build-system r-build-system)
8254 `(("r-biocgenerics" ,r-biocgenerics)
8255 ("r-biostrings" ,r-biostrings)
8256 ("r-genomeinfodb" ,r-genomeinfodb)
8257 ("r-genomicranges" ,r-genomicranges)
8258 ("r-iranges" ,r-iranges)
8259 ("r-kernlab" ,r-kernlab)
8262 ("r-rtracklayer" ,r-rtracklayer)
8263 ("r-s4vectors" ,r-s4vectors)
8264 ("r-seqinr" ,r-seqinr)))
8265 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8266 (synopsis "Gapped-kmer support vector machine")
8268 "This R package provides tools for training gapped-kmer SVM classifiers
8269 for DNA and protein sequences. This package supports several sequence
8270 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8271 (license license:gpl2+)))
8273 (define-public r-tximport
8279 (uri (bioconductor-uri "tximport" version))
8282 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8283 (build-system r-build-system)
8284 (home-page "https://bioconductor.org/packages/tximport")
8285 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8287 "This package provides tools to import transcript-level abundance,
8288 estimated counts and transcript lengths, and to summarize them into matrices
8289 for use with downstream gene-level analysis packages. Average transcript
8290 length, weighted by sample-specific transcript abundance estimates, is
8291 provided as a matrix which can be used as an offset for different expression
8292 of gene-level counts.")
8293 (license license:gpl2+)))
8295 (define-public r-rhdf5
8301 (uri (bioconductor-uri "rhdf5" version))
8304 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8305 (build-system r-build-system)
8308 (modify-phases %standard-phases
8309 (add-after 'unpack 'unpack-smallhdf5
8310 (lambda* (#:key outputs #:allow-other-keys)
8311 (system* "tar" "-xzvf"
8312 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8313 (substitute* "src/Makevars"
8314 (("^.*cd hdf5source &&.*$") "")
8315 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8316 (("^.*rm -rf hdf5.*$") "")
8317 (("^.*mv hdf5source/hdf5 ..*$") ""))
8318 (substitute* "src/hdf5/configure"
8322 `(("r-zlibbioc" ,r-zlibbioc)))
8326 (home-page "https://bioconductor.org/packages/rhdf5")
8327 (synopsis "HDF5 interface to R")
8329 "This R/Bioconductor package provides an interface between HDF5 and R.
8330 HDF5's main features are the ability to store and access very large and/or
8331 complex datasets and a wide variety of metadata on mass storage (disk) through
8332 a completely portable file format. The rhdf5 package is thus suited for the
8333 exchange of large and/or complex datasets between R and other software
8334 package, and for letting R applications work on datasets that are larger than
8335 the available RAM.")
8336 (license license:artistic2.0)))
8338 (define-public r-annotationfilter
8340 (name "r-annotationfilter")
8344 (uri (bioconductor-uri "AnnotationFilter" version))
8347 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8349 `((upstream-name . "AnnotationFilter")))
8350 (build-system r-build-system)
8352 `(("r-genomicranges" ,r-genomicranges)
8353 ("r-lazyeval" ,r-lazyeval)))
8354 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8355 (synopsis "Facilities for filtering Bioconductor annotation resources")
8357 "This package provides classes and other infrastructure to implement
8358 filters for manipulating Bioconductor annotation resources. The filters are
8359 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8360 (license license:artistic2.0)))
8362 (define-public emboss
8368 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8369 (version-major+minor version) ".0/"
8370 "EMBOSS-" version ".tar.gz"))
8373 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8374 (build-system gnu-build-system)
8377 (list (string-append "--with-hpdf="
8378 (assoc-ref %build-inputs "libharu")))
8380 (modify-phases %standard-phases
8381 (add-after 'unpack 'fix-checks
8383 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8384 ;; and zlib, but assume that they are all found at the same
8386 (substitute* "configure.in"
8387 (("CHECK_PNGDRIVER")
8388 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8389 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8390 AM_CONDITIONAL(AMPNG, true)"))
8392 (add-after 'fix-checks 'disable-update-check
8394 ;; At build time there is no connection to the Internet, so
8395 ;; looking for updates will not work.
8396 (substitute* "Makefile.am"
8397 (("\\$\\(bindir\\)/embossupdate") ""))
8399 (add-after 'disable-update-check 'autogen
8400 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8406 ("libharu" ,libharu)
8409 `(("autoconf" ,autoconf)
8410 ("automake" ,automake)
8411 ("libtool" ,libtool)
8412 ("pkg-config" ,pkg-config)))
8413 (home-page "http://emboss.sourceforge.net")
8414 (synopsis "Molecular biology analysis suite")
8415 (description "EMBOSS is the \"European Molecular Biology Open Software
8416 Suite\". EMBOSS is an analysis package specially developed for the needs of
8417 the molecular biology (e.g. EMBnet) user community. The software
8418 automatically copes with data in a variety of formats and even allows
8419 transparent retrieval of sequence data from the web. It also provides a
8420 number of libraries for the development of software in the field of molecular
8421 biology. EMBOSS also integrates a range of currently available packages and
8422 tools for sequence analysis into a seamless whole.")
8423 (license license:gpl2+)))
8426 (let ((revision "1")
8427 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8430 ;; The version is 2.13.0 even though no release archives have been
8431 ;; published as yet.
8432 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8436 (url "https://github.com/arq5x/bits.git")
8438 (file-name (string-append name "-" version "-checkout"))
8441 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8442 (build-system gnu-build-system)
8444 `(#:tests? #f ;no tests included
8446 (modify-phases %standard-phases
8448 (add-after 'unpack 'remove-cuda
8450 (substitute* "Makefile"
8452 (("(bits_test_intersections) \\\\" _ match) match))
8455 (lambda* (#:key outputs #:allow-other-keys)
8457 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8462 (home-page "https://github.com/arq5x/bits")
8463 (synopsis "Implementation of binary interval search algorithm")
8464 (description "This package provides an implementation of the
8465 BITS (Binary Interval Search) algorithm, an approach to interval set
8466 intersection. It is especially suited for the comparison of diverse genomic
8467 datasets and the exploration of large datasets of genome
8468 intervals (e.g. genes, sequence alignments).")
8469 (license license:gpl2))))
8471 (define-public piranha
8472 ;; There is no release tarball for the latest version. The latest commit is
8473 ;; older than one year at the time of this writing.
8474 (let ((revision "1")
8475 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8478 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8482 (url "https://github.com/smithlabcode/piranha.git")
8486 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8487 (build-system gnu-build-system)
8489 `(#:test-target "test"
8491 (modify-phases %standard-phases
8492 (add-after 'unpack 'copy-smithlab-cpp
8493 (lambda* (#:key inputs #:allow-other-keys)
8494 (for-each (lambda (file)
8495 (install-file file "./src/smithlab_cpp/"))
8496 (find-files (assoc-ref inputs "smithlab-cpp")))
8498 (add-after 'install 'install-to-store
8499 (lambda* (#:key outputs #:allow-other-keys)
8500 (let* ((out (assoc-ref outputs "out"))
8501 (bin (string-append out "/bin")))
8502 (for-each (lambda (file)
8503 (install-file file bin))
8504 (find-files "bin" ".*")))
8507 (list (string-append "--with-bam_tools_headers="
8508 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8509 (string-append "--with-bam_tools_library="
8510 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8512 `(("bamtools" ,bamtools)
8513 ("samtools" ,samtools-0.1)
8516 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8520 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8522 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8525 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8527 `(("python" ,python-2)))
8528 (home-page "https://github.com/smithlabcode/piranha")
8529 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8531 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8532 RIP-seq experiments. It takes input in BED or BAM format and identifies
8533 regions of statistically significant read enrichment. Additional covariates
8534 may optionally be provided to further inform the peak-calling process.")
8535 (license license:gpl3+))))
8543 (uri (string-append "https://pypi.python.org/packages/source/P"
8544 "/PePr/PePr-" version ".tar.gz"))
8547 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8548 (build-system python-build-system)
8550 `(#:python ,python-2 ; python2 only
8551 #:tests? #f)) ; no tests included
8553 `(("python2-numpy" ,python2-numpy)
8554 ("python2-scipy" ,python2-scipy)
8555 ("python2-pysam" ,python2-pysam)))
8556 (home-page "https://github.com/shawnzhangyx/PePr")
8557 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8559 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8560 that is primarily designed for data with biological replicates. It uses a
8561 negative binomial distribution to model the read counts among the samples in
8562 the same group, and look for consistent differences between ChIP and control
8563 group or two ChIP groups run under different conditions.")
8564 (license license:gpl3+)))
8566 (define-public filevercmp
8567 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8570 (version (string-append "0-1." (string-take commit 7)))
8573 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8575 (file-name (string-append name "-" version ".tar.gz"))
8577 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8578 (build-system gnu-build-system)
8580 `(#:tests? #f ; There are no tests to run.
8582 (modify-phases %standard-phases
8583 (delete 'configure) ; There is no configure phase.
8585 (lambda* (#:key outputs #:allow-other-keys)
8586 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8587 (install-file "filevercmp" bin)))))))
8588 (home-page "https://github.com/ekg/filevercmp")
8589 (synopsis "This program compares version strings")
8590 (description "This program compares version strings. It intends to be a
8591 replacement for strverscmp.")
8592 (license license:gpl3+))))
8594 (define-public multiqc
8601 (uri (pypi-uri "multiqc" version))
8604 "0fx1sx53znbgzfhbbiyd8j6cg5llpcsl5q5c45jy2c81d12piqfd"))))
8605 (build-system python-build-system)
8607 `(("python-enum34" ,python-enum34)
8608 ("python-jinja2" ,python-jinja2)
8609 ("python-simplejson" ,python-simplejson)
8610 ("python-pyyaml" ,python-pyyaml)
8611 ("python-click" ,python-click)
8612 ("python-spectra" ,python-spectra)
8613 ("python-requests" ,python-requests)
8614 ("python-markdown" ,python-markdown)
8615 ("python-lzstring" ,python-lzstring)
8616 ("python-matplotlib" ,python-matplotlib)
8617 ("python-numpy" ,python-numpy)
8618 ;; MultQC checks for the presence of nose at runtime.
