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 pkg-config)
85 #:use-module (gnu packages popt)
86 #:use-module (gnu packages protobuf)
87 #:use-module (gnu packages python)
88 #:use-module (gnu packages readline)
89 #:use-module (gnu packages ruby)
90 #:use-module (gnu packages serialization)
91 #:use-module (gnu packages shells)
92 #:use-module (gnu packages statistics)
93 #:use-module (gnu packages swig)
94 #:use-module (gnu packages tbb)
95 #:use-module (gnu packages tex)
96 #:use-module (gnu packages texinfo)
97 #:use-module (gnu packages textutils)
98 #:use-module (gnu packages time)
99 #:use-module (gnu packages tls)
100 #:use-module (gnu packages vim)
101 #:use-module (gnu packages web)
102 #:use-module (gnu packages xml)
103 #:use-module (gnu packages xorg)
104 #:use-module (srfi srfi-1)
105 #:use-module (ice-9 match))
114 (uri (cran-uri "ape" version))
117 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
118 (build-system r-build-system)
120 `(("r-lattice" ,r-lattice)
123 (home-page "http://ape-package.ird.fr/")
124 (synopsis "Analyses of phylogenetics and evolution")
126 "This package provides functions for reading, writing, plotting, and
127 manipulating phylogenetic trees, analyses of comparative data in a
128 phylogenetic framework, ancestral character analyses, analyses of
129 diversification and macroevolution, computing distances from DNA sequences,
130 and several other tools.")
131 (license license:gpl2+)))
133 (define-public aragorn
140 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
144 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
145 (build-system gnu-build-system)
147 `(#:tests? #f ; there are no tests
149 (modify-phases %standard-phases
153 (zero? (system* "gcc"
159 (string-append "aragorn" ,version ".c")))))
161 (lambda* (#:key outputs #:allow-other-keys)
162 (let* ((out (assoc-ref outputs "out"))
163 (bin (string-append out "/bin"))
164 (man (string-append out "/share/man/man1")))
166 (install-file "aragorn" bin)
168 (install-file "aragorn.1" man))
170 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
171 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
173 "Aragorn identifies transfer RNA, mitochondrial RNA and
174 transfer-messenger RNA from nucleotide sequences, based on homology to known
175 tRNA consensus sequences and RNA structure. It also outputs the secondary
176 structure of the predicted RNA.")
177 (license license:gpl2)))
185 ;; BamM is not available on pypi.
187 "https://github.com/Ecogenomics/BamM/archive/"
189 (file-name (string-append name "-" version ".tar.gz"))
192 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
193 (modules '((guix build utils)))
196 ;; Delete bundled htslib.
197 (delete-file-recursively "c/htslib-1.3.1")
199 (build-system python-build-system)
201 `(#:python ,python-2 ; BamM is Python 2 only.
202 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
203 ;; been modified from its original form.
205 (let ((htslib (assoc-ref %build-inputs "htslib")))
206 (list "--with-libhts-lib" (string-append htslib "/lib")
207 "--with-libhts-inc" (string-append htslib "/include/htslib")))
209 (modify-phases %standard-phases
210 (add-after 'unpack 'autogen
212 (with-directory-excursion "c"
213 (let ((sh (which "sh")))
214 ;; Use autogen so that 'configure' works.
215 (substitute* "autogen.sh" (("/bin/sh") sh))
216 (setenv "CONFIG_SHELL" sh)
217 (substitute* "configure" (("/bin/sh") sh))
218 (zero? (system* "./autogen.sh"))))))
220 ;; Run tests after installation so compilation only happens once.
222 (add-after 'install 'wrap-executable
223 (lambda* (#:key outputs #:allow-other-keys)
224 (let* ((out (assoc-ref outputs "out"))
225 (path (getenv "PATH")))
226 (wrap-program (string-append out "/bin/bamm")
227 `("PATH" ":" prefix (,path))))
229 (add-after 'wrap-executable 'post-install-check
230 (lambda* (#:key inputs outputs #:allow-other-keys)
232 (string-append (assoc-ref outputs "out")
237 (assoc-ref outputs "out")
239 (string-take (string-take-right
240 (assoc-ref inputs "python") 5) 3)
242 (getenv "PYTHONPATH")))
243 ;; There are 2 errors printed, but they are safe to ignore:
244 ;; 1) [E::hts_open_format] fail to open file ...
245 ;; 2) samtools view: failed to open ...
246 (zero? (system* "nosetests")))))))
248 `(("autoconf" ,autoconf)
249 ("automake" ,automake)
252 ("python-nose" ,python2-nose)
253 ("python-pysam" ,python2-pysam)))
255 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
256 ("samtools" ,samtools)
260 ("coreutils" ,coreutils)))
262 `(("python-numpy" ,python2-numpy)))
263 (home-page "http://ecogenomics.github.io/BamM/")
264 (synopsis "Metagenomics-focused BAM file manipulator")
266 "BamM is a C library, wrapped in python, to efficiently generate and
267 parse BAM files, specifically for the analysis of metagenomic data. For
268 instance, it implements several methods to assess contig-wise read coverage.")
269 (license license:lgpl3+)))
271 (define-public bamtools
278 "https://github.com/pezmaster31/bamtools/archive/v"
280 (file-name (string-append name "-" version ".tar.gz"))
283 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
284 (build-system cmake-build-system)
286 `(#:tests? #f ;no "check" target
288 (modify-phases %standard-phases
290 'configure 'set-ldflags
291 (lambda* (#:key outputs #:allow-other-keys)
295 (assoc-ref outputs "out") "/lib/bamtools")))))))
296 (inputs `(("zlib" ,zlib)))
297 (home-page "https://github.com/pezmaster31/bamtools")
298 (synopsis "C++ API and command-line toolkit for working with BAM data")
300 "BamTools provides both a C++ API and a command-line toolkit for handling
302 (license license:expat)))
304 (define-public bcftools
311 "https://github.com/samtools/bcftools/releases/download/"
312 version "/bcftools-" version ".tar.bz2"))
315 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
316 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
317 (modules '((guix build utils)))
319 ;; Delete bundled htslib.
320 '(delete-file-recursively "htslib-1.5"))))
321 (build-system gnu-build-system)
323 `(#:test-target "test"
324 #:configure-flags (list "--with-htslib=system")
328 "LIBS=-lgsl -lgslcblas"
329 (string-append "prefix=" (assoc-ref %outputs "out"))
330 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
331 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
332 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
333 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
334 (string-append "PACKAGE_VERSION=" ,version))
336 (modify-phases %standard-phases
337 (add-before 'check 'patch-tests
339 (substitute* "test/test.pl"
340 (("/bin/bash") (which "bash")))
348 (home-page "https://samtools.github.io/bcftools/")
349 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
351 "BCFtools is a set of utilities that manipulate variant calls in the
352 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
353 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
354 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
355 (license (list license:gpl3+ license:expat))))
357 (define-public bedops
363 (uri (string-append "https://github.com/bedops/bedops/archive/v"
365 (file-name (string-append name "-" version ".tar.gz"))
368 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
369 (build-system gnu-build-system)
372 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
374 (modify-phases %standard-phases
375 (add-after 'unpack 'unpack-tarballs
377 ;; FIXME: Bedops includes tarballs of minimally patched upstream
378 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
379 ;; libraries because at least one of the libraries (zlib) is
380 ;; patched to add a C++ function definition (deflateInit2cpp).
381 ;; Until the Bedops developers offer a way to link against system
382 ;; libraries we have to build the in-tree copies of these three
385 ;; See upstream discussion:
386 ;; https://github.com/bedops/bedops/issues/124
388 ;; Unpack the tarballs to benefit from shebang patching.
389 (with-directory-excursion "third-party"
390 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
391 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
392 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
393 ;; Disable unpacking of tarballs in Makefile.
394 (substitute* "system.mk/Makefile.linux"
395 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
396 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
397 (substitute* "third-party/zlib-1.2.7/Makefile.in"
398 (("^SHELL=.*$") "SHELL=bash\n"))
400 (delete 'configure))))
401 (home-page "https://github.com/bedops/bedops")
402 (synopsis "Tools for high-performance genomic feature operations")
404 "BEDOPS is a suite of tools to address common questions raised in genomic
405 studies---mostly with regard to overlap and proximity relationships between
406 data sets. It aims to be scalable and flexible, facilitating the efficient
407 and accurate analysis and management of large-scale genomic data.
409 BEDOPS provides tools that perform highly efficient and scalable Boolean and
410 other set operations, statistical calculations, archiving, conversion and
411 other management of genomic data of arbitrary scale. Tasks can be easily
412 split by chromosome for distributing whole-genome analyses across a
413 computational cluster.")
414 (license license:gpl2+)))
416 (define-public bedtools
422 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
424 (file-name (string-append name "-" version ".tar.gz"))
427 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
428 (build-system gnu-build-system)
429 (native-inputs `(("python" ,python-2)))
430 (inputs `(("samtools" ,samtools)
433 '(#:test-target "test"
435 (modify-phases %standard-phases
438 (lambda* (#:key outputs #:allow-other-keys)
439 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
440 (for-each (lambda (file)
441 (install-file file bin))
442 (find-files "bin" ".*")))
444 (home-page "https://github.com/arq5x/bedtools2")
445 (synopsis "Tools for genome analysis and arithmetic")
447 "Collectively, the bedtools utilities are a swiss-army knife of tools for
448 a wide-range of genomics analysis tasks. The most widely-used tools enable
449 genome arithmetic: that is, set theory on the genome. For example, bedtools
450 allows one to intersect, merge, count, complement, and shuffle genomic
451 intervals from multiple files in widely-used genomic file formats such as BAM,
453 (license license:gpl2)))
455 ;; Later releases of bedtools produce files with more columns than
456 ;; what Ribotaper expects.
457 (define-public bedtools-2.18
458 (package (inherit bedtools)
463 (uri (string-append "https://github.com/arq5x/bedtools2/"
464 "archive/v" version ".tar.gz"))
465 (file-name (string-append name "-" version ".tar.gz"))
468 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
470 (define-public ribotaper
476 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
477 "files/RiboTaper/RiboTaper_Version_"
481 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
482 (build-system gnu-build-system)
484 `(("bedtools" ,bedtools-2.18)
485 ("samtools" ,samtools-0.1)
486 ("r-minimal" ,r-minimal)
487 ("r-foreach" ,r-foreach)
488 ("r-xnomial" ,r-xnomial)
490 ("r-multitaper" ,r-multitaper)
491 ("r-seqinr" ,r-seqinr)))
492 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
493 (synopsis "Define translated ORFs using ribosome profiling data")
495 "Ribotaper is a method for defining translated @dfn{open reading
496 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
497 provides the Ribotaper pipeline.")
498 (license license:gpl3+)))
500 (define-public ribodiff
507 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
508 "archive/v" version ".tar.gz"))
509 (file-name (string-append name "-" version ".tar.gz"))
512 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
513 (build-system python-build-system)
517 (modify-phases %standard-phases
518 ;; Generate an installable executable script wrapper.
519 (add-after 'unpack 'patch-setup.py
521 (substitute* "setup.py"
522 (("^(.*)packages=.*" line prefix)
523 (string-append line "\n"
524 prefix "scripts=['scripts/TE.py'],\n")))
527 `(("python-numpy" ,python2-numpy)
528 ("python-matplotlib" ,python2-matplotlib)
529 ("python-scipy" ,python2-scipy)
530 ("python-statsmodels" ,python2-statsmodels)))
532 `(("python-mock" ,python2-mock)
533 ("python-nose" ,python2-nose)))
534 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
535 (synopsis "Detect translation efficiency changes from ribosome footprints")
536 (description "RiboDiff is a statistical tool that detects the protein
537 translational efficiency change from Ribo-Seq (ribosome footprinting) and
538 RNA-Seq data. It uses a generalized linear model to detect genes showing
539 difference in translational profile taking mRNA abundance into account. It
540 facilitates us to decipher the translational regulation that behave
541 independently with transcriptional regulation.")
542 (license license:gpl3+)))
544 (define-public bioawk
550 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
552 (file-name (string-append name "-" version ".tar.gz"))
554 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
555 (build-system gnu-build-system)
561 `(#:tests? #f ; There are no tests to run.
562 ;; Bison must generate files, before other targets can build.
565 (modify-phases %standard-phases
566 (delete 'configure) ; There is no configure phase.
568 (lambda* (#:key outputs #:allow-other-keys)
569 (let* ((out (assoc-ref outputs "out"))
570 (bin (string-append out "/bin"))
571 (man (string-append out "/share/man/man1")))
573 (copy-file "awk.1" (string-append man "/bioawk.1"))
574 (install-file "bioawk" bin)))))))
575 (home-page "https://github.com/lh3/bioawk")
576 (synopsis "AWK with bioinformatics extensions")
577 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
578 support of several common biological data formats, including optionally gzip'ed
579 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
580 also adds a few built-in functions and a command line option to use TAB as the
581 input/output delimiter. When the new functionality is not used, bioawk is
582 intended to behave exactly the same as the original BWK awk.")
583 (license license:x11)))
585 (define-public python2-pybedtools
587 (name "python2-pybedtools")
592 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
596 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
597 (build-system python-build-system)
598 (arguments `(#:python ,python-2)) ; no Python 3 support
600 `(("python-matplotlib" ,python2-matplotlib)))
602 `(("bedtools" ,bedtools)
603 ("samtools" ,samtools)))
605 `(("python-cython" ,python2-cython)
606 ("python-pyyaml" ,python2-pyyaml)
607 ("python-nose" ,python2-nose)))
608 (home-page "https://pythonhosted.org/pybedtools/")
609 (synopsis "Python wrapper for BEDtools programs")
611 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
612 which are widely used for genomic interval manipulation or \"genome algebra\".
613 pybedtools extends BEDTools by offering feature-level manipulations from with
615 (license license:gpl2+)))
617 (define-public python-biom-format
619 (name "python-biom-format")
624 ;; Use GitHub as source because PyPI distribution does not contain
625 ;; test data: https://github.com/biocore/biom-format/issues/693
626 (uri (string-append "https://github.com/biocore/biom-format/archive/"
628 (file-name (string-append name "-" version ".tar.gz"))
631 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
632 (build-system python-build-system)
634 `(("python-numpy" ,python-numpy)
635 ("python-scipy" ,python-scipy)
636 ("python-future" ,python-future)
637 ("python-click" ,python-click)
638 ("python-h5py" ,python-h5py)
639 ("python-pandas" ,python-pandas)))
641 `(("python-nose" ,python-nose)))
642 (home-page "http://www.biom-format.org")
643 (synopsis "Biological Observation Matrix (BIOM) format utilities")
645 "The BIOM file format is designed to be a general-use format for
646 representing counts of observations e.g. operational taxonomic units, KEGG
647 orthology groups or lipid types, in one or more biological samples
648 e.g. microbiome samples, genomes, metagenomes.")
649 (license license:bsd-3)
650 (properties `((python2-variant . ,(delay python2-biom-format))))))
652 (define-public python2-biom-format
653 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
658 (modify-phases %standard-phases
659 ;; Do not require the unmaintained pyqi library.
660 (add-after 'unpack 'remove-pyqi
662 (substitute* "setup.py"
663 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
665 ,@(package-arguments base))))))
667 (define-public bioperl-minimal
668 (let* ((inputs `(("perl-module-build" ,perl-module-build)
669 ("perl-data-stag" ,perl-data-stag)
670 ("perl-libwww" ,perl-libwww)
671 ("perl-uri" ,perl-uri)))
673 (map (compose package-name cadr)
676 (map (compose package-transitive-target-inputs cadr) inputs))))))
678 (name "bioperl-minimal")
683 (uri (string-append "https://github.com/bioperl/bioperl-live/"
685 (string-map (lambda (c)
691 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
692 (build-system perl-build-system)
695 (modify-phases %standard-phases
697 'install 'wrap-programs
698 (lambda* (#:key outputs #:allow-other-keys)
699 ;; Make sure all executables in "bin" find the required Perl
700 ;; modules at runtime. As the PERL5LIB variable contains also
701 ;; the paths of native inputs, we pick the transitive target
702 ;; inputs from %build-inputs.
703 (let* ((out (assoc-ref outputs "out"))
704 (bin (string-append out "/bin/"))
706 (cons (string-append out "/lib/perl5/site_perl")
708 (assoc-ref %build-inputs name))
709 ',transitive-inputs))
711 (for-each (lambda (file)
713 `("PERL5LIB" ":" prefix (,path))))
714 (find-files bin "\\.pl$"))
718 `(("perl-test-most" ,perl-test-most)))
719 (home-page "http://search.cpan.org/dist/BioPerl")
720 (synopsis "Bioinformatics toolkit")
722 "BioPerl is the product of a community effort to produce Perl code which
723 is useful in biology. Examples include Sequence objects, Alignment objects
724 and database searching objects. These objects not only do what they are
725 advertised to do in the documentation, but they also interact - Alignment
726 objects are made from the Sequence objects, Sequence objects have access to
727 Annotation and SeqFeature objects and databases, Blast objects can be
728 converted to Alignment objects, and so on. This means that the objects
729 provide a coordinated and extensible framework to do computational biology.")
730 (license license:perl-license))))
732 (define-public python-biopython
734 (name "python-biopython")
738 ;; use PyPi rather than biopython.org to ease updating
739 (uri (pypi-uri "biopython" version))
742 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
743 (build-system python-build-system)
746 (modify-phases %standard-phases
747 (add-before 'check 'set-home
748 ;; Some tests require a home directory to be set.
749 (lambda _ (setenv "HOME" "/tmp") #t)))))
751 `(("python-numpy" ,python-numpy)))
752 (home-page "http://biopython.org/")
753 (synopsis "Tools for biological computation in Python")
755 "Biopython is a set of tools for biological computation including parsers
756 for bioinformatics files into Python data structures; interfaces to common
757 bioinformatics programs; a standard sequence class and tools for performing
758 common operations on them; code to perform data classification; code for
759 dealing with alignments; code making it easy to split up parallelizable tasks
760 into separate processes; and more.")
761 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
763 (define-public python2-biopython
764 (package-with-python2 python-biopython))
766 ;; An outdated version of biopython is required for seqmagick, see
767 ;; https://github.com/fhcrc/seqmagick/issues/59
768 ;; When that issue has been resolved this package should be removed.
769 (define python2-biopython-1.66
771 (inherit python2-biopython)
775 (uri (pypi-uri "biopython" version))
778 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
780 (define-public bpp-core
781 ;; The last release was in 2014 and the recommended way to install from source
782 ;; is to clone the git repository, so we do this.
783 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
784 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
787 (version (string-append "2.2.0-1." (string-take commit 7)))
791 (url "http://biopp.univ-montp2.fr/git/bpp-core")
793 (file-name (string-append name "-" version "-checkout"))
796 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
797 (build-system cmake-build-system)
799 `(#:parallel-build? #f))
801 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
802 ; compile all of the bpp packages with GCC 5.
803 (home-page "http://biopp.univ-montp2.fr")
804 (synopsis "C++ libraries for Bioinformatics")
806 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
807 analysis, phylogenetics, molecular evolution and population genetics. It is
808 Object Oriented and is designed to be both easy to use and computer efficient.
809 Bio++ intends to help programmers to write computer expensive programs, by
810 providing them a set of re-usable tools.")
811 (license license:cecill-c))))
813 (define-public bpp-phyl
814 ;; The last release was in 2014 and the recommended way to install from source
815 ;; is to clone the git repository, so we do this.
816 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
817 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
820 (version (string-append "2.2.0-1." (string-take commit 7)))
824 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
826 (file-name (string-append name "-" version "-checkout"))
829 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
830 (build-system cmake-build-system)
832 `(#:parallel-build? #f
833 ;; If out-of-source, test data is not copied into the build directory
834 ;; so the tests fail.
835 #:out-of-source? #f))
837 `(("bpp-core" ,bpp-core)
839 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
842 (home-page "http://biopp.univ-montp2.fr")
843 (synopsis "Bio++ phylogenetic Library")
845 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
846 analysis, phylogenetics, molecular evolution and population genetics. This
847 library provides phylogenetics-related modules.")
848 (license license:cecill-c))))
850 (define-public bpp-popgen
851 ;; The last release was in 2014 and the recommended way to install from source
852 ;; is to clone the git repository, so we do this.
853 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
854 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
857 (version (string-append "2.2.0-1." (string-take commit 7)))
861 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
863 (file-name (string-append name "-" version "-checkout"))
866 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
867 (build-system cmake-build-system)
869 `(#:parallel-build? #f
870 #:tests? #f)) ; There are no tests.
872 `(("bpp-core" ,bpp-core)
875 (home-page "http://biopp.univ-montp2.fr")
876 (synopsis "Bio++ population genetics library")
878 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
879 analysis, phylogenetics, molecular evolution and population genetics. This
880 library provides population genetics-related modules.")
881 (license license:cecill-c))))
883 (define-public bpp-seq
884 ;; The last release was in 2014 and the recommended way to install from source
885 ;; is to clone the git repository, so we do this.
886 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
887 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
890 (version (string-append "2.2.0-1." (string-take commit 7)))
894 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
896 (file-name (string-append name "-" version "-checkout"))
899 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
900 (build-system cmake-build-system)
902 `(#:parallel-build? #f
903 ;; If out-of-source, test data is not copied into the build directory
904 ;; so the tests fail.
905 #:out-of-source? #f))
907 `(("bpp-core" ,bpp-core)
908 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
909 (home-page "http://biopp.univ-montp2.fr")
910 (synopsis "Bio++ sequence library")
912 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
913 analysis, phylogenetics, molecular evolution and population genetics. This
914 library provides sequence-related modules.")
915 (license license:cecill-c))))
917 (define-public bppsuite
918 ;; The last release was in 2014 and the recommended way to install from source
919 ;; is to clone the git repository, so we do this.
920 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
921 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
924 (version (string-append "2.2.0-1." (string-take commit 7)))
928 (url "http://biopp.univ-montp2.fr/git/bppsuite")
930 (file-name (string-append name "-" version "-checkout"))
933 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
934 (build-system cmake-build-system)
936 `(#:parallel-build? #f
937 #:tests? #f)) ; There are no tests.
941 ("texinfo" ,texinfo)))
943 `(("bpp-core" ,bpp-core)
945 ("bpp-phyl" ,bpp-phyl)
946 ("bpp-phyl" ,bpp-popgen)
948 (home-page "http://biopp.univ-montp2.fr")
949 (synopsis "Bioinformatics tools written with the Bio++ libraries")
951 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
952 analysis, phylogenetics, molecular evolution and population genetics. This
953 package provides command line tools using the Bio++ library.")
954 (license license:cecill-c))))
956 (define-public blast+
963 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
964 version "/ncbi-blast-" version "+-src.tar.gz"))
967 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
968 (patches (search-patches "blast+-fix-makefile.patch"))
969 (modules '((guix build utils)))
972 ;; Remove bundled bzip2, zlib and pcre.
973 (delete-file-recursively "c++/src/util/compress/bzip2")
974 (delete-file-recursively "c++/src/util/compress/zlib")
975 (delete-file-recursively "c++/src/util/regexp")
976 (substitute* "c++/src/util/compress/Makefile.in"
977 (("bzip2 zlib api") "api"))
978 ;; Remove useless msbuild directory
979 (delete-file-recursively
980 "c++/src/build-system/project_tree_builder/msbuild")
982 (build-system gnu-build-system)
984 `(;; There are two(!) tests for this massive library, and both fail with
985 ;; "unparsable timing stats".
986 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
987 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
990 #:parallel-build? #f ; not supported
992 (modify-phases %standard-phases
995 ;; $HOME needs to be set at some point during the configure phase
996 (lambda _ (setenv "HOME" "/tmp") #t))
999 (lambda _ (chdir "c++") #t))
1001 'enter-dir 'fix-build-system
1003 (define (which* cmd)
1004 (cond ((string=? cmd "date")
1005 ;; make call to "date" deterministic
1010 (format (current-error-port)
1011 "WARNING: Unable to find absolute path for ~s~%"
1015 ;; Rewrite hardcoded paths to various tools
1016 (substitute* (append '("src/build-system/configure.ac"
1017 "src/build-system/configure"
1018 "src/build-system/helpers/run_with_lock.c"
1019 "scripts/common/impl/if_diff.sh"
1020 "scripts/common/impl/run_with_lock.sh"
1021 "src/build-system/Makefile.configurables.real"
1022 "src/build-system/Makefile.in.top"
1023 "src/build-system/Makefile.meta.gmake=no"
1024 "src/build-system/Makefile.meta.in"
1025 "src/build-system/Makefile.meta_l"
1026 "src/build-system/Makefile.meta_p"
1027 "src/build-system/Makefile.meta_r"
1028 "src/build-system/Makefile.mk.in"
1029 "src/build-system/Makefile.requirements"
1030 "src/build-system/Makefile.rules_with_autodep.in")
1031 (find-files "scripts/common/check" "\\.sh$"))
1032 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1033 (or (which* cmd) all)))
1035 (substitute* (find-files "src/build-system" "^config.*")
1036 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1039 ;; rewrite "/var/tmp" in check script
1040 (substitute* "scripts/common/check/check_make_unix.sh"
1041 (("/var/tmp") "/tmp"))
1043 ;; do not reset PATH
1044 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1046 (("action=/bin/") "action=")
1047 (("export PATH") ":"))
1051 (lambda* (#:key inputs outputs #:allow-other-keys)
1052 (let ((out (assoc-ref outputs "out"))
1053 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1054 (include (string-append (assoc-ref outputs "include")
1055 "/include/ncbi-tools++")))
1056 ;; The 'configure' script doesn't recognize things like
1057 ;; '--enable-fast-install'.
1058 (zero? (system* "./configure.orig"
1059 (string-append "--with-build-root=" (getcwd) "/build")
1060 (string-append "--prefix=" out)
1061 (string-append "--libdir=" lib)
1062 (string-append "--includedir=" include)
1063 (string-append "--with-bz2="
1064 (assoc-ref inputs "bzip2"))
1065 (string-append "--with-z="
1066 (assoc-ref inputs "zlib"))
1067 (string-append "--with-pcre="
1068 (assoc-ref inputs "pcre"))
1069 ;; Each library is built twice by default, once
1070 ;; with "-static" in its name, and again
1073 "--with-dll"))))))))
1074 (outputs '("out" ; 21 MB
1082 ("python" ,python-wrapper)))
1085 (home-page "http://blast.ncbi.nlm.nih.gov")
1086 (synopsis "Basic local alignment search tool")
1088 "BLAST is a popular method of performing a DNA or protein sequence
1089 similarity search, using heuristics to produce results quickly. It also
1090 calculates an “expect value” that estimates how many matches would have
1091 occurred at a given score by chance, which can aid a user in judging how much
1092 confidence to have in an alignment.")
1093 ;; Most of the sources are in the public domain, with the following
1096 ;; * ./c++/include/util/bitset/
1097 ;; * ./c++/src/html/ncbi_menu*.js
1099 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1101 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1103 ;; * ./c++/src/corelib/teamcity_*
1104 (license (list license:public-domain
1110 (define-public bless
1116 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1120 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1121 (modules '((guix build utils)))
1124 ;; Remove bundled boost, pigz, zlib, and .git directory
1125 ;; FIXME: also remove bundled sources for murmurhash3 and
1126 ;; kmc once packaged.
1127 (delete-file-recursively "boost")
1128 (delete-file-recursively "pigz")
1129 (delete-file-recursively "google-sparsehash")
1130 (delete-file-recursively "zlib")
1131 (delete-file-recursively ".git")
1133 (build-system gnu-build-system)
1135 '(#:tests? #f ;no "check" target
1137 (list (string-append "ZLIB="
1138 (assoc-ref %build-inputs "zlib")
1140 (string-append "LDFLAGS="
1141 (string-join '("-lboost_filesystem"
1148 (modify-phases %standard-phases
1149 (add-after 'unpack 'do-not-build-bundled-pigz
1150 (lambda* (#:key inputs outputs #:allow-other-keys)
1151 (substitute* "Makefile"
1152 (("cd pigz/pigz-2.3.3; make") ""))
1154 (add-after 'unpack 'patch-paths-to-executables
1155 (lambda* (#:key inputs outputs #:allow-other-keys)
1156 (substitute* "parse_args.cpp"
1157 (("kmc_binary = .*")
1158 (string-append "kmc_binary = \""
1159 (assoc-ref outputs "out")
1161 (("pigz_binary = .*")
1162 (string-append "pigz_binary = \""
1163 (assoc-ref inputs "pigz")
1167 (lambda* (#:key outputs #:allow-other-keys)
1168 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1169 (for-each (lambda (file)
1170 (install-file file bin))
1171 '("bless" "kmc/bin/kmc"))
1173 (delete 'configure))))
1177 `(("openmpi" ,openmpi)
1179 ("sparsehash" ,sparsehash)
1182 (supported-systems '("x86_64-linux"))
1183 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1184 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1186 "@dfn{Bloom-filter-based error correction solution for high-throughput
1187 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1188 correction tool for genomic reads produced by @dfn{Next-generation
1189 sequencing} (NGS). BLESS produces accurate correction results with much less
1190 memory compared with previous solutions and is also able to tolerate a higher
1191 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1192 errors at the end of reads.")
1193 (license license:gpl3+)))
1195 (define-public bowtie
1201 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1203 (file-name (string-append name "-" version ".tar.gz"))
1206 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1207 (modules '((guix build utils)))
1209 '(substitute* "Makefile"
1210 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1211 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1212 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1213 (build-system gnu-build-system)
1216 ("perl-clone" ,perl-clone)
1217 ("perl-test-deep" ,perl-test-deep)
1218 ("perl-test-simple" ,perl-test-simple)
1219 ("python" ,python-2)
1226 (string-append "prefix=" (assoc-ref %outputs "out")))
1228 (modify-phases %standard-phases
1231 (lambda* (#:key outputs #:allow-other-keys)
1232 (zero? (system* "perl"
1233 "scripts/test/simple_tests.pl"
1234 "--bowtie2=./bowtie2"
1235 "--bowtie2-build=./bowtie2-build")))))))
1236 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1237 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1239 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1240 reads to long reference sequences. It is particularly good at aligning reads
1241 of about 50 up to 100s or 1,000s of characters, and particularly good at
1242 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1243 genome with an FM Index to keep its memory footprint small: for the human
1244 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1245 gapped, local, and paired-end alignment modes.")
1246 (supported-systems '("x86_64-linux"))
1247 (license license:gpl3+)))
1249 (define-public tophat
1256 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1260 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1261 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1262 (modules '((guix build utils)))
1265 ;; Remove bundled SeqAn and samtools
1266 (delete-file-recursively "src/SeqAn-1.3")
1267 (delete-file-recursively "src/samtools-0.1.18")
1269 (build-system gnu-build-system)
1271 '(#:parallel-build? #f ; not supported
1273 (modify-phases %standard-phases
1274 (add-after 'unpack 'use-system-samtools
1275 (lambda* (#:key inputs #:allow-other-keys)
1276 (substitute* "src/Makefile.in"
1277 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1278 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1279 (("SAMPROG = samtools_0\\.1\\.18") "")
1280 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1281 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1282 (substitute* '("src/common.cpp"
1284 (("samtools_0.1.18") (which "samtools")))
1285 (substitute* '("src/common.h"
1286 "src/bam2fastx.cpp")
1287 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1288 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1289 (substitute* '("src/bwt_map.h"
1291 "src/align_status.h")
1292 (("#include <bam.h>") "#include <samtools/bam.h>")
1293 (("#include <sam.h>") "#include <samtools/sam.h>"))
1298 ("samtools" ,samtools-0.1)
1299 ("ncurses" ,ncurses)
1300 ("python" ,python-2)
1304 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1305 (synopsis "Spliced read mapper for RNA-Seq data")
1307 "TopHat is a fast splice junction mapper for nucleotide sequence
1308 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1309 mammalian-sized genomes using the ultra high-throughput short read
1310 aligner Bowtie, and then analyzes the mapping results to identify
1311 splice junctions between exons.")
1312 ;; TopHat is released under the Boost Software License, Version 1.0
1313 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1314 (license license:boost1.0)))
1323 "https://github.com/lh3/bwa/releases/download/v"
1324 version "/bwa-" version ".tar.bz2"))
1327 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1328 (build-system gnu-build-system)
1330 '(#:tests? #f ;no "check" target
1332 (modify-phases %standard-phases
1334 (lambda* (#:key outputs #:allow-other-keys)
1335 (let ((bin (string-append
1336 (assoc-ref outputs "out") "/bin"))
1338 (assoc-ref outputs "out") "/share/doc/bwa"))
1340 (assoc-ref outputs "out") "/share/man/man1")))
1341 (install-file "bwa" bin)
1342 (install-file "README.md" doc)
1343 (install-file "bwa.1" man))
1345 ;; no "configure" script
1346 (delete 'configure))))
1347 (inputs `(("zlib" ,zlib)))
1348 ;; Non-portable SSE instructions are used so building fails on platforms
1349 ;; other than x86_64.
