diff options
Diffstat (limited to 'gnu/packages/bioinformatics.scm')
| -rw-r--r-- | gnu/packages/bioinformatics.scm | 2178 |
1 files changed, 493 insertions, 1685 deletions
diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm index fc2fc867ac..64fc6173db 100644 --- a/gnu/packages/bioinformatics.scm +++ b/gnu/packages/bioinformatics.scm @@ -122,6 +122,7 @@ #:use-module (gnu packages popt) #:use-module (gnu packages protobuf) #:use-module (gnu packages python) + #:use-module (gnu packages python-build) #:use-module (gnu packages python-check) #:use-module (gnu packages python-compression) #:use-module (gnu packages python-science) @@ -310,6 +311,37 @@ instance, it implements several methods to assess contig-wise read coverage.") BAM files.") (license license:expat))) +(define-public bamutils + (package + (name "bamutils") + (version "1.0.13") + (source (origin + (method url-fetch) + (uri + (string-append + "https://genome.sph.umich.edu/w/images/7/70/" + "BamUtilLibStatGen." version ".tgz")) + (sha256 + (base32 + "0asr1kmjbr3cyf4hkg865y8c2s30v87xvws4q6c8pyfi6wfd1h8n")))) + (build-system gnu-build-system) + (arguments + `(#:tests? #f ; There are no tests. + #:make-flags `("USER_WARNINGS=-std=gnu++98" + ,(string-append "INSTALLDIR=" + (assoc-ref %outputs "out") "/bin")) + #:phases + (modify-phases %standard-phases + (delete 'configure)))) + (inputs + `(("zlib" ,zlib))) + (home-page "https://genome.sph.umich.edu/wiki/BamUtil") + (synopsis "Programs for working on SAM/BAM files") + (description "This package provides several programs that perform +operations on SAM/BAM files. All of these programs are built into a +single executable called @code{bam}.") + (license license:gpl3+))) + (define-public bcftools (package (name "bcftools") @@ -830,6 +862,30 @@ 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 python-htsget + (package + (name "python-htsget") + (version "0.2.5") + (source (origin + (method url-fetch) + (uri (pypi-uri "htsget" version)) + (sha256 + (base32 + "0ic07q85vhw9djf23k57b21my7i5xp400m8gfqgr5gcryqvdr0yk")))) + (build-system python-build-system) + (native-inputs + `(("python-setuptools-scm" ,python-setuptools-scm))) + (propagated-inputs + `(("python-humanize" ,python-humanize) + ("python-requests" ,python-requests) + ("python-six" ,python-six))) + (home-page "https://pypi.org/project/htsget/") + (synopsis "Python API and command line interface for the GA4GH htsget API") + (description "This package is a client implementation of the GA4GH htsget +protocol. It provides a simple and reliable way to retrieve genomic data from +servers supporting the protocol.") + (license license:asl2.0))) + (define-public python-pybedtools (package (name "python-pybedtools") @@ -1942,6 +1998,45 @@ multiple sequence alignments.") (define-public python2-bx-python (package-with-python2 python-bx-python)) +(define-public python-pyega3 + (package + (name "python-pyega3") + (version "3.4.1") + (source (origin + (method url-fetch) + (uri (pypi-uri "pyega3" version)) + (sha256 + (base32 + "1k736in8g27rarx65ym9xk50x53zjg75h37bb8ljynxv04rypx2q")))) + (build-system python-build-system) + (arguments + `(#:tests? #f)) ; The tests require network access. + (native-inputs + `(("python-psutil" ,python-psutil) + ("python-htsget" ,python-htsget))) + (propagated-inputs + `(("python-requests" ,python-requests) + ("python-tqdm" ,python-tqdm) + ("python-urllib3" ,python-urllib3) + ("python-responses" ,python-responses))) + (home-page "https://github.com/EGA-archive/ega-download-client") + (synopsis "Python client for EGA") + (description "This package is a python-based tool for viewing and +downloading files from authorized EGA datasets. It uses the EGA data API and +has several key features: +@itemize +@item Files are transferred over secure https connections and received + unencrypted, so no need for decryption after download. +@item Downloads resume from where they left off in the event that the + connection is interrupted. +@item Supports file segmenting and parallelized download of segments, + improving overall performance. +@item After download completes, file integrity is verified using checksums. +@item Implements the GA4GH-compliant htsget protocol for download of genomic + ranges for data files with accompanying index files. +@end itemize\n") + (license license:asl2.0))) + (define-public python-pysam (package (name "python-pysam") @@ -6065,6 +6160,46 @@ Roche 454, Ion Torrent and Pacific BioSciences SMRT.") ;; 2. MD5 implementation - RSA Data Security, RFC 1321 (license (list license:gpl2+ license:public-domain))))) +(define-public mosaicatcher + (package + (name "mosaicatcher") + (version "0.3.1") + (source (origin + ;; There are no release tarballs nor tags. + (method git-fetch) + (uri (git-reference + (url "https://github.com/friendsofstrandseq/mosaicatcher") + (commit (string-append version "-dev")))) + (file-name (git-file-name name version)) + (sha256 + (base32 + "1n2s5wvvj2y0vfgjkg1q11xahpbagxz7h2vf5q7qyy25s12kbzbd")) + (patches (search-patches "mosaicatcher-unbundle-htslib.patch")))) + (build-system cmake-build-system) + (arguments + `(#:tests? #false ; there are no tests + #:phases + (modify-phases %standard-phases + (add-after 'unpack 'chdir + (lambda _ (chdir "src"))) + (replace 'install + (lambda* (#:key inputs outputs #:allow-other-keys) + (let* ((target (assoc-ref outputs "out")) + (bin (string-append target "/bin")) + (share (string-append target "/share/mosaicatcher"))) + (install-file "mosaic" bin) + (mkdir-p share) + (copy-recursively "../R" share))))))) + (inputs + `(("boost" ,boost) + ("htslib" ,htslib))) + (home-page "https://github.com/friendsofstrandseq/mosaicatcher") + (synopsis "Count and classify Strand-seq reads") + (description + "Mosaicatcher counts Strand-seq reads and classifies strand states of +each chromosome in each cell using a Hidden Markov Model.") + (license license:expat))) + (define-public ngs-sdk (package (name "ngs-sdk") @@ -7790,409 +7925,54 @@ including VCF header and contents in RDF and JSON.") (home-page "https://github.com/vcflib/bio-vcf") (license license:expat))) -(define-public r-genomicalignments - (package - (name "r-genomicalignments") - (version "1.26.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "GenomicAlignments" version)) - (sha256 - (base32 - "1q95px6s6snsax4ax955zzpdlrwp5liwf70wqq0lrk9mp6lq0hbr")))) - (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 "https://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 "1.50.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "rtracklayer" version)) - (sha256 - (base32 - "12zimhpdzjyzd81wrzz5hdbzvlgzcs22x1nnaf2jq4cba3ch5px8")))) - (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))))) - (native-inputs - `(("pkg-config" ,pkg-config))) - (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) - ("r-zlibbioc" ,r-zlibbioc))) - (home-page "https://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 "1.42.3") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "GenomicFeatures" version)) - (sha256 - (base32 - "168cf261vmcqffbzassavkjyz9a2af0l6zbv9cagkx6b1qrk3siz")))) - (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))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://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 "3.7.0") - (source (origin - (method url-fetch) - (uri (string-append "https://www.bioconductor.org/packages/" - "release/data/annotation/src/contrib/GO.db_" - version ".tar.gz")) - (sha256 - (base32 - "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5")))) - (properties - `((upstream-name . "GO.db"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi))) - (home-page "https://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-topgo - (package - (name "r-topgo") - (version "2.42.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "topGO" version)) - (sha256 - (base32 - "0vr3l9gvd3dhy446k3fkj6rm7z1abxi56rbnrs64297yzxaz1ngl")))) - (properties - `((upstream-name . "topGO"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-dbi" ,r-dbi) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-go-db" ,r-go-db) - ("r-graph" ,r-graph) - ("r-lattice" ,r-lattice) - ("r-matrixstats" ,r-matrixstats) - ("r-sparsem" ,r-sparsem))) - (home-page "https://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 "1.58.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "BSgenome" version)) - (sha256 - (base32 - "1gbvmxr6r57smgvhqgwspbcnwyk4hsfkxkpzzcs6470q03zfb4wq")))) - (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-matrixstats" ,r-matrixstats) - ("r-rsamtools" ,r-rsamtools) - ("r-rtracklayer" ,r-rtracklayer) - ("r-s4vectors" ,r-s4vectors) - ("r-xvector" ,r-xvector))) - (home-page "https://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 "1.64.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "impute" version)) - (sha256 - (base32 - "1pnjasw9i19nmxwjzrd9jbln31yc5jilfvwk414ya5zbqfsazvxa")))) - (native-inputs - `(("gfortran" ,gfortran))) - (build-system r-build-system) - (home-page "https://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 "1.22.