X-Git-Url: https://git.hcoop.net/jackhill/guix/guix.git/blobdiff_plain/f8780e96ff9c4d1439f679aff0df559d97d673dc..2a72ef561b53b69210df2c1562f9d8ced35adabd:/gnu/packages/bioconductor.scm diff --git a/gnu/packages/bioconductor.scm b/gnu/packages/bioconductor.scm index f08e1a87c4..af2d7ce335 100644 --- a/gnu/packages/bioconductor.scm +++ b/gnu/packages/bioconductor.scm @@ -29,10 +29,15 @@ #:use-module (gnu packages compression) #:use-module (gnu packages gcc) #:use-module (gnu packages graph) + #:use-module (gnu packages haskell) #:use-module (gnu packages maths) + #:use-module (gnu packages pkg-config) #:use-module (gnu packages statistics) #:use-module (gnu packages web)) + +;;; Annotations + (define-public r-bsgenome-celegans-ucsc-ce6 (package (name "r-bsgenome-celegans-ucsc-ce6") @@ -438,6 +443,58 @@ annotations for the genome of the model fruit fly Drosophila melanogaster.") based on mapping using Entrez Gene identifiers.") (license license:artistic2.0))) +(define-public r-org-hs-eg-db + (package + (name "r-org-hs-eg-db") + (version "3.7.0") + (source (origin + (method url-fetch) + ;; We cannot use bioconductor-uri here because this tarball is + ;; located under "data/annotation/" instead of "bioc/". + (uri (string-append "https://www.bioconductor.org/packages/" + "release/data/annotation/src/contrib/" + "org.Hs.eg.db_" version ".tar.gz")) + (sha256 + (base32 + "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim")))) + (properties + `((upstream-name . "org.Hs.eg.db"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi))) + (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/") + (synopsis "Genome wide annotation for Human") + (description + "This package contains genome-wide annotations for Human, primarily based +on mapping using Entrez Gene identifiers.") + (license license:artistic2.0))) + +(define-public r-org-mm-eg-db + (package + (name "r-org-mm-eg-db") + (version "3.7.0") + (source (origin + (method url-fetch) + ;; We cannot use bioconductor-uri here because this tarball is + ;; located under "data/annotation/" instead of "bioc/". + (uri (string-append "https://www.bioconductor.org/packages/" + "release/data/annotation/src/contrib/" + "org.Mm.eg.db_" version ".tar.gz")) + (sha256 + (base32 + "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx")))) + (properties + `((upstream-name . "org.Mm.eg.db"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi))) + (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/") + (synopsis "Genome wide annotation for Mouse") + (description + "This package provides mappings from Entrez gene identifiers to various +annotations for the genome of the model mouse Mus musculus.") + (license license:artistic2.0))) + (define-public r-bsgenome-hsapiens-ucsc-hg19 (package (name "r-bsgenome-hsapiens-ucsc-hg19") @@ -472,7 +529,7 @@ by UCSC (hg19, February 2009) and stored in Biostrings objects.") (define-public r-genelendatabase (package (name "r-genelendatabase") - (version "1.16.0") + (version "1.18.0") (source (origin (method url-fetch) @@ -483,7 +540,7 @@ by UCSC (hg19, February 2009) and stored in Biostrings objects.") "/geneLenDataBase_" version ".tar.gz")) (sha256 (base32 - "07mmmn53kb7v14msc13dsbm8ghssbvwcrhifrk15hn37bw2p4ja5")))) + "03gm4pvsfascx7kjg0jycpf4f572mja68wwmwigs390vbmawyb4a")))) (properties `((upstream-name . "geneLenDataBase"))) (build-system r-build-system) @@ -594,7 +651,129 @@ the TxDb object of Mouse data as provided by UCSC (mm10, December 2011) based on the knownGene track.") (license license:artistic2.0))) +(define-public r-fdb-infiniummethylation-hg19 + (package + (name "r-fdb-infiniummethylation-hg19") + (version "2.2.0") + (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/" + "FDb.InfiniumMethylation.hg19_" + version ".tar.gz")) + (sha256 + (base32 + "0gq90fvph6kgrpjb89nvzq6hl1k24swn19rgjh5g98l86mja6nk0")))) + (properties + `((upstream-name . "FDb.InfiniumMethylation.hg19"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biostrings" ,r-biostrings) + ("r-genomicfeatures" ,r-genomicfeatures) + ("r-annotationdbi" ,r-annotationdbi) + ("r-org-hs-eg-db" ,r-org-hs-eg-db) + ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene))) + (home-page "https://bioconductor.org/packages/FDb.InfiniumMethylation.hg19/") + (synopsis "Compiled HumanMethylation27 and HumanMethylation450 annotations") + (description + "This is an annotation package for Illumina Infinium DNA methylation +probes. It contains the compiled HumanMethylation27 and HumanMethylation450 +annotations.") + (license license:artistic2.0))) + +(define-public r-illuminahumanmethylationepicmanifest + (package + (name "r-illuminahumanmethylationepicmanifest") + (version "0.3.0") + (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/" + "IlluminaHumanMethylationEPICmanifest_" + version ".tar.gz")) + (sha256 + (base32 + "0alhjda5g186z8b1nsmnpfswrlj7prdz8mkwx60wkkl6hkcnk6p3")))) + (properties + `((upstream-name . "IlluminaHumanMethylationEPICmanifest"))) + (build-system r-build-system) + (propagated-inputs + `(("r-minfi" ,r-minfi))) + (home-page "https://bioconductor.org/packages/IlluminaHumanMethylationEPICmanifest/") + (synopsis "Manifest for Illumina's EPIC methylation arrays") + (description + "This is a manifest package for Illumina's EPIC methylation arrays.") + (license license:artistic2.0))) + +(define-public r-do-db + (package + (name "r-do-db") + (version "2.9") + (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/" + "DO.db_" version ".tar.gz")) + (sha256 + (base32 + "10bqqa124l61ivzy4mdd3z3ar9a6537qbxw23pc4y9w8a6dwnavn")))) + (properties + `((upstream-name . "DO.db"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi))) + (home-page "https://www.bioconductor.org/packages/DO.db/") + (synopsis "Annotation maps describing the entire Disease Ontology") + (description + "This package provides a set of annotation maps describing the entire +Disease Ontology.") + (license license:artistic2.0))) + + +;;; Experiment data + +(define-public r-hsmmsinglecell + (package + (name "r-hsmmsinglecell") + (version "1.2.0") + (source (origin + (method url-fetch) + ;; We cannot use bioconductor-uri here because this tarball is + ;; located under "data/experiment/" instead of "bioc/". + (uri (string-append "https://www.bioconductor.org/packages/" + "release/data/experiment/src/contrib/" + "HSMMSingleCell_" version ".tar.gz")) + (sha256 + (base32 + "1vxnr8gr6md85g39csy7g2sqqajiqgyvznys2qa9yixd2b01yph9")))) + (properties + `((upstream-name . "HSMMSingleCell"))) + (build-system r-build-system) + (home-page "https://www.bioconductor.org/packages/HSMMSingleCell/") + (synopsis "Single-cell RNA-Seq for differentiating human skeletal muscle myoblasts (HSMM)") + (description + "Skeletal myoblasts undergo a well-characterized sequence of +morphological and transcriptional changes during differentiation. In this +experiment, primary @dfn{human skeletal muscle myoblasts} (HSMM) were expanded +under high mitogen conditions (GM) and then differentiated by switching to +low-mitogen media (DM). RNA-Seq libraries were sequenced from each of several +hundred cells taken over a time-course of serum-induced differentiation. +Between 49 and 77 cells were captured at each of four time points (0, 24, 48, +72 hours) following serum switch using the Fluidigm C1 microfluidic system. +RNA from each cell was isolated and used to construct mRNA-Seq libraries, +which were then sequenced to a depth of ~4 million reads per library, +resulting in a complete gene expression profile for each cell.") + (license license:artistic2.0))) + +;;; Packages + (define-public r-biocgenerics (package (name "r-biocgenerics") @@ -618,14 +797,14 @@ packages.") (define-public r-annotate (package (name "r-annotate") - (version "1.60.0") + (version "1.60.1") (source (origin (method url-fetch) (uri (bioconductor-uri "annotate" version)) (sha256 (base32 - "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n")))) + "0pk6ayr3vyqxk850ljkbyil4i382ngfqcbxlv0qrp62yfqgzcjwp")))) (build-system r-build-system) (propagated-inputs `(("r-annotationdbi" ,r-annotationdbi) @@ -714,6 +893,35 @@ region sets and other genomic features.") "This package provides functions for plotting genomic data.") (license license:artistic2.0))) +(define-public r-qvalue + (package + (name "r-qvalue") + (version "2.14.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "qvalue" version)) + (sha256 + (base32 + "0kxavzm1j2mk26qicmjm90nxx4w5h3dxighzks7wzihay3k8cysc")))) + (build-system r-build-system) + (propagated-inputs + `(("r-ggplot2" ,r-ggplot2) + ("r-reshape2" ,r-reshape2))) + (home-page "http://github.com/jdstorey/qvalue") + (synopsis "Q-value estimation for false discovery rate control") + (description + "This package takes a list of p-values resulting from the simultaneous +testing of many hypotheses and estimates their q-values and local @dfn{false +discovery rate} (FDR) values. The q-value of a test measures the proportion +of false positives incurred when that particular test is called significant. +The local FDR measures the posterior probability the null hypothesis is true +given the test's p-value. Various plots are automatically generated, allowing +one to make sensible significance cut-offs. The software can be applied to +problems in genomics, brain imaging, astrophysics, and data mining.") + ;; Any version of the LGPL. + (license license:lgpl3+))) + (define-public r-diffbind (package (name "r-diffbind") @@ -1642,3 +1850,1424 @@ estimation is performed using either the EM or CEM algorithm, and the slope heuristics are used for model selection (i.e., to choose the number of clusters).") (license license:gpl3+))) + +(define-public r-deds + (package + (name "r-deds") + (version "1.56.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "DEDS" version)) + (sha256 + (base32 + "1zfgaar3bpss49zhs81mwlfzkx5lv92j8a64xd12ig88is24cw2c")))) + (properties `((upstream-name . "DEDS"))) + (build-system r-build-system) + (home-page "https://bioconductor.org/packages/DEDS/") + (synopsis "Differential expression via distance summary for microarray data") + (description + "This library contains functions that calculate various statistics of +differential expression for microarray data, including t statistics, fold +change, F statistics, SAM, moderated t and F statistics and B statistics. It +also implements a new methodology called DEDS (Differential Expression via +Distance Summary), which selects differentially expressed genes by integrating +and summarizing a set of statistics using a weighted distance approach.") + ;; Any version of the LGPL. + (license license:lgpl3+))) + +;; This is a CRAN package, but since it depends on a Bioconductor package we +;; put it here. +(define-public r-nbpseq + (package + (name "r-nbpseq") + (version "0.3.0") + (source + (origin + (method url-fetch) + (uri (cran-uri "NBPSeq" version)) + (sha256 + (base32 + "0l4ylxhs2k9ww21jjqs67fygk92avdchhx2y1ixzl7yr2yh1y9by")))) + (properties `((upstream-name . "NBPSeq"))) + (build-system r-build-system) + (propagated-inputs + `(("r-qvalue" ,r-qvalue))) + (home-page "https://cran.r-project.org/web/packages/NBPSeq") + (synopsis "Negative binomial models for RNA-Seq data") + (description + "This package provides negative binomial models for two-group comparisons +and regression inferences from RNA-sequencing data.") + (license license:gpl2))) + +(define-public r-ebseq + (package + (name "r-ebseq") + (version "1.22.