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 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
11 ;;; This file is part of GNU Guix.
13 ;;; GNU Guix is free software; you can redistribute it and/or modify it
14 ;;; under the terms of the GNU General Public License as published by
15 ;;; the Free Software Foundation; either version 3 of the License, or (at
16 ;;; your option) any later version.
18 ;;; GNU Guix is distributed in the hope that it will be useful, but
19 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;;; GNU General Public License for more details.
23 ;;; You should have received a copy of the GNU General Public License
24 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
26 (define-module (gnu packages bioinformatics)
27 #:use-module ((guix licenses) #:prefix license:)
28 #:use-module (guix packages)
29 #:use-module (guix utils)
30 #:use-module (guix download)
31 #:use-module (guix git-download)
32 #:use-module (guix hg-download)
33 #:use-module (guix build-system ant)
34 #:use-module (guix build-system gnu)
35 #:use-module (guix build-system cmake)
36 #:use-module (guix build-system ocaml)
37 #:use-module (guix build-system perl)
38 #:use-module (guix build-system python)
39 #:use-module (guix build-system r)
40 #:use-module (guix build-system ruby)
41 #:use-module (guix build-system trivial)
42 #:use-module (gnu packages)
43 #:use-module (gnu packages autotools)
44 #:use-module (gnu packages algebra)
45 #:use-module (gnu packages base)
46 #:use-module (gnu packages bash)
47 #:use-module (gnu packages bison)
48 #:use-module (gnu packages boost)
49 #:use-module (gnu packages compression)
50 #:use-module (gnu packages cpio)
51 #:use-module (gnu packages curl)
52 #:use-module (gnu packages documentation)
53 #:use-module (gnu packages datastructures)
54 #:use-module (gnu packages file)
55 #:use-module (gnu packages flex)
56 #:use-module (gnu packages gawk)
57 #:use-module (gnu packages gcc)
58 #:use-module (gnu packages gd)
59 #:use-module (gnu packages gtk)
60 #:use-module (gnu packages glib)
61 #:use-module (gnu packages groff)
62 #:use-module (gnu packages guile)
63 #:use-module (gnu packages haskell)
64 #:use-module (gnu packages image)
65 #:use-module (gnu packages imagemagick)
66 #:use-module (gnu packages java)
67 #:use-module (gnu packages ldc)
68 #:use-module (gnu packages linux)
69 #:use-module (gnu packages logging)
70 #:use-module (gnu packages machine-learning)
71 #:use-module (gnu packages man)
72 #:use-module (gnu packages maths)
73 #:use-module (gnu packages mpi)
74 #:use-module (gnu packages ncurses)
75 #:use-module (gnu packages ocaml)
76 #:use-module (gnu packages pcre)
77 #:use-module (gnu packages parallel)
78 #:use-module (gnu packages pdf)
79 #:use-module (gnu packages perl)
80 #:use-module (gnu packages pkg-config)
81 #:use-module (gnu packages popt)
82 #:use-module (gnu packages protobuf)
83 #:use-module (gnu packages python)
84 #:use-module (gnu packages readline)
85 #:use-module (gnu packages ruby)
86 #:use-module (gnu packages serialization)
87 #:use-module (gnu packages statistics)
88 #:use-module (gnu packages tbb)
89 #:use-module (gnu packages tex)
90 #:use-module (gnu packages texinfo)
91 #:use-module (gnu packages textutils)
92 #:use-module (gnu packages time)
93 #:use-module (gnu packages tls)
94 #:use-module (gnu packages vim)
95 #:use-module (gnu packages web)
96 #:use-module (gnu packages xml)
97 #:use-module (gnu packages xorg)
98 #:use-module (gnu packages zip)
99 #:use-module (srfi srfi-1))
108 (uri (cran-uri "ape" version))
111 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
112 (build-system r-build-system)
114 `(("r-lattice" ,r-lattice)
116 (home-page "http://ape-package.ird.fr/")
117 (synopsis "Analyses of phylogenetics and evolution")
119 "This package provides functions for reading, writing, plotting, and
120 manipulating phylogenetic trees, analyses of comparative data in a
121 phylogenetic framework, ancestral character analyses, analyses of
122 diversification and macroevolution, computing distances from DNA sequences,
123 and several other tools.")
124 (license license:gpl2+)))
126 (define-public aragorn
133 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
137 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
138 (build-system gnu-build-system)
140 `(#:tests? #f ; there are no tests
142 (modify-phases %standard-phases
146 (zero? (system* "gcc"
152 (string-append "aragorn" ,version ".c")))))
154 (lambda* (#:key outputs #:allow-other-keys)
155 (let* ((out (assoc-ref outputs "out"))
156 (bin (string-append out "/bin"))
157 (man (string-append out "/share/man/man1")))
159 (install-file "aragorn" bin)
161 (install-file "aragorn.1" man))
163 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
164 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
166 "Aragorn identifies transfer RNA, mitochondrial RNA and
167 transfer-messenger RNA from nucleotide sequences, based on homology to known
168 tRNA consensus sequences and RNA structure. It also outputs the secondary
169 structure of the predicted RNA.")
170 (license license:gpl2)))
178 ;; BamM is not available on pypi.
180 "https://github.com/Ecogenomics/BamM/archive/"
182 (file-name (string-append name "-" version ".tar.gz"))
185 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
186 (modules '((guix build utils)))
189 ;; Delete bundled htslib.
190 (delete-file-recursively "c/htslib-1.3.1")
192 (build-system python-build-system)
194 `(#:python ,python-2 ; BamM is Python 2 only.
195 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
196 ;; been modified from its original form.
198 (let ((htslib (assoc-ref %build-inputs "htslib")))
199 (list "--with-libhts-lib" (string-append htslib "/lib")
200 "--with-libhts-inc" (string-append htslib "/include/htslib")))
202 (modify-phases %standard-phases
203 (add-after 'unpack 'autogen
205 (with-directory-excursion "c"
206 (let ((sh (which "sh")))
207 ;; Use autogen so that 'configure' works.
208 (substitute* "autogen.sh" (("/bin/sh") sh))
209 (setenv "CONFIG_SHELL" sh)
210 (substitute* "configure" (("/bin/sh") sh))
211 (zero? (system* "./autogen.sh"))))))
213 ;; Run tests after installation so compilation only happens once.
215 (add-after 'install 'wrap-executable
216 (lambda* (#:key outputs #:allow-other-keys)
217 (let* ((out (assoc-ref outputs "out"))
218 (path (getenv "PATH")))
219 (wrap-program (string-append out "/bin/bamm")
220 `("PATH" ":" prefix (,path))))
222 (add-after 'wrap-executable 'post-install-check
223 (lambda* (#:key inputs outputs #:allow-other-keys)
225 (string-append (assoc-ref outputs "out")
230 (assoc-ref outputs "out")
232 (string-take (string-take-right
233 (assoc-ref inputs "python") 5) 3)
235 (getenv "PYTHONPATH")))
236 ;; There are 2 errors printed, but they are safe to ignore:
237 ;; 1) [E::hts_open_format] fail to open file ...
238 ;; 2) samtools view: failed to open ...
239 (zero? (system* "nosetests")))))))
241 `(("autoconf" ,autoconf)
242 ("automake" ,automake)
245 ("python-nose" ,python2-nose)
246 ("python-pysam" ,python2-pysam)))
249 ("samtools" ,samtools)
253 ("coreutils" ,coreutils)))
255 `(("python-numpy" ,python2-numpy)))
256 (home-page "http://ecogenomics.github.io/BamM/")
257 (synopsis "Metagenomics-focused BAM file manipulator")
259 "BamM is a C library, wrapped in python, to efficiently generate and
260 parse BAM files, specifically for the analysis of metagenomic data. For
261 instance, it implements several methods to assess contig-wise read coverage.")
262 (license license:lgpl3+)))
264 (define-public bamtools
271 "https://github.com/pezmaster31/bamtools/archive/v"
273 (file-name (string-append name "-" version ".tar.gz"))
276 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
277 (build-system cmake-build-system)
279 `(#:tests? #f ;no "check" target
281 (modify-phases %standard-phases
283 'configure 'set-ldflags
284 (lambda* (#:key outputs #:allow-other-keys)
288 (assoc-ref outputs "out") "/lib/bamtools")))))))
289 (inputs `(("zlib" ,zlib)))
290 (home-page "https://github.com/pezmaster31/bamtools")
291 (synopsis "C++ API and command-line toolkit for working with BAM data")
293 "BamTools provides both a C++ API and a command-line toolkit for handling
295 (license license:expat)))
297 (define-public bcftools
304 "https://github.com/samtools/bcftools/releases/download/"
305 version "/bcftools-" version ".tar.bz2"))
308 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
309 (modules '((guix build utils)))
311 ;; Delete bundled htslib.
312 '(delete-file-recursively "htslib-1.3.1"))))
313 (build-system gnu-build-system)
315 `(#:test-target "test"
319 (string-append "prefix=" (assoc-ref %outputs "out"))
320 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
321 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
322 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
323 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
325 (modify-phases %standard-phases
326 (add-after 'unpack 'patch-Makefile
328 (substitute* "Makefile"
329 ;; Do not attempt to build htslib.
330 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
331 ;; Link against GSL cblas.
332 (("-lcblas") "-lgslcblas"))
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 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
965 (modules '((guix build utils)))
968 ;; Remove bundled bzip2 and zlib
969 (delete-file-recursively "c++/src/util/compress/bzip2")
970 (delete-file-recursively "c++/src/util/compress/zlib")
971 (substitute* "c++/src/util/compress/Makefile.in"
972 (("bzip2 zlib api") "api"))
973 ;; Remove useless msbuild directory
974 (delete-file-recursively
975 "c++/src/build-system/project_tree_builder/msbuild")
977 (build-system gnu-build-system)
979 `(;; There are three(!) tests for this massive library, and all fail with
980 ;; "unparsable timing stats".
981 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
982 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
983 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
986 #:parallel-build? #f ; not supported
988 (modify-phases %standard-phases
991 ;; $HOME needs to be set at some point during the configure phase
992 (lambda _ (setenv "HOME" "/tmp") #t))
995 (lambda _ (chdir "c++") #t))
997 'enter-dir 'fix-build-system
1000 (cond ((string=? cmd "date")
1001 ;; make call to "date" deterministic
1006 (format (current-error-port)
1007 "WARNING: Unable to find absolute path for ~s~%"
1011 ;; Rewrite hardcoded paths to various tools
1012 (substitute* (append '("src/build-system/configure.ac"
1013 "src/build-system/configure"
1014 "scripts/common/impl/if_diff.sh"
1015 "scripts/common/impl/run_with_lock.sh"
1016 "src/build-system/Makefile.configurables.real"
1017 "src/build-system/Makefile.in.top"
1018 "src/build-system/Makefile.meta.gmake=no"
1019 "src/build-system/Makefile.meta.in"
1020 "src/build-system/Makefile.meta_l"
1021 "src/build-system/Makefile.meta_p"
1022 "src/build-system/Makefile.meta_r"
1023 "src/build-system/Makefile.mk.in"
1024 "src/build-system/Makefile.requirements"
1025 "src/build-system/Makefile.rules_with_autodep.in")
1026 (find-files "scripts/common/check" "\\.sh$"))
1027 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1028 (or (which* cmd) all)))
1030 (substitute* (find-files "src/build-system" "^config.*")
1031 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1034 ;; rewrite "/var/tmp" in check script
1035 (substitute* "scripts/common/check/check_make_unix.sh"
1036 (("/var/tmp") "/tmp"))
1038 ;; do not reset PATH
1039 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1041 (("action=/bin/") "action=")
1042 (("export PATH") ":"))
1046 (lambda* (#:key inputs outputs #:allow-other-keys)
1047 (let ((out (assoc-ref outputs "out"))
1048 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1049 (include (string-append (assoc-ref outputs "include")
1050 "/include/ncbi-tools++")))
1051 ;; The 'configure' script doesn't recognize things like
1052 ;; '--enable-fast-install'.
1053 (zero? (system* "./configure.orig"
1054 (string-append "--with-build-root=" (getcwd) "/build")
1055 (string-append "--prefix=" out)
1056 (string-append "--libdir=" lib)
1057 (string-append "--includedir=" include)
1058 (string-append "--with-bz2="
1059 (assoc-ref inputs "bzip2"))
1060 (string-append "--with-z="
1061 (assoc-ref inputs "zlib"))
1062 ;; Each library is built twice by default, once
1063 ;; with "-static" in its name, and again
1066 "--with-dll"))))))))
1067 (outputs '("out" ; 19 MB
1075 (home-page "http://blast.ncbi.nlm.nih.gov")
1076 (synopsis "Basic local alignment search tool")
1078 "BLAST is a popular method of performing a DNA or protein sequence
1079 similarity search, using heuristics to produce results quickly. It also
1080 calculates an “expect value” that estimates how many matches would have
1081 occurred at a given score by chance, which can aid a user in judging how much
1082 confidence to have in an alignment.")
1083 ;; Most of the sources are in the public domain, with the following
1086 ;; * ./c++/include/util/bitset/
1087 ;; * ./c++/src/html/ncbi_menu*.js
1089 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1091 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1093 ;; * ./c++/src/corelib/teamcity_*
1094 (license (list license:public-domain
1100 (define-public bless
1106 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1110 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1111 (modules '((guix build utils)))
1114 ;; Remove bundled boost, pigz, zlib, and .git directory
1115 ;; FIXME: also remove bundled sources for murmurhash3 and
1116 ;; kmc once packaged.
1117 (delete-file-recursively "boost")
1118 (delete-file-recursively "pigz")
1119 (delete-file-recursively "google-sparsehash")
1120 (delete-file-recursively "zlib")
1121 (delete-file-recursively ".git")
1123 (build-system gnu-build-system)
1125 '(#:tests? #f ;no "check" target
1127 (list (string-append "ZLIB="
1128 (assoc-ref %build-inputs "zlib")
1130 (string-append "LDFLAGS="
1131 (string-join '("-lboost_filesystem"
1138 (modify-phases %standard-phases
1139 (add-after 'unpack 'do-not-build-bundled-pigz
1140 (lambda* (#:key inputs outputs #:allow-other-keys)
1141 (substitute* "Makefile"
1142 (("cd pigz/pigz-2.3.3; make") ""))
1144 (add-after 'unpack 'patch-paths-to-executables
1145 (lambda* (#:key inputs outputs #:allow-other-keys)
1146 (substitute* "parse_args.cpp"
1147 (("kmc_binary = .*")
1148 (string-append "kmc_binary = \""
1149 (assoc-ref outputs "out")
1151 (("pigz_binary = .*")
1152 (string-append "pigz_binary = \""
1153 (assoc-ref inputs "pigz")
1157 (lambda* (#:key outputs #:allow-other-keys)
1158 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1159 (for-each (lambda (file)
1160 (install-file file bin))
1161 '("bless" "kmc/bin/kmc"))
1163 (delete 'configure))))
1167 `(("openmpi" ,openmpi)
1169 ("sparsehash" ,sparsehash)
1172 (supported-systems '("x86_64-linux"))
1173 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1174 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1176 "@dfn{Bloom-filter-based error correction solution for high-throughput
1177 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1178 correction tool for genomic reads produced by @dfn{Next-generation
1179 sequencing} (NGS). BLESS produces accurate correction results with much less
1180 memory compared with previous solutions and is also able to tolerate a higher
1181 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1182 errors at the end of reads.")
1183 (license license:gpl3+)))
1185 (define-public bowtie
1191 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1193 (file-name (string-append name "-" version ".tar.gz"))
1196 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1197 (modules '((guix build utils)))
1199 '(substitute* "Makefile"
1200 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1201 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1202 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1203 (build-system gnu-build-system)
1204 (inputs `(("perl" ,perl)
1205 ("perl-clone" ,perl-clone)
1206 ("perl-test-deep" ,perl-test-deep)
1207 ("perl-test-simple" ,perl-test-simple)
1208 ("python" ,python-2)
1214 (string-append "prefix=" (assoc-ref %outputs "out")))
1220 (lambda* (#:key outputs #:allow-other-keys)
1222 "scripts/test/simple_tests.pl"
1223 "--bowtie2=./bowtie2"
1224 "--bowtie2-build=./bowtie2-build"))
1225 %standard-phases))))
1226 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1227 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1229 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1230 reads to long reference sequences. It is particularly good at aligning reads
1231 of about 50 up to 100s or 1,000s of characters, and particularly good at
1232 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1233 genome with an FM Index to keep its memory footprint small: for the human
1234 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1235 gapped, local, and paired-end alignment modes.")
1236 (supported-systems '("x86_64-linux"))
1237 (license license:gpl3+)))
1239 (define-public tophat
1246 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1250 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1251 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1252 (modules '((guix build utils)))
1255 ;; Remove bundled SeqAn and samtools
1256 (delete-file-recursively "src/SeqAn-1.3")
1257 (delete-file-recursively "src/samtools-0.1.18")
1259 (build-system gnu-build-system)
1261 '(#:parallel-build? #f ; not supported
1263 (modify-phases %standard-phases
1264 (add-after 'unpack 'use-system-samtools
1265 (lambda* (#:key inputs #:allow-other-keys)
1266 (substitute* "src/Makefile.in"
1267 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1268 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1269 (("SAMPROG = samtools_0\\.1\\.18") "")
1270 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1271 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1272 (substitute* '("src/common.cpp"
1274 (("samtools_0.1.18") (which "samtools")))
1275 (substitute* '("src/common.h"
1276 "src/bam2fastx.cpp")
1277 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1278 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1279 (substitute* '("src/bwt_map.h"
1281 "src/align_status.h")
1282 (("#include <bam.h>") "#include <samtools/bam.h>")
1283 (("#include <sam.h>") "#include <samtools/sam.h>"))
1288 ("samtools" ,samtools-0.1)
1289 ("ncurses" ,ncurses)
1290 ("python" ,python-2)
1294 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1295 (synopsis "Spliced read mapper for RNA-Seq data")
1297 "TopHat is a fast splice junction mapper for nucleotide sequence
1298 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1299 mammalian-sized genomes using the ultra high-throughput short read
1300 aligner Bowtie, and then analyzes the mapping results to identify
1301 splice junctions between exons.")
1302 ;; TopHat is released under the Boost Software License, Version 1.0
1303 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1304 (license license:boost1.0)))
1312 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1313 version ".tar.bz2"))
1316 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1317 (build-system gnu-build-system)
1319 '(#:tests? #f ;no "check" target
1323 (lambda* (#:key outputs #:allow-other-keys)
1324 (let ((bin (string-append
1325 (assoc-ref outputs "out") "/bin"))
1327 (assoc-ref outputs "out") "/share/doc/bwa"))
1329 (assoc-ref outputs "out") "/share/man/man1")))
1330 (install-file "bwa" bin)
1331 (install-file "README.md" doc)
1332 (install-file "bwa.1" man)))
1333 ;; no "configure" script
1334 (alist-delete 'configure %standard-phases))))
1335 (inputs `(("zlib" ,zlib)))
1336 ;; Non-portable SSE instructions are used so building fails on platforms
1337 ;; other than x86_64.
1338 (supported-systems '("x86_64-linux"))
1339 (home-page "http://bio-bwa.sourceforge.net/")
1340 (synopsis "Burrows-Wheeler sequence aligner")
1342 "BWA is a software package for mapping low-divergent sequences against a
1343 large reference genome, such as the human genome. It consists of three
1344 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1345 designed for Illumina sequence reads up to 100bp, while the rest two for
1346 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1347 features such as long-read support and split alignment, but BWA-MEM, which is
1348 the latest, is generally recommended for high-quality queries as it is faster
1349 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1350 70-100bp Illumina reads.")
1351 (license license:gpl3+)))
1353 (define-public bwa-pssm
1354 (package (inherit bwa)
1359 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1360 "archive/" version ".tar.gz"))
1361 (file-name (string-append name "-" version ".tar.gz"))
1364 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1365 (build-system gnu-build-system)
1370 (home-page "http://bwa-pssm.binf.ku.dk/")
1371 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1373 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1374 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1375 existing aligners it is fast and sensitive. Unlike most other aligners,
1376 however, it is also adaptible in the sense that one can direct the alignment
1377 based on known biases within the data set. It is coded as a modification of
1378 the original BWA alignment program and shares the genome index structure as
1379 well as many of the command line options.")
1380 (license license:gpl3+)))
1382 (define-public python2-bx-python
1384 (name "python2-bx-python")
1389 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1393 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1394 (modules '((guix build utils)))
1396 '(substitute* "setup.py"
1397 ;; remove dependency on outdated "distribute" module
1398 (("^from distribute_setup import use_setuptools") "")
1399 (("^use_setuptools\\(\\)") "")))))
1400 (build-system python-build-system)
1402 `(#:tests? #f ;tests fail because test data are not included
1403 #:python ,python-2))
1405 `(("python-numpy" ,python2-numpy)
1408 `(("python-nose" ,python2-nose)))
1409 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1410 (synopsis "Tools for manipulating biological data")
1412 "bx-python provides tools for manipulating biological data, particularly
1413 multiple sequence alignments.")
1414 (license license:expat)))
1416 (define-public python-pysam
1418 (name "python-pysam")
1422 ;; Test data is missing on PyPi.
1424 "https://github.com/pysam-developers/pysam/archive/v"
1426 (file-name (string-append name "-" version ".tar.gz"))
1429 "1mmvn91agr238kwz7226xq0i7k84lg2nxywn9712mzj7gvgqhfy8"))
1430 (modules '((guix build utils)))
1432 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1433 '(delete-file-recursively "htslib"))))
1434 (build-system python-build-system)
1436 `(#:modules ((ice-9 ftw)
1438 (guix build python-build-system)
1441 (modify-phases %standard-phases
1442 (add-before 'build 'set-flags
1443 (lambda* (#:key inputs #:allow-other-keys)
1444 (setenv "HTSLIB_MODE" "external")
1445 (setenv "HTSLIB_LIBRARY_DIR"
1446 (string-append (assoc-ref inputs "htslib") "/lib"))
1447 (setenv "HTSLIB_INCLUDE_DIR"
1448 (string-append (assoc-ref inputs "htslib") "/include"))
1449 (setenv "LDFLAGS" "-lncurses")
1450 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1453 (lambda* (#:key inputs outputs #:allow-other-keys)
1454 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1455 (setenv "PYTHONPATH"
1457 (getenv "PYTHONPATH")
1458 ":" (getcwd) "/build/"
1459 (car (scandir "build"
1460 (negate (cut string-prefix? "." <>))))))
1461 ;; Step out of source dir so python does not import from CWD.
1462 (with-directory-excursion "tests"
1463 (setenv "HOME" "/tmp")
1464 (and (zero? (system* "make" "-C" "pysam_data"))
1465 (zero? (system* "make" "-C" "cbcf_data"))
1466 ;; Running nosetests without explicitly asking for a
1467 ;; single process leads to a crash. Running with multiple
1468 ;; processes fails because the tests are not designed to
1471 ;; FIXME: tests keep timing out on some systems.
1472 ;; (zero? (system* "nosetests" "-v"
1473 ;; "--processes" "1"))
1476 `(("htslib" ,htslib))) ; Included from installed header files.
1478 `(("ncurses" ,ncurses)
1481 `(("python-cython" ,python-cython)
1482 ;; Dependencies below are are for tests only.
1483 ("samtools" ,samtools)
1484 ("bcftools" ,bcftools)
1485 ("python-nose" ,python-nose)))
1486 (home-page "https://github.com/pysam-developers/pysam")
1487 (synopsis "Python bindings to the SAMtools C API")
1489 "Pysam is a Python module for reading and manipulating files in the
1490 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1491 also includes an interface for tabix.")
1492 (license license:expat)))
1494 (define-public python2-pysam
1495 (package-with-python2 python-pysam))
1497 (define-public python-twobitreader
1499 (name "python-twobitreader")
1503 (uri (pypi-uri "twobitreader" version))
1506 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1507 (build-system python-build-system)
1509 '(;; Tests are not distributed in the PyPi release.
1510 ;; TODO Try building from the Git repo or asking the upstream maintainer
1511 ;; to distribute the tests on PyPi.
1514 `(("python-sphinx" ,python-sphinx)))
1515 (home-page "https://github.com/benjschiller/twobitreader")
1516 (synopsis "Python library for reading .2bit files")
1518 "twobitreader is a Python library for reading .2bit files as used by the
1519 UCSC genome browser.")
1520 (license license:artistic2.0)))
1522 (define-public python2-twobitreader
1523 (package-with-python2 python-twobitreader))
1525 (define-public python-plastid
1527 (name "python-plastid")
1531 (uri (pypi-uri "plastid" version))
1534 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1535 (build-system python-build-system)
1537 ;; Some test files are not included.
1540 `(("python-numpy" ,python-numpy)
1541 ("python-scipy" ,python-scipy)
1542 ("python-pandas" ,python-pandas)
1543 ("python-pysam" ,python-pysam)
1544 ("python-matplotlib" ,python-matplotlib)
1545 ("python-biopython" ,python-biopython)
1546 ("python-twobitreader" ,python-twobitreader)
1547 ("python-termcolor" ,python-termcolor)))
1549 `(("python-cython" ,python-cython)
1550 ("python-nose" ,python-nose)))
1551 (home-page "https://github.com/joshuagryphon/plastid")
1552 (synopsis "Python library for genomic analysis")
1554 "plastid is a Python library for genomic analysis – in particular,
1555 high-throughput sequencing data – with an emphasis on simplicity.")
1556 (license license:bsd-3)))
1558 (define-public python2-plastid
1559 (package-with-python2 python-plastid))
1561 (define-public cd-hit
1567 (uri (string-append "https://github.com/weizhongli/cdhit"
1568 "/releases/download/V" version
1569 "/cd-hit-v" version "-2016-0711.tar.gz"))
1572 "1w8hd4fszgg29nqiz569fldwy012la77nljcmlhglgicws56z54p"))))
1573 (build-system gnu-build-system)
1575 `(#:tests? #f ; there are no tests
1577 ;; Executables are copied directly to the PREFIX.
1578 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1580 (modify-phases %standard-phases
1581 ;; No "configure" script
1583 ;; Remove sources of non-determinism
1584 (add-after 'unpack 'be-timeless
1586 (substitute* "cdhit-utility.c++"
1587 ((" \\(built on \" __DATE__ \"\\)") ""))
1588 (substitute* "cdhit-common.c++"
1589 (("__DATE__") "\"0\"")
1590 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1592 ;; The "install" target does not create the target directory
1593 (add-before 'install 'create-target-dir
1594 (lambda* (#:key outputs #:allow-other-keys)
1595 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1599 (home-page "http://weizhongli-lab.org/cd-hit/")
1600 (synopsis "Cluster and compare protein or nucleotide sequences")
1602 "CD-HIT is a program for clustering and comparing protein or nucleotide
1603 sequences. CD-HIT is designed to be fast and handle extremely large
1605 ;; The manual says: "It can be copied under the GNU General Public License
1606 ;; version 2 (GPLv2)."
1607 (license license:gpl2)))
1609 (define-public clipper
1616 "https://github.com/YeoLab/clipper/archive/"
1618 (file-name (string-append name "-" version ".tar.gz"))
1621 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1622 (modules '((guix build utils)))
1625 ;; remove unnecessary setup dependency
1626 (substitute* "setup.py"
1627 (("setup_requires = .*") ""))
1628 (for-each delete-file
1629 '("clipper/src/peaks.so"
1630 "clipper/src/readsToWiggle.so"))
1631 (delete-file-recursively "dist/")
1633 (build-system python-build-system)
1634 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1637 ("python-pybedtools" ,python2-pybedtools)
1638 ("python-cython" ,python2-cython)
1639 ("python-scikit-learn" ,python2-scikit-learn)
1640 ("python-matplotlib" ,python2-matplotlib)
1641 ("python-pandas" ,python2-pandas)
1642 ("python-pysam" ,python2-pysam)
1643 ("python-numpy" ,python2-numpy)
1644 ("python-scipy" ,python2-scipy)))
1646 `(("python-mock" ,python2-mock) ; for tests
1647 ("python-nose" ,python2-nose) ; for tests
1648 ("python-pytz" ,python2-pytz))) ; for tests
1649 (home-page "https://github.com/YeoLab/clipper")
1650 (synopsis "CLIP peak enrichment recognition")
1652 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1653 (license license:gpl2)))
1655 (define-public codingquarry
1657 (name "codingquarry")
1662 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1666 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1667 (build-system gnu-build-system)
1669 '(#:tests? #f ; no "check" target
1671 (modify-phases %standard-phases
1674 (lambda* (#:key outputs #:allow-other-keys)
1675 (let* ((out (assoc-ref outputs "out"))
1676 (bin (string-append out "/bin"))
1677 (doc (string-append out "/share/doc/codingquarry")))
1678 (install-file "INSTRUCTIONS.pdf" doc)
1679 (copy-recursively "QuarryFiles"
1680 (string-append out "/QuarryFiles"))
1681 (install-file "CodingQuarry" bin)
1682 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1683 (inputs `(("openmpi" ,openmpi)))
1684 (native-search-paths
1685 (list (search-path-specification
1686 (variable "QUARRY_PATH")
1687 (files '("QuarryFiles")))))
1688 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1689 (synopsis "Fungal gene predictor")
1690 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1691 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1692 (home-page "https://sourceforge.net/projects/codingquarry/")
1693 (license license:gpl3+)))
1695 (define-public couger
1702 "http://couger.oit.duke.edu/static/assets/COUGER"
1706 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1707 (build-system gnu-build-system)
1711 (modify-phases %standard-phases
1716 (lambda* (#:key outputs #:allow-other-keys)
1717 (let* ((out (assoc-ref outputs "out"))
1718 (bin (string-append out "/bin")))
1719 (copy-recursively "src" (string-append out "/src"))
1721 ;; Add "src" directory to module lookup path.
