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 cran)
52 #:use-module (gnu packages curl)
53 #:use-module (gnu packages documentation)
54 #:use-module (gnu packages databases)
55 #:use-module (gnu packages datastructures)
56 #:use-module (gnu packages file)
57 #:use-module (gnu packages flex)
58 #:use-module (gnu packages gawk)
59 #:use-module (gnu packages gcc)
60 #:use-module (gnu packages gd)
61 #:use-module (gnu packages gtk)
62 #:use-module (gnu packages glib)
63 #:use-module (gnu packages graph)
64 #:use-module (gnu packages groff)
65 #:use-module (gnu packages guile)
66 #:use-module (gnu packages haskell)
67 #:use-module (gnu packages image)
68 #:use-module (gnu packages imagemagick)
69 #:use-module (gnu packages java)
70 #:use-module (gnu packages ldc)
71 #:use-module (gnu packages linux)
72 #:use-module (gnu packages logging)
73 #:use-module (gnu packages machine-learning)
74 #:use-module (gnu packages man)
75 #:use-module (gnu packages maths)
76 #:use-module (gnu packages mpi)
77 #:use-module (gnu packages ncurses)
78 #:use-module (gnu packages ocaml)
79 #:use-module (gnu packages pcre)
80 #:use-module (gnu packages parallel)
81 #:use-module (gnu packages pdf)
82 #:use-module (gnu packages perl)
83 #:use-module (gnu packages pkg-config)
84 #:use-module (gnu packages popt)
85 #:use-module (gnu packages protobuf)
86 #:use-module (gnu packages python)
87 #:use-module (gnu packages readline)
88 #:use-module (gnu packages ruby)
89 #:use-module (gnu packages serialization)
90 #:use-module (gnu packages shells)
91 #:use-module (gnu packages statistics)
92 #:use-module (gnu packages swig)
93 #:use-module (gnu packages tbb)
94 #:use-module (gnu packages tex)
95 #:use-module (gnu packages texinfo)
96 #:use-module (gnu packages textutils)
97 #:use-module (gnu packages time)
98 #:use-module (gnu packages tls)
99 #:use-module (gnu packages vim)
100 #:use-module (gnu packages web)
101 #:use-module (gnu packages xml)
102 #:use-module (gnu packages xorg)
103 #:use-module (srfi srfi-1)
104 #:use-module (ice-9 match))
113 (uri (cran-uri "ape" version))
116 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
117 (build-system r-build-system)
119 `(("r-lattice" ,r-lattice)
121 (home-page "http://ape-package.ird.fr/")
122 (synopsis "Analyses of phylogenetics and evolution")
124 "This package provides functions for reading, writing, plotting, and
125 manipulating phylogenetic trees, analyses of comparative data in a
126 phylogenetic framework, ancestral character analyses, analyses of
127 diversification and macroevolution, computing distances from DNA sequences,
128 and several other tools.")
129 (license license:gpl2+)))
131 (define-public aragorn
138 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
142 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
143 (build-system gnu-build-system)
145 `(#:tests? #f ; there are no tests
147 (modify-phases %standard-phases
151 (zero? (system* "gcc"
157 (string-append "aragorn" ,version ".c")))))
159 (lambda* (#:key outputs #:allow-other-keys)
160 (let* ((out (assoc-ref outputs "out"))
161 (bin (string-append out "/bin"))
162 (man (string-append out "/share/man/man1")))
164 (install-file "aragorn" bin)
166 (install-file "aragorn.1" man))
168 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
169 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
171 "Aragorn identifies transfer RNA, mitochondrial RNA and
172 transfer-messenger RNA from nucleotide sequences, based on homology to known
173 tRNA consensus sequences and RNA structure. It also outputs the secondary
174 structure of the predicted RNA.")
175 (license license:gpl2)))
183 ;; BamM is not available on pypi.
185 "https://github.com/Ecogenomics/BamM/archive/"
187 (file-name (string-append name "-" version ".tar.gz"))
190 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
191 (modules '((guix build utils)))
194 ;; Delete bundled htslib.
195 (delete-file-recursively "c/htslib-1.3.1")
197 (build-system python-build-system)
199 `(#:python ,python-2 ; BamM is Python 2 only.
200 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
201 ;; been modified from its original form.
203 (let ((htslib (assoc-ref %build-inputs "htslib")))
204 (list "--with-libhts-lib" (string-append htslib "/lib")
205 "--with-libhts-inc" (string-append htslib "/include/htslib")))
207 (modify-phases %standard-phases
208 (add-after 'unpack 'autogen
210 (with-directory-excursion "c"
211 (let ((sh (which "sh")))
212 ;; Use autogen so that 'configure' works.
213 (substitute* "autogen.sh" (("/bin/sh") sh))
214 (setenv "CONFIG_SHELL" sh)
215 (substitute* "configure" (("/bin/sh") sh))
216 (zero? (system* "./autogen.sh"))))))
218 ;; Run tests after installation so compilation only happens once.
220 (add-after 'install 'wrap-executable
221 (lambda* (#:key outputs #:allow-other-keys)
222 (let* ((out (assoc-ref outputs "out"))
223 (path (getenv "PATH")))
224 (wrap-program (string-append out "/bin/bamm")
225 `("PATH" ":" prefix (,path))))
227 (add-after 'wrap-executable 'post-install-check
228 (lambda* (#:key inputs outputs #:allow-other-keys)
230 (string-append (assoc-ref outputs "out")
235 (assoc-ref outputs "out")
237 (string-take (string-take-right
238 (assoc-ref inputs "python") 5) 3)
240 (getenv "PYTHONPATH")))
241 ;; There are 2 errors printed, but they are safe to ignore:
242 ;; 1) [E::hts_open_format] fail to open file ...
243 ;; 2) samtools view: failed to open ...
244 (zero? (system* "nosetests")))))))
246 `(("autoconf" ,autoconf)
247 ("automake" ,automake)
250 ("python-nose" ,python2-nose)
251 ("python-pysam" ,python2-pysam)))
253 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
254 ("samtools" ,samtools)
258 ("coreutils" ,coreutils)))
260 `(("python-numpy" ,python2-numpy)))
261 (home-page "http://ecogenomics.github.io/BamM/")
262 (synopsis "Metagenomics-focused BAM file manipulator")
264 "BamM is a C library, wrapped in python, to efficiently generate and
265 parse BAM files, specifically for the analysis of metagenomic data. For
266 instance, it implements several methods to assess contig-wise read coverage.")
267 (license license:lgpl3+)))
269 (define-public bamtools
276 "https://github.com/pezmaster31/bamtools/archive/v"
278 (file-name (string-append name "-" version ".tar.gz"))
281 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
282 (build-system cmake-build-system)
284 `(#:tests? #f ;no "check" target
286 (modify-phases %standard-phases
288 'configure 'set-ldflags
289 (lambda* (#:key outputs #:allow-other-keys)
293 (assoc-ref outputs "out") "/lib/bamtools")))))))
294 (inputs `(("zlib" ,zlib)))
295 (home-page "https://github.com/pezmaster31/bamtools")
296 (synopsis "C++ API and command-line toolkit for working with BAM data")
298 "BamTools provides both a C++ API and a command-line toolkit for handling
300 (license license:expat)))
302 (define-public bcftools
309 "https://github.com/samtools/bcftools/releases/download/"
310 version "/bcftools-" version ".tar.bz2"))
313 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
314 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
315 (modules '((guix build utils)))
317 ;; Delete bundled htslib.
318 '(delete-file-recursively "htslib-1.5"))))
319 (build-system gnu-build-system)
321 `(#:test-target "test"
322 #:configure-flags (list "--with-htslib=system")
326 "LIBS=-lgsl -lgslcblas"
327 (string-append "prefix=" (assoc-ref %outputs "out"))
328 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
329 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
330 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
331 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
332 (string-append "PACKAGE_VERSION=" ,version))
334 (modify-phases %standard-phases
335 (add-before 'check 'patch-tests
337 (substitute* "test/test.pl"
338 (("/bin/bash") (which "bash")))
346 (home-page "https://samtools.github.io/bcftools/")
347 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
349 "BCFtools is a set of utilities that manipulate variant calls in the
350 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
351 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
352 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
353 (license (list license:gpl3+ license:expat))))
355 (define-public bedops
361 (uri (string-append "https://github.com/bedops/bedops/archive/v"
363 (file-name (string-append name "-" version ".tar.gz"))
366 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
367 (build-system gnu-build-system)
370 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
373 'unpack 'unpack-tarballs
375 ;; FIXME: Bedops includes tarballs of minimally patched upstream
376 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
377 ;; libraries because at least one of the libraries (zlib) is
378 ;; patched to add a C++ function definition (deflateInit2cpp).
379 ;; Until the Bedops developers offer a way to link against system
380 ;; libraries we have to build the in-tree copies of these three
383 ;; See upstream discussion:
384 ;; https://github.com/bedops/bedops/issues/124
386 ;; Unpack the tarballs to benefit from shebang patching.
387 (with-directory-excursion "third-party"
388 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
389 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
390 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
391 ;; Disable unpacking of tarballs in Makefile.
392 (substitute* "system.mk/Makefile.linux"
393 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
394 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
395 (substitute* "third-party/zlib-1.2.7/Makefile.in"
396 (("^SHELL=.*$") "SHELL=bash\n")))
397 (alist-delete 'configure %standard-phases))))
398 (home-page "https://github.com/bedops/bedops")
399 (synopsis "Tools for high-performance genomic feature operations")
401 "BEDOPS is a suite of tools to address common questions raised in genomic
402 studies---mostly with regard to overlap and proximity relationships between
403 data sets. It aims to be scalable and flexible, facilitating the efficient
404 and accurate analysis and management of large-scale genomic data.
406 BEDOPS provides tools that perform highly efficient and scalable Boolean and
407 other set operations, statistical calculations, archiving, conversion and
408 other management of genomic data of arbitrary scale. Tasks can be easily
409 split by chromosome for distributing whole-genome analyses across a
410 computational cluster.")
411 (license license:gpl2+)))
413 (define-public bedtools
419 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
421 (file-name (string-append name "-" version ".tar.gz"))
424 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
425 (build-system gnu-build-system)
426 (native-inputs `(("python" ,python-2)))
427 (inputs `(("samtools" ,samtools)
430 '(#:test-target "test"
432 (modify-phases %standard-phases
435 (lambda* (#:key outputs #:allow-other-keys)
436 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
437 (for-each (lambda (file)
438 (install-file file bin))
439 (find-files "bin" ".*")))
441 (home-page "https://github.com/arq5x/bedtools2")
442 (synopsis "Tools for genome analysis and arithmetic")
444 "Collectively, the bedtools utilities are a swiss-army knife of tools for
445 a wide-range of genomics analysis tasks. The most widely-used tools enable
446 genome arithmetic: that is, set theory on the genome. For example, bedtools
447 allows one to intersect, merge, count, complement, and shuffle genomic
448 intervals from multiple files in widely-used genomic file formats such as BAM,
450 (license license:gpl2)))
452 ;; Later releases of bedtools produce files with more columns than
453 ;; what Ribotaper expects.
454 (define-public bedtools-2.18
455 (package (inherit bedtools)
460 (uri (string-append "https://github.com/arq5x/bedtools2/"
461 "archive/v" version ".tar.gz"))
462 (file-name (string-append name "-" version ".tar.gz"))
465 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
467 (define-public ribotaper
473 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
474 "files/RiboTaper/RiboTaper_Version_"
478 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
479 (build-system gnu-build-system)
481 `(("bedtools" ,bedtools-2.18)
482 ("samtools" ,samtools-0.1)
483 ("r-minimal" ,r-minimal)
484 ("r-foreach" ,r-foreach)
485 ("r-xnomial" ,r-xnomial)
487 ("r-multitaper" ,r-multitaper)
488 ("r-seqinr" ,r-seqinr)))
489 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
490 (synopsis "Define translated ORFs using ribosome profiling data")
492 "Ribotaper is a method for defining translated @dfn{open reading
493 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
494 provides the Ribotaper pipeline.")
495 (license license:gpl3+)))
497 (define-public ribodiff
504 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
505 "archive/v" version ".tar.gz"))
506 (file-name (string-append name "-" version ".tar.gz"))
509 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
510 (build-system python-build-system)
514 (modify-phases %standard-phases
515 ;; Generate an installable executable script wrapper.
516 (add-after 'unpack 'patch-setup.py
518 (substitute* "setup.py"
519 (("^(.*)packages=.*" line prefix)
520 (string-append line "\n"
521 prefix "scripts=['scripts/TE.py'],\n")))
524 `(("python-numpy" ,python2-numpy)
525 ("python-matplotlib" ,python2-matplotlib)
526 ("python-scipy" ,python2-scipy)
527 ("python-statsmodels" ,python2-statsmodels)))
529 `(("python-mock" ,python2-mock)
530 ("python-nose" ,python2-nose)))
531 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
532 (synopsis "Detect translation efficiency changes from ribosome footprints")
533 (description "RiboDiff is a statistical tool that detects the protein
534 translational efficiency change from Ribo-Seq (ribosome footprinting) and
535 RNA-Seq data. It uses a generalized linear model to detect genes showing
536 difference in translational profile taking mRNA abundance into account. It
537 facilitates us to decipher the translational regulation that behave
538 independently with transcriptional regulation.")
539 (license license:gpl3+)))
541 (define-public bioawk
547 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
549 (file-name (string-append name "-" version ".tar.gz"))
551 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
552 (build-system gnu-build-system)
558 `(#:tests? #f ; There are no tests to run.
559 ;; Bison must generate files, before other targets can build.
562 (modify-phases %standard-phases
563 (delete 'configure) ; There is no configure phase.
565 (lambda* (#:key outputs #:allow-other-keys)
566 (let* ((out (assoc-ref outputs "out"))
567 (bin (string-append out "/bin"))
568 (man (string-append out "/share/man/man1")))
570 (copy-file "awk.1" (string-append man "/bioawk.1"))
571 (install-file "bioawk" bin)))))))
572 (home-page "https://github.com/lh3/bioawk")
573 (synopsis "AWK with bioinformatics extensions")
574 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
575 support of several common biological data formats, including optionally gzip'ed
576 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
577 also adds a few built-in functions and a command line option to use TAB as the
578 input/output delimiter. When the new functionality is not used, bioawk is
579 intended to behave exactly the same as the original BWK awk.")
580 (license license:x11)))
582 (define-public python2-pybedtools
584 (name "python2-pybedtools")
589 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
593 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
594 (build-system python-build-system)
595 (arguments `(#:python ,python-2)) ; no Python 3 support
597 `(("python-matplotlib" ,python2-matplotlib)))
599 `(("bedtools" ,bedtools)
600 ("samtools" ,samtools)))
602 `(("python-cython" ,python2-cython)
603 ("python-pyyaml" ,python2-pyyaml)
604 ("python-nose" ,python2-nose)))
605 (home-page "https://pythonhosted.org/pybedtools/")
606 (synopsis "Python wrapper for BEDtools programs")
608 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
609 which are widely used for genomic interval manipulation or \"genome algebra\".
610 pybedtools extends BEDTools by offering feature-level manipulations from with
612 (license license:gpl2+)))
614 (define-public python-biom-format
616 (name "python-biom-format")
621 ;; Use GitHub as source because PyPI distribution does not contain
622 ;; test data: https://github.com/biocore/biom-format/issues/693
623 (uri (string-append "https://github.com/biocore/biom-format/archive/"
625 (file-name (string-append name "-" version ".tar.gz"))
628 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
629 (build-system python-build-system)
631 `(("python-numpy" ,python-numpy)
632 ("python-scipy" ,python-scipy)
633 ("python-future" ,python-future)
634 ("python-click" ,python-click)
635 ("python-h5py" ,python-h5py)
636 ("python-pandas" ,python-pandas)))
638 `(("python-nose" ,python-nose)))
639 (home-page "http://www.biom-format.org")
640 (synopsis "Biological Observation Matrix (BIOM) format utilities")
642 "The BIOM file format is designed to be a general-use format for
643 representing counts of observations e.g. operational taxonomic units, KEGG
644 orthology groups or lipid types, in one or more biological samples
645 e.g. microbiome samples, genomes, metagenomes.")
646 (license license:bsd-3)
647 (properties `((python2-variant . ,(delay python2-biom-format))))))
649 (define-public python2-biom-format
650 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
655 (modify-phases %standard-phases
656 ;; Do not require the unmaintained pyqi library.
657 (add-after 'unpack 'remove-pyqi
659 (substitute* "setup.py"
660 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
662 ,@(package-arguments base))))))
664 (define-public bioperl-minimal
665 (let* ((inputs `(("perl-module-build" ,perl-module-build)
666 ("perl-data-stag" ,perl-data-stag)
667 ("perl-libwww" ,perl-libwww)
668 ("perl-uri" ,perl-uri)))
670 (map (compose package-name cadr)
673 (map (compose package-transitive-target-inputs cadr) inputs))))))
675 (name "bioperl-minimal")
680 (uri (string-append "https://github.com/bioperl/bioperl-live/"
682 (string-map (lambda (c)
688 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
689 (build-system perl-build-system)
692 (modify-phases %standard-phases
694 'install 'wrap-programs
695 (lambda* (#:key outputs #:allow-other-keys)
696 ;; Make sure all executables in "bin" find the required Perl
697 ;; modules at runtime. As the PERL5LIB variable contains also
698 ;; the paths of native inputs, we pick the transitive target
699 ;; inputs from %build-inputs.
700 (let* ((out (assoc-ref outputs "out"))
701 (bin (string-append out "/bin/"))
703 (cons (string-append out "/lib/perl5/site_perl")
705 (assoc-ref %build-inputs name))
706 ',transitive-inputs))
708 (for-each (lambda (file)
710 `("PERL5LIB" ":" prefix (,path))))
711 (find-files bin "\\.pl$"))
715 `(("perl-test-most" ,perl-test-most)))
716 (home-page "http://search.cpan.org/dist/BioPerl")
717 (synopsis "Bioinformatics toolkit")
719 "BioPerl is the product of a community effort to produce Perl code which
720 is useful in biology. Examples include Sequence objects, Alignment objects
721 and database searching objects. These objects not only do what they are
722 advertised to do in the documentation, but they also interact - Alignment
723 objects are made from the Sequence objects, Sequence objects have access to
724 Annotation and SeqFeature objects and databases, Blast objects can be
725 converted to Alignment objects, and so on. This means that the objects
726 provide a coordinated and extensible framework to do computational biology.")
727 (license license:perl-license))))
729 (define-public python-biopython
731 (name "python-biopython")
735 ;; use PyPi rather than biopython.org to ease updating
736 (uri (pypi-uri "biopython" version))
739 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
740 (build-system python-build-system)
743 (modify-phases %standard-phases
744 (add-before 'check 'set-home
745 ;; Some tests require a home directory to be set.
746 (lambda _ (setenv "HOME" "/tmp") #t)))))
748 `(("python-numpy" ,python-numpy)))
749 (home-page "http://biopython.org/")
750 (synopsis "Tools for biological computation in Python")
752 "Biopython is a set of tools for biological computation including parsers
753 for bioinformatics files into Python data structures; interfaces to common
754 bioinformatics programs; a standard sequence class and tools for performing
755 common operations on them; code to perform data classification; code for
756 dealing with alignments; code making it easy to split up parallelizable tasks
757 into separate processes; and more.")
758 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
760 (define-public python2-biopython
761 (package-with-python2 python-biopython))
763 ;; An outdated version of biopython is required for seqmagick, see
764 ;; https://github.com/fhcrc/seqmagick/issues/59
765 ;; When that issue has been resolved this package should be removed.
766 (define python2-biopython-1.66
768 (inherit python2-biopython)
772 (uri (pypi-uri "biopython" version))
775 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
777 (define-public bpp-core
778 ;; The last release was in 2014 and the recommended way to install from source
779 ;; is to clone the git repository, so we do this.
780 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
781 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
784 (version (string-append "2.2.0-1." (string-take commit 7)))
788 (url "http://biopp.univ-montp2.fr/git/bpp-core")
790 (file-name (string-append name "-" version "-checkout"))
793 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
794 (build-system cmake-build-system)
796 `(#:parallel-build? #f))
798 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
799 ; compile all of the bpp packages with GCC 5.
800 (home-page "http://biopp.univ-montp2.fr")
801 (synopsis "C++ libraries for Bioinformatics")
803 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
804 analysis, phylogenetics, molecular evolution and population genetics. It is
805 Object Oriented and is designed to be both easy to use and computer efficient.
806 Bio++ intends to help programmers to write computer expensive programs, by
807 providing them a set of re-usable tools.")
808 (license license:cecill-c))))
810 (define-public bpp-phyl
811 ;; The last release was in 2014 and the recommended way to install from source
812 ;; is to clone the git repository, so we do this.
813 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
814 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
817 (version (string-append "2.2.0-1." (string-take commit 7)))
821 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
823 (file-name (string-append name "-" version "-checkout"))
826 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
827 (build-system cmake-build-system)
829 `(#:parallel-build? #f
830 ;; If out-of-source, test data is not copied into the build directory
831 ;; so the tests fail.
832 #:out-of-source? #f))
834 `(("bpp-core" ,bpp-core)
836 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
839 (home-page "http://biopp.univ-montp2.fr")
840 (synopsis "Bio++ phylogenetic Library")
842 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
843 analysis, phylogenetics, molecular evolution and population genetics. This
844 library provides phylogenetics-related modules.")
845 (license license:cecill-c))))
847 (define-public bpp-popgen
848 ;; The last release was in 2014 and the recommended way to install from source
849 ;; is to clone the git repository, so we do this.
850 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
851 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
854 (version (string-append "2.2.0-1." (string-take commit 7)))
858 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
860 (file-name (string-append name "-" version "-checkout"))
863 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
864 (build-system cmake-build-system)
866 `(#:parallel-build? #f
867 #:tests? #f)) ; There are no tests.
869 `(("bpp-core" ,bpp-core)
872 (home-page "http://biopp.univ-montp2.fr")
873 (synopsis "Bio++ population genetics library")
875 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
876 analysis, phylogenetics, molecular evolution and population genetics. This
877 library provides population genetics-related modules.")
878 (license license:cecill-c))))
880 (define-public bpp-seq
881 ;; The last release was in 2014 and the recommended way to install from source
882 ;; is to clone the git repository, so we do this.
883 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
884 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
887 (version (string-append "2.2.0-1." (string-take commit 7)))
891 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
893 (file-name (string-append name "-" version "-checkout"))
896 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
897 (build-system cmake-build-system)
899 `(#:parallel-build? #f
900 ;; If out-of-source, test data is not copied into the build directory
901 ;; so the tests fail.
902 #:out-of-source? #f))
904 `(("bpp-core" ,bpp-core)
905 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
906 (home-page "http://biopp.univ-montp2.fr")
907 (synopsis "Bio++ sequence library")
909 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
910 analysis, phylogenetics, molecular evolution and population genetics. This
911 library provides sequence-related modules.")
912 (license license:cecill-c))))
914 (define-public bppsuite
915 ;; The last release was in 2014 and the recommended way to install from source
916 ;; is to clone the git repository, so we do this.
917 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
918 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
921 (version (string-append "2.2.0-1." (string-take commit 7)))
925 (url "http://biopp.univ-montp2.fr/git/bppsuite")
927 (file-name (string-append name "-" version "-checkout"))
930 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
931 (build-system cmake-build-system)
933 `(#:parallel-build? #f
934 #:tests? #f)) ; There are no tests.
938 ("texinfo" ,texinfo)))
940 `(("bpp-core" ,bpp-core)
942 ("bpp-phyl" ,bpp-phyl)
943 ("bpp-phyl" ,bpp-popgen)
945 (home-page "http://biopp.univ-montp2.fr")
946 (synopsis "Bioinformatics tools written with the Bio++ libraries")
948 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
949 analysis, phylogenetics, molecular evolution and population genetics. This
950 package provides command line tools using the Bio++ library.")
951 (license license:cecill-c))))
953 (define-public blast+
960 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
961 version "/ncbi-blast-" version "+-src.tar.gz"))
964 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
965 (patches (search-patches "blast+-fix-makefile.patch"))
966 (modules '((guix build utils)))
969 ;; Remove bundled bzip2, zlib and pcre.
970 (delete-file-recursively "c++/src/util/compress/bzip2")
971 (delete-file-recursively "c++/src/util/compress/zlib")
972 (delete-file-recursively "c++/src/util/regexp")
973 (substitute* "c++/src/util/compress/Makefile.in"
974 (("bzip2 zlib api") "api"))
975 ;; Remove useless msbuild directory
976 (delete-file-recursively
977 "c++/src/build-system/project_tree_builder/msbuild")
979 (build-system gnu-build-system)
981 `(;; There are two(!) tests for this massive library, and both fail with
982 ;; "unparsable timing stats".
983 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
984 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
987 #:parallel-build? #f ; not supported
989 (modify-phases %standard-phases
992 ;; $HOME needs to be set at some point during the configure phase
993 (lambda _ (setenv "HOME" "/tmp") #t))
996 (lambda _ (chdir "c++") #t))
998 'enter-dir 'fix-build-system
1000 (define (which* cmd)
1001 (cond ((string=? cmd "date")
1002 ;; make call to "date" deterministic
1007 (format (current-error-port)
1008 "WARNING: Unable to find absolute path for ~s~%"
1012 ;; Rewrite hardcoded paths to various tools
1013 (substitute* (append '("src/build-system/configure.ac"
1014 "src/build-system/configure"
1015 "src/build-system/helpers/run_with_lock.c"
1016 "scripts/common/impl/if_diff.sh"
1017 "scripts/common/impl/run_with_lock.sh"
1018 "src/build-system/Makefile.configurables.real"
1019 "src/build-system/Makefile.in.top"
1020 "src/build-system/Makefile.meta.gmake=no"
1021 "src/build-system/Makefile.meta.in"
1022 "src/build-system/Makefile.meta_l"
1023 "src/build-system/Makefile.meta_p"
1024 "src/build-system/Makefile.meta_r"
1025 "src/build-system/Makefile.mk.in"
1026 "src/build-system/Makefile.requirements"
1027 "src/build-system/Makefile.rules_with_autodep.in")
1028 (find-files "scripts/common/check" "\\.sh$"))
1029 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1030 (or (which* cmd) all)))
1032 (substitute* (find-files "src/build-system" "^config.*")
1033 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1036 ;; rewrite "/var/tmp" in check script
1037 (substitute* "scripts/common/check/check_make_unix.sh"
1038 (("/var/tmp") "/tmp"))
1040 ;; do not reset PATH
1041 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1043 (("action=/bin/") "action=")
1044 (("export PATH") ":"))
1048 (lambda* (#:key inputs outputs #:allow-other-keys)
1049 (let ((out (assoc-ref outputs "out"))
1050 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1051 (include (string-append (assoc-ref outputs "include")
1052 "/include/ncbi-tools++")))
1053 ;; The 'configure' script doesn't recognize things like
1054 ;; '--enable-fast-install'.
1055 (zero? (system* "./configure.orig"
1056 (string-append "--with-build-root=" (getcwd) "/build")
1057 (string-append "--prefix=" out)
1058 (string-append "--libdir=" lib)
1059 (string-append "--includedir=" include)
1060 (string-append "--with-bz2="
1061 (assoc-ref inputs "bzip2"))
1062 (string-append "--with-z="
1063 (assoc-ref inputs "zlib"))
1064 (string-append "--with-pcre="
1065 (assoc-ref inputs "pcre"))
1066 ;; Each library is built twice by default, once
1067 ;; with "-static" in its name, and again
1070 "--with-dll"))))))))
1071 (outputs '("out" ; 21 MB
1079 ("python" ,python-wrapper)))
1082 (home-page "http://blast.ncbi.nlm.nih.gov")
1083 (synopsis "Basic local alignment search tool")
1085 "BLAST is a popular method of performing a DNA or protein sequence
1086 similarity search, using heuristics to produce results quickly. It also
1087 calculates an “expect value” that estimates how many matches would have
1088 occurred at a given score by chance, which can aid a user in judging how much
1089 confidence to have in an alignment.")
1090 ;; Most of the sources are in the public domain, with the following
1093 ;; * ./c++/include/util/bitset/
1094 ;; * ./c++/src/html/ncbi_menu*.js
1096 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1098 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1100 ;; * ./c++/src/corelib/teamcity_*
1101 (license (list license:public-domain
1107 (define-public bless
1113 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1117 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1118 (modules '((guix build utils)))
1121 ;; Remove bundled boost, pigz, zlib, and .git directory
1122 ;; FIXME: also remove bundled sources for murmurhash3 and
1123 ;; kmc once packaged.
1124 (delete-file-recursively "boost")
1125 (delete-file-recursively "pigz")
1126 (delete-file-recursively "google-sparsehash")
1127 (delete-file-recursively "zlib")
1128 (delete-file-recursively ".git")
1130 (build-system gnu-build-system)
1132 '(#:tests? #f ;no "check" target
1134 (list (string-append "ZLIB="
1135 (assoc-ref %build-inputs "zlib")
1137 (string-append "LDFLAGS="
1138 (string-join '("-lboost_filesystem"
1145 (modify-phases %standard-phases
1146 (add-after 'unpack 'do-not-build-bundled-pigz
1147 (lambda* (#:key inputs outputs #:allow-other-keys)
1148 (substitute* "Makefile"
1149 (("cd pigz/pigz-2.3.3; make") ""))
1151 (add-after 'unpack 'patch-paths-to-executables
1152 (lambda* (#:key inputs outputs #:allow-other-keys)
1153 (substitute* "parse_args.cpp"
1154 (("kmc_binary = .*")
1155 (string-append "kmc_binary = \""
1156 (assoc-ref outputs "out")
1158 (("pigz_binary = .*")
1159 (string-append "pigz_binary = \""
1160 (assoc-ref inputs "pigz")
1164 (lambda* (#:key outputs #:allow-other-keys)
1165 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1166 (for-each (lambda (file)
1167 (install-file file bin))
1168 '("bless" "kmc/bin/kmc"))
1170 (delete 'configure))))
1174 `(("openmpi" ,openmpi)
1176 ("sparsehash" ,sparsehash)
1179 (supported-systems '("x86_64-linux"))
1180 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1181 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1183 "@dfn{Bloom-filter-based error correction solution for high-throughput
1184 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1185 correction tool for genomic reads produced by @dfn{Next-generation
1186 sequencing} (NGS). BLESS produces accurate correction results with much less
1187 memory compared with previous solutions and is also able to tolerate a higher
1188 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1189 errors at the end of reads.")
1190 (license license:gpl3+)))
1192 (define-public bowtie
1198 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1200 (file-name (string-append name "-" version ".tar.gz"))
1203 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1204 (modules '((guix build utils)))
1206 '(substitute* "Makefile"
1207 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1208 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1209 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1210 (build-system gnu-build-system)
1213 ("perl-clone" ,perl-clone)
1214 ("perl-test-deep" ,perl-test-deep)
1215 ("perl-test-simple" ,perl-test-simple)
1216 ("python" ,python-2)
1223 (string-append "prefix=" (assoc-ref %outputs "out")))
1225 (modify-phases %standard-phases
1228 (lambda* (#:key outputs #:allow-other-keys)
1229 (zero? (system* "perl"
1230 "scripts/test/simple_tests.pl"
1231 "--bowtie2=./bowtie2"
1232 "--bowtie2-build=./bowtie2-build")))))))
1233 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1234 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1236 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1237 reads to long reference sequences. It is particularly good at aligning reads
1238 of about 50 up to 100s or 1,000s of characters, and particularly good at
1239 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1240 genome with an FM Index to keep its memory footprint small: for the human
1241 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1242 gapped, local, and paired-end alignment modes.")
1243 (supported-systems '("x86_64-linux"))
1244 (license license:gpl3+)))
1246 (define-public tophat
1253 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1257 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1258 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1259 (modules '((guix build utils)))
1262 ;; Remove bundled SeqAn and samtools
1263 (delete-file-recursively "src/SeqAn-1.3")
1264 (delete-file-recursively "src/samtools-0.1.18")
1266 (build-system gnu-build-system)
1268 '(#:parallel-build? #f ; not supported
1270 (modify-phases %standard-phases
1271 (add-after 'unpack 'use-system-samtools
1272 (lambda* (#:key inputs #:allow-other-keys)
1273 (substitute* "src/Makefile.in"
1274 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1275 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1276 (("SAMPROG = samtools_0\\.1\\.18") "")
1277 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1278 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1279 (substitute* '("src/common.cpp"
1281 (("samtools_0.1.18") (which "samtools")))
1282 (substitute* '("src/common.h"
1283 "src/bam2fastx.cpp")
1284 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1285 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1286 (substitute* '("src/bwt_map.h"
1288 "src/align_status.h")
1289 (("#include <bam.h>") "#include <samtools/bam.h>")
1290 (("#include <sam.h>") "#include <samtools/sam.h>"))
1295 ("samtools" ,samtools-0.1)
1296 ("ncurses" ,ncurses)
1297 ("python" ,python-2)
1301 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1302 (synopsis "Spliced read mapper for RNA-Seq data")
1304 "TopHat is a fast splice junction mapper for nucleotide sequence
1305 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1306 mammalian-sized genomes using the ultra high-throughput short read
1307 aligner Bowtie, and then analyzes the mapping results to identify
1308 splice junctions between exons.")
1309 ;; TopHat is released under the Boost Software License, Version 1.0
1310 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1311 (license license:boost1.0)))
1319 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1320 version ".tar.bz2"))
1323 "0585ikg0gv0mpyw9iq0bq9n0hr95867bbv8jbzs9pk4slkpsymig"))))
1324 (build-system gnu-build-system)
1326 '(#:tests? #f ;no "check" target
1330 (lambda* (#:key outputs #:allow-other-keys)
1331 (let ((bin (string-append
1332 (assoc-ref outputs "out") "/bin"))
1334 (assoc-ref outputs "out") "/share/doc/bwa"))
1336 (assoc-ref outputs "out") "/share/man/man1")))
1337 (install-file "bwa" bin)
1338 (install-file "README.md" doc)
1339 (install-file "bwa.1" man)))
1340 ;; no "configure" script
1341 (alist-delete 'configure %standard-phases))))
1342 (inputs `(("zlib" ,zlib)))
1343 ;; Non-portable SSE instructions are used so building fails on platforms
1344 ;; other than x86_64.
1345 (supported-systems '("x86_64-linux"))
1346 (home-page "http://bio-bwa.sourceforge.net/")
1347 (synopsis "Burrows-Wheeler sequence aligner")
1349 "BWA is a software package for mapping low-divergent sequences against a
1350 large reference genome, such as the human genome. It consists of three
1351 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1352 designed for Illumina sequence reads up to 100bp, while the rest two for
1353 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1354 features such as long-read support and split alignment, but BWA-MEM, which is
1355 the latest, is generally recommended for high-quality queries as it is faster
1356 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1357 70-100bp Illumina reads.")
1358 (license license:gpl3+)))
1360 (define-public bwa-pssm
1361 (package (inherit bwa)
1366 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1367 "archive/" version ".tar.gz"))
1368 (file-name (string-append name "-" version ".tar.gz"))
1371 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1372 (build-system gnu-build-system)
1377 (home-page "http://bwa-pssm.binf.ku.dk/")
1378 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1380 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1381 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1382 existing aligners it is fast and sensitive. Unlike most other aligners,
1383 however, it is also adaptible in the sense that one can direct the alignment
1384 based on known biases within the data set. It is coded as a modification of
1385 the original BWA alignment program and shares the genome index structure as
1386 well as many of the command line options.")