8619 ("python-nose" ,python-nose)))
8620 (home-page "http://multiqc.info")
8621 (synopsis "Aggregate bioinformatics analysis reports")
8623 "MultiQC is a tool to aggregate bioinformatics results across many
8624 samples into a single report. It contains modules for a large number of
8625 common bioinformatics tools.")
8626 (license license:gpl3+)))
8628 (define-public r-chipseq
8635 (uri (bioconductor-uri "chipseq" version))
8638 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8639 (build-system r-build-system)
8641 `(("r-biocgenerics" ,r-biocgenerics)
8642 ("r-genomicranges" ,r-genomicranges)
8643 ("r-iranges" ,r-iranges)
8644 ("r-lattice" ,r-lattice)
8645 ("r-s4vectors" ,r-s4vectors)
8646 ("r-shortread" ,r-shortread)))
8647 (home-page "https://bioconductor.org/packages/chipseq")
8648 (synopsis "Package for analyzing ChIPseq data")
8650 "This package provides tools for processing short read data from ChIPseq
8652 (license license:artistic2.0)))
8654 (define-public r-copyhelper
8656 (name "r-copyhelper")
8661 (uri (string-append "https://bioconductor.org/packages/release/"
8662 "data/experiment/src/contrib/CopyhelpeR_"
8666 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8667 (properties `((upstream-name . "CopyhelpeR")))
8668 (build-system r-build-system)
8669 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8670 (synopsis "Helper files for CopywriteR")
8672 "This package contains the helper files that are required to run the
8673 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8674 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8675 mm10. In addition, it contains a blacklist filter to remove regions that
8676 display copy number variation. Files are stored as GRanges objects from the
8677 GenomicRanges Bioconductor package.")
8678 (license license:gpl2)))
8680 (define-public r-copywriter
8682 (name "r-copywriter")
8687 (uri (bioconductor-uri "CopywriteR" version))
8690 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
8691 (properties `((upstream-name . "CopywriteR")))
8692 (build-system r-build-system)
8694 `(("r-biocparallel" ,r-biocparallel)
8695 ("r-chipseq" ,r-chipseq)
8696 ("r-copyhelper" ,r-copyhelper)
8697 ("r-data-table" ,r-data-table)
8698 ("r-dnacopy" ,r-dnacopy)
8699 ("r-futile-logger" ,r-futile-logger)
8700 ("r-genomeinfodb" ,r-genomeinfodb)
8701 ("r-genomicalignments" ,r-genomicalignments)
8702 ("r-genomicranges" ,r-genomicranges)
8703 ("r-gtools" ,r-gtools)
8704 ("r-iranges" ,r-iranges)
8705 ("r-matrixstats" ,r-matrixstats)
8706 ("r-rsamtools" ,r-rsamtools)
8707 ("r-s4vectors" ,r-s4vectors)))
8708 (home-page "https://github.com/PeeperLab/CopywriteR")
8709 (synopsis "Copy number information from targeted sequencing")
8711 "CopywriteR extracts DNA copy number information from targeted sequencing
8712 by utilizing off-target reads. It allows for extracting uniformly distributed
8713 copy number information, can be used without reference, and can be applied to
8714 sequencing data obtained from various techniques including chromatin
8715 immunoprecipitation and target enrichment on small gene panels. Thereby,
8716 CopywriteR constitutes a widely applicable alternative to available copy
8717 number detection tools.")
8718 (license license:gpl2)))
8720 (define-public r-methylkit
8722 (name "r-methylkit")
8726 (uri (bioconductor-uri "methylKit" version))
8729 "0h53w2mrjrg2n0ndi12k9j6cwclgwcgpy25nz7nyj971aisw02xn"))))
8730 (properties `((upstream-name . "methylKit")))
8731 (build-system r-build-system)
8733 `(("r-data-table" ,r-data-table)
8734 ("r-emdbook" ,r-emdbook)
8735 ("r-fastseg" ,r-fastseg)
8736 ("r-genomeinfodb" ,r-genomeinfodb)
8737 ("r-genomicranges" ,r-genomicranges)
8738 ("r-gtools" ,r-gtools)
8739 ("r-iranges" ,r-iranges)
8740 ("r-kernsmooth" ,r-kernsmooth)
8741 ("r-limma" ,r-limma)
8742 ("r-mclust" ,r-mclust)
8743 ("r-qvalue" ,r-qvalue)
8744 ("r-r-utils" ,r-r-utils)
8746 ("r-rhtslib" ,r-rhtslib)
8747 ("r-rsamtools" ,r-rsamtools)
8748 ("r-rtracklayer" ,r-rtracklayer)
8749 ("r-s4vectors" ,r-s4vectors)
8750 ("r-zlibbioc" ,r-zlibbioc)))
8753 (home-page "https://github.com/al2na/methylKit")
8755 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8757 "MethylKit is an R package for DNA methylation analysis and annotation
8758 from high-throughput bisulfite sequencing. The package is designed to deal
8759 with sequencing data from @dfn{Reduced representation bisulfite
8760 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8761 genome bisulfite sequencing. It also has functions to analyze base-pair
8762 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8764 (license license:artistic2.0)))
8766 (define-public r-sva
8773 (uri (bioconductor-uri "sva" version))
8776 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
8777 (build-system r-build-system)
8779 `(("r-genefilter" ,r-genefilter)
8781 ("r-biocparallel" ,r-biocparallel)
8782 ("r-matrixstats" ,r-matrixstats)
8783 ("r-limma" ,r-limma)))
8784 (home-page "https://bioconductor.org/packages/sva")
8785 (synopsis "Surrogate variable analysis")
8787 "This package contains functions for removing batch effects and other
8788 unwanted variation in high-throughput experiment. It also contains functions
8789 for identifying and building surrogate variables for high-dimensional data
8790 sets. Surrogate variables are covariates constructed directly from
8791 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8792 imaging data that can be used in subsequent analyses to adjust for unknown,
8793 unmodeled, or latent sources of noise.")
8794 (license license:artistic2.0)))
8796 (define-public r-seqminer
8803 (uri (cran-uri "seqminer" version))
8806 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
8807 (build-system r-build-system)
8810 (home-page "http://seqminer.genomic.codes")
8811 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8813 "This package provides tools to integrate nucleotide sequencing
8814 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8815 ;; Any version of the GPL is acceptable
8816 (license (list license:gpl2+ license:gpl3+))))
8818 (define-public r-raremetals2
8820 (name "r-raremetals2")
8825 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8826 "b/b7/RareMETALS2_" version ".tar.gz"))
8829 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8830 (properties `((upstream-name . "RareMETALS2")))
8831 (build-system r-build-system)
8833 `(("r-seqminer" ,r-seqminer)
8834 ("r-mvtnorm" ,r-mvtnorm)
8836 ("r-compquadform" ,r-compquadform)
8837 ("r-getopt" ,r-getopt)))
8838 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8839 (synopsis "Analyze gene-level association tests for binary trait")
8841 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8842 It was designed to meta-analyze gene-level association tests for binary trait.
8843 While rareMETALS offers a near-complete solution for meta-analysis of
8844 gene-level tests for quantitative trait, it does not offer the optimal
8845 solution for binary trait. The package rareMETALS2 offers improved features
8846 for analyzing gene-level association tests in meta-analyses for binary
8848 (license license:gpl3)))
8850 (define-public r-maldiquant
8852 (name "r-maldiquant")
8857 (uri (cran-uri "MALDIquant" version))
8860 "1pmhsfvd45a44xdiml4zx3zd5fhygqyziqvygahkk9yibnyhv4cv"))))
8861 (properties `((upstream-name . "MALDIquant")))
8862 (build-system r-build-system)
8863 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8864 (synopsis "Quantitative analysis of mass spectrometry data")
8866 "This package provides a complete analysis pipeline for matrix-assisted
8867 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8868 two-dimensional mass spectrometry data. In addition to commonly used plotting
8869 and processing methods it includes distinctive features, namely baseline
8870 subtraction methods such as morphological filters (TopHat) or the
8871 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8872 alignment using warping functions, handling of replicated measurements as well
8873 as allowing spectra with different resolutions.")
8874 (license license:gpl3+)))
8876 (define-public r-protgenerics
8878 (name "r-protgenerics")
8883 (uri (bioconductor-uri "ProtGenerics" version))
8886 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
8887 (properties `((upstream-name . "ProtGenerics")))
8888 (build-system r-build-system)
8889 (home-page "https://github.com/lgatto/ProtGenerics")
8890 (synopsis "S4 generic functions for proteomics infrastructure")
8892 "This package provides S4 generic functions needed by Bioconductor
8893 proteomics packages.")
8894 (license license:artistic2.0)))
8896 (define-public r-mzr
8903 (uri (bioconductor-uri "mzR" version))
8906 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
8907 (modules '((guix build utils)))
8910 (delete-file-recursively "src/boost")
8912 (properties `((upstream-name . "mzR")))
8913 (build-system r-build-system)
8916 (modify-phases %standard-phases
8917 (add-after 'unpack 'use-system-boost
8919 (substitute* "src/Makevars"
8920 (("\\./boost/libs.*") "")
8921 (("ARCH_OBJS=" line)
8923 "\nARCH_LIBS=-lboost_system -lboost_regex \
8924 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
8927 `(("boost" ,boost) ; use this instead of the bundled boost sources
8928 ("netcdf" ,netcdf)))
8930 `(("r-biobase" ,r-biobase)
8931 ("r-biocgenerics" ,r-biocgenerics)
8932 ("r-protgenerics" ,r-protgenerics)
8934 ("r-zlibbioc" ,r-zlibbioc)))
8935 (home-page "https://github.com/sneumann/mzR/")
8936 (synopsis "Parser for mass spectrometry data files")
8938 "The mzR package provides a unified API to the common file formats and
8939 parsers available for mass spectrometry data. It comes with a wrapper for the
8940 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8941 The package contains the original code written by the ISB, and a subset of the
8942 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8943 previously been used in XCMS.")