1722 (substitute* "couger"
1724 (string-append "import sys\nsys.path.append(\""
1725 out "\")\nfrom argparse")))
1726 (install-file "couger" bin))
1729 'install 'wrap-program
1730 (lambda* (#:key inputs outputs #:allow-other-keys)
1731 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1732 (let* ((out (assoc-ref outputs "out"))
1733 (path (getenv "PYTHONPATH")))
1734 (wrap-program (string-append out "/bin/couger")
1735 `("PYTHONPATH" ":" prefix (,path))))
1738 `(("python" ,python-2)
1739 ("python2-pillow" ,python2-pillow)
1740 ("python2-numpy" ,python2-numpy)
1741 ("python2-scipy" ,python2-scipy)
1742 ("python2-matplotlib" ,python2-matplotlib)))
1744 `(("r-minimal" ,r-minimal)
1746 ("randomjungle" ,randomjungle)))
1748 `(("unzip" ,unzip)))
1749 (home-page "http://couger.oit.duke.edu")
1750 (synopsis "Identify co-factors in sets of genomic regions")
1752 "COUGER can be applied to any two sets of genomic regions bound by
1753 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1754 putative co-factors that provide specificity to each TF. The framework
1755 determines the genomic targets uniquely-bound by each TF, and identifies a
1756 small set of co-factors that best explain the in vivo binding differences
1757 between the two TFs.
1759 COUGER uses classification algorithms (support vector machines and random
1760 forests) with features that reflect the DNA binding specificities of putative
1761 co-factors. The features are generated either from high-throughput TF-DNA
1762 binding data (from protein binding microarray experiments), or from large
1763 collections of DNA motifs.")
1764 (license license:gpl3+)))
1766 (define-public clustal-omega
1768 (name "clustal-omega")
1773 "http://www.clustal.org/omega/clustal-omega-"
1777 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1778 (build-system gnu-build-system)
1780 `(("argtable" ,argtable)))
1781 (home-page "http://www.clustal.org/omega/")
1782 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1784 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1785 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1786 of handling data-sets of hundreds of thousands of sequences in reasonable
1788 (license license:gpl2+)))
1790 (define-public crossmap
1796 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1800 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1801 ;; This patch has been sent upstream already and is available
1802 ;; for download from Sourceforge, but it has not been merged.
1803 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1804 (modules '((guix build utils)))
1805 ;; remove bundled copy of pysam
1807 '(delete-file-recursively "lib/pysam"))))
1808 (build-system python-build-system)
1810 `(#:python ,python-2
1814 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1817 `(("python-numpy" ,python2-numpy)
1818 ("python-pysam" ,python2-pysam)
1821 `(("python-cython" ,python2-cython)
1822 ("python-nose" ,python2-nose)))
1823 (home-page "http://crossmap.sourceforge.net/")
1824 (synopsis "Convert genome coordinates between assemblies")
1826 "CrossMap is a program for conversion of genome coordinates or annotation
1827 files between different genome assemblies. It supports most commonly used
1828 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1829 (license license:gpl2+)))
1831 (define-public cufflinks
1837 (uri (string-append "http://cole-trapnell-lab.github.io/"
1838 "cufflinks/assets/downloads/cufflinks-"
1842 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1843 (build-system gnu-build-system)
1847 ;; The includes for "eigen" are located in a subdirectory.
1848 (string-append "EIGEN_CPPFLAGS="
1849 "-I" (assoc-ref %build-inputs "eigen")
1851 ;; Cufflinks must be linked with various boost libraries.
1852 (string-append "LDFLAGS="
1853 (string-join '("-lboost_system"
1854 "-lboost_serialization"
1855 "-lboost_thread"))))
1857 (modify-phases %standard-phases
1858 (add-after 'unpack 'fix-search-for-bam
1860 (substitute* '("ax_bam.m4"
1863 (("<bam/sam\\.h>") "<samtools/sam.h>")
1864 (("<bam/bam\\.h>") "<samtools/bam.h>")
1865 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1868 (list (string-append "--with-bam="
1869 (assoc-ref %build-inputs "samtools")))))
1872 ("samtools" ,samtools-0.1)
1875 ("python" ,python-2)
1877 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1878 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1880 "Cufflinks assembles RNA transcripts, estimates their abundances,
1881 and tests for differential expression and regulation in RNA-Seq
1882 samples. It accepts aligned RNA-Seq reads and assembles the
1883 alignments into a parsimonious set of transcripts. Cufflinks then
1884 estimates the relative abundances of these transcripts based on how
1885 many reads support each one, taking into account biases in library
1886 preparation protocols.")
1887 (license license:boost1.0)))
1889 (define-public cutadapt
1896 "https://github.com/marcelm/cutadapt/archive/v"
1898 (file-name (string-append name "-" version ".tar.gz"))
1901 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1902 (build-system python-build-system)
1905 (modify-phases %standard-phases
1906 ;; The tests must be run after installation.
1908 (add-after 'install 'check
1909 (lambda* (#:key inputs outputs #:allow-other-keys)
1910 (setenv "PYTHONPATH"
1912 (getenv "PYTHONPATH")
1913 ":" (assoc-ref outputs "out")
1915 (string-take (string-take-right
1916 (assoc-ref inputs "python") 5) 3)
1918 (zero? (system* "nosetests" "-P" "tests")))))))
1920 `(("python-xopen" ,python-xopen)))
1922 `(("python-cython" ,python-cython)
1923 ("python-nose" ,python-nose)))
1924 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1925 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1927 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1928 other types of unwanted sequence from high-throughput sequencing reads.")
1929 (license license:expat)))
1931 (define-public libbigwig
1937 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1938 "archive/" version ".tar.gz"))
1939 (file-name (string-append name "-" version ".tar.gz"))
1942 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1943 (build-system gnu-build-system)
1945 `(#:test-target "test"
1948 (string-append "prefix=" (assoc-ref %outputs "out")))
1950 (modify-phases %standard-phases
1952 (add-before 'check 'disable-curl-test
1954 (substitute* "Makefile"
1955 (("./test/testRemote.*") ""))
1957 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1958 ;; there has not yet been a release containing this change.
1959 (add-before 'install 'create-target-dirs
1960 (lambda* (#:key outputs #:allow-other-keys)
1961 (let ((out (assoc-ref outputs "out")))
1962 (mkdir-p (string-append out "/lib"))
1963 (mkdir-p (string-append out "/include"))
1969 `(("doxygen" ,doxygen)))
1970 (home-page "https://github.com/dpryan79/libBigWig")
1971 (synopsis "C library for handling bigWig files")
1973 "This package provides a C library for parsing local and remote BigWig
1975 (license license:expat)))
1977 (define-public python-pybigwig
1979 (name "python-pybigwig")
1983 (uri (pypi-uri "pyBigWig" version))
1986 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1987 (modules '((guix build utils)))
1990 ;; Delete bundled libBigWig sources
1991 (delete-file-recursively "libBigWig")))))
1992 (build-system python-build-system)
1995 (modify-phases %standard-phases
1996 (add-after 'unpack 'link-with-libBigWig
1997 (lambda* (#:key inputs #:allow-other-keys)
1998 (substitute* "setup.py"
1999 (("libs=\\[") "libs=[\"BigWig\", "))
2002 `(("libbigwig" ,libbigwig)
2005 (home-page "https://github.com/dpryan79/pyBigWig")
2006 (synopsis "Access bigWig files in Python using libBigWig")
2008 "This package provides Python bindings to the libBigWig library for
2009 accessing bigWig files.")
2010 (license license:expat)))
2012 (define-public python2-pybigwig
2013 (package-with-python2 python-pybigwig))
2015 (define-public python-dendropy
2017 (name "python-dendropy")
2022 (uri (pypi-uri "DendroPy" version))
2025 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2026 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2027 (build-system python-build-system)
2028 (home-page "http://packages.python.org/DendroPy/")
2029 (synopsis "Library for phylogenetics and phylogenetic computing")
2031 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2032 writing, simulation, processing and manipulation of phylogenetic
2033 trees (phylogenies) and characters.")
2034 (license license:bsd-3)
2035 (properties `((python2-variant . ,(delay python2-dendropy))))))
2037 (define-public python2-dendropy
2038 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2042 `(#:python ,python-2
2044 (modify-phases %standard-phases
2046 ;; There is currently a test failure that only happens on some
2047 ;; systems, and only using "setup.py test"
2048 (lambda _ (zero? (system* "nosetests")))))))
2049 (native-inputs `(("python2-nose" ,python2-nose)
2050 ,@(package-native-inputs base))))))
2053 (define-public deeptools
2059 (uri (string-append "https://github.com/fidelram/deepTools/"
2060 "archive/" version ".tar.gz"))
2061 (file-name (string-append name "-" version ".tar.gz"))
2064 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2065 (build-system python-build-system)
2067 `(#:python ,python-2))
2069 `(("python-scipy" ,python2-scipy)
2070 ("python-numpy" ,python2-numpy)
2071 ("python-numpydoc" ,python2-numpydoc)
2072 ("python-matplotlib" ,python2-matplotlib)
2073 ("python-bx-python" ,python2-bx-python)
2074 ("python-pysam" ,python2-pysam)
2075 ("python-pybigwig" ,python2-pybigwig)))
2077 `(("python-mock" ,python2-mock) ;for tests
2078 ("python-nose" ,python2-nose) ;for tests
2079 ("python-pytz" ,python2-pytz))) ;for tests
2080 (home-page "https://github.com/fidelram/deepTools")
2081 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2083 "DeepTools addresses the challenge of handling the large amounts of data
2084 that are now routinely generated from DNA sequencing centers. To do so,
2085 deepTools contains useful modules to process the mapped reads data to create
2086 coverage files in standard bedGraph and bigWig file formats. By doing so,
2087 deepTools allows the creation of normalized coverage files or the comparison
2088 between two files (for example, treatment and control). Finally, using such
2089 normalized and standardized files, multiple visualizations can be created to
2090 identify enrichments with functional annotations of the genome.")
2091 (license license:gpl3+)))
2093 (define-public diamond
2100 "https://github.com/bbuchfink/diamond/archive/v"
2102 (file-name (string-append name "-" version ".tar.gz"))
2105 "19lvz661mmgikbry0nvnsjc01fdxqbw9rl2868dvjfraxbcx9ras"))))
2106 (build-system cmake-build-system)
2108 '(#:tests? #f ; no "check" target
2110 (modify-phases %standard-phases
2111 (add-after 'unpack 'remove-native-compilation
2113 (substitute* "CMakeLists.txt" (("-march=native") ""))
2117 (home-page "https://github.com/bbuchfink/diamond")
2118 (synopsis "Accelerated BLAST compatible local sequence aligner")
2120 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2121 translated DNA query sequences against a protein reference database (BLASTP
2122 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2123 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2124 data and settings.")
2125 (license license:agpl3+)))
2127 (define-public discrover
2134 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2136 (file-name (string-append name "-" version ".tar.gz"))
2139 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2140 (build-system cmake-build-system)
2142 `(#:tests? #f ; there are no tests
2144 (modify-phases %standard-phases
2145 (add-after 'unpack 'add-missing-includes
2147 (substitute* "src/executioninformation.hpp"
2148 (("#define EXECUTIONINFORMATION_HPP" line)
2149 (string-append line "\n#include <random>")))
2150 (substitute* "src/plasma/fasta.hpp"
2151 (("#define FASTA_HPP" line)
2152 (string-append line "\n#include <random>")))
2158 `(("texlive" ,texlive)
2159 ("imagemagick" ,imagemagick)))
2160 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2161 (synopsis "Discover discriminative nucleotide sequence motifs")
2162 (description "Discrover is a motif discovery method to find binding sites
2163 of nucleic acid binding proteins.")
2164 (license license:gpl3+)))
2166 (define-public eigensoft
2167 (let ((revision "1")
2168 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2171 (version (string-append "6.1.2-"
2173 (string-take commit 9)))
2178 (url "https://github.com/DReichLab/EIG.git")
2180 (file-name (string-append "eigensoft-" commit "-checkout"))
2183 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2184 (modules '((guix build utils)))
2185 ;; Remove pre-built binaries.
2187 (delete-file-recursively "bin")
2190 (build-system gnu-build-system)
2192 `(#:tests? #f ; There are no tests.
2193 #:make-flags '("CC=gcc")
2195 (modify-phases %standard-phases
2196 ;; There is no configure phase, but the Makefile is in a
2201 ;; The link flags are incomplete.
2202 (substitute* "Makefile"
2203 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2205 ;; The provided install target only copies executables to
2206 ;; the "bin" directory in the build root.
2207 (add-after 'install 'actually-install
2208 (lambda* (#:key outputs #:allow-other-keys)
2209 (let* ((out (assoc-ref outputs "out"))
2210 (bin (string-append out "/bin")))
2211 (for-each (lambda (file)
2212 (install-file file bin))
2213 (find-files "../bin" ".*"))
2218 ("openblas" ,openblas)
2220 ("gfortran" ,gfortran "lib")))
2221 (home-page "https://github.com/DReichLab/EIG")
2222 (synopsis "Tools for population genetics")
2223 (description "The EIGENSOFT package provides tools for population
2224 genetics and stratification correction. EIGENSOFT implements methods commonly
2225 used in population genetics analyses such as PCA, computation of Tracy-Widom
2226 statistics, and finding related individuals in structured populations. It
2227 comes with a built-in plotting script and supports multiple file formats and
2228 quantitative phenotypes.")
2229 ;; The license of the eigensoft tools is Expat, but since it's
2230 ;; linking with the GNU Scientific Library (GSL) the effective
2231 ;; license is the GPL.
2232 (license license:gpl3+))))
2234 (define-public edirect
2240 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2241 "versions/2016-05-03/edirect.tar.gz"))
2244 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2245 (build-system perl-build-system)
2247 `(#:tests? #f ;no "check" target
2249 (modify-phases %standard-phases
2253 (lambda* (#:key outputs #:allow-other-keys)
2254 (let ((target (string-append (assoc-ref outputs "out")
2257 (install-file "edirect.pl" target)
2260 'install 'wrap-program
2261 (lambda* (#:key inputs outputs #:allow-other-keys)
2262 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2263 (let* ((out (assoc-ref outputs "out"))
2264 (path (getenv "PERL5LIB")))
2265 (wrap-program (string-append out "/bin/edirect.pl")
2266 `("PERL5LIB" ":" prefix (,path)))))))))
2268 `(("perl-html-parser" ,perl-html-parser)
2269 ("perl-encode-locale" ,perl-encode-locale)
2270 ("perl-file-listing" ,perl-file-listing)
2271 ("perl-html-tagset" ,perl-html-tagset)
2272 ("perl-html-tree" ,perl-html-tree)
2273 ("perl-http-cookies" ,perl-http-cookies)
2274 ("perl-http-date" ,perl-http-date)
2275 ("perl-http-message" ,perl-http-message)
2276 ("perl-http-negotiate" ,perl-http-negotiate)
2277 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2278 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2279 ("perl-net-http" ,perl-net-http)
2280 ("perl-uri" ,perl-uri)
2281 ("perl-www-robotrules" ,perl-www-robotrules)
2283 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2284 (synopsis "Tools for accessing the NCBI's set of databases")
2286 "Entrez Direct (EDirect) is a method for accessing the National Center
2287 for Biotechnology Information's (NCBI) set of interconnected
2288 databases (publication, sequence, structure, gene, variation, expression,
2289 etc.) from a terminal. Functions take search terms from command-line
2290 arguments. Individual operations are combined to build multi-step queries.
2291 Record retrieval and formatting normally complete the process.
2293 EDirect also provides an argument-driven function that simplifies the
2294 extraction of data from document summaries or other results that are returned
2295 in structured XML format. This can eliminate the need for writing custom
2296 software to answer ad hoc questions.")
2297 (license license:public-domain)))
2299 (define-public exonerate
2308 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2309 "exonerate-" version ".tar.gz"))
2312 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2313 (build-system gnu-build-system)
2315 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2317 `(("pkg-config" ,pkg-config)))
2321 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2322 (synopsis "Generic tool for biological sequence alignment")
2324 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2325 the alignment of sequences using a many alignment models, either exhaustive
2326 dynamic programming or a variety of heuristics.")
2327 (license license:gpl3)))
2329 (define-public express
2337 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2338 version "/express-" version "-src.tgz"))
2341 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2342 (build-system cmake-build-system)
2344 `(#:tests? #f ;no "check" target
2347 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2348 (lambda* (#:key inputs #:allow-other-keys)
2349 (substitute* "CMakeLists.txt"
2350 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2351 "set(Boost_USE_STATIC_LIBS OFF)")
2352 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2353 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2354 (substitute* "src/CMakeLists.txt"
2355 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2356 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2361 ("bamtools" ,bamtools)
2362 ("protobuf" ,protobuf)
2364 (home-page "http://bio.math.berkeley.edu/eXpress")
2365 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2367 "eXpress is a streaming tool for quantifying the abundances of a set of
2368 target sequences from sampled subsequences. Example applications include
2369 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2370 analysis (from RNA-Seq), transcription factor binding quantification in
2371 ChIP-Seq, and analysis of metagenomic data.")
2372 (license license:artistic2.0)))
2374 (define-public express-beta-diversity
2376 (name "express-beta-diversity")
2382 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2384 (file-name (string-append name "-" version ".tar.gz"))
2387 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2388 (build-system gnu-build-system)
2391 (modify-phases %standard-phases
2393 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2395 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2397 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2399 (lambda* (#:key outputs #:allow-other-keys)
2400 (let ((bin (string-append (assoc-ref outputs "out")
2403 (install-file "scripts/convertToEBD.py" bin)
2404 (install-file "bin/ExpressBetaDiversity" bin)
2407 `(("python" ,python-2)))
2408 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2409 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2411 "Express Beta Diversity (EBD) calculates ecological beta diversity
2412 (dissimilarity) measures between biological communities. EBD implements a
2413 variety of diversity measures including those that make use of phylogenetic
2414 similarity of community members.")
2415 (license license:gpl3+)))
2417 (define-public fasttree
2424 "http://www.microbesonline.org/fasttree/FastTree-"
2428 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2429 (build-system gnu-build-system)
2431 `(#:tests? #f ; no "check" target
2433 (modify-phases %standard-phases
2437 (lambda* (#:key source #:allow-other-keys)
2438 (and (zero? (system* "gcc"
2440 "-finline-functions"
2447 (zero? (system* "gcc"
2451 "-finline-functions"
2459 (lambda* (#:key outputs #:allow-other-keys)
2460 (let ((bin (string-append (assoc-ref outputs "out")
2463 (install-file "FastTree" bin)
2464 (install-file "FastTreeMP" bin)
2466 (home-page "http://www.microbesonline.org/fasttree")
2467 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2469 "FastTree can handle alignments with up to a million of sequences in a
2470 reasonable amount of time and memory. For large alignments, FastTree is
2471 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2472 (license license:gpl2+)))
2474 (define-public fastx-toolkit
2476 (name "fastx-toolkit")
2482 "https://github.com/agordon/fastx_toolkit/releases/download/"
2483 version "/fastx_toolkit-" version ".tar.bz2"))
2486 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2487 (build-system gnu-build-system)
2489 `(("libgtextutils" ,libgtextutils)))
2491 `(("pkg-config" ,pkg-config)))
2492 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2493 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2495 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2496 FASTA/FASTQ files preprocessing.
2498 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2499 containing multiple short-reads sequences. The main processing of such
2500 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2501 is sometimes more productive to preprocess the files before mapping the
2502 sequences to the genome---manipulating the sequences to produce better mapping
2503 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2504 (license license:agpl3+)))
2506 (define-public flexbar
2513 (string-append "mirror://sourceforge/flexbar/"
2514 version "/flexbar_v" version "_src.tgz"))
2517 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2518 (build-system cmake-build-system)
2520 `(#:configure-flags (list
2521 (string-append "-DFLEXBAR_BINARY_DIR="
2522 (assoc-ref %outputs "out")
2527 (lambda* (#:key outputs #:allow-other-keys)
2528 (setenv "PATH" (string-append
2529 (assoc-ref outputs "out") "/bin:"
2531 (chdir "../flexbar_v2.5_src/test")
2532 (zero? (system* "bash" "flexbar_validate.sh")))
2533 (alist-delete 'install %standard-phases))))
2538 `(("pkg-config" ,pkg-config)
2540 (home-page "http://flexbar.sourceforge.net")
2541 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2543 "Flexbar preprocesses high-throughput nucleotide sequencing data
2544 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2545 Moreover, trimming and filtering features are provided. Flexbar increases
2546 read mapping rates and improves genome and transcriptome assemblies. It
2547 supports next-generation sequencing data in fasta/q and csfasta/q format from
2548 Illumina, Roche 454, and the SOLiD platform.")
2549 (license license:gpl3)))
2551 (define-public fraggenescan
2553 (name "fraggenescan")
2559 (string-append "mirror://sourceforge/fraggenescan/"
2560 "FragGeneScan" version ".tar.gz"))
2562 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2563 (build-system gnu-build-system)
2566 (modify-phases %standard-phases
2568 (add-before 'build 'patch-paths
2569 (lambda* (#:key outputs #:allow-other-keys)
2570 (let* ((out (string-append (assoc-ref outputs "out")))
2571 (share (string-append out "/share/fraggenescan/")))
2572 (substitute* "run_FragGeneScan.pl"
2574 (string-append "system(\"" (which "rm")))
2576 (string-append "system(\"" (which "mv")))
2577 ;; This script and other programs expect the training files
2578 ;; to be in the non-standard location bin/train/XXX. Change
2579 ;; this to be share/fraggenescan/train/XXX instead.
2580 (("^\\$train.file = \\$dir.*")
2581 (string-append "$train_file = \""
2583 "train/\".$FGS_train_file;")))
2584 (substitute* "run_hmm.c"
2585 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2586 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2587 (substitute* "post_process.pl"
2588 (("^my \\$dir = substr.*")
2589 (string-append "my $dir = \"" share "\";"))))
2592 (lambda _ (and (zero? (system* "make" "clean"))
2593 (zero? (system* "make" "fgs")))))
2595 (lambda* (#:key outputs #:allow-other-keys)
2596 (let* ((out (string-append (assoc-ref outputs "out")))
2597 (bin (string-append out "/bin/"))
2598 (share (string-append out "/share/fraggenescan/train")))
2599 (install-file "run_FragGeneScan.pl" bin)
2600 (install-file "FragGeneScan" bin)
2601 (install-file "FGS_gff.py" bin)
2602 (install-file "post_process.pl" bin)
2603 (copy-recursively "train" share))))
2605 (add-after 'install 'post-install-check
2606 ;; In lieu of 'make check', run one of the examples and check the
2607 ;; output files gets created.
2608 (lambda* (#:key outputs #:allow-other-keys)
2609 (let* ((out (string-append (assoc-ref outputs "out")))
2610 (bin (string-append out "/bin/")))
2611 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2612 "-genome=./example/NC_000913.fna"
2616 (file-exists? "test2.faa")
2617 (file-exists? "test2.ffn")
2618 (file-exists? "test2.gff")
2619 (file-exists? "test2.out"))))))))
2622 ("python" ,python-2))) ;not compatible with python 3.
2623 (home-page "https://sourceforge.net/projects/fraggenescan/")
2624 (synopsis "Finds potentially fragmented genes in short reads")
2626 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2627 short and error-prone DNA sequencing reads. It can also be applied to predict
2628 genes in incomplete assemblies or complete genomes.")
2629 ;; GPL3+ according to private correspondense with the authors.
2630 (license license:gpl3+)))
2632 (define-public fxtract
2633 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2641 "https://github.com/ctSkennerton/fxtract/archive/"
2643 (file-name (string-append "ctstennerton-util-"
2644 (string-take util-commit 7)
2648 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2649 (build-system gnu-build-system)
2651 `(#:make-flags (list
2652 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2654 #:test-target "fxtract_test"
2656 (modify-phases %standard-phases
2658 (add-before 'build 'copy-util
2659 (lambda* (#:key inputs #:allow-other-keys)
2661 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2663 ;; Do not use make install as this requires additional dependencies.
2665 (lambda* (#:key outputs #:allow-other-keys)
2666 (let* ((out (assoc-ref outputs "out"))
2667 (bin (string-append out"/bin")))
2668 (install-file "fxtract" bin)
2674 ;; ctskennerton-util is licensed under GPL2.
2675 `(("ctskennerton-util"
2679 (url "https://github.com/ctSkennerton/util.git")
2680 (commit util-commit)))
2681 (file-name (string-append
2682 "ctstennerton-util-" util-commit "-checkout"))
2685 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2686 (home-page "https://github.com/ctSkennerton/fxtract")
2687 (synopsis "Extract sequences from FASTA and FASTQ files")
2689 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2690 or FASTQ) file given a subsequence. It uses a simple substring search for
2691 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2692 lookups or multi-pattern searching as required. By default fxtract looks in
2693 the sequence of each record but can also be told to look in the header,
2694 comment or quality sections.")
2695 ;; 'util' requires SSE instructions.
2696 (supported-systems '("x86_64-linux"))
2697 (license license:expat))))
2699 (define-public gemma
2705 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2707 (file-name (string-append name "-" version ".tar.gz"))
2710 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))))
2715 (build-system gnu-build-system)
2717 `(#:make-flags '("FORCE_DYNAMIC=1") ; use shared libs
2719 (modify-phases %standard-phases
2721 (add-before 'build 'bin-mkdir
2725 (lambda* (#:key outputs #:allow-other-keys)
2726 (let ((out (assoc-ref outputs "out")))
2727 (install-file "bin/gemma"
2730 #:tests? #f)) ; no tests included yet
2731 (home-page "https://github.com/xiangzhou/GEMMA")
2732 (synopsis "Tool for genome-wide efficient mixed model association")
2734 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2735 standard linear mixed model resolver with application in genome-wide
2736 association studies (GWAS).")
2737 (license license:gpl3)))
2746 "https://github.com/nboley/grit/archive/"
2748 (file-name (string-append name "-" version ".tar.gz"))
2751 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2752 (build-system python-build-system)
2754 `(#:python ,python-2
2757 'unpack 'generate-from-cython-sources
2758 (lambda* (#:key inputs outputs #:allow-other-keys)
2759 ;; Delete these C files to force fresh generation from pyx sources.
2760 (delete-file "grit/sparsify_support_fns.c")
2761 (delete-file "grit/call_peaks_support_fns.c")
2762 (substitute* "setup.py"
2763 (("Cython.Setup") "Cython.Build")
2764 ;; Add numpy include path to fix compilation
2766 (string-append "pyx\", ], include_dirs = ['"
2767 (assoc-ref inputs "python-numpy")
2768 "/lib/python2.7/site-packages/numpy/core/include/"
2772 `(("python-scipy" ,python2-scipy)
2773 ("python-numpy" ,python2-numpy)
2774 ("python-pysam" ,python2-pysam)
2775 ("python-networkx" ,python2-networkx)))
2777 `(("python-cython" ,python2-cython)))
2778 (home-page "http://grit-bio.org")
2779 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2781 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2782 full length transcript models. When none of these data sources are available,
2783 GRIT can be run by providing a candidate set of TES or TSS sites. In
2784 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2785 also be run in quantification mode, where it uses a provided GTF file and just
2786 estimates transcript expression.")
2787 (license license:gpl3+)))
2789 (define-public hisat
2796 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2797 version "-beta-source.zip"))
2800 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2801 (build-system gnu-build-system)
2803 `(#:tests? #f ;no check target
2804 #:make-flags '("allall"
2805 ;; Disable unsupported `popcnt' instructions on
2806 ;; architectures other than x86_64
2807 ,@(if (string-prefix? "x86_64"
2808 (or (%current-target-system)
2811 '("POPCNT_CAPABILITY=0")))
2814 'unpack 'patch-sources
2816 ;; XXX Cannot use snippet because zip files are not supported
2817 (substitute* "Makefile"
2818 (("^CC = .*$") "CC = gcc")
2819 (("^CPP = .*$") "CPP = g++")
2820 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2821 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2822 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2823 (substitute* '("hisat-build" "hisat-inspect")
2824 (("/usr/bin/env") (which "env"))))
2827 (lambda* (#:key outputs #:allow-other-keys)
2828 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2829 (for-each (lambda (file)
2830 (install-file file bin))
2833 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2834 (alist-delete 'configure %standard-phases)))))
2836 `(("unzip" ,unzip)))
2841 ;; Non-portable SSE instructions are used so building fails on platforms
2842 ;; other than x86_64.
2843 (supported-systems '("x86_64-linux"))
2844 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2845 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2847 "HISAT is a fast and sensitive spliced alignment program for mapping
2848 RNA-seq reads. In addition to one global FM index that represents a whole
2849 genome, HISAT uses a large set of small FM indexes that collectively cover the
2850 whole genome. These small indexes (called local indexes) combined with
2851 several alignment strategies enable effective alignment of RNA-seq reads, in
2852 particular, reads spanning multiple exons.")
2853 (license license:gpl3+)))
2855 (define-public hisat2
2862 ;; FIXME: a better source URL is
2863 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2864 ;; "/downloads/hisat2-" version "-source.zip")
2865 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2866 ;; but it is currently unavailable.
2867 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2868 (file-name (string-append name "-" version ".tar.gz"))
2871 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2872 (build-system gnu-build-system)
2874 `(#:tests? #f ; no check target
2875 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2876 #:modules ((guix build gnu-build-system)
2880 (modify-phases %standard-phases
2881 (add-after 'unpack 'make-deterministic
2883 (substitute* "Makefile"
2888 (lambda* (#:key outputs #:allow-other-keys)
2889 (let* ((out (assoc-ref outputs "out"))
2890 (bin (string-append out "/bin/"))
2891 (doc (string-append out "/share/doc/hisat2/")))
2893 (cut install-file <> bin)
2895 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2897 (install-file "doc/manual.inc.html" doc))
2900 `(("unzip" ,unzip) ; needed for archive from ftp
2902 ("pandoc" ,ghc-pandoc))) ; for documentation
2903 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2904 (synopsis "Graph-based alignment of genomic sequencing reads")
2905 (description "HISAT2 is a fast and sensitive alignment program for mapping
2906 next-generation sequencing reads (both DNA and RNA) to a population of human
2907 genomes (as well as to a single reference genome). In addition to using one
2908 global @dfn{graph FM} (GFM) index that represents a population of human
2909 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2910 the whole genome. These small indexes, combined with several alignment
2911 strategies, enable rapid and accurate alignment of sequencing reads. This new
2912 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2913 ;; HISAT2 contains files from Bowtie2, which is released under
2914 ;; GPLv2 or later. The HISAT2 source files are released under
2916 (license license:gpl3+)))
2918 (define-public hmmer
2926 "http://eddylab.org/software/hmmer"
2927 (version-prefix version 1) "/"
2928 version "/hmmer-" version ".tar.gz"))
2931 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2932 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2933 (build-system gnu-build-system)
2934 (native-inputs `(("perl" ,perl)))
2935 (home-page "http://hmmer.org/")
2936 (synopsis "Biosequence analysis using profile hidden Markov models")
2938 "HMMER is used for searching sequence databases for homologs of protein
2939 sequences, and for making protein sequence alignments. It implements methods
2940 using probabilistic models called profile hidden Markov models (profile
2942 (license (list license:gpl3+
2943 ;; The bundled library 'easel' is distributed
2944 ;; under The Janelia Farm Software License.