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "seqPattern" version)) - (sha256 - (base32 - "0j68n6fwycxjpl2va5fw7ajb123n758s2pq997d76dysxghmrlzq")))) - (properties - `((upstream-name . "seqPattern"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biostrings" ,r-biostrings) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-kernsmooth" ,r-kernsmooth) - ("r-plotrix" ,r-plotrix))) - (home-page "https://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 "1.22.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "genomation" version)) - (sha256 - (base32 - "1ana06irlpdgnmk8mb329nws9sm8n6max4qargf1xdcdf3rnk45g")))) - (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-rcpp" ,r-rcpp) - ("r-readr" ,r-readr) - ("r-reshape2" ,r-reshape2) - ("r-rsamtools" ,r-rsamtools) - ("r-rtracklayer" ,r-rtracklayer) - ("r-runit" ,r-runit) - ("r-s4vectors" ,r-s4vectors) - ("r-seqpattern" ,r-seqpattern))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://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 "1.22.0") - (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://bioconductor.org/packages/" - "release/data/experiment/src/contrib/" - "genomationData_" version ".tar.gz")) - (sha256 - (base32 - "0igjsvfnws3498j65ifniw0kbxfqpfr59rcjddqvq4zsj453fx1g")))) - (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 "https://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-seqlogo - (package - (name "r-seqlogo") - (version "1.56.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "seqLogo" version)) - (sha256 - (base32 - "02rpzjjfg5chlwwfbvv72cm78cg2vfmdwzars0cin9hz1hd7rnq1")))) - (properties `((upstream-name . "seqLogo"))) - (build-system r-build-system) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://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-motifrg - (package - (name "r-motifrg") - (version "1.31.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "motifRG" version)) - (sha256 - (base32 - "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn")))) - (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 "https://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-zlibbioc - (package - (name "r-zlibbioc") - (version "1.36.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "zlibbioc" version)) - (sha256 - (base32 - "0m36ddss0znvm19dhnxcclxjhgjplw8ajk8v419h20ab8an6khxg")))) - (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 r-phantompeakqualtools + (let ((commit "8d2b2d18c686d894ef5908b37da7adf72a07ef42") + (revision "1")) + (package + (name "r-phantompeakqualtools") + (version (git-version "1.2.2" revision commit)) + (source + (origin + (method git-fetch) + (uri (git-reference + (url "https://github.com/kundajelab/phantompeakqualtools") + (commit commit))) + (file-name (git-file-name name version)) + (sha256 + (base32 + "00anrvcwsp02d98qhj1xpj85644h2pp4kfzq6dgbmwmdr6jvy7p4")))) + (build-system gnu-build-system) + (arguments + `(#:tests? #f ; There are no tests. + #:phases + (modify-phases %standard-phases + (delete 'configure) + (delete 'build) + (replace 'install + (lambda* (#:key inputs outputs #:allow-other-keys) + (let ((script (string-append (assoc-ref outputs "out") + "/share/scripts"))) + (install-file "run_spp.R" script))))))) + (inputs + `(("r" ,r-minimal))) + (propagated-inputs + `(("r-catools" ,r-catools) + ("r-snow" ,r-snow) + ("r-snowfall" ,r-snowfall) + ("r-bitops" ,r-bitops) + ("r-rsamtools" ,r-rsamtools) + ("r-spp" ,r-spp) + ("gawk" ,gawk) + ("samtools" ,samtools) + ("boost" ,boost) + ("gzip" ,gzip))) + (home-page "https://github.com/kundajelab/phantompeakqualtools") + (synopsis "Informative enrichment for ChIP-seq data") + (description "This package computes informative enrichment and quality +measures for ChIP-seq/DNase-seq/FAIRE-seq/MNase-seq data. It can also be +used to obtain robust estimates of the predominant fragment length or +characteristic tag shift values in these assays.") + (license license:bsd-3)))) (define-public r-r4rna (package @@ -8217,116 +7997,6 @@ libraries for systems that do not have these available via other means.") secondary structure and comparative analysis in R.") (license license:gpl3+))) -(define-public r-rhtslib - (package - (name "r-rhtslib") - (version "1.22.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "Rhtslib" version)) - (sha256 - (base32 - "18wag2jnpda6078xjkpfdvar1gkb2myhw83gg03l39sabh35qya4")))) - (properties `((upstream-name . "Rhtslib"))) - (build-system r-build-system) - ;; Without this a temporary directory ends up in the Rhtslib.so binary, - ;; which makes R abort the build. - (arguments '(#:configure-flags '("--no-staged-install"))) - (propagated-inputs - `(("curl" ,curl) - ("zlib" ,zlib) ; packages using rhtslib need to link with zlib - ("r-zlibbioc" ,r-zlibbioc))) - (native-inputs - `(("pkg-config" ,pkg-config) - ("r-knitr" ,r-knitr))) - (home-page "https://github.com/nhayden/Rhtslib") - (synopsis "High-throughput sequencing library as an R package") - (description - "This package provides the HTSlib C library for high-throughput -nucleotide sequence analysis. The package is primarily useful to developers -of other R packages who wish to make use of HTSlib.") - (license license:lgpl2.0+))) - -(define-public r-bamsignals - (package - (name "r-bamsignals") - (version "1.22.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "bamsignals" version)) - (sha256 - (base32 - "0p3r9z9z5sfkd0b951cgr751k4z0yviyn1jfw9d4fcnyld7g1jxv")))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-rcpp" ,r-rcpp) - ("r-rhtslib" ,r-rhtslib) - ("r-zlibbioc" ,r-zlibbioc))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/bamsignals") - (synopsis "Extract read count signals from bam files") - (description - "This package efficiently obtains count vectors from indexed bam -files. It counts the number of nucleotide sequence reads in given genomic -ranges and it computes reads profiles and coverage profiles. It also handles -paired-end data.") - (license license:gpl2+))) - -(define-public r-rcas - (package - (name "r-rcas") - (version "1.16.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "RCAS" version)) - (sha256 - (base32 - "0vdxml618vqvf8xyh0zxs307p9zby0cj9dqyiiz625ilyq1hkw2m")))) - (properties `((upstream-name . "RCAS"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-biostrings" ,r-biostrings) - ("r-bsgenome" ,r-bsgenome) - ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19) - ("r-cowplot" ,r-cowplot) - ("r-data-table" ,r-data-table) - ("r-dt" ,r-dt) - ("r-genomation" ,r-genomation) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicfeatures" ,r-genomicfeatures) - ("r-genomicranges" ,r-genomicranges) - ("r-ggplot2" ,r-ggplot2) - ("r-ggseqlogo" ,r-ggseqlogo) - ("r-gprofiler2" ,r-gprofiler2) - ("r-iranges" ,r-iranges) - ("r-pbapply" ,r-pbapply) - ("r-pheatmap" ,r-pheatmap) - ("r-plotly" ,r-plotly) - ("r-plotrix" ,r-plotrix) - ("r-proxy" ,r-proxy) - ("r-ranger" ,r-ranger) - ("r-rsqlite" ,r-rsqlite) - ("r-rtracklayer" ,r-rtracklayer) - ("r-rmarkdown" ,r-rmarkdown) - ("r-s4vectors" ,r-s4vectors) - ("pandoc" ,pandoc))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (synopsis "RNA-centric annotation system") - (description - "RCAS aims to be a standalone RNA-centric annotation system that provides -intuitive reports and publication-ready graphics. This package provides the R -library implementing most of the pipeline's features.") - (home-page "https://github.com/BIMSBbioinfo/RCAS") - (license license:artistic2.0))) - (define-public rcas-web (package (name "rcas-web") @@ -8378,64 +8048,19 @@ library implementing most of the pipeline's features.") @dfn{RNA-centric annotation system} (RCAS).") (license license:agpl3+))) -(define-public r-mutationalpatterns - (package - (name "r-mutationalpatterns") - (version "3.0.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "MutationalPatterns" version)) - (sha256 - (base32 - "1988kjjgq8af0hj7chhpxi88717wwmzs9qgrwapjh0hm2hjwhn35")))) - (build-system r-build-system) - (native-inputs - `(("r-knitr" ,r-knitr))) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-biostrings" ,r-biostrings) - ("r-bsgenome" ,r-bsgenome) - ;; These two packages are suggested packages - ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5) - ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19) - ("r-cowplot" ,r-cowplot) - ("r-dplyr" ,r-dplyr) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicranges" ,r-genomicranges) - ("r-ggalluvial" ,r-ggalluvial) - ("r-ggdendro" ,r-ggdendro) - ("r-ggplot2" ,r-ggplot2) - ("r-iranges" ,r-iranges) - ("r-magrittr" ,r-magrittr) - ("r-nmf" ,r-nmf) - ("r-pracma" ,r-pracma) - ("r-purrr" ,r-purrr) - ("r-s4vectors" ,r-s4vectors) - ("r-stringr" ,r-stringr) - ("r-tibble" ,r-tibble) - ("r-tidyr" ,r-tidyr) - ("r-variantannotation" ,r-variantannotation))) - (home-page "https://bioconductor.org/packages/MutationalPatterns/") - (synopsis "Extract and visualize mutational patterns in genomic data") - (description "This package provides an extensive toolset for the -characterization and visualization of a wide range of mutational patterns -in SNV base substitution data.") - (license license:expat))) - (define-public r-chipkernels (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372") (revision "1")) (package (name "r-chipkernels") - (version (string-append "1.1-" revision "." (string-take commit 9))) + (version (git-version "1.1" revision commit)) (source (origin (method git-fetch) (uri (git-reference (url "https://github.com/ManuSetty/ChIPKernels") (commit commit))) - (file-name (string-append name "-" version)) + (file-name (git-file-name name version)) (sha256 (base32 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0")))) @@ -8490,121 +8115,6 @@ bound and non bound genomic regions to accurately identify transcription factors bound at the specific regions.") (license license:gpl2+))) -(define-public r-tximport - (package - (name "r-tximport") - (version "1.18.