8944 (license license:artistic2.0)))
8946 (define-public r-affyio
8953 (uri (bioconductor-uri "affyio" version))
8956 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
8957 (build-system r-build-system)
8959 `(("r-zlibbioc" ,r-zlibbioc)))
8962 (home-page "https://github.com/bmbolstad/affyio")
8963 (synopsis "Tools for parsing Affymetrix data files")
8965 "This package provides routines for parsing Affymetrix data files based
8966 upon file format information. The primary focus is on accessing the CEL and
8968 (license license:lgpl2.0+)))
8970 (define-public r-affy
8977 (uri (bioconductor-uri "affy" version))
8980 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
8981 (build-system r-build-system)
8983 `(("r-affyio" ,r-affyio)
8984 ("r-biobase" ,r-biobase)
8985 ("r-biocgenerics" ,r-biocgenerics)
8986 ("r-biocinstaller" ,r-biocinstaller)
8987 ("r-preprocesscore" ,r-preprocesscore)
8988 ("r-zlibbioc" ,r-zlibbioc)))
8989 (home-page "https://bioconductor.org/packages/affy")
8990 (synopsis "Methods for affymetrix oligonucleotide arrays")
8992 "This package contains functions for exploratory oligonucleotide array
8994 (license license:lgpl2.0+)))
8996 (define-public r-vsn
9003 (uri (bioconductor-uri "vsn" version))
9006 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9007 (build-system r-build-system)
9009 `(("r-affy" ,r-affy)
9010 ("r-biobase" ,r-biobase)
9011 ("r-ggplot2" ,r-ggplot2)
9012 ("r-lattice" ,r-lattice)
9013 ("r-limma" ,r-limma)))
9014 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9015 (synopsis "Variance stabilization and calibration for microarray data")
9017 "The package implements a method for normalising microarray intensities,
9018 and works for single- and multiple-color arrays. It can also be used for data
9019 from other technologies, as long as they have similar format. The method uses
9020 a robust variant of the maximum-likelihood estimator for an
9021 additive-multiplicative error model and affine calibration. The model
9022 incorporates data calibration step (a.k.a. normalization), a model for the
9023 dependence of the variance on the mean intensity and a variance stabilizing
9024 data transformation. Differences between transformed intensities are
9025 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9026 their variance is independent of the mean, and they are usually more sensitive
9027 and specific in detecting differential transcription.")
9028 (license license:artistic2.0)))
9030 (define-public r-mzid
9037 (uri (bioconductor-uri "mzID" version))
9040 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9041 (properties `((upstream-name . "mzID")))
9042 (build-system r-build-system)
9044 `(("r-doparallel" ,r-doparallel)
9045 ("r-foreach" ,r-foreach)
9046 ("r-iterators" ,r-iterators)
9048 ("r-protgenerics" ,r-protgenerics)
9051 (home-page "https://bioconductor.org/packages/mzID")
9052 (synopsis "Parser for mzIdentML files")
9054 "This package provides a parser for mzIdentML files implemented using the
9055 XML package. The parser tries to be general and able to handle all types of
9056 mzIdentML files with the drawback of having less pretty output than a vendor
9058 (license license:gpl2+)))
9060 (define-public r-pcamethods
9062 (name "r-pcamethods")
9067 (uri (bioconductor-uri "pcaMethods" version))
9070 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9071 (properties `((upstream-name . "pcaMethods")))
9072 (build-system r-build-system)
9074 `(("r-biobase" ,r-biobase)
9075 ("r-biocgenerics" ,r-biocgenerics)
9077 ("r-rcpp" ,r-rcpp)))
9078 (home-page "https://github.com/hredestig/pcamethods")
9079 (synopsis "Collection of PCA methods")
9081 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9082 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9083 for missing value estimation is included for comparison. BPCA, PPCA and
9084 NipalsPCA may be used to perform PCA on incomplete data as well as for
9085 accurate missing value estimation. A set of methods for printing and plotting
9086 the results is also provided. All PCA methods make use of the same data
9087 structure (pcaRes) to provide a common interface to the PCA results.")
9088 (license license:gpl3+)))
9090 (define-public r-msnbase
9097 (uri (bioconductor-uri "MSnbase" version))
9100 "0dqfimljhrx3gac8d1k72gppx27lz8yckyb12v4604nbviw7xd3r"))))
9101 (properties `((upstream-name . "MSnbase")))
9102 (build-system r-build-system)
9104 `(("r-affy" ,r-affy)
9105 ("r-biobase" ,r-biobase)
9106 ("r-biocgenerics" ,r-biocgenerics)
9107 ("r-biocparallel" ,r-biocparallel)
9108 ("r-digest" ,r-digest)
9109 ("r-ggplot2" ,r-ggplot2)
9110 ("r-impute" ,r-impute)
9111 ("r-iranges" ,r-iranges)
9112 ("r-lattice" ,r-lattice)
9113 ("r-maldiquant" ,r-maldiquant)
9116 ("r-pcamethods" ,r-pcamethods)
9118 ("r-preprocesscore" ,r-preprocesscore)
9119 ("r-protgenerics" ,r-protgenerics)
9121 ("r-s4vectors" ,r-s4vectors)
9124 (home-page "https://github.com/lgatto/MSnbase")
9125 (synopsis "Base functions and classes for MS-based proteomics")
9127 "This package provides basic plotting, data manipulation and processing
9128 of mass spectrometry based proteomics data.")
9129 (license license:artistic2.0)))
9131 (define-public r-msnid
9138 (uri (bioconductor-uri "MSnID" version))
9141 "1vi4ngwbayrv2jkfb4pbmdp37xn04y07rh1jcklqfh0fcrm1jdig"))))
9142 (properties `((upstream-name . "MSnID")))
9143 (build-system r-build-system)
9145 `(("r-biobase" ,r-biobase)
9146 ("r-data-table" ,r-data-table)
9147 ("r-doparallel" ,r-doparallel)
9148 ("r-dplyr" ,r-dplyr)
9149 ("r-foreach" ,r-foreach)
9150 ("r-iterators" ,r-iterators)
9151 ("r-msnbase" ,r-msnbase)
9154 ("r-protgenerics" ,r-protgenerics)
9155 ("r-r-cache" ,r-r-cache)
9157 ("r-reshape2" ,r-reshape2)))
9158 (home-page "https://bioconductor.org/packages/MSnID")
9159 (synopsis "Utilities for LC-MSn proteomics identifications")
9161 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9162 from mzIdentML (leveraging the mzID package) or text files. After collating
9163 the search results from multiple datasets it assesses their identification
9164 quality and optimize filtering criteria to achieve the maximum number of
9165 identifications while not exceeding a specified false discovery rate. It also
9166 contains a number of utilities to explore the MS/MS results and assess missed
9167 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9168 (license license:artistic2.0)))
9170 (define-public r-seurat
9171 ;; Source releases are only made for new x.0 versions. All newer versions
9172 ;; are only released as pre-built binaries. At the time of this writing the
9173 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9174 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9178 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9182 (url "https://github.com/satijalab/seurat")
9184 (file-name (string-append name "-" version "-checkout"))
9187 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9188 ;; Delete pre-built jar.
9190 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9192 (build-system r-build-system)
9195 (modify-phases %standard-phases
9196 (add-after 'unpack 'build-jar
9197 (lambda* (#:key inputs #:allow-other-keys)
9198 (let ((classesdir "tmp-classes"))
9199 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9201 (and (zero? (apply system* `("javac" "-d" ,classesdir
9202 ,@(find-files "java" "\\.java$"))))
9203 (zero? (system* "jar"
9204 "-cf" "inst/java/ModularityOptimizer.jar"
9205 "-C" classesdir ".")))))))))
9207 `(("jdk" ,icedtea "jdk")))
9210 ("r-caret" ,r-caret)
9211 ("r-cowplot" ,r-cowplot)
9212 ("r-dplyr" ,r-dplyr)
9213 ("r-fastica" ,r-fastica)
9216 ("r-gdata" ,r-gdata)
9217 ("r-ggplot2" ,r-ggplot2)
9218 ("r-gplots" ,r-gplots)
9219 ("r-gridextra" ,r-gridextra)
9220 ("r-igraph" ,r-igraph)
9221 ("r-irlba" ,r-irlba)
9223 ("r-mixtools" ,r-mixtools)
9224 ("r-pbapply" ,r-pbapply)
9226 ("r-ranger" ,r-ranger)
9227 ("r-rcolorbrewer" ,r-rcolorbrewer)
9229 ("r-rcppeigen" ,r-rcppeigen)
9230 ("r-rcppprogress" ,r-rcppprogress)
9231 ("r-reshape2" ,r-reshape2)
9233 ("r-rtsne" ,r-rtsne)
9234 ("r-stringr" ,r-stringr)
9235 ("r-tclust" ,r-tclust)
9237 ("r-vgam" ,r-vgam)))
9238 (home-page "http://www.satijalab.org/seurat")
9239 (synopsis "Seurat is an R toolkit for single cell genomics")
9241 "This package is an R package designed for QC, analysis, and
9242 exploration of single cell RNA-seq data. It easily enables widely-used
9243 analytical techniques, including the identification of highly variable genes,
9244 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9245 algorithms; density clustering, hierarchical clustering, k-means, and the
9246 discovery of differentially expressed genes and markers.")