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "EBSeq" version)) + (sha256 + (base32 + "1gzbk1hbwdan0j131ah88yryfvsiq0wqjnb09qbr4qaczpgvbad0")))) + (properties `((upstream-name . "EBSeq"))) + (build-system r-build-system) + (propagated-inputs + `(("r-blockmodeling" ,r-blockmodeling) + ("r-gplots" ,r-gplots) + ("r-testthat" ,r-testthat))) + (home-page "https://bioconductor.org/packages/EBSeq") + (synopsis "Differential expression analysis of RNA-seq data") + (description + "This package provides tools for differential expression analysis at both +gene and isoform level using RNA-seq data") + (license license:artistic2.0))) + +(define-public r-lpsymphony + (package + (name "r-lpsymphony") + (version "1.10.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "lpsymphony" version)) + (sha256 + (base32 + "0vnsf5x6gvd1k8h89al7r6xbgbxsjbxphr675czzwggz79zbvq7y")))) + (build-system r-build-system) + (inputs + `(("gfortran" ,gfortran) + ("zlib" ,zlib))) + (native-inputs + `(("pkg-config" ,pkg-config))) + (home-page "http://r-forge.r-project.org/projects/rsymphony") + (synopsis "Symphony integer linear programming solver in R") + (description + "This package was derived from Rsymphony. The package provides an R +interface to SYMPHONY, a linear programming solver written in C++. The main +difference between this package and Rsymphony is that it includes the solver +source code, while Rsymphony expects to find header and library files on the +users' system. Thus the intention of @code{lpsymphony} is to provide an easy +to install interface to SYMPHONY.") + ;; Symphony 5.4 or later is distributed under the terms of the EPL 1.0. + ;; lpsimphony is released under the same terms. + (license license:epl1.0))) + +(define-public r-ihw + (package + (name "r-ihw") + (version "1.10.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "IHW" version)) + (sha256 + (base32 + "10wqasl8k2j3y5qvak3xr2xj6symk656xww1y5n2l22nz832j19n")))) + (properties `((upstream-name . "IHW"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biocgenerics" ,r-biocgenerics) + ("r-fdrtool" ,r-fdrtool) + ("r-lpsymphony" ,r-lpsymphony) + ("r-slam" ,r-slam))) + (home-page "https://bioconductor.org/packages/IHW") + (synopsis "Independent hypothesis weighting") + (description + "@dfn{Independent hypothesis weighting} (IHW) is a multiple testing +procedure that increases power compared to the method of Benjamini and +Hochberg by assigning data-driven weights to each hypothesis. The input to +IHW is a two-column table of p-values and covariates. The covariate can be +any continuous-valued or categorical variable that is thought to be +informative on the statistical properties of each hypothesis test, while it is +independent of the p-value under the null hypothesis.") + (license license:artistic2.0))) + +(define-public r-icobra + (package + (name "r-icobra") + (version "1.10.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "iCOBRA" version)) + (sha256 + (base32 + "0i1swrm31g0zffi5pm48bfvdfqpd32d0zdchkbyipz96al46jnld")))) + (properties `((upstream-name . "iCOBRA"))) + (build-system r-build-system) + (propagated-inputs + `(("r-dplyr" ,r-dplyr) + ("r-dt" ,r-dt) + ("r-ggplot2" ,r-ggplot2) + ("r-limma" ,r-limma) + ("r-reshape2" ,r-reshape2) + ("r-rocr" ,r-rocr) + ("r-scales" ,r-scales) + ("r-shiny" ,r-shiny) + ("r-shinybs" ,r-shinybs) + ("r-shinydashboard" ,r-shinydashboard) + ("r-upsetr" ,r-upsetr))) + (home-page "https://bioconductor.org/packages/iCOBRA") + (synopsis "Comparison and visualization of ranking and assignment methods") + (description + "This package provides functions for calculation and visualization of +performance metrics for evaluation of ranking and binary +classification (assignment) methods. It also contains a Shiny application for +interactive exploration of results.") + (license license:gpl2+))) + +(define-public r-mast + (package + (name "r-mast") + (version "1.8.2") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "MAST" version)) + (sha256 + (base32 + "0rhx655dza0m6yg9jcfz2nmxqahvxx2l91kqgyp7qai0bzz9d9ix")))) + (properties `((upstream-name . "MAST"))) + (build-system r-build-system) + (propagated-inputs + `(("r-abind" ,r-abind) + ("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-data-table" ,r-data-table) + ("r-ggplot2" ,r-ggplot2) + ("r-plyr" ,r-plyr) + ("r-progress" ,r-progress) + ("r-reshape2" ,r-reshape2) + ("r-s4vectors" ,r-s4vectors) + ("r-singlecellexperiment" ,r-singlecellexperiment) + ("r-stringr" ,r-stringr) + ("r-summarizedexperiment" ,r-summarizedexperiment))) + (home-page "https://github.com/RGLab/MAST/") + (synopsis "Model-based analysis of single cell transcriptomics") + (description + "This package provides methods and models for handling zero-inflated +single cell assay data.") + (license license:gpl2+))) + +(define-public r-monocle + (package + (name "r-monocle") + (version "2.10.