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>
11 ;;; This file is part of GNU Guix.
13 ;;; GNU Guix is free software; you can redistribute it and/or modify it
14 ;;; under the terms of the GNU General Public License as published by
15 ;;; the Free Software Foundation; either version 3 of the License, or (at
16 ;;; your option) any later version.
18 ;;; GNU Guix is distributed in the hope that it will be useful, but
19 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;;; GNU General Public License for more details.
23 ;;; You should have received a copy of the GNU General Public License
24 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
26 (define-module (gnu packages bioinformatics)
27 #:use-module ((guix licenses) #:prefix license:)
28 #:use-module (guix packages)
29 #:use-module (guix utils)
30 #:use-module (guix download)
31 #:use-module (guix git-download)
32 #:use-module (guix hg-download)
33 #:use-module (guix build-system ant)
34 #:use-module (guix build-system gnu)
35 #:use-module (guix build-system cmake)
36 #:use-module (guix build-system ocaml)
37 #:use-module (guix build-system perl)
38 #:use-module (guix build-system python)
39 #:use-module (guix build-system r)
40 #:use-module (guix build-system ruby)
41 #:use-module (guix build-system trivial)
42 #:use-module (gnu packages)
43 #:use-module (gnu packages autotools)
44 #:use-module (gnu packages algebra)
45 #:use-module (gnu packages base)
46 #:use-module (gnu packages bash)
47 #:use-module (gnu packages bison)
48 #:use-module (gnu packages boost)
49 #:use-module (gnu packages compression)
50 #:use-module (gnu packages cpio)
51 #:use-module (gnu packages curl)
52 #:use-module (gnu packages documentation)
53 #:use-module (gnu packages databases)
54 #:use-module (gnu packages datastructures)
55 #:use-module (gnu packages file)
56 #:use-module (gnu packages flex)
57 #:use-module (gnu packages gawk)
58 #:use-module (gnu packages gcc)
59 #:use-module (gnu packages gd)
60 #:use-module (gnu packages gtk)
61 #:use-module (gnu packages glib)
62 #:use-module (gnu packages groff)
63 #:use-module (gnu packages guile)
64 #:use-module (gnu packages haskell)
65 #:use-module (gnu packages image)
66 #:use-module (gnu packages imagemagick)
67 #:use-module (gnu packages java)
68 #:use-module (gnu packages ldc)
69 #:use-module (gnu packages linux)
70 #:use-module (gnu packages logging)
71 #:use-module (gnu packages machine-learning)
72 #:use-module (gnu packages man)
73 #:use-module (gnu packages maths)
74 #:use-module (gnu packages mpi)
75 #:use-module (gnu packages ncurses)
76 #:use-module (gnu packages ocaml)
77 #:use-module (gnu packages pcre)
78 #:use-module (gnu packages parallel)
79 #:use-module (gnu packages pdf)
80 #:use-module (gnu packages perl)
81 #:use-module (gnu packages pkg-config)
82 #:use-module (gnu packages popt)
83 #:use-module (gnu packages protobuf)
84 #:use-module (gnu packages python)
85 #:use-module (gnu packages readline)
86 #:use-module (gnu packages ruby)
87 #:use-module (gnu packages serialization)
88 #:use-module (gnu packages shells)
89 #:use-module (gnu packages statistics)
90 #:use-module (gnu packages swig)
91 #:use-module (gnu packages tbb)
92 #:use-module (gnu packages tex)
93 #:use-module (gnu packages texinfo)
94 #:use-module (gnu packages textutils)
95 #:use-module (gnu packages time)
96 #:use-module (gnu packages tls)
97 #:use-module (gnu packages vim)
98 #:use-module (gnu packages web)
99 #:use-module (gnu packages xml)
100 #:use-module (gnu packages xorg)
101 #:use-module (srfi srfi-1)
102 #:use-module (ice-9 match))
111 (uri (cran-uri "ape" version))
114 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
115 (build-system r-build-system)
117 `(("r-lattice" ,r-lattice)
119 (home-page "http://ape-package.ird.fr/")
120 (synopsis "Analyses of phylogenetics and evolution")
122 "This package provides functions for reading, writing, plotting, and
123 manipulating phylogenetic trees, analyses of comparative data in a
124 phylogenetic framework, ancestral character analyses, analyses of
125 diversification and macroevolution, computing distances from DNA sequences,
126 and several other tools.")
127 (license license:gpl2+)))
129 (define-public aragorn
136 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
140 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
141 (build-system gnu-build-system)
143 `(#:tests? #f ; there are no tests
145 (modify-phases %standard-phases
149 (zero? (system* "gcc"
155 (string-append "aragorn" ,version ".c")))))
157 (lambda* (#:key outputs #:allow-other-keys)
158 (let* ((out (assoc-ref outputs "out"))
159 (bin (string-append out "/bin"))
160 (man (string-append out "/share/man/man1")))
162 (install-file "aragorn" bin)
164 (install-file "aragorn.1" man))
166 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
167 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
169 "Aragorn identifies transfer RNA, mitochondrial RNA and
170 transfer-messenger RNA from nucleotide sequences, based on homology to known
171 tRNA consensus sequences and RNA structure. It also outputs the secondary
172 structure of the predicted RNA.")
173 (license license:gpl2)))
181 ;; BamM is not available on pypi.
183 "https://github.com/Ecogenomics/BamM/archive/"
185 (file-name (string-append name "-" version ".tar.gz"))
188 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
189 (modules '((guix build utils)))
192 ;; Delete bundled htslib.
193 (delete-file-recursively "c/htslib-1.3.1")
195 (build-system python-build-system)
197 `(#:python ,python-2 ; BamM is Python 2 only.
198 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
199 ;; been modified from its original form.
201 (let ((htslib (assoc-ref %build-inputs "htslib")))
202 (list "--with-libhts-lib" (string-append htslib "/lib")
203 "--with-libhts-inc" (string-append htslib "/include/htslib")))
205 (modify-phases %standard-phases
206 (add-after 'unpack 'autogen
208 (with-directory-excursion "c"
209 (let ((sh (which "sh")))
210 ;; Use autogen so that 'configure' works.
211 (substitute* "autogen.sh" (("/bin/sh") sh))
212 (setenv "CONFIG_SHELL" sh)
213 (substitute* "configure" (("/bin/sh") sh))
214 (zero? (system* "./autogen.sh"))))))
216 ;; Run tests after installation so compilation only happens once.
218 (add-after 'install 'wrap-executable
219 (lambda* (#:key outputs #:allow-other-keys)
220 (let* ((out (assoc-ref outputs "out"))
221 (path (getenv "PATH")))
222 (wrap-program (string-append out "/bin/bamm")
223 `("PATH" ":" prefix (,path))))
225 (add-after 'wrap-executable 'post-install-check
226 (lambda* (#:key inputs outputs #:allow-other-keys)
228 (string-append (assoc-ref outputs "out")
233 (assoc-ref outputs "out")
235 (string-take (string-take-right
236 (assoc-ref inputs "python") 5) 3)
238 (getenv "PYTHONPATH")))
239 ;; There are 2 errors printed, but they are safe to ignore:
240 ;; 1) [E::hts_open_format] fail to open file ...
241 ;; 2) samtools view: failed to open ...
242 (zero? (system* "nosetests")))))))
244 `(("autoconf" ,autoconf)
245 ("automake" ,automake)
248 ("python-nose" ,python2-nose)
249 ("python-pysam" ,python2-pysam)))
251 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
252 ("samtools" ,samtools)
256 ("coreutils" ,coreutils)))
258 `(("python-numpy" ,python2-numpy)))
259 (home-page "http://ecogenomics.github.io/BamM/")
260 (synopsis "Metagenomics-focused BAM file manipulator")
262 "BamM is a C library, wrapped in python, to efficiently generate and
263 parse BAM files, specifically for the analysis of metagenomic data. For
264 instance, it implements several methods to assess contig-wise read coverage.")
265 (license license:lgpl3+)))
267 (define-public bamtools
274 "https://github.com/pezmaster31/bamtools/archive/v"
276 (file-name (string-append name "-" version ".tar.gz"))
279 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
280 (build-system cmake-build-system)
282 `(#:tests? #f ;no "check" target
284 (modify-phases %standard-phases
286 'configure 'set-ldflags
287 (lambda* (#:key outputs #:allow-other-keys)
291 (assoc-ref outputs "out") "/lib/bamtools")))))))
292 (inputs `(("zlib" ,zlib)))
293 (home-page "https://github.com/pezmaster31/bamtools")
294 (synopsis "C++ API and command-line toolkit for working with BAM data")
296 "BamTools provides both a C++ API and a command-line toolkit for handling
298 (license license:expat)))
300 (define-public bcftools
307 "https://github.com/samtools/bcftools/releases/download/"
308 version "/bcftools-" version ".tar.bz2"))
311 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
312 (modules '((guix build utils)))
314 ;; Delete bundled htslib.
315 '(delete-file-recursively "htslib-1.5"))))
316 (build-system gnu-build-system)
318 `(#:test-target "test"
319 #:configure-flags (list "--with-htslib=system")
323 "LIBS=-lgsl -lgslcblas"
324 (string-append "prefix=" (assoc-ref %outputs "out"))
325 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
326 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
327 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
328 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
329 (string-append "PACKAGE_VERSION=" ,version))
331 (modify-phases %standard-phases
332 (add-before 'check 'patch-tests
334 (substitute* "test/test.pl"
335 (("/bin/bash") (which "bash")))
343 (home-page "https://samtools.github.io/bcftools/")
344 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
346 "BCFtools is a set of utilities that manipulate variant calls in the
347 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
348 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
349 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
350 (license (list license:gpl3+ license:expat))))
352 (define-public bedops
358 (uri (string-append "https://github.com/bedops/bedops/archive/v"
360 (file-name (string-append name "-" version ".tar.gz"))
363 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
364 (build-system gnu-build-system)
367 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
370 'unpack 'unpack-tarballs
372 ;; FIXME: Bedops includes tarballs of minimally patched upstream
373 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
374 ;; libraries because at least one of the libraries (zlib) is
375 ;; patched to add a C++ function definition (deflateInit2cpp).
376 ;; Until the Bedops developers offer a way to link against system
377 ;; libraries we have to build the in-tree copies of these three
380 ;; See upstream discussion:
381 ;; https://github.com/bedops/bedops/issues/124
383 ;; Unpack the tarballs to benefit from shebang patching.
384 (with-directory-excursion "third-party"
385 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
386 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
387 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
388 ;; Disable unpacking of tarballs in Makefile.
389 (substitute* "system.mk/Makefile.linux"
390 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
391 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
392 (substitute* "third-party/zlib-1.2.7/Makefile.in"
393 (("^SHELL=.*$") "SHELL=bash\n")))
394 (alist-delete 'configure %standard-phases))))
395 (home-page "https://github.com/bedops/bedops")
396 (synopsis "Tools for high-performance genomic feature operations")
398 "BEDOPS is a suite of tools to address common questions raised in genomic
399 studies---mostly with regard to overlap and proximity relationships between
400 data sets. It aims to be scalable and flexible, facilitating the efficient
401 and accurate analysis and management of large-scale genomic data.
403 BEDOPS provides tools that perform highly efficient and scalable Boolean and
404 other set operations, statistical calculations, archiving, conversion and
405 other management of genomic data of arbitrary scale. Tasks can be easily
406 split by chromosome for distributing whole-genome analyses across a
407 computational cluster.")
408 (license license:gpl2+)))
410 (define-public bedtools
416 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
418 (file-name (string-append name "-" version ".tar.gz"))
421 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
422 (build-system gnu-build-system)
423 (native-inputs `(("python" ,python-2)))
424 (inputs `(("samtools" ,samtools)
427 '(#:test-target "test"
429 (modify-phases %standard-phases
432 (lambda* (#:key outputs #:allow-other-keys)
433 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
434 (for-each (lambda (file)
435 (install-file file bin))
436 (find-files "bin" ".*")))
438 (home-page "https://github.com/arq5x/bedtools2")
439 (synopsis "Tools for genome analysis and arithmetic")
441 "Collectively, the bedtools utilities are a swiss-army knife of tools for
442 a wide-range of genomics analysis tasks. The most widely-used tools enable
443 genome arithmetic: that is, set theory on the genome. For example, bedtools
444 allows one to intersect, merge, count, complement, and shuffle genomic
445 intervals from multiple files in widely-used genomic file formats such as BAM,
447 (license license:gpl2)))
449 ;; Later releases of bedtools produce files with more columns than
450 ;; what Ribotaper expects.
451 (define-public bedtools-2.18
452 (package (inherit bedtools)
457 (uri (string-append "https://github.com/arq5x/bedtools2/"
458 "archive/v" version ".tar.gz"))
459 (file-name (string-append name "-" version ".tar.gz"))
462 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
464 (define-public ribotaper
470 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
471 "files/RiboTaper/RiboTaper_Version_"
475 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
476 (build-system gnu-build-system)
478 `(("bedtools" ,bedtools-2.18)
479 ("samtools" ,samtools-0.1)
480 ("r-minimal" ,r-minimal)
481 ("r-foreach" ,r-foreach)
482 ("r-xnomial" ,r-xnomial)
484 ("r-multitaper" ,r-multitaper)
485 ("r-seqinr" ,r-seqinr)))
486 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
487 (synopsis "Define translated ORFs using ribosome profiling data")
489 "Ribotaper is a method for defining translated @dfn{open reading
490 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
491 provides the Ribotaper pipeline.")
492 (license license:gpl3+)))
494 (define-public ribodiff
501 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
502 "archive/v" version ".tar.gz"))
503 (file-name (string-append name "-" version ".tar.gz"))
506 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
507 (build-system python-build-system)
511 (modify-phases %standard-phases
512 ;; Generate an installable executable script wrapper.
513 (add-after 'unpack 'patch-setup.py
515 (substitute* "setup.py"
516 (("^(.*)packages=.*" line prefix)
517 (string-append line "\n"
518 prefix "scripts=['scripts/TE.py'],\n")))
521 `(("python-numpy" ,python2-numpy)
522 ("python-matplotlib" ,python2-matplotlib)
523 ("python-scipy" ,python2-scipy)
524 ("python-statsmodels" ,python2-statsmodels)))
526 `(("python-mock" ,python2-mock)
527 ("python-nose" ,python2-nose)))
528 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
529 (synopsis "Detect translation efficiency changes from ribosome footprints")
530 (description "RiboDiff is a statistical tool that detects the protein
531 translational efficiency change from Ribo-Seq (ribosome footprinting) and
532 RNA-Seq data. It uses a generalized linear model to detect genes showing
533 difference in translational profile taking mRNA abundance into account. It
534 facilitates us to decipher the translational regulation that behave
535 independently with transcriptional regulation.")
536 (license license:gpl3+)))
538 (define-public bioawk
544 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
546 (file-name (string-append name "-" version ".tar.gz"))
548 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
549 (build-system gnu-build-system)
555 `(#:tests? #f ; There are no tests to run.
556 ;; Bison must generate files, before other targets can build.
559 (modify-phases %standard-phases
560 (delete 'configure) ; There is no configure phase.
562 (lambda* (#:key outputs #:allow-other-keys)
563 (let* ((out (assoc-ref outputs "out"))
564 (bin (string-append out "/bin"))
565 (man (string-append out "/share/man/man1")))
567 (copy-file "awk.1" (string-append man "/bioawk.1"))
568 (install-file "bioawk" bin)))))))
569 (home-page "https://github.com/lh3/bioawk")
570 (synopsis "AWK with bioinformatics extensions")
571 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
572 support of several common biological data formats, including optionally gzip'ed
573 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
574 also adds a few built-in functions and a command line option to use TAB as the
575 input/output delimiter. When the new functionality is not used, bioawk is
576 intended to behave exactly the same as the original BWK awk.")
577 (license license:x11)))
579 (define-public python2-pybedtools
581 (name "python2-pybedtools")
586 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
590 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
591 (build-system python-build-system)
592 (arguments `(#:python ,python-2)) ; no Python 3 support
594 `(("python-matplotlib" ,python2-matplotlib)))
596 `(("bedtools" ,bedtools)
597 ("samtools" ,samtools)))
599 `(("python-cython" ,python2-cython)
600 ("python-pyyaml" ,python2-pyyaml)
601 ("python-nose" ,python2-nose)))
602 (home-page "https://pythonhosted.org/pybedtools/")
603 (synopsis "Python wrapper for BEDtools programs")
605 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
606 which are widely used for genomic interval manipulation or \"genome algebra\".
607 pybedtools extends BEDTools by offering feature-level manipulations from with
609 (license license:gpl2+)))
611 (define-public python-biom-format
613 (name "python-biom-format")
618 ;; Use GitHub as source because PyPI distribution does not contain
619 ;; test data: https://github.com/biocore/biom-format/issues/693
620 (uri (string-append "https://github.com/biocore/biom-format/archive/"
622 (file-name (string-append name "-" version ".tar.gz"))
625 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
626 (build-system python-build-system)
628 `(("python-numpy" ,python-numpy)
629 ("python-scipy" ,python-scipy)
630 ("python-future" ,python-future)
631 ("python-click" ,python-click)
632 ("python-h5py" ,python-h5py)
633 ("python-pandas" ,python-pandas)))
635 `(("python-nose" ,python-nose)))
636 (home-page "http://www.biom-format.org")
637 (synopsis "Biological Observation Matrix (BIOM) format utilities")
639 "The BIOM file format is designed to be a general-use format for
640 representing counts of observations e.g. operational taxonomic units, KEGG
641 orthology groups or lipid types, in one or more biological samples
642 e.g. microbiome samples, genomes, metagenomes.")
643 (license license:bsd-3)
644 (properties `((python2-variant . ,(delay python2-biom-format))))))
646 (define-public python2-biom-format
647 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
652 (modify-phases %standard-phases
653 ;; Do not require the unmaintained pyqi library.
654 (add-after 'unpack 'remove-pyqi
656 (substitute* "setup.py"
657 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
659 ,@(package-arguments base))))))
661 (define-public bioperl-minimal
662 (let* ((inputs `(("perl-module-build" ,perl-module-build)
663 ("perl-data-stag" ,perl-data-stag)
664 ("perl-libwww" ,perl-libwww)
665 ("perl-uri" ,perl-uri)))
667 (map (compose package-name cadr)
670 (map (compose package-transitive-target-inputs cadr) inputs))))))
672 (name "bioperl-minimal")
677 (uri (string-append "https://github.com/bioperl/bioperl-live/"
679 (string-map (lambda (c)
685 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
686 (build-system perl-build-system)
689 (modify-phases %standard-phases
691 'install 'wrap-programs
692 (lambda* (#:key outputs #:allow-other-keys)
693 ;; Make sure all executables in "bin" find the required Perl
694 ;; modules at runtime. As the PERL5LIB variable contains also
695 ;; the paths of native inputs, we pick the transitive target
696 ;; inputs from %build-inputs.
697 (let* ((out (assoc-ref outputs "out"))
698 (bin (string-append out "/bin/"))
700 (cons (string-append out "/lib/perl5/site_perl")
702 (assoc-ref %build-inputs name))
703 ',transitive-inputs))
705 (for-each (lambda (file)
707 `("PERL5LIB" ":" prefix (,path))))
708 (find-files bin "\\.pl$"))
712 `(("perl-test-most" ,perl-test-most)))
713 (home-page "http://search.cpan.org/dist/BioPerl")
714 (synopsis "Bioinformatics toolkit")
716 "BioPerl is the product of a community effort to produce Perl code which
717 is useful in biology. Examples include Sequence objects, Alignment objects
718 and database searching objects. These objects not only do what they are
719 advertised to do in the documentation, but they also interact - Alignment
720 objects are made from the Sequence objects, Sequence objects have access to
721 Annotation and SeqFeature objects and databases, Blast objects can be
722 converted to Alignment objects, and so on. This means that the objects
723 provide a coordinated and extensible framework to do computational biology.")
724 (license license:perl-license))))
726 (define-public python-biopython
728 (name "python-biopython")
732 ;; use PyPi rather than biopython.org to ease updating
733 (uri (pypi-uri "biopython" version))
736 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
737 (build-system python-build-system)
740 (modify-phases %standard-phases
741 (add-before 'check 'set-home
742 ;; Some tests require a home directory to be set.
743 (lambda _ (setenv "HOME" "/tmp") #t)))))
745 `(("python-numpy" ,python-numpy)))
746 (home-page "http://biopython.org/")
747 (synopsis "Tools for biological computation in Python")
749 "Biopython is a set of tools for biological computation including parsers
750 for bioinformatics files into Python data structures; interfaces to common
751 bioinformatics programs; a standard sequence class and tools for performing
752 common operations on them; code to perform data classification; code for
753 dealing with alignments; code making it easy to split up parallelizable tasks
754 into separate processes; and more.")
755 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
757 (define-public python2-biopython
758 (package-with-python2 python-biopython))
760 ;; An outdated version of biopython is required for seqmagick, see
761 ;; https://github.com/fhcrc/seqmagick/issues/59
762 ;; When that issue has been resolved this package should be removed.
763 (define python2-biopython-1.66
765 (inherit python2-biopython)
769 (uri (pypi-uri "biopython" version))
772 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
774 (define-public bpp-core
775 ;; The last release was in 2014 and the recommended way to install from source
776 ;; is to clone the git repository, so we do this.
777 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
778 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
781 (version (string-append "2.2.0-1." (string-take commit 7)))
785 (url "http://biopp.univ-montp2.fr/git/bpp-core")
787 (file-name (string-append name "-" version "-checkout"))
790 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
791 (build-system cmake-build-system)
793 `(#:parallel-build? #f))
795 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
796 ; compile all of the bpp packages with GCC 5.
797 (home-page "http://biopp.univ-montp2.fr")
798 (synopsis "C++ libraries for Bioinformatics")
800 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
801 analysis, phylogenetics, molecular evolution and population genetics. It is
802 Object Oriented and is designed to be both easy to use and computer efficient.
803 Bio++ intends to help programmers to write computer expensive programs, by
804 providing them a set of re-usable tools.")
805 (license license:cecill-c))))
807 (define-public bpp-phyl
808 ;; The last release was in 2014 and the recommended way to install from source
809 ;; is to clone the git repository, so we do this.
810 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
811 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
814 (version (string-append "2.2.0-1." (string-take commit 7)))
818 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
820 (file-name (string-append name "-" version "-checkout"))
823 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
824 (build-system cmake-build-system)
826 `(#:parallel-build? #f
827 ;; If out-of-source, test data is not copied into the build directory
828 ;; so the tests fail.
829 #:out-of-source? #f))
831 `(("bpp-core" ,bpp-core)
833 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
836 (home-page "http://biopp.univ-montp2.fr")
837 (synopsis "Bio++ phylogenetic Library")
839 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
840 analysis, phylogenetics, molecular evolution and population genetics. This
841 library provides phylogenetics-related modules.")
842 (license license:cecill-c))))
844 (define-public bpp-popgen
845 ;; The last release was in 2014 and the recommended way to install from source
846 ;; is to clone the git repository, so we do this.
847 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
848 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
851 (version (string-append "2.2.0-1." (string-take commit 7)))
855 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
857 (file-name (string-append name "-" version "-checkout"))
860 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
861 (build-system cmake-build-system)
863 `(#:parallel-build? #f
864 #:tests? #f)) ; There are no tests.
866 `(("bpp-core" ,bpp-core)
869 (home-page "http://biopp.univ-montp2.fr")
870 (synopsis "Bio++ population genetics library")
872 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
873 analysis, phylogenetics, molecular evolution and population genetics. This
874 library provides population genetics-related modules.")
875 (license license:cecill-c))))
877 (define-public bpp-seq
878 ;; The last release was in 2014 and the recommended way to install from source
879 ;; is to clone the git repository, so we do this.
880 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
881 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
884 (version (string-append "2.2.0-1." (string-take commit 7)))
888 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
890 (file-name (string-append name "-" version "-checkout"))
893 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
894 (build-system cmake-build-system)
896 `(#:parallel-build? #f
897 ;; If out-of-source, test data is not copied into the build directory
898 ;; so the tests fail.
899 #:out-of-source? #f))
901 `(("bpp-core" ,bpp-core)
902 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
903 (home-page "http://biopp.univ-montp2.fr")
904 (synopsis "Bio++ sequence library")
906 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
907 analysis, phylogenetics, molecular evolution and population genetics. This
908 library provides sequence-related modules.")
909 (license license:cecill-c))))
911 (define-public bppsuite
912 ;; The last release was in 2014 and the recommended way to install from source
913 ;; is to clone the git repository, so we do this.
914 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
915 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
918 (version (string-append "2.2.0-1." (string-take commit 7)))
922 (url "http://biopp.univ-montp2.fr/git/bppsuite")
924 (file-name (string-append name "-" version "-checkout"))
927 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
928 (build-system cmake-build-system)
930 `(#:parallel-build? #f
931 #:tests? #f)) ; There are no tests.
935 ("texinfo" ,texinfo)))
937 `(("bpp-core" ,bpp-core)
939 ("bpp-phyl" ,bpp-phyl)
940 ("bpp-phyl" ,bpp-popgen)
942 (home-page "http://biopp.univ-montp2.fr")
943 (synopsis "Bioinformatics tools written with the Bio++ libraries")
945 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
946 analysis, phylogenetics, molecular evolution and population genetics. This
947 package provides command line tools using the Bio++ library.")
948 (license license:cecill-c))))
950 (define-public blast+
957 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
958 version "/ncbi-blast-" version "+-src.tar.gz"))
961 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
962 (patches (search-patches "blast+-fix-makefile.patch"))
963 (modules '((guix build utils)))
966 ;; Remove bundled bzip2, zlib and pcre.
967 (delete-file-recursively "c++/src/util/compress/bzip2")
968 (delete-file-recursively "c++/src/util/compress/zlib")
969 (delete-file-recursively "c++/src/util/regexp")
970 (substitute* "c++/src/util/compress/Makefile.in"
971 (("bzip2 zlib api") "api"))
972 ;; Remove useless msbuild directory
973 (delete-file-recursively
974 "c++/src/build-system/project_tree_builder/msbuild")
976 (build-system gnu-build-system)
978 `(;; There are two(!) tests for this massive library, and both fail with
979 ;; "unparsable timing stats".
980 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
981 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
984 #:parallel-build? #f ; not supported
986 (modify-phases %standard-phases
989 ;; $HOME needs to be set at some point during the configure phase
990 (lambda _ (setenv "HOME" "/tmp") #t))
993 (lambda _ (chdir "c++") #t))
995 'enter-dir 'fix-build-system
998 (cond ((string=? cmd "date")
999 ;; make call to "date" deterministic
1004 (format (current-error-port)
1005 "WARNING: Unable to find absolute path for ~s~%"
1009 ;; Rewrite hardcoded paths to various tools
1010 (substitute* (append '("src/build-system/configure.ac"
1011 "src/build-system/configure"
1012 "src/build-system/helpers/run_with_lock.c"
1013 "scripts/common/impl/if_diff.sh"
1014 "scripts/common/impl/run_with_lock.sh"
1015 "src/build-system/Makefile.configurables.real"
1016 "src/build-system/Makefile.in.top"
1017 "src/build-system/Makefile.meta.gmake=no"
1018 "src/build-system/Makefile.meta.in"
1019 "src/build-system/Makefile.meta_l"
1020 "src/build-system/Makefile.meta_p"
1021 "src/build-system/Makefile.meta_r"
1022 "src/build-system/Makefile.mk.in"
1023 "src/build-system/Makefile.requirements"
1024 "src/build-system/Makefile.rules_with_autodep.in")
1025 (find-files "scripts/common/check" "\\.sh$"))
1026 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1027 (or (which* cmd) all)))
1029 (substitute* (find-files "src/build-system" "^config.*")
1030 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1033 ;; rewrite "/var/tmp" in check script
1034 (substitute* "scripts/common/check/check_make_unix.sh"
1035 (("/var/tmp") "/tmp"))
1037 ;; do not reset PATH
1038 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1040 (("action=/bin/") "action=")
1041 (("export PATH") ":"))
1045 (lambda* (#:key inputs outputs #:allow-other-keys)
1046 (let ((out (assoc-ref outputs "out"))
1047 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1048 (include (string-append (assoc-ref outputs "include")
1049 "/include/ncbi-tools++")))
1050 ;; The 'configure' script doesn't recognize things like
1051 ;; '--enable-fast-install'.
1052 (zero? (system* "./configure.orig"
1053 (string-append "--with-build-root=" (getcwd) "/build")
1054 (string-append "--prefix=" out)
1055 (string-append "--libdir=" lib)
1056 (string-append "--includedir=" include)
1057 (string-append "--with-bz2="
1058 (assoc-ref inputs "bzip2"))
1059 (string-append "--with-z="
1060 (assoc-ref inputs "zlib"))
1061 (string-append "--with-pcre="
1062 (assoc-ref inputs "pcre"))
1063 ;; Each library is built twice by default, once
1064 ;; with "-static" in its name, and again
1067 "--with-dll"))))))))
1068 (outputs '("out" ; 21 MB
1076 ("python" ,python-wrapper)))
1079 (home-page "http://blast.ncbi.nlm.nih.gov")
1080 (synopsis "Basic local alignment search tool")
1082 "BLAST is a popular method of performing a DNA or protein sequence
1083 similarity search, using heuristics to produce results quickly. It also
1084 calculates an “expect value” that estimates how many matches would have
1085 occurred at a given score by chance, which can aid a user in judging how much
1086 confidence to have in an alignment.")
1087 ;; Most of the sources are in the public domain, with the following
1090 ;; * ./c++/include/util/bitset/
1091 ;; * ./c++/src/html/ncbi_menu*.js
1093 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1095 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1097 ;; * ./c++/src/corelib/teamcity_*
1098 (license (list license:public-domain
1104 (define-public bless
1110 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1114 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1115 (modules '((guix build utils)))
1118 ;; Remove bundled boost, pigz, zlib, and .git directory
1119 ;; FIXME: also remove bundled sources for murmurhash3 and
1120 ;; kmc once packaged.
1121 (delete-file-recursively "boost")
1122 (delete-file-recursively "pigz")
1123 (delete-file-recursively "google-sparsehash")
1124 (delete-file-recursively "zlib")
1125 (delete-file-recursively ".git")
1127 (build-system gnu-build-system)
1129 '(#:tests? #f ;no "check" target
1131 (list (string-append "ZLIB="
1132 (assoc-ref %build-inputs "zlib")
1134 (string-append "LDFLAGS="
1135 (string-join '("-lboost_filesystem"
1142 (modify-phases %standard-phases
1143 (add-after 'unpack 'do-not-build-bundled-pigz
1144 (lambda* (#:key inputs outputs #:allow-other-keys)
1145 (substitute* "Makefile"
1146 (("cd pigz/pigz-2.3.3; make") ""))
1148 (add-after 'unpack 'patch-paths-to-executables
1149 (lambda* (#:key inputs outputs #:allow-other-keys)
1150 (substitute* "parse_args.cpp"
1151 (("kmc_binary = .*")
1152 (string-append "kmc_binary = \""
1153 (assoc-ref outputs "out")
1155 (("pigz_binary = .*")
1156 (string-append "pigz_binary = \""
1157 (assoc-ref inputs "pigz")
1161 (lambda* (#:key outputs #:allow-other-keys)
1162 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1163 (for-each (lambda (file)
1164 (install-file file bin))
1165 '("bless" "kmc/bin/kmc"))
1167 (delete 'configure))))
1171 `(("openmpi" ,openmpi)
1173 ("sparsehash" ,sparsehash)
1176 (supported-systems '("x86_64-linux"))
1177 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1178 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1180 "@dfn{Bloom-filter-based error correction solution for high-throughput
1181 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1182 correction tool for genomic reads produced by @dfn{Next-generation
1183 sequencing} (NGS). BLESS produces accurate correction results with much less
1184 memory compared with previous solutions and is also able to tolerate a higher
1185 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1186 errors at the end of reads.")
1187 (license license:gpl3+)))
1189 (define-public bowtie
1195 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1197 (file-name (string-append name "-" version ".tar.gz"))
1200 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1201 (modules '((guix build utils)))
1203 '(substitute* "Makefile"
1204 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1205 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1206 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1207 (build-system gnu-build-system)
1210 ("perl-clone" ,perl-clone)
1211 ("perl-test-deep" ,perl-test-deep)
1212 ("perl-test-simple" ,perl-test-simple)
1213 ("python" ,python-2)
1220 (string-append "prefix=" (assoc-ref %outputs "out")))
1222 (modify-phases %standard-phases
1225 (lambda* (#:key outputs #:allow-other-keys)
1226 (zero? (system* "perl"
1227 "scripts/test/simple_tests.pl"
1228 "--bowtie2=./bowtie2"
1229 "--bowtie2-build=./bowtie2-build")))))))
1230 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1231 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1233 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1234 reads to long reference sequences. It is particularly good at aligning reads
1235 of about 50 up to 100s or 1,000s of characters, and particularly good at
1236 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1237 genome with an FM Index to keep its memory footprint small: for the human
1238 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1239 gapped, local, and paired-end alignment modes.")
1240 (supported-systems '("x86_64-linux"))
1241 (license license:gpl3+)))
1243 (define-public tophat
1250 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1254 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1255 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1256 (modules '((guix build utils)))
1259 ;; Remove bundled SeqAn and samtools
1260 (delete-file-recursively "src/SeqAn-1.3")
1261 (delete-file-recursively "src/samtools-0.1.18")
1263 (build-system gnu-build-system)
1265 '(#:parallel-build? #f ; not supported
1267 (modify-phases %standard-phases
1268 (add-after 'unpack 'use-system-samtools
1269 (lambda* (#:key inputs #:allow-other-keys)
1270 (substitute* "src/Makefile.in"
1271 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1272 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1273 (("SAMPROG = samtools_0\\.1\\.18") "")
1274 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1275 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1276 (substitute* '("src/common.cpp"
1278 (("samtools_0.1.18") (which "samtools")))
1279 (substitute* '("src/common.h"
1280 "src/bam2fastx.cpp")
1281 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1282 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1283 (substitute* '("src/bwt_map.h"
1285 "src/align_status.h")
1286 (("#include <bam.h>") "#include <samtools/bam.h>")
1287 (("#include <sam.h>") "#include <samtools/sam.h>"))
1292 ("samtools" ,samtools-0.1)
1293 ("ncurses" ,ncurses)
1294 ("python" ,python-2)
1298 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1299 (synopsis "Spliced read mapper for RNA-Seq data")
1301 "TopHat is a fast splice junction mapper for nucleotide sequence
1302 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1303 mammalian-sized genomes using the ultra high-throughput short read
1304 aligner Bowtie, and then analyzes the mapping results to identify
1305 splice junctions between exons.")