9247 (license license:gpl3))))
9249 (define-public r-aroma-light
9251 (name "r-aroma-light")
9256 (uri (bioconductor-uri "aroma.light" version))
9259 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9260 (properties `((upstream-name . "aroma.light")))
9261 (build-system r-build-system)
9263 `(("r-matrixstats" ,r-matrixstats)
9264 ("r-r-methodss3" ,r-r-methodss3)
9266 ("r-r-utils" ,r-r-utils)))
9267 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9268 (synopsis "Methods for normalization and visualization of microarray data")
9270 "This package provides methods for microarray analysis that take basic
9271 data types such as matrices and lists of vectors. These methods can be used
9272 standalone, be utilized in other packages, or be wrapped up in higher-level
9274 (license license:gpl2+)))
9276 (define-public r-deseq
9283 (uri (bioconductor-uri "DESeq" version))
9286 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9287 (properties `((upstream-name . "DESeq")))
9288 (build-system r-build-system)
9290 `(("r-biobase" ,r-biobase)
9291 ("r-biocgenerics" ,r-biocgenerics)
9292 ("r-genefilter" ,r-genefilter)
9293 ("r-geneplotter" ,r-geneplotter)
9294 ("r-lattice" ,r-lattice)
9295 ("r-locfit" ,r-locfit)
9297 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9298 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9299 (synopsis "Differential gene expression analysis")
9301 "This package provides tools for estimating variance-mean dependence in
9302 count data from high-throughput genetic sequencing assays and for testing for
9303 differential expression based on a model using the negative binomial
9305 (license license:gpl3+)))
9307 (define-public r-edaseq
9314 (uri (bioconductor-uri "EDASeq" version))
9317 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9318 (properties `((upstream-name . "EDASeq")))
9319 (build-system r-build-system)
9321 `(("r-annotationdbi" ,r-annotationdbi)
9322 ("r-aroma-light" ,r-aroma-light)
9323 ("r-biobase" ,r-biobase)
9324 ("r-biocgenerics" ,r-biocgenerics)
9325 ("r-biomart" ,r-biomart)
9326 ("r-biostrings" ,r-biostrings)
9327 ("r-deseq" ,r-deseq)
9328 ("r-genomicfeatures" ,r-genomicfeatures)
9329 ("r-genomicranges" ,r-genomicranges)
9330 ("r-iranges" ,r-iranges)
9331 ("r-rsamtools" ,r-rsamtools)
9332 ("r-shortread" ,r-shortread)))
9333 (home-page "https://github.com/drisso/EDASeq")
9334 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9336 "This package provides support for numerical and graphical summaries of
9337 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9338 adjust for GC-content effect (or other gene-level effects) on read counts:
9339 loess robust local regression, global-scaling, and full-quantile
9340 normalization. Between-lane normalization procedures to adjust for
9341 distributional differences between lanes (e.g., sequencing depth):
9342 global-scaling and full-quantile normalization.")
9343 (license license:artistic2.0)))
9345 (define-public r-interactivedisplaybase
9347 (name "r-interactivedisplaybase")
9352 (uri (bioconductor-uri "interactiveDisplayBase" version))
9355 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9357 `((upstream-name . "interactiveDisplayBase")))
9358 (build-system r-build-system)
9360 `(("r-biocgenerics" ,r-biocgenerics)
9361 ("r-shiny" ,r-shiny)))
9362 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9363 (synopsis "Base package for web displays of Bioconductor objects")
9365 "This package contains the basic methods needed to generate interactive
9366 Shiny-based display methods for Bioconductor objects.")
9367 (license license:artistic2.0)))
9369 (define-public r-annotationhub
9371 (name "r-annotationhub")
9376 (uri (bioconductor-uri "AnnotationHub" version))
9379 "1arfka3czw8hkv6n2d85bgibq81s2rgkwhmpaxzhy6nw39vv7y8b"))))
9380 (properties `((upstream-name . "AnnotationHub")))
9381 (build-system r-build-system)
9383 `(("r-annotationdbi" ,r-annotationdbi)
9384 ("r-biocgenerics" ,r-biocgenerics)
9385 ("r-biocinstaller" ,r-biocinstaller)
9388 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9389 ("r-rsqlite" ,r-rsqlite)
9390 ("r-s4vectors" ,r-s4vectors)
9391 ("r-yaml" ,r-yaml)))
9392 (home-page "https://bioconductor.org/packages/AnnotationHub")
9393 (synopsis "Client to access AnnotationHub resources")
9395 "This package provides a client for the Bioconductor AnnotationHub web
9396 resource. The AnnotationHub web resource provides a central location where
9397 genomic files (e.g. VCF, bed, wig) and other resources from standard
9398 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9399 metadata about each resource, e.g., a textual description, tags, and date of
9400 modification. The client creates and manages a local cache of files retrieved
9401 by the user, helping with quick and reproducible access.")
9402 (license license:artistic2.0)))
9404 (define-public r-fastseg
9411 (uri (bioconductor-uri "fastseg" version))
9414 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9415 (build-system r-build-system)
9417 `(("r-biobase" ,r-biobase)
9418 ("r-biocgenerics" ,r-biocgenerics)
9419 ("r-genomicranges" ,r-genomicranges)
9420 ("r-iranges" ,r-iranges)
9421 ("r-s4vectors" ,r-s4vectors)))
9422 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9423 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9425 "Fastseg implements a very fast and efficient segmentation algorithm.
9426 It can segment data from DNA microarrays and data from next generation
9427 sequencing for example to detect copy number segments. Further it can segment
9428 data from RNA microarrays like tiling arrays to identify transcripts. Most
9429 generally, it can segment data given as a matrix or as a vector. Various data
9430 formats can be used as input to fastseg like expression set objects for
9431 microarrays or GRanges for sequencing data.")
9432 (license license:lgpl2.0+)))
9434 (define-public r-keggrest
9441 (uri (bioconductor-uri "KEGGREST" version))
9444 "1i3i88lj57wvpgjf75a23msgfsjv8pr2b4j1faga276p4fsblkhj"))))
9445 (properties `((upstream-name . "KEGGREST")))
9446 (build-system r-build-system)
9448 `(("r-biostrings" ,r-biostrings)
9451 (home-page "https://bioconductor.org/packages/KEGGREST")
9452 (synopsis "Client-side REST access to KEGG")
9454 "This package provides a package that provides a client interface to the
9455 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9456 (license license:artistic2.0)))
9458 (define-public r-gage
9465 (uri (bioconductor-uri "gage" version))
9468 "1r14p88q3y736pkqm4pdimf1izy1xy3xgivmj3cr4dv65kjny1zk"))))
9469 (build-system r-build-system)
9471 `(("r-annotationdbi" ,r-annotationdbi)
9472 ("r-graph" ,r-graph)
9473 ("r-keggrest" ,r-keggrest)))
9474 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9475 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9477 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9478 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9479 data attributes including sample sizes, experimental designs, assay platforms,
9480 and other types of heterogeneity. The gage package provides functions for
9481 basic GAGE analysis, result processing and presentation. In addition, it
9482 provides demo microarray data and commonly used gene set data based on KEGG
9483 pathways and GO terms. These funtions and data are also useful for gene set
9484 analysis using other methods.")
9485 (license license:gpl2+)))
9487 (define-public r-genomicfiles
9489 (name "r-genomicfiles")
9494 (uri (bioconductor-uri "GenomicFiles" version))
9497 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9498 (properties `((upstream-name . "GenomicFiles")))
9499 (build-system r-build-system)
9501 `(("r-biocgenerics" ,r-biocgenerics)
9502 ("r-biocparallel" ,r-biocparallel)
9503 ("r-genomeinfodb" ,r-genomeinfodb)
9504 ("r-genomicalignments" ,r-genomicalignments)
9505 ("r-genomicranges" ,r-genomicranges)
9506 ("r-iranges" ,r-iranges)
9507 ("r-rsamtools" ,r-rsamtools)
9508 ("r-rtracklayer" ,r-rtracklayer)
9509 ("r-s4vectors" ,r-s4vectors)
9510 ("r-summarizedexperiment" ,r-summarizedexperiment)
9511 ("r-variantannotation" ,r-variantannotation)))
9512 (home-page "https://bioconductor.org/packages/GenomicFiles")
9513 (synopsis "Distributed computing by file or by range")
9515 "This package provides infrastructure for parallel computations
9516 distributed by file or by range. User defined mapper and reducer functions
9517 provide added flexibility for data combination and manipulation.")
9518 (license license:artistic2.0)))
9520 (define-public r-complexheatmap
9522 (name "r-complexheatmap")
9527 (uri (bioconductor-uri "ComplexHeatmap" version))
9530 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9532 `((upstream-name . "ComplexHeatmap")))
9533 (build-system r-build-system)
9535 `(("r-circlize" ,r-circlize)
9536 ("r-colorspace" ,r-colorspace)
9537 ("r-getoptlong" ,r-getoptlong)
9538 ("r-globaloptions" ,r-globaloptions)
9539 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9541 "https://github.com/jokergoo/ComplexHeatmap")
9542 (synopsis "Making Complex Heatmaps")
9544 "Complex heatmaps are efficient to visualize associations between
9545 different sources of data sets and reveal potential structures. This package
9546 provides a highly flexible way to arrange multiple heatmaps and supports
9547 self-defined annotation graphics.")
9548 (license license:gpl2+)))
9550 (define-public r-dirichletmultinomial
9552 (name "r-dirichletmultinomial")
9557 (uri (bioconductor-uri "DirichletMultinomial" version))
9560 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9562 `((upstream-name . "DirichletMultinomial")))
9563 (build-system r-build-system)
9567 `(("r-biocgenerics" ,r-biocgenerics)
9568 ("r-iranges" ,r-iranges)
9569 ("r-s4vectors" ,r-s4vectors)))
9570 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9571 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9573 "Dirichlet-multinomial mixture models can be used to describe variability
9574 in microbial metagenomic data. This package is an interface to code
9575 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9577 (license license:lgpl3)))
9579 (define-public r-annotationfilter
9581 (name "r-annotationfilter")
9585 (uri (bioconductor-uri "AnnotationFilter" version))
9588 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
9590 `((upstream-name . "AnnotationFilter")))
9591 (build-system r-build-system)
9593 `(("r-genomicranges" ,r-genomicranges)
9594 ("r-lazyeval" ,r-lazyeval)))
9595 (home-page "https://github.com/Bioconductor/AnnotationFilter")
9596 (synopsis "Facilities for filtering Bioconductor annotation resources")
9598 "This package provides classes and other infrastructure to implement
9599 filters for manipulating Bioconductor annotation resources. The filters are
9600 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
9601 (license license:artistic2.0)))
9603 (define-public r-ensembldb
9605 (name "r-ensembldb")
9610 (uri (bioconductor-uri "ensembldb" version))
9613 "1w0lca3ws5j770bmls91cn93lznvv2pc8s42nybdzz3vdxjvb4m1"))))
9614 (build-system r-build-system)
9616 `(("r-annotationdbi" ,r-annotationdbi)
9617 ("r-annotationfilter" ,r-annotationfilter)
9618 ("r-annotationhub" ,r-annotationhub)
9619 ("r-biobase" ,r-biobase)
9620 ("r-biocgenerics" ,r-biocgenerics)
9621 ("r-biostrings" ,r-biostrings)
9624 ("r-genomeinfodb" ,r-genomeinfodb)
9625 ("r-genomicfeatures" ,r-genomicfeatures)
9626 ("r-genomicranges" ,r-genomicranges)
9627 ("r-iranges" ,r-iranges)
9628 ("r-protgenerics" ,r-protgenerics)
9629 ("r-rsamtools" ,r-rsamtools)
9630 ("r-rsqlite" ,r-rsqlite)
9631 ("r-rtracklayer" ,r-rtracklayer)
9632 ("r-s4vectors" ,r-s4vectors)))
9633 (home-page "https://github.com/jotsetung/ensembldb")
9634 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9636 "The package provides functions to create and use transcript-centric
9637 annotation databases/packages. The annotation for the databases are directly
9638 fetched from Ensembl using their Perl API. The functionality and data is
9639 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9640 but, in addition to retrieve all gene/transcript models and annotations from
9641 the database, the @code{ensembldb} package also provides a filter framework
9642 allowing to retrieve annotations for specific entries like genes encoded on a
9643 chromosome region or transcript models of lincRNA genes.")