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "monocle" version)) + (sha256 + (base32 + "0shwkgqs93j2l5h36yyvb1lf724107cfjrmzp5fxfj1lqc0y61lf")))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-biocviews" ,r-biocviews) + ("r-cluster" ,r-cluster) + ("r-combinat" ,r-combinat) + ("r-ddrtree" ,r-ddrtree) + ("r-densityclust" ,r-densityclust) + ("r-dplyr" ,r-dplyr) + ("r-fastica" ,r-fastica) + ("r-ggplot2" ,r-ggplot2) + ("r-hsmmsinglecell" ,r-hsmmsinglecell) + ("r-igraph" ,r-igraph) + ("r-irlba" ,r-irlba) + ("r-limma" ,r-limma) + ("r-mass" ,r-mass) + ("r-matrix" ,r-matrix) + ("r-matrixstats" ,r-matrixstats) + ("r-pheatmap" ,r-pheatmap) + ("r-plyr" ,r-plyr) + ("r-proxy" ,r-proxy) + ("r-qlcmatrix" ,r-qlcmatrix) + ("r-rann" ,r-rann) + ("r-rcpp" ,r-rcpp) + ("r-reshape2" ,r-reshape2) + ("r-rtsne" ,r-rtsne) + ("r-slam" ,r-slam) + ("r-stringr" ,r-stringr) + ("r-tibble" ,r-tibble) + ("r-vgam" ,r-vgam) + ("r-viridis" ,r-viridis))) + (home-page "https://bioconductor.org/packages/monocle") + (synopsis "Clustering, differential expression, and trajectory analysis for single-cell RNA-Seq") + (description + "Monocle performs differential expression and time-series analysis for +single-cell expression experiments. It orders individual cells according to +progress through a biological process, without knowing ahead of time which +genes define progress through that process. Monocle also performs +differential expression analysis, clustering, visualization, and other useful +tasks on single cell expression data. It is designed to work with RNA-Seq and +qPCR data, but could be used with other types as well.") + (license license:artistic2.0))) + +(define-public r-noiseq + (package + (name "r-noiseq") + (version "2.26.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "NOISeq" version)) + (sha256 + (base32 + "1wyhhi9ydlbjlz427093mdp5ppby77n37w5c2iyxlpsdk2m2nqsn")))) + (properties `((upstream-name . "NOISeq"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-matrix" ,r-matrix))) + (home-page "https://bioconductor.org/packages/NOISeq") + (synopsis "Exploratory analysis and differential expression for RNA-seq data") + (description + "This package provides tools to support the analysis of RNA-seq +expression data or other similar kind of data. It provides exploratory plots +to evaluate saturation, count distribution, expression per chromosome, type of +detected features, features length, etc. It also supports the analysis of +differential expression between two experimental conditions with no parametric +assumptions.") + (license license:artistic2.0))) + +(define-public r-scdd + (package + (name "r-scdd") + (version "1.6.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "scDD" version)) + (sha256 + (base32 + "0dp2awajd5281dwpbs0wb8ij2pq9l60p0b80xhxrb41m5qybcri8")))) + (properties `((upstream-name . "scDD"))) + (build-system r-build-system) + (propagated-inputs + `(("r-arm" ,r-arm) + ("r-biocparallel" ,r-biocparallel) + ("r-ebseq" ,r-ebseq) + ("r-fields" ,r-fields) + ("r-ggplot2" ,r-ggplot2) + ("r-mclust" ,r-mclust) + ("r-outliers" ,r-outliers) + ("r-s4vectors" ,r-s4vectors) + ("r-scran" ,r-scran) + ("r-singlecellexperiment" ,r-singlecellexperiment) + ("r-summarizedexperiment" ,r-summarizedexperiment))) + (home-page "https://github.com/kdkorthauer/scDD") + (synopsis "Mixture modeling of single-cell RNA-seq data") + (description + "This package implements a method to analyze single-cell RNA-seq data +utilizing flexible Dirichlet Process mixture models. Genes with differential +distributions of expression are classified into several interesting patterns +of differences between two conditions. The package also includes functions +for simulating data with these patterns from negative binomial +distributions.") + (license license:gpl2))) + +(define-public r-scone + (package + (name "r-scone") + (version "1.6.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "scone" version)) + (sha256 + (base32 + "0l1x4cjnfjbpx6k55sjqx03555daa6v63rq0rg6b7jpz8xxzwa7p")))) + (build-system r-build-system) + (propagated-inputs + `(("r-aroma-light" ,r-aroma-light) + ("r-biocparallel" ,r-biocparallel) + ("r-boot" ,r-boot) + ("r-class" ,r-class) + ("r-cluster" ,r-cluster) + ("r-compositions" ,r-compositions) + ("r-diptest" ,r-diptest) + ("r-edger" ,r-edger) + ("r-fpc" ,r-fpc) + ("r-gplots" ,r-gplots) + ("r-hexbin" ,r-hexbin) + ("r-limma" ,r-limma) + ("r-matrixstats" ,r-matrixstats) + ("r-mixtools" ,r-mixtools) + ("r-rarpack" ,r-rarpack) + ("r-rcolorbrewer" ,r-rcolorbrewer) + ("r-rhdf5" ,r-rhdf5) + ("r-ruvseq" ,r-ruvseq) + ("r-summarizedexperiment" ,r-summarizedexperiment))) + (home-page "https://bioconductor.org/packages/scone") + (synopsis "Single cell overview of normalized expression data") + (description + "SCONE is an R package for comparing and ranking the performance of +different normalization schemes for single-cell RNA-seq and other +high-throughput analyses.") + (license license:artistic2.0))) + +(define-public r-geoquery + (package + (name "r-geoquery") + (version "2.50.5") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "GEOquery" version)) + (sha256 + (base32 + "074dl00c8yi1ihpjkw7vl9vy2hggvipib0jn0hli0wrw7x1h9hg6")))) + (properties `((upstream-name . "GEOquery"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-dplyr" ,r-dplyr) + ("r-httr" ,r-httr) + ("r-limma" ,r-limma) + ("r-magrittr" ,r-magrittr) + ("r-readr" ,r-readr) + ("r-tidyr" ,r-tidyr) + ("r-xml2" ,r-xml2))) + (home-page "https://github.com/seandavi/GEOquery/") + (synopsis "Get data from NCBI Gene Expression Omnibus (GEO)") + (description + "The NCBI Gene Expression Omnibus (GEO) is a public repository of +microarray data. Given the rich and varied nature of this resource, it is +only natural to want to apply BioConductor tools to these data. GEOquery is +the bridge between GEO and BioConductor.") + (license license:gpl2))) + +(define-public r-illuminaio + (package + (name "r-illuminaio") + (version "0.24.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "illuminaio" version)) + (sha256 + (base32 + "1rdp9b4xlv91yzba7pd7k50s3nkljfxmdmyz5jl0j8ybhmpl6rns")))) + (build-system r-build-system) + (propagated-inputs + `(("r-base64" ,r-base64))) + (home-page "https://github.com/HenrikBengtsson/illuminaio/") + (synopsis "Parse Illumina microarray output files") + (description + "This package provides tools for parsing Illumina's microarray output +files, including IDAT.") + (license license:gpl2))) + +(define-public r-siggenes + (package + (name "r-siggenes") + (version "1.56.