#:use-module (gnu packages jemalloc)
#:use-module (gnu packages dlang)
#:use-module (gnu packages linux)
+ #:use-module (gnu packages lisp)
#:use-module (gnu packages logging)
#:use-module (gnu packages machine-learning)
#:use-module (gnu packages man)
(supported-systems '("x86_64-linux"))
(license license:gpl3+)))
+(define-public bowtie1
+ (package
+ (name "bowtie1")
+ (version "1.2.2")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
+ version "/bowtie-" version "-src.zip"))
+ (sha256
+ (base32
+ "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
+ (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)
+ (arguments
+ '(#:tests? #f ; no "check" target
+ #:make-flags
+ (list "all"
+ (string-append "prefix=" (assoc-ref %outputs "out")))
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure))))
+ (inputs
+ `(("tbb" ,tbb)
+ ("zlib" ,zlib)))
+ (supported-systems '("x86_64-linux"))
+ (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
+ (synopsis "Fast aligner for short nucleotide sequence reads")
+ (description
+ "Bowtie is a fast, memory-efficient short read aligner. It aligns short
+DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
+reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
+keep its memory footprint small: typically about 2.2 GB for the human
+genome (2.9 GB for paired-end).")
+ (license license:artistic2.0)))
+
(define-public tophat
(package
(name "tophat")
(supported-systems '("i686-linux" "x86_64-linux"))
(license license:bsd-3)))
+(define-public r-scde
+ (package
+ (name "r-scde")
+ (version "1.99.2")
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/hms-dbmi/scde.git")
+ (commit version)))
+ (file-name (git-file-name name version))
+ (sha256
+ (base32
+ "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
+ (build-system r-build-system)
+ (propagated-inputs
+ `(("r-rcpp" ,r-rcpp)
+ ("r-rcpparmadillo" ,r-rcpparmadillo)
+ ("r-mgcv" ,r-mgcv)
+ ("r-rook" ,r-rook)
+ ("r-rjson" ,r-rjson)
+ ("r-cairo" ,r-cairo)
+ ("r-rcolorbrewer" ,r-rcolorbrewer)
+ ("r-edger" ,r-edger)
+ ("r-quantreg" ,r-quantreg)
+ ("r-nnet" ,r-nnet)
+ ("r-rmtstat" ,r-rmtstat)
+ ("r-extremes" ,r-extremes)
+ ("r-pcamethods" ,r-pcamethods)
+ ("r-biocparallel" ,r-biocparallel)
+ ("r-flexmix" ,r-flexmix)))
+ (home-page "https://hms-dbmi.github.io/scde/")
+ (synopsis "R package for analyzing single-cell RNA-seq data")
+ (description "The SCDE package implements a set of statistical methods for
+analyzing single-cell RNA-seq data. SCDE fits individual error models for
+single-cell RNA-seq measurements. These models can then be used for
+assessment of differential expression between groups of cells, as well as
+other types of analysis. The SCDE package also contains the pagoda framework
+which applies pathway and gene set overdispersion analysis to identify aspects
+of transcriptional heterogeneity among single cells.")
+ ;; See https://github.com/hms-dbmi/scde/issues/38
+ (license license:gpl2)))
+
(define-public r-centipede
(package
(name "r-centipede")
information as possible.")
(license (list license:gpl2+ license:gpl3+))))
-(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-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-genefilter
(package
(name "r-genefilter")
"This package provides a pipeline for the analysis of GRO-seq data.")
(license license:gpl3+)))
-(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-sparql
(package
(name "r-sparql")
that accept short and long options.")
(license license:gpl2+)))
-(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)
- (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")
genome data packages and support for efficient SNP representation.")
(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-impute
(package
(name "r-impute")
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 "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-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-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-txdb-mmusculus-ucsc-mm10-knowngene
(package
(name "r-txdb-mmusculus-ucsc-mm10-knowngene")
based on the knownGene track.")
(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 "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-celegans-ucsc-ce10
(package
(name "r-bsgenome-celegans-ucsc-ce10")
(define-public bismark
(package
(name "bismark")
- (version "0.19.1")
+ (version "0.20.1")
(source
(origin
(method git-fetch)
(file-name (string-append name "-" version "-checkout"))
(sha256
(base32
- "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
- (snippet
- '(begin
- ;; highcharts.js is non-free software. The code is available under
- ;; CC-BY-NC or proprietary licenses only.
- (delete-file "bismark_sitrep/highcharts.js")
- #t))))
+ "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
(build-system perl-build-system)
(arguments
`(#:tests? #f ; there are no tests
+ #:modules ((guix build utils)
+ (ice-9 popen)
+ (srfi srfi-26)
+ (guix build perl-build-system))
#:phases
(modify-phases %standard-phases
+ ;; The bundled plotly.js is minified.