2945 (license:non-copyleft
2946 "file://easel/LICENSE"
2947 "See easel/LICENSE in the distribution.")))))
2949 (define-public htseq
2956 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2960 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2961 (build-system python-build-system)
2962 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2963 ;; Numpy needs to be propagated when htseq is used as a Python library.
2965 `(("python-numpy" ,python2-numpy)))
2967 `(("python-pysam" ,python2-pysam)))
2968 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2969 (synopsis "Analysing high-throughput sequencing data with Python")
2971 "HTSeq is a Python package that provides infrastructure to process data
2972 from high-throughput sequencing assays.")
2973 (license license:gpl3+)))
2975 (define-public java-htsjdk
2977 (name "java-htsjdk")
2982 "https://github.com/samtools/htsjdk/archive/"
2984 (file-name (string-append name "-" version ".tar.gz"))
2987 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2988 (modules '((guix build utils)))
2989 ;; remove build dependency on git
2990 (snippet '(substitute* "build.xml"
2991 (("failifexecutionfails=\"true\"")
2992 "failifexecutionfails=\"false\"")))))
2993 (build-system ant-build-system)
2995 `(#:tests? #f ; test require Internet access
2997 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2998 "/share/java/htsjdk/"))
2999 #:build-target "all"
3001 (modify-phases %standard-phases
3002 ;; The build phase also installs the jars
3003 (delete 'install))))
3004 (home-page "http://samtools.github.io/htsjdk/")
3005 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3007 "HTSJDK is an implementation of a unified Java library for accessing
3008 common file formats, such as SAM and VCF, used for high-throughput
3009 sequencing (HTS) data. There are also an number of useful utilities for
3010 manipulating HTS data.")
3011 (license license:expat)))
3013 (define-public htslib
3020 "https://github.com/samtools/htslib/releases/download/"
3021 version "/htslib-" version ".tar.bz2"))
3024 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
3025 (build-system gnu-build-system)
3028 (modify-phases %standard-phases
3030 'unpack 'patch-tests
3032 (substitute* "test/test.pl"
3033 (("/bin/bash") (which "bash")))
3039 (home-page "http://www.htslib.org")
3040 (synopsis "C library for reading/writing high-throughput sequencing data")
3042 "HTSlib is a C library for reading/writing high-throughput sequencing
3043 data. It also provides the bgzip, htsfile, and tabix utilities.")
3044 ;; Files under cram/ are released under the modified BSD license;
3045 ;; the rest is released under the Expat license
3046 (license (list license:expat license:bsd-3))))
3055 "https://github.com/nboley/idr/archive/"
3057 (file-name (string-append name "-" version ".tar.gz"))
3060 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3061 (build-system python-build-system)
3063 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3065 `(("python-scipy" ,python-scipy)
3066 ("python-sympy" ,python-sympy)
3067 ("python-numpy" ,python-numpy)
3068 ("python-matplotlib" ,python-matplotlib)))
3070 `(("python-cython" ,python-cython)))
3071 (home-page "https://github.com/nboley/idr")
3072 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3074 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3075 to measure the reproducibility of findings identified from replicate
3076 experiments and provide highly stable thresholds based on reproducibility.")
3077 (license license:gpl3+)))
3079 (define-public jellyfish
3085 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3086 "releases/download/v" version
3087 "/jellyfish-" version ".tar.gz"))
3090 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3091 (build-system gnu-build-system)
3092 (outputs '("out" ;for library
3093 "ruby" ;for Ruby bindings
3094 "python")) ;for Python bindings
3097 (list (string-append "--enable-ruby-binding="
3098 (assoc-ref %outputs "ruby"))
3099 (string-append "--enable-python-binding="
3100 (assoc-ref %outputs "python")))
3102 (modify-phases %standard-phases
3103 (add-before 'check 'set-SHELL-variable
3105 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3107 (setenv "SHELL" (which "bash"))
3113 ("python" ,python-2)))
3114 (synopsis "Tool for fast counting of k-mers in DNA")
3116 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3117 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3118 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3119 is a command-line program that reads FASTA and multi-FASTA files containing
3120 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3121 translated into a human-readable text format using the @code{jellyfish dump}
3122 command, or queried for specific k-mers with @code{jellyfish query}.")
3123 (home-page "http://www.genome.umd.edu/jellyfish.html")
3124 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3125 (supported-systems '("x86_64-linux"))
3126 ;; The combined work is published under the GPLv3 or later. Individual
3127 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3128 (license (list license:gpl3+ license:expat))))
3130 (define-public khmer
3137 (uri (pypi-uri "khmer" version))
3140 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3141 (patches (search-patches "khmer-use-libraries.patch"))))
3142 (build-system python-build-system)
3145 (modify-phases %standard-phases
3146 (add-after 'unpack 'set-paths
3147 (lambda* (#:key inputs outputs #:allow-other-keys)
3148 ;; Delete bundled libraries.
3149 (delete-file-recursively "third-party/zlib")
3150 (delete-file-recursively "third-party/bzip2")
3151 ;; Replace bundled seqan.
3152 (let* ((seqan-all "third-party/seqan")
3153 (seqan-include (string-append
3154 seqan-all "/core/include")))
3155 (delete-file-recursively seqan-all)
3156 (copy-recursively (string-append (assoc-ref inputs "seqan")
3158 (string-append seqan-include "/seqan")))
3159 ;; We do not replace the bundled MurmurHash as the canonical
3160 ;; repository for this code 'SMHasher' is unsuitable for
3161 ;; providing a library. See
3162 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3164 (add-after 'unpack 'set-cc
3168 ;; It is simpler to test after installation.
3170 (add-after 'install 'post-install-check
3171 (lambda* (#:key inputs outputs #:allow-other-keys)
3172 (let ((out (assoc-ref outputs "out")))
3177 (assoc-ref outputs "out")
3179 (setenv "PYTHONPATH"
3181 (getenv "PYTHONPATH")
3185 (string-take (string-take-right
3186 (assoc-ref inputs "python") 5) 3)
3188 (with-directory-excursion "build"
3189 (zero? (system* "nosetests" "khmer" "--attr"
3190 "!known_failing")))))))))
3193 ("python-nose" ,python-nose)))
3197 ("python-screed" ,python-screed)
3198 ("python-bz2file" ,python-bz2file)
3199 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3200 ;; until the next version of khmer (likely 2.1) is released.
3202 (home-page "https://khmer.readthedocs.org/")
3203 (synopsis "K-mer counting, filtering and graph traversal library")
3204 (description "The khmer software is a set of command-line tools for
3205 working with DNA shotgun sequencing data from genomes, transcriptomes,
3206 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3207 sometimes better. Khmer can also identify and fix problems with shotgun
3209 ;; When building on i686, armhf and mips64el, we get the following error:
3210 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3211 (supported-systems '("x86_64-linux"))
3212 (license license:bsd-3)))
3217 (version "2.1.0.20151222")
3220 (uri (pypi-uri "MACS2" version))
3223 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3224 (build-system python-build-system)
3226 `(#:python ,python-2 ; only compatible with Python 2.7
3227 #:tests? #f)) ; no test target
3229 `(("python-numpy" ,python2-numpy)))
3230 (home-page "https://github.com/taoliu/MACS/")
3231 (synopsis "Model based analysis for ChIP-Seq data")
3233 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3234 identifying transcript factor binding sites named Model-based Analysis of
3235 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3236 the significance of enriched ChIP regions and it improves the spatial
3237 resolution of binding sites through combining the information of both
3238 sequencing tag position and orientation.")
3239 (license license:bsd-3)))
3241 (define-public mafft
3248 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3249 "-without-extensions-src.tgz"))
3250 (file-name (string-append name "-" version ".tgz"))
3253 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3254 (build-system gnu-build-system)
3256 `(#:tests? #f ; no automated tests, though there are tests in the read me
3257 #:make-flags (let ((out (assoc-ref %outputs "out")))
3258 (list (string-append "PREFIX=" out)
3259 (string-append "BINDIR="
3260 (string-append out "/bin"))))
3262 (modify-phases %standard-phases
3263 (add-after 'unpack 'enter-dir
3264 (lambda _ (chdir "core") #t))
3265 (add-after 'enter-dir 'patch-makefile
3267 ;; on advice from the MAFFT authors, there is no need to
3268 ;; distribute mafft-profile, mafft-distance, or
3269 ;; mafft-homologs.rb as they are too "specialised".
3270 (substitute* "Makefile"
3271 ;; remove mafft-homologs.rb from SCRIPTS
3272 (("^SCRIPTS = mafft mafft-homologs.rb")
3274 ;; remove mafft-homologs from MANPAGES
3275 (("^MANPAGES = mafft.1 mafft-homologs.1")
3276 "MANPAGES = mafft.1")
3277 ;; remove mafft-distance from PROGS
3278 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3279 "PROGS = dvtditr dndfast7 dndblast sextet5")
3280 ;; remove mafft-profile from PROGS
3281 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3282 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3283 (("^rm -f mafft-profile mafft-profile.exe") "#")
3284 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3285 ;; do not install MAN pages in libexec folder
3286 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3287 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3289 (add-after 'enter-dir 'patch-paths
3290 (lambda* (#:key inputs #:allow-other-keys)
3291 (substitute* '("pairash.c"
3293 (("perl") (which "perl"))
3294 (("([\"`| ])awk" _ prefix)
3295 (string-append prefix (which "awk")))
3296 (("grep") (which "grep")))
3299 (add-after 'install 'wrap-programs
3300 (lambda* (#:key outputs #:allow-other-keys)
3301 (let* ((out (assoc-ref outputs "out"))
3302 (bin (string-append out "/bin"))
3303 (path (string-append
3304 (assoc-ref %build-inputs "coreutils") "/bin:")))
3305 (for-each (lambda (file)
3307 `("PATH" ":" prefix (,path))))
3315 ("coreutils" ,coreutils)))
3316 (home-page "http://mafft.cbrc.jp/alignment/software/")
3317 (synopsis "Multiple sequence alignment program")
3319 "MAFFT offers a range of multiple alignment methods for nucleotide and
3320 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3321 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3323 (license (license:non-copyleft
3324 "http://mafft.cbrc.jp/alignment/software/license.txt"
3325 "BSD-3 with different formatting"))))
3334 "https://github.com/marbl/mash/archive/v"
3336 (file-name (string-append name "-" version ".tar.gz"))
3339 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3340 (modules '((guix build utils)))
3342 ;; Delete bundled kseq.
3343 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3344 '(delete-file "src/mash/kseq.h"))))
3345 (build-system gnu-build-system)
3347 `(#:tests? #f ; No tests.
3350 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3351 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3352 #:make-flags (list "CC=gcc")
3354 (modify-phases %standard-phases
3355 (add-after 'unpack 'fix-includes
3357 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3358 (("^#include \"kseq\\.h\"")
3359 "#include \"htslib/kseq.h\""))
3361 (add-before 'configure 'autoconf
3362 (lambda _ (zero? (system* "autoconf")))))))
3364 `(("autoconf" ,autoconf)
3365 ;; Capnproto and htslib are statically embedded in the final
3366 ;; application. Therefore we also list their licenses, below.
3367 ("capnproto" ,capnproto)
3368 ("htslib" ,htslib)))
3372 (supported-systems '("x86_64-linux"))
3373 (home-page "https://mash.readthedocs.io")
3374 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3375 (description "Mash is a fast sequence distance estimator that uses the
3376 MinHash algorithm and is designed to work with genomes and metagenomes in the
3377 form of assemblies or reads.")
3378 (license (list license:bsd-3 ; Mash
3379 license:expat ; HTSlib and capnproto
3380 license:public-domain ; MurmurHash 3
3381 license:cpl1.0)))) ; Open Bloom Filter
3383 (define-public metabat
3384 ;; We package from a git commit because compilation of the released version
3386 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3389 (version (string-append "0.32.4-1." (string-take commit 8)))
3394 (url "https://bitbucket.org/berkeleylab/metabat.git")
3396 (file-name (string-append name "-" version))
3399 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3400 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3401 (build-system gnu-build-system)
3404 (modify-phases %standard-phases
3405 (add-after 'unpack 'fix-includes
3407 (substitute* "src/BamUtils.h"
3408 (("^#include \"bam/bam\\.h\"")
3409 "#include \"samtools/bam.h\"")
3410 (("^#include \"bam/sam\\.h\"")
3411 "#include \"samtools/sam.h\""))
3412 (substitute* "src/KseqReader.h"
3413 (("^#include \"bam/kseq\\.h\"")
3414 "#include \"htslib/kseq.h\""))
3416 (add-after 'unpack 'fix-scons
3417 (lambda* (#:key inputs #:allow-other-keys)
3418 (substitute* "SConstruct"
3419 (("^htslib_dir = 'samtools'")
3420 (string-append "hitslib_dir = '"
3421 (assoc-ref inputs "htslib")
3423 (("^samtools_dir = 'samtools'")
3424 (string-append "samtools_dir = '"
3425 (assoc-ref inputs "htslib")
3427 (("^findStaticOrShared\\('bam', hts_lib")
3428 (string-append "findStaticOrShared('bam', '"
3429 (assoc-ref inputs "samtools")
3431 ;; Do not distribute README.
3432 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3436 (lambda* (#:key inputs outputs #:allow-other-keys)
3437 (mkdir (assoc-ref outputs "out"))
3438 (zero? (system* "scons"
3441 (assoc-ref outputs "out"))
3444 (assoc-ref inputs "boost"))
3446 ;; Check and install are carried out during build phase.
3448 (delete 'install))))
3452 ("samtools" ,samtools)
3456 `(("scons" ,scons)))
3457 (home-page "https://bitbucket.org/berkeleylab/metabat")
3459 "Reconstruction of single genomes from complex microbial communities")
3461 "Grouping large genomic fragments assembled from shotgun metagenomic
3462 sequences to deconvolute complex microbial communities, or metagenome binning,
3463 enables the study of individual organisms and their interactions. MetaBAT is
3464 an automated metagenome binning software, which integrates empirical
3465 probabilistic distances of genome abundance and tetranucleotide frequency.")
3466 (license (license:non-copyleft "file://license.txt"
3467 "See license.txt in the distribution.")))))
3469 (define-public minced
3476 "https://github.com/ctSkennerton/minced/archive/"
3478 (file-name (string-append name "-" version ".tar.gz"))
3481 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3482 (build-system gnu-build-system)
3484 `(#:test-target "test"
3486 (modify-phases %standard-phases
3488 (add-before 'check 'fix-test
3490 ;; Fix test for latest version.
3491 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3492 (("minced:0.1.6") "minced:0.2.0"))
3494 (replace 'install ; No install target.
3495 (lambda* (#:key inputs outputs #:allow-other-keys)
3496 (let* ((out (assoc-ref outputs "out"))
3497 (bin (string-append out "/bin"))
3498 (wrapper (string-append bin "/minced")))
3499 ;; Minced comes with a wrapper script that tries to figure out where
3500 ;; it is located before running the JAR. Since these paths are known
3501 ;; to us, we build our own wrapper to avoid coreutils dependency.
3502 (install-file "minced.jar" bin)
3503 (with-output-to-file wrapper
3507 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3508 (assoc-ref inputs "jre") "/bin/java -jar "
3509 bin "/minced.jar \"$@\"\n"))))
3510 (chmod wrapper #o555)))))))
3512 `(("jdk" ,icedtea "jdk")))
3515 ("jre" ,icedtea "out")))
3516 (home-page "https://github.com/ctSkennerton/minced")
3517 (synopsis "Mining CRISPRs in Environmental Datasets")
3519 "MinCED is a program to find Clustered Regularly Interspaced Short
3520 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3521 unassembled metagenomic reads, but is mainly designed for full genomes and
3522 assembled metagenomic sequence.")
3523 (license license:gpl3+)))
3532 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3536 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3537 (modules '((guix build utils)))
3539 '(substitute* "setup.py"
3540 ;; Use setuptools, or else the executables are not
3542 (("distutils.core") "setuptools")
3543 ;; use "gcc" instead of "cc" for compilation
3545 "cc.set_executables(
3549 linker_so='gcc -shared'); defines")))))
3550 (build-system python-build-system)
3552 `(#:python ,python-2 ; only Python 2 is supported
3553 #:tests? #f)) ; no "test" target
3555 `(("samtools" ,samtools)
3556 ("python-numpy" ,python2-numpy)
3557 ("python-pysam" ,python2-pysam)
3558 ("python-scipy" ,python2-scipy)
3559 ("python-matplotlib" ,python2-matplotlib)))
3561 `(("python-mock" ,python2-mock) ;for tests
3562 ("python-pytz" ,python2-pytz))) ;for tests
3563 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3564 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3566 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3567 the expression level of alternatively spliced genes from RNA-Seq data, and
3568 identifies differentially regulated isoforms or exons across samples. By
3569 modeling the generative process by which reads are produced from isoforms in
3570 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3571 that a read originated from a particular isoform.")
3572 (license license:gpl2)))
3574 (define-public muscle
3577 (version "3.8.1551")
3579 (method url-fetch/tarbomb)
3581 "http://www.drive5.com/muscle/muscle_src_"
3585 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3586 (build-system gnu-build-system)
3588 `(#:make-flags (list "LDLIBS = -lm")
3590 (modify-phases %standard-phases
3593 ;; There are no tests, so just test if it runs.
3594 (lambda _ (zero? (system* "./muscle" "-version"))))
3596 (lambda* (#:key outputs #:allow-other-keys)
3597 (let* ((out (assoc-ref outputs "out"))
3598 (bin (string-append out "/bin")))
3599 (install-file "muscle" bin)))))))
3600 (home-page "http://www.drive5.com/muscle")
3601 (synopsis "Multiple sequence alignment program")
3603 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3604 program for nucleotide and protein sequences.")
3605 ;; License information found in 'muscle -h' and usage.cpp.
3606 (license license:public-domain)))
3608 (define-public newick-utils
3609 ;; There are no recent releases so we package from git.
3610 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3612 (name "newick-utils")
3613 (version (string-append "1.6-1." (string-take commit 8)))
3617 (url "https://github.com/tjunier/newick_utils.git")
3619 (file-name (string-append name "-" version "-checkout"))
3622 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3623 (build-system gnu-build-system)
3626 (modify-phases %standard-phases
3627 (add-after 'unpack 'autoconf
3628 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3630 ;; XXX: TODO: Enable Lua and Guile bindings.
3631 ;; https://github.com/tjunier/newick_utils/issues/13
3632 `(("libxml2" ,libxml2)
3636 `(("autoconf" ,autoconf)
3637 ("automake" ,automake)
3638 ("libtool" ,libtool)))
3639 (synopsis "Programs for working with newick format phylogenetic trees")
3641 "Newick-utils is a suite of utilities for processing phylogenetic trees
3642 in Newick format. Functions include re-rooting, extracting subtrees,
3643 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3644 (home-page "https://github.com/tjunier/newick_utils")
3645 (license license:bsd-3))))
3654 "https://github.com/wwood/OrfM/releases/download/v"
3655 version "/orfm-" version ".tar.gz"))
3658 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
3659 (build-system gnu-build-system)
3660 (inputs `(("zlib" ,zlib)))
3662 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3663 ("ruby-rspec" ,ruby-rspec)
3665 (synopsis "Simple and not slow open reading frame (ORF) caller")
3667 "An ORF caller finds stretches of DNA that, when translated, are not
3668 interrupted by stop codons. OrfM finds and prints these ORFs.")
3669 (home-page "https://github.com/wwood/OrfM")
3670 (license license:lgpl3+)))
3672 (define-public pplacer
3673 (let ((commit "g807f6f3"))
3676 ;; The commit should be updated with each version change.
3677 (version "1.1.alpha19")
3681 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3683 (file-name (string-append name "-" version ".tar.gz"))
3685 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3686 (build-system ocaml-build-system)
3688 `(#:ocaml ,ocaml-4.01
3689 #:findlib ,ocaml4.01-findlib
3690 #:modules ((guix build ocaml-build-system)
3694 (modify-phases %standard-phases
3696 (add-after 'unpack 'replace-bundled-cddlib
3697 (lambda* (#:key inputs #:allow-other-keys)
3698 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3699 (local-dir "cddlib_guix"))
3701 (with-directory-excursion local-dir
3702 (system* "tar" "xvf" cddlib-src))
3703 (let ((cddlib-src-folder
3704 (string-append local-dir "/"
3705 (list-ref (scandir local-dir) 2)
3710 (string-append "cdd_src/" (basename file))))
3711 (find-files cddlib-src-folder ".*[ch]$")))
3713 (add-after 'unpack 'fix-makefile
3715 ;; Remove system calls to 'git'.
3716 (substitute* "Makefile"
3717 (("^DESCRIPT:=pplacer-.*")
3719 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3720 (substitute* "myocamlbuild.ml"
3721 (("git describe --tags --long .*\\\" with")
3723 "echo -n v" ,version "-" ,commit "\" with")))
3726 (lambda* (#:key outputs #:allow-other-keys)
3727 (let* ((out (assoc-ref outputs "out"))
3728 (bin (string-append out "/bin")))
3729 (copy-recursively "bin" bin))
3734 ("ocaml-ounit" ,ocaml4.01-ounit)
3735 ("ocaml-batteries" ,ocaml4.01-batteries)
3736 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3737 ("ocaml-csv" ,ocaml4.01-csv)
3738 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3739 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3740 ("ocaml-mcl" ,ocaml4.01-mcl)
3741 ("ocaml-gsl" ,ocaml4.01-gsl)
3742 ("cddlib-src" ,(package-source cddlib))))
3744 `(("pplacer-scripts" ,pplacer-scripts)))
3745 (synopsis "Phylogenetic placement of biological sequences")
3747 "Pplacer places query sequences on a fixed reference phylogenetic tree
3748 to maximize phylogenetic likelihood or posterior probability according to a
3749 reference alignment. Pplacer is designed to be fast, to give useful
3750 information about uncertainty, and to offer advanced visualization and
3751 downstream analysis.")
3752 (home-page "http://matsen.fhcrc.org/pplacer")
3753 (license license:gpl3))))
3755 ;; This package is installed alongside 'pplacer'. It is a separate package so
3756 ;; that it can use the python-build-system for the scripts that are
3757 ;; distributed alongside the main OCaml binaries.
3758 (define pplacer-scripts
3761 (name "pplacer-scripts")
3762 (build-system python-build-system)
3764 `(#:python ,python-2
3766 (modify-phases %standard-phases
3767 (add-after 'unpack 'enter-scripts-dir
3768 (lambda _ (chdir "scripts")))
3771 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3772 (add-after 'install 'wrap-executables
3773 (lambda* (#:key inputs outputs #:allow-other-keys)
3774 (let* ((out (assoc-ref outputs "out"))
3775 (bin (string-append out "/bin")))
3776 (let ((path (string-append
3777 (assoc-ref inputs "hmmer") "/bin:"
3778 (assoc-ref inputs "infernal") "/bin")))
3780 (wrap-program (string-append bin "/refpkg_align.py")
3781 `("PATH" ":" prefix (,path))))
3782 (let ((path (string-append
3783 (assoc-ref inputs "hmmer") "/bin")))
3784 (wrap-program (string-append bin "/hrefpkg_query.py")
3785 `("PATH" ":" prefix (,path)))))
3788 `(("infernal" ,infernal)
3791 `(("python-biopython" ,python2-biopython)
3792 ("taxtastic" ,taxtastic)))
3793 (synopsis "Pplacer Python scripts")))
3795 (define-public python2-pbcore
3797 (name "python2-pbcore")
3801 (uri (pypi-uri "pbcore" version))
3804 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3805 (build-system python-build-system)
3806 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3808 `(("python-cython" ,python2-cython)
3809 ("python-numpy" ,python2-numpy)
3810 ("python-pysam" ,python2-pysam)
3811 ("python-h5py" ,python2-h5py)))
3813 `(("python-nose" ,python2-nose)
3814 ("python-sphinx" ,python2-sphinx)
3815 ("python-pyxb" ,python2-pyxb)))
3816 (home-page "http://pacificbiosciences.github.io/pbcore/")
3817 (synopsis "Library for reading and writing PacBio data files")
3819 "The pbcore package provides Python APIs for interacting with PacBio data
3820 files and writing bioinformatics applications.")
3821 (license license:bsd-3)))
3823 (define-public python2-warpedlmm
3825 (name "python2-warpedlmm")
3831 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3835 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3836 (build-system python-build-system)
3838 `(#:python ,python-2)) ; requires Python 2.7
3840 `(("python-scipy" ,python2-scipy)
3841 ("python-numpy" ,python2-numpy)
3842 ("python-matplotlib" ,python2-matplotlib)
3843 ("python-fastlmm" ,python2-fastlmm)
3844 ("python-pandas" ,python2-pandas)
3845 ("python-pysnptools" ,python2-pysnptools)))
3847 `(("python-mock" ,python2-mock)
3848 ("python-nose" ,python2-nose)
3850 (home-page "https://github.com/PMBio/warpedLMM")
3851 (synopsis "Implementation of warped linear mixed models")
3853 "WarpedLMM is a Python implementation of the warped linear mixed model,
3854 which automatically learns an optimal warping function (or transformation) for
3855 the phenotype as it models the data.")
3856 (license license:asl2.0)))
3858 (define-public pbtranscript-tofu
3859 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3861 (name "pbtranscript-tofu")
3862 (version (string-append "2.2.3." (string-take commit 7)))
3866 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3868 (file-name (string-append name "-" version "-checkout"))
3871 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3872 (modules '((guix build utils)))
3875 ;; remove bundled Cython sources
3876 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3878 (build-system python-build-system)
3880 `(#:python ,python-2
3881 ;; FIXME: Tests fail with "No such file or directory:
3882 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3885 (modify-phases %standard-phases
3886 (add-after 'unpack 'enter-directory
3888 (chdir "pbtranscript-tofu/pbtranscript/")
3890 ;; With setuptools version 18.0 and later this setup.py hack causes
3891 ;; a build error, so we disable it.
3892 (add-after 'enter-directory 'patch-setuppy
3894 (substitute* "setup.py"
3895 (("if 'setuptools.extension' in sys.modules:")
3899 `(("python-numpy" ,python2-numpy)
3900 ("python-bx-python" ,python2-bx-python)
3901 ("python-networkx" ,python2-networkx)
3902 ("python-scipy" ,python2-scipy)
3903 ("python-pbcore" ,python2-pbcore)
3904 ("python-h5py" ,python2-h5py)))
3906 `(("python-cython" ,python2-cython)
3907 ("python-nose" ,python2-nose)))
3908 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3909 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3911 "pbtranscript-tofu contains scripts to analyze transcriptome data
3912 generated using the PacBio Iso-Seq protocol.")
3913 (license license:bsd-3))))
3915 (define-public prank
3922 "http://wasabiapp.org/download/prank/prank.source."
3926 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3927 (build-system gnu-build-system)
3930 (modify-phases %standard-phases
3931 (add-after 'unpack 'enter-src-dir
3935 (add-after 'unpack 'remove-m64-flag
3936 ;; Prank will build with the correct 'bit-ness' without this flag
3937 ;; and this allows building on 32-bit machines.
3938 (lambda _ (substitute* "src/Makefile"
3943 (lambda* (#:key outputs #:allow-other-keys)
3944 (let* ((out (assoc-ref outputs "out"))
3945 (bin (string-append out "/bin"))
3946 (man (string-append out "/share/man/man1"))
3947 (path (string-append
3948 (assoc-ref %build-inputs "mafft") "/bin:"
3949 (assoc-ref %build-inputs "exonerate") "/bin:"
3950 (assoc-ref %build-inputs "bppsuite") "/bin")))
3951 (install-file "prank" bin)
3952 (wrap-program (string-append bin "/prank")
3953 `("PATH" ":" prefix (,path)))
3954 (install-file "prank.1" man))
3958 ("exonerate" ,exonerate)
3959 ("bppsuite" ,bppsuite)))
3960 (home-page "http://wasabiapp.org/software/prank/")
3961 (synopsis "Probabilistic multiple sequence alignment program")
3963 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3964 codon and amino-acid sequences. It is based on a novel algorithm that treats
3965 insertions correctly and avoids over-estimation of the number of deletion
3966 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3967 in phylogenetics and correctly takes into account the evolutionary distances
3968 between sequences. Lastly, PRANK allows for defining a potential structure
3969 for sequences to be aligned and then, simultaneously with the alignment,
3970 predicts the locations of structural units in the sequences.")
3971 (license license:gpl2+)))
3973 (define-public proteinortho
3975 (name "proteinortho")
3982 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3983 version "_src.tar.gz"))
3986 "0z4f5cg0cs8ai62hfvp4q6w66q2phcc55nhs4xj5cyhxxivjv2ai"))))
3987 (build-system gnu-build-system)
3989 `(#:test-target "test"
3991 (modify-phases %standard-phases
3993 ;; There is no configure script, so we modify the Makefile directly.
3994 (lambda* (#:key outputs #:allow-other-keys)
3995 (substitute* "Makefile"
3998 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4000 (add-before 'install 'make-install-directory
4001 ;; The install directory is not created during 'make install'.