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "siggenes" version)) + (sha256 + (base32 + "0cjlb5r04x15xkhk00i3wvpx21kj0k29pn0mj3whwqk31zznnk1b")))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-multtest" ,r-multtest))) + (home-page "https://bioconductor.org/packages/siggenes/") + (synopsis + "Multiple testing using SAM and Efron's empirical Bayes approaches") + (description + "This package provides tools for the identification of differentially +expressed genes and estimation of the @dfn{False Discovery Rate} (FDR) using +both the Significance Analysis of Microarrays (SAM) and the @dfn{Empirical +Bayes Analyses of Microarrays} (EBAM).") + (license license:lgpl2.0+))) + +(define-public r-bumphunter + (package + (name "r-bumphunter") + (version "1.24.5") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "bumphunter" version)) + (sha256 + (base32 + "1f9vk3srffbx8jpza40nd18a4y0p0z8q40mx55dlcnddkwrqi19b")))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-biocgenerics" ,r-biocgenerics) + ("r-dorng" ,r-dorng) + ("r-foreach" ,r-foreach) + ("r-genomeinfodb" ,r-genomeinfodb) + ("r-genomicfeatures" ,r-genomicfeatures) + ("r-genomicranges" ,r-genomicranges) + ("r-iranges" ,r-iranges) + ("r-iterators" ,r-iterators) + ("r-limma" ,r-limma) + ("r-locfit" ,r-locfit) + ("r-matrixstats" ,r-matrixstats) + ("r-s4vectors" ,r-s4vectors))) + (home-page "https://github.com/ririzarr/bumphunter") + (synopsis "Find bumps in genomic data") + (description + "This package provides tools for finding bumps in genomic data in order +to identify differentially methylated regions in epigenetic epidemiology +studies.") + (license license:artistic2.0))) + +(define-public r-minfi + (package + (name "r-minfi") + (version "1.28.4") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "minfi" version)) + (sha256 + (base32 + "1sjwwqb0syngvj75saaky9y06hbxsawhhcmfvavzkhicxipafv7r")))) + (build-system r-build-system) + (propagated-inputs + `(("r-beanplot" ,r-beanplot) + ("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-biocparallel" ,r-biocparallel) + ("r-biostrings" ,r-biostrings) + ("r-bumphunter" ,r-bumphunter) + ("r-data-table" ,r-data-table) + ("r-delayedarray" ,r-delayedarray) + ("r-delayedmatrixstats" ,r-delayedmatrixstats) + ("r-genefilter" ,r-genefilter) + ("r-genomeinfodb" ,r-genomeinfodb) + ("r-genomicranges" ,r-genomicranges) + ("r-geoquery" ,r-geoquery) + ("r-hdf5array" ,r-hdf5array) + ("r-illuminaio" ,r-illuminaio) + ("r-iranges" ,r-iranges) + ("r-lattice" ,r-lattice) + ("r-limma" ,r-limma) + ("r-mass" ,r-mass) + ("r-mclust" ,r-mclust) + ("r-nlme" ,r-nlme) + ("r-nor1mix" ,r-nor1mix) + ("r-preprocesscore" ,r-preprocesscore) + ("r-quadprog" ,r-quadprog) + ("r-rcolorbrewer" ,r-rcolorbrewer) + ("r-reshape" ,r-reshape) + ("r-s4vectors" ,r-s4vectors) + ("r-siggenes" ,r-siggenes) + ("r-summarizedexperiment" ,r-summarizedexperiment))) + (home-page "https://github.com/hansenlab/minfi") + (synopsis "Analyze Illumina Infinium DNA methylation arrays") + (description + "This package provides tools to analyze and visualize Illumina Infinium +methylation arrays.") + (license license:artistic2.0))) + +(define-public r-methylumi + (package + (name "r-methylumi") + (version "2.28.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "methylumi" version)) + (sha256 + (base32 + "14p2qi18cprfvb2gxng1vm48c7zwh23h88q9qjgipj9xl5axsgw2")))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotate" ,r-annotate) + ("r-annotationdbi" ,r-annotationdbi) + ("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-fdb-infiniummethylation-hg19" ,r-fdb-infiniummethylation-hg19) + ("r-genefilter" ,r-genefilter) + ("r-genomeinfodb" ,r-genomeinfodb) + ("r-genomicranges" ,r-genomicranges) + ("r-ggplot2" ,r-ggplot2) + ("r-illuminaio" ,r-illuminaio) + ("r-iranges" ,r-iranges) + ("r-lattice" ,r-lattice) + ("r-matrixstats" ,r-matrixstats) + ("r-minfi" ,r-minfi) + ("r-reshape2" ,r-reshape2) + ("r-s4vectors" ,r-s4vectors) + ("r-scales" ,r-scales) + ("r-summarizedexperiment" ,r-summarizedexperiment))) + (home-page "https://bioconductor.org/packages/methylumi") + (synopsis "Handle Illumina methylation data") + (description + "This package provides classes for holding and manipulating Illumina +methylation data. Based on eSet, it can contain MIAME information, sample +information, feature information, and multiple matrices of data. An +\"intelligent\" import function, methylumiR can read the Illumina text files +and create a MethyLumiSet. methylumIDAT can directly read raw IDAT files from +HumanMethylation27 and HumanMethylation450 microarrays. Normalization, +background correction, and quality control features for GoldenGate, Infinium, +and Infinium HD arrays are also included.") + (license license:gpl2))) + +(define-public r-lumi + (package + (name "r-lumi") + (version "2.34.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "lumi" version)) + (sha256 + (base32 + "1fpmjpgcy5n0hx9whn9m3jhjmciqq0l59nvy5addbq0a4wnjhx8q")))) + (build-system r-build-system) + (propagated-inputs + `(("r-affy" ,r-affy) + ("r-annotate" ,r-annotate) + ("r-annotationdbi" ,r-annotationdbi) + ("r-biobase" ,r-biobase) + ("r-dbi" ,r-dbi) + ("r-genomicfeatures" ,r-genomicfeatures) + ("r-genomicranges" ,r-genomicranges) + ("r-kernsmooth" ,r-kernsmooth) + ("r-lattice" ,r-lattice) + ("r-mass" ,r-mass) + ("r-methylumi" ,r-methylumi) + ("r-mgcv" ,r-mgcv) + ("r-nleqslv" ,r-nleqslv) + ("r-preprocesscore" ,r-preprocesscore) + ("r-rsqlite" ,r-rsqlite))) + (home-page "https://bioconductor.org/packages/lumi") + (synopsis "BeadArray-specific methods for Illumina methylation and expression microarrays") + (description + "The lumi package provides an integrated solution for the Illumina +microarray data analysis. It includes functions of Illumina +BeadStudio (GenomeStudio) data input, quality control, BeadArray-specific +variance stabilization, normalization and gene annotation at the probe level. +It also includes the functions of processing Illumina methylation microarrays, +especially Illumina Infinium methylation microarrays.") + (license license:lgpl2.0+))) + +(define-public r-linnorm + (package + (name "r-linnorm") + (version "2.6.