6525 lines
261 KiB
Scheme
6525 lines
261 KiB
Scheme
;;; GNU Guix --- Functional package management for GNU
|
||
;;; Copyright © 2014, 2015, 2016 Ricardo Wurmus <rekado@elephly.net>
|
||
;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
|
||
;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
|
||
;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
|
||
;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
|
||
;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
|
||
;;;
|
||
;;; This file is part of GNU Guix.
|
||
;;;
|
||
;;; GNU Guix is free software; you can redistribute it and/or modify it
|
||
;;; under the terms of the GNU General Public License as published by
|
||
;;; the Free Software Foundation; either version 3 of the License, or (at
|
||
;;; your option) any later version.
|
||
;;;
|
||
;;; GNU Guix is distributed in the hope that it will be useful, but
|
||
;;; WITHOUT ANY WARRANTY; without even the implied warranty of
|
||
;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||
;;; GNU General Public License for more details.
|
||
;;;
|
||
;;; You should have received a copy of the GNU General Public License
|
||
;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
|
||
|
||
(define-module (gnu packages bioinformatics)
|
||
#:use-module ((guix licenses) #:prefix license:)
|
||
#:use-module (guix packages)
|
||
#:use-module (guix utils)
|
||
#:use-module (guix download)
|
||
#:use-module (guix git-download)
|
||
#:use-module (guix hg-download)
|
||
#:use-module (guix build-system ant)
|
||
#:use-module (guix build-system gnu)
|
||
#:use-module (guix build-system cmake)
|
||
#:use-module (guix build-system perl)
|
||
#:use-module (guix build-system python)
|
||
#:use-module (guix build-system r)
|
||
#:use-module (guix build-system ruby)
|
||
#:use-module (guix build-system trivial)
|
||
#:use-module (gnu packages)
|
||
#:use-module (gnu packages autotools)
|
||
#:use-module (gnu packages algebra)
|
||
#:use-module (gnu packages base)
|
||
#:use-module (gnu packages bison)
|
||
#:use-module (gnu packages boost)
|
||
#:use-module (gnu packages compression)
|
||
#:use-module (gnu packages cpio)
|
||
#:use-module (gnu packages curl)
|
||
#:use-module (gnu packages documentation)
|
||
#:use-module (gnu packages datastructures)
|
||
#:use-module (gnu packages file)
|
||
#:use-module (gnu packages gawk)
|
||
#:use-module (gnu packages gcc)
|
||
#:use-module (gnu packages gd)
|
||
#:use-module (gnu packages gtk)
|
||
#:use-module (gnu packages glib)
|
||
#:use-module (gnu packages groff)
|
||
#:use-module (gnu packages image)
|
||
#:use-module (gnu packages imagemagick)
|
||
#:use-module (gnu packages java)
|
||
#:use-module (gnu packages linux)
|
||
#:use-module (gnu packages logging)
|
||
#:use-module (gnu packages machine-learning)
|
||
#:use-module (gnu packages man)
|
||
#:use-module (gnu packages maths)
|
||
#:use-module (gnu packages mpi)
|
||
#:use-module (gnu packages ncurses)
|
||
#:use-module (gnu packages pcre)
|
||
#:use-module (gnu packages parallel)
|
||
#:use-module (gnu packages pdf)
|
||
#:use-module (gnu packages perl)
|
||
#:use-module (gnu packages pkg-config)
|
||
#:use-module (gnu packages popt)
|
||
#:use-module (gnu packages protobuf)
|
||
#:use-module (gnu packages python)
|
||
#:use-module (gnu packages readline)
|
||
#:use-module (gnu packages ruby)
|
||
#:use-module (gnu packages statistics)
|
||
#:use-module (gnu packages tbb)
|
||
#:use-module (gnu packages tex)
|
||
#:use-module (gnu packages texinfo)
|
||
#:use-module (gnu packages textutils)
|
||
#:use-module (gnu packages time)
|
||
#:use-module (gnu packages tls)
|
||
#:use-module (gnu packages vim)
|
||
#:use-module (gnu packages web)
|
||
#:use-module (gnu packages xml)
|
||
#:use-module (gnu packages xorg)
|
||
#:use-module (gnu packages zip)
|
||
#:use-module (srfi srfi-1))
|
||
|
||
(define-public aragorn
|
||
(package
|
||
(name "aragorn")
|
||
(version "1.2.36")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
|
||
version ".tgz"))
|
||
(sha256
|
||
(base32
|
||
"1dg7jlz1qpqy88igjxd6ncs11ccsirb36qv1z01a0np4i4jh61mb"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; there are no tests
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'build
|
||
(lambda _
|
||
(zero? (system* "gcc"
|
||
"-O3"
|
||
"-ffast-math"
|
||
"-finline-functions"
|
||
"-o"
|
||
"aragorn"
|
||
(string-append "aragorn" ,version ".c")))))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(man (string-append out "/share/man/man1")))
|
||
(mkdir-p bin)
|
||
(copy-file "aragorn"
|
||
(string-append bin "/aragorn"))
|
||
(mkdir-p man)
|
||
(copy-file "aragorn.1"
|
||
(string-append man "/aragorn.1")))
|
||
#t)))))
|
||
(home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
|
||
(synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
|
||
(description
|
||
"Aragorn identifies transfer RNA, mitochondrial RNA and
|
||
transfer-messenger RNA from nucleotide sequences, based on homology to known
|
||
tRNA consensus sequences and RNA structure. It also outputs the secondary
|
||
structure of the predicted RNA.")
|
||
(license license:gpl2)))
|
||
|
||
(define-public bamm
|
||
(package
|
||
(name "bamm")
|
||
(version "1.7.2a")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; BamM is not available on pypi.
|
||
(uri (string-append
|
||
"https://github.com/Ecogenomics/BamM/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0nb20yml39f8fh0cahpjywsl91irh9yskig549c17xkrkl74czsq"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
`(begin
|
||
;; Delete bundled htslib.
|
||
(delete-file-recursively "c/htslib-1.3.1")
|
||
#t))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; BamM is Python 2 only.
|
||
;; Do not use bundled libhts. Do use the bundled libcfu because it has
|
||
;; been modified from its original form.
|
||
#:configure-flags
|
||
(let ((htslib (assoc-ref %build-inputs "htslib")))
|
||
(list "--with-libhts-lib" (string-append htslib "/lib")
|
||
"--with-libhts-inc" (string-append htslib "/include/htslib")))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'autogen
|
||
(lambda _
|
||
(with-directory-excursion "c"
|
||
(let ((sh (which "sh")))
|
||
;; Use autogen so that 'configure' works.
|
||
(substitute* "autogen.sh" (("/bin/sh") sh))
|
||
(setenv "CONFIG_SHELL" sh)
|
||
(substitute* "configure" (("/bin/sh") sh))
|
||
(zero? (system* "./autogen.sh"))))))
|
||
(delete 'build)
|
||
;; Run tests after installation so compilation only happens once.
|
||
(delete 'check)
|
||
(add-after 'install 'wrap-executable
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(path (getenv "PATH")))
|
||
(wrap-program (string-append out "/bin/bamm")
|
||
`("PATH" ":" prefix (,path))))
|
||
#t))
|
||
(add-after 'wrap-executable 'post-install-check
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(setenv "PATH"
|
||
(string-append (assoc-ref outputs "out")
|
||
"/bin:"
|
||
(getenv "PATH")))
|
||
(setenv "PYTHONPATH"
|
||
(string-append
|
||
(assoc-ref outputs "out")
|
||
"/lib/python"
|
||
(string-take (string-take-right
|
||
(assoc-ref inputs "python") 5) 3)
|
||
"/site-packages:"
|
||
(getenv "PYTHONPATH")))
|
||
;; There are 2 errors printed, but they are safe to ignore:
|
||
;; 1) [E::hts_open_format] fail to open file ...
|
||
;; 2) samtools view: failed to open ...
|
||
(zero? (system* "nosetests")))))))
|
||
(native-inputs
|
||
`(("autoconf" ,autoconf)
|
||
("automake" ,automake)
|
||
("libtool" ,libtool)
|
||
("zlib" ,zlib)
|
||
("python-nose" ,python2-nose)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(inputs
|
||
`(("htslib" ,htslib)
|
||
("samtools" ,samtools)
|
||
("bwa" ,bwa)
|
||
("grep" ,grep)
|
||
("sed" ,sed)
|
||
("coreutils" ,coreutils)))
|
||
(propagated-inputs
|
||
`(("python-numpy" ,python2-numpy)))
|
||
(home-page "http://ecogenomics.github.io/BamM/")
|
||
(synopsis "Metagenomics-focused BAM file manipulator")
|
||
(description
|
||
"BamM is a C library, wrapped in python, to efficiently generate and
|
||
parse BAM files, specifically for the analysis of metagenomic data. For
|
||
instance, it implements several methods to assess contig-wise read coverage.")
|
||
(license license:lgpl3+)))
|
||
|
||
(define-public bamtools
|
||
(package
|
||
(name "bamtools")
|
||
(version "2.3.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/pezmaster31/bamtools/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-before
|
||
'configure 'set-ldflags
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(setenv "LDFLAGS"
|
||
(string-append
|
||
"-Wl,-rpath="
|
||
(assoc-ref outputs "out") "/lib/bamtools")))))))
|
||
(inputs `(("zlib" ,zlib)))
|
||
(home-page "https://github.com/pezmaster31/bamtools")
|
||
(synopsis "C++ API and command-line toolkit for working with BAM data")
|
||
(description
|
||
"BamTools provides both a C++ API and a command-line toolkit for handling
|
||
BAM files.")
|
||
(license license:expat)))
|
||
|
||
(define-public bedops
|
||
(package
|
||
(name "bedops")
|
||
(version "2.4.14")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/bedops/bedops/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f
|
||
#:make-flags (list (string-append "BINDIR=" %output "/bin"))
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'unpack-tarballs
|
||
(lambda _
|
||
;; FIXME: Bedops includes tarballs of minimally patched upstream
|
||
;; libraries jansson, zlib, and bzip2. We cannot just use stock
|
||
;; libraries because at least one of the libraries (zlib) is
|
||
;; patched to add a C++ function definition (deflateInit2cpp).
|
||
;; Until the Bedops developers offer a way to link against system
|
||
;; libraries we have to build the in-tree copies of these three
|
||
;; libraries.
|
||
|
||
;; See upstream discussion:
|
||
;; https://github.com/bedops/bedops/issues/124
|
||
|
||
;; Unpack the tarballs to benefit from shebang patching.
|
||
(with-directory-excursion "third-party"
|
||
(and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
|
||
(zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
|
||
(zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
|
||
;; Disable unpacking of tarballs in Makefile.
|
||
(substitute* "system.mk/Makefile.linux"
|
||
(("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
|
||
(("\\./configure") "CONFIG_SHELL=bash ./configure"))
|
||
(substitute* "third-party/zlib-1.2.7/Makefile.in"
|
||
(("^SHELL=.*$") "SHELL=bash\n")))
|
||
(alist-delete 'configure %standard-phases))))
|
||
(home-page "https://github.com/bedops/bedops")
|
||
(synopsis "Tools for high-performance genomic feature operations")
|
||
(description
|
||
"BEDOPS is a suite of tools to address common questions raised in genomic
|
||
studies---mostly with regard to overlap and proximity relationships between
|
||
data sets. It aims to be scalable and flexible, facilitating the efficient
|
||
and accurate analysis and management of large-scale genomic data.
|
||
|
||
BEDOPS provides tools that perform highly efficient and scalable Boolean and
|
||
other set operations, statistical calculations, archiving, conversion and
|
||
other management of genomic data of arbitrary scale. Tasks can be easily
|
||
split by chromosome for distributing whole-genome analyses across a
|
||
computational cluster.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public bedtools
|
||
(package
|
||
(name "bedtools")
|
||
(version "2.26.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
|
||
(build-system gnu-build-system)
|
||
(native-inputs `(("python" ,python-2)))
|
||
(inputs `(("samtools" ,samtools)
|
||
("zlib" ,zlib)))
|
||
(arguments
|
||
'(#:test-target "test"
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
|
||
(for-each (lambda (file)
|
||
(install-file file bin))
|
||
(find-files "bin" ".*")))
|
||
#t)))))
|
||
(home-page "https://github.com/arq5x/bedtools2")
|
||
(synopsis "Tools for genome analysis and arithmetic")
|
||
(description
|
||
"Collectively, the bedtools utilities are a swiss-army knife of tools for
|
||
a wide-range of genomics analysis tasks. The most widely-used tools enable
|
||
genome arithmetic: that is, set theory on the genome. For example, bedtools
|
||
allows one to intersect, merge, count, complement, and shuffle genomic
|
||
intervals from multiple files in widely-used genomic file formats such as BAM,
|
||
BED, GFF/GTF, VCF.")
|
||
(license license:gpl2)))
|
||
|
||
;; Later releases of bedtools produce files with more columns than
|
||
;; what Ribotaper expects.
|
||
(define-public bedtools-2.18
|
||
(package (inherit bedtools)
|
||
(name "bedtools")
|
||
(version "2.18.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/arq5x/bedtools2/"
|
||
"archive/v" version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
|
||
|
||
(define-public ribotaper
|
||
(package
|
||
(name "ribotaper")
|
||
(version "1.3.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://ohlerlab.mdc-berlin.de/"
|
||
"files/RiboTaper/RiboTaper_Version_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
|
||
(build-system gnu-build-system)
|
||
(inputs
|
||
`(("bedtools" ,bedtools-2.18)
|
||
("samtools" ,samtools-0.1)
|
||
("r" ,r)
|
||
("r-foreach" ,r-foreach)
|
||
("r-xnomial" ,r-xnomial)
|
||
("r-domc" ,r-domc)
|
||
("r-multitaper" ,r-multitaper)
|
||
("r-seqinr" ,r-seqinr)))
|
||
(home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
|
||
(synopsis "Define translated ORFs using ribosome profiling data")
|
||
(description
|
||
"Ribotaper is a method for defining translated @dfn{open reading
|
||
frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
|
||
provides the Ribotaper pipeline.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public bioawk
|
||
(package
|
||
(name "bioawk")
|
||
(version "1.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/lh3/bioawk/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
|
||
(build-system gnu-build-system)
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("bison" ,bison)))
|
||
(arguments
|
||
`(#:tests? #f ; There are no tests to run.
|
||
;; Bison must generate files, before other targets can build.
|
||
#:parallel-build? #f
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure) ; There is no configure phase.
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(man (string-append out "/share/man/man1")))
|
||
(mkdir-p man)
|
||
(copy-file "awk.1" (string-append man "/bioawk.1"))
|
||
(install-file "bioawk" bin)))))))
|
||
(home-page "https://github.com/lh3/bioawk")
|
||
(synopsis "AWK with bioinformatics extensions")
|
||
(description "Bioawk is an extension to Brian Kernighan's awk, adding the
|
||
support of several common biological data formats, including optionally gzip'ed
|
||
BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
|
||
also adds a few built-in functions and a command line option to use TAB as the
|
||
input/output delimiter. When the new functionality is not used, bioawk is
|
||
intended to behave exactly the same as the original BWK awk.")
|
||
(license license:x11)))
|
||
|
||
(define-public python2-pybedtools
|
||
(package
|
||
(name "python2-pybedtools")
|
||
(version "0.6.9")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
|
||
(build-system python-build-system)
|
||
(arguments `(#:python ,python-2)) ; no Python 3 support
|
||
(inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-matplotlib" ,python2-matplotlib)))
|
||
(propagated-inputs
|
||
`(("bedtools" ,bedtools)
|
||
("samtools" ,samtools)))
|
||
(native-inputs
|
||
`(("python-pyyaml" ,python2-pyyaml)
|
||
("python-nose" ,python2-nose)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "https://pythonhosted.org/pybedtools/")
|
||
(synopsis "Python wrapper for BEDtools programs")
|
||
(description
|
||
"pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
|
||
which are widely used for genomic interval manipulation or \"genome algebra\".
|
||
pybedtools extends BEDTools by offering feature-level manipulations from with
|
||
Python.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public python-biom-format
|
||
(package
|
||
(name "python-biom-format")
|
||
(version "2.1.5")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
;; Use GitHub as source because PyPI distribution does not contain
|
||
;; test data: https://github.com/biocore/biom-format/issues/693
|
||
(uri (string-append "https://github.com/biocore/biom-format/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
|
||
(build-system python-build-system)
|
||
(inputs
|
||
`(("python-numpy" ,python-numpy)
|
||
("python-scipy" ,python-scipy)
|
||
("python-future" ,python-future)
|
||
("python-click" ,python-click)
|
||
("python-h5py" ,python-h5py)))
|
||
(home-page "http://www.biom-format.org")
|
||
(synopsis "Biological Observation Matrix (BIOM) format utilities")
|
||
(description
|
||
"The BIOM file format is designed to be a general-use format for
|
||
representing counts of observations e.g. operational taxonomic units, KEGG
|
||
orthology groups or lipid types, in one or more biological samples
|
||
e.g. microbiome samples, genomes, metagenomes.")
|
||
(license license:bsd-3)
|
||
(properties `((python2-variant . ,(delay python2-biom-format))))))
|
||
|
||
(define-public python2-biom-format
|
||
(let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
|
||
(package
|
||
(inherit base)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
;; Do not require the unmaintained pyqi library.
|
||
(add-after 'unpack 'remove-pyqi
|
||
(lambda _
|
||
(substitute* "setup.py"
|
||
(("install_requires.append\\(\"pyqi\"\\)") "pass"))
|
||
#t)))
|
||
,@(package-arguments base)))
|
||
(native-inputs `(("python2-setuptools" ,python2-setuptools)
|
||
,@(package-native-inputs base))))))
|
||
|
||
(define-public bioperl-minimal
|
||
(let* ((inputs `(("perl-module-build" ,perl-module-build)
|
||
("perl-data-stag" ,perl-data-stag)
|
||
("perl-libwww" ,perl-libwww)
|
||
("perl-uri" ,perl-uri)))
|
||
(transitive-inputs
|
||
(map (compose package-name cadr)
|
||
(delete-duplicates
|
||
(concatenate
|
||
(map (compose package-transitive-target-inputs cadr) inputs))))))
|
||
(package
|
||
(name "bioperl-minimal")
|
||
(version "1.6.924")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://cpan/authors/id/C/CJ/CJFIELDS/BioPerl-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1l3npcvvvwjlhkna9dndpfv1hklhrgva013kw96m0n1wpd37ask1"))))
|
||
(build-system perl-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after
|
||
'install 'wrap-programs
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
;; Make sure all executables in "bin" find the required Perl
|
||
;; modules at runtime. As the PERL5LIB variable contains also
|
||
;; the paths of native inputs, we pick the transitive target
|
||
;; inputs from %build-inputs.
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin/"))
|
||
(path (string-join
|
||
(cons (string-append out "/lib/perl5/site_perl")
|
||
(map (lambda (name)
|
||
(assoc-ref %build-inputs name))
|
||
',transitive-inputs))
|
||
":")))
|
||
(for-each (lambda (file)
|
||
(wrap-program file
|
||
`("PERL5LIB" ":" prefix (,path))))
|
||
(find-files bin "\\.pl$"))
|
||
#t))))))
|
||
(inputs inputs)
|
||
(native-inputs
|
||
`(("perl-test-most" ,perl-test-most)))
|
||
(home-page "http://search.cpan.org/dist/BioPerl")
|
||
(synopsis "Bioinformatics toolkit")
|
||
(description
|
||
"BioPerl is the product of a community effort to produce Perl code which
|
||
is useful in biology. Examples include Sequence objects, Alignment objects
|
||
and database searching objects. These objects not only do what they are
|
||
advertised to do in the documentation, but they also interact - Alignment
|
||
objects are made from the Sequence objects, Sequence objects have access to
|
||
Annotation and SeqFeature objects and databases, Blast objects can be
|
||
converted to Alignment objects, and so on. This means that the objects
|
||
provide a coordinated and extensible framework to do computational biology.")
|
||
(license (package-license perl)))))
|
||
|
||
(define-public python-biopython
|
||
(package
|
||
(name "python-biopython")
|
||
(version "1.66")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; use PyPi rather than biopython.org to ease updating
|
||
(uri (pypi-uri "biopython" version))
|
||
(sha256
|
||
(base32
|
||
"1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))
|
||
(build-system python-build-system)
|
||
(inputs
|
||
`(("python-numpy" ,python-numpy)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://biopython.org/")
|
||
(synopsis "Tools for biological computation in Python")
|
||
(description
|
||
"Biopython is a set of tools for biological computation including parsers
|
||
for bioinformatics files into Python data structures; interfaces to common
|
||
bioinformatics programs; a standard sequence class and tools for performing
|
||
common operations on them; code to perform data classification; code for
|
||
dealing with alignments; code making it easy to split up parallelizable tasks
|
||
into separate processes; and more.")
|
||
(license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
|
||
|
||
(define-public python2-biopython
|
||
(package (inherit (package-with-python2 python-biopython))
|
||
(inputs
|
||
`(("python2-numpy" ,python2-numpy)))))
|
||
|
||
(define-public bpp-core
|
||
;; The last release was in 2014 and the recommended way to install from source
|
||
;; is to clone the git repository, so we do this.
|
||
;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
|
||
(let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
|
||
(package
|
||
(name "bpp-core")
|
||
(version (string-append "2.2.0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "http://biopp.univ-montp2.fr/git/bpp-core")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f))
|
||
(inputs
|
||
`(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
|
||
; compile all of the bpp packages with GCC 5.
|
||
(home-page "http://biopp.univ-montp2.fr")
|
||
(synopsis "C++ libraries for Bioinformatics")
|
||
(description
|
||
"Bio++ is a set of C++ libraries for Bioinformatics, including sequence
|
||
analysis, phylogenetics, molecular evolution and population genetics. It is
|
||
Object Oriented and is designed to be both easy to use and computer efficient.
|
||
Bio++ intends to help programmers to write computer expensive programs, by
|
||
providing them a set of re-usable tools.")
|
||
(license license:cecill-c))))
|
||
|
||
(define-public bpp-phyl
|
||
;; The last release was in 2014 and the recommended way to install from source
|
||
;; is to clone the git repository, so we do this.
|
||
;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
|
||
(let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
|
||
(package
|
||
(name "bpp-phyl")
|
||
(version (string-append "2.2.0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "http://biopp.univ-montp2.fr/git/bpp-phyl")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f
|
||
;; If out-of-source, test data is not copied into the build directory
|
||
;; so the tests fail.
|
||
#:out-of-source? #f))
|
||
(inputs
|
||
`(("bpp-core" ,bpp-core)
|
||
("bpp-seq" ,bpp-seq)
|
||
;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
|
||
;; modern GCC.
|
||
("gcc" ,gcc-5)))
|
||
(home-page "http://biopp.univ-montp2.fr")
|
||
(synopsis "Bio++ phylogenetic Library")
|
||
(description
|
||
"Bio++ is a set of C++ libraries for Bioinformatics, including sequence
|
||
analysis, phylogenetics, molecular evolution and population genetics. This
|
||
library provides phylogenetics-related modules.")
|
||
(license license:cecill-c))))
|
||
|
||
(define-public bpp-popgen
|
||
;; The last release was in 2014 and the recommended way to install from source
|
||
;; is to clone the git repository, so we do this.
|
||
;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
|
||
(let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
|
||
(package
|
||
(name "bpp-popgen")
|
||
(version (string-append "2.2.0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "http://biopp.univ-montp2.fr/git/bpp-popgen")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f
|
||
#:tests? #f)) ; There are no tests.
|
||
(inputs
|
||
`(("bpp-core" ,bpp-core)
|
||
("bpp-seq" ,bpp-seq)
|
||
("gcc" ,gcc-5)))
|
||
(home-page "http://biopp.univ-montp2.fr")
|
||
(synopsis "Bio++ population genetics library")
|
||
(description
|
||
"Bio++ is a set of C++ libraries for Bioinformatics, including sequence
|
||
analysis, phylogenetics, molecular evolution and population genetics. This
|
||
library provides population genetics-related modules.")
|
||
(license license:cecill-c))))
|
||
|
||
(define-public bpp-seq
|
||
;; The last release was in 2014 and the recommended way to install from source
|
||
;; is to clone the git repository, so we do this.
|
||
;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
|
||
(let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
|
||
(package
|
||
(name "bpp-seq")
|
||
(version (string-append "2.2.0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "http://biopp.univ-montp2.fr/git/bpp-seq")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f
|
||
;; If out-of-source, test data is not copied into the build directory
|
||
;; so the tests fail.
|
||
#:out-of-source? #f))
|
||
(inputs
|
||
`(("bpp-core" ,bpp-core)
|
||
("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
|
||
(home-page "http://biopp.univ-montp2.fr")
|
||
(synopsis "Bio++ sequence library")
|
||
(description
|
||
"Bio++ is a set of C++ libraries for Bioinformatics, including sequence
|
||
analysis, phylogenetics, molecular evolution and population genetics. This
|
||
library provides sequence-related modules.")
|
||
(license license:cecill-c))))
|
||
|
||
(define-public bppsuite
|
||
;; The last release was in 2014 and the recommended way to install from source
|
||
;; is to clone the git repository, so we do this.
|
||
;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
|
||
(let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
|
||
(package
|
||
(name "bppsuite")
|
||
(version (string-append "2.2.0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "http://biopp.univ-montp2.fr/git/bppsuite")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f
|
||
#:tests? #f)) ; There are no tests.
|
||
(native-inputs
|
||
`(("groff" ,groff)
|
||
("man-db" ,man-db)
|
||
("texinfo" ,texinfo)))
|
||
(inputs
|
||
`(("bpp-core" ,bpp-core)
|
||
("bpp-seq" ,bpp-seq)
|
||
("bpp-phyl" ,bpp-phyl)
|
||
("bpp-phyl" ,bpp-popgen)
|
||
("gcc" ,gcc-5)))
|
||
(home-page "http://biopp.univ-montp2.fr")
|
||
(synopsis "Bioinformatics tools written with the Bio++ libraries")
|
||
(description
|
||
"Bio++ is a set of C++ libraries for Bioinformatics, including sequence
|
||
analysis, phylogenetics, molecular evolution and population genetics. This
|
||
package provides command line tools using the Bio++ library.")