1306 ;; TopHat is released under the Boost Software License, Version 1.0
1307 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1308 (license license:boost1.0)))
1316 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1317 version ".tar.bz2"))
1320 "0585ikg0gv0mpyw9iq0bq9n0hr95867bbv8jbzs9pk4slkpsymig"))))
1321 (build-system gnu-build-system)
1323 '(#:tests? #f ;no "check" target
1327 (lambda* (#:key outputs #:allow-other-keys)
1328 (let ((bin (string-append
1329 (assoc-ref outputs "out") "/bin"))
1331 (assoc-ref outputs "out") "/share/doc/bwa"))
1333 (assoc-ref outputs "out") "/share/man/man1")))
1334 (install-file "bwa" bin)
1335 (install-file "README.md" doc)
1336 (install-file "bwa.1" man)))
1337 ;; no "configure" script
1338 (alist-delete 'configure %standard-phases))))
1339 (inputs `(("zlib" ,zlib)))
1340 ;; Non-portable SSE instructions are used so building fails on platforms
1341 ;; other than x86_64.
1342 (supported-systems '("x86_64-linux"))
1343 (home-page "http://bio-bwa.sourceforge.net/")
1344 (synopsis "Burrows-Wheeler sequence aligner")
1346 "BWA is a software package for mapping low-divergent sequences against a
1347 large reference genome, such as the human genome. It consists of three
1348 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1349 designed for Illumina sequence reads up to 100bp, while the rest two for
1350 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1351 features such as long-read support and split alignment, but BWA-MEM, which is
1352 the latest, is generally recommended for high-quality queries as it is faster
1353 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1354 70-100bp Illumina reads.")
1355 (license license:gpl3+)))
1357 (define-public bwa-pssm
1358 (package (inherit bwa)
1363 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1364 "archive/" version ".tar.gz"))
1365 (file-name (string-append name "-" version ".tar.gz"))
1368 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1369 (build-system gnu-build-system)
1374 (home-page "http://bwa-pssm.binf.ku.dk/")
1375 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1377 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1378 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1379 existing aligners it is fast and sensitive. Unlike most other aligners,
1380 however, it is also adaptible in the sense that one can direct the alignment
1381 based on known biases within the data set. It is coded as a modification of
1382 the original BWA alignment program and shares the genome index structure as
1383 well as many of the command line options.")
1384 (license license:gpl3+)))
1386 (define-public python2-bx-python
1388 (name "python2-bx-python")
1392 (uri (pypi-uri "bx-python" version))
1395 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1396 (modules '((guix build utils)))
1398 '(substitute* "setup.py"
1399 ;; remove dependency on outdated "distribute" module
1400 (("^from distribute_setup import use_setuptools") "")
1401 (("^use_setuptools\\(\\)") "")))))
1402 (build-system python-build-system)
1404 `(#:tests? #f ;tests fail because test data are not included
1405 #:python ,python-2))
1407 `(("python-numpy" ,python2-numpy)
1410 `(("python-nose" ,python2-nose)))
1411 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1412 (synopsis "Tools for manipulating biological data")
1414 "bx-python provides tools for manipulating biological data, particularly
1415 multiple sequence alignments.")
1416 (license license:expat)))
1418 (define-public python-pysam
1420 (name "python-pysam")
1421 (version "0.11.2.2")
1424 ;; Test data is missing on PyPi.
1426 "https://github.com/pysam-developers/pysam/archive/v"
1428 (file-name (string-append name "-" version ".tar.gz"))
1431 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1432 (modules '((guix build utils)))
1434 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1435 '(delete-file-recursively "htslib"))))
1436 (build-system python-build-system)
1438 `(#:modules ((ice-9 ftw)
1440 (guix build python-build-system)
1443 (modify-phases %standard-phases
1444 (add-before 'build 'set-flags
1445 (lambda* (#:key inputs #:allow-other-keys)
1446 (setenv "HTSLIB_MODE" "external")
1447 (setenv "HTSLIB_LIBRARY_DIR"
1448 (string-append (assoc-ref inputs "htslib") "/lib"))
1449 (setenv "HTSLIB_INCLUDE_DIR"
1450 (string-append (assoc-ref inputs "htslib") "/include"))
1451 (setenv "LDFLAGS" "-lncurses")
1452 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1455 (lambda* (#:key inputs outputs #:allow-other-keys)
1456 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1457 (setenv "PYTHONPATH"
1459 (getenv "PYTHONPATH")
1460 ":" (getcwd) "/build/"
1461 (car (scandir "build"
1462 (negate (cut string-prefix? "." <>))))))
1463 ;; Step out of source dir so python does not import from CWD.
1464 (with-directory-excursion "tests"
1465 (setenv "HOME" "/tmp")
1466 (and (zero? (system* "make" "-C" "pysam_data"))
1467 (zero? (system* "make" "-C" "cbcf_data"))
1468 ;; Running nosetests without explicitly asking for a
1469 ;; single process leads to a crash. Running with multiple
1470 ;; processes fails because the tests are not designed to
1473 ;; FIXME: tests keep timing out on some systems.
1474 ;; (zero? (system* "nosetests" "-v"
1475 ;; "--processes" "1"))
1478 `(("htslib" ,htslib))) ; Included from installed header files.
1480 `(("ncurses" ,ncurses)
1483 `(("python-cython" ,python-cython)
1484 ;; Dependencies below are are for tests only.
1485 ("samtools" ,samtools)
1486 ("bcftools" ,bcftools)
1487 ("python-nose" ,python-nose)))
1488 (home-page "https://github.com/pysam-developers/pysam")
1489 (synopsis "Python bindings to the SAMtools C API")
1491 "Pysam is a Python module for reading and manipulating files in the
1492 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1493 also includes an interface for tabix.")
1494 (license license:expat)))
1496 (define-public python2-pysam
1497 (package-with-python2 python-pysam))
1499 (define-public python-twobitreader
1501 (name "python-twobitreader")
1505 (uri (pypi-uri "twobitreader" version))
1508 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1509 (build-system python-build-system)
1511 '(;; Tests are not distributed in the PyPi release.
1512 ;; TODO Try building from the Git repo or asking the upstream maintainer
1513 ;; to distribute the tests on PyPi.
1516 `(("python-sphinx" ,python-sphinx)))
1517 (home-page "https://github.com/benjschiller/twobitreader")
1518 (synopsis "Python library for reading .2bit files")
1520 "twobitreader is a Python library for reading .2bit files as used by the
1521 UCSC genome browser.")
1522 (license license:artistic2.0)))
1524 (define-public python2-twobitreader
1525 (package-with-python2 python-twobitreader))
1527 (define-public python-plastid
1529 (name "python-plastid")
1533 (uri (pypi-uri "plastid" version))
1536 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1537 (build-system python-build-system)
1539 ;; Some test files are not included.
1542 `(("python-numpy" ,python-numpy)
1543 ("python-scipy" ,python-scipy)
1544 ("python-pandas" ,python-pandas)
1545 ("python-pysam" ,python-pysam)
1546 ("python-matplotlib" ,python-matplotlib)
1547 ("python-biopython" ,python-biopython)
1548 ("python-twobitreader" ,python-twobitreader)
1549 ("python-termcolor" ,python-termcolor)))
1551 `(("python-cython" ,python-cython)
1552 ("python-nose" ,python-nose)))
1553 (home-page "https://github.com/joshuagryphon/plastid")
1554 (synopsis "Python library for genomic analysis")
1556 "plastid is a Python library for genomic analysis – in particular,
1557 high-throughput sequencing data – with an emphasis on simplicity.")
1558 (license license:bsd-3)))
1560 (define-public python2-plastid
1561 (package-with-python2 python-plastid))
1563 (define-public cd-hit
1569 (uri (string-append "https://github.com/weizhongli/cdhit"
1570 "/releases/download/V" version
1572 "-2017-0621-source.tar.gz"))
1575 "1386dg2npx8p62wmv08mjzsd2z3waknb9j1gg3gkvblcy57hymnn"))))
1576 (build-system gnu-build-system)
1578 `(#:tests? #f ; there are no tests
1580 ;; Executables are copied directly to the PREFIX.
1581 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1583 (modify-phases %standard-phases
1584 ;; No "configure" script
1586 ;; Remove sources of non-determinism
1587 (add-after 'unpack 'be-timeless
1589 (substitute* "cdhit-utility.c++"
1590 ((" \\(built on \" __DATE__ \"\\)") ""))
1591 (substitute* "cdhit-common.c++"
1592 (("__DATE__") "\"0\"")
1593 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1595 ;; The "install" target does not create the target directory.
1596 (add-before 'install 'create-target-dir
1597 (lambda* (#:key outputs #:allow-other-keys)
1598 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1602 (home-page "http://weizhongli-lab.org/cd-hit/")
1603 (synopsis "Cluster and compare protein or nucleotide sequences")
1605 "CD-HIT is a program for clustering and comparing protein or nucleotide
1606 sequences. CD-HIT is designed to be fast and handle extremely large
1608 ;; The manual says: "It can be copied under the GNU General Public License
1609 ;; version 2 (GPLv2)."
1610 (license license:gpl2)))
1612 (define-public clipper
1619 "https://github.com/YeoLab/clipper/archive/"
1621 (file-name (string-append name "-" version ".tar.gz"))
1624 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1625 (modules '((guix build utils)))
1628 ;; remove unnecessary setup dependency
1629 (substitute* "setup.py"
1630 (("setup_requires = .*") ""))
1631 (for-each delete-file
1632 '("clipper/src/peaks.so"
1633 "clipper/src/readsToWiggle.so"))
1634 (delete-file-recursively "dist/")
1636 (build-system python-build-system)
1637 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1640 ("python-pybedtools" ,python2-pybedtools)
1641 ("python-cython" ,python2-cython)
1642 ("python-scikit-learn" ,python2-scikit-learn)
1643 ("python-matplotlib" ,python2-matplotlib)
1644 ("python-pandas" ,python2-pandas)
1645 ("python-pysam" ,python2-pysam)
1646 ("python-numpy" ,python2-numpy)
1647 ("python-scipy" ,python2-scipy)))
1649 `(("python-mock" ,python2-mock) ; for tests
1650 ("python-nose" ,python2-nose) ; for tests
1651 ("python-pytz" ,python2-pytz))) ; for tests
1652 (home-page "https://github.com/YeoLab/clipper")
1653 (synopsis "CLIP peak enrichment recognition")
1655 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1656 (license license:gpl2)))
1658 (define-public codingquarry
1660 (name "codingquarry")
1665 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1669 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1670 (build-system gnu-build-system)
1672 '(#:tests? #f ; no "check" target
1674 (modify-phases %standard-phases
1677 (lambda* (#:key outputs #:allow-other-keys)
1678 (let* ((out (assoc-ref outputs "out"))
1679 (bin (string-append out "/bin"))
1680 (doc (string-append out "/share/doc/codingquarry")))
1681 (install-file "INSTRUCTIONS.pdf" doc)
1682 (copy-recursively "QuarryFiles"
1683 (string-append out "/QuarryFiles"))
1684 (install-file "CodingQuarry" bin)
1685 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1686 (inputs `(("openmpi" ,openmpi)))
1687 (native-search-paths
1688 (list (search-path-specification
1689 (variable "QUARRY_PATH")
1690 (files '("QuarryFiles")))))
1691 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1692 (synopsis "Fungal gene predictor")
1693 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1694 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1695 (home-page "https://sourceforge.net/projects/codingquarry/")
1696 (license license:gpl3+)))
1698 (define-public couger
1705 "http://couger.oit.duke.edu/static/assets/COUGER"
1709 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1710 (build-system gnu-build-system)
1714 (modify-phases %standard-phases
1719 (lambda* (#:key outputs #:allow-other-keys)
1720 (let* ((out (assoc-ref outputs "out"))
1721 (bin (string-append out "/bin")))
1722 (copy-recursively "src" (string-append out "/src"))
1724 ;; Add "src" directory to module lookup path.
1725 (substitute* "couger"
1727 (string-append "import sys\nsys.path.append(\""
1728 out "\")\nfrom argparse")))
1729 (install-file "couger" bin))
1732 'install 'wrap-program
1733 (lambda* (#:key inputs outputs #:allow-other-keys)
1734 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1735 (let* ((out (assoc-ref outputs "out"))
1736 (path (getenv "PYTHONPATH")))
1737 (wrap-program (string-append out "/bin/couger")
1738 `("PYTHONPATH" ":" prefix (,path))))
1741 `(("python" ,python-2)
1742 ("python2-pillow" ,python2-pillow)
1743 ("python2-numpy" ,python2-numpy)
1744 ("python2-scipy" ,python2-scipy)
1745 ("python2-matplotlib" ,python2-matplotlib)))
1747 `(("r-minimal" ,r-minimal)
1749 ("randomjungle" ,randomjungle)))
1751 `(("unzip" ,unzip)))
1752 (home-page "http://couger.oit.duke.edu")
1753 (synopsis "Identify co-factors in sets of genomic regions")
1755 "COUGER can be applied to any two sets of genomic regions bound by
1756 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1757 putative co-factors that provide specificity to each TF. The framework
1758 determines the genomic targets uniquely-bound by each TF, and identifies a
1759 small set of co-factors that best explain the in vivo binding differences
1760 between the two TFs.
1762 COUGER uses classification algorithms (support vector machines and random
1763 forests) with features that reflect the DNA binding specificities of putative
1764 co-factors. The features are generated either from high-throughput TF-DNA
1765 binding data (from protein binding microarray experiments), or from large
1766 collections of DNA motifs.")
1767 (license license:gpl3+)))
1769 (define-public clustal-omega
1771 (name "clustal-omega")
1776 "http://www.clustal.org/omega/clustal-omega-"
1780 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1781 (build-system gnu-build-system)
1783 `(("argtable" ,argtable)))
1784 (home-page "http://www.clustal.org/omega/")
1785 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1787 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1788 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1789 of handling data-sets of hundreds of thousands of sequences in reasonable
1791 (license license:gpl2+)))
1793 (define-public crossmap
1799 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1803 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1804 ;; This patch has been sent upstream already and is available
1805 ;; for download from Sourceforge, but it has not been merged.
1806 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1807 (modules '((guix build utils)))
1808 ;; remove bundled copy of pysam
1810 '(delete-file-recursively "lib/pysam"))))
1811 (build-system python-build-system)
1813 `(#:python ,python-2
1817 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1820 `(("python-numpy" ,python2-numpy)
1821 ("python-pysam" ,python2-pysam)
1824 `(("python-cython" ,python2-cython)
1825 ("python-nose" ,python2-nose)))
1826 (home-page "http://crossmap.sourceforge.net/")
1827 (synopsis "Convert genome coordinates between assemblies")
1829 "CrossMap is a program for conversion of genome coordinates or annotation
1830 files between different genome assemblies. It supports most commonly used
1831 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1832 (license license:gpl2+)))
1834 (define-public cufflinks
1840 (uri (string-append "http://cole-trapnell-lab.github.io/"
1841 "cufflinks/assets/downloads/cufflinks-"
1845 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1846 (build-system gnu-build-system)
1850 ;; The includes for "eigen" are located in a subdirectory.
1851 (string-append "EIGEN_CPPFLAGS="
1852 "-I" (assoc-ref %build-inputs "eigen")
1854 ;; Cufflinks must be linked with various boost libraries.
1855 (string-append "LDFLAGS="
1856 (string-join '("-lboost_system"
1857 "-lboost_serialization"
1858 "-lboost_thread"))))
1860 (modify-phases %standard-phases
1861 (add-after 'unpack 'fix-search-for-bam
1863 (substitute* '("ax_bam.m4"
1866 (("<bam/sam\\.h>") "<samtools/sam.h>")
1867 (("<bam/bam\\.h>") "<samtools/bam.h>")
1868 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1871 (list (string-append "--with-bam="
1872 (assoc-ref %build-inputs "samtools")))))
1875 ("samtools" ,samtools-0.1)
1878 ("python" ,python-2)
1880 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1881 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1883 "Cufflinks assembles RNA transcripts, estimates their abundances,
1884 and tests for differential expression and regulation in RNA-Seq
1885 samples. It accepts aligned RNA-Seq reads and assembles the
1886 alignments into a parsimonious set of transcripts. Cufflinks then
1887 estimates the relative abundances of these transcripts based on how
1888 many reads support each one, taking into account biases in library
1889 preparation protocols.")
1890 (license license:boost1.0)))
1892 (define-public cutadapt
1899 "https://github.com/marcelm/cutadapt/archive/v"
1901 (file-name (string-append name "-" version ".tar.gz"))
1904 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1905 (build-system python-build-system)
1908 (modify-phases %standard-phases
1909 ;; The tests must be run after installation.
1911 (add-after 'install 'check
1912 (lambda* (#:key inputs outputs #:allow-other-keys)
1913 (setenv "PYTHONPATH"
1915 (getenv "PYTHONPATH")
1916 ":" (assoc-ref outputs "out")
1918 (string-take (string-take-right
1919 (assoc-ref inputs "python") 5) 3)
1921 (zero? (system* "nosetests" "-P" "tests")))))))
1923 `(("python-xopen" ,python-xopen)))
1925 `(("python-cython" ,python-cython)
1926 ("python-nose" ,python-nose)))
1927 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1928 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1930 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1931 other types of unwanted sequence from high-throughput sequencing reads.")
1932 (license license:expat)))
1934 (define-public libbigwig
1940 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1941 "archive/" version ".tar.gz"))
1942 (file-name (string-append name "-" version ".tar.gz"))
1945 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1946 (build-system gnu-build-system)
1948 `(#:test-target "test"
1951 (string-append "prefix=" (assoc-ref %outputs "out")))
1953 (modify-phases %standard-phases
1955 (add-before 'check 'disable-curl-test
1957 (substitute* "Makefile"
1958 (("./test/testRemote.*") ""))
1960 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1961 ;; there has not yet been a release containing this change.
1962 (add-before 'install 'create-target-dirs
1963 (lambda* (#:key outputs #:allow-other-keys)
1964 (let ((out (assoc-ref outputs "out")))
1965 (mkdir-p (string-append out "/lib"))
1966 (mkdir-p (string-append out "/include"))
1972 `(("doxygen" ,doxygen)))
1973 (home-page "https://github.com/dpryan79/libBigWig")
1974 (synopsis "C library for handling bigWig files")
1976 "This package provides a C library for parsing local and remote BigWig
1978 (license license:expat)))
1980 (define-public python-pybigwig
1982 (name "python-pybigwig")
1986 (uri (pypi-uri "pyBigWig" version))
1989 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1990 (modules '((guix build utils)))
1993 ;; Delete bundled libBigWig sources
1994 (delete-file-recursively "libBigWig")))))
1995 (build-system python-build-system)
1998 (modify-phases %standard-phases
1999 (add-after 'unpack 'link-with-libBigWig
2000 (lambda* (#:key inputs #:allow-other-keys)
2001 (substitute* "setup.py"
2002 (("libs=\\[") "libs=[\"BigWig\", "))
2005 `(("libbigwig" ,libbigwig)
2008 (home-page "https://github.com/dpryan79/pyBigWig")
2009 (synopsis "Access bigWig files in Python using libBigWig")
2011 "This package provides Python bindings to the libBigWig library for
2012 accessing bigWig files.")
2013 (license license:expat)))
2015 (define-public python2-pybigwig
2016 (package-with-python2 python-pybigwig))
2018 (define-public python-dendropy
2020 (name "python-dendropy")
2025 (uri (pypi-uri "DendroPy" version))
2028 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2029 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2030 (build-system python-build-system)
2031 (home-page "http://packages.python.org/DendroPy/")
2032 (synopsis "Library for phylogenetics and phylogenetic computing")
2034 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2035 writing, simulation, processing and manipulation of phylogenetic
2036 trees (phylogenies) and characters.")
2037 (license license:bsd-3)
2038 (properties `((python2-variant . ,(delay python2-dendropy))))))
2040 (define-public python2-dendropy
2041 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2045 `(#:python ,python-2
2047 (modify-phases %standard-phases
2049 ;; There is currently a test failure that only happens on some
2050 ;; systems, and only using "setup.py test"
2051 (lambda _ (zero? (system* "nosetests")))))))
2052 (native-inputs `(("python2-nose" ,python2-nose)
2053 ,@(package-native-inputs base))))))
2055 (define-public python-py2bit
2057 (name "python-py2bit")
2062 (uri (pypi-uri "py2bit" version))
2065 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2066 (build-system python-build-system)
2067 (home-page "https://github.com/dpryan79/py2bit")
2068 (synopsis "Access 2bit files using lib2bit")
2070 "This package provides Python bindings for lib2bit to access 2bit files
2072 (license license:expat)))
2074 (define-public deeptools
2080 (uri (string-append "https://github.com/fidelram/deepTools/"
2081 "archive/" version ".tar.gz"))
2082 (file-name (string-append name "-" version ".tar.gz"))
2085 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2086 (build-system python-build-system)
2088 `(("python-scipy" ,python-scipy)
2089 ("python-numpy" ,python-numpy)
2090 ("python-numpydoc" ,python-numpydoc)
2091 ("python-matplotlib" ,python-matplotlib)
2092 ("python-pysam" ,python-pysam)
2093 ("python-py2bit" ,python-py2bit)
2094 ("python-pybigwig" ,python-pybigwig)))
2096 `(("python-mock" ,python-mock) ;for tests
2097 ("python-nose" ,python-nose) ;for tests
2098 ("python-pytz" ,python-pytz))) ;for tests
2099 (home-page "https://github.com/fidelram/deepTools")
2100 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2102 "DeepTools addresses the challenge of handling the large amounts of data
2103 that are now routinely generated from DNA sequencing centers. To do so,
2104 deepTools contains useful modules to process the mapped reads data to create
2105 coverage files in standard bedGraph and bigWig file formats. By doing so,
2106 deepTools allows the creation of normalized coverage files or the comparison
2107 between two files (for example, treatment and control). Finally, using such
2108 normalized and standardized files, multiple visualizations can be created to
2109 identify enrichments with functional annotations of the genome.")
2110 (license license:gpl3+)))
2112 (define-public diamond
2119 "https://github.com/bbuchfink/diamond/archive/v"
2121 (file-name (string-append name "-" version ".tar.gz"))
2124 "04i03046g3l2vk9722z47r1p7j415g97vvz6d76ywmbawyiihcb1"))))
2125 (build-system cmake-build-system)
2127 '(#:tests? #f ; no "check" target
2129 (modify-phases %standard-phases
2130 (add-after 'unpack 'remove-native-compilation
2132 (substitute* "CMakeLists.txt" (("-march=native") ""))
2136 (home-page "https://github.com/bbuchfink/diamond")
2137 (synopsis "Accelerated BLAST compatible local sequence aligner")
2139 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2140 translated DNA query sequences against a protein reference database (BLASTP
2141 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2142 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2143 data and settings.")
2144 (license license:agpl3+)))
2146 (define-public discrover
2153 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2155 (file-name (string-append name "-" version ".tar.gz"))
2158 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2159 (build-system cmake-build-system)
2161 `(#:tests? #f ; there are no tests
2163 (modify-phases %standard-phases
2164 (add-after 'unpack 'add-missing-includes
2166 (substitute* "src/executioninformation.hpp"
2167 (("#define EXECUTIONINFORMATION_HPP" line)
2168 (string-append line "\n#include <random>")))
2169 (substitute* "src/plasma/fasta.hpp"
2170 (("#define FASTA_HPP" line)
2171 (string-append line "\n#include <random>")))
2177 `(("texlive" ,texlive)
2178 ("imagemagick" ,imagemagick)))
2179 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2180 (synopsis "Discover discriminative nucleotide sequence motifs")
2181 (description "Discrover is a motif discovery method to find binding sites
2182 of nucleic acid binding proteins.")
2183 (license license:gpl3+)))
2185 (define-public eigensoft
2186 (let ((revision "1")
2187 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2190 (version (string-append "6.1.2-"
2192 (string-take commit 9)))
2197 (url "https://github.com/DReichLab/EIG.git")
2199 (file-name (string-append "eigensoft-" commit "-checkout"))
2202 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2203 (modules '((guix build utils)))
2204 ;; Remove pre-built binaries.
2206 (delete-file-recursively "bin")
2209 (build-system gnu-build-system)
2211 `(#:tests? #f ; There are no tests.
2212 #:make-flags '("CC=gcc")
2214 (modify-phases %standard-phases
2215 ;; There is no configure phase, but the Makefile is in a
2220 ;; The link flags are incomplete.
2221 (substitute* "Makefile"
2222 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2224 ;; The provided install target only copies executables to
2225 ;; the "bin" directory in the build root.
2226 (add-after 'install 'actually-install
2227 (lambda* (#:key outputs #:allow-other-keys)
2228 (let* ((out (assoc-ref outputs "out"))
2229 (bin (string-append out "/bin")))
2230 (for-each (lambda (file)
2231 (install-file file bin))
2232 (find-files "../bin" ".*"))
2237 ("openblas" ,openblas)
2239 ("gfortran" ,gfortran "lib")))
2240 (home-page "https://github.com/DReichLab/EIG")
2241 (synopsis "Tools for population genetics")
2242 (description "The EIGENSOFT package provides tools for population
2243 genetics and stratification correction. EIGENSOFT implements methods commonly
2244 used in population genetics analyses such as PCA, computation of Tracy-Widom
2245 statistics, and finding related individuals in structured populations. It
2246 comes with a built-in plotting script and supports multiple file formats and
2247 quantitative phenotypes.")
2248 ;; The license of the eigensoft tools is Expat, but since it's
2249 ;; linking with the GNU Scientific Library (GSL) the effective
2250 ;; license is the GPL.
2251 (license license:gpl3+))))
2253 (define-public edirect
2259 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2260 "versions/2016-05-03/edirect.tar.gz"))
2263 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2264 (build-system perl-build-system)
2266 `(#:tests? #f ;no "check" target
2268 (modify-phases %standard-phases
2272 (lambda* (#:key outputs #:allow-other-keys)
2273 (let ((target (string-append (assoc-ref outputs "out")
2276 (install-file "edirect.pl" target)
2279 'install 'wrap-program
2280 (lambda* (#:key inputs outputs #:allow-other-keys)
2281 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2282 (let* ((out (assoc-ref outputs "out"))
2283 (path (getenv "PERL5LIB")))
2284 (wrap-program (string-append out "/bin/edirect.pl")
2285 `("PERL5LIB" ":" prefix (,path)))))))))
2287 `(("perl-html-parser" ,perl-html-parser)
2288 ("perl-encode-locale" ,perl-encode-locale)
2289 ("perl-file-listing" ,perl-file-listing)
2290 ("perl-html-tagset" ,perl-html-tagset)
2291 ("perl-html-tree" ,perl-html-tree)
2292 ("perl-http-cookies" ,perl-http-cookies)
2293 ("perl-http-date" ,perl-http-date)
2294 ("perl-http-message" ,perl-http-message)
2295 ("perl-http-negotiate" ,perl-http-negotiate)
2296 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2297 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2298 ("perl-net-http" ,perl-net-http)
2299 ("perl-uri" ,perl-uri)
2300 ("perl-www-robotrules" ,perl-www-robotrules)
2302 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2303 (synopsis "Tools for accessing the NCBI's set of databases")
2305 "Entrez Direct (EDirect) is a method for accessing the National Center
2306 for Biotechnology Information's (NCBI) set of interconnected
2307 databases (publication, sequence, structure, gene, variation, expression,
2308 etc.) from a terminal. Functions take search terms from command-line
2309 arguments. Individual operations are combined to build multi-step queries.
2310 Record retrieval and formatting normally complete the process.
2312 EDirect also provides an argument-driven function that simplifies the
2313 extraction of data from document summaries or other results that are returned
2314 in structured XML format. This can eliminate the need for writing custom
2315 software to answer ad hoc questions.")
2316 (license license:public-domain)))
2318 (define-public exonerate
2327 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2328 "exonerate-" version ".tar.gz"))
2331 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2332 (build-system gnu-build-system)
2334 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2336 `(("pkg-config" ,pkg-config)))
2340 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2341 (synopsis "Generic tool for biological sequence alignment")
2343 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2344 the alignment of sequences using a many alignment models, either exhaustive
2345 dynamic programming or a variety of heuristics.")
2346 (license license:gpl3)))
2348 (define-public express
2356 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2357 version "/express-" version "-src.tgz"))
2360 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2361 (build-system cmake-build-system)
2363 `(#:tests? #f ;no "check" target
2366 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2367 (lambda* (#:key inputs #:allow-other-keys)
2368 (substitute* "CMakeLists.txt"
2369 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2370 "set(Boost_USE_STATIC_LIBS OFF)")
2371 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2372 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2373 (substitute* "src/CMakeLists.txt"
2374 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2375 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2380 ("bamtools" ,bamtools)
2381 ("protobuf" ,protobuf)
2383 (home-page "http://bio.math.berkeley.edu/eXpress")
2384 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2386 "eXpress is a streaming tool for quantifying the abundances of a set of
2387 target sequences from sampled subsequences. Example applications include
2388 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2389 analysis (from RNA-Seq), transcription factor binding quantification in
2390 ChIP-Seq, and analysis of metagenomic data.")
2391 (license license:artistic2.0)))
2393 (define-public express-beta-diversity
2395 (name "express-beta-diversity")
2401 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2403 (file-name (string-append name "-" version ".tar.gz"))
2406 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2407 (build-system gnu-build-system)
2410 (modify-phases %standard-phases
2412 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2414 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2416 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2418 (lambda* (#:key outputs #:allow-other-keys)
2419 (let ((bin (string-append (assoc-ref outputs "out")
2422 (install-file "scripts/convertToEBD.py" bin)
2423 (install-file "bin/ExpressBetaDiversity" bin)
2426 `(("python" ,python-2)))
2427 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2428 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2430 "Express Beta Diversity (EBD) calculates ecological beta diversity
2431 (dissimilarity) measures between biological communities. EBD implements a
2432 variety of diversity measures including those that make use of phylogenetic
2433 similarity of community members.")
2434 (license license:gpl3+)))
2436 (define-public fasttree
2443 "http://www.microbesonline.org/fasttree/FastTree-"
2447 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2448 (build-system gnu-build-system)
2450 `(#:tests? #f ; no "check" target
2452 (modify-phases %standard-phases
2456 (lambda* (#:key source #:allow-other-keys)
2457 (and (zero? (system* "gcc"
2459 "-finline-functions"
2466 (zero? (system* "gcc"
2470 "-finline-functions"
2478 (lambda* (#:key outputs #:allow-other-keys)
2479 (let ((bin (string-append (assoc-ref outputs "out")
2482 (install-file "FastTree" bin)
2483 (install-file "FastTreeMP" bin)
2485 (home-page "http://www.microbesonline.org/fasttree")
2486 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2488 "FastTree can handle alignments with up to a million of sequences in a
2489 reasonable amount of time and memory. For large alignments, FastTree is
2490 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2491 (license license:gpl2+)))
2493 (define-public fastx-toolkit
2495 (name "fastx-toolkit")
2501 "https://github.com/agordon/fastx_toolkit/releases/download/"
2502 version "/fastx_toolkit-" version ".tar.bz2"))
2505 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2506 (build-system gnu-build-system)
2508 `(("libgtextutils" ,libgtextutils)))
2510 `(("pkg-config" ,pkg-config)))
2511 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2512 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2514 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2515 FASTA/FASTQ files preprocessing.
2517 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2518 containing multiple short-reads sequences. The main processing of such
2519 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2520 is sometimes more productive to preprocess the files before mapping the
2521 sequences to the genome---manipulating the sequences to produce better mapping
2522 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2523 (license license:agpl3+)))
2525 (define-public flexbar
2532 (string-append "mirror://sourceforge/flexbar/"
2533 version "/flexbar_v" version "_src.tgz"))
2536 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2537 (build-system cmake-build-system)
2539 `(#:configure-flags (list
2540 (string-append "-DFLEXBAR_BINARY_DIR="
2541 (assoc-ref %outputs "out")
2546 (lambda* (#:key outputs #:allow-other-keys)
2547 (setenv "PATH" (string-append
2548 (assoc-ref outputs "out") "/bin:"
2550 (chdir "../flexbar_v2.5_src/test")
2551 (zero? (system* "bash" "flexbar_validate.sh")))
2552 (alist-delete 'install %standard-phases))))
2557 `(("pkg-config" ,pkg-config)
2559 (home-page "http://flexbar.sourceforge.net")
2560 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2562 "Flexbar preprocesses high-throughput nucleotide sequencing data
2563 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2564 Moreover, trimming and filtering features are provided. Flexbar increases
2565 read mapping rates and improves genome and transcriptome assemblies. It
2566 supports next-generation sequencing data in fasta/q and csfasta/q format from
2567 Illumina, Roche 454, and the SOLiD platform.")
2568 (license license:gpl3)))
2570 (define-public fraggenescan
2572 (name "fraggenescan")
2578 (string-append "mirror://sourceforge/fraggenescan/"
2579 "FragGeneScan" version ".tar.gz"))
2581 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2582 (build-system gnu-build-system)
2585 (modify-phases %standard-phases
2587 (add-before 'build 'patch-paths
2588 (lambda* (#:key outputs #:allow-other-keys)
2589 (let* ((out (string-append (assoc-ref outputs "out")))
2590 (share (string-append out "/share/fraggenescan/")))
2591 (substitute* "run_FragGeneScan.pl"
2593 (string-append "system(\"" (which "rm")))
2595 (string-append "system(\"" (which "mv")))
2596 (("\\\"awk") (string-append "\"" (which "awk")))
2597 ;; This script and other programs expect the training files
2598 ;; to be in the non-standard location bin/train/XXX. Change
2599 ;; this to be share/fraggenescan/train/XXX instead.