1350 (supported-systems '("x86_64-linux"))
1351 (home-page "http://bio-bwa.sourceforge.net/")
1352 (synopsis "Burrows-Wheeler sequence aligner")
1354 "BWA is a software package for mapping low-divergent sequences against a
1355 large reference genome, such as the human genome. It consists of three
1356 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1357 designed for Illumina sequence reads up to 100bp, while the rest two for
1358 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1359 features such as long-read support and split alignment, but BWA-MEM, which is
1360 the latest, is generally recommended for high-quality queries as it is faster
1361 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1362 70-100bp Illumina reads.")
1363 (license license:gpl3+)))
1365 (define-public bwa-pssm
1366 (package (inherit bwa)
1371 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1372 "archive/" version ".tar.gz"))
1373 (file-name (string-append name "-" version ".tar.gz"))
1376 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1377 (build-system gnu-build-system)
1382 (home-page "http://bwa-pssm.binf.ku.dk/")
1383 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1385 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1386 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1387 existing aligners it is fast and sensitive. Unlike most other aligners,
1388 however, it is also adaptible in the sense that one can direct the alignment
1389 based on known biases within the data set. It is coded as a modification of
1390 the original BWA alignment program and shares the genome index structure as
1391 well as many of the command line options.")
1392 (license license:gpl3+)))
1394 (define-public python2-bx-python
1396 (name "python2-bx-python")
1400 (uri (pypi-uri "bx-python" version))
1403 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1404 (modules '((guix build utils)))
1406 '(substitute* "setup.py"
1407 ;; remove dependency on outdated "distribute" module
1408 (("^from distribute_setup import use_setuptools") "")
1409 (("^use_setuptools\\(\\)") "")))))
1410 (build-system python-build-system)
1412 `(#:tests? #f ;tests fail because test data are not included
1413 #:python ,python-2))
1415 `(("python-numpy" ,python2-numpy)
1418 `(("python-nose" ,python2-nose)))
1419 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1420 (synopsis "Tools for manipulating biological data")
1422 "bx-python provides tools for manipulating biological data, particularly
1423 multiple sequence alignments.")
1424 (license license:expat)))
1426 (define-public python-pysam
1428 (name "python-pysam")
1429 (version "0.11.2.2")
1432 ;; Test data is missing on PyPi.
1434 "https://github.com/pysam-developers/pysam/archive/v"
1436 (file-name (string-append name "-" version ".tar.gz"))
1439 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1440 (modules '((guix build utils)))
1442 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1443 '(delete-file-recursively "htslib"))))
1444 (build-system python-build-system)
1446 `(#:modules ((ice-9 ftw)
1448 (guix build python-build-system)
1451 (modify-phases %standard-phases
1452 (add-before 'build 'set-flags
1453 (lambda* (#:key inputs #:allow-other-keys)
1454 (setenv "HTSLIB_MODE" "external")
1455 (setenv "HTSLIB_LIBRARY_DIR"
1456 (string-append (assoc-ref inputs "htslib") "/lib"))
1457 (setenv "HTSLIB_INCLUDE_DIR"
1458 (string-append (assoc-ref inputs "htslib") "/include"))
1459 (setenv "LDFLAGS" "-lncurses")
1460 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1463 (lambda* (#:key inputs outputs #:allow-other-keys)
1464 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1465 (setenv "PYTHONPATH"
1467 (getenv "PYTHONPATH")
1468 ":" (getcwd) "/build/"
1469 (car (scandir "build"
1470 (negate (cut string-prefix? "." <>))))))
1471 ;; Step out of source dir so python does not import from CWD.
1472 (with-directory-excursion "tests"
1473 (setenv "HOME" "/tmp")
1474 (and (zero? (system* "make" "-C" "pysam_data"))
1475 (zero? (system* "make" "-C" "cbcf_data"))
1476 ;; Running nosetests without explicitly asking for a
1477 ;; single process leads to a crash. Running with multiple
1478 ;; processes fails because the tests are not designed to
1481 ;; FIXME: tests keep timing out on some systems.
1482 ;; (zero? (system* "nosetests" "-v"
1483 ;; "--processes" "1"))
1486 `(("htslib" ,htslib))) ; Included from installed header files.
1488 `(("ncurses" ,ncurses)
1491 `(("python-cython" ,python-cython)
1492 ;; Dependencies below are are for tests only.
1493 ("samtools" ,samtools)
1494 ("bcftools" ,bcftools)
1495 ("python-nose" ,python-nose)))
1496 (home-page "https://github.com/pysam-developers/pysam")
1497 (synopsis "Python bindings to the SAMtools C API")
1499 "Pysam is a Python module for reading and manipulating files in the
1500 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1501 also includes an interface for tabix.")
1502 (license license:expat)))
1504 (define-public python2-pysam
1505 (package-with-python2 python-pysam))
1507 (define-public python-twobitreader
1509 (name "python-twobitreader")
1513 (uri (pypi-uri "twobitreader" version))
1516 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1517 (build-system python-build-system)
1519 '(;; Tests are not distributed in the PyPi release.
1520 ;; TODO Try building from the Git repo or asking the upstream maintainer
1521 ;; to distribute the tests on PyPi.
1524 `(("python-sphinx" ,python-sphinx)))
1525 (home-page "https://github.com/benjschiller/twobitreader")
1526 (synopsis "Python library for reading .2bit files")
1528 "twobitreader is a Python library for reading .2bit files as used by the
1529 UCSC genome browser.")
1530 (license license:artistic2.0)))
1532 (define-public python2-twobitreader
1533 (package-with-python2 python-twobitreader))
1535 (define-public python-plastid
1537 (name "python-plastid")
1541 (uri (pypi-uri "plastid" version))
1544 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1545 (build-system python-build-system)
1547 ;; Some test files are not included.
1550 `(("python-numpy" ,python-numpy)
1551 ("python-scipy" ,python-scipy)
1552 ("python-pandas" ,python-pandas)
1553 ("python-pysam" ,python-pysam)
1554 ("python-matplotlib" ,python-matplotlib)
1555 ("python-biopython" ,python-biopython)
1556 ("python-twobitreader" ,python-twobitreader)
1557 ("python-termcolor" ,python-termcolor)))
1559 `(("python-cython" ,python-cython)
1560 ("python-nose" ,python-nose)))
1561 (home-page "https://github.com/joshuagryphon/plastid")
1562 (synopsis "Python library for genomic analysis")
1564 "plastid is a Python library for genomic analysis – in particular,
1565 high-throughput sequencing data – with an emphasis on simplicity.")
1566 (license license:bsd-3)))
1568 (define-public python2-plastid
1569 (package-with-python2 python-plastid))
1571 (define-public cd-hit
1577 (uri (string-append "https://github.com/weizhongli/cdhit"
1578 "/releases/download/V" version
1580 "-2017-0621-source.tar.gz"))
1583 "1386dg2npx8p62wmv08mjzsd2z3waknb9j1gg3gkvblcy57hymnn"))))
1584 (build-system gnu-build-system)
1586 `(#:tests? #f ; there are no tests
1588 ;; Executables are copied directly to the PREFIX.
1589 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1591 (modify-phases %standard-phases
1592 ;; No "configure" script
1594 ;; Remove sources of non-determinism
1595 (add-after 'unpack 'be-timeless
1597 (substitute* "cdhit-utility.c++"
1598 ((" \\(built on \" __DATE__ \"\\)") ""))
1599 (substitute* "cdhit-common.c++"
1600 (("__DATE__") "\"0\"")
1601 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1603 ;; The "install" target does not create the target directory.
1604 (add-before 'install 'create-target-dir
1605 (lambda* (#:key outputs #:allow-other-keys)
1606 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1610 (home-page "http://weizhongli-lab.org/cd-hit/")
1611 (synopsis "Cluster and compare protein or nucleotide sequences")
1613 "CD-HIT is a program for clustering and comparing protein or nucleotide
1614 sequences. CD-HIT is designed to be fast and handle extremely large
1616 ;; The manual says: "It can be copied under the GNU General Public License
1617 ;; version 2 (GPLv2)."
1618 (license license:gpl2)))
1620 (define-public clipper
1627 "https://github.com/YeoLab/clipper/archive/"
1629 (file-name (string-append name "-" version ".tar.gz"))
1632 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1633 (modules '((guix build utils)))
1636 ;; remove unnecessary setup dependency
1637 (substitute* "setup.py"
1638 (("setup_requires = .*") ""))
1639 (for-each delete-file
1640 '("clipper/src/peaks.so"
1641 "clipper/src/readsToWiggle.so"))
1642 (delete-file-recursively "dist/")
1644 (build-system python-build-system)
1645 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1647 `(("htseq" ,python2-htseq)
1648 ("python-pybedtools" ,python2-pybedtools)
1649 ("python-cython" ,python2-cython)
1650 ("python-scikit-learn" ,python2-scikit-learn)
1651 ("python-matplotlib" ,python2-matplotlib)
1652 ("python-pandas" ,python2-pandas)
1653 ("python-pysam" ,python2-pysam)
1654 ("python-numpy" ,python2-numpy)
1655 ("python-scipy" ,python2-scipy)))
1657 `(("python-mock" ,python2-mock) ; for tests
1658 ("python-nose" ,python2-nose) ; for tests
1659 ("python-pytz" ,python2-pytz))) ; for tests
1660 (home-page "https://github.com/YeoLab/clipper")
1661 (synopsis "CLIP peak enrichment recognition")
1663 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1664 (license license:gpl2)))
1666 (define-public codingquarry
1668 (name "codingquarry")
1673 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1677 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1678 (build-system gnu-build-system)
1680 '(#:tests? #f ; no "check" target
1682 (modify-phases %standard-phases
1685 (lambda* (#:key outputs #:allow-other-keys)
1686 (let* ((out (assoc-ref outputs "out"))
1687 (bin (string-append out "/bin"))
1688 (doc (string-append out "/share/doc/codingquarry")))
1689 (install-file "INSTRUCTIONS.pdf" doc)
1690 (copy-recursively "QuarryFiles"
1691 (string-append out "/QuarryFiles"))
1692 (install-file "CodingQuarry" bin)
1693 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1694 (inputs `(("openmpi" ,openmpi)))
1695 (native-search-paths
1696 (list (search-path-specification
1697 (variable "QUARRY_PATH")
1698 (files '("QuarryFiles")))))
1699 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1700 (synopsis "Fungal gene predictor")
1701 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1702 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1703 (home-page "https://sourceforge.net/projects/codingquarry/")
1704 (license license:gpl3+)))
1706 (define-public couger
1713 "http://couger.oit.duke.edu/static/assets/COUGER"
1717 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1718 (build-system gnu-build-system)
1722 (modify-phases %standard-phases
1727 (lambda* (#:key outputs #:allow-other-keys)
1728 (let* ((out (assoc-ref outputs "out"))
1729 (bin (string-append out "/bin")))
1730 (copy-recursively "src" (string-append out "/src"))
1732 ;; Add "src" directory to module lookup path.
1733 (substitute* "couger"
1735 (string-append "import sys\nsys.path.append(\""
1736 out "\")\nfrom argparse")))
1737 (install-file "couger" bin))
1740 'install 'wrap-program
1741 (lambda* (#:key inputs outputs #:allow-other-keys)
1742 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1743 (let* ((out (assoc-ref outputs "out"))
1744 (path (getenv "PYTHONPATH")))
1745 (wrap-program (string-append out "/bin/couger")
1746 `("PYTHONPATH" ":" prefix (,path))))
1749 `(("python" ,python-2)
1750 ("python2-pillow" ,python2-pillow)
1751 ("python2-numpy" ,python2-numpy)
1752 ("python2-scipy" ,python2-scipy)
1753 ("python2-matplotlib" ,python2-matplotlib)))
1755 `(("r-minimal" ,r-minimal)
1757 ("randomjungle" ,randomjungle)))
1759 `(("unzip" ,unzip)))
1760 (home-page "http://couger.oit.duke.edu")
1761 (synopsis "Identify co-factors in sets of genomic regions")
1763 "COUGER can be applied to any two sets of genomic regions bound by
1764 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1765 putative co-factors that provide specificity to each TF. The framework
1766 determines the genomic targets uniquely-bound by each TF, and identifies a
1767 small set of co-factors that best explain the in vivo binding differences
1768 between the two TFs.
1770 COUGER uses classification algorithms (support vector machines and random
1771 forests) with features that reflect the DNA binding specificities of putative
1772 co-factors. The features are generated either from high-throughput TF-DNA
1773 binding data (from protein binding microarray experiments), or from large
1774 collections of DNA motifs.")
1775 (license license:gpl3+)))
1777 (define-public clustal-omega
1779 (name "clustal-omega")
1783 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1787 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1788 (build-system gnu-build-system)
1790 `(("argtable" ,argtable)))
1791 (home-page "http://www.clustal.org/omega/")
1792 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1794 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1795 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1796 of handling data-sets of hundreds of thousands of sequences in reasonable
1798 (license license:gpl2+)))
1800 (define-public crossmap
1806 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1810 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1811 ;; This patch has been sent upstream already and is available
1812 ;; for download from Sourceforge, but it has not been merged.
1813 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1814 (modules '((guix build utils)))
1815 ;; remove bundled copy of pysam
1817 '(delete-file-recursively "lib/pysam"))))
1818 (build-system python-build-system)
1820 `(#:python ,python-2
1822 (modify-phases %standard-phases
1823 (add-after 'unpack 'set-env
1824 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1826 `(("python-numpy" ,python2-numpy)
1827 ("python-pysam" ,python2-pysam)
1830 `(("python-cython" ,python2-cython)
1831 ("python-nose" ,python2-nose)))
1832 (home-page "http://crossmap.sourceforge.net/")
1833 (synopsis "Convert genome coordinates between assemblies")
1835 "CrossMap is a program for conversion of genome coordinates or annotation
1836 files between different genome assemblies. It supports most commonly used
1837 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1838 (license license:gpl2+)))
1840 (define-public cutadapt
1847 "https://github.com/marcelm/cutadapt/archive/v"
1849 (file-name (string-append name "-" version ".tar.gz"))
1852 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1853 (build-system python-build-system)
1856 (modify-phases %standard-phases
1857 ;; The tests must be run after installation.
1859 (add-after 'install 'check
1860 (lambda* (#:key inputs outputs #:allow-other-keys)
1861 (setenv "PYTHONPATH"
1863 (getenv "PYTHONPATH")
1864 ":" (assoc-ref outputs "out")
1866 (string-take (string-take-right
1867 (assoc-ref inputs "python") 5) 3)
1869 (zero? (system* "nosetests" "-P" "tests")))))))
1871 `(("python-xopen" ,python-xopen)))
1873 `(("python-cython" ,python-cython)
1874 ("python-nose" ,python-nose)))
1875 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1876 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1878 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1879 other types of unwanted sequence from high-throughput sequencing reads.")
1880 (license license:expat)))
1882 (define-public libbigwig
1888 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1889 "archive/" version ".tar.gz"))
1890 (file-name (string-append name "-" version ".tar.gz"))
1893 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1894 (build-system gnu-build-system)
1896 `(#:test-target "test"
1899 (string-append "prefix=" (assoc-ref %outputs "out")))
1901 (modify-phases %standard-phases
1903 (add-before 'check 'disable-curl-test
1905 (substitute* "Makefile"
1906 (("./test/testRemote.*") ""))
1908 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1909 ;; there has not yet been a release containing this change.
1910 (add-before 'install 'create-target-dirs
1911 (lambda* (#:key outputs #:allow-other-keys)
1912 (let ((out (assoc-ref outputs "out")))
1913 (mkdir-p (string-append out "/lib"))
1914 (mkdir-p (string-append out "/include"))
1920 `(("doxygen" ,doxygen)))
1921 (home-page "https://github.com/dpryan79/libBigWig")
1922 (synopsis "C library for handling bigWig files")
1924 "This package provides a C library for parsing local and remote BigWig
1926 (license license:expat)))
1928 (define-public python-pybigwig
1930 (name "python-pybigwig")
1934 (uri (pypi-uri "pyBigWig" version))
1937 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1938 (modules '((guix build utils)))
1941 ;; Delete bundled libBigWig sources
1942 (delete-file-recursively "libBigWig")))))
1943 (build-system python-build-system)
1946 (modify-phases %standard-phases
1947 (add-after 'unpack 'link-with-libBigWig
1948 (lambda* (#:key inputs #:allow-other-keys)
1949 (substitute* "setup.py"
1950 (("libs=\\[") "libs=[\"BigWig\", "))
1953 `(("libbigwig" ,libbigwig)
1956 (home-page "https://github.com/dpryan79/pyBigWig")
1957 (synopsis "Access bigWig files in Python using libBigWig")
1959 "This package provides Python bindings to the libBigWig library for
1960 accessing bigWig files.")
1961 (license license:expat)))
1963 (define-public python2-pybigwig
1964 (package-with-python2 python-pybigwig))
1966 (define-public python-dendropy
1968 (name "python-dendropy")
1973 (uri (pypi-uri "DendroPy" version))
1976 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1977 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1978 (build-system python-build-system)
1979 (home-page "http://packages.python.org/DendroPy/")
1980 (synopsis "Library for phylogenetics and phylogenetic computing")
1982 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1983 writing, simulation, processing and manipulation of phylogenetic
1984 trees (phylogenies) and characters.")
1985 (license license:bsd-3)
1986 (properties `((python2-variant . ,(delay python2-dendropy))))))
1988 (define-public python2-dendropy
1989 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1993 `(#:python ,python-2
1995 (modify-phases %standard-phases
1997 ;; There is currently a test failure that only happens on some
1998 ;; systems, and only using "setup.py test"
1999 (lambda _ (zero? (system* "nosetests")))))))
2000 (native-inputs `(("python2-nose" ,python2-nose)
2001 ,@(package-native-inputs base))))))
2003 (define-public python-py2bit
2005 (name "python-py2bit")
2010 (uri (pypi-uri "py2bit" version))
2013 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2014 (build-system python-build-system)
2015 (home-page "https://github.com/dpryan79/py2bit")
2016 (synopsis "Access 2bit files using lib2bit")
2018 "This package provides Python bindings for lib2bit to access 2bit files
2020 (license license:expat)))
2022 (define-public deeptools
2028 (uri (string-append "https://github.com/fidelram/deepTools/"
2029 "archive/" version ".tar.gz"))
2030 (file-name (string-append name "-" version ".tar.gz"))
2033 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2034 (build-system python-build-system)
2036 `(("python-scipy" ,python-scipy)
2037 ("python-numpy" ,python-numpy)
2038 ("python-numpydoc" ,python-numpydoc)
2039 ("python-matplotlib" ,python-matplotlib)
2040 ("python-pysam" ,python-pysam)
2041 ("python-py2bit" ,python-py2bit)
2042 ("python-pybigwig" ,python-pybigwig)))
2044 `(("python-mock" ,python-mock) ;for tests
2045 ("python-nose" ,python-nose) ;for tests
2046 ("python-pytz" ,python-pytz))) ;for tests
2047 (home-page "https://github.com/fidelram/deepTools")
2048 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2050 "DeepTools addresses the challenge of handling the large amounts of data
2051 that are now routinely generated from DNA sequencing centers. To do so,
2052 deepTools contains useful modules to process the mapped reads data to create
2053 coverage files in standard bedGraph and bigWig file formats. By doing so,
2054 deepTools allows the creation of normalized coverage files or the comparison
2055 between two files (for example, treatment and control). Finally, using such
2056 normalized and standardized files, multiple visualizations can be created to
2057 identify enrichments with functional annotations of the genome.")
2058 (license license:gpl3+)))
2060 (define-public diamond
2067 "https://github.com/bbuchfink/diamond/archive/v"
2069 (file-name (string-append name "-" version ".tar.gz"))
2072 "1zrnr59pqdg56wxfdx3xg4h4d8fa14cxq5kfmc3q88hxrj42rqgs"))))
2073 (build-system cmake-build-system)
2075 '(#:tests? #f ; no "check" target
2077 (modify-phases %standard-phases
2078 (add-after 'unpack 'remove-native-compilation
2080 (substitute* "CMakeLists.txt" (("-march=native") ""))
2084 (home-page "https://github.com/bbuchfink/diamond")
2085 (synopsis "Accelerated BLAST compatible local sequence aligner")
2087 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2088 translated DNA query sequences against a protein reference database (BLASTP
2089 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2090 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2091 data and settings.")
2092 (license license:agpl3+)))
2094 (define-public discrover
2101 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2103 (file-name (string-append name "-" version ".tar.gz"))
2106 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2107 (build-system cmake-build-system)
2109 `(#:tests? #f ; there are no tests
2111 (modify-phases %standard-phases
2112 (add-after 'unpack 'add-missing-includes
2114 (substitute* "src/executioninformation.hpp"
2115 (("#define EXECUTIONINFORMATION_HPP" line)
2116 (string-append line "\n#include <random>")))
2117 (substitute* "src/plasma/fasta.hpp"
2118 (("#define FASTA_HPP" line)
2119 (string-append line "\n#include <random>")))
2125 `(("texlive" ,texlive)
2126 ("imagemagick" ,imagemagick)))
2127 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2128 (synopsis "Discover discriminative nucleotide sequence motifs")
2129 (description "Discrover is a motif discovery method to find binding sites
2130 of nucleic acid binding proteins.")
2131 (license license:gpl3+)))
2133 (define-public eigensoft
2134 (let ((revision "1")
2135 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2138 (version (string-append "6.1.2-"
2140 (string-take commit 9)))
2145 (url "https://github.com/DReichLab/EIG.git")
2147 (file-name (string-append "eigensoft-" commit "-checkout"))
2150 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2151 (modules '((guix build utils)))
2152 ;; Remove pre-built binaries.
2154 (delete-file-recursively "bin")
2157 (build-system gnu-build-system)
2159 `(#:tests? #f ; There are no tests.
2160 #:make-flags '("CC=gcc")
2162 (modify-phases %standard-phases
2163 ;; There is no configure phase, but the Makefile is in a
2168 ;; The link flags are incomplete.
2169 (substitute* "Makefile"
2170 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2172 ;; The provided install target only copies executables to
2173 ;; the "bin" directory in the build root.
2174 (add-after 'install 'actually-install
2175 (lambda* (#:key outputs #:allow-other-keys)
2176 (let* ((out (assoc-ref outputs "out"))
2177 (bin (string-append out "/bin")))
2178 (for-each (lambda (file)
2179 (install-file file bin))
2180 (find-files "../bin" ".*"))
2185 ("openblas" ,openblas)
2187 ("gfortran" ,gfortran "lib")))
2188 (home-page "https://github.com/DReichLab/EIG")
2189 (synopsis "Tools for population genetics")
2190 (description "The EIGENSOFT package provides tools for population
2191 genetics and stratification correction. EIGENSOFT implements methods commonly
2192 used in population genetics analyses such as PCA, computation of Tracy-Widom
2193 statistics, and finding related individuals in structured populations. It
2194 comes with a built-in plotting script and supports multiple file formats and
2195 quantitative phenotypes.")
2196 ;; The license of the eigensoft tools is Expat, but since it's
2197 ;; linking with the GNU Scientific Library (GSL) the effective
2198 ;; license is the GPL.
2199 (license license:gpl3+))))
2201 (define-public edirect
2207 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2208 "versions/2016-05-03/edirect.tar.gz"))
2211 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2212 (build-system perl-build-system)
2214 `(#:tests? #f ;no "check" target
2216 (modify-phases %standard-phases
2220 (lambda* (#:key outputs #:allow-other-keys)
2221 (let ((target (string-append (assoc-ref outputs "out")
2224 (install-file "edirect.pl" target)
2227 'install 'wrap-program
2228 (lambda* (#:key inputs outputs #:allow-other-keys)
2229 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2230 (let* ((out (assoc-ref outputs "out"))
2231 (path (getenv "PERL5LIB")))
2232 (wrap-program (string-append out "/bin/edirect.pl")
2233 `("PERL5LIB" ":" prefix (,path)))))))))
2235 `(("perl-html-parser" ,perl-html-parser)
2236 ("perl-encode-locale" ,perl-encode-locale)
2237 ("perl-file-listing" ,perl-file-listing)
2238 ("perl-html-tagset" ,perl-html-tagset)
2239 ("perl-html-tree" ,perl-html-tree)
2240 ("perl-http-cookies" ,perl-http-cookies)
2241 ("perl-http-date" ,perl-http-date)
2242 ("perl-http-message" ,perl-http-message)
2243 ("perl-http-negotiate" ,perl-http-negotiate)
2244 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2245 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2246 ("perl-net-http" ,perl-net-http)
2247 ("perl-uri" ,perl-uri)
2248 ("perl-www-robotrules" ,perl-www-robotrules)
2250 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2251 (synopsis "Tools for accessing the NCBI's set of databases")
2253 "Entrez Direct (EDirect) is a method for accessing the National Center
2254 for Biotechnology Information's (NCBI) set of interconnected
2255 databases (publication, sequence, structure, gene, variation, expression,
2256 etc.) from a terminal. Functions take search terms from command-line
2257 arguments. Individual operations are combined to build multi-step queries.
2258 Record retrieval and formatting normally complete the process.
2260 EDirect also provides an argument-driven function that simplifies the
2261 extraction of data from document summaries or other results that are returned
2262 in structured XML format. This can eliminate the need for writing custom
2263 software to answer ad hoc questions.")
2264 (license license:public-domain)))
2266 (define-public exonerate
2275 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2276 "exonerate-" version ".tar.gz"))
2279 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2280 (build-system gnu-build-system)
2282 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2284 `(("pkg-config" ,pkg-config)))
2288 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2289 (synopsis "Generic tool for biological sequence alignment")
2291 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2292 the alignment of sequences using a many alignment models, either exhaustive
2293 dynamic programming or a variety of heuristics.")
2294 (license license:gpl3)))
2296 (define-public express
2304 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2305 version "/express-" version "-src.tgz"))
2308 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2309 (build-system cmake-build-system)
2311 `(#:tests? #f ;no "check" target
2313 (modify-phases %standard-phases
2314 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2315 (lambda* (#:key inputs #:allow-other-keys)
2316 (substitute* "CMakeLists.txt"
2317 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2318 "set(Boost_USE_STATIC_LIBS OFF)")
2319 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2320 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2321 (substitute* "src/CMakeLists.txt"
2322 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2323 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2327 ("bamtools" ,bamtools)
2328 ("protobuf" ,protobuf)
2330 (home-page "http://bio.math.berkeley.edu/eXpress")
2331 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2333 "eXpress is a streaming tool for quantifying the abundances of a set of
2334 target sequences from sampled subsequences. Example applications include
2335 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2336 analysis (from RNA-Seq), transcription factor binding quantification in
2337 ChIP-Seq, and analysis of metagenomic data.")
2338 (license license:artistic2.0)))
2340 (define-public express-beta-diversity
2342 (name "express-beta-diversity")
2348 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2350 (file-name (string-append name "-" version ".tar.gz"))
2353 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2354 (build-system gnu-build-system)
2357 (modify-phases %standard-phases
2359 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2361 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2363 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2365 (lambda* (#:key outputs #:allow-other-keys)
2366 (let ((bin (string-append (assoc-ref outputs "out")
2369 (install-file "scripts/convertToEBD.py" bin)
2370 (install-file "bin/ExpressBetaDiversity" bin)
2373 `(("python" ,python-2)))
2374 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2375 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2377 "Express Beta Diversity (EBD) calculates ecological beta diversity
2378 (dissimilarity) measures between biological communities. EBD implements a
2379 variety of diversity measures including those that make use of phylogenetic
2380 similarity of community members.")
2381 (license license:gpl3+)))
2383 (define-public fasttree
2390 "http://www.microbesonline.org/fasttree/FastTree-"
2394 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2395 (build-system gnu-build-system)
2397 `(#:tests? #f ; no "check" target
2399 (modify-phases %standard-phases
2403 (lambda* (#:key source #:allow-other-keys)
2404 (and (zero? (system* "gcc"
2406 "-finline-functions"
2413 (zero? (system* "gcc"
2417 "-finline-functions"
2425 (lambda* (#:key outputs #:allow-other-keys)
2426 (let ((bin (string-append (assoc-ref outputs "out")
2429 (install-file "FastTree" bin)
2430 (install-file "FastTreeMP" bin)
2432 (home-page "http://www.microbesonline.org/fasttree")
2433 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2435 "FastTree can handle alignments with up to a million of sequences in a
2436 reasonable amount of time and memory. For large alignments, FastTree is
2437 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2438 (license license:gpl2+)))
2440 (define-public fastx-toolkit
2442 (name "fastx-toolkit")
2448 "https://github.com/agordon/fastx_toolkit/releases/download/"
2449 version "/fastx_toolkit-" version ".tar.bz2"))
2452 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2453 (build-system gnu-build-system)
2455 `(("libgtextutils" ,libgtextutils)))
2457 `(("pkg-config" ,pkg-config)))
2458 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2459 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2461 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2462 FASTA/FASTQ files preprocessing.
2464 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2465 containing multiple short-reads sequences. The main processing of such
2466 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2467 is sometimes more productive to preprocess the files before mapping the
2468 sequences to the genome---manipulating the sequences to produce better mapping
2469 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2470 (license license:agpl3+)))
2472 (define-public flexbar
2479 (string-append "mirror://sourceforge/flexbar/"
2480 version "/flexbar_v" version "_src.tgz"))
2483 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2484 (build-system cmake-build-system)
2486 `(#:configure-flags (list
2487 (string-append "-DFLEXBAR_BINARY_DIR="
2488 (assoc-ref %outputs "out")
2491 (modify-phases %standard-phases
2493 (lambda* (#:key outputs #:allow-other-keys)
2494 (setenv "PATH" (string-append
2495 (assoc-ref outputs "out") "/bin:"
2497 (chdir "../flexbar_v2.5_src/test")
2498 (zero? (system* "bash" "flexbar_validate.sh"))))
2499 (delete 'install))))
2504 `(("pkg-config" ,pkg-config)
2506 (home-page "http://flexbar.sourceforge.net")
2507 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2509 "Flexbar preprocesses high-throughput nucleotide sequencing data
2510 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2511 Moreover, trimming and filtering features are provided. Flexbar increases
2512 read mapping rates and improves genome and transcriptome assemblies. It
2513 supports next-generation sequencing data in fasta/q and csfasta/q format from
2514 Illumina, Roche 454, and the SOLiD platform.")
2515 (license license:gpl3)))
2517 (define-public fraggenescan
2519 (name "fraggenescan")
2525 (string-append "mirror://sourceforge/fraggenescan/"
2526 "FragGeneScan" version ".tar.gz"))
2528 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2529 (build-system gnu-build-system)
2532 (modify-phases %standard-phases
2534 (add-before 'build 'patch-paths
2535 (lambda* (#:key outputs #:allow-other-keys)
2536 (let* ((out (string-append (assoc-ref outputs "out")))
2537 (share (string-append out "/share/fraggenescan/")))
2538 (substitute* "run_FragGeneScan.pl"
2540 (string-append "system(\"" (which "rm")))
2542 (string-append "system(\"" (which "mv")))
2543 (("\\\"awk") (string-append "\"" (which "awk")))
2544 ;; This script and other programs expect the training files
2545 ;; to be in the non-standard location bin/train/XXX. Change
2546 ;; this to be share/fraggenescan/train/XXX instead.
2547 (("^\\$train.file = \\$dir.*")
2548 (string-append "$train_file = \""
2550 "train/\".$FGS_train_file;")))
2551 (substitute* "run_hmm.c"
2552 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2553 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2556 (lambda _ (and (zero? (system* "make" "clean"))
2557 (zero? (system* "make" "fgs")))))
2559 (lambda* (#:key outputs #:allow-other-keys)
2560 (let* ((out (string-append (assoc-ref outputs "out")))
2561 (bin (string-append out "/bin/"))
2562 (share (string-append out "/share/fraggenescan/train")))
2563 (install-file "run_FragGeneScan.pl" bin)
2564 (install-file "FragGeneScan" bin)
2565 (copy-recursively "train" share))))
2567 (add-after 'install 'post-install-check
2568 ;; In lieu of 'make check', run one of the examples and check the
2569 ;; output files gets created.
2570 (lambda* (#:key outputs #:allow-other-keys)
2571 (let* ((out (string-append (assoc-ref outputs "out")))
2572 (bin (string-append out "/bin/"))
2573 (frag (string-append bin "run_FragGeneScan.pl")))
2574 (and (zero? (system* frag ; Test complete genome.