4002 (lambda* (#:key outputs #:allow-other-keys)
4003 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4005 (add-after 'install 'wrap-programs
4006 (lambda* (#:key inputs outputs #:allow-other-keys)
4007 (let* ((path (getenv "PATH"))
4008 (out (assoc-ref outputs "out"))
4009 (binary (string-append out "/bin/proteinortho5.pl")))
4010 (wrap-program binary `("PATH" ":" prefix (,path))))
4014 ("python" ,python-2)
4015 ("blast+" ,blast+)))
4016 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4017 (synopsis "Detect orthologous genes across species")
4019 "Proteinortho is a tool to detect orthologous genes across different
4020 species. For doing so, it compares similarities of given gene sequences and
4021 clusters them to find significant groups. The algorithm was designed to handle
4022 large-scale data and can be applied to hundreds of species at once.")
4023 (license license:gpl2+)))
4025 (define-public pyicoteo
4032 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4033 "pyicoteo/get/v" version ".tar.bz2"))
4034 (file-name (string-append name "-" version ".tar.bz2"))
4037 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4038 (build-system python-build-system)
4040 `(#:python ,python-2 ; does not work with Python 3
4041 #:tests? #f)) ; there are no tests
4043 `(("python2-matplotlib" ,python2-matplotlib)))
4044 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4045 (synopsis "Analyze high-throughput genetic sequencing data")
4047 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4048 sequencing data. It works with genomic coordinates. There are currently six
4049 different command-line tools:
4052 @item pyicoregion: for generating exploratory regions automatically;
4053 @item pyicoenrich: for differential enrichment between two conditions;
4054 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4055 @item pyicos: for genomic coordinates manipulation;
4056 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4057 @item pyicount: to count how many reads from N experiment files overlap in a
4059 @item pyicotrocol: to combine operations from pyicoteo.
4061 (license license:gpl3+)))
4063 (define-public prodigal
4070 "https://github.com/hyattpd/Prodigal/archive/v"
4072 (file-name (string-append name "-" version ".tar.gz"))
4075 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4076 (build-system gnu-build-system)
4078 `(#:tests? #f ;no check target
4079 #:make-flags (list (string-append "INSTALLDIR="
4080 (assoc-ref %outputs "out")
4083 (modify-phases %standard-phases
4084 (delete 'configure))))
4085 (home-page "http://prodigal.ornl.gov")
4086 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4088 "Prodigal runs smoothly on finished genomes, draft genomes, and
4089 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4090 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4091 partial genes, and identifies translation initiation sites.")
4092 (license license:gpl3+)))
4094 (define-public roary
4102 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4106 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
4107 (build-system perl-build-system)
4110 (modify-phases %standard-phases
4115 ;; The tests are not run by default, so we run each test file
4117 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4119 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4120 (getenv "PERL5LIB")))
4121 (zero? (length (filter (lambda (file)
4122 (display file)(display "\n")
4123 (not (zero? (system* "perl" file))))
4124 (find-files "t" ".*\\.t$"))))))
4126 ;; There is no 'install' target in the Makefile.
4127 (lambda* (#:key outputs #:allow-other-keys)
4128 (let* ((out (assoc-ref outputs "out"))
4129 (bin (string-append out "/bin"))
4130 (perl (string-append out "/lib/perl5/site_perl"))
4131 (roary-plots "contrib/roary_plots"))
4134 (copy-recursively "bin" bin)
4135 (copy-recursively "lib" perl)
4137 (add-after 'install 'wrap-programs
4138 (lambda* (#:key inputs outputs #:allow-other-keys)
4139 (let* ((out (assoc-ref outputs "out"))
4140 (perl5lib (getenv "PERL5LIB"))
4141 (path (getenv "PATH")))
4142 (for-each (lambda (prog)
4143 (let ((binary (string-append out "/" prog)))
4144 (wrap-program binary
4145 `("PERL5LIB" ":" prefix
4146 (,(string-append perl5lib ":" out
4147 "/lib/perl5/site_perl"))))
4148 (wrap-program binary
4150 (,(string-append path ":" out "/bin"))))))
4151 (find-files "bin" ".*[^R]$"))
4153 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4154 (r-site-lib (getenv "R_LIBS_SITE"))
4156 (string-append (assoc-ref inputs "coreutils") "/bin")))
4158 `("R_LIBS_SITE" ":" prefix
4159 (,(string-append r-site-lib ":" out "/site-library/"))))
4162 (,(string-append coreutils-path ":" out "/bin"))))))
4165 `(("perl-env-path" ,perl-env-path)
4166 ("perl-test-files" ,perl-test-files)
4167 ("perl-test-most" ,perl-test-most)
4168 ("perl-test-output" ,perl-test-output)))
4170 `(("perl-array-utils" ,perl-array-utils)
4171 ("bioperl" ,bioperl-minimal)
4172 ("perl-exception-class" ,perl-exception-class)
4173 ("perl-file-find-rule" ,perl-file-find-rule)
4174 ("perl-file-grep" ,perl-file-grep)
4175 ("perl-file-slurper" ,perl-file-slurper)
4176 ("perl-file-which" ,perl-file-which)
4177 ("perl-graph" ,perl-graph)
4178 ("perl-graph-readwrite" ,perl-graph-readwrite)
4179 ("perl-log-log4perl" ,perl-log-log4perl)
4180 ("perl-moose" ,perl-moose)
4181 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4182 ("perl-text-csv" ,perl-text-csv)
4183 ("bedtools" ,bedtools)
4187 ("parallel" ,parallel)
4190 ("fasttree" ,fasttree)
4194 ("r-minimal" ,r-minimal)
4195 ("r-ggplot2" ,r-ggplot2)
4196 ("coreutils" ,coreutils)))
4197 (home-page "http://sanger-pathogens.github.io/Roary")
4198 (synopsis "High speed stand-alone pan genome pipeline")
4200 "Roary is a high speed stand alone pan genome pipeline, which takes
4201 annotated assemblies in GFF3 format (produced by the Prokka program) and
4202 calculates the pan genome. Using a standard desktop PC, it can analyse
4203 datasets with thousands of samples, without compromising the quality of the
4204 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4205 single processor. Roary is not intended for metagenomics or for comparing
4206 extremely diverse sets of genomes.")
4207 (license license:gpl3)))
4209 (define-public raxml
4218 "https://github.com/stamatak/standard-RAxML/archive/v"
4220 (file-name (string-append name "-" version ".tar.gz"))
4223 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4224 (build-system gnu-build-system)
4226 `(#:tests? #f ; There are no tests.
4227 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4228 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4230 (modify-phases %standard-phases
4233 (lambda* (#:key outputs #:allow-other-keys)
4234 (let* ((out (assoc-ref outputs "out"))
4235 (bin (string-append out "/bin"))
4236 (executable "raxmlHPC-HYBRID"))
4237 (install-file executable bin)
4238 (symlink (string-append bin "/" executable) "raxml"))
4241 `(("openmpi" ,openmpi)))
4242 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4243 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4245 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4247 (license license:gpl2+)))
4257 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4260 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4261 (patches (search-patches "rsem-makefile.patch"))
4262 (modules '((guix build utils)))
4265 ;; remove bundled copy of boost
4266 (delete-file-recursively "boost")
4268 (build-system gnu-build-system)
4270 `(#:tests? #f ;no "check" target
4272 (modify-phases %standard-phases
4273 ;; No "configure" script.
4274 ;; Do not build bundled samtools library.
4277 (substitute* "Makefile"
4278 (("^all : sam/libbam.a") "all : "))
4281 (lambda* (#:key outputs #:allow-other-keys)
4282 (let* ((out (string-append (assoc-ref outputs "out")))
4283 (bin (string-append out "/bin/"))
4284 (perl (string-append out "/lib/perl5/site_perl")))
4287 (for-each (lambda (file)
4288 (install-file file bin))
4289 (find-files "." "rsem-.*"))
4290 (install-file "rsem_perl_utils.pm" perl))
4293 'install 'wrap-program
4294 (lambda* (#:key outputs #:allow-other-keys)
4295 (let ((out (assoc-ref outputs "out")))
4296 (for-each (lambda (prog)
4297 (wrap-program (string-append out "/bin/" prog)
4298 `("PERL5LIB" ":" prefix
4299 (,(string-append out "/lib/perl5/site_perl")))))
4300 '("rsem-plot-transcript-wiggles"
4301 "rsem-calculate-expression"
4302 "rsem-generate-ngvector"
4304 "rsem-prepare-reference")))
4308 ("ncurses" ,ncurses)
4309 ("r-minimal" ,r-minimal)
4311 ("samtools" ,samtools-0.1)
4313 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4314 (synopsis "Estimate gene expression levels from RNA-Seq data")
4316 "RSEM is a software package for estimating gene and isoform expression
4317 levels from RNA-Seq data. The RSEM package provides a user-friendly
4318 interface, supports threads for parallel computation of the EM algorithm,
4319 single-end and paired-end read data, quality scores, variable-length reads and
4320 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4321 interval estimates for expression levels. For visualization, it can generate
4322 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4323 (license license:gpl3+)))
4325 (define-public rseqc
4333 (string-append "mirror://sourceforge/rseqc/"
4334 "RSeQC-" version ".tar.gz"))
4336 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4337 (modules '((guix build utils)))
4340 ;; remove bundled copy of pysam
4341 (delete-file-recursively "lib/pysam")
4342 (substitute* "setup.py"
4343 ;; remove dependency on outdated "distribute" module
4344 (("^from distribute_setup import use_setuptools") "")
4345 (("^use_setuptools\\(\\)") "")
4346 ;; do not use bundled copy of pysam
4347 (("^have_pysam = False") "have_pysam = True"))))))
4348 (build-system python-build-system)
4349 (arguments `(#:python ,python-2))
4351 `(("python-cython" ,python2-cython)
4352 ("python-pysam" ,python2-pysam)
4353 ("python-numpy" ,python2-numpy)
4356 `(("python-nose" ,python2-nose)))
4357 (home-page "http://rseqc.sourceforge.net/")
4358 (synopsis "RNA-seq quality control package")
4360 "RSeQC provides a number of modules that can comprehensively evaluate
4361 high throughput sequence data, especially RNA-seq data. Some basic modules
4362 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4363 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4364 distribution, coverage uniformity, strand specificity, etc.")
4365 (license license:gpl3+)))
4368 ;; There are no release tarballs. According to the installation
4369 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4370 ;; stable release is identified by this changeset ID.
4371 (let ((changeset "2329130")
4375 (version (string-append "0-" revision "." changeset))
4379 (url "https://bitbucket.org/libsleipnir/sleipnir")
4380 (changeset changeset)))
4383 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4384 (build-system gnu-build-system)
4386 `(#:modules ((srfi srfi-1)
4387 (guix build gnu-build-system)
4390 (let ((dirs '("SeekMiner"
4396 (modify-phases %standard-phases
4397 (add-before 'configure 'bootstrap
4399 (zero? (system* "bash" "gen_auto"))))
4400 (add-after 'build 'build-additional-tools
4401 (lambda* (#:key make-flags #:allow-other-keys)
4402 (every (lambda (dir)
4403 (with-directory-excursion (string-append "tools/" dir)
4404 (zero? (apply system* "make" make-flags))))
4406 (add-after 'install 'install-additional-tools
4407 (lambda* (#:key make-flags #:allow-other-keys)
4408 (fold (lambda (dir result)
4409 (with-directory-excursion (string-append "tools/" dir)
4411 (zero? (apply system*
4412 `("make" ,@make-flags "install"))))))
4418 ("readline" ,readline)
4419 ("gengetopt" ,gengetopt)
4420 ("log4cpp" ,log4cpp)))
4422 `(("autoconf" ,autoconf)
4423 ("automake" ,automake)
4425 (home-page "http://seek.princeton.edu")
4426 (synopsis "Gene co-expression search engine")
4428 "SEEK is a computational gene co-expression search engine. SEEK provides
4429 biologists with a way to navigate the massive human expression compendium that
4430 now contains thousands of expression datasets. SEEK returns a robust ranking
4431 of co-expressed genes in the biological area of interest defined by the user's
4432 query genes. It also prioritizes thousands of expression datasets according
4433 to the user's query of interest.")
4434 (license license:cc-by3.0))))
4436 (define-public samtools
4444 (string-append "mirror://sourceforge/samtools/samtools/"
4445 version "/samtools-" version ".tar.bz2"))
4448 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4449 (build-system gnu-build-system)
4451 `(#:modules ((ice-9 ftw)
4453 (guix build gnu-build-system)
4455 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4456 #:configure-flags (list "--with-ncurses")
4459 'unpack 'patch-tests
4461 (substitute* "test/test.pl"
4462 ;; The test script calls out to /bin/bash
4463 (("/bin/bash") (which "bash")))
4466 'install 'install-library
4467 (lambda* (#:key outputs #:allow-other-keys)
4468 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4469 (install-file "libbam.a" lib)
4472 'install 'install-headers
4473 (lambda* (#:key outputs #:allow-other-keys)
4474 (let ((include (string-append (assoc-ref outputs "out")
4475 "/include/samtools/")))
4476 (for-each (lambda (file)
4477 (install-file file include))
4478 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4480 %standard-phases)))))
4481 (native-inputs `(("pkg-config" ,pkg-config)))
4482 (inputs `(("ncurses" ,ncurses)
4486 (home-page "http://samtools.sourceforge.net")
4487 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4489 "Samtools implements various utilities for post-processing nucleotide
4490 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4491 variant calling (in conjunction with bcftools), and a simple alignment
4493 (license license:expat)))
4495 (define-public samtools-0.1
4496 ;; This is the most recent version of the 0.1 line of samtools. The input
4497 ;; and output formats differ greatly from that used and produced by samtools
4498 ;; 1.x and is still used in many bioinformatics pipelines.
4499 (package (inherit samtools)
4505 (string-append "mirror://sourceforge/samtools/samtools/"
4506 version "/samtools-" version ".tar.bz2"))
4508 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4510 `(#:tests? #f ;no "check" target
4511 ,@(substitute-keyword-arguments (package-arguments samtools)
4512 ((#:make-flags flags)
4513 `(cons "LIBCURSES=-lncurses" ,flags))
4515 `(modify-phases ,phases
4517 (lambda* (#:key outputs #:allow-other-keys)
4518 (let ((bin (string-append
4519 (assoc-ref outputs "out") "/bin")))
4521 (install-file "samtools" bin)
4523 (delete 'patch-tests)
4524 (delete 'configure))))))))
4526 (define-public mosaik
4527 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4532 ;; There are no release tarballs nor tags.
4535 (url "https://github.com/wanpinglee/MOSAIK.git")
4537 (file-name (string-append name "-" version))
4540 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4541 (build-system gnu-build-system)
4543 `(#:tests? #f ; no tests
4544 #:make-flags (list "CC=gcc")
4546 (modify-phases %standard-phases
4548 (lambda _ (chdir "src") #t))
4550 (lambda* (#:key outputs #:allow-other-keys)
4551 (let ((bin (string-append (assoc-ref outputs "out")
4554 (copy-recursively "../bin" bin)
4559 (supported-systems '("x86_64-linux"))
4560 (home-page "https://github.com/wanpinglee/MOSAIK")
4561 (synopsis "Map nucleotide sequence reads to reference genomes")
4563 "MOSAIK is a program for mapping second and third-generation sequencing
4564 reads to a reference genome. MOSAIK can align reads generated by all the
4565 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4566 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4567 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4568 ;; code released into the public domain:
4569 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4570 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4571 (license (list license:gpl2+ license:public-domain)))))
4573 (define-public ngs-sdk
4581 (string-append "https://github.com/ncbi/ngs/archive/"
4583 (file-name (string-append name "-" version ".tar.gz"))
4586 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4587 (build-system gnu-build-system)
4589 `(#:parallel-build? #f ; not supported
4590 #:tests? #f ; no "check" target
4594 (lambda* (#:key outputs #:allow-other-keys)
4595 (let ((out (assoc-ref outputs "out")))
4596 ;; The 'configure' script doesn't recognize things like
4597 ;; '--enable-fast-install'.
4598 (zero? (system* "./configure"
4599 (string-append "--build-prefix=" (getcwd) "/build")
4600 (string-append "--prefix=" out)))))
4603 (lambda _ (chdir "ngs-sdk") #t)
4604 %standard-phases))))
4605 (native-inputs `(("perl" ,perl)))
4606 ;; According to the test
4607 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4608 ;; in ngs-sdk/setup/konfigure.perl
4609 (supported-systems '("i686-linux" "x86_64-linux"))
4610 (home-page "https://github.com/ncbi/ngs")
4611 (synopsis "API for accessing Next Generation Sequencing data")
4613 "NGS is a domain-specific API for accessing reads, alignments and pileups
4614 produced from Next Generation Sequencing. The API itself is independent from
4615 any particular back-end implementation, and supports use of multiple back-ends
4617 (license license:public-domain)))
4619 (define-public java-ngs
4620 (package (inherit ngs-sdk)
4623 `(,@(substitute-keyword-arguments
4624 `(#:modules ((guix build gnu-build-system)
4628 ,@(package-arguments ngs-sdk))
4630 `(modify-phases ,phases
4631 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4633 `(("jdk" ,icedtea "jdk")
4634 ("ngs-sdk" ,ngs-sdk)))
4635 (synopsis "Java bindings for NGS SDK")))
4637 (define-public ncbi-vdb
4645 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4647 (file-name (string-append name "-" version ".tar.gz"))
4650 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4651 (build-system gnu-build-system)
4653 `(#:parallel-build? #f ; not supported
4654 #:tests? #f ; no "check" target
4656 (modify-phases %standard-phases
4658 (lambda* (#:key inputs outputs #:allow-other-keys)
4659 (let ((out (assoc-ref outputs "out")))
4660 ;; Override include path for libmagic
4661 (substitute* "setup/package.prl"
4662 (("name => 'magic', Include => '/usr/include'")
4663 (string-append "name=> 'magic', Include => '"
4664 (assoc-ref inputs "libmagic")
4667 ;; Install kdf5 library (needed by sra-tools)
4668 (substitute* "build/Makefile.install"
4669 (("LIBRARIES_TO_INSTALL =")
4670 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4672 (substitute* "build/Makefile.env"
4673 (("CFLAGS =" prefix)
4674 (string-append prefix "-msse2 ")))
4676 ;; Override search path for ngs-java
4677 (substitute* "setup/package.prl"
4678 (("/usr/local/ngs/ngs-java")
4679 (assoc-ref inputs "java-ngs")))
4681 ;; The 'configure' script doesn't recognize things like
4682 ;; '--enable-fast-install'.
4685 (string-append "--build-prefix=" (getcwd) "/build")
4686 (string-append "--prefix=" (assoc-ref outputs "out"))
4687 (string-append "--debug")
4688 (string-append "--with-xml2-prefix="
4689 (assoc-ref inputs "libxml2"))
4690 (string-append "--with-ngs-sdk-prefix="
4691 (assoc-ref inputs "ngs-sdk"))
4692 (string-append "--with-hdf5-prefix="
4693 (assoc-ref inputs "hdf5")))))))
4694 (add-after 'install 'install-interfaces
4695 (lambda* (#:key outputs #:allow-other-keys)
4696 ;; Install interface libraries. On i686 the interface libraries
4697 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4698 ;; architecture name ("i386") instead of the target system prefix
4700 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4701 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4702 ,(system->linux-architecture
4703 (or (%current-target-system)
4706 (string-append (assoc-ref outputs "out")
4708 ;; Install interface headers
4709 (copy-recursively "interfaces"
4710 (string-append (assoc-ref outputs "out")
4713 ;; These files are needed by sra-tools.
4714 (add-after 'install 'install-configuration-files
4715 (lambda* (#:key outputs #:allow-other-keys)
4716 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4718 (install-file "libs/kfg/default.kfg" target)
4719 (install-file "libs/kfg/certs.kfg" target))
4722 `(("libxml2" ,libxml2)
4723 ("ngs-sdk" ,ngs-sdk)
4724 ("java-ngs" ,java-ngs)
4727 (native-inputs `(("perl" ,perl)))
4728 ;; NCBI-VDB requires SSE capability.
4729 (supported-systems '("i686-linux" "x86_64-linux"))
4730 (home-page "https://github.com/ncbi/ncbi-vdb")
4731 (synopsis "Database engine for genetic information")
4733 "The NCBI-VDB library implements a highly compressed columnar data
4734 warehousing engine that is most often used to store genetic information.
4735 Databases are stored in a portable image within the file system, and can be
4736 accessed/downloaded on demand across HTTP.")
4737 (license license:public-domain)))
4739 (define-public plink
4747 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4748 version "-src.zip"))
4750 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4751 (patches (search-patches "plink-1.07-unclobber-i.patch"
4752 "plink-endian-detection.patch"))))
4753 (build-system gnu-build-system)
4755 '(#:tests? #f ;no "check" target
4756 #:make-flags (list (string-append "LIB_LAPACK="
4757 (assoc-ref %build-inputs "lapack")
4758 "/lib/liblapack.so")
4761 ;; disable phoning home
4764 (modify-phases %standard-phases
4765 ;; no "configure" script
4768 (lambda* (#:key outputs #:allow-other-keys)
4769 (let ((bin (string-append (assoc-ref outputs "out")
4771 (install-file "plink" bin)
4775 ("lapack" ,lapack)))
4777 `(("unzip" ,unzip)))
4778 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4779 (synopsis "Whole genome association analysis toolset")
4781 "PLINK is a whole genome association analysis toolset, designed to
4782 perform a range of basic, large-scale analyses in a computationally efficient
4783 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4784 so there is no support for steps prior to this (e.g. study design and
4785 planning, generating genotype or CNV calls from raw data). Through
4786 integration with gPLINK and Haploview, there is some support for the
4787 subsequent visualization, annotation and storage of results.")
4788 ;; Code is released under GPLv2, except for fisher.h, which is under
4790 (license (list license:gpl2 license:lgpl2.1+))))
4792 (define-public smithlab-cpp
4793 (let ((revision "1")
4794 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4796 (name "smithlab-cpp")
4797 (version (string-append "0." revision "." (string-take commit 7)))
4801 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4803 (file-name (string-append name "-" version "-checkout"))
4806 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4807 (build-system gnu-build-system)
4809 `(#:modules ((guix build gnu-build-system)
4812 #:tests? #f ;no "check" target
4814 (modify-phases %standard-phases
4815 (add-after 'unpack 'use-samtools-headers
4817 (substitute* '("SAM.cpp"
4819 (("sam.h") "samtools/sam.h"))
4822 (lambda* (#:key outputs #:allow-other-keys)
4823 (let* ((out (assoc-ref outputs "out"))
4824 (lib (string-append out "/lib"))
4825 (include (string-append out "/include/smithlab-cpp")))
4828 (for-each (cut install-file <> lib)
4829 (find-files "." "\\.o$"))
4830 (for-each (cut install-file <> include)
4831 (find-files "." "\\.hpp$")))
4833 (delete 'configure))))
4835 `(("samtools" ,samtools-0.1)
4837 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4838 (synopsis "C++ helper library for functions used in Smith lab projects")
4840 "Smithlab CPP is a C++ library that includes functions used in many of
4841 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4842 structures, classes for genomic regions, mapped sequencing reads, etc.")
4843 (license license:gpl3+))))
4845 (define-public preseq
4851 (uri (string-append "https://github.com/smithlabcode/"
4852 "preseq/archive/v" version ".tar.gz"))
4853 (file-name (string-append name "-" version ".tar.gz"))
4855 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4856 (modules '((guix build utils)))
4858 ;; Remove bundled samtools.
4859 '(delete-file-recursively "samtools"))))
4860 (build-system gnu-build-system)
4862 `(#:tests? #f ;no "check" target
4864 (modify-phases %standard-phases
4865 (delete 'configure))
4867 (list (string-append "PREFIX="
4868 (assoc-ref %outputs "out"))
4869 (string-append "LIBBAM="
4870 (assoc-ref %build-inputs "samtools")
4872 (string-append "SMITHLAB_CPP="
4873 (assoc-ref %build-inputs "smithlab-cpp")
4876 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4879 ("samtools" ,samtools-0.1)
4880 ("smithlab-cpp" ,smithlab-cpp)
4882 (home-page "http://smithlabresearch.org/software/preseq/")
4883 (synopsis "Program for analyzing library complexity")
4885 "The preseq package is aimed at predicting and estimating the complexity
4886 of a genomic sequencing library, equivalent to predicting and estimating the
4887 number of redundant reads from a given sequencing depth and how many will be
4888 expected from additional sequencing using an initial sequencing experiment.
4889 The estimates can then be used to examine the utility of further sequencing,
4890 optimize the sequencing depth, or to screen multiple libraries to avoid low
4891 complexity samples.")
4892 (license license:gpl3+)))
4894 (define-public python-screed
4896 (name "python-screed")
4901 (uri (pypi-uri "screed" version))
4904 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4905 (build-system python-build-system)
4908 (modify-phases %standard-phases
4911 (setenv "PYTHONPATH"
4912 (string-append (getenv "PYTHONPATH") ":."))
4913 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4915 `(("python-nose" ,python-nose)))
4917 `(("python-bz2file" ,python-bz2file)))
4918 (home-page "https://github.com/dib-lab/screed/")
4919 (synopsis "Short read sequence database utilities")
4920 (description "Screed parses FASTA and FASTQ files and generates databases.
4921 Values such as sequence name, sequence description, sequence quality and the
4922 sequence itself can be retrieved from these databases.")
4923 (license license:bsd-3)))
4925 (define-public python2-screed
4926 (package-with-python2 python-screed))
4928 (define-public sra-tools
4936 (string-append "https://github.com/ncbi/sra-tools/archive/"
4938 (file-name (string-append name "-" version ".tar.gz"))
4941 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
4942 (build-system gnu-build-system)
4944 `(#:parallel-build? #f ; not supported
4945 #:tests? #f ; no "check" target
4947 (list (string-append "DEFAULT_CRT="
4948 (assoc-ref %build-inputs "ncbi-vdb")
4950 (string-append "DEFAULT_KFG="
4951 (assoc-ref %build-inputs "ncbi-vdb")
4953 (string-append "VDB_LIBDIR="
4954 (assoc-ref %build-inputs "ncbi-vdb")
4955 ,(if (string-prefix? "x86_64"
4956 (or (%current-target-system)
4961 (modify-phases %standard-phases
4963 (lambda* (#:key inputs outputs #:allow-other-keys)
4964 ;; The build system expects a directory containing the sources and
4965 ;; raw build output of ncbi-vdb, including files that are not
4966 ;; installed. Since we are building against an installed version of
4967 ;; ncbi-vdb, the following modifications are needed.
4968 (substitute* "setup/konfigure.perl"
4969 ;; Make the configure script look for the "ilib" directory of
4970 ;; "ncbi-vdb" without first checking for the existence of a
4971 ;; matching library in its "lib" directory.
4972 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4973 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4974 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4975 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4976 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4979 (substitute* "tools/copycat/Makefile"
4980 (("smagic-static") "lmagic"))
4982 ;; The 'configure' script doesn't recognize things like
4983 ;; '--enable-fast-install'.
4986 (string-append "--build-prefix=" (getcwd) "/build")
4987 (string-append "--prefix=" (assoc-ref outputs "out"))
4988 (string-append "--debug")
4989 (string-append "--with-fuse-prefix="
4990 (assoc-ref inputs "fuse"))
4991 (string-append "--with-magic-prefix="
4992 (assoc-ref inputs "libmagic"))
4993 ;; TODO: building with libxml2 fails with linker errors
4994 ;; (string-append "--with-xml2-prefix="
4995 ;; (assoc-ref inputs "libxml2"))
4996 (string-append "--with-ncbi-vdb-sources="
4997 (assoc-ref inputs "ncbi-vdb"))
4998 (string-append "--with-ncbi-vdb-build="
4999 (assoc-ref inputs "ncbi-vdb"))
5000 (string-append "--with-ngs-sdk-prefix="
5001 (assoc-ref inputs "ngs-sdk"))
5002 (string-append "--with-hdf5-prefix="
5003 (assoc-ref inputs "hdf5"))))))
5004 ;; This version of sra-tools fails to build with glibc because of a
5005 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5006 ;; contains a definition of "canonicalize", so we rename it.
5008 ;; See upstream bug report:
5009 ;; https://github.com/ncbi/sra-tools/issues/67
5010 (add-after 'unpack 'patch-away-glibc-conflict
5012 (substitute* "tools/bam-loader/bam.c"
5013 (("canonicalize\\(" line)
5014 (string-append "sra_tools_" line)))
5016 (native-inputs `(("perl" ,perl)))
5018 `(("ngs-sdk" ,ngs-sdk)
5019 ("ncbi-vdb" ,ncbi-vdb)
5024 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5025 (synopsis "Tools and libraries for reading and writing sequencing data")
5027 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5028 reading of sequencing files from the Sequence Read Archive (SRA) database and
5029 writing files into the .sra format.")
5030 (license license:public-domain)))
5032 (define-public seqan
5038 (uri (string-append "http://packages.seqan.de/seqan-library/"
5039 "seqan-library-" version ".tar.bz2"))
5042 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5043 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5044 ;; makes sense to split the outputs.
5045 (outputs '("out" "doc"))
5046 (build-system trivial-build-system)
5048 `(#:modules ((guix build utils))
5051 (use-modules (guix build utils))
5052 (let ((tar (assoc-ref %build-inputs "tar"))
5053 (bzip (assoc-ref %build-inputs "bzip2"))
5054 (out (assoc-ref %outputs "out"))
5055 (doc (assoc-ref %outputs "doc")))
5056 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5057 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5058 (chdir (string-append "seqan-library-" ,version))
5059 (copy-recursively "include" (string-append out "/include"))
5060 (copy-recursively "share" (string-append doc "/share"))))))
5062 `(("source" ,source)
5065 (home-page "http://www.seqan.de")
5066 (synopsis "Library for nucleotide sequence analysis")
5068 "SeqAn is a C++ library of efficient algorithms and data structures for
5069 the analysis of sequences with the focus on biological data. It contains
5070 algorithms and data structures for string representation and their
5071 manipulation, online and indexed string search, efficient I/O of
5072 bioinformatics file formats, sequence alignment, and more.")