1387 (license license:gpl3+)))
1389 (define-public python2-bx-python
1391 (name "python2-bx-python")
1395 (uri (pypi-uri "bx-python" version))
1398 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1399 (modules '((guix build utils)))
1401 '(substitute* "setup.py"
1402 ;; remove dependency on outdated "distribute" module
1403 (("^from distribute_setup import use_setuptools") "")
1404 (("^use_setuptools\\(\\)") "")))))
1405 (build-system python-build-system)
1407 `(#:tests? #f ;tests fail because test data are not included
1408 #:python ,python-2))
1410 `(("python-numpy" ,python2-numpy)
1413 `(("python-nose" ,python2-nose)))
1414 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1415 (synopsis "Tools for manipulating biological data")
1417 "bx-python provides tools for manipulating biological data, particularly
1418 multiple sequence alignments.")
1419 (license license:expat)))
1421 (define-public python-pysam
1423 (name "python-pysam")
1424 (version "0.11.2.2")
1427 ;; Test data is missing on PyPi.
1429 "https://github.com/pysam-developers/pysam/archive/v"
1431 (file-name (string-append name "-" version ".tar.gz"))
1434 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1435 (modules '((guix build utils)))
1437 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1438 '(delete-file-recursively "htslib"))))
1439 (build-system python-build-system)
1441 `(#:modules ((ice-9 ftw)
1443 (guix build python-build-system)
1446 (modify-phases %standard-phases
1447 (add-before 'build 'set-flags
1448 (lambda* (#:key inputs #:allow-other-keys)
1449 (setenv "HTSLIB_MODE" "external")
1450 (setenv "HTSLIB_LIBRARY_DIR"
1451 (string-append (assoc-ref inputs "htslib") "/lib"))
1452 (setenv "HTSLIB_INCLUDE_DIR"
1453 (string-append (assoc-ref inputs "htslib") "/include"))
1454 (setenv "LDFLAGS" "-lncurses")
1455 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1458 (lambda* (#:key inputs outputs #:allow-other-keys)
1459 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1460 (setenv "PYTHONPATH"
1462 (getenv "PYTHONPATH")
1463 ":" (getcwd) "/build/"
1464 (car (scandir "build"
1465 (negate (cut string-prefix? "." <>))))))
1466 ;; Step out of source dir so python does not import from CWD.
1467 (with-directory-excursion "tests"
1468 (setenv "HOME" "/tmp")
1469 (and (zero? (system* "make" "-C" "pysam_data"))
1470 (zero? (system* "make" "-C" "cbcf_data"))
1471 ;; Running nosetests without explicitly asking for a
1472 ;; single process leads to a crash. Running with multiple
1473 ;; processes fails because the tests are not designed to
1476 ;; FIXME: tests keep timing out on some systems.
1477 ;; (zero? (system* "nosetests" "-v"
1478 ;; "--processes" "1"))
1481 `(("htslib" ,htslib))) ; Included from installed header files.
1483 `(("ncurses" ,ncurses)
1486 `(("python-cython" ,python-cython)
1487 ;; Dependencies below are are for tests only.
1488 ("samtools" ,samtools)
1489 ("bcftools" ,bcftools)
1490 ("python-nose" ,python-nose)))
1491 (home-page "https://github.com/pysam-developers/pysam")
1492 (synopsis "Python bindings to the SAMtools C API")
1494 "Pysam is a Python module for reading and manipulating files in the
1495 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1496 also includes an interface for tabix.")
1497 (license license:expat)))
1499 (define-public python2-pysam
1500 (package-with-python2 python-pysam))
1502 (define-public python-twobitreader
1504 (name "python-twobitreader")
1508 (uri (pypi-uri "twobitreader" version))
1511 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1512 (build-system python-build-system)
1514 '(;; Tests are not distributed in the PyPi release.
1515 ;; TODO Try building from the Git repo or asking the upstream maintainer
1516 ;; to distribute the tests on PyPi.
1519 `(("python-sphinx" ,python-sphinx)))
1520 (home-page "https://github.com/benjschiller/twobitreader")
1521 (synopsis "Python library for reading .2bit files")
1523 "twobitreader is a Python library for reading .2bit files as used by the
1524 UCSC genome browser.")
1525 (license license:artistic2.0)))
1527 (define-public python2-twobitreader
1528 (package-with-python2 python-twobitreader))
1530 (define-public python-plastid
1532 (name "python-plastid")
1536 (uri (pypi-uri "plastid" version))
1539 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1540 (build-system python-build-system)
1542 ;; Some test files are not included.
1545 `(("python-numpy" ,python-numpy)
1546 ("python-scipy" ,python-scipy)
1547 ("python-pandas" ,python-pandas)
1548 ("python-pysam" ,python-pysam)
1549 ("python-matplotlib" ,python-matplotlib)
1550 ("python-biopython" ,python-biopython)
1551 ("python-twobitreader" ,python-twobitreader)
1552 ("python-termcolor" ,python-termcolor)))
1554 `(("python-cython" ,python-cython)
1555 ("python-nose" ,python-nose)))
1556 (home-page "https://github.com/joshuagryphon/plastid")
1557 (synopsis "Python library for genomic analysis")
1559 "plastid is a Python library for genomic analysis – in particular,
1560 high-throughput sequencing data – with an emphasis on simplicity.")
1561 (license license:bsd-3)))
1563 (define-public python2-plastid
1564 (package-with-python2 python-plastid))
1566 (define-public cd-hit
1572 (uri (string-append "https://github.com/weizhongli/cdhit"
1573 "/releases/download/V" version
1575 "-2017-0621-source.tar.gz"))
1578 "1386dg2npx8p62wmv08mjzsd2z3waknb9j1gg3gkvblcy57hymnn"))))
1579 (build-system gnu-build-system)
1581 `(#:tests? #f ; there are no tests
1583 ;; Executables are copied directly to the PREFIX.
1584 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1586 (modify-phases %standard-phases
1587 ;; No "configure" script
1589 ;; Remove sources of non-determinism
1590 (add-after 'unpack 'be-timeless
1592 (substitute* "cdhit-utility.c++"
1593 ((" \\(built on \" __DATE__ \"\\)") ""))
1594 (substitute* "cdhit-common.c++"
1595 (("__DATE__") "\"0\"")
1596 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1598 ;; The "install" target does not create the target directory.
1599 (add-before 'install 'create-target-dir
1600 (lambda* (#:key outputs #:allow-other-keys)
1601 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1605 (home-page "http://weizhongli-lab.org/cd-hit/")
1606 (synopsis "Cluster and compare protein or nucleotide sequences")
1608 "CD-HIT is a program for clustering and comparing protein or nucleotide
1609 sequences. CD-HIT is designed to be fast and handle extremely large
1611 ;; The manual says: "It can be copied under the GNU General Public License
1612 ;; version 2 (GPLv2)."
1613 (license license:gpl2)))
1615 (define-public clipper
1622 "https://github.com/YeoLab/clipper/archive/"
1624 (file-name (string-append name "-" version ".tar.gz"))
1627 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1628 (modules '((guix build utils)))
1631 ;; remove unnecessary setup dependency
1632 (substitute* "setup.py"
1633 (("setup_requires = .*") ""))
1634 (for-each delete-file
1635 '("clipper/src/peaks.so"
1636 "clipper/src/readsToWiggle.so"))
1637 (delete-file-recursively "dist/")
1639 (build-system python-build-system)
1640 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1642 `(("htseq" ,python2-htseq)
1643 ("python-pybedtools" ,python2-pybedtools)
1644 ("python-cython" ,python2-cython)
1645 ("python-scikit-learn" ,python2-scikit-learn)
1646 ("python-matplotlib" ,python2-matplotlib)
1647 ("python-pandas" ,python2-pandas)
1648 ("python-pysam" ,python2-pysam)
1649 ("python-numpy" ,python2-numpy)
1650 ("python-scipy" ,python2-scipy)))
1652 `(("python-mock" ,python2-mock) ; for tests
1653 ("python-nose" ,python2-nose) ; for tests
1654 ("python-pytz" ,python2-pytz))) ; for tests
1655 (home-page "https://github.com/YeoLab/clipper")
1656 (synopsis "CLIP peak enrichment recognition")
1658 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1659 (license license:gpl2)))
1661 (define-public codingquarry
1663 (name "codingquarry")
1668 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1672 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1673 (build-system gnu-build-system)
1675 '(#:tests? #f ; no "check" target
1677 (modify-phases %standard-phases
1680 (lambda* (#:key outputs #:allow-other-keys)
1681 (let* ((out (assoc-ref outputs "out"))
1682 (bin (string-append out "/bin"))
1683 (doc (string-append out "/share/doc/codingquarry")))
1684 (install-file "INSTRUCTIONS.pdf" doc)
1685 (copy-recursively "QuarryFiles"
1686 (string-append out "/QuarryFiles"))
1687 (install-file "CodingQuarry" bin)
1688 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1689 (inputs `(("openmpi" ,openmpi)))
1690 (native-search-paths
1691 (list (search-path-specification
1692 (variable "QUARRY_PATH")
1693 (files '("QuarryFiles")))))
1694 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1695 (synopsis "Fungal gene predictor")
1696 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1697 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1698 (home-page "https://sourceforge.net/projects/codingquarry/")
1699 (license license:gpl3+)))
1701 (define-public couger
1708 "http://couger.oit.duke.edu/static/assets/COUGER"
1712 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1713 (build-system gnu-build-system)
1717 (modify-phases %standard-phases
1722 (lambda* (#:key outputs #:allow-other-keys)
1723 (let* ((out (assoc-ref outputs "out"))
1724 (bin (string-append out "/bin")))
1725 (copy-recursively "src" (string-append out "/src"))
1727 ;; Add "src" directory to module lookup path.
1728 (substitute* "couger"
1730 (string-append "import sys\nsys.path.append(\""
1731 out "\")\nfrom argparse")))
1732 (install-file "couger" bin))
1735 'install 'wrap-program
1736 (lambda* (#:key inputs outputs #:allow-other-keys)
1737 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1738 (let* ((out (assoc-ref outputs "out"))
1739 (path (getenv "PYTHONPATH")))
1740 (wrap-program (string-append out "/bin/couger")
1741 `("PYTHONPATH" ":" prefix (,path))))
1744 `(("python" ,python-2)
1745 ("python2-pillow" ,python2-pillow)
1746 ("python2-numpy" ,python2-numpy)
1747 ("python2-scipy" ,python2-scipy)
1748 ("python2-matplotlib" ,python2-matplotlib)))
1750 `(("r-minimal" ,r-minimal)
1752 ("randomjungle" ,randomjungle)))
1754 `(("unzip" ,unzip)))
1755 (home-page "http://couger.oit.duke.edu")
1756 (synopsis "Identify co-factors in sets of genomic regions")
1758 "COUGER can be applied to any two sets of genomic regions bound by
1759 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1760 putative co-factors that provide specificity to each TF. The framework
1761 determines the genomic targets uniquely-bound by each TF, and identifies a
1762 small set of co-factors that best explain the in vivo binding differences
1763 between the two TFs.
1765 COUGER uses classification algorithms (support vector machines and random
1766 forests) with features that reflect the DNA binding specificities of putative
1767 co-factors. The features are generated either from high-throughput TF-DNA
1768 binding data (from protein binding microarray experiments), or from large
1769 collections of DNA motifs.")
1770 (license license:gpl3+)))
1772 (define-public clustal-omega
1774 (name "clustal-omega")
1779 "http://www.clustal.org/omega/clustal-omega-"
1783 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1784 (build-system gnu-build-system)
1786 `(("argtable" ,argtable)))
1787 (home-page "http://www.clustal.org/omega/")
1788 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1790 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1791 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1792 of handling data-sets of hundreds of thousands of sequences in reasonable
1794 (license license:gpl2+)))
1796 (define-public crossmap
1802 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1806 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1807 ;; This patch has been sent upstream already and is available
1808 ;; for download from Sourceforge, but it has not been merged.
1809 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1810 (modules '((guix build utils)))
1811 ;; remove bundled copy of pysam
1813 '(delete-file-recursively "lib/pysam"))))
1814 (build-system python-build-system)
1816 `(#:python ,python-2
1820 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1823 `(("python-numpy" ,python2-numpy)
1824 ("python-pysam" ,python2-pysam)
1827 `(("python-cython" ,python2-cython)
1828 ("python-nose" ,python2-nose)))
1829 (home-page "http://crossmap.sourceforge.net/")
1830 (synopsis "Convert genome coordinates between assemblies")
1832 "CrossMap is a program for conversion of genome coordinates or annotation
1833 files between different genome assemblies. It supports most commonly used
1834 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1835 (license license:gpl2+)))
1837 (define-public cufflinks
1843 (uri (string-append "http://cole-trapnell-lab.github.io/"
1844 "cufflinks/assets/downloads/cufflinks-"
1848 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1849 (build-system gnu-build-system)
1853 ;; The includes for "eigen" are located in a subdirectory.
1854 (string-append "EIGEN_CPPFLAGS="
1855 "-I" (assoc-ref %build-inputs "eigen")
1857 ;; Cufflinks must be linked with various boost libraries.
1858 (string-append "LDFLAGS="
1859 (string-join '("-lboost_system"
1860 "-lboost_serialization"
1861 "-lboost_thread"))))
1863 (modify-phases %standard-phases
1864 (add-after 'unpack 'fix-search-for-bam
1866 (substitute* '("ax_bam.m4"
1869 (("<bam/sam\\.h>") "<samtools/sam.h>")
1870 (("<bam/bam\\.h>") "<samtools/bam.h>")
1871 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1874 (list (string-append "--with-bam="
1875 (assoc-ref %build-inputs "samtools")))))
1878 ("samtools" ,samtools-0.1)
1881 ("python" ,python-2)
1883 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1884 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1886 "Cufflinks assembles RNA transcripts, estimates their abundances,
1887 and tests for differential expression and regulation in RNA-Seq
1888 samples. It accepts aligned RNA-Seq reads and assembles the
1889 alignments into a parsimonious set of transcripts. Cufflinks then
1890 estimates the relative abundances of these transcripts based on how
1891 many reads support each one, taking into account biases in library
1892 preparation protocols.")
1893 (license license:boost1.0)))
1895 (define-public cutadapt
1902 "https://github.com/marcelm/cutadapt/archive/v"
1904 (file-name (string-append name "-" version ".tar.gz"))
1907 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1908 (build-system python-build-system)
1911 (modify-phases %standard-phases
1912 ;; The tests must be run after installation.
1914 (add-after 'install 'check
1915 (lambda* (#:key inputs outputs #:allow-other-keys)
1916 (setenv "PYTHONPATH"
1918 (getenv "PYTHONPATH")
1919 ":" (assoc-ref outputs "out")
1921 (string-take (string-take-right
1922 (assoc-ref inputs "python") 5) 3)
1924 (zero? (system* "nosetests" "-P" "tests")))))))
1926 `(("python-xopen" ,python-xopen)))
1928 `(("python-cython" ,python-cython)
1929 ("python-nose" ,python-nose)))
1930 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1931 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1933 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1934 other types of unwanted sequence from high-throughput sequencing reads.")
1935 (license license:expat)))
1937 (define-public libbigwig
1943 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1944 "archive/" version ".tar.gz"))
1945 (file-name (string-append name "-" version ".tar.gz"))
1948 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1949 (build-system gnu-build-system)
1951 `(#:test-target "test"
1954 (string-append "prefix=" (assoc-ref %outputs "out")))
1956 (modify-phases %standard-phases
1958 (add-before 'check 'disable-curl-test
1960 (substitute* "Makefile"
1961 (("./test/testRemote.*") ""))
1963 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1964 ;; there has not yet been a release containing this change.
1965 (add-before 'install 'create-target-dirs
1966 (lambda* (#:key outputs #:allow-other-keys)
1967 (let ((out (assoc-ref outputs "out")))
1968 (mkdir-p (string-append out "/lib"))
1969 (mkdir-p (string-append out "/include"))
1975 `(("doxygen" ,doxygen)))
1976 (home-page "https://github.com/dpryan79/libBigWig")
1977 (synopsis "C library for handling bigWig files")
1979 "This package provides a C library for parsing local and remote BigWig
1981 (license license:expat)))
1983 (define-public python-pybigwig
1985 (name "python-pybigwig")
1989 (uri (pypi-uri "pyBigWig" version))
1992 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1993 (modules '((guix build utils)))
1996 ;; Delete bundled libBigWig sources
1997 (delete-file-recursively "libBigWig")))))
1998 (build-system python-build-system)
2001 (modify-phases %standard-phases
2002 (add-after 'unpack 'link-with-libBigWig
2003 (lambda* (#:key inputs #:allow-other-keys)
2004 (substitute* "setup.py"
2005 (("libs=\\[") "libs=[\"BigWig\", "))
2008 `(("libbigwig" ,libbigwig)
2011 (home-page "https://github.com/dpryan79/pyBigWig")
2012 (synopsis "Access bigWig files in Python using libBigWig")
2014 "This package provides Python bindings to the libBigWig library for
2015 accessing bigWig files.")
2016 (license license:expat)))
2018 (define-public python2-pybigwig
2019 (package-with-python2 python-pybigwig))
2021 (define-public python-dendropy
2023 (name "python-dendropy")
2028 (uri (pypi-uri "DendroPy" version))
2031 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2032 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2033 (build-system python-build-system)
2034 (home-page "http://packages.python.org/DendroPy/")
2035 (synopsis "Library for phylogenetics and phylogenetic computing")
2037 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2038 writing, simulation, processing and manipulation of phylogenetic
2039 trees (phylogenies) and characters.")
2040 (license license:bsd-3)
2041 (properties `((python2-variant . ,(delay python2-dendropy))))))
2043 (define-public python2-dendropy
2044 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2048 `(#:python ,python-2
2050 (modify-phases %standard-phases
2052 ;; There is currently a test failure that only happens on some
2053 ;; systems, and only using "setup.py test"
2054 (lambda _ (zero? (system* "nosetests")))))))
2055 (native-inputs `(("python2-nose" ,python2-nose)
2056 ,@(package-native-inputs base))))))
2058 (define-public python-py2bit
2060 (name "python-py2bit")
2065 (uri (pypi-uri "py2bit" version))
2068 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2069 (build-system python-build-system)
2070 (home-page "https://github.com/dpryan79/py2bit")
2071 (synopsis "Access 2bit files using lib2bit")
2073 "This package provides Python bindings for lib2bit to access 2bit files
2075 (license license:expat)))
2077 (define-public deeptools
2083 (uri (string-append "https://github.com/fidelram/deepTools/"
2084 "archive/" version ".tar.gz"))
2085 (file-name (string-append name "-" version ".tar.gz"))
2088 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2089 (build-system python-build-system)
2091 `(("python-scipy" ,python-scipy)
2092 ("python-numpy" ,python-numpy)
2093 ("python-numpydoc" ,python-numpydoc)
2094 ("python-matplotlib" ,python-matplotlib)
2095 ("python-pysam" ,python-pysam)
2096 ("python-py2bit" ,python-py2bit)
2097 ("python-pybigwig" ,python-pybigwig)))
2099 `(("python-mock" ,python-mock) ;for tests
2100 ("python-nose" ,python-nose) ;for tests
2101 ("python-pytz" ,python-pytz))) ;for tests
2102 (home-page "https://github.com/fidelram/deepTools")
2103 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2105 "DeepTools addresses the challenge of handling the large amounts of data
2106 that are now routinely generated from DNA sequencing centers. To do so,
2107 deepTools contains useful modules to process the mapped reads data to create
2108 coverage files in standard bedGraph and bigWig file formats. By doing so,
2109 deepTools allows the creation of normalized coverage files or the comparison
2110 between two files (for example, treatment and control). Finally, using such
2111 normalized and standardized files, multiple visualizations can be created to
2112 identify enrichments with functional annotations of the genome.")
2113 (license license:gpl3+)))
2115 (define-public diamond
2122 "https://github.com/bbuchfink/diamond/archive/v"
2124 (file-name (string-append name "-" version ".tar.gz"))
2127 "13qqzwg54n5dqh8pm5n3v8x6gqbczzakphwwjix63qv60hcd5bqd"))))
2128 (build-system cmake-build-system)
2130 '(#:tests? #f ; no "check" target
2132 (modify-phases %standard-phases
2133 (add-after 'unpack 'remove-native-compilation
2135 (substitute* "CMakeLists.txt" (("-march=native") ""))
2139 (home-page "https://github.com/bbuchfink/diamond")
2140 (synopsis "Accelerated BLAST compatible local sequence aligner")
2142 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2143 translated DNA query sequences against a protein reference database (BLASTP
2144 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2145 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2146 data and settings.")
2147 (license license:agpl3+)))
2149 (define-public discrover
2156 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2158 (file-name (string-append name "-" version ".tar.gz"))
2161 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2162 (build-system cmake-build-system)
2164 `(#:tests? #f ; there are no tests
2166 (modify-phases %standard-phases
2167 (add-after 'unpack 'add-missing-includes
2169 (substitute* "src/executioninformation.hpp"
2170 (("#define EXECUTIONINFORMATION_HPP" line)
2171 (string-append line "\n#include <random>")))
2172 (substitute* "src/plasma/fasta.hpp"
2173 (("#define FASTA_HPP" line)
2174 (string-append line "\n#include <random>")))
2180 `(("texlive" ,texlive)
2181 ("imagemagick" ,imagemagick)))
2182 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2183 (synopsis "Discover discriminative nucleotide sequence motifs")
2184 (description "Discrover is a motif discovery method to find binding sites
2185 of nucleic acid binding proteins.")
2186 (license license:gpl3+)))
2188 (define-public eigensoft
2189 (let ((revision "1")
2190 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2193 (version (string-append "6.1.2-"
2195 (string-take commit 9)))
2200 (url "https://github.com/DReichLab/EIG.git")
2202 (file-name (string-append "eigensoft-" commit "-checkout"))
2205 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2206 (modules '((guix build utils)))
2207 ;; Remove pre-built binaries.
2209 (delete-file-recursively "bin")
2212 (build-system gnu-build-system)
2214 `(#:tests? #f ; There are no tests.
2215 #:make-flags '("CC=gcc")
2217 (modify-phases %standard-phases
2218 ;; There is no configure phase, but the Makefile is in a
2223 ;; The link flags are incomplete.
2224 (substitute* "Makefile"
2225 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2227 ;; The provided install target only copies executables to
2228 ;; the "bin" directory in the build root.
2229 (add-after 'install 'actually-install
2230 (lambda* (#:key outputs #:allow-other-keys)
2231 (let* ((out (assoc-ref outputs "out"))
2232 (bin (string-append out "/bin")))
2233 (for-each (lambda (file)
2234 (install-file file bin))
2235 (find-files "../bin" ".*"))
2240 ("openblas" ,openblas)
2242 ("gfortran" ,gfortran "lib")))
2243 (home-page "https://github.com/DReichLab/EIG")
2244 (synopsis "Tools for population genetics")
2245 (description "The EIGENSOFT package provides tools for population
2246 genetics and stratification correction. EIGENSOFT implements methods commonly
2247 used in population genetics analyses such as PCA, computation of Tracy-Widom
2248 statistics, and finding related individuals in structured populations. It
2249 comes with a built-in plotting script and supports multiple file formats and
2250 quantitative phenotypes.")
2251 ;; The license of the eigensoft tools is Expat, but since it's
2252 ;; linking with the GNU Scientific Library (GSL) the effective
2253 ;; license is the GPL.
2254 (license license:gpl3+))))
2256 (define-public edirect
2262 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2263 "versions/2016-05-03/edirect.tar.gz"))
2266 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2267 (build-system perl-build-system)
2269 `(#:tests? #f ;no "check" target
2271 (modify-phases %standard-phases
2275 (lambda* (#:key outputs #:allow-other-keys)
2276 (let ((target (string-append (assoc-ref outputs "out")
2279 (install-file "edirect.pl" target)
2282 'install 'wrap-program
2283 (lambda* (#:key inputs outputs #:allow-other-keys)
2284 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2285 (let* ((out (assoc-ref outputs "out"))
2286 (path (getenv "PERL5LIB")))
2287 (wrap-program (string-append out "/bin/edirect.pl")
2288 `("PERL5LIB" ":" prefix (,path)))))))))
2290 `(("perl-html-parser" ,perl-html-parser)
2291 ("perl-encode-locale" ,perl-encode-locale)
2292 ("perl-file-listing" ,perl-file-listing)
2293 ("perl-html-tagset" ,perl-html-tagset)
2294 ("perl-html-tree" ,perl-html-tree)
2295 ("perl-http-cookies" ,perl-http-cookies)
2296 ("perl-http-date" ,perl-http-date)
2297 ("perl-http-message" ,perl-http-message)
2298 ("perl-http-negotiate" ,perl-http-negotiate)
2299 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2300 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2301 ("perl-net-http" ,perl-net-http)
2302 ("perl-uri" ,perl-uri)
2303 ("perl-www-robotrules" ,perl-www-robotrules)
2305 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2306 (synopsis "Tools for accessing the NCBI's set of databases")
2308 "Entrez Direct (EDirect) is a method for accessing the National Center
2309 for Biotechnology Information's (NCBI) set of interconnected
2310 databases (publication, sequence, structure, gene, variation, expression,
2311 etc.) from a terminal. Functions take search terms from command-line
2312 arguments. Individual operations are combined to build multi-step queries.
2313 Record retrieval and formatting normally complete the process.
2315 EDirect also provides an argument-driven function that simplifies the
2316 extraction of data from document summaries or other results that are returned
2317 in structured XML format. This can eliminate the need for writing custom
2318 software to answer ad hoc questions.")
2319 (license license:public-domain)))
2321 (define-public exonerate
2330 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2331 "exonerate-" version ".tar.gz"))
2334 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2335 (build-system gnu-build-system)
2337 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2339 `(("pkg-config" ,pkg-config)))
2343 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2344 (synopsis "Generic tool for biological sequence alignment")
2346 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2347 the alignment of sequences using a many alignment models, either exhaustive
2348 dynamic programming or a variety of heuristics.")
2349 (license license:gpl3)))
2351 (define-public express
2359 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2360 version "/express-" version "-src.tgz"))
2363 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2364 (build-system cmake-build-system)
2366 `(#:tests? #f ;no "check" target
2369 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2370 (lambda* (#:key inputs #:allow-other-keys)
2371 (substitute* "CMakeLists.txt"
2372 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2373 "set(Boost_USE_STATIC_LIBS OFF)")
2374 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2375 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2376 (substitute* "src/CMakeLists.txt"
2377 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2378 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2383 ("bamtools" ,bamtools)
2384 ("protobuf" ,protobuf)
2386 (home-page "http://bio.math.berkeley.edu/eXpress")
2387 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2389 "eXpress is a streaming tool for quantifying the abundances of a set of
2390 target sequences from sampled subsequences. Example applications include
2391 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2392 analysis (from RNA-Seq), transcription factor binding quantification in
2393 ChIP-Seq, and analysis of metagenomic data.")
2394 (license license:artistic2.0)))
2396 (define-public express-beta-diversity
2398 (name "express-beta-diversity")
2404 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2406 (file-name (string-append name "-" version ".tar.gz"))
2409 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2410 (build-system gnu-build-system)
2413 (modify-phases %standard-phases
2415 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2417 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2419 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2421 (lambda* (#:key outputs #:allow-other-keys)
2422 (let ((bin (string-append (assoc-ref outputs "out")
2425 (install-file "scripts/convertToEBD.py" bin)
2426 (install-file "bin/ExpressBetaDiversity" bin)
2429 `(("python" ,python-2)))
2430 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2431 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2433 "Express Beta Diversity (EBD) calculates ecological beta diversity
2434 (dissimilarity) measures between biological communities. EBD implements a
2435 variety of diversity measures including those that make use of phylogenetic
2436 similarity of community members.")
2437 (license license:gpl3+)))
2439 (define-public fasttree
2446 "http://www.microbesonline.org/fasttree/FastTree-"
2450 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2451 (build-system gnu-build-system)
2453 `(#:tests? #f ; no "check" target
2455 (modify-phases %standard-phases
2459 (lambda* (#:key source #:allow-other-keys)
2460 (and (zero? (system* "gcc"
2462 "-finline-functions"
2469 (zero? (system* "gcc"
2473 "-finline-functions"
2481 (lambda* (#:key outputs #:allow-other-keys)
2482 (let ((bin (string-append (assoc-ref outputs "out")
2485 (install-file "FastTree" bin)
2486 (install-file "FastTreeMP" bin)
2488 (home-page "http://www.microbesonline.org/fasttree")
2489 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2491 "FastTree can handle alignments with up to a million of sequences in a
2492 reasonable amount of time and memory. For large alignments, FastTree is
2493 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2494 (license license:gpl2+)))
2496 (define-public fastx-toolkit
2498 (name "fastx-toolkit")
2504 "https://github.com/agordon/fastx_toolkit/releases/download/"
2505 version "/fastx_toolkit-" version ".tar.bz2"))
2508 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2509 (build-system gnu-build-system)
2511 `(("libgtextutils" ,libgtextutils)))
2513 `(("pkg-config" ,pkg-config)))
2514 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2515 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2517 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2518 FASTA/FASTQ files preprocessing.
2520 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2521 containing multiple short-reads sequences. The main processing of such
2522 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2523 is sometimes more productive to preprocess the files before mapping the
2524 sequences to the genome---manipulating the sequences to produce better mapping
2525 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2526 (license license:agpl3+)))
2528 (define-public flexbar
2535 (string-append "mirror://sourceforge/flexbar/"
2536 version "/flexbar_v" version "_src.tgz"))
2539 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2540 (build-system cmake-build-system)
2542 `(#:configure-flags (list
2543 (string-append "-DFLEXBAR_BINARY_DIR="
2544 (assoc-ref %outputs "out")
2549 (lambda* (#:key outputs #:allow-other-keys)
2550 (setenv "PATH" (string-append
2551 (assoc-ref outputs "out") "/bin:"
2553 (chdir "../flexbar_v2.5_src/test")
2554 (zero? (system* "bash" "flexbar_validate.sh")))
2555 (alist-delete 'install %standard-phases))))
2560 `(("pkg-config" ,pkg-config)
2562 (home-page "http://flexbar.sourceforge.net")
2563 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2565 "Flexbar preprocesses high-throughput nucleotide sequencing data
2566 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2567 Moreover, trimming and filtering features are provided. Flexbar increases
2568 read mapping rates and improves genome and transcriptome assemblies. It
2569 supports next-generation sequencing data in fasta/q and csfasta/q format from
2570 Illumina, Roche 454, and the SOLiD platform.")
2571 (license license:gpl3)))
2573 (define-public fraggenescan
2575 (name "fraggenescan")
2581 (string-append "mirror://sourceforge/fraggenescan/"
2582 "FragGeneScan" version ".tar.gz"))
2584 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2585 (build-system gnu-build-system)
2588 (modify-phases %standard-phases
2590 (add-before 'build 'patch-paths
2591 (lambda* (#:key outputs #:allow-other-keys)
2592 (let* ((out (string-append (assoc-ref outputs "out")))
2593 (share (string-append out "/share/fraggenescan/")))
2594 (substitute* "run_FragGeneScan.pl"
2596 (string-append "system(\"" (which "rm")))
2598 (string-append "system(\"" (which "mv")))
2599 (("\\\"awk") (string-append "\"" (which "awk")))
2600 ;; This script and other programs expect the training files
2601 ;; to be in the non-standard location bin/train/XXX. Change
2602 ;; this to be share/fraggenescan/train/XXX instead.
2603 (("^\\$train.file = \\$dir.*")
2604 (string-append "$train_file = \""
2606 "train/\".$FGS_train_file;")))
2607 (substitute* "run_hmm.c"
2608 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2609 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2612 (lambda _ (and (zero? (system* "make" "clean"))
2613 (zero? (system* "make" "fgs")))))
2615 (lambda* (#:key outputs #:allow-other-keys)
2616 (let* ((out (string-append (assoc-ref outputs "out")))
2617 (bin (string-append out "/bin/"))
2618 (share (string-append out "/share/fraggenescan/train")))
2619 (install-file "run_FragGeneScan.pl" bin)
2620 (install-file "FragGeneScan" bin)
2621 (copy-recursively "train" share))))
2623 (add-after 'install 'post-install-check
2624 ;; In lieu of 'make check', run one of the examples and check the
2625 ;; output files gets created.
2626 (lambda* (#:key outputs #:allow-other-keys)
2627 (let* ((out (string-append (assoc-ref outputs "out")))
2628 (bin (string-append out "/bin/"))
2629 (frag (string-append bin "run_FragGeneScan.pl")))
2630 (and (zero? (system* frag ; Test complete genome.
2631 "-genome=./example/NC_000913.fna"
2635 (file-exists? "test2.faa")
2636 (file-exists? "test2.ffn")
2637 (file-exists? "test2.gff")
2638 (file-exists? "test2.out")
2639 (zero? (system* ; Test incomplete sequences.
2641 "-genome=./example/NC_000913-fgs.ffn"
2644 "-train=454_30")))))))))
2647 ("python" ,python-2))) ;not compatible with python 3.
2648 (home-page "https://sourceforge.net/projects/fraggenescan/")
2649 (synopsis "Finds potentially fragmented genes in short reads")
2651 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2652 short and error-prone DNA sequencing reads. It can also be applied to predict
2653 genes in incomplete assemblies or complete genomes.")
2654 ;; GPL3+ according to private correspondense with the authors.
2655 (license license:gpl3+)))
2657 (define-public fxtract
2658 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2666 "https://github.com/ctSkennerton/fxtract/archive/"
2668 (file-name (string-append "ctstennerton-util-"
2669 (string-take util-commit 7)
2673 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2674 (build-system gnu-build-system)
2676 `(#:make-flags (list
2677 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2679 #:test-target "fxtract_test"
2681 (modify-phases %standard-phases
2683 (add-before 'build 'copy-util
2684 (lambda* (#:key inputs #:allow-other-keys)
2686 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2688 ;; Do not use make install as this requires additional dependencies.
2690 (lambda* (#:key outputs #:allow-other-keys)
2691 (let* ((out (assoc-ref outputs "out"))
2692 (bin (string-append out"/bin")))
2693 (install-file "fxtract" bin)
2699 ;; ctskennerton-util is licensed under GPL2.
2700 `(("ctskennerton-util"
2704 (url "https://github.com/ctSkennerton/util.git")
2705 (commit util-commit)))
2706 (file-name (string-append
2707 "ctstennerton-util-" util-commit "-checkout"))
2710 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2711 (home-page "https://github.com/ctSkennerton/fxtract")
2712 (synopsis "Extract sequences from FASTA and FASTQ files")
2714 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2715 or FASTQ) file given a subsequence. It uses a simple substring search for
2716 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2717 lookups or multi-pattern searching as required. By default fxtract looks in
2718 the sequence of each record but can also be told to look in the header,
2719 comment or quality sections.")
2720 ;; 'util' requires SSE instructions.
2721 (supported-systems '("x86_64-linux"))
2722 (license license:expat))))
2724 (define-public gemma
2730 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2732 (file-name (string-append name "-" version ".tar.gz"))
2735 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2736 (patches (search-patches "gemma-intel-compat.patch"))))
2741 (build-system gnu-build-system)
2744 '(,@(match (%current-system)
2746 '("FORCE_DYNAMIC=1"))
2748 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2750 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2752 (modify-phases %standard-phases
2754 (add-before 'build 'bin-mkdir
2759 (lambda* (#:key outputs #:allow-other-keys)
2760 (let ((out (assoc-ref outputs "out")))
2761 (install-file "bin/gemma"
2765 #:tests? #f)) ; no tests included yet
2766 (home-page "https://github.com/xiangzhou/GEMMA")
2767 (synopsis "Tool for genome-wide efficient mixed model association")
2769 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2770 standard linear mixed model resolver with application in genome-wide
2771 association studies (GWAS).")