2575 "-genome=./example/NC_000913.fna"
2579 (file-exists? "test2.faa")
2580 (file-exists? "test2.ffn")
2581 (file-exists? "test2.gff")
2582 (file-exists? "test2.out")
2583 (zero? (system* ; Test incomplete sequences.
2585 "-genome=./example/NC_000913-fgs.ffn"
2588 "-train=454_30")))))))))
2591 ("python" ,python-2))) ;not compatible with python 3.
2592 (home-page "https://sourceforge.net/projects/fraggenescan/")
2593 (synopsis "Finds potentially fragmented genes in short reads")
2595 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2596 short and error-prone DNA sequencing reads. It can also be applied to predict
2597 genes in incomplete assemblies or complete genomes.")
2598 ;; GPL3+ according to private correspondense with the authors.
2599 (license license:gpl3+)))
2601 (define-public fxtract
2602 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2610 "https://github.com/ctSkennerton/fxtract/archive/"
2612 (file-name (string-append "ctstennerton-util-"
2613 (string-take util-commit 7)
2617 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2618 (build-system gnu-build-system)
2620 `(#:make-flags (list
2621 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2623 #:test-target "fxtract_test"
2625 (modify-phases %standard-phases
2627 (add-before 'build 'copy-util
2628 (lambda* (#:key inputs #:allow-other-keys)
2630 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2632 ;; Do not use make install as this requires additional dependencies.
2634 (lambda* (#:key outputs #:allow-other-keys)
2635 (let* ((out (assoc-ref outputs "out"))
2636 (bin (string-append out"/bin")))
2637 (install-file "fxtract" bin)
2643 ;; ctskennerton-util is licensed under GPL2.
2644 `(("ctskennerton-util"
2648 (url "https://github.com/ctSkennerton/util.git")
2649 (commit util-commit)))
2650 (file-name (string-append
2651 "ctstennerton-util-" util-commit "-checkout"))
2654 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2655 (home-page "https://github.com/ctSkennerton/fxtract")
2656 (synopsis "Extract sequences from FASTA and FASTQ files")
2658 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2659 or FASTQ) file given a subsequence. It uses a simple substring search for
2660 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2661 lookups or multi-pattern searching as required. By default fxtract looks in
2662 the sequence of each record but can also be told to look in the header,
2663 comment or quality sections.")
2664 ;; 'util' requires SSE instructions.
2665 (supported-systems '("x86_64-linux"))
2666 (license license:expat))))
2668 (define-public gemma
2674 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2676 (file-name (string-append name "-" version ".tar.gz"))
2679 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2680 (patches (search-patches "gemma-intel-compat.patch"))))
2685 (build-system gnu-build-system)
2688 '(,@(match (%current-system)
2690 '("FORCE_DYNAMIC=1"))
2692 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2694 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2696 (modify-phases %standard-phases
2698 (add-before 'build 'bin-mkdir
2703 (lambda* (#:key outputs #:allow-other-keys)
2704 (let ((out (assoc-ref outputs "out")))
2705 (install-file "bin/gemma"
2709 #:tests? #f)) ; no tests included yet
2710 (home-page "https://github.com/xiangzhou/GEMMA")
2711 (synopsis "Tool for genome-wide efficient mixed model association")
2713 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2714 standard linear mixed model resolver with application in genome-wide
2715 association studies (GWAS).")
2716 (license license:gpl3)))
2725 "https://github.com/nboley/grit/archive/"
2727 (file-name (string-append name "-" version ".tar.gz"))
2730 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2731 (build-system python-build-system)
2733 `(#:python ,python-2
2735 (modify-phases %standard-phases
2736 (add-after 'unpack 'generate-from-cython-sources
2737 (lambda* (#:key inputs outputs #:allow-other-keys)
2738 ;; Delete these C files to force fresh generation from pyx sources.
2739 (delete-file "grit/sparsify_support_fns.c")
2740 (delete-file "grit/call_peaks_support_fns.c")
2741 (substitute* "setup.py"
2742 (("Cython.Setup") "Cython.Build")
2743 ;; Add numpy include path to fix compilation
2745 (string-append "pyx\", ], include_dirs = ['"
2746 (assoc-ref inputs "python-numpy")
2747 "/lib/python2.7/site-packages/numpy/core/include/"
2751 `(("python-scipy" ,python2-scipy)
2752 ("python-numpy" ,python2-numpy)
2753 ("python-pysam" ,python2-pysam)
2754 ("python-networkx" ,python2-networkx)))
2756 `(("python-cython" ,python2-cython)))
2757 (home-page "http://grit-bio.org")
2758 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2760 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2761 full length transcript models. When none of these data sources are available,
2762 GRIT can be run by providing a candidate set of TES or TSS sites. In
2763 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2764 also be run in quantification mode, where it uses a provided GTF file and just
2765 estimates transcript expression.")
2766 (license license:gpl3+)))
2768 (define-public hisat
2775 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2776 version "-beta-source.zip"))
2779 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2780 (build-system gnu-build-system)
2782 `(#:tests? #f ;no check target
2783 #:make-flags '("allall"
2784 ;; Disable unsupported `popcnt' instructions on
2785 ;; architectures other than x86_64
2786 ,@(if (string-prefix? "x86_64"
2787 (or (%current-target-system)
2790 '("POPCNT_CAPABILITY=0")))
2792 (modify-phases %standard-phases
2793 (add-after 'unpack 'patch-sources
2795 ;; XXX Cannot use snippet because zip files are not supported
2796 (substitute* "Makefile"
2797 (("^CC = .*$") "CC = gcc")
2798 (("^CPP = .*$") "CPP = g++")
2799 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2800 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2801 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2802 (substitute* '("hisat-build" "hisat-inspect")
2803 (("/usr/bin/env") (which "env")))
2806 (lambda* (#:key outputs #:allow-other-keys)
2807 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2808 (for-each (lambda (file)
2809 (install-file file bin))
2812 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2814 (delete 'configure))))
2816 `(("unzip" ,unzip)))
2821 ;; Non-portable SSE instructions are used so building fails on platforms
2822 ;; other than x86_64.
2823 (supported-systems '("x86_64-linux"))
2824 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2825 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2827 "HISAT is a fast and sensitive spliced alignment program for mapping
2828 RNA-seq reads. In addition to one global FM index that represents a whole
2829 genome, HISAT uses a large set of small FM indexes that collectively cover the
2830 whole genome. These small indexes (called local indexes) combined with
2831 several alignment strategies enable effective alignment of RNA-seq reads, in
2832 particular, reads spanning multiple exons.")
2833 (license license:gpl3+)))
2835 (define-public hisat2
2842 ;; FIXME: a better source URL is
2843 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2844 ;; "/downloads/hisat2-" version "-source.zip")
2845 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2846 ;; but it is currently unavailable.
2847 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2848 (file-name (string-append name "-" version ".tar.gz"))
2851 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2852 (build-system gnu-build-system)
2854 `(#:tests? #f ; no check target
2855 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2856 #:modules ((guix build gnu-build-system)
2860 (modify-phases %standard-phases
2861 (add-after 'unpack 'make-deterministic
2863 (substitute* "Makefile"
2868 (lambda* (#:key outputs #:allow-other-keys)
2869 (let* ((out (assoc-ref outputs "out"))
2870 (bin (string-append out "/bin/"))
2871 (doc (string-append out "/share/doc/hisat2/")))
2873 (cut install-file <> bin)
2875 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2877 (install-file "doc/manual.inc.html" doc))
2880 `(("unzip" ,unzip) ; needed for archive from ftp
2882 ("pandoc" ,ghc-pandoc))) ; for documentation
2883 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2884 (synopsis "Graph-based alignment of genomic sequencing reads")
2885 (description "HISAT2 is a fast and sensitive alignment program for mapping
2886 next-generation sequencing reads (both DNA and RNA) to a population of human
2887 genomes (as well as to a single reference genome). In addition to using one
2888 global @dfn{graph FM} (GFM) index that represents a population of human
2889 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2890 the whole genome. These small indexes, combined with several alignment
2891 strategies, enable rapid and accurate alignment of sequencing reads. This new
2892 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2893 ;; HISAT2 contains files from Bowtie2, which is released under
2894 ;; GPLv2 or later. The HISAT2 source files are released under
2896 (license license:gpl3+)))
2898 (define-public hmmer
2906 "http://eddylab.org/software/hmmer"
2907 (version-prefix version 1) "/"
2908 version "/hmmer-" version ".tar.gz"))
2911 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2912 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2913 (build-system gnu-build-system)
2914 (native-inputs `(("perl" ,perl)))
2915 (home-page "http://hmmer.org/")
2916 (synopsis "Biosequence analysis using profile hidden Markov models")
2918 "HMMER is used for searching sequence databases for homologs of protein
2919 sequences, and for making protein sequence alignments. It implements methods
2920 using probabilistic models called profile hidden Markov models (profile
2922 (license (list license:gpl3+
2923 ;; The bundled library 'easel' is distributed
2924 ;; under The Janelia Farm Software License.
2925 (license:non-copyleft
2926 "file://easel/LICENSE"
2927 "See easel/LICENSE in the distribution.")))))
2929 (define-public htseq
2935 (uri (pypi-uri "HTSeq" version))
2938 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2939 (build-system python-build-system)
2941 `(("python-cython" ,python-cython)))
2942 ;; Numpy needs to be propagated when htseq is used as a Python library.
2944 `(("python-numpy" ,python-numpy)))
2946 `(("python-pysam" ,python-pysam)
2947 ("python-matplotlib" ,python-matplotlib)))
2948 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2949 (synopsis "Analysing high-throughput sequencing data with Python")
2951 "HTSeq is a Python package that provides infrastructure to process data
2952 from high-throughput sequencing assays.")
2953 (license license:gpl3+)))
2955 (define-public python2-htseq
2956 (package-with-python2 htseq))
2958 (define-public java-htsjdk
2960 (name "java-htsjdk")
2965 "https://github.com/samtools/htsjdk/archive/"
2967 (file-name (string-append name "-" version ".tar.gz"))
2970 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2971 (modules '((guix build utils)))
2972 ;; remove build dependency on git
2973 (snippet '(substitute* "build.xml"
2974 (("failifexecutionfails=\"true\"")
2975 "failifexecutionfails=\"false\"")))))
2976 (build-system ant-build-system)
2978 `(#:tests? #f ; test require Internet access
2980 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2981 "/share/java/htsjdk/"))
2982 #:build-target "all"
2984 (modify-phases %standard-phases
2985 ;; The build phase also installs the jars
2986 (delete 'install))))
2987 (home-page "http://samtools.github.io/htsjdk/")
2988 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2990 "HTSJDK is an implementation of a unified Java library for accessing
2991 common file formats, such as SAM and VCF, used for high-throughput
2992 sequencing (HTS) data. There are also an number of useful utilities for
2993 manipulating HTS data.")
2994 (license license:expat)))
2996 (define-public htslib
3003 "https://github.com/samtools/htslib/releases/download/"
3004 version "/htslib-" version ".tar.bz2"))
3007 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3008 (build-system gnu-build-system)
3011 (modify-phases %standard-phases
3013 'unpack 'patch-tests
3015 (substitute* "test/test.pl"
3016 (("/bin/bash") (which "bash")))
3019 `(("openssl" ,openssl)
3024 (home-page "http://www.htslib.org")
3025 (synopsis "C library for reading/writing high-throughput sequencing data")
3027 "HTSlib is a C library for reading/writing high-throughput sequencing
3028 data. It also provides the bgzip, htsfile, and tabix utilities.")
3029 ;; Files under cram/ are released under the modified BSD license;
3030 ;; the rest is released under the Expat license
3031 (license (list license:expat license:bsd-3))))
3033 ;; This package should be removed once no packages rely upon it.
3041 "https://github.com/samtools/htslib/releases/download/"
3042 version "/htslib-" version ".tar.bz2"))
3045 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3054 "https://github.com/nboley/idr/archive/"
3056 (file-name (string-append name "-" version ".tar.gz"))
3059 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3060 (build-system python-build-system)
3062 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3064 `(("python-scipy" ,python-scipy)
3065 ("python-sympy" ,python-sympy)
3066 ("python-numpy" ,python-numpy)
3067 ("python-matplotlib" ,python-matplotlib)))
3069 `(("python-cython" ,python-cython)))
3070 (home-page "https://github.com/nboley/idr")
3071 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3073 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3074 to measure the reproducibility of findings identified from replicate
3075 experiments and provide highly stable thresholds based on reproducibility.")
3076 (license license:gpl3+)))
3078 (define-public jellyfish
3084 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3085 "releases/download/v" version
3086 "/jellyfish-" version ".tar.gz"))
3089 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3090 (build-system gnu-build-system)
3091 (outputs '("out" ;for library
3092 "ruby" ;for Ruby bindings
3093 "python")) ;for Python bindings
3096 (list (string-append "--enable-ruby-binding="
3097 (assoc-ref %outputs "ruby"))
3098 (string-append "--enable-python-binding="
3099 (assoc-ref %outputs "python")))
3101 (modify-phases %standard-phases
3102 (add-before 'check 'set-SHELL-variable
3104 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3106 (setenv "SHELL" (which "bash"))
3112 ("python" ,python-2)))
3113 (synopsis "Tool for fast counting of k-mers in DNA")
3115 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3116 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3117 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3118 is a command-line program that reads FASTA and multi-FASTA files containing
3119 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3120 translated into a human-readable text format using the @code{jellyfish dump}
3121 command, or queried for specific k-mers with @code{jellyfish query}.")
3122 (home-page "http://www.genome.umd.edu/jellyfish.html")
3123 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3124 (supported-systems '("x86_64-linux"))
3125 ;; The combined work is published under the GPLv3 or later. Individual
3126 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3127 (license (list license:gpl3+ license:expat))))
3129 (define-public khmer
3136 (uri (pypi-uri "khmer" version))
3139 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3140 (patches (search-patches "khmer-use-libraries.patch"))))
3141 (build-system python-build-system)
3144 (modify-phases %standard-phases
3145 (add-after 'unpack 'set-paths
3146 (lambda* (#:key inputs outputs #:allow-other-keys)
3147 ;; Delete bundled libraries.
3148 (delete-file-recursively "third-party/zlib")
3149 (delete-file-recursively "third-party/bzip2")
3150 ;; Replace bundled seqan.
3151 (let* ((seqan-all "third-party/seqan")
3152 (seqan-include (string-append
3153 seqan-all "/core/include")))
3154 (delete-file-recursively seqan-all)
3155 (copy-recursively (string-append (assoc-ref inputs "seqan")
3157 (string-append seqan-include "/seqan")))
3158 ;; We do not replace the bundled MurmurHash as the canonical
3159 ;; repository for this code 'SMHasher' is unsuitable for
3160 ;; providing a library. See
3161 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3163 (add-after 'unpack 'set-cc
3167 ;; It is simpler to test after installation.
3169 (add-after 'install 'post-install-check
3170 (lambda* (#:key inputs outputs #:allow-other-keys)
3171 (let ((out (assoc-ref outputs "out")))
3176 (assoc-ref outputs "out")
3178 (setenv "PYTHONPATH"
3180 (getenv "PYTHONPATH")
3184 (string-take (string-take-right
3185 (assoc-ref inputs "python") 5) 3)
3187 (with-directory-excursion "build"
3188 (zero? (system* "nosetests" "khmer" "--attr"
3189 "!known_failing")))))))))
3192 ("python-nose" ,python-nose)))
3196 ("python-screed" ,python-screed)
3197 ("python-bz2file" ,python-bz2file)
3198 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3199 ;; until the next version of khmer (likely 2.1) is released.
3201 (home-page "https://khmer.readthedocs.org/")
3202 (synopsis "K-mer counting, filtering and graph traversal library")
3203 (description "The khmer software is a set of command-line tools for
3204 working with DNA shotgun sequencing data from genomes, transcriptomes,
3205 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3206 sometimes better. Khmer can also identify and fix problems with shotgun
3208 ;; When building on i686, armhf and mips64el, we get the following error:
3209 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3210 (supported-systems '("x86_64-linux"))
3211 (license license:bsd-3)))
3213 (define-public kaiju
3220 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3222 (file-name (string-append name "-" version ".tar.gz"))
3225 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3226 (build-system gnu-build-system)
3228 `(#:tests? #f ; There are no tests.
3230 (modify-phases %standard-phases
3232 (add-before 'build 'move-to-src-dir
3233 (lambda _ (chdir "src") #t))
3235 (lambda* (#:key inputs outputs #:allow-other-keys)
3236 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3239 (copy-recursively "bin" bin)
3240 (copy-recursively "util" bin))
3244 (home-page "http://kaiju.binf.ku.dk/")
3245 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3246 (description "Kaiju is a program for sensitive taxonomic classification
3247 of high-throughput sequencing reads from metagenomic whole genome sequencing
3249 (license license:gpl3+)))
3254 (version "2.1.0.20151222")
3257 (uri (pypi-uri "MACS2" version))
3260 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3261 (build-system python-build-system)
3263 `(#:python ,python-2 ; only compatible with Python 2.7
3264 #:tests? #f)) ; no test target
3266 `(("python-numpy" ,python2-numpy)))
3267 (home-page "https://github.com/taoliu/MACS/")
3268 (synopsis "Model based analysis for ChIP-Seq data")
3270 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3271 identifying transcript factor binding sites named Model-based Analysis of
3272 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3273 the significance of enriched ChIP regions and it improves the spatial
3274 resolution of binding sites through combining the information of both
3275 sequencing tag position and orientation.")
3276 (license license:bsd-3)))
3278 (define-public mafft
3285 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3286 "-without-extensions-src.tgz"))
3287 (file-name (string-append name "-" version ".tgz"))
3290 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3291 (build-system gnu-build-system)
3293 `(#:tests? #f ; no automated tests, though there are tests in the read me
3294 #:make-flags (let ((out (assoc-ref %outputs "out")))
3295 (list (string-append "PREFIX=" out)
3296 (string-append "BINDIR="
3297 (string-append out "/bin"))))
3299 (modify-phases %standard-phases
3300 (add-after 'unpack 'enter-dir
3301 (lambda _ (chdir "core") #t))
3302 (add-after 'enter-dir 'patch-makefile
3304 ;; on advice from the MAFFT authors, there is no need to
3305 ;; distribute mafft-profile, mafft-distance, or
3306 ;; mafft-homologs.rb as they are too "specialised".
3307 (substitute* "Makefile"
3308 ;; remove mafft-homologs.rb from SCRIPTS
3309 (("^SCRIPTS = mafft mafft-homologs.rb")
3311 ;; remove mafft-homologs from MANPAGES
3312 (("^MANPAGES = mafft.1 mafft-homologs.1")
3313 "MANPAGES = mafft.1")
3314 ;; remove mafft-distance from PROGS
3315 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3316 "PROGS = dvtditr dndfast7 dndblast sextet5")
3317 ;; remove mafft-profile from PROGS
3318 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3319 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3320 (("^rm -f mafft-profile mafft-profile.exe") "#")
3321 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3322 ;; do not install MAN pages in libexec folder
3323 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3324 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3326 (add-after 'enter-dir 'patch-paths
3327 (lambda* (#:key inputs #:allow-other-keys)
3328 (substitute* '("pairash.c"
3330 (("perl") (which "perl"))
3331 (("([\"`| ])awk" _ prefix)
3332 (string-append prefix (which "awk")))
3333 (("grep") (which "grep")))
3336 (add-after 'install 'wrap-programs
3337 (lambda* (#:key outputs #:allow-other-keys)
3338 (let* ((out (assoc-ref outputs "out"))
3339 (bin (string-append out "/bin"))
3340 (path (string-append
3341 (assoc-ref %build-inputs "coreutils") "/bin:")))
3342 (for-each (lambda (file)
3344 `("PATH" ":" prefix (,path))))
3352 ("coreutils" ,coreutils)))
3353 (home-page "http://mafft.cbrc.jp/alignment/software/")
3354 (synopsis "Multiple sequence alignment program")
3356 "MAFFT offers a range of multiple alignment methods for nucleotide and
3357 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3358 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3360 (license (license:non-copyleft
3361 "http://mafft.cbrc.jp/alignment/software/license.txt"
3362 "BSD-3 with different formatting"))))
3371 "https://github.com/marbl/mash/archive/v"
3373 (file-name (string-append name "-" version ".tar.gz"))
3376 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3377 (modules '((guix build utils)))
3379 ;; Delete bundled kseq.
3380 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3381 '(delete-file "src/mash/kseq.h"))))
3382 (build-system gnu-build-system)
3384 `(#:tests? #f ; No tests.
3387 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3388 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3389 #:make-flags (list "CC=gcc")
3391 (modify-phases %standard-phases
3392 (add-after 'unpack 'fix-includes
3394 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3395 (("^#include \"kseq\\.h\"")
3396 "#include \"htslib/kseq.h\""))
3398 (add-after 'fix-includes 'autoconf
3399 (lambda _ (zero? (system* "autoconf")))))))
3401 `(("autoconf" ,autoconf)
3402 ;; Capnproto and htslib are statically embedded in the final
3403 ;; application. Therefore we also list their licenses, below.
3404 ("capnproto" ,capnproto)
3405 ("htslib" ,htslib)))
3409 (supported-systems '("x86_64-linux"))
3410 (home-page "https://mash.readthedocs.io")
3411 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3412 (description "Mash is a fast sequence distance estimator that uses the
3413 MinHash algorithm and is designed to work with genomes and metagenomes in the
3414 form of assemblies or reads.")
3415 (license (list license:bsd-3 ; Mash
3416 license:expat ; HTSlib and capnproto
3417 license:public-domain ; MurmurHash 3
3418 license:cpl1.0)))) ; Open Bloom Filter
3420 (define-public metabat
3427 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3429 (file-name (string-append name "-" version ".tar.gz"))
3432 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3433 (patches (search-patches "metabat-fix-compilation.patch"))))
3434 (build-system gnu-build-system)
3437 (modify-phases %standard-phases
3438 (add-after 'unpack 'fix-includes
3440 (substitute* "src/BamUtils.h"
3441 (("^#include \"bam/bam\\.h\"")
3442 "#include \"samtools/bam.h\"")
3443 (("^#include \"bam/sam\\.h\"")
3444 "#include \"samtools/sam.h\""))
3445 (substitute* "src/KseqReader.h"
3446 (("^#include \"bam/kseq\\.h\"")
3447 "#include \"htslib/kseq.h\""))
3449 (add-after 'unpack 'fix-scons
3450 (lambda* (#:key inputs #:allow-other-keys)
3451 (substitute* "SConstruct"
3452 (("^htslib_dir += 'samtools'")
3453 (string-append "htslib_dir = '"
3454 (assoc-ref inputs "htslib")
3456 (("^samtools_dir = 'samtools'")
3457 (string-append "samtools_dir = '"
3458 (assoc-ref inputs "samtools")
3460 (("^findStaticOrShared\\('bam', hts_lib")
3461 (string-append "findStaticOrShared('bam', '"
3462 (assoc-ref inputs "samtools")
3464 ;; Do not distribute README.
3465 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3469 (lambda* (#:key inputs outputs #:allow-other-keys)
3470 (mkdir (assoc-ref outputs "out"))
3471 (zero? (system* "scons"
3474 (assoc-ref outputs "out"))
3477 (assoc-ref inputs "boost"))
3479 ;; Check and install are carried out during build phase.
3481 (delete 'install))))
3485 ("samtools" ,samtools)
3489 `(("scons" ,scons)))
3490 (home-page "https://bitbucket.org/berkeleylab/metabat")
3492 "Reconstruction of single genomes from complex microbial communities")
3494 "Grouping large genomic fragments assembled from shotgun metagenomic
3495 sequences to deconvolute complex microbial communities, or metagenome binning,
3496 enables the study of individual organisms and their interactions. MetaBAT is
3497 an automated metagenome binning software, which integrates empirical
3498 probabilistic distances of genome abundance and tetranucleotide frequency.")
3499 ;; The source code contains inline assembly.
3500 (supported-systems '("x86_64-linux" "i686-linux"))
3501 (license (license:non-copyleft "file://license.txt"
3502 "See license.txt in the distribution."))))
3504 (define-public minced
3511 "https://github.com/ctSkennerton/minced/archive/"
3513 (file-name (string-append name "-" version ".tar.gz"))
3516 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3517 (build-system gnu-build-system)
3519 `(#:test-target "test"
3521 (modify-phases %standard-phases
3523 (add-before 'check 'fix-test
3525 ;; Fix test for latest version.
3526 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3527 (("minced:0.1.6") "minced:0.2.0"))
3529 (replace 'install ; No install target.
3530 (lambda* (#:key inputs outputs #:allow-other-keys)
3531 (let* ((out (assoc-ref outputs "out"))
3532 (bin (string-append out "/bin"))
3533 (wrapper (string-append bin "/minced")))
3534 ;; Minced comes with a wrapper script that tries to figure out where
3535 ;; it is located before running the JAR. Since these paths are known
3536 ;; to us, we build our own wrapper to avoid coreutils dependency.
3537 (install-file "minced.jar" bin)
3538 (with-output-to-file wrapper
3542 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3543 (assoc-ref inputs "jre") "/bin/java -jar "
3544 bin "/minced.jar \"$@\"\n"))))
3545 (chmod wrapper #o555)))))))
3547 `(("jdk" ,icedtea "jdk")))
3550 ("jre" ,icedtea "out")))
3551 (home-page "https://github.com/ctSkennerton/minced")
3552 (synopsis "Mining CRISPRs in Environmental Datasets")
3554 "MinCED is a program to find Clustered Regularly Interspaced Short
3555 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3556 unassembled metagenomic reads, but is mainly designed for full genomes and
3557 assembled metagenomic sequence.")
3558 (license license:gpl3+)))
3567 "https://pypi.python.org/packages/source/m/misopy/misopy-"
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 "03dfr2cd5fp80bcr65923zpdzrasvcxl7c2vgh8373v25a1yfap7"))))
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-exception-class" ,perl-exception-class)
4208 ("perl-file-find-rule" ,perl-file-find-rule)
4209 ("perl-file-grep" ,perl-file-grep)
4210 ("perl-file-slurper" ,perl-file-slurper)
4211 ("perl-file-which" ,perl-file-which)
4212 ("perl-graph" ,perl-graph)
4213 ("perl-graph-readwrite" ,perl-graph-readwrite)
4214 ("perl-log-log4perl" ,perl-log-log4perl)
4215 ("perl-moose" ,perl-moose)
4216 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4217 ("perl-text-csv" ,perl-text-csv)
4218 ("bedtools" ,bedtools)
4222 ("parallel" ,parallel)
4225 ("fasttree" ,fasttree)
4229 ("r-minimal" ,r-minimal)
4230 ("r-ggplot2" ,r-ggplot2)
4231 ("coreutils" ,coreutils)))
4232 (home-page "http://sanger-pathogens.github.io/Roary")
4233 (synopsis "High speed stand-alone pan genome pipeline")
4235 "Roary is a high speed stand alone pan genome pipeline, which takes
4236 annotated assemblies in GFF3 format (produced by the Prokka program) and
4237 calculates the pan genome. Using a standard desktop PC, it can analyse
4238 datasets with thousands of samples, without compromising the quality of the
4239 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4240 single processor. Roary is not intended for metagenomics or for comparing
4241 extremely diverse sets of genomes.")
4242 (license license:gpl3)))
4244 (define-public raxml
4253 "https://github.com/stamatak/standard-RAxML/archive/v"
4255 (file-name (string-append name "-" version ".tar.gz"))
4258 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4259 (build-system gnu-build-system)
4261 `(#:tests? #f ; There are no tests.
4262 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4263 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4265 (modify-phases %standard-phases
4268 (lambda* (#:key outputs #:allow-other-keys)
4269 (let* ((out (assoc-ref outputs "out"))
4270 (bin (string-append out "/bin"))
4271 (executable "raxmlHPC-HYBRID"))
4272 (install-file executable bin)
4273 (symlink (string-append bin "/" executable) "raxml"))
4276 `(("openmpi" ,openmpi)))
4277 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4278 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4280 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4282 ;; The source includes x86 specific code
4283 (supported-systems '("x86_64-linux" "i686-linux"))
4284 (license license:gpl2+)))
4294 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4297 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4298 (patches (search-patches "rsem-makefile.patch"))
4299 (modules '((guix build utils)))
4302 ;; remove bundled copy of boost
4303 (delete-file-recursively "boost")
4305 (build-system gnu-build-system)
4307 `(#:tests? #f ;no "check" target
4309 (modify-phases %standard-phases
4310 ;; No "configure" script.
4311 ;; Do not build bundled samtools library.
4314 (substitute* "Makefile"
4315 (("^all : sam/libbam.a") "all : "))
4318 (lambda* (#:key outputs #:allow-other-keys)
4319 (let* ((out (string-append (assoc-ref outputs "out")))
4320 (bin (string-append out "/bin/"))
4321 (perl (string-append out "/lib/perl5/site_perl")))
4324 (for-each (lambda (file)
4325 (install-file file bin))
4326 (find-files "." "rsem-.*"))
4327 (install-file "rsem_perl_utils.pm" perl))
4330 'install 'wrap-program
4331 (lambda* (#:key outputs #:allow-other-keys)
4332 (let ((out (assoc-ref outputs "out")))
4333 (for-each (lambda (prog)
4334 (wrap-program (string-append out "/bin/" prog)
4335 `("PERL5LIB" ":" prefix
4336 (,(string-append out "/lib/perl5/site_perl")))))
4337 '("rsem-plot-transcript-wiggles"
4338 "rsem-calculate-expression"
4339 "rsem-generate-ngvector"
4341 "rsem-prepare-reference")))
4345 ("ncurses" ,ncurses)
4346 ("r-minimal" ,r-minimal)
4348 ("samtools" ,samtools-0.1)
4350 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4351 (synopsis "Estimate gene expression levels from RNA-Seq data")
4353 "RSEM is a software package for estimating gene and isoform expression
4354 levels from RNA-Seq data. The RSEM package provides a user-friendly
4355 interface, supports threads for parallel computation of the EM algorithm,
4356 single-end and paired-end read data, quality scores, variable-length reads and
4357 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4358 interval estimates for expression levels. For visualization, it can generate
4359 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4360 (license license:gpl3+)))
4362 (define-public rseqc
4370 (string-append "mirror://sourceforge/rseqc/"
4371 "RSeQC-" version ".tar.gz"))
4373 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4374 (modules '((guix build utils)))
4377 ;; remove bundled copy of pysam
4378 (delete-file-recursively "lib/pysam")
4379 (substitute* "setup.py"
4380 ;; remove dependency on outdated "distribute" module
4381 (("^from distribute_setup import use_setuptools") "")
4382 (("^use_setuptools\\(\\)") "")
4383 ;; do not use bundled copy of pysam
4384 (("^have_pysam = False") "have_pysam = True"))))))
4385 (build-system python-build-system)
4386 (arguments `(#:python ,python-2))
4388 `(("python-cython" ,python2-cython)
4389 ("python-pysam" ,python2-pysam)
4390 ("python-numpy" ,python2-numpy)
4393 `(("python-nose" ,python2-nose)))
4394 (home-page "http://rseqc.sourceforge.net/")
4395 (synopsis "RNA-seq quality control package")
4397 "RSeQC provides a number of modules that can comprehensively evaluate
4398 high throughput sequence data, especially RNA-seq data. Some basic modules
4399 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4400 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4401 distribution, coverage uniformity, strand specificity, etc.")
4402 (license license:gpl3+)))
4405 ;; There are no release tarballs. According to the installation
4406 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4407 ;; stable release is identified by this changeset ID.
4408 (let ((changeset "2329130")
4412 (version (string-append "0-" revision "." changeset))
4416 (url "https://bitbucket.org/libsleipnir/sleipnir")
4417 (changeset changeset)))
4420 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4421 (build-system gnu-build-system)
4423 `(#:modules ((srfi srfi-1)
4424 (guix build gnu-build-system)
4427 (let ((dirs '("SeekMiner"
4433 (modify-phases %standard-phases
4434 (add-before 'configure 'bootstrap
4436 (zero? (system* "bash" "gen_auto"))))
4437 (add-after 'build 'build-additional-tools
4438 (lambda* (#:key make-flags #:allow-other-keys)
4439 (every (lambda (dir)
4440 (with-directory-excursion (string-append "tools/" dir)
4441 (zero? (apply system* "make" make-flags))))
4443 (add-after 'install 'install-additional-tools
4444 (lambda* (#:key make-flags #:allow-other-keys)
4445 (fold (lambda (dir result)
4446 (with-directory-excursion (string-append "tools/" dir)
4448 (zero? (apply system*
4449 `("make" ,@make-flags "install"))))))
4455 ("readline" ,readline)
4456 ("gengetopt" ,gengetopt)
4457 ("log4cpp" ,log4cpp)))
4459 `(("autoconf" ,autoconf)
4460 ("automake" ,automake)
4462 (home-page "http://seek.princeton.edu")
4463 (synopsis "Gene co-expression search engine")
4465 "SEEK is a computational gene co-expression search engine. SEEK provides
4466 biologists with a way to navigate the massive human expression compendium that
4467 now contains thousands of expression datasets. SEEK returns a robust ranking
4468 of co-expressed genes in the biological area of interest defined by the user's
4469 query genes. It also prioritizes thousands of expression datasets according
4470 to the user's query of interest.")