2600 (("^\\$train.file = \\$dir.*")
2601 (string-append "$train_file = \""
2603 "train/\".$FGS_train_file;")))
2604 (substitute* "run_hmm.c"
2605 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2606 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2609 (lambda _ (and (zero? (system* "make" "clean"))
2610 (zero? (system* "make" "fgs")))))
2612 (lambda* (#:key outputs #:allow-other-keys)
2613 (let* ((out (string-append (assoc-ref outputs "out")))
2614 (bin (string-append out "/bin/"))
2615 (share (string-append out "/share/fraggenescan/train")))
2616 (install-file "run_FragGeneScan.pl" bin)
2617 (install-file "FragGeneScan" bin)
2618 (copy-recursively "train" share))))
2620 (add-after 'install 'post-install-check
2621 ;; In lieu of 'make check', run one of the examples and check the
2622 ;; output files gets created.
2623 (lambda* (#:key outputs #:allow-other-keys)
2624 (let* ((out (string-append (assoc-ref outputs "out")))
2625 (bin (string-append out "/bin/"))
2626 (frag (string-append bin "run_FragGeneScan.pl")))
2627 (and (zero? (system* frag ; Test complete genome.
2628 "-genome=./example/NC_000913.fna"
2632 (file-exists? "test2.faa")
2633 (file-exists? "test2.ffn")
2634 (file-exists? "test2.gff")
2635 (file-exists? "test2.out")
2636 (zero? (system* ; Test incomplete sequences.
2638 "-genome=./example/NC_000913-fgs.ffn"
2641 "-train=454_30")))))))))
2644 ("python" ,python-2))) ;not compatible with python 3.
2645 (home-page "https://sourceforge.net/projects/fraggenescan/")
2646 (synopsis "Finds potentially fragmented genes in short reads")
2648 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2649 short and error-prone DNA sequencing reads. It can also be applied to predict
2650 genes in incomplete assemblies or complete genomes.")
2651 ;; GPL3+ according to private correspondense with the authors.
2652 (license license:gpl3+)))
2654 (define-public fxtract
2655 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2663 "https://github.com/ctSkennerton/fxtract/archive/"
2665 (file-name (string-append "ctstennerton-util-"
2666 (string-take util-commit 7)
2670 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2671 (build-system gnu-build-system)
2673 `(#:make-flags (list
2674 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2676 #:test-target "fxtract_test"
2678 (modify-phases %standard-phases
2680 (add-before 'build 'copy-util
2681 (lambda* (#:key inputs #:allow-other-keys)
2683 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2685 ;; Do not use make install as this requires additional dependencies.
2687 (lambda* (#:key outputs #:allow-other-keys)
2688 (let* ((out (assoc-ref outputs "out"))
2689 (bin (string-append out"/bin")))
2690 (install-file "fxtract" bin)
2696 ;; ctskennerton-util is licensed under GPL2.
2697 `(("ctskennerton-util"
2701 (url "https://github.com/ctSkennerton/util.git")
2702 (commit util-commit)))
2703 (file-name (string-append
2704 "ctstennerton-util-" util-commit "-checkout"))
2707 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2708 (home-page "https://github.com/ctSkennerton/fxtract")
2709 (synopsis "Extract sequences from FASTA and FASTQ files")
2711 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2712 or FASTQ) file given a subsequence. It uses a simple substring search for
2713 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2714 lookups or multi-pattern searching as required. By default fxtract looks in
2715 the sequence of each record but can also be told to look in the header,
2716 comment or quality sections.")
2717 ;; 'util' requires SSE instructions.
2718 (supported-systems '("x86_64-linux"))
2719 (license license:expat))))
2721 (define-public gemma
2727 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2729 (file-name (string-append name "-" version ".tar.gz"))
2732 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2733 (patches (search-patches "gemma-intel-compat.patch"))))
2738 (build-system gnu-build-system)
2741 '(,@(match (%current-system)
2743 '("FORCE_DYNAMIC=1"))
2745 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2747 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2749 (modify-phases %standard-phases
2751 (add-before 'build 'bin-mkdir
2756 (lambda* (#:key outputs #:allow-other-keys)
2757 (let ((out (assoc-ref outputs "out")))
2758 (install-file "bin/gemma"
2762 #:tests? #f)) ; no tests included yet
2763 (home-page "https://github.com/xiangzhou/GEMMA")
2764 (synopsis "Tool for genome-wide efficient mixed model association")
2766 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2767 standard linear mixed model resolver with application in genome-wide
2768 association studies (GWAS).")
2769 (license license:gpl3)))
2778 "https://github.com/nboley/grit/archive/"
2780 (file-name (string-append name "-" version ".tar.gz"))
2783 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2784 (build-system python-build-system)
2786 `(#:python ,python-2
2789 'unpack 'generate-from-cython-sources
2790 (lambda* (#:key inputs outputs #:allow-other-keys)
2791 ;; Delete these C files to force fresh generation from pyx sources.
2792 (delete-file "grit/sparsify_support_fns.c")
2793 (delete-file "grit/call_peaks_support_fns.c")
2794 (substitute* "setup.py"
2795 (("Cython.Setup") "Cython.Build")
2796 ;; Add numpy include path to fix compilation
2798 (string-append "pyx\", ], include_dirs = ['"
2799 (assoc-ref inputs "python-numpy")
2800 "/lib/python2.7/site-packages/numpy/core/include/"
2804 `(("python-scipy" ,python2-scipy)
2805 ("python-numpy" ,python2-numpy)
2806 ("python-pysam" ,python2-pysam)
2807 ("python-networkx" ,python2-networkx)))
2809 `(("python-cython" ,python2-cython)))
2810 (home-page "http://grit-bio.org")
2811 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2813 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2814 full length transcript models. When none of these data sources are available,
2815 GRIT can be run by providing a candidate set of TES or TSS sites. In
2816 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2817 also be run in quantification mode, where it uses a provided GTF file and just
2818 estimates transcript expression.")
2819 (license license:gpl3+)))
2821 (define-public hisat
2828 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2829 version "-beta-source.zip"))
2832 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2833 (build-system gnu-build-system)
2835 `(#:tests? #f ;no check target
2836 #:make-flags '("allall"
2837 ;; Disable unsupported `popcnt' instructions on
2838 ;; architectures other than x86_64
2839 ,@(if (string-prefix? "x86_64"
2840 (or (%current-target-system)
2843 '("POPCNT_CAPABILITY=0")))
2846 'unpack 'patch-sources
2848 ;; XXX Cannot use snippet because zip files are not supported
2849 (substitute* "Makefile"
2850 (("^CC = .*$") "CC = gcc")
2851 (("^CPP = .*$") "CPP = g++")
2852 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2853 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2854 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2855 (substitute* '("hisat-build" "hisat-inspect")
2856 (("/usr/bin/env") (which "env"))))
2859 (lambda* (#:key outputs #:allow-other-keys)
2860 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2861 (for-each (lambda (file)
2862 (install-file file bin))
2865 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2866 (alist-delete 'configure %standard-phases)))))
2868 `(("unzip" ,unzip)))
2873 ;; Non-portable SSE instructions are used so building fails on platforms
2874 ;; other than x86_64.
2875 (supported-systems '("x86_64-linux"))
2876 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2877 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2879 "HISAT is a fast and sensitive spliced alignment program for mapping
2880 RNA-seq reads. In addition to one global FM index that represents a whole
2881 genome, HISAT uses a large set of small FM indexes that collectively cover the
2882 whole genome. These small indexes (called local indexes) combined with
2883 several alignment strategies enable effective alignment of RNA-seq reads, in
2884 particular, reads spanning multiple exons.")
2885 (license license:gpl3+)))
2887 (define-public hisat2
2894 ;; FIXME: a better source URL is
2895 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2896 ;; "/downloads/hisat2-" version "-source.zip")
2897 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2898 ;; but it is currently unavailable.
2899 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2900 (file-name (string-append name "-" version ".tar.gz"))
2903 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2904 (build-system gnu-build-system)
2906 `(#:tests? #f ; no check target
2907 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2908 #:modules ((guix build gnu-build-system)
2912 (modify-phases %standard-phases
2913 (add-after 'unpack 'make-deterministic
2915 (substitute* "Makefile"
2920 (lambda* (#:key outputs #:allow-other-keys)
2921 (let* ((out (assoc-ref outputs "out"))
2922 (bin (string-append out "/bin/"))
2923 (doc (string-append out "/share/doc/hisat2/")))
2925 (cut install-file <> bin)
2927 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2929 (install-file "doc/manual.inc.html" doc))
2932 `(("unzip" ,unzip) ; needed for archive from ftp
2934 ("pandoc" ,ghc-pandoc))) ; for documentation
2935 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2936 (synopsis "Graph-based alignment of genomic sequencing reads")
2937 (description "HISAT2 is a fast and sensitive alignment program for mapping
2938 next-generation sequencing reads (both DNA and RNA) to a population of human
2939 genomes (as well as to a single reference genome). In addition to using one
2940 global @dfn{graph FM} (GFM) index that represents a population of human
2941 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2942 the whole genome. These small indexes, combined with several alignment
2943 strategies, enable rapid and accurate alignment of sequencing reads. This new
2944 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2945 ;; HISAT2 contains files from Bowtie2, which is released under
2946 ;; GPLv2 or later. The HISAT2 source files are released under
2948 (license license:gpl3+)))
2950 (define-public hmmer
2958 "http://eddylab.org/software/hmmer"
2959 (version-prefix version 1) "/"
2960 version "/hmmer-" version ".tar.gz"))
2963 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2964 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2965 (build-system gnu-build-system)
2966 (native-inputs `(("perl" ,perl)))
2967 (home-page "http://hmmer.org/")
2968 (synopsis "Biosequence analysis using profile hidden Markov models")
2970 "HMMER is used for searching sequence databases for homologs of protein
2971 sequences, and for making protein sequence alignments. It implements methods
2972 using probabilistic models called profile hidden Markov models (profile
2974 (license (list license:gpl3+
2975 ;; The bundled library 'easel' is distributed
2976 ;; under The Janelia Farm Software License.
2977 (license:non-copyleft
2978 "file://easel/LICENSE"
2979 "See easel/LICENSE in the distribution.")))))
2981 (define-public htseq
2988 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2992 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2993 (build-system python-build-system)
2994 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2995 ;; Numpy needs to be propagated when htseq is used as a Python library.
2997 `(("python-numpy" ,python2-numpy)))
2999 `(("python-pysam" ,python2-pysam)))
3000 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3001 (synopsis "Analysing high-throughput sequencing data with Python")
3003 "HTSeq is a Python package that provides infrastructure to process data
3004 from high-throughput sequencing assays.")
3005 (license license:gpl3+)))
3007 (define-public java-htsjdk
3009 (name "java-htsjdk")
3014 "https://github.com/samtools/htsjdk/archive/"
3016 (file-name (string-append name "-" version ".tar.gz"))
3019 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
3020 (modules '((guix build utils)))
3021 ;; remove build dependency on git
3022 (snippet '(substitute* "build.xml"
3023 (("failifexecutionfails=\"true\"")
3024 "failifexecutionfails=\"false\"")))))
3025 (build-system ant-build-system)
3027 `(#:tests? #f ; test require Internet access
3029 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3030 "/share/java/htsjdk/"))
3031 #:build-target "all"
3033 (modify-phases %standard-phases
3034 ;; The build phase also installs the jars
3035 (delete 'install))))
3036 (home-page "http://samtools.github.io/htsjdk/")
3037 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3039 "HTSJDK is an implementation of a unified Java library for accessing
3040 common file formats, such as SAM and VCF, used for high-throughput
3041 sequencing (HTS) data. There are also an number of useful utilities for
3042 manipulating HTS data.")
3043 (license license:expat)))
3045 (define-public htslib
3052 "https://github.com/samtools/htslib/releases/download/"
3053 version "/htslib-" version ".tar.bz2"))
3056 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3057 (build-system gnu-build-system)
3060 (modify-phases %standard-phases
3062 'unpack 'patch-tests
3064 (substitute* "test/test.pl"
3065 (("/bin/bash") (which "bash")))
3068 `(("openssl" ,openssl)
3073 (home-page "http://www.htslib.org")
3074 (synopsis "C library for reading/writing high-throughput sequencing data")
3076 "HTSlib is a C library for reading/writing high-throughput sequencing
3077 data. It also provides the bgzip, htsfile, and tabix utilities.")
3078 ;; Files under cram/ are released under the modified BSD license;
3079 ;; the rest is released under the Expat license
3080 (license (list license:expat license:bsd-3))))
3082 ;; This package should be removed once no packages rely upon it.
3090 "https://github.com/samtools/htslib/releases/download/"
3091 version "/htslib-" version ".tar.bz2"))
3094 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3103 "https://github.com/nboley/idr/archive/"
3105 (file-name (string-append name "-" version ".tar.gz"))
3108 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3109 (build-system python-build-system)
3111 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3113 `(("python-scipy" ,python-scipy)
3114 ("python-sympy" ,python-sympy)
3115 ("python-numpy" ,python-numpy)
3116 ("python-matplotlib" ,python-matplotlib)))
3118 `(("python-cython" ,python-cython)))
3119 (home-page "https://github.com/nboley/idr")
3120 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3122 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3123 to measure the reproducibility of findings identified from replicate
3124 experiments and provide highly stable thresholds based on reproducibility.")
3125 (license license:gpl3+)))
3127 (define-public jellyfish
3133 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3134 "releases/download/v" version
3135 "/jellyfish-" version ".tar.gz"))
3138 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3139 (build-system gnu-build-system)
3140 (outputs '("out" ;for library
3141 "ruby" ;for Ruby bindings
3142 "python")) ;for Python bindings
3145 (list (string-append "--enable-ruby-binding="
3146 (assoc-ref %outputs "ruby"))
3147 (string-append "--enable-python-binding="
3148 (assoc-ref %outputs "python")))
3150 (modify-phases %standard-phases
3151 (add-before 'check 'set-SHELL-variable
3153 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3155 (setenv "SHELL" (which "bash"))
3161 ("python" ,python-2)))
3162 (synopsis "Tool for fast counting of k-mers in DNA")
3164 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3165 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3166 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3167 is a command-line program that reads FASTA and multi-FASTA files containing
3168 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3169 translated into a human-readable text format using the @code{jellyfish dump}
3170 command, or queried for specific k-mers with @code{jellyfish query}.")
3171 (home-page "http://www.genome.umd.edu/jellyfish.html")
3172 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3173 (supported-systems '("x86_64-linux"))
3174 ;; The combined work is published under the GPLv3 or later. Individual
3175 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3176 (license (list license:gpl3+ license:expat))))
3178 (define-public khmer
3185 (uri (pypi-uri "khmer" version))
3188 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3189 (patches (search-patches "khmer-use-libraries.patch"))))
3190 (build-system python-build-system)
3193 (modify-phases %standard-phases
3194 (add-after 'unpack 'set-paths
3195 (lambda* (#:key inputs outputs #:allow-other-keys)
3196 ;; Delete bundled libraries.
3197 (delete-file-recursively "third-party/zlib")
3198 (delete-file-recursively "third-party/bzip2")
3199 ;; Replace bundled seqan.
3200 (let* ((seqan-all "third-party/seqan")
3201 (seqan-include (string-append
3202 seqan-all "/core/include")))
3203 (delete-file-recursively seqan-all)
3204 (copy-recursively (string-append (assoc-ref inputs "seqan")
3206 (string-append seqan-include "/seqan")))
3207 ;; We do not replace the bundled MurmurHash as the canonical
3208 ;; repository for this code 'SMHasher' is unsuitable for
3209 ;; providing a library. See
3210 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3212 (add-after 'unpack 'set-cc
3216 ;; It is simpler to test after installation.
3218 (add-after 'install 'post-install-check
3219 (lambda* (#:key inputs outputs #:allow-other-keys)
3220 (let ((out (assoc-ref outputs "out")))
3225 (assoc-ref outputs "out")
3227 (setenv "PYTHONPATH"
3229 (getenv "PYTHONPATH")
3233 (string-take (string-take-right
3234 (assoc-ref inputs "python") 5) 3)
3236 (with-directory-excursion "build"
3237 (zero? (system* "nosetests" "khmer" "--attr"
3238 "!known_failing")))))))))
3241 ("python-nose" ,python-nose)))
3245 ("python-screed" ,python-screed)
3246 ("python-bz2file" ,python-bz2file)
3247 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3248 ;; until the next version of khmer (likely 2.1) is released.
3250 (home-page "https://khmer.readthedocs.org/")
3251 (synopsis "K-mer counting, filtering and graph traversal library")
3252 (description "The khmer software is a set of command-line tools for
3253 working with DNA shotgun sequencing data from genomes, transcriptomes,
3254 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3255 sometimes better. Khmer can also identify and fix problems with shotgun
3257 ;; When building on i686, armhf and mips64el, we get the following error:
3258 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3259 (supported-systems '("x86_64-linux"))
3260 (license license:bsd-3)))
3262 (define-public kaiju
3269 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3271 (file-name (string-append name "-" version ".tar.gz"))
3274 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3275 (build-system gnu-build-system)
3277 `(#:tests? #f ; There are no tests.
3279 (modify-phases %standard-phases
3281 (add-before 'build 'move-to-src-dir
3282 (lambda _ (chdir "src") #t))
3284 (lambda* (#:key inputs outputs #:allow-other-keys)
3285 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3288 (copy-recursively "bin" bin)
3289 (copy-recursively "util" bin))
3293 (home-page "http://kaiju.binf.ku.dk/")
3294 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3295 (description "Kaiju is a program for sensitive taxonomic classification
3296 of high-throughput sequencing reads from metagenomic whole genome sequencing
3298 (license license:gpl3+)))
3303 (version "2.1.0.20151222")
3306 (uri (pypi-uri "MACS2" version))
3309 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3310 (build-system python-build-system)
3312 `(#:python ,python-2 ; only compatible with Python 2.7
3313 #:tests? #f)) ; no test target
3315 `(("python-numpy" ,python2-numpy)))
3316 (home-page "https://github.com/taoliu/MACS/")
3317 (synopsis "Model based analysis for ChIP-Seq data")
3319 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3320 identifying transcript factor binding sites named Model-based Analysis of
3321 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3322 the significance of enriched ChIP regions and it improves the spatial
3323 resolution of binding sites through combining the information of both
3324 sequencing tag position and orientation.")
3325 (license license:bsd-3)))
3327 (define-public mafft
3334 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3335 "-without-extensions-src.tgz"))
3336 (file-name (string-append name "-" version ".tgz"))
3339 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3340 (build-system gnu-build-system)
3342 `(#:tests? #f ; no automated tests, though there are tests in the read me
3343 #:make-flags (let ((out (assoc-ref %outputs "out")))
3344 (list (string-append "PREFIX=" out)
3345 (string-append "BINDIR="
3346 (string-append out "/bin"))))
3348 (modify-phases %standard-phases
3349 (add-after 'unpack 'enter-dir
3350 (lambda _ (chdir "core") #t))
3351 (add-after 'enter-dir 'patch-makefile
3353 ;; on advice from the MAFFT authors, there is no need to
3354 ;; distribute mafft-profile, mafft-distance, or
3355 ;; mafft-homologs.rb as they are too "specialised".
3356 (substitute* "Makefile"
3357 ;; remove mafft-homologs.rb from SCRIPTS
3358 (("^SCRIPTS = mafft mafft-homologs.rb")
3360 ;; remove mafft-homologs from MANPAGES
3361 (("^MANPAGES = mafft.1 mafft-homologs.1")
3362 "MANPAGES = mafft.1")
3363 ;; remove mafft-distance from PROGS
3364 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3365 "PROGS = dvtditr dndfast7 dndblast sextet5")
3366 ;; remove mafft-profile from PROGS
3367 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3368 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3369 (("^rm -f mafft-profile mafft-profile.exe") "#")
3370 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3371 ;; do not install MAN pages in libexec folder
3372 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3373 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3375 (add-after 'enter-dir 'patch-paths
3376 (lambda* (#:key inputs #:allow-other-keys)
3377 (substitute* '("pairash.c"
3379 (("perl") (which "perl"))
3380 (("([\"`| ])awk" _ prefix)
3381 (string-append prefix (which "awk")))
3382 (("grep") (which "grep")))
3385 (add-after 'install 'wrap-programs
3386 (lambda* (#:key outputs #:allow-other-keys)
3387 (let* ((out (assoc-ref outputs "out"))
3388 (bin (string-append out "/bin"))
3389 (path (string-append
3390 (assoc-ref %build-inputs "coreutils") "/bin:")))
3391 (for-each (lambda (file)
3393 `("PATH" ":" prefix (,path))))
3401 ("coreutils" ,coreutils)))
3402 (home-page "http://mafft.cbrc.jp/alignment/software/")
3403 (synopsis "Multiple sequence alignment program")
3405 "MAFFT offers a range of multiple alignment methods for nucleotide and
3406 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3407 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3409 (license (license:non-copyleft
3410 "http://mafft.cbrc.jp/alignment/software/license.txt"
3411 "BSD-3 with different formatting"))))
3420 "https://github.com/marbl/mash/archive/v"
3422 (file-name (string-append name "-" version ".tar.gz"))
3425 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3426 (modules '((guix build utils)))
3428 ;; Delete bundled kseq.
3429 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3430 '(delete-file "src/mash/kseq.h"))))
3431 (build-system gnu-build-system)
3433 `(#:tests? #f ; No tests.
3436 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3437 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3438 #:make-flags (list "CC=gcc")
3440 (modify-phases %standard-phases
3441 (add-after 'unpack 'fix-includes
3443 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3444 (("^#include \"kseq\\.h\"")
3445 "#include \"htslib/kseq.h\""))
3447 (add-before 'configure 'autoconf
3448 (lambda _ (zero? (system* "autoconf")))))))
3450 `(("autoconf" ,autoconf)
3451 ;; Capnproto and htslib are statically embedded in the final
3452 ;; application. Therefore we also list their licenses, below.
3453 ("capnproto" ,capnproto)
3454 ("htslib" ,htslib)))
3458 (supported-systems '("x86_64-linux"))
3459 (home-page "https://mash.readthedocs.io")
3460 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3461 (description "Mash is a fast sequence distance estimator that uses the
3462 MinHash algorithm and is designed to work with genomes and metagenomes in the
3463 form of assemblies or reads.")
3464 (license (list license:bsd-3 ; Mash
3465 license:expat ; HTSlib and capnproto
3466 license:public-domain ; MurmurHash 3
3467 license:cpl1.0)))) ; Open Bloom Filter
3469 (define-public metabat
3470 ;; We package from a git commit because compilation of the released version
3472 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3475 (version (string-append "0.32.4-1." (string-take commit 8)))
3480 (url "https://bitbucket.org/berkeleylab/metabat.git")
3482 (file-name (string-append name "-" version))
3485 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3486 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3487 (build-system gnu-build-system)
3490 (modify-phases %standard-phases
3491 (add-after 'unpack 'fix-includes
3493 (substitute* "src/BamUtils.h"
3494 (("^#include \"bam/bam\\.h\"")
3495 "#include \"samtools/bam.h\"")
3496 (("^#include \"bam/sam\\.h\"")
3497 "#include \"samtools/sam.h\""))
3498 (substitute* "src/KseqReader.h"
3499 (("^#include \"bam/kseq\\.h\"")
3500 "#include \"htslib/kseq.h\""))
3502 (add-after 'unpack 'fix-scons
3503 (lambda* (#:key inputs #:allow-other-keys)
3504 (substitute* "SConstruct"
3505 (("^htslib_dir = 'samtools'")
3506 (string-append "hitslib_dir = '"
3507 (assoc-ref inputs "htslib")
3509 (("^samtools_dir = 'samtools'")
3510 (string-append "samtools_dir = '"
3511 (assoc-ref inputs "htslib")
3513 (("^findStaticOrShared\\('bam', hts_lib")
3514 (string-append "findStaticOrShared('bam', '"
3515 (assoc-ref inputs "samtools")
3517 ;; Do not distribute README.
3518 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3522 (lambda* (#:key inputs outputs #:allow-other-keys)
3523 (mkdir (assoc-ref outputs "out"))
3524 (zero? (system* "scons"
3527 (assoc-ref outputs "out"))
3530 (assoc-ref inputs "boost"))
3532 ;; Check and install are carried out during build phase.
3534 (delete 'install))))
3538 ("samtools" ,samtools)
3542 `(("scons" ,scons)))
3543 (home-page "https://bitbucket.org/berkeleylab/metabat")
3545 "Reconstruction of single genomes from complex microbial communities")
3547 "Grouping large genomic fragments assembled from shotgun metagenomic
3548 sequences to deconvolute complex microbial communities, or metagenome binning,
3549 enables the study of individual organisms and their interactions. MetaBAT is
3550 an automated metagenome binning software, which integrates empirical
3551 probabilistic distances of genome abundance and tetranucleotide frequency.")
3552 (license (license:non-copyleft "file://license.txt"
3553 "See license.txt in the distribution.")))))
3555 (define-public minced
3562 "https://github.com/ctSkennerton/minced/archive/"
3564 (file-name (string-append name "-" version ".tar.gz"))
3567 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3568 (build-system gnu-build-system)
3570 `(#:test-target "test"
3572 (modify-phases %standard-phases
3574 (add-before 'check 'fix-test
3576 ;; Fix test for latest version.
3577 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3578 (("minced:0.1.6") "minced:0.2.0"))
3580 (replace 'install ; No install target.
3581 (lambda* (#:key inputs outputs #:allow-other-keys)
3582 (let* ((out (assoc-ref outputs "out"))
3583 (bin (string-append out "/bin"))
3584 (wrapper (string-append bin "/minced")))
3585 ;; Minced comes with a wrapper script that tries to figure out where
3586 ;; it is located before running the JAR. Since these paths are known
3587 ;; to us, we build our own wrapper to avoid coreutils dependency.
3588 (install-file "minced.jar" bin)
3589 (with-output-to-file wrapper
3593 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3594 (assoc-ref inputs "jre") "/bin/java -jar "
3595 bin "/minced.jar \"$@\"\n"))))
3596 (chmod wrapper #o555)))))))
3598 `(("jdk" ,icedtea "jdk")))
3601 ("jre" ,icedtea "out")))
3602 (home-page "https://github.com/ctSkennerton/minced")
3603 (synopsis "Mining CRISPRs in Environmental Datasets")
3605 "MinCED is a program to find Clustered Regularly Interspaced Short
3606 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3607 unassembled metagenomic reads, but is mainly designed for full genomes and
3608 assembled metagenomic sequence.")
3609 (license license:gpl3+)))
3618 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3622 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3623 (modules '((guix build utils)))
3625 '(substitute* "setup.py"
3626 ;; Use setuptools, or else the executables are not
3628 (("distutils.core") "setuptools")
3629 ;; use "gcc" instead of "cc" for compilation
3631 "cc.set_executables(
3635 linker_so='gcc -shared'); defines")))))
3636 (build-system python-build-system)
3638 `(#:python ,python-2 ; only Python 2 is supported
3639 #:tests? #f)) ; no "test" target
3641 `(("samtools" ,samtools)
3642 ("python-numpy" ,python2-numpy)
3643 ("python-pysam" ,python2-pysam)
3644 ("python-scipy" ,python2-scipy)
3645 ("python-matplotlib" ,python2-matplotlib)))
3647 `(("python-mock" ,python2-mock) ;for tests
3648 ("python-pytz" ,python2-pytz))) ;for tests
3649 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3650 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3652 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3653 the expression level of alternatively spliced genes from RNA-Seq data, and
3654 identifies differentially regulated isoforms or exons across samples. By
3655 modeling the generative process by which reads are produced from isoforms in
3656 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3657 that a read originated from a particular isoform.")
3658 (license license:gpl2)))
3660 (define-public muscle
3663 (version "3.8.1551")
3665 (method url-fetch/tarbomb)
3667 "http://www.drive5.com/muscle/muscle_src_"
3671 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3672 (build-system gnu-build-system)
3674 `(#:make-flags (list "LDLIBS = -lm")
3676 (modify-phases %standard-phases
3679 ;; There are no tests, so just test if it runs.
3680 (lambda _ (zero? (system* "./muscle" "-version"))))
3682 (lambda* (#:key outputs #:allow-other-keys)
3683 (let* ((out (assoc-ref outputs "out"))
3684 (bin (string-append out "/bin")))
3685 (install-file "muscle" bin)))))))
3686 (home-page "http://www.drive5.com/muscle")
3687 (synopsis "Multiple sequence alignment program")
3689 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3690 program for nucleotide and protein sequences.")
3691 ;; License information found in 'muscle -h' and usage.cpp.
3692 (license license:public-domain)))
3694 (define-public newick-utils
3695 ;; There are no recent releases so we package from git.
3696 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3698 (name "newick-utils")
3699 (version (string-append "1.6-1." (string-take commit 8)))
3703 (url "https://github.com/tjunier/newick_utils.git")
3705 (file-name (string-append name "-" version "-checkout"))
3708 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3709 (build-system gnu-build-system)
3712 (modify-phases %standard-phases
3713 (add-after 'unpack 'autoconf
3714 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3716 ;; XXX: TODO: Enable Lua and Guile bindings.
3717 ;; https://github.com/tjunier/newick_utils/issues/13
3718 `(("libxml2" ,libxml2)
3722 `(("autoconf" ,autoconf)
3723 ("automake" ,automake)
3724 ("libtool" ,libtool)))
3725 (synopsis "Programs for working with newick format phylogenetic trees")
3727 "Newick-utils is a suite of utilities for processing phylogenetic trees
3728 in Newick format. Functions include re-rooting, extracting subtrees,
3729 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3730 (home-page "https://github.com/tjunier/newick_utils")
3731 (license license:bsd-3))))
3740 "https://github.com/wwood/OrfM/releases/download/v"
3741 version "/orfm-" version ".tar.gz"))
3744 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3745 (build-system gnu-build-system)
3746 (inputs `(("zlib" ,zlib)))
3748 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3749 ("ruby-rspec" ,ruby-rspec)
3751 (synopsis "Simple and not slow open reading frame (ORF) caller")
3753 "An ORF caller finds stretches of DNA that, when translated, are not
3754 interrupted by stop codons. OrfM finds and prints these ORFs.")
3755 (home-page "https://github.com/wwood/OrfM")
3756 (license license:lgpl3+)))
3758 (define-public pplacer
3759 (let ((commit "g807f6f3"))
3762 ;; The commit should be updated with each version change.
3763 (version "1.1.alpha19")
3767 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3769 (file-name (string-append name "-" version ".tar.gz"))
3771 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3772 (build-system ocaml-build-system)
3774 `(#:ocaml ,ocaml-4.01
3775 #:findlib ,ocaml4.01-findlib
3776 #:modules ((guix build ocaml-build-system)
3780 (modify-phases %standard-phases
3782 (add-after 'unpack 'replace-bundled-cddlib
3783 (lambda* (#:key inputs #:allow-other-keys)
3784 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3785 (local-dir "cddlib_guix"))
3787 (with-directory-excursion local-dir
3788 (system* "tar" "xvf" cddlib-src))
3789 (let ((cddlib-src-folder
3790 (string-append local-dir "/"
3791 (list-ref (scandir local-dir) 2)
3796 (string-append "cdd_src/" (basename file))))
3797 (find-files cddlib-src-folder ".*[ch]$")))
3799 (add-after 'unpack 'fix-makefile
3801 ;; Remove system calls to 'git'.
3802 (substitute* "Makefile"
3803 (("^DESCRIPT:=pplacer-.*")
3805 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3806 (substitute* "myocamlbuild.ml"
3807 (("git describe --tags --long .*\\\" with")
3809 "echo -n v" ,version "-" ,commit "\" with")))
3812 (lambda* (#:key outputs #:allow-other-keys)
3813 (let* ((out (assoc-ref outputs "out"))
3814 (bin (string-append out "/bin")))
3815 (copy-recursively "bin" bin))
3820 ("ocaml-ounit" ,ocaml4.01-ounit)
3821 ("ocaml-batteries" ,ocaml4.01-batteries)
3822 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3823 ("ocaml-csv" ,ocaml4.01-csv)
3824 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3825 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3826 ("ocaml-mcl" ,ocaml4.01-mcl)
3827 ("ocaml-gsl" ,ocaml4.01-gsl)
3828 ("cddlib-src" ,(package-source cddlib))))
3830 `(("pplacer-scripts" ,pplacer-scripts)))
3831 (synopsis "Phylogenetic placement of biological sequences")
3833 "Pplacer places query sequences on a fixed reference phylogenetic tree
3834 to maximize phylogenetic likelihood or posterior probability according to a
3835 reference alignment. Pplacer is designed to be fast, to give useful
3836 information about uncertainty, and to offer advanced visualization and
3837 downstream analysis.")
3838 (home-page "http://matsen.fhcrc.org/pplacer")
3839 (license license:gpl3))))
3841 ;; This package is installed alongside 'pplacer'. It is a separate package so
3842 ;; that it can use the python-build-system for the scripts that are
3843 ;; distributed alongside the main OCaml binaries.