2772 (license license:gpl3)))
2781 "https://github.com/nboley/grit/archive/"
2783 (file-name (string-append name "-" version ".tar.gz"))
2786 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2787 (build-system python-build-system)
2789 `(#:python ,python-2
2792 'unpack 'generate-from-cython-sources
2793 (lambda* (#:key inputs outputs #:allow-other-keys)
2794 ;; Delete these C files to force fresh generation from pyx sources.
2795 (delete-file "grit/sparsify_support_fns.c")
2796 (delete-file "grit/call_peaks_support_fns.c")
2797 (substitute* "setup.py"
2798 (("Cython.Setup") "Cython.Build")
2799 ;; Add numpy include path to fix compilation
2801 (string-append "pyx\", ], include_dirs = ['"
2802 (assoc-ref inputs "python-numpy")
2803 "/lib/python2.7/site-packages/numpy/core/include/"
2807 `(("python-scipy" ,python2-scipy)
2808 ("python-numpy" ,python2-numpy)
2809 ("python-pysam" ,python2-pysam)
2810 ("python-networkx" ,python2-networkx)))
2812 `(("python-cython" ,python2-cython)))
2813 (home-page "http://grit-bio.org")
2814 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2816 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2817 full length transcript models. When none of these data sources are available,
2818 GRIT can be run by providing a candidate set of TES or TSS sites. In
2819 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2820 also be run in quantification mode, where it uses a provided GTF file and just
2821 estimates transcript expression.")
2822 (license license:gpl3+)))
2824 (define-public hisat
2831 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2832 version "-beta-source.zip"))
2835 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2836 (build-system gnu-build-system)
2838 `(#:tests? #f ;no check target
2839 #:make-flags '("allall"
2840 ;; Disable unsupported `popcnt' instructions on
2841 ;; architectures other than x86_64
2842 ,@(if (string-prefix? "x86_64"
2843 (or (%current-target-system)
2846 '("POPCNT_CAPABILITY=0")))
2849 'unpack 'patch-sources
2851 ;; XXX Cannot use snippet because zip files are not supported
2852 (substitute* "Makefile"
2853 (("^CC = .*$") "CC = gcc")
2854 (("^CPP = .*$") "CPP = g++")
2855 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2856 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2857 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2858 (substitute* '("hisat-build" "hisat-inspect")
2859 (("/usr/bin/env") (which "env"))))
2862 (lambda* (#:key outputs #:allow-other-keys)
2863 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2864 (for-each (lambda (file)
2865 (install-file file bin))
2868 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2869 (alist-delete 'configure %standard-phases)))))
2871 `(("unzip" ,unzip)))
2876 ;; Non-portable SSE instructions are used so building fails on platforms
2877 ;; other than x86_64.
2878 (supported-systems '("x86_64-linux"))
2879 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2880 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2882 "HISAT is a fast and sensitive spliced alignment program for mapping
2883 RNA-seq reads. In addition to one global FM index that represents a whole
2884 genome, HISAT uses a large set of small FM indexes that collectively cover the
2885 whole genome. These small indexes (called local indexes) combined with
2886 several alignment strategies enable effective alignment of RNA-seq reads, in
2887 particular, reads spanning multiple exons.")
2888 (license license:gpl3+)))
2890 (define-public hisat2
2897 ;; FIXME: a better source URL is
2898 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2899 ;; "/downloads/hisat2-" version "-source.zip")
2900 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2901 ;; but it is currently unavailable.
2902 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2903 (file-name (string-append name "-" version ".tar.gz"))
2906 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2907 (build-system gnu-build-system)
2909 `(#:tests? #f ; no check target
2910 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2911 #:modules ((guix build gnu-build-system)
2915 (modify-phases %standard-phases
2916 (add-after 'unpack 'make-deterministic
2918 (substitute* "Makefile"
2923 (lambda* (#:key outputs #:allow-other-keys)
2924 (let* ((out (assoc-ref outputs "out"))
2925 (bin (string-append out "/bin/"))
2926 (doc (string-append out "/share/doc/hisat2/")))
2928 (cut install-file <> bin)
2930 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2932 (install-file "doc/manual.inc.html" doc))
2935 `(("unzip" ,unzip) ; needed for archive from ftp
2937 ("pandoc" ,ghc-pandoc))) ; for documentation
2938 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2939 (synopsis "Graph-based alignment of genomic sequencing reads")
2940 (description "HISAT2 is a fast and sensitive alignment program for mapping
2941 next-generation sequencing reads (both DNA and RNA) to a population of human
2942 genomes (as well as to a single reference genome). In addition to using one
2943 global @dfn{graph FM} (GFM) index that represents a population of human
2944 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2945 the whole genome. These small indexes, combined with several alignment
2946 strategies, enable rapid and accurate alignment of sequencing reads. This new
2947 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2948 ;; HISAT2 contains files from Bowtie2, which is released under
2949 ;; GPLv2 or later. The HISAT2 source files are released under
2951 (license license:gpl3+)))
2953 (define-public hmmer
2961 "http://eddylab.org/software/hmmer"
2962 (version-prefix version 1) "/"
2963 version "/hmmer-" version ".tar.gz"))
2966 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2967 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2968 (build-system gnu-build-system)
2969 (native-inputs `(("perl" ,perl)))
2970 (home-page "http://hmmer.org/")
2971 (synopsis "Biosequence analysis using profile hidden Markov models")
2973 "HMMER is used for searching sequence databases for homologs of protein
2974 sequences, and for making protein sequence alignments. It implements methods
2975 using probabilistic models called profile hidden Markov models (profile
2977 (license (list license:gpl3+
2978 ;; The bundled library 'easel' is distributed
2979 ;; under The Janelia Farm Software License.
2980 (license:non-copyleft
2981 "file://easel/LICENSE"
2982 "See easel/LICENSE in the distribution.")))))
2984 (define-public htseq
2990 (uri (pypi-uri "HTSeq" version))
2993 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2994 (build-system python-build-system)
2996 `(("python-cython" ,python-cython)))
2997 ;; Numpy needs to be propagated when htseq is used as a Python library.
2999 `(("python-numpy" ,python-numpy)))
3001 `(("python-pysam" ,python-pysam)
3002 ("python-matplotlib" ,python-matplotlib)))
3003 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3004 (synopsis "Analysing high-throughput sequencing data with Python")
3006 "HTSeq is a Python package that provides infrastructure to process data
3007 from high-throughput sequencing assays.")
3008 (license license:gpl3+)))
3010 (define-public python2-htseq
3011 (package-with-python2 htseq))
3013 (define-public java-htsjdk
3015 (name "java-htsjdk")
3020 "https://github.com/samtools/htsjdk/archive/"
3022 (file-name (string-append name "-" version ".tar.gz"))
3025 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
3026 (modules '((guix build utils)))
3027 ;; remove build dependency on git
3028 (snippet '(substitute* "build.xml"
3029 (("failifexecutionfails=\"true\"")
3030 "failifexecutionfails=\"false\"")))))
3031 (build-system ant-build-system)
3033 `(#:tests? #f ; test require Internet access
3035 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3036 "/share/java/htsjdk/"))
3037 #:build-target "all"
3039 (modify-phases %standard-phases
3040 ;; The build phase also installs the jars
3041 (delete 'install))))
3042 (home-page "http://samtools.github.io/htsjdk/")
3043 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3045 "HTSJDK is an implementation of a unified Java library for accessing
3046 common file formats, such as SAM and VCF, used for high-throughput
3047 sequencing (HTS) data. There are also an number of useful utilities for
3048 manipulating HTS data.")
3049 (license license:expat)))
3051 (define-public htslib
3058 "https://github.com/samtools/htslib/releases/download/"
3059 version "/htslib-" version ".tar.bz2"))
3062 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3063 (build-system gnu-build-system)
3066 (modify-phases %standard-phases
3068 'unpack 'patch-tests
3070 (substitute* "test/test.pl"
3071 (("/bin/bash") (which "bash")))
3074 `(("openssl" ,openssl)
3079 (home-page "http://www.htslib.org")
3080 (synopsis "C library for reading/writing high-throughput sequencing data")
3082 "HTSlib is a C library for reading/writing high-throughput sequencing
3083 data. It also provides the bgzip, htsfile, and tabix utilities.")
3084 ;; Files under cram/ are released under the modified BSD license;
3085 ;; the rest is released under the Expat license
3086 (license (list license:expat license:bsd-3))))
3088 ;; This package should be removed once no packages rely upon it.
3096 "https://github.com/samtools/htslib/releases/download/"
3097 version "/htslib-" version ".tar.bz2"))
3100 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3109 "https://github.com/nboley/idr/archive/"
3111 (file-name (string-append name "-" version ".tar.gz"))
3114 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3115 (build-system python-build-system)
3117 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3119 `(("python-scipy" ,python-scipy)
3120 ("python-sympy" ,python-sympy)
3121 ("python-numpy" ,python-numpy)
3122 ("python-matplotlib" ,python-matplotlib)))
3124 `(("python-cython" ,python-cython)))
3125 (home-page "https://github.com/nboley/idr")
3126 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3128 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3129 to measure the reproducibility of findings identified from replicate
3130 experiments and provide highly stable thresholds based on reproducibility.")
3131 (license license:gpl3+)))
3133 (define-public jellyfish
3139 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3140 "releases/download/v" version
3141 "/jellyfish-" version ".tar.gz"))
3144 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3145 (build-system gnu-build-system)
3146 (outputs '("out" ;for library
3147 "ruby" ;for Ruby bindings
3148 "python")) ;for Python bindings
3151 (list (string-append "--enable-ruby-binding="
3152 (assoc-ref %outputs "ruby"))
3153 (string-append "--enable-python-binding="
3154 (assoc-ref %outputs "python")))
3156 (modify-phases %standard-phases
3157 (add-before 'check 'set-SHELL-variable
3159 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3161 (setenv "SHELL" (which "bash"))
3167 ("python" ,python-2)))
3168 (synopsis "Tool for fast counting of k-mers in DNA")
3170 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3171 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3172 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3173 is a command-line program that reads FASTA and multi-FASTA files containing
3174 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3175 translated into a human-readable text format using the @code{jellyfish dump}
3176 command, or queried for specific k-mers with @code{jellyfish query}.")
3177 (home-page "http://www.genome.umd.edu/jellyfish.html")
3178 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3179 (supported-systems '("x86_64-linux"))
3180 ;; The combined work is published under the GPLv3 or later. Individual
3181 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3182 (license (list license:gpl3+ license:expat))))
3184 (define-public khmer
3191 (uri (pypi-uri "khmer" version))
3194 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3195 (patches (search-patches "khmer-use-libraries.patch"))))
3196 (build-system python-build-system)
3199 (modify-phases %standard-phases
3200 (add-after 'unpack 'set-paths
3201 (lambda* (#:key inputs outputs #:allow-other-keys)
3202 ;; Delete bundled libraries.
3203 (delete-file-recursively "third-party/zlib")
3204 (delete-file-recursively "third-party/bzip2")
3205 ;; Replace bundled seqan.
3206 (let* ((seqan-all "third-party/seqan")
3207 (seqan-include (string-append
3208 seqan-all "/core/include")))
3209 (delete-file-recursively seqan-all)
3210 (copy-recursively (string-append (assoc-ref inputs "seqan")
3212 (string-append seqan-include "/seqan")))
3213 ;; We do not replace the bundled MurmurHash as the canonical
3214 ;; repository for this code 'SMHasher' is unsuitable for
3215 ;; providing a library. See
3216 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3218 (add-after 'unpack 'set-cc
3222 ;; It is simpler to test after installation.
3224 (add-after 'install 'post-install-check
3225 (lambda* (#:key inputs outputs #:allow-other-keys)
3226 (let ((out (assoc-ref outputs "out")))
3231 (assoc-ref outputs "out")
3233 (setenv "PYTHONPATH"
3235 (getenv "PYTHONPATH")
3239 (string-take (string-take-right
3240 (assoc-ref inputs "python") 5) 3)
3242 (with-directory-excursion "build"
3243 (zero? (system* "nosetests" "khmer" "--attr"
3244 "!known_failing")))))))))
3247 ("python-nose" ,python-nose)))
3251 ("python-screed" ,python-screed)
3252 ("python-bz2file" ,python-bz2file)
3253 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3254 ;; until the next version of khmer (likely 2.1) is released.
3256 (home-page "https://khmer.readthedocs.org/")
3257 (synopsis "K-mer counting, filtering and graph traversal library")
3258 (description "The khmer software is a set of command-line tools for
3259 working with DNA shotgun sequencing data from genomes, transcriptomes,
3260 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3261 sometimes better. Khmer can also identify and fix problems with shotgun
3263 ;; When building on i686, armhf and mips64el, we get the following error:
3264 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3265 (supported-systems '("x86_64-linux"))
3266 (license license:bsd-3)))
3268 (define-public kaiju
3275 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3277 (file-name (string-append name "-" version ".tar.gz"))
3280 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3281 (build-system gnu-build-system)
3283 `(#:tests? #f ; There are no tests.
3285 (modify-phases %standard-phases
3287 (add-before 'build 'move-to-src-dir
3288 (lambda _ (chdir "src") #t))
3290 (lambda* (#:key inputs outputs #:allow-other-keys)
3291 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3294 (copy-recursively "bin" bin)
3295 (copy-recursively "util" bin))
3299 (home-page "http://kaiju.binf.ku.dk/")
3300 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3301 (description "Kaiju is a program for sensitive taxonomic classification
3302 of high-throughput sequencing reads from metagenomic whole genome sequencing
3304 (license license:gpl3+)))
3309 (version "2.1.0.20151222")
3312 (uri (pypi-uri "MACS2" version))
3315 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3316 (build-system python-build-system)
3318 `(#:python ,python-2 ; only compatible with Python 2.7
3319 #:tests? #f)) ; no test target
3321 `(("python-numpy" ,python2-numpy)))
3322 (home-page "https://github.com/taoliu/MACS/")
3323 (synopsis "Model based analysis for ChIP-Seq data")
3325 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3326 identifying transcript factor binding sites named Model-based Analysis of
3327 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3328 the significance of enriched ChIP regions and it improves the spatial
3329 resolution of binding sites through combining the information of both
3330 sequencing tag position and orientation.")
3331 (license license:bsd-3)))
3333 (define-public mafft
3340 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3341 "-without-extensions-src.tgz"))
3342 (file-name (string-append name "-" version ".tgz"))
3345 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3346 (build-system gnu-build-system)
3348 `(#:tests? #f ; no automated tests, though there are tests in the read me
3349 #:make-flags (let ((out (assoc-ref %outputs "out")))
3350 (list (string-append "PREFIX=" out)
3351 (string-append "BINDIR="
3352 (string-append out "/bin"))))
3354 (modify-phases %standard-phases
3355 (add-after 'unpack 'enter-dir
3356 (lambda _ (chdir "core") #t))
3357 (add-after 'enter-dir 'patch-makefile
3359 ;; on advice from the MAFFT authors, there is no need to
3360 ;; distribute mafft-profile, mafft-distance, or
3361 ;; mafft-homologs.rb as they are too "specialised".
3362 (substitute* "Makefile"
3363 ;; remove mafft-homologs.rb from SCRIPTS
3364 (("^SCRIPTS = mafft mafft-homologs.rb")
3366 ;; remove mafft-homologs from MANPAGES
3367 (("^MANPAGES = mafft.1 mafft-homologs.1")
3368 "MANPAGES = mafft.1")
3369 ;; remove mafft-distance from PROGS
3370 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3371 "PROGS = dvtditr dndfast7 dndblast sextet5")
3372 ;; remove mafft-profile from PROGS
3373 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3374 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3375 (("^rm -f mafft-profile mafft-profile.exe") "#")
3376 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3377 ;; do not install MAN pages in libexec folder
3378 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3379 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3381 (add-after 'enter-dir 'patch-paths
3382 (lambda* (#:key inputs #:allow-other-keys)
3383 (substitute* '("pairash.c"
3385 (("perl") (which "perl"))
3386 (("([\"`| ])awk" _ prefix)
3387 (string-append prefix (which "awk")))
3388 (("grep") (which "grep")))
3391 (add-after 'install 'wrap-programs
3392 (lambda* (#:key outputs #:allow-other-keys)
3393 (let* ((out (assoc-ref outputs "out"))
3394 (bin (string-append out "/bin"))
3395 (path (string-append
3396 (assoc-ref %build-inputs "coreutils") "/bin:")))
3397 (for-each (lambda (file)
3399 `("PATH" ":" prefix (,path))))
3407 ("coreutils" ,coreutils)))
3408 (home-page "http://mafft.cbrc.jp/alignment/software/")
3409 (synopsis "Multiple sequence alignment program")
3411 "MAFFT offers a range of multiple alignment methods for nucleotide and
3412 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3413 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3415 (license (license:non-copyleft
3416 "http://mafft.cbrc.jp/alignment/software/license.txt"
3417 "BSD-3 with different formatting"))))
3426 "https://github.com/marbl/mash/archive/v"
3428 (file-name (string-append name "-" version ".tar.gz"))
3431 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3432 (modules '((guix build utils)))
3434 ;; Delete bundled kseq.
3435 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3436 '(delete-file "src/mash/kseq.h"))))
3437 (build-system gnu-build-system)
3439 `(#:tests? #f ; No tests.
3442 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3443 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3444 #:make-flags (list "CC=gcc")
3446 (modify-phases %standard-phases
3447 (add-after 'unpack 'fix-includes
3449 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3450 (("^#include \"kseq\\.h\"")
3451 "#include \"htslib/kseq.h\""))
3453 (add-before 'configure 'autoconf
3454 (lambda _ (zero? (system* "autoconf")))))))
3456 `(("autoconf" ,autoconf)
3457 ;; Capnproto and htslib are statically embedded in the final
3458 ;; application. Therefore we also list their licenses, below.
3459 ("capnproto" ,capnproto)
3460 ("htslib" ,htslib)))
3464 (supported-systems '("x86_64-linux"))
3465 (home-page "https://mash.readthedocs.io")
3466 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3467 (description "Mash is a fast sequence distance estimator that uses the
3468 MinHash algorithm and is designed to work with genomes and metagenomes in the
3469 form of assemblies or reads.")
3470 (license (list license:bsd-3 ; Mash
3471 license:expat ; HTSlib and capnproto
3472 license:public-domain ; MurmurHash 3
3473 license:cpl1.0)))) ; Open Bloom Filter
3475 (define-public metabat
3483 (url "https://bitbucket.org/berkeleylab/metabat.git")
3484 (commit "d0ad65367ffc8e08d1a9dd1388d6170daa047e5c")))
3485 (file-name (string-append name "-" version "-checkout"))
3488 "1rlsrkz8iq8xah65222p055kzv5i3szz8bwysnvnh0pv72wvv6ww"))
3489 (patches (search-patches "metabat-remove-compilation-date.patch"
3490 "metabat-fix-compilation.patch"))))
3491 (build-system gnu-build-system)
3494 (modify-phases %standard-phases
3495 (add-after 'unpack 'fix-includes
3497 (substitute* "src/BamUtils.h"
3498 (("^#include \"bam/bam\\.h\"")
3499 "#include \"samtools/bam.h\"")
3500 (("^#include \"bam/sam\\.h\"")
3501 "#include \"samtools/sam.h\""))
3502 (substitute* "src/KseqReader.h"
3503 (("^#include \"bam/kseq\\.h\"")
3504 "#include \"htslib/kseq.h\""))
3506 (add-after 'unpack 'fix-scons
3507 (lambda* (#:key inputs #:allow-other-keys)
3508 (substitute* "SConstruct"
3509 (("^htslib_dir += 'samtools'")
3510 (string-append "htslib_dir = '"
3511 (assoc-ref inputs "htslib")
3513 (("^samtools_dir = 'samtools'")
3514 (string-append "samtools_dir = '"
3515 (assoc-ref inputs "samtools")
3517 (("^findStaticOrShared\\('bam', hts_lib")
3518 (string-append "findStaticOrShared('bam', '"
3519 (assoc-ref inputs "samtools")
3521 ;; Do not distribute README.
3522 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3526 (lambda* (#:key inputs outputs #:allow-other-keys)
3527 (mkdir (assoc-ref outputs "out"))
3528 (zero? (system* "scons"
3531 (assoc-ref outputs "out"))
3534 (assoc-ref inputs "boost"))
3536 ;; Check and install are carried out during build phase.
3538 (delete 'install))))
3542 ("samtools" ,samtools)
3546 `(("scons" ,scons)))
3547 (home-page "https://bitbucket.org/berkeleylab/metabat")
3549 "Reconstruction of single genomes from complex microbial communities")
3551 "Grouping large genomic fragments assembled from shotgun metagenomic
3552 sequences to deconvolute complex microbial communities, or metagenome binning,
3553 enables the study of individual organisms and their interactions. MetaBAT is
3554 an automated metagenome binning software, which integrates empirical
3555 probabilistic distances of genome abundance and tetranucleotide frequency.")
3556 ;; The source code contains inline assembly.
3557 (supported-systems '("x86_64-linux" "i686-linux"))
3558 (license (license:non-copyleft "file://license.txt"
3559 "See license.txt in the distribution."))))
3561 (define-public minced
3568 "https://github.com/ctSkennerton/minced/archive/"
3570 (file-name (string-append name "-" version ".tar.gz"))
3573 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3574 (build-system gnu-build-system)
3576 `(#:test-target "test"
3578 (modify-phases %standard-phases
3580 (add-before 'check 'fix-test
3582 ;; Fix test for latest version.
3583 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3584 (("minced:0.1.6") "minced:0.2.0"))
3586 (replace 'install ; No install target.
3587 (lambda* (#:key inputs outputs #:allow-other-keys)
3588 (let* ((out (assoc-ref outputs "out"))
3589 (bin (string-append out "/bin"))
3590 (wrapper (string-append bin "/minced")))
3591 ;; Minced comes with a wrapper script that tries to figure out where
3592 ;; it is located before running the JAR. Since these paths are known
3593 ;; to us, we build our own wrapper to avoid coreutils dependency.
3594 (install-file "minced.jar" bin)
3595 (with-output-to-file wrapper
3599 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3600 (assoc-ref inputs "jre") "/bin/java -jar "
3601 bin "/minced.jar \"$@\"\n"))))
3602 (chmod wrapper #o555)))))))
3604 `(("jdk" ,icedtea "jdk")))
3607 ("jre" ,icedtea "out")))
3608 (home-page "https://github.com/ctSkennerton/minced")
3609 (synopsis "Mining CRISPRs in Environmental Datasets")
3611 "MinCED is a program to find Clustered Regularly Interspaced Short
3612 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3613 unassembled metagenomic reads, but is mainly designed for full genomes and
3614 assembled metagenomic sequence.")
3615 (license license:gpl3+)))
3624 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3628 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3629 (modules '((guix build utils)))
3631 '(substitute* "setup.py"
3632 ;; Use setuptools, or else the executables are not
3634 (("distutils.core") "setuptools")
3635 ;; use "gcc" instead of "cc" for compilation
3637 "cc.set_executables(
3641 linker_so='gcc -shared'); defines")))))
3642 (build-system python-build-system)
3644 `(#:python ,python-2 ; only Python 2 is supported
3645 #:tests? #f)) ; no "test" target
3647 `(("samtools" ,samtools)
3648 ("python-numpy" ,python2-numpy)
3649 ("python-pysam" ,python2-pysam)
3650 ("python-scipy" ,python2-scipy)
3651 ("python-matplotlib" ,python2-matplotlib)))
3653 `(("python-mock" ,python2-mock) ;for tests
3654 ("python-pytz" ,python2-pytz))) ;for tests
3655 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3656 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3658 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3659 the expression level of alternatively spliced genes from RNA-Seq data, and
3660 identifies differentially regulated isoforms or exons across samples. By
3661 modeling the generative process by which reads are produced from isoforms in
3662 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3663 that a read originated from a particular isoform.")
3664 (license license:gpl2)))
3666 (define-public muscle
3669 (version "3.8.1551")
3671 (method url-fetch/tarbomb)
3673 "http://www.drive5.com/muscle/muscle_src_"
3677 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3678 (build-system gnu-build-system)
3680 `(#:make-flags (list "LDLIBS = -lm")
3682 (modify-phases %standard-phases
3685 ;; There are no tests, so just test if it runs.
3686 (lambda _ (zero? (system* "./muscle" "-version"))))
3688 (lambda* (#:key outputs #:allow-other-keys)
3689 (let* ((out (assoc-ref outputs "out"))
3690 (bin (string-append out "/bin")))
3691 (install-file "muscle" bin)))))))
3692 (home-page "http://www.drive5.com/muscle")
3693 (synopsis "Multiple sequence alignment program")
3695 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3696 program for nucleotide and protein sequences.")
3697 ;; License information found in 'muscle -h' and usage.cpp.
3698 (license license:public-domain)))
3700 (define-public newick-utils
3701 ;; There are no recent releases so we package from git.
3702 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3704 (name "newick-utils")
3705 (version (string-append "1.6-1." (string-take commit 8)))
3709 (url "https://github.com/tjunier/newick_utils.git")
3711 (file-name (string-append name "-" version "-checkout"))
3714 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3715 (build-system gnu-build-system)
3718 (modify-phases %standard-phases
3719 (add-after 'unpack 'autoconf
3720 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3722 ;; XXX: TODO: Enable Lua and Guile bindings.
3723 ;; https://github.com/tjunier/newick_utils/issues/13
3724 `(("libxml2" ,libxml2)
3728 `(("autoconf" ,autoconf)
3729 ("automake" ,automake)
3730 ("libtool" ,libtool)))
3731 (synopsis "Programs for working with newick format phylogenetic trees")
3733 "Newick-utils is a suite of utilities for processing phylogenetic trees
3734 in Newick format. Functions include re-rooting, extracting subtrees,
3735 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3736 (home-page "https://github.com/tjunier/newick_utils")
3737 (license license:bsd-3))))
3746 "https://github.com/wwood/OrfM/releases/download/v"
3747 version "/orfm-" version ".tar.gz"))
3750 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3751 (build-system gnu-build-system)
3752 (inputs `(("zlib" ,zlib)))
3754 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3755 ("ruby-rspec" ,ruby-rspec)
3757 (synopsis "Simple and not slow open reading frame (ORF) caller")
3759 "An ORF caller finds stretches of DNA that, when translated, are not
3760 interrupted by stop codons. OrfM finds and prints these ORFs.")
3761 (home-page "https://github.com/wwood/OrfM")
3762 (license license:lgpl3+)))
3764 (define-public pplacer
3765 (let ((commit "g807f6f3"))
3768 ;; The commit should be updated with each version change.
3769 (version "1.1.alpha19")
3773 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3775 (file-name (string-append name "-" version ".tar.gz"))
3777 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3778 (build-system ocaml-build-system)
3780 `(#:ocaml ,ocaml-4.01
3781 #:findlib ,ocaml4.01-findlib
3782 #:modules ((guix build ocaml-build-system)
3786 (modify-phases %standard-phases
3788 (add-after 'unpack 'replace-bundled-cddlib
3789 (lambda* (#:key inputs #:allow-other-keys)
3790 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3791 (local-dir "cddlib_guix"))
3793 (with-directory-excursion local-dir
3794 (system* "tar" "xvf" cddlib-src))
3795 (let ((cddlib-src-folder
3796 (string-append local-dir "/"
3797 (list-ref (scandir local-dir) 2)
3802 (string-append "cdd_src/" (basename file))))
3803 (find-files cddlib-src-folder ".*[ch]$")))
3805 (add-after 'unpack 'fix-makefile
3807 ;; Remove system calls to 'git'.
3808 (substitute* "Makefile"
3809 (("^DESCRIPT:=pplacer-.*")
3811 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3812 (substitute* "myocamlbuild.ml"
3813 (("git describe --tags --long .*\\\" with")
3815 "echo -n v" ,version "-" ,commit "\" with")))
3818 (lambda* (#:key outputs #:allow-other-keys)
3819 (let* ((out (assoc-ref outputs "out"))
3820 (bin (string-append out "/bin")))
3821 (copy-recursively "bin" bin))
3826 ("ocaml-ounit" ,ocaml4.01-ounit)
3827 ("ocaml-batteries" ,ocaml4.01-batteries)
3828 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3829 ("ocaml-csv" ,ocaml4.01-csv)
3830 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3831 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3832 ("ocaml-mcl" ,ocaml4.01-mcl)
3833 ("ocaml-gsl" ,ocaml4.01-gsl)
3834 ("cddlib-src" ,(package-source cddlib))))
3836 `(("pplacer-scripts" ,pplacer-scripts)))
3837 (synopsis "Phylogenetic placement of biological sequences")
3839 "Pplacer places query sequences on a fixed reference phylogenetic tree
3840 to maximize phylogenetic likelihood or posterior probability according to a
3841 reference alignment. Pplacer is designed to be fast, to give useful
3842 information about uncertainty, and to offer advanced visualization and
3843 downstream analysis.")
3844 (home-page "http://matsen.fhcrc.org/pplacer")
3845 (license license:gpl3))))
3847 ;; This package is installed alongside 'pplacer'. It is a separate package so
3848 ;; that it can use the python-build-system for the scripts that are
3849 ;; distributed alongside the main OCaml binaries.
3850 (define pplacer-scripts
3853 (name "pplacer-scripts")
3854 (build-system python-build-system)
3856 `(#:python ,python-2
3858 (modify-phases %standard-phases
3859 (add-after 'unpack 'enter-scripts-dir
3860 (lambda _ (chdir "scripts")))
3863 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3864 (add-after 'install 'wrap-executables
3865 (lambda* (#:key inputs outputs #:allow-other-keys)
3866 (let* ((out (assoc-ref outputs "out"))
3867 (bin (string-append out "/bin")))
3868 (let ((path (string-append
3869 (assoc-ref inputs "hmmer") "/bin:"
3870 (assoc-ref inputs "infernal") "/bin")))
3872 (wrap-program (string-append bin "/refpkg_align.py")
3873 `("PATH" ":" prefix (,path))))
3874 (let ((path (string-append
3875 (assoc-ref inputs "hmmer") "/bin")))
3876 (wrap-program (string-append bin "/hrefpkg_query.py")
3877 `("PATH" ":" prefix (,path)))))
3880 `(("infernal" ,infernal)
3883 `(("python-biopython" ,python2-biopython)
3884 ("taxtastic" ,taxtastic)))
3885 (synopsis "Pplacer Python scripts")))
3887 (define-public python2-pbcore
3889 (name "python2-pbcore")
3893 (uri (pypi-uri "pbcore" version))
3896 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3897 (build-system python-build-system)
3898 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3900 `(("python-cython" ,python2-cython)
3901 ("python-numpy" ,python2-numpy)
3902 ("python-pysam" ,python2-pysam)
3903 ("python-h5py" ,python2-h5py)))
3905 `(("python-nose" ,python2-nose)
3906 ("python-sphinx" ,python2-sphinx)
3907 ("python-pyxb" ,python2-pyxb)))
3908 (home-page "http://pacificbiosciences.github.io/pbcore/")
3909 (synopsis "Library for reading and writing PacBio data files")
3911 "The pbcore package provides Python APIs for interacting with PacBio data
3912 files and writing bioinformatics applications.")
3913 (license license:bsd-3)))
3915 (define-public python2-warpedlmm
3917 (name "python2-warpedlmm")
3923 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3927 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3928 (build-system python-build-system)
3930 `(#:python ,python-2)) ; requires Python 2.7
3932 `(("python-scipy" ,python2-scipy)
3933 ("python-numpy" ,python2-numpy)
3934 ("python-matplotlib" ,python2-matplotlib)
3935 ("python-fastlmm" ,python2-fastlmm)
3936 ("python-pandas" ,python2-pandas)
3937 ("python-pysnptools" ,python2-pysnptools)))
3939 `(("python-mock" ,python2-mock)
3940 ("python-nose" ,python2-nose)
3942 (home-page "https://github.com/PMBio/warpedLMM")
3943 (synopsis "Implementation of warped linear mixed models")
3945 "WarpedLMM is a Python implementation of the warped linear mixed model,
3946 which automatically learns an optimal warping function (or transformation) for
3947 the phenotype as it models the data.")
3948 (license license:asl2.0)))
3950 (define-public pbtranscript-tofu
3951 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3953 (name "pbtranscript-tofu")
3954 (version (string-append "2.2.3." (string-take commit 7)))
3958 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3960 (file-name (string-append name "-" version "-checkout"))
3963 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3964 (modules '((guix build utils)))
3967 ;; remove bundled Cython sources
3968 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3970 (build-system python-build-system)
3972 `(#:python ,python-2
3973 ;; FIXME: Tests fail with "No such file or directory:
3974 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3977 (modify-phases %standard-phases
3978 (add-after 'unpack 'enter-directory
3980 (chdir "pbtranscript-tofu/pbtranscript/")
3982 ;; With setuptools version 18.0 and later this setup.py hack causes
3983 ;; a build error, so we disable it.
3984 (add-after 'enter-directory 'patch-setuppy
3986 (substitute* "setup.py"
3987 (("if 'setuptools.extension' in sys.modules:")
3991 `(("python-numpy" ,python2-numpy)
3992 ("python-bx-python" ,python2-bx-python)
3993 ("python-networkx" ,python2-networkx)
3994 ("python-scipy" ,python2-scipy)
3995 ("python-pbcore" ,python2-pbcore)
3996 ("python-h5py" ,python2-h5py)))
3998 `(("python-cython" ,python2-cython)
3999 ("python-nose" ,python2-nose)))
4000 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4001 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4003 "pbtranscript-tofu contains scripts to analyze transcriptome data
4004 generated using the PacBio Iso-Seq protocol.")
4005 (license license:bsd-3))))
4007 (define-public prank
4014 "http://wasabiapp.org/download/prank/prank.source."
4018 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4019 (build-system gnu-build-system)
4022 (modify-phases %standard-phases
4023 (add-after 'unpack 'enter-src-dir
4027 (add-after 'unpack 'remove-m64-flag
4028 ;; Prank will build with the correct 'bit-ness' without this flag
4029 ;; and this allows building on 32-bit machines.
4030 (lambda _ (substitute* "src/Makefile"
4035 (lambda* (#:key outputs #:allow-other-keys)
4036 (let* ((out (assoc-ref outputs "out"))
4037 (bin (string-append out "/bin"))
4038 (man (string-append out "/share/man/man1"))
4039 (path (string-append
4040 (assoc-ref %build-inputs "mafft") "/bin:"
4041 (assoc-ref %build-inputs "exonerate") "/bin:"
4042 (assoc-ref %build-inputs "bppsuite") "/bin")))
4043 (install-file "prank" bin)
4044 (wrap-program (string-append bin "/prank")
4045 `("PATH" ":" prefix (,path)))
4046 (install-file "prank.1" man))
4050 ("exonerate" ,exonerate)
4051 ("bppsuite" ,bppsuite)))
4052 (home-page "http://wasabiapp.org/software/prank/")
4053 (synopsis "Probabilistic multiple sequence alignment program")
4055 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4056 codon and amino-acid sequences. It is based on a novel algorithm that treats
4057 insertions correctly and avoids over-estimation of the number of deletion
4058 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4059 in phylogenetics and correctly takes into account the evolutionary distances
4060 between sequences. Lastly, PRANK allows for defining a potential structure
4061 for sequences to be aligned and then, simultaneously with the alignment,
4062 predicts the locations of structural units in the sequences.")