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "Linnorm" version)) + (sha256 + (base32 + "1qgk8m5kc409flqxs3vnf228v3z0112q8py9hgfgyiwvi6yzdbp6")))) + (properties `((upstream-name . "Linnorm"))) + (build-system r-build-system) + (propagated-inputs + `(("r-amap" ,r-amap) + ("r-apcluster" ,r-apcluster) + ("r-ellipse" ,r-ellipse) + ("r-fastcluster" ,r-fastcluster) + ("r-fpc" ,r-fpc) + ("r-ggdendro" ,r-ggdendro) + ("r-ggplot2" ,r-ggplot2) + ("r-gmodels" ,r-gmodels) + ("r-igraph" ,r-igraph) + ("r-limma" ,r-limma) + ("r-mass" ,r-mass) + ("r-mclust" ,r-mclust) + ("r-rcpp" ,r-rcpp) + ("r-rcpparmadillo" ,r-rcpparmadillo) + ("r-rtsne" ,r-rtsne) + ("r-statmod" ,r-statmod) + ("r-vegan" ,r-vegan) + ("r-zoo" ,r-zoo))) + (home-page "http://www.jjwanglab.org/Linnorm/") + (synopsis "Linear model and normality based transformation method") + (description + "Linnorm is an R package for the analysis of RNA-seq, scRNA-seq, ChIP-seq +count data or any large scale count data. It transforms such datasets for +parametric tests. In addition to the transformtion function (@code{Linnorm}), +the following pipelines are implemented: + +@enumerate +@item Library size/batch effect normalization (@code{Linnorm.Norm}) +@item Cell subpopluation analysis and visualization using t-SNE or PCA K-means + clustering or hierarchical clustering (@code{Linnorm.tSNE}, + @code{Linnorm.PCA}, @code{Linnorm.HClust}) +@item Differential expression analysis or differential peak detection using + limma (@code{Linnorm.limma}) +@item Highly variable gene discovery and visualization (@code{Linnorm.HVar}) +@item Gene correlation network analysis and visualization (@code{Linnorm.Cor}) +@item Stable gene selection for scRNA-seq data; for users without or who do + not want to rely on spike-in genes (@code{Linnorm.SGenes}) +@item Data imputation (@code{Linnorm.DataImput}). +@end enumerate + +Linnorm can work with raw count, CPM, RPKM, FPKM and TPM. Additionally, the +@code{RnaXSim} function is included for simulating RNA-seq data for the +evaluation of DEG analysis methods.") + (license license:expat))) + +(define-public r-ioniser + (package + (name "r-ioniser") + (version "2.6.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "IONiseR" version)) + (sha256 + (base32 + "01lqisdlsvym8nhgpzn7lpcddk9lv9253dy9v65r2dicb5xqhj00")))) + (properties `((upstream-name . "IONiseR"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biocgenerics" ,r-biocgenerics) + ("r-biocparallel" ,r-biocparallel) + ("r-biostrings" ,r-biostrings) + ("r-bit64" ,r-bit64) + ("r-dplyr" ,r-dplyr) + ("r-ggplot2" ,r-ggplot2) + ("r-magrittr" ,r-magrittr) + ("r-rhdf5" ,r-rhdf5) + ("r-shortread" ,r-shortread) + ("r-stringr" ,r-stringr) + ("r-tibble" ,r-tibble) + ("r-tidyr" ,r-tidyr) + ("r-xvector" ,r-xvector))) + (home-page "https://bioconductor.org/packages/IONiseR/") + (synopsis "Quality assessment tools for Oxford Nanopore MinION data") + (description + "IONiseR provides tools for the quality assessment of Oxford Nanopore +MinION data. It extracts summary statistics from a set of fast5 files and can +be used either before or after base calling. In addition to standard +summaries of the read-types produced, it provides a number of plots for +visualising metrics relative to experiment run time or spatially over the +surface of a flowcell.") + (license license:expat))) + +;; This is a CRAN package, but it depends on packages from Bioconductor. +(define-public r-gkmsvm + (package + (name "r-gkmsvm") + (version "0.79.0") + (source + (origin + (method url-fetch) + (uri (cran-uri "gkmSVM" version)) + (sha256 + (base32 + "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3")))) + (properties `((upstream-name . "gkmSVM"))) + (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-kernlab" ,r-kernlab) + ("r-rcpp" ,r-rcpp) + ("r-rocr" ,r-rocr) + ("r-rtracklayer" ,r-rtracklayer) + ("r-s4vectors" ,r-s4vectors) + ("r-seqinr" ,r-seqinr))) + (home-page "https://cran.r-project.org/web/packages/gkmSVM") + (synopsis "Gapped-kmer support vector machine") + (description + "This R package provides tools for training gapped-kmer SVM classifiers +for DNA and protein sequences. This package supports several sequence +kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.") + (license license:gpl2+))) + +(define-public r-triform + (package + (name "r-triform") + (version "1.24.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "triform" version)) + (sha256 + (base32 + "12ca24pv1r5vbw3rq345jqg7x3prrbsxk6445zikpzfblwmw0b4s")))) + (build-system r-build-system) + (propagated-inputs + `(("r-biocgenerics" ,r-biocgenerics) + ("r-iranges" ,r-iranges) + ("r-yaml" ,r-yaml))) + (home-page "https://bioconductor.org/packages/triform/") + (synopsis "Find enriched regions in transcription factor ChIP-sequencing data") + (description + "The Triform algorithm uses model-free statistics to identify peak-like +distributions of TF ChIP sequencing reads, taking advantage of an improved +peak definition in combination with known profile characteristics.") + (license license:gpl2))) + +(define-public r-varianttools + (package + (name "r-varianttools") + (version "1.24.