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "tximport" version)) - (sha256 - (base32 - "1nxnlvl4iv2392xa72j0lzy2xnb3vrvyhfrdj9l54znwkrryyq34")))) - (build-system r-build-system) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/tximport") - (synopsis "Import and summarize transcript-level estimates for gene-level analysis") - (description - "This package provides tools to import transcript-level abundance, -estimated counts and transcript lengths, and to summarize them into matrices -for use with downstream gene-level analysis packages. Average transcript -length, weighted by sample-specific transcript abundance estimates, is -provided as a matrix which can be used as an offset for different expression -of gene-level counts.") - (license license:gpl2+))) - -(define-public r-rhdf5filters - (package - (name "r-rhdf5filters") - (version "1.2.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "rhdf5filters" version)) - (sha256 - (base32 - "1bjlgc76vx0z81s8vci9ln1d2s3b157qnm32xs36mnyjk31ivasz")))) - (properties `((upstream-name . "rhdf5filters"))) - (build-system r-build-system) - (propagated-inputs - `(("r-rhdf5lib" ,r-rhdf5lib))) - (inputs - `(("zlib" ,zlib))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/grimbough/rhdf5filters") - (synopsis "HDF5 compression filters") - (description - "This package provides a collection of compression filters for use with -HDF5 datasets.") - (license license:bsd-2))) - -(define-public r-rhdf5 - (package - (name "r-rhdf5") - (version "2.34.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "rhdf5" version)) - (sha256 - (base32 - "0almr1vscrgj5g4dyrags131wia2pmdbdidlpskbgm44ha6hpmqi")))) - (build-system r-build-system) - (arguments - `(#:phases - (modify-phases %standard-phases - (add-after 'unpack 'fix-linking - (lambda _ - (substitute* "src/Makevars" - ;; This is to avoid having a plain directory on the list of - ;; libraries to link. - (("\\(RHDF5_LIBS\\)" match) - (string-append match "/libhdf5.a"))) - #t))))) - (propagated-inputs - `(("r-rhdf5filters" ,r-rhdf5filters) - ("r-rhdf5lib" ,r-rhdf5lib))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/rhdf5") - (synopsis "HDF5 interface to R") - (description - "This R/Bioconductor package provides an interface between HDF5 and R. -HDF5's main features are the ability to store and access very large and/or -complex datasets and a wide variety of metadata on mass storage (disk) through -a completely portable file format. The rhdf5 package is thus suited for the -exchange of large and/or complex datasets between R and other software -package, and for letting R applications work on datasets that are larger than -the available RAM.") - (license license:artistic2.0))) - -(define-public r-annotationfilter - (package - (name "r-annotationfilter") - (version "1.14.0") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "AnnotationFilter" version)) - (sha256 - (base32 - "0npk0laa2rc93rsh6yikj886zf2fl53a050j07fj9w67j0q0h3s9")))) - (properties - `((upstream-name . "AnnotationFilter"))) - (build-system r-build-system) - (propagated-inputs - `(("r-genomicranges" ,r-genomicranges) - ("r-lazyeval" ,r-lazyeval))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/Bioconductor/AnnotationFilter") - (synopsis "Facilities for filtering Bioconductor annotation resources") - (description - "This package provides classes and other infrastructure to implement -filters for manipulating Bioconductor annotation resources. The filters are -used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.") - (license license:artistic2.0))) - (define-public emboss (package (name "emboss") @@ -8675,13 +8185,13 @@ tools for sequence analysis into a seamless whole.") (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))) + (version (git-version "2.13.0" revision commit)) (source (origin (method git-fetch) (uri (git-reference (url "https://github.com/arq5x/bits") (commit commit))) - (file-name (string-append name "-" version "-checkout")) + (file-name (git-file-name name version)) (sha256 (base32 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs")))) @@ -8721,7 +8231,7 @@ intervals (e.g. genes, sequence alignments).") (commit "0466d364b71117d01e4471b74c514436cc281233")) (package (name "piranha") - (version (string-append "1.2.1-" revision "." (string-take commit 9))) + (version (git-version "1.2.1" revision commit)) (source (origin (method git-fetch) (uri (git-reference @@ -8810,10 +8320,11 @@ group or two ChIP groups run under different conditions.") (license license:gpl3+))) (define-public filevercmp - (let ((commit "1a9b779b93d0b244040274794d402106907b71b7")) + (let ((commit "1a9b779b93d0b244040274794d402106907b71b7") + (revision "1")) (package (name "filevercmp") - (version (string-append "0-1." (string-take commit 7))) + (version (git-version "0" revision commit)) (source (origin (method git-fetch) (uri (git-reference @@ -8927,176 +8438,6 @@ analysis, variant tools is project based and provides a whole set of tools to manipulate and analyze genetic variants.") (license license:gpl3+))) -(define-public r-chipseq - (package - (name "r-chipseq") - (version "1.40.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "chipseq" version)) - (sha256 - (base32 - "12pzq24aarvgxfmhcad0l5g951xqdvvi7bspgbsvlvmfkqd74j2v")))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-lattice" ,r-lattice) - ("r-s4vectors" ,r-s4vectors) - ("r-shortread" ,r-shortread))) - (home-page "https://bioconductor.org/packages/chipseq") - (synopsis "Package for analyzing ChIPseq data") - (description - "This package provides tools for processing short read data from ChIPseq -experiments.") - (license license:artistic2.0))) - -(define-public r-copyhelper - (package - (name "r-copyhelper") - (version "1.6.0") - (source - (origin - (method url-fetch) - (uri (string-append "https://bioconductor.org/packages/release/" - "data/experiment/src/contrib/CopyhelpeR_" - version ".tar.gz")) - (sha256 - (base32 - "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq")))) - (properties `((upstream-name . "CopyhelpeR"))) - (build-system r-build-system) - (home-page "https://bioconductor.org/packages/CopyhelpeR/") - (synopsis "Helper files for CopywriteR") - (description - "This package contains the helper files that are required to run the -Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content -and mappability files for the reference genomes hg18, hg19, hg38, mm9 and -mm10. In addition, it contains a blacklist filter to remove regions that -display copy number variation. Files are stored as GRanges objects from the -GenomicRanges Bioconductor package.") - (license license:gpl2))) - -(define-public r-copywriter - (package - (name "r-copywriter") - (version "2.22.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "CopywriteR" version)) - (sha256 - (base32 - "060p6l6l8i6b15hyyz5v5kkxih3h4wcciixii51m9mn82z23xr2f")))) - (properties `((upstream-name . "CopywriteR"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocparallel" ,r-biocparallel) - ("r-chipseq" ,r-chipseq) - ("r-copyhelper" ,r-copyhelper) - ("r-data-table" ,r-data-table) - ("r-dnacopy" ,r-dnacopy) - ("r-futile-logger" ,r-futile-logger) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicalignments" ,r-genomicalignments) - ("r-genomicranges" ,r-genomicranges) - ("r-gtools" ,r-gtools) - ("r-iranges" ,r-iranges) - ("r-matrixstats" ,r-matrixstats) - ("r-rsamtools" ,r-rsamtools) - ("r-s4vectors" ,r-s4vectors))) - (home-page "https://github.com/PeeperLab/CopywriteR") - (synopsis "Copy number information from targeted sequencing") - (description - "CopywriteR extracts DNA copy number information from targeted sequencing -by utilizing off-target reads. It allows for extracting uniformly distributed -copy number information, can be used without reference, and can be applied to -sequencing data obtained from various techniques including chromatin -immunoprecipitation and target enrichment on small gene panels. Thereby, -CopywriteR constitutes a widely applicable alternative to available copy -number detection tools.") - (license license:gpl2))) - -(define-public r-methylkit - (package - (name "r-methylkit") - (version "1.16.1") - (source (origin - (method url-fetch) - (uri (bioconductor-uri "methylKit" version)) - (sha256 - (base32 - "1c9b11gfh3cc37iwym9rgsba3mh2xkp78a1gvnjqhzlkiz667mn3")))) - (properties `((upstream-name . "methylKit"))) - (build-system r-build-system) - (propagated-inputs - `(("r-data-table" ,r-data-table) - ("r-emdbook" ,r-emdbook) - ("r-fastseg" ,r-fastseg) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicranges" ,r-genomicranges) - ("r-gtools" ,r-gtools) - ("r-iranges" ,r-iranges) - ("r-kernsmooth" ,r-kernsmooth) - ("r-limma" ,r-limma) - ("r-mclust" ,r-mclust) - ("r-mgcv" ,r-mgcv) - ("r-qvalue" ,r-qvalue) - ("r-r-utils" ,r-r-utils) - ("r-rcpp" ,r-rcpp) - ("r-rhtslib" ,r-rhtslib) - ("r-rsamtools" ,r-rsamtools) - ("r-rtracklayer" ,r-rtracklayer) - ("r-s4vectors" ,r-s4vectors) - ("r-zlibbioc" ,r-zlibbioc))) - (native-inputs - `(("r-knitr" ,r-knitr))) ; for vignettes - (home-page "https://github.com/al2na/methylKit") - (synopsis - "DNA methylation analysis from high-throughput bisulfite sequencing results") - (description - "MethylKit is an R package for DNA methylation analysis and annotation -from high-throughput bisulfite sequencing. The package is designed to deal -with sequencing data from @dfn{Reduced representation bisulfite -sequencing} (RRBS) and its variants, but also target-capture methods and whole -genome bisulfite sequencing. It also has functions to analyze base-pair -resolution 5hmC data from experimental protocols such as oxBS-Seq and -TAB-Seq.") - (license license:artistic2.0))) - -(define-public r-sva - (package - (name "r-sva") - (version "3.38.