|
||
(license license:cecill-c))))
|
||
|
||
(define-public blast+
|
||
(package
|
||
(name "blast+")
|
||
(version "2.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
|
||
version "/ncbi-blast-" version "+-src.tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; Remove bundled bzip2 and zlib
|
||
(delete-file-recursively "c++/src/util/compress/bzip2")
|
||
(delete-file-recursively "c++/src/util/compress/zlib")
|
||
(substitute* "c++/src/util/compress/Makefile.in"
|
||
(("bzip2 zlib api") "api"))
|
||
;; Remove useless msbuild directory
|
||
(delete-file-recursively
|
||
"c++/src/build-system/project_tree_builder/msbuild")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(;; There are three(!) tests for this massive library, and all fail with
|
||
;; "unparsable timing stats".
|
||
;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
|
||
;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
|
||
;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
|
||
#:tests? #f
|
||
#:out-of-source? #t
|
||
#:parallel-build? #f ; not supported
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-before
|
||
'configure 'set-HOME
|
||
;; $HOME needs to be set at some point during the configure phase
|
||
(lambda _ (setenv "HOME" "/tmp") #t))
|
||
(add-after
|
||
'unpack 'enter-dir
|
||
(lambda _ (chdir "c++") #t))
|
||
(add-after
|
||
'enter-dir 'fix-build-system
|
||
(lambda _
|
||
(define (which* cmd)
|
||
(cond ((string=? cmd "date")
|
||
;; make call to "date" deterministic
|
||
"date -d @0")
|
||
((which cmd)
|
||
=> identity)
|
||
(else
|
||
(format (current-error-port)
|
||
"WARNING: Unable to find absolute path for ~s~%"
|
||
cmd)
|
||
#f)))
|
||
|
||
;; Rewrite hardcoded paths to various tools
|
||
(substitute* (append '("src/build-system/configure.ac"
|
||
"src/build-system/configure"
|
||
"scripts/common/impl/if_diff.sh"
|
||
"scripts/common/impl/run_with_lock.sh"
|
||
"src/build-system/Makefile.configurables.real"
|
||
"src/build-system/Makefile.in.top"
|
||
"src/build-system/Makefile.meta.gmake=no"
|
||
"src/build-system/Makefile.meta.in"
|
||
"src/build-system/Makefile.meta_l"
|
||
"src/build-system/Makefile.meta_p"
|
||
"src/build-system/Makefile.meta_r"
|
||
"src/build-system/Makefile.mk.in"
|
||
"src/build-system/Makefile.requirements"
|
||
"src/build-system/Makefile.rules_with_autodep.in")
|
||
(find-files "scripts/common/check" "\\.sh$"))
|
||
(("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
|
||
(or (which* cmd) all)))
|
||
|
||
(substitute* (find-files "src/build-system" "^config.*")
|
||
(("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
|
||
(("^PATH=.*") ""))
|
||
|
||
;; rewrite "/var/tmp" in check script
|
||
(substitute* "scripts/common/check/check_make_unix.sh"
|
||
(("/var/tmp") "/tmp"))
|
||
|
||
;; do not reset PATH
|
||
(substitute* (find-files "scripts/common/impl/" "\\.sh$")
|
||
(("^ *PATH=.*") "")
|
||
(("action=/bin/") "action=")
|
||
(("export PATH") ":"))
|
||
#t))
|
||
(replace
|
||
'configure
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out"))
|
||
(lib (string-append (assoc-ref outputs "lib") "/lib"))
|
||
(include (string-append (assoc-ref outputs "include")
|
||
"/include/ncbi-tools++")))
|
||
;; The 'configure' script doesn't recognize things like
|
||
;; '--enable-fast-install'.
|
||
(zero? (system* "./configure.orig"
|
||
(string-append "--with-build-root=" (getcwd) "/build")
|
||
(string-append "--prefix=" out)
|
||
(string-append "--libdir=" lib)
|
||
(string-append "--includedir=" include)
|
||
(string-append "--with-bz2="
|
||
(assoc-ref inputs "bzip2"))
|
||
(string-append "--with-z="
|
||
(assoc-ref inputs "zlib"))
|
||
;; Each library is built twice by default, once
|
||
;; with "-static" in its name, and again
|
||
;; without.
|
||
"--without-static"
|
||
"--with-dll"))))))))
|
||
(outputs '("out" ; 19 MB
|
||
"lib" ; 203 MB
|
||
"include")) ; 32 MB
|
||
(inputs
|
||
`(("bzip2" ,bzip2)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("cpio" ,cpio)))
|
||
(home-page "http://blast.ncbi.nlm.nih.gov")
|
||
(synopsis "Basic local alignment search tool")
|
||
(description
|
||
"BLAST is a popular method of performing a DNA or protein sequence
|
||
similarity search, using heuristics to produce results quickly. It also
|
||
calculates an “expect value” that estimates how many matches would have
|
||
occurred at a given score by chance, which can aid a user in judging how much
|
||
confidence to have in an alignment.")
|
||
;; Most of the sources are in the public domain, with the following
|
||
;; exceptions:
|
||
;; * Expat:
|
||
;; * ./c++/include/util/bitset/
|
||
;; * ./c++/src/html/ncbi_menu*.js
|
||
;; * Boost license:
|
||
;; * ./c++/include/util/impl/floating_point_comparison.hpp
|
||
;; * LGPL 2+:
|
||
;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
|
||
;; * ASL 2.0:
|
||
;; * ./c++/src/corelib/teamcity_*
|
||
(license (list license:public-domain
|
||
license:expat
|
||
license:boost1.0
|
||
license:lgpl2.0+
|
||
license:asl2.0))))
|
||
|
||
(define-public bless
|
||
(package
|
||
(name "bless")
|
||
(version "1p02")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://sourceforge/bless-ec/bless.v"
|
||
version ".tgz"))
|
||
(sha256
|
||
(base32
|
||
"0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
`(begin
|
||
;; Remove bundled boost, pigz, zlib, and .git directory
|
||
;; FIXME: also remove bundled sources for murmurhash3 and
|
||
;; kmc once packaged.
|
||
(delete-file-recursively "boost")
|
||
(delete-file-recursively "pigz")
|
||
(delete-file-recursively "google-sparsehash")
|
||
(delete-file-recursively "zlib")
|
||
(delete-file-recursively ".git")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f ;no "check" target
|
||
#:make-flags
|
||
(list (string-append "ZLIB="
|
||
(assoc-ref %build-inputs "zlib")
|
||
"/lib/libz.a")
|
||
(string-append "LDFLAGS="
|
||
(string-join '("-lboost_filesystem"
|
||
"-lboost_system"
|
||
"-lboost_iostreams"
|
||
"-lz"
|
||
"-fopenmp"
|
||
"-std=c++11"))))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'do-not-build-bundled-pigz
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(substitute* "Makefile"
|
||
(("cd pigz/pigz-2.3.3; make") ""))
|
||
#t))
|
||
(add-after 'unpack 'patch-paths-to-executables
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(substitute* "parse_args.cpp"
|
||
(("kmc_binary = .*")
|
||
(string-append "kmc_binary = \""
|
||
(assoc-ref outputs "out")
|
||
"/bin/kmc\";"))
|
||
(("pigz_binary = .*")
|
||
(string-append "pigz_binary = \""
|
||
(assoc-ref inputs "pigz")
|
||
"/bin/pigz\";")))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
|
||
(for-each (lambda (file)
|
||
(install-file file bin))
|
||
'("bless" "kmc/bin/kmc"))
|
||
#t)))
|
||
(delete 'configure))))
|
||
(native-inputs
|
||
`(("perl" ,perl)))
|
||
(inputs
|
||
`(("openmpi" ,openmpi)
|
||
("boost" ,boost)
|
||
("sparsehash" ,sparsehash)
|
||
("pigz" ,pigz)
|
||
("zlib" ,zlib)))
|
||
(supported-systems '("x86_64-linux"))
|
||
(home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
|
||
(synopsis "Bloom-filter-based error correction tool for NGS reads")
|
||
(description
|
||
"@dfn{Bloom-filter-based error correction solution for high-throughput
|
||
sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
|
||
correction tool for genomic reads produced by @dfn{Next-generation
|
||
sequencing} (NGS). BLESS produces accurate correction results with much less
|
||
memory compared with previous solutions and is also able to tolerate a higher
|
||
false-positive rate. BLESS can extend reads like DNA assemblers to correct
|
||
errors at the end of reads.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public bowtie
|
||
(package
|
||
(name "bowtie")
|
||
(version "2.2.6")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1ssfvymxfrap6f9pf86s9bvsbqdgka4abr2r7j3mgr4w1l289m86"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(substitute* "Makefile"
|
||
;; replace BUILD_HOST and BUILD_TIME for deterministic build
|
||
(("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
|
||
(("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
|
||
(build-system gnu-build-system)
|
||
(inputs `(("perl" ,perl)
|
||
("perl-clone" ,perl-clone)
|
||
("perl-test-deep" ,perl-test-deep)
|
||
("perl-test-simple" ,perl-test-simple)
|
||
("python" ,python-2)
|
||
("tbb" ,tbb)))
|
||
(arguments
|
||
'(#:make-flags
|
||
(list "allall"
|
||
"WITH_TBB=1"
|
||
(string-append "prefix=" (assoc-ref %outputs "out")))
|
||
#:phases
|
||
(alist-delete
|
||
'configure
|
||
(alist-replace
|
||
'check
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(system* "perl"
|
||
"scripts/test/simple_tests.pl"
|
||
"--bowtie2=./bowtie2"
|
||
"--bowtie2-build=./bowtie2-build"))
|
||
%standard-phases))))
|
||
(home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
|
||
(synopsis "Fast and sensitive nucleotide sequence read aligner")
|
||
(description
|
||
"Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
|
||
reads to long reference sequences. It is particularly good at aligning reads
|
||
of about 50 up to 100s or 1,000s of characters, and particularly good at
|
||
aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
|
||
genome with an FM Index to keep its memory footprint small: for the human
|
||
genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
|
||
gapped, local, and paired-end alignment modes.")
|
||
(supported-systems '("x86_64-linux"))
|
||
(license license:gpl3+)))
|
||
|
||
(define-public tophat
|
||
(package
|
||
(name "tophat")
|
||
(version "2.1.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://ccb.jhu.edu/software/tophat/downloads/tophat-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
|
||
(patches (search-patches "tophat-build-with-later-seqan.patch"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; Remove bundled SeqAn and samtools
|
||
(delete-file-recursively "src/SeqAn-1.3")
|
||
(delete-file-recursively "src/samtools-0.1.18")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:parallel-build? #f ; not supported
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'use-system-samtools
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(substitute* "src/Makefile.in"
|
||
(("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
|
||
(("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
|
||
(("SAMPROG = samtools_0\\.1\\.18") "")
|
||
(("\\$\\(samtools_0_1_18_SOURCES\\)") "")
|
||
(("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
|
||
(substitute* '("src/common.cpp"
|
||
"src/tophat.py")
|
||
(("samtools_0.1.18") (which "samtools")))
|
||
(substitute* '("src/common.h"
|
||
"src/bam2fastx.cpp")
|
||
(("#include \"bam.h\"") "#include <samtools/bam.h>")
|
||
(("#include \"sam.h\"") "#include <samtools/sam.h>"))
|
||
(substitute* '("src/bwt_map.h"
|
||
"src/map2gtf.h"
|
||
"src/align_status.h")
|
||
(("#include <bam.h>") "#include <samtools/bam.h>")
|
||
(("#include <sam.h>") "#include <samtools/sam.h>"))
|
||
#t)))))
|
||
(inputs
|
||
`(("boost" ,boost)
|
||
("bowtie" ,bowtie)
|
||
("samtools" ,samtools-0.1)
|
||
("ncurses" ,ncurses)
|
||
("python" ,python-2)
|
||
("perl" ,perl)
|
||
("zlib" ,zlib)
|
||
("seqan" ,seqan)))
|
||
(home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
|
||
(synopsis "Spliced read mapper for RNA-Seq data")
|
||
(description
|
||
"TopHat is a fast splice junction mapper for nucleotide sequence
|
||
reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
|
||
mammalian-sized genomes using the ultra high-throughput short read
|
||
aligner Bowtie, and then analyzes the mapping results to identify
|
||
splice junctions between exons.")
|
||
;; TopHat is released under the Boost Software License, Version 1.0
|
||
;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
|
||
(license license:boost1.0)))
|
||
|
||
(define-public bwa
|
||
(package
|
||
(name "bwa")
|
||
(version "0.7.12")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
|
||
version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(alist-replace
|
||
'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append
|
||
(assoc-ref outputs "out") "/bin"))
|
||
(doc (string-append
|
||
(assoc-ref outputs "out") "/share/doc/bwa"))
|
||
(man (string-append
|
||
(assoc-ref outputs "out") "/share/man/man1")))
|
||
(mkdir-p bin)
|
||
(mkdir-p doc)
|
||
(mkdir-p man)
|
||
(install-file "bwa" bin)
|
||
(install-file "README.md" doc)
|
||
(install-file "bwa.1" man)))
|
||
;; no "configure" script
|
||
(alist-delete 'configure %standard-phases))))
|
||
(inputs `(("zlib" ,zlib)))
|
||
;; Non-portable SSE instructions are used so building fails on platforms
|
||
;; other than x86_64.
|
||
(supported-systems '("x86_64-linux"))
|
||
(home-page "http://bio-bwa.sourceforge.net/")
|
||
(synopsis "Burrows-Wheeler sequence aligner")
|
||
(description
|
||
"BWA is a software package for mapping low-divergent sequences against a
|
||
large reference genome, such as the human genome. It consists of three
|
||
algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
|
||
designed for Illumina sequence reads up to 100bp, while the rest two for
|
||
longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
|
||
features such as long-read support and split alignment, but BWA-MEM, which is
|
||
the latest, is generally recommended for high-quality queries as it is faster
|
||
and more accurate. BWA-MEM also has better performance than BWA-backtrack for
|
||
70-100bp Illumina reads.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public bwa-pssm
|
||
(package (inherit bwa)
|
||
(name "bwa-pssm")
|
||
(version "0.5.11")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
|
||
"archive/" version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
|
||
(build-system gnu-build-system)
|
||
(inputs
|
||
`(("gdsl" ,gdsl)
|
||
("zlib" ,zlib)
|
||
("perl" ,perl)))
|
||
(home-page "http://bwa-pssm.binf.ku.dk/")
|
||
(synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
|
||
(description
|
||
"BWA-PSSM is a probabilistic short genomic sequence read aligner based on
|
||
the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
|
||
existing aligners it is fast and sensitive. Unlike most other aligners,
|
||
however, it is also adaptible in the sense that one can direct the alignment
|
||
based on known biases within the data set. It is coded as a modification of
|
||
the original BWA alignment program and shares the genome index structure as
|
||
well as many of the command line options.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public python2-bx-python
|
||
(package
|
||
(name "python2-bx-python")
|
||
(version "0.7.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/b/bx-python/bx-python-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(substitute* "setup.py"
|
||
;; remove dependency on outdated "distribute" module
|
||
(("^from distribute_setup import use_setuptools") "")
|
||
(("^use_setuptools\\(\\)") "")))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;tests fail because test data are not included
|
||
#:python ,python-2))
|
||
(inputs
|
||
`(("python-numpy" ,python2-numpy)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("python-nose" ,python2-nose)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://bitbucket.org/james_taylor/bx-python/")
|
||
(synopsis "Tools for manipulating biological data")
|
||
(description
|
||
"bx-python provides tools for manipulating biological data, particularly
|
||
multiple sequence alignments.")
|
||
(license license:expat)))
|
||
|
||
(define-public python-pysam
|
||
(package
|
||
(name "python-pysam")
|
||
(version "0.8.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "pysam" version))
|
||
(sha256
|
||
(base32
|
||
"1slx5mb94mzm5qzk52q270sab0sar95j67w1g1k452nz3s9j7krh"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; tests are excluded in the manifest
|
||
#:phases
|
||
(alist-cons-before
|
||
'build 'set-flags
|
||
(lambda _
|
||
(setenv "LDFLAGS" "-lncurses")
|
||
(setenv "CFLAGS" "-D_CURSES_LIB=1"))
|
||
%standard-phases)))
|
||
(inputs
|
||
`(("ncurses" ,ncurses)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("python-cython" ,python-cython)
|
||
("python-setuptools" ,python-setuptools)))
|
||
(home-page "https://github.com/pysam-developers/pysam")
|
||
(synopsis "Python bindings to the SAMtools C API")
|
||
(description
|
||
"Pysam is a Python module for reading and manipulating files in the
|
||
SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
|
||
also includes an interface for tabix.")
|
||
(license license:expat)))
|
||
|
||
(define-public python2-pysam
|
||
(package-with-python2 python-pysam))
|
||
|
||
(define-public python-twobitreader
|
||
(package
|
||
(name "python-twobitreader")
|
||
(version "3.1.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "twobitreader" version))
|
||
(sha256
|
||
(base32
|
||
"0y408fp6psqzwxpcpqn0wp7fr41dwz8d54wpj6j261fj5q8vs169"))))
|
||
(properties `((python2-variant . ,(delay python2-twobitreader))))
|
||
(build-system python-build-system)
|
||
(native-inputs
|
||
`(("python-sphinx" ,python-sphinx)))
|
||
(home-page "https://github.com/benjschiller/twobitreader")
|
||
(synopsis "Python library for reading .2bit files")
|
||
(description
|
||
"twobitreader is a Python library for reading .2bit files as used by the
|
||
UCSC genome browser.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public python2-twobitreader
|
||
(let ((base (package-with-python2 (strip-python2-variant python-twobitreader))))
|
||
(package
|
||
(inherit base)
|
||
(native-inputs `(("python2-setuptools" ,python2-setuptools)
|
||
,@(package-native-inputs base))))))
|
||
|
||
(define-public python-plastid
|
||
(package
|
||
(name "python-plastid")
|
||
(version "0.4.5")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "plastid" version))
|
||
(sha256
|
||
(base32
|
||
"1nhxw8a5gn9as58i2ih52c5cjwj48ik418pzsjwph3s66mmy9yvq"))))
|
||
(properties `((python2-variant . ,(delay python2-plastid))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
;; Some test files are not included.
|
||
`(#:tests? #f))
|
||
(propagated-inputs
|
||
`(("python-numpy" ,python-numpy)
|
||
("python-scipy" ,python-scipy)
|
||
("python-pandas" ,python-pandas)
|
||
("python-pysam" ,python-pysam)
|
||
("python-matplotlib" ,python-matplotlib)
|
||
("python-biopython" ,python-biopython)
|
||
("python-twobitreader" ,python-twobitreader)))
|
||
(native-inputs
|
||
`(("python-cython" ,python-cython)
|
||
("python-nose" ,python-nose)))
|
||
(home-page "https://github.com/joshuagryphon/plastid")
|
||
(synopsis "Python library for genomic analysis")
|
||
(description
|
||
"plastid is a Python library for genomic analysis – in particular,
|
||
high-throughput sequencing data – with an emphasis on simplicity.")
|
||
(license license:bsd-3)))
|
||
|
||
(define-public python2-plastid
|
||
(let ((base (package-with-python2 (strip-python2-variant python-plastid))))
|
||
(package
|
||
(inherit base)
|
||
;; setuptools is required at runtime
|
||
(propagated-inputs `(("python2-setuptools" ,python2-setuptools)
|
||
,@(package-propagated-inputs base))))))
|
||
|
||
(define-public cd-hit
|
||
(package
|
||
(name "cd-hit")
|
||
(version "4.6.5")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/weizhongli/cdhit"
|
||
"/releases/download/V" version
|
||
"/cd-hit-v" version "-2016-0304.tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; there are no tests
|
||
#:make-flags
|
||
;; Executables are copied directly to the PREFIX.
|
||
(list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; No "configure" script
|
||
(delete 'configure)
|
||
;; Remove sources of non-determinism
|
||
(add-after 'unpack 'be-timeless
|
||
(lambda _
|
||
(substitute* "cdhit-utility.c++"
|
||
((" \\(built on \" __DATE__ \"\\)") ""))
|
||
(substitute* "cdhit-common.c++"
|
||
(("__DATE__") "\"0\"")
|
||
(("\", %s, \" __TIME__ \"\\\\n\", date") ""))
|
||
#t))
|
||
;; The "install" target does not create the target directory
|
||
(add-before 'install 'create-target-dir
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
|
||
#t)))))
|
||
(inputs
|
||
`(("perl" ,perl)))
|
||
(home-page "http://weizhongli-lab.org/cd-hit/")
|
||
(synopsis "Cluster and compare protein or nucleotide sequences")
|
||
(description
|
||
"CD-HIT is a program for clustering and comparing protein or nucleotide
|
||
sequences. CD-HIT is designed to be fast and handle extremely large
|
||
databases.")
|
||
;; The manual says: "It can be copied under the GNU General Public License
|
||
;; version 2 (GPLv2)."
|
||
(license license:gpl2)))
|
||
|
||
(define-public clipper
|
||
(package
|
||
(name "clipper")
|
||
(version "0.3.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/YeoLab/clipper/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1q7jpimsqln7ic44i8v2rx2haj5wvik8hc1s2syd31zcn0xk1iyq"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
;; remove unnecessary setup dependency
|
||
'(substitute* "setup.py"
|
||
(("setup_requires = .*") "")))))
|
||
(build-system python-build-system)
|
||
(arguments `(#:python ,python-2)) ; only Python 2 is supported
|
||
(inputs
|
||
`(("htseq" ,htseq)
|
||
("python-pybedtools" ,python2-pybedtools)
|
||
("python-cython" ,python2-cython)
|
||
("python-scikit-learn" ,python2-scikit-learn)
|
||
("python-matplotlib" ,python2-matplotlib)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-scipy" ,python2-scipy)))
|
||
(native-inputs
|
||
`(("python-mock" ,python2-mock) ; for tests
|
||
("python-pytz" ,python2-pytz) ; for tests
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "https://github.com/YeoLab/clipper")
|
||
(synopsis "CLIP peak enrichment recognition")
|
||
(description
|
||
"CLIPper is a tool to define peaks in CLIP-seq datasets.")
|
||
(license license:gpl2)))
|
||
|
||
(define-public codingquarry
|
||
(package
|
||
(name "codingquarry")
|
||
(version "2.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"mirror://sourceforge/codingquarry/CodingQuarry_v"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f ; no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(doc (string-append out "/share/doc/codingquarry")))
|
||
(install-file "INSTRUCTIONS.pdf" doc)
|
||
(copy-recursively "QuarryFiles"
|
||
(string-append out "/QuarryFiles"))
|
||
(install-file "CodingQuarry" bin)
|
||
(install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
|
||
(inputs `(("openmpi" ,openmpi)))
|
||
(native-search-paths
|
||
(list (search-path-specification
|
||
(variable "QUARRY_PATH")
|
||
(files '("QuarryFiles")))))
|
||
(native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
|
||
(synopsis "Fungal gene predictor")
|
||
(description "CodingQuarry is a highly accurate, self-training GHMM fungal
|
||
gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
|
||
(home-page "https://sourceforge.net/projects/codingquarry/")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public couger
|
||
(package
|
||
(name "couger")
|
||
(version "1.8.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://couger.oit.duke.edu/static/assets/COUGER"
|
||
version ".zip"))
|
||
(sha256
|
||
(base32
|
||
"04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(delete 'build)
|
||
(replace
|
||
'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
(copy-recursively "src" (string-append out "/src"))
|
||
(mkdir (string-append out "/bin"))
|
||
;; Add "src" directory to module lookup path.
|
||
(substitute* "couger"
|
||
(("from argparse")
|
||
(string-append "import sys\nsys.path.append(\""
|
||
out "\")\nfrom argparse")))
|
||
(copy-file "couger" (string-append out "/bin/couger")))
|
||
#t))
|
||
(add-after
|
||
'install 'wrap-program
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
;; Make sure 'couger' runs with the correct PYTHONPATH.