5073 (license license:bsd-3)))
5075 (define-public seqmagick
5083 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5087 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5088 (build-system python-build-system)
5090 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5091 `(#:python ,python-2
5093 (modify-phases %standard-phases
5094 ;; Current test in setup.py does not work as of 0.6.1,
5095 ;; so use nose to run tests instead for now. See
5096 ;; https://github.com/fhcrc/seqmagick/issues/55
5097 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5099 ;; biopython-1.66 is required due to
5100 ;; https://github.com/fhcrc/seqmagick/issues/59
5101 ;; When that issue is resolved the 'python2-biopython-1.66' package
5102 ;; should be removed.
5103 `(("python-biopython" ,python2-biopython-1.66)))
5105 `(("python-nose" ,python2-nose)))
5106 (home-page "https://github.com/fhcrc/seqmagick")
5107 (synopsis "Tools for converting and modifying sequence files")
5109 "Bioinformaticians often have to convert sequence files between formats
5110 and do little manipulations on them, and it's not worth writing scripts for
5111 that. Seqmagick is a utility to expose the file format conversion in
5112 BioPython in a convenient way. Instead of having a big mess of scripts, there
5113 is one that takes arguments.")
5114 (license license:gpl3)))
5116 (define-public seqtk
5123 "https://github.com/lh3/seqtk/archive/v"
5125 (file-name (string-append name "-" version ".tar.gz"))
5128 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5129 (modules '((guix build utils)))
5132 ;; Remove extraneous header files, as is done in the seqtk
5134 (for-each (lambda (file) (delete-file file))
5135 (list "ksort.h" "kstring.h" "kvec.h"))
5137 (build-system gnu-build-system)
5140 (modify-phases %standard-phases
5143 ;; There are no tests, so we just run a sanity check.
5144 (lambda _ (zero? (system* "./seqtk" "seq"))))
5146 (lambda* (#:key outputs #:allow-other-keys)
5147 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5148 (install-file "seqtk" bin)))))))
5151 (home-page "https://github.com/lh3/seqtk")
5152 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5154 "Seqtk is a fast and lightweight tool for processing sequences in the
5155 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5156 optionally compressed by gzip.")
5157 (license license:expat)))
5159 (define-public snap-aligner
5161 (name "snap-aligner")
5162 (version "1.0beta.18")
5166 "https://github.com/amplab/snap/archive/v"
5168 (file-name (string-append name "-" version ".tar.gz"))
5171 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5172 (build-system gnu-build-system)
5175 (modify-phases %standard-phases
5177 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5179 (lambda* (#:key outputs #:allow-other-keys)
5180 (let* ((out (assoc-ref outputs "out"))
5181 (bin (string-append out "/bin")))
5182 (install-file "snap-aligner" bin)
5183 (install-file "SNAPCommand" bin)
5187 (home-page "http://snap.cs.berkeley.edu/")
5188 (synopsis "Short read DNA sequence aligner")
5190 "SNAP is a fast and accurate aligner for short DNA reads. It is
5191 optimized for modern read lengths of 100 bases or higher, and takes advantage
5192 of these reads to align data quickly through a hash-based indexing scheme.")
5193 ;; 32-bit systems are not supported by the unpatched code.
5194 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5195 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5196 ;; systems without a lot of memory cannot make good use of this program.
5197 (supported-systems '("x86_64-linux"))
5198 (license license:asl2.0)))
5200 (define-public sortmerna
5208 "https://github.com/biocore/sortmerna/archive/"
5210 (file-name (string-append name "-" version ".tar.gz"))
5213 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5214 (build-system gnu-build-system)
5215 (outputs '("out" ;for binaries
5216 "db")) ;for sequence databases
5219 (modify-phases %standard-phases
5221 (lambda* (#:key outputs #:allow-other-keys)
5222 (let* ((out (assoc-ref outputs "out"))
5223 (bin (string-append out "/bin"))
5224 (db (assoc-ref outputs "db"))
5226 (string-append db "/share/sortmerna/rRNA_databases")))
5227 (install-file "sortmerna" bin)
5228 (install-file "indexdb_rna" bin)
5229 (for-each (lambda (file)
5230 (install-file file share))
5231 (find-files "rRNA_databases" ".*fasta"))
5235 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5236 (synopsis "Biological sequence analysis tool for NGS reads")
5238 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5239 and operational taxonomic unit (OTU) picking of next generation
5240 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5241 allows for fast and sensitive analyses of nucleotide sequences. The main
5242 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5243 (license license:lgpl3)))
5251 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5253 (file-name (string-append name "-" version ".tar.gz"))
5256 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5257 (modules '((guix build utils)))
5260 (substitute* "source/Makefile"
5262 ;; Remove pre-built binaries and bundled htslib sources.
5263 (delete-file-recursively "bin/MacOSX_x86_64")
5264 (delete-file-recursively "bin/Linux_x86_64")
5265 (delete-file-recursively "bin/Linux_x86_64_static")
5266 (delete-file-recursively "source/htslib")
5268 (build-system gnu-build-system)
5270 '(#:tests? #f ;no check target
5271 #:make-flags '("STAR")
5273 (modify-phases %standard-phases
5274 (add-after 'unpack 'enter-source-dir
5275 (lambda _ (chdir "source") #t))
5276 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5278 (substitute* "Makefile"
5279 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5281 (substitute* '("BAMfunctions.cpp"
5286 "bamRemoveDuplicates.cpp")
5287 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5288 (string-append "#include <" header ">")))
5289 (substitute* "IncludeDefine.h"
5290 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5291 (string-append "<" header ">")))
5294 (lambda* (#:key outputs #:allow-other-keys)
5295 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5296 (install-file "STAR" bin))
5298 (delete 'configure))))
5300 `(("vim" ,vim))) ; for xxd
5302 `(("htslib" ,htslib)
5304 (home-page "https://github.com/alexdobin/STAR")
5305 (synopsis "Universal RNA-seq aligner")
5307 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5308 based on a previously undescribed RNA-seq alignment algorithm that uses
5309 sequential maximum mappable seed search in uncompressed suffix arrays followed
5310 by seed clustering and stitching procedure. In addition to unbiased de novo
5311 detection of canonical junctions, STAR can discover non-canonical splices and
5312 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5314 ;; Only 64-bit systems are supported according to the README.
5315 (supported-systems '("x86_64-linux" "mips64el-linux"))
5316 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5317 (license license:gpl3+)))
5319 (define-public subread
5325 (uri (string-append "mirror://sourceforge/subread/subread-"
5326 version "/subread-" version "-source.tar.gz"))
5329 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5330 (build-system gnu-build-system)
5332 `(#:tests? #f ;no "check" target
5333 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5334 ;; optimizations by default, so we override these flags such that x86_64
5335 ;; flags are only added when the build target is an x86_64 system.
5337 (list (let ((system ,(or (%current-target-system)
5339 (flags '("-ggdb" "-fomit-frame-pointer"
5340 "-ffast-math" "-funroll-loops"
5341 "-fmessage-length=0"
5342 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5344 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5345 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5346 (if (string-prefix? "x86_64" system)
5347 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5348 (string-append "CCFLAGS=" (string-join flags))))
5349 "-f" "Makefile.Linux"
5350 "CC=gcc ${CCFLAGS}")
5354 (lambda _ (chdir "src") #t)
5357 (lambda* (#:key outputs #:allow-other-keys)
5358 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5360 (copy-recursively "../bin" bin)))
5361 ;; no "configure" script
5362 (alist-delete 'configure %standard-phases)))))
5363 (inputs `(("zlib" ,zlib)))
5364 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5365 (synopsis "Tool kit for processing next-gen sequencing data")
5367 "The subread package contains the following tools: subread aligner, a
5368 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5369 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5370 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5371 against local background noises.")
5372 (license license:gpl3+)))
5374 (define-public stringtie
5380 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5381 "stringtie-" version ".tar.gz"))
5384 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5385 (modules '((guix build utils)))
5388 (delete-file-recursively "samtools-0.1.18")
5390 (build-system gnu-build-system)
5392 `(#:tests? #f ;no test suite
5394 (modify-phases %standard-phases
5395 ;; no configure script
5397 (add-before 'build 'use-system-samtools
5399 (substitute* "Makefile"
5400 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5402 (substitute* '("gclib/GBam.h"
5404 (("#include \"(bam|sam|kstring).h\"" _ header)
5405 (string-append "#include <samtools/" header ".h>")))
5407 (add-after 'unpack 'remove-duplicate-typedef
5409 ;; This typedef conflicts with the typedef in
5410 ;; glibc-2.25/include/bits/types.h
5411 (substitute* "gclib/GThreads.h"
5412 (("typedef long long __intmax_t;") ""))
5415 (lambda* (#:key outputs #:allow-other-keys)
5416 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5417 (install-file "stringtie" bin)
5420 `(("samtools" ,samtools-0.1)
5422 (home-page "http://ccb.jhu.edu/software/stringtie/")
5423 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5425 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5426 alignments into potential transcripts. It uses a novel network flow algorithm
5427 as well as an optional de novo assembly step to assemble and quantitate
5428 full-length transcripts representing multiple splice variants for each gene
5429 locus. Its input can include not only the alignments of raw reads used by
5430 other transcript assemblers, but also alignments of longer sequences that have
5431 been assembled from those reads. To identify differentially expressed genes
5432 between experiments, StringTie's output can be processed either by the
5433 Cuffdiff or Ballgown programs.")
5434 (license license:artistic2.0)))
5436 (define-public taxtastic
5440 ;; Versions after 0.5.4 do not appear to be distributed on PyPI so we
5441 ;; download the package from GitHub.
5445 "https://github.com/fhcrc/taxtastic/archive/v"
5447 (file-name (string-append name "-" version ".tar.gz"))
5450 "1s0h5y1lds1c40jhir5585ffm6yjyn8h5aqimpgv64rhqhfv56xx"))))
5451 (build-system python-build-system)
5453 `(#:python ,python-2
5455 (modify-phases %standard-phases
5458 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5460 `(("python-sqlalchemy" ,python2-sqlalchemy)
5461 ("python-decorator" ,python2-decorator)
5462 ("python-biopython" ,python2-biopython)
5463 ("python-pandas" ,python2-pandas)))
5464 (home-page "https://github.com/fhcrc/taxtastic")
5465 (synopsis "Tools for taxonomic naming and annotation")
5467 "Taxtastic is software written in python used to build and maintain
5468 reference packages i.e. collections of reference trees, reference alignments,
5469 profiles, and associated taxonomic information.")
5470 (license license:gpl3+)))
5472 (define-public vcftools
5479 "https://github.com/vcftools/vcftools/releases/download/v"
5480 version "/vcftools-" version ".tar.gz"))
5483 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5484 (build-system gnu-build-system)
5486 `(#:tests? #f ; no "check" target
5488 "CFLAGS=-O2" ; override "-m64" flag
5489 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5490 (string-append "MANDIR=" (assoc-ref %outputs "out")
5491 "/share/man/man1"))))
5493 `(("pkg-config" ,pkg-config)))
5497 (home-page "https://vcftools.github.io/")
5498 (synopsis "Tools for working with VCF files")
5500 "VCFtools is a program package designed for working with VCF files, such
5501 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5502 provide easily accessible methods for working with complex genetic variation
5503 data in the form of VCF files.")
5504 ;; The license is declared as LGPLv3 in the README and
5505 ;; at https://vcftools.github.io/license.html
5506 (license license:lgpl3)))
5508 (define-public infernal
5514 (uri (string-append "http://eddylab.org/software/infernal/"
5515 "infernal-" version ".tar.gz"))
5518 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5519 (build-system gnu-build-system)
5521 `(("perl" ,perl))) ; for tests
5522 (home-page "http://eddylab.org/infernal/")
5523 (synopsis "Inference of RNA alignments")
5524 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5525 searching DNA sequence databases for RNA structure and sequence similarities.
5526 It is an implementation of a special case of profile stochastic context-free
5527 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5528 profile, but it scores a combination of sequence consensus and RNA secondary
5529 structure consensus, so in many cases, it is more capable of identifying RNA
5530 homologs that conserve their secondary structure more than their primary
5532 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5533 (supported-systems '("i686-linux" "x86_64-linux"))
5534 (license license:bsd-3)))
5536 (define-public r-centipede
5538 (name "r-centipede")
5542 (uri (string-append "http://download.r-forge.r-project.org/"
5543 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5546 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5547 (build-system r-build-system)
5548 (home-page "http://centipede.uchicago.edu/")
5549 (synopsis "Predict transcription factor binding sites")
5551 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5552 of the genome that are bound by particular transcription factors. It starts
5553 by identifying a set of candidate binding sites, and then aims to classify the
5554 sites according to whether each site is bound or not bound by a transcription
5555 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5556 between two different types of motif instances using as much relevant
5557 information as possible.")
5558 (license (list license:gpl2+ license:gpl3+))))
5560 (define-public r-vegan
5567 (uri (cran-uri "vegan" version))
5570 "15zcxfix2d854897k1lr0sfmj2n00339nlsppcr3zrb238lb2mi5"))))
5571 (build-system r-build-system)
5573 `(("gfortran" ,gfortran)
5574 ("r-knitr" ,r-knitr)))
5576 `(("r-cluster" ,r-cluster)
5577 ("r-lattice" ,r-lattice)
5580 ("r-permute" ,r-permute)))
5581 (home-page "https://cran.r-project.org/web/packages/vegan")
5582 (synopsis "Functions for community ecology")
5584 "The vegan package provides tools for descriptive community ecology. It
5585 has most basic functions of diversity analysis, community ordination and
5586 dissimilarity analysis. Most of its multivariate tools can be used for other
5587 data types as well.")
5588 (license license:gpl2+)))
5590 (define-public r-annotate
5597 (uri (bioconductor-uri "annotate" version))
5600 "03hmbvp3i6lvd307fqdg7akxi2qp322rlky3bzw0zccgm0i0221g"))))
5601 (build-system r-build-system)
5603 `(("r-annotationdbi" ,r-annotationdbi)
5604 ("r-biobase" ,r-biobase)
5605 ("r-biocgenerics" ,r-biocgenerics)
5607 ("r-rcurl" ,r-rcurl)
5609 ("r-xtable" ,r-xtable)))
5611 "http://bioconductor.org/packages/annotate")
5612 (synopsis "Annotation for microarrays")
5613 (description "This package provides R environments for the annotation of
5615 (license license:artistic2.0)))
5617 (define-public r-geneplotter
5619 (name "r-geneplotter")
5624 (uri (bioconductor-uri "geneplotter" version))
5627 "0a0ajns21db5rrjl16bq6wawggsnxr00fg184pc38nmfghv4z4b6"))))
5628 (build-system r-build-system)
5630 `(("r-annotate" ,r-annotate)
5631 ("r-annotationdbi" ,r-annotationdbi)
5632 ("r-biobase" ,r-biobase)
5633 ("r-biocgenerics" ,r-biocgenerics)
5634 ("r-lattice" ,r-lattice)
5635 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5636 (home-page "http://bioconductor.org/packages/geneplotter")
5637 (synopsis "Graphics functions for genomic data")
5639 "This package provides functions for plotting genomic data.")
5640 (license license:artistic2.0)))
5642 (define-public r-genefilter
5644 (name "r-genefilter")
5649 (uri (bioconductor-uri "genefilter" version))
5652 "0sf2hdi9nv6r83vn1y65m4jiba8pffddpj46d6yjn5rlsixplmqg"))))
5653 (build-system r-build-system)
5655 `(("gfortran" ,gfortran)))
5657 `(("r-annotate" ,r-annotate)
5658 ("r-annotationdbi" ,r-annotationdbi)
5659 ("r-biobase" ,r-biobase)
5660 ("r-s4vectors" ,r-s4vectors)
5661 ("r-survival" ,r-survival)))
5662 (home-page "http://bioconductor.org/packages/genefilter")
5663 (synopsis "Filter genes from high-throughput experiments")
5665 "This package provides basic functions for filtering genes from
5666 high-throughput sequencing experiments.")
5667 (license license:artistic2.0)))
5669 (define-public r-deseq2
5676 (uri (bioconductor-uri "DESeq2" version))
5679 "0m0apn3xi4kdkinsj4xkw5cwysicyjr6xxlxhpa4scyv589am1s5"))))
5680 (properties `((upstream-name . "DESeq2")))
5681 (build-system r-build-system)
5683 `(("r-biobase" ,r-biobase)
5684 ("r-biocgenerics" ,r-biocgenerics)
5685 ("r-biocparallel" ,r-biocparallel)
5686 ("r-genefilter" ,r-genefilter)
5687 ("r-geneplotter" ,r-geneplotter)
5688 ("r-genomicranges" ,r-genomicranges)
5689 ("r-ggplot2" ,r-ggplot2)
5690 ("r-hmisc" ,r-hmisc)
5691 ("r-iranges" ,r-iranges)
5692 ("r-locfit" ,r-locfit)
5694 ("r-rcpparmadillo" ,r-rcpparmadillo)
5695 ("r-s4vectors" ,r-s4vectors)
5696 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5697 (home-page "http://bioconductor.org/packages/DESeq2")
5698 (synopsis "Differential gene expression analysis")
5700 "This package provides functions to estimate variance-mean dependence in
5701 count data from high-throughput nucleotide sequencing assays and test for
5702 differential expression based on a model using the negative binomial
5704 (license license:lgpl3+)))
5706 (define-public r-annotationforge
5708 (name "r-annotationforge")
5713 (uri (bioconductor-uri "AnnotationForge" version))
5716 "01kd86vvgpa4a5zivcy4g6z8rhcykasdskrz8yqsqz211sd1xsr3"))))
5718 `((upstream-name . "AnnotationForge")))
5719 (build-system r-build-system)
5721 `(("r-annotationdbi" ,r-annotationdbi)
5722 ("r-biobase" ,r-biobase)
5723 ("r-biocgenerics" ,r-biocgenerics)
5725 ("r-rcurl" ,r-rcurl)
5726 ("r-rsqlite" ,r-rsqlite)
5727 ("r-s4vectors" ,r-s4vectors)
5729 (home-page "http://bioconductor.org/packages/AnnotationForge")
5730 (synopsis "Code for building annotation database packages")
5732 "This package provides code for generating Annotation packages and their
5733 databases. Packages produced are intended to be used with AnnotationDbi.")
5734 (license license:artistic2.0)))
5736 (define-public r-rbgl
5743 (uri (bioconductor-uri "RBGL" version))
5746 "11db6kvz453ypj9ds3xpjqzwrrjck84ijn4wlhkfyz2dzdgd5ryv"))))
5747 (properties `((upstream-name . "RBGL")))
5748 (build-system r-build-system)
5749 (propagated-inputs `(("r-graph" ,r-graph)))
5750 (home-page "http://www.bioconductor.org/packages/RBGL")
5751 (synopsis "Interface to the Boost graph library")
5753 "This package provides a fairly extensive and comprehensive interface to
5754 the graph algorithms contained in the Boost library.")
5755 (license license:artistic2.0)))
5757 (define-public r-gseabase
5764 (uri (bioconductor-uri "GSEABase" version))
5767 "1c6i6g4fj3b8wjyxyygr7i3v8sxrq1ffb2bbicya5ah2gdaclfad"))))
5768 (properties `((upstream-name . "GSEABase")))
5769 (build-system r-build-system)
5771 `(("r-annotate" ,r-annotate)
5772 ("r-annotationdbi" ,r-annotationdbi)
5773 ("r-biobase" ,r-biobase)
5774 ("r-biocgenerics" ,r-biocgenerics)
5775 ("r-graph" ,r-graph)
5777 (home-page "http://bioconductor.org/packages/GSEABase")
5778 (synopsis "Gene set enrichment data structures and methods")
5780 "This package provides classes and methods to support @dfn{Gene Set
5781 Enrichment Analysis} (GSEA).")
5782 (license license:artistic2.0)))
5784 (define-public r-category
5791 (uri (bioconductor-uri "Category" version))
5794 "0swcmihyjg0fhaaydl9hm24aj9zffw3bibza9y6sqs6jaqd97f09"))))
5795 (properties `((upstream-name . "Category")))
5796 (build-system r-build-system)
5798 `(("r-annotate" ,r-annotate)
5799 ("r-annotationdbi" ,r-annotationdbi)
5800 ("r-biobase" ,r-biobase)
5801 ("r-biocgenerics" ,r-biocgenerics)
5802 ("r-genefilter" ,r-genefilter)
5803 ("r-graph" ,r-graph)
5804 ("r-gseabase" ,r-gseabase)
5805 ("r-matrix" ,r-matrix)
5807 ("r-rsqlite" ,r-rsqlite)))
5808 (home-page "http://bioconductor.org/packages/Category")
5809 (synopsis "Category analysis")
5811 "This package provides a collection of tools for performing category
5813 (license license:artistic2.0)))
5815 (define-public r-gostats
5822 (uri (bioconductor-uri "GOstats" version))
5825 "0qvqjgfnd9ap4rikvyxa9p4dhcnccvkw8phzv88vghh6pq463d62"))))
5826 (properties `((upstream-name . "GOstats")))
5827 (build-system r-build-system)
5829 `(("r-annotate" ,r-annotate)
5830 ("r-annotationdbi" ,r-annotationdbi)
5831 ("r-annotationforge" ,r-annotationforge)
5832 ("r-biobase" ,r-biobase)
5833 ("r-category" ,r-category)
5834 ("r-go-db" ,r-go-db)
5835 ("r-graph" ,r-graph)
5836 ("r-rbgl" ,r-rbgl)))
5837 (home-page "http://bioconductor.org/packages/GOstats")
5838 (synopsis "Tools for manipulating GO and microarrays")
5840 "This package provides a set of tools for interacting with GO and
5841 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5842 testing and other simple calculations.")
5843 (license license:artistic2.0)))
5845 (define-public r-shortread
5847 (name "r-shortread")
5852 (uri (bioconductor-uri "ShortRead" version))
5855 "0ayk3d5625ymb5g2gycq6banzqmyd642xrwjzhdshz2dwid7kly8"))))
5856 (properties `((upstream-name . "ShortRead")))
5857 (build-system r-build-system)
5861 `(("r-biobase" ,r-biobase)
5862 ("r-biocgenerics" ,r-biocgenerics)
5863 ("r-biocparallel" ,r-biocparallel)
5864 ("r-biostrings" ,r-biostrings)
5865 ("r-genomeinfodb" ,r-genomeinfodb)
5866 ("r-genomicalignments" ,r-genomicalignments)
5867 ("r-genomicranges" ,r-genomicranges)
5868 ("r-hwriter" ,r-hwriter)
5869 ("r-iranges" ,r-iranges)
5870 ("r-lattice" ,r-lattice)
5871 ("r-latticeextra" ,r-latticeextra)
5872 ("r-rsamtools" ,r-rsamtools)
5873 ("r-s4vectors" ,r-s4vectors)
5874 ("r-xvector" ,r-xvector)
5875 ("r-zlibbioc" ,r-zlibbioc)))
5876 (home-page "http://bioconductor.org/packages/ShortRead")
5877 (synopsis "FASTQ input and manipulation tools")
5879 "This package implements sampling, iteration, and input of FASTQ files.
5880 It includes functions for filtering and trimming reads, and for generating a
5881 quality assessment report. Data are represented as
5882 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5883 purposes. The package also contains legacy support for early single-end,
5884 ungapped alignment formats.")
5885 (license license:artistic2.0)))
5887 (define-public r-systempiper
5889 (name "r-systempiper")
5894 (uri (bioconductor-uri "systemPipeR" version))
5897 "0c3m5rq63ypv15yca97yag5d4vgd7xj9by2a4sd8z0pcmpajz0hw"))))
5898 (properties `((upstream-name . "systemPipeR")))
5899 (build-system r-build-system)
5901 `(("r-annotate" ,r-annotate)
5902 ("r-batchjobs" ,r-batchjobs)
5903 ("r-biocgenerics" ,r-biocgenerics)
5904 ("r-biostrings" ,r-biostrings)
5905 ("r-deseq2" ,r-deseq2)
5906 ("r-edger" ,r-edger)
5907 ("r-genomicfeatures" ,r-genomicfeatures)
5908 ("r-genomicranges" ,r-genomicranges)
5909 ("r-ggplot2" ,r-ggplot2)
5910 ("r-go-db" ,r-go-db)
5911 ("r-gostats" ,r-gostats)
5912 ("r-limma" ,r-limma)
5913 ("r-pheatmap" ,r-pheatmap)
5914 ("r-rjson" ,r-rjson)
5915 ("r-rsamtools" ,r-rsamtools)
5916 ("r-shortread" ,r-shortread)
5917 ("r-summarizedexperiment" ,r-summarizedexperiment)
5918 ("r-variantannotation" ,r-variantannotation)))
5919 (home-page "https://github.com/tgirke/systemPipeR")
5920 (synopsis "Next generation sequencing workflow and reporting environment")
5922 "This R package provides tools for building and running automated
5923 end-to-end analysis workflows for a wide range of @dfn{next generation
5924 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5925 Important features include a uniform workflow interface across different NGS
5926 applications, automated report generation, and support for running both R and
5927 command-line software, such as NGS aligners or peak/variant callers, on local
5928 computers or compute clusters. Efficient handling of complex sample sets and
5929 experimental designs is facilitated by a consistently implemented sample
5930 annotation infrastructure.")
5931 (license license:artistic2.0)))
5933 (define-public r-grohmm
5940 (uri (bioconductor-uri "groHMM" version))
5943 "16k1kp4sbhh0vp7dzywafq52csq42ksqfrqfy4bdv1qbd7536dpd"))))
5944 (properties `((upstream-name . "groHMM")))
5945 (build-system r-build-system)
5947 `(("r-genomeinfodb" ,r-genomeinfodb)
5948 ("r-genomicalignments" ,r-genomicalignments)
5949 ("r-genomicranges" ,r-genomicranges)
5950 ("r-iranges" ,r-iranges)
5952 ("r-rtracklayer" ,r-rtracklayer)
5953 ("r-s4vectors" ,r-s4vectors)))
5954 (home-page "https://github.com/Kraus-Lab/groHMM")
5955 (synopsis "GRO-seq analysis pipeline")
5957 "This package provides a pipeline for the analysis of GRO-seq data.")
5958 (license license:gpl3+)))
5960 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5962 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5966 ;; We cannot use bioconductor-uri here because this tarball is
5967 ;; located under "data/annotation/" instead of "bioc/".
5968 (uri (string-append "http://bioconductor.org/packages/"
5969 "release/data/annotation/src/contrib"
5970 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5974 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5976 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5977 (build-system r-build-system)
5978 ;; As this package provides little more than a very large data file it
5979 ;; doesn't make sense to build substitutes.
5980 (arguments `(#:substitutable? #f))
5982 `(("r-genomicfeatures" ,r-genomicfeatures)))
5984 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5985 (synopsis "Annotation package for human genome in TxDb format")
5987 "This package provides an annotation database of Homo sapiens genome
5988 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5989 track. The database is exposed as a @code{TxDb} object.")
5990 (license license:artistic2.0)))
5992 (define-public vsearch
6000 "https://github.com/torognes/vsearch/archive/v"
6002 (file-name (string-append name "-" version ".tar.gz"))
6005 "0hc110ycqpa54nr6x173qg7190hk08qp7yz7zzqxlsypqnpc5zzp"))
6006 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6009 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6010 ;; for this in the patch.
6011 (delete-file "src/city.h")
6012 (delete-file "src/citycrc.h")
6013 (delete-file "src/city.cc")
6015 (build-system gnu-build-system)
6018 (modify-phases %standard-phases
6019 (add-before 'configure 'autogen
6020 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6024 ("cityhash" ,cityhash)))
6026 `(("autoconf" ,autoconf)
6027 ("automake" ,automake)))
6028 (synopsis "Sequence search tools for metagenomics")
6030 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6031 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6032 masking. The tool takes advantage of parallelism in the form of SIMD
6033 vectorization as well as multiple threads to perform accurate alignments at
6034 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6035 Needleman-Wunsch).")
6036 (home-page "https://github.com/torognes/vsearch")
6037 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6039 (supported-systems '("x86_64-linux"))
6040 ;; Dual licensed; also includes public domain source.
6041 (license (list license:gpl3 license:bsd-2))))
6043 (define-public pardre
6046 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6051 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6055 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6056 (build-system gnu-build-system)
6058 `(#:tests? #f ; no tests included
6060 (modify-phases %standard-phases
6063 (lambda* (#:key outputs #:allow-other-keys)
6064 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6065 (install-file "ParDRe" bin)
6068 `(("openmpi" ,openmpi)
6070 (synopsis "Parallel tool to remove duplicate DNA reads")
6072 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6073 Duplicate reads can be seen as identical or nearly identical sequences with
6074 some mismatches. This tool lets users avoid the analysis of unnecessary
6075 reads, reducing the time of subsequent procedures with the
6076 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6077 in order to exploit the parallel capabilities of multicore clusters. It is
6078 faster than multithreaded counterparts (end of 2015) for the same number of
6079 cores and, thanks to the message-passing technology, it can be executed on
6081 (home-page "https://sourceforge.net/projects/pardre/")
6082 (license license:gpl3+)))
6084 (define-public ruby-bio-kseq
6086 (name "ruby-bio-kseq")
6091 (uri (rubygems-uri "bio-kseq" version))
6094 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6095 (build-system ruby-build-system)
6097 `(#:test-target "spec"))
6099 `(("bundler" ,bundler)
6100 ("ruby-rspec" ,ruby-rspec)
6101 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6104 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6106 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6107 FASTQ parsing code. It provides a fast iterator over sequences and their
6109 (home-page "https://github.com/gusevfe/bio-kseq")
6110 (license license:expat)))
6112 (define-public bio-locus
6119 (uri (rubygems-uri "bio-locus" version))
6122 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6123 (build-system ruby-build-system)
6125 `(("ruby-rspec" ,ruby-rspec)))
6126 (synopsis "Tool for fast querying of genome locations")
6128 "Bio-locus is a tabix-like tool for fast querying of genome
6129 locations. Many file formats in bioinformatics contain records that
6130 start with a chromosome name and a position for a SNP, or a start-end
6131 position for indels. Bio-locus allows users to store this chr+pos or
6132 chr+pos+alt information in a database.")