9644 ;; No version specified
9645 (license license:lgpl3+)))
9647 (define-public r-organismdbi
9649 (name "r-organismdbi")
9654 (uri (bioconductor-uri "OrganismDbi" version))
9657 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9658 (properties `((upstream-name . "OrganismDbi")))
9659 (build-system r-build-system)
9661 `(("r-annotationdbi" ,r-annotationdbi)
9662 ("r-biobase" ,r-biobase)
9663 ("r-biocgenerics" ,r-biocgenerics)
9664 ("r-biocinstaller" ,r-biocinstaller)
9666 ("r-genomicfeatures" ,r-genomicfeatures)
9667 ("r-genomicranges" ,r-genomicranges)
9668 ("r-graph" ,r-graph)
9669 ("r-iranges" ,r-iranges)
9671 ("r-s4vectors" ,r-s4vectors)))
9672 (home-page "https://bioconductor.org/packages/OrganismDbi")
9673 (synopsis "Software to enable the smooth interfacing of database packages")
9674 (description "The package enables a simple unified interface to several
9675 annotation packages each of which has its own schema by taking advantage of
9676 the fact that each of these packages implements a select methods.")
9677 (license license:artistic2.0)))
9679 (define-public r-biovizbase
9681 (name "r-biovizbase")
9686 (uri (bioconductor-uri "biovizBase" version))
9689 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
9690 (properties `((upstream-name . "biovizBase")))
9691 (build-system r-build-system)
9693 `(("r-annotationdbi" ,r-annotationdbi)
9694 ("r-annotationfilter" ,r-annotationfilter)
9695 ("r-biocgenerics" ,r-biocgenerics)
9696 ("r-biostrings" ,r-biostrings)
9697 ("r-dichromat" ,r-dichromat)
9698 ("r-ensembldb" ,r-ensembldb)
9699 ("r-genomeinfodb" ,r-genomeinfodb)
9700 ("r-genomicalignments" ,r-genomicalignments)
9701 ("r-genomicfeatures" ,r-genomicfeatures)
9702 ("r-genomicranges" ,r-genomicranges)
9703 ("r-hmisc" ,r-hmisc)
9704 ("r-iranges" ,r-iranges)
9705 ("r-rcolorbrewer" ,r-rcolorbrewer)
9706 ("r-rsamtools" ,r-rsamtools)
9707 ("r-s4vectors" ,r-s4vectors)
9708 ("r-scales" ,r-scales)
9709 ("r-summarizedexperiment" ,r-summarizedexperiment)
9710 ("r-variantannotation" ,r-variantannotation)))
9711 (home-page "https://bioconductor.org/packages/biovizBase")
9712 (synopsis "Basic graphic utilities for visualization of genomic data")
9714 "The biovizBase package is designed to provide a set of utilities, color
9715 schemes and conventions for genomic data. It serves as the base for various
9716 high-level packages for biological data visualization. This saves development
9717 effort and encourages consistency.")
9718 (license license:artistic2.0)))
9720 (define-public r-ggbio
9727 (uri (bioconductor-uri "ggbio" version))
9730 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
9731 (build-system r-build-system)
9733 `(("r-annotationdbi" ,r-annotationdbi)
9734 ("r-annotationfilter" ,r-annotationfilter)
9735 ("r-biobase" ,r-biobase)
9736 ("r-biocgenerics" ,r-biocgenerics)
9737 ("r-biostrings" ,r-biostrings)
9738 ("r-biovizbase" ,r-biovizbase)
9739 ("r-bsgenome" ,r-bsgenome)
9740 ("r-ensembldb" ,r-ensembldb)
9741 ("r-genomeinfodb" ,r-genomeinfodb)
9742 ("r-genomicalignments" ,r-genomicalignments)
9743 ("r-genomicfeatures" ,r-genomicfeatures)
9744 ("r-genomicranges" ,r-genomicranges)
9745 ("r-ggally" ,r-ggally)
9746 ("r-ggplot2" ,r-ggplot2)
9747 ("r-gridextra" ,r-gridextra)
9748 ("r-gtable" ,r-gtable)
9749 ("r-hmisc" ,r-hmisc)
9750 ("r-iranges" ,r-iranges)
9751 ("r-organismdbi" ,r-organismdbi)
9752 ("r-reshape2" ,r-reshape2)
9753 ("r-rsamtools" ,r-rsamtools)
9754 ("r-rtracklayer" ,r-rtracklayer)
9755 ("r-s4vectors" ,r-s4vectors)
9756 ("r-scales" ,r-scales)
9757 ("r-summarizedexperiment" ,r-summarizedexperiment)
9758 ("r-variantannotation" ,r-variantannotation)))
9759 (home-page "http://www.tengfei.name/ggbio/")
9760 (synopsis "Visualization tools for genomic data")
9762 "The ggbio package extends and specializes the grammar of graphics for
9763 biological data. The graphics are designed to answer common scientific
9764 questions, in particular those often asked of high throughput genomics data.
9765 All core Bioconductor data structures are supported, where appropriate. The
9766 package supports detailed views of particular genomic regions, as well as
9767 genome-wide overviews. Supported overviews include ideograms and grand linear
9768 views. High-level plots include sequence fragment length, edge-linked
9769 interval to data view, mismatch pileup, and several splicing summaries.")
9770 (license license:artistic2.0)))
9772 (define-public r-gprofiler
9774 (name "r-gprofiler")
9779 (uri (cran-uri "gProfileR" version))
9782 "1qix15d0wa9nspdclcawml94mng4qmr2jciv7d24py315wfsvv8p"))))
9783 (properties `((upstream-name . "gProfileR")))
9784 (build-system r-build-system)
9786 `(("r-plyr" ,r-plyr)
9787 ("r-rcurl" ,r-rcurl)))
9788 (home-page "http://cran.r-project.org/web/packages/gProfileR/")
9789 (synopsis "Interface to the g:Profiler toolkit")
9791 "This package provides tools for functional enrichment analysis,
9792 gene identifier conversion and mapping homologous genes across related
9793 organisms via the @code{g:Profiler} toolkit.")
9794 (license license:gpl2+)))
9796 (define-public r-gqtlbase
9803 (uri (bioconductor-uri "gQTLBase" version))
9806 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
9807 (properties `((upstream-name . "gQTLBase")))
9808 (build-system r-build-system)
9810 `(("r-batchjobs" ,r-batchjobs)
9811 ("r-bbmisc" ,r-bbmisc)
9812 ("r-biocgenerics" ,r-biocgenerics)
9814 ("r-doparallel" ,r-doparallel)
9816 ("r-ffbase" ,r-ffbase)
9817 ("r-foreach" ,r-foreach)
9818 ("r-genomicfiles" ,r-genomicfiles)
9819 ("r-genomicranges" ,r-genomicranges)
9820 ("r-rtracklayer" ,r-rtracklayer)
9821 ("r-s4vectors" ,r-s4vectors)
9822 ("r-summarizedexperiment" ,r-summarizedexperiment)))
9823 (home-page "https://bioconductor.org/packages/gQTLBase")
9824 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
9826 "The purpose of this package is to simplify the storage and interrogation
9827 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
9829 (license license:artistic2.0)))
9831 (define-public r-snpstats
9838 (uri (bioconductor-uri "snpStats" version))
9841 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
9842 (properties `((upstream-name . "snpStats")))
9843 (build-system r-build-system)
9844 (inputs `(("zlib" ,zlib)))
9846 `(("r-biocgenerics" ,r-biocgenerics)
9847 ("r-matrix" ,r-matrix)
9848 ("r-survival" ,r-survival)
9849 ("r-zlibbioc" ,r-zlibbioc)))
9850 (home-page "https://bioconductor.org/packages/snpStats")
9851 (synopsis "Methods for SNP association studies")
9853 "This package provides classes and statistical methods for large
9854 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
9855 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
9856 (license license:gpl3)))
9858 (define-public r-org-hs-eg-db
9860 (name "r-org-hs-eg-db")
9864 ;; We cannot use bioconductor-uri here because this tarball is
9865 ;; located under "data/annotation/" instead of "bioc/".
9866 (uri (string-append "http://www.bioconductor.org/packages/"
9867 "release/data/annotation/src/contrib/"
9872 "0izzmas99j64sc4x8pxi09xw0ra1941kjrsl8sjxl0cjw1d2b32z"))))
9874 `((upstream-name . "org.Hs.eg.db")))
9875 (build-system r-build-system)
9877 `(("r-annotationdbi" ,r-annotationdbi)))
9878 (home-page "https://bioconductor.org/packages/org.Hs.eg.db/")
9879 (synopsis "Genome-wide annotation for Human")
9881 "This package contains genome-wide annotations for Human, primarily based
9882 on mapping using Entrez Gene identifiers.")
9883 (license license:artistic2.0)))
9885 (define-public r-homo-sapiens
9887 (name "r-homo-sapiens")
9891 ;; We cannot use bioconductor-uri here because this tarball is
9892 ;; located under "data/annotation/" instead of "bioc/".
9893 (uri (string-append "http://www.bioconductor.org/packages/"
9894 "release/data/annotation/src/contrib/"
9899 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
9901 `((upstream-name . "Homo.sapiens")))
9902 (build-system r-build-system)
9904 `(("r-genomicfeatures" ,r-genomicfeatures)
9905 ("r-go-db" ,r-go-db)
9906 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
9907 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
9908 ("r-organismdbi" ,r-organismdbi)
9909 ("r-annotationdbi" ,r-annotationdbi)))
9910 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
9911 (synopsis "Annotation package for the Homo.sapiens object")
9913 "This package contains the Homo.sapiens object to access data from
9914 several related annotation packages.")