3844 (define pplacer-scripts
3847 (name "pplacer-scripts")
3848 (build-system python-build-system)
3850 `(#:python ,python-2
3852 (modify-phases %standard-phases
3853 (add-after 'unpack 'enter-scripts-dir
3854 (lambda _ (chdir "scripts")))
3857 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3858 (add-after 'install 'wrap-executables
3859 (lambda* (#:key inputs outputs #:allow-other-keys)
3860 (let* ((out (assoc-ref outputs "out"))
3861 (bin (string-append out "/bin")))
3862 (let ((path (string-append
3863 (assoc-ref inputs "hmmer") "/bin:"
3864 (assoc-ref inputs "infernal") "/bin")))
3866 (wrap-program (string-append bin "/refpkg_align.py")
3867 `("PATH" ":" prefix (,path))))
3868 (let ((path (string-append
3869 (assoc-ref inputs "hmmer") "/bin")))
3870 (wrap-program (string-append bin "/hrefpkg_query.py")
3871 `("PATH" ":" prefix (,path)))))
3874 `(("infernal" ,infernal)
3877 `(("python-biopython" ,python2-biopython)
3878 ("taxtastic" ,taxtastic)))
3879 (synopsis "Pplacer Python scripts")))
3881 (define-public python2-pbcore
3883 (name "python2-pbcore")
3887 (uri (pypi-uri "pbcore" version))
3890 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3891 (build-system python-build-system)
3892 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3894 `(("python-cython" ,python2-cython)
3895 ("python-numpy" ,python2-numpy)
3896 ("python-pysam" ,python2-pysam)
3897 ("python-h5py" ,python2-h5py)))
3899 `(("python-nose" ,python2-nose)
3900 ("python-sphinx" ,python2-sphinx)
3901 ("python-pyxb" ,python2-pyxb)))
3902 (home-page "http://pacificbiosciences.github.io/pbcore/")
3903 (synopsis "Library for reading and writing PacBio data files")
3905 "The pbcore package provides Python APIs for interacting with PacBio data
3906 files and writing bioinformatics applications.")
3907 (license license:bsd-3)))
3909 (define-public python2-warpedlmm
3911 (name "python2-warpedlmm")
3917 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3921 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3922 (build-system python-build-system)
3924 `(#:python ,python-2)) ; requires Python 2.7
3926 `(("python-scipy" ,python2-scipy)
3927 ("python-numpy" ,python2-numpy)
3928 ("python-matplotlib" ,python2-matplotlib)
3929 ("python-fastlmm" ,python2-fastlmm)
3930 ("python-pandas" ,python2-pandas)
3931 ("python-pysnptools" ,python2-pysnptools)))
3933 `(("python-mock" ,python2-mock)
3934 ("python-nose" ,python2-nose)
3936 (home-page "https://github.com/PMBio/warpedLMM")
3937 (synopsis "Implementation of warped linear mixed models")
3939 "WarpedLMM is a Python implementation of the warped linear mixed model,
3940 which automatically learns an optimal warping function (or transformation) for
3941 the phenotype as it models the data.")
3942 (license license:asl2.0)))
3944 (define-public pbtranscript-tofu
3945 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3947 (name "pbtranscript-tofu")
3948 (version (string-append "2.2.3." (string-take commit 7)))
3952 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3954 (file-name (string-append name "-" version "-checkout"))
3957 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3958 (modules '((guix build utils)))
3961 ;; remove bundled Cython sources
3962 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3964 (build-system python-build-system)
3966 `(#:python ,python-2
3967 ;; FIXME: Tests fail with "No such file or directory:
3968 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3971 (modify-phases %standard-phases
3972 (add-after 'unpack 'enter-directory
3974 (chdir "pbtranscript-tofu/pbtranscript/")
3976 ;; With setuptools version 18.0 and later this setup.py hack causes
3977 ;; a build error, so we disable it.
3978 (add-after 'enter-directory 'patch-setuppy
3980 (substitute* "setup.py"
3981 (("if 'setuptools.extension' in sys.modules:")
3985 `(("python-numpy" ,python2-numpy)
3986 ("python-bx-python" ,python2-bx-python)
3987 ("python-networkx" ,python2-networkx)
3988 ("python-scipy" ,python2-scipy)
3989 ("python-pbcore" ,python2-pbcore)
3990 ("python-h5py" ,python2-h5py)))
3992 `(("python-cython" ,python2-cython)
3993 ("python-nose" ,python2-nose)))
3994 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3995 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3997 "pbtranscript-tofu contains scripts to analyze transcriptome data
3998 generated using the PacBio Iso-Seq protocol.")
3999 (license license:bsd-3))))
4001 (define-public prank
4008 "http://wasabiapp.org/download/prank/prank.source."
4012 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4013 (build-system gnu-build-system)
4016 (modify-phases %standard-phases
4017 (add-after 'unpack 'enter-src-dir
4021 (add-after 'unpack 'remove-m64-flag
4022 ;; Prank will build with the correct 'bit-ness' without this flag
4023 ;; and this allows building on 32-bit machines.
4024 (lambda _ (substitute* "src/Makefile"
4029 (lambda* (#:key outputs #:allow-other-keys)
4030 (let* ((out (assoc-ref outputs "out"))
4031 (bin (string-append out "/bin"))
4032 (man (string-append out "/share/man/man1"))
4033 (path (string-append
4034 (assoc-ref %build-inputs "mafft") "/bin:"
4035 (assoc-ref %build-inputs "exonerate") "/bin:"
4036 (assoc-ref %build-inputs "bppsuite") "/bin")))
4037 (install-file "prank" bin)
4038 (wrap-program (string-append bin "/prank")
4039 `("PATH" ":" prefix (,path)))
4040 (install-file "prank.1" man))
4044 ("exonerate" ,exonerate)
4045 ("bppsuite" ,bppsuite)))
4046 (home-page "http://wasabiapp.org/software/prank/")
4047 (synopsis "Probabilistic multiple sequence alignment program")
4049 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4050 codon and amino-acid sequences. It is based on a novel algorithm that treats
4051 insertions correctly and avoids over-estimation of the number of deletion
4052 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4053 in phylogenetics and correctly takes into account the evolutionary distances
4054 between sequences. Lastly, PRANK allows for defining a potential structure
4055 for sequences to be aligned and then, simultaneously with the alignment,
4056 predicts the locations of structural units in the sequences.")
4057 (license license:gpl2+)))
4059 (define-public proteinortho
4061 (name "proteinortho")
4068 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4069 version "_src.tar.gz"))
4072 "0z4f5cg0cs8ai62hfvp4q6w66q2phcc55nhs4xj5cyhxxivjv2ai"))))
4073 (build-system gnu-build-system)
4075 `(#:test-target "test"
4077 (modify-phases %standard-phases
4079 ;; There is no configure script, so we modify the Makefile directly.
4080 (lambda* (#:key outputs #:allow-other-keys)
4081 (substitute* "Makefile"
4084 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4086 (add-before 'install 'make-install-directory
4087 ;; The install directory is not created during 'make install'.
4088 (lambda* (#:key outputs #:allow-other-keys)
4089 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4091 (add-after 'install 'wrap-programs
4092 (lambda* (#:key inputs outputs #:allow-other-keys)
4093 (let* ((path (getenv "PATH"))
4094 (out (assoc-ref outputs "out"))
4095 (binary (string-append out "/bin/proteinortho5.pl")))
4096 (wrap-program binary `("PATH" ":" prefix (,path))))
4100 ("python" ,python-2)
4101 ("blast+" ,blast+)))
4102 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4103 (synopsis "Detect orthologous genes across species")
4105 "Proteinortho is a tool to detect orthologous genes across different
4106 species. For doing so, it compares similarities of given gene sequences and
4107 clusters them to find significant groups. The algorithm was designed to handle
4108 large-scale data and can be applied to hundreds of species at once.")
4109 (license license:gpl2+)))
4111 (define-public pyicoteo
4118 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4119 "pyicoteo/get/v" version ".tar.bz2"))
4120 (file-name (string-append name "-" version ".tar.bz2"))
4123 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4124 (build-system python-build-system)
4126 `(#:python ,python-2 ; does not work with Python 3
4127 #:tests? #f)) ; there are no tests
4129 `(("python2-matplotlib" ,python2-matplotlib)))
4130 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4131 (synopsis "Analyze high-throughput genetic sequencing data")
4133 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4134 sequencing data. It works with genomic coordinates. There are currently six
4135 different command-line tools:
4138 @item pyicoregion: for generating exploratory regions automatically;
4139 @item pyicoenrich: for differential enrichment between two conditions;
4140 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4141 @item pyicos: for genomic coordinates manipulation;
4142 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4143 @item pyicount: to count how many reads from N experiment files overlap in a
4145 @item pyicotrocol: to combine operations from pyicoteo.
4147 (license license:gpl3+)))
4149 (define-public prodigal
4156 "https://github.com/hyattpd/Prodigal/archive/v"
4158 (file-name (string-append name "-" version ".tar.gz"))
4161 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4162 (build-system gnu-build-system)
4164 `(#:tests? #f ;no check target
4165 #:make-flags (list (string-append "INSTALLDIR="
4166 (assoc-ref %outputs "out")
4169 (modify-phases %standard-phases
4170 (delete 'configure))))
4171 (home-page "http://prodigal.ornl.gov")
4172 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4174 "Prodigal runs smoothly on finished genomes, draft genomes, and
4175 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4176 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4177 partial genes, and identifies translation initiation sites.")
4178 (license license:gpl3+)))
4180 (define-public roary
4188 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4192 "03dfr2cd5fp80bcr65923zpdzrasvcxl7c2vgh8373v25a1yfap7"))))
4193 (build-system perl-build-system)
4196 (modify-phases %standard-phases
4201 ;; The tests are not run by default, so we run each test file
4203 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4205 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4206 (getenv "PERL5LIB")))
4207 (zero? (length (filter (lambda (file)
4208 (display file)(display "\n")
4209 (not (zero? (system* "perl" file))))
4210 (find-files "t" ".*\\.t$"))))))
4212 ;; There is no 'install' target in the Makefile.
4213 (lambda* (#:key outputs #:allow-other-keys)
4214 (let* ((out (assoc-ref outputs "out"))
4215 (bin (string-append out "/bin"))
4216 (perl (string-append out "/lib/perl5/site_perl"))
4217 (roary-plots "contrib/roary_plots"))
4220 (copy-recursively "bin" bin)
4221 (copy-recursively "lib" perl)
4223 (add-after 'install 'wrap-programs
4224 (lambda* (#:key inputs outputs #:allow-other-keys)
4225 (let* ((out (assoc-ref outputs "out"))
4226 (perl5lib (getenv "PERL5LIB"))
4227 (path (getenv "PATH")))
4228 (for-each (lambda (prog)
4229 (let ((binary (string-append out "/" prog)))
4230 (wrap-program binary
4231 `("PERL5LIB" ":" prefix
4232 (,(string-append perl5lib ":" out
4233 "/lib/perl5/site_perl"))))
4234 (wrap-program binary
4236 (,(string-append path ":" out "/bin"))))))
4237 (find-files "bin" ".*[^R]$"))
4239 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4240 (r-site-lib (getenv "R_LIBS_SITE"))
4242 (string-append (assoc-ref inputs "coreutils") "/bin")))
4244 `("R_LIBS_SITE" ":" prefix
4245 (,(string-append r-site-lib ":" out "/site-library/"))))
4248 (,(string-append coreutils-path ":" out "/bin"))))))
4251 `(("perl-env-path" ,perl-env-path)
4252 ("perl-test-files" ,perl-test-files)
4253 ("perl-test-most" ,perl-test-most)
4254 ("perl-test-output" ,perl-test-output)))
4256 `(("perl-array-utils" ,perl-array-utils)
4257 ("bioperl" ,bioperl-minimal)
4258 ("perl-exception-class" ,perl-exception-class)
4259 ("perl-file-find-rule" ,perl-file-find-rule)
4260 ("perl-file-grep" ,perl-file-grep)
4261 ("perl-file-slurper" ,perl-file-slurper)
4262 ("perl-file-which" ,perl-file-which)
4263 ("perl-graph" ,perl-graph)
4264 ("perl-graph-readwrite" ,perl-graph-readwrite)
4265 ("perl-log-log4perl" ,perl-log-log4perl)
4266 ("perl-moose" ,perl-moose)
4267 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4268 ("perl-text-csv" ,perl-text-csv)
4269 ("bedtools" ,bedtools)
4273 ("parallel" ,parallel)
4276 ("fasttree" ,fasttree)
4280 ("r-minimal" ,r-minimal)
4281 ("r-ggplot2" ,r-ggplot2)
4282 ("coreutils" ,coreutils)))
4283 (home-page "http://sanger-pathogens.github.io/Roary")
4284 (synopsis "High speed stand-alone pan genome pipeline")
4286 "Roary is a high speed stand alone pan genome pipeline, which takes
4287 annotated assemblies in GFF3 format (produced by the Prokka program) and
4288 calculates the pan genome. Using a standard desktop PC, it can analyse
4289 datasets with thousands of samples, without compromising the quality of the
4290 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4291 single processor. Roary is not intended for metagenomics or for comparing
4292 extremely diverse sets of genomes.")
4293 (license license:gpl3)))
4295 (define-public raxml
4304 "https://github.com/stamatak/standard-RAxML/archive/v"
4306 (file-name (string-append name "-" version ".tar.gz"))
4309 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4310 (build-system gnu-build-system)
4312 `(#:tests? #f ; There are no tests.
4313 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4314 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4316 (modify-phases %standard-phases
4319 (lambda* (#:key outputs #:allow-other-keys)
4320 (let* ((out (assoc-ref outputs "out"))
4321 (bin (string-append out "/bin"))
4322 (executable "raxmlHPC-HYBRID"))
4323 (install-file executable bin)
4324 (symlink (string-append bin "/" executable) "raxml"))
4327 `(("openmpi" ,openmpi)))
4328 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4329 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4331 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4333 ;; The source includes x86 specific code
4334 (supported-systems '("x86_64-linux" "i686-linux"))
4335 (license license:gpl2+)))
4345 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4348 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4349 (patches (search-patches "rsem-makefile.patch"))
4350 (modules '((guix build utils)))
4353 ;; remove bundled copy of boost
4354 (delete-file-recursively "boost")
4356 (build-system gnu-build-system)
4358 `(#:tests? #f ;no "check" target
4360 (modify-phases %standard-phases
4361 ;; No "configure" script.
4362 ;; Do not build bundled samtools library.
4365 (substitute* "Makefile"
4366 (("^all : sam/libbam.a") "all : "))
4369 (lambda* (#:key outputs #:allow-other-keys)
4370 (let* ((out (string-append (assoc-ref outputs "out")))
4371 (bin (string-append out "/bin/"))
4372 (perl (string-append out "/lib/perl5/site_perl")))
4375 (for-each (lambda (file)
4376 (install-file file bin))
4377 (find-files "." "rsem-.*"))
4378 (install-file "rsem_perl_utils.pm" perl))
4381 'install 'wrap-program
4382 (lambda* (#:key outputs #:allow-other-keys)
4383 (let ((out (assoc-ref outputs "out")))
4384 (for-each (lambda (prog)
4385 (wrap-program (string-append out "/bin/" prog)
4386 `("PERL5LIB" ":" prefix
4387 (,(string-append out "/lib/perl5/site_perl")))))
4388 '("rsem-plot-transcript-wiggles"
4389 "rsem-calculate-expression"
4390 "rsem-generate-ngvector"
4392 "rsem-prepare-reference")))
4396 ("ncurses" ,ncurses)
4397 ("r-minimal" ,r-minimal)
4399 ("samtools" ,samtools-0.1)
4401 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4402 (synopsis "Estimate gene expression levels from RNA-Seq data")
4404 "RSEM is a software package for estimating gene and isoform expression
4405 levels from RNA-Seq data. The RSEM package provides a user-friendly
4406 interface, supports threads for parallel computation of the EM algorithm,
4407 single-end and paired-end read data, quality scores, variable-length reads and
4408 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4409 interval estimates for expression levels. For visualization, it can generate
4410 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4411 (license license:gpl3+)))
4413 (define-public rseqc
4421 (string-append "mirror://sourceforge/rseqc/"
4422 "RSeQC-" version ".tar.gz"))
4424 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4425 (modules '((guix build utils)))
4428 ;; remove bundled copy of pysam
4429 (delete-file-recursively "lib/pysam")
4430 (substitute* "setup.py"
4431 ;; remove dependency on outdated "distribute" module
4432 (("^from distribute_setup import use_setuptools") "")
4433 (("^use_setuptools\\(\\)") "")
4434 ;; do not use bundled copy of pysam
4435 (("^have_pysam = False") "have_pysam = True"))))))
4436 (build-system python-build-system)
4437 (arguments `(#:python ,python-2))
4439 `(("python-cython" ,python2-cython)
4440 ("python-pysam" ,python2-pysam)
4441 ("python-numpy" ,python2-numpy)
4444 `(("python-nose" ,python2-nose)))
4445 (home-page "http://rseqc.sourceforge.net/")
4446 (synopsis "RNA-seq quality control package")
4448 "RSeQC provides a number of modules that can comprehensively evaluate
4449 high throughput sequence data, especially RNA-seq data. Some basic modules
4450 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4451 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4452 distribution, coverage uniformity, strand specificity, etc.")
4453 (license license:gpl3+)))
4456 ;; There are no release tarballs. According to the installation
4457 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4458 ;; stable release is identified by this changeset ID.
4459 (let ((changeset "2329130")
4463 (version (string-append "0-" revision "." changeset))
4467 (url "https://bitbucket.org/libsleipnir/sleipnir")
4468 (changeset changeset)))
4471 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4472 (build-system gnu-build-system)
4474 `(#:modules ((srfi srfi-1)
4475 (guix build gnu-build-system)
4478 (let ((dirs '("SeekMiner"
4484 (modify-phases %standard-phases
4485 (add-before 'configure 'bootstrap
4487 (zero? (system* "bash" "gen_auto"))))
4488 (add-after 'build 'build-additional-tools
4489 (lambda* (#:key make-flags #:allow-other-keys)
4490 (every (lambda (dir)
4491 (with-directory-excursion (string-append "tools/" dir)
4492 (zero? (apply system* "make" make-flags))))
4494 (add-after 'install 'install-additional-tools
4495 (lambda* (#:key make-flags #:allow-other-keys)
4496 (fold (lambda (dir result)
4497 (with-directory-excursion (string-append "tools/" dir)
4499 (zero? (apply system*
4500 `("make" ,@make-flags "install"))))))
4506 ("readline" ,readline)
4507 ("gengetopt" ,gengetopt)
4508 ("log4cpp" ,log4cpp)))
4510 `(("autoconf" ,autoconf)
4511 ("automake" ,automake)
4513 (home-page "http://seek.princeton.edu")
4514 (synopsis "Gene co-expression search engine")
4516 "SEEK is a computational gene co-expression search engine. SEEK provides
4517 biologists with a way to navigate the massive human expression compendium that
4518 now contains thousands of expression datasets. SEEK returns a robust ranking
4519 of co-expressed genes in the biological area of interest defined by the user's
4520 query genes. It also prioritizes thousands of expression datasets according
4521 to the user's query of interest.")
4522 (license license:cc-by3.0))))
4524 (define-public samtools
4532 (string-append "mirror://sourceforge/samtools/samtools/"
4533 version "/samtools-" version ".tar.bz2"))
4536 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4537 (build-system gnu-build-system)
4539 `(#:modules ((ice-9 ftw)
4541 (guix build gnu-build-system)
4543 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4544 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4546 (modify-phases %standard-phases
4547 (add-after 'unpack 'patch-tests
4549 (substitute* "test/test.pl"
4550 ;; The test script calls out to /bin/bash
4551 (("/bin/bash") (which "bash")))
4553 (add-after 'install 'install-library
4554 (lambda* (#:key outputs #:allow-other-keys)
4555 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4556 (install-file "libbam.a" lib)
4558 (add-after 'install 'install-headers
4559 (lambda* (#:key outputs #:allow-other-keys)
4560 (let ((include (string-append (assoc-ref outputs "out")
4561 "/include/samtools/")))
4562 (for-each (lambda (file)
4563 (install-file file include))
4564 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4566 (native-inputs `(("pkg-config" ,pkg-config)))
4568 `(("htslib" ,htslib)
4569 ("ncurses" ,ncurses)
4573 (home-page "http://samtools.sourceforge.net")
4574 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4576 "Samtools implements various utilities for post-processing nucleotide
4577 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4578 variant calling (in conjunction with bcftools), and a simple alignment
4580 (license license:expat)))
4582 (define-public samtools-0.1
4583 ;; This is the most recent version of the 0.1 line of samtools. The input
4584 ;; and output formats differ greatly from that used and produced by samtools
4585 ;; 1.x and is still used in many bioinformatics pipelines.
4586 (package (inherit samtools)
4592 (string-append "mirror://sourceforge/samtools/samtools/"
4593 version "/samtools-" version ".tar.bz2"))
4595 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4597 `(#:tests? #f ;no "check" target
4598 ,@(substitute-keyword-arguments (package-arguments samtools)
4599 ((#:make-flags flags)
4600 `(cons "LIBCURSES=-lncurses" ,flags))
4602 `(modify-phases ,phases
4604 (lambda* (#:key outputs #:allow-other-keys)
4605 (let ((bin (string-append
4606 (assoc-ref outputs "out") "/bin")))
4608 (install-file "samtools" bin)
4610 (delete 'patch-tests)
4611 (delete 'configure))))))))
4613 (define-public mosaik
4614 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4619 ;; There are no release tarballs nor tags.
4622 (url "https://github.com/wanpinglee/MOSAIK.git")
4624 (file-name (string-append name "-" version))
4627 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4628 (build-system gnu-build-system)
4630 `(#:tests? #f ; no tests
4631 #:make-flags (list "CC=gcc")
4633 (modify-phases %standard-phases
4635 (lambda _ (chdir "src") #t))
4637 (lambda* (#:key outputs #:allow-other-keys)
4638 (let ((bin (string-append (assoc-ref outputs "out")
4641 (copy-recursively "../bin" bin)
4646 (supported-systems '("x86_64-linux"))
4647 (home-page "https://github.com/wanpinglee/MOSAIK")
4648 (synopsis "Map nucleotide sequence reads to reference genomes")
4650 "MOSAIK is a program for mapping second and third-generation sequencing
4651 reads to a reference genome. MOSAIK can align reads generated by all the
4652 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4653 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4654 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4655 ;; code released into the public domain:
4656 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4657 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4658 (license (list license:gpl2+ license:public-domain)))))
4660 (define-public ngs-sdk
4668 (string-append "https://github.com/ncbi/ngs/archive/"
4670 (file-name (string-append name "-" version ".tar.gz"))
4673 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4674 (build-system gnu-build-system)
4676 `(#:parallel-build? #f ; not supported
4677 #:tests? #f ; no "check" target
4681 (lambda* (#:key outputs #:allow-other-keys)
4682 (let ((out (assoc-ref outputs "out")))
4683 ;; The 'configure' script doesn't recognize things like
4684 ;; '--enable-fast-install'.
4685 (zero? (system* "./configure"
4686 (string-append "--build-prefix=" (getcwd) "/build")
4687 (string-append "--prefix=" out)))))
4690 (lambda _ (chdir "ngs-sdk") #t)
4691 %standard-phases))))
4692 (native-inputs `(("perl" ,perl)))
4693 ;; According to the test
4694 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4695 ;; in ngs-sdk/setup/konfigure.perl
4696 (supported-systems '("i686-linux" "x86_64-linux"))
4697 (home-page "https://github.com/ncbi/ngs")
4698 (synopsis "API for accessing Next Generation Sequencing data")
4700 "NGS is a domain-specific API for accessing reads, alignments and pileups
4701 produced from Next Generation Sequencing. The API itself is independent from
4702 any particular back-end implementation, and supports use of multiple back-ends
4704 (license license:public-domain)))
4706 (define-public java-ngs
4707 (package (inherit ngs-sdk)
4710 `(,@(substitute-keyword-arguments
4711 `(#:modules ((guix build gnu-build-system)
4715 ,@(package-arguments ngs-sdk))
4717 `(modify-phases ,phases
4718 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4720 `(("jdk" ,icedtea "jdk")
4721 ("ngs-sdk" ,ngs-sdk)))
4722 (synopsis "Java bindings for NGS SDK")))
4724 (define-public ncbi-vdb
4732 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4734 (file-name (string-append name "-" version ".tar.gz"))
4737 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4738 (build-system gnu-build-system)
4740 `(#:parallel-build? #f ; not supported
4741 #:tests? #f ; no "check" target
4743 (modify-phases %standard-phases
4745 (lambda* (#:key inputs outputs #:allow-other-keys)
4746 (let ((out (assoc-ref outputs "out")))
4747 ;; Override include path for libmagic
4748 (substitute* "setup/package.prl"
4749 (("name => 'magic', Include => '/usr/include'")
4750 (string-append "name=> 'magic', Include => '"
4751 (assoc-ref inputs "libmagic")
4754 ;; Install kdf5 library (needed by sra-tools)
4755 (substitute* "build/Makefile.install"
4756 (("LIBRARIES_TO_INSTALL =")
4757 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4759 (substitute* "build/Makefile.env"
4760 (("CFLAGS =" prefix)
4761 (string-append prefix "-msse2 ")))
4763 ;; Override search path for ngs-java
4764 (substitute* "setup/package.prl"
4765 (("/usr/local/ngs/ngs-java")
4766 (assoc-ref inputs "java-ngs")))
4768 ;; The 'configure' script doesn't recognize things like
4769 ;; '--enable-fast-install'.
4772 (string-append "--build-prefix=" (getcwd) "/build")
4773 (string-append "--prefix=" (assoc-ref outputs "out"))
4774 (string-append "--debug")
4775 (string-append "--with-xml2-prefix="
4776 (assoc-ref inputs "libxml2"))
4777 (string-append "--with-ngs-sdk-prefix="
4778 (assoc-ref inputs "ngs-sdk"))
4779 (string-append "--with-hdf5-prefix="
4780 (assoc-ref inputs "hdf5")))))))
4781 (add-after 'install 'install-interfaces
4782 (lambda* (#:key outputs #:allow-other-keys)
4783 ;; Install interface libraries. On i686 the interface libraries
4784 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4785 ;; architecture name ("i386") instead of the target system prefix
4787 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4788 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4789 ,(system->linux-architecture
4790 (or (%current-target-system)
4793 (string-append (assoc-ref outputs "out")
4795 ;; Install interface headers
4796 (copy-recursively "interfaces"
4797 (string-append (assoc-ref outputs "out")
4800 ;; These files are needed by sra-tools.
4801 (add-after 'install 'install-configuration-files
4802 (lambda* (#:key outputs #:allow-other-keys)
4803 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4805 (install-file "libs/kfg/default.kfg" target)
4806 (install-file "libs/kfg/certs.kfg" target))
4809 `(("libxml2" ,libxml2)
4810 ("ngs-sdk" ,ngs-sdk)
4811 ("java-ngs" ,java-ngs)
4814 (native-inputs `(("perl" ,perl)))
4815 ;; NCBI-VDB requires SSE capability.
4816 (supported-systems '("i686-linux" "x86_64-linux"))
4817 (home-page "https://github.com/ncbi/ncbi-vdb")
4818 (synopsis "Database engine for genetic information")
4820 "The NCBI-VDB library implements a highly compressed columnar data
4821 warehousing engine that is most often used to store genetic information.
4822 Databases are stored in a portable image within the file system, and can be
4823 accessed/downloaded on demand across HTTP.")
4824 (license license:public-domain)))
4826 (define-public plink
4834 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4835 version "-src.zip"))
4837 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4838 (patches (search-patches "plink-1.07-unclobber-i.patch"
4839 "plink-endian-detection.patch"))))
4840 (build-system gnu-build-system)
4842 '(#:tests? #f ;no "check" target
4843 #:make-flags (list (string-append "LIB_LAPACK="
4844 (assoc-ref %build-inputs "lapack")
4845 "/lib/liblapack.so")
4848 ;; disable phoning home
4851 (modify-phases %standard-phases
4852 ;; no "configure" script
4855 (lambda* (#:key outputs #:allow-other-keys)
4856 (let ((bin (string-append (assoc-ref outputs "out")
4858 (install-file "plink" bin)
4862 ("lapack" ,lapack)))
4864 `(("unzip" ,unzip)))
4865 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4866 (synopsis "Whole genome association analysis toolset")
4868 "PLINK is a whole genome association analysis toolset, designed to
4869 perform a range of basic, large-scale analyses in a computationally efficient
4870 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4871 so there is no support for steps prior to this (e.g. study design and
4872 planning, generating genotype or CNV calls from raw data). Through
4873 integration with gPLINK and Haploview, there is some support for the
4874 subsequent visualization, annotation and storage of results.")
4875 ;; Code is released under GPLv2, except for fisher.h, which is under
4877 (license (list license:gpl2 license:lgpl2.1+))))
4879 (define-public smithlab-cpp
4880 (let ((revision "1")
4881 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4883 (name "smithlab-cpp")
4884 (version (string-append "0." revision "." (string-take commit 7)))
4888 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4890 (file-name (string-append name "-" version "-checkout"))
4893 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4894 (build-system gnu-build-system)
4896 `(#:modules ((guix build gnu-build-system)
4899 #:tests? #f ;no "check" target
4901 (modify-phases %standard-phases
4902 (add-after 'unpack 'use-samtools-headers
4904 (substitute* '("SAM.cpp"
4906 (("sam.h") "samtools/sam.h"))
4909 (lambda* (#:key outputs #:allow-other-keys)
4910 (let* ((out (assoc-ref outputs "out"))
4911 (lib (string-append out "/lib"))
4912 (include (string-append out "/include/smithlab-cpp")))
4915 (for-each (cut install-file <> lib)
4916 (find-files "." "\\.o$"))
4917 (for-each (cut install-file <> include)
4918 (find-files "." "\\.hpp$")))
4920 (delete 'configure))))
4922 `(("samtools" ,samtools-0.1)
4924 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4925 (synopsis "C++ helper library for functions used in Smith lab projects")
4927 "Smithlab CPP is a C++ library that includes functions used in many of
4928 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4929 structures, classes for genomic regions, mapped sequencing reads, etc.")
4930 (license license:gpl3+))))
4932 (define-public preseq
4938 (uri (string-append "https://github.com/smithlabcode/"
4939 "preseq/archive/v" version ".tar.gz"))
4940 (file-name (string-append name "-" version ".tar.gz"))
4942 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4943 (modules '((guix build utils)))
4945 ;; Remove bundled samtools.
4946 '(delete-file-recursively "samtools"))))
4947 (build-system gnu-build-system)
4949 `(#:tests? #f ;no "check" target
4951 (modify-phases %standard-phases
4952 (delete 'configure))
4954 (list (string-append "PREFIX="
4955 (assoc-ref %outputs "out"))
4956 (string-append "LIBBAM="
4957 (assoc-ref %build-inputs "samtools")
4959 (string-append "SMITHLAB_CPP="
4960 (assoc-ref %build-inputs "smithlab-cpp")
4963 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4966 ("samtools" ,samtools-0.1)
4967 ("smithlab-cpp" ,smithlab-cpp)
4969 (home-page "http://smithlabresearch.org/software/preseq/")
4970 (synopsis "Program for analyzing library complexity")
4972 "The preseq package is aimed at predicting and estimating the complexity
4973 of a genomic sequencing library, equivalent to predicting and estimating the
4974 number of redundant reads from a given sequencing depth and how many will be
4975 expected from additional sequencing using an initial sequencing experiment.
4976 The estimates can then be used to examine the utility of further sequencing,
4977 optimize the sequencing depth, or to screen multiple libraries to avoid low
4978 complexity samples.")
4979 (license license:gpl3+)))
4981 (define-public python-screed
4983 (name "python-screed")
4988 (uri (pypi-uri "screed" version))
4991 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4992 (build-system python-build-system)
4995 (modify-phases %standard-phases
4998 (setenv "PYTHONPATH"
4999 (string-append (getenv "PYTHONPATH") ":."))
5000 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5002 `(("python-nose" ,python-nose)))
5004 `(("python-bz2file" ,python-bz2file)))
5005 (home-page "https://github.com/dib-lab/screed/")
5006 (synopsis "Short read sequence database utilities")
5007 (description "Screed parses FASTA and FASTQ files and generates databases.
5008 Values such as sequence name, sequence description, sequence quality and the
5009 sequence itself can be retrieved from these databases.")
5010 (license license:bsd-3)))
5012 (define-public python2-screed
5013 (package-with-python2 python-screed))
5015 (define-public sra-tools
5023 (string-append "https://github.com/ncbi/sra-tools/archive/"
5025 (file-name (string-append name "-" version ".tar.gz"))
5028 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5029 (build-system gnu-build-system)
5031 `(#:parallel-build? #f ; not supported
5032 #:tests? #f ; no "check" target
5034 (list (string-append "DEFAULT_CRT="
5035 (assoc-ref %build-inputs "ncbi-vdb")
5037 (string-append "DEFAULT_KFG="
5038 (assoc-ref %build-inputs "ncbi-vdb")
5040 (string-append "VDB_LIBDIR="
5041 (assoc-ref %build-inputs "ncbi-vdb")
5042 ,(if (string-prefix? "x86_64"
5043 (or (%current-target-system)
5048 (modify-phases %standard-phases
5050 (lambda* (#:key inputs outputs #:allow-other-keys)
5051 ;; The build system expects a directory containing the sources and
5052 ;; raw build output of ncbi-vdb, including files that are not
5053 ;; installed. Since we are building against an installed version of
5054 ;; ncbi-vdb, the following modifications are needed.
5055 (substitute* "setup/konfigure.perl"
5056 ;; Make the configure script look for the "ilib" directory of
5057 ;; "ncbi-vdb" without first checking for the existence of a
5058 ;; matching library in its "lib" directory.
5059 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5060 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5061 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5062 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5063 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5066 (substitute* "tools/copycat/Makefile"
5067 (("smagic-static") "lmagic"))
5069 ;; The 'configure' script doesn't recognize things like
5070 ;; '--enable-fast-install'.