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "sva" version)) - (sha256 - (base32 - "1hpzzg3qrgkd8kwg1m5gq94cikjgk9j4l1wk58fxl49s6fmd13zy")))) - (build-system r-build-system) - (propagated-inputs - `(("r-edger" ,r-edger) - ("r-genefilter" ,r-genefilter) - ("r-mgcv" ,r-mgcv) - ("r-biocparallel" ,r-biocparallel) - ("r-matrixstats" ,r-matrixstats) - ("r-limma" ,r-limma))) - (home-page "https://bioconductor.org/packages/sva") - (synopsis "Surrogate variable analysis") - (description - "This package contains functions for removing batch effects and other -unwanted variation in high-throughput experiment. It also contains functions -for identifying and building surrogate variables for high-dimensional data -sets. Surrogate variables are covariates constructed directly from -high-dimensional data like gene expression/RNA sequencing/methylation/brain -imaging data that can be used in subsequent analyses to adjust for unknown, -unmodeled, or latent sources of noise.") - (license license:artistic2.0))) - (define-public r-raremetals2 (package (name "r-raremetals2") @@ -9129,807 +8470,6 @@ for analyzing gene-level association tests in meta-analyses for binary trait.") (license license:gpl3))) -(define-public r-protgenerics - (package - (name "r-protgenerics") - (version "1.22.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "ProtGenerics" version)) - (sha256 - (base32 - "0yihxphgkshvfv1sn67wc4zvr2zlzws2j7ki3zabm6vyfkfdkfiz")))) - (properties `((upstream-name . "ProtGenerics"))) - (build-system r-build-system) - (home-page "https://github.com/lgatto/ProtGenerics") - (synopsis "S4 generic functions for proteomics infrastructure") - (description - "This package provides S4 generic functions needed by Bioconductor -proteomics packages.") - (license license:artistic2.0))) - -(define-public r-mzr - (package - (name "r-mzr") - (version "2.24.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "mzR" version)) - (sha256 - (base32 - "0ik0yrjhvk8r5pm990chn2aadp0gqzzkkm0027682ky34xp142sg")) - (modules '((guix build utils))) - (snippet - '(begin - (delete-file-recursively "src/boost") - #t)))) - (properties `((upstream-name . "mzR"))) - (build-system r-build-system) - (arguments - `(#:phases - (modify-phases %standard-phases - (add-after 'unpack 'use-system-boost - (lambda _ - (substitute* "src/Makevars" - (("\\./boost/libs.*") "") - ;; This is to avoid having a plain directory on the list of - ;; libraries to link. - (("\\(RHDF5_LIBS\\)" match) - (string-append match "/libhdf5.a")) - (("PKG_LIBS=") "PKG_LIBS=$(BOOST_LIBS) ") - (("\\ARCH_OBJS=" line) - (string-append line - "\nBOOST_LIBS=-lboost_system -lboost_regex \ --lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n"))) - #t))))) - (inputs - `(;; Our default boost package won't work here, unfortunately, even with - ;; mzR version 2.24.1. - ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources - ("zlib" ,zlib))) - (propagated-inputs - `(("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-ncdf4" ,r-ncdf4) - ("r-protgenerics" ,r-protgenerics) - ("r-rcpp" ,r-rcpp) - ("r-rhdf5lib" ,r-rhdf5lib) - ("r-zlibbioc" ,r-zlibbioc))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/sneumann/mzR/") - (synopsis "Parser for mass spectrometry data files") - (description - "The mzR package provides a unified API to the common file formats and -parsers available for mass spectrometry data. It comes with a wrapper for the -ISB random access parser for mass spectrometry mzXML, mzData and mzML files. -The package contains the original code written by the ISB, and a subset of the -proteowizard library for mzML and mzIdentML. The netCDF reading code has -previously been used in XCMS.") - (license license:artistic2.0))) - -(define-public r-affyio - (package - (name "r-affyio") - (version "1.60.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "affyio" version)) - (sha256 - (base32 - "14xnzrxrvgxgixjhq5a9fdgcmrxam2j74hwidkc9if92ffv6s83h")))) - (build-system r-build-system) - (propagated-inputs - `(("r-zlibbioc" ,r-zlibbioc))) - (inputs - `(("zlib" ,zlib))) - (home-page "https://github.com/bmbolstad/affyio") - (synopsis "Tools for parsing Affymetrix data files") - (description - "This package provides routines for parsing Affymetrix data files based -upon file format information. The primary focus is on accessing the CEL and -CDF file formats.") - (license license:lgpl2.0+))) - -(define-public r-affy - (package - (name "r-affy") - (version "1.68.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "affy" version)) - (sha256 - (base32 - "0ywz548cbzk2k1njnxhlk5ydzvz2dk78ka8kx53gwrmdc4sc2b06")))) - (build-system r-build-system) - (propagated-inputs - `(("r-affyio" ,r-affyio) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocmanager" ,r-biocmanager) - ("r-preprocesscore" ,r-preprocesscore) - ("r-zlibbioc" ,r-zlibbioc))) - (inputs - `(("zlib" ,zlib))) - (home-page "https://bioconductor.org/packages/affy") - (synopsis "Methods for affymetrix oligonucleotide arrays") - (description - "This package contains functions for exploratory oligonucleotide array -analysis.") - (license license:lgpl2.0+))) - -(define-public r-vsn - (package - (name "r-vsn") - (version "3.58.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "vsn" version)) - (sha256 - (base32 - "0dfrfflidpnphwyqzmmfiz9blfqv6qa09xlwgfabhpfsf3ml2rlb")))) - (build-system r-build-system) - (propagated-inputs - `(("r-affy" ,r-affy) - ("r-biobase" ,r-biobase) - ("r-ggplot2" ,r-ggplot2) - ("r-lattice" ,r-lattice) - ("r-limma" ,r-limma))) - (native-inputs - `(("r-knitr" ,r-knitr))) ; for vignettes - (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html") - (synopsis "Variance stabilization and calibration for microarray data") - (description - "The package implements a method for normalising microarray intensities, -and works for single- and multiple-color arrays. It can also be used for data -from other technologies, as long as they have similar format. The method uses -a robust variant of the maximum-likelihood estimator for an -additive-multiplicative error model and affine calibration. The model -incorporates data calibration step (a.k.a. normalization), a model for the -dependence of the variance on the mean intensity and a variance stabilizing -data transformation. Differences between transformed intensities are -analogous to \"normalized log-ratios\". However, in contrast to the latter, -their variance is independent of the mean, and they are usually more sensitive -and specific in detecting differential transcription.") - (license license:artistic2.0))) - -(define-public r-mzid - (package - (name "r-mzid") - (version "1.28.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "mzID" version)) - (sha256 - (base32 - "0s7d6cz1li7v3ni6n6hrdspl93yiyr283kmbbd3hhkfgzgx6kpq2")))) - (properties `((upstream-name . "mzID"))) - (build-system r-build-system) - (propagated-inputs - `(("r-doparallel" ,r-doparallel) - ("r-foreach" ,r-foreach) - ("r-iterators" ,r-iterators) - ("r-plyr" ,r-plyr) - ("r-protgenerics" ,r-protgenerics) - ("r-xml" ,r-xml))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/mzID") - (synopsis "Parser for mzIdentML files") - (description - "This package provides a parser for mzIdentML files implemented using the -XML package. The parser tries to be general and able to handle all types of -mzIdentML files with the drawback of having less pretty output than a vendor -specific parser.") - (license license:gpl2+))) - -(define-public r-pcamethods - (package - (name "r-pcamethods") - (version "1.82.