+ (add-after 'unpack 'replace-plotly.js
+ (lambda* (#:key inputs #:allow-other-keys)
+ (let* ((file (assoc-ref inputs "plotly.js"))
+ (installed "plotly/plotly.js"))
+ (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
+ (call-with-output-file installed
+ (cut dump-port minified <>))))
+ #t))
(delete 'configure)
(delete 'build)
(replace 'install
"deduplicate_bismark"
"filter_non_conversion"
"bam2nuc"
- "bismark2summary")))
+ "bismark2summary"
+ "NOMe_filtering")))
(substitute* "bismark2report"
- (("\\$RealBin/bismark_sitrep")
- (string-append share "/bismark_sitrep")))
+ (("\\$RealBin/plotly")
+ (string-append share "/plotly")))
(mkdir-p share)
(mkdir-p docdir)
(mkdir-p bin)
(for-each (lambda (file) (install-file file docdir))
docs)
(copy-recursively "Docs/Images" (string-append docdir "/Images"))
- (copy-recursively "bismark_sitrep"
- (string-append share "/bismark_sitrep"))
+ (copy-recursively "plotly"
+ (string-append share "/plotly"))
;; Fix references to gunzip
(substitute* (map (lambda (file)
"/bin/gunzip -c")))
#t))))))
(inputs
- `(("gzip" ,gzip)))
+ `(("gzip" ,gzip)
+ ("perl-carp" ,perl-carp)
+ ("perl-getopt-long" ,perl-getopt-long)))
+ (native-inputs
+ `(("plotly.js"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
+ "v1.39.4/dist/plotly.js"))
+ (sha256
+ (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
+ ("uglify-js" ,uglify-js)))
(home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
(synopsis "Map bisulfite treated sequence reads and analyze methylation")
(description "Bismark is a program to map bisulfite treated sequencing
(define-public pigx-chipseq
(package
(name "pigx-chipseq")
- (version "0.0.21")
+ (version "0.0.31")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
"/pigx_chipseq-" version ".tar.gz"))
(sha256
(base32
- "0psgdzlnx5xwhlhpss5yvmnl7yv19y9742l97m04f7awd8w74gxs"))))
+ "0l3vd9xwqzap3mmyj8xwqp84kj7scbq308diqnwg2albphl75xqs"))))
(build-system gnu-build-system)
;; parts of the tests rely on access to the network
(arguments '(#:tests? #f))
HTML reports with interesting findings about your samples.")
(license license:gpl3+)))
+(define-public genrich
+ (package
+ (name "genrich")
+ (version "0.5")
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/jsh58/Genrich.git")
+ (commit (string-append "v" version))))
+ (sha256
+ (base32
+ "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:tests? #f ; there are none
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
+ #t)))))
+ (inputs
+ `(("zlib" ,zlib)))
+ (home-page "https://github.com/jsh58/Genrich")
+ (synopsis "Detecting sites of genomic enrichment")
+ (description "Genrich is a peak-caller for genomic enrichment
+assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
+following the assay and produces a file detailing peaks of significant
+enrichment.")
+ (license license:expat)))
+
(define-public mantis
(let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
(revision "1"))
approximate the gradient at each iteration of gradient descent. This package
is a Cython wrapper for FIt-SNE.")
(license license:bsd-4)))
+
+(define-public velvet
+ (package
+ (name "velvet")
+ (version "1.2.10")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
+ "velvet_" version ".tgz"))
+ (sha256
+ (base32
+ "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
+ ;; Delete bundled libraries
+ (modules '((guix build utils)))
+ (snippet
+ '(begin
+ (delete-file "Manual.pdf")
+ (delete-file-recursively "third-party")
+ #t))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:make-flags '("OPENMP=t")
+ #:test-target "test"
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (add-after 'unpack 'fix-zlib-include
+ (lambda _
+ (substitute* "src/binarySequences.c"
+ (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
+ #t))
+ (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/velvet")))
+ (mkdir-p bin)
+ (mkdir-p doc)
+ (install-file "velveth" bin)
+ (install-file "velvetg" bin)
+ (install-file "Manual.pdf" doc)
+ (install-file "Columbus_manual.pdf" doc)
+ #t))))))
+ (inputs
+ `(("openmpi" ,openmpi)
+ ("zlib" ,zlib)))
+ (native-inputs
+ `(("texlive" ,(texlive-union (list texlive-latex-graphics
+ texlive-latex-hyperref)))))
+ (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
+ (synopsis "Nucleic acid sequence assembler for very short reads")
+ (description
+ "Velvet is a de novo genomic assembler specially designed for short read
+sequencing technologies, such as Solexa or 454. Velvet currently takes in
+short read sequences, removes errors then produces high quality unique
+contigs. It then uses paired read information, if available, to retrieve the
+repeated areas between contigs.")
+ (license license:gpl2+)))
HCoop / jackhill / guix / guix.git / blobdiff