4471 (license license:cc-by3.0))))
4473 (define-public samtools
4481 (string-append "mirror://sourceforge/samtools/samtools/"
4482 version "/samtools-" version ".tar.bz2"))
4485 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4486 (build-system gnu-build-system)
4488 `(#:modules ((ice-9 ftw)
4490 (guix build gnu-build-system)
4492 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4493 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4495 (modify-phases %standard-phases
4496 (add-after 'unpack 'patch-tests
4498 (substitute* "test/test.pl"
4499 ;; The test script calls out to /bin/bash
4500 (("/bin/bash") (which "bash")))
4502 (add-after 'install 'install-library
4503 (lambda* (#:key outputs #:allow-other-keys)
4504 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4505 (install-file "libbam.a" lib)
4507 (add-after 'install 'install-headers
4508 (lambda* (#:key outputs #:allow-other-keys)
4509 (let ((include (string-append (assoc-ref outputs "out")
4510 "/include/samtools/")))
4511 (for-each (lambda (file)
4512 (install-file file include))
4513 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4515 (native-inputs `(("pkg-config" ,pkg-config)))
4517 `(("htslib" ,htslib)
4518 ("ncurses" ,ncurses)
4522 (home-page "http://samtools.sourceforge.net")
4523 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4525 "Samtools implements various utilities for post-processing nucleotide
4526 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4527 variant calling (in conjunction with bcftools), and a simple alignment
4529 (license license:expat)))
4531 (define-public samtools-0.1
4532 ;; This is the most recent version of the 0.1 line of samtools. The input
4533 ;; and output formats differ greatly from that used and produced by samtools
4534 ;; 1.x and is still used in many bioinformatics pipelines.
4535 (package (inherit samtools)
4541 (string-append "mirror://sourceforge/samtools/samtools/"
4542 version "/samtools-" version ".tar.bz2"))
4544 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4546 `(#:tests? #f ;no "check" target
4547 ,@(substitute-keyword-arguments (package-arguments samtools)
4548 ((#:make-flags flags)
4549 `(cons "LIBCURSES=-lncurses" ,flags))
4551 `(modify-phases ,phases
4553 (lambda* (#:key outputs #:allow-other-keys)
4554 (let ((bin (string-append
4555 (assoc-ref outputs "out") "/bin")))
4557 (install-file "samtools" bin)
4559 (delete 'patch-tests)
4560 (delete 'configure))))))))
4562 (define-public mosaik
4563 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4568 ;; There are no release tarballs nor tags.
4571 (url "https://github.com/wanpinglee/MOSAIK.git")
4573 (file-name (string-append name "-" version))
4576 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4577 (build-system gnu-build-system)
4579 `(#:tests? #f ; no tests
4580 #:make-flags (list "CC=gcc")
4582 (modify-phases %standard-phases
4584 (lambda _ (chdir "src") #t))
4586 (lambda* (#:key outputs #:allow-other-keys)
4587 (let ((bin (string-append (assoc-ref outputs "out")
4590 (copy-recursively "../bin" bin)
4595 (supported-systems '("x86_64-linux"))
4596 (home-page "https://github.com/wanpinglee/MOSAIK")
4597 (synopsis "Map nucleotide sequence reads to reference genomes")
4599 "MOSAIK is a program for mapping second and third-generation sequencing
4600 reads to a reference genome. MOSAIK can align reads generated by all the
4601 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4602 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4603 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4604 ;; code released into the public domain:
4605 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4606 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4607 (license (list license:gpl2+ license:public-domain)))))
4609 (define-public ngs-sdk
4617 (string-append "https://github.com/ncbi/ngs/archive/"
4619 (file-name (string-append name "-" version ".tar.gz"))
4622 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4623 (build-system gnu-build-system)
4625 `(#:parallel-build? #f ; not supported
4626 #:tests? #f ; no "check" target
4628 (modify-phases %standard-phases
4630 (lambda* (#:key outputs #:allow-other-keys)
4631 (let ((out (assoc-ref outputs "out")))
4632 ;; Allow 'konfigure.perl' to find 'package.prl'.
4634 (string-append ".:" (getenv "PERL5LIB")))
4636 ;; The 'configure' script doesn't recognize things like
4637 ;; '--enable-fast-install'.
4638 (zero? (system* "./configure"
4639 (string-append "--build-prefix=" (getcwd) "/build")
4640 (string-append "--prefix=" out))))))
4641 (add-after 'unpack 'enter-dir
4642 (lambda _ (chdir "ngs-sdk") #t)))))
4643 (native-inputs `(("perl" ,perl)))
4644 ;; According to the test
4645 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4646 ;; in ngs-sdk/setup/konfigure.perl
4647 (supported-systems '("i686-linux" "x86_64-linux"))
4648 (home-page "https://github.com/ncbi/ngs")
4649 (synopsis "API for accessing Next Generation Sequencing data")
4651 "NGS is a domain-specific API for accessing reads, alignments and pileups
4652 produced from Next Generation Sequencing. The API itself is independent from
4653 any particular back-end implementation, and supports use of multiple back-ends
4655 (license license:public-domain)))
4657 (define-public java-ngs
4658 (package (inherit ngs-sdk)
4661 `(,@(substitute-keyword-arguments
4662 `(#:modules ((guix build gnu-build-system)
4666 ,@(package-arguments ngs-sdk))
4668 `(modify-phases ,phases
4669 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4671 `(("jdk" ,icedtea "jdk")
4672 ("ngs-sdk" ,ngs-sdk)))
4673 (synopsis "Java bindings for NGS SDK")))
4675 (define-public ncbi-vdb
4683 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4685 (file-name (string-append name "-" version ".tar.gz"))
4688 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4689 (build-system gnu-build-system)
4691 `(#:parallel-build? #f ; not supported
4692 #:tests? #f ; no "check" target
4694 (modify-phases %standard-phases
4695 (add-before 'configure 'set-perl-search-path
4697 ;; Work around "dotless @INC" build failure.
4699 (string-append (getcwd) "/setup:"
4700 (getenv "PERL5LIB")))
4703 (lambda* (#:key inputs outputs #:allow-other-keys)
4704 (let ((out (assoc-ref outputs "out")))
4705 ;; Override include path for libmagic
4706 (substitute* "setup/package.prl"
4707 (("name => 'magic', Include => '/usr/include'")
4708 (string-append "name=> 'magic', Include => '"
4709 (assoc-ref inputs "libmagic")
4712 ;; Install kdf5 library (needed by sra-tools)
4713 (substitute* "build/Makefile.install"
4714 (("LIBRARIES_TO_INSTALL =")
4715 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4717 (substitute* "build/Makefile.env"
4718 (("CFLAGS =" prefix)
4719 (string-append prefix "-msse2 ")))
4721 ;; Override search path for ngs-java
4722 (substitute* "setup/package.prl"
4723 (("/usr/local/ngs/ngs-java")
4724 (assoc-ref inputs "java-ngs")))
4726 ;; The 'configure' script doesn't recognize things like
4727 ;; '--enable-fast-install'.
4730 (string-append "--build-prefix=" (getcwd) "/build")
4731 (string-append "--prefix=" (assoc-ref outputs "out"))
4732 (string-append "--debug")
4733 (string-append "--with-xml2-prefix="
4734 (assoc-ref inputs "libxml2"))
4735 (string-append "--with-ngs-sdk-prefix="
4736 (assoc-ref inputs "ngs-sdk"))
4737 (string-append "--with-hdf5-prefix="
4738 (assoc-ref inputs "hdf5")))))))
4739 (add-after 'install 'install-interfaces
4740 (lambda* (#:key outputs #:allow-other-keys)
4741 ;; Install interface libraries. On i686 the interface libraries
4742 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4743 ;; architecture name ("i386") instead of the target system prefix
4745 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4746 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4747 ,(system->linux-architecture
4748 (or (%current-target-system)
4751 (string-append (assoc-ref outputs "out")
4753 ;; Install interface headers
4754 (copy-recursively "interfaces"
4755 (string-append (assoc-ref outputs "out")
4758 ;; These files are needed by sra-tools.
4759 (add-after 'install 'install-configuration-files
4760 (lambda* (#:key outputs #:allow-other-keys)
4761 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4763 (install-file "libs/kfg/default.kfg" target)
4764 (install-file "libs/kfg/certs.kfg" target))
4767 `(("libxml2" ,libxml2)
4768 ("ngs-sdk" ,ngs-sdk)
4769 ("java-ngs" ,java-ngs)
4772 (native-inputs `(("perl" ,perl)))
4773 ;; NCBI-VDB requires SSE capability.
4774 (supported-systems '("i686-linux" "x86_64-linux"))
4775 (home-page "https://github.com/ncbi/ncbi-vdb")
4776 (synopsis "Database engine for genetic information")
4778 "The NCBI-VDB library implements a highly compressed columnar data
4779 warehousing engine that is most often used to store genetic information.
4780 Databases are stored in a portable image within the file system, and can be
4781 accessed/downloaded on demand across HTTP.")
4782 (license license:public-domain)))
4784 (define-public plink
4792 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4793 version "-src.zip"))
4795 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4796 (patches (search-patches "plink-1.07-unclobber-i.patch"
4797 "plink-endian-detection.patch"))))
4798 (build-system gnu-build-system)
4800 '(#:tests? #f ;no "check" target
4801 #:make-flags (list (string-append "LIB_LAPACK="
4802 (assoc-ref %build-inputs "lapack")
4803 "/lib/liblapack.so")
4806 ;; disable phoning home
4809 (modify-phases %standard-phases
4810 ;; no "configure" script
4813 (lambda* (#:key outputs #:allow-other-keys)
4814 (let ((bin (string-append (assoc-ref outputs "out")
4816 (install-file "plink" bin)
4820 ("lapack" ,lapack)))
4822 `(("unzip" ,unzip)))
4823 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4824 (synopsis "Whole genome association analysis toolset")
4826 "PLINK is a whole genome association analysis toolset, designed to
4827 perform a range of basic, large-scale analyses in a computationally efficient
4828 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4829 so there is no support for steps prior to this (e.g. study design and
4830 planning, generating genotype or CNV calls from raw data). Through
4831 integration with gPLINK and Haploview, there is some support for the
4832 subsequent visualization, annotation and storage of results.")
4833 ;; Code is released under GPLv2, except for fisher.h, which is under
4835 (license (list license:gpl2 license:lgpl2.1+))))
4837 (define-public plink-ng
4838 (package (inherit plink)
4844 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
4846 (file-name (string-append name "-" version ".tar.gz"))
4848 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
4849 (build-system gnu-build-system)
4851 '(#:tests? #f ;no "check" target
4852 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
4853 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
4855 "-f" "Makefile.std")
4857 (modify-phases %standard-phases
4858 (add-after 'unpack 'chdir
4859 (lambda _ (chdir "1.9") #t))
4860 (delete 'configure) ; no "configure" script
4862 (lambda* (#:key outputs #:allow-other-keys)
4863 (let ((bin (string-append (assoc-ref outputs "out")
4865 (install-file "plink" bin)
4870 ("openblas" ,openblas)))
4871 (home-page "https://www.cog-genomics.org/plink/")
4872 (license license:gpl3+)))
4874 (define-public smithlab-cpp
4875 (let ((revision "1")
4876 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4878 (name "smithlab-cpp")
4879 (version (string-append "0." revision "." (string-take commit 7)))
4883 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4885 (file-name (string-append name "-" version "-checkout"))
4888 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4889 (build-system gnu-build-system)
4891 `(#:modules ((guix build gnu-build-system)
4894 #:tests? #f ;no "check" target
4896 (modify-phases %standard-phases
4897 (add-after 'unpack 'use-samtools-headers
4899 (substitute* '("SAM.cpp"
4901 (("sam.h") "samtools/sam.h"))
4904 (lambda* (#:key outputs #:allow-other-keys)
4905 (let* ((out (assoc-ref outputs "out"))
4906 (lib (string-append out "/lib"))
4907 (include (string-append out "/include/smithlab-cpp")))
4910 (for-each (cut install-file <> lib)
4911 (find-files "." "\\.o$"))
4912 (for-each (cut install-file <> include)
4913 (find-files "." "\\.hpp$")))
4915 (delete 'configure))))
4917 `(("samtools" ,samtools-0.1)
4919 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4920 (synopsis "C++ helper library for functions used in Smith lab projects")
4922 "Smithlab CPP is a C++ library that includes functions used in many of
4923 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4924 structures, classes for genomic regions, mapped sequencing reads, etc.")
4925 (license license:gpl3+))))
4927 (define-public preseq
4933 (uri (string-append "https://github.com/smithlabcode/"
4934 "preseq/archive/v" version ".tar.gz"))
4935 (file-name (string-append name "-" version ".tar.gz"))
4937 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4938 (modules '((guix build utils)))
4940 ;; Remove bundled samtools.
4941 '(delete-file-recursively "samtools"))))
4942 (build-system gnu-build-system)
4944 `(#:tests? #f ;no "check" target
4946 (modify-phases %standard-phases
4947 (delete 'configure))
4949 (list (string-append "PREFIX="
4950 (assoc-ref %outputs "out"))
4951 (string-append "LIBBAM="
4952 (assoc-ref %build-inputs "samtools")
4954 (string-append "SMITHLAB_CPP="
4955 (assoc-ref %build-inputs "smithlab-cpp")
4958 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4961 ("samtools" ,samtools-0.1)
4962 ("smithlab-cpp" ,smithlab-cpp)
4964 (home-page "http://smithlabresearch.org/software/preseq/")
4965 (synopsis "Program for analyzing library complexity")
4967 "The preseq package is aimed at predicting and estimating the complexity
4968 of a genomic sequencing library, equivalent to predicting and estimating the
4969 number of redundant reads from a given sequencing depth and how many will be
4970 expected from additional sequencing using an initial sequencing experiment.
4971 The estimates can then be used to examine the utility of further sequencing,
4972 optimize the sequencing depth, or to screen multiple libraries to avoid low
4973 complexity samples.")
4974 (license license:gpl3+)))
4976 (define-public python-screed
4978 (name "python-screed")
4983 (uri (pypi-uri "screed" version))
4986 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4987 (build-system python-build-system)
4990 (modify-phases %standard-phases
4993 (setenv "PYTHONPATH"
4994 (string-append (getenv "PYTHONPATH") ":."))
4995 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4997 `(("python-nose" ,python-nose)))
4999 `(("python-bz2file" ,python-bz2file)))
5000 (home-page "https://github.com/dib-lab/screed/")
5001 (synopsis "Short read sequence database utilities")
5002 (description "Screed parses FASTA and FASTQ files and generates databases.
5003 Values such as sequence name, sequence description, sequence quality and the
5004 sequence itself can be retrieved from these databases.")
5005 (license license:bsd-3)))
5007 (define-public python2-screed
5008 (package-with-python2 python-screed))
5010 (define-public sra-tools
5018 (string-append "https://github.com/ncbi/sra-tools/archive/"
5020 (file-name (string-append name "-" version ".tar.gz"))
5023 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5024 (build-system gnu-build-system)
5026 `(#:parallel-build? #f ; not supported
5027 #:tests? #f ; no "check" target
5029 (list (string-append "DEFAULT_CRT="
5030 (assoc-ref %build-inputs "ncbi-vdb")
5032 (string-append "DEFAULT_KFG="
5033 (assoc-ref %build-inputs "ncbi-vdb")
5035 (string-append "VDB_LIBDIR="
5036 (assoc-ref %build-inputs "ncbi-vdb")
5037 ,(if (string-prefix? "x86_64"
5038 (or (%current-target-system)
5043 (modify-phases %standard-phases
5044 (add-before 'configure 'set-perl-search-path
5046 ;; Work around "dotless @INC" build failure.
5048 (string-append (getcwd) "/setup:"
5049 (getenv "PERL5LIB")))
5052 (lambda* (#:key inputs outputs #:allow-other-keys)
5053 ;; The build system expects a directory containing the sources and
5054 ;; raw build output of ncbi-vdb, including files that are not
5055 ;; installed. Since we are building against an installed version of
5056 ;; ncbi-vdb, the following modifications are needed.
5057 (substitute* "setup/konfigure.perl"
5058 ;; Make the configure script look for the "ilib" directory of
5059 ;; "ncbi-vdb" without first checking for the existence of a
5060 ;; matching library in its "lib" directory.
5061 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5062 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5063 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5064 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5065 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5068 (substitute* "tools/copycat/Makefile"
5069 (("smagic-static") "lmagic"))
5071 ;; The 'configure' script doesn't recognize things like
5072 ;; '--enable-fast-install'.
5075 (string-append "--build-prefix=" (getcwd) "/build")
5076 (string-append "--prefix=" (assoc-ref outputs "out"))
5077 (string-append "--debug")
5078 (string-append "--with-fuse-prefix="
5079 (assoc-ref inputs "fuse"))
5080 (string-append "--with-magic-prefix="
5081 (assoc-ref inputs "libmagic"))
5082 ;; TODO: building with libxml2 fails with linker errors
5083 ;; (string-append "--with-xml2-prefix="
5084 ;; (assoc-ref inputs "libxml2"))
5085 (string-append "--with-ncbi-vdb-sources="
5086 (assoc-ref inputs "ncbi-vdb"))
5087 (string-append "--with-ncbi-vdb-build="
5088 (assoc-ref inputs "ncbi-vdb"))
5089 (string-append "--with-ngs-sdk-prefix="
5090 (assoc-ref inputs "ngs-sdk"))
5091 (string-append "--with-hdf5-prefix="
5092 (assoc-ref inputs "hdf5"))))))
5093 ;; This version of sra-tools fails to build with glibc because of a
5094 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5095 ;; contains a definition of "canonicalize", so we rename it.
5097 ;; See upstream bug report:
5098 ;; https://github.com/ncbi/sra-tools/issues/67
5099 (add-after 'unpack 'patch-away-glibc-conflict
5101 (substitute* "tools/bam-loader/bam.c"
5102 (("canonicalize\\(" line)
5103 (string-append "sra_tools_" line)))
5105 (native-inputs `(("perl" ,perl)))
5107 `(("ngs-sdk" ,ngs-sdk)
5108 ("ncbi-vdb" ,ncbi-vdb)
5113 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5114 (synopsis "Tools and libraries for reading and writing sequencing data")
5116 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5117 reading of sequencing files from the Sequence Read Archive (SRA) database and
5118 writing files into the .sra format.")
5119 (license license:public-domain)))
5121 (define-public seqan
5127 (uri (string-append "http://packages.seqan.de/seqan-library/"
5128 "seqan-library-" version ".tar.bz2"))
5131 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5132 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5133 ;; makes sense to split the outputs.
5134 (outputs '("out" "doc"))
5135 (build-system trivial-build-system)
5137 `(#:modules ((guix build utils))
5140 (use-modules (guix build utils))
5141 (let ((tar (assoc-ref %build-inputs "tar"))
5142 (bzip (assoc-ref %build-inputs "bzip2"))
5143 (out (assoc-ref %outputs "out"))
5144 (doc (assoc-ref %outputs "doc")))
5145 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5146 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5147 (chdir (string-append "seqan-library-" ,version))
5148 (copy-recursively "include" (string-append out "/include"))
5149 (copy-recursively "share" (string-append doc "/share"))))))
5151 `(("source" ,source)
5154 (home-page "http://www.seqan.de")
5155 (synopsis "Library for nucleotide sequence analysis")
5157 "SeqAn is a C++ library of efficient algorithms and data structures for
5158 the analysis of sequences with the focus on biological data. It contains
5159 algorithms and data structures for string representation and their
5160 manipulation, online and indexed string search, efficient I/O of
5161 bioinformatics file formats, sequence alignment, and more.")
5162 (license license:bsd-3)))
5164 (define-public seqmagick
5172 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5176 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5177 (build-system python-build-system)
5179 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5180 `(#:python ,python-2
5182 (modify-phases %standard-phases
5183 ;; Current test in setup.py does not work as of 0.6.1,
5184 ;; so use nose to run tests instead for now. See
5185 ;; https://github.com/fhcrc/seqmagick/issues/55
5186 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5188 ;; biopython-1.66 is required due to
5189 ;; https://github.com/fhcrc/seqmagick/issues/59
5190 ;; When that issue is resolved the 'python2-biopython-1.66' package
5191 ;; should be removed.
5192 `(("python-biopython" ,python2-biopython-1.66)))
5194 `(("python-nose" ,python2-nose)))
5195 (home-page "https://github.com/fhcrc/seqmagick")
5196 (synopsis "Tools for converting and modifying sequence files")
5198 "Bioinformaticians often have to convert sequence files between formats
5199 and do little manipulations on them, and it's not worth writing scripts for
5200 that. Seqmagick is a utility to expose the file format conversion in
5201 BioPython in a convenient way. Instead of having a big mess of scripts, there
5202 is one that takes arguments.")
5203 (license license:gpl3)))
5205 (define-public seqtk
5212 "https://github.com/lh3/seqtk/archive/v"
5214 (file-name (string-append name "-" version ".tar.gz"))
5217 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5218 (modules '((guix build utils)))
5221 ;; Remove extraneous header files, as is done in the seqtk
5223 (for-each (lambda (file) (delete-file file))
5224 (list "ksort.h" "kstring.h" "kvec.h"))
5226 (build-system gnu-build-system)
5229 (modify-phases %standard-phases
5232 ;; There are no tests, so we just run a sanity check.
5233 (lambda _ (zero? (system* "./seqtk" "seq"))))
5235 (lambda* (#:key outputs #:allow-other-keys)
5236 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5237 (install-file "seqtk" bin)))))))
5240 (home-page "https://github.com/lh3/seqtk")
5241 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5243 "Seqtk is a fast and lightweight tool for processing sequences in the
5244 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5245 optionally compressed by gzip.")
5246 (license license:expat)))
5248 (define-public snap-aligner
5250 (name "snap-aligner")
5251 (version "1.0beta.18")
5255 "https://github.com/amplab/snap/archive/v"
5257 (file-name (string-append name "-" version ".tar.gz"))
5260 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5261 (build-system gnu-build-system)
5264 (modify-phases %standard-phases
5266 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5268 (lambda* (#:key outputs #:allow-other-keys)
5269 (let* ((out (assoc-ref outputs "out"))
5270 (bin (string-append out "/bin")))
5271 (install-file "snap-aligner" bin)
5272 (install-file "SNAPCommand" bin)
5276 (home-page "http://snap.cs.berkeley.edu/")
5277 (synopsis "Short read DNA sequence aligner")
5279 "SNAP is a fast and accurate aligner for short DNA reads. It is
5280 optimized for modern read lengths of 100 bases or higher, and takes advantage
5281 of these reads to align data quickly through a hash-based indexing scheme.")
5282 ;; 32-bit systems are not supported by the unpatched code.
5283 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5284 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5285 ;; systems without a lot of memory cannot make good use of this program.
5286 (supported-systems '("x86_64-linux"))
5287 (license license:asl2.0)))
5289 (define-public sortmerna
5297 "https://github.com/biocore/sortmerna/archive/"
5299 (file-name (string-append name "-" version ".tar.gz"))
5302 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5303 (build-system gnu-build-system)
5304 (outputs '("out" ;for binaries
5305 "db")) ;for sequence databases
5308 (modify-phases %standard-phases
5310 (lambda* (#:key outputs #:allow-other-keys)
5311 (let* ((out (assoc-ref outputs "out"))
5312 (bin (string-append out "/bin"))
5313 (db (assoc-ref outputs "db"))
5315 (string-append db "/share/sortmerna/rRNA_databases")))
5316 (install-file "sortmerna" bin)
5317 (install-file "indexdb_rna" bin)
5318 (for-each (lambda (file)
5319 (install-file file share))
5320 (find-files "rRNA_databases" ".*fasta"))
5324 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5325 (synopsis "Biological sequence analysis tool for NGS reads")
5327 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5328 and operational taxonomic unit (OTU) picking of next generation
5329 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5330 allows for fast and sensitive analyses of nucleotide sequences. The main
5331 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5332 ;; The source includes x86 specific code
5333 (supported-systems '("x86_64-linux" "i686-linux"))
5334 (license license:lgpl3)))
5342 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5344 (file-name (string-append name "-" version ".tar.gz"))
5347 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5348 (modules '((guix build utils)))
5351 (substitute* "source/Makefile"
5353 ;; Remove pre-built binaries and bundled htslib sources.
5354 (delete-file-recursively "bin/MacOSX_x86_64")
5355 (delete-file-recursively "bin/Linux_x86_64")
5356 (delete-file-recursively "bin/Linux_x86_64_static")
5357 (delete-file-recursively "source/htslib")
5359 (build-system gnu-build-system)
5361 '(#:tests? #f ;no check target
5362 #:make-flags '("STAR")
5364 (modify-phases %standard-phases
5365 (add-after 'unpack 'enter-source-dir
5366 (lambda _ (chdir "source") #t))
5367 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5369 (substitute* "Makefile"
5370 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5372 (substitute* '("BAMfunctions.cpp"
5377 "bamRemoveDuplicates.cpp")
5378 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5379 (string-append "#include <" header ">")))
5380 (substitute* "IncludeDefine.h"
5381 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5382 (string-append "<" header ">")))
5385 (lambda* (#:key outputs #:allow-other-keys)
5386 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5387 (install-file "STAR" bin))
5389 (delete 'configure))))
5393 `(("htslib" ,htslib)
5395 (home-page "https://github.com/alexdobin/STAR")
5396 (synopsis "Universal RNA-seq aligner")
5398 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5399 based on a previously undescribed RNA-seq alignment algorithm that uses
5400 sequential maximum mappable seed search in uncompressed suffix arrays followed
5401 by seed clustering and stitching procedure. In addition to unbiased de novo
5402 detection of canonical junctions, STAR can discover non-canonical splices and
5403 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5405 ;; Only 64-bit systems are supported according to the README.
5406 (supported-systems '("x86_64-linux" "mips64el-linux"))
5407 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5408 (license license:gpl3+)))
5410 (define-public subread
5416 (uri (string-append "mirror://sourceforge/subread/subread-"
5417 version "/subread-" version "-source.tar.gz"))
5420 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5421 (build-system gnu-build-system)
5423 `(#:tests? #f ;no "check" target
5424 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5425 ;; optimizations by default, so we override these flags such that x86_64
5426 ;; flags are only added when the build target is an x86_64 system.
5428 (list (let ((system ,(or (%current-target-system)
5430 (flags '("-ggdb" "-fomit-frame-pointer"
5431 "-ffast-math" "-funroll-loops"
5432 "-fmessage-length=0"
5433 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5435 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5436 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5437 (if (string-prefix? "x86_64" system)
5438 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5439 (string-append "CCFLAGS=" (string-join flags))))
5440 "-f" "Makefile.Linux"
5441 "CC=gcc ${CCFLAGS}")
5443 (modify-phases %standard-phases
5444 (add-after 'unpack 'enter-dir
5445 (lambda _ (chdir "src") #t))
5447 (lambda* (#:key outputs #:allow-other-keys)
5448 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5450 (copy-recursively "../bin" bin))))
5451 ;; no "configure" script
5452 (delete 'configure))))
5453 (inputs `(("zlib" ,zlib)))
5454 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5455 (synopsis "Tool kit for processing next-gen sequencing data")
5457 "The subread package contains the following tools: subread aligner, a
5458 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5459 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5460 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5461 against local background noises.")
5462 (license license:gpl3+)))
5464 (define-public stringtie
5470 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5471 "stringtie-" version ".tar.gz"))
5474 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5475 (modules '((guix build utils)))
5478 (delete-file-recursively "samtools-0.1.18")
5480 (build-system gnu-build-system)
5482 `(#:tests? #f ;no test suite
5484 (modify-phases %standard-phases
5485 ;; no configure script
5487 (add-before 'build 'use-system-samtools
5489 (substitute* "Makefile"
5490 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5492 (substitute* '("gclib/GBam.h"
5494 (("#include \"(bam|sam|kstring).h\"" _ header)
5495 (string-append "#include <samtools/" header ".h>")))
5497 (add-after 'unpack 'remove-duplicate-typedef
5499 ;; This typedef conflicts with the typedef in
5500 ;; glibc-2.25/include/bits/types.h
5501 (substitute* "gclib/GThreads.h"
5502 (("typedef long long __intmax_t;") ""))
5505 (lambda* (#:key outputs #:allow-other-keys)
5506 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5507 (install-file "stringtie" bin)
5510 `(("samtools" ,samtools-0.1)
5512 (home-page "http://ccb.jhu.edu/software/stringtie/")
5513 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5515 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5516 alignments into potential transcripts. It uses a novel network flow algorithm
5517 as well as an optional de novo assembly step to assemble and quantitate
5518 full-length transcripts representing multiple splice variants for each gene
5519 locus. Its input can include not only the alignments of raw reads used by
5520 other transcript assemblers, but also alignments of longer sequences that have
5521 been assembled from those reads. To identify differentially expressed genes
5522 between experiments, StringTie's output can be processed either by the
5523 Cuffdiff or Ballgown programs.")
5524 (license license:artistic2.0)))
5526 (define-public taxtastic
5532 (uri (pypi-uri "taxtastic" version))
5535 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5536 (build-system python-build-system)
5538 `(#:python ,python-2
5540 (modify-phases %standard-phases
5543 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5545 `(("python-sqlalchemy" ,python2-sqlalchemy)
5546 ("python-decorator" ,python2-decorator)
5547 ("python-biopython" ,python2-biopython)
5548 ("python-pandas" ,python2-pandas)))
5549 (home-page "https://github.com/fhcrc/taxtastic")
5550 (synopsis "Tools for taxonomic naming and annotation")
5552 "Taxtastic is software written in python used to build and maintain
5553 reference packages i.e. collections of reference trees, reference alignments,
5554 profiles, and associated taxonomic information.")
5555 (license license:gpl3+)))
5557 (define-public vcftools
5564 "https://github.com/vcftools/vcftools/releases/download/v"
5565 version "/vcftools-" version ".tar.gz"))
5568 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5569 (build-system gnu-build-system)
5571 `(#:tests? #f ; no "check" target
5573 "CFLAGS=-O2" ; override "-m64" flag
5574 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5575 (string-append "MANDIR=" (assoc-ref %outputs "out")
5576 "/share/man/man1"))))
5578 `(("pkg-config" ,pkg-config)))
5582 (home-page "https://vcftools.github.io/")
5583 (synopsis "Tools for working with VCF files")
5585 "VCFtools is a program package designed for working with VCF files, such
5586 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5587 provide easily accessible methods for working with complex genetic variation
5588 data in the form of VCF files.")
5589 ;; The license is declared as LGPLv3 in the README and
5590 ;; at https://vcftools.github.io/license.html
5591 (license license:lgpl3)))
5593 (define-public infernal
5599 (uri (string-append "http://eddylab.org/software/infernal/"
5600 "infernal-" version ".tar.gz"))
5603 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5604 (build-system gnu-build-system)
5606 `(("perl" ,perl))) ; for tests
5607 (home-page "http://eddylab.org/infernal/")
5608 (synopsis "Inference of RNA alignments")
5609 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5610 searching DNA sequence databases for RNA structure and sequence similarities.
5611 It is an implementation of a special case of profile stochastic context-free
5612 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5613 profile, but it scores a combination of sequence consensus and RNA secondary
5614 structure consensus, so in many cases, it is more capable of identifying RNA
5615 homologs that conserve their secondary structure more than their primary
5617 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5618 (supported-systems '("i686-linux" "x86_64-linux"))
5619 (license license:bsd-3)))
5621 (define-public r-centipede
5623 (name "r-centipede")
5627 (uri (string-append "http://download.r-forge.r-project.org/"
5628 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5631 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5632 (build-system r-build-system)
5633 (home-page "http://centipede.uchicago.edu/")
5634 (synopsis "Predict transcription factor binding sites")
5636 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5637 of the genome that are bound by particular transcription factors. It starts
5638 by identifying a set of candidate binding sites, and then aims to classify the
5639 sites according to whether each site is bound or not bound by a transcription
5640 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5641 between two different types of motif instances using as much relevant
5642 information as possible.")