5073 (string-append "--build-prefix=" (getcwd) "/build")
5074 (string-append "--prefix=" (assoc-ref outputs "out"))
5075 (string-append "--debug")
5076 (string-append "--with-fuse-prefix="
5077 (assoc-ref inputs "fuse"))
5078 (string-append "--with-magic-prefix="
5079 (assoc-ref inputs "libmagic"))
5080 ;; TODO: building with libxml2 fails with linker errors
5081 ;; (string-append "--with-xml2-prefix="
5082 ;; (assoc-ref inputs "libxml2"))
5083 (string-append "--with-ncbi-vdb-sources="
5084 (assoc-ref inputs "ncbi-vdb"))
5085 (string-append "--with-ncbi-vdb-build="
5086 (assoc-ref inputs "ncbi-vdb"))
5087 (string-append "--with-ngs-sdk-prefix="
5088 (assoc-ref inputs "ngs-sdk"))
5089 (string-append "--with-hdf5-prefix="
5090 (assoc-ref inputs "hdf5"))))))
5091 ;; This version of sra-tools fails to build with glibc because of a
5092 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5093 ;; contains a definition of "canonicalize", so we rename it.
5095 ;; See upstream bug report:
5096 ;; https://github.com/ncbi/sra-tools/issues/67
5097 (add-after 'unpack 'patch-away-glibc-conflict
5099 (substitute* "tools/bam-loader/bam.c"
5100 (("canonicalize\\(" line)
5101 (string-append "sra_tools_" line)))
5103 (native-inputs `(("perl" ,perl)))
5105 `(("ngs-sdk" ,ngs-sdk)
5106 ("ncbi-vdb" ,ncbi-vdb)
5111 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5112 (synopsis "Tools and libraries for reading and writing sequencing data")
5114 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5115 reading of sequencing files from the Sequence Read Archive (SRA) database and
5116 writing files into the .sra format.")
5117 (license license:public-domain)))
5119 (define-public seqan
5125 (uri (string-append "http://packages.seqan.de/seqan-library/"
5126 "seqan-library-" version ".tar.bz2"))
5129 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5130 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5131 ;; makes sense to split the outputs.
5132 (outputs '("out" "doc"))
5133 (build-system trivial-build-system)
5135 `(#:modules ((guix build utils))
5138 (use-modules (guix build utils))
5139 (let ((tar (assoc-ref %build-inputs "tar"))
5140 (bzip (assoc-ref %build-inputs "bzip2"))
5141 (out (assoc-ref %outputs "out"))
5142 (doc (assoc-ref %outputs "doc")))
5143 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5144 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5145 (chdir (string-append "seqan-library-" ,version))
5146 (copy-recursively "include" (string-append out "/include"))
5147 (copy-recursively "share" (string-append doc "/share"))))))
5149 `(("source" ,source)
5152 (home-page "http://www.seqan.de")
5153 (synopsis "Library for nucleotide sequence analysis")
5155 "SeqAn is a C++ library of efficient algorithms and data structures for
5156 the analysis of sequences with the focus on biological data. It contains
5157 algorithms and data structures for string representation and their
5158 manipulation, online and indexed string search, efficient I/O of
5159 bioinformatics file formats, sequence alignment, and more.")
5160 (license license:bsd-3)))
5162 (define-public seqmagick
5170 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5174 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5175 (build-system python-build-system)
5177 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5178 `(#:python ,python-2
5180 (modify-phases %standard-phases
5181 ;; Current test in setup.py does not work as of 0.6.1,
5182 ;; so use nose to run tests instead for now. See
5183 ;; https://github.com/fhcrc/seqmagick/issues/55
5184 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5186 ;; biopython-1.66 is required due to
5187 ;; https://github.com/fhcrc/seqmagick/issues/59
5188 ;; When that issue is resolved the 'python2-biopython-1.66' package
5189 ;; should be removed.
5190 `(("python-biopython" ,python2-biopython-1.66)))
5192 `(("python-nose" ,python2-nose)))
5193 (home-page "https://github.com/fhcrc/seqmagick")
5194 (synopsis "Tools for converting and modifying sequence files")
5196 "Bioinformaticians often have to convert sequence files between formats
5197 and do little manipulations on them, and it's not worth writing scripts for
5198 that. Seqmagick is a utility to expose the file format conversion in
5199 BioPython in a convenient way. Instead of having a big mess of scripts, there
5200 is one that takes arguments.")
5201 (license license:gpl3)))
5203 (define-public seqtk
5210 "https://github.com/lh3/seqtk/archive/v"
5212 (file-name (string-append name "-" version ".tar.gz"))
5215 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5216 (modules '((guix build utils)))
5219 ;; Remove extraneous header files, as is done in the seqtk
5221 (for-each (lambda (file) (delete-file file))
5222 (list "ksort.h" "kstring.h" "kvec.h"))
5224 (build-system gnu-build-system)
5227 (modify-phases %standard-phases
5230 ;; There are no tests, so we just run a sanity check.
5231 (lambda _ (zero? (system* "./seqtk" "seq"))))
5233 (lambda* (#:key outputs #:allow-other-keys)
5234 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5235 (install-file "seqtk" bin)))))))
5238 (home-page "https://github.com/lh3/seqtk")
5239 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5241 "Seqtk is a fast and lightweight tool for processing sequences in the
5242 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5243 optionally compressed by gzip.")
5244 (license license:expat)))
5246 (define-public snap-aligner
5248 (name "snap-aligner")
5249 (version "1.0beta.18")
5253 "https://github.com/amplab/snap/archive/v"
5255 (file-name (string-append name "-" version ".tar.gz"))
5258 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5259 (build-system gnu-build-system)
5262 (modify-phases %standard-phases
5264 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5266 (lambda* (#:key outputs #:allow-other-keys)
5267 (let* ((out (assoc-ref outputs "out"))
5268 (bin (string-append out "/bin")))
5269 (install-file "snap-aligner" bin)
5270 (install-file "SNAPCommand" bin)
5274 (home-page "http://snap.cs.berkeley.edu/")
5275 (synopsis "Short read DNA sequence aligner")
5277 "SNAP is a fast and accurate aligner for short DNA reads. It is
5278 optimized for modern read lengths of 100 bases or higher, and takes advantage
5279 of these reads to align data quickly through a hash-based indexing scheme.")
5280 ;; 32-bit systems are not supported by the unpatched code.
5281 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5282 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5283 ;; systems without a lot of memory cannot make good use of this program.
5284 (supported-systems '("x86_64-linux"))
5285 (license license:asl2.0)))
5287 (define-public sortmerna
5295 "https://github.com/biocore/sortmerna/archive/"
5297 (file-name (string-append name "-" version ".tar.gz"))
5300 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5301 (build-system gnu-build-system)
5302 (outputs '("out" ;for binaries
5303 "db")) ;for sequence databases
5306 (modify-phases %standard-phases
5308 (lambda* (#:key outputs #:allow-other-keys)
5309 (let* ((out (assoc-ref outputs "out"))
5310 (bin (string-append out "/bin"))
5311 (db (assoc-ref outputs "db"))
5313 (string-append db "/share/sortmerna/rRNA_databases")))
5314 (install-file "sortmerna" bin)
5315 (install-file "indexdb_rna" bin)
5316 (for-each (lambda (file)
5317 (install-file file share))
5318 (find-files "rRNA_databases" ".*fasta"))
5322 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5323 (synopsis "Biological sequence analysis tool for NGS reads")
5325 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5326 and operational taxonomic unit (OTU) picking of next generation
5327 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5328 allows for fast and sensitive analyses of nucleotide sequences. The main
5329 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5330 ;; The source includes x86 specific code
5331 (supported-systems '("x86_64-linux" "i686-linux"))
5332 (license license:lgpl3)))
5340 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5342 (file-name (string-append name "-" version ".tar.gz"))
5345 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5346 (modules '((guix build utils)))
5349 (substitute* "source/Makefile"
5351 ;; Remove pre-built binaries and bundled htslib sources.
5352 (delete-file-recursively "bin/MacOSX_x86_64")
5353 (delete-file-recursively "bin/Linux_x86_64")
5354 (delete-file-recursively "bin/Linux_x86_64_static")
5355 (delete-file-recursively "source/htslib")
5357 (build-system gnu-build-system)
5359 '(#:tests? #f ;no check target
5360 #:make-flags '("STAR")
5362 (modify-phases %standard-phases
5363 (add-after 'unpack 'enter-source-dir
5364 (lambda _ (chdir "source") #t))
5365 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5367 (substitute* "Makefile"
5368 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5370 (substitute* '("BAMfunctions.cpp"
5375 "bamRemoveDuplicates.cpp")
5376 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5377 (string-append "#include <" header ">")))
5378 (substitute* "IncludeDefine.h"
5379 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5380 (string-append "<" header ">")))
5383 (lambda* (#:key outputs #:allow-other-keys)
5384 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5385 (install-file "STAR" bin))
5387 (delete 'configure))))
5389 `(("vim" ,vim))) ; for xxd
5391 `(("htslib" ,htslib)
5393 (home-page "https://github.com/alexdobin/STAR")
5394 (synopsis "Universal RNA-seq aligner")
5396 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5397 based on a previously undescribed RNA-seq alignment algorithm that uses
5398 sequential maximum mappable seed search in uncompressed suffix arrays followed
5399 by seed clustering and stitching procedure. In addition to unbiased de novo
5400 detection of canonical junctions, STAR can discover non-canonical splices and
5401 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5403 ;; Only 64-bit systems are supported according to the README.
5404 (supported-systems '("x86_64-linux" "mips64el-linux"))
5405 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5406 (license license:gpl3+)))
5408 (define-public subread
5414 (uri (string-append "mirror://sourceforge/subread/subread-"
5415 version "/subread-" version "-source.tar.gz"))
5418 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5419 (build-system gnu-build-system)
5421 `(#:tests? #f ;no "check" target
5422 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5423 ;; optimizations by default, so we override these flags such that x86_64
5424 ;; flags are only added when the build target is an x86_64 system.
5426 (list (let ((system ,(or (%current-target-system)
5428 (flags '("-ggdb" "-fomit-frame-pointer"
5429 "-ffast-math" "-funroll-loops"
5430 "-fmessage-length=0"
5431 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5433 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5434 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5435 (if (string-prefix? "x86_64" system)
5436 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5437 (string-append "CCFLAGS=" (string-join flags))))
5438 "-f" "Makefile.Linux"
5439 "CC=gcc ${CCFLAGS}")
5443 (lambda _ (chdir "src") #t)
5446 (lambda* (#:key outputs #:allow-other-keys)
5447 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5449 (copy-recursively "../bin" bin)))
5450 ;; no "configure" script
5451 (alist-delete 'configure %standard-phases)))))
5452 (inputs `(("zlib" ,zlib)))
5453 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5454 (synopsis "Tool kit for processing next-gen sequencing data")
5456 "The subread package contains the following tools: subread aligner, a
5457 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5458 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5459 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5460 against local background noises.")
5461 (license license:gpl3+)))
5463 (define-public stringtie
5469 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5470 "stringtie-" version ".tar.gz"))
5473 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5474 (modules '((guix build utils)))
5477 (delete-file-recursively "samtools-0.1.18")
5479 (build-system gnu-build-system)
5481 `(#:tests? #f ;no test suite
5483 (modify-phases %standard-phases
5484 ;; no configure script
5486 (add-before 'build 'use-system-samtools
5488 (substitute* "Makefile"
5489 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5491 (substitute* '("gclib/GBam.h"
5493 (("#include \"(bam|sam|kstring).h\"" _ header)
5494 (string-append "#include <samtools/" header ".h>")))
5496 (add-after 'unpack 'remove-duplicate-typedef
5498 ;; This typedef conflicts with the typedef in
5499 ;; glibc-2.25/include/bits/types.h
5500 (substitute* "gclib/GThreads.h"
5501 (("typedef long long __intmax_t;") ""))
5504 (lambda* (#:key outputs #:allow-other-keys)
5505 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5506 (install-file "stringtie" bin)
5509 `(("samtools" ,samtools-0.1)
5511 (home-page "http://ccb.jhu.edu/software/stringtie/")
5512 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5514 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5515 alignments into potential transcripts. It uses a novel network flow algorithm
5516 as well as an optional de novo assembly step to assemble and quantitate
5517 full-length transcripts representing multiple splice variants for each gene
5518 locus. Its input can include not only the alignments of raw reads used by
5519 other transcript assemblers, but also alignments of longer sequences that have
5520 been assembled from those reads. To identify differentially expressed genes
5521 between experiments, StringTie's output can be processed either by the
5522 Cuffdiff or Ballgown programs.")
5523 (license license:artistic2.0)))
5525 (define-public taxtastic
5531 (uri (pypi-uri "taxtastic" version))
5534 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5535 (build-system python-build-system)
5537 `(#:python ,python-2
5539 (modify-phases %standard-phases
5542 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5544 `(("python-sqlalchemy" ,python2-sqlalchemy)
5545 ("python-decorator" ,python2-decorator)
5546 ("python-biopython" ,python2-biopython)
5547 ("python-pandas" ,python2-pandas)))
5548 (home-page "https://github.com/fhcrc/taxtastic")
5549 (synopsis "Tools for taxonomic naming and annotation")
5551 "Taxtastic is software written in python used to build and maintain
5552 reference packages i.e. collections of reference trees, reference alignments,
5553 profiles, and associated taxonomic information.")
5554 (license license:gpl3+)))
5556 (define-public vcftools
5563 "https://github.com/vcftools/vcftools/releases/download/v"
5564 version "/vcftools-" version ".tar.gz"))
5567 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5568 (build-system gnu-build-system)
5570 `(#:tests? #f ; no "check" target
5572 "CFLAGS=-O2" ; override "-m64" flag
5573 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5574 (string-append "MANDIR=" (assoc-ref %outputs "out")
5575 "/share/man/man1"))))
5577 `(("pkg-config" ,pkg-config)))
5581 (home-page "https://vcftools.github.io/")
5582 (synopsis "Tools for working with VCF files")
5584 "VCFtools is a program package designed for working with VCF files, such
5585 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5586 provide easily accessible methods for working with complex genetic variation
5587 data in the form of VCF files.")
5588 ;; The license is declared as LGPLv3 in the README and
5589 ;; at https://vcftools.github.io/license.html
5590 (license license:lgpl3)))
5592 (define-public infernal
5598 (uri (string-append "http://eddylab.org/software/infernal/"
5599 "infernal-" version ".tar.gz"))
5602 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5603 (build-system gnu-build-system)
5605 `(("perl" ,perl))) ; for tests
5606 (home-page "http://eddylab.org/infernal/")
5607 (synopsis "Inference of RNA alignments")
5608 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5609 searching DNA sequence databases for RNA structure and sequence similarities.
5610 It is an implementation of a special case of profile stochastic context-free
5611 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5612 profile, but it scores a combination of sequence consensus and RNA secondary
5613 structure consensus, so in many cases, it is more capable of identifying RNA
5614 homologs that conserve their secondary structure more than their primary
5616 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5617 (supported-systems '("i686-linux" "x86_64-linux"))
5618 (license license:bsd-3)))
5620 (define-public r-centipede
5622 (name "r-centipede")
5626 (uri (string-append "http://download.r-forge.r-project.org/"
5627 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5630 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5631 (build-system r-build-system)
5632 (home-page "http://centipede.uchicago.edu/")
5633 (synopsis "Predict transcription factor binding sites")
5635 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5636 of the genome that are bound by particular transcription factors. It starts
5637 by identifying a set of candidate binding sites, and then aims to classify the
5638 sites according to whether each site is bound or not bound by a transcription
5639 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5640 between two different types of motif instances using as much relevant
5641 information as possible.")
5642 (license (list license:gpl2+ license:gpl3+))))
5644 (define-public r-vegan
5651 (uri (cran-uri "vegan" version))
5654 "15zcxfix2d854897k1lr0sfmj2n00339nlsppcr3zrb238lb2mi5"))))
5655 (build-system r-build-system)
5657 `(("gfortran" ,gfortran)
5658 ("r-knitr" ,r-knitr)))
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 "03hmbvp3i6lvd307fqdg7akxi2qp322rlky3bzw0zccgm0i0221g"))))
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 "http://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 "0a0ajns21db5rrjl16bq6wawggsnxr00fg184pc38nmfghv4z4b6"))))
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 "http://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 "0sf2hdi9nv6r83vn1y65m4jiba8pffddpj46d6yjn5rlsixplmqg"))))
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 "http://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 "0m0apn3xi4kdkinsj4xkw5cwysicyjr6xxlxhpa4scyv589am1s5"))))
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 "http://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-annotationforge
5792 (name "r-annotationforge")
5797 (uri (bioconductor-uri "AnnotationForge" version))
5800 "01kd86vvgpa4a5zivcy4g6z8rhcykasdskrz8yqsqz211sd1xsr3"))))
5802 `((upstream-name . "AnnotationForge")))
5803 (build-system r-build-system)
5805 `(("r-annotationdbi" ,r-annotationdbi)
5806 ("r-biobase" ,r-biobase)
5807 ("r-biocgenerics" ,r-biocgenerics)
5809 ("r-rcurl" ,r-rcurl)
5810 ("r-rsqlite" ,r-rsqlite)
5811 ("r-s4vectors" ,r-s4vectors)
5813 (home-page "http://bioconductor.org/packages/AnnotationForge")
5814 (synopsis "Code for building annotation database packages")
5816 "This package provides code for generating Annotation packages and their
5817 databases. Packages produced are intended to be used with AnnotationDbi.")
5818 (license license:artistic2.0)))
5820 (define-public r-rbgl
5827 (uri (bioconductor-uri "RBGL" version))
5830 "11db6kvz453ypj9ds3xpjqzwrrjck84ijn4wlhkfyz2dzdgd5ryv"))))
5831 (properties `((upstream-name . "RBGL")))
5832 (build-system r-build-system)
5833 (propagated-inputs `(("r-graph" ,r-graph)))
5834 (home-page "http://www.bioconductor.org/packages/RBGL")
5835 (synopsis "Interface to the Boost graph library")
5837 "This package provides a fairly extensive and comprehensive interface to
5838 the graph algorithms contained in the Boost library.")
5839 (license license:artistic2.0)))
5841 (define-public r-gseabase
5848 (uri (bioconductor-uri "GSEABase" version))
5851 "1c6i6g4fj3b8wjyxyygr7i3v8sxrq1ffb2bbicya5ah2gdaclfad"))))
5852 (properties `((upstream-name . "GSEABase")))
5853 (build-system r-build-system)
5855 `(("r-annotate" ,r-annotate)
5856 ("r-annotationdbi" ,r-annotationdbi)
5857 ("r-biobase" ,r-biobase)
5858 ("r-biocgenerics" ,r-biocgenerics)
5859 ("r-graph" ,r-graph)
5861 (home-page "http://bioconductor.org/packages/GSEABase")
5862 (synopsis "Gene set enrichment data structures and methods")
5864 "This package provides classes and methods to support @dfn{Gene Set
5865 Enrichment Analysis} (GSEA).")
5866 (license license:artistic2.0)))
5868 (define-public r-category
5875 (uri (bioconductor-uri "Category" version))
5878 "0swcmihyjg0fhaaydl9hm24aj9zffw3bibza9y6sqs6jaqd97f09"))))
5879 (properties `((upstream-name . "Category")))
5880 (build-system r-build-system)
5882 `(("r-annotate" ,r-annotate)
5883 ("r-annotationdbi" ,r-annotationdbi)
5884 ("r-biobase" ,r-biobase)
5885 ("r-biocgenerics" ,r-biocgenerics)
5886 ("r-genefilter" ,r-genefilter)
5887 ("r-graph" ,r-graph)
5888 ("r-gseabase" ,r-gseabase)
5889 ("r-matrix" ,r-matrix)
5891 ("r-rsqlite" ,r-rsqlite)))
5892 (home-page "http://bioconductor.org/packages/Category")
5893 (synopsis "Category analysis")
5895 "This package provides a collection of tools for performing category
5897 (license license:artistic2.0)))
5899 (define-public r-gostats
5906 (uri (bioconductor-uri "GOstats" version))
5909 "0qvqjgfnd9ap4rikvyxa9p4dhcnccvkw8phzv88vghh6pq463d62"))))
5910 (properties `((upstream-name . "GOstats")))
5911 (build-system r-build-system)
5913 `(("r-annotate" ,r-annotate)
5914 ("r-annotationdbi" ,r-annotationdbi)
5915 ("r-annotationforge" ,r-annotationforge)
5916 ("r-biobase" ,r-biobase)
5917 ("r-category" ,r-category)
5918 ("r-go-db" ,r-go-db)
5919 ("r-graph" ,r-graph)
5920 ("r-rbgl" ,r-rbgl)))
5921 (home-page "http://bioconductor.org/packages/GOstats")
5922 (synopsis "Tools for manipulating GO and microarrays")
5924 "This package provides a set of tools for interacting with GO and
5925 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5926 testing and other simple calculations.")
5927 (license license:artistic2.0)))
5929 (define-public r-shortread
5931 (name "r-shortread")
5936 (uri (bioconductor-uri "ShortRead" version))
5939 "0ayk3d5625ymb5g2gycq6banzqmyd642xrwjzhdshz2dwid7kly8"))))
5940 (properties `((upstream-name . "ShortRead")))
5941 (build-system r-build-system)
5945 `(("r-biobase" ,r-biobase)
5946 ("r-biocgenerics" ,r-biocgenerics)
5947 ("r-biocparallel" ,r-biocparallel)
5948 ("r-biostrings" ,r-biostrings)
5949 ("r-genomeinfodb" ,r-genomeinfodb)
5950 ("r-genomicalignments" ,r-genomicalignments)
5951 ("r-genomicranges" ,r-genomicranges)
5952 ("r-hwriter" ,r-hwriter)
5953 ("r-iranges" ,r-iranges)
5954 ("r-lattice" ,r-lattice)
5955 ("r-latticeextra" ,r-latticeextra)
5956 ("r-rsamtools" ,r-rsamtools)
5957 ("r-s4vectors" ,r-s4vectors)
5958 ("r-xvector" ,r-xvector)
5959 ("r-zlibbioc" ,r-zlibbioc)))
5960 (home-page "http://bioconductor.org/packages/ShortRead")
5961 (synopsis "FASTQ input and manipulation tools")
5963 "This package implements sampling, iteration, and input of FASTQ files.
5964 It includes functions for filtering and trimming reads, and for generating a
5965 quality assessment report. Data are represented as
5966 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5967 purposes. The package also contains legacy support for early single-end,
5968 ungapped alignment formats.")
5969 (license license:artistic2.0)))
5971 (define-public r-systempiper
5973 (name "r-systempiper")
5978 (uri (bioconductor-uri "systemPipeR" version))
5981 "0c3m5rq63ypv15yca97yag5d4vgd7xj9by2a4sd8z0pcmpajz0hw"))))
5982 (properties `((upstream-name . "systemPipeR")))
5983 (build-system r-build-system)
5985 `(("r-annotate" ,r-annotate)
5986 ("r-batchjobs" ,r-batchjobs)
5987 ("r-biocgenerics" ,r-biocgenerics)
5988 ("r-biostrings" ,r-biostrings)
5989 ("r-deseq2" ,r-deseq2)
5990 ("r-edger" ,r-edger)
5991 ("r-genomicfeatures" ,r-genomicfeatures)
5992 ("r-genomicranges" ,r-genomicranges)
5993 ("r-ggplot2" ,r-ggplot2)
5994 ("r-go-db" ,r-go-db)
5995 ("r-gostats" ,r-gostats)
5996 ("r-limma" ,r-limma)
5997 ("r-pheatmap" ,r-pheatmap)
5998 ("r-rjson" ,r-rjson)
5999 ("r-rsamtools" ,r-rsamtools)
6000 ("r-shortread" ,r-shortread)
6001 ("r-summarizedexperiment" ,r-summarizedexperiment)
6002 ("r-variantannotation" ,r-variantannotation)))
6003 (home-page "https://github.com/tgirke/systemPipeR")
6004 (synopsis "Next generation sequencing workflow and reporting environment")
6006 "This R package provides tools for building and running automated
6007 end-to-end analysis workflows for a wide range of @dfn{next generation
6008 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6009 Important features include a uniform workflow interface across different NGS
6010 applications, automated report generation, and support for running both R and
6011 command-line software, such as NGS aligners or peak/variant callers, on local
6012 computers or compute clusters. Efficient handling of complex sample sets and
6013 experimental designs is facilitated by a consistently implemented sample
6014 annotation infrastructure.")
6015 (license license:artistic2.0)))
6017 (define-public r-grohmm
6024 (uri (bioconductor-uri "groHMM" version))
6027 "16k1kp4sbhh0vp7dzywafq52csq42ksqfrqfy4bdv1qbd7536dpd"))))
6028 (properties `((upstream-name . "groHMM")))
6029 (build-system r-build-system)
6031 `(("r-genomeinfodb" ,r-genomeinfodb)
6032 ("r-genomicalignments" ,r-genomicalignments)
6033 ("r-genomicranges" ,r-genomicranges)
6034 ("r-iranges" ,r-iranges)
6036 ("r-rtracklayer" ,r-rtracklayer)
6037 ("r-s4vectors" ,r-s4vectors)))
6038 (home-page "https://github.com/Kraus-Lab/groHMM")
6039 (synopsis "GRO-seq analysis pipeline")
6041 "This package provides a pipeline for the analysis of GRO-seq data.")
6042 (license license:gpl3+)))
6044 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6046 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6050 ;; We cannot use bioconductor-uri here because this tarball is
6051 ;; located under "data/annotation/" instead of "bioc/".
6052 (uri (string-append "http://bioconductor.org/packages/"
6053 "release/data/annotation/src/contrib"
6054 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6058 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6060 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6061 (build-system r-build-system)
6062 ;; As this package provides little more than a very large data file it
6063 ;; doesn't make sense to build substitutes.
6064 (arguments `(#:substitutable? #f))
6066 `(("r-genomicfeatures" ,r-genomicfeatures)))
6068 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6069 (synopsis "Annotation package for human genome in TxDb format")
6071 "This package provides an annotation database of Homo sapiens genome
6072 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6073 track. The database is exposed as a @code{TxDb} object.")
6074 (license license:artistic2.0)))
6076 (define-public vsearch
6084 "https://github.com/torognes/vsearch/archive/v"
6086 (file-name (string-append name "-" version ".tar.gz"))
6089 "0hc110ycqpa54nr6x173qg7190hk08qp7yz7zzqxlsypqnpc5zzp"))
6090 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6093 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6094 ;; for this in the patch.
6095 (delete-file "src/city.h")
6096 (delete-file "src/citycrc.h")
6097 (delete-file "src/city.cc")
6099 (build-system gnu-build-system)
6102 (modify-phases %standard-phases
6103 (add-before 'configure 'autogen
6104 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6108 ("cityhash" ,cityhash)))
6110 `(("autoconf" ,autoconf)
6111 ("automake" ,automake)))
6112 (synopsis "Sequence search tools for metagenomics")
6114 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6115 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6116 masking. The tool takes advantage of parallelism in the form of SIMD
6117 vectorization as well as multiple threads to perform accurate alignments at
6118 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6119 Needleman-Wunsch).")
6120 (home-page "https://github.com/torognes/vsearch")
6121 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6123 (supported-systems '("x86_64-linux"))
6124 ;; Dual licensed; also includes public domain source.
6125 (license (list license:gpl3 license:bsd-2))))
6127 (define-public pardre
6130 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6135 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6139 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6140 (build-system gnu-build-system)
6142 `(#:tests? #f ; no tests included
6144 (modify-phases %standard-phases
6147 (lambda* (#:key outputs #:allow-other-keys)
6148 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6149 (install-file "ParDRe" bin)
6152 `(("openmpi" ,openmpi)
6154 (synopsis "Parallel tool to remove duplicate DNA reads")
6156 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6157 Duplicate reads can be seen as identical or nearly identical sequences with
6158 some mismatches. This tool lets users avoid the analysis of unnecessary
6159 reads, reducing the time of subsequent procedures with the
6160 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6161 in order to exploit the parallel capabilities of multicore clusters. It is
6162 faster than multithreaded counterparts (end of 2015) for the same number of
6163 cores and, thanks to the message-passing technology, it can be executed on
6165 (home-page "https://sourceforge.net/projects/pardre/")
6166 (license license:gpl3+)))
6168 (define-public ruby-bio-kseq
6170 (name "ruby-bio-kseq")
6175 (uri (rubygems-uri "bio-kseq" version))
6178 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6179 (build-system ruby-build-system)
6181 `(#:test-target "spec"))
6183 `(("bundler" ,bundler)
6184 ("ruby-rspec" ,ruby-rspec)
6185 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6188 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6190 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6191 FASTQ parsing code. It provides a fast iterator over sequences and their
6193 (home-page "https://github.com/gusevfe/bio-kseq")
6194 (license license:expat)))
6196 (define-public bio-locus
6203 (uri (rubygems-uri "bio-locus" version))
6206 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6207 (build-system ruby-build-system)
6209 `(("ruby-rspec" ,ruby-rspec)))
6210 (synopsis "Tool for fast querying of genome locations")
6212 "Bio-locus is a tabix-like tool for fast querying of genome
6213 locations. Many file formats in bioinformatics contain records that
6214 start with a chromosome name and a position for a SNP, or a start-end
6215 position for indels. Bio-locus allows users to store this chr+pos or
6216 chr+pos+alt information in a database.")
6217 (home-page "https://github.com/pjotrp/bio-locus")
6218 (license license:expat)))
6220 (define-public bio-blastxmlparser
6222 (name "bio-blastxmlparser")
6226 (uri (rubygems-uri "bio-blastxmlparser" version))
6229 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6230 (build-system ruby-build-system)
6232 `(("ruby-bio-logger" ,ruby-bio-logger)
6233 ("ruby-nokogiri" ,ruby-nokogiri)))
6235 `(("ruby-rspec" ,ruby-rspec)))
6236 (synopsis "Fast big data BLAST XML parser and library")
6238 "Very fast parallel big-data BLAST XML file parser which can be used as
6239 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6240 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6241 (home-page "https://github.com/pjotrp/blastxmlparser")
6242 (license license:expat)))
6244 (define-public bioruby
6251 (uri (rubygems-uri "bio" version))
6254 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6255 (build-system ruby-build-system)
6257 `(("ruby-libxml" ,ruby-libxml)))
6259 `(("which" ,which))) ; required for test phase
6262 (modify-phases %standard-phases
6263 (add-before 'build 'patch-test-command
6265 (substitute* '("test/functional/bio/test_command.rb")
6266 (("/bin/sh") (which "sh")))
6267 (substitute* '("test/functional/bio/test_command.rb")
6268 (("/bin/ls") (which "ls")))
6269 (substitute* '("test/functional/bio/test_command.rb")
6270 (("which") (which "which")))
6271 (substitute* '("test/functional/bio/test_command.rb",
6272 "test/data/command/echoarg2.sh")
6273 (("/bin/echo") (which "echo")))
6275 (synopsis "Ruby library, shell and utilities for bioinformatics")
6276 (description "BioRuby comes with a comprehensive set of Ruby development
6277 tools and libraries for bioinformatics and molecular biology. BioRuby has
6278 components for sequence analysis, pathway analysis, protein modelling and
6279 phylogenetic analysis; it supports many widely used data formats and provides
6280 easy access to databases, external programs and public web services, including
6281 BLAST, KEGG, GenBank, MEDLINE and GO.")
6282 (home-page "http://bioruby.org/")
6283 ;; Code is released under Ruby license, except for setup
6284 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6285 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6287 (define-public r-acsnminer
6289 (name "r-acsnminer")
6290 (version "0.16.8.25")
6293 (uri (cran-uri "ACSNMineR" version))
6296 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6297 (properties `((upstream-name . "ACSNMineR")))
6298 (build-system r-build-system)
6300 `(("r-ggplot2" ,r-ggplot2)
6301 ("r-gridextra" ,r-gridextra)))
6302 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6303 (synopsis "Gene enrichment analysis")
6305 "This package provides tools to compute and represent gene set enrichment
6306 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6307 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6308 enrichment can be run with hypergeometric test or Fisher exact test, and can
6309 use multiple corrections. Visualization of data can be done either by
6310 barplots or heatmaps.")
6311 (license license:gpl2+)))
6313 (define-public r-biocgenerics
6315 (name "r-biocgenerics")
6319 (uri (bioconductor-uri "BiocGenerics" version))
6322 "0qbmz2qxwwi30xpxpvp2h1h7l494rbbz5d9pls5cfhqdv3wnpzsv"))))
6324 `((upstream-name . "BiocGenerics")))
6325 (build-system r-build-system)
6326 (home-page "http://bioconductor.org/packages/BiocGenerics")
6327 (synopsis "S4 generic functions for Bioconductor")
6329 "This package provides S4 generic functions needed by many Bioconductor
6331 (license license:artistic2.0)))
6333 (define-public r-biocinstaller
6335 (name "r-biocinstaller")
6339 (uri (bioconductor-uri "BiocInstaller" version))
6342 "0njw2q3lq1rrjx8qzw5d2130l72bmd3g2z8qlxqmkdcbmmgliyj2"))))
6344 `((upstream-name . "BiocInstaller")))
6345 (build-system r-build-system)
6346 (home-page "http://bioconductor.org/packages/BiocInstaller")
6347 (synopsis "Install Bioconductor packages")
6348 (description "This package is used to install and update R packages from
6349 Bioconductor, CRAN, and Github.")
6350 (license license:artistic2.0)))
6352 (define-public r-biocviews
6354 (name "r-biocviews")
6358 (uri (bioconductor-uri "biocViews" version))
6361 "17hi8w0w63f5yc43kid5pbld3ca78sj6n8x9dmkbl8h48818xbga"))))
6363 `((upstream-name . "biocViews")))
6364 (build-system r-build-system)
6366 `(("r-biobase" ,r-biobase)
6367 ("r-graph" ,r-graph)
6369 ("r-rcurl" ,r-rcurl)
6371 ("r-knitr" ,r-knitr)
6372 ("r-runit" ,r-runit)))
6373 (home-page "http://bioconductor.org/packages/biocViews")
6374 (synopsis "Bioconductor package categorization helper")
6375 (description "The purpose of biocViews is to create HTML pages that
6376 categorize packages in a Bioconductor package repository according to keywords,
6377 also known as views, in a controlled vocabulary.")