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(path (getenv "PYTHONPATH")))
|
||
(wrap-program (string-append out "/bin/couger")
|
||
`("PYTHONPATH" ":" prefix (,path))))
|
||
#t)))))
|
||
(inputs
|
||
`(("python" ,python-2)
|
||
("python2-pillow" ,python2-pillow)
|
||
("python2-numpy" ,python2-numpy)
|
||
("python2-scipy" ,python2-scipy)
|
||
("python2-matplotlib" ,python2-matplotlib)))
|
||
(propagated-inputs
|
||
`(("r" ,r)
|
||
("libsvm" ,libsvm)
|
||
("randomjungle" ,randomjungle)))
|
||
(native-inputs
|
||
`(("unzip" ,unzip)))
|
||
(home-page "http://couger.oit.duke.edu")
|
||
(synopsis "Identify co-factors in sets of genomic regions")
|
||
(description
|
||
"COUGER can be applied to any two sets of genomic regions bound by
|
||
paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
|
||
putative co-factors that provide specificity to each TF. The framework
|
||
determines the genomic targets uniquely-bound by each TF, and identifies a
|
||
small set of co-factors that best explain the in vivo binding differences
|
||
between the two TFs.
|
||
|
||
COUGER uses classification algorithms (support vector machines and random
|
||
forests) with features that reflect the DNA binding specificities of putative
|
||
co-factors. The features are generated either from high-throughput TF-DNA
|
||
binding data (from protein binding microarray experiments), or from large
|
||
collections of DNA motifs.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public clustal-omega
|
||
(package
|
||
(name "clustal-omega")
|
||
(version "1.2.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://www.clustal.org/omega/clustal-omega-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
|
||
(build-system gnu-build-system)
|
||
(inputs
|
||
`(("argtable" ,argtable)))
|
||
(home-page "http://www.clustal.org/omega/")
|
||
(synopsis "Multiple sequence aligner for protein and DNA/RNA")
|
||
(description
|
||
"Clustal-Omega is a general purpose multiple sequence alignment (MSA)
|
||
program for protein and DNA/RNA. It produces high quality MSAs and is capable
|
||
of handling data-sets of hundreds of thousands of sequences in reasonable
|
||
time.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public crossmap
|
||
(package
|
||
(name "crossmap")
|
||
(version "0.2.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
|
||
;; This patch has been sent upstream already and is available
|
||
;; for download from Sourceforge, but it has not been merged.
|
||
(patches (search-patches "crossmap-allow-system-pysam.patch"))
|
||
(modules '((guix build utils)))
|
||
;; remove bundled copy of pysam
|
||
(snippet
|
||
'(delete-file-recursively "lib/pysam"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'set-env
|
||
(lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
|
||
%standard-phases)))
|
||
(inputs
|
||
`(("python-numpy" ,python2-numpy)
|
||
("python-pysam" ,python2-pysam)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-nose" ,python2-nose)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://crossmap.sourceforge.net/")
|
||
(synopsis "Convert genome coordinates between assemblies")
|
||
(description
|
||
"CrossMap is a program for conversion of genome coordinates or annotation
|
||
files between different genome assemblies. It supports most commonly used
|
||
file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public cufflinks
|
||
(package
|
||
(name "cufflinks")
|
||
(version "2.2.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "http://cole-trapnell-lab.github.io/"
|
||
"cufflinks/assets/downloads/cufflinks-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:make-flags
|
||
(list
|
||
;; The includes for "eigen" are located in a subdirectory.
|
||
(string-append "EIGEN_CPPFLAGS="
|
||
"-I" (assoc-ref %build-inputs "eigen")
|
||
"/include/eigen3/")
|
||
;; Cufflinks must be linked with various boost libraries.
|
||
(string-append "LDFLAGS="
|
||
(string-join '("-lboost_system"
|
||
"-lboost_serialization"
|
||
"-lboost_thread"))))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'fix-search-for-bam
|
||
(lambda _
|
||
(substitute* '("ax_bam.m4"
|
||
"configure"
|
||
"src/hits.h")
|
||
(("<bam/sam\\.h>") "<samtools/sam.h>")
|
||
(("<bam/bam\\.h>") "<samtools/bam.h>")
|
||
(("<bam/version\\.hpp>") "<samtools/version.h>"))
|
||
#t)))
|
||
#:configure-flags
|
||
(list (string-append "--with-bam="
|
||
(assoc-ref %build-inputs "samtools")))))
|
||
(inputs
|
||
`(("eigen" ,eigen)
|
||
("samtools" ,samtools-0.1)
|
||
("htslib" ,htslib)
|
||
("boost" ,boost)
|
||
("python" ,python-2)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://cole-trapnell-lab.github.io/cufflinks/")
|
||
(synopsis "Transcriptome assembly and RNA-Seq expression analysis")
|
||
(description
|
||
"Cufflinks assembles RNA transcripts, estimates their abundances,
|
||
and tests for differential expression and regulation in RNA-Seq
|
||
samples. It accepts aligned RNA-Seq reads and assembles the
|
||
alignments into a parsimonious set of transcripts. Cufflinks then
|
||
estimates the relative abundances of these transcripts based on how
|
||
many reads support each one, taking into account biases in library
|
||
preparation protocols.")
|
||
(license license:boost1.0)))
|
||
|
||
(define-public cutadapt
|
||
(package
|
||
(name "cutadapt")
|
||
(version "1.8")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/marcelm/cutadapt/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
;; tests must be run after install
|
||
`(#:phases (alist-cons-after
|
||
'install 'check
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(setenv "PYTHONPATH"
|
||
(string-append
|
||
(getenv "PYTHONPATH")
|
||
":" (assoc-ref outputs "out")
|
||
"/lib/python"
|
||
(string-take (string-take-right
|
||
(assoc-ref inputs "python") 5) 3)
|
||
"/site-packages"))
|
||
(zero? (system* "nosetests" "-P" "tests")))
|
||
(alist-delete 'check %standard-phases))))
|
||
(native-inputs
|
||
`(("python-cython" ,python-cython)
|
||
("python-nose" ,python-nose)
|
||
("python-setuptools" ,python-setuptools)))
|
||
(home-page "https://code.google.com/p/cutadapt/")
|
||
(synopsis "Remove adapter sequences from nucleotide sequencing reads")
|
||
(description
|
||
"Cutadapt finds and removes adapter sequences, primers, poly-A tails and
|
||
other types of unwanted sequence from high-throughput sequencing reads.")
|
||
(license license:expat)))
|
||
|
||
(define-public libbigwig
|
||
(package
|
||
(name "libbigwig")
|
||
(version "0.1.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/dpryan79/libBigWig/"
|
||
"archive/" version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:test-target "test"
|
||
#:make-flags
|
||
(list "CC=gcc"
|
||
(string-append "prefix=" (assoc-ref %outputs "out")))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(add-before 'check 'disable-curl-test
|
||
(lambda _
|
||
(substitute* "Makefile"
|
||
(("./test/testRemote.*") ""))
|
||
#t))
|
||
;; This has been fixed with the upstream commit 4ff6959cd8a0, but
|
||
;; there has not yet been a release containing this change.
|
||
(add-before 'install 'create-target-dirs
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
(mkdir-p (string-append out "/lib"))
|
||
(mkdir-p (string-append out "/include"))
|
||
#t))))))
|
||
(inputs
|
||
`(("zlib" ,zlib)
|
||
("curl" ,curl)))
|
||
(native-inputs
|
||
`(("doxygen" ,doxygen)))
|
||
(home-page "https://github.com/dpryan79/libBigWig")
|
||
(synopsis "C library for handling bigWig files")
|
||
(description
|
||
"This package provides a C library for parsing local and remote BigWig
|
||
files.")
|
||
(license license:expat)))
|
||
|
||
(define-public python-pybigwig
|
||
(package
|
||
(name "python-pybigwig")
|
||
(version "0.2.5")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "pyBigWig" version))
|
||
(sha256
|
||
(base32
|
||
"0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; Delete bundled libBigWig sources
|
||
(delete-file-recursively "libBigWig")))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'link-with-libBigWig
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(substitute* "setup.py"
|
||
(("libs=\\[") "libs=[\"BigWig\", "))
|
||
#t)))))
|
||
(inputs
|
||
`(("libbigwig" ,libbigwig)
|
||
("zlib" ,zlib)
|
||
("curl" ,curl)))
|
||
(home-page "https://github.com/dpryan79/pyBigWig")
|
||
(synopsis "Access bigWig files in Python using libBigWig")
|
||
(description
|
||
"This package provides Python bindings to the libBigWig library for
|
||
accessing bigWig files.")
|
||
(license license:expat)))
|
||
|
||
(define-public python2-pybigwig
|
||
(let ((pybigwig (package-with-python2 python-pybigwig)))
|
||
(package (inherit pybigwig)
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools))))))
|
||
|
||
(define-public python-dendropy
|
||
(package
|
||
(name "python-dendropy")
|
||
(version "4.1.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "DendroPy" version))
|
||
(sha256
|
||
(base32
|
||
"1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))
|
||
;; There are two known test failures that will be fixed in the next
|
||
;; release after 4.1.0.
|
||
;; https://github.com/jeetsukumaran/DendroPy/issues/48
|
||
(patches (search-patches
|
||
"python-dendropy-exclude-failing-tests.patch"))))
|
||
(build-system python-build-system)
|
||
(home-page "http://packages.python.org/DendroPy/")
|
||
(synopsis "Library for phylogenetics and phylogenetic computing")
|
||
(description
|
||
"DendroPy is a library for phylogenetics and phylogenetic computing: reading,
|
||
writing, simulation, processing and manipulation of phylogenetic
|
||
trees (phylogenies) and characters.")
|
||
(license license:bsd-3)
|
||
(properties `((python2-variant . ,(delay python2-dendropy))))))
|
||
|
||
(define-public python2-dendropy
|
||
(let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
|
||
(package
|
||
(inherit base)
|
||
(native-inputs `(("python2-setuptools" ,python2-setuptools)
|
||
,@(package-native-inputs base))))))
|
||
|
||
|
||
(define-public deeptools
|
||
(package
|
||
(name "deeptools")
|
||
(version "2.1.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/fidelram/deepTools/"
|
||
"archive/" version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2))
|
||
(inputs
|
||
`(("python-scipy" ,python2-scipy)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-numpydoc" ,python2-numpydoc)
|
||
("python-matplotlib" ,python2-matplotlib)
|
||
("python-bx-python" ,python2-bx-python)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-pybigwig" ,python2-pybigwig)))
|
||
(native-inputs
|
||
`(("python-mock" ,python2-mock) ;for tests
|
||
("python-pytz" ,python2-pytz) ;for tests
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "https://github.com/fidelram/deepTools")
|
||
(synopsis "Tools for normalizing and visualizing deep-sequencing data")
|
||
(description
|
||
"DeepTools addresses the challenge of handling the large amounts of data
|
||
that are now routinely generated from DNA sequencing centers. To do so,
|
||
deepTools contains useful modules to process the mapped reads data to create
|
||
coverage files in standard bedGraph and bigWig file formats. By doing so,
|
||
deepTools allows the creation of normalized coverage files or the comparison
|
||
between two files (for example, treatment and control). Finally, using such
|
||
normalized and standardized files, multiple visualizations can be created to
|
||
identify enrichments with functional annotations of the genome.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public diamond
|
||
(package
|
||
(name "diamond")
|
||
(version "0.8.18")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/bbuchfink/diamond/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1r8klhbzn5cfzg9g69dd0sk4c0bd8cg1g5id8blsqi273bymm4jl"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
'(#:tests? #f ; no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'remove-native-compilation
|
||
(lambda _
|
||
(substitute* "CMakeLists.txt" (("-march=native") ""))
|
||
#t)))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(home-page "https://github.com/bbuchfink/diamond")
|
||
(synopsis "Accelerated BLAST compatible local sequence aligner")
|
||
(description
|
||
"DIAMOND is a BLAST-compatible local aligner for mapping protein and
|
||
translated DNA query sequences against a protein reference database (BLASTP
|
||
and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
|
||
reads at a typical sensitivity of 90-99% relative to BLAST depending on the
|
||
data and settings.")
|
||
;; diamond fails to build on other platforms
|
||
;; https://github.com/bbuchfink/diamond/issues/18
|
||
(supported-systems '("x86_64-linux"))
|
||
(license (license:non-copyleft "file://src/COPYING"
|
||
"See src/COPYING in the distribution."))))
|
||
|
||
(define-public discrover
|
||
(package
|
||
(name "discrover")
|
||
(version "1.6.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/maaskola/discrover/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
|
||
(build-system cmake-build-system)
|
||
(arguments `(#:tests? #f)) ; there are no tests
|
||
(inputs
|
||
`(("boost" ,boost)
|
||
("cairo" ,cairo)))
|
||
(native-inputs
|
||
`(("texlive" ,texlive)
|
||
("imagemagick" ,imagemagick)))
|
||
(home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
|
||
(synopsis "Discover discriminative nucleotide sequence motifs")
|
||
(description "Discrover is a motif discovery method to find binding sites
|
||
of nucleic acid binding proteins.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public eigensoft
|
||
(let ((revision "1")
|
||
(commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
|
||
(package
|
||
(name "eigensoft")
|
||
(version (string-append "6.1.2-"
|
||
revision "."
|
||
(string-take commit 9)))
|
||
(source
|
||
(origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/DReichLab/EIG.git")
|
||
(commit commit)))
|
||
(file-name (string-append "eigensoft-" commit "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
|
||
(modules '((guix build utils)))
|
||
;; Remove pre-built binaries.
|
||
(snippet '(begin
|
||
(delete-file-recursively "bin")
|
||
(mkdir "bin")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; There are no tests.
|
||
#:make-flags '("CC=gcc")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; There is no configure phase, but the Makefile is in a
|
||
;; sub-directory.
|
||
(replace 'configure
|
||
(lambda _
|
||
(chdir "src")
|
||
;; The link flags are incomplete.
|
||
(substitute* "Makefile"
|
||
(("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
|
||
#t))
|
||
;; The provided install target only copies executables to
|
||
;; the "bin" directory in the build root.
|
||
(add-after 'install 'actually-install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin")))
|
||
(mkdir-p bin)
|
||
(for-each (lambda (file)
|
||
(install-file file bin))
|
||
(find-files "../bin" ".*"))
|
||
#t))))))
|
||
(inputs
|
||
`(("gsl" ,gsl)
|
||
("lapack" ,lapack)
|
||
("openblas" ,openblas)
|
||
("perl" ,perl)
|
||
("gfortran" ,gfortran "lib")))
|
||
(home-page "https://github.com/DReichLab/EIG")
|
||
(synopsis "Tools for population genetics")
|
||
(description "The EIGENSOFT package provides tools for population
|
||
genetics and stratification correction. EIGENSOFT implements methods commonly
|
||
used in population genetics analyses such as PCA, computation of Tracy-Widom
|
||
statistics, and finding related individuals in structured populations. It
|
||
comes with a built-in plotting script and supports multiple file formats and
|
||
quantitative phenotypes.")
|
||
;; The license of the eigensoft tools is Expat, but since it's
|
||
;; linking with the GNU Scientific Library (GSL) the effective
|
||
;; license is the GPL.
|
||
(license license:gpl3+))))
|
||
|
||
(define-public edirect
|
||
(package
|
||
(name "edirect")
|
||
(version "4.10")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
|
||
"versions/2016-05-03/edirect.tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
|
||
(build-system perl-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(delete 'build)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((target (string-append (assoc-ref outputs "out")
|
||
"/bin")))
|
||
(mkdir-p target)
|
||
(copy-file "edirect.pl"
|
||
(string-append target "/edirect.pl"))
|
||
#t)))
|
||
(add-after
|
||
'install 'wrap-program
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
;; Make sure 'edirect.pl' finds all perl inputs at runtime.
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(path (getenv "PERL5LIB")))
|
||
(wrap-program (string-append out "/bin/edirect.pl")
|
||
`("PERL5LIB" ":" prefix (,path)))))))))
|
||
(inputs
|
||
`(("perl-html-parser" ,perl-html-parser)
|
||
("perl-encode-locale" ,perl-encode-locale)
|
||
("perl-file-listing" ,perl-file-listing)
|
||
("perl-html-tagset" ,perl-html-tagset)
|
||
("perl-html-tree" ,perl-html-tree)
|
||
("perl-http-cookies" ,perl-http-cookies)
|
||
("perl-http-date" ,perl-http-date)
|
||
("perl-http-message" ,perl-http-message)
|
||
("perl-http-negotiate" ,perl-http-negotiate)
|
||
("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
|
||
("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
|
||
("perl-net-http" ,perl-net-http)
|
||
("perl-uri" ,perl-uri)
|
||
("perl-www-robotrules" ,perl-www-robotrules)
|
||
("perl" ,perl)))
|
||
(home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
|
||
(synopsis "Tools for accessing the NCBI's set of databases")
|
||
(description
|
||
"Entrez Direct (EDirect) is a method for accessing the National Center
|
||
for Biotechnology Information's (NCBI) set of interconnected
|
||
databases (publication, sequence, structure, gene, variation, expression,
|
||
etc.) from a terminal. Functions take search terms from command-line
|
||
arguments. Individual operations are combined to build multi-step queries.
|
||
Record retrieval and formatting normally complete the process.
|
||
|
||
EDirect also provides an argument-driven function that simplifies the
|
||
extraction of data from document summaries or other results that are returned
|
||
in structured XML format. This can eliminate the need for writing custom
|
||
software to answer ad hoc questions.")
|
||
(license license:public-domain)))
|
||
|
||
(define-public exonerate
|
||
(package
|
||
(name "exonerate")
|
||
(version "2.4.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append
|
||
"http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
|
||
"exonerate-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f)) ; Building in parallel fails on some machines.
|
||
(native-inputs
|
||
`(("pkg-config" ,pkg-config)))
|
||
(inputs
|
||
`(("glib" ,glib)))
|
||
(home-page
|
||
"https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
|
||
(synopsis "Generic tool for biological sequence alignment")
|
||
(description
|
||
"Exonerate is a generic tool for pairwise sequence comparison. It allows
|
||
the alignment of sequences using a many alignment models, either exhaustive
|
||
dynamic programming or a variety of heuristics.")
|
||
(license license:gpl3)))
|
||
|
||
(define-public express
|
||
(package
|
||
(name "express")
|
||
(version "1.5.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append
|
||
"http://bio.math.berkeley.edu/eXpress/downloads/express-"
|
||
version "/express-" version "-src.tgz"))
|
||
(sha256
|
||
(base32
|
||
"03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'use-shared-boost-libs-and-set-bamtools-paths
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(substitute* "CMakeLists.txt"
|
||
(("set\\(Boost_USE_STATIC_LIBS ON\\)")
|
||
"set(Boost_USE_STATIC_LIBS OFF)")
|
||
(("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
|
||
(string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
|
||
(substitute* "src/CMakeLists.txt"
|
||
(("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
|
||
(string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
|
||
#t)
|
||
%standard-phases)))
|
||
(inputs
|
||
`(("boost" ,boost)
|
||
("bamtools" ,bamtools)
|
||
("protobuf" ,protobuf)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://bio.math.berkeley.edu/eXpress")
|
||
(synopsis "Streaming quantification for high-throughput genomic sequencing")
|
||
(description
|
||
"eXpress is a streaming tool for quantifying the abundances of a set of
|
||
target sequences from sampled subsequences. Example applications include
|
||
transcript-level RNA-Seq quantification, allele-specific/haplotype expression
|
||
analysis (from RNA-Seq), transcription factor binding quantification in
|
||
ChIP-Seq, and analysis of metagenomic data.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public express-beta-diversity
|
||
(package
|
||
(name "express-beta-diversity")
|
||
(version "1.0.7")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append
|
||
"https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(add-before 'build 'enter-source (lambda _ (chdir "source") #t))
|
||
(replace 'check
|
||
(lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
|
||
"-u"))))
|
||
(add-after 'check 'exit-source (lambda _ (chdir "..") #t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out")
|
||
"/bin")))
|
||
(mkdir-p bin)
|
||
(copy-file "scripts/convertToEBD.py"
|
||
(string-append bin "/convertToEBD.py"))
|
||
(copy-file "bin/ExpressBetaDiversity"
|
||
(string-append bin "/ExpressBetaDiversity"))
|
||
#t))))))
|
||
(inputs
|
||
`(("python" ,python-2)))
|
||
(home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
|
||
(synopsis "Taxon- and phylogenetic-based beta diversity measures")
|
||
(description
|
||
"Express Beta Diversity (EBD) calculates ecological beta diversity
|
||
(dissimilarity) measures between biological communities. EBD implements a
|
||
variety of diversity measures including those that make use of phylogenetic
|
||
similarity of community members.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public fasttree
|
||
(package
|
||
(name "fasttree")
|
||
(version "2.1.9")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://www.microbesonline.org/fasttree/FastTree-"
|
||
version ".c"))
|
||
(sha256
|
||
(base32
|
||
"0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'unpack)
|
||
(delete 'configure)
|
||
(replace 'build
|
||
(lambda* (#:key source #:allow-other-keys)
|
||
(and (zero? (system* "gcc"
|
||
"-O3"
|
||
"-finline-functions"
|
||
"-funroll-loops"
|
||
"-Wall"
|
||
"-o"
|
||
"FastTree"
|
||
source
|
||
"-lm"))
|
||
(zero? (system* "gcc"
|
||
"-DOPENMP"
|
||
"-fopenmp"
|
||
"-O3"
|
||
"-finline-functions"
|
||
"-funroll-loops"
|
||
"-Wall"
|
||
"-o"
|
||
"FastTreeMP"
|
||
source
|
||
"-lm")))))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out")
|
||
"/bin")))
|
||
(mkdir-p bin)
|
||
(copy-file "FastTree"
|
||
(string-append bin "/FastTree"))
|
||
(copy-file "FastTreeMP"
|
||
(string-append bin "/FastTreeMP"))
|
||
#t))))))
|
||
(home-page "http://www.microbesonline.org/fasttree")
|
||
(synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
|
||
(description
|
||
"FastTree can handle alignments with up to a million of sequences in a
|
||
reasonable amount of time and memory. For large alignments, FastTree is
|
||
100-1,000 times faster than PhyML 3.0 or RAxML 7.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public fastx-toolkit
|
||
(package
|
||
(name "fastx-toolkit")
|
||
(version "0.0.14")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append
|
||
"https://github.com/agordon/fastx_toolkit/releases/download/"
|
||
version "/fastx_toolkit-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
|
||
(build-system gnu-build-system)
|
||
(inputs
|
||
`(("libgtextutils" ,libgtextutils)))
|
||
(native-inputs
|
||
`(("pkg-config" ,pkg-config)))
|
||
(home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
|
||
(synopsis "Tools for FASTA/FASTQ file preprocessing")
|
||
(description
|
||
"The FASTX-Toolkit is a collection of command line tools for Short-Reads
|
||
FASTA/FASTQ files preprocessing.
|
||
|
||
Next-Generation sequencing machines usually produce FASTA or FASTQ files,
|
||
containing multiple short-reads sequences. The main processing of such
|
||
FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
|
||
is sometimes more productive to preprocess the files before mapping the
|
||
sequences to the genome---manipulating the sequences to produce better mapping
|
||
results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
|
||
(license license:agpl3+)))
|
||
|
||
(define-public flexbar
|
||
(package
|
||
(name "flexbar")
|
||
(version "2.5")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "mirror://sourceforge/flexbar/"
|
||
version "/flexbar_v" version "_src.tgz"))
|
||
(sha256
|
||
(base32
|
||
"13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
|
||
(build-system cmake-build-system)
|
||
(arguments
|
||
`(#:configure-flags (list
|
||
(string-append "-DFLEXBAR_BINARY_DIR="
|
||
(assoc-ref %outputs "out")
|
||
"/bin/"))
|
||
#:phases
|
||
(alist-replace
|
||
'check
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(setenv "PATH" (string-append
|
||
(assoc-ref outputs "out") "/bin:"
|
||
(getenv "PATH")))
|
||
(chdir "../flexbar_v2.5_src/test")
|
||
(zero? (system* "bash" "flexbar_validate.sh")))
|
||
(alist-delete 'install %standard-phases))))
|
||
(inputs
|
||
`(("tbb" ,tbb)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("pkg-config" ,pkg-config)
|
||
("seqan" ,seqan)))
|
||
(home-page "http://flexbar.sourceforge.net")
|
||
(synopsis "Barcode and adapter removal tool for sequencing platforms")
|
||
(description
|
||
"Flexbar preprocesses high-throughput nucleotide sequencing data
|
||
efficiently. It demultiplexes barcoded runs and removes adapter sequences.
|
||
Moreover, trimming and filtering features are provided. Flexbar increases
|
||
read mapping rates and improves genome and transcriptome assemblies. It
|
||
supports next-generation sequencing data in fasta/q and csfasta/q format from
|
||
Illumina, Roche 454, and the SOLiD platform.")
|
||
(license license:gpl3)))
|
||
|
||
(define-public fraggenescan
|
||
(package
|
||
(name "fraggenescan")
|
||
(version "1.20")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "mirror://sourceforge/fraggenescan/"
|
||
"FragGeneScan" version ".tar.gz"))
|
||
(sha256
|
||
(base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(add-before 'build 'patch-paths
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (string-append (assoc-ref outputs "out")))
|
||
(share (string-append out "/share/fraggenescan/")))
|
||
(substitute* "run_FragGeneScan.pl"
|
||
(("system\\(\"rm")
|
||
(string-append "system(\"" (which "rm")))
|
||
(("system\\(\"mv")
|
||
(string-append "system(\"" (which "mv")))
|
||
;; This script and other programs expect the training files
|
||
;; to be in the non-standard location bin/train/XXX. Change
|
||
;; this to be share/fraggenescan/train/XXX instead.
|
||
(("^\\$train.file = \\$dir.*")
|
||
(string-append "$train_file = \""
|
||
share
|
||
"train/\".$FGS_train_file;")))
|
||
(substitute* "run_hmm.c"
|
||
(("^ strcat\\(train_dir, \\\"train/\\\"\\);")
|
||
(string-append " strcpy(train_dir, \"" share "/train/\");")))
|
||
(substitute* "post_process.pl"
|
||
(("^my \\$dir = substr.*")
|
||
(string-append "my $dir = \"" share "\";"))))
|
||
#t))
|
||
(replace 'build
|
||
(lambda _ (and (zero? (system* "make" "clean"))
|
||
(zero? (system* "make" "fgs")))))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (string-append (assoc-ref outputs "out")))
|
||
(bin (string-append out "/bin/"))
|
||
(share (string-append out "/share/fraggenescan/train")))
|
||
(install-file "run_FragGeneScan.pl" bin)
|
||
(install-file "FragGeneScan" bin)
|
||
(install-file "FGS_gff.py" bin)
|
||
(install-file "post_process.pl" bin)
|
||
(copy-recursively "train" share))))
|
||
(delete 'check)
|
||
(add-after 'install 'post-install-check
|
||
;; In lieu of 'make check', run one of the examples and check the
|
||
;; output files gets created.
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (string-append (assoc-ref outputs "out")))
|
||
(bin (string-append out "/bin/")))
|
||
(and (zero? (system* (string-append bin "run_FragGeneScan.pl")
|
||
"-genome=./example/NC_000913.fna"
|
||
"-out=./test2"
|
||
"-complete=1"
|
||
"-train=complete"))
|
||
(file-exists? "test2.faa")
|
||
(file-exists? "test2.ffn")
|
||
(file-exists? "test2.gff")
|
||
(file-exists? "test2.out"))))))))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("python" ,python-2))) ;not compatible with python 3.
|
||
(home-page "https://sourceforge.net/projects/fraggenescan/")
|
||
(synopsis "Finds potentially fragmented genes in short reads")
|
||
(description
|
||
"FragGeneScan is a program for predicting bacterial and archaeal genes in
|
||
short and error-prone DNA sequencing reads. It can also be applied to predict
|
||
genes in incomplete assemblies or complete genomes.")
|
||
;; GPL3+ according to private correspondense with the authors.
|
||
(license license:gpl3+)))
|
||
|
||
(define-public fxtract
|
||
(let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
|
||
(package
|
||
(name "fxtract")
|
||
(version "2.3")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/ctSkennerton/fxtract/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append "ctstennerton-util-"
|
||
(string-take util-commit 7)
|
||
"-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:make-flags (list
|
||
(string-append "PREFIX=" (assoc-ref %outputs "out"))
|
||
"CC=gcc")
|
||
#:test-target "fxtract_test"
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(add-before 'build 'copy-util
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(rmdir "util")
|
||
(copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
|
||
#t))
|
||
;; Do not use make install as this requires additional dependencies.