5643 (license (list license:gpl2+ license:gpl3+))))
5645 (define-public r-vegan
5652 (uri (cran-uri "vegan" version))
5655 "1n57dzv2aid6iqd9fkqik401sidqanhzsawyak94qbiyh6dbd1x9"))))
5656 (build-system r-build-system)
5658 `(("gfortran" ,gfortran)))
5660 `(("r-cluster" ,r-cluster)
5661 ("r-lattice" ,r-lattice)
5664 ("r-permute" ,r-permute)))
5665 (home-page "https://cran.r-project.org/web/packages/vegan")
5666 (synopsis "Functions for community ecology")
5668 "The vegan package provides tools for descriptive community ecology. It
5669 has most basic functions of diversity analysis, community ordination and
5670 dissimilarity analysis. Most of its multivariate tools can be used for other
5671 data types as well.")
5672 (license license:gpl2+)))
5674 (define-public r-annotate
5681 (uri (bioconductor-uri "annotate" version))
5684 "0wlrp3v2jxw9is98ap39dfi7z97kmw1wv1xi4h7yfh12zpj2r8l0"))))
5685 (build-system r-build-system)
5687 `(("r-annotationdbi" ,r-annotationdbi)
5688 ("r-biobase" ,r-biobase)
5689 ("r-biocgenerics" ,r-biocgenerics)
5691 ("r-rcurl" ,r-rcurl)
5693 ("r-xtable" ,r-xtable)))
5695 "https://bioconductor.org/packages/annotate")
5696 (synopsis "Annotation for microarrays")
5697 (description "This package provides R environments for the annotation of
5699 (license license:artistic2.0)))
5701 (define-public r-geneplotter
5703 (name "r-geneplotter")
5708 (uri (bioconductor-uri "geneplotter" version))
5711 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
5712 (build-system r-build-system)
5714 `(("r-annotate" ,r-annotate)
5715 ("r-annotationdbi" ,r-annotationdbi)
5716 ("r-biobase" ,r-biobase)
5717 ("r-biocgenerics" ,r-biocgenerics)
5718 ("r-lattice" ,r-lattice)
5719 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5720 (home-page "https://bioconductor.org/packages/geneplotter")
5721 (synopsis "Graphics functions for genomic data")
5723 "This package provides functions for plotting genomic data.")
5724 (license license:artistic2.0)))
5726 (define-public r-genefilter
5728 (name "r-genefilter")
5733 (uri (bioconductor-uri "genefilter" version))
5736 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
5737 (build-system r-build-system)
5739 `(("gfortran" ,gfortran)))
5741 `(("r-annotate" ,r-annotate)
5742 ("r-annotationdbi" ,r-annotationdbi)
5743 ("r-biobase" ,r-biobase)
5744 ("r-s4vectors" ,r-s4vectors)
5745 ("r-survival" ,r-survival)))
5746 (home-page "https://bioconductor.org/packages/genefilter")
5747 (synopsis "Filter genes from high-throughput experiments")
5749 "This package provides basic functions for filtering genes from
5750 high-throughput sequencing experiments.")
5751 (license license:artistic2.0)))
5753 (define-public r-deseq2
5760 (uri (bioconductor-uri "DESeq2" version))
5763 "1hcxnkkjfvz4hj8iqidshwsjq7jnl1z7wj63dvcwlx1zx5aichyh"))))
5764 (properties `((upstream-name . "DESeq2")))
5765 (build-system r-build-system)
5767 `(("r-biobase" ,r-biobase)
5768 ("r-biocgenerics" ,r-biocgenerics)
5769 ("r-biocparallel" ,r-biocparallel)
5770 ("r-genefilter" ,r-genefilter)
5771 ("r-geneplotter" ,r-geneplotter)
5772 ("r-genomicranges" ,r-genomicranges)
5773 ("r-ggplot2" ,r-ggplot2)
5774 ("r-hmisc" ,r-hmisc)
5775 ("r-iranges" ,r-iranges)
5776 ("r-locfit" ,r-locfit)
5778 ("r-rcpparmadillo" ,r-rcpparmadillo)
5779 ("r-s4vectors" ,r-s4vectors)
5780 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5781 (home-page "https://bioconductor.org/packages/DESeq2")
5782 (synopsis "Differential gene expression analysis")
5784 "This package provides functions to estimate variance-mean dependence in
5785 count data from high-throughput nucleotide sequencing assays and test for
5786 differential expression based on a model using the negative binomial
5788 (license license:lgpl3+)))
5790 (define-public r-dexseq
5797 (uri (bioconductor-uri "DEXSeq" version))
5800 "0qxwnz2ffhav9slcn095k206cfza9i3i5l7w1154plf08gpy1d1d"))))
5801 (properties `((upstream-name . "DEXSeq")))
5802 (build-system r-build-system)
5804 `(("r-annotationdbi" ,r-annotationdbi)
5805 ("r-biobase" ,r-biobase)
5806 ("r-biocgenerics" ,r-biocgenerics)
5807 ("r-biocparallel" ,r-biocparallel)
5808 ("r-biomart" ,r-biomart)
5809 ("r-deseq2" ,r-deseq2)
5810 ("r-genefilter" ,r-genefilter)
5811 ("r-geneplotter" ,r-geneplotter)
5812 ("r-genomicranges" ,r-genomicranges)
5813 ("r-hwriter" ,r-hwriter)
5814 ("r-iranges" ,r-iranges)
5815 ("r-rcolorbrewer" ,r-rcolorbrewer)
5816 ("r-rsamtools" ,r-rsamtools)
5817 ("r-s4vectors" ,r-s4vectors)
5818 ("r-statmod" ,r-statmod)
5819 ("r-stringr" ,r-stringr)
5820 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5821 (home-page "https://bioconductor.org/packages/DEXSeq")
5822 (synopsis "Inference of differential exon usage in RNA-Seq")
5824 "This package is focused on finding differential exon usage using RNA-seq
5825 exon counts between samples with different experimental designs. It provides
5826 functions that allows the user to make the necessary statistical tests based
5827 on a model that uses the negative binomial distribution to estimate the
5828 variance between biological replicates and generalized linear models for
5829 testing. The package also provides functions for the visualization and
5830 exploration of the results.")
5831 (license license:gpl3+)))
5833 (define-public r-annotationforge
5835 (name "r-annotationforge")
5840 (uri (bioconductor-uri "AnnotationForge" version))
5843 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
5845 `((upstream-name . "AnnotationForge")))
5846 (build-system r-build-system)
5848 `(("r-annotationdbi" ,r-annotationdbi)
5849 ("r-biobase" ,r-biobase)
5850 ("r-biocgenerics" ,r-biocgenerics)
5852 ("r-rcurl" ,r-rcurl)
5853 ("r-rsqlite" ,r-rsqlite)
5854 ("r-s4vectors" ,r-s4vectors)
5856 (home-page "https://bioconductor.org/packages/AnnotationForge")
5857 (synopsis "Code for building annotation database packages")
5859 "This package provides code for generating Annotation packages and their
5860 databases. Packages produced are intended to be used with AnnotationDbi.")
5861 (license license:artistic2.0)))
5863 (define-public r-rbgl
5870 (uri (bioconductor-uri "RBGL" version))
5873 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
5874 (properties `((upstream-name . "RBGL")))
5875 (build-system r-build-system)
5876 (propagated-inputs `(("r-graph" ,r-graph)))
5877 (home-page "https://www.bioconductor.org/packages/RBGL")
5878 (synopsis "Interface to the Boost graph library")
5880 "This package provides a fairly extensive and comprehensive interface to
5881 the graph algorithms contained in the Boost library.")
5882 (license license:artistic2.0)))
5884 (define-public r-gseabase
5891 (uri (bioconductor-uri "GSEABase" version))
5894 "0kpkl6c5lrar6ip7wlhvd5axqlb9lb5l3lgbdb3dlih32c3nz0yq"))))
5895 (properties `((upstream-name . "GSEABase")))
5896 (build-system r-build-system)
5898 `(("r-annotate" ,r-annotate)
5899 ("r-annotationdbi" ,r-annotationdbi)
5900 ("r-biobase" ,r-biobase)
5901 ("r-biocgenerics" ,r-biocgenerics)
5902 ("r-graph" ,r-graph)
5904 (home-page "https://bioconductor.org/packages/GSEABase")
5905 (synopsis "Gene set enrichment data structures and methods")
5907 "This package provides classes and methods to support @dfn{Gene Set
5908 Enrichment Analysis} (GSEA).")
5909 (license license:artistic2.0)))
5911 (define-public r-category
5918 (uri (bioconductor-uri "Category" version))
5921 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
5922 (properties `((upstream-name . "Category")))
5923 (build-system r-build-system)
5925 `(("r-annotate" ,r-annotate)
5926 ("r-annotationdbi" ,r-annotationdbi)
5927 ("r-biobase" ,r-biobase)
5928 ("r-biocgenerics" ,r-biocgenerics)
5929 ("r-genefilter" ,r-genefilter)
5930 ("r-graph" ,r-graph)
5931 ("r-gseabase" ,r-gseabase)
5932 ("r-matrix" ,r-matrix)
5935 (home-page "https://bioconductor.org/packages/Category")
5936 (synopsis "Category analysis")
5938 "This package provides a collection of tools for performing category
5940 (license license:artistic2.0)))
5942 (define-public r-gostats
5949 (uri (bioconductor-uri "GOstats" version))
5952 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
5953 (properties `((upstream-name . "GOstats")))
5954 (build-system r-build-system)
5956 `(("r-annotate" ,r-annotate)
5957 ("r-annotationdbi" ,r-annotationdbi)
5958 ("r-annotationforge" ,r-annotationforge)
5959 ("r-biobase" ,r-biobase)
5960 ("r-category" ,r-category)
5961 ("r-go-db" ,r-go-db)
5962 ("r-graph" ,r-graph)
5963 ("r-rgraphviz" ,r-rgraphviz)
5964 ("r-rbgl" ,r-rbgl)))
5965 (home-page "https://bioconductor.org/packages/GOstats")
5966 (synopsis "Tools for manipulating GO and microarrays")
5968 "This package provides a set of tools for interacting with GO and
5969 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5970 testing and other simple calculations.")
5971 (license license:artistic2.0)))
5973 (define-public r-shortread
5975 (name "r-shortread")
5980 (uri (bioconductor-uri "ShortRead" version))
5983 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
5984 (properties `((upstream-name . "ShortRead")))
5985 (build-system r-build-system)
5989 `(("r-biobase" ,r-biobase)
5990 ("r-biocgenerics" ,r-biocgenerics)
5991 ("r-biocparallel" ,r-biocparallel)
5992 ("r-biostrings" ,r-biostrings)
5993 ("r-genomeinfodb" ,r-genomeinfodb)
5994 ("r-genomicalignments" ,r-genomicalignments)
5995 ("r-genomicranges" ,r-genomicranges)
5996 ("r-hwriter" ,r-hwriter)
5997 ("r-iranges" ,r-iranges)
5998 ("r-lattice" ,r-lattice)
5999 ("r-latticeextra" ,r-latticeextra)
6000 ("r-rsamtools" ,r-rsamtools)
6001 ("r-s4vectors" ,r-s4vectors)
6002 ("r-xvector" ,r-xvector)
6003 ("r-zlibbioc" ,r-zlibbioc)))
6004 (home-page "https://bioconductor.org/packages/ShortRead")
6005 (synopsis "FASTQ input and manipulation tools")
6007 "This package implements sampling, iteration, and input of FASTQ files.
6008 It includes functions for filtering and trimming reads, and for generating a
6009 quality assessment report. Data are represented as
6010 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6011 purposes. The package also contains legacy support for early single-end,
6012 ungapped alignment formats.")
6013 (license license:artistic2.0)))
6015 (define-public r-systempiper
6017 (name "r-systempiper")
6022 (uri (bioconductor-uri "systemPipeR" version))
6025 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6026 (properties `((upstream-name . "systemPipeR")))
6027 (build-system r-build-system)
6029 `(("r-annotate" ,r-annotate)
6030 ("r-batchjobs" ,r-batchjobs)
6031 ("r-biocgenerics" ,r-biocgenerics)
6032 ("r-biostrings" ,r-biostrings)
6033 ("r-deseq2" ,r-deseq2)
6034 ("r-edger" ,r-edger)
6035 ("r-genomicfeatures" ,r-genomicfeatures)
6036 ("r-genomicranges" ,r-genomicranges)
6037 ("r-ggplot2" ,r-ggplot2)
6038 ("r-go-db" ,r-go-db)
6039 ("r-gostats" ,r-gostats)
6040 ("r-limma" ,r-limma)
6041 ("r-pheatmap" ,r-pheatmap)
6042 ("r-rjson" ,r-rjson)
6043 ("r-rsamtools" ,r-rsamtools)
6044 ("r-shortread" ,r-shortread)
6045 ("r-summarizedexperiment" ,r-summarizedexperiment)
6046 ("r-variantannotation" ,r-variantannotation)))
6047 (home-page "https://github.com/tgirke/systemPipeR")
6048 (synopsis "Next generation sequencing workflow and reporting environment")
6050 "This R package provides tools for building and running automated
6051 end-to-end analysis workflows for a wide range of @dfn{next generation
6052 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6053 Important features include a uniform workflow interface across different NGS
6054 applications, automated report generation, and support for running both R and
6055 command-line software, such as NGS aligners or peak/variant callers, on local
6056 computers or compute clusters. Efficient handling of complex sample sets and
6057 experimental designs is facilitated by a consistently implemented sample
6058 annotation infrastructure.")
6059 (license license:artistic2.0)))
6061 (define-public r-grohmm
6068 (uri (bioconductor-uri "groHMM" version))
6071 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6072 (properties `((upstream-name . "groHMM")))
6073 (build-system r-build-system)
6075 `(("r-genomeinfodb" ,r-genomeinfodb)
6076 ("r-genomicalignments" ,r-genomicalignments)
6077 ("r-genomicranges" ,r-genomicranges)
6078 ("r-iranges" ,r-iranges)
6080 ("r-rtracklayer" ,r-rtracklayer)
6081 ("r-s4vectors" ,r-s4vectors)))
6082 (home-page "https://github.com/Kraus-Lab/groHMM")
6083 (synopsis "GRO-seq analysis pipeline")
6085 "This package provides a pipeline for the analysis of GRO-seq data.")
6086 (license license:gpl3+)))
6088 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6090 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6094 ;; We cannot use bioconductor-uri here because this tarball is
6095 ;; located under "data/annotation/" instead of "bioc/".
6096 (uri (string-append "https://bioconductor.org/packages/"
6097 "release/data/annotation/src/contrib"
6098 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6102 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6104 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6105 (build-system r-build-system)
6106 ;; As this package provides little more than a very large data file it
6107 ;; doesn't make sense to build substitutes.
6108 (arguments `(#:substitutable? #f))
6110 `(("r-genomicfeatures" ,r-genomicfeatures)))
6112 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6113 (synopsis "Annotation package for human genome in TxDb format")
6115 "This package provides an annotation database of Homo sapiens genome
6116 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6117 track. The database is exposed as a @code{TxDb} object.")
6118 (license license:artistic2.0)))
6120 (define-public r-sparql
6126 (uri (cran-uri "SPARQL" version))
6129 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6130 (properties `((upstream-name . "SPARQL")))
6131 (build-system r-build-system)
6133 `(("r-rcurl" ,r-rcurl)
6135 (home-page "http://cran.r-project.org/web/packages/SPARQL")
6136 (synopsis "SPARQL client for R")
6137 (description "This package provides an interface to use SPARQL to pose
6138 SELECT or UPDATE queries to an end-point.")
6139 ;; The only license indication is found in the DESCRIPTION file,
6140 ;; which states GPL-3. So we cannot assume GPLv3+.
6141 (license license:gpl3)))
6143 (define-public vsearch
6151 "https://github.com/torognes/vsearch/archive/v"
6153 (file-name (string-append name "-" version ".tar.gz"))
6156 "1z10psrwhflchwzw1fvzwnsn59xglf94qrn7msj93fpnjgafvmks"))
6157 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6160 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6161 ;; for this in the patch.
6162 (delete-file "src/city.h")
6163 (delete-file "src/citycrc.h")
6164 (delete-file "src/city.cc")
6166 (build-system gnu-build-system)
6169 (modify-phases %standard-phases
6170 (add-after 'unpack 'autogen
6171 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6175 ("cityhash" ,cityhash)))
6177 `(("autoconf" ,autoconf)
6178 ("automake" ,automake)))
6179 (synopsis "Sequence search tools for metagenomics")
6181 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6182 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6183 masking. The tool takes advantage of parallelism in the form of SIMD
6184 vectorization as well as multiple threads to perform accurate alignments at
6185 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6186 Needleman-Wunsch).")
6187 (home-page "https://github.com/torognes/vsearch")
6188 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6190 (supported-systems '("x86_64-linux"))
6191 ;; Dual licensed; also includes public domain source.
6192 (license (list license:gpl3 license:bsd-2))))
6194 (define-public pardre
6197 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6202 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6206 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6207 (build-system gnu-build-system)
6209 `(#:tests? #f ; no tests included
6211 (modify-phases %standard-phases
6214 (lambda* (#:key outputs #:allow-other-keys)
6215 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6216 (install-file "ParDRe" bin)
6219 `(("openmpi" ,openmpi)
6221 (synopsis "Parallel tool to remove duplicate DNA reads")
6223 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6224 Duplicate reads can be seen as identical or nearly identical sequences with
6225 some mismatches. This tool lets users avoid the analysis of unnecessary
6226 reads, reducing the time of subsequent procedures with the
6227 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6228 in order to exploit the parallel capabilities of multicore clusters. It is
6229 faster than multithreaded counterparts (end of 2015) for the same number of
6230 cores and, thanks to the message-passing technology, it can be executed on
6232 (home-page "https://sourceforge.net/projects/pardre/")
6233 (license license:gpl3+)))
6235 (define-public ruby-bio-kseq
6237 (name "ruby-bio-kseq")
6242 (uri (rubygems-uri "bio-kseq" version))
6245 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6246 (build-system ruby-build-system)
6248 `(#:test-target "spec"))
6250 `(("bundler" ,bundler)
6251 ("ruby-rspec" ,ruby-rspec)
6252 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6255 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6257 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6258 FASTQ parsing code. It provides a fast iterator over sequences and their
6260 (home-page "https://github.com/gusevfe/bio-kseq")
6261 (license license:expat)))
6263 (define-public bio-locus
6270 (uri (rubygems-uri "bio-locus" version))
6273 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6274 (build-system ruby-build-system)
6276 `(("ruby-rspec" ,ruby-rspec)))
6277 (synopsis "Tool for fast querying of genome locations")
6279 "Bio-locus is a tabix-like tool for fast querying of genome
6280 locations. Many file formats in bioinformatics contain records that
6281 start with a chromosome name and a position for a SNP, or a start-end
6282 position for indels. Bio-locus allows users to store this chr+pos or
6283 chr+pos+alt information in a database.")
6284 (home-page "https://github.com/pjotrp/bio-locus")
6285 (license license:expat)))
6287 (define-public bio-blastxmlparser
6289 (name "bio-blastxmlparser")
6293 (uri (rubygems-uri "bio-blastxmlparser" version))
6296 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6297 (build-system ruby-build-system)
6299 `(("ruby-bio-logger" ,ruby-bio-logger)
6300 ("ruby-nokogiri" ,ruby-nokogiri)))
6302 `(("ruby-rspec" ,ruby-rspec)))
6303 (synopsis "Fast big data BLAST XML parser and library")
6305 "Very fast parallel big-data BLAST XML file parser which can be used as
6306 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6307 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6308 (home-page "https://github.com/pjotrp/blastxmlparser")
6309 (license license:expat)))
6311 (define-public bioruby
6318 (uri (rubygems-uri "bio" version))
6321 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6322 (build-system ruby-build-system)
6324 `(("ruby-libxml" ,ruby-libxml)))
6326 `(("which" ,which))) ; required for test phase
6329 (modify-phases %standard-phases
6330 (add-before 'build 'patch-test-command
6332 (substitute* '("test/functional/bio/test_command.rb")
6333 (("/bin/sh") (which "sh")))
6334 (substitute* '("test/functional/bio/test_command.rb")
6335 (("/bin/ls") (which "ls")))
6336 (substitute* '("test/functional/bio/test_command.rb")
6337 (("which") (which "which")))
6338 (substitute* '("test/functional/bio/test_command.rb",
6339 "test/data/command/echoarg2.sh")
6340 (("/bin/echo") (which "echo")))
6342 (synopsis "Ruby library, shell and utilities for bioinformatics")
6343 (description "BioRuby comes with a comprehensive set of Ruby development
6344 tools and libraries for bioinformatics and molecular biology. BioRuby has
6345 components for sequence analysis, pathway analysis, protein modelling and
6346 phylogenetic analysis; it supports many widely used data formats and provides
6347 easy access to databases, external programs and public web services, including
6348 BLAST, KEGG, GenBank, MEDLINE and GO.")
6349 (home-page "http://bioruby.org/")
6350 ;; Code is released under Ruby license, except for setup
6351 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6352 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6354 (define-public r-acsnminer
6356 (name "r-acsnminer")
6357 (version "0.16.8.25")
6360 (uri (cran-uri "ACSNMineR" version))
6363 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6364 (properties `((upstream-name . "ACSNMineR")))
6365 (build-system r-build-system)
6367 `(("r-ggplot2" ,r-ggplot2)
6368 ("r-gridextra" ,r-gridextra)))
6369 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6370 (synopsis "Gene enrichment analysis")
6372 "This package provides tools to compute and represent gene set enrichment
6373 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6374 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6375 enrichment can be run with hypergeometric test or Fisher exact test, and can
6376 use multiple corrections. Visualization of data can be done either by
6377 barplots or heatmaps.")
6378 (license license:gpl2+)))
6380 (define-public r-biocgenerics
6382 (name "r-biocgenerics")
6386 (uri (bioconductor-uri "BiocGenerics" version))
6389 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6391 `((upstream-name . "BiocGenerics")))
6392 (build-system r-build-system)
6393 (home-page "https://bioconductor.org/packages/BiocGenerics")
6394 (synopsis "S4 generic functions for Bioconductor")
6396 "This package provides S4 generic functions needed by many Bioconductor
6398 (license license:artistic2.0)))
6400 (define-public r-biocinstaller
6402 (name "r-biocinstaller")
6406 (uri (bioconductor-uri "BiocInstaller" version))
6409 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6411 `((upstream-name . "BiocInstaller")))
6412 (build-system r-build-system)
6413 (home-page "https://bioconductor.org/packages/BiocInstaller")
6414 (synopsis "Install Bioconductor packages")
6415 (description "This package is used to install and update R packages from
6416 Bioconductor, CRAN, and Github.")
6417 (license license:artistic2.0)))
6419 (define-public r-biocviews
6421 (name "r-biocviews")
6425 (uri (bioconductor-uri "biocViews" version))
6428 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6430 `((upstream-name . "biocViews")))
6431 (build-system r-build-system)
6433 `(("r-biobase" ,r-biobase)
6434 ("r-graph" ,r-graph)
6436 ("r-rcurl" ,r-rcurl)
6438 ("r-runit" ,r-runit)))
6439 (home-page "https://bioconductor.org/packages/biocViews")
6440 (synopsis "Bioconductor package categorization helper")
6441 (description "The purpose of biocViews is to create HTML pages that
6442 categorize packages in a Bioconductor package repository according to keywords,
6443 also known as views, in a controlled vocabulary.")
6444 (license license:artistic2.0)))
6446 (define-public r-bookdown
6452 (uri (cran-uri "bookdown" version))
6455 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
6456 (build-system r-build-system)
6458 `(("r-htmltools" ,r-htmltools)
6459 ("r-knitr" ,r-knitr)
6460 ("r-rmarkdown" ,r-rmarkdown)
6461 ("r-yaml" ,r-yaml)))
6462 (home-page "https://github.com/rstudio/bookdown")
6463 (synopsis "Authoring books and technical documents with R markdown")
6464 (description "This package provides output formats and utilities for
6465 authoring books and technical documents with R Markdown.")
6466 (license license:gpl3)))
6468 (define-public r-biocstyle
6470 (name "r-biocstyle")
6474 (uri (bioconductor-uri "BiocStyle" version))
6477 "05f2j9fx8s5gh4f8qkl6wcz32ghz04wxhqb3xxcn1bj24qd7x1x8"))))
6479 `((upstream-name . "BiocStyle")))
6480 (build-system r-build-system)
6482 `(("r-bookdown" ,r-bookdown)
6483 ("r-knitr" ,r-knitr)
6484 ("r-rmarkdown" ,r-rmarkdown)
6485 ("r-yaml" ,r-yaml)))
6486 (home-page "https://bioconductor.org/packages/BiocStyle")
6487 (synopsis "Bioconductor formatting styles")
6488 (description "This package provides standard formatting styles for
6489 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6491 (license license:artistic2.0)))
6493 (define-public r-bioccheck
6495 (name "r-bioccheck")
6499 (uri (bioconductor-uri "BiocCheck" version))
6502 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6504 `((upstream-name . "BiocCheck")))
6505 (build-system r-build-system)
6508 (modify-phases %standard-phases
6509 ;; This package can be used by calling BiocCheck(<package>) from
6510 ;; within R, or by running R CMD BiocCheck <package>. This phase
6511 ;; makes sure the latter works. For this to work, the BiocCheck
6512 ;; script must be somewhere on the PATH (not the R bin directory).
6513 (add-after 'install 'install-bioccheck-subcommand
6514 (lambda* (#:key outputs #:allow-other-keys)
6515 (let* ((out (assoc-ref outputs "out"))
6516 (dest-dir (string-append out "/bin"))
6518 (string-append out "/site-library/BiocCheck/script/")))
6520 (symlink (string-append script-dir "/checkBadDeps.R")
6521 (string-append dest-dir "/checkBadDeps.R"))
6522 (symlink (string-append script-dir "/BiocCheck")
6523 (string-append dest-dir "/BiocCheck")))
6526 `(("r-codetools" ,r-codetools)
6527 ("r-graph" ,r-graph)
6529 ("r-optparse" ,r-optparse)
6530 ("r-biocinstaller" ,r-biocinstaller)
6531 ("r-biocviews" ,r-biocviews)
6532 ("r-stringdist" ,r-stringdist)))
6533 (home-page "https://bioconductor.org/packages/BiocCheck")
6534 (synopsis "Executes Bioconductor-specific package checks")
6535 (description "This package contains tools to perform additional quality
6536 checks on R packages that are to be submitted to the Bioconductor repository.")
6537 (license license:artistic2.0)))
6539 (define-public r-getopt
6546 (uri (cran-uri "getopt" version))
6549 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6550 (build-system r-build-system)
6551 (home-page "https://github.com/trevorld/getopt")
6552 (synopsis "Command-line option processor for R")
6554 "This package is designed to be used with Rscript to write shebang
6555 scripts that accept short and long options. Many users will prefer to
6556 use the packages @code{optparse} or @code{argparse} which add extra
6557 features like automatically generated help options and usage texts,
6558 support for default values, positional argument support, etc.")
6559 (license license:gpl2+)))
6561 (define-public r-optparse
6568 (uri (cran-uri "optparse" version))
6571 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6572 (build-system r-build-system)
6574 `(("r-getopt" ,r-getopt)))
6576 "https://github.com/trevorld/optparse")
6577 (synopsis "Command line option parser")
6579 "This package provides a command line parser inspired by Python's
6580 @code{optparse} library to be used with Rscript to write shebang scripts
6581 that accept short and long options.")
6582 (license license:gpl2+)))
6584 (define-public r-dnacopy
6590 (uri (bioconductor-uri "DNAcopy" version))
6593 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6595 `((upstream-name . "DNAcopy")))
6596 (build-system r-build-system)
6598 `(("gfortran" ,gfortran)))
6599 (home-page "https://bioconductor.org/packages/DNAcopy")
6600 (synopsis "Implementation of a circular binary segmentation algorithm")
6601 (description "This package implements the circular binary segmentation (CBS)
6602 algorithm to segment DNA copy number data and identify genomic regions with
6603 abnormal copy number.")
6604 (license license:gpl2+)))
6606 (define-public r-s4vectors
6608 (name "r-s4vectors")
6612 (uri (bioconductor-uri "S4Vectors" version))
6615 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6617 `((upstream-name . "S4Vectors")))
6618 (build-system r-build-system)
6620 `(("r-biocgenerics" ,r-biocgenerics)))
6621 (home-page "https://bioconductor.org/packages/S4Vectors")
6622 (synopsis "S4 implementation of vectors and lists")
6624 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6625 classes and a set of generic functions that extend the semantic of ordinary
6626 vectors and lists in R. Package developers can easily implement vector-like
6627 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6628 In addition, a few low-level concrete subclasses of general interest (e.g.
6629 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6630 S4Vectors package itself.")
6631 (license license:artistic2.0)))
6633 (define-public r-seqinr
6640 (uri (cran-uri "seqinr" version))
6643 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6644 (build-system r-build-system)
6646 `(("r-ade4" ,r-ade4)
6647 ("r-segmented" ,r-segmented)))
6650 (home-page "http://seqinr.r-forge.r-project.org/")
6651 (synopsis "Biological sequences retrieval and analysis")
6653 "This package provides tools for exploratory data analysis and data
6654 visualization of biological sequence (DNA and protein) data. It also includes
6655 utilities for sequence data management under the ACNUC system.")
6656 (license license:gpl2+)))
6658 (define-public r-iranges
6664 (uri (bioconductor-uri "IRanges" version))
6667 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
6669 `((upstream-name . "IRanges")))
6670 (build-system r-build-system)
6672 `(("r-biocgenerics" ,r-biocgenerics)
6673 ("r-s4vectors" ,r-s4vectors)))
6674 (home-page "https://bioconductor.org/packages/IRanges")
6675 (synopsis "Infrastructure for manipulating intervals on sequences")
6677 "This package provides efficient low-level and highly reusable S4 classes
6678 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6679 generally, data that can be organized sequentially (formally defined as
6680 @code{Vector} objects), as well as views on these @code{Vector} objects.
6681 Efficient list-like classes are also provided for storing big collections of
6682 instances of the basic classes. All classes in the package use consistent
6683 naming and share the same rich and consistent \"Vector API\" as much as
6685 (license license:artistic2.0)))
6687 (define-public r-genomeinfodbdata
6689 (name "r-genomeinfodbdata")
6693 ;; We cannot use bioconductor-uri here because this tarball is
6694 ;; located under "data/annotation/" instead of "bioc/".
6695 (uri (string-append "https://bioconductor.org/packages/release/"
6696 "data/annotation/src/contrib/GenomeInfoDbData_"
6700 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6702 `((upstream-name . "GenomeInfoDbData")))
6703 (build-system r-build-system)
6704 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
6705 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6706 (description "This package contains data for mapping between NCBI taxonomy
6707 ID and species. It is used by functions in the GenomeInfoDb package.")
6708 (license license:artistic2.0)))
6710 (define-public r-genomeinfodb
6712 (name "r-genomeinfodb")
6716 (uri (bioconductor-uri "GenomeInfoDb" version))
6719 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
6721 `((upstream-name . "GenomeInfoDb")))
6722 (build-system r-build-system)
6724 `(("r-biocgenerics" ,r-biocgenerics)
6725 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6726 ("r-iranges" ,r-iranges)
6727 ("r-rcurl" ,r-rcurl)
6728 ("r-s4vectors" ,r-s4vectors)))
6729 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
6730 (synopsis "Utilities for manipulating chromosome identifiers")
6732 "This package contains data and functions that define and allow
6733 translation between different chromosome sequence naming conventions (e.g.,
6734 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6735 names in their natural, rather than lexicographic, order.")
