;;; GNU Guix --- Functional package management for GNU ;;; Copyright © 2014, 2015 Ricardo Wurmus ;;; ;;; 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 . (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 build-system gnu) #:use-module (guix build-system cmake) #:use-module (guix build-system python) #:use-module (guix build-system trivial) #:use-module (gnu packages) #:use-module (gnu packages base) #:use-module (gnu packages compression) #:use-module (gnu packages java) #:use-module (gnu packages maths) #:use-module (gnu packages ncurses) #:use-module (gnu packages perl) #:use-module (gnu packages pkg-config) #:use-module (gnu packages popt) #:use-module (gnu packages python) #:use-module (gnu packages statistics) #:use-module (gnu packages swig) #:use-module (gnu packages tbb) #:use-module (gnu packages vim) #:use-module (gnu packages xml) #:use-module (gnu packages zip)) (define-public bedops (package (name "bedops") (version "2.4.5") (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 "0wmg6j0icimlrnsidaxrzf3hfgjvlkkcwvpdg7n4gg7hdv2m9ni5")))) (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=.*$") "SHELL=bash\n"))) (alist-delete 'configure %standard-phases)))) (home-page "https://github.com/bedops/bedops") (synopsis "Tools for high-performance genomic feature operations") (description "BEDOPS is a suite of tools to address common questions raised in genomic studies---mostly with regard to overlap and proximity relationships between data sets. It aims to be scalable and flexible, facilitating the efficient and accurate analysis and management of large-scale genomic data. BEDOPS provides tools that perform highly efficient and scalable Boolean and other set operations, statistical calculations, archiving, conversion and other management of genomic data of arbitrary scale. Tasks can be easily split by chromosome for distributing whole-genome analyses across a computational cluster.") (license license:gpl2+))) (define-public bedtools (package (name "bedtools") (version "2.22.0") (source (origin (method url-fetch) (uri (string-append "https://github.com/arq5x/bedtools2/archive/v" version ".tar.gz")) (file-name (string-append name "-" version ".tar.gz")) (sha256 (base32 "16aq0w3dmbd0853j32xk9jin4vb6v6fgakfyvrsmsjizzbn3fpfl")))) (build-system gnu-build-system) (native-inputs `(("python" ,python-2))) (inputs `(("samtools" ,samtools) ("zlib" ,zlib))) (arguments '(#:test-target "test" #:phases (alist-cons-after 'unpack 'patch-makefile-SHELL-definition (lambda _ ;; patch-makefile-SHELL cannot be used here as it does not ;; yet patch definitions with `:='. Since changes to ;; patch-makefile-SHELL result in a full rebuild, features ;; of patch-makefile-SHELL are reimplemented here. (substitute* "Makefile" (("^SHELL := .*$") (string-append "SHELL := " (which "bash") " -e \n")))) (alist-delete 'configure (alist-replace 'install (lambda* (#:key outputs #:allow-other-keys) (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) (mkdir-p bin) (for-each (lambda (file) (copy-file file (string-append bin (basename file)))) (find-files "bin" ".*")))) %standard-phases))))) (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))) (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 bowtie (package (name "bowtie") (version "2.2.4") (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 "15dnbqippwvhyh9zqjhaxkabk7lm1xbh1nvar1x4b5kwm117zijn")) (modules '((guix build utils))) (snippet '(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\\\"\""))) (patches (list (search-patch "bowtie-fix-makefile.patch"))))) (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))) (arguments '(#:make-flags '("allall") #:phases (alist-delete 'configure (alist-replace 'install (lambda* (#:key outputs #:allow-other-keys) (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) (mkdir-p bin) (for-each (lambda (file) (copy-file file (string-append bin file))) (find-files "." "bowtie2.