4063 (license license:gpl2+)))
4065 (define-public proteinortho
4067 (name "proteinortho")
4074 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4075 version "_src.tar.gz"))
4078 "0z4f5cg0cs8ai62hfvp4q6w66q2phcc55nhs4xj5cyhxxivjv2ai"))))
4079 (build-system gnu-build-system)
4081 `(#:test-target "test"
4083 (modify-phases %standard-phases
4085 ;; There is no configure script, so we modify the Makefile directly.
4086 (lambda* (#:key outputs #:allow-other-keys)
4087 (substitute* "Makefile"
4090 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4092 (add-before 'install 'make-install-directory
4093 ;; The install directory is not created during 'make install'.
4094 (lambda* (#:key outputs #:allow-other-keys)
4095 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4097 (add-after 'install 'wrap-programs
4098 (lambda* (#:key inputs outputs #:allow-other-keys)
4099 (let* ((path (getenv "PATH"))
4100 (out (assoc-ref outputs "out"))
4101 (binary (string-append out "/bin/proteinortho5.pl")))
4102 (wrap-program binary `("PATH" ":" prefix (,path))))
4106 ("python" ,python-2)
4107 ("blast+" ,blast+)))
4108 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4109 (synopsis "Detect orthologous genes across species")
4111 "Proteinortho is a tool to detect orthologous genes across different
4112 species. For doing so, it compares similarities of given gene sequences and
4113 clusters them to find significant groups. The algorithm was designed to handle
4114 large-scale data and can be applied to hundreds of species at once.")
4115 (license license:gpl2+)))
4117 (define-public pyicoteo
4124 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4125 "pyicoteo/get/v" version ".tar.bz2"))
4126 (file-name (string-append name "-" version ".tar.bz2"))
4129 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4130 (build-system python-build-system)
4132 `(#:python ,python-2 ; does not work with Python 3
4133 #:tests? #f)) ; there are no tests
4135 `(("python2-matplotlib" ,python2-matplotlib)))
4136 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4137 (synopsis "Analyze high-throughput genetic sequencing data")
4139 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4140 sequencing data. It works with genomic coordinates. There are currently six
4141 different command-line tools:
4144 @item pyicoregion: for generating exploratory regions automatically;
4145 @item pyicoenrich: for differential enrichment between two conditions;
4146 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4147 @item pyicos: for genomic coordinates manipulation;
4148 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4149 @item pyicount: to count how many reads from N experiment files overlap in a
4151 @item pyicotrocol: to combine operations from pyicoteo.
4153 (license license:gpl3+)))
4155 (define-public prodigal
4162 "https://github.com/hyattpd/Prodigal/archive/v"
4164 (file-name (string-append name "-" version ".tar.gz"))
4167 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4168 (build-system gnu-build-system)
4170 `(#:tests? #f ;no check target
4171 #:make-flags (list (string-append "INSTALLDIR="
4172 (assoc-ref %outputs "out")
4175 (modify-phases %standard-phases
4176 (delete 'configure))))
4177 (home-page "http://prodigal.ornl.gov")
4178 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4180 "Prodigal runs smoothly on finished genomes, draft genomes, and
4181 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4182 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4183 partial genes, and identifies translation initiation sites.")
4184 (license license:gpl3+)))
4186 (define-public roary
4194 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4198 "03dfr2cd5fp80bcr65923zpdzrasvcxl7c2vgh8373v25a1yfap7"))))
4199 (build-system perl-build-system)
4202 (modify-phases %standard-phases
4207 ;; The tests are not run by default, so we run each test file
4209 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4211 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4212 (getenv "PERL5LIB")))
4213 (zero? (length (filter (lambda (file)
4214 (display file)(display "\n")
4215 (not (zero? (system* "perl" file))))
4216 (find-files "t" ".*\\.t$"))))))
4218 ;; There is no 'install' target in the Makefile.
4219 (lambda* (#:key outputs #:allow-other-keys)
4220 (let* ((out (assoc-ref outputs "out"))
4221 (bin (string-append out "/bin"))
4222 (perl (string-append out "/lib/perl5/site_perl"))
4223 (roary-plots "contrib/roary_plots"))
4226 (copy-recursively "bin" bin)
4227 (copy-recursively "lib" perl)
4229 (add-after 'install 'wrap-programs
4230 (lambda* (#:key inputs outputs #:allow-other-keys)
4231 (let* ((out (assoc-ref outputs "out"))
4232 (perl5lib (getenv "PERL5LIB"))
4233 (path (getenv "PATH")))
4234 (for-each (lambda (prog)
4235 (let ((binary (string-append out "/" prog)))
4236 (wrap-program binary
4237 `("PERL5LIB" ":" prefix
4238 (,(string-append perl5lib ":" out
4239 "/lib/perl5/site_perl"))))
4240 (wrap-program binary
4242 (,(string-append path ":" out "/bin"))))))
4243 (find-files "bin" ".*[^R]$"))
4245 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4246 (r-site-lib (getenv "R_LIBS_SITE"))
4248 (string-append (assoc-ref inputs "coreutils") "/bin")))
4250 `("R_LIBS_SITE" ":" prefix
4251 (,(string-append r-site-lib ":" out "/site-library/"))))
4254 (,(string-append coreutils-path ":" out "/bin"))))))
4257 `(("perl-env-path" ,perl-env-path)
4258 ("perl-test-files" ,perl-test-files)
4259 ("perl-test-most" ,perl-test-most)
4260 ("perl-test-output" ,perl-test-output)))
4262 `(("perl-array-utils" ,perl-array-utils)
4263 ("bioperl" ,bioperl-minimal)
4264 ("perl-exception-class" ,perl-exception-class)
4265 ("perl-file-find-rule" ,perl-file-find-rule)
4266 ("perl-file-grep" ,perl-file-grep)
4267 ("perl-file-slurper" ,perl-file-slurper)
4268 ("perl-file-which" ,perl-file-which)
4269 ("perl-graph" ,perl-graph)
4270 ("perl-graph-readwrite" ,perl-graph-readwrite)
4271 ("perl-log-log4perl" ,perl-log-log4perl)
4272 ("perl-moose" ,perl-moose)
4273 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4274 ("perl-text-csv" ,perl-text-csv)
4275 ("bedtools" ,bedtools)
4279 ("parallel" ,parallel)
4282 ("fasttree" ,fasttree)
4286 ("r-minimal" ,r-minimal)
4287 ("r-ggplot2" ,r-ggplot2)
4288 ("coreutils" ,coreutils)))
4289 (home-page "http://sanger-pathogens.github.io/Roary")
4290 (synopsis "High speed stand-alone pan genome pipeline")
4292 "Roary is a high speed stand alone pan genome pipeline, which takes
4293 annotated assemblies in GFF3 format (produced by the Prokka program) and
4294 calculates the pan genome. Using a standard desktop PC, it can analyse
4295 datasets with thousands of samples, without compromising the quality of the
4296 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4297 single processor. Roary is not intended for metagenomics or for comparing
4298 extremely diverse sets of genomes.")
4299 (license license:gpl3)))
4301 (define-public raxml
4310 "https://github.com/stamatak/standard-RAxML/archive/v"
4312 (file-name (string-append name "-" version ".tar.gz"))
4315 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4316 (build-system gnu-build-system)
4318 `(#:tests? #f ; There are no tests.
4319 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4320 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4322 (modify-phases %standard-phases
4325 (lambda* (#:key outputs #:allow-other-keys)
4326 (let* ((out (assoc-ref outputs "out"))
4327 (bin (string-append out "/bin"))
4328 (executable "raxmlHPC-HYBRID"))
4329 (install-file executable bin)
4330 (symlink (string-append bin "/" executable) "raxml"))
4333 `(("openmpi" ,openmpi)))
4334 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4335 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4337 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4339 ;; The source includes x86 specific code
4340 (supported-systems '("x86_64-linux" "i686-linux"))
4341 (license license:gpl2+)))
4351 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4354 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4355 (patches (search-patches "rsem-makefile.patch"))
4356 (modules '((guix build utils)))
4359 ;; remove bundled copy of boost
4360 (delete-file-recursively "boost")
4362 (build-system gnu-build-system)
4364 `(#:tests? #f ;no "check" target
4366 (modify-phases %standard-phases
4367 ;; No "configure" script.
4368 ;; Do not build bundled samtools library.
4371 (substitute* "Makefile"
4372 (("^all : sam/libbam.a") "all : "))
4375 (lambda* (#:key outputs #:allow-other-keys)
4376 (let* ((out (string-append (assoc-ref outputs "out")))
4377 (bin (string-append out "/bin/"))
4378 (perl (string-append out "/lib/perl5/site_perl")))
4381 (for-each (lambda (file)
4382 (install-file file bin))
4383 (find-files "." "rsem-.*"))
4384 (install-file "rsem_perl_utils.pm" perl))
4387 'install 'wrap-program
4388 (lambda* (#:key outputs #:allow-other-keys)
4389 (let ((out (assoc-ref outputs "out")))
4390 (for-each (lambda (prog)
4391 (wrap-program (string-append out "/bin/" prog)
4392 `("PERL5LIB" ":" prefix
4393 (,(string-append out "/lib/perl5/site_perl")))))
4394 '("rsem-plot-transcript-wiggles"
4395 "rsem-calculate-expression"
4396 "rsem-generate-ngvector"
4398 "rsem-prepare-reference")))
4402 ("ncurses" ,ncurses)
4403 ("r-minimal" ,r-minimal)
4405 ("samtools" ,samtools-0.1)
4407 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4408 (synopsis "Estimate gene expression levels from RNA-Seq data")
4410 "RSEM is a software package for estimating gene and isoform expression
4411 levels from RNA-Seq data. The RSEM package provides a user-friendly
4412 interface, supports threads for parallel computation of the EM algorithm,
4413 single-end and paired-end read data, quality scores, variable-length reads and
4414 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4415 interval estimates for expression levels. For visualization, it can generate
4416 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4417 (license license:gpl3+)))
4419 (define-public rseqc
4427 (string-append "mirror://sourceforge/rseqc/"
4428 "RSeQC-" version ".tar.gz"))
4430 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4431 (modules '((guix build utils)))
4434 ;; remove bundled copy of pysam
4435 (delete-file-recursively "lib/pysam")
4436 (substitute* "setup.py"
4437 ;; remove dependency on outdated "distribute" module
4438 (("^from distribute_setup import use_setuptools") "")
4439 (("^use_setuptools\\(\\)") "")
4440 ;; do not use bundled copy of pysam
4441 (("^have_pysam = False") "have_pysam = True"))))))
4442 (build-system python-build-system)
4443 (arguments `(#:python ,python-2))
4445 `(("python-cython" ,python2-cython)
4446 ("python-pysam" ,python2-pysam)
4447 ("python-numpy" ,python2-numpy)
4450 `(("python-nose" ,python2-nose)))
4451 (home-page "http://rseqc.sourceforge.net/")
4452 (synopsis "RNA-seq quality control package")
4454 "RSeQC provides a number of modules that can comprehensively evaluate
4455 high throughput sequence data, especially RNA-seq data. Some basic modules
4456 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4457 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4458 distribution, coverage uniformity, strand specificity, etc.")
4459 (license license:gpl3+)))
4462 ;; There are no release tarballs. According to the installation
4463 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4464 ;; stable release is identified by this changeset ID.
4465 (let ((changeset "2329130")
4469 (version (string-append "0-" revision "." changeset))
4473 (url "https://bitbucket.org/libsleipnir/sleipnir")
4474 (changeset changeset)))
4477 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4478 (build-system gnu-build-system)
4480 `(#:modules ((srfi srfi-1)
4481 (guix build gnu-build-system)
4484 (let ((dirs '("SeekMiner"
4490 (modify-phases %standard-phases
4491 (add-before 'configure 'bootstrap
4493 (zero? (system* "bash" "gen_auto"))))
4494 (add-after 'build 'build-additional-tools
4495 (lambda* (#:key make-flags #:allow-other-keys)
4496 (every (lambda (dir)
4497 (with-directory-excursion (string-append "tools/" dir)
4498 (zero? (apply system* "make" make-flags))))
4500 (add-after 'install 'install-additional-tools
4501 (lambda* (#:key make-flags #:allow-other-keys)
4502 (fold (lambda (dir result)
4503 (with-directory-excursion (string-append "tools/" dir)
4505 (zero? (apply system*
4506 `("make" ,@make-flags "install"))))))
4512 ("readline" ,readline)
4513 ("gengetopt" ,gengetopt)
4514 ("log4cpp" ,log4cpp)))
4516 `(("autoconf" ,autoconf)
4517 ("automake" ,automake)
4519 (home-page "http://seek.princeton.edu")
4520 (synopsis "Gene co-expression search engine")
4522 "SEEK is a computational gene co-expression search engine. SEEK provides
4523 biologists with a way to navigate the massive human expression compendium that
4524 now contains thousands of expression datasets. SEEK returns a robust ranking
4525 of co-expressed genes in the biological area of interest defined by the user's
4526 query genes. It also prioritizes thousands of expression datasets according
4527 to the user's query of interest.")
4528 (license license:cc-by3.0))))
4530 (define-public samtools
4538 (string-append "mirror://sourceforge/samtools/samtools/"
4539 version "/samtools-" version ".tar.bz2"))
4542 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4543 (build-system gnu-build-system)
4545 `(#:modules ((ice-9 ftw)
4547 (guix build gnu-build-system)
4549 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4550 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4552 (modify-phases %standard-phases
4553 (add-after 'unpack 'patch-tests
4555 (substitute* "test/test.pl"
4556 ;; The test script calls out to /bin/bash
4557 (("/bin/bash") (which "bash")))
4559 (add-after 'install 'install-library
4560 (lambda* (#:key outputs #:allow-other-keys)
4561 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4562 (install-file "libbam.a" lib)
4564 (add-after 'install 'install-headers
4565 (lambda* (#:key outputs #:allow-other-keys)
4566 (let ((include (string-append (assoc-ref outputs "out")
4567 "/include/samtools/")))
4568 (for-each (lambda (file)
4569 (install-file file include))
4570 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4572 (native-inputs `(("pkg-config" ,pkg-config)))
4574 `(("htslib" ,htslib)
4575 ("ncurses" ,ncurses)
4579 (home-page "http://samtools.sourceforge.net")
4580 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4582 "Samtools implements various utilities for post-processing nucleotide
4583 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4584 variant calling (in conjunction with bcftools), and a simple alignment
4586 (license license:expat)))
4588 (define-public samtools-0.1
4589 ;; This is the most recent version of the 0.1 line of samtools. The input
4590 ;; and output formats differ greatly from that used and produced by samtools
4591 ;; 1.x and is still used in many bioinformatics pipelines.
4592 (package (inherit samtools)
4598 (string-append "mirror://sourceforge/samtools/samtools/"
4599 version "/samtools-" version ".tar.bz2"))
4601 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4603 `(#:tests? #f ;no "check" target
4604 ,@(substitute-keyword-arguments (package-arguments samtools)
4605 ((#:make-flags flags)
4606 `(cons "LIBCURSES=-lncurses" ,flags))
4608 `(modify-phases ,phases
4610 (lambda* (#:key outputs #:allow-other-keys)
4611 (let ((bin (string-append
4612 (assoc-ref outputs "out") "/bin")))
4614 (install-file "samtools" bin)
4616 (delete 'patch-tests)
4617 (delete 'configure))))))))
4619 (define-public mosaik
4620 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4625 ;; There are no release tarballs nor tags.
4628 (url "https://github.com/wanpinglee/MOSAIK.git")
4630 (file-name (string-append name "-" version))
4633 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4634 (build-system gnu-build-system)
4636 `(#:tests? #f ; no tests
4637 #:make-flags (list "CC=gcc")
4639 (modify-phases %standard-phases
4641 (lambda _ (chdir "src") #t))
4643 (lambda* (#:key outputs #:allow-other-keys)
4644 (let ((bin (string-append (assoc-ref outputs "out")
4647 (copy-recursively "../bin" bin)
4652 (supported-systems '("x86_64-linux"))
4653 (home-page "https://github.com/wanpinglee/MOSAIK")
4654 (synopsis "Map nucleotide sequence reads to reference genomes")
4656 "MOSAIK is a program for mapping second and third-generation sequencing
4657 reads to a reference genome. MOSAIK can align reads generated by all the
4658 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4659 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4660 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4661 ;; code released into the public domain:
4662 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4663 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4664 (license (list license:gpl2+ license:public-domain)))))
4666 (define-public ngs-sdk
4674 (string-append "https://github.com/ncbi/ngs/archive/"
4676 (file-name (string-append name "-" version ".tar.gz"))
4679 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4680 (build-system gnu-build-system)
4682 `(#:parallel-build? #f ; not supported
4683 #:tests? #f ; no "check" target
4687 (lambda* (#:key outputs #:allow-other-keys)
4688 (let ((out (assoc-ref outputs "out")))
4689 ;; Allow 'konfigure.perl' to find 'package.prl'.
4691 (string-append ".:" (getenv "PERL5LIB")))
4693 ;; The 'configure' script doesn't recognize things like
4694 ;; '--enable-fast-install'.
4695 (zero? (system* "./configure"
4696 (string-append "--build-prefix=" (getcwd) "/build")
4697 (string-append "--prefix=" out)))))
4700 (lambda _ (chdir "ngs-sdk") #t)
4701 %standard-phases))))
4702 (native-inputs `(("perl" ,perl)))
4703 ;; According to the test
4704 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4705 ;; in ngs-sdk/setup/konfigure.perl
4706 (supported-systems '("i686-linux" "x86_64-linux"))
4707 (home-page "https://github.com/ncbi/ngs")
4708 (synopsis "API for accessing Next Generation Sequencing data")
4710 "NGS is a domain-specific API for accessing reads, alignments and pileups
4711 produced from Next Generation Sequencing. The API itself is independent from
4712 any particular back-end implementation, and supports use of multiple back-ends
4714 (license license:public-domain)))
4716 (define-public java-ngs
4717 (package (inherit ngs-sdk)
4720 `(,@(substitute-keyword-arguments
4721 `(#:modules ((guix build gnu-build-system)
4725 ,@(package-arguments ngs-sdk))
4727 `(modify-phases ,phases
4728 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4730 `(("jdk" ,icedtea "jdk")
4731 ("ngs-sdk" ,ngs-sdk)))
4732 (synopsis "Java bindings for NGS SDK")))
4734 (define-public ncbi-vdb
4742 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4744 (file-name (string-append name "-" version ".tar.gz"))
4747 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4748 (build-system gnu-build-system)
4750 `(#:parallel-build? #f ; not supported
4751 #:tests? #f ; no "check" target
4753 (modify-phases %standard-phases
4755 (lambda* (#:key inputs outputs #:allow-other-keys)
4756 (let ((out (assoc-ref outputs "out")))
4757 ;; Override include path for libmagic
4758 (substitute* "setup/package.prl"
4759 (("name => 'magic', Include => '/usr/include'")
4760 (string-append "name=> 'magic', Include => '"
4761 (assoc-ref inputs "libmagic")
4764 ;; Install kdf5 library (needed by sra-tools)
4765 (substitute* "build/Makefile.install"
4766 (("LIBRARIES_TO_INSTALL =")
4767 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4769 (substitute* "build/Makefile.env"
4770 (("CFLAGS =" prefix)
4771 (string-append prefix "-msse2 ")))
4773 ;; Override search path for ngs-java
4774 (substitute* "setup/package.prl"
4775 (("/usr/local/ngs/ngs-java")
4776 (assoc-ref inputs "java-ngs")))
4778 ;; The 'configure' script doesn't recognize things like
4779 ;; '--enable-fast-install'.
4782 (string-append "--build-prefix=" (getcwd) "/build")
4783 (string-append "--prefix=" (assoc-ref outputs "out"))
4784 (string-append "--debug")
4785 (string-append "--with-xml2-prefix="
4786 (assoc-ref inputs "libxml2"))
4787 (string-append "--with-ngs-sdk-prefix="
4788 (assoc-ref inputs "ngs-sdk"))
4789 (string-append "--with-hdf5-prefix="
4790 (assoc-ref inputs "hdf5")))))))
4791 (add-after 'install 'install-interfaces
4792 (lambda* (#:key outputs #:allow-other-keys)
4793 ;; Install interface libraries. On i686 the interface libraries
4794 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4795 ;; architecture name ("i386") instead of the target system prefix
4797 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4798 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4799 ,(system->linux-architecture
4800 (or (%current-target-system)
4803 (string-append (assoc-ref outputs "out")
4805 ;; Install interface headers
4806 (copy-recursively "interfaces"
4807 (string-append (assoc-ref outputs "out")
4810 ;; These files are needed by sra-tools.
4811 (add-after 'install 'install-configuration-files
4812 (lambda* (#:key outputs #:allow-other-keys)
4813 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4815 (install-file "libs/kfg/default.kfg" target)
4816 (install-file "libs/kfg/certs.kfg" target))
4819 `(("libxml2" ,libxml2)
4820 ("ngs-sdk" ,ngs-sdk)
4821 ("java-ngs" ,java-ngs)
4824 (native-inputs `(("perl" ,perl)))
4825 ;; NCBI-VDB requires SSE capability.
4826 (supported-systems '("i686-linux" "x86_64-linux"))
4827 (home-page "https://github.com/ncbi/ncbi-vdb")
4828 (synopsis "Database engine for genetic information")
4830 "The NCBI-VDB library implements a highly compressed columnar data
4831 warehousing engine that is most often used to store genetic information.
4832 Databases are stored in a portable image within the file system, and can be
4833 accessed/downloaded on demand across HTTP.")
4834 (license license:public-domain)))
4836 (define-public plink
4844 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4845 version "-src.zip"))
4847 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4848 (patches (search-patches "plink-1.07-unclobber-i.patch"
4849 "plink-endian-detection.patch"))))
4850 (build-system gnu-build-system)
4852 '(#:tests? #f ;no "check" target
4853 #:make-flags (list (string-append "LIB_LAPACK="
4854 (assoc-ref %build-inputs "lapack")
4855 "/lib/liblapack.so")
4858 ;; disable phoning home
4861 (modify-phases %standard-phases
4862 ;; no "configure" script
4865 (lambda* (#:key outputs #:allow-other-keys)
4866 (let ((bin (string-append (assoc-ref outputs "out")
4868 (install-file "plink" bin)
4872 ("lapack" ,lapack)))
4874 `(("unzip" ,unzip)))
4875 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4876 (synopsis "Whole genome association analysis toolset")
4878 "PLINK is a whole genome association analysis toolset, designed to
4879 perform a range of basic, large-scale analyses in a computationally efficient
4880 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4881 so there is no support for steps prior to this (e.g. study design and
4882 planning, generating genotype or CNV calls from raw data). Through
4883 integration with gPLINK and Haploview, there is some support for the
4884 subsequent visualization, annotation and storage of results.")
4885 ;; Code is released under GPLv2, except for fisher.h, which is under
4887 (license (list license:gpl2 license:lgpl2.1+))))
4889 (define-public smithlab-cpp
4890 (let ((revision "1")
4891 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4893 (name "smithlab-cpp")
4894 (version (string-append "0." revision "." (string-take commit 7)))
4898 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4900 (file-name (string-append name "-" version "-checkout"))
4903 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4904 (build-system gnu-build-system)
4906 `(#:modules ((guix build gnu-build-system)
4909 #:tests? #f ;no "check" target
4911 (modify-phases %standard-phases
4912 (add-after 'unpack 'use-samtools-headers
4914 (substitute* '("SAM.cpp"
4916 (("sam.h") "samtools/sam.h"))
4919 (lambda* (#:key outputs #:allow-other-keys)
4920 (let* ((out (assoc-ref outputs "out"))
4921 (lib (string-append out "/lib"))
4922 (include (string-append out "/include/smithlab-cpp")))
4925 (for-each (cut install-file <> lib)
4926 (find-files "." "\\.o$"))
4927 (for-each (cut install-file <> include)
4928 (find-files "." "\\.hpp$")))
4930 (delete 'configure))))
4932 `(("samtools" ,samtools-0.1)
4934 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4935 (synopsis "C++ helper library for functions used in Smith lab projects")
4937 "Smithlab CPP is a C++ library that includes functions used in many of
4938 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4939 structures, classes for genomic regions, mapped sequencing reads, etc.")
4940 (license license:gpl3+))))
4942 (define-public preseq
4948 (uri (string-append "https://github.com/smithlabcode/"
4949 "preseq/archive/v" version ".tar.gz"))
4950 (file-name (string-append name "-" version ".tar.gz"))
4952 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4953 (modules '((guix build utils)))
4955 ;; Remove bundled samtools.
4956 '(delete-file-recursively "samtools"))))
4957 (build-system gnu-build-system)
4959 `(#:tests? #f ;no "check" target
4961 (modify-phases %standard-phases
4962 (delete 'configure))
4964 (list (string-append "PREFIX="
4965 (assoc-ref %outputs "out"))
4966 (string-append "LIBBAM="
4967 (assoc-ref %build-inputs "samtools")
4969 (string-append "SMITHLAB_CPP="
4970 (assoc-ref %build-inputs "smithlab-cpp")
4973 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4976 ("samtools" ,samtools-0.1)
4977 ("smithlab-cpp" ,smithlab-cpp)
4979 (home-page "http://smithlabresearch.org/software/preseq/")
4980 (synopsis "Program for analyzing library complexity")
4982 "The preseq package is aimed at predicting and estimating the complexity
4983 of a genomic sequencing library, equivalent to predicting and estimating the
4984 number of redundant reads from a given sequencing depth and how many will be
4985 expected from additional sequencing using an initial sequencing experiment.
4986 The estimates can then be used to examine the utility of further sequencing,
4987 optimize the sequencing depth, or to screen multiple libraries to avoid low
4988 complexity samples.")
4989 (license license:gpl3+)))
4991 (define-public python-screed
4993 (name "python-screed")
4998 (uri (pypi-uri "screed" version))
5001 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5002 (build-system python-build-system)
5005 (modify-phases %standard-phases
5008 (setenv "PYTHONPATH"
5009 (string-append (getenv "PYTHONPATH") ":."))
5010 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5012 `(("python-nose" ,python-nose)))
5014 `(("python-bz2file" ,python-bz2file)))
5015 (home-page "https://github.com/dib-lab/screed/")
5016 (synopsis "Short read sequence database utilities")
5017 (description "Screed parses FASTA and FASTQ files and generates databases.
5018 Values such as sequence name, sequence description, sequence quality and the
5019 sequence itself can be retrieved from these databases.")
5020 (license license:bsd-3)))
5022 (define-public python2-screed
5023 (package-with-python2 python-screed))
5025 (define-public sra-tools
5033 (string-append "https://github.com/ncbi/sra-tools/archive/"
5035 (file-name (string-append name "-" version ".tar.gz"))
5038 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5039 (build-system gnu-build-system)
5041 `(#:parallel-build? #f ; not supported
5042 #:tests? #f ; no "check" target
5044 (list (string-append "DEFAULT_CRT="
5045 (assoc-ref %build-inputs "ncbi-vdb")
5047 (string-append "DEFAULT_KFG="
5048 (assoc-ref %build-inputs "ncbi-vdb")
5050 (string-append "VDB_LIBDIR="
5051 (assoc-ref %build-inputs "ncbi-vdb")
5052 ,(if (string-prefix? "x86_64"
5053 (or (%current-target-system)
5058 (modify-phases %standard-phases
5060 (lambda* (#:key inputs outputs #:allow-other-keys)
5061 ;; The build system expects a directory containing the sources and
5062 ;; raw build output of ncbi-vdb, including files that are not
5063 ;; installed. Since we are building against an installed version of
5064 ;; ncbi-vdb, the following modifications are needed.
5065 (substitute* "setup/konfigure.perl"
5066 ;; Make the configure script look for the "ilib" directory of
5067 ;; "ncbi-vdb" without first checking for the existence of a
5068 ;; matching library in its "lib" directory.
5069 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5070 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5071 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5072 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5073 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5076 (substitute* "tools/copycat/Makefile"
5077 (("smagic-static") "lmagic"))
5079 ;; The 'configure' script doesn't recognize things like
5080 ;; '--enable-fast-install'.
5083 (string-append "--build-prefix=" (getcwd) "/build")
5084 (string-append "--prefix=" (assoc-ref outputs "out"))
5085 (string-append "--debug")
5086 (string-append "--with-fuse-prefix="
5087 (assoc-ref inputs "fuse"))
5088 (string-append "--with-magic-prefix="
5089 (assoc-ref inputs "libmagic"))
5090 ;; TODO: building with libxml2 fails with linker errors
5091 ;; (string-append "--with-xml2-prefix="
5092 ;; (assoc-ref inputs "libxml2"))
5093 (string-append "--with-ncbi-vdb-sources="
5094 (assoc-ref inputs "ncbi-vdb"))
5095 (string-append "--with-ncbi-vdb-build="
5096 (assoc-ref inputs "ncbi-vdb"))
5097 (string-append "--with-ngs-sdk-prefix="
5098 (assoc-ref inputs "ngs-sdk"))
5099 (string-append "--with-hdf5-prefix="
5100 (assoc-ref inputs "hdf5"))))))
5101 ;; This version of sra-tools fails to build with glibc because of a
5102 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5103 ;; contains a definition of "canonicalize", so we rename it.
5105 ;; See upstream bug report:
5106 ;; https://github.com/ncbi/sra-tools/issues/67
5107 (add-after 'unpack 'patch-away-glibc-conflict
5109 (substitute* "tools/bam-loader/bam.c"
5110 (("canonicalize\\(" line)
5111 (string-append "sra_tools_" line)))
5113 (native-inputs `(("perl" ,perl)))
5115 `(("ngs-sdk" ,ngs-sdk)
5116 ("ncbi-vdb" ,ncbi-vdb)
5121 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5122 (synopsis "Tools and libraries for reading and writing sequencing data")
5124 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5125 reading of sequencing files from the Sequence Read Archive (SRA) database and
5126 writing files into the .sra format.")
5127 (license license:public-domain)))
5129 (define-public seqan
5135 (uri (string-append "http://packages.seqan.de/seqan-library/"
5136 "seqan-library-" version ".tar.bz2"))
5139 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5140 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5141 ;; makes sense to split the outputs.
5142 (outputs '("out" "doc"))
5143 (build-system trivial-build-system)
5145 `(#:modules ((guix build utils))
5148 (use-modules (guix build utils))
5149 (let ((tar (assoc-ref %build-inputs "tar"))
5150 (bzip (assoc-ref %build-inputs "bzip2"))
5151 (out (assoc-ref %outputs "out"))
5152 (doc (assoc-ref %outputs "doc")))
5153 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5154 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5155 (chdir (string-append "seqan-library-" ,version))
5156 (copy-recursively "include" (string-append out "/include"))
5157 (copy-recursively "share" (string-append doc "/share"))))))
5159 `(("source" ,source)
5162 (home-page "http://www.seqan.de")
5163 (synopsis "Library for nucleotide sequence analysis")
5165 "SeqAn is a C++ library of efficient algorithms and data structures for
5166 the analysis of sequences with the focus on biological data. It contains
5167 algorithms and data structures for string representation and their
5168 manipulation, online and indexed string search, efficient I/O of
5169 bioinformatics file formats, sequence alignment, and more.")
5170 (license license:bsd-3)))
5172 (define-public seqmagick
5180 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5184 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5185 (build-system python-build-system)
5187 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5188 `(#:python ,python-2
5190 (modify-phases %standard-phases
5191 ;; Current test in setup.py does not work as of 0.6.1,
5192 ;; so use nose to run tests instead for now. See
5193 ;; https://github.com/fhcrc/seqmagick/issues/55
5194 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5196 ;; biopython-1.66 is required due to
5197 ;; https://github.com/fhcrc/seqmagick/issues/59
5198 ;; When that issue is resolved the 'python2-biopython-1.66' package
5199 ;; should be removed.
5200 `(("python-biopython" ,python2-biopython-1.66)))
5202 `(("python-nose" ,python2-nose)))
5203 (home-page "https://github.com/fhcrc/seqmagick")
5204 (synopsis "Tools for converting and modifying sequence files")
5206 "Bioinformaticians often have to convert sequence files between formats
5207 and do little manipulations on them, and it's not worth writing scripts for
5208 that. Seqmagick is a utility to expose the file format conversion in
5209 BioPython in a convenient way. Instead of having a big mess of scripts, there
5210 is one that takes arguments.")
5211 (license license:gpl3)))
5213 (define-public seqtk
5220 "https://github.com/lh3/seqtk/archive/v"
5222 (file-name (string-append name "-" version ".tar.gz"))
5225 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5226 (modules '((guix build utils)))
5229 ;; Remove extraneous header files, as is done in the seqtk
5231 (for-each (lambda (file) (delete-file file))
5232 (list "ksort.h" "kstring.h" "kvec.h"))
5234 (build-system gnu-build-system)
5237 (modify-phases %standard-phases
5240 ;; There are no tests, so we just run a sanity check.
5241 (lambda _ (zero? (system* "./seqtk" "seq"))))
5243 (lambda* (#:key outputs #:allow-other-keys)
5244 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5245 (install-file "seqtk" bin)))))))
5248 (home-page "https://github.com/lh3/seqtk")
5249 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5251 "Seqtk is a fast and lightweight tool for processing sequences in the
5252 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5253 optionally compressed by gzip.")
5254 (license license:expat)))
5256 (define-public snap-aligner
5258 (name "snap-aligner")
5259 (version "1.0beta.18")
5263 "https://github.com/amplab/snap/archive/v"
5265 (file-name (string-append name "-" version ".tar.gz"))
5268 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5269 (build-system gnu-build-system)
5272 (modify-phases %standard-phases
5274 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5276 (lambda* (#:key outputs #:allow-other-keys)
5277 (let* ((out (assoc-ref outputs "out"))
5278 (bin (string-append out "/bin")))
5279 (install-file "snap-aligner" bin)
5280 (install-file "SNAPCommand" bin)
5284 (home-page "http://snap.cs.berkeley.edu/")
5285 (synopsis "Short read DNA sequence aligner")
5287 "SNAP is a fast and accurate aligner for short DNA reads. It is
5288 optimized for modern read lengths of 100 bases or higher, and takes advantage
5289 of these reads to align data quickly through a hash-based indexing scheme.")
5290 ;; 32-bit systems are not supported by the unpatched code.
5291 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5292 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5293 ;; systems without a lot of memory cannot make good use of this program.
5294 (supported-systems '("x86_64-linux"))
5295 (license license:asl2.0)))
5297 (define-public sortmerna
5305 "https://github.com/biocore/sortmerna/archive/"
5307 (file-name (string-append name "-" version ".tar.gz"))
5310 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5311 (build-system gnu-build-system)
5312 (outputs '("out" ;for binaries
5313 "db")) ;for sequence databases
5316 (modify-phases %standard-phases
5318 (lambda* (#:key outputs #:allow-other-keys)
5319 (let* ((out (assoc-ref outputs "out"))
5320 (bin (string-append out "/bin"))
5321 (db (assoc-ref outputs "db"))
5323 (string-append db "/share/sortmerna/rRNA_databases")))
5324 (install-file "sortmerna" bin)
5325 (install-file "indexdb_rna" bin)
5326 (for-each (lambda (file)
5327 (install-file file share))
5328 (find-files "rRNA_databases" ".*fasta"))
5332 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5333 (synopsis "Biological sequence analysis tool for NGS reads")
5335 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5336 and operational taxonomic unit (OTU) picking of next generation
5337 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5338 allows for fast and sensitive analyses of nucleotide sequences. The main
5339 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5340 ;; The source includes x86 specific code
5341 (supported-systems '("x86_64-linux" "i686-linux"))
5342 (license license:lgpl3)))
5350 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5352 (file-name (string-append name "-" version ".tar.gz"))
5355 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5356 (modules '((guix build utils)))
5359 (substitute* "source/Makefile"
5361 ;; Remove pre-built binaries and bundled htslib sources.