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out"/bin")))
|
||
(install-file "fxtract" bin)
|
||
#t))))))
|
||
(inputs
|
||
`(("pcre" ,pcre)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
;; ctskennerton-util is licensed under GPL2.
|
||
`(("ctskennerton-util"
|
||
,(origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/ctSkennerton/util.git")
|
||
(commit util-commit)))
|
||
(file-name (string-append
|
||
"ctstennerton-util-" util-commit "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
|
||
(home-page "https://github.com/ctSkennerton/fxtract")
|
||
(synopsis "Extract sequences from FASTA and FASTQ files")
|
||
(description
|
||
"Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
|
||
or FASTQ) file given a subsequence. It uses a simple substring search for
|
||
basic tasks but can change to using POSIX regular expressions, PCRE, hash
|
||
lookups or multi-pattern searching as required. By default fxtract looks in
|
||
the sequence of each record but can also be told to look in the header,
|
||
comment or quality sections.")
|
||
;; 'util' requires SSE instructions.
|
||
(supported-systems '("x86_64-linux"))
|
||
(license license:expat))))
|
||
|
||
(define-public grit
|
||
(package
|
||
(name "grit")
|
||
(version "2.0.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/nboley/grit/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'generate-from-cython-sources
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
;; Delete these C files to force fresh generation from pyx sources.
|
||
(delete-file "grit/sparsify_support_fns.c")
|
||
(delete-file "grit/call_peaks_support_fns.c")
|
||
(substitute* "setup.py"
|
||
(("Cython.Setup") "Cython.Build")
|
||
;; Add numpy include path to fix compilation
|
||
(("pyx\", \\]")
|
||
(string-append "pyx\", ], include_dirs = ['"
|
||
(assoc-ref inputs "python-numpy")
|
||
"/lib/python2.7/site-packages/numpy/core/include/"
|
||
"']"))) #t)
|
||
%standard-phases)))
|
||
(inputs
|
||
`(("python-scipy" ,python2-scipy)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-networkx" ,python2-networkx)))
|
||
(native-inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://grit-bio.org")
|
||
(synopsis "Tool for integrative analysis of RNA-seq type assays")
|
||
(description
|
||
"GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
|
||
full length transcript models. When none of these data sources are available,
|
||
GRIT can be run by providing a candidate set of TES or TSS sites. In
|
||
addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
|
||
also be run in quantification mode, where it uses a provided GTF file and just
|
||
estimates transcript expression.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public hisat
|
||
(package
|
||
(name "hisat")
|
||
(version "0.1.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://ccb.jhu.edu/software/hisat/downloads/hisat-"
|
||
version "-beta-source.zip"))
|
||
(sha256
|
||
(base32
|
||
"1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no check target
|
||
#:make-flags '("allall"
|
||
;; Disable unsupported `popcnt' instructions on
|
||
;; architectures other than x86_64
|
||
,@(if (string-prefix? "x86_64"
|
||
(or (%current-target-system)
|
||
(%current-system)))
|
||
'()
|
||
'("POPCNT_CAPABILITY=0")))
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'patch-sources
|
||
(lambda _
|
||
;; XXX Cannot use snippet because zip files are not supported
|
||
(substitute* "Makefile"
|
||
(("^CC = .*$") "CC = gcc")
|
||
(("^CPP = .*$") "CPP = g++")
|
||
;; replace BUILD_HOST and BUILD_TIME for deterministic build
|
||
(("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
|
||
(("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
|
||
(substitute* '("hisat-build" "hisat-inspect")
|
||
(("/usr/bin/env") (which "env"))))
|
||
(alist-replace
|
||
'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bi/")))
|
||
(for-each (lambda (file)
|
||
(install-file file bin))
|
||
(find-files
|
||
"."
|
||
"hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
|
||
(alist-delete 'configure %standard-phases)))))
|
||
(native-inputs
|
||
`(("unzip" ,unzip)))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("python" ,python)
|
||
("zlib" ,zlib)))
|
||
;; Non-portable SSE instructions are used so building fails on platforms
|
||
;; other than x86_64.
|
||
(supported-systems '("x86_64-linux"))
|
||
(home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
|
||
(synopsis "Hierarchical indexing for spliced alignment of transcripts")
|
||
(description
|
||
"HISAT is a fast and sensitive spliced alignment program for mapping
|
||
RNA-seq reads. In addition to one global FM index that represents a whole
|
||
genome, HISAT uses a large set of small FM indexes that collectively cover the
|
||
whole genome. These small indexes (called local indexes) combined with
|
||
several alignment strategies enable effective alignment of RNA-seq reads, in
|
||
particular, reads spanning multiple exons.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public hmmer
|
||
(package
|
||
(name "hmmer")
|
||
(version "3.1b2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://eddylab.org/software/hmmer"
|
||
(version-prefix version 1) "/"
|
||
version "/hmmer-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
|
||
(build-system gnu-build-system)
|
||
(native-inputs `(("perl" ,perl)))
|
||
(home-page "http://hmmer.org/")
|
||
(synopsis "Biosequence analysis using profile hidden Markov models")
|
||
(description
|
||
"HMMER is used for searching sequence databases for homologs of protein
|
||
sequences, and for making protein sequence alignments. It implements methods
|
||
using probabilistic models called profile hidden Markov models (profile
|
||
HMMs).")
|
||
(license (list license:gpl3+
|
||
;; The bundled library 'easel' is distributed
|
||
;; under The Janelia Farm Software License.
|
||
(license:non-copyleft
|
||
"file://easel/LICENSE"
|
||
"See easel/LICENSE in the distribution.")))))
|
||
|
||
(define-public htseq
|
||
(package
|
||
(name "htseq")
|
||
(version "0.6.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
|
||
(build-system python-build-system)
|
||
(arguments `(#:python ,python-2)) ; only Python 2 is supported
|
||
;; Numpy needs to be propagated when htseq is used as a Python library.
|
||
(propagated-inputs
|
||
`(("python-numpy" ,python2-numpy)))
|
||
(inputs
|
||
`(("python-pysam" ,python2-pysam)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://www-huber.embl.de/users/anders/HTSeq/")
|
||
(synopsis "Analysing high-throughput sequencing data with Python")
|
||
(description
|
||
"HTSeq is a Python package that provides infrastructure to process data
|
||
from high-throughput sequencing assays.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public java-htsjdk
|
||
(package
|
||
(name "java-htsjdk")
|
||
(version "1.129")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/samtools/htsjdk/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
|
||
(modules '((guix build utils)))
|
||
;; remove build dependency on git
|
||
(snippet '(substitute* "build.xml"
|
||
(("failifexecutionfails=\"true\"")
|
||
"failifexecutionfails=\"false\"")))))
|
||
(build-system ant-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; test require Internet access
|
||
#:make-flags
|
||
(list (string-append "-Ddist=" (assoc-ref %outputs "out")
|
||
"/share/java/htsjdk/"))
|
||
#:build-target "all"
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; The build phase also installs the jars
|
||
(delete 'install))))
|
||
(home-page "http://samtools.github.io/htsjdk/")
|
||
(synopsis "Java API for high-throughput sequencing data (HTS) formats")
|
||
(description
|
||
"HTSJDK is an implementation of a unified Java library for accessing
|
||
common file formats, such as SAM and VCF, used for high-throughput
|
||
sequencing (HTS) data. There are also an number of useful utilities for
|
||
manipulating HTS data.")
|
||
(license license:expat)))
|
||
|
||
(define-public htslib
|
||
(package
|
||
(name "htslib")
|
||
(version "1.3.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/samtools/htslib/releases/download/"
|
||
version "/htslib-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after
|
||
'unpack 'patch-tests
|
||
(lambda _
|
||
(substitute* "test/test.pl"
|
||
(("/bin/bash") (which "bash")))
|
||
#t)))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("perl" ,perl)))
|
||
(home-page "http://www.htslib.org")
|
||
(synopsis "C library for reading/writing high-throughput sequencing data")
|
||
(description
|
||
"HTSlib is a C library for reading/writing high-throughput sequencing
|
||
data. It also provides the bgzip, htsfile, and tabix utilities.")
|
||
;; Files under cram/ are released under the modified BSD license;
|
||
;; the rest is released under the Expat license
|
||
(license (list license:expat license:bsd-3))))
|
||
|
||
(define-public idr
|
||
(package
|
||
(name "idr")
|
||
(version "2.0.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/nboley/idr/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after
|
||
'install 'wrap-program
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(python-version (string-take (string-take-right
|
||
(assoc-ref inputs "python") 5) 3))
|
||
(path (string-join
|
||
(map (lambda (name)
|
||
(string-append (assoc-ref inputs name)
|
||
"/lib/python" python-version
|
||
"/site-packages"))
|
||
'("python-scipy"
|
||
"python-numpy"
|
||
"python-matplotlib"))
|
||
":")))
|
||
(wrap-program (string-append out "/bin/idr")
|
||
`("PYTHONPATH" ":" prefix (,path))))
|
||
#t)))))
|
||
(inputs
|
||
`(("python-scipy" ,python-scipy)
|
||
("python-numpy" ,python-numpy)
|
||
("python-matplotlib" ,python-matplotlib)))
|
||
(native-inputs
|
||
`(("python-cython" ,python-cython)
|
||
("python-setuptools" ,python-setuptools)))
|
||
(home-page "https://github.com/nboley/idr")
|
||
(synopsis "Tool to measure the irreproducible discovery rate (IDR)")
|
||
(description
|
||
"The IDR (Irreproducible Discovery Rate) framework is a unified approach
|
||
to measure the reproducibility of findings identified from replicate
|
||
experiments and provide highly stable thresholds based on reproducibility.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public jellyfish
|
||
(package
|
||
(name "jellyfish")
|
||
(version "2.2.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/gmarcais/Jellyfish/"
|
||
"releases/download/v" version
|
||
"/jellyfish-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
|
||
(build-system gnu-build-system)
|
||
(outputs '("out" ;for library
|
||
"ruby" ;for Ruby bindings
|
||
"python")) ;for Python bindings
|
||
(arguments
|
||
`(#:configure-flags
|
||
(list (string-append "--enable-ruby-binding="
|
||
(assoc-ref %outputs "ruby"))
|
||
(string-append "--enable-python-binding="
|
||
(assoc-ref %outputs "python")))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-before 'check 'set-SHELL-variable
|
||
(lambda _
|
||
;; generator_manager.hpp either uses /bin/sh or $SHELL
|
||
;; to run tests.
|
||
(setenv "SHELL" (which "bash"))
|
||
#t)))))
|
||
(native-inputs
|
||
`(("bc" ,bc)
|
||
("time" ,time)
|
||
("ruby" ,ruby)
|
||
("python" ,python-2)))
|
||
(synopsis "Tool for fast counting of k-mers in DNA")
|
||
(description
|
||
"Jellyfish is a tool for fast, memory-efficient counting of k-mers in
|
||
DNA. A k-mer is a substring of length k, and counting the occurrences of all
|
||
such substrings is a central step in many analyses of DNA sequence. Jellyfish
|
||
is a command-line program that reads FASTA and multi-FASTA files containing
|
||
DNA sequences. It outputs its k-mer counts in a binary format, which can be
|
||
translated into a human-readable text format using the @code{jellyfish dump}
|
||
command, or queried for specific k-mers with @code{jellyfish query}.")
|
||
(home-page "http://www.genome.umd.edu/jellyfish.html")
|
||
;; The combined work is published under the GPLv3 or later. Individual
|
||
;; files such as lib/jsoncpp.cpp are released under the Expat license.
|
||
(license (list license:gpl3+ license:expat))))
|
||
|
||
(define-public khmer
|
||
(package
|
||
(name "khmer")
|
||
(version "2.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "khmer" version))
|
||
(sha256
|
||
(base32
|
||
"0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
|
||
(patches (search-patches "khmer-use-libraries.patch"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'set-paths
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
;; Delete bundled libraries.
|
||
(delete-file-recursively "third-party/zlib")
|
||
(delete-file-recursively "third-party/bzip2")
|
||
;; Replace bundled seqan.
|
||
(let* ((seqan-all "third-party/seqan")
|
||
(seqan-include (string-append
|
||
seqan-all "/core/include")))
|
||
(delete-file-recursively seqan-all)
|
||
(copy-recursively (string-append (assoc-ref inputs "seqan")
|
||
"/include/seqan")
|
||
(string-append seqan-include "/seqan")))
|
||
;; We do not replace the bundled MurmurHash as the canonical
|
||
;; repository for this code 'SMHasher' is unsuitable for
|
||
;; providing a library. See
|
||
;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
|
||
#t))
|
||
(add-after 'unpack 'set-cc
|
||
(lambda _
|
||
(setenv "CC" "gcc")
|
||
#t))
|
||
;; It is simpler to test after installation.
|
||
(delete 'check)
|
||
(add-after 'install 'post-install-check
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
(setenv "PATH"
|
||
(string-append
|
||
(getenv "PATH")
|
||
":"
|
||
(assoc-ref outputs "out")
|
||
"/bin"))
|
||
(setenv "PYTHONPATH"
|
||
(string-append
|
||
(getenv "PYTHONPATH")
|
||
":"
|
||
out
|
||
"/lib/python"
|
||
(string-take (string-take-right
|
||
(assoc-ref inputs "python") 5) 3)
|
||
"/site-packages"))
|
||
(with-directory-excursion "build"
|
||
(zero? (system* "nosetests" "khmer" "--attr"
|
||
"!known_failing")))))))))
|
||
(native-inputs
|
||
`(("seqan" ,seqan)
|
||
("python-nose" ,python-nose)))
|
||
(inputs
|
||
`(("zlib" ,zlib)
|
||
("bzip2" ,bzip2)
|
||
("python-screed" ,python-screed)
|
||
("python-bz2file" ,python-bz2file)))
|
||
(home-page "https://khmer.readthedocs.org/")
|
||
(synopsis "K-mer counting, filtering and graph traversal library")
|
||
(description "The khmer software is a set of command-line tools for
|
||
working with DNA shotgun sequencing data from genomes, transcriptomes,
|
||
metagenomes and single cells. Khmer can make de novo assemblies faster, and
|
||
sometimes better. Khmer can also identify and fix problems with shotgun
|
||
data.")
|
||
;; When building on i686, armhf and mips64el, we get the following error:
|
||
;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
|
||
(supported-systems '("x86_64-linux"))
|
||
(license license:bsd-3)))
|
||
|
||
(define-public macs
|
||
(package
|
||
(name "macs")
|
||
(version "2.1.0.20151222")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "MACS2" version))
|
||
(sha256
|
||
(base32
|
||
"1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; only compatible with Python 2.7
|
||
#:tests? #f)) ; no test target
|
||
(inputs
|
||
`(("python-numpy" ,python2-numpy)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://github.com/taoliu/MACS/")
|
||
(synopsis "Model based analysis for ChIP-Seq data")
|
||
(description
|
||
"MACS is an implementation of a ChIP-Seq analysis algorithm for
|
||
identifying transcript factor binding sites named Model-based Analysis of
|
||
ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
|
||
the significance of enriched ChIP regions and it improves the spatial
|
||
resolution of binding sites through combining the information of both
|
||
sequencing tag position and orientation.")
|
||
(license license:bsd-3)))
|
||
|
||
(define-public mafft
|
||
(package
|
||
(name "mafft")
|
||
(version "7.299")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://mafft.cbrc.jp/alignment/software/mafft-" version
|
||
"-without-extensions-src.tgz"))
|
||
(file-name (string-append name "-" version ".tgz"))
|
||
(sha256
|
||
(base32
|
||
"1pwwdy5a17ggx8h9v9y712ilswj27dc3d23r65l56jgjz67y5zc0"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; no automated tests, though there are tests in the read me
|
||
#:make-flags (let ((out (assoc-ref %outputs "out")))
|
||
(list (string-append "PREFIX=" out)
|
||
(string-append "BINDIR="
|
||
(string-append out "/bin"))))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'enter-dir
|
||
(lambda _ (chdir "core") #t))
|
||
(add-after 'enter-dir 'patch-makefile
|
||
(lambda _
|
||
;; on advice from the MAFFT authors, there is no need to
|
||
;; distribute mafft-profile, mafft-distance, or
|
||
;; mafft-homologs.rb as they are too "specialised".
|
||
(substitute* "Makefile"
|
||
;; remove mafft-homologs.rb from SCRIPTS
|
||
(("^SCRIPTS = mafft mafft-homologs.rb")
|
||
"SCRIPTS = mafft")
|
||
;; remove mafft-homologs from MANPAGES
|
||
(("^MANPAGES = mafft.1 mafft-homologs.1")
|
||
"MANPAGES = mafft.1")
|
||
;; remove mafft-distance from PROGS
|
||
(("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
|
||
"PROGS = dvtditr dndfast7 dndblast sextet5")
|
||
;; remove mafft-profile from PROGS
|
||
(("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
|
||
"splittbfast disttbfast tbfast f2cl mccaskillwrap")
|
||
(("^rm -f mafft-profile mafft-profile.exe") "#")
|
||
(("^rm -f mafft-distance mafft-distance.exe") ")#")
|
||
;; do not install MAN pages in libexec folder
|
||
(("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
|
||
\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
|
||
#t))
|
||
(add-after 'enter-dir 'patch-paths
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(substitute* '("pairash.c"
|
||
"mafft.tmpl")
|
||
(("perl") (which "perl"))
|
||
(("([\"`| ])awk" _ prefix)
|
||
(string-append prefix (which "awk")))
|
||
(("grep") (which "grep")))
|
||
#t))
|
||
(delete 'configure))))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("gawk" ,gawk)
|
||
("grep" ,grep)))
|
||
(propagated-inputs
|
||
`(("coreutils" ,coreutils)))
|
||
(home-page "http://mafft.cbrc.jp/alignment/software/")
|
||
(synopsis "Multiple sequence alignment program")
|
||
(description
|
||
"MAFFT offers a range of multiple alignment methods for nucleotide and
|
||
protein sequences. For instance, it offers L-INS-i (accurate; for alignment
|
||
of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
|
||
sequences).")
|
||
(license (license:non-copyleft
|
||
"http://mafft.cbrc.jp/alignment/software/license.txt"
|
||
"BSD-3 with different formatting"))))
|
||
|
||
(define-public metabat
|
||
(package
|
||
(name "metabat")
|
||
(version "0.26.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://bitbucket.org/berkeleylab/metabat/get/"
|
||
version ".tar.bz2"))
|
||
(file-name (string-append name "-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"1vpfvgsn8wdsv1g7z73zxcncskx7dy7bw5msg1hhibk25ay11pyg"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'fix-includes
|
||
(lambda _
|
||
(substitute* "src/BamUtils.h"
|
||
(("^#include \"bam/bam\\.h\"")
|
||
"#include \"samtools/bam.h\"")
|
||
(("^#include \"bam/sam\\.h\"")
|
||
"#include \"samtools/sam.h\""))
|
||
(substitute* "src/KseqReader.h"
|
||
(("^#include \"bam/kseq\\.h\"")
|
||
"#include \"htslib/kseq.h\""))
|
||
#t))
|
||
(add-after 'unpack 'fix-scons
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(substitute* "SConstruct"
|
||
(("^htslib_dir = 'samtools'")
|
||
(string-append "hitslib_dir = '"
|
||
(assoc-ref inputs "htslib")
|
||
"'"))
|
||
(("^samtools_dir = 'samtools'")
|
||
(string-append "samtools_dir = '"
|
||
(assoc-ref inputs "htslib")
|
||
"'"))
|
||
(("^findStaticOrShared\\('bam', hts_lib")
|
||
(string-append "findStaticOrShared('bam', '"
|
||
(assoc-ref inputs "samtools")
|
||
"/lib'"))
|
||
;; Do not distribute README.
|
||
(("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
|
||
#t))
|
||
(delete 'configure)
|
||
(replace 'build
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(mkdir (assoc-ref outputs "out"))
|
||
(zero? (system* "scons"
|
||
(string-append
|
||
"PREFIX="
|
||
(assoc-ref outputs "out"))
|
||
(string-append
|
||
"BOOST_ROOT="
|
||
(assoc-ref inputs "boost"))
|
||
"install"))))
|
||
;; Check and install are carried out during build phase.
|
||
(delete 'check)
|
||
(delete 'install))))
|
||
(inputs
|
||
`(("zlib" ,zlib)
|
||
("perl" ,perl)
|
||
("samtools" ,samtools)
|
||
("htslib" ,htslib)
|
||
("boost" ,boost)))
|
||
(native-inputs
|
||
`(("scons" ,scons)))
|
||
(home-page "https://bitbucket.org/berkeleylab/metabat")
|
||
(synopsis
|
||
"Reconstruction of single genomes from complex microbial communities")
|
||
(description
|
||
"Grouping large genomic fragments assembled from shotgun metagenomic
|
||
sequences to deconvolute complex microbial communities, or metagenome binning,
|
||
enables the study of individual organisms and their interactions. MetaBAT is
|
||
an automated metagenome binning software, which integrates empirical
|
||
probabilistic distances of genome abundance and tetranucleotide frequency.")
|
||
(license (license:non-copyleft "file://license.txt"
|
||
"See license.txt in the distribution."))))
|
||
|
||
(define-public miso
|
||
(package
|
||
(name "miso")
|
||
(version "0.5.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/m/misopy/misopy-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(substitute* "setup.py"
|
||
;; Use setuptools, or else the executables are not
|
||
;; installed.
|
||
(("distutils.core") "setuptools")
|
||
;; use "gcc" instead of "cc" for compilation
|
||
(("^defines")
|
||
"cc.set_executables(
|
||
compiler='gcc',
|
||
compiler_so='gcc',
|
||
linker_exe='gcc',
|
||
linker_so='gcc -shared'); defines")))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; only Python 2 is supported
|
||
#:tests? #f)) ; no "test" target
|
||
(inputs
|
||
`(("samtools" ,samtools)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-scipy" ,python2-scipy)
|
||
("python-matplotlib" ,python2-matplotlib)))
|
||
(native-inputs
|
||
`(("python-mock" ,python2-mock) ;for tests
|
||
("python-pytz" ,python2-pytz) ;for tests
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "http://genes.mit.edu/burgelab/miso/index.html")
|
||
(synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
|
||
(description
|
||
"MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
|
||
the expression level of alternatively spliced genes from RNA-Seq data, and
|
||
identifies differentially regulated isoforms or exons across samples. By
|
||
modeling the generative process by which reads are produced from isoforms in
|
||
RNA-Seq, the MISO model uses Bayesian inference to compute the probability
|
||
that a read originated from a particular isoform.")
|
||
(license license:gpl2)))
|
||
|
||
(define-public muscle
|
||
(package
|
||
(name "muscle")
|
||
(version "3.8.1551")
|
||
(source (origin
|
||
(method url-fetch/tarbomb)
|
||
(file-name (string-append name "-" version))
|
||
(uri (string-append
|
||
"http://www.drive5.com/muscle/muscle_src_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:make-flags (list "LDLIBS = -lm")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'check
|
||
;; There are no tests, so just test if it runs.
|
||
(lambda _ (zero? (system* "./muscle" "-version"))))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin")))
|
||
(install-file "muscle" bin)))))))
|
||
(home-page "http://www.drive5.com/muscle")
|
||
(synopsis "Multiple sequence alignment program")
|
||
(description
|
||
"MUSCLE aims to be a fast and accurate multiple sequence alignment
|
||
program for nucleotide and protein sequences.")
|
||
;; License information found in 'muscle -h' and usage.cpp.
|
||
(license license:public-domain)))
|
||
|
||
(define-public orfm
|
||
(package
|
||
(name "orfm")
|
||
(version "0.5.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/wwood/OrfM/releases/download/v"
|
||
version "/orfm-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
|
||
(build-system gnu-build-system)
|
||
(inputs `(("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("ruby-bio-commandeer" ,ruby-bio-commandeer)
|
||
("ruby-rspec" ,ruby-rspec)
|
||
("ruby" ,ruby)))
|
||
(synopsis "Simple and not slow open reading frame (ORF) caller")
|
||
(description
|
||
"An ORF caller finds stretches of DNA that, when translated, are not
|
||
interrupted by stop codons. OrfM finds and prints these ORFs.")
|
||
(home-page "https://github.com/wwood/OrfM")
|
||
(license license:lgpl3+)))
|
||
|
||
(define-public python2-pbcore
|
||
(package
|
||
(name "python2-pbcore")
|
||
(version "1.2.8")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "pbcore" version))
|
||
(sha256
|
||
(base32
|
||
"02pfn5raa3zf739672bg0dkx7z3j2c4nx7vmpfjqy5b12jrqpymk"))))
|
||
(build-system python-build-system)
|
||
(arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
|
||
(inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-h5py" ,python2-h5py)))
|
||
(native-inputs
|
||
`(("python-docutils" ,python2-docutils)
|
||
("python-nose" ,python2-nose)
|
||
("python-setuptools" ,python2-setuptools)
|
||
("python-sphinx" ,python2-sphinx)))
|
||
(home-page "http://pacificbiosciences.github.io/pbcore/")
|
||
(synopsis "Library for reading and writing PacBio data files")
|
||
(description
|
||
"The pbcore package provides Python APIs for interacting with PacBio data
|
||
files and writing bioinformatics applications.")
|
||
(license license:bsd-3)))
|
||
|
||
(define-public python2-warpedlmm
|
||
(package
|
||
(name "python2-warpedlmm")
|
||
(version "0.21")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
|
||
version ".zip"))
|
||
(sha256
|
||
(base32
|
||
"1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; requires Python 2.7
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after
|
||
'install 'remove-bin-directory
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
;; The "bin" directory only contains wrappers for running
|
||
;; the module tests. They are not needed after the
|
||
;; "check" phase.