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "VariantTools" version)) + (sha256 + (base32 + "1ml3pl7xnxvzr6zkypr80xzw6nffswk29gzxycn42473sc4ixn7j")))) + (properties `((upstream-name . "VariantTools"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-biocparallel" ,r-biocparallel) + ("r-biostrings" ,r-biostrings) + ("r-bsgenome" ,r-bsgenome) + ("r-genomeinfodb" ,r-genomeinfodb) + ("r-genomicfeatures" ,r-genomicfeatures) + ("r-genomicranges" ,r-genomicranges) + ("r-iranges" ,r-iranges) + ("r-matrix" ,r-matrix) + ("r-rsamtools" ,r-rsamtools) + ("r-rtracklayer" ,r-rtracklayer) + ("r-s4vectors" ,r-s4vectors) + ("r-variantannotation" ,r-variantannotation))) + (home-page "https://bioconductor.org/packages/VariantTools/") + (synopsis "Tools for exploratory analysis of variant calls") + (description + "Explore, diagnose, and compare variant calls using filters. The +VariantTools package supports a workflow for loading data, calling single +sample variants and tumor-specific somatic mutations or other sample-specific +variant types (e.g., RNA editing). Most of the functions operate on +alignments (BAM files) or datasets of called variants. The user is expected +to have already aligned the reads with a separate tool, e.g., GSNAP via +gmapR.") + (license license:artistic2.0))) + +(define-public r-heatplus + (package + (name "r-heatplus") + (version "2.28.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "Heatplus" version)) + (sha256 + (base32 + "0drspjzgb23ra2kdvpxhsd8mdifsf97fcf668llyz2hr0r39fc48")))) + (properties `((upstream-name . "Heatplus"))) + (build-system r-build-system) + (propagated-inputs + `(("r-rcolorbrewer" ,r-rcolorbrewer))) + (home-page "https://github.com/alexploner/Heatplus") + (synopsis "Heatmaps with row and/or column covariates and colored clusters") + (description + "This package provides tools to display a rectangular heatmap (intensity +plot) of a data matrix. By default, both samples (columns) and features (row) +of the matrix are sorted according to a hierarchical clustering, and the +corresponding dendrogram is plotted. Optionally, panels with additional +information about samples and features can be added to the plot.") + (license license:gpl2+))) + +(define-public r-gosemsim + (package + (name "r-gosemsim") + (version "2.8.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "GOSemSim" version)) + (sha256 + (base32 + "0ckihpy8jmgn2np1avprz76v9z7i5hqm2gj514c6dmmq3csbc7ib")))) + (properties `((upstream-name . "GOSemSim"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-go-db" ,r-go-db) + ("r-rcpp" ,r-rcpp))) + (home-page "https://guangchuangyu.github.io/software/GOSemSim") + (synopsis "GO-terms semantic similarity measures") + (description + "The semantic comparisons of @dfn{Gene Ontology} (GO) annotations provide +quantitative ways to compute similarities between genes and gene groups, and +have became important basis for many bioinformatics analysis approaches. +GOSemSim is an R package for semantic similarity computation among GO terms, +sets of GO terms, gene products and gene clusters.") + (license license:artistic2.0))) + +(define-public r-anota + (package + (name "r-anota") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "anota" version)) + (sha256 + (base32 + "182fp6dpws516y0igvwn6936higfqvy25haa0xs273f8aczr9cf0")))) + (build-system r-build-system) + (propagated-inputs + `(("r-multtest" ,r-multtest) + ("r-qvalue" ,r-qvalue))) + (home-page "https://bioconductor.org/packages/anota/") + (synopsis "Analysis of translational activity") + (description + "Genome wide studies of translational control is emerging as a tool to +study verious biological conditions. The output from such analysis is both +the mRNA level (e.g. cytosolic mRNA level) and the levl of mRNA actively +involved in translation (the actively translating mRNA level) for each mRNA. +The standard analysis of such data strives towards identifying differential +translational between two or more sample classes - i.e. differences in +actively translated mRNA levels that are independent of underlying differences +in cytosolic mRNA levels. This package allows for such analysis using partial +variances and the random variance model. As 10s of thousands of mRNAs are +analyzed in parallell the library performs a number of tests to assure that +the data set is suitable for such analysis.") + (license license:gpl3))) + +(define-public r-sigpathway + (package + (name "r-sigpathway") + (version "1.50.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "sigPathway" version)) + (sha256 + (base32 + "0pygrla2q2151981gshzv51jnj60h1df3vby5gsxqvxn2pdr4bv3")))) + (properties `((upstream-name . "sigPathway"))) + (build-system r-build-system) + (home-page "https://www.pnas.org/cgi/doi/10.1073/pnas.0506577102") + (synopsis "Pathway analysis") + (description + "This package is used to conduct pathway analysis by calculating the NT_k +and NE_k statistics in a statistical framework for determining whether a +specified group of genes for a pathway has a coordinated association with a +phenotype of interest.") + (license license:gpl2))) + +(define-public r-fgsea + (package + (name "r-fgsea") + (version "1.8.