6133 (home-page "https://github.com/pjotrp/bio-locus")
6134 (license license:expat)))
6136 (define-public bio-blastxmlparser
6138 (name "bio-blastxmlparser")
6142 (uri (rubygems-uri "bio-blastxmlparser" version))
6145 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6146 (build-system ruby-build-system)
6148 `(("ruby-bio-logger" ,ruby-bio-logger)
6149 ("ruby-nokogiri" ,ruby-nokogiri)))
6151 `(("ruby-rspec" ,ruby-rspec)))
6152 (synopsis "Fast big data BLAST XML parser and library")
6154 "Very fast parallel big-data BLAST XML file parser which can be used as
6155 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6156 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6157 (home-page "https://github.com/pjotrp/blastxmlparser")
6158 (license license:expat)))
6160 (define-public bioruby
6167 (uri (rubygems-uri "bio" version))
6170 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6171 (build-system ruby-build-system)
6173 `(("ruby-libxml" ,ruby-libxml)))
6175 `(("which" ,which))) ; required for test phase
6178 (modify-phases %standard-phases
6179 (add-before 'build 'patch-test-command
6181 (substitute* '("test/functional/bio/test_command.rb")
6182 (("/bin/sh") (which "sh")))
6183 (substitute* '("test/functional/bio/test_command.rb")
6184 (("/bin/ls") (which "ls")))
6185 (substitute* '("test/functional/bio/test_command.rb")
6186 (("which") (which "which")))
6187 (substitute* '("test/functional/bio/test_command.rb",
6188 "test/data/command/echoarg2.sh")
6189 (("/bin/echo") (which "echo")))
6191 (synopsis "Ruby library, shell and utilities for bioinformatics")
6192 (description "BioRuby comes with a comprehensive set of Ruby development
6193 tools and libraries for bioinformatics and molecular biology. BioRuby has
6194 components for sequence analysis, pathway analysis, protein modelling and
6195 phylogenetic analysis; it supports many widely used data formats and provides
6196 easy access to databases, external programs and public web services, including
6197 BLAST, KEGG, GenBank, MEDLINE and GO.")
6198 (home-page "http://bioruby.org/")
6199 ;; Code is released under Ruby license, except for setup
6200 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6201 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6203 (define-public r-acsnminer
6205 (name "r-acsnminer")
6206 (version "0.16.8.25")
6209 (uri (cran-uri "ACSNMineR" version))
6212 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6213 (properties `((upstream-name . "ACSNMineR")))
6214 (build-system r-build-system)
6216 `(("r-ggplot2" ,r-ggplot2)
6217 ("r-gridextra" ,r-gridextra)))
6218 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6219 (synopsis "Gene enrichment analysis")
6221 "This package provides tools to compute and represent gene set enrichment
6222 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6223 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6224 enrichment can be run with hypergeometric test or Fisher exact test, and can
6225 use multiple corrections. Visualization of data can be done either by
6226 barplots or heatmaps.")
6227 (license license:gpl2+)))
6229 (define-public r-biocgenerics
6231 (name "r-biocgenerics")
6235 (uri (bioconductor-uri "BiocGenerics" version))
6238 "0qbmz2qxwwi30xpxpvp2h1h7l494rbbz5d9pls5cfhqdv3wnpzsv"))))
6240 `((upstream-name . "BiocGenerics")))
6241 (build-system r-build-system)
6242 (home-page "http://bioconductor.org/packages/BiocGenerics")
6243 (synopsis "S4 generic functions for Bioconductor")
6245 "This package provides S4 generic functions needed by many Bioconductor
6247 (license license:artistic2.0)))
6249 (define-public r-biocinstaller
6251 (name "r-biocinstaller")
6255 (uri (bioconductor-uri "BiocInstaller" version))
6258 "0njw2q3lq1rrjx8qzw5d2130l72bmd3g2z8qlxqmkdcbmmgliyj2"))))
6260 `((upstream-name . "BiocInstaller")))
6261 (build-system r-build-system)
6262 (home-page "http://bioconductor.org/packages/BiocInstaller")
6263 (synopsis "Install Bioconductor packages")
6264 (description "This package is used to install and update R packages from
6265 Bioconductor, CRAN, and Github.")
6266 (license license:artistic2.0)))
6268 (define-public r-biocviews
6270 (name "r-biocviews")
6274 (uri (bioconductor-uri "biocViews" version))
6277 "17hi8w0w63f5yc43kid5pbld3ca78sj6n8x9dmkbl8h48818xbga"))))
6279 `((upstream-name . "biocViews")))
6280 (build-system r-build-system)
6282 `(("r-biobase" ,r-biobase)
6283 ("r-graph" ,r-graph)
6285 ("r-rcurl" ,r-rcurl)
6287 ("r-knitr" ,r-knitr)
6288 ("r-runit" ,r-runit)))
6289 (home-page "http://bioconductor.org/packages/biocViews")
6290 (synopsis "Bioconductor package categorization helper")
6291 (description "The purpose of biocViews is to create HTML pages that
6292 categorize packages in a Bioconductor package repository according to keywords,
6293 also known as views, in a controlled vocabulary.")
6294 (license license:artistic2.0)))
6296 (define-public r-bookdown
6302 (uri (cran-uri "bookdown" version))
6305 "0r9bchzg7im6psc3jphvshzbidc5bv5xaih1qg7b5518jy4iyvb9"))))
6306 (build-system r-build-system)
6308 `(("r-htmltools" ,r-htmltools)
6309 ("r-knitr" ,r-knitr)
6310 ("r-rmarkdown" ,r-rmarkdown)
6311 ("r-yaml" ,r-yaml)))
6312 (home-page "https://github.com/rstudio/bookdown")
6313 (synopsis "Authoring books and technical documents with R markdown")
6314 (description "This package provides output formats and utilities for
6315 authoring books and technical documents with R Markdown.")
6316 (license license:gpl3)))
6318 (define-public r-biocstyle
6320 (name "r-biocstyle")
6324 (uri (bioconductor-uri "BiocStyle" version))
6327 "1n2c8rj920wmk3q2khmjfnhn5i4b3lmhx1whnghk0zk3jf88hvbi"))))
6329 `((upstream-name . "BiocStyle")))
6330 (build-system r-build-system)
6332 `(("r-bookdown" ,r-bookdown)
6333 ("r-knitr" ,r-knitr)
6334 ("r-rmarkdown" ,r-rmarkdown)
6335 ("r-yaml" ,r-yaml)))
6336 (home-page "http://bioconductor.org/packages/BiocStyle")
6337 (synopsis "Bioconductor formatting styles")
6338 (description "This package provides standard formatting styles for
6339 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6341 (license license:artistic2.0)))
6343 (define-public r-bioccheck
6345 (name "r-bioccheck")
6349 (uri (bioconductor-uri "BiocCheck" version))
6352 "01zkw5hggzvn0wj4msac71k1mknq4h2inn1c2hwqgw4cy1675wl0"))))
6354 `((upstream-name . "BiocCheck")))
6355 (build-system r-build-system)
6358 (modify-phases %standard-phases
6359 ;; This package can be used by calling BiocCheck(<package>) from
6360 ;; within R, or by running R CMD BiocCheck <package>. This phase
6361 ;; makes sure the latter works. For this to work, the BiocCheck
6362 ;; script must be somewhere on the PATH (not the R bin directory).
6363 (add-after 'install 'install-bioccheck-subcommand
6364 (lambda* (#:key outputs #:allow-other-keys)
6365 (let* ((out (assoc-ref outputs "out"))
6366 (dest-dir (string-append out "/bin"))
6368 (string-append out "/site-library/BiocCheck/script/")))
6370 (symlink (string-append script-dir "/checkBadDeps.R")
6371 (string-append dest-dir "/checkBadDeps.R"))
6372 (symlink (string-append script-dir "/BiocCheck")
6373 (string-append dest-dir "/BiocCheck")))
6376 `(("which" ,which)))
6378 `(("r-codetools" ,r-codetools)
6379 ("r-graph" ,r-graph)
6381 ("r-optparse" ,r-optparse)
6382 ("r-biocinstaller" ,r-biocinstaller)
6383 ("r-biocviews" ,r-biocviews)))
6384 (home-page "http://bioconductor.org/packages/BiocCheck")
6385 (synopsis "Executes Bioconductor-specific package checks")
6386 (description "This package contains tools to perform additional quality
6387 checks on R packages that are to be submitted to the Bioconductor repository.")
6388 (license license:artistic2.0)))
6390 (define-public r-getopt
6397 (uri (cran-uri "getopt" version))
6400 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6401 (build-system r-build-system)
6402 (home-page "https://github.com/trevorld/getopt")
6403 (synopsis "Command-line option processor for R")
6405 "This package is designed to be used with Rscript to write shebang
6406 scripts that accept short and long options. Many users will prefer to
6407 use the packages @code{optparse} or @code{argparse} which add extra
6408 features like automatically generated help options and usage texts,
6409 support for default values, positional argument support, etc.")
6410 (license license:gpl2+)))
6412 (define-public r-optparse
6419 (uri (cran-uri "optparse" version))
6422 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6423 (build-system r-build-system)
6425 `(("r-getopt" ,r-getopt)))
6427 "https://github.com/trevorld/optparse")
6428 (synopsis "Command line option parser")
6430 "This package provides a command line parser inspired by Python's
6431 @code{optparse} library to be used with Rscript to write shebang scripts
6432 that accept short and long options.")
6433 (license license:gpl2+)))
6435 (define-public r-dnacopy
6441 (uri (bioconductor-uri "DNAcopy" version))
6444 "0112ry62z18m7rdyrn3gvbxq2f6m44cawhcfb1f02z9xzlsj0k28"))))
6446 `((upstream-name . "DNAcopy")))
6447 (build-system r-build-system)
6449 `(("gfortran" ,gfortran)))
6450 (home-page "https://bioconductor.org/packages/DNAcopy")
6451 (synopsis "Implementation of a circular binary segmentation algorithm")
6452 (description "This package implements the circular binary segmentation (CBS)
6453 algorithm to segment DNA copy number data and identify genomic regions with
6454 abnormal copy number.")
6455 (license license:gpl2+)))
6457 (define-public r-s4vectors
6459 (name "r-s4vectors")
6463 (uri (bioconductor-uri "S4Vectors" version))
6466 "0ywwrs4d752xfk0p0w122kvi0xvp6nmxnyynchbsa8zciqymhgv8"))))
6468 `((upstream-name . "S4Vectors")))
6469 (build-system r-build-system)
6471 `(("r-biocgenerics" ,r-biocgenerics)))
6472 (home-page "http://bioconductor.org/packages/S4Vectors")
6473 (synopsis "S4 implementation of vectors and lists")
6475 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6476 classes and a set of generic functions that extend the semantic of ordinary
6477 vectors and lists in R. Package developers can easily implement vector-like
6478 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6479 In addition, a few low-level concrete subclasses of general interest (e.g.
6480 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6481 S4Vectors package itself.")
6482 (license license:artistic2.0)))
6484 (define-public r-seqinr
6491 (uri (cran-uri "seqinr" version))
6494 "13d0qxm2244wgdl2dy2s8vnrnf5fx4n47if9gkb49dqx6c0sx8s2"))))
6495 (build-system r-build-system)
6497 `(("r-ade4" ,r-ade4)
6498 ("r-segmented" ,r-segmented)))
6501 (home-page "http://seqinr.r-forge.r-project.org/")
6502 (synopsis "Biological sequences retrieval and analysis")
6504 "This package provides tools for exploratory data analysis and data
6505 visualization of biological sequence (DNA and protein) data. It also includes
6506 utilities for sequence data management under the ACNUC system.")
6507 (license license:gpl2+)))
6509 (define-public r-iranges
6515 (uri (bioconductor-uri "IRanges" version))
6518 "0zp4mxm9h1p4krj7m7cinkvwa2ibqkq59jwpan97yvhb4z8q0d6n"))))
6520 `((upstream-name . "IRanges")))
6521 (build-system r-build-system)
6523 `(("r-biocgenerics" ,r-biocgenerics)
6524 ("r-s4vectors" ,r-s4vectors)))
6525 (home-page "http://bioconductor.org/packages/IRanges")
6526 (synopsis "Infrastructure for manipulating intervals on sequences")
6528 "This package provides efficient low-level and highly reusable S4 classes
6529 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6530 generally, data that can be organized sequentially (formally defined as
6531 @code{Vector} objects), as well as views on these @code{Vector} objects.
6532 Efficient list-like classes are also provided for storing big collections of
6533 instances of the basic classes. All classes in the package use consistent
6534 naming and share the same rich and consistent \"Vector API\" as much as
6536 (license license:artistic2.0)))
6538 (define-public r-genomeinfodbdata
6540 (name "r-genomeinfodbdata")
6544 ;; We cannot use bioconductor-uri here because this tarball is
6545 ;; located under "data/annotation/" instead of "bioc/".
6546 (uri (string-append "https://bioconductor.org/packages/release/"
6547 "data/annotation/src/contrib/GenomeInfoDbData_"
6551 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6553 `((upstream-name . "GenomeInfoDbData")))
6554 (build-system r-build-system)
6555 (home-page "http://bioconductor.org/packages/GenomeInfoDbData")
6556 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6557 (description "This package contains data for mapping between NCBI taxonomy
6558 ID and species. It is used by functions in the GenomeInfoDb package.")
6559 (license license:artistic2.0)))
6561 (define-public r-genomeinfodb
6563 (name "r-genomeinfodb")
6567 (uri (bioconductor-uri "GenomeInfoDb" version))
6570 "1bwwhscjl376a5p43mx8ijrqajxmgypbqhv049pgagl22hkkf0y3"))))
6572 `((upstream-name . "GenomeInfoDb")))
6573 (build-system r-build-system)
6575 `(("r-biocgenerics" ,r-biocgenerics)
6576 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6577 ("r-iranges" ,r-iranges)
6578 ("r-rcurl" ,r-rcurl)
6579 ("r-s4vectors" ,r-s4vectors)))
6580 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6581 (synopsis "Utilities for manipulating chromosome identifiers")
6583 "This package contains data and functions that define and allow
6584 translation between different chromosome sequence naming conventions (e.g.,
6585 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6586 names in their natural, rather than lexicographic, order.")
6587 (license license:artistic2.0)))
6589 (define-public r-edger
6595 (uri (bioconductor-uri "edgeR" version))
6598 "02l17i6xh33dv10swwvyfxrmv5kp23iv278iwvkfq2mnipasfnb9"))))
6599 (properties `((upstream-name . "edgeR")))
6600 (build-system r-build-system)
6602 `(("r-limma" ,r-limma)
6603 ("r-locfit" ,r-locfit)
6604 ("r-statmod" ,r-statmod))) ;for estimateDisp
6605 (home-page "http://bioinf.wehi.edu.au/edgeR")
6606 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6607 (description "This package can do differential expression analysis of
6608 RNA-seq expression profiles with biological replication. It implements a range
6609 of statistical methodology based on the negative binomial distributions,
6610 including empirical Bayes estimation, exact tests, generalized linear models
6611 and quasi-likelihood tests. It be applied to differential signal analysis of
6612 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6614 (license license:gpl2+)))
6616 (define-public r-variantannotation
6618 (name "r-variantannotation")
6622 (uri (bioconductor-uri "VariantAnnotation" version))
6625 "05hpm4as36kvpiqhgnkfjwfx0a05p304c21ggba29iac4nanm8b3"))))
6627 `((upstream-name . "VariantAnnotation")))
6631 `(("r-annotationdbi" ,r-annotationdbi)
6632 ("r-biobase" ,r-biobase)
6633 ("r-biocgenerics" ,r-biocgenerics)
6634 ("r-biostrings" ,r-biostrings)
6635 ("r-bsgenome" ,r-bsgenome)
6637 ("r-genomeinfodb" ,r-genomeinfodb)
6638 ("r-genomicfeatures" ,r-genomicfeatures)
6639 ("r-genomicranges" ,r-genomicranges)
6640 ("r-iranges" ,r-iranges)
6641 ("r-summarizedexperiment" ,r-summarizedexperiment)
6642 ("r-rsamtools" ,r-rsamtools)
6643 ("r-rtracklayer" ,r-rtracklayer)
6644 ("r-s4vectors" ,r-s4vectors)
6645 ("r-xvector" ,r-xvector)
6646 ("r-zlibbioc" ,r-zlibbioc)))
6647 (build-system r-build-system)
6648 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6649 (synopsis "Package for annotation of genetic variants")
6650 (description "This R package can annotate variants, compute amino acid
6651 coding changes and predict coding outcomes.")
6652 (license license:artistic2.0)))
6654 (define-public r-limma
6660 (uri (bioconductor-uri "limma" version))
6663 "0q7rqm86nwq0rg4fjggfr7xqybjrxj425vni3cva70b4c8d1h425"))))
6664 (build-system r-build-system)
6665 (home-page "http://bioinf.wehi.edu.au/limma")
6666 (synopsis "Package for linear models for microarray and RNA-seq data")
6667 (description "This package can be used for the analysis of gene expression
6668 studies, especially the use of linear models for analysing designed experiments
6669 and the assessment of differential expression. The analysis methods apply to
6670 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6671 (license license:gpl2+)))
6673 (define-public r-xvector
6679 (uri (bioconductor-uri "XVector" version))
6682 "01n09f4jdm60684lzikp02zf9gjan8bdrjx740vggr21q9fa69wn"))))
6684 `((upstream-name . "XVector")))
6685 (build-system r-build-system)
6688 (modify-phases %standard-phases
6689 (add-after 'unpack 'use-system-zlib
6691 (substitute* "DESCRIPTION"
6692 (("zlibbioc, ") ""))
6693 (substitute* "NAMESPACE"
6694 (("import\\(zlibbioc\\)") ""))
6699 `(("r-biocgenerics" ,r-biocgenerics)
6700 ("r-iranges" ,r-iranges)
6701 ("r-s4vectors" ,r-s4vectors)))
6702 (home-page "http://bioconductor.org/packages/XVector")
6703 (synopsis "Representation and manpulation of external sequences")
6705 "This package provides memory efficient S4 classes for storing sequences
6706 \"externally\" (behind an R external pointer, or on disk).")
6707 (license license:artistic2.0)))
6709 (define-public r-genomicranges
6711 (name "r-genomicranges")
6715 (uri (bioconductor-uri "GenomicRanges" version))
6718 "10x9zx0b7j05d1j6p0xs4q4f4wzbhf3rq64wzi9cgv7f44q43a5n"))))
6720 `((upstream-name . "GenomicRanges")))
6721 (build-system r-build-system)
6723 `(("r-biocgenerics" ,r-biocgenerics)
6724 ("r-genomeinfodb" ,r-genomeinfodb)
6725 ("r-iranges" ,r-iranges)
6726 ("r-s4vectors" ,r-s4vectors)
6727 ("r-xvector" ,r-xvector)))
6728 (home-page "http://bioconductor.org/packages/GenomicRanges")
6729 (synopsis "Representation and manipulation of genomic intervals")
6731 "This package provides tools to efficiently represent and manipulate
6732 genomic annotations and alignments is playing a central role when it comes to
6733 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6734 GenomicRanges package defines general purpose containers for storing and
6735 manipulating genomic intervals and variables defined along a genome.")
6736 (license license:artistic2.0)))
6738 (define-public r-biobase
6744 (uri (bioconductor-uri "Biobase" version))
6747 "0x7pf5xsdcj12dbf5qqki2c6bd5madqg2fbiq5xgisarpc9v6c1m"))))
6749 `((upstream-name . "Biobase")))
6750 (build-system r-build-system)
6752 `(("r-biocgenerics" ,r-biocgenerics)))
6753 (home-page "http://bioconductor.org/packages/Biobase")
6754 (synopsis "Base functions for Bioconductor")
6756 "This package provides functions that are needed by many other packages
6757 on Bioconductor or which replace R functions.")
6758 (license license:artistic2.0)))
6760 (define-public r-annotationdbi
6762 (name "r-annotationdbi")
6766 (uri (bioconductor-uri "AnnotationDbi" version))
6769 "1xffm98s817mfc827cnr0by6167nlrl1glxzjawzz0rkghs41g27"))))
6771 `((upstream-name . "AnnotationDbi")))
6772 (build-system r-build-system)
6774 `(("r-biobase" ,r-biobase)
6775 ("r-biocgenerics" ,r-biocgenerics)
6777 ("r-iranges" ,r-iranges)
6778 ("r-rsqlite" ,r-rsqlite)
6779 ("r-s4vectors" ,r-s4vectors)))
6780 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6781 (synopsis "Annotation database interface")
6783 "This package provides user interface and database connection code for
6784 annotation data packages using SQLite data storage.")
6785 (license license:artistic2.0)))
6787 (define-public r-biomart
6793 (uri (bioconductor-uri "biomaRt" version))
6796 "0knkxh23vl9pa0by03xr6dy9aiah714cmf54jl828k51l9wv5l2j"))))
6798 `((upstream-name . "biomaRt")))
6799 (build-system r-build-system)
6801 `(("r-annotationdbi" ,r-annotationdbi)
6802 ("r-rcurl" ,r-rcurl)
6804 (home-page "http://bioconductor.org/packages/biomaRt")
6805 (synopsis "Interface to BioMart databases")
6807 "biomaRt provides an interface to a growing collection of databases
6808 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6809 package enables retrieval of large amounts of data in a uniform way without
6810 the need to know the underlying database schemas or write complex SQL queries.
6811 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6812 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6813 users direct access to a diverse set of data and enable a wide range of
6814 powerful online queries from gene annotation to database mining.")
6815 (license license:artistic2.0)))
6817 (define-public r-biocparallel
6819 (name "r-biocparallel")
6823 (uri (bioconductor-uri "BiocParallel" version))
6826 "01ph0kq70b5gkd7n6a4myjlvwzgc0hi4xfwz8h17h06n9p5sdwa9"))))
6828 `((upstream-name . "BiocParallel")))
6829 (build-system r-build-system)
6831 `(("r-futile-logger" ,r-futile-logger)
6832 ("r-snow" ,r-snow)))
6833 (home-page "http://bioconductor.org/packages/BiocParallel")
6834 (synopsis "Bioconductor facilities for parallel evaluation")
6836 "This package provides modified versions and novel implementation of
6837 functions for parallel evaluation, tailored to use with Bioconductor
6839 (license (list license:gpl2+ license:gpl3+))))
6841 (define-public r-biostrings
6843 (name "r-biostrings")
6847 (uri (bioconductor-uri "Biostrings" version))
6850 "0ixgx12cx2z4n2khxq83crz9gc21qckj2v78y2p31567kfsw7clg"))))
6852 `((upstream-name . "Biostrings")))
6853 (build-system r-build-system)
6855 `(("r-biocgenerics" ,r-biocgenerics)
6856 ("r-iranges" ,r-iranges)
6857 ("r-s4vectors" ,r-s4vectors)
6858 ("r-xvector" ,r-xvector)))
6859 (home-page "http://bioconductor.org/packages/Biostrings")
6860 (synopsis "String objects and algorithms for biological sequences")
6862 "This package provides memory efficient string containers, string
6863 matching algorithms, and other utilities, for fast manipulation of large
6864 biological sequences or sets of sequences.")
6865 (license license:artistic2.0)))
6867 (define-public r-rsamtools
6869 (name "r-rsamtools")
6873 (uri (bioconductor-uri "Rsamtools" version))
6876 "1zx6vhdz3lksbfy98jj3qzl7cxgspigm2pbsd5835b12r6mc5w6d"))))
6878 `((upstream-name . "Rsamtools")))
6879 (build-system r-build-system)
6882 (modify-phases %standard-phases
6883 (add-after 'unpack 'use-system-zlib
6885 (substitute* "DESCRIPTION"
6886 (("zlibbioc, ") ""))
6887 (substitute* "NAMESPACE"
6888 (("import\\(zlibbioc\\)") ""))
6893 `(("r-biocgenerics" ,r-biocgenerics)
6894 ("r-biocparallel" ,r-biocparallel)
6895 ("r-biostrings" ,r-biostrings)
6896 ("r-bitops" ,r-bitops)
6897 ("r-genomeinfodb" ,r-genomeinfodb)
6898 ("r-genomicranges" ,r-genomicranges)
6899 ("r-iranges" ,r-iranges)
6900 ("r-s4vectors" ,r-s4vectors)
6901 ("r-xvector" ,r-xvector)))
6902 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6903 (synopsis "Interface to samtools, bcftools, and tabix")
6905 "This package provides an interface to the 'samtools', 'bcftools', and
6906 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6907 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6909 (license license:expat)))
6911 (define-public r-delayedarray
6913 (name "r-delayedarray")
6917 (uri (bioconductor-uri "DelayedArray" version))
6920 "0pcsk0f2dg2ldzprs1cccqrk53jrysmm6ccgjj5wh6z3x17g7g2r"))))
6922 `((upstream-name . "DelayedArray")))
6923 (build-system r-build-system)
6925 `(("r-biocgenerics" ,r-biocgenerics)
6926 ("r-s4vectors" ,r-s4vectors)
6927 ("r-iranges" ,r-iranges)
6928 ("r-matrixstats" ,r-matrixstats)))
6929 (home-page "http://bioconductor.org/packages/DelayedArray")
6930 (synopsis "Delayed operations on array-like objects")
6932 "Wrapping an array-like object (typically an on-disk object) in a
6933 @code{DelayedArray} object allows one to perform common array operations on it
6934 without loading the object in memory. In order to reduce memory usage and
6935 optimize performance, operations on the object are either delayed or executed
6936 using a block processing mechanism. Note that this also works on in-memory
6937 array-like objects like @code{DataFrame} objects (typically with Rle columns),
6938 @code{Matrix} objects, and ordinary arrays and data frames.")
6939 (license license:artistic2.0)))
6941 (define-public r-summarizedexperiment
6943 (name "r-summarizedexperiment")
6947 (uri (bioconductor-uri "SummarizedExperiment" version))
6950 "1szjbzzz4pyip891nji71caalxh0rhqiv7rpv6q54swlrqpfkqkw"))))
6952 `((upstream-name . "SummarizedExperiment")))
6953 (build-system r-build-system)
6955 `(("r-biobase" ,r-biobase)
6956 ("r-biocgenerics" ,r-biocgenerics)
6957 ("r-delayedarray" ,r-delayedarray)
6958 ("r-genomeinfodb" ,r-genomeinfodb)
6959 ("r-genomicranges" ,r-genomicranges)
6960 ("r-iranges" ,r-iranges)
6961 ("r-matrix" ,r-matrix)
6962 ("r-s4vectors" ,r-s4vectors)))
6963 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6964 (synopsis "Container for representing genomic ranges by sample")
6966 "The SummarizedExperiment container contains one or more assays, each
6967 represented by a matrix-like object of numeric or other mode. The rows
6968 typically represent genomic ranges of interest and the columns represent
6970 (license license:artistic2.0)))
6972 (define-public r-genomicalignments
6974 (name "r-genomicalignments")
6978 (uri (bioconductor-uri "GenomicAlignments" version))
6981 "1aagyrdk5309a7awg42lg0bpirp91i6i2ddvpmrs38pzriwahnjy"))))
6983 `((upstream-name . "GenomicAlignments")))
6984 (build-system r-build-system)
6986 `(("r-biocgenerics" ,r-biocgenerics)
6987 ("r-biocparallel" ,r-biocparallel)
6988 ("r-biostrings" ,r-biostrings)
6989 ("r-genomeinfodb" ,r-genomeinfodb)
6990 ("r-genomicranges" ,r-genomicranges)
6991 ("r-iranges" ,r-iranges)
6992 ("r-rsamtools" ,r-rsamtools)
6993 ("r-s4vectors" ,r-s4vectors)
6994 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6995 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6996 (synopsis "Representation and manipulation of short genomic alignments")
6998 "This package provides efficient containers for storing and manipulating
6999 short genomic alignments (typically obtained by aligning short reads to a
7000 reference genome). This includes read counting, computing the coverage,
7001 junction detection, and working with the nucleotide content of the
7003 (license license:artistic2.0)))
7005 (define-public r-rtracklayer
7007 (name "r-rtracklayer")
7011 (uri (bioconductor-uri "rtracklayer" version))
7014 "0dv7p3wzmx57inznf6fb06417zcm48g7fpazyahxny7bqgzwq0ig"))))
7015 (build-system r-build-system)
7018 (modify-phases %standard-phases
7019 (add-after 'unpack 'use-system-zlib
7021 (substitute* "DESCRIPTION"
7022 (("zlibbioc, ") ""))
7023 (substitute* "NAMESPACE"
7024 (("import\\(zlibbioc\\)") ""))
7029 `(("r-biocgenerics" ,r-biocgenerics)
7030 ("r-biostrings" ,r-biostrings)
7031 ("r-genomeinfodb" ,r-genomeinfodb)
7032 ("r-genomicalignments" ,r-genomicalignments)
7033 ("r-genomicranges" ,r-genomicranges)
7034 ("r-iranges" ,r-iranges)
7035 ("r-rcurl" ,r-rcurl)
7036 ("r-rsamtools" ,r-rsamtools)
7037 ("r-s4vectors" ,r-s4vectors)
7039 ("r-xvector" ,r-xvector)))
7040 (home-page "http://bioconductor.org/packages/rtracklayer")
7041 (synopsis "R interface to genome browsers and their annotation tracks")
7043 "rtracklayer is an extensible framework for interacting with multiple
7044 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7045 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7046 built-in). The user may export/import tracks to/from the supported browsers,
7047 as well as query and modify the browser state, such as the current viewport.")