5362 (delete-file-recursively "bin/MacOSX_x86_64")
5363 (delete-file-recursively "bin/Linux_x86_64")
5364 (delete-file-recursively "bin/Linux_x86_64_static")
5365 (delete-file-recursively "source/htslib")
5367 (build-system gnu-build-system)
5369 '(#:tests? #f ;no check target
5370 #:make-flags '("STAR")
5372 (modify-phases %standard-phases
5373 (add-after 'unpack 'enter-source-dir
5374 (lambda _ (chdir "source") #t))
5375 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5377 (substitute* "Makefile"
5378 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5380 (substitute* '("BAMfunctions.cpp"
5385 "bamRemoveDuplicates.cpp")
5386 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5387 (string-append "#include <" header ">")))
5388 (substitute* "IncludeDefine.h"
5389 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5390 (string-append "<" header ">")))
5393 (lambda* (#:key outputs #:allow-other-keys)
5394 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5395 (install-file "STAR" bin))
5397 (delete 'configure))))
5399 `(("vim" ,vim))) ; for xxd
5401 `(("htslib" ,htslib)
5403 (home-page "https://github.com/alexdobin/STAR")
5404 (synopsis "Universal RNA-seq aligner")
5406 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5407 based on a previously undescribed RNA-seq alignment algorithm that uses
5408 sequential maximum mappable seed search in uncompressed suffix arrays followed
5409 by seed clustering and stitching procedure. In addition to unbiased de novo
5410 detection of canonical junctions, STAR can discover non-canonical splices and
5411 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5413 ;; Only 64-bit systems are supported according to the README.
5414 (supported-systems '("x86_64-linux" "mips64el-linux"))
5415 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5416 (license license:gpl3+)))
5418 (define-public subread
5424 (uri (string-append "mirror://sourceforge/subread/subread-"
5425 version "/subread-" version "-source.tar.gz"))
5428 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5429 (build-system gnu-build-system)
5431 `(#:tests? #f ;no "check" target
5432 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5433 ;; optimizations by default, so we override these flags such that x86_64
5434 ;; flags are only added when the build target is an x86_64 system.
5436 (list (let ((system ,(or (%current-target-system)
5438 (flags '("-ggdb" "-fomit-frame-pointer"
5439 "-ffast-math" "-funroll-loops"
5440 "-fmessage-length=0"
5441 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5443 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5444 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5445 (if (string-prefix? "x86_64" system)
5446 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5447 (string-append "CCFLAGS=" (string-join flags))))
5448 "-f" "Makefile.Linux"
5449 "CC=gcc ${CCFLAGS}")
5453 (lambda _ (chdir "src") #t)
5456 (lambda* (#:key outputs #:allow-other-keys)
5457 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5459 (copy-recursively "../bin" bin)))
5460 ;; no "configure" script
5461 (alist-delete 'configure %standard-phases)))))
5462 (inputs `(("zlib" ,zlib)))
5463 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5464 (synopsis "Tool kit for processing next-gen sequencing data")
5466 "The subread package contains the following tools: subread aligner, a
5467 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5468 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5469 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5470 against local background noises.")
5471 (license license:gpl3+)))
5473 (define-public stringtie
5479 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5480 "stringtie-" version ".tar.gz"))
5483 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5484 (modules '((guix build utils)))
5487 (delete-file-recursively "samtools-0.1.18")
5489 (build-system gnu-build-system)
5491 `(#:tests? #f ;no test suite
5493 (modify-phases %standard-phases
5494 ;; no configure script
5496 (add-before 'build 'use-system-samtools
5498 (substitute* "Makefile"
5499 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5501 (substitute* '("gclib/GBam.h"
5503 (("#include \"(bam|sam|kstring).h\"" _ header)
5504 (string-append "#include <samtools/" header ".h>")))
5506 (add-after 'unpack 'remove-duplicate-typedef
5508 ;; This typedef conflicts with the typedef in
5509 ;; glibc-2.25/include/bits/types.h
5510 (substitute* "gclib/GThreads.h"
5511 (("typedef long long __intmax_t;") ""))
5514 (lambda* (#:key outputs #:allow-other-keys)
5515 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5516 (install-file "stringtie" bin)
5519 `(("samtools" ,samtools-0.1)
5521 (home-page "http://ccb.jhu.edu/software/stringtie/")
5522 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5524 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5525 alignments into potential transcripts. It uses a novel network flow algorithm
5526 as well as an optional de novo assembly step to assemble and quantitate
5527 full-length transcripts representing multiple splice variants for each gene
5528 locus. Its input can include not only the alignments of raw reads used by
5529 other transcript assemblers, but also alignments of longer sequences that have
5530 been assembled from those reads. To identify differentially expressed genes
5531 between experiments, StringTie's output can be processed either by the
5532 Cuffdiff or Ballgown programs.")
5533 (license license:artistic2.0)))
5535 (define-public taxtastic
5541 (uri (pypi-uri "taxtastic" version))
5544 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5545 (build-system python-build-system)
5547 `(#:python ,python-2
5549 (modify-phases %standard-phases
5552 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5554 `(("python-sqlalchemy" ,python2-sqlalchemy)
5555 ("python-decorator" ,python2-decorator)
5556 ("python-biopython" ,python2-biopython)
5557 ("python-pandas" ,python2-pandas)))
5558 (home-page "https://github.com/fhcrc/taxtastic")
5559 (synopsis "Tools for taxonomic naming and annotation")
5561 "Taxtastic is software written in python used to build and maintain
5562 reference packages i.e. collections of reference trees, reference alignments,
5563 profiles, and associated taxonomic information.")
5564 (license license:gpl3+)))
5566 (define-public vcftools
5573 "https://github.com/vcftools/vcftools/releases/download/v"
5574 version "/vcftools-" version ".tar.gz"))
5577 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5578 (build-system gnu-build-system)
5580 `(#:tests? #f ; no "check" target
5582 "CFLAGS=-O2" ; override "-m64" flag
5583 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5584 (string-append "MANDIR=" (assoc-ref %outputs "out")
5585 "/share/man/man1"))))
5587 `(("pkg-config" ,pkg-config)))
5591 (home-page "https://vcftools.github.io/")
5592 (synopsis "Tools for working with VCF files")
5594 "VCFtools is a program package designed for working with VCF files, such
5595 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5596 provide easily accessible methods for working with complex genetic variation
5597 data in the form of VCF files.")
5598 ;; The license is declared as LGPLv3 in the README and
5599 ;; at https://vcftools.github.io/license.html
5600 (license license:lgpl3)))
5602 (define-public infernal
5608 (uri (string-append "http://eddylab.org/software/infernal/"
5609 "infernal-" version ".tar.gz"))
5612 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5613 (build-system gnu-build-system)
5615 `(("perl" ,perl))) ; for tests
5616 (home-page "http://eddylab.org/infernal/")
5617 (synopsis "Inference of RNA alignments")
5618 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5619 searching DNA sequence databases for RNA structure and sequence similarities.
5620 It is an implementation of a special case of profile stochastic context-free
5621 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5622 profile, but it scores a combination of sequence consensus and RNA secondary
5623 structure consensus, so in many cases, it is more capable of identifying RNA
5624 homologs that conserve their secondary structure more than their primary
5626 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5627 (supported-systems '("i686-linux" "x86_64-linux"))
5628 (license license:bsd-3)))
5630 (define-public r-centipede
5632 (name "r-centipede")
5636 (uri (string-append "http://download.r-forge.r-project.org/"
5637 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5640 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5641 (build-system r-build-system)
5642 (home-page "http://centipede.uchicago.edu/")
5643 (synopsis "Predict transcription factor binding sites")
5645 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5646 of the genome that are bound by particular transcription factors. It starts
5647 by identifying a set of candidate binding sites, and then aims to classify the
5648 sites according to whether each site is bound or not bound by a transcription
5649 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5650 between two different types of motif instances using as much relevant
5651 information as possible.")
5652 (license (list license:gpl2+ license:gpl3+))))
5654 (define-public r-vegan
5661 (uri (cran-uri "vegan" version))
5664 "15zcxfix2d854897k1lr0sfmj2n00339nlsppcr3zrb238lb2mi5"))))
5665 (build-system r-build-system)
5667 `(("gfortran" ,gfortran)
5668 ("r-knitr" ,r-knitr)))
5670 `(("r-cluster" ,r-cluster)
5671 ("r-lattice" ,r-lattice)
5674 ("r-permute" ,r-permute)))
5675 (home-page "https://cran.r-project.org/web/packages/vegan")
5676 (synopsis "Functions for community ecology")
5678 "The vegan package provides tools for descriptive community ecology. It
5679 has most basic functions of diversity analysis, community ordination and
5680 dissimilarity analysis. Most of its multivariate tools can be used for other
5681 data types as well.")
5682 (license license:gpl2+)))
5684 (define-public r-annotate
5691 (uri (bioconductor-uri "annotate" version))
5694 "03hmbvp3i6lvd307fqdg7akxi2qp322rlky3bzw0zccgm0i0221g"))))
5695 (build-system r-build-system)
5697 `(("r-annotationdbi" ,r-annotationdbi)
5698 ("r-biobase" ,r-biobase)
5699 ("r-biocgenerics" ,r-biocgenerics)
5701 ("r-rcurl" ,r-rcurl)
5703 ("r-xtable" ,r-xtable)))
5705 "http://bioconductor.org/packages/annotate")
5706 (synopsis "Annotation for microarrays")
5707 (description "This package provides R environments for the annotation of
5709 (license license:artistic2.0)))
5711 (define-public r-geneplotter
5713 (name "r-geneplotter")
5718 (uri (bioconductor-uri "geneplotter" version))
5721 "0a0ajns21db5rrjl16bq6wawggsnxr00fg184pc38nmfghv4z4b6"))))
5722 (build-system r-build-system)
5724 `(("r-annotate" ,r-annotate)
5725 ("r-annotationdbi" ,r-annotationdbi)
5726 ("r-biobase" ,r-biobase)
5727 ("r-biocgenerics" ,r-biocgenerics)
5728 ("r-lattice" ,r-lattice)
5729 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5730 (home-page "http://bioconductor.org/packages/geneplotter")
5731 (synopsis "Graphics functions for genomic data")
5733 "This package provides functions for plotting genomic data.")
5734 (license license:artistic2.0)))
5736 (define-public r-genefilter
5738 (name "r-genefilter")
5743 (uri (bioconductor-uri "genefilter" version))
5746 "0sf2hdi9nv6r83vn1y65m4jiba8pffddpj46d6yjn5rlsixplmqg"))))
5747 (build-system r-build-system)
5749 `(("gfortran" ,gfortran)))
5751 `(("r-annotate" ,r-annotate)
5752 ("r-annotationdbi" ,r-annotationdbi)
5753 ("r-biobase" ,r-biobase)
5754 ("r-s4vectors" ,r-s4vectors)
5755 ("r-survival" ,r-survival)))
5756 (home-page "http://bioconductor.org/packages/genefilter")
5757 (synopsis "Filter genes from high-throughput experiments")
5759 "This package provides basic functions for filtering genes from
5760 high-throughput sequencing experiments.")
5761 (license license:artistic2.0)))
5763 (define-public r-deseq2
5770 (uri (bioconductor-uri "DESeq2" version))
5773 "01pvyljxkwazxl510v7h0971nx65iqd2bdkbdhw3xzind0n9pdvq"))))
5774 (properties `((upstream-name . "DESeq2")))
5775 (build-system r-build-system)
5777 `(("r-biobase" ,r-biobase)
5778 ("r-biocgenerics" ,r-biocgenerics)
5779 ("r-biocparallel" ,r-biocparallel)
5780 ("r-genefilter" ,r-genefilter)
5781 ("r-geneplotter" ,r-geneplotter)
5782 ("r-genomicranges" ,r-genomicranges)
5783 ("r-ggplot2" ,r-ggplot2)
5784 ("r-hmisc" ,r-hmisc)
5785 ("r-iranges" ,r-iranges)
5786 ("r-locfit" ,r-locfit)
5788 ("r-rcpparmadillo" ,r-rcpparmadillo)
5789 ("r-s4vectors" ,r-s4vectors)
5790 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5791 (home-page "http://bioconductor.org/packages/DESeq2")
5792 (synopsis "Differential gene expression analysis")
5794 "This package provides functions to estimate variance-mean dependence in
5795 count data from high-throughput nucleotide sequencing assays and test for
5796 differential expression based on a model using the negative binomial
5798 (license license:lgpl3+)))
5800 (define-public r-dexseq
5807 (uri (bioconductor-uri "DEXSeq" version))
5810 "085aqk1wlzzqcqcqhvz74y099kr2ln5dwdxd3rl6zan806mgwahg"))))
5811 (properties `((upstream-name . "DEXSeq")))
5812 (build-system r-build-system)
5814 `(("r-annotationdbi" ,r-annotationdbi)
5815 ("r-biobase" ,r-biobase)
5816 ("r-biocgenerics" ,r-biocgenerics)
5817 ("r-biocparallel" ,r-biocparallel)
5818 ("r-biomart" ,r-biomart)
5819 ("r-deseq2" ,r-deseq2)
5820 ("r-genefilter" ,r-genefilter)
5821 ("r-geneplotter" ,r-geneplotter)
5822 ("r-genomicranges" ,r-genomicranges)
5823 ("r-hwriter" ,r-hwriter)
5824 ("r-iranges" ,r-iranges)
5825 ("r-rcolorbrewer" ,r-rcolorbrewer)
5826 ("r-rsamtools" ,r-rsamtools)
5827 ("r-s4vectors" ,r-s4vectors)
5828 ("r-statmod" ,r-statmod)
5829 ("r-stringr" ,r-stringr)
5830 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5831 (home-page "http://bioconductor.org/packages/DEXSeq")
5832 (synopsis "Inference of differential exon usage in RNA-Seq")
5834 "This package is focused on finding differential exon usage using RNA-seq
5835 exon counts between samples with different experimental designs. It provides
5836 functions that allows the user to make the necessary statistical tests based
5837 on a model that uses the negative binomial distribution to estimate the
5838 variance between biological replicates and generalized linear models for
5839 testing. The package also provides functions for the visualization and
5840 exploration of the results.")
5841 (license license:gpl3+)))
5843 (define-public r-annotationforge
5845 (name "r-annotationforge")
5850 (uri (bioconductor-uri "AnnotationForge" version))
5853 "1366qvykd9cpcvwgc5g9mm9adw9rxw6p4814dd6l5fyb0pwpmysx"))))
5855 `((upstream-name . "AnnotationForge")))
5856 (build-system r-build-system)
5858 `(("r-annotationdbi" ,r-annotationdbi)
5859 ("r-biobase" ,r-biobase)
5860 ("r-biocgenerics" ,r-biocgenerics)
5862 ("r-rcurl" ,r-rcurl)
5863 ("r-rsqlite" ,r-rsqlite)
5864 ("r-s4vectors" ,r-s4vectors)
5866 (home-page "http://bioconductor.org/packages/AnnotationForge")
5867 (synopsis "Code for building annotation database packages")
5869 "This package provides code for generating Annotation packages and their
5870 databases. Packages produced are intended to be used with AnnotationDbi.")
5871 (license license:artistic2.0)))
5873 (define-public r-rbgl
5880 (uri (bioconductor-uri "RBGL" version))
5883 "11db6kvz453ypj9ds3xpjqzwrrjck84ijn4wlhkfyz2dzdgd5ryv"))))
5884 (properties `((upstream-name . "RBGL")))
5885 (build-system r-build-system)
5886 (propagated-inputs `(("r-graph" ,r-graph)))
5887 (home-page "http://www.bioconductor.org/packages/RBGL")
5888 (synopsis "Interface to the Boost graph library")
5890 "This package provides a fairly extensive and comprehensive interface to
5891 the graph algorithms contained in the Boost library.")
5892 (license license:artistic2.0)))
5894 (define-public r-gseabase
5901 (uri (bioconductor-uri "GSEABase" version))
5904 "1c6i6g4fj3b8wjyxyygr7i3v8sxrq1ffb2bbicya5ah2gdaclfad"))))
5905 (properties `((upstream-name . "GSEABase")))
5906 (build-system r-build-system)
5908 `(("r-annotate" ,r-annotate)
5909 ("r-annotationdbi" ,r-annotationdbi)
5910 ("r-biobase" ,r-biobase)
5911 ("r-biocgenerics" ,r-biocgenerics)
5912 ("r-graph" ,r-graph)
5914 (home-page "http://bioconductor.org/packages/GSEABase")
5915 (synopsis "Gene set enrichment data structures and methods")
5917 "This package provides classes and methods to support @dfn{Gene Set
5918 Enrichment Analysis} (GSEA).")
5919 (license license:artistic2.0)))
5921 (define-public r-category
5928 (uri (bioconductor-uri "Category" version))
5931 "1w186nhc85bglcgmbcrsdbb8l6rph21pl5kdwjqwkp0jnr9z0ifn"))))
5932 (properties `((upstream-name . "Category")))
5933 (build-system r-build-system)
5935 `(("r-annotate" ,r-annotate)
5936 ("r-annotationdbi" ,r-annotationdbi)
5937 ("r-biobase" ,r-biobase)
5938 ("r-biocgenerics" ,r-biocgenerics)
5939 ("r-genefilter" ,r-genefilter)
5940 ("r-graph" ,r-graph)
5941 ("r-gseabase" ,r-gseabase)
5942 ("r-matrix" ,r-matrix)
5944 ("r-rsqlite" ,r-rsqlite)))
5945 (home-page "http://bioconductor.org/packages/Category")
5946 (synopsis "Category analysis")
5948 "This package provides a collection of tools for performing category
5950 (license license:artistic2.0)))
5952 (define-public r-gostats
5959 (uri (bioconductor-uri "GOstats" version))
5962 "0qvqjgfnd9ap4rikvyxa9p4dhcnccvkw8phzv88vghh6pq463d62"))))
5963 (properties `((upstream-name . "GOstats")))
5964 (build-system r-build-system)
5966 `(("r-annotate" ,r-annotate)
5967 ("r-annotationdbi" ,r-annotationdbi)
5968 ("r-annotationforge" ,r-annotationforge)
5969 ("r-biobase" ,r-biobase)
5970 ("r-category" ,r-category)
5971 ("r-go-db" ,r-go-db)
5972 ("r-graph" ,r-graph)
5973 ("r-rbgl" ,r-rbgl)))
5974 (home-page "http://bioconductor.org/packages/GOstats")
5975 (synopsis "Tools for manipulating GO and microarrays")
5977 "This package provides a set of tools for interacting with GO and
5978 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5979 testing and other simple calculations.")
5980 (license license:artistic2.0)))
5982 (define-public r-shortread
5984 (name "r-shortread")
5989 (uri (bioconductor-uri "ShortRead" version))
5992 "0ayk3d5625ymb5g2gycq6banzqmyd642xrwjzhdshz2dwid7kly8"))))
5993 (properties `((upstream-name . "ShortRead")))
5994 (build-system r-build-system)
5998 `(("r-biobase" ,r-biobase)
5999 ("r-biocgenerics" ,r-biocgenerics)
6000 ("r-biocparallel" ,r-biocparallel)
6001 ("r-biostrings" ,r-biostrings)
6002 ("r-genomeinfodb" ,r-genomeinfodb)
6003 ("r-genomicalignments" ,r-genomicalignments)
6004 ("r-genomicranges" ,r-genomicranges)
6005 ("r-hwriter" ,r-hwriter)
6006 ("r-iranges" ,r-iranges)
6007 ("r-lattice" ,r-lattice)
6008 ("r-latticeextra" ,r-latticeextra)
6009 ("r-rsamtools" ,r-rsamtools)
6010 ("r-s4vectors" ,r-s4vectors)
6011 ("r-xvector" ,r-xvector)
6012 ("r-zlibbioc" ,r-zlibbioc)))
6013 (home-page "http://bioconductor.org/packages/ShortRead")
6014 (synopsis "FASTQ input and manipulation tools")
6016 "This package implements sampling, iteration, and input of FASTQ files.
6017 It includes functions for filtering and trimming reads, and for generating a
6018 quality assessment report. Data are represented as
6019 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6020 purposes. The package also contains legacy support for early single-end,
6021 ungapped alignment formats.")
6022 (license license:artistic2.0)))
6024 (define-public r-systempiper
6026 (name "r-systempiper")
6031 (uri (bioconductor-uri "systemPipeR" version))
6034 "0c3m5rq63ypv15yca97yag5d4vgd7xj9by2a4sd8z0pcmpajz0hw"))))
6035 (properties `((upstream-name . "systemPipeR")))
6036 (build-system r-build-system)
6038 `(("r-annotate" ,r-annotate)
6039 ("r-batchjobs" ,r-batchjobs)
6040 ("r-biocgenerics" ,r-biocgenerics)
6041 ("r-biostrings" ,r-biostrings)
6042 ("r-deseq2" ,r-deseq2)
6043 ("r-edger" ,r-edger)
6044 ("r-genomicfeatures" ,r-genomicfeatures)
6045 ("r-genomicranges" ,r-genomicranges)
6046 ("r-ggplot2" ,r-ggplot2)
6047 ("r-go-db" ,r-go-db)
6048 ("r-gostats" ,r-gostats)
6049 ("r-limma" ,r-limma)
6050 ("r-pheatmap" ,r-pheatmap)
6051 ("r-rjson" ,r-rjson)
6052 ("r-rsamtools" ,r-rsamtools)
6053 ("r-shortread" ,r-shortread)
6054 ("r-summarizedexperiment" ,r-summarizedexperiment)
6055 ("r-variantannotation" ,r-variantannotation)))
6056 (home-page "https://github.com/tgirke/systemPipeR")
6057 (synopsis "Next generation sequencing workflow and reporting environment")
6059 "This R package provides tools for building and running automated
6060 end-to-end analysis workflows for a wide range of @dfn{next generation
6061 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6062 Important features include a uniform workflow interface across different NGS
6063 applications, automated report generation, and support for running both R and
6064 command-line software, such as NGS aligners or peak/variant callers, on local
6065 computers or compute clusters. Efficient handling of complex sample sets and
6066 experimental designs is facilitated by a consistently implemented sample
6067 annotation infrastructure.")
6068 (license license:artistic2.0)))
6070 (define-public r-grohmm
6077 (uri (bioconductor-uri "groHMM" version))
6080 "16k1kp4sbhh0vp7dzywafq52csq42ksqfrqfy4bdv1qbd7536dpd"))))
6081 (properties `((upstream-name . "groHMM")))
6082 (build-system r-build-system)
6084 `(("r-genomeinfodb" ,r-genomeinfodb)
6085 ("r-genomicalignments" ,r-genomicalignments)
6086 ("r-genomicranges" ,r-genomicranges)
6087 ("r-iranges" ,r-iranges)
6089 ("r-rtracklayer" ,r-rtracklayer)
6090 ("r-s4vectors" ,r-s4vectors)))
6091 (home-page "https://github.com/Kraus-Lab/groHMM")
6092 (synopsis "GRO-seq analysis pipeline")
6094 "This package provides a pipeline for the analysis of GRO-seq data.")
6095 (license license:gpl3+)))
6097 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6099 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6103 ;; We cannot use bioconductor-uri here because this tarball is
6104 ;; located under "data/annotation/" instead of "bioc/".
6105 (uri (string-append "http://bioconductor.org/packages/"
6106 "release/data/annotation/src/contrib"
6107 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6111 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6113 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6114 (build-system r-build-system)
6115 ;; As this package provides little more than a very large data file it
6116 ;; doesn't make sense to build substitutes.
6117 (arguments `(#:substitutable? #f))
6119 `(("r-genomicfeatures" ,r-genomicfeatures)))
6121 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6122 (synopsis "Annotation package for human genome in TxDb format")
6124 "This package provides an annotation database of Homo sapiens genome
6125 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6126 track. The database is exposed as a @code{TxDb} object.")
6127 (license license:artistic2.0)))
6129 (define-public vsearch
6137 "https://github.com/torognes/vsearch/archive/v"
6139 (file-name (string-append name "-" version ".tar.gz"))
6142 "0hc110ycqpa54nr6x173qg7190hk08qp7yz7zzqxlsypqnpc5zzp"))
6143 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6146 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6147 ;; for this in the patch.
6148 (delete-file "src/city.h")
6149 (delete-file "src/citycrc.h")
6150 (delete-file "src/city.cc")
6152 (build-system gnu-build-system)
6155 (modify-phases %standard-phases
6156 (add-before 'configure 'autogen
6157 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6161 ("cityhash" ,cityhash)))
6163 `(("autoconf" ,autoconf)
6164 ("automake" ,automake)))
6165 (synopsis "Sequence search tools for metagenomics")
6167 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6168 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6169 masking. The tool takes advantage of parallelism in the form of SIMD
6170 vectorization as well as multiple threads to perform accurate alignments at
6171 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6172 Needleman-Wunsch).")
6173 (home-page "https://github.com/torognes/vsearch")
6174 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6176 (supported-systems '("x86_64-linux"))
6177 ;; Dual licensed; also includes public domain source.
6178 (license (list license:gpl3 license:bsd-2))))
6180 (define-public pardre
6183 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6188 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6192 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6193 (build-system gnu-build-system)
6195 `(#:tests? #f ; no tests included
6197 (modify-phases %standard-phases
6200 (lambda* (#:key outputs #:allow-other-keys)
6201 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6202 (install-file "ParDRe" bin)
6205 `(("openmpi" ,openmpi)
6207 (synopsis "Parallel tool to remove duplicate DNA reads")
6209 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6210 Duplicate reads can be seen as identical or nearly identical sequences with
6211 some mismatches. This tool lets users avoid the analysis of unnecessary
6212 reads, reducing the time of subsequent procedures with the
6213 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6214 in order to exploit the parallel capabilities of multicore clusters. It is
6215 faster than multithreaded counterparts (end of 2015) for the same number of
6216 cores and, thanks to the message-passing technology, it can be executed on
6218 (home-page "https://sourceforge.net/projects/pardre/")
6219 (license license:gpl3+)))
6221 (define-public ruby-bio-kseq
6223 (name "ruby-bio-kseq")
6228 (uri (rubygems-uri "bio-kseq" version))
6231 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6232 (build-system ruby-build-system)
6234 `(#:test-target "spec"))
6236 `(("bundler" ,bundler)
6237 ("ruby-rspec" ,ruby-rspec)
6238 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6241 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6243 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6244 FASTQ parsing code. It provides a fast iterator over sequences and their
6246 (home-page "https://github.com/gusevfe/bio-kseq")
6247 (license license:expat)))
6249 (define-public bio-locus
6256 (uri (rubygems-uri "bio-locus" version))
6259 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6260 (build-system ruby-build-system)
6262 `(("ruby-rspec" ,ruby-rspec)))
6263 (synopsis "Tool for fast querying of genome locations")
6265 "Bio-locus is a tabix-like tool for fast querying of genome
6266 locations. Many file formats in bioinformatics contain records that
6267 start with a chromosome name and a position for a SNP, or a start-end
6268 position for indels. Bio-locus allows users to store this chr+pos or
6269 chr+pos+alt information in a database.")
6270 (home-page "https://github.com/pjotrp/bio-locus")
6271 (license license:expat)))
6273 (define-public bio-blastxmlparser
6275 (name "bio-blastxmlparser")
6279 (uri (rubygems-uri "bio-blastxmlparser" version))
6282 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6283 (build-system ruby-build-system)
6285 `(("ruby-bio-logger" ,ruby-bio-logger)
6286 ("ruby-nokogiri" ,ruby-nokogiri)))
6288 `(("ruby-rspec" ,ruby-rspec)))
6289 (synopsis "Fast big data BLAST XML parser and library")
6291 "Very fast parallel big-data BLAST XML file parser which can be used as
6292 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6293 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6294 (home-page "https://github.com/pjotrp/blastxmlparser")
6295 (license license:expat)))
6297 (define-public bioruby
6304 (uri (rubygems-uri "bio" version))
6307 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6308 (build-system ruby-build-system)
6310 `(("ruby-libxml" ,ruby-libxml)))
6312 `(("which" ,which))) ; required for test phase
6315 (modify-phases %standard-phases
6316 (add-before 'build 'patch-test-command
6318 (substitute* '("test/functional/bio/test_command.rb")
6319 (("/bin/sh") (which "sh")))
6320 (substitute* '("test/functional/bio/test_command.rb")
6321 (("/bin/ls") (which "ls")))
6322 (substitute* '("test/functional/bio/test_command.rb")
6323 (("which") (which "which")))
6324 (substitute* '("test/functional/bio/test_command.rb",
6325 "test/data/command/echoarg2.sh")
6326 (("/bin/echo") (which "echo")))
6328 (synopsis "Ruby library, shell and utilities for bioinformatics")
6329 (description "BioRuby comes with a comprehensive set of Ruby development
6330 tools and libraries for bioinformatics and molecular biology. BioRuby has
6331 components for sequence analysis, pathway analysis, protein modelling and
6332 phylogenetic analysis; it supports many widely used data formats and provides
6333 easy access to databases, external programs and public web services, including
6334 BLAST, KEGG, GenBank, MEDLINE and GO.")
6335 (home-page "http://bioruby.org/")
6336 ;; Code is released under Ruby license, except for setup
6337 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6338 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6340 (define-public r-acsnminer
6342 (name "r-acsnminer")
6343 (version "0.16.8.25")
6346 (uri (cran-uri "ACSNMineR" version))
6349 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6350 (properties `((upstream-name . "ACSNMineR")))
6351 (build-system r-build-system)
6353 `(("r-ggplot2" ,r-ggplot2)
6354 ("r-gridextra" ,r-gridextra)))
6355 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6356 (synopsis "Gene enrichment analysis")
6358 "This package provides tools to compute and represent gene set enrichment
6359 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6360 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6361 enrichment can be run with hypergeometric test or Fisher exact test, and can
6362 use multiple corrections. Visualization of data can be done either by
6363 barplots or heatmaps.")
6364 (license license:gpl2+)))
6366 (define-public r-biocgenerics
6368 (name "r-biocgenerics")
6372 (uri (bioconductor-uri "BiocGenerics" version))
6375 "0qbmz2qxwwi30xpxpvp2h1h7l494rbbz5d9pls5cfhqdv3wnpzsv"))))
6377 `((upstream-name . "BiocGenerics")))
6378 (build-system r-build-system)
6379 (home-page "http://bioconductor.org/packages/BiocGenerics")
6380 (synopsis "S4 generic functions for Bioconductor")
6382 "This package provides S4 generic functions needed by many Bioconductor
6384 (license license:artistic2.0)))
6386 (define-public r-biocinstaller
6388 (name "r-biocinstaller")
6392 (uri (bioconductor-uri "BiocInstaller" version))
6395 "0njw2q3lq1rrjx8qzw5d2130l72bmd3g2z8qlxqmkdcbmmgliyj2"))))
6397 `((upstream-name . "BiocInstaller")))
6398 (build-system r-build-system)
6399 (home-page "http://bioconductor.org/packages/BiocInstaller")
6400 (synopsis "Install Bioconductor packages")
6401 (description "This package is used to install and update R packages from
6402 Bioconductor, CRAN, and Github.")
6403 (license license:artistic2.0)))
6405 (define-public r-biocviews
6407 (name "r-biocviews")
6411 (uri (bioconductor-uri "biocViews" version))
6414 "17hi8w0w63f5yc43kid5pbld3ca78sj6n8x9dmkbl8h48818xbga"))))
6416 `((upstream-name . "biocViews")))
6417 (build-system r-build-system)
6419 `(("r-biobase" ,r-biobase)
6420 ("r-graph" ,r-graph)
6422 ("r-rcurl" ,r-rcurl)
6424 ("r-knitr" ,r-knitr)
6425 ("r-runit" ,r-runit)))
6426 (home-page "http://bioconductor.org/packages/biocViews")
6427 (synopsis "Bioconductor package categorization helper")
6428 (description "The purpose of biocViews is to create HTML pages that
6429 categorize packages in a Bioconductor package repository according to keywords,
6430 also known as views, in a controlled vocabulary.")
6431 (license license:artistic2.0)))
6433 (define-public r-bookdown
6439 (uri (cran-uri "bookdown" version))
6442 "1fp1k7hivrb7s2dwgrsqy9s7xg6pk9hczhrc149y1dwh901j6qvv"))))
6443 (build-system r-build-system)
6445 `(("r-htmltools" ,r-htmltools)
6446 ("r-knitr" ,r-knitr)
6447 ("r-rmarkdown" ,r-rmarkdown)
6448 ("r-yaml" ,r-yaml)))
6449 (home-page "https://github.com/rstudio/bookdown")
6450 (synopsis "Authoring books and technical documents with R markdown")
6451 (description "This package provides output formats and utilities for
6452 authoring books and technical documents with R Markdown.")
6453 (license license:gpl3)))
6455 (define-public r-biocstyle
6457 (name "r-biocstyle")
6461 (uri (bioconductor-uri "BiocStyle" version))
6464 "0bmgmsfll923v573g0kyzlmjd7gly5jwgd8vkrcwvbam1gz75f2c"))))
6466 `((upstream-name . "BiocStyle")))
6467 (build-system r-build-system)
6469 `(("r-bookdown" ,r-bookdown)
6470 ("r-knitr" ,r-knitr)
6471 ("r-rmarkdown" ,r-rmarkdown)
6472 ("r-yaml" ,r-yaml)))
6473 (home-page "http://bioconductor.org/packages/BiocStyle")
6474 (synopsis "Bioconductor formatting styles")
6475 (description "This package provides standard formatting styles for
6476 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6478 (license license:artistic2.0)))
6480 (define-public r-bioccheck
6482 (name "r-bioccheck")
6486 (uri (bioconductor-uri "BiocCheck" version))
6489 "01zkw5hggzvn0wj4msac71k1mknq4h2inn1c2hwqgw4cy1675wl0"))))
6491 `((upstream-name . "BiocCheck")))
6492 (build-system r-build-system)
6495 (modify-phases %standard-phases
6496 ;; This package can be used by calling BiocCheck(<package>) from
6497 ;; within R, or by running R CMD BiocCheck <package>. This phase
6498 ;; makes sure the latter works. For this to work, the BiocCheck
6499 ;; script must be somewhere on the PATH (not the R bin directory).
6500 (add-after 'install 'install-bioccheck-subcommand
6501 (lambda* (#:key outputs #:allow-other-keys)
6502 (let* ((out (assoc-ref outputs "out"))
6503 (dest-dir (string-append out "/bin"))
6505 (string-append out "/site-library/BiocCheck/script/")))
6507 (symlink (string-append script-dir "/checkBadDeps.R")
6508 (string-append dest-dir "/checkBadDeps.R"))
6509 (symlink (string-append script-dir "/BiocCheck")
6510 (string-append dest-dir "/BiocCheck")))
6513 `(("which" ,which)))
6515 `(("r-codetools" ,r-codetools)
6516 ("r-graph" ,r-graph)
6518 ("r-optparse" ,r-optparse)
6519 ("r-biocinstaller" ,r-biocinstaller)
6520 ("r-biocviews" ,r-biocviews)))
6521 (home-page "http://bioconductor.org/packages/BiocCheck")
6522 (synopsis "Executes Bioconductor-specific package checks")
6523 (description "This package contains tools to perform additional quality
6524 checks on R packages that are to be submitted to the Bioconductor repository.")