*")))) (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 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) (copy-file "bwa" (string-append bin "/bwa")) (copy-file "README.md" (string-append doc "/README.md")) (copy-file "bwa.1" (string-append man "/bwa.1")))) ;; no "configure" script (alist-delete 'configure %standard-phases)))) (inputs `(("zlib" ,zlib))) (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 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 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")) (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 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 "0.1.6") (source (origin (method url-fetch) (uri (string-append "mirror://sourceforge/crossmap/CrossMap-" version ".tar.gz")) (sha256 (base32 "163hi5gjgij6cndxlvbkp5jjwr0k4wbm9im6d2210278q7k9kpnp")) ;; patch has been sent upstream already (patches (list (search-patch "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 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 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 `(;; There is no test target, although there is a directory containing ;; test data and scripts (launched by flexbar_validate.sh). #:tests? #f #:configure-flags (list (string-append "-DFLEXBAR_BINARY_DIR=" (assoc-ref %outputs "out") "/bin/")) #:phases (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 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") "/bin/"))) (mkdir-p bin) (for-each (lambda (file) (copy-file file (string-append bin file))) (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))) (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 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 (inputs `(("python-numpy" ,python2-numpy) ("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 htsjdk (package (name "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 gnu-build-system) (arguments `(#:modules ((srfi srfi-1) (guix build gnu-build-system) (guix build utils)) #:phases (alist-replace 'build (lambda _ (setenv "JAVA_HOME" (assoc-ref %build-inputs "jdk")) (zero? (system* "ant" "all" (string-append "-Ddist=" (assoc-ref %outputs "out") "/share/java/htsjdk/")))) (fold alist-delete %standard-phases '(configure install check))))) (native-inputs `(("ant" ,ant) ("jdk" ,icedtea6 "jdk"))) (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 macs (package (name "macs") (version "2.1.0.20140616") (source (origin (method url-fetch) (uri (string-append "https://pypi.python.org/packages/source/M/MACS2/MACS2-" version ".tar.gz")) (sha256 (base32 "11lmiw6avqhwn75sn59g4lfkrr2kk20r3rgfbx9xfqb8rg9mi2n6")))) (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 miso (package (name "miso") (version "0.5.3") (source (origin (method url-fetch) (uri (string-append "http://pypi.python.org/packages/source/m/misopy/misopy-" version ".tar.gz")) (sha256 (base32 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w")) (modules '((guix build utils))) ;; use "gcc" instead of "cc" for compilation (snippet '(substitute* "setup.py" (("^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-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 python2-pbcore (package (name "python2-pbcore") (version "0.9.3") (source (origin (method url-fetch) (uri (string-append "https://github.com/PacificBiosciences/pbcore/archive/" version ".tar.gz")) (file-name (string-append name "-" version ".tar.gz")) (sha256 (base32 "1z46rwjac93jm87cbj2zgjg6qvsgs65140wkbbxsvxps7ai4pm09")))) (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-setuptools" ,python2-setuptools))) (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 pbtranscript-tofu (let ((commit "c7bbd5472")) (package (name "pbtranscript-tofu") (version (string-append "0.4.1." commit)) (source (origin (method git-fetch) (uri (git-reference (url "https://github.com/PacificBiosciences/cDNA_primer.git") (commit commit))) (file-name (string-append name "-" version ".tar.gz")) (sha256 (base32 "148xkzi689c49g6fdhckp6mnmj2qhjdf1j4wifm6ja7ij95d7fxx")))) (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 (alist-cons-after 'unpack 'enter-directory-and-clean-up (lambda _ (chdir "pbtranscript-tofu/pbtranscript/") ;; Delete clutter (delete-file-recursively "dist/") (delete-file-recursively "build/") (delete-file-recursively "setuptools_cython-0.2.1-py2.6.egg/") (delete-file-recursively "pbtools.pbtranscript.egg-info") (delete-file "Cython-0.20.1.tar.gz") (delete-file "setuptools_cython-0.2.1-py2.7.egg") (delete-file "setuptools_cython-0.2.1.tar.gz") (delete-file "setup.cfg") (for-each delete-file (find-files "." "\\.so$")) ;; files should be writable for install phase (for-each (lambda (f) (chmod f #o755)) (find-files "." "\\.py$"))) %standard-phases))) (inputs `(("python-cython" ,python2-cython) ("python-numpy" ,python2-numpy) ("python-bx-python" ,python2-bx-python) ("python-networkx" ,python2-networkx) ("python-scipy" ,python2-scipy) ("python-pbcore" ,python2-pbcore))) (native-inputs `(("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 rseqc (package (name "rseqc") (version "2.6.1") (source (origin (method url-fetch) (uri (string-append "mirror://sourceforge/rseqc/" version "/RSeQC-" version ".tar.gz")) (sha256 (base32 "09rf0x9d6apjja5l01cgprj7vigpw6kiqhy34ibwwlxil0db0ri4")) (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 samtools (package (name "samtools") (version "1.1") (source (origin (method url-fetch) (uri (string-append "mirror://sourceforge/samtools/" version "/samtools-" version ".tar.bz2")) (sha256 (base32 "1y5p2hs4gif891b4ik20275a8xf3qrr1zh9wpysp4g8m0g1jckf2")))) (build-system gnu-build-system) (arguments `(;; There are 87 test failures when building on non-64-bit architectures ;; due to invalid test data. This has since been fixed upstream (see ;; ), but as there has ;; not been a new release we disable the tests for all non-64-bit ;; systems. #:tests? ,(string=? (or (%current-system) (%current-target-system)) "x86_64-linux") #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out"))) #:phases (alist-cons-after 'unpack 'patch-makefile-curses (lambda _ (substitute* "Makefile" (("-lcurses") "-lncurses"))) (alist-cons-after 'unpack 'patch-tests (lambda* (#:key inputs #:allow-other-keys) (let ((bash (assoc-ref inputs "bash"))) (substitute* "test/test.pl" ;; The test script calls out to /bin/bash (("/bin/bash") (string-append bash "/bin/bash")) ;; There are two failing tests upstream relating to the "stats" ;; subcommand in test_usage_subcommand ("did not have Usage" ;; and "usage did not mention samtools stats"), so we disable ;; them. (("(test_usage_subcommand\\(.*\\);)" cmd) (string-append "unless ($subcommand eq 'stats') {" cmd "};"))))) (alist-delete 'configure %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 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 star (package (name "star") (version "2.4.0j") (source (origin (method url-fetch) (uri (string-append "https://github.com/alexdobin/STAR/archive/STAR_" version ".tar.gz")) (sha256 (base32 "1y3bciych1aw6s7k8sy1saj23dcan9wk4d4f96an499slkxwz712")) (modules '((guix build utils))) (snippet '(substitute* "source/Makefile" (("/bin/rm") "rm"))))) (build-system gnu-build-system) (arguments '(#:tests? #f ;no check target #:make-flags '("STAR") #:phases (alist-cons-after 'unpack 'enter-source-dir (lambda _ (chdir "source")) (alist-replace 'install (lambda* (#:key outputs #:allow-other-keys) (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) (mkdir-p bin) (copy-file "STAR" (string-append bin "STAR")))) (alist-delete 'configure %standard-phases))))) (native-inputs `(("vim" ,vim))) ; for xxd (inputs `(("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.") ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed. (license license:gpl3+))) (define-public shogun (package (name "shogun") (version "4.0.0") (source (origin (method url-fetch) (uri (string-append "ftp://shogun-toolbox.org/shogun/releases/" (version-major+minor version) "/sources/shogun-" version ".tar.bz2")) (sha256 (base32 "159nlijnb7mnrv9za80wnm1shwvy45hgrqzn51hxy7gw4z6d6fdb")))) (build-system cmake-build-system) (arguments '(#:tests? #f ;no check target #:phases (alist-cons-after 'unpack 'delete-broken-symlinks (lambda _ (for-each delete-file '("applications/arts/data" "applications/asp/data" "applications/easysvm/data" "applications/msplicer/data" "applications/ocr/data" "examples/documented/data" "examples/documented/matlab_static" "examples/documented/octave_static" "examples/undocumented/data" "examples/undocumented/matlab_static" "examples/undocumented/octave_static" "tests/integration/data" "tests/integration/matlab_static" "tests/integration/octave_static" "tests/integration/python_modular/tests")) #t) (alist-cons-after 'unpack 'change-R-target-path (lambda* (#:key outputs #:allow-other-keys) (substitute* '("src/interfaces/r_modular/CMakeLists.txt" "src/interfaces/r_static/CMakeLists.txt" "examples/undocumented/r_modular/CMakeLists.txt") (("\\$\\{R_COMPONENT_LIB_PATH\\}") (string-append (assoc-ref outputs "out") "/lib/R/library/"))) #t) (alist-cons-after 'unpack 'fix-octave-modules (lambda* (#:key outputs #:allow-other-keys) (substitute* '("src/interfaces/octave_modular/CMakeLists.txt" "src/interfaces/octave_static/CMakeLists.txt") (("^include_directories\\(\\$\\{OCTAVE_INCLUDE_DIRS\\}") "include_directories(${OCTAVE_INCLUDE_DIRS} ${OCTAVE_INCLUDE_DIRS}/octave")) ;; change target directory (substitute* "src/interfaces/octave_modular/CMakeLists.txt" (("\\$\\{OCTAVE_OCT_LOCAL_API_FILE_DIR\\}") (string-append (assoc-ref outputs "out") "/share/octave/packages"))) #t) (alist-cons-before 'build 'set-HOME ;; $HOME needs to be set at some point during the build phase (lambda _ (setenv "HOME" "/tmp") #t) %standard-phases)))) #:configure-flags (list "-DUSE_SVMLIGHT=OFF" ;disable proprietary SVMLIGHT ;;"-DJavaModular=ON" ;requires unpackaged jblas ;;"-DRubyModular=ON" ;requires unpackaged ruby-narray ;;"-DPerlModular=ON" ;"FindPerlLibs" does not exist ;;"-DLuaModular=ON" ;fails because lua doesn't build pkgconfig file "-DOctaveModular=ON" "-DOctaveStatic=ON" "-DPythonModular=ON" "-DPythonStatic=ON" "-DRModular=ON" "-DRStatic=ON" "-DCmdLineStatic=ON"))) (inputs `(("python" ,python) ("numpy" ,python-numpy) ("r" ,r) ("octave" ,octave) ("swig" ,swig) ("hdf5" ,hdf5) ("atlas" ,atlas) ("arpack" ,arpack-ng) ("lapack" ,lapack) ("glpk" ,glpk) ("libxml2" ,libxml2) ("lzo" ,lzo) ("zlib" ,zlib))) (native-inputs `(("pkg-config" ,pkg-config))) (home-page "http://shogun-toolbox.org/") (synopsis "Machine learning toolbox") (description "The Shogun Machine learning toolbox provides a wide range of unified and efficient Machine Learning (ML) methods. The toolbox seamlessly allows to combine multiple data representations, algorithm classes, and general purpose tools. This enables both rapid prototyping of data pipelines and extensibility in terms of new algorithms.") (license license:gpl3+))) (define-public vcftools (package (name "vcftools") (version "0.1.12b") (source (origin (method url-fetch) (uri (string-append "mirror://sourceforge/vcftools/vcftools_" version ".tar.gz")) (sha256 (base32 "148al9h7f8g8my2qdnpax51kdd2yjrivlx6frvakf4lz5r8j88wx")))) (build-system gnu-build-system) (arguments `(#:tests? #f ; no "check" target #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out")) (string-append "MANDIR=" (assoc-ref %outputs "out") "/share/man/man1")) #:phases (alist-cons-after 'unpack 'patch-manpage-install (lambda _ (substitute* "Makefile" (("cp \\$\\{PREFIX\\}/cpp/vcftools.1") "cp ./cpp/vcftools.1"))) (alist-delete 'configure %standard-phases)))) (inputs `(("perl" ,perl) ("zlib" ,zlib))) (home-page "http://vcftools.sourceforge.net/") (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 http://vcftools.sourceforge.net/license.html (license license:lgpl3)))