9915 (license license:artistic2.0)))
9917 (define-public r-erma
9924 (uri (bioconductor-uri "erma" version))
9927 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
9928 (build-system r-build-system)
9930 `(("r-annotationdbi" ,r-annotationdbi)
9931 ("r-biobase" ,r-biobase)
9932 ("r-biocgenerics" ,r-biocgenerics)
9933 ("r-foreach" ,r-foreach)
9934 ("r-genomicfiles" ,r-genomicfiles)
9935 ("r-genomicranges" ,r-genomicranges)
9936 ("r-ggplot2" ,r-ggplot2)
9937 ("r-homo-sapiens" ,r-homo-sapiens)
9938 ("r-rtracklayer" ,r-rtracklayer)
9939 ("r-s4vectors" ,r-s4vectors)
9940 ("r-shiny" ,r-shiny)
9941 ("r-summarizedexperiment" ,r-summarizedexperiment)))
9942 (home-page "https://bioconductor.org/packages/erma")
9943 (synopsis "Epigenomic road map adventures")
9945 "The epigenomics road map describes locations of epigenetic marks in DNA
9946 from a variety of cell types. Of interest are locations of histone
9947 modifications, sites of DNA methylation, and regions of accessible chromatin.
9948 This package presents a selection of elements of the road map including
9949 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
9950 by Ernst and Kellis.")
9951 (license license:artistic2.0)))
9953 (define-public r-ldblock
9960 (uri (bioconductor-uri "ldblock" version))
9963 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
9964 (build-system r-build-system)
9966 `(("r-erma" ,r-erma)
9967 ("r-genomeinfodb" ,r-genomeinfodb)
9968 ("r-genomicfiles" ,r-genomicfiles)
9969 ("r-go-db" ,r-go-db)
9970 ("r-homo-sapiens" ,r-homo-sapiens)
9971 ("r-matrix" ,r-matrix)
9972 ("r-rsamtools" ,r-rsamtools)
9973 ("r-snpstats" ,r-snpstats)
9974 ("r-variantannotation" ,r-variantannotation)))
9975 (home-page "https://bioconductor.org/packages/ldblock")
9976 (synopsis "Data structures for linkage disequilibrium measures in populations")
9978 "This package defines data structures for @dfn{linkage
9979 disequilibrium} (LD) measures in populations. Its purpose is to simplify
9980 handling of existing population-level data for the purpose of flexibly
9981 defining LD blocks.")
9982 (license license:artistic2.0)))
9984 (define-public r-gqtlstats
9986 (name "r-gqtlstats")
9991 (uri (bioconductor-uri "gQTLstats" version))
9994 "1cbdqawxzgna8rrgj3siph5sw4d2pb57qc0gn6ibfkhyk45f8gdv"))))
9995 (properties `((upstream-name . "gQTLstats")))
9996 (build-system r-build-system)
9998 `(("r-annotationdbi" ,r-annotationdbi)
9999 ("r-batchjobs" ,r-batchjobs)
10000 ("r-bbmisc" ,r-bbmisc)
10001 ("r-beeswarm" ,r-beeswarm)
10002 ("r-biobase" ,r-biobase)
10003 ("r-biocgenerics" ,r-biocgenerics)
10004 ("r-doparallel" ,r-doparallel)
10005 ("r-dplyr" ,r-dplyr)
10007 ("r-ffbase" ,r-ffbase)
10008 ("r-foreach" ,r-foreach)
10009 ("r-genomeinfodb" ,r-genomeinfodb)
10010 ("r-genomicfeatures" ,r-genomicfeatures)
10011 ("r-genomicfiles" ,r-genomicfiles)
10012 ("r-genomicranges" ,r-genomicranges)
10013 ("r-ggbeeswarm" ,r-ggbeeswarm)
10014 ("r-ggplot2" ,r-ggplot2)
10015 ("r-gqtlbase" ,r-gqtlbase)
10016 ("r-hardyweinberg" ,r-hardyweinberg)
10017 ("r-iranges" ,r-iranges)
10018 ("r-ldblock" ,r-ldblock)
10019 ("r-limma" ,r-limma)
10021 ("r-plotly" ,r-plotly)
10022 ("r-reshape2" ,r-reshape2)
10023 ("r-s4vectors" ,r-s4vectors)
10024 ("r-shiny" ,r-shiny)
10025 ("r-snpstats" ,r-snpstats)
10026 ("r-summarizedexperiment" ,r-summarizedexperiment)
10027 ("r-variantannotation" ,r-variantannotation)))
10028 (home-page "https://bioconductor.org/packages/gQTLstats")
10029 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10031 "This package provides tools for the computationally efficient analysis
10032 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10033 The software in this package aims to support refinements and functional
10034 interpretation of members of a collection of association statistics on a
10035 family of feature/genome hypotheses.")
10036 (license license:artistic2.0)))
10038 (define-public r-gviz
10045 (uri (bioconductor-uri "Gviz" version))
10048 "1lrw65a8426wpxw975wjcaiacpp6fqa00nif1yxigyankbfs23c8"))))
10049 (properties `((upstream-name . "Gviz")))
10050 (build-system r-build-system)
10052 `(("r-annotationdbi" ,r-annotationdbi)
10053 ("r-biobase" ,r-biobase)
10054 ("r-biocgenerics" ,r-biocgenerics)
10055 ("r-biomart" ,r-biomart)
10056 ("r-biostrings" ,r-biostrings)
10057 ("r-biovizbase" ,r-biovizbase)
10058 ("r-bsgenome" ,r-bsgenome)
10059 ("r-digest" ,r-digest)
10060 ("r-genomeinfodb" ,r-genomeinfodb)
10061 ("r-genomicalignments" ,r-genomicalignments)
10062 ("r-genomicfeatures" ,r-genomicfeatures)
10063 ("r-genomicranges" ,r-genomicranges)
10064 ("r-iranges" ,r-iranges)
10065 ("r-lattice" ,r-lattice)
10066 ("r-latticeextra" ,r-latticeextra)
10067 ("r-matrixstats" ,r-matrixstats)
10068 ("r-rcolorbrewer" ,r-rcolorbrewer)
10069 ("r-rsamtools" ,r-rsamtools)
10070 ("r-rtracklayer" ,r-rtracklayer)
10071 ("r-s4vectors" ,r-s4vectors)
10072 ("r-xvector" ,r-xvector)))
10073 (home-page "https://bioconductor.org/packages/Gviz")
10074 (synopsis "Plotting data and annotation information along genomic coordinates")
10076 "Genomic data analyses requires integrated visualization of known genomic
10077 information and new experimental data. Gviz uses the biomaRt and the
10078 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10079 and translates this to e.g. gene/transcript structures in viewports of the
10080 grid graphics package. This results in genomic information plotted together
10082 (license license:artistic2.0)))
10084 (define-public r-gwascat
10091 (uri (bioconductor-uri "gwascat" version))
10094 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10095 (build-system r-build-system)
10097 `(("r-annotationdbi" ,r-annotationdbi)
10098 ("r-annotationhub" ,r-annotationhub)
10099 ("r-biocgenerics" ,r-biocgenerics)
10100 ("r-biostrings" ,r-biostrings)
10101 ("r-genomeinfodb" ,r-genomeinfodb)
10102 ("r-genomicfeatures" ,r-genomicfeatures)
10103 ("r-genomicranges" ,r-genomicranges)
10104 ("r-ggbio" ,r-ggbio)
10105 ("r-ggplot2" ,r-ggplot2)
10106 ("r-gqtlstats" ,r-gqtlstats)
10107 ("r-graph" ,r-graph)
10109 ("r-homo-sapiens" ,r-homo-sapiens)
10110 ("r-iranges" ,r-iranges)
10111 ("r-rsamtools" ,r-rsamtools)
10112 ("r-rtracklayer" ,r-rtracklayer)
10113 ("r-s4vectors" ,r-s4vectors)
10114 ("r-snpstats" ,r-snpstats)
10115 ("r-summarizedexperiment" ,r-summarizedexperiment)
10116 ("r-variantannotation" ,r-variantannotation)))
10117 (home-page "https://bioconductor.org/packages/gwascat")
10118 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10120 "This package provides tools for representing and modeling data in the
10121 EMBL-EBI GWAS catalog.")
10122 (license license:artistic2.0)))
10124 (define-public r-sushi
10130 (uri (bioconductor-uri "Sushi" version))
10133 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10134 (properties `((upstream-name . "Sushi")))
10135 (build-system r-build-system)
10137 `(("r-biomart" ,r-biomart)
10139 (home-page "https://bioconductor.org/packages/Sushi")
10140 (synopsis "Tools for visualizing genomics data")
10142 "This package provides flexible, quantitative, and integrative genomic
10143 visualizations for publication-quality multi-panel figures.")
10144 (license license:gpl2+)))
10146 (define-public r-fithic
10152 (uri (bioconductor-uri "FitHiC" version))
10155 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10156 (properties `((upstream-name . "FitHiC")))
10157 (build-system r-build-system)
10159 `(("r-data-table" ,r-data-table)
10160 ("r-fdrtool" ,r-fdrtool)
10161 ("r-rcpp" ,r-rcpp)))
10162 (home-page "https://bioconductor.org/packages/FitHiC")
10163 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10165 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10166 intra-chromosomal contact maps produced by genome-wide genome architecture
10167 assays such as Hi-C.")