6525 (license license:artistic2.0)))
6527 (define-public r-getopt
6534 (uri (cran-uri "getopt" version))
6537 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6538 (build-system r-build-system)
6539 (home-page "https://github.com/trevorld/getopt")
6540 (synopsis "Command-line option processor for R")
6542 "This package is designed to be used with Rscript to write shebang
6543 scripts that accept short and long options. Many users will prefer to
6544 use the packages @code{optparse} or @code{argparse} which add extra
6545 features like automatically generated help options and usage texts,
6546 support for default values, positional argument support, etc.")
6547 (license license:gpl2+)))
6549 (define-public r-optparse
6556 (uri (cran-uri "optparse" version))
6559 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6560 (build-system r-build-system)
6562 `(("r-getopt" ,r-getopt)))
6564 "https://github.com/trevorld/optparse")
6565 (synopsis "Command line option parser")
6567 "This package provides a command line parser inspired by Python's
6568 @code{optparse} library to be used with Rscript to write shebang scripts
6569 that accept short and long options.")
6570 (license license:gpl2+)))
6572 (define-public r-dnacopy
6578 (uri (bioconductor-uri "DNAcopy" version))
6581 "0f0x83db7rm5xf9fg5pjhvs4i165qqaf01lbwb8kj13fsqpwx15p"))))
6583 `((upstream-name . "DNAcopy")))
6584 (build-system r-build-system)
6586 `(("gfortran" ,gfortran)))
6587 (home-page "https://bioconductor.org/packages/DNAcopy")
6588 (synopsis "Implementation of a circular binary segmentation algorithm")
6589 (description "This package implements the circular binary segmentation (CBS)
6590 algorithm to segment DNA copy number data and identify genomic regions with
6591 abnormal copy number.")
6592 (license license:gpl2+)))
6594 (define-public r-s4vectors
6596 (name "r-s4vectors")
6600 (uri (bioconductor-uri "S4Vectors" version))
6603 "1r7s4pfw026qazzic090mhk8d9m39j2nwl87dyqcpdylyq7gq5qs"))))
6605 `((upstream-name . "S4Vectors")))
6606 (build-system r-build-system)
6608 `(("r-biocgenerics" ,r-biocgenerics)))
6609 (home-page "http://bioconductor.org/packages/S4Vectors")
6610 (synopsis "S4 implementation of vectors and lists")
6612 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6613 classes and a set of generic functions that extend the semantic of ordinary
6614 vectors and lists in R. Package developers can easily implement vector-like
6615 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6616 In addition, a few low-level concrete subclasses of general interest (e.g.
6617 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6618 S4Vectors package itself.")
6619 (license license:artistic2.0)))
6621 (define-public r-seqinr
6628 (uri (cran-uri "seqinr" version))
6631 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6632 (build-system r-build-system)
6634 `(("r-ade4" ,r-ade4)
6635 ("r-segmented" ,r-segmented)))
6638 (home-page "http://seqinr.r-forge.r-project.org/")
6639 (synopsis "Biological sequences retrieval and analysis")
6641 "This package provides tools for exploratory data analysis and data
6642 visualization of biological sequence (DNA and protein) data. It also includes
6643 utilities for sequence data management under the ACNUC system.")
6644 (license license:gpl2+)))
6646 (define-public r-iranges
6652 (uri (bioconductor-uri "IRanges" version))
6655 "1brmzs3rsf97gymridrh9c9r3vws8b3rpghaanxnniw36lmcajfy"))))
6657 `((upstream-name . "IRanges")))
6658 (build-system r-build-system)
6660 `(("r-biocgenerics" ,r-biocgenerics)
6661 ("r-s4vectors" ,r-s4vectors)))
6662 (home-page "http://bioconductor.org/packages/IRanges")
6663 (synopsis "Infrastructure for manipulating intervals on sequences")
6665 "This package provides efficient low-level and highly reusable S4 classes
6666 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6667 generally, data that can be organized sequentially (formally defined as
6668 @code{Vector} objects), as well as views on these @code{Vector} objects.
6669 Efficient list-like classes are also provided for storing big collections of
6670 instances of the basic classes. All classes in the package use consistent
6671 naming and share the same rich and consistent \"Vector API\" as much as
6673 (license license:artistic2.0)))
6675 (define-public r-genomeinfodbdata
6677 (name "r-genomeinfodbdata")
6681 ;; We cannot use bioconductor-uri here because this tarball is
6682 ;; located under "data/annotation/" instead of "bioc/".
6683 (uri (string-append "https://bioconductor.org/packages/release/"
6684 "data/annotation/src/contrib/GenomeInfoDbData_"
6688 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6690 `((upstream-name . "GenomeInfoDbData")))
6691 (build-system r-build-system)
6692 (home-page "http://bioconductor.org/packages/GenomeInfoDbData")
6693 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6694 (description "This package contains data for mapping between NCBI taxonomy
6695 ID and species. It is used by functions in the GenomeInfoDb package.")
6696 (license license:artistic2.0)))
6698 (define-public r-genomeinfodb
6700 (name "r-genomeinfodb")
6704 (uri (bioconductor-uri "GenomeInfoDb" version))
6707 "1hjxgmcnrngp1307ipqaq9hgxz4j0ldn7d46knhzs30k2r4qnrfp"))))
6709 `((upstream-name . "GenomeInfoDb")))
6710 (build-system r-build-system)
6712 `(("r-biocgenerics" ,r-biocgenerics)
6713 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6714 ("r-iranges" ,r-iranges)
6715 ("r-rcurl" ,r-rcurl)
6716 ("r-s4vectors" ,r-s4vectors)))
6717 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6718 (synopsis "Utilities for manipulating chromosome identifiers")
6720 "This package contains data and functions that define and allow
6721 translation between different chromosome sequence naming conventions (e.g.,
6722 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6723 names in their natural, rather than lexicographic, order.")
6724 (license license:artistic2.0)))
6726 (define-public r-edger
6732 (uri (bioconductor-uri "edgeR" version))
6735 "02l17i6xh33dv10swwvyfxrmv5kp23iv278iwvkfq2mnipasfnb9"))))
6736 (properties `((upstream-name . "edgeR")))
6737 (build-system r-build-system)
6739 `(("r-limma" ,r-limma)
6740 ("r-locfit" ,r-locfit)
6741 ("r-statmod" ,r-statmod))) ;for estimateDisp
6742 (home-page "http://bioinf.wehi.edu.au/edgeR")
6743 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6744 (description "This package can do differential expression analysis of
6745 RNA-seq expression profiles with biological replication. It implements a range
6746 of statistical methodology based on the negative binomial distributions,
6747 including empirical Bayes estimation, exact tests, generalized linear models
6748 and quasi-likelihood tests. It be applied to differential signal analysis of
6749 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6751 (license license:gpl2+)))
6753 (define-public r-variantannotation
6755 (name "r-variantannotation")
6759 (uri (bioconductor-uri "VariantAnnotation" version))
6762 "0sr3vdn85x5zdxh80cfwlpfdpi2hmjy3fwi00ac3jya4v145vawr"))))
6764 `((upstream-name . "VariantAnnotation")))
6768 `(("r-annotationdbi" ,r-annotationdbi)
6769 ("r-biobase" ,r-biobase)
6770 ("r-biocgenerics" ,r-biocgenerics)
6771 ("r-biostrings" ,r-biostrings)
6772 ("r-bsgenome" ,r-bsgenome)
6774 ("r-genomeinfodb" ,r-genomeinfodb)
6775 ("r-genomicfeatures" ,r-genomicfeatures)
6776 ("r-genomicranges" ,r-genomicranges)
6777 ("r-iranges" ,r-iranges)
6778 ("r-summarizedexperiment" ,r-summarizedexperiment)
6779 ("r-rsamtools" ,r-rsamtools)
6780 ("r-rtracklayer" ,r-rtracklayer)
6781 ("r-s4vectors" ,r-s4vectors)
6782 ("r-xvector" ,r-xvector)
6783 ("r-zlibbioc" ,r-zlibbioc)))
6784 (build-system r-build-system)
6785 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6786 (synopsis "Package for annotation of genetic variants")
6787 (description "This R package can annotate variants, compute amino acid
6788 coding changes and predict coding outcomes.")
6789 (license license:artistic2.0)))
6791 (define-public r-limma
6797 (uri (bioconductor-uri "limma" version))
6800 "0p2ayha9g9w5r8s7pgdf16mkmdbqwh6f35jh07g3b8gyra48gwiw"))))
6801 (build-system r-build-system)
6802 (home-page "http://bioinf.wehi.edu.au/limma")
6803 (synopsis "Package for linear models for microarray and RNA-seq data")
6804 (description "This package can be used for the analysis of gene expression
6805 studies, especially the use of linear models for analysing designed experiments
6806 and the assessment of differential expression. The analysis methods apply to
6807 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6808 (license license:gpl2+)))
6810 (define-public r-xvector
6816 (uri (bioconductor-uri "XVector" version))
6819 "01n09f4jdm60684lzikp02zf9gjan8bdrjx740vggr21q9fa69wn"))))
6821 `((upstream-name . "XVector")))
6822 (build-system r-build-system)
6825 (modify-phases %standard-phases
6826 (add-after 'unpack 'use-system-zlib
6828 (substitute* "DESCRIPTION"
6829 (("zlibbioc, ") ""))
6830 (substitute* "NAMESPACE"
6831 (("import\\(zlibbioc\\)") ""))
6836 `(("r-biocgenerics" ,r-biocgenerics)
6837 ("r-iranges" ,r-iranges)
6838 ("r-s4vectors" ,r-s4vectors)))
6839 (home-page "http://bioconductor.org/packages/XVector")
6840 (synopsis "Representation and manpulation of external sequences")
6842 "This package provides memory efficient S4 classes for storing sequences
6843 \"externally\" (behind an R external pointer, or on disk).")
6844 (license license:artistic2.0)))
6846 (define-public r-genomicranges
6848 (name "r-genomicranges")
6852 (uri (bioconductor-uri "GenomicRanges" version))
6855 "1y15kg1q81h8rmga83ljiwr8whkajcargfjiljr212d6if17ys1z"))))
6857 `((upstream-name . "GenomicRanges")))
6858 (build-system r-build-system)
6860 `(("r-biocgenerics" ,r-biocgenerics)
6861 ("r-genomeinfodb" ,r-genomeinfodb)
6862 ("r-iranges" ,r-iranges)
6863 ("r-s4vectors" ,r-s4vectors)
6864 ("r-xvector" ,r-xvector)))
6865 (home-page "http://bioconductor.org/packages/GenomicRanges")
6866 (synopsis "Representation and manipulation of genomic intervals")
6868 "This package provides tools to efficiently represent and manipulate
6869 genomic annotations and alignments is playing a central role when it comes to
6870 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6871 GenomicRanges package defines general purpose containers for storing and
6872 manipulating genomic intervals and variables defined along a genome.")
6873 (license license:artistic2.0)))
6875 (define-public r-biobase
6881 (uri (bioconductor-uri "Biobase" version))
6884 "0sr48nqx5bqid4g6lr9zr9286xh842w717yvmssvddb5xxynib6f"))))
6886 `((upstream-name . "Biobase")))
6887 (build-system r-build-system)
6889 `(("r-biocgenerics" ,r-biocgenerics)))
6890 (home-page "http://bioconductor.org/packages/Biobase")
6891 (synopsis "Base functions for Bioconductor")
6893 "This package provides functions that are needed by many other packages
6894 on Bioconductor or which replace R functions.")
6895 (license license:artistic2.0)))
6897 (define-public r-annotationdbi
6899 (name "r-annotationdbi")
6903 (uri (bioconductor-uri "AnnotationDbi" version))
6906 "1lsamnbf07zzsy5asy5hn97n2a4layv58w2bzd90ikcdx0gmzarj"))))
6908 `((upstream-name . "AnnotationDbi")))
6909 (build-system r-build-system)
6911 `(("r-biobase" ,r-biobase)
6912 ("r-biocgenerics" ,r-biocgenerics)
6914 ("r-iranges" ,r-iranges)
6915 ("r-rsqlite" ,r-rsqlite)
6916 ("r-s4vectors" ,r-s4vectors)))
6917 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6918 (synopsis "Annotation database interface")
6920 "This package provides user interface and database connection code for
6921 annotation data packages using SQLite data storage.")
6922 (license license:artistic2.0)))
6924 (define-public r-biomart
6930 (uri (bioconductor-uri "biomaRt" version))
6933 "0fhpbjlsgbqxrpj6nzhhk9q3ph81n5x4p7mmd097xjjn6b05w1d8"))))
6935 `((upstream-name . "biomaRt")))
6936 (build-system r-build-system)
6938 `(("r-annotationdbi" ,r-annotationdbi)
6939 ("r-rcurl" ,r-rcurl)
6941 (home-page "http://bioconductor.org/packages/biomaRt")
6942 (synopsis "Interface to BioMart databases")
6944 "biomaRt provides an interface to a growing collection of databases
6945 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6946 package enables retrieval of large amounts of data in a uniform way without
6947 the need to know the underlying database schemas or write complex SQL queries.
6948 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6949 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6950 users direct access to a diverse set of data and enable a wide range of
6951 powerful online queries from gene annotation to database mining.")
6952 (license license:artistic2.0)))
6954 (define-public r-biocparallel
6956 (name "r-biocparallel")
6960 (uri (bioconductor-uri "BiocParallel" version))
6963 "08mdfxyk9nwz77v0xhlvs19p2wj0phgm5c5b25vm0xh3749njsp0"))))
6965 `((upstream-name . "BiocParallel")))
6966 (build-system r-build-system)
6968 `(("r-futile-logger" ,r-futile-logger)
6969 ("r-snow" ,r-snow)))
6970 (home-page "http://bioconductor.org/packages/BiocParallel")
6971 (synopsis "Bioconductor facilities for parallel evaluation")
6973 "This package provides modified versions and novel implementation of
6974 functions for parallel evaluation, tailored to use with Bioconductor
6976 (license (list license:gpl2+ license:gpl3+))))
6978 (define-public r-biostrings
6980 (name "r-biostrings")
6984 (uri (bioconductor-uri "Biostrings" version))
6987 "12c5abgshwq86357jr0r9039y6vl4d6ngysy89rsnr23ldnsirjp"))))
6989 `((upstream-name . "Biostrings")))
6990 (build-system r-build-system)
6992 `(("r-biocgenerics" ,r-biocgenerics)
6993 ("r-iranges" ,r-iranges)
6994 ("r-s4vectors" ,r-s4vectors)
6995 ("r-xvector" ,r-xvector)))
6996 (home-page "http://bioconductor.org/packages/Biostrings")
6997 (synopsis "String objects and algorithms for biological sequences")
6999 "This package provides memory efficient string containers, string
7000 matching algorithms, and other utilities, for fast manipulation of large
7001 biological sequences or sets of sequences.")
7002 (license license:artistic2.0)))
7004 (define-public r-rsamtools
7006 (name "r-rsamtools")
7010 (uri (bioconductor-uri "Rsamtools" version))
7013 "1zx6vhdz3lksbfy98jj3qzl7cxgspigm2pbsd5835b12r6mc5w6d"))))
7015 `((upstream-name . "Rsamtools")))
7016 (build-system r-build-system)
7019 (modify-phases %standard-phases
7020 (add-after 'unpack 'use-system-zlib
7022 (substitute* "DESCRIPTION"
7023 (("zlibbioc, ") ""))
7024 (substitute* "NAMESPACE"
7025 (("import\\(zlibbioc\\)") ""))
7030 `(("r-biocgenerics" ,r-biocgenerics)
7031 ("r-biocparallel" ,r-biocparallel)
7032 ("r-biostrings" ,r-biostrings)
7033 ("r-bitops" ,r-bitops)
7034 ("r-genomeinfodb" ,r-genomeinfodb)
7035 ("r-genomicranges" ,r-genomicranges)
7036 ("r-iranges" ,r-iranges)
7037 ("r-s4vectors" ,r-s4vectors)
7038 ("r-xvector" ,r-xvector)))
7039 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7040 (synopsis "Interface to samtools, bcftools, and tabix")
7042 "This package provides an interface to the 'samtools', 'bcftools', and
7043 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7044 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7046 (license license:expat)))
7048 (define-public r-delayedarray
7050 (name "r-delayedarray")
7054 (uri (bioconductor-uri "DelayedArray" version))
7057 "02dfqp4md9xaqjj712ijc3jswghmipr5hwkd5hr0x1xi6l2fb69g"))))
7059 `((upstream-name . "DelayedArray")))
7060 (build-system r-build-system)
7062 `(("r-biocgenerics" ,r-biocgenerics)
7063 ("r-s4vectors" ,r-s4vectors)
7064 ("r-iranges" ,r-iranges)
7065 ("r-matrixstats" ,r-matrixstats)))
7066 (home-page "http://bioconductor.org/packages/DelayedArray")
7067 (synopsis "Delayed operations on array-like objects")
7069 "Wrapping an array-like object (typically an on-disk object) in a
7070 @code{DelayedArray} object allows one to perform common array operations on it
7071 without loading the object in memory. In order to reduce memory usage and
7072 optimize performance, operations on the object are either delayed or executed
7073 using a block processing mechanism. Note that this also works on in-memory
7074 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7075 @code{Matrix} objects, and ordinary arrays and data frames.")
7076 (license license:artistic2.0)))
7078 (define-public r-summarizedexperiment
7080 (name "r-summarizedexperiment")
7084 (uri (bioconductor-uri "SummarizedExperiment" version))
7087 "0j7xn7pk52d383fb1wplcggacl2586c4zi0alkgfc3wz7qq9w13s"))))
7089 `((upstream-name . "SummarizedExperiment")))
7090 (build-system r-build-system)
7092 `(("r-biobase" ,r-biobase)
7093 ("r-biocgenerics" ,r-biocgenerics)
7094 ("r-delayedarray" ,r-delayedarray)
7095 ("r-genomeinfodb" ,r-genomeinfodb)
7096 ("r-genomicranges" ,r-genomicranges)
7097 ("r-iranges" ,r-iranges)
7098 ("r-matrix" ,r-matrix)
7099 ("r-s4vectors" ,r-s4vectors)))
7100 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
7101 (synopsis "Container for representing genomic ranges by sample")
7103 "The SummarizedExperiment container contains one or more assays, each
7104 represented by a matrix-like object of numeric or other mode. The rows
7105 typically represent genomic ranges of interest and the columns represent
7107 (license license:artistic2.0)))
7109 (define-public r-genomicalignments
7111 (name "r-genomicalignments")
7115 (uri (bioconductor-uri "GenomicAlignments" version))
7118 "127690sys4i5q3l4vxnjg4xg8q19qlw2258vgs5d1156w9ypp04h"))))
7120 `((upstream-name . "GenomicAlignments")))
7121 (build-system r-build-system)
7123 `(("r-biocgenerics" ,r-biocgenerics)
7124 ("r-biocparallel" ,r-biocparallel)
7125 ("r-biostrings" ,r-biostrings)
7126 ("r-genomeinfodb" ,r-genomeinfodb)
7127 ("r-genomicranges" ,r-genomicranges)
7128 ("r-iranges" ,r-iranges)
7129 ("r-rsamtools" ,r-rsamtools)
7130 ("r-s4vectors" ,r-s4vectors)
7131 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7132 (home-page "http://bioconductor.org/packages/GenomicAlignments")
7133 (synopsis "Representation and manipulation of short genomic alignments")
7135 "This package provides efficient containers for storing and manipulating
7136 short genomic alignments (typically obtained by aligning short reads to a
7137 reference genome). This includes read counting, computing the coverage,
7138 junction detection, and working with the nucleotide content of the
7140 (license license:artistic2.0)))
7142 (define-public r-rtracklayer
7144 (name "r-rtracklayer")
7148 (uri (bioconductor-uri "rtracklayer" version))
7151 "050q1rv04w31168ljr975vxva31n9lqdx84rnmsk6zcr6p640ffp"))))
7152 (build-system r-build-system)
7155 (modify-phases %standard-phases
7156 (add-after 'unpack 'use-system-zlib
7158 (substitute* "DESCRIPTION"
7159 (("zlibbioc, ") ""))
7160 (substitute* "NAMESPACE"
7161 (("import\\(zlibbioc\\)") ""))
7166 `(("r-biocgenerics" ,r-biocgenerics)
7167 ("r-biostrings" ,r-biostrings)
7168 ("r-genomeinfodb" ,r-genomeinfodb)
7169 ("r-genomicalignments" ,r-genomicalignments)
7170 ("r-genomicranges" ,r-genomicranges)
7171 ("r-iranges" ,r-iranges)
7172 ("r-rcurl" ,r-rcurl)
7173 ("r-rsamtools" ,r-rsamtools)
7174 ("r-s4vectors" ,r-s4vectors)
7176 ("r-xvector" ,r-xvector)))
7177 (home-page "http://bioconductor.org/packages/rtracklayer")
7178 (synopsis "R interface to genome browsers and their annotation tracks")
7180 "rtracklayer is an extensible framework for interacting with multiple
7181 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7182 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7183 built-in). The user may export/import tracks to/from the supported browsers,
7184 as well as query and modify the browser state, such as the current viewport.")
7185 (license license:artistic2.0)))
7187 (define-public r-genomicfeatures
7189 (name "r-genomicfeatures")
7193 (uri (bioconductor-uri "GenomicFeatures" version))
7196 "01ylvg275iy0cvsbxkbfxcf9pi9al597v5wnlqi2xdpmrcxyc3q0"))))
7198 `((upstream-name . "GenomicFeatures")))
7199 (build-system r-build-system)
7201 `(("r-annotationdbi" ,r-annotationdbi)
7202 ("r-biobase" ,r-biobase)
7203 ("r-biocgenerics" ,r-biocgenerics)
7204 ("r-biomart" ,r-biomart)
7205 ("r-biostrings" ,r-biostrings)
7207 ("r-genomeinfodb" ,r-genomeinfodb)
7208 ("r-genomicranges" ,r-genomicranges)
7209 ("r-iranges" ,r-iranges)
7210 ("r-rcurl" ,r-rcurl)
7211 ("r-rsqlite" ,r-rsqlite)
7212 ("r-rtracklayer" ,r-rtracklayer)
7213 ("r-s4vectors" ,r-s4vectors)
7214 ("r-xvector" ,r-xvector)))
7215 (home-page "http://bioconductor.org/packages/GenomicFeatures")
7216 (synopsis "Tools for working with transcript centric annotations")
7218 "This package provides a set of tools and methods for making and
7219 manipulating transcript centric annotations. With these tools the user can
7220 easily download the genomic locations of the transcripts, exons and cds of a
7221 given organism, from either the UCSC Genome Browser or a BioMart
7222 database (more sources will be supported in the future). This information is
7223 then stored in a local database that keeps track of the relationship between
7224 transcripts, exons, cds and genes. Flexible methods are provided for
7225 extracting the desired features in a convenient format.")
7226 (license license:artistic2.0)))
7228 (define-public r-go-db
7234 (uri (string-append "http://www.bioconductor.org/packages/"
7235 "release/data/annotation/src/contrib/GO.db_"
7239 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7241 `((upstream-name . "GO.db")))
7242 (build-system r-build-system)
7244 `(("r-annotationdbi" ,r-annotationdbi)))
7245 (home-page "http://bioconductor.org/packages/GO.db")
7246 (synopsis "Annotation maps describing the entire Gene Ontology")
7248 "The purpose of this GO.db annotation package is to provide detailed
7249 information about the latest version of the Gene Ontologies.")
7250 (license license:artistic2.0)))
7252 (define-public r-graph
7258 (uri (bioconductor-uri "graph" version))
7261 "0hx9wslnrci7c5i1gd1zlpjmgrkdnx9gabfgmzzwfnykk1mdvvna"))))
7262 (build-system r-build-system)
7264 `(("r-biocgenerics" ,r-biocgenerics)))
7265 (home-page "http://bioconductor.org/packages/graph")
7266 (synopsis "Handle graph data structures in R")
7268 "This package implements some simple graph handling capabilities for R.")
7269 (license license:artistic2.0)))
7271 (define-public r-topgo
7277 (uri (bioconductor-uri "topGO" version))
7280 "04kvxz9qsxfz0np7wlrzp4r95nykz94x7mqpyyk76f90g6m66vcc"))))
7282 `((upstream-name . "topGO")))
7283 (build-system r-build-system)
7285 `(("r-annotationdbi" ,r-annotationdbi)
7287 ("r-biobase" ,r-biobase)
7288 ("r-biocgenerics" ,r-biocgenerics)
7289 ("r-go-db" ,r-go-db)
7290 ("r-graph" ,r-graph)
7291 ("r-lattice" ,r-lattice)
7292 ("r-matrixstats" ,r-matrixstats)
7293 ("r-sparsem" ,r-sparsem)))
7294 (home-page "http://bioconductor.org/packages/topGO")
7295 (synopsis "Enrichment analysis for gene ontology")
7297 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7298 terms while accounting for the topology of the GO graph. Different test
7299 statistics and different methods for eliminating local similarities and
7300 dependencies between GO terms can be implemented and applied.")
7301 ;; Any version of the LGPL applies.
7302 (license license:lgpl2.1+)))
7304 (define-public r-bsgenome
7310 (uri (bioconductor-uri "BSgenome" version))
7313 "18dlknwk3xvi52hamxf9pl5bjc5806mpw98xwvx5xajn8mrxiy5h"))))
7315 `((upstream-name . "BSgenome")))
7316 (build-system r-build-system)
7318 `(("r-biocgenerics" ,r-biocgenerics)
7319 ("r-biostrings" ,r-biostrings)
7320 ("r-genomeinfodb" ,r-genomeinfodb)
7321 ("r-genomicranges" ,r-genomicranges)
7322 ("r-iranges" ,r-iranges)
7323 ("r-rsamtools" ,r-rsamtools)
7324 ("r-rtracklayer" ,r-rtracklayer)
7325 ("r-s4vectors" ,r-s4vectors)
7326 ("r-xvector" ,r-xvector)))
7327 (home-page "http://bioconductor.org/packages/BSgenome")
7328 (synopsis "Infrastructure for Biostrings-based genome data packages")
7330 "This package provides infrastructure shared by all Biostrings-based
7331 genome data packages and support for efficient SNP representation.")
7332 (license license:artistic2.0)))
7334 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7336 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7340 ;; We cannot use bioconductor-uri here because this tarball is
7341 ;; located under "data/annotation/" instead of "bioc/".
7342 (uri (string-append "http://www.bioconductor.org/packages/"
7343 "release/data/annotation/src/contrib/"
7344 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7348 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7350 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7351 (build-system r-build-system)
7352 ;; As this package provides little more than a very large data file it
7353 ;; doesn't make sense to build substitutes.
7354 (arguments `(#:substitutable? #f))
7356 `(("r-bsgenome" ,r-bsgenome)))
7358 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7359 (synopsis "Full genome sequences for Homo sapiens")
7361 "This package provides full genome sequences for Homo sapiens from
7362 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7363 (license license:artistic2.0)))
7365 (define-public r-impute
7371 (uri (bioconductor-uri "impute" version))
7374 "0va45vfixy3np549md87h3b3rbavm54gfnmnjhpr9hf02lll6zxs"))))
7376 `(("gfortran" ,gfortran)))
7377 (build-system r-build-system)
7378 (home-page "http://bioconductor.org/packages/impute")
7379 (synopsis "Imputation for microarray data")
7381 "This package provides a function to impute missing gene expression
7382 microarray data, using nearest neighbor averaging.")
7383 (license license:gpl2+)))
7385 (define-public r-seqpattern
7387 (name "r-seqpattern")
7391 (uri (bioconductor-uri "seqPattern" version))
7394 "0yw5251sirv3283xgmfmfbf900xp8dwvqfk88mr945s3by5hx99v"))))
7396 `((upstream-name . "seqPattern")))
7397 (build-system r-build-system)
7399 `(("r-biostrings" ,r-biostrings)
7400 ("r-genomicranges" ,r-genomicranges)
7401 ("r-iranges" ,r-iranges)
7402 ("r-kernsmooth" ,r-kernsmooth)
7403 ("r-plotrix" ,r-plotrix)))
7404 (home-page "http://bioconductor.org/packages/seqPattern")
7405 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7407 "This package provides tools to visualize oligonucleotide patterns and
7408 sequence motif occurrences across a large set of sequences centred at a common
7409 reference point and sorted by a user defined feature.")
7410 (license license:gpl3+)))
7412 (define-public r-genomation
7414 (name "r-genomation")
7418 (uri (bioconductor-uri "genomation" version))
7421 "0r71nf8p3aq3yffqxg4yir1zmm7rar5a57nmy1kpqpn8kaf2svjl"))))
7422 (build-system r-build-system)
7424 `(("r-biostrings" ,r-biostrings)
7425 ("r-bsgenome" ,r-bsgenome)
7426 ("r-data-table" ,r-data-table)
7427 ("r-genomeinfodb" ,r-genomeinfodb)
7428 ("r-genomicalignments" ,r-genomicalignments)
7429 ("r-genomicranges" ,r-genomicranges)
7430 ("r-ggplot2" ,r-ggplot2)
7431 ("r-gridbase" ,r-gridbase)
7432 ("r-impute" ,r-impute)
7433 ("r-iranges" ,r-iranges)
7434 ("r-matrixstats" ,r-matrixstats)
7435 ("r-plotrix" ,r-plotrix)
7438 ("r-readr" ,r-readr)
7439 ("r-reshape2" ,r-reshape2)
7440 ("r-rhtslib" ,r-rhtslib)
7441 ("r-rsamtools" ,r-rsamtools)
7442 ("r-rtracklayer" ,r-rtracklayer)
7443 ("r-runit" ,r-runit)
7444 ("r-s4vectors" ,r-s4vectors)
7445 ("r-seqpattern" ,r-seqpattern)))
7448 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7449 (synopsis "Summary, annotation and visualization of genomic data")
7451 "This package provides a package for summary and annotation of genomic
7452 intervals. Users can visualize and quantify genomic intervals over
7453 pre-defined functional regions, such as promoters, exons, introns, etc. The
7454 genomic intervals represent regions with a defined chromosome position, which
7455 may be associated with a score, such as aligned reads from HT-seq experiments,
7456 TF binding sites, methylation scores, etc. The package can use any tabular
7457 genomic feature data as long as it has minimal information on the locations of
7458 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7459 (license license:artistic2.0)))
7461 (define-public r-genomationdata
7463 (name "r-genomationdata")
7467 ;; We cannot use bioconductor-uri here because this tarball is
7468 ;; located under "data/annotation/" instead of "bioc/".
7469 (uri (string-append "https://bioconductor.org/packages/"
7470 "release/data/experiment/src/contrib/"
7471 "genomationData_" version ".tar.gz"))
7474 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7475 (build-system r-build-system)
7476 ;; As this package provides little more than large data files, it doesn't
7477 ;; make sense to build substitutes.
7478 (arguments `(#:substitutable? #f))
7480 `(("r-knitr" ,r-knitr)))
7481 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7482 (synopsis "Experimental data for use with the genomation package")
7484 "This package contains experimental genetic data for use with the
7485 genomation package. Included are Chip Seq, Methylation and Cage data,
7486 downloaded from Encode.")
7487 (license license:gpl3+)))
7489 (define-public r-org-hs-eg-db
7491 (name "r-org-hs-eg-db")
7495 ;; We cannot use bioconductor-uri here because this tarball is
7496 ;; located under "data/annotation/" instead of "bioc/".
7497 (uri (string-append "http://www.bioconductor.org/packages/"
7498 "release/data/annotation/src/contrib/"
7499 "org.Hs.eg.db_" version ".tar.gz"))
7502 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7504 `((upstream-name . "org.Hs.eg.db")))
7505 (build-system r-build-system)
7507 `(("r-annotationdbi" ,r-annotationdbi)))
7508 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7509 (synopsis "Genome wide annotation for Human")
7511 "This package provides mappings from Entrez gene identifiers to various
7512 annotations for the human genome.")
7513 (license license:artistic2.0)))
7515 (define-public r-org-ce-eg-db
7517 (name "r-org-ce-eg-db")
7521 ;; We cannot use bioconductor-uri here because this tarball is
7522 ;; located under "data/annotation/" instead of "bioc/".
7523 (uri (string-append "http://www.bioconductor.org/packages/"
7524 "release/data/annotation/src/contrib/"
7525 "org.Ce.eg.db_" version ".tar.gz"))
7528 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7530 `((upstream-name . "org.Ce.eg.db")))
7531 (build-system r-build-system)
7533 `(("r-annotationdbi" ,r-annotationdbi)))
7534 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7535 (synopsis "Genome wide annotation for Worm")
7537 "This package provides mappings from Entrez gene identifiers to various
7538 annotations for the genome of the model worm Caenorhabditis elegans.")
7539 (license license:artistic2.0)))
7541 (define-public r-org-dm-eg-db
7543 (name "r-org-dm-eg-db")
7547 ;; We cannot use bioconductor-uri here because this tarball is
7548 ;; located under "data/annotation/" instead of "bioc/".
7549 (uri (string-append "http://www.bioconductor.org/packages/"
7550 "release/data/annotation/src/contrib/"
7551 "org.Dm.eg.db_" version ".tar.gz"))
7554 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7556 `((upstream-name . "org.Dm.eg.db")))
7557 (build-system r-build-system)
7559 `(("r-annotationdbi" ,r-annotationdbi)))
7560 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7561 (synopsis "Genome wide annotation for Fly")
7563 "This package provides mappings from Entrez gene identifiers to various
7564 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7565 (license license:artistic2.0)))
7567 (define-public r-org-mm-eg-db
7569 (name "r-org-mm-eg-db")
7573 ;; We cannot use bioconductor-uri here because this tarball is
7574 ;; located under "data/annotation/" instead of "bioc/".
7575 (uri (string-append "http://www.bioconductor.org/packages/"
7576 "release/data/annotation/src/contrib/"
7577 "org.Mm.eg.db_" version ".tar.gz"))
7580 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7582 `((upstream-name . "org.Mm.eg.db")))
7583 (build-system r-build-system)
7585 `(("r-annotationdbi" ,r-annotationdbi)))
7586 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7587 (synopsis "Genome wide annotation for Mouse")
7589 "This package provides mappings from Entrez gene identifiers to various
7590 annotations for the genome of the model mouse Mus musculus.")
7591 (license license:artistic2.0)))
7593 (define-public r-seqlogo
7600 (uri (bioconductor-uri "seqLogo" version))
7603 "19d5zmy7m8svljwgbmrb4vxkq18slq0f3all6k2ayv42b8w44h6q"))))
7604 (properties `((upstream-name . "seqLogo")))
7605 (build-system r-build-system)
7606 (home-page "http://bioconductor.org/packages/seqLogo")
7607 (synopsis "Sequence logos for DNA sequence alignments")
7609 "seqLogo takes the position weight matrix of a DNA sequence motif and
7610 plots the corresponding sequence logo as introduced by Schneider and
7612 (license license:lgpl2.0+)))
7614 (define-public r-bsgenome-hsapiens-ucsc-hg19
7616 (name "r-bsgenome-hsapiens-ucsc-hg19")
7620 ;; We cannot use bioconductor-uri here because this tarball is
7621 ;; located under "data/annotation/" instead of "bioc/".
7622 (uri (string-append "http://www.bioconductor.org/packages/"
7623 "release/data/annotation/src/contrib/"
7624 "BSgenome.Hsapiens.UCSC.hg19_"
7628 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7630 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7631 (build-system r-build-system)
7632 ;; As this package provides little more than a very large data file it
7633 ;; doesn't make sense to build substitutes.