6378 (license license:artistic2.0)))
6380 (define-public r-bookdown
6386 (uri (cran-uri "bookdown" version))
6389 "0r9bchzg7im6psc3jphvshzbidc5bv5xaih1qg7b5518jy4iyvb9"))))
6390 (build-system r-build-system)
6392 `(("r-htmltools" ,r-htmltools)
6393 ("r-knitr" ,r-knitr)
6394 ("r-rmarkdown" ,r-rmarkdown)
6395 ("r-yaml" ,r-yaml)))
6396 (home-page "https://github.com/rstudio/bookdown")
6397 (synopsis "Authoring books and technical documents with R markdown")
6398 (description "This package provides output formats and utilities for
6399 authoring books and technical documents with R Markdown.")
6400 (license license:gpl3)))
6402 (define-public r-biocstyle
6404 (name "r-biocstyle")
6408 (uri (bioconductor-uri "BiocStyle" version))
6411 "1n2c8rj920wmk3q2khmjfnhn5i4b3lmhx1whnghk0zk3jf88hvbi"))))
6413 `((upstream-name . "BiocStyle")))
6414 (build-system r-build-system)
6416 `(("r-bookdown" ,r-bookdown)
6417 ("r-knitr" ,r-knitr)
6418 ("r-rmarkdown" ,r-rmarkdown)
6419 ("r-yaml" ,r-yaml)))
6420 (home-page "http://bioconductor.org/packages/BiocStyle")
6421 (synopsis "Bioconductor formatting styles")
6422 (description "This package provides standard formatting styles for
6423 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6425 (license license:artistic2.0)))
6427 (define-public r-bioccheck
6429 (name "r-bioccheck")
6433 (uri (bioconductor-uri "BiocCheck" version))
6436 "01zkw5hggzvn0wj4msac71k1mknq4h2inn1c2hwqgw4cy1675wl0"))))
6438 `((upstream-name . "BiocCheck")))
6439 (build-system r-build-system)
6442 (modify-phases %standard-phases
6443 ;; This package can be used by calling BiocCheck(<package>) from
6444 ;; within R, or by running R CMD BiocCheck <package>. This phase
6445 ;; makes sure the latter works. For this to work, the BiocCheck
6446 ;; script must be somewhere on the PATH (not the R bin directory).
6447 (add-after 'install 'install-bioccheck-subcommand
6448 (lambda* (#:key outputs #:allow-other-keys)
6449 (let* ((out (assoc-ref outputs "out"))
6450 (dest-dir (string-append out "/bin"))
6452 (string-append out "/site-library/BiocCheck/script/")))
6454 (symlink (string-append script-dir "/checkBadDeps.R")
6455 (string-append dest-dir "/checkBadDeps.R"))
6456 (symlink (string-append script-dir "/BiocCheck")
6457 (string-append dest-dir "/BiocCheck")))
6460 `(("which" ,which)))
6462 `(("r-codetools" ,r-codetools)
6463 ("r-graph" ,r-graph)
6465 ("r-optparse" ,r-optparse)
6466 ("r-biocinstaller" ,r-biocinstaller)
6467 ("r-biocviews" ,r-biocviews)))
6468 (home-page "http://bioconductor.org/packages/BiocCheck")
6469 (synopsis "Executes Bioconductor-specific package checks")
6470 (description "This package contains tools to perform additional quality
6471 checks on R packages that are to be submitted to the Bioconductor repository.")
6472 (license license:artistic2.0)))
6474 (define-public r-getopt
6481 (uri (cran-uri "getopt" version))
6484 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6485 (build-system r-build-system)
6486 (home-page "https://github.com/trevorld/getopt")
6487 (synopsis "Command-line option processor for R")
6489 "This package is designed to be used with Rscript to write shebang
6490 scripts that accept short and long options. Many users will prefer to
6491 use the packages @code{optparse} or @code{argparse} which add extra
6492 features like automatically generated help options and usage texts,
6493 support for default values, positional argument support, etc.")
6494 (license license:gpl2+)))
6496 (define-public r-optparse
6503 (uri (cran-uri "optparse" version))
6506 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6507 (build-system r-build-system)
6509 `(("r-getopt" ,r-getopt)))
6511 "https://github.com/trevorld/optparse")
6512 (synopsis "Command line option parser")
6514 "This package provides a command line parser inspired by Python's
6515 @code{optparse} library to be used with Rscript to write shebang scripts
6516 that accept short and long options.")
6517 (license license:gpl2+)))
6519 (define-public r-dnacopy
6525 (uri (bioconductor-uri "DNAcopy" version))
6528 "0112ry62z18m7rdyrn3gvbxq2f6m44cawhcfb1f02z9xzlsj0k28"))))
6530 `((upstream-name . "DNAcopy")))
6531 (build-system r-build-system)
6533 `(("gfortran" ,gfortran)))
6534 (home-page "https://bioconductor.org/packages/DNAcopy")
6535 (synopsis "Implementation of a circular binary segmentation algorithm")
6536 (description "This package implements the circular binary segmentation (CBS)
6537 algorithm to segment DNA copy number data and identify genomic regions with
6538 abnormal copy number.")
6539 (license license:gpl2+)))
6541 (define-public r-s4vectors
6543 (name "r-s4vectors")
6547 (uri (bioconductor-uri "S4Vectors" version))
6550 "1r7s4pfw026qazzic090mhk8d9m39j2nwl87dyqcpdylyq7gq5qs"))))
6552 `((upstream-name . "S4Vectors")))
6553 (build-system r-build-system)
6555 `(("r-biocgenerics" ,r-biocgenerics)))
6556 (home-page "http://bioconductor.org/packages/S4Vectors")
6557 (synopsis "S4 implementation of vectors and lists")
6559 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6560 classes and a set of generic functions that extend the semantic of ordinary
6561 vectors and lists in R. Package developers can easily implement vector-like
6562 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6563 In addition, a few low-level concrete subclasses of general interest (e.g.
6564 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6565 S4Vectors package itself.")
6566 (license license:artistic2.0)))
6568 (define-public r-seqinr
6575 (uri (cran-uri "seqinr" version))
6578 "13d0qxm2244wgdl2dy2s8vnrnf5fx4n47if9gkb49dqx6c0sx8s2"))))
6579 (build-system r-build-system)
6581 `(("r-ade4" ,r-ade4)
6582 ("r-segmented" ,r-segmented)))
6585 (home-page "http://seqinr.r-forge.r-project.org/")
6586 (synopsis "Biological sequences retrieval and analysis")
6588 "This package provides tools for exploratory data analysis and data
6589 visualization of biological sequence (DNA and protein) data. It also includes
6590 utilities for sequence data management under the ACNUC system.")
6591 (license license:gpl2+)))
6593 (define-public r-iranges
6599 (uri (bioconductor-uri "IRanges" version))
6602 "0zp4mxm9h1p4krj7m7cinkvwa2ibqkq59jwpan97yvhb4z8q0d6n"))))
6604 `((upstream-name . "IRanges")))
6605 (build-system r-build-system)
6607 `(("r-biocgenerics" ,r-biocgenerics)
6608 ("r-s4vectors" ,r-s4vectors)))
6609 (home-page "http://bioconductor.org/packages/IRanges")
6610 (synopsis "Infrastructure for manipulating intervals on sequences")
6612 "This package provides efficient low-level and highly reusable S4 classes
6613 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6614 generally, data that can be organized sequentially (formally defined as
6615 @code{Vector} objects), as well as views on these @code{Vector} objects.
6616 Efficient list-like classes are also provided for storing big collections of
6617 instances of the basic classes. All classes in the package use consistent
6618 naming and share the same rich and consistent \"Vector API\" as much as
6620 (license license:artistic2.0)))
6622 (define-public r-genomeinfodbdata
6624 (name "r-genomeinfodbdata")
6628 ;; We cannot use bioconductor-uri here because this tarball is
6629 ;; located under "data/annotation/" instead of "bioc/".
6630 (uri (string-append "https://bioconductor.org/packages/release/"
6631 "data/annotation/src/contrib/GenomeInfoDbData_"
6635 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6637 `((upstream-name . "GenomeInfoDbData")))
6638 (build-system r-build-system)
6639 (home-page "http://bioconductor.org/packages/GenomeInfoDbData")
6640 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6641 (description "This package contains data for mapping between NCBI taxonomy
6642 ID and species. It is used by functions in the GenomeInfoDb package.")
6643 (license license:artistic2.0)))
6645 (define-public r-genomeinfodb
6647 (name "r-genomeinfodb")
6651 (uri (bioconductor-uri "GenomeInfoDb" version))
6654 "1bwwhscjl376a5p43mx8ijrqajxmgypbqhv049pgagl22hkkf0y3"))))
6656 `((upstream-name . "GenomeInfoDb")))
6657 (build-system r-build-system)
6659 `(("r-biocgenerics" ,r-biocgenerics)
6660 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6661 ("r-iranges" ,r-iranges)
6662 ("r-rcurl" ,r-rcurl)
6663 ("r-s4vectors" ,r-s4vectors)))
6664 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6665 (synopsis "Utilities for manipulating chromosome identifiers")
6667 "This package contains data and functions that define and allow
6668 translation between different chromosome sequence naming conventions (e.g.,
6669 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6670 names in their natural, rather than lexicographic, order.")
6671 (license license:artistic2.0)))
6673 (define-public r-edger
6679 (uri (bioconductor-uri "edgeR" version))
6682 "02l17i6xh33dv10swwvyfxrmv5kp23iv278iwvkfq2mnipasfnb9"))))
6683 (properties `((upstream-name . "edgeR")))
6684 (build-system r-build-system)
6686 `(("r-limma" ,r-limma)
6687 ("r-locfit" ,r-locfit)
6688 ("r-statmod" ,r-statmod))) ;for estimateDisp
6689 (home-page "http://bioinf.wehi.edu.au/edgeR")
6690 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6691 (description "This package can do differential expression analysis of
6692 RNA-seq expression profiles with biological replication. It implements a range
6693 of statistical methodology based on the negative binomial distributions,
6694 including empirical Bayes estimation, exact tests, generalized linear models
6695 and quasi-likelihood tests. It be applied to differential signal analysis of
6696 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6698 (license license:gpl2+)))
6700 (define-public r-variantannotation
6702 (name "r-variantannotation")
6706 (uri (bioconductor-uri "VariantAnnotation" version))
6709 "05hpm4as36kvpiqhgnkfjwfx0a05p304c21ggba29iac4nanm8b3"))))
6711 `((upstream-name . "VariantAnnotation")))
6715 `(("r-annotationdbi" ,r-annotationdbi)
6716 ("r-biobase" ,r-biobase)
6717 ("r-biocgenerics" ,r-biocgenerics)
6718 ("r-biostrings" ,r-biostrings)
6719 ("r-bsgenome" ,r-bsgenome)
6721 ("r-genomeinfodb" ,r-genomeinfodb)
6722 ("r-genomicfeatures" ,r-genomicfeatures)
6723 ("r-genomicranges" ,r-genomicranges)
6724 ("r-iranges" ,r-iranges)
6725 ("r-summarizedexperiment" ,r-summarizedexperiment)
6726 ("r-rsamtools" ,r-rsamtools)
6727 ("r-rtracklayer" ,r-rtracklayer)
6728 ("r-s4vectors" ,r-s4vectors)
6729 ("r-xvector" ,r-xvector)
6730 ("r-zlibbioc" ,r-zlibbioc)))
6731 (build-system r-build-system)
6732 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6733 (synopsis "Package for annotation of genetic variants")
6734 (description "This R package can annotate variants, compute amino acid
6735 coding changes and predict coding outcomes.")
6736 (license license:artistic2.0)))
6738 (define-public r-limma
6744 (uri (bioconductor-uri "limma" version))
6747 "0q7rqm86nwq0rg4fjggfr7xqybjrxj425vni3cva70b4c8d1h425"))))
6748 (build-system r-build-system)
6749 (home-page "http://bioinf.wehi.edu.au/limma")
6750 (synopsis "Package for linear models for microarray and RNA-seq data")
6751 (description "This package can be used for the analysis of gene expression
6752 studies, especially the use of linear models for analysing designed experiments
6753 and the assessment of differential expression. The analysis methods apply to
6754 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6755 (license license:gpl2+)))
6757 (define-public r-xvector
6763 (uri (bioconductor-uri "XVector" version))
6766 "01n09f4jdm60684lzikp02zf9gjan8bdrjx740vggr21q9fa69wn"))))
6768 `((upstream-name . "XVector")))
6769 (build-system r-build-system)
6772 (modify-phases %standard-phases
6773 (add-after 'unpack 'use-system-zlib
6775 (substitute* "DESCRIPTION"
6776 (("zlibbioc, ") ""))
6777 (substitute* "NAMESPACE"
6778 (("import\\(zlibbioc\\)") ""))
6783 `(("r-biocgenerics" ,r-biocgenerics)
6784 ("r-iranges" ,r-iranges)
6785 ("r-s4vectors" ,r-s4vectors)))
6786 (home-page "http://bioconductor.org/packages/XVector")
6787 (synopsis "Representation and manpulation of external sequences")
6789 "This package provides memory efficient S4 classes for storing sequences
6790 \"externally\" (behind an R external pointer, or on disk).")
6791 (license license:artistic2.0)))
6793 (define-public r-genomicranges
6795 (name "r-genomicranges")
6799 (uri (bioconductor-uri "GenomicRanges" version))
6802 "1y15kg1q81h8rmga83ljiwr8whkajcargfjiljr212d6if17ys1z"))))
6804 `((upstream-name . "GenomicRanges")))
6805 (build-system r-build-system)
6807 `(("r-biocgenerics" ,r-biocgenerics)
6808 ("r-genomeinfodb" ,r-genomeinfodb)
6809 ("r-iranges" ,r-iranges)
6810 ("r-s4vectors" ,r-s4vectors)
6811 ("r-xvector" ,r-xvector)))
6812 (home-page "http://bioconductor.org/packages/GenomicRanges")
6813 (synopsis "Representation and manipulation of genomic intervals")
6815 "This package provides tools to efficiently represent and manipulate
6816 genomic annotations and alignments is playing a central role when it comes to
6817 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6818 GenomicRanges package defines general purpose containers for storing and
6819 manipulating genomic intervals and variables defined along a genome.")
6820 (license license:artistic2.0)))
6822 (define-public r-biobase
6828 (uri (bioconductor-uri "Biobase" version))
6831 "0x7pf5xsdcj12dbf5qqki2c6bd5madqg2fbiq5xgisarpc9v6c1m"))))
6833 `((upstream-name . "Biobase")))
6834 (build-system r-build-system)
6836 `(("r-biocgenerics" ,r-biocgenerics)))
6837 (home-page "http://bioconductor.org/packages/Biobase")
6838 (synopsis "Base functions for Bioconductor")
6840 "This package provides functions that are needed by many other packages
6841 on Bioconductor or which replace R functions.")
6842 (license license:artistic2.0)))
6844 (define-public r-annotationdbi
6846 (name "r-annotationdbi")
6850 (uri (bioconductor-uri "AnnotationDbi" version))
6853 "1xffm98s817mfc827cnr0by6167nlrl1glxzjawzz0rkghs41g27"))))
6855 `((upstream-name . "AnnotationDbi")))
6856 (build-system r-build-system)
6858 `(("r-biobase" ,r-biobase)
6859 ("r-biocgenerics" ,r-biocgenerics)
6861 ("r-iranges" ,r-iranges)
6862 ("r-rsqlite" ,r-rsqlite)
6863 ("r-s4vectors" ,r-s4vectors)))
6864 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6865 (synopsis "Annotation database interface")
6867 "This package provides user interface and database connection code for
6868 annotation data packages using SQLite data storage.")
6869 (license license:artistic2.0)))
6871 (define-public r-biomart
6877 (uri (bioconductor-uri "biomaRt" version))
6880 "0knkxh23vl9pa0by03xr6dy9aiah714cmf54jl828k51l9wv5l2j"))))
6882 `((upstream-name . "biomaRt")))
6883 (build-system r-build-system)
6885 `(("r-annotationdbi" ,r-annotationdbi)
6886 ("r-rcurl" ,r-rcurl)
6888 (home-page "http://bioconductor.org/packages/biomaRt")
6889 (synopsis "Interface to BioMart databases")
6891 "biomaRt provides an interface to a growing collection of databases
6892 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6893 package enables retrieval of large amounts of data in a uniform way without
6894 the need to know the underlying database schemas or write complex SQL queries.
6895 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6896 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6897 users direct access to a diverse set of data and enable a wide range of
6898 powerful online queries from gene annotation to database mining.")
6899 (license license:artistic2.0)))
6901 (define-public r-biocparallel
6903 (name "r-biocparallel")
6907 (uri (bioconductor-uri "BiocParallel" version))
6910 "01ph0kq70b5gkd7n6a4myjlvwzgc0hi4xfwz8h17h06n9p5sdwa9"))))
6912 `((upstream-name . "BiocParallel")))
6913 (build-system r-build-system)
6915 `(("r-futile-logger" ,r-futile-logger)
6916 ("r-snow" ,r-snow)))
6917 (home-page "http://bioconductor.org/packages/BiocParallel")
6918 (synopsis "Bioconductor facilities for parallel evaluation")
6920 "This package provides modified versions and novel implementation of
6921 functions for parallel evaluation, tailored to use with Bioconductor
6923 (license (list license:gpl2+ license:gpl3+))))
6925 (define-public r-biostrings
6927 (name "r-biostrings")
6931 (uri (bioconductor-uri "Biostrings" version))
6934 "0ixgx12cx2z4n2khxq83crz9gc21qckj2v78y2p31567kfsw7clg"))))
6936 `((upstream-name . "Biostrings")))
6937 (build-system r-build-system)
6939 `(("r-biocgenerics" ,r-biocgenerics)
6940 ("r-iranges" ,r-iranges)
6941 ("r-s4vectors" ,r-s4vectors)
6942 ("r-xvector" ,r-xvector)))
6943 (home-page "http://bioconductor.org/packages/Biostrings")
6944 (synopsis "String objects and algorithms for biological sequences")
6946 "This package provides memory efficient string containers, string
6947 matching algorithms, and other utilities, for fast manipulation of large
6948 biological sequences or sets of sequences.")
6949 (license license:artistic2.0)))
6951 (define-public r-rsamtools
6953 (name "r-rsamtools")
6957 (uri (bioconductor-uri "Rsamtools" version))
6960 "1zx6vhdz3lksbfy98jj3qzl7cxgspigm2pbsd5835b12r6mc5w6d"))))
6962 `((upstream-name . "Rsamtools")))
6963 (build-system r-build-system)
6966 (modify-phases %standard-phases
6967 (add-after 'unpack 'use-system-zlib
6969 (substitute* "DESCRIPTION"
6970 (("zlibbioc, ") ""))
6971 (substitute* "NAMESPACE"
6972 (("import\\(zlibbioc\\)") ""))
6977 `(("r-biocgenerics" ,r-biocgenerics)
6978 ("r-biocparallel" ,r-biocparallel)
6979 ("r-biostrings" ,r-biostrings)
6980 ("r-bitops" ,r-bitops)
6981 ("r-genomeinfodb" ,r-genomeinfodb)
6982 ("r-genomicranges" ,r-genomicranges)
6983 ("r-iranges" ,r-iranges)
6984 ("r-s4vectors" ,r-s4vectors)
6985 ("r-xvector" ,r-xvector)))
6986 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6987 (synopsis "Interface to samtools, bcftools, and tabix")
6989 "This package provides an interface to the 'samtools', 'bcftools', and
6990 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6991 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6993 (license license:expat)))
6995 (define-public r-delayedarray
6997 (name "r-delayedarray")
7001 (uri (bioconductor-uri "DelayedArray" version))
7004 "0pcsk0f2dg2ldzprs1cccqrk53jrysmm6ccgjj5wh6z3x17g7g2r"))))
7006 `((upstream-name . "DelayedArray")))
7007 (build-system r-build-system)
7009 `(("r-biocgenerics" ,r-biocgenerics)
7010 ("r-s4vectors" ,r-s4vectors)
7011 ("r-iranges" ,r-iranges)
7012 ("r-matrixstats" ,r-matrixstats)))
7013 (home-page "http://bioconductor.org/packages/DelayedArray")
7014 (synopsis "Delayed operations on array-like objects")
7016 "Wrapping an array-like object (typically an on-disk object) in a
7017 @code{DelayedArray} object allows one to perform common array operations on it
7018 without loading the object in memory. In order to reduce memory usage and
7019 optimize performance, operations on the object are either delayed or executed
7020 using a block processing mechanism. Note that this also works on in-memory
7021 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7022 @code{Matrix} objects, and ordinary arrays and data frames.")
7023 (license license:artistic2.0)))
7025 (define-public r-summarizedexperiment
7027 (name "r-summarizedexperiment")
7031 (uri (bioconductor-uri "SummarizedExperiment" version))
7034 "1szjbzzz4pyip891nji71caalxh0rhqiv7rpv6q54swlrqpfkqkw"))))
7036 `((upstream-name . "SummarizedExperiment")))
7037 (build-system r-build-system)
7039 `(("r-biobase" ,r-biobase)
7040 ("r-biocgenerics" ,r-biocgenerics)
7041 ("r-delayedarray" ,r-delayedarray)
7042 ("r-genomeinfodb" ,r-genomeinfodb)
7043 ("r-genomicranges" ,r-genomicranges)
7044 ("r-iranges" ,r-iranges)
7045 ("r-matrix" ,r-matrix)
7046 ("r-s4vectors" ,r-s4vectors)))
7047 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
7048 (synopsis "Container for representing genomic ranges by sample")
7050 "The SummarizedExperiment container contains one or more assays, each
7051 represented by a matrix-like object of numeric or other mode. The rows
7052 typically represent genomic ranges of interest and the columns represent
7054 (license license:artistic2.0)))
7056 (define-public r-genomicalignments
7058 (name "r-genomicalignments")
7062 (uri (bioconductor-uri "GenomicAlignments" version))
7065 "1aagyrdk5309a7awg42lg0bpirp91i6i2ddvpmrs38pzriwahnjy"))))
7067 `((upstream-name . "GenomicAlignments")))
7068 (build-system r-build-system)
7070 `(("r-biocgenerics" ,r-biocgenerics)
7071 ("r-biocparallel" ,r-biocparallel)
7072 ("r-biostrings" ,r-biostrings)
7073 ("r-genomeinfodb" ,r-genomeinfodb)
7074 ("r-genomicranges" ,r-genomicranges)
7075 ("r-iranges" ,r-iranges)
7076 ("r-rsamtools" ,r-rsamtools)
7077 ("r-s4vectors" ,r-s4vectors)
7078 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7079 (home-page "http://bioconductor.org/packages/GenomicAlignments")
7080 (synopsis "Representation and manipulation of short genomic alignments")
7082 "This package provides efficient containers for storing and manipulating
7083 short genomic alignments (typically obtained by aligning short reads to a
7084 reference genome). This includes read counting, computing the coverage,
7085 junction detection, and working with the nucleotide content of the
7087 (license license:artistic2.0)))
7089 (define-public r-rtracklayer
7091 (name "r-rtracklayer")
7095 (uri (bioconductor-uri "rtracklayer" version))
7098 "0dv7p3wzmx57inznf6fb06417zcm48g7fpazyahxny7bqgzwq0ig"))))
7099 (build-system r-build-system)
7102 (modify-phases %standard-phases
7103 (add-after 'unpack 'use-system-zlib
7105 (substitute* "DESCRIPTION"
7106 (("zlibbioc, ") ""))
7107 (substitute* "NAMESPACE"
7108 (("import\\(zlibbioc\\)") ""))
7113 `(("r-biocgenerics" ,r-biocgenerics)
7114 ("r-biostrings" ,r-biostrings)
7115 ("r-genomeinfodb" ,r-genomeinfodb)
7116 ("r-genomicalignments" ,r-genomicalignments)
7117 ("r-genomicranges" ,r-genomicranges)
7118 ("r-iranges" ,r-iranges)
7119 ("r-rcurl" ,r-rcurl)
7120 ("r-rsamtools" ,r-rsamtools)
7121 ("r-s4vectors" ,r-s4vectors)
7123 ("r-xvector" ,r-xvector)))
7124 (home-page "http://bioconductor.org/packages/rtracklayer")
7125 (synopsis "R interface to genome browsers and their annotation tracks")
7127 "rtracklayer is an extensible framework for interacting with multiple
7128 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7129 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7130 built-in). The user may export/import tracks to/from the supported browsers,
7131 as well as query and modify the browser state, such as the current viewport.")
7132 (license license:artistic2.0)))
7134 (define-public r-genomicfeatures
7136 (name "r-genomicfeatures")
7140 (uri (bioconductor-uri "GenomicFeatures" version))
7143 "1pjxlr34ygv8pvfwpyq268wpgqzphiwpij85fyhjqdwdp0a253ik"))))
7145 `((upstream-name . "GenomicFeatures")))
7146 (build-system r-build-system)
7148 `(("r-annotationdbi" ,r-annotationdbi)
7149 ("r-biobase" ,r-biobase)
7150 ("r-biocgenerics" ,r-biocgenerics)
7151 ("r-biomart" ,r-biomart)
7152 ("r-biostrings" ,r-biostrings)
7154 ("r-genomeinfodb" ,r-genomeinfodb)
7155 ("r-genomicranges" ,r-genomicranges)
7156 ("r-iranges" ,r-iranges)
7157 ("r-rcurl" ,r-rcurl)
7158 ("r-rsqlite" ,r-rsqlite)
7159 ("r-rtracklayer" ,r-rtracklayer)
7160 ("r-s4vectors" ,r-s4vectors)
7161 ("r-xvector" ,r-xvector)))
7162 (home-page "http://bioconductor.org/packages/GenomicFeatures")
7163 (synopsis "Tools for working with transcript centric annotations")
7165 "This package provides a set of tools and methods for making and
7166 manipulating transcript centric annotations. With these tools the user can
7167 easily download the genomic locations of the transcripts, exons and cds of a
7168 given organism, from either the UCSC Genome Browser or a BioMart
7169 database (more sources will be supported in the future). This information is
7170 then stored in a local database that keeps track of the relationship between
7171 transcripts, exons, cds and genes. Flexible methods are provided for
7172 extracting the desired features in a convenient format.")
7173 (license license:artistic2.0)))
7175 (define-public r-go-db
7181 (uri (string-append "http://www.bioconductor.org/packages/"
7182 "release/data/annotation/src/contrib/GO.db_"
7186 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7188 `((upstream-name . "GO.db")))
7189 (build-system r-build-system)
7191 `(("r-annotationdbi" ,r-annotationdbi)))
7192 (home-page "http://bioconductor.org/packages/GO.db")
7193 (synopsis "Annotation maps describing the entire Gene Ontology")
7195 "The purpose of this GO.db annotation package is to provide detailed
7196 information about the latest version of the Gene Ontologies.")
7197 (license license:artistic2.0)))
7199 (define-public r-graph
7205 (uri (bioconductor-uri "graph" version))
7208 "0hx9wslnrci7c5i1gd1zlpjmgrkdnx9gabfgmzzwfnykk1mdvvna"))))
7209 (build-system r-build-system)
7211 `(("r-biocgenerics" ,r-biocgenerics)))
7212 (home-page "http://bioconductor.org/packages/graph")
7213 (synopsis "Handle graph data structures in R")
7215 "This package implements some simple graph handling capabilities for R.")
7216 (license license:artistic2.0)))
7218 (define-public r-topgo
7224 (uri (bioconductor-uri "topGO" version))
7227 "04kvxz9qsxfz0np7wlrzp4r95nykz94x7mqpyyk76f90g6m66vcc"))))
7229 `((upstream-name . "topGO")))
7230 (build-system r-build-system)
7232 `(("r-annotationdbi" ,r-annotationdbi)
7234 ("r-biobase" ,r-biobase)
7235 ("r-biocgenerics" ,r-biocgenerics)
7236 ("r-go-db" ,r-go-db)
7237 ("r-graph" ,r-graph)
7238 ("r-lattice" ,r-lattice)
7239 ("r-matrixstats" ,r-matrixstats)
7240 ("r-sparsem" ,r-sparsem)))
7241 (home-page "http://bioconductor.org/packages/topGO")
7242 (synopsis "Enrichment analysis for gene ontology")
7244 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7245 terms while accounting for the topology of the GO graph. Different test
7246 statistics and different methods for eliminating local similarities and
7247 dependencies between GO terms can be implemented and applied.")
7248 ;; Any version of the LGPL applies.
7249 (license license:lgpl2.1+)))
7251 (define-public r-bsgenome
7257 (uri (bioconductor-uri "BSgenome" version))
7260 "18dlknwk3xvi52hamxf9pl5bjc5806mpw98xwvx5xajn8mrxiy5h"))))
7262 `((upstream-name . "BSgenome")))
7263 (build-system r-build-system)
7265 `(("r-biocgenerics" ,r-biocgenerics)
7266 ("r-biostrings" ,r-biostrings)
7267 ("r-genomeinfodb" ,r-genomeinfodb)
7268 ("r-genomicranges" ,r-genomicranges)
7269 ("r-iranges" ,r-iranges)
7270 ("r-rsamtools" ,r-rsamtools)
7271 ("r-rtracklayer" ,r-rtracklayer)
7272 ("r-s4vectors" ,r-s4vectors)
7273 ("r-xvector" ,r-xvector)))
7274 (home-page "http://bioconductor.org/packages/BSgenome")
7275 (synopsis "Infrastructure for Biostrings-based genome data packages")
7277 "This package provides infrastructure shared by all Biostrings-based
7278 genome data packages and support for efficient SNP representation.")
7279 (license license:artistic2.0)))
7281 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7283 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7287 ;; We cannot use bioconductor-uri here because this tarball is
7288 ;; located under "data/annotation/" instead of "bioc/".
7289 (uri (string-append "http://www.bioconductor.org/packages/"
7290 "release/data/annotation/src/contrib/"
7291 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7295 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7297 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7298 (build-system r-build-system)
7299 ;; As this package provides little more than a very large data file it
7300 ;; doesn't make sense to build substitutes.
7301 (arguments `(#:substitutable? #f))
7303 `(("r-bsgenome" ,r-bsgenome)))
7305 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7306 (synopsis "Full genome sequences for Homo sapiens")
7308 "This package provides full genome sequences for Homo sapiens from
7309 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7310 (license license:artistic2.0)))
7312 (define-public r-impute
7318 (uri (bioconductor-uri "impute" version))
7321 "0va45vfixy3np549md87h3b3rbavm54gfnmnjhpr9hf02lll6zxs"))))
7323 `(("gfortran" ,gfortran)))
7324 (build-system r-build-system)
7325 (home-page "http://bioconductor.org/packages/impute")
7326 (synopsis "Imputation for microarray data")
7328 "This package provides a function to impute missing gene expression
7329 microarray data, using nearest neighbor averaging.")
7330 (license license:gpl2+)))
7332 (define-public r-seqpattern
7334 (name "r-seqpattern")
7338 (uri (bioconductor-uri "seqPattern" version))
7341 "0yw5251sirv3283xgmfmfbf900xp8dwvqfk88mr945s3by5hx99v"))))
7343 `((upstream-name . "seqPattern")))
7344 (build-system r-build-system)
7346 `(("r-biostrings" ,r-biostrings)
7347 ("r-genomicranges" ,r-genomicranges)
7348 ("r-iranges" ,r-iranges)
7349 ("r-kernsmooth" ,r-kernsmooth)
7350 ("r-plotrix" ,r-plotrix)))
7351 (home-page "http://bioconductor.org/packages/seqPattern")
7352 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7354 "This package provides tools to visualize oligonucleotide patterns and
7355 sequence motif occurrences across a large set of sequences centred at a common
7356 reference point and sorted by a user defined feature.")
7357 (license license:gpl3+)))
7359 (define-public r-genomation
7361 (name "r-genomation")
7365 (uri (bioconductor-uri "genomation" version))
7368 "0r71nf8p3aq3yffqxg4yir1zmm7rar5a57nmy1kpqpn8kaf2svjl"))))
7369 (build-system r-build-system)
7371 `(("r-biostrings" ,r-biostrings)
7372 ("r-bsgenome" ,r-bsgenome)
7373 ("r-data-table" ,r-data-table)
7374 ("r-genomeinfodb" ,r-genomeinfodb)
7375 ("r-genomicalignments" ,r-genomicalignments)
7376 ("r-genomicranges" ,r-genomicranges)
7377 ("r-ggplot2" ,r-ggplot2)
7378 ("r-gridbase" ,r-gridbase)
7379 ("r-impute" ,r-impute)
7380 ("r-iranges" ,r-iranges)
7381 ("r-matrixstats" ,r-matrixstats)
7382 ("r-plotrix" ,r-plotrix)
7385 ("r-readr" ,r-readr)
7386 ("r-reshape2" ,r-reshape2)
7387 ("r-rhtslib" ,r-rhtslib)
7388 ("r-rsamtools" ,r-rsamtools)
7389 ("r-rtracklayer" ,r-rtracklayer)
7390 ("r-runit" ,r-runit)
7391 ("r-s4vectors" ,r-s4vectors)
7392 ("r-seqpattern" ,r-seqpattern)))
7395 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7396 (synopsis "Summary, annotation and visualization of genomic data")
7398 "This package provides a package for summary and annotation of genomic
7399 intervals. Users can visualize and quantify genomic intervals over
7400 pre-defined functional regions, such as promoters, exons, introns, etc. The
7401 genomic intervals represent regions with a defined chromosome position, which
7402 may be associated with a score, such as aligned reads from HT-seq experiments,
7403 TF binding sites, methylation scores, etc. The package can use any tabular
7404 genomic feature data as long as it has minimal information on the locations of
7405 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7406 (license license:artistic2.0)))
7408 (define-public r-genomationdata
7410 (name "r-genomationdata")
7414 ;; We cannot use bioconductor-uri here because this tarball is
7415 ;; located under "data/annotation/" instead of "bioc/".