10168 (license license:gpl2+)))
10170 (define-public r-hitc
10176 (uri (bioconductor-uri "HiTC" version))
10179 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10180 (properties `((upstream-name . "HiTC")))
10181 (build-system r-build-system)
10183 `(("r-biostrings" ,r-biostrings)
10184 ("r-genomeinfodb" ,r-genomeinfodb)
10185 ("r-genomicranges" ,r-genomicranges)
10186 ("r-iranges" ,r-iranges)
10187 ("r-matrix" ,r-matrix)
10188 ("r-rcolorbrewer" ,r-rcolorbrewer)
10189 ("r-rtracklayer" ,r-rtracklayer)))
10190 (home-page "https://bioconductor.org/packages/HiTC")
10191 (synopsis "High throughput chromosome conformation capture analysis")
10193 "The HiTC package was developed to explore high-throughput \"C\" data
10194 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10195 quality controls, normalization, visualization, and further analysis are also
10197 (license license:artistic2.0)))
10199 (define-public r-qvalue
10206 (uri (bioconductor-uri "qvalue" version))
10209 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10210 (build-system r-build-system)
10212 `(("r-ggplot2" ,r-ggplot2)
10213 ("r-reshape2" ,r-reshape2)))
10214 (home-page "http://github.com/jdstorey/qvalue")
10215 (synopsis "Q-value estimation for false discovery rate control")
10217 "This package takes a list of p-values resulting from the simultaneous
10218 testing of many hypotheses and estimates their q-values and local @dfn{false
10219 discovery rate} (FDR) values. The q-value of a test measures the proportion
10220 of false positives incurred when that particular test is called significant.
10221 The local FDR measures the posterior probability the null hypothesis is true
10222 given the test's p-value. Various plots are automatically generated, allowing
10223 one to make sensible significance cut-offs. The software can be applied to
10224 problems in genomics, brain imaging, astrophysics, and data mining.")
10225 ;; Any version of the LGPL.
10226 (license license:lgpl3+)))
10228 (define htslib-for-sambamba
10229 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10232 (name "htslib-for-sambamba")
10233 (version (string-append "1.3.1-1." (string-take commit 9)))
10237 (uri (git-reference
10238 (url "https://github.com/lomereiter/htslib.git")
10240 (file-name (string-append "htslib-" version "-checkout"))
10243 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10245 (substitute-keyword-arguments (package-arguments htslib)
10247 `(modify-phases ,phases
10248 (add-after 'unpack 'bootstrap
10250 (zero? (system* "autoreconf" "-vif"))))))))
10252 `(("autoconf" ,autoconf)
10253 ("automake" ,automake)
10254 ,@(package-native-inputs htslib))))))
10256 (define-public sambamba
10263 (uri (string-append "https://github.com/lomereiter/sambamba/"
10264 "archive/v" version ".tar.gz"))
10265 (file-name (string-append name "-" version ".tar.gz"))
10268 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10269 (build-system gnu-build-system)
10271 `(#:tests? #f ; there is no test target
10273 '("D_COMPILER=ldc2"
10274 ;; Override "--compiler" flag only.
10275 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10276 "sambamba-ldmd2-64")
10278 (modify-phases %standard-phases
10279 (delete 'configure)
10280 (add-after 'unpack 'place-biod
10281 (lambda* (#:key inputs #:allow-other-keys)
10282 (copy-recursively (assoc-ref inputs "biod") "BioD")
10284 (add-after 'unpack 'unbundle-prerequisites
10286 (substitute* "Makefile"
10287 ((" htslib-static lz4-static") ""))
10290 (lambda* (#:key outputs #:allow-other-keys)
10291 (let* ((out (assoc-ref outputs "out"))
10292 (bin (string-append out "/bin")))
10294 (install-file "build/sambamba" bin)
10300 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10303 (uri (git-reference
10304 (url "https://github.com/biod/BioD.git")
10306 (file-name (string-append "biod-"
10307 (string-take commit 9)
10311 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10314 ("htslib" ,htslib-for-sambamba)))
10315 (home-page "http://lomereiter.github.io/sambamba")
10316 (synopsis "Tools for working with SAM/BAM data")
10317 (description "Sambamba is a high performance modern robust and
10318 fast tool (and library), written in the D programming language, for
10319 working with SAM and BAM files. Current parallelised functionality is
10320 an important subset of samtools functionality, including view, index,
10321 sort, markdup, and depth.")
10322 (license license:gpl2+)))
10324 (define-public ritornello
10326 (name "ritornello")
10330 (uri (string-append "https://github.com/KlugerLab/"
10331 "Ritornello/archive/v"
10332 version ".tar.gz"))
10333 (file-name (string-append name "-" version ".tar.gz"))
10336 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10337 (build-system gnu-build-system)
10339 `(#:tests? #f ; there are no tests
10341 (modify-phases %standard-phases
10342 (add-after 'unpack 'patch-samtools-references
10343 (lambda* (#:key inputs #:allow-other-keys)
10344 (substitute* '("src/SamStream.h"
10345 "src/BufferedGenomeReader.h")
10346 (("<sam.h>") "<samtools/sam.h>"))
10348 (delete 'configure)
10350 (lambda* (#:key inputs outputs #:allow-other-keys)
10351 (let* ((out (assoc-ref outputs "out"))
10352 (bin (string-append out "/bin/")))
10354 (install-file "bin/Ritornello" bin)
10357 `(("samtools" ,samtools-0.1)
10361 (home-page "https://github.com/KlugerLab/Ritornello")
10362 (synopsis "Control-free peak caller for ChIP-seq data")
10363 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10364 signal processing that can accurately call binding events without the need to
10365 do a pair total DNA input or IgG control sample. It has been tested for use
10366 with narrow binding events such as transcription factor ChIP-seq.")
10367 (license license:gpl3+)))
10369 (define-public trim-galore
10371 (name "trim-galore")
10376 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10377 "projects/trim_galore/trim_galore_v"
10381 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10382 (build-system gnu-build-system)
10384 `(#:tests? #f ; no tests
10386 (modify-phases %standard-phases
10387 ;; The archive contains plain files.
10389 (lambda* (#:key source #:allow-other-keys)
10390 (zero? (system* "unzip" source))))
10391 (delete 'configure)
10393 (add-after 'unpack 'hardcode-tool-references
10394 (lambda* (#:key inputs #:allow-other-keys)
10395 (substitute* "trim_galore"
10396 (("\\$path_to_cutadapt = 'cutadapt'")
10397 (string-append "$path_to_cutadapt = '"
10398 (assoc-ref inputs "cutadapt")
10401 (string-append "| "
10402 (assoc-ref inputs "gzip")
10405 (string-append "\""
10406 (assoc-ref inputs "gzip")
10410 (lambda* (#:key outputs #:allow-other-keys)
10411 (let ((bin (string-append (assoc-ref outputs "out")
10414 (install-file "trim_galore" bin)
10419 ("cutadapt" ,cutadapt)))
10421 `(("unzip" ,unzip)))
10422 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10423 (synopsis "Wrapper around Cutadapt and FastQC")
10424 (description "Trim Galore! is a wrapper script to automate quality and
10425 adapter trimming as well as quality control, with some added functionality to
10426 remove biased methylation positions for RRBS sequence files.")
10427 (license license:gpl3+)))
10429 (define-public gess
10435 (uri (string-append "http://compbio.uthscsa.edu/"
10437 "gess-" version ".src.tar.gz"))
10440 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10441 (build-system gnu-build-system)
10443 `(#:tests? #f ; no tests
10445 (modify-phases %standard-phases
10446 (delete 'configure)
10449 (lambda* (#:key inputs outputs #:allow-other-keys)
10450 (let* ((python (assoc-ref inputs "python"))
10451 (out (assoc-ref outputs "out"))
10452 (bin (string-append out "/bin/"))
10453 (target (string-append
10454 out "/lib/python2.7/site-packages/gess/")))
10456 (copy-recursively "." target)
10457 ;; Make GESS.py executable
10458 (chmod (string-append target "GESS.py") #o555)
10459 ;; Add Python shebang to the top and make Matplotlib
10461 (substitute* (string-append target "GESS.py")
10462 (("\"\"\"Description:" line)
10463 (string-append "#!" (which "python") "
10465 matplotlib.use('Agg')
10467 ;; Make sure GESS has all modules in its path
10468 (wrap-program (string-append target "GESS.py")
10469 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10471 (symlink (string-append target "GESS.py")
10472 (string-append bin "GESS.py"))
10475 `(("python" ,python-2)
10476 ("python2-pysam" ,python2-pysam)
10477 ("python2-scipy" ,python2-scipy)
10478 ("python2-numpy" ,python2-numpy)
10479 ("python2-networkx" ,python2-networkx)
10480 ("python2-biopython" ,python2-biopython)))
10481 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10482 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10484 "GESS is an implementation of a novel computational method to detect de
10485 novo exon-skipping events directly from raw RNA-seq data without the prior
10486 knowledge of gene annotation information. GESS stands for the graph-based
10487 exon-skipping scanner detection scheme.")
10488 (license license:bsd-3)))
10490 (define-public phylip
10497 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10498 "download/phylip-" version ".tar.gz"))
10501 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10502 (build-system gnu-build-system)
10504 `(#:tests? #f ; no check target
10505 #:make-flags (list "-f" "Makefile.unx" "install")
10506 #:parallel-build? #f ; not supported
10508 (modify-phases %standard-phases
10509 (add-after 'unpack 'enter-dir
10510 (lambda _ (chdir "src") #t))
10511 (delete 'configure)
10513 (lambda* (#:key inputs outputs #:allow-other-keys)
10514 (let ((target (string-append (assoc-ref outputs "out")
10517 (for-each (lambda (file)
10518 (install-file file target))
10519 (find-files "../exe" ".*")))
10521 (home-page "http://evolution.genetics.washington.edu/phylip/")
10522 (synopsis "Tools for inferring phylogenies")
10523 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10524 programs for inferring phylogenies (evolutionary trees).")
10525 (license license:bsd-2)))
10534 (uri (string-append "https://integrativemodeling.org/"
10535 version "/download/imp-" version ".tar.gz"))
10538 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10539 (build-system cmake-build-system)
10541 `(;; FIXME: Some tests fail because they produce warnings, others fail
10542 ;; because the PYTHONPATH does not include the modeller's directory.
10544 ;; Do not place libraries in an architecture-specific directory.