|
||
(delete-file-recursively
|
||
(string-append (assoc-ref outputs "out") "/bin"))
|
||
#t)))))
|
||
(propagated-inputs
|
||
`(("python-scipy" ,python2-scipy)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-matplotlib" ,python2-matplotlib)
|
||
("python-fastlmm" ,python2-fastlmm)
|
||
("python-pandas" ,python2-pandas)
|
||
("python-pysnptools" ,python2-pysnptools)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools)
|
||
("python-mock" ,python2-mock)
|
||
("python-nose" ,python2-nose)
|
||
("unzip" ,unzip)))
|
||
(home-page "https://github.com/PMBio/warpedLMM")
|
||
(synopsis "Implementation of warped linear mixed models")
|
||
(description
|
||
"WarpedLMM is a Python implementation of the warped linear mixed model,
|
||
which automatically learns an optimal warping function (or transformation) for
|
||
the phenotype as it models the data.")
|
||
(license license:asl2.0)))
|
||
|
||
(define-public pbtranscript-tofu
|
||
(let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
|
||
(package
|
||
(name "pbtranscript-tofu")
|
||
(version (string-append "2.2.3." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/PacificBiosciences/cDNA_primer.git")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; remove bundled Cython sources
|
||
(delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
|
||
#t))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2
|
||
;; With standard flags, the install phase attempts to create a zip'd
|
||
;; egg file, and fails with an error: 'ZIP does not support timestamps
|
||
;; before 1980'
|
||
#:configure-flags '("--single-version-externally-managed"
|
||
"--record=pbtranscript-tofu.txt")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'enter-directory
|
||
(lambda _
|
||
(chdir "pbtranscript-tofu/pbtranscript/")
|
||
#t))
|
||
;; With setuptools version 18.0 and later this setup.py hack causes
|
||
;; a build error, so we disable it.
|
||
(add-after 'enter-directory 'patch-setuppy
|
||
(lambda _
|
||
(substitute* "setup.py"
|
||
(("if 'setuptools.extension' in sys.modules:")
|
||
"if False:"))
|
||
#t)))))
|
||
(inputs
|
||
`(("python-numpy" ,python2-numpy)
|
||
("python-bx-python" ,python2-bx-python)
|
||
("python-networkx" ,python2-networkx)
|
||
("python-scipy" ,python2-scipy)
|
||
("python-pbcore" ,python2-pbcore)
|
||
("python-h5py" ,python2-h5py)))
|
||
(native-inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-nose" ,python2-nose)
|
||
("python-setuptools" ,python2-setuptools)))
|
||
(home-page "https://github.com/PacificBiosciences/cDNA_primer")
|
||
(synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
|
||
(description
|
||
"pbtranscript-tofu contains scripts to analyze transcriptome data
|
||
generated using the PacBio Iso-Seq protocol.")
|
||
(license license:bsd-3))))
|
||
|
||
(define-public prank
|
||
(package
|
||
(name "prank")
|
||
(version "150803")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://wasabiapp.org/download/prank/prank.source."
|
||
version ".tgz"))
|
||
(sha256
|
||
(base32
|
||
"0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'enter-src-dir
|
||
(lambda _
|
||
(chdir "src")
|
||
#t))
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(man (string-append out "/share/man/man1"))
|
||
(path (string-append
|
||
(assoc-ref %build-inputs "mafft") "/bin:"
|
||
(assoc-ref %build-inputs "exonerate") "/bin:"
|
||
(assoc-ref %build-inputs "bppsuite") "/bin")))
|
||
(install-file "prank" bin)
|
||
(wrap-program (string-append bin "/prank")
|
||
`("PATH" ":" prefix (,path)))
|
||
(install-file "prank.1" man))
|
||
#t)))))
|
||
(inputs
|
||
`(("mafft" ,mafft)
|
||
("exonerate" ,exonerate)
|
||
("bppsuite" ,bppsuite)))
|
||
(home-page "http://wasabiapp.org/software/prank/")
|
||
(synopsis "Probabilistic multiple sequence alignment program")
|
||
(description
|
||
"PRANK is a probabilistic multiple sequence alignment program for DNA,
|
||
codon and amino-acid sequences. It is based on a novel algorithm that treats
|
||
insertions correctly and avoids over-estimation of the number of deletion
|
||
events. In addition, PRANK borrows ideas from maximum likelihood methods used
|
||
in phylogenetics and correctly takes into account the evolutionary distances
|
||
between sequences. Lastly, PRANK allows for defining a potential structure
|
||
for sequences to be aligned and then, simultaneously with the alignment,
|
||
predicts the locations of structural units in the sequences.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public pyicoteo
|
||
(package
|
||
(name "pyicoteo")
|
||
(version "2.0.7")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
|
||
"pyicoteo/get/v" version ".tar.bz2"))
|
||
(file-name (string-append name "-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; does not work with Python 3
|
||
#:tests? #f)) ; there are no tests
|
||
(inputs
|
||
`(("python2-matplotlib" ,python2-matplotlib)))
|
||
(home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
|
||
(synopsis "Analyze high-throughput genetic sequencing data")
|
||
(description
|
||
"Pyicoteo is a suite of tools for the analysis of high-throughput genetic
|
||
sequencing data. It works with genomic coordinates. There are currently six
|
||
different command-line tools:
|
||
|
||
@enumerate
|
||
@item pyicoregion: for generating exploratory regions automatically;
|
||
@item pyicoenrich: for differential enrichment between two conditions;
|
||
@item pyicoclip: for calling CLIP-Seq peaks without a control;
|
||
@item pyicos: for genomic coordinates manipulation;
|
||
@item pyicoller: for peak calling on punctuated ChIP-Seq;
|
||
@item pyicount: to count how many reads from N experiment files overlap in a
|
||
region file;
|
||
@item pyicotrocol: to combine operations from pyicoteo.
|
||
@end enumerate\n")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public prodigal
|
||
(package
|
||
(name "prodigal")
|
||
(version "2.6.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/hyattpd/Prodigal/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no check target
|
||
#:make-flags (list (string-append "INSTALLDIR="
|
||
(assoc-ref %outputs "out")
|
||
"/bin"))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure))))
|
||
(home-page "http://prodigal.ornl.gov")
|
||
(synopsis "Protein-coding gene prediction for Archaea and Bacteria")
|
||
(description
|
||
"Prodigal runs smoothly on finished genomes, draft genomes, and
|
||
metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
|
||
format. It runs quickly, in an unsupervised fashion, handles gaps, handles
|
||
partial genes, and identifies translation initiation sites.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public roary
|
||
(package
|
||
(name "roary")
|
||
(version "3.6.8")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0g0pzcv8y7n2w8q7c9q0a7s2ghkwci6w8smg9mjw4agad5cd7yaw"))))
|
||
(build-system perl-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(delete 'build)
|
||
(replace 'check
|
||
(lambda _
|
||
;; The tests are not run by default, so we run each test file
|
||
;; directly.
|
||
(setenv "PATH" (string-append (getcwd) "/bin" ":"
|
||
(getenv "PATH")))
|
||
(setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
|
||
(getenv "PERL5LIB")))
|
||
(zero? (length (filter (lambda (file)
|
||
(display file)(display "\n")
|
||
(not (zero? (system* "perl" file))))
|
||
(find-files "t" ".*\\.t$"))))))
|
||
(replace 'install
|
||
;; There is no 'install' target in the Makefile.
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(perl (string-append out "/lib/perl5/site_perl"))
|
||
(roary-plots "contrib/roary_plots"))
|
||
(mkdir-p bin)
|
||
(mkdir-p perl)
|
||
(copy-recursively "bin" bin)
|
||
(copy-recursively "lib" perl)
|
||
#t)))
|
||
(add-after 'install 'wrap-programs
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(perl5lib (getenv "PERL5LIB"))
|
||
(path (getenv "PATH")))
|
||
(for-each (lambda (prog)
|
||
(let ((binary (string-append out "/" prog)))
|
||
(wrap-program binary
|
||
`("PERL5LIB" ":" prefix
|
||
(,(string-append perl5lib ":" out
|
||
"/lib/perl5/site_perl"))))
|
||
(wrap-program binary
|
||
`("PATH" ":" prefix
|
||
(,(string-append path ":" out "/bin"))))))
|
||
(find-files "bin" ".*[^R]$"))
|
||
(let ((file
|
||
(string-append out "/bin/roary-create_pan_genome_plots.R"))
|
||
(r-site-lib (getenv "R_LIBS_SITE"))
|
||
(coreutils-path
|
||
(string-append (assoc-ref inputs "coreutils") "/bin")))
|
||
(wrap-program file
|
||
`("R_LIBS_SITE" ":" prefix
|
||
(,(string-append r-site-lib ":" out "/site-library/"))))
|
||
(wrap-program file
|
||
`("PATH" ":" prefix
|
||
(,(string-append coreutils-path ":" out "/bin"))))))
|
||
#t)))))
|
||
(native-inputs
|
||
`(("perl-env-path" ,perl-env-path)
|
||
("perl-test-files" ,perl-test-files)
|
||
("perl-test-most" ,perl-test-most)
|
||
("perl-test-output" ,perl-test-output)))
|
||
(inputs
|
||
`(("perl-array-utils" ,perl-array-utils)
|
||
("bioperl" ,bioperl-minimal)
|
||
("perl-exception-class" ,perl-exception-class)
|
||
("perl-file-find-rule" ,perl-file-find-rule)
|
||
("perl-file-grep" ,perl-file-grep)
|
||
("perl-file-slurper" ,perl-file-slurper)
|
||
("perl-file-which" ,perl-file-which)
|
||
("perl-graph" ,perl-graph)
|
||
("perl-graph-readwrite" ,perl-graph-readwrite)
|
||
("perl-log-log4perl" ,perl-log-log4perl)
|
||
("perl-moose" ,perl-moose)
|
||
("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
|
||
("perl-text-csv" ,perl-text-csv)
|
||
("bedtools" ,bedtools)
|
||
("cd-hit" ,cd-hit)
|
||
("blast+" ,blast+)
|
||
("mcl" ,mcl)
|
||
("parallel" ,parallel)
|
||
("prank" ,prank)
|
||
("mafft" ,mafft)
|
||
("fasttree" ,fasttree)
|
||
("grep" ,grep)
|
||
("sed" ,sed)
|
||
("gawk" ,gawk)
|
||
("r" ,r)
|
||
("r-ggplot2" ,r-ggplot2)
|
||
("coreutils" ,coreutils)))
|
||
(home-page "http://sanger-pathogens.github.io/Roary")
|
||
(synopsis "High speed stand-alone pan genome pipeline")
|
||
(description
|
||
"Roary is a high speed stand alone pan genome pipeline, which takes
|
||
annotated assemblies in GFF3 format (produced by the Prokka program) and
|
||
calculates the pan genome. Using a standard desktop PC, it can analyse
|
||
datasets with thousands of samples, without compromising the quality of the
|
||
results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
|
||
single processor. Roary is not intended for metagenomics or for comparing
|
||
extremely diverse sets of genomes.")
|
||
(license license:gpl3)))
|
||
|
||
(define-public raxml
|
||
(package
|
||
(name "raxml")
|
||
(version "8.2.9")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append
|
||
"https://github.com/stamatak/standard-RAxML/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; There are no tests.
|
||
;; Use 'standard' Makefile rather than SSE or AVX ones.
|
||
#:make-flags (list "-f" "Makefile.HYBRID.gcc")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(executable "raxmlHPC-HYBRID"))
|
||
(install-file executable bin)
|
||
(symlink (string-append bin "/" executable) "raxml"))
|
||
#t)))))
|
||
(inputs
|
||
`(("openmpi" ,openmpi)))
|
||
(home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
|
||
(synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
|
||
(description
|
||
"RAxML is a tool for phylogenetic analysis and post-analysis of large
|
||
phylogenies.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public rsem
|
||
(package
|
||
(name "rsem")
|
||
(version "1.2.20")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
|
||
(patches (search-patches "rsem-makefile.patch"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; remove bundled copy of boost
|
||
(delete-file-recursively "boost")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; No "configure" script.
|
||
;; Do not build bundled samtools library.
|
||
(replace 'configure
|
||
(lambda _
|
||
(substitute* "Makefile"
|
||
(("^all : sam/libbam.a") "all : "))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (string-append (assoc-ref outputs "out")))
|
||
(bin (string-append out "/bin/"))
|
||
(perl (string-append out "/lib/perl5/site_perl")))
|
||
(mkdir-p bin)
|
||
(mkdir-p perl)
|
||
(for-each (lambda (file)
|
||
(copy-file file
|
||
(string-append bin (basename file))))
|
||
(find-files "." "rsem-.*"))
|
||
(copy-file "rsem_perl_utils.pm"
|
||
(string-append perl "/rsem_perl_utils.pm")))
|
||
#t))
|
||
(add-after
|
||
'install 'wrap-program
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
(for-each (lambda (prog)
|
||
(wrap-program (string-append out "/bin/" prog)
|
||
`("PERL5LIB" ":" prefix
|
||
(,(string-append out "/lib/perl5/site_perl")))))
|
||
'("rsem-plot-transcript-wiggles"
|
||
"rsem-calculate-expression"
|
||
"rsem-generate-ngvector"
|
||
"rsem-run-ebseq"
|
||
"rsem-prepare-reference")))
|
||
#t)))))
|
||
(inputs
|
||
`(("boost" ,boost)
|
||
("ncurses" ,ncurses)
|
||
("r" ,r)
|
||
("perl" ,perl)
|
||
("samtools" ,samtools-0.1)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://deweylab.biostat.wisc.edu/rsem/")
|
||
(synopsis "Estimate gene expression levels from RNA-Seq data")
|
||
(description
|
||
"RSEM is a software package for estimating gene and isoform expression
|
||
levels from RNA-Seq data. The RSEM package provides a user-friendly
|
||
interface, supports threads for parallel computation of the EM algorithm,
|
||
single-end and paired-end read data, quality scores, variable-length reads and
|
||
RSPD estimation. In addition, it provides posterior mean and 95% credibility
|
||
interval estimates for expression levels. For visualization, it can generate
|
||
BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public rseqc
|
||
(package
|
||
(name "rseqc")
|
||
(version "2.6.1")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "mirror://sourceforge/rseqc/"
|
||
"RSeQC-" version ".tar.gz"))
|
||
(sha256
|
||
(base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; remove bundled copy of pysam
|
||
(delete-file-recursively "lib/pysam")
|
||
(substitute* "setup.py"
|
||
;; remove dependency on outdated "distribute" module
|
||
(("^from distribute_setup import use_setuptools") "")
|
||
(("^use_setuptools\\(\\)") "")
|
||
;; do not use bundled copy of pysam
|
||
(("^have_pysam = False") "have_pysam = True"))))))
|
||
(build-system python-build-system)
|
||
(arguments `(#:python ,python-2))
|
||
(inputs
|
||
`(("python-cython" ,python2-cython)
|
||
("python-pysam" ,python2-pysam)
|
||
("python-numpy" ,python2-numpy)
|
||
("python-setuptools" ,python2-setuptools)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("python-nose" ,python2-nose)))
|
||
(home-page "http://rseqc.sourceforge.net/")
|
||
(synopsis "RNA-seq quality control package")
|
||
(description
|
||
"RSeQC provides a number of modules that can comprehensively evaluate
|
||
high throughput sequence data, especially RNA-seq data. Some basic modules
|
||
inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
|
||
while RNA-seq specific modules evaluate sequencing saturation, mapped reads
|
||
distribution, coverage uniformity, strand specificity, etc.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public seek
|
||
;; There are no release tarballs. According to the installation
|
||
;; instructions at http://seek.princeton.edu/installation.jsp, the latest
|
||
;; stable release is identified by this changeset ID.
|
||
(let ((changeset "2329130")
|
||
(revision "1"))
|
||
(package
|
||
(name "seek")
|
||
(version (string-append "0-" revision "." changeset))
|
||
(source (origin
|
||
(method hg-fetch)
|
||
(uri (hg-reference
|
||
(url "https://bitbucket.org/libsleipnir/sleipnir")
|
||
(changeset changeset)))
|
||
(sha256
|
||
(base32
|
||
"0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:modules ((srfi srfi-1)
|
||
(guix build gnu-build-system)
|
||
(guix build utils))
|
||
#:phases
|
||
(let ((dirs '("SeekMiner"
|
||
"SeekEvaluator"
|
||
"SeekPrep"
|
||
"Distancer"
|
||
"Data2DB"
|
||
"PCL2Bin")))
|
||
(modify-phases %standard-phases
|
||
(add-before 'configure 'bootstrap
|
||
(lambda _
|
||
(zero? (system* "bash" "gen_auto"))))
|
||
(add-after 'build 'build-additional-tools
|
||
(lambda* (#:key make-flags #:allow-other-keys)
|
||
(every (lambda (dir)
|
||
(with-directory-excursion (string-append "tools/" dir)
|
||
(zero? (apply system* "make" make-flags))))
|
||
dirs)))
|
||
(add-after 'install 'install-additional-tools
|
||
(lambda* (#:key make-flags #:allow-other-keys)
|
||
(fold (lambda (dir result)
|
||
(with-directory-excursion (string-append "tools/" dir)
|
||
(and result
|
||
(zero? (apply system*
|
||
`("make" ,@make-flags "install"))))))
|
||
#t dirs)))))))
|
||
(inputs
|
||
`(("gsl" ,gsl)
|
||
("boost" ,boost)
|
||
("libsvm" ,libsvm)
|
||
("readline" ,readline)
|
||
("gengetopt" ,gengetopt)
|
||
("log4cpp" ,log4cpp)))
|
||
(native-inputs
|
||
`(("autoconf" ,autoconf)
|
||
("automake" ,automake)
|
||
("perl" ,perl)))
|
||
(home-page "http://seek.princeton.edu")
|
||
(synopsis "Gene co-expression search engine")
|
||
(description
|
||
"SEEK is a computational gene co-expression search engine. SEEK provides
|
||
biologists with a way to navigate the massive human expression compendium that
|
||
now contains thousands of expression datasets. SEEK returns a robust ranking
|
||
of co-expressed genes in the biological area of interest defined by the user's
|
||
query genes. It also prioritizes thousands of expression datasets according
|
||
to the user's query of interest.")
|
||
(license license:cc-by3.0))))
|
||
|
||
(define-public samtools
|
||
(package
|
||
(name "samtools")
|
||
(version "1.3.1")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "mirror://sourceforge/samtools/samtools/"
|
||
version "/samtools-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:modules ((ice-9 ftw)
|
||
(ice-9 regex)
|
||
(guix build gnu-build-system)
|
||
(guix build utils))
|
||
#:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
|
||
#:configure-flags (list "--with-ncurses")
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'patch-tests
|
||
(lambda _
|
||
(substitute* "test/test.pl"
|
||
;; The test script calls out to /bin/bash
|
||
(("/bin/bash") (which "bash")))
|
||
#t)
|
||
(alist-cons-after
|
||
'install 'install-library
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((lib (string-append (assoc-ref outputs "out") "/lib")))
|
||
(install-file "libbam.a" lib)))
|
||
(alist-cons-after
|
||
'install 'install-headers
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((include (string-append (assoc-ref outputs "out")
|
||
"/include/samtools/")))
|
||
(for-each (lambda (file)
|
||
(install-file file include))
|
||
(scandir "." (lambda (name) (string-match "\\.h$" name))))
|
||
#t))
|
||
%standard-phases)))))
|
||
(native-inputs `(("pkg-config" ,pkg-config)))
|
||
(inputs `(("ncurses" ,ncurses)
|
||
("perl" ,perl)
|
||
("python" ,python)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://samtools.sourceforge.net")
|
||
(synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
|
||
(description
|
||
"Samtools implements various utilities for post-processing nucleotide
|
||
sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
|
||
variant calling (in conjunction with bcftools), and a simple alignment
|
||
viewer.")
|
||
(license license:expat)))
|
||
|
||
(define-public samtools-0.1
|
||
;; This is the most recent version of the 0.1 line of samtools. The input
|
||
;; and output formats differ greatly from that used and produced by samtools
|
||
;; 1.x and is still used in many bioinformatics pipelines.
|
||
(package (inherit samtools)
|
||
(version "0.1.19")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "mirror://sourceforge/samtools/samtools/"
|
||
version "/samtools-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
,@(substitute-keyword-arguments (package-arguments samtools)
|
||
((#:make-flags flags)
|
||
`(cons "LIBCURSES=-lncurses" ,flags))
|
||
((#:phases phases)
|
||
`(modify-phases ,phases
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append
|
||
(assoc-ref outputs "out") "/bin")))
|
||
(mkdir-p bin)
|
||
(copy-file "samtools"
|
||
(string-append bin "/samtools")))))
|
||
(delete 'patch-tests)
|
||
(delete 'configure))))))))
|
||
|
||
(define-public mosaik
|
||
(let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
|
||
(package
|
||
(name "mosaik")
|
||
(version "2.2.30")
|
||
(source (origin
|
||
;; There are no release tarballs nor tags.
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/wanpinglee/MOSAIK.git")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version))
|
||
(sha256
|
||
(base32
|
||
"17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; no tests
|
||
#:make-flags (list "CC=gcc")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(replace 'configure
|
||
(lambda _ (chdir "src") #t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out")
|
||
"/bin")))
|
||
(mkdir-p bin)
|
||
(copy-recursively "../bin" bin)
|
||
#t))))))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("zlib" ,zlib)))
|
||
(supported-systems '("x86_64-linux"))
|
||
(home-page "https://code.google.com/p/mosaik-aligner/")
|
||
(synopsis "Map nucleotide sequence reads to reference genomes")
|
||
(description
|
||
"MOSAIK is a program for mapping second and third-generation sequencing
|
||
reads to a reference genome. MOSAIK can align reads generated by all the
|
||
major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
|
||
Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
|
||
;; MOSAIK is released under the GPLv2+ with the exception of third-party
|
||
;; code released into the public domain:
|
||
;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
|
||
;; 2. MD5 implementation - RSA Data Security, RFC 1321
|
||
(license (list license:gpl2+ license:public-domain)))))
|
||
|
||
(define-public ngs-sdk
|
||
(package
|
||
(name "ngs-sdk")
|
||
(version "1.2.3")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "https://github.com/ncbi/ngs/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"15074fdi94c6pjy83hhk22r86kfvzpaz2i07h3rqg9yy6x3w0pk2"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f ; not supported
|
||
#:tests? #f ; no "check" target
|
||
#:phases
|
||
(alist-replace
|
||
'configure
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
;; The 'configure' script doesn't recognize things like
|
||
;; '--enable-fast-install'.
|
||
(zero? (system* "./configure"
|
||
(string-append "--build-prefix=" (getcwd) "/build")
|
||
(string-append "--prefix=" out)))))
|
||
(alist-cons-after
|
||
'unpack 'enter-dir
|
||
(lambda _ (chdir "ngs-sdk") #t)
|
||
%standard-phases))))
|
||
(native-inputs `(("perl" ,perl)))
|
||
;; According to the test
|
||
;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
|
||
;; in ngs-sdk/setup/konfigure.perl
|
||
(supported-systems '("i686-linux" "x86_64-linux"))
|
||
(home-page "https://github.com/ncbi/ngs")
|
||
(synopsis "API for accessing Next Generation Sequencing data")
|
||
(description
|
||
"NGS is a domain-specific API for accessing reads, alignments and pileups
|
||
produced from Next Generation Sequencing. The API itself is independent from
|
||
any particular back-end implementation, and supports use of multiple back-ends
|
||
simultaneously.")
|
||
(license license:public-domain)))
|
||
|
||
(define-public java-ngs
|
||
(package (inherit ngs-sdk)
|
||
(name "java-ngs")
|
||
(arguments
|
||
`(,@(substitute-keyword-arguments
|
||
`(#:modules ((guix build gnu-build-system)
|
||
(guix build utils)
|
||
(srfi srfi-1)
|
||
(srfi srfi-26))
|
||
,@(package-arguments ngs-sdk))
|
||
((#:phases phases)
|
||
`(modify-phases ,phases
|
||
(replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
|
||
(inputs
|
||
`(("jdk" ,icedtea "jdk")
|
||
("ngs-sdk" ,ngs-sdk)))
|
||
(synopsis "Java bindings for NGS SDK")))
|
||
|
||
(define-public ncbi-vdb
|
||
(package
|
||
(name "ncbi-vdb")
|
||
(version "2.5.7")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "https://github.com/ncbi/ncbi-vdb/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0hay5hy8ynva3mi5wbn4wmq1q23qwxc3aqzbb86hg3x4f1r73270"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f ; not supported
|
||
#:tests? #f ; no "check" target
|
||
#:phases
|
||
(alist-replace
|
||
'configure
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
(let ((out (assoc-ref outputs "out")))
|
||
;; Override include path for libmagic
|
||
(substitute* "setup/package.prl"
|
||
(("name => 'magic', Include => '/usr/include'")
|
||
(string-append "name=> 'magic', Include => '"
|
||
(assoc-ref inputs "libmagic")
|
||
"/include" "'")))
|
||
|
||
;; Install kdf5 library (needed by sra-tools)
|
||
(substitute* "build/Makefile.install"
|
||
(("LIBRARIES_TO_INSTALL =")
|
||
"LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
|
||
|
||
;; The 'configure' script doesn't recognize things like
|
||
;; '--enable-fast-install'.
|
||
(zero? (system*
|
||
"./configure"
|
||
(string-append "--build-prefix=" (getcwd) "/build")
|
||
(string-append "--prefix=" (assoc-ref outputs "out"))
|
||
(string-append "--debug")
|
||
(string-append "--with-xml2-prefix="
|
||
(assoc-ref inputs "libxml2"))
|
||
(string-append "--with-ngs-sdk-prefix="
|
||
(assoc-ref inputs "ngs-sdk"))
|
||
(string-append "--with-ngs-java-prefix="
|
||
(assoc-ref inputs "java-ngs"))
|
||
(string-append "--with-hdf5-prefix="
|
||
(assoc-ref inputs "hdf5"))))))
|
||
(alist-cons-after
|
||
'install 'install-interfaces
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
;; Install interface libraries. On i686 the interface libraries
|
||
;; are installed to "linux/gcc/i386", so we need to use the Linux
|
||
;; architecture name ("i386") instead of the target system prefix
|
||
;; ("i686").