7416 (uri (string-append "https://bioconductor.org/packages/"
7417 "release/data/experiment/src/contrib/"
7418 "genomationData_" version ".tar.gz"))
7421 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7422 (build-system r-build-system)
7423 ;; As this package provides little more than large data files, it doesn't
7424 ;; make sense to build substitutes.
7425 (arguments `(#:substitutable? #f))
7427 `(("r-knitr" ,r-knitr)))
7428 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7429 (synopsis "Experimental data for use with the genomation package")
7431 "This package contains experimental genetic data for use with the
7432 genomation package. Included are Chip Seq, Methylation and Cage data,
7433 downloaded from Encode.")
7434 (license license:gpl3+)))
7436 (define-public r-org-hs-eg-db
7438 (name "r-org-hs-eg-db")
7442 ;; We cannot use bioconductor-uri here because this tarball is
7443 ;; located under "data/annotation/" instead of "bioc/".
7444 (uri (string-append "http://www.bioconductor.org/packages/"
7445 "release/data/annotation/src/contrib/"
7446 "org.Hs.eg.db_" version ".tar.gz"))
7449 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7451 `((upstream-name . "org.Hs.eg.db")))
7452 (build-system r-build-system)
7454 `(("r-annotationdbi" ,r-annotationdbi)))
7455 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7456 (synopsis "Genome wide annotation for Human")
7458 "This package provides mappings from Entrez gene identifiers to various
7459 annotations for the human genome.")
7460 (license license:artistic2.0)))
7462 (define-public r-org-ce-eg-db
7464 (name "r-org-ce-eg-db")
7468 ;; We cannot use bioconductor-uri here because this tarball is
7469 ;; located under "data/annotation/" instead of "bioc/".
7470 (uri (string-append "http://www.bioconductor.org/packages/"
7471 "release/data/annotation/src/contrib/"
7472 "org.Ce.eg.db_" version ".tar.gz"))
7475 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7477 `((upstream-name . "org.Ce.eg.db")))
7478 (build-system r-build-system)
7480 `(("r-annotationdbi" ,r-annotationdbi)))
7481 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7482 (synopsis "Genome wide annotation for Worm")
7484 "This package provides mappings from Entrez gene identifiers to various
7485 annotations for the genome of the model worm Caenorhabditis elegans.")
7486 (license license:artistic2.0)))
7488 (define-public r-org-dm-eg-db
7490 (name "r-org-dm-eg-db")
7494 ;; We cannot use bioconductor-uri here because this tarball is
7495 ;; located under "data/annotation/" instead of "bioc/".
7496 (uri (string-append "http://www.bioconductor.org/packages/"
7497 "release/data/annotation/src/contrib/"
7498 "org.Dm.eg.db_" version ".tar.gz"))
7501 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7503 `((upstream-name . "org.Dm.eg.db")))
7504 (build-system r-build-system)
7506 `(("r-annotationdbi" ,r-annotationdbi)))
7507 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7508 (synopsis "Genome wide annotation for Fly")
7510 "This package provides mappings from Entrez gene identifiers to various
7511 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7512 (license license:artistic2.0)))
7514 (define-public r-org-mm-eg-db
7516 (name "r-org-mm-eg-db")
7520 ;; We cannot use bioconductor-uri here because this tarball is
7521 ;; located under "data/annotation/" instead of "bioc/".
7522 (uri (string-append "http://www.bioconductor.org/packages/"
7523 "release/data/annotation/src/contrib/"
7524 "org.Mm.eg.db_" version ".tar.gz"))
7527 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7529 `((upstream-name . "org.Mm.eg.db")))
7530 (build-system r-build-system)
7532 `(("r-annotationdbi" ,r-annotationdbi)))
7533 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7534 (synopsis "Genome wide annotation for Mouse")
7536 "This package provides mappings from Entrez gene identifiers to various
7537 annotations for the genome of the model mouse Mus musculus.")
7538 (license license:artistic2.0)))
7540 (define-public r-seqlogo
7547 (uri (bioconductor-uri "seqLogo" version))
7550 "19d5zmy7m8svljwgbmrb4vxkq18slq0f3all6k2ayv42b8w44h6q"))))
7551 (properties `((upstream-name . "seqLogo")))
7552 (build-system r-build-system)
7553 (home-page "http://bioconductor.org/packages/seqLogo")
7554 (synopsis "Sequence logos for DNA sequence alignments")
7556 "seqLogo takes the position weight matrix of a DNA sequence motif and
7557 plots the corresponding sequence logo as introduced by Schneider and
7559 (license license:lgpl2.0+)))
7561 (define-public r-bsgenome-hsapiens-ucsc-hg19
7563 (name "r-bsgenome-hsapiens-ucsc-hg19")
7567 ;; We cannot use bioconductor-uri here because this tarball is
7568 ;; located under "data/annotation/" instead of "bioc/".
7569 (uri (string-append "http://www.bioconductor.org/packages/"
7570 "release/data/annotation/src/contrib/"
7571 "BSgenome.Hsapiens.UCSC.hg19_"
7575 "0479qx4bapgcp5chj10a63chk0s28x9cx1gamz3f5m3yd7jzwcf2"))))
7577 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7578 (build-system r-build-system)
7579 ;; As this package provides little more than a very large data file it
7580 ;; doesn't make sense to build substitutes.
7581 (arguments `(#:substitutable? #f))
7583 `(("r-bsgenome" ,r-bsgenome)))
7585 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7586 (synopsis "Full genome sequences for Homo sapiens")
7588 "This package provides full genome sequences for Homo sapiens as provided
7589 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7590 (license license:artistic2.0)))
7592 (define-public r-bsgenome-mmusculus-ucsc-mm9
7594 (name "r-bsgenome-mmusculus-ucsc-mm9")
7598 ;; We cannot use bioconductor-uri here because this tarball is
7599 ;; located under "data/annotation/" instead of "bioc/".
7600 (uri (string-append "http://www.bioconductor.org/packages/"
7601 "release/data/annotation/src/contrib/"
7602 "BSgenome.Mmusculus.UCSC.mm9_"
7606 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7608 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7609 (build-system r-build-system)
7610 ;; As this package provides little more than a very large data file it
7611 ;; doesn't make sense to build substitutes.
7612 (arguments `(#:substitutable? #f))
7614 `(("r-bsgenome" ,r-bsgenome)))
7616 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7617 (synopsis "Full genome sequences for Mouse")
7619 "This package provides full genome sequences for Mus musculus (Mouse) as
7620 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7621 (license license:artistic2.0)))
7623 (define-public r-bsgenome-mmusculus-ucsc-mm10
7625 (name "r-bsgenome-mmusculus-ucsc-mm10")
7629 ;; We cannot use bioconductor-uri here because this tarball is
7630 ;; located under "data/annotation/" instead of "bioc/".
7631 (uri (string-append "http://www.bioconductor.org/packages/"
7632 "release/data/annotation/src/contrib/"
7633 "BSgenome.Mmusculus.UCSC.mm10_"
7637 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7639 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7640 (build-system r-build-system)
7641 ;; As this package provides little more than a very large data file it
7642 ;; doesn't make sense to build substitutes.
7643 (arguments `(#:substitutable? #f))
7645 `(("r-bsgenome" ,r-bsgenome)))
7647 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7648 (synopsis "Full genome sequences for Mouse")
7650 "This package provides full genome sequences for Mus
7651 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7652 in Biostrings objects.")
7653 (license license:artistic2.0)))
7655 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7657 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7661 ;; We cannot use bioconductor-uri here because this tarball is
7662 ;; located under "data/annotation/" instead of "bioc/".
7663 (uri (string-append "http://www.bioconductor.org/packages/"
7664 "release/data/annotation/src/contrib/"
7665 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7669 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7671 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7672 (build-system r-build-system)
7673 ;; As this package provides little more than a very large data file it
7674 ;; doesn't make sense to build substitutes.
7675 (arguments `(#:substitutable? #f))
7677 `(("r-bsgenome" ,r-bsgenome)
7678 ("r-genomicfeatures" ,r-genomicfeatures)
7679 ("r-annotationdbi" ,r-annotationdbi)))
7681 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7682 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7684 "This package loads a TxDb object, which is an R interface to
7685 prefabricated databases contained in this package. This package provides
7686 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7687 based on the knownGene track.")
7688 (license license:artistic2.0)))
7690 (define-public r-bsgenome-celegans-ucsc-ce6
7692 (name "r-bsgenome-celegans-ucsc-ce6")
7696 ;; We cannot use bioconductor-uri here because this tarball is
7697 ;; located under "data/annotation/" instead of "bioc/".
7698 (uri (string-append "http://www.bioconductor.org/packages/"
7699 "release/data/annotation/src/contrib/"
7700 "BSgenome.Celegans.UCSC.ce6_"
7704 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7706 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
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 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7715 (synopsis "Full genome sequences for Worm")
7717 "This package provides full genome sequences for Caenorhabditis
7718 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7720 (license license:artistic2.0)))
7722 (define-public r-bsgenome-celegans-ucsc-ce10
7724 (name "r-bsgenome-celegans-ucsc-ce10")
7728 ;; We cannot use bioconductor-uri here because this tarball is
7729 ;; located under "data/annotation/" instead of "bioc/".
7730 (uri (string-append "http://www.bioconductor.org/packages/"
7731 "release/data/annotation/src/contrib/"
7732 "BSgenome.Celegans.UCSC.ce10_"
7736 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7738 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
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)))
7746 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7747 (synopsis "Full genome sequences for Worm")
7749 "This package provides full genome sequences for Caenorhabditis
7750 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7752 (license license:artistic2.0)))
7754 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7756 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7760 ;; We cannot use bioconductor-uri here because this tarball is
7761 ;; located under "data/annotation/" instead of "bioc/".
7762 (uri (string-append "http://www.bioconductor.org/packages/"
7763 "release/data/annotation/src/contrib/"
7764 "BSgenome.Dmelanogaster.UCSC.dm3_"
7768 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7770 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7771 (build-system r-build-system)
7772 ;; As this package provides little more than a very large data file it
7773 ;; doesn't make sense to build substitutes.
7774 (arguments `(#:substitutable? #f))
7776 `(("r-bsgenome" ,r-bsgenome)))
7778 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7779 (synopsis "Full genome sequences for Fly")
7781 "This package provides full genome sequences for Drosophila
7782 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7783 Biostrings objects.")
7784 (license license:artistic2.0)))
7786 (define-public r-motifrg
7793 (uri (bioconductor-uri "motifRG" version))
7796 "0lxxpqyljiyk73vyq6ss46q13g81pm24q87mkzdsqlr5zx427ch6"))))
7797 (properties `((upstream-name . "motifRG")))
7798 (build-system r-build-system)
7800 `(("r-biostrings" ,r-biostrings)
7801 ("r-bsgenome" ,r-bsgenome)
7802 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7803 ("r-iranges" ,r-iranges)
7804 ("r-seqlogo" ,r-seqlogo)
7805 ("r-xvector" ,r-xvector)))
7806 (home-page "http://bioconductor.org/packages/motifRG")
7807 (synopsis "Discover motifs in high throughput sequencing data")
7809 "This package provides tools for discriminative motif discovery in high
7810 throughput genetic sequencing data sets using regression methods.")
7811 (license license:artistic2.0)))
7813 (define-public r-qtl
7820 (uri (string-append "mirror://cran/src/contrib/qtl_"
7824 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7825 (build-system r-build-system)
7826 (home-page "http://rqtl.org/")
7827 (synopsis "R package for analyzing QTL experiments in genetics")
7828 (description "R/qtl is an extension library for the R statistics
7829 system. It is used to analyze experimental crosses for identifying
7830 genes contributing to variation in quantitative traits (so-called
7831 quantitative trait loci, QTLs).
7833 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7834 identify genotyping errors, and to perform single-QTL and two-QTL,
7835 two-dimensional genome scans.")
7836 (license license:gpl3)))
7838 (define-public r-zlibbioc
7844 (uri (bioconductor-uri "zlibbioc" version))
7847 "1kdgwwlh39mgwzj3zq71za4iv40sq625ghnyrndv5wrivrcr2igv"))))
7849 `((upstream-name . "zlibbioc")))
7850 (build-system r-build-system)
7851 (home-page "https://bioconductor.org/packages/zlibbioc")
7852 (synopsis "Provider for zlib-1.2.5 to R packages")
7853 (description "This package uses the source code of zlib-1.2.5 to create
7854 libraries for systems that do not have these available via other means.")
7855 (license license:artistic2.0)))
7857 (define-public r-r4rna
7864 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7868 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7869 (build-system r-build-system)
7871 `(("r-optparse" ,r-optparse)
7872 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7873 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7874 (synopsis "Analysis framework for RNA secondary structure")
7876 "The R4RNA package aims to be a general framework for the analysis of RNA
7877 secondary structure and comparative analysis in R.")
7878 (license license:gpl3+)))
7880 (define-public r-rhtslib
7887 (uri (bioconductor-uri "Rhtslib" version))
7890 "0jj5h81z5gyf4j3lp2l3zsm6pgbmalgrngr8qdpygc20phndpp0b"))))
7891 (properties `((upstream-name . "Rhtslib")))
7892 (build-system r-build-system)
7894 `(("r-zlibbioc" ,r-zlibbioc)))
7898 `(("autoconf" ,autoconf)))
7899 (home-page "https://github.com/nhayden/Rhtslib")
7900 (synopsis "High-throughput sequencing library as an R package")
7902 "This package provides the HTSlib C library for high-throughput
7903 nucleotide sequence analysis. The package is primarily useful to developers
7904 of other R packages who wish to make use of HTSlib.")
7905 (license license:lgpl2.0+)))
7907 (define-public r-bamsignals
7909 (name "r-bamsignals")
7914 (uri (bioconductor-uri "bamsignals" version))
7917 "0knx69zzdaak2sjim8k9mygmcjxpa705m8013ld5zwpgi8dag9mc"))))
7918 (build-system r-build-system)
7920 `(("r-biocgenerics" ,r-biocgenerics)
7921 ("r-genomicranges" ,r-genomicranges)
7922 ("r-iranges" ,r-iranges)
7924 ("r-rhtslib" ,r-rhtslib)
7925 ("r-zlibbioc" ,r-zlibbioc)))
7928 (home-page "http://bioconductor.org/packages/bamsignals")
7929 (synopsis "Extract read count signals from bam files")
7931 "This package allows to efficiently obtain count vectors from indexed bam
7932 files. It counts the number of nucleotide sequence reads in given genomic
7933 ranges and it computes reads profiles and coverage profiles. It also handles
7935 (license license:gpl2+)))
7937 (define-public r-rcas
7943 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7945 (file-name (string-append name "-" version ".tar.gz"))
7948 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7949 (build-system r-build-system)
7951 `(("r-knitr" ,r-knitr)
7952 ("r-testthat" ,r-testthat)
7953 ;; During vignette building knitr checks that "pandoc-citeproc"
7955 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7957 `(("r-data-table" ,r-data-table)
7958 ("r-biomart" ,r-biomart)
7959 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7960 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7961 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7962 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7963 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7964 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7965 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7966 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7967 ("r-topgo" ,r-topgo)
7969 ("r-plotly" ,r-plotly)
7970 ("r-plotrix" ,r-plotrix)
7971 ("r-motifrg" ,r-motifrg)
7972 ("r-genomation" ,r-genomation)
7973 ("r-genomicfeatures" ,r-genomicfeatures)
7974 ("r-rtracklayer" ,r-rtracklayer)
7975 ("r-rmarkdown" ,r-rmarkdown)))
7976 (synopsis "RNA-centric annotation system")
7978 "RCAS aims to be a standalone RNA-centric annotation system that provides
7979 intuitive reports and publication-ready graphics. This package provides the R
7980 library implementing most of the pipeline's features.")
7981 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7982 (license license:expat)))
7984 (define-public rcas-web
7991 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7992 "releases/download/v" version
7993 "/rcas-web-" version ".tar.gz"))
7996 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7997 (build-system gnu-build-system)
8000 (modify-phases %standard-phases
8001 (add-after 'install 'wrap-executable
8002 (lambda* (#:key inputs outputs #:allow-other-keys)
8003 (let* ((out (assoc-ref outputs "out"))
8004 (json (assoc-ref inputs "guile-json"))
8005 (redis (assoc-ref inputs "guile-redis"))
8006 (path (string-append
8007 json "/share/guile/site/2.2:"
8008 redis "/share/guile/site/2.2")))
8009 (wrap-program (string-append out "/bin/rcas-web")
8010 `("GUILE_LOAD_PATH" ":" = (,path))
8011 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8012 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8015 `(("r-minimal" ,r-minimal)
8017 ("guile-next" ,guile-2.2)
8018 ("guile-json" ,guile-json)
8019 ("guile-redis" ,guile2.2-redis)))
8021 `(("pkg-config" ,pkg-config)))
8022 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8023 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8024 (description "This package provides a simple web interface for the
8025 @dfn{RNA-centric annotation system} (RCAS).")
8026 (license license:agpl3+)))
8028 (define-public r-mutationalpatterns
8030 (name "r-mutationalpatterns")
8035 (uri (bioconductor-uri "MutationalPatterns" version))
8038 "1s50diwh1j6vg3mgahh6bczvq74mfdbmwjrad4d5lh723gnc5pjg"))))
8039 (build-system r-build-system)
8041 `(("r-biocgenerics" ,r-biocgenerics)
8042 ("r-biostrings" ,r-biostrings)
8043 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8044 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8045 ("r-genomicranges" ,r-genomicranges)
8046 ("r-genomeinfodb" ,r-genomeinfodb)
8047 ("r-ggplot2" ,r-ggplot2)
8048 ("r-gridextra" ,r-gridextra)
8049 ("r-iranges" ,r-iranges)
8052 ("r-pracma" ,r-pracma)
8053 ("r-reshape2" ,r-reshape2)
8054 ("r-summarizedexperiment" ,r-summarizedexperiment)
8055 ("r-variantannotation" ,r-variantannotation)))
8056 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
8057 (synopsis "Extract and visualize mutational patterns in genomic data")
8058 (description "This package provides an extensive toolset for the
8059 characterization and visualization of a wide range of mutational patterns
8060 in SNV base substitution data.")
8061 (license license:expat)))
8063 (define-public r-wgcna
8070 (uri (cran-uri "WGCNA" version))
8073 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
8074 (properties `((upstream-name . "WGCNA")))
8075 (build-system r-build-system)
8077 `(("r-annotationdbi" ,r-annotationdbi)
8078 ("r-doparallel" ,r-doparallel)
8079 ("r-dynamictreecut" ,r-dynamictreecut)
8080 ("r-fastcluster" ,r-fastcluster)
8081 ("r-foreach" ,r-foreach)
8082 ("r-go-db" ,r-go-db)
8083 ("r-hmisc" ,r-hmisc)
8084 ("r-impute" ,r-impute)
8085 ("r-matrixstats" ,r-matrixstats)
8086 ("r-preprocesscore" ,r-preprocesscore)))
8088 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8089 (synopsis "Weighted correlation network analysis")
8091 "This package provides functions necessary to perform Weighted
8092 Correlation Network Analysis on high-dimensional data. It includes functions
8093 for rudimentary data cleaning, construction and summarization of correlation
8094 networks, module identification and functions for relating both variables and
8095 modules to sample traits. It also includes a number of utility functions for
8096 data manipulation and visualization.")
8097 (license license:gpl2+)))
8099 (define-public r-chipkernels
8100 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8103 (name "r-chipkernels")
8104 (version (string-append "1.1-" revision "." (string-take commit 9)))
8109 (url "https://github.com/ManuSetty/ChIPKernels.git")
8111 (file-name (string-append name "-" version))
8114 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8115 (build-system r-build-system)
8117 `(("r-iranges" ,r-iranges)
8118 ("r-xvector" ,r-xvector)
8119 ("r-biostrings" ,r-biostrings)
8120 ("r-bsgenome" ,r-bsgenome)
8121 ("r-gtools" ,r-gtools)
8122 ("r-genomicranges" ,r-genomicranges)
8123 ("r-sfsmisc" ,r-sfsmisc)
8124 ("r-kernlab" ,r-kernlab)
8125 ("r-s4vectors" ,r-s4vectors)
8126 ("r-biocgenerics" ,r-biocgenerics)))
8127 (home-page "https://github.com/ManuSetty/ChIPKernels")
8128 (synopsis "Build string kernels for DNA Sequence analysis")
8129 (description "ChIPKernels is an R package for building different string
8130 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8131 must be built and this dictionary can be used for determining kernels for DNA
8133 (license license:gpl2+))))
8135 (define-public r-seqgl
8142 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8143 "archive/" version ".tar.gz"))
8144 (file-name (string-append name "-" version ".tar.gz"))
8147 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8148 (build-system r-build-system)
8150 `(("r-biostrings" ,r-biostrings)
8151 ("r-chipkernels" ,r-chipkernels)
8152 ("r-genomicranges" ,r-genomicranges)
8153 ("r-spams" ,r-spams)
8154 ("r-wgcna" ,r-wgcna)
8155 ("r-fastcluster" ,r-fastcluster)))
8156 (home-page "https://github.com/ManuSetty/SeqGL")
8157 (synopsis "Group lasso for Dnase/ChIP-seq data")
8158 (description "SeqGL is a group lasso based algorithm to extract
8159 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8160 This package presents a method which uses group lasso to discriminate between
8161 bound and non bound genomic regions to accurately identify transcription
8162 factors bound at the specific regions.")
8163 (license license:gpl2+)))
8165 (define-public r-gkmsvm
8172 (uri (cran-uri "gkmSVM" version))
8175 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8176 (properties `((upstream-name . "gkmSVM")))
8177 (build-system r-build-system)
8179 `(("r-biocgenerics" ,r-biocgenerics)
8180 ("r-biostrings" ,r-biostrings)
8181 ("r-genomeinfodb" ,r-genomeinfodb)
8182 ("r-genomicranges" ,r-genomicranges)
8183 ("r-iranges" ,r-iranges)
8184 ("r-kernlab" ,r-kernlab)
8187 ("r-rtracklayer" ,r-rtracklayer)
8188 ("r-s4vectors" ,r-s4vectors)
8189 ("r-seqinr" ,r-seqinr)))
8190 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8191 (synopsis "Gapped-kmer support vector machine")
8193 "This R package provides tools for training gapped-kmer SVM classifiers
8194 for DNA and protein sequences. This package supports several sequence
8195 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8196 (license license:gpl2+)))
8198 (define-public r-tximport
8204 (uri (bioconductor-uri "tximport" version))
8207 "1mklb02bj4gnbjlmb7vv6k4lr3w9fp3pzli9rddbrwd0y5n8fcpx"))))
8208 (build-system r-build-system)
8209 (home-page "http://bioconductor.org/packages/tximport")
8210 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8212 "This package provides tools to import transcript-level abundance,
8213 estimated counts and transcript lengths, and to summarize them into matrices
8214 for use with downstream gene-level analysis packages. Average transcript
8215 length, weighted by sample-specific transcript abundance estimates, is
8216 provided as a matrix which can be used as an offset for different expression
8217 of gene-level counts.")
8218 (license license:gpl2+)))
8220 (define-public r-rhdf5
8226 (uri (bioconductor-uri "rhdf5" version))
8229 "1p6f5i6l44phl772a38x9cav2sya37bkqbkjzdc4pmyfzkv1j6hy"))))
8230 (build-system r-build-system)
8233 (modify-phases %standard-phases
8234 (add-after 'unpack 'unpack-smallhdf5
8235 (lambda* (#:key outputs #:allow-other-keys)
8236 (system* "tar" "-xzvf"
8237 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8238 (substitute* "src/Makevars"
8239 (("^.*cd hdf5source &&.*$") "")
8240 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8241 (("^.*rm -rf hdf5.*$") "")
8242 (("^.*mv hdf5source/hdf5 ..*$") ""))
8243 (substitute* "src/hdf5/configure"
8247 `(("r-zlibbioc" ,r-zlibbioc)))
8251 (home-page "http://bioconductor.org/packages/rhdf5")
8252 (synopsis "HDF5 interface to R")
8254 "This R/Bioconductor package provides an interface between HDF5 and R.
8255 HDF5's main features are the ability to store and access very large and/or
8256 complex datasets and a wide variety of metadata on mass storage (disk) through
8257 a completely portable file format. The rhdf5 package is thus suited for the
8258 exchange of large and/or complex datasets between R and other software
8259 package, and for letting R applications work on datasets that are larger than
8260 the available RAM.")
8261 (license license:artistic2.0)))
8263 (define-public emboss
8269 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8270 (version-major+minor version) ".0/"
8271 "EMBOSS-" version ".tar.gz"))
8274 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8275 (build-system gnu-build-system)
8278 (list (string-append "--with-hpdf="
8279 (assoc-ref %build-inputs "libharu")))
8281 (modify-phases %standard-phases
8282 (add-after 'unpack 'fix-checks
8284 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8285 ;; and zlib, but assume that they are all found at the same
8287 (substitute* "configure.in"
8288 (("CHECK_PNGDRIVER")
8289 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8290 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8291 AM_CONDITIONAL(AMPNG, true)"))
8293 (add-after 'unpack 'disable-update-check
8295 ;; At build time there is no connection to the Internet, so
8296 ;; looking for updates will not work.
8297 (substitute* "Makefile.am"
8298 (("\\$\\(bindir\\)/embossupdate") ""))
8300 (add-before 'configure 'autogen
8301 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8307 ("libharu" ,libharu)
8310 `(("autoconf" ,autoconf)
8311 ("automake" ,automake)
8312 ("libtool" ,libtool)
8313 ("pkg-config" ,pkg-config)))
8314 (home-page "http://emboss.sourceforge.net")
8315 (synopsis "Molecular biology analysis suite")
8316 (description "EMBOSS is the \"European Molecular Biology Open Software
8317 Suite\". EMBOSS is an analysis package specially developed for the needs of
8318 the molecular biology (e.g. EMBnet) user community. The software
8319 automatically copes with data in a variety of formats and even allows
8320 transparent retrieval of sequence data from the web. It also provides a
8321 number of libraries for the development of software in the field of molecular
8322 biology. EMBOSS also integrates a range of currently available packages and
8323 tools for sequence analysis into a seamless whole.")
8324 (license license:gpl2+)))
8327 (let ((revision "1")
8328 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8331 ;; The version is 2.13.0 even though no release archives have been
8332 ;; published as yet.
8333 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8337 (url "https://github.com/arq5x/bits.git")
8339 (file-name (string-append name "-" version "-checkout"))
8342 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8343 (build-system gnu-build-system)
8345 `(#:tests? #f ;no tests included
8347 (modify-phases %standard-phases
8349 (add-after 'unpack 'remove-cuda
8351 (substitute* "Makefile"
8353 (("(bits_test_intersections) \\\\" _ match) match))
8356 (lambda* (#:key outputs #:allow-other-keys)
8358 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8363 (home-page "https://github.com/arq5x/bits")
8364 (synopsis "Implementation of binary interval search algorithm")
8365 (description "This package provides an implementation of the
8366 BITS (Binary Interval Search) algorithm, an approach to interval set
8367 intersection. It is especially suited for the comparison of diverse genomic
8368 datasets and the exploration of large datasets of genome
8369 intervals (e.g. genes, sequence alignments).")
8370 (license license:gpl2))))
8372 (define-public piranha
8373 ;; There is no release tarball for the latest version. The latest commit is
8374 ;; older than one year at the time of this writing.
8375 (let ((revision "1")
8376 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8379 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8383 (url "https://github.com/smithlabcode/piranha.git")
8387 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8388 (build-system gnu-build-system)
8390 `(#:test-target "test"
8392 (modify-phases %standard-phases
8393 (add-after 'unpack 'copy-smithlab-cpp
8394 (lambda* (#:key inputs #:allow-other-keys)
8395 (for-each (lambda (file)
8396 (install-file file "./src/smithlab_cpp/"))
8397 (find-files (assoc-ref inputs "smithlab-cpp")))
8399 (add-after 'install 'install-to-store
8400 (lambda* (#:key outputs #:allow-other-keys)
8401 (let* ((out (assoc-ref outputs "out"))
8402 (bin (string-append out "/bin")))
8403 (for-each (lambda (file)
8404 (install-file file bin))
8405 (find-files "bin" ".*")))
8408 (list (string-append "--with-bam_tools_headers="
8409 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8410 (string-append "--with-bam_tools_library="
8411 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8413 `(("bamtools" ,bamtools)
8414 ("samtools" ,samtools-0.1)
8417 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8421 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8423 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8426 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8428 `(("python" ,python-2)))
8429 (home-page "https://github.com/smithlabcode/piranha")
8430 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8432 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8433 RIP-seq experiments. It takes input in BED or BAM format and identifies
8434 regions of statistically significant read enrichment. Additional covariates
8435 may optionally be provided to further inform the peak-calling process.")
8436 (license license:gpl3+))))
8444 (uri (string-append "https://pypi.python.org/packages/source/P"
8445 "/PePr/PePr-" version ".tar.gz"))
8448 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8449 (build-system python-build-system)
8451 `(#:python ,python-2 ; python2 only
8452 #:tests? #f)) ; no tests included
8454 `(("python2-numpy" ,python2-numpy)
8455 ("python2-scipy" ,python2-scipy)
8456 ("python2-pysam" ,python2-pysam)))
8457 (home-page "https://github.com/shawnzhangyx/PePr")
8458 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8460 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8461 that is primarily designed for data with biological replicates. It uses a
8462 negative binomial distribution to model the read counts among the samples in
8463 the same group, and look for consistent differences between ChIP and control
8464 group or two ChIP groups run under different conditions.")
8465 (license license:gpl3+)))
8467 (define-public filevercmp
8468 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8471 (version (string-append "0-1." (string-take commit 7)))
8474 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8476 (file-name (string-append name "-" version ".tar.gz"))
8478 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8479 (build-system gnu-build-system)
8481 `(#:tests? #f ; There are no tests to run.
8483 (modify-phases %standard-phases
8484 (delete 'configure) ; There is no configure phase.
8486 (lambda* (#:key outputs #:allow-other-keys)
8487 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8488 (install-file "filevercmp" bin)))))))
8489 (home-page "https://github.com/ekg/filevercmp")
8490 (synopsis "This program compares version strings")
8491 (description "This program compares version strings. It intends to be a
8492 replacement for strverscmp.")
8493 (license license:gpl3+))))
8495 (define-public multiqc
8502 (uri (pypi-uri "multiqc" version))
8505 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8506 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8507 (build-system python-build-system)
8509 ;; Tests are to be introduced in the next version, see
8510 ;; https://github.com/ewels/MultiQC/issues/376
8513 `(("python-jinja2" ,python-jinja2)
8514 ("python-simplejson" ,python-simplejson)
8515 ("python-pyyaml" ,python-pyyaml)
8516 ("python-click" ,python-click)
8517 ("python-matplotlib" ,python-matplotlib)
8518 ("python-numpy" ,python-numpy)
8519 ;; MultQC checks for the presence of nose at runtime.
8520 ("python-nose" ,python-nose)))
8521 (home-page "http://multiqc.info")
8522 (synopsis "Aggregate bioinformatics analysis reports")
8524 "MultiQC is a tool to aggregate bioinformatics results across many
8525 samples into a single report. It contains modules for a large number of
8526 common bioinformatics tools.")
8527 (license license:gpl3)))
8529 (define-public r-chipseq
8536 (uri (bioconductor-uri "chipseq" version))
8539 "1hahyqiwb2ch8214xqpw0c3jpiwkmyf3dwz0xc87jx6cdnzipj3i"))))
8540 (build-system r-build-system)
8542 `(("r-biocgenerics" ,r-biocgenerics)
8543 ("r-genomicranges" ,r-genomicranges)
8544 ("r-iranges" ,r-iranges)
8545 ("r-s4vectors" ,r-s4vectors)
8546 ("r-shortread" ,r-shortread)))
8547 (home-page "http://bioconductor.org/packages/chipseq")
8548 (synopsis "Package for analyzing ChIPseq data")
8550 "This package provides tools for processing short read data from ChIPseq
8552 (license license:artistic2.0)))
8554 (define-public r-copyhelper
8556 (name "r-copyhelper")
8561 (uri (string-append "http://bioconductor.org/packages/release/"
8562 "data/experiment/src/contrib/CopyhelpeR_"
8566 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8567 (properties `((upstream-name . "CopyhelpeR")))
8568 (build-system r-build-system)
8569 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8570 (synopsis "Helper files for CopywriteR")
8572 "This package contains the helper files that are required to run the
8573 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8574 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8575 mm10. In addition, it contains a blacklist filter to remove regions that
8576 display copy number variation. Files are stored as GRanges objects from the
8577 GenomicRanges Bioconductor package.")
8578 (license license:gpl2)))
8580 (define-public r-copywriter
8582 (name "r-copywriter")
8587 (uri (bioconductor-uri "CopywriteR" version))
8590 "183nmrqmdf9syqljslvwv7mhs9ar5xizzq98imgsc80q0m25ncjf"))))
8591 (properties `((upstream-name . "CopywriteR")))
8592 (build-system r-build-system)
8594 `(("r-biocparallel" ,r-biocparallel)
8595 ("r-chipseq" ,r-chipseq)
8596 ("r-copyhelper" ,r-copyhelper)
8597 ("r-data-table" ,r-data-table)
8598 ("r-dnacopy" ,r-dnacopy)
8599 ("r-futile-logger" ,r-futile-logger)
8600 ("r-genomeinfodb" ,r-genomeinfodb)
8601 ("r-genomicalignments" ,r-genomicalignments)
8602 ("r-genomicranges" ,r-genomicranges)
8603 ("r-gtools" ,r-gtools)
8604 ("r-iranges" ,r-iranges)
8605 ("r-matrixstats" ,r-matrixstats)
8606 ("r-rsamtools" ,r-rsamtools)
8607 ("r-s4vectors" ,r-s4vectors)))
8608 (home-page "https://github.com/PeeperLab/CopywriteR")
8609 (synopsis "Copy number information from targeted sequencing")
8611 "CopywriteR extracts DNA copy number information from targeted sequencing
8612 by utilizing off-target reads. It allows for extracting uniformly distributed
8613 copy number information, can be used without reference, and can be applied to
8614 sequencing data obtained from various techniques including chromatin
8615 immunoprecipitation and target enrichment on small gene panels. Thereby,
8616 CopywriteR constitutes a widely applicable alternative to available copy
8617 number detection tools.")