10546 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
10553 ("python" ,python-2)))
10555 `(("python2-numpy" ,python2-numpy)
10556 ("python2-scipy" ,python2-scipy)
10557 ("python2-pandas" ,python2-pandas)
10558 ("python2-scikit-learn" ,python2-scikit-learn)
10559 ("python2-networkx" ,python2-networkx)))
10560 (home-page "https://integrativemodeling.org")
10561 (synopsis "Integrative modeling platform")
10562 (description "IMP's broad goal is to contribute to a comprehensive
10563 structural characterization of biomolecules ranging in size and complexity
10564 from small peptides to large macromolecular assemblies, by integrating data
10565 from diverse biochemical and biophysical experiments. IMP provides a C++ and
10566 Python toolbox for solving complex modeling problems, and a number of
10567 applications for tackling some common problems in a user-friendly way.")
10568 ;; IMP is largely available under the GNU Lesser GPL; see the file
10569 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10570 ;; available under the GNU GPL (see the file COPYING.GPL).
10571 (license (list license:lgpl2.1+
10574 (define-public tadbit
10580 (uri (string-append "https://github.com/3DGenomes/TADbit/"
10581 "archive/v" version ".tar.gz"))
10582 (file-name (string-append name "-" version ".tar.gz"))
10585 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
10586 (build-system python-build-system)
10588 `(;; Tests are included and must be run after installation, but
10589 ;; they are incomplete and thus cannot be run.
10593 (modify-phases %standard-phases
10594 (add-after 'unpack 'fix-problems-with-setup.py
10595 (lambda* (#:key outputs #:allow-other-keys)
10596 ;; setup.py opens these files for writing
10597 (chmod "_pytadbit/_version.py" #o664)
10598 (chmod "README.rst" #o664)
10600 ;; Don't attempt to install the bash completions to
10601 ;; the home directory.
10602 (rename-file "extras/.bash_completion"
10604 (substitute* "setup.py"
10605 (("\\(path.expanduser\\('~'\\)")
10606 (string-append "(\""
10607 (assoc-ref outputs "out")
10608 "/etc/bash_completion.d\""))
10609 (("extras/\\.bash_completion")
10613 ;; TODO: add Chimera for visualization
10616 ("python2-scipy" ,python2-scipy)
10617 ("python2-numpy" ,python2-numpy)
10618 ("python2-matplotlib" ,python2-matplotlib)
10619 ("python2-pysam" ,python2-pysam)))
10620 (home-page "http://3dgenomes.github.io/TADbit/")
10621 (synopsis "Analyze, model, and explore 3C-based data")
10623 "TADbit is a complete Python library to deal with all steps to analyze,
10624 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
10625 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
10626 correct interaction matrices, identify and compare the so-called
10627 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
10628 interaction matrices, and finally, extract structural properties from the
10629 models. TADbit is complemented by TADkit for visualizing 3D models.")
10630 (license license:gpl3+)))
10632 (define-public kentutils
10635 ;; 302.1.0 is out, but the only difference is the inclusion of
10636 ;; pre-built binaries.
10637 (version "302.0.0")
10641 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
10642 "archive/v" version ".tar.gz"))
10643 (file-name (string-append name "-" version ".tar.gz"))
10646 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
10647 (modules '((guix build utils)
10652 ;; Only the contents of the specified directories are free
10653 ;; for all uses, so we remove the rest. "hg/autoSql" and
10654 ;; "hg/autoXml" are nominally free, but they depend on a
10655 ;; library that is built from the sources in "hg/lib",
10656 ;; which is nonfree.
10657 (let ((free (list "." ".."
10658 "utils" "lib" "inc" "tagStorm"
10659 "parasol" "htslib"))
10660 (directory? (lambda (file)
10661 (eq? 'directory (stat:type (stat file))))))
10662 (for-each (lambda (file)
10663 (and (directory? file)
10664 (delete-file-recursively file)))
10665 (map (cut string-append "src/" <>)
10668 (not (member file free)))))))
10669 ;; Only make the utils target, not the userApps target,
10670 ;; because that requires libraries we won't build.
10671 (substitute* "Makefile"
10672 ((" userApps") " utils"))
10673 ;; Only build libraries that are free.
10674 (substitute* "src/makefile"
10675 (("DIRS =.*") "DIRS =\n")
10676 (("cd jkOwnLib.*") "")
10679 (substitute* "src/utils/makefile"
10680 ;; These tools depend on "jkhgap.a", which is part of the
10681 ;; nonfree "src/hg/lib" directory.
10682 (("raSqlQuery") "")
10683 (("pslLiftSubrangeBlat") "")
10685 ;; Do not build UCSC tools, which may require nonfree
10687 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
10689 (build-system gnu-build-system)
10691 `( ;; There is no global test target and the test target for
10692 ;; individual tools depends on input files that are not
10696 (modify-phases %standard-phases
10697 (add-after 'unpack 'fix-paths
10699 (substitute* "Makefile"
10700 (("/bin/echo") (which "echo")))
10702 (add-after 'unpack 'prepare-samtabix
10703 (lambda* (#:key inputs #:allow-other-keys)
10704 (copy-recursively (assoc-ref inputs "samtabix")
10707 (delete 'configure)
10709 (lambda* (#:key outputs #:allow-other-keys)
10710 (let ((bin (string-append (assoc-ref outputs "out")
10712 (copy-recursively "bin" bin))
10718 (uri (git-reference
10719 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
10720 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
10723 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
10730 ("openssl" ,openssl)))
10731 (home-page "http://genome.cse.ucsc.edu/index.html")
10732 (synopsis "Assorted bioinformatics utilities")
10733 (description "This package provides the kentUtils, a selection of
10734 bioinformatics utilities used in combination with the UCSC genome
10736 ;; Only a subset of the sources are released under a non-copyleft
10737 ;; free software license. All other sources are removed in a
10738 ;; snippet. See this bug report for an explanation of how the
10739 ;; license statements apply:
10740 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
10741 (license (license:non-copyleft
10742 "http://genome.ucsc.edu/license/"
10743 "The contents of this package are free for all uses."))))
10745 (define-public f-seq
10746 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
10750 (version (string-append "1.1-" revision "." (string-take commit 7)))
10753 (uri (git-reference
10754 (url "https://github.com/aboyle/F-seq.git")
10756 (file-name (string-append name "-" version))
10759 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
10760 (modules '((guix build utils)))
10761 ;; Remove bundled Java library archives.
10764 (for-each delete-file (find-files "lib" ".*"))
10766 (build-system ant-build-system)
10768 `(#:tests? #f ; no tests included
10770 (modify-phases %standard-phases
10772 (lambda* (#:key inputs outputs #:allow-other-keys)
10773 (let* ((target (assoc-ref outputs "out"))
10774 (doc (string-append target "/share/doc/f-seq/")))
10777 (substitute* "bin/linux/fseq"
10778 (("java") (which "java"))
10779 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10780 (string-append (assoc-ref inputs "java-commons-cli")
10781 "/share/java/commons-cli.jar"))
10783 (string-append "REALDIR=" target "/bin\n")))
10784 (install-file "README.txt" doc)
10785 (install-file "bin/linux/fseq" (string-append target "/bin"))
10786 (install-file "build~/fseq.jar" (string-append target "/lib"))
10787 (copy-recursively "lib" (string-append target "/lib"))
10791 ("java-commons-cli" ,java-commons-cli)))
10792 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10793 (synopsis "Feature density estimator for high-throughput sequence tags")
10795 "F-Seq is a software package that generates a continuous tag sequence
10796 density estimation allowing identification of biologically meaningful sites
10797 such as transcription factor binding sites (ChIP-seq) or regions of open
10798 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10800 (license license:gpl3+))))
10802 (define-public bismark
10809 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10810 "archive/" version ".tar.gz"))
10811 (file-name (string-append name "-" version ".tar.gz"))
10814 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10815 (build-system perl-build-system)
10817 `(#:tests? #f ; there are no tests
10819 (modify-phases %standard-phases
10820 (delete 'configure)
10823 (lambda* (#:key outputs #:allow-other-keys)
10824 (let ((bin (string-append (assoc-ref outputs "out")
10826 (docdir (string-append (assoc-ref outputs "out")
10827 "/share/doc/bismark"))
10828 (docs '("Bismark_User_Guide.pdf"
10829 "RELEASE_NOTES.txt"))
10830 (scripts '("bismark"
10831 "bismark_genome_preparation"
10832 "bismark_methylation_extractor"
10835 "coverage2cytosine"
10836 "deduplicate_bismark"
10837 "bismark_sitrep.tpl"
10839 "bismark2summary")))
10842 (for-each (lambda (file) (install-file file bin))
10844 (for-each (lambda (file) (install-file file docdir))
10847 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10848 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
10849 (description "Bismark is a program to map bisulfite treated sequencing
10850 reads to a genome of interest and perform methylation calls in a single step.
10851 The output can be easily imported into a genome viewer, such as SeqMonk, and
10852 enables a researcher to analyse the methylation levels of their samples
10853 straight away. Its main features are:
10856 @item Bisulfite mapping and methylation calling in one single step
10857 @item Supports single-end and paired-end read alignments
10858 @item Supports ungapped and gapped alignments
10859 @item Alignment seed length, number of mismatches etc are adjustable
10860 @item Output discriminates between cytosine methylation in CpG, CHG
10863 (license license:gpl3+)))
10865 (define-public paml
10871 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
10872 "paml" version ".tgz"))
10875 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
10876 (modules '((guix build utils)))
10877 ;; Remove Windows binaries
10880 (for-each delete-file (find-files "." "\\.exe$"))
10882 (build-system gnu-build-system)
10884 `(#:tests? #f ; there are no tests
10885 #:make-flags '("CC=gcc")
10887 (modify-phases %standard-phases
10888 (replace 'configure
10890 (substitute* "src/BFdriver.c"
10891 (("/bin/bash") (which "bash")))
10895 (lambda* (#:key outputs #:allow-other-keys)
10896 (let ((tools '("baseml" "basemlg" "codeml"
10897 "pamp" "evolver" "yn00" "chi2"))
10898 (bin (string-append (assoc-ref outputs "out") "/bin"))
10899 (docdir (string-append (assoc-ref outputs "out")
10900 "/share/doc/paml")))
10902 (for-each (lambda (file) (install-file file bin)) tools)
10903 (copy-recursively "../doc" docdir)
10905 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
10906 (synopsis "Phylogentic analysis by maximum likelihood")
10907 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
10908 contains a few programs for model fitting and phylogenetic tree reconstruction
10909 using nucleotide or amino-acid sequence data.")
10911 (license license:gpl3)))