6736 (license license:artistic2.0)))
6738 (define-public r-edger
6744 (uri (bioconductor-uri "edgeR" version))
6747 "01qnxwr9rmz8r5ga3hvjk632365ga2aygx71mxkk7jiad2pjznsp"))))
6748 (properties `((upstream-name . "edgeR")))
6749 (build-system r-build-system)
6751 `(("r-limma" ,r-limma)
6752 ("r-locfit" ,r-locfit)
6754 ("r-statmod" ,r-statmod))) ;for estimateDisp
6755 (home-page "http://bioinf.wehi.edu.au/edgeR")
6756 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6757 (description "This package can do differential expression analysis of
6758 RNA-seq expression profiles with biological replication. It implements a range
6759 of statistical methodology based on the negative binomial distributions,
6760 including empirical Bayes estimation, exact tests, generalized linear models
6761 and quasi-likelihood tests. It be applied to differential signal analysis of
6762 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6764 (license license:gpl2+)))
6766 (define-public r-variantannotation
6768 (name "r-variantannotation")
6772 (uri (bioconductor-uri "VariantAnnotation" version))
6775 "1lllp2vgyfbrar1yg28ji7am470hfzrzxm1bgdk68xpnrwcgcl25"))))
6777 `((upstream-name . "VariantAnnotation")))
6781 `(("r-annotationdbi" ,r-annotationdbi)
6782 ("r-biobase" ,r-biobase)
6783 ("r-biocgenerics" ,r-biocgenerics)
6784 ("r-biostrings" ,r-biostrings)
6785 ("r-bsgenome" ,r-bsgenome)
6787 ("r-genomeinfodb" ,r-genomeinfodb)
6788 ("r-genomicfeatures" ,r-genomicfeatures)
6789 ("r-genomicranges" ,r-genomicranges)
6790 ("r-iranges" ,r-iranges)
6791 ("r-summarizedexperiment" ,r-summarizedexperiment)
6792 ("r-rsamtools" ,r-rsamtools)
6793 ("r-rtracklayer" ,r-rtracklayer)
6794 ("r-s4vectors" ,r-s4vectors)
6795 ("r-xvector" ,r-xvector)
6796 ("r-zlibbioc" ,r-zlibbioc)))
6797 (build-system r-build-system)
6798 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6799 (synopsis "Package for annotation of genetic variants")
6800 (description "This R package can annotate variants, compute amino acid
6801 coding changes and predict coding outcomes.")
6802 (license license:artistic2.0)))
6804 (define-public r-limma
6810 (uri (bioconductor-uri "limma" version))
6813 "0a15gsaky0hfrkx8wrrmp0labzxpq6m2hrd33zl206wyas8bqzcs"))))
6814 (build-system r-build-system)
6815 (home-page "http://bioinf.wehi.edu.au/limma")
6816 (synopsis "Package for linear models for microarray and RNA-seq data")
6817 (description "This package can be used for the analysis of gene expression
6818 studies, especially the use of linear models for analysing designed experiments
6819 and the assessment of differential expression. The analysis methods apply to
6820 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6821 (license license:gpl2+)))
6823 (define-public r-xvector
6829 (uri (bioconductor-uri "XVector" version))
6832 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
6834 `((upstream-name . "XVector")))
6835 (build-system r-build-system)
6838 (modify-phases %standard-phases
6839 (add-after 'unpack 'use-system-zlib
6841 (substitute* "DESCRIPTION"
6842 (("zlibbioc, ") ""))
6843 (substitute* "NAMESPACE"
6844 (("import\\(zlibbioc\\)") ""))
6849 `(("r-biocgenerics" ,r-biocgenerics)
6850 ("r-iranges" ,r-iranges)
6851 ("r-s4vectors" ,r-s4vectors)))
6852 (home-page "https://bioconductor.org/packages/XVector")
6853 (synopsis "Representation and manpulation of external sequences")
6855 "This package provides memory efficient S4 classes for storing sequences
6856 \"externally\" (behind an R external pointer, or on disk).")
6857 (license license:artistic2.0)))
6859 (define-public r-genomicranges
6861 (name "r-genomicranges")
6865 (uri (bioconductor-uri "GenomicRanges" version))
6868 "10ra2sjn17h6gilm9iz0cygp9ijpgbirljlc4drwrnivnw9cmi2a"))))
6870 `((upstream-name . "GenomicRanges")))
6871 (build-system r-build-system)
6873 `(("r-biocgenerics" ,r-biocgenerics)
6874 ("r-genomeinfodb" ,r-genomeinfodb)
6875 ("r-iranges" ,r-iranges)
6876 ("r-s4vectors" ,r-s4vectors)
6877 ("r-xvector" ,r-xvector)))
6878 (home-page "https://bioconductor.org/packages/GenomicRanges")
6879 (synopsis "Representation and manipulation of genomic intervals")
6881 "This package provides tools to efficiently represent and manipulate
6882 genomic annotations and alignments is playing a central role when it comes to
6883 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6884 GenomicRanges package defines general purpose containers for storing and
6885 manipulating genomic intervals and variables defined along a genome.")
6886 (license license:artistic2.0)))
6888 (define-public r-biobase
6894 (uri (bioconductor-uri "Biobase" version))
6897 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
6899 `((upstream-name . "Biobase")))
6900 (build-system r-build-system)
6902 `(("r-biocgenerics" ,r-biocgenerics)))
6903 (home-page "https://bioconductor.org/packages/Biobase")
6904 (synopsis "Base functions for Bioconductor")
6906 "This package provides functions that are needed by many other packages
6907 on Bioconductor or which replace R functions.")
6908 (license license:artistic2.0)))
6910 (define-public r-annotationdbi
6912 (name "r-annotationdbi")
6916 (uri (bioconductor-uri "AnnotationDbi" version))
6919 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
6921 `((upstream-name . "AnnotationDbi")))
6922 (build-system r-build-system)
6924 `(("r-biobase" ,r-biobase)
6925 ("r-biocgenerics" ,r-biocgenerics)
6927 ("r-iranges" ,r-iranges)
6928 ("r-rsqlite" ,r-rsqlite)
6929 ("r-s4vectors" ,r-s4vectors)))
6930 (home-page "https://bioconductor.org/packages/AnnotationDbi")
6931 (synopsis "Annotation database interface")
6933 "This package provides user interface and database connection code for
6934 annotation data packages using SQLite data storage.")
6935 (license license:artistic2.0)))
6937 (define-public r-biomart
6943 (uri (bioconductor-uri "biomaRt" version))
6946 "1dn3ysf0vb3mmg2b3380g0j1ajf88x4rh7fddfp990h2xlnsy2cx"))))
6948 `((upstream-name . "biomaRt")))
6949 (build-system r-build-system)
6951 `(("r-annotationdbi" ,r-annotationdbi)
6952 ("r-progress" ,r-progress)
6953 ("r-rcurl" ,r-rcurl)
6954 ("r-stringr" ,r-stringr)
6956 (home-page "https://bioconductor.org/packages/biomaRt")
6957 (synopsis "Interface to BioMart databases")
6959 "biomaRt provides an interface to a growing collection of databases
6960 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6961 package enables retrieval of large amounts of data in a uniform way without
6962 the need to know the underlying database schemas or write complex SQL queries.
6963 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6964 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6965 users direct access to a diverse set of data and enable a wide range of
6966 powerful online queries from gene annotation to database mining.")
6967 (license license:artistic2.0)))
6969 (define-public r-biocparallel
6971 (name "r-biocparallel")
6975 (uri (bioconductor-uri "BiocParallel" version))
6978 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
6980 `((upstream-name . "BiocParallel")))
6981 (build-system r-build-system)
6983 `(("r-futile-logger" ,r-futile-logger)
6986 (home-page "https://bioconductor.org/packages/BiocParallel")
6987 (synopsis "Bioconductor facilities for parallel evaluation")
6989 "This package provides modified versions and novel implementation of
6990 functions for parallel evaluation, tailored to use with Bioconductor
6992 (license (list license:gpl2+ license:gpl3+))))
6994 (define-public r-biostrings
6996 (name "r-biostrings")
7000 (uri (bioconductor-uri "Biostrings" version))
7003 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7005 `((upstream-name . "Biostrings")))
7006 (build-system r-build-system)
7008 `(("r-biocgenerics" ,r-biocgenerics)
7009 ("r-iranges" ,r-iranges)
7010 ("r-s4vectors" ,r-s4vectors)
7011 ("r-xvector" ,r-xvector)))
7012 (home-page "https://bioconductor.org/packages/Biostrings")
7013 (synopsis "String objects and algorithms for biological sequences")
7015 "This package provides memory efficient string containers, string
7016 matching algorithms, and other utilities, for fast manipulation of large
7017 biological sequences or sets of sequences.")
7018 (license license:artistic2.0)))
7020 (define-public r-rsamtools
7022 (name "r-rsamtools")
7026 (uri (bioconductor-uri "Rsamtools" version))
7029 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7031 `((upstream-name . "Rsamtools")))
7032 (build-system r-build-system)
7035 (modify-phases %standard-phases
7036 (add-after 'unpack 'use-system-zlib
7038 (substitute* "DESCRIPTION"
7039 (("zlibbioc, ") ""))
7040 (substitute* "NAMESPACE"
7041 (("import\\(zlibbioc\\)") ""))
7046 `(("r-biocgenerics" ,r-biocgenerics)
7047 ("r-biocparallel" ,r-biocparallel)
7048 ("r-biostrings" ,r-biostrings)
7049 ("r-bitops" ,r-bitops)
7050 ("r-genomeinfodb" ,r-genomeinfodb)
7051 ("r-genomicranges" ,r-genomicranges)
7052 ("r-iranges" ,r-iranges)
7053 ("r-s4vectors" ,r-s4vectors)
7054 ("r-xvector" ,r-xvector)))
7055 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7056 (synopsis "Interface to samtools, bcftools, and tabix")
7058 "This package provides an interface to the 'samtools', 'bcftools', and
7059 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7060 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7062 (license license:expat)))
7064 (define-public r-delayedarray
7066 (name "r-delayedarray")
7070 (uri (bioconductor-uri "DelayedArray" version))
7073 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7075 `((upstream-name . "DelayedArray")))
7076 (build-system r-build-system)
7078 `(("r-biocgenerics" ,r-biocgenerics)
7079 ("r-s4vectors" ,r-s4vectors)
7080 ("r-iranges" ,r-iranges)
7081 ("r-matrixstats" ,r-matrixstats)))
7082 (home-page "https://bioconductor.org/packages/DelayedArray")
7083 (synopsis "Delayed operations on array-like objects")
7085 "Wrapping an array-like object (typically an on-disk object) in a
7086 @code{DelayedArray} object allows one to perform common array operations on it
7087 without loading the object in memory. In order to reduce memory usage and
7088 optimize performance, operations on the object are either delayed or executed
7089 using a block processing mechanism. Note that this also works on in-memory
7090 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7091 @code{Matrix} objects, and ordinary arrays and data frames.")
7092 (license license:artistic2.0)))
7094 (define-public r-summarizedexperiment
7096 (name "r-summarizedexperiment")
7100 (uri (bioconductor-uri "SummarizedExperiment" version))
7103 "1011r8l0k8420j31bmh4xdcp6ka5bzf4bqhip84v5b6alpkcbvmf"))))
7105 `((upstream-name . "SummarizedExperiment")))
7106 (build-system r-build-system)
7108 `(("r-biobase" ,r-biobase)
7109 ("r-biocgenerics" ,r-biocgenerics)
7110 ("r-delayedarray" ,r-delayedarray)
7111 ("r-genomeinfodb" ,r-genomeinfodb)
7112 ("r-genomicranges" ,r-genomicranges)
7113 ("r-iranges" ,r-iranges)
7114 ("r-matrix" ,r-matrix)
7115 ("r-s4vectors" ,r-s4vectors)))
7116 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7117 (synopsis "Container for representing genomic ranges by sample")
7119 "The SummarizedExperiment container contains one or more assays, each
7120 represented by a matrix-like object of numeric or other mode. The rows
7121 typically represent genomic ranges of interest and the columns represent
7123 (license license:artistic2.0)))
7125 (define-public r-genomicalignments
7127 (name "r-genomicalignments")
7131 (uri (bioconductor-uri "GenomicAlignments" version))
7134 "0sw30lj11wv7ifzypqm04lcah987crqwvj48wz3flaw3biw41zfi"))))
7136 `((upstream-name . "GenomicAlignments")))
7137 (build-system r-build-system)
7139 `(("r-biocgenerics" ,r-biocgenerics)
7140 ("r-biocparallel" ,r-biocparallel)
7141 ("r-biostrings" ,r-biostrings)
7142 ("r-genomeinfodb" ,r-genomeinfodb)
7143 ("r-genomicranges" ,r-genomicranges)
7144 ("r-iranges" ,r-iranges)
7145 ("r-rsamtools" ,r-rsamtools)
7146 ("r-s4vectors" ,r-s4vectors)
7147 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7148 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7149 (synopsis "Representation and manipulation of short genomic alignments")
7151 "This package provides efficient containers for storing and manipulating
7152 short genomic alignments (typically obtained by aligning short reads to a
7153 reference genome). This includes read counting, computing the coverage,
7154 junction detection, and working with the nucleotide content of the
7156 (license license:artistic2.0)))
7158 (define-public r-rtracklayer
7160 (name "r-rtracklayer")
7164 (uri (bioconductor-uri "rtracklayer" version))
7167 "12al1ygzy9p4myxa1fd817m28x2fj6f863znk9bw3hp7knbi98dh"))))
7168 (build-system r-build-system)
7171 (modify-phases %standard-phases
7172 (add-after 'unpack 'use-system-zlib
7174 (substitute* "DESCRIPTION"
7175 ((" zlibbioc,") ""))
7176 (substitute* "NAMESPACE"
7177 (("import\\(zlibbioc\\)") ""))
7182 `(("r-biocgenerics" ,r-biocgenerics)
7183 ("r-biostrings" ,r-biostrings)
7184 ("r-genomeinfodb" ,r-genomeinfodb)
7185 ("r-genomicalignments" ,r-genomicalignments)
7186 ("r-genomicranges" ,r-genomicranges)
7187 ("r-iranges" ,r-iranges)
7188 ("r-rcurl" ,r-rcurl)
7189 ("r-rsamtools" ,r-rsamtools)
7190 ("r-s4vectors" ,r-s4vectors)
7192 ("r-xvector" ,r-xvector)))
7193 (home-page "https://bioconductor.org/packages/rtracklayer")
7194 (synopsis "R interface to genome browsers and their annotation tracks")
7196 "rtracklayer is an extensible framework for interacting with multiple
7197 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7198 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7199 built-in). The user may export/import tracks to/from the supported browsers,
7200 as well as query and modify the browser state, such as the current viewport.")
7201 (license license:artistic2.0)))
7203 (define-public r-genomicfeatures
7205 (name "r-genomicfeatures")
7209 (uri (bioconductor-uri "GenomicFeatures" version))
7212 "1khjvq1ffhqavkwf8n7bilknci60lxbg52icrcf2vnb9k8rlpghs"))))
7214 `((upstream-name . "GenomicFeatures")))
7215 (build-system r-build-system)
7217 `(("r-annotationdbi" ,r-annotationdbi)
7218 ("r-biobase" ,r-biobase)
7219 ("r-biocgenerics" ,r-biocgenerics)
7220 ("r-biomart" ,r-biomart)
7221 ("r-biostrings" ,r-biostrings)
7223 ("r-genomeinfodb" ,r-genomeinfodb)
7224 ("r-genomicranges" ,r-genomicranges)
7225 ("r-iranges" ,r-iranges)
7226 ("r-rcurl" ,r-rcurl)
7227 ("r-rsqlite" ,r-rsqlite)
7228 ("r-rmysql" ,r-rmysql)
7229 ("r-rtracklayer" ,r-rtracklayer)
7230 ("r-s4vectors" ,r-s4vectors)
7231 ("r-xvector" ,r-xvector)))
7232 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7233 (synopsis "Tools for working with transcript centric annotations")
7235 "This package provides a set of tools and methods for making and
7236 manipulating transcript centric annotations. With these tools the user can
7237 easily download the genomic locations of the transcripts, exons and cds of a
7238 given organism, from either the UCSC Genome Browser or a BioMart
7239 database (more sources will be supported in the future). This information is
7240 then stored in a local database that keeps track of the relationship between
7241 transcripts, exons, cds and genes. Flexible methods are provided for
7242 extracting the desired features in a convenient format.")
7243 (license license:artistic2.0)))
7245 (define-public r-go-db
7251 (uri (string-append "https://www.bioconductor.org/packages/"
7252 "release/data/annotation/src/contrib/GO.db_"
7256 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7258 `((upstream-name . "GO.db")))
7259 (build-system r-build-system)
7261 `(("r-annotationdbi" ,r-annotationdbi)))
7262 (home-page "https://bioconductor.org/packages/GO.db")
7263 (synopsis "Annotation maps describing the entire Gene Ontology")
7265 "The purpose of this GO.db annotation package is to provide detailed
7266 information about the latest version of the Gene Ontologies.")
7267 (license license:artistic2.0)))
7269 (define-public r-graph
7275 (uri (bioconductor-uri "graph" version))
7278 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7279 (build-system r-build-system)
7281 `(("r-biocgenerics" ,r-biocgenerics)))
7282 (home-page "https://bioconductor.org/packages/graph")
7283 (synopsis "Handle graph data structures in R")
7285 "This package implements some simple graph handling capabilities for R.")
7286 (license license:artistic2.0)))
7288 (define-public r-topgo
7294 (uri (bioconductor-uri "topGO" version))
7297 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
7299 `((upstream-name . "topGO")))
7300 (build-system r-build-system)
7302 `(("r-annotationdbi" ,r-annotationdbi)
7304 ("r-biobase" ,r-biobase)
7305 ("r-biocgenerics" ,r-biocgenerics)
7306 ("r-go-db" ,r-go-db)
7307 ("r-graph" ,r-graph)
7308 ("r-lattice" ,r-lattice)
7309 ("r-matrixstats" ,r-matrixstats)
7310 ("r-sparsem" ,r-sparsem)))
7311 (home-page "https://bioconductor.org/packages/topGO")
7312 (synopsis "Enrichment analysis for gene ontology")
7314 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7315 terms while accounting for the topology of the GO graph. Different test
7316 statistics and different methods for eliminating local similarities and
7317 dependencies between GO terms can be implemented and applied.")
7318 ;; Any version of the LGPL applies.
7319 (license license:lgpl2.1+)))
7321 (define-public r-bsgenome
7327 (uri (bioconductor-uri "BSgenome" version))
7330 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7332 `((upstream-name . "BSgenome")))
7333 (build-system r-build-system)
7335 `(("r-biocgenerics" ,r-biocgenerics)
7336 ("r-biostrings" ,r-biostrings)
7337 ("r-genomeinfodb" ,r-genomeinfodb)
7338 ("r-genomicranges" ,r-genomicranges)
7339 ("r-iranges" ,r-iranges)
7340 ("r-rsamtools" ,r-rsamtools)
7341 ("r-rtracklayer" ,r-rtracklayer)
7342 ("r-s4vectors" ,r-s4vectors)
7343 ("r-xvector" ,r-xvector)))
7344 (home-page "https://bioconductor.org/packages/BSgenome")
7345 (synopsis "Infrastructure for Biostrings-based genome data packages")
7347 "This package provides infrastructure shared by all Biostrings-based
7348 genome data packages and support for efficient SNP representation.")
7349 (license license:artistic2.0)))
7351 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7353 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7357 ;; We cannot use bioconductor-uri here because this tarball is
7358 ;; located under "data/annotation/" instead of "bioc/".
7359 (uri (string-append "https://www.bioconductor.org/packages/"
7360 "release/data/annotation/src/contrib/"
7361 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7365 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7367 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7368 (build-system r-build-system)
7369 ;; As this package provides little more than a very large data file it
7370 ;; doesn't make sense to build substitutes.
7371 (arguments `(#:substitutable? #f))
7373 `(("r-bsgenome" ,r-bsgenome)))
7375 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7376 (synopsis "Full genome sequences for Homo sapiens")
7378 "This package provides full genome sequences for Homo sapiens from
7379 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7380 (license license:artistic2.0)))
7382 (define-public r-impute
7388 (uri (bioconductor-uri "impute" version))
7391 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7393 `(("gfortran" ,gfortran)))
7394 (build-system r-build-system)
7395 (home-page "https://bioconductor.org/packages/impute")
7396 (synopsis "Imputation for microarray data")
7398 "This package provides a function to impute missing gene expression
7399 microarray data, using nearest neighbor averaging.")
7400 (license license:gpl2+)))
7402 (define-public r-seqpattern
7404 (name "r-seqpattern")
7408 (uri (bioconductor-uri "seqPattern" version))
7411 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7413 `((upstream-name . "seqPattern")))
7414 (build-system r-build-system)
7416 `(("r-biostrings" ,r-biostrings)
7417 ("r-genomicranges" ,r-genomicranges)
7418 ("r-iranges" ,r-iranges)
7419 ("r-kernsmooth" ,r-kernsmooth)
7420 ("r-plotrix" ,r-plotrix)))
7421 (home-page "https://bioconductor.org/packages/seqPattern")
7422 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7424 "This package provides tools to visualize oligonucleotide patterns and
7425 sequence motif occurrences across a large set of sequences centred at a common
7426 reference point and sorted by a user defined feature.")
7427 (license license:gpl3+)))
7429 (define-public r-genomation
7431 (name "r-genomation")
7435 (uri (bioconductor-uri "genomation" version))
7438 "1ddd8c9w1f1i1ga9rpbwiic8rsaws1chdxx4j38bpyaiy4zhz1ca"))))
7439 (build-system r-build-system)
7441 `(("r-biostrings" ,r-biostrings)
7442 ("r-bsgenome" ,r-bsgenome)
7443 ("r-data-table" ,r-data-table)
7444 ("r-genomeinfodb" ,r-genomeinfodb)
7445 ("r-genomicalignments" ,r-genomicalignments)
7446 ("r-genomicranges" ,r-genomicranges)
7447 ("r-ggplot2" ,r-ggplot2)
7448 ("r-gridbase" ,r-gridbase)
7449 ("r-impute" ,r-impute)
7450 ("r-iranges" ,r-iranges)
7451 ("r-matrixstats" ,r-matrixstats)
7452 ("r-plotrix" ,r-plotrix)
7455 ("r-readr" ,r-readr)
7456 ("r-reshape2" ,r-reshape2)
7457 ("r-rsamtools" ,r-rsamtools)
7458 ("r-rtracklayer" ,r-rtracklayer)
7459 ("r-runit" ,r-runit)
7460 ("r-s4vectors" ,r-s4vectors)
7461 ("r-seqpattern" ,r-seqpattern)))
7462 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7463 (synopsis "Summary, annotation and visualization of genomic data")
7465 "This package provides a package for summary and annotation of genomic
7466 intervals. Users can visualize and quantify genomic intervals over
7467 pre-defined functional regions, such as promoters, exons, introns, etc. The
7468 genomic intervals represent regions with a defined chromosome position, which
7469 may be associated with a score, such as aligned reads from HT-seq experiments,
7470 TF binding sites, methylation scores, etc. The package can use any tabular
7471 genomic feature data as long as it has minimal information on the locations of
7472 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7473 (license license:artistic2.0)))
7475 (define-public r-genomationdata
7477 (name "r-genomationdata")
7481 ;; We cannot use bioconductor-uri here because this tarball is
7482 ;; located under "data/annotation/" instead of "bioc/".
7483 (uri (string-append "https://bioconductor.org/packages/"
7484 "release/data/experiment/src/contrib/"
7485 "genomationData_" version ".tar.gz"))
7488 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7489 (build-system r-build-system)
7490 ;; As this package provides little more than large data files, it doesn't
7491 ;; make sense to build substitutes.
7492 (arguments `(#:substitutable? #f))
7494 `(("r-knitr" ,r-knitr)))
7495 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7496 (synopsis "Experimental data for use with the genomation package")
7498 "This package contains experimental genetic data for use with the
7499 genomation package. Included are Chip Seq, Methylation and Cage data,
7500 downloaded from Encode.")
7501 (license license:gpl3+)))
7503 (define-public r-org-hs-eg-db
7505 (name "r-org-hs-eg-db")
7509 ;; We cannot use bioconductor-uri here because this tarball is
7510 ;; located under "data/annotation/" instead of "bioc/".
7511 (uri (string-append "https://www.bioconductor.org/packages/"
7512 "release/data/annotation/src/contrib/"
7513 "org.Hs.eg.db_" version ".tar.gz"))
7516 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7518 `((upstream-name . "org.Hs.eg.db")))
7519 (build-system r-build-system)
7521 `(("r-annotationdbi" ,r-annotationdbi)))
7522 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7523 (synopsis "Genome wide annotation for Human")
7525 "This package provides mappings from Entrez gene identifiers to various
7526 annotations for the human genome.")
7527 (license license:artistic2.0)))
7529 (define-public r-org-ce-eg-db
7531 (name "r-org-ce-eg-db")
7535 ;; We cannot use bioconductor-uri here because this tarball is
7536 ;; located under "data/annotation/" instead of "bioc/".
7537 (uri (string-append "https://www.bioconductor.org/packages/"
7538 "release/data/annotation/src/contrib/"
7539 "org.Ce.eg.db_" version ".tar.gz"))
7542 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7544 `((upstream-name . "org.Ce.eg.db")))
7545 (build-system r-build-system)
7547 `(("r-annotationdbi" ,r-annotationdbi)))
7548 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7549 (synopsis "Genome wide annotation for Worm")
7551 "This package provides mappings from Entrez gene identifiers to various
7552 annotations for the genome of the model worm Caenorhabditis elegans.")
7553 (license license:artistic2.0)))
7555 (define-public r-org-dm-eg-db
7557 (name "r-org-dm-eg-db")
7561 ;; We cannot use bioconductor-uri here because this tarball is
7562 ;; located under "data/annotation/" instead of "bioc/".
7563 (uri (string-append "https://www.bioconductor.org/packages/"
7564 "release/data/annotation/src/contrib/"
7565 "org.Dm.eg.db_" version ".tar.gz"))
7568 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7570 `((upstream-name . "org.Dm.eg.db")))
7571 (build-system r-build-system)
7573 `(("r-annotationdbi" ,r-annotationdbi)))
7574 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7575 (synopsis "Genome wide annotation for Fly")
7577 "This package provides mappings from Entrez gene identifiers to various
7578 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7579 (license license:artistic2.0)))
7581 (define-public r-org-mm-eg-db
7583 (name "r-org-mm-eg-db")
7587 ;; We cannot use bioconductor-uri here because this tarball is
7588 ;; located under "data/annotation/" instead of "bioc/".
7589 (uri (string-append "https://www.bioconductor.org/packages/"
7590 "release/data/annotation/src/contrib/"
7591 "org.Mm.eg.db_" version ".tar.gz"))
7594 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7596 `((upstream-name . "org.Mm.eg.db")))
7597 (build-system r-build-system)
7599 `(("r-annotationdbi" ,r-annotationdbi)))
7600 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7601 (synopsis "Genome wide annotation for Mouse")
7603 "This package provides mappings from Entrez gene identifiers to various
7604 annotations for the genome of the model mouse Mus musculus.")
7605 (license license:artistic2.0)))
7607 (define-public r-seqlogo
7614 (uri (bioconductor-uri "seqLogo" version))
7617 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7618 (properties `((upstream-name . "seqLogo")))
7619 (build-system r-build-system)
7620 (home-page "https://bioconductor.org/packages/seqLogo")
7621 (synopsis "Sequence logos for DNA sequence alignments")
7623 "seqLogo takes the position weight matrix of a DNA sequence motif and
7624 plots the corresponding sequence logo as introduced by Schneider and
7626 (license license:lgpl2.0+)))
7628 (define-public r-bsgenome-hsapiens-ucsc-hg19
7630 (name "r-bsgenome-hsapiens-ucsc-hg19")
7634 ;; We cannot use bioconductor-uri here because this tarball is
7635 ;; located under "data/annotation/" instead of "bioc/".
7636 (uri (string-append "https://www.bioconductor.org/packages/"
7637 "release/data/annotation/src/contrib/"
7638 "BSgenome.Hsapiens.UCSC.hg19_"
7642 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7644 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7645 (build-system r-build-system)
7646 ;; As this package provides little more than a very large data file it
7647 ;; doesn't make sense to build substitutes.
7648 (arguments `(#:substitutable? #f))
7650 `(("r-bsgenome" ,r-bsgenome)))
7652 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7653 (synopsis "Full genome sequences for Homo sapiens")
7655 "This package provides full genome sequences for Homo sapiens as provided
7656 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7657 (license license:artistic2.0)))
7659 (define-public r-bsgenome-mmusculus-ucsc-mm9
7661 (name "r-bsgenome-mmusculus-ucsc-mm9")
7665 ;; We cannot use bioconductor-uri here because this tarball is
7666 ;; located under "data/annotation/" instead of "bioc/".
7667 (uri (string-append "https://www.bioconductor.org/packages/"
7668 "release/data/annotation/src/contrib/"
7669 "BSgenome.Mmusculus.UCSC.mm9_"
7673 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7675 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7676 (build-system r-build-system)
7677 ;; As this package provides little more than a very large data file it
7678 ;; doesn't make sense to build substitutes.
7679 (arguments `(#:substitutable? #f))
7681 `(("r-bsgenome" ,r-bsgenome)))
7683 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7684 (synopsis "Full genome sequences for Mouse")
7686 "This package provides full genome sequences for Mus musculus (Mouse) as
7687 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7688 (license license:artistic2.0)))
7690 (define-public r-bsgenome-mmusculus-ucsc-mm10
7692 (name "r-bsgenome-mmusculus-ucsc-mm10")
7696 ;; We cannot use bioconductor-uri here because this tarball is
7697 ;; located under "data/annotation/" instead of "bioc/".
7698 (uri (string-append "https://www.bioconductor.org/packages/"
7699 "release/data/annotation/src/contrib/"
7700 "BSgenome.Mmusculus.UCSC.mm10_"
7704 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7706 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7707 (build-system r-build-system)
7708 ;; As this package provides little more than a very large data file it
7709 ;; doesn't make sense to build substitutes.
7710 (arguments `(#:substitutable? #f))
7712 `(("r-bsgenome" ,r-bsgenome)))
7714 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7715 (synopsis "Full genome sequences for Mouse")
7717 "This package provides full genome sequences for Mus
7718 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7719 in Biostrings objects.")
7720 (license license:artistic2.0)))
7722 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7724 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7728 ;; We cannot use bioconductor-uri here because this tarball is
7729 ;; located under "data/annotation/" instead of "bioc/".
7730 (uri (string-append "https://www.bioconductor.org/packages/"
7731 "release/data/annotation/src/contrib/"
7732 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7736 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7738 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7739 (build-system r-build-system)
7740 ;; As this package provides little more than a very large data file it
7741 ;; doesn't make sense to build substitutes.
7742 (arguments `(#:substitutable? #f))
7744 `(("r-bsgenome" ,r-bsgenome)
7745 ("r-genomicfeatures" ,r-genomicfeatures)
7746 ("r-annotationdbi" ,r-annotationdbi)))
7748 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7749 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7751 "This package loads a TxDb object, which is an R interface to
7752 prefabricated databases contained in this package. This package provides
7753 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7754 based on the knownGene track.")
7755 (license license:artistic2.0)))
7757 (define-public r-bsgenome-celegans-ucsc-ce6
7759 (name "r-bsgenome-celegans-ucsc-ce6")
7763 ;; We cannot use bioconductor-uri here because this tarball is
7764 ;; located under "data/annotation/" instead of "bioc/".
7765 (uri (string-append "https://www.bioconductor.org/packages/"
7766 "release/data/annotation/src/contrib/"
7767 "BSgenome.Celegans.UCSC.ce6_"
7771 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7773 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7774 (build-system r-build-system)
7775 ;; As this package provides little more than a very large data file it
7776 ;; doesn't make sense to build substitutes.
7777 (arguments `(#:substitutable? #f))
7779 `(("r-bsgenome" ,r-bsgenome)))
7781 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7782 (synopsis "Full genome sequences for Worm")
7784 "This package provides full genome sequences for Caenorhabditis
7785 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7787 (license license:artistic2.0)))
7789 (define-public r-bsgenome-celegans-ucsc-ce10
7791 (name "r-bsgenome-celegans-ucsc-ce10")
7795 ;; We cannot use bioconductor-uri here because this tarball is
7796 ;; located under "data/annotation/" instead of "bioc/".
7797 (uri (string-append "https://www.bioconductor.org/packages/"
7798 "release/data/annotation/src/contrib/"
7799 "BSgenome.Celegans.UCSC.ce10_"
7803 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7805 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7806 (build-system r-build-system)
7807 ;; As this package provides little more than a very large data file it
7808 ;; doesn't make sense to build substitutes.
7809 (arguments `(#:substitutable? #f))
7811 `(("r-bsgenome" ,r-bsgenome)))
7813 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7814 (synopsis "Full genome sequences for Worm")
7816 "This package provides full genome sequences for Caenorhabditis
7817 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7819 (license license:artistic2.0)))
7821 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7823 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7827 ;; We cannot use bioconductor-uri here because this tarball is
7828 ;; located under "data/annotation/" instead of "bioc/".
7829 (uri (string-append "https://www.bioconductor.org/packages/"
7830 "release/data/annotation/src/contrib/"
7831 "BSgenome.Dmelanogaster.UCSC.dm3_"
7835 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7837 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7838 (build-system r-build-system)
7839 ;; As this package provides little more than a very large data file it
7840 ;; doesn't make sense to build substitutes.