7048 (license license:artistic2.0)))
7050 (define-public r-genomicfeatures
7052 (name "r-genomicfeatures")
7056 (uri (bioconductor-uri "GenomicFeatures" version))
7059 "1pjxlr34ygv8pvfwpyq268wpgqzphiwpij85fyhjqdwdp0a253ik"))))
7061 `((upstream-name . "GenomicFeatures")))
7062 (build-system r-build-system)
7064 `(("r-annotationdbi" ,r-annotationdbi)
7065 ("r-biobase" ,r-biobase)
7066 ("r-biocgenerics" ,r-biocgenerics)
7067 ("r-biomart" ,r-biomart)
7068 ("r-biostrings" ,r-biostrings)
7070 ("r-genomeinfodb" ,r-genomeinfodb)
7071 ("r-genomicranges" ,r-genomicranges)
7072 ("r-iranges" ,r-iranges)
7073 ("r-rcurl" ,r-rcurl)
7074 ("r-rsqlite" ,r-rsqlite)
7075 ("r-rtracklayer" ,r-rtracklayer)
7076 ("r-s4vectors" ,r-s4vectors)
7077 ("r-xvector" ,r-xvector)))
7078 (home-page "http://bioconductor.org/packages/GenomicFeatures")
7079 (synopsis "Tools for working with transcript centric annotations")
7081 "This package provides a set of tools and methods for making and
7082 manipulating transcript centric annotations. With these tools the user can
7083 easily download the genomic locations of the transcripts, exons and cds of a
7084 given organism, from either the UCSC Genome Browser or a BioMart
7085 database (more sources will be supported in the future). This information is
7086 then stored in a local database that keeps track of the relationship between
7087 transcripts, exons, cds and genes. Flexible methods are provided for
7088 extracting the desired features in a convenient format.")
7089 (license license:artistic2.0)))
7091 (define-public r-go-db
7097 (uri (string-append "http://www.bioconductor.org/packages/"
7098 "release/data/annotation/src/contrib/GO.db_"
7102 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7104 `((upstream-name . "GO.db")))
7105 (build-system r-build-system)
7107 `(("r-annotationdbi" ,r-annotationdbi)))
7108 (home-page "http://bioconductor.org/packages/GO.db")
7109 (synopsis "Annotation maps describing the entire Gene Ontology")
7111 "The purpose of this GO.db annotation package is to provide detailed
7112 information about the latest version of the Gene Ontologies.")
7113 (license license:artistic2.0)))
7115 (define-public r-graph
7121 (uri (bioconductor-uri "graph" version))
7124 "0hx9wslnrci7c5i1gd1zlpjmgrkdnx9gabfgmzzwfnykk1mdvvna"))))
7125 (build-system r-build-system)
7127 `(("r-biocgenerics" ,r-biocgenerics)))
7128 (home-page "http://bioconductor.org/packages/graph")
7129 (synopsis "Handle graph data structures in R")
7131 "This package implements some simple graph handling capabilities for R.")
7132 (license license:artistic2.0)))
7134 (define-public r-topgo
7140 (uri (bioconductor-uri "topGO" version))
7143 "04kvxz9qsxfz0np7wlrzp4r95nykz94x7mqpyyk76f90g6m66vcc"))))
7145 `((upstream-name . "topGO")))
7146 (build-system r-build-system)
7148 `(("r-annotationdbi" ,r-annotationdbi)
7150 ("r-biobase" ,r-biobase)
7151 ("r-biocgenerics" ,r-biocgenerics)
7152 ("r-go-db" ,r-go-db)
7153 ("r-graph" ,r-graph)
7154 ("r-lattice" ,r-lattice)
7155 ("r-matrixstats" ,r-matrixstats)
7156 ("r-sparsem" ,r-sparsem)))
7157 (home-page "http://bioconductor.org/packages/topGO")
7158 (synopsis "Enrichment analysis for gene ontology")
7160 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7161 terms while accounting for the topology of the GO graph. Different test
7162 statistics and different methods for eliminating local similarities and
7163 dependencies between GO terms can be implemented and applied.")
7164 ;; Any version of the LGPL applies.
7165 (license license:lgpl2.1+)))
7167 (define-public r-bsgenome
7173 (uri (bioconductor-uri "BSgenome" version))
7176 "18dlknwk3xvi52hamxf9pl5bjc5806mpw98xwvx5xajn8mrxiy5h"))))
7178 `((upstream-name . "BSgenome")))
7179 (build-system r-build-system)
7181 `(("r-biocgenerics" ,r-biocgenerics)
7182 ("r-biostrings" ,r-biostrings)
7183 ("r-genomeinfodb" ,r-genomeinfodb)
7184 ("r-genomicranges" ,r-genomicranges)
7185 ("r-iranges" ,r-iranges)
7186 ("r-rsamtools" ,r-rsamtools)
7187 ("r-rtracklayer" ,r-rtracklayer)
7188 ("r-s4vectors" ,r-s4vectors)
7189 ("r-xvector" ,r-xvector)))
7190 (home-page "http://bioconductor.org/packages/BSgenome")
7191 (synopsis "Infrastructure for Biostrings-based genome data packages")
7193 "This package provides infrastructure shared by all Biostrings-based
7194 genome data packages and support for efficient SNP representation.")
7195 (license license:artistic2.0)))
7197 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7199 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7203 ;; We cannot use bioconductor-uri here because this tarball is
7204 ;; located under "data/annotation/" instead of "bioc/".
7205 (uri (string-append "http://www.bioconductor.org/packages/"
7206 "release/data/annotation/src/contrib/"
7207 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7211 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7213 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7214 (build-system r-build-system)
7215 ;; As this package provides little more than a very large data file it
7216 ;; doesn't make sense to build substitutes.
7217 (arguments `(#:substitutable? #f))
7219 `(("r-bsgenome" ,r-bsgenome)))
7221 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7222 (synopsis "Full genome sequences for Homo sapiens")
7224 "This package provides full genome sequences for Homo sapiens from
7225 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7226 (license license:artistic2.0)))
7228 (define-public r-impute
7234 (uri (bioconductor-uri "impute" version))
7237 "0va45vfixy3np549md87h3b3rbavm54gfnmnjhpr9hf02lll6zxs"))))
7239 `(("gfortran" ,gfortran)))
7240 (build-system r-build-system)
7241 (home-page "http://bioconductor.org/packages/impute")
7242 (synopsis "Imputation for microarray data")
7244 "This package provides a function to impute missing gene expression
7245 microarray data, using nearest neighbor averaging.")
7246 (license license:gpl2+)))
7248 (define-public r-seqpattern
7250 (name "r-seqpattern")
7254 (uri (bioconductor-uri "seqPattern" version))
7257 "0yw5251sirv3283xgmfmfbf900xp8dwvqfk88mr945s3by5hx99v"))))
7259 `((upstream-name . "seqPattern")))
7260 (build-system r-build-system)
7262 `(("r-biostrings" ,r-biostrings)
7263 ("r-genomicranges" ,r-genomicranges)
7264 ("r-iranges" ,r-iranges)
7265 ("r-kernsmooth" ,r-kernsmooth)
7266 ("r-plotrix" ,r-plotrix)))
7267 (home-page "http://bioconductor.org/packages/seqPattern")
7268 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7270 "This package provides tools to visualize oligonucleotide patterns and
7271 sequence motif occurrences across a large set of sequences centred at a common
7272 reference point and sorted by a user defined feature.")
7273 (license license:gpl3+)))
7275 (define-public r-genomation
7277 (name "r-genomation")
7281 (uri (bioconductor-uri "genomation" version))
7284 "0r71nf8p3aq3yffqxg4yir1zmm7rar5a57nmy1kpqpn8kaf2svjl"))))
7285 (build-system r-build-system)
7287 `(("r-biostrings" ,r-biostrings)
7288 ("r-bsgenome" ,r-bsgenome)
7289 ("r-data-table" ,r-data-table)
7290 ("r-genomeinfodb" ,r-genomeinfodb)
7291 ("r-genomicalignments" ,r-genomicalignments)
7292 ("r-genomicranges" ,r-genomicranges)
7293 ("r-ggplot2" ,r-ggplot2)
7294 ("r-gridbase" ,r-gridbase)
7295 ("r-impute" ,r-impute)
7296 ("r-iranges" ,r-iranges)
7297 ("r-matrixstats" ,r-matrixstats)
7298 ("r-plotrix" ,r-plotrix)
7301 ("r-readr" ,r-readr)
7302 ("r-reshape2" ,r-reshape2)
7303 ("r-rhtslib" ,r-rhtslib)
7304 ("r-rsamtools" ,r-rsamtools)
7305 ("r-rtracklayer" ,r-rtracklayer)
7306 ("r-runit" ,r-runit)
7307 ("r-s4vectors" ,r-s4vectors)
7308 ("r-seqpattern" ,r-seqpattern)))
7311 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7312 (synopsis "Summary, annotation and visualization of genomic data")
7314 "This package provides a package for summary and annotation of genomic
7315 intervals. Users can visualize and quantify genomic intervals over
7316 pre-defined functional regions, such as promoters, exons, introns, etc. The
7317 genomic intervals represent regions with a defined chromosome position, which
7318 may be associated with a score, such as aligned reads from HT-seq experiments,
7319 TF binding sites, methylation scores, etc. The package can use any tabular
7320 genomic feature data as long as it has minimal information on the locations of
7321 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7322 (license license:artistic2.0)))
7324 (define-public r-genomationdata
7326 (name "r-genomationdata")
7330 ;; We cannot use bioconductor-uri here because this tarball is
7331 ;; located under "data/annotation/" instead of "bioc/".
7332 (uri (string-append "https://bioconductor.org/packages/"
7333 "release/data/experiment/src/contrib/"
7334 "genomationData_" version ".tar.gz"))
7337 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7338 (build-system r-build-system)
7339 ;; As this package provides little more than large data files, it doesn't
7340 ;; make sense to build substitutes.
7341 (arguments `(#:substitutable? #f))
7343 `(("r-knitr" ,r-knitr)))
7344 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7345 (synopsis "Experimental data for use with the genomation package")
7347 "This package contains experimental genetic data for use with the
7348 genomation package. Included are Chip Seq, Methylation and Cage data,
7349 downloaded from Encode.")
7350 (license license:gpl3+)))
7352 (define-public r-org-hs-eg-db
7354 (name "r-org-hs-eg-db")
7358 ;; We cannot use bioconductor-uri here because this tarball is
7359 ;; located under "data/annotation/" instead of "bioc/".
7360 (uri (string-append "http://www.bioconductor.org/packages/"
7361 "release/data/annotation/src/contrib/"
7362 "org.Hs.eg.db_" version ".tar.gz"))
7365 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7367 `((upstream-name . "org.Hs.eg.db")))
7368 (build-system r-build-system)
7370 `(("r-annotationdbi" ,r-annotationdbi)))
7371 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7372 (synopsis "Genome wide annotation for Human")
7374 "This package provides mappings from Entrez gene identifiers to various
7375 annotations for the human genome.")
7376 (license license:artistic2.0)))
7378 (define-public r-org-ce-eg-db
7380 (name "r-org-ce-eg-db")
7384 ;; We cannot use bioconductor-uri here because this tarball is
7385 ;; located under "data/annotation/" instead of "bioc/".
7386 (uri (string-append "http://www.bioconductor.org/packages/"
7387 "release/data/annotation/src/contrib/"
7388 "org.Ce.eg.db_" version ".tar.gz"))
7391 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7393 `((upstream-name . "org.Ce.eg.db")))
7394 (build-system r-build-system)
7396 `(("r-annotationdbi" ,r-annotationdbi)))
7397 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7398 (synopsis "Genome wide annotation for Worm")
7400 "This package provides mappings from Entrez gene identifiers to various
7401 annotations for the genome of the model worm Caenorhabditis elegans.")
7402 (license license:artistic2.0)))
7404 (define-public r-org-dm-eg-db
7406 (name "r-org-dm-eg-db")
7410 ;; We cannot use bioconductor-uri here because this tarball is
7411 ;; located under "data/annotation/" instead of "bioc/".
7412 (uri (string-append "http://www.bioconductor.org/packages/"
7413 "release/data/annotation/src/contrib/"
7414 "org.Dm.eg.db_" version ".tar.gz"))
7417 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7419 `((upstream-name . "org.Dm.eg.db")))
7420 (build-system r-build-system)
7422 `(("r-annotationdbi" ,r-annotationdbi)))
7423 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7424 (synopsis "Genome wide annotation for Fly")
7426 "This package provides mappings from Entrez gene identifiers to various
7427 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7428 (license license:artistic2.0)))
7430 (define-public r-org-mm-eg-db
7432 (name "r-org-mm-eg-db")
7436 ;; We cannot use bioconductor-uri here because this tarball is
7437 ;; located under "data/annotation/" instead of "bioc/".
7438 (uri (string-append "http://www.bioconductor.org/packages/"
7439 "release/data/annotation/src/contrib/"
7440 "org.Mm.eg.db_" version ".tar.gz"))
7443 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7445 `((upstream-name . "org.Mm.eg.db")))
7446 (build-system r-build-system)
7448 `(("r-annotationdbi" ,r-annotationdbi)))
7449 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7450 (synopsis "Genome wide annotation for Mouse")
7452 "This package provides mappings from Entrez gene identifiers to various
7453 annotations for the genome of the model mouse Mus musculus.")
7454 (license license:artistic2.0)))
7456 (define-public r-seqlogo
7463 (uri (bioconductor-uri "seqLogo" version))
7466 "19d5zmy7m8svljwgbmrb4vxkq18slq0f3all6k2ayv42b8w44h6q"))))
7467 (properties `((upstream-name . "seqLogo")))
7468 (build-system r-build-system)
7469 (home-page "http://bioconductor.org/packages/seqLogo")
7470 (synopsis "Sequence logos for DNA sequence alignments")
7472 "seqLogo takes the position weight matrix of a DNA sequence motif and
7473 plots the corresponding sequence logo as introduced by Schneider and
7475 (license license:lgpl2.0+)))
7477 (define-public r-bsgenome-hsapiens-ucsc-hg19
7479 (name "r-bsgenome-hsapiens-ucsc-hg19")
7483 ;; We cannot use bioconductor-uri here because this tarball is
7484 ;; located under "data/annotation/" instead of "bioc/".
7485 (uri (string-append "http://www.bioconductor.org/packages/"
7486 "release/data/annotation/src/contrib/"
7487 "BSgenome.Hsapiens.UCSC.hg19_"
7491 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7493 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7494 (build-system r-build-system)
7495 ;; As this package provides little more than a very large data file it
7496 ;; doesn't make sense to build substitutes.
7497 (arguments `(#:substitutable? #f))
7499 `(("r-bsgenome" ,r-bsgenome)))
7501 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7502 (synopsis "Full genome sequences for Homo sapiens")
7504 "This package provides full genome sequences for Homo sapiens as provided
7505 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7506 (license license:artistic2.0)))
7508 (define-public r-bsgenome-mmusculus-ucsc-mm9
7510 (name "r-bsgenome-mmusculus-ucsc-mm9")
7514 ;; We cannot use bioconductor-uri here because this tarball is
7515 ;; located under "data/annotation/" instead of "bioc/".
7516 (uri (string-append "http://www.bioconductor.org/packages/"
7517 "release/data/annotation/src/contrib/"
7518 "BSgenome.Mmusculus.UCSC.mm9_"
7522 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7524 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7525 (build-system r-build-system)
7526 ;; As this package provides little more than a very large data file it
7527 ;; doesn't make sense to build substitutes.
7528 (arguments `(#:substitutable? #f))
7530 `(("r-bsgenome" ,r-bsgenome)))
7532 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7533 (synopsis "Full genome sequences for Mouse")
7535 "This package provides full genome sequences for Mus musculus (Mouse) as
7536 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7537 (license license:artistic2.0)))
7539 (define-public r-bsgenome-mmusculus-ucsc-mm10
7541 (name "r-bsgenome-mmusculus-ucsc-mm10")
7545 ;; We cannot use bioconductor-uri here because this tarball is
7546 ;; located under "data/annotation/" instead of "bioc/".
7547 (uri (string-append "http://www.bioconductor.org/packages/"
7548 "release/data/annotation/src/contrib/"
7549 "BSgenome.Mmusculus.UCSC.mm10_"
7553 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7555 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7556 (build-system r-build-system)
7557 ;; As this package provides little more than a very large data file it
7558 ;; doesn't make sense to build substitutes.
7559 (arguments `(#:substitutable? #f))
7561 `(("r-bsgenome" ,r-bsgenome)))
7563 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7564 (synopsis "Full genome sequences for Mouse")
7566 "This package provides full genome sequences for Mus
7567 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7568 in Biostrings objects.")
7569 (license license:artistic2.0)))
7571 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7573 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7577 ;; We cannot use bioconductor-uri here because this tarball is
7578 ;; located under "data/annotation/" instead of "bioc/".
7579 (uri (string-append "http://www.bioconductor.org/packages/"
7580 "release/data/annotation/src/contrib/"
7581 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7585 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7587 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7588 (build-system r-build-system)
7589 ;; As this package provides little more than a very large data file it
7590 ;; doesn't make sense to build substitutes.
7591 (arguments `(#:substitutable? #f))
7593 `(("r-bsgenome" ,r-bsgenome)
7594 ("r-genomicfeatures" ,r-genomicfeatures)
7595 ("r-annotationdbi" ,r-annotationdbi)))
7597 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7598 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7600 "This package loads a TxDb object, which is an R interface to
7601 prefabricated databases contained in this package. This package provides
7602 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7603 based on the knownGene track.")
7604 (license license:artistic2.0)))
7606 (define-public r-bsgenome-celegans-ucsc-ce6
7608 (name "r-bsgenome-celegans-ucsc-ce6")
7612 ;; We cannot use bioconductor-uri here because this tarball is
7613 ;; located under "data/annotation/" instead of "bioc/".
7614 (uri (string-append "http://www.bioconductor.org/packages/"
7615 "release/data/annotation/src/contrib/"
7616 "BSgenome.Celegans.UCSC.ce6_"
7620 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7622 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7623 (build-system r-build-system)
7624 ;; As this package provides little more than a very large data file it
7625 ;; doesn't make sense to build substitutes.
7626 (arguments `(#:substitutable? #f))
7628 `(("r-bsgenome" ,r-bsgenome)))
7630 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7631 (synopsis "Full genome sequences for Worm")
7633 "This package provides full genome sequences for Caenorhabditis
7634 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7636 (license license:artistic2.0)))
7638 (define-public r-bsgenome-celegans-ucsc-ce10
7640 (name "r-bsgenome-celegans-ucsc-ce10")
7644 ;; We cannot use bioconductor-uri here because this tarball is
7645 ;; located under "data/annotation/" instead of "bioc/".
7646 (uri (string-append "http://www.bioconductor.org/packages/"
7647 "release/data/annotation/src/contrib/"
7648 "BSgenome.Celegans.UCSC.ce10_"
7652 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7654 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7655 (build-system r-build-system)
7656 ;; As this package provides little more than a very large data file it
7657 ;; doesn't make sense to build substitutes.
7658 (arguments `(#:substitutable? #f))
7660 `(("r-bsgenome" ,r-bsgenome)))
7662 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7663 (synopsis "Full genome sequences for Worm")
7665 "This package provides full genome sequences for Caenorhabditis
7666 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7668 (license license:artistic2.0)))
7670 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7672 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7676 ;; We cannot use bioconductor-uri here because this tarball is
7677 ;; located under "data/annotation/" instead of "bioc/".
7678 (uri (string-append "http://www.bioconductor.org/packages/"
7679 "release/data/annotation/src/contrib/"
7680 "BSgenome.Dmelanogaster.UCSC.dm3_"
7684 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7686 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7687 (build-system r-build-system)
7688 ;; As this package provides little more than a very large data file it
7689 ;; doesn't make sense to build substitutes.
7690 (arguments `(#:substitutable? #f))
7692 `(("r-bsgenome" ,r-bsgenome)))
7694 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7695 (synopsis "Full genome sequences for Fly")
7697 "This package provides full genome sequences for Drosophila
7698 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7699 Biostrings objects.")
7700 (license license:artistic2.0)))
7702 (define-public r-motifrg
7709 (uri (bioconductor-uri "motifRG" version))
7712 "0lxxpqyljiyk73vyq6ss46q13g81pm24q87mkzdsqlr5zx427ch6"))))
7713 (properties `((upstream-name . "motifRG")))
7714 (build-system r-build-system)
7716 `(("r-biostrings" ,r-biostrings)
7717 ("r-bsgenome" ,r-bsgenome)
7718 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7719 ("r-iranges" ,r-iranges)
7720 ("r-seqlogo" ,r-seqlogo)
7721 ("r-xvector" ,r-xvector)))
7722 (home-page "http://bioconductor.org/packages/motifRG")
7723 (synopsis "Discover motifs in high throughput sequencing data")
7725 "This package provides tools for discriminative motif discovery in high
7726 throughput genetic sequencing data sets using regression methods.")
7727 (license license:artistic2.0)))
7729 (define-public r-qtl
7736 (uri (string-append "mirror://cran/src/contrib/qtl_"
7740 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7741 (build-system r-build-system)
7742 (home-page "http://rqtl.org/")
7743 (synopsis "R package for analyzing QTL experiments in genetics")
7744 (description "R/qtl is an extension library for the R statistics
7745 system. It is used to analyze experimental crosses for identifying
7746 genes contributing to variation in quantitative traits (so-called
7747 quantitative trait loci, QTLs).
7749 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7750 identify genotyping errors, and to perform single-QTL and two-QTL,
7751 two-dimensional genome scans.")
7752 (license license:gpl3)))
7754 (define-public r-zlibbioc
7760 (uri (bioconductor-uri "zlibbioc" version))
7763 "1kdgwwlh39mgwzj3zq71za4iv40sq625ghnyrndv5wrivrcr2igv"))))
7765 `((upstream-name . "zlibbioc")))
7766 (build-system r-build-system)
7767 (home-page "https://bioconductor.org/packages/zlibbioc")
7768 (synopsis "Provider for zlib-1.2.5 to R packages")
7769 (description "This package uses the source code of zlib-1.2.5 to create
7770 libraries for systems that do not have these available via other means.")
7771 (license license:artistic2.0)))
7773 (define-public r-r4rna
7780 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7784 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7785 (build-system r-build-system)
7787 `(("r-optparse" ,r-optparse)
7788 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7789 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7790 (synopsis "Analysis framework for RNA secondary structure")
7792 "The R4RNA package aims to be a general framework for the analysis of RNA
7793 secondary structure and comparative analysis in R.")
7794 (license license:gpl3+)))
7796 (define-public r-rhtslib
7803 (uri (bioconductor-uri "Rhtslib" version))
7806 "0jj5h81z5gyf4j3lp2l3zsm6pgbmalgrngr8qdpygc20phndpp0b"))))
7807 (properties `((upstream-name . "Rhtslib")))
7808 (build-system r-build-system)
7810 `(("r-zlibbioc" ,r-zlibbioc)))
7814 `(("autoconf" ,autoconf)))
7815 (home-page "https://github.com/nhayden/Rhtslib")
7816 (synopsis "High-throughput sequencing library as an R package")
7818 "This package provides the HTSlib C library for high-throughput
7819 nucleotide sequence analysis. The package is primarily useful to developers
7820 of other R packages who wish to make use of HTSlib.")
7821 (license license:lgpl2.0+)))
7823 (define-public r-bamsignals
7825 (name "r-bamsignals")
7830 (uri (bioconductor-uri "bamsignals" version))
7833 "0knx69zzdaak2sjim8k9mygmcjxpa705m8013ld5zwpgi8dag9mc"))))
7834 (build-system r-build-system)
7836 `(("r-biocgenerics" ,r-biocgenerics)
7837 ("r-genomicranges" ,r-genomicranges)
7838 ("r-iranges" ,r-iranges)
7840 ("r-rhtslib" ,r-rhtslib)
7841 ("r-zlibbioc" ,r-zlibbioc)))
7844 (home-page "http://bioconductor.org/packages/bamsignals")
7845 (synopsis "Extract read count signals from bam files")
7847 "This package allows to efficiently obtain count vectors from indexed bam
7848 files. It counts the number of nucleotide sequence reads in given genomic
7849 ranges and it computes reads profiles and coverage profiles. It also handles
7851 (license license:gpl2+)))
7853 (define-public r-rcas
7859 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7861 (file-name (string-append name "-" version ".tar.gz"))
7864 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7865 (build-system r-build-system)
7867 `(("r-knitr" ,r-knitr)
7868 ("r-testthat" ,r-testthat)
7869 ;; During vignette building knitr checks that "pandoc-citeproc"
7871 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7873 `(("r-data-table" ,r-data-table)
7874 ("r-biomart" ,r-biomart)
7875 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7876 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7877 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7878 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7879 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7880 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7881 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7882 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7883 ("r-topgo" ,r-topgo)
7885 ("r-plotly" ,r-plotly)
7886 ("r-plotrix" ,r-plotrix)
7887 ("r-motifrg" ,r-motifrg)
7888 ("r-genomation" ,r-genomation)
7889 ("r-genomicfeatures" ,r-genomicfeatures)
7890 ("r-rtracklayer" ,r-rtracklayer)
7891 ("r-rmarkdown" ,r-rmarkdown)))
7892 (synopsis "RNA-centric annotation system")
7894 "RCAS aims to be a standalone RNA-centric annotation system that provides
7895 intuitive reports and publication-ready graphics. This package provides the R
7896 library implementing most of the pipeline's features.")
7897 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7898 (license license:expat)))
7900 (define-public rcas-web
7907 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7908 "releases/download/v" version
7909 "/rcas-web-" version ".tar.gz"))
7912 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7913 (build-system gnu-build-system)
7916 (modify-phases %standard-phases
7917 (add-after 'install 'wrap-executable
7918 (lambda* (#:key inputs outputs #:allow-other-keys)
7919 (let* ((out (assoc-ref outputs "out"))
7920 (json (assoc-ref inputs "guile-json"))
7921 (redis (assoc-ref inputs "guile-redis"))
7922 (path (string-append
7923 json "/share/guile/site/2.2:"
7924 redis "/share/guile/site/2.2")))
7925 (wrap-program (string-append out "/bin/rcas-web")
7926 `("GUILE_LOAD_PATH" ":" = (,path))
7927 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7928 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7931 `(("r-minimal" ,r-minimal)
7933 ("guile-next" ,guile-2.2)
7934 ("guile-json" ,guile-json)
7935 ("guile-redis" ,guile2.2-redis)))
7937 `(("pkg-config" ,pkg-config)))
7938 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7939 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7940 (description "This package provides a simple web interface for the
7941 @dfn{RNA-centric annotation system} (RCAS).")
7942 (license license:agpl3+)))
7944 (define-public r-mutationalpatterns
7946 (name "r-mutationalpatterns")
7951 (uri (bioconductor-uri "MutationalPatterns" version))
7954 "1s50diwh1j6vg3mgahh6bczvq74mfdbmwjrad4d5lh723gnc5pjg"))))
7955 (build-system r-build-system)
7957 `(("r-biocgenerics" ,r-biocgenerics)
7958 ("r-biostrings" ,r-biostrings)
7959 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
7960 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7961 ("r-genomicranges" ,r-genomicranges)
7962 ("r-genomeinfodb" ,r-genomeinfodb)
7963 ("r-ggplot2" ,r-ggplot2)
7964 ("r-gridextra" ,r-gridextra)
7965 ("r-iranges" ,r-iranges)
7968 ("r-pracma" ,r-pracma)
7969 ("r-reshape2" ,r-reshape2)
7970 ("r-summarizedexperiment" ,r-summarizedexperiment)
7971 ("r-variantannotation" ,r-variantannotation)))
7972 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7973 (synopsis "Extract and visualize mutational patterns in genomic data")
7974 (description "This package provides an extensive toolset for the
7975 characterization and visualization of a wide range of mutational patterns
7976 in SNV base substitution data.")
7977 (license license:expat)))
7979 (define-public r-wgcna
7986 (uri (cran-uri "WGCNA" version))
7989 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7990 (properties `((upstream-name . "WGCNA")))
7991 (build-system r-build-system)
7993 `(("r-annotationdbi" ,r-annotationdbi)
7994 ("r-doparallel" ,r-doparallel)
7995 ("r-dynamictreecut" ,r-dynamictreecut)
7996 ("r-fastcluster" ,r-fastcluster)
7997 ("r-foreach" ,r-foreach)
7998 ("r-go-db" ,r-go-db)
7999 ("r-hmisc" ,r-hmisc)
8000 ("r-impute" ,r-impute)
8001 ("r-matrixstats" ,r-matrixstats)
8002 ("r-preprocesscore" ,r-preprocesscore)))
8004 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8005 (synopsis "Weighted correlation network analysis")
8007 "This package provides functions necessary to perform Weighted
8008 Correlation Network Analysis on high-dimensional data. It includes functions
8009 for rudimentary data cleaning, construction and summarization of correlation
8010 networks, module identification and functions for relating both variables and
8011 modules to sample traits. It also includes a number of utility functions for
8012 data manipulation and visualization.")
8013 (license license:gpl2+)))
8015 (define-public r-chipkernels
8016 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8019 (name "r-chipkernels")
8020 (version (string-append "1.1-" revision "." (string-take commit 9)))
8025 (url "https://github.com/ManuSetty/ChIPKernels.git")
8027 (file-name (string-append name "-" version))
8030 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8031 (build-system r-build-system)
8033 `(("r-iranges" ,r-iranges)
8034 ("r-xvector" ,r-xvector)
8035 ("r-biostrings" ,r-biostrings)
8036 ("r-bsgenome" ,r-bsgenome)
8037 ("r-gtools" ,r-gtools)
8038 ("r-genomicranges" ,r-genomicranges)
8039 ("r-sfsmisc" ,r-sfsmisc)
8040 ("r-kernlab" ,r-kernlab)
8041 ("r-s4vectors" ,r-s4vectors)
8042 ("r-biocgenerics" ,r-biocgenerics)))
8043 (home-page "https://github.com/ManuSetty/ChIPKernels")
8044 (synopsis "Build string kernels for DNA Sequence analysis")
8045 (description "ChIPKernels is an R package for building different string
8046 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8047 must be built and this dictionary can be used for determining kernels for DNA
8049 (license license:gpl2+))))
8051 (define-public r-seqgl
8058 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8059 "archive/" version ".tar.gz"))
8060 (file-name (string-append name "-" version ".tar.gz"))
8063 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8064 (build-system r-build-system)
8066 `(("r-biostrings" ,r-biostrings)
8067 ("r-chipkernels" ,r-chipkernels)
8068 ("r-genomicranges" ,r-genomicranges)
8069 ("r-spams" ,r-spams)
8070 ("r-wgcna" ,r-wgcna)
8071 ("r-fastcluster" ,r-fastcluster)))
8072 (home-page "https://github.com/ManuSetty/SeqGL")
8073 (synopsis "Group lasso for Dnase/ChIP-seq data")
8074 (description "SeqGL is a group lasso based algorithm to extract
8075 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8076 This package presents a method which uses group lasso to discriminate between
8077 bound and non bound genomic regions to accurately identify transcription
8078 factors bound at the specific regions.")