8618 (license license:gpl2)))
8620 (define-public r-sva
8627 (uri (bioconductor-uri "sva" version))
8630 "04pxl61iyc845wmqca1qv8kbb8zcp0qp72zgvgki3zzmrph9a362"))))
8631 (build-system r-build-system)
8633 `(("r-genefilter" ,r-genefilter)
8634 ("r-mgcv" ,r-mgcv)))
8635 (home-page "http://bioconductor.org/packages/sva")
8636 (synopsis "Surrogate variable analysis")
8638 "This package contains functions for removing batch effects and other
8639 unwanted variation in high-throughput experiment. It also contains functions
8640 for identifying and building surrogate variables for high-dimensional data
8641 sets. Surrogate variables are covariates constructed directly from
8642 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8643 imaging data that can be used in subsequent analyses to adjust for unknown,
8644 unmodeled, or latent sources of noise.")
8645 (license license:artistic2.0)))
8647 (define-public r-seqminer
8654 (uri (cran-uri "seqminer" version))
8657 "0sfkxrc9gy5a8fadzyzfzh7l5grasm8cj6cd2nnpv85ws6mqr6qd"))))
8658 (build-system r-build-system)
8661 (home-page "http://seqminer.genomic.codes")
8662 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8664 "This package provides tools to integrate nucleotide sequencing
8665 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8666 ;; Any version of the GPL is acceptable
8667 (license (list license:gpl2+ license:gpl3+))))
8669 (define-public r-raremetals2
8671 (name "r-raremetals2")
8676 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8677 "b/b7/RareMETALS2_" version ".tar.gz"))
8680 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8681 (properties `((upstream-name . "RareMETALS2")))
8682 (build-system r-build-system)
8684 `(("r-seqminer" ,r-seqminer)
8685 ("r-mvtnorm" ,r-mvtnorm)
8687 ("r-compquadform" ,r-compquadform)
8688 ("r-getopt" ,r-getopt)))
8689 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8690 (synopsis "Analyze gene-level association tests for binary trait")
8692 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8693 It was designed to meta-analyze gene-level association tests for binary trait.
8694 While rareMETALS offers a near-complete solution for meta-analysis of
8695 gene-level tests for quantitative trait, it does not offer the optimal
8696 solution for binary trait. The package rareMETALS2 offers improved features
8697 for analyzing gene-level association tests in meta-analyses for binary
8699 (license license:gpl3)))
8701 (define-public r-maldiquant
8703 (name "r-maldiquant")
8708 (uri (cran-uri "MALDIquant" version))
8711 "0z5srzsfgsgi4bssr4chls4ry6d18y2g9143znqmraylppwrrqzr"))))
8712 (properties `((upstream-name . "MALDIquant")))
8713 (build-system r-build-system)
8714 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8715 (synopsis "Quantitative analysis of mass spectrometry data")
8717 "This package provides a complete analysis pipeline for matrix-assisted
8718 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8719 two-dimensional mass spectrometry data. In addition to commonly used plotting
8720 and processing methods it includes distinctive features, namely baseline
8721 subtraction methods such as morphological filters (TopHat) or the
8722 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8723 alignment using warping functions, handling of replicated measurements as well
8724 as allowing spectra with different resolutions.")
8725 (license license:gpl3+)))
8727 (define-public r-protgenerics
8729 (name "r-protgenerics")
8734 (uri (bioconductor-uri "ProtGenerics" version))
8737 "08idb3rvxn4fl7rd66jasyqz47cb76dbc3968r1g26jr2ci3w1pl"))))
8738 (properties `((upstream-name . "ProtGenerics")))
8739 (build-system r-build-system)
8740 (home-page "https://github.com/lgatto/ProtGenerics")
8741 (synopsis "S4 generic functions for proteomics infrastructure")
8743 "This package provides S4 generic functions needed by Bioconductor
8744 proteomics packages.")
8745 (license license:artistic2.0)))
8747 (define-public r-mzr
8754 (uri (bioconductor-uri "mzR" version))
8757 "1zir46h320n2vbrky6q3m8l221f3wdjlfsnx4ak9xca5min24xm7"))))
8758 (properties `((upstream-name . "mzR")))
8759 (build-system r-build-system)
8761 `(("netcdf" ,netcdf)))
8763 `(("r-biobase" ,r-biobase)
8764 ("r-biocgenerics" ,r-biocgenerics)
8765 ("r-protgenerics" ,r-protgenerics)
8767 ("r-zlibbioc" ,r-zlibbioc)))
8768 (home-page "https://github.com/sneumann/mzR/")
8769 (synopsis "Parser for mass spectrometry data files")
8771 "The mzR package provides a unified API to the common file formats and
8772 parsers available for mass spectrometry data. It comes with a wrapper for the
8773 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8774 The package contains the original code written by the ISB, and a subset of the
8775 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8776 previously been used in XCMS.")
8777 (license license:artistic2.0)))
8779 (define-public r-affyio
8786 (uri (bioconductor-uri "affyio" version))
8789 "13w6al9296q916w0w6ngbsk25b21ahla1b6n40fcqhbvhyfii6sj"))))
8790 (build-system r-build-system)
8792 `(("r-zlibbioc" ,r-zlibbioc)))
8795 (home-page "https://github.com/bmbolstad/affyio")
8796 (synopsis "Tools for parsing Affymetrix data files")
8798 "This package provides routines for parsing Affymetrix data files based
8799 upon file format information. The primary focus is on accessing the CEL and
8801 (license license:lgpl2.0+)))
8803 (define-public r-affy
8810 (uri (bioconductor-uri "affy" version))
8813 "0azwg2qxzgflr1rjvbdln5i5rbcr9gs36kqlacd9cwl1szb9ad3m"))))
8814 (build-system r-build-system)
8816 `(("r-affyio" ,r-affyio)
8817 ("r-biobase" ,r-biobase)
8818 ("r-biocgenerics" ,r-biocgenerics)
8819 ("r-biocinstaller" ,r-biocinstaller)
8820 ("r-preprocesscore" ,r-preprocesscore)
8821 ("r-zlibbioc" ,r-zlibbioc)))
8822 (home-page "http://bioconductor.org/packages/affy")
8823 (synopsis "Methods for affymetrix oligonucleotide arrays")
8825 "This package contains functions for exploratory oligonucleotide array
8827 (license license:lgpl2.0+)))
8829 (define-public r-vsn
8836 (uri (bioconductor-uri "vsn" version))
8839 "0qhg3a4sc62pfdxcpvmk831rk138xh4zx4f1s39jhxpqqhmr7jvk"))))
8840 (build-system r-build-system)
8842 `(("r-affy" ,r-affy)
8843 ("r-biobase" ,r-biobase)
8844 ("r-ggplot2" ,r-ggplot2)
8845 ("r-hexbin" ,r-hexbin)
8846 ("r-lattice" ,r-lattice)
8847 ("r-limma" ,r-limma)))
8848 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8849 (synopsis "Variance stabilization and calibration for microarray data")
8851 "The package implements a method for normalising microarray intensities,
8852 and works for single- and multiple-color arrays. It can also be used for data
8853 from other technologies, as long as they have similar format. The method uses
8854 a robust variant of the maximum-likelihood estimator for an
8855 additive-multiplicative error model and affine calibration. The model
8856 incorporates data calibration step (a.k.a. normalization), a model for the
8857 dependence of the variance on the mean intensity and a variance stabilizing
8858 data transformation. Differences between transformed intensities are
8859 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8860 their variance is independent of the mean, and they are usually more sensitive
8861 and specific in detecting differential transcription.")
8862 (license license:artistic2.0)))
8864 (define-public r-mzid
8871 (uri (bioconductor-uri "mzID" version))
8874 "11xnild02jz24vbsfy92lb7jlqqwnrswg66a7r4rsw8d2ibrbk33"))))
8875 (properties `((upstream-name . "mzID")))
8876 (build-system r-build-system)
8878 `(("r-doparallel" ,r-doparallel)
8879 ("r-foreach" ,r-foreach)
8880 ("r-iterators" ,r-iterators)
8882 ("r-protgenerics" ,r-protgenerics)
8885 (home-page "http://bioconductor.org/packages/mzID")
8886 (synopsis "Parser for mzIdentML files")
8888 "This package provides a parser for mzIdentML files implemented using the
8889 XML package. The parser tries to be general and able to handle all types of
8890 mzIdentML files with the drawback of having less pretty output than a vendor
8892 (license license:gpl2+)))
8894 (define-public r-pcamethods
8896 (name "r-pcamethods")
8901 (uri (bioconductor-uri "pcaMethods" version))
8904 "0c4lphqyzj577ws4s172391cgv00s5nhy152zp18k2k4diyhq6n0"))))
8905 (properties `((upstream-name . "pcaMethods")))
8906 (build-system r-build-system)
8908 `(("r-biobase" ,r-biobase)
8909 ("r-biocgenerics" ,r-biocgenerics)
8911 ("r-rcpp" ,r-rcpp)))
8912 (home-page "https://github.com/hredestig/pcamethods")
8913 (synopsis "Collection of PCA methods")
8915 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8916 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8917 for missing value estimation is included for comparison. BPCA, PPCA and
8918 NipalsPCA may be used to perform PCA on incomplete data as well as for
8919 accurate missing value estimation. A set of methods for printing and plotting
8920 the results is also provided. All PCA methods make use of the same data
8921 structure (pcaRes) to provide a common interface to the PCA results.")
8922 (license license:gpl3+)))
8924 (define-public r-msnbase
8931 (uri (bioconductor-uri "MSnbase" version))
8934 "1n9bbdlp8d8bx2mqby0c4yylz1yil42scbkxqgyrfr9s5sn6dqff"))))
8935 (properties `((upstream-name . "MSnbase")))
8936 (build-system r-build-system)
8938 `(("r-affy" ,r-affy)
8939 ("r-biobase" ,r-biobase)
8940 ("r-biocgenerics" ,r-biocgenerics)
8941 ("r-biocparallel" ,r-biocparallel)
8942 ("r-digest" ,r-digest)
8943 ("r-ggplot2" ,r-ggplot2)
8944 ("r-impute" ,r-impute)
8945 ("r-iranges" ,r-iranges)
8946 ("r-maldiquant" ,r-maldiquant)
8949 ("r-pcamethods" ,r-pcamethods)
8951 ("r-preprocesscore" ,r-preprocesscore)
8952 ("r-protgenerics" ,r-protgenerics)
8954 ("r-reshape2" ,r-reshape2)
8955 ("r-s4vectors" ,r-s4vectors)
8958 (home-page "https://github.com/lgatto/MSnbase")
8959 (synopsis "Base functions and classes for MS-based proteomics")
8961 "This package provides basic plotting, data manipulation and processing
8962 of mass spectrometry based proteomics data.")
8963 (license license:artistic2.0)))
8965 (define-public r-msnid
8972 (uri (bioconductor-uri "MSnID" version))
8975 "0pjwargi5lif8q53fd43ql67p3yk9w10jychafd9qgbaw5k3f68k"))))
8976 (properties `((upstream-name . "MSnID")))
8977 (build-system r-build-system)
8979 `(("r-biobase" ,r-biobase)
8980 ("r-data-table" ,r-data-table)
8981 ("r-doparallel" ,r-doparallel)
8982 ("r-dplyr" ,r-dplyr)
8983 ("r-foreach" ,r-foreach)
8984 ("r-iterators" ,r-iterators)
8985 ("r-msnbase" ,r-msnbase)
8988 ("r-protgenerics" ,r-protgenerics)
8989 ("r-r-cache" ,r-r-cache)
8991 ("r-reshape2" ,r-reshape2)))
8992 (home-page "http://bioconductor.org/packages/MSnID")
8993 (synopsis "Utilities for LC-MSn proteomics identifications")
8995 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8996 from mzIdentML (leveraging the mzID package) or text files. After collating
8997 the search results from multiple datasets it assesses their identification
8998 quality and optimize filtering criteria to achieve the maximum number of
8999 identifications while not exceeding a specified false discovery rate. It also
9000 contains a number of utilities to explore the MS/MS results and assess missed
9001 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9002 (license license:artistic2.0)))
9004 (define-public r-seurat
9005 ;; Source releases are only made for new x.0 versions. All newer versions
9006 ;; are only released as pre-built binaries. At the time of this writing the
9007 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9008 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9012 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9016 (url "https://github.com/satijalab/seurat")
9018 (file-name (string-append name "-" version "-checkout"))
9021 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9022 ;; Delete pre-built jar.
9024 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9026 (build-system r-build-system)
9029 (modify-phases %standard-phases
9030 (add-after 'unpack 'build-jar
9031 (lambda* (#:key inputs #:allow-other-keys)
9032 (let ((classesdir "tmp-classes"))
9033 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9035 (and (zero? (apply system* `("javac" "-d" ,classesdir
9036 ,@(find-files "java" "\\.java$"))))
9037 (zero? (system* "jar"
9038 "-cf" "inst/java/ModularityOptimizer.jar"
9039 "-C" classesdir ".")))))))))
9041 `(("jdk" ,icedtea "jdk")))
9044 ("r-caret" ,r-caret)
9045 ("r-cowplot" ,r-cowplot)
9046 ("r-dplyr" ,r-dplyr)
9047 ("r-fastica" ,r-fastica)
9050 ("r-gdata" ,r-gdata)
9051 ("r-ggplot2" ,r-ggplot2)
9052 ("r-gplots" ,r-gplots)
9053 ("r-gridextra" ,r-gridextra)
9054 ("r-igraph" ,r-igraph)
9055 ("r-irlba" ,r-irlba)
9057 ("r-mixtools" ,r-mixtools)
9058 ("r-pbapply" ,r-pbapply)
9060 ("r-ranger" ,r-ranger)
9061 ("r-rcolorbrewer" ,r-rcolorbrewer)
9063 ("r-rcppeigen" ,r-rcppeigen)
9064 ("r-rcppprogress" ,r-rcppprogress)
9065 ("r-reshape2" ,r-reshape2)
9067 ("r-rtsne" ,r-rtsne)
9068 ("r-stringr" ,r-stringr)
9069 ("r-tclust" ,r-tclust)
9071 ("r-vgam" ,r-vgam)))
9072 (home-page "http://www.satijalab.org/seurat")
9073 (synopsis "Seurat is an R toolkit for single cell genomics")
9075 "This package is an R package designed for QC, analysis, and
9076 exploration of single cell RNA-seq data. It easily enables widely-used
9077 analytical techniques, including the identification of highly variable genes,
9078 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9079 algorithms; density clustering, hierarchical clustering, k-means, and the
9080 discovery of differentially expressed genes and markers.")
9081 (license license:gpl3))))
9083 (define-public r-aroma-light
9085 (name "r-aroma-light")
9090 (uri (bioconductor-uri "aroma.light" version))
9093 "10snykmmx36qaymyf5s1n1km8hsscyzpykcpf0mzsrcv8ml9rp8a"))))
9094 (properties `((upstream-name . "aroma.light")))
9095 (build-system r-build-system)
9097 `(("r-matrixstats" ,r-matrixstats)
9098 ("r-r-methodss3" ,r-r-methodss3)
9100 ("r-r-utils" ,r-r-utils)))
9101 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9102 (synopsis "Methods for normalization and visualization of microarray data")
9104 "This package provides methods for microarray analysis that take basic
9105 data types such as matrices and lists of vectors. These methods can be used
9106 standalone, be utilized in other packages, or be wrapped up in higher-level
9108 (license license:gpl2+)))
9110 (define-public r-deseq
9117 (uri (bioconductor-uri "DESeq" version))
9120 "0j3dgcxd64m9qknmlcbdzvg4xhp981xd6nbwsvnqjfn6yypslgyw"))))
9121 (properties `((upstream-name . "DESeq")))
9122 (build-system r-build-system)
9124 `(("r-biobase" ,r-biobase)
9125 ("r-biocgenerics" ,r-biocgenerics)
9126 ("r-genefilter" ,r-genefilter)
9127 ("r-geneplotter" ,r-geneplotter)
9128 ("r-lattice" ,r-lattice)
9129 ("r-locfit" ,r-locfit)
9131 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9132 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9133 (synopsis "Differential gene expression analysis")
9135 "This package provides tools for estimating variance-mean dependence in
9136 count data from high-throughput genetic sequencing assays and for testing for
9137 differential expression based on a model using the negative binomial
9139 (license license:gpl3+)))
9141 (define-public r-edaseq
9148 (uri (bioconductor-uri "EDASeq" version))
9151 "0f25dfc8hdii9fjm3bf89vy9jkxv23sa62fkcga5b4gkipwrvm9a"))))
9152 (properties `((upstream-name . "EDASeq")))
9153 (build-system r-build-system)
9155 `(("r-annotationdbi" ,r-annotationdbi)
9156 ("r-aroma-light" ,r-aroma-light)
9157 ("r-biobase" ,r-biobase)
9158 ("r-biocgenerics" ,r-biocgenerics)
9159 ("r-biomart" ,r-biomart)
9160 ("r-biostrings" ,r-biostrings)
9161 ("r-deseq" ,r-deseq)
9162 ("r-genomicfeatures" ,r-genomicfeatures)
9163 ("r-genomicranges" ,r-genomicranges)
9164 ("r-iranges" ,r-iranges)
9165 ("r-rsamtools" ,r-rsamtools)
9166 ("r-shortread" ,r-shortread)))
9167 (home-page "https://github.com/drisso/EDASeq")
9168 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9170 "This package provides support for numerical and graphical summaries of
9171 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9172 adjust for GC-content effect (or other gene-level effects) on read counts:
9173 loess robust local regression, global-scaling, and full-quantile
9174 normalization. Between-lane normalization procedures to adjust for
9175 distributional differences between lanes (e.g., sequencing depth):
9176 global-scaling and full-quantile normalization.")
9177 (license license:artistic2.0)))
9179 (define htslib-for-sambamba
9180 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9183 (name "htslib-for-sambamba")
9184 (version (string-append "1.3.1-1." (string-take commit 9)))
9189 (url "https://github.com/lomereiter/htslib.git")
9191 (file-name (string-append "htslib-" version "-checkout"))
9194 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9196 (substitute-keyword-arguments (package-arguments htslib)
9198 `(modify-phases ,phases
9199 (add-before 'configure 'bootstrap
9201 (zero? (system* "autoreconf" "-vif"))))))))
9203 `(("autoconf" ,autoconf)
9204 ("automake" ,automake)
9205 ,@(package-native-inputs htslib))))))
9207 (define-public sambamba
9214 (uri (string-append "https://github.com/lomereiter/sambamba/"
9215 "archive/v" version ".tar.gz"))
9216 (file-name (string-append name "-" version ".tar.gz"))
9219 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9220 (build-system gnu-build-system)
9222 `(#:tests? #f ; there is no test target
9225 ;; Override "--compiler" flag only.
9226 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9227 "sambamba-ldmd2-64")
9229 (modify-phases %standard-phases
9231 (add-after 'unpack 'place-biod
9232 (lambda* (#:key inputs #:allow-other-keys)
9233 (copy-recursively (assoc-ref inputs "biod") "BioD")
9235 (add-after 'unpack 'unbundle-prerequisites
9237 (substitute* "Makefile"
9238 ((" htslib-static lz4-static") ""))
9241 (lambda* (#:key outputs #:allow-other-keys)
9242 (let* ((out (assoc-ref outputs "out"))
9243 (bin (string-append out "/bin")))
9245 (install-file "build/sambamba" bin)
9251 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9255 (url "https://github.com/biod/BioD.git")
9257 (file-name (string-append "biod-"
9258 (string-take commit 9)
9262 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9265 ("htslib" ,htslib-for-sambamba)))
9266 (home-page "http://lomereiter.github.io/sambamba")
9267 (synopsis "Tools for working with SAM/BAM data")
9268 (description "Sambamba is a high performance modern robust and
9269 fast tool (and library), written in the D programming language, for
9270 working with SAM and BAM files. Current parallelised functionality is
9271 an important subset of samtools functionality, including view, index,
9272 sort, markdup, and depth.")
9273 (license license:gpl2+)))
9275 (define-public ritornello
9281 (uri (string-append "https://github.com/KlugerLab/"
9282 "Ritornello/archive/v"
9284 (file-name (string-append name "-" version ".tar.gz"))
9287 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
9288 (build-system gnu-build-system)
9290 `(#:tests? #f ; there are no tests
9292 (modify-phases %standard-phases
9293 (add-after 'unpack 'patch-samtools-references
9294 (lambda* (#:key inputs #:allow-other-keys)
9295 (substitute* '("src/SamStream.h"
9296 "src/BufferedGenomeReader.h")
9297 (("<sam.h>") "<samtools/sam.h>"))
9301 (lambda* (#:key inputs outputs #:allow-other-keys)
9302 (let* ((out (assoc-ref outputs "out"))
9303 (bin (string-append out "/bin/")))
9305 (install-file "bin/Ritornello" bin)
9308 `(("samtools" ,samtools-0.1)
9312 (home-page "https://github.com/KlugerLab/Ritornello")
9313 (synopsis "Control-free peak caller for ChIP-seq data")
9314 (description "Ritornello is a ChIP-seq peak calling algorithm based on
9315 signal processing that can accurately call binding events without the need to
9316 do a pair total DNA input or IgG control sample. It has been tested for use
9317 with narrow binding events such as transcription factor ChIP-seq.")
9318 (license license:gpl3+)))
9320 (define-public trim-galore
9322 (name "trim-galore")
9327 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
9328 "projects/trim_galore/trim_galore_v"
9332 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
9333 (build-system gnu-build-system)
9335 `(#:tests? #f ; no tests
9337 (modify-phases %standard-phases
9338 ;; The archive contains plain files.
9340 (lambda* (#:key source #:allow-other-keys)
9341 (zero? (system* "unzip" source))))
9344 (add-after 'unpack 'hardcode-tool-references
9345 (lambda* (#:key inputs #:allow-other-keys)
9346 (substitute* "trim_galore"
9347 (("\\$path_to_cutadapt = 'cutadapt'")
9348 (string-append "$path_to_cutadapt = '"
9349 (assoc-ref inputs "cutadapt")
9353 (assoc-ref inputs "gzip")
9357 (assoc-ref inputs "gzip")
9361 (lambda* (#:key outputs #:allow-other-keys)
9362 (let ((bin (string-append (assoc-ref outputs "out")
9365 (install-file "trim_galore" bin)
9370 ("cutadapt" ,cutadapt)))
9372 `(("unzip" ,unzip)))
9373 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
9374 (synopsis "Wrapper around Cutadapt and FastQC")
9375 (description "Trim Galore! is a wrapper script to automate quality and
9376 adapter trimming as well as quality control, with some added functionality to
9377 remove biased methylation positions for RRBS sequence files.")
9378 (license license:gpl3+)))
9386 (uri (string-append "http://compbio.uthscsa.edu/"
9388 "gess-" version ".src.tar.gz"))
9391 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
9392 (build-system gnu-build-system)
9394 `(#:tests? #f ; no tests
9396 (modify-phases %standard-phases
9400 (lambda* (#:key inputs outputs #:allow-other-keys)
9401 (let* ((python (assoc-ref inputs "python"))
9402 (out (assoc-ref outputs "out"))
9403 (bin (string-append out "/bin/"))
9404 (target (string-append
9405 out "/lib/python2.7/site-packages/gess/")))
9407 (copy-recursively "." target)
9408 ;; Make GESS.py executable
9409 (chmod (string-append target "GESS.py") #o555)
9410 ;; Add Python shebang to the top and make Matplotlib
9412 (substitute* (string-append target "GESS.py")
9413 (("\"\"\"Description:" line)
9414 (string-append "#!" (which "python") "
9416 matplotlib.use('Agg')
9418 ;; Make sure GESS has all modules in its path
9419 (wrap-program (string-append target "GESS.py")
9420 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
9422 (symlink (string-append target "GESS.py")
9423 (string-append bin "GESS.py"))
9426 `(("python" ,python-2)
9427 ("python2-pysam" ,python2-pysam)
9428 ("python2-scipy" ,python2-scipy)
9429 ("python2-numpy" ,python2-numpy)
9430 ("python2-networkx" ,python2-networkx)
9431 ("python2-biopython" ,python2-biopython)))
9432 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
9433 (synopsis "Detect exon-skipping events from raw RNA-seq data")
9435 "GESS is an implementation of a novel computational method to detect de
9436 novo exon-skipping events directly from raw RNA-seq data without the prior
9437 knowledge of gene annotation information. GESS stands for the graph-based
9438 exon-skipping scanner detection scheme.")
9439 (license license:bsd-3)))
9441 (define-public phylip
9448 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
9449 "download/phylip-" version ".tar.gz"))
9452 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
9453 (build-system gnu-build-system)
9455 `(#:tests? #f ; no check target
9456 #:make-flags (list "-f" "Makefile.unx" "install")
9457 #:parallel-build? #f ; not supported
9459 (modify-phases %standard-phases
9460 (add-after 'unpack 'enter-dir
9461 (lambda _ (chdir "src") #t))
9464 (lambda* (#:key inputs outputs #:allow-other-keys)
9465 (let ((target (string-append (assoc-ref outputs "out")
9468 (for-each (lambda (file)
9469 (install-file file target))
9470 (find-files "../exe" ".*")))
9472 (home-page "http://evolution.genetics.washington.edu/phylip/")
9473 (synopsis "Tools for inferring phylogenies")
9474 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
9475 programs for inferring phylogenies (evolutionary trees).")
9476 (license license:bsd-2)))
9485 (uri (string-append "https://integrativemodeling.org/"
9486 version "/download/imp-" version ".tar.gz"))
9489 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
9490 (build-system cmake-build-system)
9492 `(;; FIXME: Some tests fail because they produce warnings, others fail
9493 ;; because the PYTHONPATH does not include the modeller's directory.
9495 ;; Do not place libraries in an architecture-specific directory.
9497 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
9504 ("python" ,python-2)))
9506 `(("python2-numpy" ,python2-numpy)
9507 ("python2-scipy" ,python2-scipy)
9508 ("python2-pandas" ,python2-pandas)
9509 ("python2-scikit-learn" ,python2-scikit-learn)
9510 ("python2-networkx" ,python2-networkx)))
9511 (home-page "https://integrativemodeling.org")
9512 (synopsis "Integrative modeling platform")
9513 (description "IMP's broad goal is to contribute to a comprehensive
9514 structural characterization of biomolecules ranging in size and complexity
9515 from small peptides to large macromolecular assemblies, by integrating data
9516 from diverse biochemical and biophysical experiments. IMP provides a C++ and
9517 Python toolbox for solving complex modeling problems, and a number of
9518 applications for tackling some common problems in a user-friendly way.")
9519 ;; IMP is largely available under the GNU Lesser GPL; see the file
9520 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
9521 ;; available under the GNU GPL (see the file COPYING.GPL).
9522 (license (list license:lgpl2.1+
9525 (define-public tadbit
9531 (uri (string-append "https://github.com/3DGenomes/TADbit/"
9532 "archive/v" version ".tar.gz"))
9533 (file-name (string-append name "-" version ".tar.gz"))
9536 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
9537 (build-system python-build-system)
9539 `(;; Tests are included and must be run after installation, but
9540 ;; they are incomplete and thus cannot be run.
9544 (modify-phases %standard-phases
9545 (add-after 'unpack 'fix-problems-with-setup.py
9546 (lambda* (#:key outputs #:allow-other-keys)
9547 ;; setup.py opens these files for writing
9548 (chmod "_pytadbit/_version.py" #o664)
9549 (chmod "README.rst" #o664)
9551 ;; Don't attempt to install the bash completions to
9552 ;; the home directory.
9553 (rename-file "extras/.bash_completion"
9555 (substitute* "setup.py"
9556 (("\\(path.expanduser\\('~'\\)")
9557 (string-append "(\""
9558 (assoc-ref outputs "out")
9559 "/etc/bash_completion.d\""))
9560 (("extras/\\.bash_completion")
9564 ;; TODO: add Chimera for visualization
9567 ("python2-scipy" ,python2-scipy)
9568 ("python2-numpy" ,python2-numpy)
9569 ("python2-matplotlib" ,python2-matplotlib)
9570 ("python2-pysam" ,python2-pysam)))
9571 (home-page "http://3dgenomes.github.io/TADbit/")
9572 (synopsis "Analyze, model, and explore 3C-based data")
9574 "TADbit is a complete Python library to deal with all steps to analyze,
9575 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
9576 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
9577 correct interaction matrices, identify and compare the so-called
9578 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
9579 interaction matrices, and finally, extract structural properties from the
9580 models. TADbit is complemented by TADkit for visualizing 3D models.")
9581 (license license:gpl3+)))
9583 (define-public kentutils
9586 ;; 302.1.0 is out, but the only difference is the inclusion of
9587 ;; pre-built binaries.
9592 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
9593 "archive/v" version ".tar.gz"))
9594 (file-name (string-append name "-" version ".tar.gz"))
9597 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
9598 (modules '((guix build utils)
9603 ;; Only the contents of the specified directories are free
9604 ;; for all uses, so we remove the rest. "hg/autoSql" and
9605 ;; "hg/autoXml" are nominally free, but they depend on a
9606 ;; library that is built from the sources in "hg/lib",
9607 ;; which is nonfree.
9608 (let ((free (list "." ".."
9609 "utils" "lib" "inc" "tagStorm"
9610 "parasol" "htslib"))
9611 (directory? (lambda (file)
9612 (eq? 'directory (stat:type (stat file))))))
9613 (for-each (lambda (file)
9614 (and (directory? file)
9615 (delete-file-recursively file)))
9616 (map (cut string-append "src/" <>)
9619 (not (member file free)))))))
9620 ;; Only make the utils target, not the userApps target,
9621 ;; because that requires libraries we won't build.
9622 (substitute* "Makefile"
9623 ((" userApps") " utils"))
9624 ;; Only build libraries that are free.
9625 (substitute* "src/makefile"
9626 (("DIRS =.*") "DIRS =\n")
9627 (("cd jkOwnLib.*") "")
9630 (substitute* "src/utils/makefile"
9631 ;; These tools depend on "jkhgap.a", which is part of the
9632 ;; nonfree "src/hg/lib" directory.
9634 (("pslLiftSubrangeBlat") "")
9636 ;; Do not build UCSC tools, which may require nonfree
9638 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
9640 (build-system gnu-build-system)
9642 `( ;; There is no global test target and the test target for
9643 ;; individual tools depends on input files that are not
9647 (modify-phases %standard-phases
9648 (add-after 'unpack 'fix-paths
9650 (substitute* "Makefile"
9651 (("/bin/echo") (which "echo")))
9653 (add-after 'unpack 'prepare-samtabix
9654 (lambda* (#:key inputs #:allow-other-keys)
9655 (copy-recursively (assoc-ref inputs "samtabix")
9660 (lambda* (#:key outputs #:allow-other-keys)
9661 (let ((bin (string-append (assoc-ref outputs "out")
9663 (copy-recursively "bin" bin))
9670 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
9671 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
9674 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
9681 ("openssl" ,openssl)))
9682 (home-page "http://genome.cse.ucsc.edu/index.html")
9683 (synopsis "Assorted bioinformatics utilities")
9684 (description "This package provides the kentUtils, a selection of
9685 bioinformatics utilities used in combination with the UCSC genome
9687 ;; Only a subset of the sources are released under a non-copyleft
9688 ;; free software license. All other sources are removed in a
9689 ;; snippet. See this bug report for an explanation of how the
9690 ;; license statements apply:
9691 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
9692 (license (license:non-copyleft
9693 "http://genome.ucsc.edu/license/"
9694 "The contents of this package are free for all uses."))))
9696 (define-public f-seq
9697 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
9701 (version (string-append "1.1-" revision "." commit))
9705 (url "https://github.com/aboyle/F-seq.git")
9707 (file-name (string-append name "-" version))
9710 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
9711 (modules '((guix build utils)))
9712 ;; Remove bundled Java library archives.
9715 (for-each delete-file (find-files "lib" ".*"))
9717 (build-system ant-build-system)
9719 `(#:tests? #f ; no tests included
9721 (modify-phases %standard-phases
9723 (lambda* (#:key outputs #:allow-other-keys)
9724 (let* ((target (assoc-ref outputs "out"))
9725 (doc (string-append target "/share/doc/f-seq/")))
9728 (substitute* "bin/linux/fseq"
9729 (("java") (which "java")))
9730 (install-file "README.txt" doc)
9731 (install-file "bin/linux/fseq" (string-append target "/bin"))
9732 (install-file "build~/fseq.jar" (string-append target "/lib"))
9733 (copy-recursively "lib" (string-append target "/lib"))
9737 ("java-commons-cli" ,java-commons-cli)))
9738 (home-page "http://fureylab.web.unc.edu/software/fseq/")
9739 (synopsis "Feature density estimator for high-throughput sequence tags")
9741 "F-Seq is a software package that generates a continuous tag sequence
9742 density estimation allowing identification of biologically meaningful sites
9743 such as transcription factor binding sites (ChIP-seq) or regions of open
9744 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
9746 (license license:gpl3+))))