7841 (arguments `(#:substitutable? #f))
7843 `(("r-bsgenome" ,r-bsgenome)))
7845 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7846 (synopsis "Full genome sequences for Fly")
7848 "This package provides full genome sequences for Drosophila
7849 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7850 Biostrings objects.")
7851 (license license:artistic2.0)))
7853 (define-public r-motifrg
7860 (uri (bioconductor-uri "motifRG" version))
7863 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
7864 (properties `((upstream-name . "motifRG")))
7865 (build-system r-build-system)
7867 `(("r-biostrings" ,r-biostrings)
7868 ("r-bsgenome" ,r-bsgenome)
7869 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7870 ("r-iranges" ,r-iranges)
7871 ("r-seqlogo" ,r-seqlogo)
7872 ("r-xvector" ,r-xvector)))
7873 (home-page "https://bioconductor.org/packages/motifRG")
7874 (synopsis "Discover motifs in high throughput sequencing data")
7876 "This package provides tools for discriminative motif discovery in high
7877 throughput genetic sequencing data sets using regression methods.")
7878 (license license:artistic2.0)))
7880 (define-public r-qtl
7887 (uri (string-append "mirror://cran/src/contrib/qtl_"
7891 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
7892 (build-system r-build-system)
7893 (home-page "http://rqtl.org/")
7894 (synopsis "R package for analyzing QTL experiments in genetics")
7895 (description "R/qtl is an extension library for the R statistics
7896 system. It is used to analyze experimental crosses for identifying
7897 genes contributing to variation in quantitative traits (so-called
7898 quantitative trait loci, QTLs).
7900 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7901 identify genotyping errors, and to perform single-QTL and two-QTL,
7902 two-dimensional genome scans.")
7903 (license license:gpl3)))
7905 (define-public r-zlibbioc
7911 (uri (bioconductor-uri "zlibbioc" version))
7914 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
7916 `((upstream-name . "zlibbioc")))
7917 (build-system r-build-system)
7918 (home-page "https://bioconductor.org/packages/zlibbioc")
7919 (synopsis "Provider for zlib-1.2.5 to R packages")
7920 (description "This package uses the source code of zlib-1.2.5 to create
7921 libraries for systems that do not have these available via other means.")
7922 (license license:artistic2.0)))
7924 (define-public r-r4rna
7931 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7935 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7936 (build-system r-build-system)
7938 `(("r-optparse" ,r-optparse)
7939 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7940 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7941 (synopsis "Analysis framework for RNA secondary structure")
7943 "The R4RNA package aims to be a general framework for the analysis of RNA
7944 secondary structure and comparative analysis in R.")
7945 (license license:gpl3+)))
7947 (define-public r-rhtslib
7954 (uri (bioconductor-uri "Rhtslib" version))
7957 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
7958 (properties `((upstream-name . "Rhtslib")))
7959 (build-system r-build-system)
7961 `(("r-zlibbioc" ,r-zlibbioc)))
7965 `(("autoconf" ,autoconf)))
7966 (home-page "https://github.com/nhayden/Rhtslib")
7967 (synopsis "High-throughput sequencing library as an R package")
7969 "This package provides the HTSlib C library for high-throughput
7970 nucleotide sequence analysis. The package is primarily useful to developers
7971 of other R packages who wish to make use of HTSlib.")
7972 (license license:lgpl2.0+)))
7974 (define-public r-bamsignals
7976 (name "r-bamsignals")
7981 (uri (bioconductor-uri "bamsignals" version))
7984 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
7985 (build-system r-build-system)
7987 `(("r-biocgenerics" ,r-biocgenerics)
7988 ("r-genomicranges" ,r-genomicranges)
7989 ("r-iranges" ,r-iranges)
7991 ("r-rhtslib" ,r-rhtslib)
7992 ("r-zlibbioc" ,r-zlibbioc)))
7995 (home-page "https://bioconductor.org/packages/bamsignals")
7996 (synopsis "Extract read count signals from bam files")
7998 "This package allows to efficiently obtain count vectors from indexed bam
7999 files. It counts the number of nucleotide sequence reads in given genomic
8000 ranges and it computes reads profiles and coverage profiles. It also handles
8002 (license license:gpl2+)))
8004 (define-public r-rcas
8010 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8012 (file-name (string-append name "-" version ".tar.gz"))
8015 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8016 (build-system r-build-system)
8018 `(("r-knitr" ,r-knitr)
8019 ("r-testthat" ,r-testthat)
8020 ;; During vignette building knitr checks that "pandoc-citeproc"
8022 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8024 `(("r-data-table" ,r-data-table)
8025 ("r-biomart" ,r-biomart)
8026 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8027 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8028 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8029 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8030 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8031 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8032 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8033 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8034 ("r-topgo" ,r-topgo)
8036 ("r-pbapply" ,r-pbapply)
8037 ("r-plotly" ,r-plotly)
8038 ("r-plotrix" ,r-plotrix)
8039 ("r-motifrg" ,r-motifrg)
8040 ("r-genomation" ,r-genomation)
8041 ("r-genomicfeatures" ,r-genomicfeatures)
8042 ("r-rtracklayer" ,r-rtracklayer)
8043 ("r-rmarkdown" ,r-rmarkdown)))
8044 (synopsis "RNA-centric annotation system")
8046 "RCAS aims to be a standalone RNA-centric annotation system that provides
8047 intuitive reports and publication-ready graphics. This package provides the R
8048 library implementing most of the pipeline's features.")
8049 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8050 (license license:artistic2.0)))
8052 (define-public rcas-web
8059 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8060 "releases/download/v" version
8061 "/rcas-web-" version ".tar.gz"))
8064 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8065 (build-system gnu-build-system)
8068 (modify-phases %standard-phases
8069 (add-after 'install 'wrap-executable
8070 (lambda* (#:key inputs outputs #:allow-other-keys)
8071 (let* ((out (assoc-ref outputs "out"))
8072 (json (assoc-ref inputs "guile-json"))
8073 (redis (assoc-ref inputs "guile-redis"))
8074 (path (string-append
8075 json "/share/guile/site/2.2:"
8076 redis "/share/guile/site/2.2")))
8077 (wrap-program (string-append out "/bin/rcas-web")
8078 `("GUILE_LOAD_PATH" ":" = (,path))
8079 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8080 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8083 `(("r-minimal" ,r-minimal)
8085 ("guile-next" ,guile-2.2)
8086 ("guile-json" ,guile-json)
8087 ("guile-redis" ,guile2.2-redis)))
8089 `(("pkg-config" ,pkg-config)))
8090 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8091 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8092 (description "This package provides a simple web interface for the
8093 @dfn{RNA-centric annotation system} (RCAS).")
8094 (license license:agpl3+)))
8096 (define-public r-mutationalpatterns
8098 (name "r-mutationalpatterns")
8103 (uri (bioconductor-uri "MutationalPatterns" version))
8106 "0sqbrswg8ylkjb9q3vqcb5ggwixynwj6hyv2n4sk7snyk61z3fq9"))))
8107 (build-system r-build-system)
8109 `(("r-biocgenerics" ,r-biocgenerics)
8110 ("r-biostrings" ,r-biostrings)
8111 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8112 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8113 ("r-genomicranges" ,r-genomicranges)
8114 ("r-genomeinfodb" ,r-genomeinfodb)
8115 ("r-ggplot2" ,r-ggplot2)
8116 ("r-gridextra" ,r-gridextra)
8117 ("r-iranges" ,r-iranges)
8120 ("r-pracma" ,r-pracma)
8121 ("r-reshape2" ,r-reshape2)
8122 ("r-cowplot" ,r-cowplot)
8123 ("r-ggdendro" ,r-ggdendro)
8124 ("r-s4vectors" ,r-s4vectors)
8125 ("r-summarizedexperiment" ,r-summarizedexperiment)
8126 ("r-variantannotation" ,r-variantannotation)))
8127 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8128 (synopsis "Extract and visualize mutational patterns in genomic data")
8129 (description "This package provides an extensive toolset for the
8130 characterization and visualization of a wide range of mutational patterns
8131 in SNV base substitution data.")
8132 (license license:expat)))
8134 (define-public r-wgcna
8141 (uri (cran-uri "WGCNA" version))
8144 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
8145 (properties `((upstream-name . "WGCNA")))
8146 (build-system r-build-system)
8148 `(("r-annotationdbi" ,r-annotationdbi)
8149 ("r-doparallel" ,r-doparallel)
8150 ("r-dynamictreecut" ,r-dynamictreecut)
8151 ("r-fastcluster" ,r-fastcluster)
8152 ("r-foreach" ,r-foreach)
8153 ("r-go-db" ,r-go-db)
8154 ("r-hmisc" ,r-hmisc)
8155 ("r-impute" ,r-impute)
8157 ("r-robust" ,r-robust)
8158 ("r-survival" ,r-survival)
8159 ("r-matrixstats" ,r-matrixstats)
8160 ("r-preprocesscore" ,r-preprocesscore)))
8162 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8163 (synopsis "Weighted correlation network analysis")
8165 "This package provides functions necessary to perform Weighted
8166 Correlation Network Analysis on high-dimensional data. It includes functions
8167 for rudimentary data cleaning, construction and summarization of correlation
8168 networks, module identification and functions for relating both variables and
8169 modules to sample traits. It also includes a number of utility functions for
8170 data manipulation and visualization.")
8171 (license license:gpl2+)))
8173 (define-public r-chipkernels
8174 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8177 (name "r-chipkernels")
8178 (version (string-append "1.1-" revision "." (string-take commit 9)))
8183 (url "https://github.com/ManuSetty/ChIPKernels.git")
8185 (file-name (string-append name "-" version))
8188 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8189 (build-system r-build-system)
8191 `(("r-iranges" ,r-iranges)
8192 ("r-xvector" ,r-xvector)
8193 ("r-biostrings" ,r-biostrings)
8194 ("r-bsgenome" ,r-bsgenome)
8195 ("r-gtools" ,r-gtools)
8196 ("r-genomicranges" ,r-genomicranges)
8197 ("r-sfsmisc" ,r-sfsmisc)
8198 ("r-kernlab" ,r-kernlab)
8199 ("r-s4vectors" ,r-s4vectors)
8200 ("r-biocgenerics" ,r-biocgenerics)))
8201 (home-page "https://github.com/ManuSetty/ChIPKernels")
8202 (synopsis "Build string kernels for DNA Sequence analysis")
8203 (description "ChIPKernels is an R package for building different string
8204 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8205 must be built and this dictionary can be used for determining kernels for DNA
8207 (license license:gpl2+))))
8209 (define-public r-seqgl
8216 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8217 "archive/" version ".tar.gz"))
8218 (file-name (string-append name "-" version ".tar.gz"))
8221 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8222 (build-system r-build-system)
8224 `(("r-biostrings" ,r-biostrings)
8225 ("r-chipkernels" ,r-chipkernels)
8226 ("r-genomicranges" ,r-genomicranges)
8227 ("r-spams" ,r-spams)
8228 ("r-wgcna" ,r-wgcna)
8229 ("r-fastcluster" ,r-fastcluster)))
8230 (home-page "https://github.com/ManuSetty/SeqGL")
8231 (synopsis "Group lasso for Dnase/ChIP-seq data")
8232 (description "SeqGL is a group lasso based algorithm to extract
8233 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8234 This package presents a method which uses group lasso to discriminate between
8235 bound and non bound genomic regions to accurately identify transcription
8236 factors bound at the specific regions.")
8237 (license license:gpl2+)))
8239 (define-public r-gkmsvm
8246 (uri (cran-uri "gkmSVM" version))
8249 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8250 (properties `((upstream-name . "gkmSVM")))
8251 (build-system r-build-system)
8253 `(("r-biocgenerics" ,r-biocgenerics)
8254 ("r-biostrings" ,r-biostrings)
8255 ("r-genomeinfodb" ,r-genomeinfodb)
8256 ("r-genomicranges" ,r-genomicranges)
8257 ("r-iranges" ,r-iranges)
8258 ("r-kernlab" ,r-kernlab)
8261 ("r-rtracklayer" ,r-rtracklayer)
8262 ("r-s4vectors" ,r-s4vectors)
8263 ("r-seqinr" ,r-seqinr)))
8264 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8265 (synopsis "Gapped-kmer support vector machine")
8267 "This R package provides tools for training gapped-kmer SVM classifiers
8268 for DNA and protein sequences. This package supports several sequence
8269 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8270 (license license:gpl2+)))
8272 (define-public r-tximport
8278 (uri (bioconductor-uri "tximport" version))
8281 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8282 (build-system r-build-system)
8283 (home-page "https://bioconductor.org/packages/tximport")
8284 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8286 "This package provides tools to import transcript-level abundance,
8287 estimated counts and transcript lengths, and to summarize them into matrices
8288 for use with downstream gene-level analysis packages. Average transcript
8289 length, weighted by sample-specific transcript abundance estimates, is
8290 provided as a matrix which can be used as an offset for different expression
8291 of gene-level counts.")
8292 (license license:gpl2+)))
8294 (define-public r-rhdf5
8300 (uri (bioconductor-uri "rhdf5" version))
8303 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8304 (build-system r-build-system)
8307 (modify-phases %standard-phases
8308 (add-after 'unpack 'unpack-smallhdf5
8309 (lambda* (#:key outputs #:allow-other-keys)
8310 (system* "tar" "-xzvf"
8311 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8312 (substitute* "src/Makevars"
8313 (("^.*cd hdf5source &&.*$") "")
8314 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8315 (("^.*rm -rf hdf5.*$") "")
8316 (("^.*mv hdf5source/hdf5 ..*$") ""))
8317 (substitute* "src/hdf5/configure"
8321 `(("r-zlibbioc" ,r-zlibbioc)))
8325 (home-page "https://bioconductor.org/packages/rhdf5")
8326 (synopsis "HDF5 interface to R")
8328 "This R/Bioconductor package provides an interface between HDF5 and R.
8329 HDF5's main features are the ability to store and access very large and/or
8330 complex datasets and a wide variety of metadata on mass storage (disk) through
8331 a completely portable file format. The rhdf5 package is thus suited for the
8332 exchange of large and/or complex datasets between R and other software
8333 package, and for letting R applications work on datasets that are larger than
8334 the available RAM.")
8335 (license license:artistic2.0)))
8337 (define-public r-annotationfilter
8339 (name "r-annotationfilter")
8343 (uri (bioconductor-uri "AnnotationFilter" version))
8346 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8348 `((upstream-name . "AnnotationFilter")))
8349 (build-system r-build-system)
8351 `(("r-genomicranges" ,r-genomicranges)
8352 ("r-lazyeval" ,r-lazyeval)))
8353 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8354 (synopsis "Facilities for filtering Bioconductor annotation resources")
8356 "This package provides classes and other infrastructure to implement
8357 filters for manipulating Bioconductor annotation resources. The filters are
8358 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8359 (license license:artistic2.0)))
8361 (define-public emboss
8367 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8368 (version-major+minor version) ".0/"
8369 "EMBOSS-" version ".tar.gz"))
8372 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8373 (build-system gnu-build-system)
8376 (list (string-append "--with-hpdf="
8377 (assoc-ref %build-inputs "libharu")))
8379 (modify-phases %standard-phases
8380 (add-after 'unpack 'fix-checks
8382 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8383 ;; and zlib, but assume that they are all found at the same
8385 (substitute* "configure.in"
8386 (("CHECK_PNGDRIVER")
8387 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8388 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8389 AM_CONDITIONAL(AMPNG, true)"))
8391 (add-after 'fix-checks 'disable-update-check
8393 ;; At build time there is no connection to the Internet, so
8394 ;; looking for updates will not work.
8395 (substitute* "Makefile.am"
8396 (("\\$\\(bindir\\)/embossupdate") ""))
8398 (add-after 'disable-update-check 'autogen
8399 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8405 ("libharu" ,libharu)
8408 `(("autoconf" ,autoconf)
8409 ("automake" ,automake)
8410 ("libtool" ,libtool)
8411 ("pkg-config" ,pkg-config)))
8412 (home-page "http://emboss.sourceforge.net")
8413 (synopsis "Molecular biology analysis suite")
8414 (description "EMBOSS is the \"European Molecular Biology Open Software
8415 Suite\". EMBOSS is an analysis package specially developed for the needs of
8416 the molecular biology (e.g. EMBnet) user community. The software
8417 automatically copes with data in a variety of formats and even allows
8418 transparent retrieval of sequence data from the web. It also provides a
8419 number of libraries for the development of software in the field of molecular
8420 biology. EMBOSS also integrates a range of currently available packages and
8421 tools for sequence analysis into a seamless whole.")
8422 (license license:gpl2+)))
8425 (let ((revision "1")
8426 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8429 ;; The version is 2.13.0 even though no release archives have been
8430 ;; published as yet.
8431 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8435 (url "https://github.com/arq5x/bits.git")
8437 (file-name (string-append name "-" version "-checkout"))
8440 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8441 (build-system gnu-build-system)
8443 `(#:tests? #f ;no tests included
8445 (modify-phases %standard-phases
8447 (add-after 'unpack 'remove-cuda
8449 (substitute* "Makefile"
8451 (("(bits_test_intersections) \\\\" _ match) match))
8454 (lambda* (#:key outputs #:allow-other-keys)
8456 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8461 (home-page "https://github.com/arq5x/bits")
8462 (synopsis "Implementation of binary interval search algorithm")
8463 (description "This package provides an implementation of the
8464 BITS (Binary Interval Search) algorithm, an approach to interval set
8465 intersection. It is especially suited for the comparison of diverse genomic
8466 datasets and the exploration of large datasets of genome
8467 intervals (e.g. genes, sequence alignments).")
8468 (license license:gpl2))))
8470 (define-public piranha
8471 ;; There is no release tarball for the latest version. The latest commit is
8472 ;; older than one year at the time of this writing.
8473 (let ((revision "1")
8474 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8477 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8481 (url "https://github.com/smithlabcode/piranha.git")
8485 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8486 (build-system gnu-build-system)
8488 `(#:test-target "test"
8490 (modify-phases %standard-phases
8491 (add-after 'unpack 'copy-smithlab-cpp
8492 (lambda* (#:key inputs #:allow-other-keys)
8493 (for-each (lambda (file)
8494 (install-file file "./src/smithlab_cpp/"))
8495 (find-files (assoc-ref inputs "smithlab-cpp")))
8497 (add-after 'install 'install-to-store
8498 (lambda* (#:key outputs #:allow-other-keys)
8499 (let* ((out (assoc-ref outputs "out"))
8500 (bin (string-append out "/bin")))
8501 (for-each (lambda (file)
8502 (install-file file bin))
8503 (find-files "bin" ".*")))
8506 (list (string-append "--with-bam_tools_headers="
8507 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8508 (string-append "--with-bam_tools_library="
8509 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8511 `(("bamtools" ,bamtools)
8512 ("samtools" ,samtools-0.1)
8515 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8519 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8521 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8524 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8526 `(("python" ,python-2)))
8527 (home-page "https://github.com/smithlabcode/piranha")
8528 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8530 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8531 RIP-seq experiments. It takes input in BED or BAM format and identifies
8532 regions of statistically significant read enrichment. Additional covariates
8533 may optionally be provided to further inform the peak-calling process.")
8534 (license license:gpl3+))))
8542 (uri (string-append "https://pypi.python.org/packages/source/P"
8543 "/PePr/PePr-" version ".tar.gz"))
8546 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8547 (build-system python-build-system)
8549 `(#:python ,python-2 ; python2 only
8550 #:tests? #f)) ; no tests included
8552 `(("python2-numpy" ,python2-numpy)
8553 ("python2-scipy" ,python2-scipy)
8554 ("python2-pysam" ,python2-pysam)))
8555 (home-page "https://github.com/shawnzhangyx/PePr")
8556 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8558 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8559 that is primarily designed for data with biological replicates. It uses a
8560 negative binomial distribution to model the read counts among the samples in
8561 the same group, and look for consistent differences between ChIP and control
8562 group or two ChIP groups run under different conditions.")
8563 (license license:gpl3+)))
8565 (define-public filevercmp
8566 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8569 (version (string-append "0-1." (string-take commit 7)))
8572 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8574 (file-name (string-append name "-" version ".tar.gz"))
8576 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8577 (build-system gnu-build-system)
8579 `(#:tests? #f ; There are no tests to run.
8581 (modify-phases %standard-phases
8582 (delete 'configure) ; There is no configure phase.
8584 (lambda* (#:key outputs #:allow-other-keys)
8585 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8586 (install-file "filevercmp" bin)))))))
8587 (home-page "https://github.com/ekg/filevercmp")
8588 (synopsis "This program compares version strings")
8589 (description "This program compares version strings. It intends to be a
8590 replacement for strverscmp.")
8591 (license license:gpl3+))))
8593 (define-public multiqc
8600 (uri (pypi-uri "multiqc" version))
8603 "0fx1sx53znbgzfhbbiyd8j6cg5llpcsl5q5c45jy2c81d12piqfd"))))
8604 (build-system python-build-system)
8606 `(("python-enum34" ,python-enum34)
8607 ("python-jinja2" ,python-jinja2)
8608 ("python-simplejson" ,python-simplejson)
8609 ("python-pyyaml" ,python-pyyaml)
8610 ("python-click" ,python-click)
8611 ("python-spectra" ,python-spectra)
8612 ("python-requests" ,python-requests)
8613 ("python-markdown" ,python-markdown)
8614 ("python-lzstring" ,python-lzstring)
8615 ("python-matplotlib" ,python-matplotlib)
8616 ("python-numpy" ,python-numpy)
8617 ;; MultQC checks for the presence of nose at runtime.
8618 ("python-nose" ,python-nose)))
8619 (home-page "http://multiqc.info")
8620 (synopsis "Aggregate bioinformatics analysis reports")
8622 "MultiQC is a tool to aggregate bioinformatics results across many
8623 samples into a single report. It contains modules for a large number of
8624 common bioinformatics tools.")
8625 (license license:gpl3+)))
8627 (define-public r-chipseq
8634 (uri (bioconductor-uri "chipseq" version))
8637 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8638 (build-system r-build-system)
8640 `(("r-biocgenerics" ,r-biocgenerics)
8641 ("r-genomicranges" ,r-genomicranges)
8642 ("r-iranges" ,r-iranges)
8643 ("r-lattice" ,r-lattice)
8644 ("r-s4vectors" ,r-s4vectors)
8645 ("r-shortread" ,r-shortread)))
8646 (home-page "https://bioconductor.org/packages/chipseq")
8647 (synopsis "Package for analyzing ChIPseq data")
8649 "This package provides tools for processing short read data from ChIPseq
8651 (license license:artistic2.0)))
8653 (define-public r-copyhelper
8655 (name "r-copyhelper")
8660 (uri (string-append "https://bioconductor.org/packages/release/"
8661 "data/experiment/src/contrib/CopyhelpeR_"
8665 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8666 (properties `((upstream-name . "CopyhelpeR")))
8667 (build-system r-build-system)
8668 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8669 (synopsis "Helper files for CopywriteR")
8671 "This package contains the helper files that are required to run the
8672 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8673 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8674 mm10. In addition, it contains a blacklist filter to remove regions that
8675 display copy number variation. Files are stored as GRanges objects from the
8676 GenomicRanges Bioconductor package.")
8677 (license license:gpl2)))
8679 (define-public r-copywriter
8681 (name "r-copywriter")
8686 (uri (bioconductor-uri "CopywriteR" version))
8689 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
8690 (properties `((upstream-name . "CopywriteR")))
8691 (build-system r-build-system)
8693 `(("r-biocparallel" ,r-biocparallel)
8694 ("r-chipseq" ,r-chipseq)
8695 ("r-copyhelper" ,r-copyhelper)
8696 ("r-data-table" ,r-data-table)
8697 ("r-dnacopy" ,r-dnacopy)
8698 ("r-futile-logger" ,r-futile-logger)
8699 ("r-genomeinfodb" ,r-genomeinfodb)
8700 ("r-genomicalignments" ,r-genomicalignments)
8701 ("r-genomicranges" ,r-genomicranges)
8702 ("r-gtools" ,r-gtools)
8703 ("r-iranges" ,r-iranges)
8704 ("r-matrixstats" ,r-matrixstats)
8705 ("r-rsamtools" ,r-rsamtools)
8706 ("r-s4vectors" ,r-s4vectors)))
8707 (home-page "https://github.com/PeeperLab/CopywriteR")
8708 (synopsis "Copy number information from targeted sequencing")
8710 "CopywriteR extracts DNA copy number information from targeted sequencing
8711 by utilizing off-target reads. It allows for extracting uniformly distributed
8712 copy number information, can be used without reference, and can be applied to
8713 sequencing data obtained from various techniques including chromatin
8714 immunoprecipitation and target enrichment on small gene panels. Thereby,
8715 CopywriteR constitutes a widely applicable alternative to available copy
8716 number detection tools.")
8717 (license license:gpl2)))
8719 (define-public r-methylkit
8721 (name "r-methylkit")
8725 (uri (bioconductor-uri "methylKit" version))
8728 "0h53w2mrjrg2n0ndi12k9j6cwclgwcgpy25nz7nyj971aisw02xn"))))
8729 (properties `((upstream-name . "methylKit")))
8730 (build-system r-build-system)
8732 `(("r-data-table" ,r-data-table)
8733 ("r-emdbook" ,r-emdbook)
8734 ("r-fastseg" ,r-fastseg)
8735 ("r-genomeinfodb" ,r-genomeinfodb)
8736 ("r-genomicranges" ,r-genomicranges)
8737 ("r-gtools" ,r-gtools)
8738 ("r-iranges" ,r-iranges)
8739 ("r-kernsmooth" ,r-kernsmooth)
8740 ("r-limma" ,r-limma)
8741 ("r-mclust" ,r-mclust)
8742 ("r-qvalue" ,r-qvalue)
8743 ("r-r-utils" ,r-r-utils)
8745 ("r-rhtslib" ,r-rhtslib)
8746 ("r-rsamtools" ,r-rsamtools)
8747 ("r-rtracklayer" ,r-rtracklayer)
8748 ("r-s4vectors" ,r-s4vectors)
8749 ("r-zlibbioc" ,r-zlibbioc)))
8752 (home-page "http://code.google.com/p/methylkit/")
8754 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8756 "MethylKit is an R package for DNA methylation analysis and annotation
8757 from high-throughput bisulfite sequencing. The package is designed to deal
8758 with sequencing data from @dfn{Reduced representation bisulfite
8759 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8760 genome bisulfite sequencing. It also has functions to analyze base-pair
8761 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8763 (license license:artistic2.0)))
8765 (define-public r-sva
8772 (uri (bioconductor-uri "sva" version))
8775 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
8776 (build-system r-build-system)
8778 `(("r-genefilter" ,r-genefilter)
8780 ("r-biocparallel" ,r-biocparallel)
8781 ("r-matrixstats" ,r-matrixstats)
8782 ("r-limma" ,r-limma)))
8783 (home-page "https://bioconductor.org/packages/sva")
8784 (synopsis "Surrogate variable analysis")
8786 "This package contains functions for removing batch effects and other
8787 unwanted variation in high-throughput experiment. It also contains functions
8788 for identifying and building surrogate variables for high-dimensional data
8789 sets. Surrogate variables are covariates constructed directly from
8790 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8791 imaging data that can be used in subsequent analyses to adjust for unknown,
8792 unmodeled, or latent sources of noise.")
8793 (license license:artistic2.0)))
8795 (define-public r-seqminer
8802 (uri (cran-uri "seqminer" version))
8805 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
8806 (build-system r-build-system)
8809 (home-page "http://seqminer.genomic.codes")
8810 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8812 "This package provides tools to integrate nucleotide sequencing
8813 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8814 ;; Any version of the GPL is acceptable
8815 (license (list license:gpl2+ license:gpl3+))))
8817 (define-public r-raremetals2
8819 (name "r-raremetals2")
8824 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8825 "b/b7/RareMETALS2_" version ".tar.gz"))
8828 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8829 (properties `((upstream-name . "RareMETALS2")))
8830 (build-system r-build-system)
8832 `(("r-seqminer" ,r-seqminer)
8833 ("r-mvtnorm" ,r-mvtnorm)
8835 ("r-compquadform" ,r-compquadform)
8836 ("r-getopt" ,r-getopt)))
8837 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8838 (synopsis "Analyze gene-level association tests for binary trait")
8840 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8841 It was designed to meta-analyze gene-level association tests for binary trait.
8842 While rareMETALS offers a near-complete solution for meta-analysis of
8843 gene-level tests for quantitative trait, it does not offer the optimal
8844 solution for binary trait. The package rareMETALS2 offers improved features
8845 for analyzing gene-level association tests in meta-analyses for binary
8847 (license license:gpl3)))
8849 (define-public r-maldiquant
8851 (name "r-maldiquant")
8856 (uri (cran-uri "MALDIquant" version))
8859 "1pmhsfvd45a44xdiml4zx3zd5fhygqyziqvygahkk9yibnyhv4cv"))))
8860 (properties `((upstream-name . "MALDIquant")))
8861 (build-system r-build-system)
8862 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8863 (synopsis "Quantitative analysis of mass spectrometry data")
8865 "This package provides a complete analysis pipeline for matrix-assisted
8866 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8867 two-dimensional mass spectrometry data. In addition to commonly used plotting
8868 and processing methods it includes distinctive features, namely baseline
8869 subtraction methods such as morphological filters (TopHat) or the
8870 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8871 alignment using warping functions, handling of replicated measurements as well
8872 as allowing spectra with different resolutions.")
8873 (license license:gpl3+)))
8875 (define-public r-protgenerics
8877 (name "r-protgenerics")
8882 (uri (bioconductor-uri "ProtGenerics" version))
8885 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
8886 (properties `((upstream-name . "ProtGenerics")))
8887 (build-system r-build-system)
8888 (home-page "https://github.com/lgatto/ProtGenerics")
8889 (synopsis "S4 generic functions for proteomics infrastructure")
8891 "This package provides S4 generic functions needed by Bioconductor
8892 proteomics packages.")
8893 (license license:artistic2.0)))
8895 (define-public r-mzr
8902 (uri (bioconductor-uri "mzR" version))
8905 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
8906 (modules '((guix build utils)))
8909 (delete-file-recursively "src/boost")
8911 (properties `((upstream-name . "mzR")))
8912 (build-system r-build-system)
8915 (modify-phases %standard-phases
8916 (add-after 'unpack 'use-system-boost
8918 (substitute* "src/Makevars"
8919 (("\\./boost/libs.*") "")
8920 (("ARCH_OBJS=" line)
8922 "\nARCH_LIBS=-lboost_system -lboost_regex \
8923 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
8926 `(("boost" ,boost) ; use this instead of the bundled boost sources
8927 ("netcdf" ,netcdf)))
8929 `(("r-biobase" ,r-biobase)
8930 ("r-biocgenerics" ,r-biocgenerics)
8931 ("r-protgenerics" ,r-protgenerics)
8933 ("r-zlibbioc" ,r-zlibbioc)))
8934 (home-page "https://github.com/sneumann/mzR/")
8935 (synopsis "Parser for mass spectrometry data files")
8937 "The mzR package provides a unified API to the common file formats and
8938 parsers available for mass spectrometry data. It comes with a wrapper for the
8939 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8940 The package contains the original code written by the ISB, and a subset of the
8941 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8942 previously been used in XCMS.")
8943 (license license:artistic2.0)))
8945 (define-public r-affyio
8952 (uri (bioconductor-uri "affyio" version))
8955 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
8956 (build-system r-build-system)
8958 `(("r-zlibbioc" ,r-zlibbioc)))
8961 (home-page "https://github.com/bmbolstad/affyio")
8962 (synopsis "Tools for parsing Affymetrix data files")
8964 "This package provides routines for parsing Affymetrix data files based
8965 upon file format information. The primary focus is on accessing the CEL and
8967 (license license:lgpl2.0+)))
8969 (define-public r-affy
8976 (uri (bioconductor-uri "affy" version))
8979 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
8980 (build-system r-build-system)
8982 `(("r-affyio" ,r-affyio)
8983 ("r-biobase" ,r-biobase)
8984 ("r-biocgenerics" ,r-biocgenerics)
8985 ("r-biocinstaller" ,r-biocinstaller)
8986 ("r-preprocesscore" ,r-preprocesscore)
8987 ("r-zlibbioc" ,r-zlibbioc)))
8988 (home-page "https://bioconductor.org/packages/affy")
8989 (synopsis "Methods for affymetrix oligonucleotide arrays")
8991 "This package contains functions for exploratory oligonucleotide array
8993 (license license:lgpl2.0+)))
8995 (define-public r-vsn
9002 (uri (bioconductor-uri "vsn" version))
9005 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9006 (build-system r-build-system)
9008 `(("r-affy" ,r-affy)
9009 ("r-biobase" ,r-biobase)
9010 ("r-ggplot2" ,r-ggplot2)
9011 ("r-lattice" ,r-lattice)
9012 ("r-limma" ,r-limma)))
9013 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9014 (synopsis "Variance stabilization and calibration for microarray data")
9016 "The package implements a method for normalising microarray intensities,
9017 and works for single- and multiple-color arrays. It can also be used for data
9018 from other technologies, as long as they have similar format. The method uses
9019 a robust variant of the maximum-likelihood estimator for an
9020 additive-multiplicative error model and affine calibration. The model
9021 incorporates data calibration step (a.k.a. normalization), a model for the
9022 dependence of the variance on the mean intensity and a variance stabilizing
9023 data transformation. Differences between transformed intensities are
9024 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9025 their variance is independent of the mean, and they are usually more sensitive
9026 and specific in detecting differential transcription.")
