;;; GNU Guix --- Functional package management for GNU
-;;; Copyright © 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
-;;; Copyright © 2018 Roel Janssen <roel@gnu.org>
-;;; Copyright © 2018 Tobias Geerinckx-Rice <me@tobias.gr>
+;;; Copyright © 2016, 2017, 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
+;;; Copyright © 2016, 2017, 2018 Roel Janssen <roel@gnu.org>
+;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
;;;
;;; This file is part of GNU Guix.
;;;
#:use-module (gnu packages bioinformatics)
#:use-module (gnu packages cran)
#:use-module (gnu packages compression)
+ #:use-module (gnu packages gcc)
#:use-module (gnu packages graph)
#:use-module (gnu packages maths)
#:use-module (gnu packages statistics)
#:use-module (gnu packages web))
+(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 "https://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
+ "https://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-dm6
(package
(name "r-bsgenome-dmelanogaster-ucsc-dm6")
Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by default.")
(license license:artistic2.0)))
+(define-public r-bsgenome-hsapiens-1000genomes-hs37d5
+ (package
+ (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
+ (version "0.99.1")
+ (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://www.bioconductor.org/packages/"
+ "release/data/annotation/src/contrib/"
+ "BSgenome.Hsapiens.1000genomes.hs37d5_"
+ version ".tar.gz"))
+ (sha256
+ (base32
+ "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
+ (properties
+ `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
+ (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
+ "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
+ (synopsis "Full genome sequences for Homo sapiens")
+ (description
+ "This package provides full genome sequences for Homo sapiens from
+1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
+ (license license:artistic2.0)))
+
(define-public r-bsgenome-hsapiens-ucsc-hg19-masked
(package
(name "r-bsgenome-hsapiens-ucsc-hg19-masked")
default.")
(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 "https://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
+ "https://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-mm9-masked
(package
(name "r-bsgenome-mmusculus-ucsc-mm9-masked")
default." )
(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 "https://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
+ "https://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-org-dr-eg-db
+ (package
+ (name "r-org-dr-eg-db")
+ (version "3.7.0")
+ (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 "https://www.bioconductor.org/packages/"
+ "release/data/annotation/src/contrib/"
+ "org.Dr.eg.db_" version ".tar.gz"))
+ (sha256
+ (base32
+ "1xs5wsbcpy0iwbjyiv7fax57djqc529ai5fk1qfsdcvlja3cpglx"))))
+ (properties
+ `((upstream-name . "org.Dr.eg.db")))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-annotationdbi" ,r-annotationdbi)))
+ (home-page "https://www.bioconductor.org/packages/org.Dr.eg.db/")
+ (synopsis "Annotation for Zebrafish")
+ (description
+ "This package provides genome wide annotations for Zebrafish, primarily
+based on mapping using Entrez Gene identifiers.")
+ (license license:artistic2.0)))
+
+(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 "https://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
+ "https://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-genelendatabase
(package
(name "r-genelendatabase")
genomes and gene ID formats, largely based on the UCSC table browser.")
(license license:lgpl2.0+)))
+(define-public r-txdb-hsapiens-ucsc-hg19-knowngene
+ (package
+ (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
+ (version "3.2.2")
+ (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/annotation/src/contrib"
+ "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
+ version ".tar.gz"))
+ (sha256
+ (base32
+ "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
+ (properties
+ `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
+ (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-genomicfeatures" ,r-genomicfeatures)))
+ (home-page
+ "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
+ (synopsis "Annotation package for human genome in TxDb format")
+ (description
+ "This package provides an annotation database of Homo sapiens genome
+data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
+track. The database is exposed as a @code{TxDb} object.")
+ (license license:artistic2.0)))
+
(define-public r-txdb-mmusculus-ucsc-mm9-knowngene
(package
(name "r-txdb-mmusculus-ucsc-mm9-knowngene")
(license license:artistic2.0)))
\f
+(define-public r-biocgenerics
+ (package
+ (name "r-biocgenerics")
+ (version "0.28.0")
+ (source (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "BiocGenerics" version))
+ (sha256
+ (base32
+ "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
+ (properties
+ `((upstream-name . "BiocGenerics")))
+ (build-system r-build-system)
+ (home-page "https://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-annotate
+ (package
+ (name "r-annotate")
+ (version "1.60.0")
+ (source
+ (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "annotate" version))
+ (sha256
+ (base32
+ "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-annotationdbi" ,r-annotationdbi)
+ ("r-biobase" ,r-biobase)
+ ("r-biocgenerics" ,r-biocgenerics)
+ ("r-dbi" ,r-dbi)
+ ("r-rcurl" ,r-rcurl)
+ ("r-xml" ,r-xml)
+ ("r-xtable" ,r-xtable)))
+ (home-page
+ "https://bioconductor.org/packages/annotate")
+ (synopsis "Annotation for microarrays")
+ (description "This package provides R environments for the annotation of
+microarrays.")