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "pcaMethods" version)) - (sha256 - (base32 - "04xb4vjky6hq58l30i1iq9rv5gzjdxnidjxpnzg7pvg67vz8pgf0")))) - (properties `((upstream-name . "pcaMethods"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-mass" ,r-mass) - ("r-rcpp" ,r-rcpp))) - (home-page "https://github.com/hredestig/pcamethods") - (synopsis "Collection of PCA methods") - (description - "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA, -Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method -for missing value estimation is included for comparison. BPCA, PPCA and -NipalsPCA may be used to perform PCA on incomplete data as well as for -accurate missing value estimation. A set of methods for printing and plotting -the results is also provided. All PCA methods make use of the same data -structure (pcaRes) to provide a common interface to the PCA results.") - (license license:gpl3+))) - -(define-public r-msnbase - (package - (name "r-msnbase") - (version "2.16.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "MSnbase" version)) - (sha256 - (base32 - "0hxzs9zzljywqxr7q388hshpy1pdryhl0zkwffqbxpf5pcf92d3h")))) - (properties `((upstream-name . "MSnbase"))) - (build-system r-build-system) - (propagated-inputs - `(("r-affy" ,r-affy) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocparallel" ,r-biocparallel) - ("r-digest" ,r-digest) - ("r-ggplot2" ,r-ggplot2) - ("r-impute" ,r-impute) - ("r-iranges" ,r-iranges) - ("r-lattice" ,r-lattice) - ("r-maldiquant" ,r-maldiquant) - ("r-mass" ,r-mass) - ("r-mzid" ,r-mzid) - ("r-mzr" ,r-mzr) - ("r-pcamethods" ,r-pcamethods) - ("r-plyr" ,r-plyr) - ("r-preprocesscore" ,r-preprocesscore) - ("r-protgenerics" ,r-protgenerics) - ("r-rcpp" ,r-rcpp) - ("r-s4vectors" ,r-s4vectors) - ("r-scales" ,r-scales) - ("r-vsn" ,r-vsn) - ("r-xml" ,r-xml))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/lgatto/MSnbase") - (synopsis "Base functions and classes for MS-based proteomics") - (description - "This package provides basic plotting, data manipulation and processing -of mass spectrometry based proteomics data.") - (license license:artistic2.0))) - -(define-public r-msnid - (package - (name "r-msnid") - (version "1.24.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "MSnID" version)) - (sha256 - (base32 - "05bncy7lw2a3h8xgnavjiz56pc6mk8q7l6qdd81197nawxs3j02d")))) - (properties `((upstream-name . "MSnID"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-annotationhub" ,r-annotationhub) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocstyle" ,r-biocstyle) - ("r-biostrings" ,r-biostrings) - ("r-data-table" ,r-data-table) - ("r-doparallel" ,r-doparallel) - ("r-dplyr" ,r-dplyr) - ("r-foreach" ,r-foreach) - ("r-ggplot2" ,r-ggplot2) - ("r-iterators" ,r-iterators) - ("r-msnbase" ,r-msnbase) - ("r-msmstests" ,r-msmstests) - ("r-mzid" ,r-mzid) - ("r-mzr" ,r-mzr) - ("r-protgenerics" ,r-protgenerics) - ("r-purrr" ,r-purrr) - ("r-r-cache" ,r-r-cache) - ("r-rcpp" ,r-rcpp) - ("r-reshape2" ,r-reshape2) - ("r-rlang" ,r-rlang) - ("r-runit" ,r-runit) - ("r-stringr" ,r-stringr) - ("r-tibble" ,r-tibble) - ("r-xtable" ,r-xtable))) - (home-page "https://bioconductor.org/packages/MSnID") - (synopsis "Utilities for LC-MSn proteomics identifications") - (description - "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data -from mzIdentML (leveraging the mzID package) or text files. After collating -the search results from multiple datasets it assesses their identification -quality and optimize filtering criteria to achieve the maximum number of -identifications while not exceeding a specified false discovery rate. It also -contains a number of utilities to explore the MS/MS results and assess missed -and irregular enzymatic cleavages, mass measurement accuracy, etc.") - (license license:artistic2.0))) - -(define-public r-aroma-light - (package - (name "r-aroma-light") - (version "3.20.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "aroma.light" version)) - (sha256 - (base32 - "0pi37rlfqh24p9wd7l1xb3f7c7938xdscgcc5agp8c9qhajq25a0")))) - (properties `((upstream-name . "aroma.light"))) - (build-system r-build-system) - (propagated-inputs - `(("r-matrixstats" ,r-matrixstats) - ("r-r-methodss3" ,r-r-methodss3) - ("r-r-oo" ,r-r-oo) - ("r-r-utils" ,r-r-utils))) - (home-page "https://github.com/HenrikBengtsson/aroma.light") - (synopsis "Methods for normalization and visualization of microarray data") - (description - "This package provides methods for microarray analysis that take basic -data types such as matrices and lists of vectors. These methods can be used -standalone, be utilized in other packages, or be wrapped up in higher-level -classes.") - (license license:gpl2+))) - -(define-public r-deseq - (package - (name "r-deseq") - (version "1.39.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "DESeq" version)) - (sha256 - (base32 - "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1")))) - (properties `((upstream-name . "DESeq"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-genefilter" ,r-genefilter) - ("r-geneplotter" ,r-geneplotter) - ("r-lattice" ,r-lattice) - ("r-locfit" ,r-locfit) - ("r-mass" ,r-mass) - ("r-rcolorbrewer" ,r-rcolorbrewer))) - (home-page "https://www-huber.embl.de/users/anders/DESeq/") - (synopsis "Differential gene expression analysis") - (description - "This package provides tools for estimating variance-mean dependence in -count data from high-throughput genetic sequencing assays and for testing for -differential expression based on a model using the negative binomial -distribution.") - (license license:gpl3+))) - -(define-public r-edaseq - (package - (name "r-edaseq") - (version "2.24.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "EDASeq" version)) - (sha256 - (base32 - "0fznj7lsgkss1svv4rq8g87s1gmnbd7hccim41dv1c2w2nl0n2ip")))) - (properties `((upstream-name . "EDASeq"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-aroma-light" ,r-aroma-light) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocmanager" ,r-biocmanager) - ("r-biomart" ,r-biomart) - ("r-biostrings" ,r-biostrings) - ("r-genomicfeatures" ,r-genomicfeatures) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-rsamtools" ,r-rsamtools) - ("r-shortread" ,r-shortread))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/drisso/EDASeq") - (synopsis "Exploratory data analysis and normalization for RNA-Seq") - (description - "This package provides support for numerical and graphical summaries of -RNA-Seq genomic read data. Provided within-lane normalization procedures to -adjust for GC-content effect (or other gene-level effects) on read counts: -loess robust local regression, global-scaling, and full-quantile -normalization. Between-lane normalization procedures to adjust for -distributional differences between lanes (e.g., sequencing depth): -global-scaling and full-quantile normalization.") - (license license:artistic2.0))) - -(define-public r-interactivedisplaybase - (package - (name "r-interactivedisplaybase") - (version "1.28.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "interactiveDisplayBase" version)) - (sha256 - (base32 - "08id2hkx4ssxj34dildx00a4j3z0nv171b7b0wl6xjks7wk6lv01")))) - (properties - `((upstream-name . "interactiveDisplayBase"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-dt" ,r-dt) - ("r-shiny" ,r-shiny))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/interactiveDisplayBase") - (synopsis "Base package for web displays of Bioconductor objects") - (description - "This package contains the basic methods needed to generate interactive -Shiny-based display methods for Bioconductor objects.") - (license license:artistic2.0))) - -(define-public r-annotationhub - (package - (name "r-annotationhub") - (version "2.22.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "AnnotationHub" version)) - (sha256 - (base32 - "08d7m0n4jkpajsj0bvi5xd4vi1zqczl6lnrh8kqi2fbjkrvwdqp5")))) - (properties `((upstream-name . "AnnotationHub"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-biocfilecache" ,r-biocfilecache) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocmanager" ,r-biocmanager) - ("r-biocversion" ,r-biocversion) - ("r-curl" ,r-curl) - ("r-dplyr" ,r-dplyr) - ("r-httr" ,r-httr) - ("r-interactivedisplaybase" ,r-interactivedisplaybase) - ("r-rappdirs" ,r-rappdirs) - ("r-rsqlite" ,r-rsqlite) - ("r-s4vectors" ,r-s4vectors) - ("r-yaml" ,r-yaml))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/AnnotationHub") - (synopsis "Client to access AnnotationHub resources") - (description - "This package provides a client for the Bioconductor AnnotationHub web -resource. The AnnotationHub web resource provides a central location where -genomic files (e.g. VCF, bed, wig) and other resources from standard -locations (e.g. UCSC, Ensembl) can be discovered. The resource includes -metadata about each resource, e.g., a textual description, tags, and date of -modification. The client creates and manages a local cache of files retrieved -by the user, helping with quick and reproducible access.") - (license license:artistic2.0))) - -(define-public r-fastseg - (package - (name "r-fastseg") - (version "1.36.