7634 (arguments `(#:substitutable? #f))
7636 `(("r-bsgenome" ,r-bsgenome)))
7638 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7639 (synopsis "Full genome sequences for Homo sapiens")
7641 "This package provides full genome sequences for Homo sapiens as provided
7642 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7643 (license license:artistic2.0)))
7645 (define-public r-bsgenome-mmusculus-ucsc-mm9
7647 (name "r-bsgenome-mmusculus-ucsc-mm9")
7651 ;; We cannot use bioconductor-uri here because this tarball is
7652 ;; located under "data/annotation/" instead of "bioc/".
7653 (uri (string-append "http://www.bioconductor.org/packages/"
7654 "release/data/annotation/src/contrib/"
7655 "BSgenome.Mmusculus.UCSC.mm9_"
7659 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7661 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7662 (build-system r-build-system)
7663 ;; As this package provides little more than a very large data file it
7664 ;; doesn't make sense to build substitutes.
7665 (arguments `(#:substitutable? #f))
7667 `(("r-bsgenome" ,r-bsgenome)))
7669 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7670 (synopsis "Full genome sequences for Mouse")
7672 "This package provides full genome sequences for Mus musculus (Mouse) as
7673 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7674 (license license:artistic2.0)))
7676 (define-public r-bsgenome-mmusculus-ucsc-mm10
7678 (name "r-bsgenome-mmusculus-ucsc-mm10")
7682 ;; We cannot use bioconductor-uri here because this tarball is
7683 ;; located under "data/annotation/" instead of "bioc/".
7684 (uri (string-append "http://www.bioconductor.org/packages/"
7685 "release/data/annotation/src/contrib/"
7686 "BSgenome.Mmusculus.UCSC.mm10_"
7690 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7692 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7693 (build-system r-build-system)
7694 ;; As this package provides little more than a very large data file it
7695 ;; doesn't make sense to build substitutes.
7696 (arguments `(#:substitutable? #f))
7698 `(("r-bsgenome" ,r-bsgenome)))
7700 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7701 (synopsis "Full genome sequences for Mouse")
7703 "This package provides full genome sequences for Mus
7704 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7705 in Biostrings objects.")
7706 (license license:artistic2.0)))
7708 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7710 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7714 ;; We cannot use bioconductor-uri here because this tarball is
7715 ;; located under "data/annotation/" instead of "bioc/".
7716 (uri (string-append "http://www.bioconductor.org/packages/"
7717 "release/data/annotation/src/contrib/"
7718 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7722 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7724 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7725 (build-system r-build-system)
7726 ;; As this package provides little more than a very large data file it
7727 ;; doesn't make sense to build substitutes.
7728 (arguments `(#:substitutable? #f))
7730 `(("r-bsgenome" ,r-bsgenome)
7731 ("r-genomicfeatures" ,r-genomicfeatures)
7732 ("r-annotationdbi" ,r-annotationdbi)))
7734 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7735 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7737 "This package loads a TxDb object, which is an R interface to
7738 prefabricated databases contained in this package. This package provides
7739 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7740 based on the knownGene track.")
7741 (license license:artistic2.0)))
7743 (define-public r-bsgenome-celegans-ucsc-ce6
7745 (name "r-bsgenome-celegans-ucsc-ce6")
7749 ;; We cannot use bioconductor-uri here because this tarball is
7750 ;; located under "data/annotation/" instead of "bioc/".
7751 (uri (string-append "http://www.bioconductor.org/packages/"
7752 "release/data/annotation/src/contrib/"
7753 "BSgenome.Celegans.UCSC.ce6_"
7757 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7759 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7760 (build-system r-build-system)
7761 ;; As this package provides little more than a very large data file it
7762 ;; doesn't make sense to build substitutes.
7763 (arguments `(#:substitutable? #f))
7765 `(("r-bsgenome" ,r-bsgenome)))
7767 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7768 (synopsis "Full genome sequences for Worm")
7770 "This package provides full genome sequences for Caenorhabditis
7771 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7773 (license license:artistic2.0)))
7775 (define-public r-bsgenome-celegans-ucsc-ce10
7777 (name "r-bsgenome-celegans-ucsc-ce10")
7781 ;; We cannot use bioconductor-uri here because this tarball is
7782 ;; located under "data/annotation/" instead of "bioc/".
7783 (uri (string-append "http://www.bioconductor.org/packages/"
7784 "release/data/annotation/src/contrib/"
7785 "BSgenome.Celegans.UCSC.ce10_"
7789 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7791 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7792 (build-system r-build-system)
7793 ;; As this package provides little more than a very large data file it
7794 ;; doesn't make sense to build substitutes.
7795 (arguments `(#:substitutable? #f))
7797 `(("r-bsgenome" ,r-bsgenome)))
7799 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7800 (synopsis "Full genome sequences for Worm")
7802 "This package provides full genome sequences for Caenorhabditis
7803 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7805 (license license:artistic2.0)))
7807 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7809 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7813 ;; We cannot use bioconductor-uri here because this tarball is
7814 ;; located under "data/annotation/" instead of "bioc/".
7815 (uri (string-append "http://www.bioconductor.org/packages/"
7816 "release/data/annotation/src/contrib/"
7817 "BSgenome.Dmelanogaster.UCSC.dm3_"
7821 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7823 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7824 (build-system r-build-system)
7825 ;; As this package provides little more than a very large data file it
7826 ;; doesn't make sense to build substitutes.
7827 (arguments `(#:substitutable? #f))
7829 `(("r-bsgenome" ,r-bsgenome)))
7831 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7832 (synopsis "Full genome sequences for Fly")
7834 "This package provides full genome sequences for Drosophila
7835 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7836 Biostrings objects.")
7837 (license license:artistic2.0)))
7839 (define-public r-motifrg
7846 (uri (bioconductor-uri "motifRG" version))
7849 "0lxxpqyljiyk73vyq6ss46q13g81pm24q87mkzdsqlr5zx427ch6"))))
7850 (properties `((upstream-name . "motifRG")))
7851 (build-system r-build-system)
7853 `(("r-biostrings" ,r-biostrings)
7854 ("r-bsgenome" ,r-bsgenome)
7855 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7856 ("r-iranges" ,r-iranges)
7857 ("r-seqlogo" ,r-seqlogo)
7858 ("r-xvector" ,r-xvector)))
7859 (home-page "http://bioconductor.org/packages/motifRG")
7860 (synopsis "Discover motifs in high throughput sequencing data")
7862 "This package provides tools for discriminative motif discovery in high
7863 throughput genetic sequencing data sets using regression methods.")
7864 (license license:artistic2.0)))
7866 (define-public r-qtl
7873 (uri (string-append "mirror://cran/src/contrib/qtl_"
7877 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
7878 (build-system r-build-system)
7879 (home-page "http://rqtl.org/")
7880 (synopsis "R package for analyzing QTL experiments in genetics")
7881 (description "R/qtl is an extension library for the R statistics
7882 system. It is used to analyze experimental crosses for identifying
7883 genes contributing to variation in quantitative traits (so-called
7884 quantitative trait loci, QTLs).
7886 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7887 identify genotyping errors, and to perform single-QTL and two-QTL,
7888 two-dimensional genome scans.")
7889 (license license:gpl3)))
7891 (define-public r-zlibbioc
7897 (uri (bioconductor-uri "zlibbioc" version))
7900 "1kdgwwlh39mgwzj3zq71za4iv40sq625ghnyrndv5wrivrcr2igv"))))
7902 `((upstream-name . "zlibbioc")))
7903 (build-system r-build-system)
7904 (home-page "https://bioconductor.org/packages/zlibbioc")
7905 (synopsis "Provider for zlib-1.2.5 to R packages")
7906 (description "This package uses the source code of zlib-1.2.5 to create
7907 libraries for systems that do not have these available via other means.")
7908 (license license:artistic2.0)))
7910 (define-public r-r4rna
7917 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7921 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7922 (build-system r-build-system)
7924 `(("r-optparse" ,r-optparse)
7925 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7926 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7927 (synopsis "Analysis framework for RNA secondary structure")
7929 "The R4RNA package aims to be a general framework for the analysis of RNA
7930 secondary structure and comparative analysis in R.")
7931 (license license:gpl3+)))
7933 (define-public r-rhtslib
7940 (uri (bioconductor-uri "Rhtslib" version))
7943 "0jj5h81z5gyf4j3lp2l3zsm6pgbmalgrngr8qdpygc20phndpp0b"))))
7944 (properties `((upstream-name . "Rhtslib")))
7945 (build-system r-build-system)
7947 `(("r-zlibbioc" ,r-zlibbioc)))
7951 `(("autoconf" ,autoconf)))
7952 (home-page "https://github.com/nhayden/Rhtslib")
7953 (synopsis "High-throughput sequencing library as an R package")
7955 "This package provides the HTSlib C library for high-throughput
7956 nucleotide sequence analysis. The package is primarily useful to developers
7957 of other R packages who wish to make use of HTSlib.")
7958 (license license:lgpl2.0+)))
7960 (define-public r-bamsignals
7962 (name "r-bamsignals")
7967 (uri (bioconductor-uri "bamsignals" version))
7970 "0knx69zzdaak2sjim8k9mygmcjxpa705m8013ld5zwpgi8dag9mc"))))
7971 (build-system r-build-system)
7973 `(("r-biocgenerics" ,r-biocgenerics)
7974 ("r-genomicranges" ,r-genomicranges)
7975 ("r-iranges" ,r-iranges)
7977 ("r-rhtslib" ,r-rhtslib)
7978 ("r-zlibbioc" ,r-zlibbioc)))
7981 (home-page "http://bioconductor.org/packages/bamsignals")
7982 (synopsis "Extract read count signals from bam files")
7984 "This package allows to efficiently obtain count vectors from indexed bam
7985 files. It counts the number of nucleotide sequence reads in given genomic
7986 ranges and it computes reads profiles and coverage profiles. It also handles
7988 (license license:gpl2+)))
7990 (define-public r-rcas
7996 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7998 (file-name (string-append name "-" version ".tar.gz"))
8001 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
8002 (build-system r-build-system)
8004 `(("r-knitr" ,r-knitr)
8005 ("r-testthat" ,r-testthat)
8006 ;; During vignette building knitr checks that "pandoc-citeproc"
8008 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8010 `(("r-data-table" ,r-data-table)
8011 ("r-biomart" ,r-biomart)
8012 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8013 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8014 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8015 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8016 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8017 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8018 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8019 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8020 ("r-topgo" ,r-topgo)
8022 ("r-plotly" ,r-plotly)
8023 ("r-plotrix" ,r-plotrix)
8024 ("r-motifrg" ,r-motifrg)
8025 ("r-genomation" ,r-genomation)
8026 ("r-genomicfeatures" ,r-genomicfeatures)
8027 ("r-rtracklayer" ,r-rtracklayer)
8028 ("r-rmarkdown" ,r-rmarkdown)))
8029 (synopsis "RNA-centric annotation system")
8031 "RCAS aims to be a standalone RNA-centric annotation system that provides
8032 intuitive reports and publication-ready graphics. This package provides the R
8033 library implementing most of the pipeline's features.")
8034 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8035 (license license:expat)))
8037 (define-public rcas-web
8044 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8045 "releases/download/v" version
8046 "/rcas-web-" version ".tar.gz"))
8049 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
8050 (build-system gnu-build-system)
8053 (modify-phases %standard-phases
8054 (add-after 'install 'wrap-executable
8055 (lambda* (#:key inputs outputs #:allow-other-keys)
8056 (let* ((out (assoc-ref outputs "out"))
8057 (json (assoc-ref inputs "guile-json"))
8058 (redis (assoc-ref inputs "guile-redis"))
8059 (path (string-append
8060 json "/share/guile/site/2.2:"
8061 redis "/share/guile/site/2.2")))
8062 (wrap-program (string-append out "/bin/rcas-web")
8063 `("GUILE_LOAD_PATH" ":" = (,path))
8064 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8065 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8068 `(("r-minimal" ,r-minimal)
8070 ("guile-next" ,guile-2.2)
8071 ("guile-json" ,guile-json)
8072 ("guile-redis" ,guile2.2-redis)))
8074 `(("pkg-config" ,pkg-config)))
8075 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8076 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8077 (description "This package provides a simple web interface for the
8078 @dfn{RNA-centric annotation system} (RCAS).")
8079 (license license:agpl3+)))
8081 (define-public r-mutationalpatterns
8083 (name "r-mutationalpatterns")
8088 (uri (bioconductor-uri "MutationalPatterns" version))
8091 "1s50diwh1j6vg3mgahh6bczvq74mfdbmwjrad4d5lh723gnc5pjg"))))
8092 (build-system r-build-system)
8094 `(("r-biocgenerics" ,r-biocgenerics)
8095 ("r-biostrings" ,r-biostrings)
8096 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8097 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8098 ("r-genomicranges" ,r-genomicranges)
8099 ("r-genomeinfodb" ,r-genomeinfodb)
8100 ("r-ggplot2" ,r-ggplot2)
8101 ("r-gridextra" ,r-gridextra)
8102 ("r-iranges" ,r-iranges)
8105 ("r-pracma" ,r-pracma)
8106 ("r-reshape2" ,r-reshape2)
8107 ("r-summarizedexperiment" ,r-summarizedexperiment)
8108 ("r-variantannotation" ,r-variantannotation)))
8109 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
8110 (synopsis "Extract and visualize mutational patterns in genomic data")
8111 (description "This package provides an extensive toolset for the
8112 characterization and visualization of a wide range of mutational patterns
8113 in SNV base substitution data.")
8114 (license license:expat)))
8116 (define-public r-wgcna
8123 (uri (cran-uri "WGCNA" version))
8126 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
8127 (properties `((upstream-name . "WGCNA")))
8128 (build-system r-build-system)
8130 `(("r-annotationdbi" ,r-annotationdbi)
8131 ("r-doparallel" ,r-doparallel)
8132 ("r-dynamictreecut" ,r-dynamictreecut)
8133 ("r-fastcluster" ,r-fastcluster)
8134 ("r-foreach" ,r-foreach)
8135 ("r-go-db" ,r-go-db)
8136 ("r-hmisc" ,r-hmisc)
8137 ("r-impute" ,r-impute)
8139 ("r-robust" ,r-robust)
8140 ("r-survival" ,r-survival)
8141 ("r-matrixstats" ,r-matrixstats)
8142 ("r-preprocesscore" ,r-preprocesscore)))
8144 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8145 (synopsis "Weighted correlation network analysis")
8147 "This package provides functions necessary to perform Weighted
8148 Correlation Network Analysis on high-dimensional data. It includes functions
8149 for rudimentary data cleaning, construction and summarization of correlation
8150 networks, module identification and functions for relating both variables and
8151 modules to sample traits. It also includes a number of utility functions for
8152 data manipulation and visualization.")
8153 (license license:gpl2+)))
8155 (define-public r-chipkernels
8156 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8159 (name "r-chipkernels")
8160 (version (string-append "1.1-" revision "." (string-take commit 9)))
8165 (url "https://github.com/ManuSetty/ChIPKernels.git")
8167 (file-name (string-append name "-" version))
8170 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8171 (build-system r-build-system)
8173 `(("r-iranges" ,r-iranges)
8174 ("r-xvector" ,r-xvector)
8175 ("r-biostrings" ,r-biostrings)
8176 ("r-bsgenome" ,r-bsgenome)
8177 ("r-gtools" ,r-gtools)
8178 ("r-genomicranges" ,r-genomicranges)
8179 ("r-sfsmisc" ,r-sfsmisc)
8180 ("r-kernlab" ,r-kernlab)
8181 ("r-s4vectors" ,r-s4vectors)
8182 ("r-biocgenerics" ,r-biocgenerics)))
8183 (home-page "https://github.com/ManuSetty/ChIPKernels")
8184 (synopsis "Build string kernels for DNA Sequence analysis")
8185 (description "ChIPKernels is an R package for building different string
8186 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8187 must be built and this dictionary can be used for determining kernels for DNA
8189 (license license:gpl2+))))
8191 (define-public r-seqgl
8198 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8199 "archive/" version ".tar.gz"))
8200 (file-name (string-append name "-" version ".tar.gz"))
8203 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8204 (build-system r-build-system)
8206 `(("r-biostrings" ,r-biostrings)
8207 ("r-chipkernels" ,r-chipkernels)
8208 ("r-genomicranges" ,r-genomicranges)
8209 ("r-spams" ,r-spams)
8210 ("r-wgcna" ,r-wgcna)
8211 ("r-fastcluster" ,r-fastcluster)))
8212 (home-page "https://github.com/ManuSetty/SeqGL")
8213 (synopsis "Group lasso for Dnase/ChIP-seq data")
8214 (description "SeqGL is a group lasso based algorithm to extract
8215 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8216 This package presents a method which uses group lasso to discriminate between
8217 bound and non bound genomic regions to accurately identify transcription
8218 factors bound at the specific regions.")
8219 (license license:gpl2+)))
8221 (define-public r-gkmsvm
8228 (uri (cran-uri "gkmSVM" version))
8231 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8232 (properties `((upstream-name . "gkmSVM")))
8233 (build-system r-build-system)
8235 `(("r-biocgenerics" ,r-biocgenerics)
8236 ("r-biostrings" ,r-biostrings)
8237 ("r-genomeinfodb" ,r-genomeinfodb)
8238 ("r-genomicranges" ,r-genomicranges)
8239 ("r-iranges" ,r-iranges)
8240 ("r-kernlab" ,r-kernlab)
8243 ("r-rtracklayer" ,r-rtracklayer)
8244 ("r-s4vectors" ,r-s4vectors)
8245 ("r-seqinr" ,r-seqinr)))
8246 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8247 (synopsis "Gapped-kmer support vector machine")
8249 "This R package provides tools for training gapped-kmer SVM classifiers
8250 for DNA and protein sequences. This package supports several sequence
8251 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8252 (license license:gpl2+)))
8254 (define-public r-tximport
8260 (uri (bioconductor-uri "tximport" version))
8263 "1mklb02bj4gnbjlmb7vv6k4lr3w9fp3pzli9rddbrwd0y5n8fcpx"))))
8264 (build-system r-build-system)
8265 (home-page "http://bioconductor.org/packages/tximport")
8266 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8268 "This package provides tools to import transcript-level abundance,
8269 estimated counts and transcript lengths, and to summarize them into matrices
8270 for use with downstream gene-level analysis packages. Average transcript
8271 length, weighted by sample-specific transcript abundance estimates, is
8272 provided as a matrix which can be used as an offset for different expression
8273 of gene-level counts.")
8274 (license license:gpl2+)))
8276 (define-public r-rhdf5
8282 (uri (bioconductor-uri "rhdf5" version))
8285 "1p6f5i6l44phl772a38x9cav2sya37bkqbkjzdc4pmyfzkv1j6hy"))))
8286 (build-system r-build-system)
8289 (modify-phases %standard-phases
8290 (add-after 'unpack 'unpack-smallhdf5
8291 (lambda* (#:key outputs #:allow-other-keys)
8292 (system* "tar" "-xzvf"
8293 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8294 (substitute* "src/Makevars"
8295 (("^.*cd hdf5source &&.*$") "")
8296 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8297 (("^.*rm -rf hdf5.*$") "")
8298 (("^.*mv hdf5source/hdf5 ..*$") ""))
8299 (substitute* "src/hdf5/configure"
8303 `(("r-zlibbioc" ,r-zlibbioc)))
8307 (home-page "http://bioconductor.org/packages/rhdf5")
8308 (synopsis "HDF5 interface to R")
8310 "This R/Bioconductor package provides an interface between HDF5 and R.
8311 HDF5's main features are the ability to store and access very large and/or
8312 complex datasets and a wide variety of metadata on mass storage (disk) through
8313 a completely portable file format. The rhdf5 package is thus suited for the
8314 exchange of large and/or complex datasets between R and other software
8315 package, and for letting R applications work on datasets that are larger than
8316 the available RAM.")
8317 (license license:artistic2.0)))
8319 (define-public r-annotationfilter
8321 (name "r-annotationfilter")
8325 (uri (bioconductor-uri "AnnotationFilter" version))
8328 "0pxvswjzwibdfmrkdragxmzcl844z73pmkn82z92wahwa6gjfyi7"))))
8330 `((upstream-name . "AnnotationFilter")))
8331 (build-system r-build-system)
8333 `(("r-genomicranges" ,r-genomicranges)
8334 ("r-lazyeval" ,r-lazyeval)))
8335 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8336 (synopsis "Facilities for filtering Bioconductor annotation resources")
8338 "This package provides classes and other infrastructure to implement
8339 filters for manipulating Bioconductor annotation resources. The filters are
8340 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8341 (license license:artistic2.0)))
8343 (define-public emboss
8349 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8350 (version-major+minor version) ".0/"
8351 "EMBOSS-" version ".tar.gz"))
8354 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8355 (build-system gnu-build-system)
8358 (list (string-append "--with-hpdf="
8359 (assoc-ref %build-inputs "libharu")))
8361 (modify-phases %standard-phases
8362 (add-after 'unpack 'fix-checks
8364 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8365 ;; and zlib, but assume that they are all found at the same
8367 (substitute* "configure.in"
8368 (("CHECK_PNGDRIVER")
8369 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8370 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8371 AM_CONDITIONAL(AMPNG, true)"))
8373 (add-after 'unpack 'disable-update-check
8375 ;; At build time there is no connection to the Internet, so
8376 ;; looking for updates will not work.
8377 (substitute* "Makefile.am"
8378 (("\\$\\(bindir\\)/embossupdate") ""))
8380 (add-before 'configure 'autogen
8381 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8387 ("libharu" ,libharu)
8390 `(("autoconf" ,autoconf)
8391 ("automake" ,automake)
8392 ("libtool" ,libtool)
8393 ("pkg-config" ,pkg-config)))
8394 (home-page "http://emboss.sourceforge.net")
8395 (synopsis "Molecular biology analysis suite")
8396 (description "EMBOSS is the \"European Molecular Biology Open Software
8397 Suite\". EMBOSS is an analysis package specially developed for the needs of
8398 the molecular biology (e.g. EMBnet) user community. The software
8399 automatically copes with data in a variety of formats and even allows
8400 transparent retrieval of sequence data from the web. It also provides a
8401 number of libraries for the development of software in the field of molecular
8402 biology. EMBOSS also integrates a range of currently available packages and
8403 tools for sequence analysis into a seamless whole.")
8404 (license license:gpl2+)))
8407 (let ((revision "1")
8408 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8411 ;; The version is 2.13.0 even though no release archives have been
8412 ;; published as yet.
8413 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8417 (url "https://github.com/arq5x/bits.git")
8419 (file-name (string-append name "-" version "-checkout"))
8422 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8423 (build-system gnu-build-system)
8425 `(#:tests? #f ;no tests included
8427 (modify-phases %standard-phases
8429 (add-after 'unpack 'remove-cuda
8431 (substitute* "Makefile"
8433 (("(bits_test_intersections) \\\\" _ match) match))
8436 (lambda* (#:key outputs #:allow-other-keys)
8438 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8443 (home-page "https://github.com/arq5x/bits")
8444 (synopsis "Implementation of binary interval search algorithm")
8445 (description "This package provides an implementation of the
8446 BITS (Binary Interval Search) algorithm, an approach to interval set
8447 intersection. It is especially suited for the comparison of diverse genomic
8448 datasets and the exploration of large datasets of genome
8449 intervals (e.g. genes, sequence alignments).")
8450 (license license:gpl2))))
8452 (define-public piranha
8453 ;; There is no release tarball for the latest version. The latest commit is
8454 ;; older than one year at the time of this writing.
8455 (let ((revision "1")
8456 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8459 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8463 (url "https://github.com/smithlabcode/piranha.git")
8467 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8468 (build-system gnu-build-system)
8470 `(#:test-target "test"
8472 (modify-phases %standard-phases
8473 (add-after 'unpack 'copy-smithlab-cpp
8474 (lambda* (#:key inputs #:allow-other-keys)
8475 (for-each (lambda (file)
8476 (install-file file "./src/smithlab_cpp/"))
8477 (find-files (assoc-ref inputs "smithlab-cpp")))
8479 (add-after 'install 'install-to-store
8480 (lambda* (#:key outputs #:allow-other-keys)
8481 (let* ((out (assoc-ref outputs "out"))
8482 (bin (string-append out "/bin")))
8483 (for-each (lambda (file)
8484 (install-file file bin))
8485 (find-files "bin" ".*")))
8488 (list (string-append "--with-bam_tools_headers="
8489 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8490 (string-append "--with-bam_tools_library="
8491 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8493 `(("bamtools" ,bamtools)
8494 ("samtools" ,samtools-0.1)
8497 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8501 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8503 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8506 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8508 `(("python" ,python-2)))
8509 (home-page "https://github.com/smithlabcode/piranha")
8510 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8512 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8513 RIP-seq experiments. It takes input in BED or BAM format and identifies
8514 regions of statistically significant read enrichment. Additional covariates
8515 may optionally be provided to further inform the peak-calling process.")
8516 (license license:gpl3+))))
8524 (uri (string-append "https://pypi.python.org/packages/source/P"
8525 "/PePr/PePr-" version ".tar.gz"))
8528 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8529 (build-system python-build-system)
8531 `(#:python ,python-2 ; python2 only
8532 #:tests? #f)) ; no tests included
8534 `(("python2-numpy" ,python2-numpy)
8535 ("python2-scipy" ,python2-scipy)
8536 ("python2-pysam" ,python2-pysam)))
8537 (home-page "https://github.com/shawnzhangyx/PePr")
8538 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8540 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8541 that is primarily designed for data with biological replicates. It uses a
8542 negative binomial distribution to model the read counts among the samples in
8543 the same group, and look for consistent differences between ChIP and control
8544 group or two ChIP groups run under different conditions.")
8545 (license license:gpl3+)))
8547 (define-public filevercmp
8548 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8551 (version (string-append "0-1." (string-take commit 7)))
8554 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8556 (file-name (string-append name "-" version ".tar.gz"))
8558 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8559 (build-system gnu-build-system)
8561 `(#:tests? #f ; There are no tests to run.
8563 (modify-phases %standard-phases
8564 (delete 'configure) ; There is no configure phase.
8566 (lambda* (#:key outputs #:allow-other-keys)
8567 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8568 (install-file "filevercmp" bin)))))))
8569 (home-page "https://github.com/ekg/filevercmp")
8570 (synopsis "This program compares version strings")
8571 (description "This program compares version strings. It intends to be a
8572 replacement for strverscmp.")
8573 (license license:gpl3+))))
8575 (define-public multiqc
8582 (uri (pypi-uri "multiqc" version))
8585 "032svgym67k2ds7wp0cxzv79gi30yrdl45zbqn74lni3dk04qm33"))))
8586 (build-system python-build-system)
8588 `(("python-jinja2" ,python-jinja2)
8589 ("python-simplejson" ,python-simplejson)
8590 ("python-pyyaml" ,python-pyyaml)
8591 ("python-click" ,python-click)
8592 ("python-spectra" ,python-spectra)
8593 ("python-requests" ,python-requests)
8594 ("python-markdown" ,python-markdown)
8595 ("python-lzstring" ,python-lzstring)
8596 ("python-matplotlib" ,python-matplotlib)
8597 ("python-numpy" ,python-numpy)
8598 ;; MultQC checks for the presence of nose at runtime.
8599 ("python-nose" ,python-nose)))
8600 (home-page "http://multiqc.info")
8601 (synopsis "Aggregate bioinformatics analysis reports")
8603 "MultiQC is a tool to aggregate bioinformatics results across many
8604 samples into a single report. It contains modules for a large number of
8605 common bioinformatics tools.")
8606 (license license:gpl3)))
8608 (define-public r-chipseq
8615 (uri (bioconductor-uri "chipseq" version))
8618 "1hahyqiwb2ch8214xqpw0c3jpiwkmyf3dwz0xc87jx6cdnzipj3i"))))
8619 (build-system r-build-system)
8621 `(("r-biocgenerics" ,r-biocgenerics)
8622 ("r-genomicranges" ,r-genomicranges)
8623 ("r-iranges" ,r-iranges)
8624 ("r-s4vectors" ,r-s4vectors)
8625 ("r-shortread" ,r-shortread)))
8626 (home-page "http://bioconductor.org/packages/chipseq")
8627 (synopsis "Package for analyzing ChIPseq data")
8629 "This package provides tools for processing short read data from ChIPseq
8631 (license license:artistic2.0)))
8633 (define-public r-copyhelper
8635 (name "r-copyhelper")
8640 (uri (string-append "http://bioconductor.org/packages/release/"
8641 "data/experiment/src/contrib/CopyhelpeR_"
8645 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8646 (properties `((upstream-name . "CopyhelpeR")))
8647 (build-system r-build-system)
8648 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8649 (synopsis "Helper files for CopywriteR")
8651 "This package contains the helper files that are required to run the
8652 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8653 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8654 mm10. In addition, it contains a blacklist filter to remove regions that
8655 display copy number variation. Files are stored as GRanges objects from the
8656 GenomicRanges Bioconductor package.")
8657 (license license:gpl2)))
8659 (define-public r-copywriter
8661 (name "r-copywriter")
8666 (uri (bioconductor-uri "CopywriteR" version))
8669 "0xgqnq5v5213b3nzvlmjysjb7w1bc0iblqpmzbjqn7n0ib0qyhbm"))))
8670 (properties `((upstream-name . "CopywriteR")))
8671 (build-system r-build-system)
8673 `(("r-biocparallel" ,r-biocparallel)
8674 ("r-chipseq" ,r-chipseq)
8675 ("r-copyhelper" ,r-copyhelper)
8676 ("r-data-table" ,r-data-table)
8677 ("r-dnacopy" ,r-dnacopy)
8678 ("r-futile-logger" ,r-futile-logger)
8679 ("r-genomeinfodb" ,r-genomeinfodb)
8680 ("r-genomicalignments" ,r-genomicalignments)
8681 ("r-genomicranges" ,r-genomicranges)
8682 ("r-gtools" ,r-gtools)
8683 ("r-iranges" ,r-iranges)
8684 ("r-matrixstats" ,r-matrixstats)
8685 ("r-rsamtools" ,r-rsamtools)
8686 ("r-s4vectors" ,r-s4vectors)))
8687 (home-page "https://github.com/PeeperLab/CopywriteR")
8688 (synopsis "Copy number information from targeted sequencing")
8690 "CopywriteR extracts DNA copy number information from targeted sequencing
8691 by utilizing off-target reads. It allows for extracting uniformly distributed
8692 copy number information, can be used without reference, and can be applied to
8693 sequencing data obtained from various techniques including chromatin
8694 immunoprecipitation and target enrichment on small gene panels. Thereby,
8695 CopywriteR constitutes a widely applicable alternative to available copy
8696 number detection tools.")
8697 (license license:gpl2)))
8699 (define-public r-methylkit
8701 (name "r-methylkit")
8705 (uri (bioconductor-uri "methylKit" version))
8708 "02acdjf6jl0c1glymin84pdna4farn4vv0gb6107d9iqz3y3gkmm"))))
8709 (properties `((upstream-name . "methylKit")))
8710 (build-system r-build-system)
8712 `(("r-data-table" ,r-data-table)
8713 ("r-emdbook" ,r-emdbook)
8714 ("r-fastseg" ,r-fastseg)
8715 ("r-genomeinfodb" ,r-genomeinfodb)
8716 ("r-genomicranges" ,r-genomicranges)
8717 ("r-gtools" ,r-gtools)
8718 ("r-iranges" ,r-iranges)
8719 ("r-kernsmooth" ,r-kernsmooth)
8720 ("r-limma" ,r-limma)
8721 ("r-mclust" ,r-mclust)
8722 ("r-qvalue" ,r-qvalue)
8723 ("r-r-utils" ,r-r-utils)
8725 ("r-rhtslib" ,r-rhtslib)
8726 ("r-rsamtools" ,r-rsamtools)
8727 ("r-rtracklayer" ,r-rtracklayer)
8728 ("r-s4vectors" ,r-s4vectors)
8729 ("r-zlibbioc" ,r-zlibbioc)))
8732 (home-page "http://code.google.com/p/methylkit/")
8734 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8736 "MethylKit is an R package for DNA methylation analysis and annotation
8737 from high-throughput bisulfite sequencing. The package is designed to deal
8738 with sequencing data from @dfn{Reduced representation bisulfite
8739 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8740 genome bisulfite sequencing. It also has functions to analyze base-pair
8741 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8743 (license license:artistic2.0)))
8745 (define-public r-sva
8752 (uri (bioconductor-uri "sva" version))
8755 "0wcway4ai9im81xnrzb1vij2iidq5pw24qhjfgacmhxvx3dzhbsc"))))
8756 (build-system r-build-system)
8758 `(("r-genefilter" ,r-genefilter)
8760 ("r-biocparallel" ,r-biocparallel)
8761 ("r-matrixstats" ,r-matrixstats)
8762 ("r-limma" ,r-limma)))
8763 (home-page "http://bioconductor.org/packages/sva")
8764 (synopsis "Surrogate variable analysis")
8766 "This package contains functions for removing batch effects and other
8767 unwanted variation in high-throughput experiment. It also contains functions
8768 for identifying and building surrogate variables for high-dimensional data
8769 sets. Surrogate variables are covariates constructed directly from
8770 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8771 imaging data that can be used in subsequent analyses to adjust for unknown,
8772 unmodeled, or latent sources of noise.")
8773 (license license:artistic2.0)))
8775 (define-public r-seqminer
8782 (uri (cran-uri "seqminer" version))
8785 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
8786 (build-system r-build-system)
8789 (home-page "http://seqminer.genomic.codes")
8790 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8792 "This package provides tools to integrate nucleotide sequencing
8793 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8794 ;; Any version of the GPL is acceptable
8795 (license (list license:gpl2+ license:gpl3+))))
8797 (define-public r-raremetals2
8799 (name "r-raremetals2")
8804 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8805 "b/b7/RareMETALS2_" version ".tar.gz"))
8808 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8809 (properties `((upstream-name . "RareMETALS2")))
8810 (build-system r-build-system)
8812 `(("r-seqminer" ,r-seqminer)
8813 ("r-mvtnorm" ,r-mvtnorm)
8815 ("r-compquadform" ,r-compquadform)
8816 ("r-getopt" ,r-getopt)))
8817 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8818 (synopsis "Analyze gene-level association tests for binary trait")
8820 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8821 It was designed to meta-analyze gene-level association tests for binary trait.
8822 While rareMETALS offers a near-complete solution for meta-analysis of
8823 gene-level tests for quantitative trait, it does not offer the optimal
8824 solution for binary trait. The package rareMETALS2 offers improved features
8825 for analyzing gene-level association tests in meta-analyses for binary
8827 (license license:gpl3)))
8829 (define-public r-maldiquant
8831 (name "r-maldiquant")
8836 (uri (cran-uri "MALDIquant" version))
8839 "0z5srzsfgsgi4bssr4chls4ry6d18y2g9143znqmraylppwrrqzr"))))
8840 (properties `((upstream-name . "MALDIquant")))
8841 (build-system r-build-system)
8842 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8843 (synopsis "Quantitative analysis of mass spectrometry data")
8845 "This package provides a complete analysis pipeline for matrix-assisted
8846 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8847 two-dimensional mass spectrometry data. In addition to commonly used plotting
8848 and processing methods it includes distinctive features, namely baseline
8849 subtraction methods such as morphological filters (TopHat) or the
8850 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8851 alignment using warping functions, handling of replicated measurements as well
8852 as allowing spectra with different resolutions.")