+ (license license:artistic2.0)))
+
(define-public r-hpar
(package
(name "r-hpar")
region sets and other genomic features.")
(license license:artistic2.0)))
+(define-public r-geneplotter
+ (package
+ (name "r-geneplotter")
+ (version "1.60.0")
+ (source
+ (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "geneplotter" version))
+ (sha256
+ (base32
+ "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-annotate" ,r-annotate)
+ ("r-annotationdbi" ,r-annotationdbi)
+ ("r-biobase" ,r-biobase)
+ ("r-biocgenerics" ,r-biocgenerics)
+ ("r-lattice" ,r-lattice)
+ ("r-rcolorbrewer" ,r-rcolorbrewer)))
+ (home-page "https://bioconductor.org/packages/geneplotter")
+ (synopsis "Graphics functions for genomic data")
+ (description
+ "This package provides functions for plotting genomic data.")
+ (license license:artistic2.0)))
+
(define-public r-diffbind
(package
(name "r-diffbind")
"This package provides a quality control pipeline for ChIP-exo/nexus
sequencing data.")
(license license:gpl2+)))
+
+(define-public r-copynumber
+ (package
+ (name "r-copynumber")
+ (version "1.22.0")
+ (source (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "copynumber" version))
+ (sha256
+ (base32
+ "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-s4vectors" ,r-s4vectors)
+ ("r-iranges" ,r-iranges)
+ ("r-genomicranges" ,r-genomicranges)
+ ("r-biocgenerics" ,r-biocgenerics)))
+ (home-page "https://bioconductor.org/packages/copynumber")
+ (synopsis "Segmentation of single- and multi-track copy number data")
+ (description
+ "This package segments single- and multi-track copy number data by a
+penalized least squares regression method.")
+ (license license:artistic2.0)))
+
+(define-public r-dnacopy
+ (package
+ (name "r-dnacopy")
+ (version "1.56.0")
+ (source
+ (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "DNAcopy" version))
+ (sha256
+ (base32
+ "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
+ (properties `((upstream-name . "DNAcopy")))
+ (build-system r-build-system)
+ (native-inputs `(("gfortran" ,gfortran)))
+ (home-page "https://bioconductor.org/packages/DNAcopy")
+ (synopsis "DNA copy number data analysis")
+ (description
+ "This package implements the @dfn{circular binary segmentation} (CBS)
+algorithm to segment DNA copy number data and identify genomic regions with
+abnormal copy number.")
+ (license license:gpl2+)))
+
+;; This is a CRAN package, but it uncharacteristically depends on a
+;; Bioconductor package.
+(define-public r-htscluster
+ (package
+ (name "r-htscluster")
+ (version "2.0.8")
+ (source
+ (origin
+ (method url-fetch)
+ (uri (cran-uri "HTSCluster" version))
+ (sha256
+ (base32
+ "0wnbfh6hdx8692jilgmv8sys1zm6fqc6mim7vvjhyqlmpm8gm0kg"))))
+ (properties `((upstream-name . "HTSCluster")))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-capushe" ,r-capushe)
+ ("r-edger" ,r-edger)
+ ("r-plotrix" ,r-plotrix)))
+ (home-page "https://cran.r-project.org/web/packages/HTSCluster")
+ (synopsis "Clustering high-throughput transcriptome sequencing (HTS) data")
+ (description
+ "This package provides a Poisson mixture model is implemented to cluster
+genes from high-throughput transcriptome sequencing (RNA-seq) data. Parameter
+estimation is performed using either the EM or CEM algorithm, and the slope
+heuristics are used for model selection (i.e., to choose the number of
+clusters).")
+ (license license:gpl3+)))