|
||
(mkdir (string-append (assoc-ref outputs "out") "/ilib"))
|
||
(copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
|
||
,(system->linux-architecture
|
||
(or (%current-target-system)
|
||
(%current-system)))
|
||
"/rel/ilib")
|
||
(string-append (assoc-ref outputs "out")
|
||
"/ilib"))
|
||
;; Install interface headers
|
||
(copy-recursively "interfaces"
|
||
(string-append (assoc-ref outputs "out")
|
||
"/include")))
|
||
%standard-phases))))
|
||
(inputs
|
||
`(("libxml2" ,libxml2)
|
||
("ngs-sdk" ,ngs-sdk)
|
||
("java-ngs" ,java-ngs)
|
||
("libmagic" ,file)
|
||
("hdf5" ,hdf5)))
|
||
(native-inputs `(("perl" ,perl)))
|
||
(home-page "https://github.com/ncbi/ncbi-vdb")
|
||
(synopsis "Database engine for genetic information")
|
||
(description
|
||
"The NCBI-VDB library implements a highly compressed columnar data
|
||
warehousing engine that is most often used to store genetic information.
|
||
Databases are stored in a portable image within the file system, and can be
|
||
accessed/downloaded on demand across HTTP.")
|
||
(license license:public-domain)))
|
||
|
||
(define-public plink
|
||
(package
|
||
(name "plink")
|
||
(version "1.07")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
|
||
version "-src.zip"))
|
||
(sha256
|
||
(base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
|
||
(patches (search-patches "plink-1.07-unclobber-i.patch"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f ;no "check" target
|
||
#:make-flags (list (string-append "LIB_LAPACK="
|
||
(assoc-ref %build-inputs "lapack")
|
||
"/lib/liblapack.so")
|
||
"WITH_LAPACK=1"
|
||
"FORCE_DYNAMIC=1"
|
||
;; disable phoning home
|
||
"WITH_WEBCHECK=")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; no "configure" script
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out")
|
||
"/bin/")))
|
||
(install-file "plink" bin)
|
||
#t))))))
|
||
(inputs
|
||
`(("zlib" ,zlib)
|
||
("lapack" ,lapack)))
|
||
(native-inputs
|
||
`(("unzip" ,unzip)))
|
||
(home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
|
||
(synopsis "Whole genome association analysis toolset")
|
||
(description
|
||
"PLINK is a whole genome association analysis toolset, designed to
|
||
perform a range of basic, large-scale analyses in a computationally efficient
|
||
manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
|
||
so there is no support for steps prior to this (e.g. study design and
|
||
planning, generating genotype or CNV calls from raw data). Through
|
||
integration with gPLINK and Haploview, there is some support for the
|
||
subsequent visualization, annotation and storage of results.")
|
||
;; Code is released under GPLv2, except for fisher.h, which is under
|
||
;; LGPLv2.1+
|
||
(license (list license:gpl2 license:lgpl2.1+))))
|
||
|
||
(define-public smithlab-cpp
|
||
(let ((revision "1")
|
||
(commit "728a097bec88c6f4b8528b685932049e660eff2e"))
|
||
(package
|
||
(name "smithlab-cpp")
|
||
(version (string-append "0." revision "." (string-take commit 7)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/smithlabcode/smithlab_cpp.git")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:modules ((guix build gnu-build-system)
|
||
(guix build utils)
|
||
(srfi srfi-26))
|
||
#:tests? #f ;no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'use-samtools-headers
|
||
(lambda _
|
||
(substitute* '("SAM.cpp"
|
||
"SAM.hpp")
|
||
(("sam.h") "samtools/sam.h"))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(lib (string-append out "/lib"))
|
||
(include (string-append out "/include/smithlab-cpp")))
|
||
(mkdir-p lib)
|
||
(mkdir-p include)
|
||
(for-each (cut install-file <> lib)
|
||
(find-files "." "\\.o$"))
|
||
(for-each (cut install-file <> include)
|
||
(find-files "." "\\.hpp$")))
|
||
#t))
|
||
(delete 'configure))))
|
||
(inputs
|
||
`(("samtools" ,samtools-0.1)
|
||
("zlib" ,zlib)))
|
||
(home-page "https://github.com/smithlabcode/smithlab_cpp")
|
||
(synopsis "C++ helper library for functions used in Smith lab projects")
|
||
(description
|
||
"Smithlab CPP is a C++ library that includes functions used in many of
|
||
the Smith lab bioinformatics projects, such as a wrapper around Samtools data
|
||
structures, classes for genomic regions, mapped sequencing reads, etc.")
|
||
(license license:gpl3+))))
|
||
|
||
(define-public preseq
|
||
(package
|
||
(name "preseq")
|
||
(version "2.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/smithlabcode/"
|
||
"preseq/archive/v" version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
;; Remove bundled samtools.
|
||
'(delete-file-recursively "samtools"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure))
|
||
#:make-flags
|
||
(list (string-append "PREFIX="
|
||
(assoc-ref %outputs "out"))
|
||
(string-append "LIBBAM="
|
||
(assoc-ref %build-inputs "samtools")
|
||
"/lib/libbam.a")
|
||
(string-append "SMITHLAB_CPP="
|
||
(assoc-ref %build-inputs "smithlab-cpp")
|
||
"/lib")
|
||
"PROGS=preseq"
|
||
"INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
|
||
(inputs
|
||
`(("gsl" ,gsl)
|
||
("samtools" ,samtools-0.1)
|
||
("smithlab-cpp" ,smithlab-cpp)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://smithlabresearch.org/software/preseq/")
|
||
(synopsis "Program for analyzing library complexity")
|
||
(description
|
||
"The preseq package is aimed at predicting and estimating the complexity
|
||
of a genomic sequencing library, equivalent to predicting and estimating the
|
||
number of redundant reads from a given sequencing depth and how many will be
|
||
expected from additional sequencing using an initial sequencing experiment.
|
||
The estimates can then be used to examine the utility of further sequencing,
|
||
optimize the sequencing depth, or to screen multiple libraries to avoid low
|
||
complexity samples.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public python-screed
|
||
(package
|
||
(name "python-screed")
|
||
(version "0.9")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "screed" version))
|
||
(sha256
|
||
(base32
|
||
"18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(replace 'check
|
||
(lambda _
|
||
(setenv "PYTHONPATH"
|
||
(string-append (getenv "PYTHONPATH") ":."))
|
||
(zero? (system* "nosetests" "--attr" "!known_failing")))))))
|
||
(native-inputs
|
||
`(("python-nose" ,python-nose)))
|
||
(inputs
|
||
`(("python-bz2file" ,python-bz2file)))
|
||
(home-page "http://github.com/dib-lab/screed/")
|
||
(synopsis "Short read sequence database utilities")
|
||
(description "Screed parses FASTA and FASTQ files and generates databases.
|
||
Values such as sequence name, sequence description, sequence quality and the
|
||
sequence itself can be retrieved from these databases.")
|
||
(license license:bsd-3)))
|
||
|
||
(define-public python2-screed
|
||
(let ((base (package-with-python2 (strip-python2-variant python-screed))))
|
||
(package
|
||
(inherit base)
|
||
(native-inputs `(("python2-setuptools" ,python2-setuptools)
|
||
,@(package-native-inputs base))))))
|
||
|
||
(define-public sra-tools
|
||
(package
|
||
(name "sra-tools")
|
||
(version "2.5.7")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri
|
||
(string-append "https://github.com/ncbi/sra-tools/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0q93qg744x787d08qmjmdafki1wkbvkdwynayjnjd454gkd26jl5"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:parallel-build? #f ; not supported
|
||
#:tests? #f ; no "check" target
|
||
#:phases
|
||
(alist-replace
|
||
'configure
|
||
(lambda* (#:key inputs outputs #:allow-other-keys)
|
||
;; The build system expects a directory containing the sources and
|
||
;; raw build output of ncbi-vdb, including files that are not
|
||
;; installed. Since we are building against an installed version of
|
||
;; ncbi-vdb, the following modifications are needed.
|
||
(substitute* "setup/konfigure.perl"
|
||
;; Make the configure script look for the "ilib" directory of
|
||
;; "ncbi-vdb" without first checking for the existence of a
|
||
;; matching library in its "lib" directory.
|
||
(("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
|
||
"my $f = File::Spec->catdir($ilibdir, $ilib);")
|
||
;; Look for interface libraries in ncbi-vdb's "ilib" directory.
|
||
(("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
|
||
"my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
|
||
|
||
;; The 'configure' script doesn't recognize things like
|
||
;; '--enable-fast-install'.
|
||
(zero? (system*
|
||
"./configure"
|
||
(string-append "--build-prefix=" (getcwd) "/build")
|
||
(string-append "--prefix=" (assoc-ref outputs "out"))
|
||
(string-append "--debug")
|
||
(string-append "--with-fuse-prefix="
|
||
(assoc-ref inputs "fuse"))
|
||
(string-append "--with-magic-prefix="
|
||
(assoc-ref inputs "libmagic"))
|
||
;; TODO: building with libxml2 fails with linker errors
|
||
;; (string-append "--with-xml2-prefix="
|
||
;; (assoc-ref inputs "libxml2"))
|
||
(string-append "--with-ncbi-vdb-sources="
|
||
(assoc-ref inputs "ncbi-vdb"))
|
||
(string-append "--with-ncbi-vdb-build="
|
||
(assoc-ref inputs "ncbi-vdb"))
|
||
(string-append "--with-ngs-sdk-prefix="
|
||
(assoc-ref inputs "ngs-sdk"))
|
||
(string-append "--with-hdf5-prefix="
|
||
(assoc-ref inputs "hdf5")))))
|
||
%standard-phases)))
|
||
(native-inputs `(("perl" ,perl)))
|
||
(inputs
|
||
`(("ngs-sdk" ,ngs-sdk)
|
||
("ncbi-vdb" ,ncbi-vdb)
|
||
("libmagic" ,file)
|
||
("fuse" ,fuse)
|
||
("hdf5" ,hdf5)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
|
||
(synopsis "Tools and libraries for reading and writing sequencing data")
|
||
(description
|
||
"The SRA Toolkit from NCBI is a collection of tools and libraries for
|
||
reading of sequencing files from the Sequence Read Archive (SRA) database and
|
||
writing files into the .sra format.")
|
||
(license license:public-domain)))
|
||
|
||
(define-public seqan
|
||
(package
|
||
(name "seqan")
|
||
(version "1.4.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "http://packages.seqan.de/seqan-library/"
|
||
"seqan-library-" version ".tar.bz2"))
|
||
(sha256
|
||
(base32
|
||
"05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
|
||
;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
|
||
;; makes sense to split the outputs.
|
||
(outputs '("out" "doc"))
|
||
(build-system trivial-build-system)
|
||
(arguments
|
||
`(#:modules ((guix build utils))
|
||
#:builder
|
||
(begin
|
||
(use-modules (guix build utils))
|
||
(let ((tar (assoc-ref %build-inputs "tar"))
|
||
(bzip (assoc-ref %build-inputs "bzip2"))
|
||
(out (assoc-ref %outputs "out"))
|
||
(doc (assoc-ref %outputs "doc")))
|
||
(setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
|
||
(system* "tar" "xvf" (assoc-ref %build-inputs "source"))
|
||
(chdir (string-append "seqan-library-" ,version))
|
||
(copy-recursively "include" (string-append out "/include"))
|
||
(copy-recursively "share" (string-append doc "/share"))))))
|
||
(native-inputs
|
||
`(("source" ,source)
|
||
("tar" ,tar)
|
||
("bzip2" ,bzip2)))
|
||
(home-page "http://www.seqan.de")
|
||
(synopsis "Library for nucleotide sequence analysis")
|
||
(description
|
||
"SeqAn is a C++ library of efficient algorithms and data structures for
|
||
the analysis of sequences with the focus on biological data. It contains
|
||
algorithms and data structures for string representation and their
|
||
manipulation, online and indexed string search, efficient I/O of
|
||
bioinformatics file formats, sequence alignment, and more.")
|
||
(license license:bsd-3)))
|
||
|
||
(define-public seqmagick
|
||
(package
|
||
(name "seqmagick")
|
||
(version "0.6.1")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
|
||
`(#:python ,python-2
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; Current test in setup.py does not work as of 0.6.1,
|
||
;; so use nose to run tests instead for now. See
|
||
;; https://github.com/fhcrc/seqmagick/issues/55
|
||
(replace 'check (lambda _ (zero? (system* "nosetests")))))))
|
||
(inputs
|
||
`(("python-biopython" ,python2-biopython)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python2-setuptools)
|
||
("python-nose" ,python2-nose)))
|
||
(home-page "http://github.com/fhcrc/seqmagick")
|
||
(synopsis "Tools for converting and modifying sequence files")
|
||
(description
|
||
"Bioinformaticians often have to convert sequence files between formats
|
||
and do little manipulations on them, and it's not worth writing scripts for
|
||
that. Seqmagick is a utility to expose the file format conversion in
|
||
BioPython in a convenient way. Instead of having a big mess of scripts, there
|
||
is one that takes arguments.")
|
||
(license license:gpl3)))
|
||
|
||
(define-public snap-aligner
|
||
(package
|
||
(name "snap-aligner")
|
||
(version "1.0beta.18")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/amplab/snap/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'check (lambda _ (zero? (system* "./unit_tests"))))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin")))
|
||
(mkdir-p bin)
|
||
(install-file "snap-aligner" bin)
|
||
(install-file "SNAPCommand" bin)
|
||
#t))))))
|
||
(native-inputs
|
||
`(("zlib" ,zlib)))
|
||
(home-page "http://snap.cs.berkeley.edu/")
|
||
(synopsis "Short read DNA sequence aligner")
|
||
(description
|
||
"SNAP is a fast and accurate aligner for short DNA reads. It is
|
||
optimized for modern read lengths of 100 bases or higher, and takes advantage
|
||
of these reads to align data quickly through a hash-based indexing scheme.")
|
||
;; 32-bit systems are not supported by the unpatched code.
|
||
;; Following the bug reports https://github.com/amplab/snap/issues/68 and
|
||
;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
|
||
;; systems without a lot of memory cannot make good use of this program.
|
||
(supported-systems '("x86_64-linux"))
|
||
(license license:asl2.0)))
|
||
|
||
(define-public sortmerna
|
||
(package
|
||
(name "sortmerna")
|
||
(version "2.1b")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/biocore/sortmerna/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
|
||
(build-system gnu-build-system)
|
||
(outputs '("out" ;for binaries
|
||
"db")) ;for sequence databases
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin"))
|
||
(db (assoc-ref outputs "db"))
|
||
(share
|
||
(string-append db "/share/sortmerna/rRNA_databases")))
|
||
(install-file "sortmerna" bin)
|
||
(install-file "indexdb_rna" bin)
|
||
(for-each (lambda (file)
|
||
(install-file file share))
|
||
(find-files "rRNA_databases" ".*fasta"))
|
||
#t))))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
|
||
(synopsis "Biological sequence analysis tool for NGS reads")
|
||
(description
|
||
"SortMeRNA is a biological sequence analysis tool for filtering, mapping
|
||
and operational taxonomic unit (OTU) picking of next generation
|
||
sequencing (NGS) reads. The core algorithm is based on approximate seeds and
|
||
allows for fast and sensitive analyses of nucleotide sequences. The main
|
||
application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
|
||
(license license:lgpl3)))
|
||
|
||
(define-public star
|
||
(package
|
||
(name "star")
|
||
(version "2.5.2a")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/alexdobin/STAR/archive/"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0xjlsm4p9flln111hv4xx7xy94c2nl53zvdvbk9winmiradjsdra"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
(substitute* "source/Makefile"
|
||
(("/bin/rm") "rm"))
|
||
;; Remove pre-built binaries and bundled htslib sources.
|
||
(delete-file-recursively "bin/MacOSX_x86_64")
|
||
(delete-file-recursively "bin/Linux_x86_64")
|
||
(delete-file-recursively "source/htslib")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
'(#:tests? #f ;no check target
|
||
#:make-flags '("STAR")
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'enter-source-dir
|
||
(lambda _ (chdir "source") #t))
|
||
(add-after 'enter-source-dir 'do-not-use-bundled-htslib
|
||
(lambda _
|
||
(substitute* "Makefile"
|
||
(("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
|
||
_ prefix) prefix))
|
||
(substitute* '("BAMfunctions.cpp"
|
||
"signalFromBAM.h"
|
||
"bam_cat.h"
|
||
"bam_cat.c"
|
||
"STAR.cpp"
|
||
"bamRemoveDuplicates.cpp")
|
||
(("#include \"htslib/([^\"]+\\.h)\"" _ header)
|
||
(string-append "#include <" header ">")))
|
||
(substitute* "IncludeDefine.h"
|
||
(("\"htslib/(htslib/[^\"]+.h)\"" _ header)
|
||
(string-append "<" header ">")))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
|
||
(install-file "STAR" bin))
|
||
#t))
|
||
(delete 'configure))))
|
||
(native-inputs
|
||
`(("vim" ,vim))) ; for xxd
|
||
(inputs
|
||
`(("htslib" ,htslib)
|
||
("zlib" ,zlib)))
|
||
(home-page "https://github.com/alexdobin/STAR")
|
||
(synopsis "Universal RNA-seq aligner")
|
||
(description
|
||
"The Spliced Transcripts Alignment to a Reference (STAR) software is
|
||
based on a previously undescribed RNA-seq alignment algorithm that uses
|
||
sequential maximum mappable seed search in uncompressed suffix arrays followed
|
||
by seed clustering and stitching procedure. In addition to unbiased de novo
|
||
detection of canonical junctions, STAR can discover non-canonical splices and
|
||
chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
|
||
sequences.")
|
||
;; Only 64-bit systems are supported according to the README.
|
||
(supported-systems '("x86_64-linux" "mips64el-linux"))
|
||
;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
|
||
(license license:gpl3+)))
|
||
|
||
(define-public subread
|
||
(package
|
||
(name "subread")
|
||
(version "1.4.6-p2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://sourceforge/subread/subread-"
|
||
version "/subread-" version "-source.tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"06sv9mpcsdj6p68y15d6gi70lca3lxmzk0dn61hg0kfsa7rxmsr3"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no "check" target
|
||
;; The CC and CCFLAGS variables are set to contain a lot of x86_64
|
||
;; optimizations by default, so we override these flags such that x86_64
|
||
;; flags are only added when the build target is an x86_64 system.
|
||
#:make-flags
|
||
(list (let ((system ,(or (%current-target-system)
|
||
(%current-system)))
|
||
(flags '("-ggdb" "-fomit-frame-pointer"
|
||
"-ffast-math" "-funroll-loops"
|
||
"-fmessage-length=0"
|
||
"-O9" "-Wall" "-DMAKE_FOR_EXON"
|
||
"-DMAKE_STANDALONE"
|
||
"-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
|
||
(flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
|
||
(if (string-prefix? "x86_64" system)
|
||
(string-append "CCFLAGS=" (string-join (append flags flags64)))
|
||
(string-append "CCFLAGS=" (string-join flags))))
|
||
"-f" "Makefile.Linux"
|
||
"CC=gcc ${CCFLAGS}")
|
||
#:phases
|
||
(alist-cons-after
|
||
'unpack 'enter-dir
|
||
(lambda _ (chdir "src") #t)
|
||
(alist-replace
|
||
'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
|
||
(mkdir-p bin)
|
||
(copy-recursively "../bin" bin)))
|
||
;; no "configure" script
|
||
(alist-delete 'configure %standard-phases)))))
|
||
(inputs `(("zlib" ,zlib)))
|
||
(home-page "http://bioinf.wehi.edu.au/subread-package/")
|
||
(synopsis "Tool kit for processing next-gen sequencing data")
|
||
(description
|
||
"The subread package contains the following tools: subread aligner, a
|
||
general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
|
||
and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
|
||
features; exactSNP: a SNP caller that discovers SNPs by testing signals
|
||
against local background noises.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public stringtie
|
||
(package
|
||
(name "stringtie")
|
||
(version "1.2.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
|
||
"stringtie-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
(delete-file-recursively "samtools-0.1.18")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no test suite
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; no configure script
|
||
(delete 'configure)
|
||
(add-before 'build 'use-system-samtools
|
||
(lambda _
|
||
(substitute* "Makefile"
|
||
(("stringtie: \\$\\{BAM\\}/libbam\\.a")
|
||
"stringtie: "))
|
||
(substitute* '("gclib/GBam.h"
|
||
"gclib/GBam.cpp")
|
||
(("#include \"(bam|sam|kstring).h\"" _ header)
|
||
(string-append "#include <samtools/" header ".h>")))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
|
||
(install-file "stringtie" bin)
|
||
#t))))))
|
||
(inputs
|
||
`(("samtools" ,samtools-0.1)
|
||
("zlib" ,zlib)))
|
||
(home-page "http://ccb.jhu.edu/software/stringtie/")
|
||
(synopsis "Transcript assembly and quantification for RNA-Seq data")
|
||
(description
|
||
"StringTie is a fast and efficient assembler of RNA-Seq sequence
|
||
alignments into potential transcripts. It uses a novel network flow algorithm
|
||
as well as an optional de novo assembly step to assemble and quantitate
|
||
full-length transcripts representing multiple splice variants for each gene
|
||
locus. Its input can include not only the alignments of raw reads used by
|
||
other transcript assemblers, but also alignments of longer sequences that have
|
||
been assembled from those reads. To identify differentially expressed genes
|
||
between experiments, StringTie's output can be processed either by the
|
||
Cuffdiff or Ballgown programs.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public vcftools
|
||
(package
|
||
(name "vcftools")
|
||
(version "0.1.14")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/vcftools/vcftools/releases/download/v"
|
||
version "/vcftools-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; no "check" target
|
||
#:make-flags (list
|
||
"CFLAGS=-O2" ; override "-m64" flag
|
||
(string-append "PREFIX=" (assoc-ref %outputs "out"))
|
||
(string-append "MANDIR=" (assoc-ref %outputs "out")
|
||
"/share/man/man1"))))
|
||
(native-inputs
|
||
`(("pkg-config" ,pkg-config)))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("zlib" ,zlib)))
|
||
(home-page "https://vcftools.github.io/")
|
||
(synopsis "Tools for working with VCF files")
|
||
(description
|
||
"VCFtools is a program package designed for working with VCF files, such
|
||
as those generated by the 1000 Genomes Project. The aim of VCFtools is to
|
||
provide easily accessible methods for working with complex genetic variation
|
||
data in the form of VCF files.")
|
||
;; The license is declared as LGPLv3 in the README and
|
||
;; at https://vcftools.github.io/license.html
|
||
(license license:lgpl3)))
|
||
|
||
(define-public r-vegan
|
||
(package
|
||
(name "r-vegan")
|
||
(version "2.4-0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (cran-uri "vegan" version))
|
||
(sha256
|
||
(base32
|
||
"10cygzkyg2m0y054ygivqxrkvqz792qsg6bmbdfzaqq37qv4wc7z"))))
|
||
(build-system r-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'revert-test-deletion
|
||
;; The distributed sources do not include tests with the CRAN
|
||
;; package. Here we revert the commit
|
||
;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
|
||
;; tests. There are plans to not delete tests in future as
|
||
;; documented at https://github.com/vegandevs/vegan/issues/181.