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "fastseg" version)) - (sha256 - (base32 - "1ln6w93ag4wanp0nrm0pqngbfc88w95zq2kcj583hbxy885dkg4f")))) - (build-system r-build-system) - (propagated-inputs - `(("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-s4vectors" ,r-s4vectors))) - (home-page "https://www.bioinf.jku.at/software/fastseg/index.html") - (synopsis "Fast segmentation algorithm for genetic sequencing data") - (description - "Fastseg implements a very fast and efficient segmentation algorithm. -It can segment data from DNA microarrays and data from next generation -sequencing for example to detect copy number segments. Further it can segment -data from RNA microarrays like tiling arrays to identify transcripts. Most -generally, it can segment data given as a matrix or as a vector. Various data -formats can be used as input to fastseg like expression set objects for -microarrays or GRanges for sequencing data.") - (license license:lgpl2.0+))) - -(define-public r-keggrest - (package - (name "r-keggrest") - (version "1.30.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "KEGGREST" version)) - (sha256 - (base32 - "0k9z85xf9la2y98xqmdmjb8mci9fh2fdybkl77x1yl26hyalip0s")))) - (properties `((upstream-name . "KEGGREST"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biostrings" ,r-biostrings) - ("r-httr" ,r-httr) - ("r-png" ,r-png))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://bioconductor.org/packages/KEGGREST") - (synopsis "Client-side REST access to KEGG") - (description - "This package provides a package that provides a client interface to the -@dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.") - (license license:artistic2.0))) - -(define-public r-gage - (package - (name "r-gage") - (version "2.40.2") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "gage" version)) - (sha256 - (base32 - "1bs0hx8sqiyl08dqn2zx31kbv5aci4xvrs71pplx2yxal3jf5178")))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-go-db" ,r-go-db) - ("r-graph" ,r-graph) - ("r-keggrest" ,r-keggrest))) - (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/" - "articles/10.1186/1471-2105-10-161")) - (synopsis "Generally applicable gene-set enrichment for pathway analysis") - (description - "GAGE is a published method for gene set (enrichment or GSEA) or pathway -analysis. GAGE is generally applicable independent of microarray or RNA-Seq -data attributes including sample sizes, experimental designs, assay platforms, -and other types of heterogeneity. The gage package provides functions for -basic GAGE analysis, result processing and presentation. In addition, it -provides demo microarray data and commonly used gene set data based on KEGG -pathways and GO terms. These functions and data are also useful for gene set -analysis using other methods.") - (license license:gpl2+))) - -(define-public r-genomicfiles - (package - (name "r-genomicfiles") - (version "1.26.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "GenomicFiles" version)) - (sha256 - (base32 - "0awnf0m1pz7cw9wvh9cfxz9k7xm6wnvjm7xbxf139lrhd4nlyqjz")))) - (properties `((upstream-name . "GenomicFiles"))) - (build-system r-build-system) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-biocparallel" ,r-biocparallel) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicalignments" ,r-genomicalignments) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-matrixgenerics" ,r-matrixgenerics) - ("r-rsamtools" ,r-rsamtools) - ("r-rtracklayer" ,r-rtracklayer) - ("r-s4vectors" ,r-s4vectors) - ("r-summarizedexperiment" ,r-summarizedexperiment) - ("r-variantannotation" ,r-variantannotation))) - (home-page "https://bioconductor.org/packages/GenomicFiles") - (synopsis "Distributed computing by file or by range") - (description - "This package provides infrastructure for parallel computations -distributed by file or by range. User defined mapper and reducer functions -provide added flexibility for data combination and manipulation.") - (license license:artistic2.0))) - -(define-public r-complexheatmap - (package - (name "r-complexheatmap") - (version "2.6.2") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "ComplexHeatmap" version)) - (sha256 - (base32 - "1nx1xxpq8zrvi990v9fmvx3msl85pdz5dp1gp6m78q6i4s2alg5x")))) - (properties - `((upstream-name . "ComplexHeatmap"))) - (build-system r-build-system) - (propagated-inputs - `(("r-cairo" ,r-cairo) - ("r-circlize" ,r-circlize) - ("r-clue" ,r-clue) - ("r-colorspace" ,r-colorspace) - ("r-digest" ,r-digest) - ("r-getoptlong" ,r-getoptlong) - ("r-globaloptions" ,r-globaloptions) - ("r-iranges" ,r-iranges) - ("r-matrixstats" ,r-matrixstats) - ("r-png" ,r-png) - ("r-rcolorbrewer" ,r-rcolorbrewer) - ("r-s4vectors" ,r-s4vectors))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page - "https://github.com/jokergoo/ComplexHeatmap") - (synopsis "Making Complex Heatmaps") - (description - "Complex heatmaps are efficient to visualize associations between -different sources of data sets and reveal potential structures. This package -provides a highly flexible way to arrange multiple heatmaps and supports -self-defined annotation graphics.") - (license license:gpl2+))) - -(define-public r-dirichletmultinomial - (package - (name "r-dirichletmultinomial") - (version "1.32.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "DirichletMultinomial" version)) - (sha256 - (base32 - "098zql6ryd1b0gkq4cjybblyh0x8xidxxfygqq5a5x9asl8y4vsk")))) - (properties - `((upstream-name . "DirichletMultinomial"))) - (build-system r-build-system) - (inputs - `(("gsl" ,gsl))) - (propagated-inputs - `(("r-biocgenerics" ,r-biocgenerics) - ("r-iranges" ,r-iranges) - ("r-s4vectors" ,r-s4vectors))) - (home-page "https://bioconductor.org/packages/DirichletMultinomial") - (synopsis "Dirichlet-Multinomial mixture models for microbiome data") - (description - "Dirichlet-multinomial mixture models can be used to describe variability -in microbial metagenomic data. This package is an interface to code -originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2): -1-15.") - (license license:lgpl3))) - -(define-public r-ensembldb - (package - (name "r-ensembldb") - (version "2.14.1") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "ensembldb" version)) - (sha256 - (base32 - "1hxwfh19qafpdhzprvw4nr8ks3gz7f0y8gyfhk8yqmmvvnvgqv40")))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-annotationfilter" ,r-annotationfilter) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biostrings" ,r-biostrings) - ("r-curl" ,r-curl) - ("r-dbi" ,r-dbi) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicfeatures" ,r-genomicfeatures) - ("r-genomicranges" ,r-genomicranges) - ("r-iranges" ,r-iranges) - ("r-protgenerics" ,r-protgenerics) - ("r-rsamtools" ,r-rsamtools) - ("r-rsqlite" ,r-rsqlite) - ("r-rtracklayer" ,r-rtracklayer) - ("r-s4vectors" ,r-s4vectors))) - (native-inputs - `(("r-knitr" ,r-knitr))) - (home-page "https://github.com/jotsetung/ensembldb") - (synopsis "Utilities to create and use Ensembl-based annotation databases") - (description - "The package provides functions to create and use transcript-centric -annotation databases/packages. The annotation for the databases are directly -fetched from Ensembl using their Perl API. The functionality and data is -similar to that of the TxDb packages from the @code{GenomicFeatures} package, -but, in addition to retrieve all gene/transcript models and annotations from -the database, the @code{ensembldb} package also provides a filter framework -allowing to retrieve annotations for specific entries like genes encoded on a -chromosome region or transcript models of lincRNA genes.") - ;; No version specified - (license license:lgpl3+))) - -(define-public r-organismdbi - (package - (name "r-organismdbi") - (version "1.32.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "OrganismDbi" version)) - (sha256 - (base32 - "1mklnzs0d0ygcdibwfnk5xqr8ln6wpa00qcaw9c68m342kql0jqw")))) - (properties `((upstream-name . "OrganismDbi"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-biobase" ,r-biobase) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biocmanager" ,r-biocmanager) - ("r-dbi" ,r-dbi) - ("r-genomicfeatures" ,r-genomicfeatures) - ("r-genomicranges" ,r-genomicranges) - ("r-graph" ,r-graph) - ("r-iranges" ,r-iranges) - ("r-rbgl" ,r-rbgl) - ("r-s4vectors" ,r-s4vectors))) - (home-page "https://bioconductor.org/packages/OrganismDbi") - (synopsis "Software to enable the smooth interfacing of database packages") - (description "The package enables a simple unified interface to several -annotation packages each of which has its own schema by taking advantage of -the fact that each of these packages implements a select methods.") - (license license:artistic2.0))) - -(define-public r-biovizbase - (package - (name "r-biovizbase") - (version "1.38.0") - (source - (origin - (method url-fetch) - (uri (bioconductor-uri "biovizBase" version)) - (sha256 - (base32 - "10jflvadfcgxq2jnfxkpn417xd8ibh3zllz9rsqnq5w3wgfr4fhq")))) - (properties `((upstream-name . "biovizBase"))) - (build-system r-build-system) - (propagated-inputs - `(("r-annotationdbi" ,r-annotationdbi) - ("r-annotationfilter" ,r-annotationfilter) - ("r-biocgenerics" ,r-biocgenerics) - ("r-biostrings" ,r-biostrings) - ("r-dichromat" ,r-dichromat) - ("r-ensembldb" ,r-ensembldb) - ("r-genomeinfodb" ,r-genomeinfodb) - ("r-genomicalignments" ,r-genomicalignments) - ("r-genomicfeatures" ,r-genomicfeatures) - ("r-genomicranges" ,r-genomicranges) - ("r-hmisc" ,r-hmisc) - ("r-iranges" ,r-iranges) - ("r-rcolorbrewer" ,r-rcolorbrewer) - ("r-rlang" ,r-rlang) - ("r-rsamtools" ,r-rsamtools) - ("r-s4vectors" ,r-s4vectors) - ("r-scales" ,r-scales) - ("r-summarizedexperiment" ,r-summarizedexperiment) - ("r-variantannotation" ,r-variantannotation))) - (home-page "https://bioconductor.org/packages/biovizBase") - (synopsis "Basic graphic utilities for visualization of genomic data") - (description - "The biovizBase package is designed to provide a set of utilities, color -schemes and conventions for genomic data. It serves as the base for various -high-level packages for biological data visualization. This saves development -effort and encourages consistency.") - (license license:artistic2.0))) - (define-public r-dropbead (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247") (revision "2")) @@ -10549,13 +9089,13 @@ browser.") (revision "1")) (package (name "f-seq") - (version (string-append "1.1-" revision "." (string-take commit 7))) + (version (git-version "1.1" revision commit)) (source (origin (method git-fetch) (uri (git-reference (url "https://github.com/aboyle/F-seq") (commit commit))) - (file-name (string-append name "-" version)) + (file-name (git-file-name name version)) (sha256 (base32 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h")) @@ -10613,7 +9153,7 @@ Browser.") (uri (git-reference (url "https://github.com/FelixKrueger/Bismark") (commit version))) - (file-name (string-append name "-" version "-checkout")) + (file-name (git-file-name name version)) (sha256 (base32 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9")))) @@ -11753,7 +10293,7 @@ once. This package provides tools to perform Drop-seq analyses.") (define-public pigx-rnaseq (package (name "pigx-rnaseq") - (version "0.0.10") + (version "0.0.13") (source (origin (method url-fetch) (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/" @@ -11761,7 +10301,7 @@ once. This package provides tools to perform Drop-seq analyses.") "/pigx_rnaseq-" version ".tar.gz")) (sha256 (base32 - "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw")))) + "0z9zid2c8q16lfzlnjd63nparknhv31qgv4h79algmvhkakm2pgk")))) (build-system gnu-build-system) (arguments `(#:parallel-tests? #f ; not supported @@ -11771,19 +10311,17 @@ once. This package provides tools to perform Drop-seq analyses.") (add-after 'unpack 'disable-resource-intensive-test (lambda _ (substitute* "Makefile.in" - (("(^ tests/test_trim_galore/test.sh).*" _ m) m) (("^ tests/test_multiqc/test.sh") "") - (("^ test.sh") "")) - #t))))) + (("^ test.sh") ""))))))) (inputs `(("coreutils" ,coreutils) ("sed" ,sed) ("gzip" ,gzip) ("snakemake" ,snakemake) - ("fastqc" ,fastqc) ("multiqc" ,multiqc) ("star" ,star-for-pigx) - ("trim-galore" ,trim-galore) + ("hisat2" ,hisat2) + ("fastp" ,fastp) ("htseq" ,htseq) ("samtools" ,samtools) ("r-minimal" ,r-minimal) @@ -12032,6 +10570,54 @@ and interactive quality reports. The pipeline is designed to work with UMI based methods.") (license license:gpl3+))) +(define-public pigx-sars-cov2-ww + (package + (name "pigx-sars-cov2-ww") + (version "0.0.1") + (source (origin + (method url-fetch) + (uri (string-append "https://github.com/BIMSBbioinfo/pigx_sarscov2_ww/" + "releases/download/v" version + "/pigx_sars-cov2-ww-" version ".tar.gz")) + (sha256 + (base32 + "1h1rfl3dyf7pid74xxgiyr4x1l5yj000wcz5crm1bdbaz8p7b7ic")))) + (build-system gnu-build-system) + (inputs + `(("bash-minimal" ,bash-minimal) + ("bwa" ,bwa) + ("ensembl-vep" ,ensembl-vep) + ("fastqc" ,fastqc) + ("kraken2" ,kraken2) + ("krona-tools" ,krona-tools) + ("lofreq" ,lofreq) + ("multiqc" ,multiqc) + ("prinseq" ,prinseq) + ("python-pyyaml" ,python-pyyaml) + ("python-wrapper" ,python-wrapper) + ("r-base64url" ,r-base64url) + ("r-dplyr" ,r-dplyr) + ("r-dt" ,r-dt) + ("r-ggplot2" ,r-ggplot2) + ("r-magrittr" ,r-magrittr) + ("r-minimal" ,r-minimal) + ("r-plotly" ,r-plotly) + ("r-qpcr" ,r-qpcr) + ("r-reshape2" ,r-reshape2) + ("r-rmarkdown" ,r-rmarkdown) + ("r-stringr" ,r-stringr) + ("r-tidyr" ,r-tidyr) + ("samtools" ,samtools) + ("snakemake" ,snakemake))) + (home-page "https://bioinformatics.mdc-berlin.de/pigx/") + (synopsis "Analysis pipeline for wastewater sequencing") + (description "PiGx SARS-CoV-2 is a pipeline for analysing data from +sequenced wastewater samples and identifying given variants-of-concern of +SARS-CoV-2. The pipeline can be used for continuous sampling. The output +report will provide an intuitive visual overview about the development of +variant abundance over time and location.") + (license license:gpl3+))) + (define-public pigx (package (name "pigx") @@ -12190,7 +10776,7 @@ version does count multisplits.") (define-public minimap2 (package (name "minimap2") - (version "2.17") + (version "2.18") (source (origin (method url-fetch) @@ -12199,11 +10785,13 @@ version does count multisplits.") "minimap2-" version ".tar.bz2")) (sha256 (base32 - "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn")) - (patches (search-patches "minimap2-aarch64-support.patch")))) + "1d7fvdqcqd6wns875rkyd7f34ii15gc9l1sivd2wbbpcb0fi0mbs")))) (build-system gnu-build-system) (arguments `(#:tests? #f ; there are none + #:modules ((guix build utils) + (guix build gnu-build-system) + (srfi srfi-26)) #:make-flags (list (string-append "CC=" ,(cc-for-target)) (let ((system ,(or (%current-target-system) @@ -12226,10 +10814,30 @@ version does count multisplits.") (lambda* (#:key outputs #:allow-other-keys) (let* ((out (assoc-ref outputs "out")) (bin (string-append out "/bin")) + (lib (string-append out "/lib")) + (inc (string-append out "/include")) (man (string-append out "/share/man/man1"))) (install-file "minimap2" bin) - (mkdir-p man) - (install-file "minimap2.1" man)) + (install-file "libminimap2.a" lib) + (install-file "minimap2.1" man) + (map (cut install-file <> inc) + (find-files "." "\\.h$")) + ;; Not this file. + (delete-file (string-append inc "/emmintrin.h")) + (mkdir-p (string-append lib "/pkgconfig")) + (with-output-to-file (string-append lib "/pkgconfig/minimap2.pc") + (lambda _ + (format #t "prefix=~a~@ + exec_prefix=${prefix}~@ + libdir=${exec_prefix}/lib~@ + includedir=${prefix}/include~@ + ~@ + Name: libminimap2~@ + Version: ~a~@ + Description: A versatile pairwise aligner for genomic and spliced nucleotide sequence~@ + Libs: -L${libdir} -lminimap2~@ + Cflags: -I${includedir}~%" + out ,version)))) #t))))) (inputs `(("zlib" ,zlib))) @@ -12346,6 +10954,96 @@ contigs alone.") (license (list license:gpl2+ ; bundled ogdf license:gpl3+)))) +(define-public libmaus2 + (package + (name "libmaus2") + (version "2.0.786") + (source (origin + (method git-fetch) + (uri (git-reference + (url "https://gitlab.com/german.tischler/libmaus2") + (commit (string-append version "-release-20210531143054")))) + (file-name (git-file-name name version)) + (sha256 + (base32 + "1rxakmwjcx2yq5sjh3v849f7dfw4xzc2fyzf6s28s3p95z84w564")))) + (build-system gnu-build-system) + ;; The test suite attempts to execute ../test-driver, which does not exist. + (arguments '(#:tests? #false)) + (propagated-inputs + `(("zlib" ,zlib))) + (native-inputs + `(("gcc" ,gcc-10) ;Code has C++17 requirements + ("pkg-config" ,pkg-config))) + (home-page "https://gitlab.com/german.tischler/libmaus2") + (synopsis "Collection of data structures and algorithms useful for bioinformatics") + (description "libmaus2 is a collection of data structures and +algorithms. It contains: + +@itemize +@item I/O classes (single byte and UTF-8); +@item @code{bitio} classes (input, output and various forms of bit level + manipulation); +@item text indexing classes (suffix and LCP array, fulltext and minute (FM), + etc.); +@item BAM sequence alignment files input/output (simple and collating); +and many lower level support classes. +@end itemize\n") + ;; The code is explicitly available under the terms of either GPLv2 or + ;; GPLv3 according to the AUTHORS file, though most files have a GPLv3+ + ;; license header. + (license (list license:gpl2+ license:gpl3+)))) + +(define-public biobambam2 + (package + (name "biobambam2") + (version "2.0.182") + (source (origin + (method git-fetch) + (uri (git-reference + (url "https://gitlab.com/german.tischler/biobambam2") + (commit (string-append version "-release-20210412001032")))) + (file-name (git-file-name name version)) + (sha256 + (base32 + "0b7w7a2a7hpkgrdn0n7hy4pilzrj82zqrh7q4bg1l0cd6bqr60m5")))) + (build-system gnu-build-system) + (arguments + ;; The test suite attempts to execute ../test-driver, which does not exist. + `(#:tests? #false + #:configure-flags + (list (string-append "--with-libmaus2=" + (assoc-ref %build-inputs "libmaus2"))))) + (inputs + `(("libmaus2" ,libmaus2) + ("xerces-c" ,xerces-c))) + (native-inputs + `(("gcc" ,gcc-10) ;Code has C++17 requirements + ("pkg-config" ,pkg-config))) + (home-page "https://gitlab.com/german.tischler/biobambam2") + (synopsis "Tools for processing BAM files") + (description "This package contains some tools for processing BAM files +including: + +@itemize +@item bamsormadup: parallel sorting and duplicate marking +@item bamcollate2: reads BAM and writes BAM reordered such that alignment or + collated by query name +@item bammarkduplicates: reads BAM and writes BAM with duplicate alignments + marked using the BAM flags field +@item bammaskflags: reads BAM and writes BAM while masking (removing) bits + from the flags column +@item bamrecompress: reads BAM and writes BAM with a defined compression + setting. This tool is capable of multi-threading. +@item bamsort: reads BAM and writes BAM resorted by coordinates or query name +@item bamtofastq: reads BAM and writes FastQ; output can be collated or + uncollated by query name. +@end itemize +") + ;; The COPYING file states that the code is distributed under version 3 of + ;; the GPL, but the license headers include the "or later" clause. + (license license:gpl3+))) + (define-public r-circus (package (name "r-circus") @@ -12501,17 +11199,80 @@ spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA) in RNA-seq data.") (license license:gpl3)))) +(define-public fit-sne + (package + (name "fit-sne") + (version "1.2.1") + (source + (origin + (method git-fetch) + (uri (git-reference + (url "https://github.com/KlugerLab/FIt-SNE") + (commit (string-append "v" version)))) + (file-name (git-file-name name version)) + (sha256 + (base32 + "1imq4577awc226wvygf94kpz156qdfw8xl0w0f7ss4w10lhmpmf5")))) + (build-system gnu-build-system) + (arguments + `(#:tests? #false ; there are none + #:phases + ;; There is no build system. + (modify-phases %standard-phases + (delete 'configure) + (replace 'build + (lambda _ + (invoke "g++" "-std=c++11" "-O3" + "src/sptree.cpp" + "src/tsne.cpp" + "src/nbodyfft.cpp" + "-o" "bin/fast_tsne" + "-pthread" "-lfftw3" "-lm" + "-Wno-address-of-packed-member"))) + (replace 'install + (lambda* (#:key outputs #:allow-other-keys) + (let* ((out (assoc-ref outputs "out")) + (bin (string-append out "/bin")) + (share (string-append out "/share/fit-sne"))) + (for-each (lambda (file) (install-file file bin)) + (find-files "bin")) + + (substitute* "fast_tsne.R" + (("^FAST_TSNE_SCRIPT_DIR.*") + (string-append "FAST_TSNE_SCRIPT_DIR = \"" out "\"\n"))) + (install-file "fast_tsne.R" share))))))) + (inputs + `(("fftw" ,fftw))) + (home-page "https://github.com/KlugerLab/FIt-SNE") + (synopsis "Fast Fourier Transform-accelerated interpolation-based t-SNE") + (description "@dfn{t-Stochastic Neighborhood Embedding} (t-SNE) is a +method for dimensionality reduction and visualization of high dimensional +datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to +approximate the gradient at each iteration of gradient descent. This +implementation differs in these ways: + +@itemize +@item Instead of approximating the N-body simulation using Barnes-Hut, we + interpolate onto an equispaced grid and use FFT to perform the convolution. +@item Instead of computing nearest neighbors using vantage-point trees, we + approximate nearest neighbors using the Annoy library. The neighbor lookups + are multithreaded to take advantage of machines with multiple cores. +@end itemize +") + ;; See LICENSE.txt for details on what license applies to what files. + (license (list license:bsd-4 license:expat license:asl2.0)))) + (define-public python-scanpy (package (name "python-scanpy") - (version "1.4.6") + (version "1.7.2") (source (origin (method url-fetch) (uri (pypi-uri "scanpy" version)) (sha256 (base32 - "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l")))) + "0c66adnfizsyk0h8bv2yhmay876z0klpxwpn4z6m71wly7yplpmd")))) (build-system python-build-system) (arguments `(#:phases @@ -12522,12 +11283,28 @@ in RNA-seq data.") (delete-file-recursively "scanpy/tests/notebooks") (delete-file "scanpy/tests/test_clustering.py") (delete-file "scanpy/tests/test_datasets.py") + (delete-file "scanpy/tests/test_highly_variable_genes.py") ;; TODO: I can't get the plotting tests to work, even with Xvfb. (delete-file "scanpy/tests/test_plotting.py") (delete-file "scanpy/tests/test_preprocessing.py") (delete-file "scanpy/tests/test_read_10x.py") + ;; The following tests need anndata.tests, which aren't included + ;; in the final python-anndata package. + (delete-file "scanpy/tests/test_combat.py") + (delete-file "scanpy/tests/test_embedding_plots.py") + (delete-file "scanpy/tests/test_normalization.py") + (delete-file "scanpy/tests/test_pca.py") + (delete-file "scanpy/tests/external/test_scrublet.py") + + ;; The following tests requires 'scanorama', which isn't + ;; packaged yet. + (delete-file "scanpy/tests/external/test_scanorama_integrate.py") + + (setenv "PYTHONPATH" + (string-append (getcwd) ":" + (getenv "PYTHONPATH"))) (invoke "pytest")))))) (propagated-inputs `(("python-anndata" ,python-anndata) @@ -12548,11 +11325,14 @@ in RNA-seq data.") ("python-seaborn" ,python-seaborn) ("python-statsmodels" ,python-statsmodels) ("python-tables" ,python-tables) + ("python-pytoml" ,python-pytoml) ("python-tqdm" ,python-tqdm) ("python-umap-learn" ,python-umap-learn))) (native-inputs - `(("python-pytest" ,python-pytest) - ("python-setuptools-scm" ,python-setuptools-scm))) + `(("python-leidenalg" ,python-leidenalg) + ("python-pytest" ,python-pytest) + ("python-setuptools-scm" ,python-setuptools-scm) + ("python-sinfo" ,python-sinfo))) (home-page "https://github.com/theislab/scanpy") (synopsis "Single-Cell Analysis in Python.") (description "Scanpy is a scalable toolkit for analyzing single-cell gene @@ -12874,15 +11654,39 @@ fasta subsequences.") (define-public python-cooler (package (name "python-cooler") - (version "0.8.7") + (version "0.8.11") (source (origin (method url-fetch) (uri (pypi-uri "cooler" version)) (sha256 (base32 - "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp")))) + "1i96fmpsimj4wrx51rxn8lw2gqxf5a2pvrj5rwdd6ivnm3pmhyrn")))) (build-system python-build-system) + (arguments + `(#:phases + (modify-phases %standard-phases + (add-after 'unpack 'patch-tests + (lambda _ + (substitute* "tests/test_create.py" + (("def test_roundtrip") + (string-append "@pytest.mark.skip(reason=\"requires network " + "access to genome.ucsc.edu\")\n" + "def test_roundtrip"))) + (substitute* "tests/test_util.py" + (("def test_fetch_chromsizes") + (string-append "@pytest.mark.skip(reason=\"requires network " + "access to genome.ucsc.edu\")\n" + "def test_fetch_chromsizes"))) + ;; This test depends on ipytree, which contains a lot of minified + ;; JavaScript. + (substitute* "tests/test_fileops.py" + (("def test_print_trees") + "def _test_print_trees")))) + (replace 'check + (lambda* (#:key tests? #:allow-other-keys) + (when tests? + (invoke "python" "-m" "pytest" "-v"))))))) (propagated-inputs `(("python-asciitree" ,python-asciitree) ("python-biopython" ,python-biopython) @@ -12898,11 +11702,17 @@ fasta subsequences.") ("python-pysam" ,python-pysam) ("python-pyyaml" ,python-pyyaml) ("python-scipy" ,python-scipy) - ("python-simplejson" ,python-simplejson))) + ("python-simplejson" ,python-simplejson) + ("python-six" ,python-six) + ("python-sparse" ,python-sparse))) (native-inputs - `(("python-mock" ,python-mock) - ("python-pytest" ,python-pytest))) - (home-page "https://github.com/mirnylab/cooler") + `(("python-codecov" ,python-codecov) + ("python-mock" ,python-mock) + ("python-pytest" ,python-pytest) + ("python-pytest-cov" ,python-pytest-cov) + ("python-pytest-flake8" ,python-pytest-flake8))) + ;; Almost all the projects of the Mirnylab are moved under Open2C umbrella + (home-page "https://github.com/open2c/cooler") (synopsis "Sparse binary format for genomic interaction matrices") (description "Cooler is a support library for a sparse, compressed, binary persistent @@ -14701,7 +13511,7 @@ manipulations on VCF files.") (define-public freebayes (package (name "freebayes") - (version "1.3.3") + (version "1.3.5") (source (origin (method git-fetch) (uri (git-reference @@ -14709,8 +13519,7 @@ manipulations on VCF files.") (commit (string-append "v" version)))) (file-name (git-file-name name version)) (sha256 - (base32 "0myz3giad7jqp6ricdfnig9ymlcps2h67mlivadvx97ngagm85z8")) - (patches (search-patches "freebayes-devendor-deps.patch")) + (base32 "1l0z88gq57kva677a6xri5g9k2d9h9lk5yk1q2xmq64wqhv7dvc3")) (modules '((guix build utils))) (snippet '(begin @@ -14722,8 +13531,7 @@ manipulations on VCF files.") ("htslib" ,htslib) ("smithwaterman" ,smithwaterman) ("tabixpp" ,tabixpp) - ("vcflib" ,vcflib) - ("zlib" ,zlib))) + ("vcflib" ,vcflib))) (native-inputs `(("bash-tap" ,bash-tap) ("bc" ,bc) @@ -14756,13 +13564,13 @@ manipulations on VCF files.") (string-append bash-tap "/bin/bash-tap-bootstrap")) (("source.*bash-tap-bootstrap") (string-append "source " bash-tap "/bin/bash-tap-bootstrap"))) - (substitute* "meson.build" - ;; Some inputs aren't actually needed. - ((".*bamtools/src.*") "") - ((".*multichoose.*") "")) (substitute* '("src/BedReader.cpp" "src/BedReader.h") (("../intervaltree/IntervalTree.h") "IntervalTree.h")) + (substitute* "meson.build" + ;; Our pkg-config file is vcflib.pc + (("libvcflib") "vcflib") + (("vcflib_inc,") "")) #t))) (add-after 'unpack 'unpack-submodule-sources (lambda* (#:key inputs #:allow-other-keys) |