8079 (license license:gpl2+)))
8081 (define-public r-gkmsvm
8088 (uri (cran-uri "gkmSVM" version))
8091 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8092 (properties `((upstream-name . "gkmSVM")))
8093 (build-system r-build-system)
8095 `(("r-biocgenerics" ,r-biocgenerics)
8096 ("r-biostrings" ,r-biostrings)
8097 ("r-genomeinfodb" ,r-genomeinfodb)
8098 ("r-genomicranges" ,r-genomicranges)
8099 ("r-iranges" ,r-iranges)
8100 ("r-kernlab" ,r-kernlab)
8103 ("r-rtracklayer" ,r-rtracklayer)
8104 ("r-s4vectors" ,r-s4vectors)
8105 ("r-seqinr" ,r-seqinr)))
8106 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8107 (synopsis "Gapped-kmer support vector machine")
8109 "This R package provides tools for training gapped-kmer SVM classifiers
8110 for DNA and protein sequences. This package supports several sequence
8111 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8112 (license license:gpl2+)))
8114 (define-public r-tximport
8120 (uri (bioconductor-uri "tximport" version))
8123 "1mklb02bj4gnbjlmb7vv6k4lr3w9fp3pzli9rddbrwd0y5n8fcpx"))))
8124 (build-system r-build-system)
8125 (home-page "http://bioconductor.org/packages/tximport")
8126 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8128 "This package provides tools to import transcript-level abundance,
8129 estimated counts and transcript lengths, and to summarize them into matrices
8130 for use with downstream gene-level analysis packages. Average transcript
8131 length, weighted by sample-specific transcript abundance estimates, is
8132 provided as a matrix which can be used as an offset for different expression
8133 of gene-level counts.")
8134 (license license:gpl2+)))
8136 (define-public r-rhdf5
8142 (uri (bioconductor-uri "rhdf5" version))
8145 "1p6f5i6l44phl772a38x9cav2sya37bkqbkjzdc4pmyfzkv1j6hy"))))
8146 (build-system r-build-system)
8149 (modify-phases %standard-phases
8150 (add-after 'unpack 'unpack-smallhdf5
8151 (lambda* (#:key outputs #:allow-other-keys)
8152 (system* "tar" "-xzvf"
8153 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8154 (substitute* "src/Makevars"
8155 (("^.*cd hdf5source &&.*$") "")
8156 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8157 (("^.*rm -rf hdf5.*$") "")
8158 (("^.*mv hdf5source/hdf5 ..*$") ""))
8159 (substitute* "src/hdf5/configure"
8163 `(("r-zlibbioc" ,r-zlibbioc)))
8167 (home-page "http://bioconductor.org/packages/rhdf5")
8168 (synopsis "HDF5 interface to R")
8170 "This R/Bioconductor package provides an interface between HDF5 and R.
8171 HDF5's main features are the ability to store and access very large and/or
8172 complex datasets and a wide variety of metadata on mass storage (disk) through
8173 a completely portable file format. The rhdf5 package is thus suited for the
8174 exchange of large and/or complex datasets between R and other software
8175 package, and for letting R applications work on datasets that are larger than
8176 the available RAM.")
8177 (license license:artistic2.0)))
8179 (define-public emboss
8185 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8186 (version-major+minor version) ".0/"
8187 "EMBOSS-" version ".tar.gz"))
8190 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8191 (build-system gnu-build-system)
8194 (list (string-append "--with-hpdf="
8195 (assoc-ref %build-inputs "libharu")))
8197 (modify-phases %standard-phases
8198 (add-after 'unpack 'fix-checks
8200 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8201 ;; and zlib, but assume that they are all found at the same
8203 (substitute* "configure.in"
8204 (("CHECK_PNGDRIVER")
8205 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8206 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8207 AM_CONDITIONAL(AMPNG, true)"))
8209 (add-after 'unpack 'disable-update-check
8211 ;; At build time there is no connection to the Internet, so
8212 ;; looking for updates will not work.
8213 (substitute* "Makefile.am"
8214 (("\\$\\(bindir\\)/embossupdate") ""))
8216 (add-before 'configure 'autogen
8217 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8223 ("libharu" ,libharu)
8226 `(("autoconf" ,autoconf)
8227 ("automake" ,automake)
8228 ("libtool" ,libtool)
8229 ("pkg-config" ,pkg-config)))
8230 (home-page "http://emboss.sourceforge.net")
8231 (synopsis "Molecular biology analysis suite")
8232 (description "EMBOSS is the \"European Molecular Biology Open Software
8233 Suite\". EMBOSS is an analysis package specially developed for the needs of
8234 the molecular biology (e.g. EMBnet) user community. The software
8235 automatically copes with data in a variety of formats and even allows
8236 transparent retrieval of sequence data from the web. It also provides a
8237 number of libraries for the development of software in the field of molecular
8238 biology. EMBOSS also integrates a range of currently available packages and
8239 tools for sequence analysis into a seamless whole.")
8240 (license license:gpl2+)))
8243 (let ((revision "1")
8244 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8247 ;; The version is 2.13.0 even though no release archives have been
8248 ;; published as yet.
8249 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8253 (url "https://github.com/arq5x/bits.git")
8255 (file-name (string-append name "-" version "-checkout"))
8258 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8259 (build-system gnu-build-system)
8261 `(#:tests? #f ;no tests included
8263 (modify-phases %standard-phases
8265 (add-after 'unpack 'remove-cuda
8267 (substitute* "Makefile"
8269 (("(bits_test_intersections) \\\\" _ match) match))
8272 (lambda* (#:key outputs #:allow-other-keys)
8274 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8279 (home-page "https://github.com/arq5x/bits")
8280 (synopsis "Implementation of binary interval search algorithm")
8281 (description "This package provides an implementation of the
8282 BITS (Binary Interval Search) algorithm, an approach to interval set
8283 intersection. It is especially suited for the comparison of diverse genomic
8284 datasets and the exploration of large datasets of genome
8285 intervals (e.g. genes, sequence alignments).")
8286 (license license:gpl2))))
8288 (define-public piranha
8289 ;; There is no release tarball for the latest version. The latest commit is
8290 ;; older than one year at the time of this writing.
8291 (let ((revision "1")
8292 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8295 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8299 (url "https://github.com/smithlabcode/piranha.git")
8303 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8304 (build-system gnu-build-system)
8306 `(#:test-target "test"
8308 (modify-phases %standard-phases
8309 (add-after 'unpack 'copy-smithlab-cpp
8310 (lambda* (#:key inputs #:allow-other-keys)
8311 (for-each (lambda (file)
8312 (install-file file "./src/smithlab_cpp/"))
8313 (find-files (assoc-ref inputs "smithlab-cpp")))
8315 (add-after 'install 'install-to-store
8316 (lambda* (#:key outputs #:allow-other-keys)
8317 (let* ((out (assoc-ref outputs "out"))
8318 (bin (string-append out "/bin")))
8319 (for-each (lambda (file)
8320 (install-file file bin))
8321 (find-files "bin" ".*")))
8324 (list (string-append "--with-bam_tools_headers="
8325 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8326 (string-append "--with-bam_tools_library="
8327 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8329 `(("bamtools" ,bamtools)
8330 ("samtools" ,samtools-0.1)
8333 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8337 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8339 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8342 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8344 `(("python" ,python-2)))
8345 (home-page "https://github.com/smithlabcode/piranha")
8346 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8348 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8349 RIP-seq experiments. It takes input in BED or BAM format and identifies
8350 regions of statistically significant read enrichment. Additional covariates
8351 may optionally be provided to further inform the peak-calling process.")
8352 (license license:gpl3+))))
8360 (uri (string-append "https://pypi.python.org/packages/source/P"
8361 "/PePr/PePr-" version ".tar.gz"))
8364 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8365 (build-system python-build-system)
8367 `(#:python ,python-2 ; python2 only
8368 #:tests? #f)) ; no tests included
8370 `(("python2-numpy" ,python2-numpy)
8371 ("python2-scipy" ,python2-scipy)
8372 ("python2-pysam" ,python2-pysam)))
8373 (home-page "https://github.com/shawnzhangyx/PePr")
8374 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8376 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8377 that is primarily designed for data with biological replicates. It uses a
8378 negative binomial distribution to model the read counts among the samples in
8379 the same group, and look for consistent differences between ChIP and control
8380 group or two ChIP groups run under different conditions.")
8381 (license license:gpl3+)))
8383 (define-public filevercmp
8384 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8387 (version (string-append "0-1." (string-take commit 7)))
8390 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8392 (file-name (string-append name "-" version ".tar.gz"))
8394 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8395 (build-system gnu-build-system)
8397 `(#:tests? #f ; There are no tests to run.
8399 (modify-phases %standard-phases
8400 (delete 'configure) ; There is no configure phase.
8402 (lambda* (#:key outputs #:allow-other-keys)
8403 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8404 (install-file "filevercmp" bin)))))))
8405 (home-page "https://github.com/ekg/filevercmp")
8406 (synopsis "This program compares version strings")
8407 (description "This program compares version strings. It intends to be a
8408 replacement for strverscmp.")
8409 (license license:gpl3+))))
8411 (define-public multiqc
8418 (uri (pypi-uri "multiqc" version))
8421 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8422 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8423 (build-system python-build-system)
8425 ;; Tests are to be introduced in the next version, see
8426 ;; https://github.com/ewels/MultiQC/issues/376
8429 `(("python-jinja2" ,python-jinja2)
8430 ("python-simplejson" ,python-simplejson)
8431 ("python-pyyaml" ,python-pyyaml)
8432 ("python-click" ,python-click)
8433 ("python-matplotlib" ,python-matplotlib)
8434 ("python-numpy" ,python-numpy)
8435 ;; MultQC checks for the presence of nose at runtime.
8436 ("python-nose" ,python-nose)))
8437 (home-page "http://multiqc.info")
8438 (synopsis "Aggregate bioinformatics analysis reports")
8440 "MultiQC is a tool to aggregate bioinformatics results across many
8441 samples into a single report. It contains modules for a large number of
8442 common bioinformatics tools.")
8443 (license license:gpl3)))
8445 (define-public r-chipseq
8452 (uri (bioconductor-uri "chipseq" version))
8455 "1hahyqiwb2ch8214xqpw0c3jpiwkmyf3dwz0xc87jx6cdnzipj3i"))))
8456 (build-system r-build-system)
8458 `(("r-biocgenerics" ,r-biocgenerics)
8459 ("r-genomicranges" ,r-genomicranges)
8460 ("r-iranges" ,r-iranges)
8461 ("r-s4vectors" ,r-s4vectors)
8462 ("r-shortread" ,r-shortread)))
8463 (home-page "http://bioconductor.org/packages/chipseq")
8464 (synopsis "Package for analyzing ChIPseq data")
8466 "This package provides tools for processing short read data from ChIPseq
8468 (license license:artistic2.0)))
8470 (define-public r-copyhelper
8472 (name "r-copyhelper")
8477 (uri (string-append "http://bioconductor.org/packages/release/"
8478 "data/experiment/src/contrib/CopyhelpeR_"
8482 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8483 (properties `((upstream-name . "CopyhelpeR")))
8484 (build-system r-build-system)
8485 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8486 (synopsis "Helper files for CopywriteR")
8488 "This package contains the helper files that are required to run the
8489 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8490 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8491 mm10. In addition, it contains a blacklist filter to remove regions that
8492 display copy number variation. Files are stored as GRanges objects from the
8493 GenomicRanges Bioconductor package.")
8494 (license license:gpl2)))
8496 (define-public r-copywriter
8498 (name "r-copywriter")
8503 (uri (bioconductor-uri "CopywriteR" version))
8506 "183nmrqmdf9syqljslvwv7mhs9ar5xizzq98imgsc80q0m25ncjf"))))
8507 (properties `((upstream-name . "CopywriteR")))
8508 (build-system r-build-system)
8510 `(("r-biocparallel" ,r-biocparallel)
8511 ("r-chipseq" ,r-chipseq)
8512 ("r-copyhelper" ,r-copyhelper)
8513 ("r-data-table" ,r-data-table)
8514 ("r-dnacopy" ,r-dnacopy)
8515 ("r-futile-logger" ,r-futile-logger)
8516 ("r-genomeinfodb" ,r-genomeinfodb)
8517 ("r-genomicalignments" ,r-genomicalignments)
8518 ("r-genomicranges" ,r-genomicranges)
8519 ("r-gtools" ,r-gtools)
8520 ("r-iranges" ,r-iranges)
8521 ("r-matrixstats" ,r-matrixstats)
8522 ("r-rsamtools" ,r-rsamtools)
8523 ("r-s4vectors" ,r-s4vectors)))
8524 (home-page "https://github.com/PeeperLab/CopywriteR")
8525 (synopsis "Copy number information from targeted sequencing")
8527 "CopywriteR extracts DNA copy number information from targeted sequencing
8528 by utilizing off-target reads. It allows for extracting uniformly distributed
8529 copy number information, can be used without reference, and can be applied to
8530 sequencing data obtained from various techniques including chromatin
8531 immunoprecipitation and target enrichment on small gene panels. Thereby,
8532 CopywriteR constitutes a widely applicable alternative to available copy
8533 number detection tools.")
8534 (license license:gpl2)))
8536 (define-public r-sva
8543 (uri (bioconductor-uri "sva" version))
8546 "04pxl61iyc845wmqca1qv8kbb8zcp0qp72zgvgki3zzmrph9a362"))))
8547 (build-system r-build-system)
8549 `(("r-genefilter" ,r-genefilter)
8550 ("r-mgcv" ,r-mgcv)))
8551 (home-page "http://bioconductor.org/packages/sva")
8552 (synopsis "Surrogate variable analysis")
8554 "This package contains functions for removing batch effects and other
8555 unwanted variation in high-throughput experiment. It also contains functions
8556 for identifying and building surrogate variables for high-dimensional data
8557 sets. Surrogate variables are covariates constructed directly from
8558 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8559 imaging data that can be used in subsequent analyses to adjust for unknown,
8560 unmodeled, or latent sources of noise.")
8561 (license license:artistic2.0)))
8563 (define-public r-seqminer
8570 (uri (cran-uri "seqminer" version))
8573 "0sfkxrc9gy5a8fadzyzfzh7l5grasm8cj6cd2nnpv85ws6mqr6qd"))))
8574 (build-system r-build-system)
8577 (home-page "http://seqminer.genomic.codes")
8578 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8580 "This package provides tools to integrate nucleotide sequencing
8581 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8582 ;; Any version of the GPL is acceptable
8583 (license (list license:gpl2+ license:gpl3+))))
8585 (define-public r-raremetals2
8587 (name "r-raremetals2")
8592 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8593 "b/b7/RareMETALS2_" version ".tar.gz"))
8596 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8597 (properties `((upstream-name . "RareMETALS2")))
8598 (build-system r-build-system)
8600 `(("r-seqminer" ,r-seqminer)
8601 ("r-mvtnorm" ,r-mvtnorm)
8603 ("r-compquadform" ,r-compquadform)
8604 ("r-getopt" ,r-getopt)))
8605 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8606 (synopsis "Analyze gene-level association tests for binary trait")
8608 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8609 It was designed to meta-analyze gene-level association tests for binary trait.
8610 While rareMETALS offers a near-complete solution for meta-analysis of
8611 gene-level tests for quantitative trait, it does not offer the optimal
8612 solution for binary trait. The package rareMETALS2 offers improved features
8613 for analyzing gene-level association tests in meta-analyses for binary
8615 (license license:gpl3)))
8617 (define-public r-maldiquant
8619 (name "r-maldiquant")
8624 (uri (cran-uri "MALDIquant" version))
8627 "0z5srzsfgsgi4bssr4chls4ry6d18y2g9143znqmraylppwrrqzr"))))
8628 (properties `((upstream-name . "MALDIquant")))
8629 (build-system r-build-system)
8630 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8631 (synopsis "Quantitative analysis of mass spectrometry data")
8633 "This package provides a complete analysis pipeline for matrix-assisted
8634 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8635 two-dimensional mass spectrometry data. In addition to commonly used plotting
8636 and processing methods it includes distinctive features, namely baseline
8637 subtraction methods such as morphological filters (TopHat) or the
8638 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8639 alignment using warping functions, handling of replicated measurements as well
8640 as allowing spectra with different resolutions.")
8641 (license license:gpl3+)))
8643 (define-public r-protgenerics
8645 (name "r-protgenerics")
8650 (uri (bioconductor-uri "ProtGenerics" version))
8653 "08idb3rvxn4fl7rd66jasyqz47cb76dbc3968r1g26jr2ci3w1pl"))))
8654 (properties `((upstream-name . "ProtGenerics")))
8655 (build-system r-build-system)
8656 (home-page "https://github.com/lgatto/ProtGenerics")
8657 (synopsis "S4 generic functions for proteomics infrastructure")
8659 "This package provides S4 generic functions needed by Bioconductor
8660 proteomics packages.")
8661 (license license:artistic2.0)))
8663 (define-public r-mzr
8670 (uri (bioconductor-uri "mzR" version))
8673 "1zir46h320n2vbrky6q3m8l221f3wdjlfsnx4ak9xca5min24xm7"))))
8674 (properties `((upstream-name . "mzR")))
8675 (build-system r-build-system)
8677 `(("netcdf" ,netcdf)))
8679 `(("r-biobase" ,r-biobase)
8680 ("r-biocgenerics" ,r-biocgenerics)
8681 ("r-protgenerics" ,r-protgenerics)
8683 ("r-zlibbioc" ,r-zlibbioc)))
8684 (home-page "https://github.com/sneumann/mzR/")
8685 (synopsis "Parser for mass spectrometry data files")
8687 "The mzR package provides a unified API to the common file formats and
8688 parsers available for mass spectrometry data. It comes with a wrapper for the
8689 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8690 The package contains the original code written by the ISB, and a subset of the
8691 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8692 previously been used in XCMS.")
8693 (license license:artistic2.0)))
8695 (define-public r-affyio
8702 (uri (bioconductor-uri "affyio" version))
8705 "13w6al9296q916w0w6ngbsk25b21ahla1b6n40fcqhbvhyfii6sj"))))
8706 (build-system r-build-system)
8708 `(("r-zlibbioc" ,r-zlibbioc)))
8711 (home-page "https://github.com/bmbolstad/affyio")
8712 (synopsis "Tools for parsing Affymetrix data files")
8714 "This package provides routines for parsing Affymetrix data files based
8715 upon file format information. The primary focus is on accessing the CEL and
8717 (license license:lgpl2.0+)))
8719 (define-public r-affy
8726 (uri (bioconductor-uri "affy" version))
8729 "0azwg2qxzgflr1rjvbdln5i5rbcr9gs36kqlacd9cwl1szb9ad3m"))))
8730 (build-system r-build-system)
8732 `(("r-affyio" ,r-affyio)
8733 ("r-biobase" ,r-biobase)
8734 ("r-biocgenerics" ,r-biocgenerics)
8735 ("r-biocinstaller" ,r-biocinstaller)
8736 ("r-preprocesscore" ,r-preprocesscore)
8737 ("r-zlibbioc" ,r-zlibbioc)))
8738 (home-page "http://bioconductor.org/packages/affy")
8739 (synopsis "Methods for affymetrix oligonucleotide arrays")
8741 "This package contains functions for exploratory oligonucleotide array
8743 (license license:lgpl2.0+)))
8745 (define-public r-vsn
8752 (uri (bioconductor-uri "vsn" version))
8755 "0qhg3a4sc62pfdxcpvmk831rk138xh4zx4f1s39jhxpqqhmr7jvk"))))
8756 (build-system r-build-system)
8758 `(("r-affy" ,r-affy)
8759 ("r-biobase" ,r-biobase)
8760 ("r-ggplot2" ,r-ggplot2)
8761 ("r-hexbin" ,r-hexbin)
8762 ("r-lattice" ,r-lattice)
8763 ("r-limma" ,r-limma)))
8764 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8765 (synopsis "Variance stabilization and calibration for microarray data")
8767 "The package implements a method for normalising microarray intensities,
8768 and works for single- and multiple-color arrays. It can also be used for data
8769 from other technologies, as long as they have similar format. The method uses
8770 a robust variant of the maximum-likelihood estimator for an
8771 additive-multiplicative error model and affine calibration. The model
8772 incorporates data calibration step (a.k.a. normalization), a model for the
8773 dependence of the variance on the mean intensity and a variance stabilizing
8774 data transformation. Differences between transformed intensities are
8775 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8776 their variance is independent of the mean, and they are usually more sensitive
8777 and specific in detecting differential transcription.")
8778 (license license:artistic2.0)))
8780 (define-public r-mzid
8787 (uri (bioconductor-uri "mzID" version))
8790 "11xnild02jz24vbsfy92lb7jlqqwnrswg66a7r4rsw8d2ibrbk33"))))
8791 (properties `((upstream-name . "mzID")))
8792 (build-system r-build-system)
8794 `(("r-doparallel" ,r-doparallel)
8795 ("r-foreach" ,r-foreach)
8796 ("r-iterators" ,r-iterators)
8798 ("r-protgenerics" ,r-protgenerics)
8801 (home-page "http://bioconductor.org/packages/mzID")
8802 (synopsis "Parser for mzIdentML files")
8804 "This package provides a parser for mzIdentML files implemented using the
8805 XML package. The parser tries to be general and able to handle all types of
8806 mzIdentML files with the drawback of having less pretty output than a vendor
8808 (license license:gpl2+)))
8810 (define-public r-pcamethods
8812 (name "r-pcamethods")
8817 (uri (bioconductor-uri "pcaMethods" version))
8820 "0c4lphqyzj577ws4s172391cgv00s5nhy152zp18k2k4diyhq6n0"))))
8821 (properties `((upstream-name . "pcaMethods")))
8822 (build-system r-build-system)
8824 `(("r-biobase" ,r-biobase)
8825 ("r-biocgenerics" ,r-biocgenerics)
8827 ("r-rcpp" ,r-rcpp)))
8828 (home-page "https://github.com/hredestig/pcamethods")
8829 (synopsis "Collection of PCA methods")
8831 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8832 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8833 for missing value estimation is included for comparison. BPCA, PPCA and
8834 NipalsPCA may be used to perform PCA on incomplete data as well as for
8835 accurate missing value estimation. A set of methods for printing and plotting
8836 the results is also provided. All PCA methods make use of the same data
8837 structure (pcaRes) to provide a common interface to the PCA results.")
8838 (license license:gpl3+)))
8840 (define-public r-msnbase
8847 (uri (bioconductor-uri "MSnbase" version))
8850 "1n9bbdlp8d8bx2mqby0c4yylz1yil42scbkxqgyrfr9s5sn6dqff"))))
8851 (properties `((upstream-name . "MSnbase")))
8852 (build-system r-build-system)
8854 `(("r-affy" ,r-affy)
8855 ("r-biobase" ,r-biobase)
8856 ("r-biocgenerics" ,r-biocgenerics)
8857 ("r-biocparallel" ,r-biocparallel)
8858 ("r-digest" ,r-digest)
8859 ("r-ggplot2" ,r-ggplot2)
8860 ("r-impute" ,r-impute)
8861 ("r-iranges" ,r-iranges)
8862 ("r-maldiquant" ,r-maldiquant)
8865 ("r-pcamethods" ,r-pcamethods)
8867 ("r-preprocesscore" ,r-preprocesscore)
8868 ("r-protgenerics" ,r-protgenerics)
8870 ("r-reshape2" ,r-reshape2)
8871 ("r-s4vectors" ,r-s4vectors)
8874 (home-page "https://github.com/lgatto/MSnbase")
8875 (synopsis "Base functions and classes for MS-based proteomics")
8877 "This package provides basic plotting, data manipulation and processing
8878 of mass spectrometry based proteomics data.")
8879 (license license:artistic2.0)))
8881 (define-public r-msnid
8888 (uri (bioconductor-uri "MSnID" version))
8891 "0pjwargi5lif8q53fd43ql67p3yk9w10jychafd9qgbaw5k3f68k"))))
8892 (properties `((upstream-name . "MSnID")))
8893 (build-system r-build-system)
8895 `(("r-biobase" ,r-biobase)
8896 ("r-data-table" ,r-data-table)
8897 ("r-doparallel" ,r-doparallel)
8898 ("r-dplyr" ,r-dplyr)
8899 ("r-foreach" ,r-foreach)
8900 ("r-iterators" ,r-iterators)
8901 ("r-msnbase" ,r-msnbase)
8904 ("r-protgenerics" ,r-protgenerics)
8905 ("r-r-cache" ,r-r-cache)
8907 ("r-reshape2" ,r-reshape2)))
8908 (home-page "http://bioconductor.org/packages/MSnID")
8909 (synopsis "Utilities for LC-MSn proteomics identifications")
8911 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8912 from mzIdentML (leveraging the mzID package) or text files. After collating
8913 the search results from multiple datasets it assesses their identification
8914 quality and optimize filtering criteria to achieve the maximum number of
8915 identifications while not exceeding a specified false discovery rate. It also
8916 contains a number of utilities to explore the MS/MS results and assess missed
8917 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
8918 (license license:artistic2.0)))
8920 (define-public r-seurat
8921 ;; Source releases are only made for new x.0 versions. All newer versions
8922 ;; are only released as pre-built binaries. At the time of this writing the
8923 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
8924 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
8928 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
8932 (url "https://github.com/satijalab/seurat")
8934 (file-name (string-append name "-" version "-checkout"))
8937 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
8938 ;; Delete pre-built jar.
8940 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
8942 (build-system r-build-system)
8945 (modify-phases %standard-phases
8946 (add-after 'unpack 'build-jar
8947 (lambda* (#:key inputs #:allow-other-keys)
8948 (let ((classesdir "tmp-classes"))
8949 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
8951 (and (zero? (apply system* `("javac" "-d" ,classesdir
8952 ,@(find-files "java" "\\.java$"))))
8953 (zero? (system* "jar"
8954 "-cf" "inst/java/ModularityOptimizer.jar"
8955 "-C" classesdir ".")))))))))
8957 `(("jdk" ,icedtea "jdk")))
8960 ("r-caret" ,r-caret)
8961 ("r-cowplot" ,r-cowplot)
8962 ("r-dplyr" ,r-dplyr)
8963 ("r-fastica" ,r-fastica)
8966 ("r-gdata" ,r-gdata)
8967 ("r-ggplot2" ,r-ggplot2)
8968 ("r-gplots" ,r-gplots)
8969 ("r-gridextra" ,r-gridextra)
8970 ("r-igraph" ,r-igraph)
8971 ("r-irlba" ,r-irlba)
8973 ("r-mixtools" ,r-mixtools)
8974 ("r-pbapply" ,r-pbapply)
8976 ("r-ranger" ,r-ranger)
8977 ("r-rcolorbrewer" ,r-rcolorbrewer)
8979 ("r-rcppeigen" ,r-rcppeigen)
8980 ("r-rcppprogress" ,r-rcppprogress)
8981 ("r-reshape2" ,r-reshape2)
8983 ("r-rtsne" ,r-rtsne)
8984 ("r-stringr" ,r-stringr)
8985 ("r-tclust" ,r-tclust)
8987 ("r-vgam" ,r-vgam)))
8988 (home-page "http://www.satijalab.org/seurat")
8989 (synopsis "Seurat is an R toolkit for single cell genomics")
8991 "This package is an R package designed for QC, analysis, and
8992 exploration of single cell RNA-seq data. It easily enables widely-used
8993 analytical techniques, including the identification of highly variable genes,
8994 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
8995 algorithms; density clustering, hierarchical clustering, k-means, and the
8996 discovery of differentially expressed genes and markers.")
8997 (license license:gpl3))))
8999 (define htslib-for-sambamba
9000 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9003 (name "htslib-for-sambamba")
9004 (version (string-append "1.3.1-1." (string-take commit 9)))
9009 (url "https://github.com/lomereiter/htslib.git")
9011 (file-name (string-append "htslib-" version "-checkout"))
9014 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9016 (substitute-keyword-arguments (package-arguments htslib)
9018 `(modify-phases ,phases
9019 (add-before 'configure 'bootstrap
9021 (zero? (system* "autoreconf" "-vif"))))))))
9023 `(("autoconf" ,autoconf)
9024 ("automake" ,automake)
9025 ,@(package-native-inputs htslib))))))
9027 (define-public sambamba
9034 (uri (string-append "https://github.com/lomereiter/sambamba/"
9035 "archive/v" version ".tar.gz"))
9036 (file-name (string-append name "-" version ".tar.gz"))
9039 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9040 (build-system gnu-build-system)
9042 `(#:tests? #f ; there is no test target
9045 ;; Override "--compiler" flag only.
9046 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9047 "sambamba-ldmd2-64")
9049 (modify-phases %standard-phases
9051 (add-after 'unpack 'place-biod
9052 (lambda* (#:key inputs #:allow-other-keys)
9053 (copy-recursively (assoc-ref inputs "biod") "BioD")
9055 (add-after 'unpack 'unbundle-prerequisites
9057 (substitute* "Makefile"
9058 ((" htslib-static lz4-static") ""))
9061 (lambda* (#:key outputs #:allow-other-keys)
9062 (let* ((out (assoc-ref outputs "out"))
9063 (bin (string-append out "/bin")))
9065 (install-file "build/sambamba" bin)
9071 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9075 (url "https://github.com/biod/BioD.git")
9077 (file-name (string-append "biod-"
9078 (string-take commit 9)
9082 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9085 ("htslib" ,htslib-for-sambamba)))
9086 (home-page "http://lomereiter.github.io/sambamba")
9087 (synopsis "Tools for working with SAM/BAM data")
9088 (description "Sambamba is a high performance modern robust and
9089 fast tool (and library), written in the D programming language, for
9090 working with SAM and BAM files. Current parallelised functionality is
9091 an important subset of samtools functionality, including view, index,
9092 sort, markdup, and depth.")
9093 (license license:gpl2+)))