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(zero?
|
||
(system* "patch" "-R" "-p1" "-i"
|
||
(assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
|
||
(native-inputs
|
||
`(("gfortran" ,gfortran)
|
||
("r-knitr" ,r-knitr)
|
||
("r-vegan-delete-tests-patch"
|
||
,(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/vegandevs/vegan/commit/"
|
||
"591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
|
||
(sha256
|
||
(base32
|
||
"0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
|
||
(propagated-inputs
|
||
`(("r-cluster" ,r-cluster)
|
||
("r-lattice" ,r-lattice)
|
||
("r-mgcv" ,r-mgcv)
|
||
("r-permute" ,r-permute)))
|
||
(home-page "https://cran.r-project.org/web/packages/vegan")
|
||
(synopsis "Functions for community ecology")
|
||
(description
|
||
"The vegan package provides tools for descriptive community ecology. It
|
||
has most basic functions of diversity analysis, community ordination and
|
||
dissimilarity analysis. Most of its multivariate tools can be used for other
|
||
data types as well.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public vsearch
|
||
(package
|
||
(name "vsearch")
|
||
(version "2.0.1")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append
|
||
"https://github.com/torognes/vsearch/archive/v"
|
||
version ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0q7szwbf7r29yxkhb415a8i51vj87kvl5ap7h09w7k9ycb2ywvzw"))
|
||
(modules '((guix build utils)))
|
||
(snippet
|
||
'(begin
|
||
;; Remove bundled cityhash and '-mtune=native'.
|
||
(substitute* "src/Makefile.am"
|
||
(("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
|
||
-O3 -mtune=native -Wall -Wsign-compare")
|
||
(string-append "AM_CXXFLAGS=-lcityhash"
|
||
" -O3 -Wall -Wsign-compare"))
|
||
(("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
|
||
"__top_builddir__bin_vsearch_SOURCES = \\")
|
||
(("^city.h \\\\") "\\")
|
||
(("^citycrc.h \\\\") "\\")
|
||
(("^libcityhash_a.*") "")
|
||
(("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
|
||
libcityhash.a")
|
||
"noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
|
||
(("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
|
||
libcpu_sse2.a libcityhash.a")
|
||
"__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
|
||
libcpu_sse2.a -lcityhash"))
|
||
(substitute* "src/vsearch.h"
|
||
(("^\\#include \"city.h\"") "#include <city.h>")
|
||
(("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
|
||
(delete-file "src/city.h")
|
||
(delete-file "src/citycrc.h")
|
||
(delete-file "src/city.cc")
|
||
#t))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-before 'configure 'autogen
|
||
(lambda _ (zero? (system* "autoreconf" "-vif")))))))
|
||
(inputs
|
||
`(("zlib" ,zlib)
|
||
("bzip2" ,bzip2)
|
||
("cityhash" ,cityhash)))
|
||
(native-inputs
|
||
`(("autoconf" ,autoconf)
|
||
("automake" ,automake)))
|
||
(synopsis "Sequence search tools for metagenomics")
|
||
(description
|
||
"VSEARCH supports DNA sequence searching, clustering, chimera detection,
|
||
dereplication, pairwise alignment, shuffling, subsampling, sorting and
|
||
masking. The tool takes advantage of parallelism in the form of SIMD
|
||
vectorization as well as multiple threads to perform accurate alignments at
|
||
high speed. VSEARCH uses an optimal global aligner (full dynamic programming
|
||
Needleman-Wunsch).")
|
||
(home-page "https://github.com/torognes/vsearch")
|
||
;; vsearch uses non-portable SSE intrinsics so building fails on other
|
||
;; platforms.
|
||
(supported-systems '("x86_64-linux"))
|
||
;; Dual licensed; also includes public domain source.
|
||
(license (list license:gpl3 license:bsd-2))))
|
||
|
||
(define-public pardre
|
||
(package
|
||
(name "pardre")
|
||
(version "1.1.5")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0zkyjzv4s8q2h5npalhirbk17r5b1h0n2a42mh7njzlf047h9bhy"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; no tests included
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin")))
|
||
(mkdir-p bin)
|
||
(install-file "ParDRe" bin)
|
||
#t))))))
|
||
(inputs
|
||
`(("openmpi" ,openmpi)
|
||
("zlib" ,zlib)))
|
||
(synopsis "Parallel tool to remove duplicate DNA reads")
|
||
(description
|
||
"ParDRe is a parallel tool to remove duplicate genetic sequence reads.
|
||
Duplicate reads can be seen as identical or nearly identical sequences with
|
||
some mismatches. This tool lets users avoid the analysis of unnecessary
|
||
reads, reducing the time of subsequent procedures with the
|
||
dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
|
||
in order to exploit the parallel capabilities of multicore clusters. It is
|
||
faster than multithreaded counterparts (end of 2015) for the same number of
|
||
cores and, thanks to the message-passing technology, it can be executed on
|
||
clusters.")
|
||
(home-page "https://sourceforge.net/projects/pardre/")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public ruby-bio-kseq
|
||
(package
|
||
(name "ruby-bio-kseq")
|
||
(version "0.0.2")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (rubygems-uri "bio-kseq" version))
|
||
(sha256
|
||
(base32
|
||
"1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
|
||
(build-system ruby-build-system)
|
||
(arguments
|
||
`(#:test-target "spec"))
|
||
(native-inputs
|
||
`(("bundler" ,bundler)
|
||
("ruby-rspec" ,ruby-rspec)
|
||
("ruby-rake-compiler" ,ruby-rake-compiler)))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
|
||
(description
|
||
"@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
|
||
FASTQ parsing code. It provides a fast iterator over sequences and their
|
||
quality scores.")
|
||
(home-page "https://github.com/gusevfe/bio-kseq")
|
||
(license license:expat)))
|
||
|
||
(define-public bio-locus
|
||
(package
|
||
(name "bio-locus")
|
||
(version "0.0.7")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (rubygems-uri "bio-locus" version))
|
||
(sha256
|
||
(base32
|
||
"02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
|
||
(build-system ruby-build-system)
|
||
(native-inputs
|
||
`(("ruby-rspec" ,ruby-rspec)))
|
||
(synopsis "Tool for fast querying of genome locations")
|
||
(description
|
||
"Bio-locus is a tabix-like tool for fast querying of genome
|
||
locations. Many file formats in bioinformatics contain records that
|
||
start with a chromosome name and a position for a SNP, or a start-end
|
||
position for indels. Bio-locus allows users to store this chr+pos or
|
||
chr+pos+alt information in a database.")
|
||
(home-page "https://github.com/pjotrp/bio-locus")
|
||
(license license:expat)))
|
||
|
||
(define-public bio-blastxmlparser
|
||
(package
|
||
(name "bio-blastxmlparser")
|
||
(version "2.0.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (rubygems-uri "bio-blastxmlparser" version))
|
||
(sha256
|
||
(base32
|
||
"1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
|
||
(build-system ruby-build-system)
|
||
(propagated-inputs
|
||
`(("ruby-bio-logger" ,ruby-bio-logger)
|
||
("ruby-nokogiri" ,ruby-nokogiri)))
|
||
(inputs
|
||
`(("ruby-rspec" ,ruby-rspec)))
|
||
(synopsis "Fast big data BLAST XML parser and library")
|
||
(description
|
||
"Very fast parallel big-data BLAST XML file parser which can be used as
|
||
command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
|
||
generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
|
||
(home-page "http://github.com/pjotrp/blastxmlparser")
|
||
(license license:expat)))
|
||
|
||
(define-public bioruby
|
||
(package
|
||
(name "bioruby")
|
||
(version "1.5.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (rubygems-uri "bio" version))
|
||
(sha256
|
||
(base32
|
||
"01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
|
||
(build-system ruby-build-system)
|
||
(propagated-inputs
|
||
`(("ruby-libxml" ,ruby-libxml)))
|
||
(native-inputs
|
||
`(("which" ,which))) ; required for test phase
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-before 'build 'patch-test-command
|
||
(lambda _
|
||
(substitute* '("test/functional/bio/test_command.rb")
|
||
(("/bin/sh") (which "sh")))
|
||
(substitute* '("test/functional/bio/test_command.rb")
|
||
(("/bin/ls") (which "ls")))
|
||
(substitute* '("test/functional/bio/test_command.rb")
|
||
(("which") (which "which")))
|
||
(substitute* '("test/functional/bio/test_command.rb",
|
||
"test/data/command/echoarg2.sh")
|
||
(("/bin/echo") (which "echo")))
|
||
#t)))))
|
||
(synopsis "Ruby library, shell and utilities for bioinformatics")
|
||
(description "BioRuby comes with a comprehensive set of Ruby development
|
||
tools and libraries for bioinformatics and molecular biology. BioRuby has
|
||
components for sequence analysis, pathway analysis, protein modelling and
|
||
phylogenetic analysis; it supports many widely used data formats and provides
|
||
easy access to databases, external programs and public web services, including
|
||
BLAST, KEGG, GenBank, MEDLINE and GO.")
|
||
(home-page "http://bioruby.org/")
|
||
;; Code is released under Ruby license, except for setup
|
||
;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
|
||
(license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
|
||
|
||
(define-public r-acsnminer
|
||
(package
|
||
(name "r-acsnminer")
|
||
(version "0.16.01.29")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (cran-uri "ACSNMineR" version))
|
||
(sha256
|
||
(base32
|
||
"1b1243wkncanm1blkqzicjgzb576vzcg4iwinsgn2xqr7f264amf"))))
|
||
(properties `((upstream-name . "ACSNMineR")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-ggplot2" ,r-ggplot2)
|
||
("r-gridextra" ,r-gridextra)))
|
||
(home-page "http://cran.r-project.org/web/packages/ACSNMineR")
|
||
(synopsis "Gene enrichment analysis")
|
||
(description
|
||
"This package provides tools to compute and represent gene set enrichment
|
||
or depletion from your data based on pre-saved maps from the @dfn{Atlas of
|
||
Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
|
||
enrichment can be run with hypergeometric test or Fisher exact test, and can
|
||
use multiple corrections. Visualization of data can be done either by
|
||
barplots or heatmaps.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-biocgenerics
|
||
(package
|
||
(name "r-biocgenerics")
|
||
(version "0.18.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "BiocGenerics" version))
|
||
(sha256
|
||
(base32
|
||
"1jjp48vbph09w5bmc7368gjjywsa1lmzfybpiwlypr60b51vlkp6"))))
|
||
(properties
|
||
`((upstream-name . "BiocGenerics")))
|
||
(build-system r-build-system)
|
||
(home-page "http://bioconductor.org/packages/BiocGenerics")
|
||
(synopsis "S4 generic functions for Bioconductor")
|
||
(description
|
||
"This package provides S4 generic functions needed by many Bioconductor
|
||
packages.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-dnacopy
|
||
(package
|
||
(name "r-dnacopy")
|
||
(version "1.46.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "DNAcopy" version))
|
||
(sha256
|
||
(base32
|
||
"0vwv2mndfjpcjp4sybg75abc7xnx8zyw8zjk717k6xh8c33ymcip"))))
|
||
(properties
|
||
`((upstream-name . "DNAcopy")))
|
||
(build-system r-build-system)
|
||
(inputs
|
||
`(("gfortran" ,gfortran)))
|
||
(home-page "https://bioconductor.org/packages/DNAcopy")
|
||
(synopsis "Implementation of a circular binary segmentation algorithm")
|
||
(description "This package implements the circular binary segmentation (CBS)
|
||
algorithm to segment DNA copy number data and identify genomic regions with
|
||
abnormal copy number.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-s4vectors
|
||
(package
|
||
(name "r-s4vectors")
|
||
(version "0.10.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "S4Vectors" version))
|
||
(sha256
|
||
(base32
|
||
"0cvq9yb97cka7lg5nimvzxbz8b2hxkscmjdqb5z23w5c7hrbjffp"))))
|
||
(properties
|
||
`((upstream-name . "S4Vectors")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)))
|
||
(home-page "http://bioconductor.org/packages/S4Vectors")
|
||
(synopsis "S4 implementation of vectors and lists")
|
||
(description
|
||
"The S4Vectors package defines the @code{Vector} and @code{List} virtual
|
||
classes and a set of generic functions that extend the semantic of ordinary
|
||
vectors and lists in R. Package developers can easily implement vector-like
|
||
or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
|
||
In addition, a few low-level concrete subclasses of general interest (e.g.
|
||
@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
|
||
S4Vectors package itself.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-seqinr
|
||
(package
|
||
(name "r-seqinr")
|
||
(version "3.1-3")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (cran-uri "seqinr" version))
|
||
(sha256
|
||
(base32
|
||
"0bbjfwbqg74wsamb3iz01g0ssdpdpg65gh00y9xlnpk4wb990n4n"))))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-ade4" ,r-ade4)))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(home-page "http://seqinr.r-forge.r-project.org/")
|
||
(synopsis "Biological sequences retrieval and analysis")
|
||
(description
|
||
"This package provides tools for exploratory data analysis and data
|
||
visualization of biological sequence (DNA and protein) data. It also includes
|
||
utilities for sequence data management under the ACNUC system.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-iranges
|
||
(package
|
||
(name "r-iranges")
|
||
(version "2.6.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "IRanges" version))
|
||
(sha256
|
||
(base32
|
||
"06pyam3bjjfw2m3l86rda503lsz2jcg645lcnhvrz6qi0nv359yg"))))
|
||
(properties
|
||
`((upstream-name . "IRanges")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-s4vectors" ,r-s4vectors)))
|
||
(home-page "http://bioconductor.org/packages/IRanges")
|
||
(synopsis "Infrastructure for manipulating intervals on sequences")
|
||
(description
|
||
"This package provides efficient low-level and highly reusable S4 classes
|
||
for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
|
||
generally, data that can be organized sequentially (formally defined as
|
||
@code{Vector} objects), as well as views on these @code{Vector} objects.
|
||
Efficient list-like classes are also provided for storing big collections of
|
||
instances of the basic classes. All classes in the package use consistent
|
||
naming and share the same rich and consistent \"Vector API\" as much as
|
||
possible.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-genomeinfodb
|
||
(package
|
||
(name "r-genomeinfodb")
|
||
(version "1.8.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "GenomeInfoDb" version))
|
||
(sha256
|
||
(base32
|
||
"03s2khhdwz06xr58cjpkil935y6p7f6ljqkbkkcai73qxl1k4ica"))))
|
||
(properties
|
||
`((upstream-name . "GenomeInfoDb")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-iranges" ,r-iranges)
|
||
("r-s4vectors" ,r-s4vectors)))
|
||
(home-page "http://bioconductor.org/packages/GenomeInfoDb")
|
||
(synopsis "Utilities for manipulating chromosome identifiers")
|
||
(description
|
||
"This package contains data and functions that define and allow
|
||
translation between different chromosome sequence naming conventions (e.g.,
|
||
\"chr1\" versus \"1\"), including a function that attempts to place sequence
|
||
names in their natural, rather than lexicographic, order.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-edger
|
||
(package
|
||
(name "r-edger")
|
||
(version "3.14.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "edgeR" version))
|
||
(sha256
|
||
(base32
|
||
"14vrygy7rz5ngaap4kgkvr3j18y5l6m742n79h68plk6iqgmsskn"))))
|
||
(properties `((upstream-name . "edgeR")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-limma" ,r-limma)))
|
||
(home-page "http://bioinf.wehi.edu.au/edgeR")
|
||
(synopsis "EdgeR does empirical analysis of digital gene expression data")
|
||
(description "This package can do differential expression analysis of
|
||
RNA-seq expression profiles with biological replication. It implements a range
|
||
of statistical methodology based on the negative binomial distributions,
|
||
including empirical Bayes estimation, exact tests, generalized linear models
|
||
and quasi-likelihood tests. It be applied to differential signal analysis of
|
||
other types of genomic data that produce counts, including ChIP-seq, SAGE and
|
||
CAGE.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-variantannotation
|
||
(package
|
||
(name "r-variantannotation")
|
||
(version "1.18.6")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "VariantAnnotation" version))
|
||
(sha256
|
||
(base32
|
||
"17q2b3wlv3250v6qm114srkarxykpd5rqmg4kzymmqsn1b8hynhv"))))
|
||
(properties
|
||
`((upstream-name . "VariantAnnotation")))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)
|
||
("r-biocgenerics" ,r-biocgenerics)
|
||
("r-bsgenome" ,r-bsgenome)
|
||
("r-dbi" ,r-dbi)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicfeatures" ,r-genomicfeatures)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-summarizedexperiment" ,r-summarizedexperiment)
|
||
("r-rsamtools" ,r-rsamtools)
|
||
("r-zlibbioc" ,r-zlibbioc)))
|
||
(build-system r-build-system)
|
||
(home-page "https://bioconductor.org/packages/VariantAnnotation")
|
||
(synopsis "Package for annotation of genetic variants")
|
||
(description "This R package can annotate variants, compute amino acid
|
||
coding changes and predict coding outcomes.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-limma
|
||
(package
|
||
(name "r-limma")
|
||
(version "3.28.17")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "limma" version))
|
||
(sha256
|
||
(base32
|
||
"124n8dbvl1yy8b1068kqmqszpfhaawk5xfyb73vixma2i66nrcyk"))))
|
||
(build-system r-build-system)
|
||
(home-page "http://bioinf.wehi.edu.au/limma")
|
||
(synopsis "Package for linear models for microarray and RNA-seq data")
|
||
(description "This package can be used for the analysis of gene expression
|
||
studies, especially the use of linear models for analysing designed experiments
|
||
and the assessment of differential expression. The analysis methods apply to
|
||
different technologies, including microarrays, RNA-seq, and quantitative PCR.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-xvector
|
||
(package
|
||
(name "r-xvector")
|
||
(version "0.12.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "XVector" version))
|
||
(sha256
|
||
(base32
|
||
"1kydy9f5y0ihn2mbkamr1kh0g1d3g1k9d7s4i09qgw9ysr6j414v"))))
|
||
(properties
|
||
`((upstream-name . "XVector")))
|
||
(build-system r-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'use-system-zlib
|
||
(lambda _
|
||
(substitute* "DESCRIPTION"
|
||
(("zlibbioc, ") ""))
|
||
(substitute* "NAMESPACE"
|
||
(("import\\(zlibbioc\\)") ""))
|
||
#t)))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-iranges" ,r-iranges)
|
||
("r-s4vectors" ,r-s4vectors)))
|
||
(home-page "http://bioconductor.org/packages/XVector")
|
||
(synopsis "Representation and manpulation of external sequences")
|
||
(description
|
||
"This package provides memory efficient S4 classes for storing sequences
|
||
\"externally\" (behind an R external pointer, or on disk).")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-genomicranges
|
||
(package
|
||
(name "r-genomicranges")
|
||
(version "1.24.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "GenomicRanges" version))
|
||
(sha256
|
||
(base32
|
||
"183kdz76rz93v69k6x684bpwa28xixp83bsyf6xfy182h6vh8x89"))))
|
||
(properties
|
||
`((upstream-name . "GenomicRanges")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/GenomicRanges")
|
||
(synopsis "Representation and manipulation of genomic intervals")
|
||
(description
|
||
"This package provides tools to efficiently represent and manipulate
|
||
genomic annotations and alignments is playing a central role when it comes to
|
||
analyzing high-throughput sequencing data (a.k.a. NGS data). The
|
||
GenomicRanges package defines general purpose containers for storing and
|
||
manipulating genomic intervals and variables defined along a genome.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-biobase
|
||
(package
|
||
(name "r-biobase")
|
||
(version "2.32.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "Biobase" version))
|
||
(sha256
|
||
(base32
|
||
"0q4icv9n5rc2qfkv6k1wjhmfcpzcyr8f45m2z3xharbdv912kl1i"))))
|
||
(properties
|
||
`((upstream-name . "Biobase")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)))
|
||
(home-page "http://bioconductor.org/packages/Biobase")
|
||
(synopsis "Base functions for Bioconductor")
|
||
(description
|
||
"This package provides functions that are needed by many other packages
|
||
on Bioconductor or which replace R functions.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-annotationdbi
|
||
(package
|
||
(name "r-annotationdbi")
|
||
(version "1.34.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "AnnotationDbi" version))
|
||
(sha256
|
||
(base32
|
||
"1k3gfsjrivc7467vg0h705hh4dvzgdhknz62j7zmfxm67qk9r8rq"))))
|
||
(properties
|
||
`((upstream-name . "AnnotationDbi")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biobase" ,r-biobase)
|
||
("r-biocgenerics" ,r-biocgenerics)
|
||
("r-dbi" ,r-dbi)
|
||
("r-iranges" ,r-iranges)
|
||
("r-rsqlite" ,r-rsqlite)
|
||
("r-s4vectors" ,r-s4vectors)))
|
||
(home-page "http://bioconductor.org/packages/AnnotationDbi")
|
||
(synopsis "Annotation database interface")
|
||
(description
|
||
"This package provides user interface and database connection code for
|
||
annotation data packages using SQLite data storage.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-biomart
|
||
(package
|
||
(name "r-biomart")
|
||
(version "2.28.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "biomaRt" version))
|
||
(sha256
|
||
(base32
|
||
"1g0w6an9hkflgyhvq6pmrs92s93qarv23v636b9a4bz771wjvm5v"))))
|
||
(properties
|
||
`((upstream-name . "biomaRt")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)
|
||
("r-rcurl" ,r-rcurl)
|
||
("r-xml" ,r-xml)))
|
||
(home-page "http://bioconductor.org/packages/biomaRt")
|
||
(synopsis "Interface to BioMart databases")
|
||
(description
|
||
"biomaRt provides an interface to a growing collection of databases
|
||
implementing the @url{BioMart software suite, http://www.biomart.org}. The
|
||
package enables retrieval of large amounts of data in a uniform way without
|
||
the need to know the underlying database schemas or write complex SQL queries.
|
||
Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
|
||
Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
|
||
users direct access to a diverse set of data and enable a wide range of
|
||
powerful online queries from gene annotation to database mining.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-biocparallel
|
||
(package
|
||
(name "r-biocparallel")
|
||
(version "1.6.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "BiocParallel" version))
|
||
(sha256
|
||
(base32
|
||
"1gb3lpafhx9wi7wbjdvczdf837qq1arpymcr438jwx39biv9dwb4"))))
|
||
(properties
|
||
`((upstream-name . "BiocParallel")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-futile-logger" ,r-futile-logger)
|
||
("r-snow" ,r-snow)))
|
||
(home-page "http://bioconductor.org/packages/BiocParallel")
|
||
(synopsis "Bioconductor facilities for parallel evaluation")
|
||
(description
|
||
"This package provides modified versions and novel implementation of
|
||
functions for parallel evaluation, tailored to use with Bioconductor
|
||
objects.")
|
||
(license (list license:gpl2+ license:gpl3+))))
|
||
|
||
(define-public r-biostrings
|
||
(package
|
||
(name "r-biostrings")
|
||
(version "2.40.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "Biostrings" version))
|
||
(sha256
|
||
(base32
|
||
"153rfws5sdha324p1nv7jp75ip6ny0f62jzhqcvs46l85h3i8zgh"))))
|
||
(properties
|
||
`((upstream-name . "Biostrings")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-iranges" ,r-iranges)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/Biostrings")
|
||
(synopsis "String objects and algorithms for biological sequences")
|
||
(description
|
||
"This package provides memory efficient string containers, string
|
||
matching algorithms, and other utilities, for fast manipulation of large
|
||
biological sequences or sets of sequences.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-rsamtools
|
||
(package
|
||
(name "r-rsamtools")
|
||
(version "1.24.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "Rsamtools" version))
|
||
(sha256
|
||
(base32
|
||
"0w0drs8cpk8nlazq64ag7nm1w5jd1m8riialivm01hz5zcra7scb"))))
|
||
(properties
|
||
`((upstream-name . "Rsamtools")))
|
||
(build-system r-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'use-system-zlib
|
||
(lambda _
|
||
(substitute* "DESCRIPTION"
|
||
(("zlibbioc, ") ""))
|
||
(substitute* "NAMESPACE"
|
||
(("import\\(zlibbioc\\)") ""))
|
||
#t)))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-biocparallel" ,r-biocparallel)
|
||
("r-biostrings" ,r-biostrings)
|
||
("r-bitops" ,r-bitops)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
|
||
(synopsis "Interface to samtools, bcftools, and tabix")
|
||
(description
|
||
"This package provides an interface to the 'samtools', 'bcftools', and
|
||
'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
|
||
binary variant call (BCF) and compressed indexed tab-delimited (tabix)
|
||
files.")
|
||
(license license:expat)))
|
||
|
||
(define-public r-summarizedexperiment
|
||
(package
|
||
(name "r-summarizedexperiment")
|
||
(version "1.2.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "SummarizedExperiment" version))
|
||
(sha256
|
||
(base32
|
||
"0c43fsrha886sd0diislnlf8r5h5x7fbhphkzcm0rw3k2jz8wlyk"))))
|
||
(properties
|
||
`((upstream-name . "SummarizedExperiment")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biobase" ,r-biobase)
|
||
("r-biocgenerics" ,r-biocgenerics)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-s4vectors" ,r-s4vectors)))
|
||
(home-page "http://bioconductor.org/packages/SummarizedExperiment")
|
||
(synopsis "Container for representing genomic ranges by sample")
|
||
(description
|
||
"The SummarizedExperiment container contains one or more assays, each
|
||
represented by a matrix-like object of numeric or other mode. The rows
|
||
typically represent genomic ranges of interest and the columns represent
|
||
samples.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-genomicalignments
|
||
(package
|
||
(name "r-genomicalignments")
|
||
(version "1.8.4")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "GenomicAlignments" version))
|
||
(sha256
|
||
(base32
|
||
"1cccvalmm83ilk1kpq31ll8kdy9xclsr4pm4mlcc7bmp0rwkd2p2"))))
|
||
(properties
|
||
`((upstream-name . "GenomicAlignments")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-biocparallel" ,r-biocparallel)
|
||
("r-biostrings" ,r-biostrings)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-rsamtools" ,r-rsamtools)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-summarizedexperiment" ,r-summarizedexperiment)))
|
||
(home-page "http://bioconductor.org/packages/GenomicAlignments")
|
||
(synopsis "Representation and manipulation of short genomic alignments")
|
||
(description
|
||
"This package provides efficient containers for storing and manipulating
|
||
short genomic alignments (typically obtained by aligning short reads to a
|
||
reference genome). This includes read counting, computing the coverage,
|
||
junction detection, and working with the nucleotide content of the
|
||
alignments.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-rtracklayer
|
||
(package
|
||
(name "r-rtracklayer")
|
||
(version "1.32.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "rtracklayer" version))
|
||
(sha256
|
||
(base32
|
||
"190767zpwc7maqjpy0x5bpkm0jp1vfawy9991fifw0mc634cjkga"))))
|
||
(build-system r-build-system)
|
||
(arguments
|
||
`(#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'use-system-zlib
|
||
(lambda _
|
||
(substitute* "DESCRIPTION"
|
||
(("zlibbioc, ") ""))
|
||
(substitute* "NAMESPACE"
|
||
(("import\\(zlibbioc\\)") ""))
|
||
#t)))))
|
||
(inputs
|
||
`(("zlib" ,zlib)))
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-biostrings" ,r-biostrings)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicalignments" ,r-genomicalignments)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-rcurl" ,r-rcurl)
|
||
("r-rsamtools" ,r-rsamtools)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-xml" ,r-xml)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/rtracklayer")
|
||
(synopsis "R interface to genome browsers and their annotation tracks")
|
||
(description
|
||
"rtracklayer is an extensible framework for interacting with multiple
|
||
genome browsers (currently UCSC built-in) and manipulating annotation tracks
|
||
in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
|
||
built-in). The user may export/import tracks to/from the supported browsers,
|
||
as well as query and modify the browser state, such as the current viewport.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-genomicfeatures
|
||
(package
|
||
(name "r-genomicfeatures")
|
||
(version "1.24.5")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "GenomicFeatures" version))
|
||
(sha256
|
||
(base32
|
||
"17qpisdgqyjz2mnaiwc4dx7dg11pwq3mkvmkah9zn07g9rhh8f7p"))))
|
||
(properties
|
||
`((upstream-name . "GenomicFeatures")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)
|
||
("r-biobase" ,r-biobase)
|
||
("r-biocgenerics" ,r-biocgenerics)
|
||
("r-biomart" ,r-biomart)
|
||
("r-biostrings" ,r-biostrings)
|
||
("r-dbi" ,r-dbi)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-rcurl" ,r-rcurl)
|
||
("r-rsqlite" ,r-rsqlite)
|
||
("r-rtracklayer" ,r-rtracklayer)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/GenomicFeatures")
|
||
(synopsis "Tools for working with transcript centric annotations")
|
||
(description
|
||
"This package provides a set of tools and methods for making and
|
||
manipulating transcript centric annotations. With these tools the user can
|
||
easily download the genomic locations of the transcripts, exons and cds of a
|
||
given organism, from either the UCSC Genome Browser or a BioMart
|
||
database (more sources will be supported in the future). This information is
|
||
then stored in a local database that keeps track of the relationship between
|
||
transcripts, exons, cds and genes. Flexible methods are provided for
|
||
extracting the desired features in a convenient format.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-go-db
|
||
(package
|
||
(name "r-go-db")
|
||
(version "3.2.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/GO.db_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"00gariag9ampz82dh0xllrc26r85d7vdcwc0vca5zdy147rwxr7f"))))
|
||
(properties
|
||
`((upstream-name . "GO.db")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)))
|
||
(home-page "http://bioconductor.org/packages/GO.db")
|
||
(synopsis "Annotation maps describing the entire Gene Ontology")
|
||
(description
|
||
"The purpose of this GO.db annotation package is to provide detailed
|
||
information about the latest version of the Gene Ontologies.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-graph
|
||
(package
|
||
(name "r-graph")
|
||
(version "1.50.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "graph" version))
|
||
(sha256
|
||
(base32
|
||
"0ys5s19m5r30rlr0fnx2h0z2qw7n2xrad4l2yfb1bbrk8dwyf4pi"))))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)))
|
||
(home-page "http://bioconductor.org/packages/graph")
|
||
(synopsis "Handle graph data structures in R")
|
||
(description
|
||
"This package implements some simple graph handling capabilities for R.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-topgo
|
||
(package
|
||
(name "r-topgo")
|
||
(version "2.24.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "topGO" version))
|
||
(sha256
|
||
(base32
|
||
"1p4vsl32qhjw15yv9ym01ni63gjg73jaghlf17wc4zfn3iaz2zar"))))
|
||
(properties
|
||
`((upstream-name . "topGO")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)
|
||
("r-biobase" ,r-biobase)
|
||
("r-biocgenerics" ,r-biocgenerics)
|
||
("r-go-db" ,r-go-db)
|
||
("r-matrixstats" ,r-matrixstats)
|
||
("r-graph" ,r-graph)
|
||
("r-sparsem" ,r-sparsem)))
|
||
(home-page "http://bioconductor.org/packages/topGO")
|
||
(synopsis "Enrichment analysis for gene ontology")
|
||
(description
|
||
"The topGO package provides tools for testing @dfn{gene ontology} (GO)
|
||
terms while accounting for the topology of the GO graph. Different test
|
||
statistics and different methods for eliminating local similarities and
|
||
dependencies between GO terms can be implemented and applied.")