9027 (license license:artistic2.0)))
9029 (define-public r-mzid
9036 (uri (bioconductor-uri "mzID" version))
9039 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9040 (properties `((upstream-name . "mzID")))
9041 (build-system r-build-system)
9043 `(("r-doparallel" ,r-doparallel)
9044 ("r-foreach" ,r-foreach)
9045 ("r-iterators" ,r-iterators)
9047 ("r-protgenerics" ,r-protgenerics)
9050 (home-page "https://bioconductor.org/packages/mzID")
9051 (synopsis "Parser for mzIdentML files")
9053 "This package provides a parser for mzIdentML files implemented using the
9054 XML package. The parser tries to be general and able to handle all types of
9055 mzIdentML files with the drawback of having less pretty output than a vendor
9057 (license license:gpl2+)))
9059 (define-public r-pcamethods
9061 (name "r-pcamethods")
9066 (uri (bioconductor-uri "pcaMethods" version))
9069 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9070 (properties `((upstream-name . "pcaMethods")))
9071 (build-system r-build-system)
9073 `(("r-biobase" ,r-biobase)
9074 ("r-biocgenerics" ,r-biocgenerics)
9076 ("r-rcpp" ,r-rcpp)))
9077 (home-page "https://github.com/hredestig/pcamethods")
9078 (synopsis "Collection of PCA methods")
9080 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9081 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9082 for missing value estimation is included for comparison. BPCA, PPCA and
9083 NipalsPCA may be used to perform PCA on incomplete data as well as for
9084 accurate missing value estimation. A set of methods for printing and plotting
9085 the results is also provided. All PCA methods make use of the same data
9086 structure (pcaRes) to provide a common interface to the PCA results.")
9087 (license license:gpl3+)))
9089 (define-public r-msnbase
9096 (uri (bioconductor-uri "MSnbase" version))
9099 "0dqfimljhrx3gac8d1k72gppx27lz8yckyb12v4604nbviw7xd3r"))))
9100 (properties `((upstream-name . "MSnbase")))
9101 (build-system r-build-system)
9103 `(("r-affy" ,r-affy)
9104 ("r-biobase" ,r-biobase)
9105 ("r-biocgenerics" ,r-biocgenerics)
9106 ("r-biocparallel" ,r-biocparallel)
9107 ("r-digest" ,r-digest)
9108 ("r-ggplot2" ,r-ggplot2)
9109 ("r-impute" ,r-impute)
9110 ("r-iranges" ,r-iranges)
9111 ("r-lattice" ,r-lattice)
9112 ("r-maldiquant" ,r-maldiquant)
9115 ("r-pcamethods" ,r-pcamethods)
9117 ("r-preprocesscore" ,r-preprocesscore)
9118 ("r-protgenerics" ,r-protgenerics)
9120 ("r-s4vectors" ,r-s4vectors)
9123 (home-page "https://github.com/lgatto/MSnbase")
9124 (synopsis "Base functions and classes for MS-based proteomics")
9126 "This package provides basic plotting, data manipulation and processing
9127 of mass spectrometry based proteomics data.")
9128 (license license:artistic2.0)))
9130 (define-public r-msnid
9137 (uri (bioconductor-uri "MSnID" version))
9140 "1vi4ngwbayrv2jkfb4pbmdp37xn04y07rh1jcklqfh0fcrm1jdig"))))
9141 (properties `((upstream-name . "MSnID")))
9142 (build-system r-build-system)
9144 `(("r-biobase" ,r-biobase)
9145 ("r-data-table" ,r-data-table)
9146 ("r-doparallel" ,r-doparallel)
9147 ("r-dplyr" ,r-dplyr)
9148 ("r-foreach" ,r-foreach)
9149 ("r-iterators" ,r-iterators)
9150 ("r-msnbase" ,r-msnbase)
9153 ("r-protgenerics" ,r-protgenerics)
9154 ("r-r-cache" ,r-r-cache)
9156 ("r-reshape2" ,r-reshape2)))
9157 (home-page "https://bioconductor.org/packages/MSnID")
9158 (synopsis "Utilities for LC-MSn proteomics identifications")
9160 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9161 from mzIdentML (leveraging the mzID package) or text files. After collating
9162 the search results from multiple datasets it assesses their identification
9163 quality and optimize filtering criteria to achieve the maximum number of
9164 identifications while not exceeding a specified false discovery rate. It also
9165 contains a number of utilities to explore the MS/MS results and assess missed
9166 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9167 (license license:artistic2.0)))
9169 (define-public r-seurat
9170 ;; Source releases are only made for new x.0 versions. All newer versions
9171 ;; are only released as pre-built binaries. At the time of this writing the
9172 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9173 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9177 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9181 (url "https://github.com/satijalab/seurat")
9183 (file-name (string-append name "-" version "-checkout"))
9186 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9187 ;; Delete pre-built jar.
9189 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9191 (build-system r-build-system)
9194 (modify-phases %standard-phases
9195 (add-after 'unpack 'build-jar
9196 (lambda* (#:key inputs #:allow-other-keys)
9197 (let ((classesdir "tmp-classes"))
9198 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9200 (and (zero? (apply system* `("javac" "-d" ,classesdir
9201 ,@(find-files "java" "\\.java$"))))
9202 (zero? (system* "jar"
9203 "-cf" "inst/java/ModularityOptimizer.jar"
9204 "-C" classesdir ".")))))))))
9206 `(("jdk" ,icedtea "jdk")))
9209 ("r-caret" ,r-caret)
9210 ("r-cowplot" ,r-cowplot)
9211 ("r-dplyr" ,r-dplyr)
9212 ("r-fastica" ,r-fastica)
9215 ("r-gdata" ,r-gdata)
9216 ("r-ggplot2" ,r-ggplot2)
9217 ("r-gplots" ,r-gplots)
9218 ("r-gridextra" ,r-gridextra)
9219 ("r-igraph" ,r-igraph)
9220 ("r-irlba" ,r-irlba)
9222 ("r-mixtools" ,r-mixtools)
9223 ("r-pbapply" ,r-pbapply)
9225 ("r-ranger" ,r-ranger)
9226 ("r-rcolorbrewer" ,r-rcolorbrewer)
9228 ("r-rcppeigen" ,r-rcppeigen)
9229 ("r-rcppprogress" ,r-rcppprogress)
9230 ("r-reshape2" ,r-reshape2)
9232 ("r-rtsne" ,r-rtsne)
9233 ("r-stringr" ,r-stringr)
9234 ("r-tclust" ,r-tclust)
9236 ("r-vgam" ,r-vgam)))
9237 (home-page "http://www.satijalab.org/seurat")
9238 (synopsis "Seurat is an R toolkit for single cell genomics")
9240 "This package is an R package designed for QC, analysis, and
9241 exploration of single cell RNA-seq data. It easily enables widely-used
9242 analytical techniques, including the identification of highly variable genes,
9243 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9244 algorithms; density clustering, hierarchical clustering, k-means, and the
9245 discovery of differentially expressed genes and markers.")
9246 (license license:gpl3))))
9248 (define-public r-aroma-light
9250 (name "r-aroma-light")
9255 (uri (bioconductor-uri "aroma.light" version))
9258 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9259 (properties `((upstream-name . "aroma.light")))
9260 (build-system r-build-system)
9262 `(("r-matrixstats" ,r-matrixstats)
9263 ("r-r-methodss3" ,r-r-methodss3)
9265 ("r-r-utils" ,r-r-utils)))
9266 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9267 (synopsis "Methods for normalization and visualization of microarray data")
9269 "This package provides methods for microarray analysis that take basic
9270 data types such as matrices and lists of vectors. These methods can be used
9271 standalone, be utilized in other packages, or be wrapped up in higher-level
9273 (license license:gpl2+)))
9275 (define-public r-deseq
9282 (uri (bioconductor-uri "DESeq" version))
9285 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9286 (properties `((upstream-name . "DESeq")))
9287 (build-system r-build-system)
9289 `(("r-biobase" ,r-biobase)
9290 ("r-biocgenerics" ,r-biocgenerics)
9291 ("r-genefilter" ,r-genefilter)
9292 ("r-geneplotter" ,r-geneplotter)
9293 ("r-lattice" ,r-lattice)
9294 ("r-locfit" ,r-locfit)
9296 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9297 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9298 (synopsis "Differential gene expression analysis")
9300 "This package provides tools for estimating variance-mean dependence in
9301 count data from high-throughput genetic sequencing assays and for testing for
9302 differential expression based on a model using the negative binomial
9304 (license license:gpl3+)))
9306 (define-public r-edaseq
9313 (uri (bioconductor-uri "EDASeq" version))
9316 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9317 (properties `((upstream-name . "EDASeq")))
9318 (build-system r-build-system)
9320 `(("r-annotationdbi" ,r-annotationdbi)
9321 ("r-aroma-light" ,r-aroma-light)
9322 ("r-biobase" ,r-biobase)
9323 ("r-biocgenerics" ,r-biocgenerics)
9324 ("r-biomart" ,r-biomart)
9325 ("r-biostrings" ,r-biostrings)
9326 ("r-deseq" ,r-deseq)
9327 ("r-genomicfeatures" ,r-genomicfeatures)
9328 ("r-genomicranges" ,r-genomicranges)
9329 ("r-iranges" ,r-iranges)
9330 ("r-rsamtools" ,r-rsamtools)
9331 ("r-shortread" ,r-shortread)))
9332 (home-page "https://github.com/drisso/EDASeq")
9333 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9335 "This package provides support for numerical and graphical summaries of
9336 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9337 adjust for GC-content effect (or other gene-level effects) on read counts:
9338 loess robust local regression, global-scaling, and full-quantile
9339 normalization. Between-lane normalization procedures to adjust for
9340 distributional differences between lanes (e.g., sequencing depth):
9341 global-scaling and full-quantile normalization.")
9342 (license license:artistic2.0)))
9344 (define-public r-interactivedisplaybase
9346 (name "r-interactivedisplaybase")
9351 (uri (bioconductor-uri "interactiveDisplayBase" version))
9354 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9356 `((upstream-name . "interactiveDisplayBase")))
9357 (build-system r-build-system)
9359 `(("r-biocgenerics" ,r-biocgenerics)
9360 ("r-shiny" ,r-shiny)))
9361 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9362 (synopsis "Base package for web displays of Bioconductor objects")
9364 "This package contains the basic methods needed to generate interactive
9365 Shiny-based display methods for Bioconductor objects.")
9366 (license license:artistic2.0)))
9368 (define-public r-annotationhub
9370 (name "r-annotationhub")
9375 (uri (bioconductor-uri "AnnotationHub" version))
9378 "1arfka3czw8hkv6n2d85bgibq81s2rgkwhmpaxzhy6nw39vv7y8b"))))
9379 (properties `((upstream-name . "AnnotationHub")))
9380 (build-system r-build-system)
9382 `(("r-annotationdbi" ,r-annotationdbi)
9383 ("r-biocgenerics" ,r-biocgenerics)
9384 ("r-biocinstaller" ,r-biocinstaller)
9387 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9388 ("r-rsqlite" ,r-rsqlite)
9389 ("r-s4vectors" ,r-s4vectors)
9390 ("r-yaml" ,r-yaml)))
9391 (home-page "https://bioconductor.org/packages/AnnotationHub")
9392 (synopsis "Client to access AnnotationHub resources")
9394 "This package provides a client for the Bioconductor AnnotationHub web
9395 resource. The AnnotationHub web resource provides a central location where
9396 genomic files (e.g. VCF, bed, wig) and other resources from standard
9397 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9398 metadata about each resource, e.g., a textual description, tags, and date of
9399 modification. The client creates and manages a local cache of files retrieved
9400 by the user, helping with quick and reproducible access.")
9401 (license license:artistic2.0)))
9403 (define-public r-fastseg
9410 (uri (bioconductor-uri "fastseg" version))
9413 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9414 (build-system r-build-system)
9416 `(("r-biobase" ,r-biobase)
9417 ("r-biocgenerics" ,r-biocgenerics)
9418 ("r-genomicranges" ,r-genomicranges)
9419 ("r-iranges" ,r-iranges)
9420 ("r-s4vectors" ,r-s4vectors)))
9421 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9422 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9424 "Fastseg implements a very fast and efficient segmentation algorithm.
9425 It can segment data from DNA microarrays and data from next generation
9426 sequencing for example to detect copy number segments. Further it can segment
9427 data from RNA microarrays like tiling arrays to identify transcripts. Most
9428 generally, it can segment data given as a matrix or as a vector. Various data
9429 formats can be used as input to fastseg like expression set objects for
9430 microarrays or GRanges for sequencing data.")
9431 (license license:lgpl2.0+)))
9433 (define-public r-qvalue
9440 (uri (bioconductor-uri "qvalue" version))
9443 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
9444 (build-system r-build-system)
9446 `(("r-ggplot2" ,r-ggplot2)
9447 ("r-reshape2" ,r-reshape2)))
9448 (home-page "http://github.com/jdstorey/qvalue")
9449 (synopsis "Q-value estimation for false discovery rate control")
9451 "This package takes a list of p-values resulting from the simultaneous
9452 testing of many hypotheses and estimates their q-values and local @dfn{false
9453 discovery rate} (FDR) values. The q-value of a test measures the proportion
9454 of false positives incurred when that particular test is called significant.
9455 The local FDR measures the posterior probability the null hypothesis is true
9456 given the test's p-value. Various plots are automatically generated, allowing
9457 one to make sensible significance cut-offs. The software can be applied to
9458 problems in genomics, brain imaging, astrophysics, and data mining.")
9459 ;; Any version of the LGPL.
9460 (license license:lgpl3+)))
9462 (define htslib-for-sambamba
9463 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9466 (name "htslib-for-sambamba")
9467 (version (string-append "1.3.1-1." (string-take commit 9)))
9472 (url "https://github.com/lomereiter/htslib.git")
9474 (file-name (string-append "htslib-" version "-checkout"))
9477 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9479 (substitute-keyword-arguments (package-arguments htslib)
9481 `(modify-phases ,phases
9482 (add-after 'unpack 'bootstrap
9484 (zero? (system* "autoreconf" "-vif"))))))))
9486 `(("autoconf" ,autoconf)
9487 ("automake" ,automake)
9488 ,@(package-native-inputs htslib))))))
9490 (define-public sambamba
9497 (uri (string-append "https://github.com/lomereiter/sambamba/"
9498 "archive/v" version ".tar.gz"))
9499 (file-name (string-append name "-" version ".tar.gz"))
9502 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9503 (build-system gnu-build-system)
9505 `(#:tests? #f ; there is no test target
9508 ;; Override "--compiler" flag only.
9509 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9510 "sambamba-ldmd2-64")
9512 (modify-phases %standard-phases
9514 (add-after 'unpack 'place-biod
9515 (lambda* (#:key inputs #:allow-other-keys)
9516 (copy-recursively (assoc-ref inputs "biod") "BioD")
9518 (add-after 'unpack 'unbundle-prerequisites
9520 (substitute* "Makefile"
9521 ((" htslib-static lz4-static") ""))
9524 (lambda* (#:key outputs #:allow-other-keys)
9525 (let* ((out (assoc-ref outputs "out"))
9526 (bin (string-append out "/bin")))
9528 (install-file "build/sambamba" bin)
9534 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9538 (url "https://github.com/biod/BioD.git")
9540 (file-name (string-append "biod-"
9541 (string-take commit 9)
9545 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9548 ("htslib" ,htslib-for-sambamba)))
9549 (home-page "http://lomereiter.github.io/sambamba")
9550 (synopsis "Tools for working with SAM/BAM data")
9551 (description "Sambamba is a high performance modern robust and
9552 fast tool (and library), written in the D programming language, for
9553 working with SAM and BAM files. Current parallelised functionality is
9554 an important subset of samtools functionality, including view, index,
9555 sort, markdup, and depth.")
9556 (license license:gpl2+)))
9558 (define-public ritornello
9564 (uri (string-append "https://github.com/KlugerLab/"
9565 "Ritornello/archive/v"
9567 (file-name (string-append name "-" version ".tar.gz"))
9570 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
9571 (build-system gnu-build-system)
9573 `(#:tests? #f ; there are no tests
9575 (modify-phases %standard-phases
9576 (add-after 'unpack 'patch-samtools-references
9577 (lambda* (#:key inputs #:allow-other-keys)
9578 (substitute* '("src/SamStream.h"
9579 "src/BufferedGenomeReader.h")
9580 (("<sam.h>") "<samtools/sam.h>"))
9584 (lambda* (#:key inputs outputs #:allow-other-keys)
9585 (let* ((out (assoc-ref outputs "out"))
9586 (bin (string-append out "/bin/")))
9588 (install-file "bin/Ritornello" bin)
9591 `(("samtools" ,samtools-0.1)
9595 (home-page "https://github.com/KlugerLab/Ritornello")
9596 (synopsis "Control-free peak caller for ChIP-seq data")
9597 (description "Ritornello is a ChIP-seq peak calling algorithm based on
9598 signal processing that can accurately call binding events without the need to
9599 do a pair total DNA input or IgG control sample. It has been tested for use
9600 with narrow binding events such as transcription factor ChIP-seq.")
9601 (license license:gpl3+)))
9603 (define-public trim-galore
9605 (name "trim-galore")
9610 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
9611 "projects/trim_galore/trim_galore_v"
9615 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
9616 (build-system gnu-build-system)
9618 `(#:tests? #f ; no tests
9620 (modify-phases %standard-phases
9621 ;; The archive contains plain files.
9623 (lambda* (#:key source #:allow-other-keys)
9624 (zero? (system* "unzip" source))))
9627 (add-after 'unpack 'hardcode-tool-references
9628 (lambda* (#:key inputs #:allow-other-keys)
9629 (substitute* "trim_galore"
9630 (("\\$path_to_cutadapt = 'cutadapt'")
9631 (string-append "$path_to_cutadapt = '"
9632 (assoc-ref inputs "cutadapt")
9636 (assoc-ref inputs "gzip")
9640 (assoc-ref inputs "gzip")
9644 (lambda* (#:key outputs #:allow-other-keys)
9645 (let ((bin (string-append (assoc-ref outputs "out")
9648 (install-file "trim_galore" bin)
9653 ("cutadapt" ,cutadapt)))
9655 `(("unzip" ,unzip)))
9656 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
9657 (synopsis "Wrapper around Cutadapt and FastQC")
9658 (description "Trim Galore! is a wrapper script to automate quality and
9659 adapter trimming as well as quality control, with some added functionality to
9660 remove biased methylation positions for RRBS sequence files.")
9661 (license license:gpl3+)))
9669 (uri (string-append "http://compbio.uthscsa.edu/"
9671 "gess-" version ".src.tar.gz"))
9674 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
9675 (build-system gnu-build-system)
9677 `(#:tests? #f ; no tests
9679 (modify-phases %standard-phases
9683 (lambda* (#:key inputs outputs #:allow-other-keys)
9684 (let* ((python (assoc-ref inputs "python"))
9685 (out (assoc-ref outputs "out"))
9686 (bin (string-append out "/bin/"))
9687 (target (string-append
9688 out "/lib/python2.7/site-packages/gess/")))
9690 (copy-recursively "." target)
9691 ;; Make GESS.py executable
9692 (chmod (string-append target "GESS.py") #o555)
9693 ;; Add Python shebang to the top and make Matplotlib
9695 (substitute* (string-append target "GESS.py")
9696 (("\"\"\"Description:" line)
9697 (string-append "#!" (which "python") "
9699 matplotlib.use('Agg')
9701 ;; Make sure GESS has all modules in its path
9702 (wrap-program (string-append target "GESS.py")
9703 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
9705 (symlink (string-append target "GESS.py")
9706 (string-append bin "GESS.py"))
9709 `(("python" ,python-2)
9710 ("python2-pysam" ,python2-pysam)
9711 ("python2-scipy" ,python2-scipy)
9712 ("python2-numpy" ,python2-numpy)
9713 ("python2-networkx" ,python2-networkx)
9714 ("python2-biopython" ,python2-biopython)))
9715 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
9716 (synopsis "Detect exon-skipping events from raw RNA-seq data")
9718 "GESS is an implementation of a novel computational method to detect de
9719 novo exon-skipping events directly from raw RNA-seq data without the prior
9720 knowledge of gene annotation information. GESS stands for the graph-based
9721 exon-skipping scanner detection scheme.")
9722 (license license:bsd-3)))
9724 (define-public phylip
9731 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
9732 "download/phylip-" version ".tar.gz"))
9735 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
9736 (build-system gnu-build-system)
9738 `(#:tests? #f ; no check target
9739 #:make-flags (list "-f" "Makefile.unx" "install")
9740 #:parallel-build? #f ; not supported
9742 (modify-phases %standard-phases
9743 (add-after 'unpack 'enter-dir
9744 (lambda _ (chdir "src") #t))
9747 (lambda* (#:key inputs outputs #:allow-other-keys)
9748 (let ((target (string-append (assoc-ref outputs "out")
9751 (for-each (lambda (file)
9752 (install-file file target))
9753 (find-files "../exe" ".*")))
9755 (home-page "http://evolution.genetics.washington.edu/phylip/")
9756 (synopsis "Tools for inferring phylogenies")
9757 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
9758 programs for inferring phylogenies (evolutionary trees).")
9759 (license license:bsd-2)))
9768 (uri (string-append "https://integrativemodeling.org/"
9769 version "/download/imp-" version ".tar.gz"))
9772 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
9773 (build-system cmake-build-system)
9775 `(;; FIXME: Some tests fail because they produce warnings, others fail
9776 ;; because the PYTHONPATH does not include the modeller's directory.
9778 ;; Do not place libraries in an architecture-specific directory.
9780 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
9787 ("python" ,python-2)))
9789 `(("python2-numpy" ,python2-numpy)
9790 ("python2-scipy" ,python2-scipy)
9791 ("python2-pandas" ,python2-pandas)
9792 ("python2-scikit-learn" ,python2-scikit-learn)
9793 ("python2-networkx" ,python2-networkx)))
9794 (home-page "https://integrativemodeling.org")
9795 (synopsis "Integrative modeling platform")
9796 (description "IMP's broad goal is to contribute to a comprehensive
9797 structural characterization of biomolecules ranging in size and complexity
9798 from small peptides to large macromolecular assemblies, by integrating data
9799 from diverse biochemical and biophysical experiments. IMP provides a C++ and
9800 Python toolbox for solving complex modeling problems, and a number of
9801 applications for tackling some common problems in a user-friendly way.")
9802 ;; IMP is largely available under the GNU Lesser GPL; see the file
9803 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
9804 ;; available under the GNU GPL (see the file COPYING.GPL).
9805 (license (list license:lgpl2.1+
9808 (define-public tadbit
9814 (uri (string-append "https://github.com/3DGenomes/TADbit/"
9815 "archive/v" version ".tar.gz"))
9816 (file-name (string-append name "-" version ".tar.gz"))
9819 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
9820 (build-system python-build-system)
9822 `(;; Tests are included and must be run after installation, but
9823 ;; they are incomplete and thus cannot be run.
9827 (modify-phases %standard-phases
9828 (add-after 'unpack 'fix-problems-with-setup.py
9829 (lambda* (#:key outputs #:allow-other-keys)
9830 ;; setup.py opens these files for writing
9831 (chmod "_pytadbit/_version.py" #o664)
9832 (chmod "README.rst" #o664)
9834 ;; Don't attempt to install the bash completions to
9835 ;; the home directory.
9836 (rename-file "extras/.bash_completion"
9838 (substitute* "setup.py"
9839 (("\\(path.expanduser\\('~'\\)")
9840 (string-append "(\""
9841 (assoc-ref outputs "out")
9842 "/etc/bash_completion.d\""))
9843 (("extras/\\.bash_completion")
9847 ;; TODO: add Chimera for visualization
9850 ("python2-scipy" ,python2-scipy)
9851 ("python2-numpy" ,python2-numpy)
9852 ("python2-matplotlib" ,python2-matplotlib)
9853 ("python2-pysam" ,python2-pysam)))
9854 (home-page "http://3dgenomes.github.io/TADbit/")
9855 (synopsis "Analyze, model, and explore 3C-based data")
9857 "TADbit is a complete Python library to deal with all steps to analyze,
9858 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
9859 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
9860 correct interaction matrices, identify and compare the so-called
9861 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
9862 interaction matrices, and finally, extract structural properties from the
9863 models. TADbit is complemented by TADkit for visualizing 3D models.")
9864 (license license:gpl3+)))
9866 (define-public kentutils
9869 ;; 302.1.0 is out, but the only difference is the inclusion of
9870 ;; pre-built binaries.
9875 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
9876 "archive/v" version ".tar.gz"))
9877 (file-name (string-append name "-" version ".tar.gz"))
9880 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
9881 (modules '((guix build utils)
9886 ;; Only the contents of the specified directories are free
9887 ;; for all uses, so we remove the rest. "hg/autoSql" and
9888 ;; "hg/autoXml" are nominally free, but they depend on a
9889 ;; library that is built from the sources in "hg/lib",
9890 ;; which is nonfree.
9891 (let ((free (list "." ".."
9892 "utils" "lib" "inc" "tagStorm"
9893 "parasol" "htslib"))
9894 (directory? (lambda (file)
9895 (eq? 'directory (stat:type (stat file))))))
9896 (for-each (lambda (file)
9897 (and (directory? file)
9898 (delete-file-recursively file)))
9899 (map (cut string-append "src/" <>)
9902 (not (member file free)))))))
9903 ;; Only make the utils target, not the userApps target,
9904 ;; because that requires libraries we won't build.
9905 (substitute* "Makefile"
9906 ((" userApps") " utils"))
9907 ;; Only build libraries that are free.
9908 (substitute* "src/makefile"
9909 (("DIRS =.*") "DIRS =\n")
9910 (("cd jkOwnLib.*") "")
9913 (substitute* "src/utils/makefile"
9914 ;; These tools depend on "jkhgap.a", which is part of the
9915 ;; nonfree "src/hg/lib" directory.
9917 (("pslLiftSubrangeBlat") "")
9919 ;; Do not build UCSC tools, which may require nonfree
9921 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
9923 (build-system gnu-build-system)
9925 `( ;; There is no global test target and the test target for
9926 ;; individual tools depends on input files that are not
9930 (modify-phases %standard-phases
9931 (add-after 'unpack 'fix-paths
9933 (substitute* "Makefile"
9934 (("/bin/echo") (which "echo")))
9936 (add-after 'unpack 'prepare-samtabix
9937 (lambda* (#:key inputs #:allow-other-keys)
9938 (copy-recursively (assoc-ref inputs "samtabix")
9943 (lambda* (#:key outputs #:allow-other-keys)
9944 (let ((bin (string-append (assoc-ref outputs "out")
9946 (copy-recursively "bin" bin))
9953 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
9954 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
9957 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
9964 ("openssl" ,openssl)))
9965 (home-page "http://genome.cse.ucsc.edu/index.html")
9966 (synopsis "Assorted bioinformatics utilities")
9967 (description "This package provides the kentUtils, a selection of
9968 bioinformatics utilities used in combination with the UCSC genome
9970 ;; Only a subset of the sources are released under a non-copyleft
9971 ;; free software license. All other sources are removed in a
9972 ;; snippet. See this bug report for an explanation of how the
9973 ;; license statements apply:
9974 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
9975 (license (license:non-copyleft
9976 "http://genome.ucsc.edu/license/"
9977 "The contents of this package are free for all uses."))))
9979 (define-public f-seq
9980 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
9984 (version (string-append "1.1-" revision "." (string-take commit 7)))
9988 (url "https://github.com/aboyle/F-seq.git")
9990 (file-name (string-append name "-" version))
9993 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
9994 (modules '((guix build utils)))
9995 ;; Remove bundled Java library archives.
9998 (for-each delete-file (find-files "lib" ".*"))
10000 (build-system ant-build-system)
10002 `(#:tests? #f ; no tests included
10004 (modify-phases %standard-phases
10006 (lambda* (#:key inputs outputs #:allow-other-keys)
10007 (let* ((target (assoc-ref outputs "out"))
10008 (doc (string-append target "/share/doc/f-seq/")))
10011 (substitute* "bin/linux/fseq"
10012 (("java") (which "java"))
10013 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10014 (string-append (assoc-ref inputs "java-commons-cli")
10015 "/share/java/commons-cli.jar"))
10017 (string-append "REALDIR=" target "/bin\n")))
10018 (install-file "README.txt" doc)
10019 (install-file "bin/linux/fseq" (string-append target "/bin"))
10020 (install-file "build~/fseq.jar" (string-append target "/lib"))
10021 (copy-recursively "lib" (string-append target "/lib"))
10025 ("java-commons-cli" ,java-commons-cli)))
10026 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10027 (synopsis "Feature density estimator for high-throughput sequence tags")
10029 "F-Seq is a software package that generates a continuous tag sequence
10030 density estimation allowing identification of biologically meaningful sites
10031 such as transcription factor binding sites (ChIP-seq) or regions of open
10032 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10034 (license license:gpl3+))))
10036 (define-public bismark
10043 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10044 "archive/" version ".tar.gz"))
10045 (file-name (string-append name "-" version ".tar.gz"))
10048 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10049 (build-system perl-build-system)
10051 `(#:tests? #f ; there are no tests
10053 (modify-phases %standard-phases
10054 (delete 'configure)
10057 (lambda* (#:key outputs #:allow-other-keys)
10058 (let ((bin (string-append (assoc-ref outputs "out")
10060 (docdir (string-append (assoc-ref outputs "out")
10061 "/share/doc/bismark"))
10062 (docs '("Bismark_User_Guide.pdf"
10063 "RELEASE_NOTES.txt"))
10064 (scripts '("bismark"
10065 "bismark_genome_preparation"
10066 "bismark_methylation_extractor"
10069 "coverage2cytosine"
10070 "deduplicate_bismark"
10071 "bismark_sitrep.tpl"
10073 "bismark2summary")))
10076 (for-each (lambda (file) (install-file file bin))
10078 (for-each (lambda (file) (install-file file docdir))
10081 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10082 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
10083 (description "Bismark is a program to map bisulfite treated sequencing
10084 reads to a genome of interest and perform methylation calls in a single step.
10085 The output can be easily imported into a genome viewer, such as SeqMonk, and
10086 enables a researcher to analyse the methylation levels of their samples
10087 straight away. Its main features are:
10090 @item Bisulfite mapping and methylation calling in one single step
10091 @item Supports single-end and paired-end read alignments
10092 @item Supports ungapped and gapped alignments
10093 @item Alignment seed length, number of mismatches etc are adjustable
10094 @item Output discriminates between cytosine methylation in CpG, CHG
10097 (license license:gpl3+)))
10099 (define-public paml
10105 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
10106 "paml" version ".tgz"))
10109 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
10110 (modules '((guix build utils)))
10111 ;; Remove Windows binaries
10114 (for-each delete-file (find-files "." "\\.exe$"))
10116 (build-system gnu-build-system)
10118 `(#:tests? #f ; there are no tests
10119 #:make-flags '("CC=gcc")
10121 (modify-phases %standard-phases
10122 (replace 'configure
10124 (substitute* "src/BFdriver.c"
10125 (("/bin/bash") (which "bash")))
10129 (lambda* (#:key outputs #:allow-other-keys)
10130 (let ((tools '("baseml" "basemlg" "codeml"
10131 "pamp" "evolver" "yn00" "chi2"))
10132 (bin (string-append (assoc-ref outputs "out") "/bin"))
10133 (docdir (string-append (assoc-ref outputs "out")
10134 "/share/doc/paml")))
10136 (for-each (lambda (file) (install-file file bin)) tools)
10137 (copy-recursively "../doc" docdir)
10139 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
10140 (synopsis "Phylogentic analysis by maximum likelihood")
10141 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
10142 contains a few programs for model fitting and phylogenetic tree reconstruction
10143 using nucleotide or amino-acid sequence data.")
10145 (license license:gpl3)))