8853 (license license:gpl3+)))
8855 (define-public r-protgenerics
8857 (name "r-protgenerics")
8862 (uri (bioconductor-uri "ProtGenerics" version))
8865 "08idb3rvxn4fl7rd66jasyqz47cb76dbc3968r1g26jr2ci3w1pl"))))
8866 (properties `((upstream-name . "ProtGenerics")))
8867 (build-system r-build-system)
8868 (home-page "https://github.com/lgatto/ProtGenerics")
8869 (synopsis "S4 generic functions for proteomics infrastructure")
8871 "This package provides S4 generic functions needed by Bioconductor
8872 proteomics packages.")
8873 (license license:artistic2.0)))
8875 (define-public r-mzr
8882 (uri (bioconductor-uri "mzR" version))
8885 "1zir46h320n2vbrky6q3m8l221f3wdjlfsnx4ak9xca5min24xm7"))))
8886 (properties `((upstream-name . "mzR")))
8887 (build-system r-build-system)
8890 ("netcdf" ,netcdf)))
8892 `(("r-biobase" ,r-biobase)
8893 ("r-biocgenerics" ,r-biocgenerics)
8894 ("r-protgenerics" ,r-protgenerics)
8896 ("r-zlibbioc" ,r-zlibbioc)))
8897 (home-page "https://github.com/sneumann/mzR/")
8898 (synopsis "Parser for mass spectrometry data files")
8900 "The mzR package provides a unified API to the common file formats and
8901 parsers available for mass spectrometry data. It comes with a wrapper for the
8902 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8903 The package contains the original code written by the ISB, and a subset of the
8904 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8905 previously been used in XCMS.")
8906 (license license:artistic2.0)))
8908 (define-public r-affyio
8915 (uri (bioconductor-uri "affyio" version))
8918 "13w6al9296q916w0w6ngbsk25b21ahla1b6n40fcqhbvhyfii6sj"))))
8919 (build-system r-build-system)
8921 `(("r-zlibbioc" ,r-zlibbioc)))
8924 (home-page "https://github.com/bmbolstad/affyio")
8925 (synopsis "Tools for parsing Affymetrix data files")
8927 "This package provides routines for parsing Affymetrix data files based
8928 upon file format information. The primary focus is on accessing the CEL and
8930 (license license:lgpl2.0+)))
8932 (define-public r-affy
8939 (uri (bioconductor-uri "affy" version))
8942 "0azwg2qxzgflr1rjvbdln5i5rbcr9gs36kqlacd9cwl1szb9ad3m"))))
8943 (build-system r-build-system)
8945 `(("r-affyio" ,r-affyio)
8946 ("r-biobase" ,r-biobase)
8947 ("r-biocgenerics" ,r-biocgenerics)
8948 ("r-biocinstaller" ,r-biocinstaller)
8949 ("r-preprocesscore" ,r-preprocesscore)
8950 ("r-zlibbioc" ,r-zlibbioc)))
8951 (home-page "http://bioconductor.org/packages/affy")
8952 (synopsis "Methods for affymetrix oligonucleotide arrays")
8954 "This package contains functions for exploratory oligonucleotide array
8956 (license license:lgpl2.0+)))
8958 (define-public r-vsn
8965 (uri (bioconductor-uri "vsn" version))
8968 "0qhg3a4sc62pfdxcpvmk831rk138xh4zx4f1s39jhxpqqhmr7jvk"))))
8969 (build-system r-build-system)
8971 `(("r-affy" ,r-affy)
8972 ("r-biobase" ,r-biobase)
8973 ("r-ggplot2" ,r-ggplot2)
8974 ("r-hexbin" ,r-hexbin)
8975 ("r-lattice" ,r-lattice)
8976 ("r-limma" ,r-limma)))
8977 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8978 (synopsis "Variance stabilization and calibration for microarray data")
8980 "The package implements a method for normalising microarray intensities,
8981 and works for single- and multiple-color arrays. It can also be used for data
8982 from other technologies, as long as they have similar format. The method uses
8983 a robust variant of the maximum-likelihood estimator for an
8984 additive-multiplicative error model and affine calibration. The model
8985 incorporates data calibration step (a.k.a. normalization), a model for the
8986 dependence of the variance on the mean intensity and a variance stabilizing
8987 data transformation. Differences between transformed intensities are
8988 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8989 their variance is independent of the mean, and they are usually more sensitive
8990 and specific in detecting differential transcription.")
8991 (license license:artistic2.0)))
8993 (define-public r-mzid
9000 (uri (bioconductor-uri "mzID" version))
9003 "11xnild02jz24vbsfy92lb7jlqqwnrswg66a7r4rsw8d2ibrbk33"))))
9004 (properties `((upstream-name . "mzID")))
9005 (build-system r-build-system)
9007 `(("r-doparallel" ,r-doparallel)
9008 ("r-foreach" ,r-foreach)
9009 ("r-iterators" ,r-iterators)
9011 ("r-protgenerics" ,r-protgenerics)
9014 (home-page "http://bioconductor.org/packages/mzID")
9015 (synopsis "Parser for mzIdentML files")
9017 "This package provides a parser for mzIdentML files implemented using the
9018 XML package. The parser tries to be general and able to handle all types of
9019 mzIdentML files with the drawback of having less pretty output than a vendor
9021 (license license:gpl2+)))
9023 (define-public r-pcamethods
9025 (name "r-pcamethods")
9030 (uri (bioconductor-uri "pcaMethods" version))
9033 "0c4lphqyzj577ws4s172391cgv00s5nhy152zp18k2k4diyhq6n0"))))
9034 (properties `((upstream-name . "pcaMethods")))
9035 (build-system r-build-system)
9037 `(("r-biobase" ,r-biobase)
9038 ("r-biocgenerics" ,r-biocgenerics)
9040 ("r-rcpp" ,r-rcpp)))
9041 (home-page "https://github.com/hredestig/pcamethods")
9042 (synopsis "Collection of PCA methods")
9044 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9045 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9046 for missing value estimation is included for comparison. BPCA, PPCA and
9047 NipalsPCA may be used to perform PCA on incomplete data as well as for
9048 accurate missing value estimation. A set of methods for printing and plotting
9049 the results is also provided. All PCA methods make use of the same data
9050 structure (pcaRes) to provide a common interface to the PCA results.")
9051 (license license:gpl3+)))
9053 (define-public r-msnbase
9060 (uri (bioconductor-uri "MSnbase" version))
9063 "1n9bbdlp8d8bx2mqby0c4yylz1yil42scbkxqgyrfr9s5sn6dqff"))))
9064 (properties `((upstream-name . "MSnbase")))
9065 (build-system r-build-system)
9067 `(("r-affy" ,r-affy)
9068 ("r-biobase" ,r-biobase)
9069 ("r-biocgenerics" ,r-biocgenerics)
9070 ("r-biocparallel" ,r-biocparallel)
9071 ("r-digest" ,r-digest)
9072 ("r-ggplot2" ,r-ggplot2)
9073 ("r-impute" ,r-impute)
9074 ("r-iranges" ,r-iranges)
9075 ("r-maldiquant" ,r-maldiquant)
9078 ("r-pcamethods" ,r-pcamethods)
9080 ("r-preprocesscore" ,r-preprocesscore)
9081 ("r-protgenerics" ,r-protgenerics)
9083 ("r-reshape2" ,r-reshape2)
9084 ("r-s4vectors" ,r-s4vectors)
9087 (home-page "https://github.com/lgatto/MSnbase")
9088 (synopsis "Base functions and classes for MS-based proteomics")
9090 "This package provides basic plotting, data manipulation and processing
9091 of mass spectrometry based proteomics data.")
9092 (license license:artistic2.0)))
9094 (define-public r-msnid
9101 (uri (bioconductor-uri "MSnID" version))
9104 "0pjwargi5lif8q53fd43ql67p3yk9w10jychafd9qgbaw5k3f68k"))))
9105 (properties `((upstream-name . "MSnID")))
9106 (build-system r-build-system)
9108 `(("r-biobase" ,r-biobase)
9109 ("r-data-table" ,r-data-table)
9110 ("r-doparallel" ,r-doparallel)
9111 ("r-dplyr" ,r-dplyr)
9112 ("r-foreach" ,r-foreach)
9113 ("r-iterators" ,r-iterators)
9114 ("r-msnbase" ,r-msnbase)
9117 ("r-protgenerics" ,r-protgenerics)
9118 ("r-r-cache" ,r-r-cache)
9120 ("r-reshape2" ,r-reshape2)))
9121 (home-page "http://bioconductor.org/packages/MSnID")
9122 (synopsis "Utilities for LC-MSn proteomics identifications")
9124 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9125 from mzIdentML (leveraging the mzID package) or text files. After collating
9126 the search results from multiple datasets it assesses their identification
9127 quality and optimize filtering criteria to achieve the maximum number of
9128 identifications while not exceeding a specified false discovery rate. It also
9129 contains a number of utilities to explore the MS/MS results and assess missed
9130 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9131 (license license:artistic2.0)))
9133 (define-public r-seurat
9134 ;; Source releases are only made for new x.0 versions. All newer versions
9135 ;; are only released as pre-built binaries. At the time of this writing the
9136 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9137 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9141 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9145 (url "https://github.com/satijalab/seurat")
9147 (file-name (string-append name "-" version "-checkout"))
9150 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9151 ;; Delete pre-built jar.
9153 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9155 (build-system r-build-system)
9158 (modify-phases %standard-phases
9159 (add-after 'unpack 'build-jar
9160 (lambda* (#:key inputs #:allow-other-keys)
9161 (let ((classesdir "tmp-classes"))
9162 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9164 (and (zero? (apply system* `("javac" "-d" ,classesdir
9165 ,@(find-files "java" "\\.java$"))))
9166 (zero? (system* "jar"
9167 "-cf" "inst/java/ModularityOptimizer.jar"
9168 "-C" classesdir ".")))))))))
9170 `(("jdk" ,icedtea "jdk")))
9173 ("r-caret" ,r-caret)
9174 ("r-cowplot" ,r-cowplot)
9175 ("r-dplyr" ,r-dplyr)
9176 ("r-fastica" ,r-fastica)
9179 ("r-gdata" ,r-gdata)
9180 ("r-ggplot2" ,r-ggplot2)
9181 ("r-gplots" ,r-gplots)
9182 ("r-gridextra" ,r-gridextra)
9183 ("r-igraph" ,r-igraph)
9184 ("r-irlba" ,r-irlba)
9186 ("r-mixtools" ,r-mixtools)
9187 ("r-pbapply" ,r-pbapply)
9189 ("r-ranger" ,r-ranger)
9190 ("r-rcolorbrewer" ,r-rcolorbrewer)
9192 ("r-rcppeigen" ,r-rcppeigen)
9193 ("r-rcppprogress" ,r-rcppprogress)
9194 ("r-reshape2" ,r-reshape2)
9196 ("r-rtsne" ,r-rtsne)
9197 ("r-stringr" ,r-stringr)
9198 ("r-tclust" ,r-tclust)
9200 ("r-vgam" ,r-vgam)))
9201 (home-page "http://www.satijalab.org/seurat")
9202 (synopsis "Seurat is an R toolkit for single cell genomics")
9204 "This package is an R package designed for QC, analysis, and
9205 exploration of single cell RNA-seq data. It easily enables widely-used
9206 analytical techniques, including the identification of highly variable genes,
9207 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9208 algorithms; density clustering, hierarchical clustering, k-means, and the
9209 discovery of differentially expressed genes and markers.")
9210 (license license:gpl3))))
9212 (define-public r-aroma-light
9214 (name "r-aroma-light")
9219 (uri (bioconductor-uri "aroma.light" version))
9222 "10snykmmx36qaymyf5s1n1km8hsscyzpykcpf0mzsrcv8ml9rp8a"))))
9223 (properties `((upstream-name . "aroma.light")))
9224 (build-system r-build-system)
9226 `(("r-matrixstats" ,r-matrixstats)
9227 ("r-r-methodss3" ,r-r-methodss3)
9229 ("r-r-utils" ,r-r-utils)))
9230 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9231 (synopsis "Methods for normalization and visualization of microarray data")
9233 "This package provides methods for microarray analysis that take basic
9234 data types such as matrices and lists of vectors. These methods can be used
9235 standalone, be utilized in other packages, or be wrapped up in higher-level
9237 (license license:gpl2+)))
9239 (define-public r-deseq
9246 (uri (bioconductor-uri "DESeq" version))
9249 "0j3dgcxd64m9qknmlcbdzvg4xhp981xd6nbwsvnqjfn6yypslgyw"))))
9250 (properties `((upstream-name . "DESeq")))
9251 (build-system r-build-system)
9253 `(("r-biobase" ,r-biobase)
9254 ("r-biocgenerics" ,r-biocgenerics)
9255 ("r-genefilter" ,r-genefilter)
9256 ("r-geneplotter" ,r-geneplotter)
9257 ("r-lattice" ,r-lattice)
9258 ("r-locfit" ,r-locfit)
9260 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9261 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9262 (synopsis "Differential gene expression analysis")
9264 "This package provides tools for estimating variance-mean dependence in
9265 count data from high-throughput genetic sequencing assays and for testing for
9266 differential expression based on a model using the negative binomial
9268 (license license:gpl3+)))
9270 (define-public r-edaseq
9277 (uri (bioconductor-uri "EDASeq" version))
9280 "0f25dfc8hdii9fjm3bf89vy9jkxv23sa62fkcga5b4gkipwrvm9a"))))
9281 (properties `((upstream-name . "EDASeq")))
9282 (build-system r-build-system)
9284 `(("r-annotationdbi" ,r-annotationdbi)
9285 ("r-aroma-light" ,r-aroma-light)
9286 ("r-biobase" ,r-biobase)
9287 ("r-biocgenerics" ,r-biocgenerics)
9288 ("r-biomart" ,r-biomart)
9289 ("r-biostrings" ,r-biostrings)
9290 ("r-deseq" ,r-deseq)
9291 ("r-genomicfeatures" ,r-genomicfeatures)
9292 ("r-genomicranges" ,r-genomicranges)
9293 ("r-iranges" ,r-iranges)
9294 ("r-rsamtools" ,r-rsamtools)
9295 ("r-shortread" ,r-shortread)))
9296 (home-page "https://github.com/drisso/EDASeq")
9297 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9299 "This package provides support for numerical and graphical summaries of
9300 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9301 adjust for GC-content effect (or other gene-level effects) on read counts:
9302 loess robust local regression, global-scaling, and full-quantile
9303 normalization. Between-lane normalization procedures to adjust for
9304 distributional differences between lanes (e.g., sequencing depth):
9305 global-scaling and full-quantile normalization.")
9306 (license license:artistic2.0)))
9308 (define-public r-interactivedisplaybase
9310 (name "r-interactivedisplaybase")
9315 (uri (bioconductor-uri "interactiveDisplayBase" version))
9318 "12f6ap4bl3h2iwwhg8i3r9a7yyd28d8i5lb3fj1vnfvjs762r7r7"))))
9320 `((upstream-name . "interactiveDisplayBase")))
9321 (build-system r-build-system)
9323 `(("r-biocgenerics" ,r-biocgenerics)
9324 ("r-shiny" ,r-shiny)))
9325 (home-page "http://bioconductor.org/packages/interactiveDisplayBase")
9326 (synopsis "Base package for web displays of Bioconductor objects")
9328 "This package contains the basic methods needed to generate interactive
9329 Shiny-based display methods for Bioconductor objects.")
9330 (license license:artistic2.0)))
9332 (define-public r-annotationhub
9334 (name "r-annotationhub")
9339 (uri (bioconductor-uri "AnnotationHub" version))
9342 "1nh5si3j1nv37jcg4260582ayjg18851np47cskrm54prnvhwd9r"))))
9343 (properties `((upstream-name . "AnnotationHub")))
9344 (build-system r-build-system)
9346 `(("r-annotationdbi" ,r-annotationdbi)
9347 ("r-biocgenerics" ,r-biocgenerics)
9348 ("r-biocinstaller" ,r-biocinstaller)
9350 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9351 ("r-rsqlite" ,r-rsqlite)
9352 ("r-s4vectors" ,r-s4vectors)
9353 ("r-yaml" ,r-yaml)))
9354 (home-page "http://bioconductor.org/packages/AnnotationHub")
9355 (synopsis "Client to access AnnotationHub resources")
9357 "This package provides a client for the Bioconductor AnnotationHub web
9358 resource. The AnnotationHub web resource provides a central location where
9359 genomic files (e.g. VCF, bed, wig) and other resources from standard
9360 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9361 metadata about each resource, e.g., a textual description, tags, and date of
9362 modification. The client creates and manages a local cache of files retrieved
9363 by the user, helping with quick and reproducible access.")
9364 (license license:artistic2.0)))
9366 (define-public r-fastseg
9373 (uri (bioconductor-uri "fastseg" version))
9376 "083wiz03q9mynwchs9frlpp6c84dncri5ncibx6h82p228cpja6h"))))
9377 (build-system r-build-system)
9379 `(("r-biobase" ,r-biobase)
9380 ("r-biocgenerics" ,r-biocgenerics)
9381 ("r-genomicranges" ,r-genomicranges)
9382 ("r-iranges" ,r-iranges)
9383 ("r-s4vectors" ,r-s4vectors)))
9384 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9385 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9387 "Fastseg implements a very fast and efficient segmentation algorithm.
9388 It can segment data from DNA microarrays and data from next generation
9389 sequencing for example to detect copy number segments. Further it can segment
9390 data from RNA microarrays like tiling arrays to identify transcripts. Most
9391 generally, it can segment data given as a matrix or as a vector. Various data
9392 formats can be used as input to fastseg like expression set objects for
9393 microarrays or GRanges for sequencing data.")
9394 (license license:lgpl2.0+)))
9396 (define-public r-qvalue
9403 (uri (bioconductor-uri "qvalue" version))
9406 "1dxdwa767a9r8n61r272ypi09qblcdfpzzwkmri74y5mbp1r3y4i"))))
9407 (build-system r-build-system)
9409 `(("r-ggplot2" ,r-ggplot2)
9410 ("r-reshape2" ,r-reshape2)))
9411 (home-page "http://github.com/jdstorey/qvalue")
9412 (synopsis "Q-value estimation for false discovery rate control")
9414 "This package takes a list of p-values resulting from the simultaneous
9415 testing of many hypotheses and estimates their q-values and local @dfn{false
9416 discovery rate} (FDR) values. The q-value of a test measures the proportion
9417 of false positives incurred when that particular test is called significant.
9418 The local FDR measures the posterior probability the null hypothesis is true
9419 given the test's p-value. Various plots are automatically generated, allowing
9420 one to make sensible significance cut-offs. The software can be applied to
9421 problems in genomics, brain imaging, astrophysics, and data mining.")
9422 ;; Any version of the LGPL.
9423 (license license:lgpl3+)))
9425 (define htslib-for-sambamba
9426 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9429 (name "htslib-for-sambamba")
9430 (version (string-append "1.3.1-1." (string-take commit 9)))
9435 (url "https://github.com/lomereiter/htslib.git")
9437 (file-name (string-append "htslib-" version "-checkout"))
9440 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9442 (substitute-keyword-arguments (package-arguments htslib)
9444 `(modify-phases ,phases
9445 (add-before 'configure 'bootstrap
9447 (zero? (system* "autoreconf" "-vif"))))))))
9449 `(("autoconf" ,autoconf)
9450 ("automake" ,automake)
9451 ,@(package-native-inputs htslib))))))
9453 (define-public sambamba
9460 (uri (string-append "https://github.com/lomereiter/sambamba/"
9461 "archive/v" version ".tar.gz"))
9462 (file-name (string-append name "-" version ".tar.gz"))
9465 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9466 (build-system gnu-build-system)
9468 `(#:tests? #f ; there is no test target
9471 ;; Override "--compiler" flag only.
9472 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9473 "sambamba-ldmd2-64")
9475 (modify-phases %standard-phases
9477 (add-after 'unpack 'place-biod
9478 (lambda* (#:key inputs #:allow-other-keys)
9479 (copy-recursively (assoc-ref inputs "biod") "BioD")
9481 (add-after 'unpack 'unbundle-prerequisites
9483 (substitute* "Makefile"
9484 ((" htslib-static lz4-static") ""))
9487 (lambda* (#:key outputs #:allow-other-keys)
9488 (let* ((out (assoc-ref outputs "out"))
9489 (bin (string-append out "/bin")))
9491 (install-file "build/sambamba" bin)
9497 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9501 (url "https://github.com/biod/BioD.git")
9503 (file-name (string-append "biod-"
9504 (string-take commit 9)
9508 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9511 ("htslib" ,htslib-for-sambamba)))
9512 (home-page "http://lomereiter.github.io/sambamba")
9513 (synopsis "Tools for working with SAM/BAM data")
9514 (description "Sambamba is a high performance modern robust and
9515 fast tool (and library), written in the D programming language, for
9516 working with SAM and BAM files. Current parallelised functionality is
9517 an important subset of samtools functionality, including view, index,
9518 sort, markdup, and depth.")
9519 (license license:gpl2+)))
9521 (define-public ritornello
9527 (uri (string-append "https://github.com/KlugerLab/"
9528 "Ritornello/archive/v"
9530 (file-name (string-append name "-" version ".tar.gz"))
9533 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
9534 (build-system gnu-build-system)
9536 `(#:tests? #f ; there are no tests
9538 (modify-phases %standard-phases
9539 (add-after 'unpack 'patch-samtools-references
9540 (lambda* (#:key inputs #:allow-other-keys)
9541 (substitute* '("src/SamStream.h"
9542 "src/BufferedGenomeReader.h")
9543 (("<sam.h>") "<samtools/sam.h>"))
9547 (lambda* (#:key inputs outputs #:allow-other-keys)
9548 (let* ((out (assoc-ref outputs "out"))
9549 (bin (string-append out "/bin/")))
9551 (install-file "bin/Ritornello" bin)
9554 `(("samtools" ,samtools-0.1)
9558 (home-page "https://github.com/KlugerLab/Ritornello")
9559 (synopsis "Control-free peak caller for ChIP-seq data")
9560 (description "Ritornello is a ChIP-seq peak calling algorithm based on
9561 signal processing that can accurately call binding events without the need to
9562 do a pair total DNA input or IgG control sample. It has been tested for use
9563 with narrow binding events such as transcription factor ChIP-seq.")
9564 (license license:gpl3+)))
9566 (define-public trim-galore
9568 (name "trim-galore")
9573 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
9574 "projects/trim_galore/trim_galore_v"
9578 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
9579 (build-system gnu-build-system)
9581 `(#:tests? #f ; no tests
9583 (modify-phases %standard-phases
9584 ;; The archive contains plain files.
9586 (lambda* (#:key source #:allow-other-keys)
9587 (zero? (system* "unzip" source))))
9590 (add-after 'unpack 'hardcode-tool-references
9591 (lambda* (#:key inputs #:allow-other-keys)
9592 (substitute* "trim_galore"
9593 (("\\$path_to_cutadapt = 'cutadapt'")
9594 (string-append "$path_to_cutadapt = '"
9595 (assoc-ref inputs "cutadapt")
9599 (assoc-ref inputs "gzip")
9603 (assoc-ref inputs "gzip")
9607 (lambda* (#:key outputs #:allow-other-keys)
9608 (let ((bin (string-append (assoc-ref outputs "out")
9611 (install-file "trim_galore" bin)
9616 ("cutadapt" ,cutadapt)))
9618 `(("unzip" ,unzip)))
9619 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
9620 (synopsis "Wrapper around Cutadapt and FastQC")
9621 (description "Trim Galore! is a wrapper script to automate quality and
9622 adapter trimming as well as quality control, with some added functionality to
9623 remove biased methylation positions for RRBS sequence files.")
9624 (license license:gpl3+)))
9632 (uri (string-append "http://compbio.uthscsa.edu/"
9634 "gess-" version ".src.tar.gz"))
9637 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
9638 (build-system gnu-build-system)
9640 `(#:tests? #f ; no tests
9642 (modify-phases %standard-phases
9646 (lambda* (#:key inputs outputs #:allow-other-keys)
9647 (let* ((python (assoc-ref inputs "python"))
9648 (out (assoc-ref outputs "out"))
9649 (bin (string-append out "/bin/"))
9650 (target (string-append
9651 out "/lib/python2.7/site-packages/gess/")))
9653 (copy-recursively "." target)
9654 ;; Make GESS.py executable
9655 (chmod (string-append target "GESS.py") #o555)
9656 ;; Add Python shebang to the top and make Matplotlib
9658 (substitute* (string-append target "GESS.py")
9659 (("\"\"\"Description:" line)
9660 (string-append "#!" (which "python") "
9662 matplotlib.use('Agg')
9664 ;; Make sure GESS has all modules in its path
9665 (wrap-program (string-append target "GESS.py")
9666 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
9668 (symlink (string-append target "GESS.py")
9669 (string-append bin "GESS.py"))
9672 `(("python" ,python-2)
9673 ("python2-pysam" ,python2-pysam)
9674 ("python2-scipy" ,python2-scipy)
9675 ("python2-numpy" ,python2-numpy)
9676 ("python2-networkx" ,python2-networkx)
9677 ("python2-biopython" ,python2-biopython)))
9678 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
9679 (synopsis "Detect exon-skipping events from raw RNA-seq data")
9681 "GESS is an implementation of a novel computational method to detect de
9682 novo exon-skipping events directly from raw RNA-seq data without the prior
9683 knowledge of gene annotation information. GESS stands for the graph-based
9684 exon-skipping scanner detection scheme.")
9685 (license license:bsd-3)))
9687 (define-public phylip
9694 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
9695 "download/phylip-" version ".tar.gz"))
9698 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
9699 (build-system gnu-build-system)
9701 `(#:tests? #f ; no check target
9702 #:make-flags (list "-f" "Makefile.unx" "install")
9703 #:parallel-build? #f ; not supported
9705 (modify-phases %standard-phases
9706 (add-after 'unpack 'enter-dir
9707 (lambda _ (chdir "src") #t))
9710 (lambda* (#:key inputs outputs #:allow-other-keys)
9711 (let ((target (string-append (assoc-ref outputs "out")
9714 (for-each (lambda (file)
9715 (install-file file target))
9716 (find-files "../exe" ".*")))
9718 (home-page "http://evolution.genetics.washington.edu/phylip/")
9719 (synopsis "Tools for inferring phylogenies")
9720 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
9721 programs for inferring phylogenies (evolutionary trees).")
9722 (license license:bsd-2)))
9731 (uri (string-append "https://integrativemodeling.org/"
9732 version "/download/imp-" version ".tar.gz"))
9735 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
9736 (build-system cmake-build-system)
9738 `(;; FIXME: Some tests fail because they produce warnings, others fail
9739 ;; because the PYTHONPATH does not include the modeller's directory.
9741 ;; Do not place libraries in an architecture-specific directory.
9743 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
9750 ("python" ,python-2)))
9752 `(("python2-numpy" ,python2-numpy)
9753 ("python2-scipy" ,python2-scipy)
9754 ("python2-pandas" ,python2-pandas)
9755 ("python2-scikit-learn" ,python2-scikit-learn)
9756 ("python2-networkx" ,python2-networkx)))
9757 (home-page "https://integrativemodeling.org")
9758 (synopsis "Integrative modeling platform")
9759 (description "IMP's broad goal is to contribute to a comprehensive
9760 structural characterization of biomolecules ranging in size and complexity
9761 from small peptides to large macromolecular assemblies, by integrating data
9762 from diverse biochemical and biophysical experiments. IMP provides a C++ and
9763 Python toolbox for solving complex modeling problems, and a number of
9764 applications for tackling some common problems in a user-friendly way.")
9765 ;; IMP is largely available under the GNU Lesser GPL; see the file
9766 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
9767 ;; available under the GNU GPL (see the file COPYING.GPL).
9768 (license (list license:lgpl2.1+
9771 (define-public tadbit
9777 (uri (string-append "https://github.com/3DGenomes/TADbit/"
9778 "archive/v" version ".tar.gz"))
9779 (file-name (string-append name "-" version ".tar.gz"))
9782 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
9783 (build-system python-build-system)
9785 `(;; Tests are included and must be run after installation, but
9786 ;; they are incomplete and thus cannot be run.
9790 (modify-phases %standard-phases
9791 (add-after 'unpack 'fix-problems-with-setup.py
9792 (lambda* (#:key outputs #:allow-other-keys)
9793 ;; setup.py opens these files for writing
9794 (chmod "_pytadbit/_version.py" #o664)
9795 (chmod "README.rst" #o664)
9797 ;; Don't attempt to install the bash completions to
9798 ;; the home directory.
9799 (rename-file "extras/.bash_completion"
9801 (substitute* "setup.py"
9802 (("\\(path.expanduser\\('~'\\)")
9803 (string-append "(\""
9804 (assoc-ref outputs "out")
9805 "/etc/bash_completion.d\""))
9806 (("extras/\\.bash_completion")
9810 ;; TODO: add Chimera for visualization
9813 ("python2-scipy" ,python2-scipy)
9814 ("python2-numpy" ,python2-numpy)
9815 ("python2-matplotlib" ,python2-matplotlib)
9816 ("python2-pysam" ,python2-pysam)))
9817 (home-page "http://3dgenomes.github.io/TADbit/")
9818 (synopsis "Analyze, model, and explore 3C-based data")
9820 "TADbit is a complete Python library to deal with all steps to analyze,
9821 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
9822 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
9823 correct interaction matrices, identify and compare the so-called
9824 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
9825 interaction matrices, and finally, extract structural properties from the
9826 models. TADbit is complemented by TADkit for visualizing 3D models.")
9827 (license license:gpl3+)))
9829 (define-public kentutils
9832 ;; 302.1.0 is out, but the only difference is the inclusion of
9833 ;; pre-built binaries.
9838 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
9839 "archive/v" version ".tar.gz"))
9840 (file-name (string-append name "-" version ".tar.gz"))
9843 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
9844 (modules '((guix build utils)
9849 ;; Only the contents of the specified directories are free
9850 ;; for all uses, so we remove the rest. "hg/autoSql" and
9851 ;; "hg/autoXml" are nominally free, but they depend on a
9852 ;; library that is built from the sources in "hg/lib",
9853 ;; which is nonfree.
9854 (let ((free (list "." ".."
9855 "utils" "lib" "inc" "tagStorm"
9856 "parasol" "htslib"))
9857 (directory? (lambda (file)
9858 (eq? 'directory (stat:type (stat file))))))
9859 (for-each (lambda (file)
9860 (and (directory? file)
9861 (delete-file-recursively file)))
9862 (map (cut string-append "src/" <>)
9865 (not (member file free)))))))
9866 ;; Only make the utils target, not the userApps target,
9867 ;; because that requires libraries we won't build.
9868 (substitute* "Makefile"
9869 ((" userApps") " utils"))
9870 ;; Only build libraries that are free.
9871 (substitute* "src/makefile"
9872 (("DIRS =.*") "DIRS =\n")
9873 (("cd jkOwnLib.*") "")
9876 (substitute* "src/utils/makefile"
9877 ;; These tools depend on "jkhgap.a", which is part of the
9878 ;; nonfree "src/hg/lib" directory.
9880 (("pslLiftSubrangeBlat") "")
9882 ;; Do not build UCSC tools, which may require nonfree
9884 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
9886 (build-system gnu-build-system)
9888 `( ;; There is no global test target and the test target for
9889 ;; individual tools depends on input files that are not
9893 (modify-phases %standard-phases
9894 (add-after 'unpack 'fix-paths
9896 (substitute* "Makefile"
9897 (("/bin/echo") (which "echo")))
9899 (add-after 'unpack 'prepare-samtabix
9900 (lambda* (#:key inputs #:allow-other-keys)
9901 (copy-recursively (assoc-ref inputs "samtabix")
9906 (lambda* (#:key outputs #:allow-other-keys)
9907 (let ((bin (string-append (assoc-ref outputs "out")
9909 (copy-recursively "bin" bin))
9916 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
9917 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
9920 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
9927 ("openssl" ,openssl)))
9928 (home-page "http://genome.cse.ucsc.edu/index.html")
9929 (synopsis "Assorted bioinformatics utilities")
9930 (description "This package provides the kentUtils, a selection of
9931 bioinformatics utilities used in combination with the UCSC genome
9933 ;; Only a subset of the sources are released under a non-copyleft
9934 ;; free software license. All other sources are removed in a
9935 ;; snippet. See this bug report for an explanation of how the
9936 ;; license statements apply:
9937 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
9938 (license (license:non-copyleft
9939 "http://genome.ucsc.edu/license/"
9940 "The contents of this package are free for all uses."))))
9942 (define-public f-seq
9943 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
9947 (version (string-append "1.1-" revision "." commit))
9951 (url "https://github.com/aboyle/F-seq.git")
9953 (file-name (string-append name "-" version))
9956 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
9957 (modules '((guix build utils)))
9958 ;; Remove bundled Java library archives.
9961 (for-each delete-file (find-files "lib" ".*"))
9963 (build-system ant-build-system)
9965 `(#:tests? #f ; no tests included
9967 (modify-phases %standard-phases
9969 (lambda* (#:key outputs #:allow-other-keys)
9970 (let* ((target (assoc-ref outputs "out"))
9971 (doc (string-append target "/share/doc/f-seq/")))
9974 (substitute* "bin/linux/fseq"
9975 (("java") (which "java")))
9976 (install-file "README.txt" doc)
9977 (install-file "bin/linux/fseq" (string-append target "/bin"))
9978 (install-file "build~/fseq.jar" (string-append target "/lib"))
9979 (copy-recursively "lib" (string-append target "/lib"))
9983 ("java-commons-cli" ,java-commons-cli)))
9984 (home-page "http://fureylab.web.unc.edu/software/fseq/")
9985 (synopsis "Feature density estimator for high-throughput sequence tags")
9987 "F-Seq is a software package that generates a continuous tag sequence
9988 density estimation allowing identification of biologically meaningful sites
9989 such as transcription factor binding sites (ChIP-seq) or regions of open
9990 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
9992 (license license:gpl3+))))
9994 (define-public bismark
10001 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10002 "archive/" version ".tar.gz"))
10003 (file-name (string-append name "-" version ".tar.gz"))
10006 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10007 (build-system perl-build-system)
10009 `(#:tests? #f ; there are no tests
10011 (modify-phases %standard-phases
10012 (delete 'configure)
10015 (lambda* (#:key outputs #:allow-other-keys)
10016 (let ((bin (string-append (assoc-ref outputs "out")
10018 (docdir (string-append (assoc-ref outputs "out")
10019 "/share/doc/bismark"))
10020 (docs '("Bismark_User_Guide.pdf"
10021 "RELEASE_NOTES.txt"))
10022 (scripts '("bismark"
10023 "bismark_genome_preparation"
10024 "bismark_methylation_extractor"
10027 "coverage2cytosine"
10028 "deduplicate_bismark"
10029 "bismark_sitrep.tpl"
10031 "bismark2summary")))
10034 (for-each (lambda (file) (install-file file bin))
10036 (for-each (lambda (file) (install-file file docdir))
10039 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10040 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
10041 (description "Bismark is a program to map bisulfite treated sequencing
10042 reads to a genome of interest and perform methylation calls in a single step.
10043 The output can be easily imported into a genome viewer, such as SeqMonk, and
10044 enables a researcher to analyse the methylation levels of their samples
10045 straight away. Its main features are:
10048 @item Bisulfite mapping and methylation calling in one single step
10049 @item Supports single-end and paired-end read alignments
10050 @item Supports ungapped and gapped alignments
10051 @item Alignment seed length, number of mismatches etc are adjustable
10052 @item Output discriminates between cytosine methylation in CpG, CHG
10055 (license license:gpl3+)))