|
||
;; Any version of the LGPL applies.
|
||
(license license:lgpl2.1+)))
|
||
|
||
(define-public r-bsgenome
|
||
(package
|
||
(name "r-bsgenome")
|
||
(version "1.40.1")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "BSgenome" version))
|
||
(sha256
|
||
(base32
|
||
"0zmlzlcwairka59is5wmkh6knh6j4d328z9fsw3v91fx6gavjl2n"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biocgenerics" ,r-biocgenerics)
|
||
("r-biostrings" ,r-biostrings)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-rsamtools" ,r-rsamtools)
|
||
("r-rtracklayer" ,r-rtracklayer)
|
||
("r-s4vectors" ,r-s4vectors)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/BSgenome")
|
||
(synopsis "Infrastructure for Biostrings-based genome data packages")
|
||
(description
|
||
"This package provides infrastructure shared by all Biostrings-based
|
||
genome data packages and support for efficient SNP representation.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-impute
|
||
(package
|
||
(name "r-impute")
|
||
(version "1.46.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "impute" version))
|
||
(sha256
|
||
(base32
|
||
"0v9ibgv8kp8il52miz7b7z65mv6irqxylx6lfzkxgvxd970dgrz0"))))
|
||
(inputs
|
||
`(("gfortran" ,gfortran)))
|
||
(build-system r-build-system)
|
||
(home-page "http://bioconductor.org/packages/impute")
|
||
(synopsis "Imputation for microarray data")
|
||
(description
|
||
"This package provides a function to impute missing gene expression
|
||
microarray data, using nearest neighbor averaging.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public r-seqpattern
|
||
(package
|
||
(name "r-seqpattern")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "seqPattern" version))
|
||
(sha256
|
||
(base32
|
||
"1dj9hfnbdj11yjxwd8jmxrdkj7n6gmaaj6244g2psgarhjcp4wfb"))))
|
||
(properties
|
||
`((upstream-name . "seqPattern")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biostrings" ,r-biostrings)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-iranges" ,r-iranges)
|
||
("r-plotrix" ,r-plotrix)))
|
||
(home-page "http://bioconductor.org/packages/seqPattern")
|
||
(synopsis "Visualising oligonucleotide patterns and motif occurrences")
|
||
(description
|
||
"This package provides tools to visualize oligonucleotide patterns and
|
||
sequence motif occurrences across a large set of sequences centred at a common
|
||
reference point and sorted by a user defined feature.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public r-genomation
|
||
(package
|
||
(name "r-genomation")
|
||
(version "1.4.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "genomation" version))
|
||
(sha256
|
||
(base32
|
||
"017hxh3yhizlsswd2vw8504arkckrcgq5zraiw67lldq9wzs5qzg"))))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biostrings" ,r-biostrings)
|
||
("r-bsgenome" ,r-bsgenome)
|
||
("r-data-table" ,r-data-table)
|
||
("r-genomeinfodb" ,r-genomeinfodb)
|
||
("r-genomicalignments" ,r-genomicalignments)
|
||
("r-genomicranges" ,r-genomicranges)
|
||
("r-ggplot2" ,r-ggplot2)
|
||
("r-gridbase" ,r-gridbase)
|
||
("r-impute" ,r-impute)
|
||
("r-iranges" ,r-iranges)
|
||
("r-matrixstats" ,r-matrixstats)
|
||
("r-plotrix" ,r-plotrix)
|
||
("r-plyr" ,r-plyr)
|
||
("r-readr" ,r-readr)
|
||
("r-reshape2" ,r-reshape2)
|
||
("r-rsamtools" ,r-rsamtools)
|
||
("r-rtracklayer" ,r-rtracklayer)
|
||
("r-seqpattern" ,r-seqpattern)))
|
||
(home-page "http://bioinformatics.mdc-berlin.de/genomation/")
|
||
(synopsis "Summary, annotation and visualization of genomic data")
|
||
(description
|
||
"This package provides a package for summary and annotation of genomic
|
||
intervals. Users can visualize and quantify genomic intervals over
|
||
pre-defined functional regions, such as promoters, exons, introns, etc. The
|
||
genomic intervals represent regions with a defined chromosome position, which
|
||
may be associated with a score, such as aligned reads from HT-seq experiments,
|
||
TF binding sites, methylation scores, etc. The package can use any tabular
|
||
genomic feature data as long as it has minimal information on the locations of
|
||
genomic intervals. In addition, it can use BAM or BigWig files as input.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-genomationdata
|
||
(package
|
||
(name "r-genomationdata")
|
||
(version "1.4.2")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "https://bioconductor.org/packages/"
|
||
"release/data/experiment/src/contrib/"
|
||
"genomationData_" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1zl7gg144fs7zfycsmq5492sm1bqy7l527xbc2zj04schd9wsan2"))))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than large data files, it doesn't
|
||
;; make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(native-inputs
|
||
`(("r-knitr" ,r-knitr)))
|
||
(home-page "http://bioinformatics.mdc-berlin.de/genomation/")
|
||
(synopsis "Experimental data for use with the genomation package")
|
||
(description
|
||
"This package contains experimental genetic data for use with the
|
||
genomation package. Included are Chip Seq, Methylation and Cage data,
|
||
downloaded from Encode.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public r-org-hs-eg-db
|
||
(package
|
||
(name "r-org-hs-eg-db")
|
||
(version "3.2.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"org.Hs.eg.db_" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0xicgkbh6xkvs74s1piafqac63dyz2ycdyil4pj4ghhxx2sabm6p"))))
|
||
(properties
|
||
`((upstream-name . "org.Hs.eg.db")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)))
|
||
(home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
|
||
(synopsis "Genome wide annotation for Human")
|
||
(description
|
||
"This package provides mappings from Entrez gene identifiers to various
|
||
annotations for the human genome.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-org-ce-eg-db
|
||
(package
|
||
(name "r-org-ce-eg-db")
|
||
(version "3.2.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"org.Ce.eg.db_" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1d0lx00ybq34yqs6mziaa0lrh77xm0ggsmi76g6k95f77gi7m1sw"))))
|
||
(properties
|
||
`((upstream-name . "org.Ce.eg.db")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)))
|
||
(home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
|
||
(synopsis "Genome wide annotation for Worm")
|
||
(description
|
||
"This package provides mappings from Entrez gene identifiers to various
|
||
annotations for the genome of the model worm Caenorhabditis elegans.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-org-dm-eg-db
|
||
(package
|
||
(name "r-org-dm-eg-db")
|
||
(version "3.2.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"org.Dm.eg.db_" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0mib46c7nr00l7mh290n383za9hyl91a1dc6jhjbk884jmxaxyz6"))))
|
||
(properties
|
||
`((upstream-name . "org.Dm.eg.db")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)))
|
||
(home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
|
||
(synopsis "Genome wide annotation for Fly")
|
||
(description
|
||
"This package provides mappings from Entrez gene identifiers to various
|
||
annotations for the genome of the model fruit fly Drosophila melanogaster.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-org-mm-eg-db
|
||
(package
|
||
(name "r-org-mm-eg-db")
|
||
(version "3.2.3")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"org.Mm.eg.db_" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0wh1pm3npdg7070875kfgiid3bqkz3q7rq6snhk6bxfvph00298y"))))
|
||
(properties
|
||
`((upstream-name . "org.Mm.eg.db")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-annotationdbi" ,r-annotationdbi)))
|
||
(home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
|
||
(synopsis "Genome wide annotation for Mouse")
|
||
(description
|
||
"This package provides mappings from Entrez gene identifiers to various
|
||
annotations for the genome of the model mouse Mus musculus.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-seqlogo
|
||
(package
|
||
(name "r-seqlogo")
|
||
(version "1.38.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "seqLogo" version))
|
||
(sha256
|
||
(base32
|
||
"01jddx62nhi3r7czbh9hxy0wwpazbc9ax1fgagfxl6p4kx9xz9rb"))))
|
||
(properties `((upstream-name . "seqLogo")))
|
||
(build-system r-build-system)
|
||
(home-page "http://bioconductor.org/packages/seqLogo")
|
||
(synopsis "Sequence logos for DNA sequence alignments")
|
||
(description
|
||
"seqLogo takes the position weight matrix of a DNA sequence motif and
|
||
plots the corresponding sequence logo as introduced by Schneider and
|
||
Stephens (1990).")
|
||
(license license:lgpl2.0+)))
|
||
|
||
(define-public r-bsgenome-hsapiens-ucsc-hg19
|
||
(package
|
||
(name "r-bsgenome-hsapiens-ucsc-hg19")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"BSgenome.Hsapiens.UCSC.hg19_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than a very large data file it
|
||
;; doesn't make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(propagated-inputs
|
||
`(("r-bsgenome" ,r-bsgenome)))
|
||
(home-page
|
||
"http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
|
||
(synopsis "Full genome sequences for Homo sapiens")
|
||
(description
|
||
"This package provides full genome sequences for Homo sapiens as provided
|
||
by UCSC (hg19, February 2009) and stored in Biostrings objects.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-bsgenome-mmusculus-ucsc-mm9
|
||
(package
|
||
(name "r-bsgenome-mmusculus-ucsc-mm9")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"BSgenome.Mmusculus.UCSC.mm9_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than a very large data file it
|
||
;; doesn't make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(propagated-inputs
|
||
`(("r-bsgenome" ,r-bsgenome)))
|
||
(home-page
|
||
"http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
|
||
(synopsis "Full genome sequences for Mouse")
|
||
(description
|
||
"This package provides full genome sequences for Mus musculus (Mouse) as
|
||
provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-bsgenome-mmusculus-ucsc-mm10
|
||
(package
|
||
(name "r-bsgenome-mmusculus-ucsc-mm10")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"BSgenome.Mmusculus.UCSC.mm10_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than a very large data file it
|
||
;; doesn't make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(propagated-inputs
|
||
`(("r-bsgenome" ,r-bsgenome)))
|
||
(home-page
|
||
"http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
|
||
(synopsis "Full genome sequences for Mouse")
|
||
(description
|
||
"This package provides full genome sequences for Mus
|
||
musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
|
||
in Biostrings objects.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-bsgenome-celegans-ucsc-ce6
|
||
(package
|
||
(name "r-bsgenome-celegans-ucsc-ce6")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"BSgenome.Celegans.UCSC.ce6_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than a very large data file it
|
||
;; doesn't make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(propagated-inputs
|
||
`(("r-bsgenome" ,r-bsgenome)))
|
||
(home-page
|
||
"http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
|
||
(synopsis "Full genome sequences for Worm")
|
||
(description
|
||
"This package provides full genome sequences for Caenorhabditis
|
||
elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
|
||
objects.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-bsgenome-dmelanogaster-ucsc-dm3
|
||
(package
|
||
(name "r-bsgenome-dmelanogaster-ucsc-dm3")
|
||
(version "1.4.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
;; We cannot use bioconductor-uri here because this tarball is
|
||
;; located under "data/annotation/" instead of "bioc/".
|
||
(uri (string-append "http://www.bioconductor.org/packages/"
|
||
"release/data/annotation/src/contrib/"
|
||
"BSgenome.Dmelanogaster.UCSC.dm3_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
|
||
(properties
|
||
`((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
|
||
(build-system r-build-system)
|
||
;; As this package provides little more than a very large data file it
|
||
;; doesn't make sense to build substitutes.
|
||
(arguments `(#:substitutable? #f))
|
||
(propagated-inputs
|
||
`(("r-bsgenome" ,r-bsgenome)))
|
||
(home-page
|
||
"http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
|
||
(synopsis "Full genome sequences for Fly")
|
||
(description
|
||
"This package provides full genome sequences for Drosophila
|
||
melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
|
||
Biostrings objects.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-motifrg
|
||
(package
|
||
(name "r-motifrg")
|
||
(version "1.16.0")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "motifRG" version))
|
||
(sha256
|
||
(base32
|
||
"1ds22paqc0923y6z1fy0arw0wxvvmglfvfgarhywv1qywhq68mbq"))))
|
||
(properties `((upstream-name . "motifRG")))
|
||
(build-system r-build-system)
|
||
(propagated-inputs
|
||
`(("r-biostrings" ,r-biostrings)
|
||
("r-bsgenome" ,r-bsgenome)
|
||
("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
|
||
("r-iranges" ,r-iranges)
|
||
("r-seqlogo" ,r-seqlogo)
|
||
("r-xvector" ,r-xvector)))
|
||
(home-page "http://bioconductor.org/packages/motifRG")
|
||
(synopsis "Discover motifs in high throughput sequencing data")
|
||
(description
|
||
"This package provides tools for discriminative motif discovery in high
|
||
throughput genetic sequencing data sets using regression methods.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public r-qtl
|
||
(package
|
||
(name "r-qtl")
|
||
(version "1.39-5")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (string-append "mirror://cran/src/contrib/qtl_"
|
||
version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
|
||
(build-system r-build-system)
|
||
(home-page "http://rqtl.org/")
|
||
(synopsis "R package for analyzing QTL experiments in genetics")
|
||
(description "R/qtl is an extension library for the R statistics
|
||
system. It is used to analyze experimental crosses for identifying
|
||
genes contributing to variation in quantitative traits (so-called
|
||
quantitative trait loci, QTLs).
|
||
|
||
Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
|
||
identify genotyping errors, and to perform single-QTL and two-QTL,
|
||
two-dimensional genome scans.")
|
||
(license license:gpl3)))
|
||
|
||
(define-public r-zlibbioc
|
||
(package
|
||
(name "r-zlibbioc")
|
||
(version "1.18.0")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (bioconductor-uri "zlibbioc" version))
|
||
(sha256
|
||
(base32
|
||
"0m8l7zpx1l3qsk73k3ibkxxzzff938x3qhnwki1ymf3cnsg8cb36"))))
|
||
(properties
|
||
`((upstream-name . "zlibbioc")))
|
||
(build-system r-build-system)
|
||
(home-page "https://bioconductor.org/packages/zlibbioc")
|
||
(synopsis "Provider for zlib-1.2.5 to R packages")
|
||
(description "This package uses the source code of zlib-1.2.5 to create
|
||
libraries for systems that do not have these available via other means.")
|
||
(license license:artistic2.0)))
|
||
|
||
(define-public emboss
|
||
(package
|
||
(name "emboss")
|
||
(version "6.5.7")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
|
||
(version-major+minor version) ".0/"
|
||
"EMBOSS-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:configure-flags
|
||
(list (string-append "--with-hpdf="
|
||
(assoc-ref %build-inputs "libharu")))
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'fix-checks
|
||
(lambda _
|
||
;; The PNGDRIVER tests check for the presence of libgd, libpng
|
||
;; and zlib, but assume that they are all found at the same
|
||
;; prefix.
|
||
(substitute* "configure.in"
|
||
(("CHECK_PNGDRIVER")
|
||
"LIBS=\"$LIBS -lgd -lpng -lz -lm\"
|
||
AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
|
||
AM_CONDITIONAL(AMPNG, true)"))
|
||
#t))
|
||
(add-after 'unpack 'disable-update-check
|
||
(lambda _
|
||
;; At build time there is no connection to the Internet, so
|
||
;; looking for updates will not work.
|
||
(substitute* "Makefile.am"
|
||
(("\\$\\(bindir\\)/embossupdate") ""))
|
||
#t))
|
||
(add-before 'configure 'autogen
|
||
(lambda _ (zero? (system* "autoreconf" "-vif")))))))
|
||
(inputs
|
||
`(("perl" ,perl)
|
||
("libpng" ,libpng)
|
||
("gd" ,gd)
|
||
("libx11" ,libx11)
|
||
("libharu" ,libharu)
|
||
("zlib" ,zlib)))
|
||
(native-inputs
|
||
`(("autoconf" ,autoconf)
|
||
("automake" ,automake)
|
||
("libtool" ,libtool)
|
||
("pkg-config" ,pkg-config)))
|
||
(home-page "http://emboss.sourceforge.net")
|
||
(synopsis "Molecular biology analysis suite")
|
||
(description "EMBOSS is the \"European Molecular Biology Open Software
|
||
Suite\". EMBOSS is an analysis package specially developed for the needs of
|
||
the molecular biology (e.g. EMBnet) user community. The software
|
||
automatically copes with data in a variety of formats and even allows
|
||
transparent retrieval of sequence data from the web. It also provides a
|
||
number of libraries for the development of software in the field of molecular
|
||
biology. EMBOSS also integrates a range of currently available packages and
|
||
tools for sequence analysis into a seamless whole.")
|
||
(license license:gpl2+)))
|
||
|
||
(define-public bits
|
||
(let ((revision "1")
|
||
(commit "3cc4567896d9d6442923da944beb704750a08d2d"))
|
||
(package
|
||
(name "bits")
|
||
;; The version is 2.13.0 even though no release archives have been
|
||
;; published as yet.
|
||
(version (string-append "2.13.0-" revision "." (string-take commit 9)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/arq5x/bits.git")
|
||
(commit commit)))
|
||
(file-name (string-append name "-" version "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ;no tests included
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure)
|
||
(add-after 'unpack 'remove-cuda
|
||
(lambda _
|
||
(substitute* "Makefile"
|
||
((".*_cuda") "")
|
||
(("(bits_test_intersections) \\\\" _ match) match))
|
||
#t))
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(copy-recursively
|
||
"bin" (string-append (assoc-ref outputs "out") "/bin"))
|
||
#t)))))
|
||
(inputs
|
||
`(("gsl" ,gsl)
|
||
("zlib" ,zlib)))
|
||
(home-page "https://github.com/arq5x/bits")
|
||
(synopsis "Implementation of binary interval search algorithm")
|
||
(description "This package provides an implementation of the
|
||
BITS (Binary Interval Search) algorithm, an approach to interval set
|
||
intersection. It is especially suited for the comparison of diverse genomic
|
||
datasets and the exploration of large datasets of genome
|
||
intervals (e.g. genes, sequence alignments).")
|
||
(license license:gpl2))))
|
||
|
||
(define-public piranha
|
||
;; There is no release tarball for the latest version. The latest commit is
|
||
;; older than one year at the time of this writing.
|
||
(let ((revision "1")
|
||
(commit "0466d364b71117d01e4471b74c514436cc281233"))
|
||
(package
|
||
(name "piranha")
|
||
(version (string-append "1.2.1-" revision "." (string-take commit 9)))
|
||
(source (origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/smithlabcode/piranha.git")
|
||
(commit commit)))
|
||
(sha256
|
||
(base32
|
||
"117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:test-target "test"
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(add-after 'unpack 'copy-smithlab-cpp
|
||
(lambda* (#:key inputs #:allow-other-keys)
|
||
(for-each (lambda (file)
|
||
(install-file file "./src/smithlab_cpp/"))
|
||
(find-files (assoc-ref inputs "smithlab-cpp")))
|
||
#t))
|
||
(add-after 'install 'install-to-store
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let* ((out (assoc-ref outputs "out"))
|
||
(bin (string-append out "/bin")))
|
||
(mkdir-p bin)
|
||
(for-each (lambda (file)
|
||
(install-file file bin))
|
||
(find-files "bin" ".*")))
|
||
#t)))
|
||
#:configure-flags
|
||
(list (string-append "--with-bam_tools_headers="
|
||
(assoc-ref %build-inputs "bamtools") "/include/bamtools")
|
||
(string-append "--with-bam_tools_library="
|
||
(assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
|
||
(inputs
|
||
`(("bamtools" ,bamtools)
|
||
("samtools" ,samtools-0.1)
|
||
("gsl" ,gsl)
|
||
("smithlab-cpp"
|
||
,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
|
||
(origin
|
||
(method git-fetch)
|
||
(uri (git-reference
|
||
(url "https://github.com/smithlabcode/smithlab_cpp.git")
|
||
(commit commit)))
|
||
(file-name (string-append "smithlab_cpp-" commit "-checkout"))
|
||
(sha256
|
||
(base32
|
||
"0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
|
||
(native-inputs
|
||
`(("python" ,python-2)))
|
||
(home-page "https://github.com/smithlabcode/piranha")
|
||
(synopsis "Peak-caller for CLIP-seq and RIP-seq data")
|
||
(description
|
||
"Piranha is a peak-caller for genomic data produced by CLIP-seq and
|
||
RIP-seq experiments. It takes input in BED or BAM format and identifies
|
||
regions of statistically significant read enrichment. Additional covariates
|
||
may optionally be provided to further inform the peak-calling process.")
|
||
(license license:gpl3+))))
|
||
|
||
(define-public pepr
|
||
(package
|
||
(name "pepr")
|
||
(version "1.0.9")
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://pypi.python.org/packages/source/P"
|
||
"/PePr/PePr-" version ".tar.gz"))
|
||
(sha256
|
||
(base32
|
||
"0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
|
||
(build-system python-build-system)
|
||
(arguments
|
||
`(#:python ,python-2 ; python2 only
|
||
#:tests? #f ; no tests included
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
;; When setuptools is used a ".egg" archive is generated and
|
||
;; installed. This makes it hard to actually run PePr. This issue
|
||
;; has been reported upstream:
|
||
;; https://github.com/shawnzhangyx/PePr/issues/9
|
||
(add-after 'unpack 'disable-egg-generation
|
||
(lambda _
|
||
(substitute* "setup.py"
|
||
(("from setuptools import setup")
|
||
"from distutils.core import setup"))
|
||
#t)))))
|
||
(propagated-inputs
|
||
`(("python2-numpy" ,python2-numpy)
|
||
("python2-scipy" ,python2-scipy)
|
||
("python2-pysam" ,python2-pysam)))
|
||
(home-page "https://code.google.com/p/pepr-chip-seq/")
|
||
(synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
|
||
(description
|
||
"PePr is a ChIP-Seq peak calling or differential binding analysis tool
|
||
that is primarily designed for data with biological replicates. It uses a
|
||
negative binomial distribution to model the read counts among the samples in
|
||
the same group, and look for consistent differences between ChIP and control
|
||
group or two ChIP groups run under different conditions.")
|
||
(license license:gpl3+)))
|
||
|
||
(define-public filevercmp
|
||
(let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
|
||
(package
|
||
(name "filevercmp")
|
||
(version (string-append "0-1." (string-take commit 7)))
|
||
(source (origin
|
||
(method url-fetch)
|
||
(uri (string-append "https://github.com/ekg/filevercmp/archive/"
|
||
commit ".tar.gz"))
|
||
(file-name (string-append name "-" version ".tar.gz"))
|
||
(sha256
|
||
(base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
|
||
(build-system gnu-build-system)
|
||
(arguments
|
||
`(#:tests? #f ; There are no tests to run.
|
||
#:phases
|
||
(modify-phases %standard-phases
|
||
(delete 'configure) ; There is no configure phase.
|
||
(replace 'install
|
||
(lambda* (#:key outputs #:allow-other-keys)
|
||
(let ((bin (string-append (assoc-ref outputs "out") "/bin")))
|
||
(install-file "filevercmp" bin)))))))
|
||
(home-page "https://github.com/ekg/filevercmp")
|
||
(synopsis "This program compares version strings")
|
||
(description "This program compares version strings. It intends to be a
|
||
replacement for strverscmp.")
|
||
(license license:gpl3+))))
|
||
|
||
(define-public multiqc
|
||
(package
|
||
(name "multiqc")
|
||
(version "0.6")
|
||
(source
|
||
(origin
|
||
(method url-fetch)
|
||
(uri (pypi-uri "multiqc" version))
|
||
(sha256
|
||
(base32
|
||
"0avw11h63ldpxy5pizc3wl1wa01ha7q10wb240nggsjz3jaqvyiy"))))
|
||
(build-system python-build-system)
|
||
(propagated-inputs
|
||
`(("python-jinja2" ,python-jinja2)
|
||
("python-simplejson" ,python-simplejson)
|
||
("python-pyyaml" ,python-pyyaml)
|
||
("python-click" ,python-click)
|
||
("python-matplotlib" ,python-matplotlib)
|
||
("python-numpy" ,python-numpy)))
|
||
(native-inputs
|
||
`(("python-setuptools" ,python-setuptools)))
|
||
(home-page "http://multiqc.info")
|
||
(synopsis "Aggregate bioinformatics analysis reports")
|
||
(description
|
||
"MultiQC is a tool to aggregate bioinformatics results across many
|
||
samples into a single report. It contains modules for a large number of
|
||
common bioinformatics tools.")
|
||
(license license:gpl3)))
|