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "fgsea" version)) + (sha256 + (base32 + "0cxxvlmg340l5l5fz4abbwppiri0ibg4navvq5k3wg511mz8ma2q")))) + (build-system r-build-system) + (propagated-inputs + `(("r-biocparallel" ,r-biocparallel) + ("r-data-table" ,r-data-table) + ("r-fastmatch" ,r-fastmatch) + ("r-ggplot2" ,r-ggplot2) + ("r-gridextra" ,r-gridextra) + ("r-matrix" ,r-matrix) + ("r-rcpp" ,r-rcpp))) + (home-page "https://github.com/ctlab/fgsea/") + (synopsis "Fast gene set enrichment analysis") + (description + "The package implements an algorithm for fast gene set enrichment +analysis. Using the fast algorithm allows to make more permutations and get +more fine grained p-values, which allows to use accurate stantard approaches +to multiple hypothesis correction.") + (license license:expat))) + +(define-public r-dose + (package + (name "r-dose") + (version "3.8.2") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "DOSE" version)) + (sha256 + (base32 + "1gh7dhvfc71kawxcfx8xqlir7mwvg5mmz4lqrdrvw5knvi2h3mfa")))) + (properties `((upstream-name . "DOSE"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-biocparallel" ,r-biocparallel) + ("r-do-db" ,r-do-db) + ("r-fgsea" ,r-fgsea) + ("r-ggplot2" ,r-ggplot2) + ("r-gosemsim" ,r-gosemsim) + ("r-qvalue" ,r-qvalue) + ("r-reshape2" ,r-reshape2) + ("r-s4vectors" ,r-s4vectors))) + (home-page "https://guangchuangyu.github.io/software/DOSE/") + (synopsis "Disease ontology semantic and enrichment analysis") + (description + "This package implements five methods proposed by Resnik, Schlicker, +Jiang, Lin and Wang, respectively, for measuring semantic similarities among +@dfn{Disease ontology} (DO) terms and gene products. Enrichment analyses +including hypergeometric model and gene set enrichment analysis are also +implemented for discovering disease associations of high-throughput biological +data.") + (license license:artistic2.0))) + +(define-public r-enrichplot + (package + (name "r-enrichplot") + (version "1.2.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "enrichplot" version)) + (sha256 + (base32 + "0cxqfpy6py4k3z3lnlkiwx89r4ymfpdc4hm25dfpazqgjflz5is7")))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-cowplot" ,r-cowplot) + ("r-dose" ,r-dose) + ("r-europepmc" ,r-europepmc) + ("r-ggplot2" ,r-ggplot2) + ("r-ggplotify" ,r-ggplotify) + ("r-ggraph" ,r-ggraph) + ("r-ggridges" ,r-ggridges) + ("r-gosemsim" ,r-gosemsim) + ("r-gridextra" ,r-gridextra) + ("r-igraph" ,r-igraph) + ("r-purrr" ,r-purrr) + ("r-rcolorbrewer" ,r-rcolorbrewer) + ("r-reshape2" ,r-reshape2) + ("r-upsetr" ,r-upsetr))) + (home-page "https://github.com/GuangchuangYu/enrichplot") + (synopsis "Visualization of functional enrichment result") + (description + "The enrichplot package implements several visualization methods for +interpreting functional enrichment results obtained from ORA or GSEA analyses. +All the visualization methods are developed based on ggplot2 graphics.") + (license license:artistic2.0))) + +(define-public r-clusterprofiler + (package + (name "r-clusterprofiler") + (version "3.10.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "clusterProfiler" version)) + (sha256 + (base32 + "1v4fh8ll7zk8yhbaa0nq9xvqrb05kyvbpwkqpnjf07s873805rxm")))) + (properties + `((upstream-name . "clusterProfiler"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-dose" ,r-dose) + ("r-enrichplot" ,r-enrichplot) + ("r-ggplot2" ,r-ggplot2) + ("r-go-db" ,r-go-db) + ("r-gosemsim" ,r-gosemsim) + ("r-magrittr" ,r-magrittr) + ("r-plyr" ,r-plyr) + ("r-qvalue" ,r-qvalue) + ("r-rvcheck" ,r-rvcheck) + ("r-tidyr" ,r-tidyr))) + (home-page "https://guangchuangyu.github.io/software/clusterProfiler/") + (synopsis "Analysis and visualization of functional profiles for gene clusters") + (description + "This package implements methods to analyze and visualize functional +profiles (GO and KEGG) of gene and gene clusters.") + (license license:artistic2.0))) + +(define-public r-mlinterfaces + (package + (name "r-mlinterfaces") + (version "1.62.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "MLInterfaces" version)) + (sha256 + (base32 + "12bgplyzfh0hkwmdp5w4cs5zw3ygdhzmiqzm8vhjyni6m9nrxwy8")))) + (properties `((upstream-name . "MLInterfaces"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotate" ,r-annotate) + ("r-biobase" ,r-biobase) + ("r-biocgenerics" ,r-biocgenerics) + ("r-cluster" ,r-cluster) + ("r-fpc" ,r-fpc) + ("r-gbm" ,r-gbm) + ("r-gdata" ,r-gdata) + ("r-genefilter" ,r-genefilter) + ("r-ggvis" ,r-ggvis) + ("r-hwriter" ,r-hwriter) + ("r-mass" ,r-mass) + ("r-mlbench" ,r-mlbench) + ("r-pls" ,r-pls) + ("r-rcolorbrewer" ,r-rcolorbrewer) + ("r-rda" ,r-rda) + ("r-rpart" ,r-rpart) + ("r-sfsmisc" ,r-sfsmisc) + ("r-shiny" ,r-shiny) + ("r-threejs" ,r-threejs))) + (home-page "https://bioconductor.org/packages/MLInterfaces/") + (synopsis "Interfaces to R machine learning procedures") + (description + "This package provides uniform interfaces to machine learning code for +data in R and Bioconductor containers.") + ;; Any version of the LGPL. + (license license:lgpl2.1+))) + +(define-public r-annaffy + (package + (name "r-annaffy") + (version "1.54.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "annaffy" version)) + (sha256 + (base32 + "16c6allp4vlx0g3nffanrm0mkkf8s2n31dccw4bflnx2pr81bmd5")))) + (build-system r-build-system) + (arguments + `(#:phases + (modify-phases %standard-phases + (add-after 'unpack 'remove-reference-to-non-free-data + (lambda _ + (substitute* "DESCRIPTION" + ((", KEGG.db") "")) + #t))))) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi) + ("r-biobase" ,r-biobase) + ("r-dbi" ,r-dbi) + ("r-go-db" ,r-go-db))) + (home-page "https://bioconductor.org/packages/annaffy/") + (synopsis "Annotation tools for Affymetrix biological metadata") + (description + "This package provides functions for handling data from Bioconductor +Affymetrix annotation data packages. It produces compact HTML and text +reports including experimental data and URL links to many online databases. +It allows searching of biological metadata using various criteria.") + ;; Any version of the LGPL according to the DESCRIPTION file. A copy of + ;; the LGPL 2.1 is included. + (license license:lgpl2.1+))) + +(define-public r-a4core + (package + (name "r-a4core") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4Core" version)) + (sha256 + (base32 + "1d62afxkfp9zbp59ijcn4wd1gdynygw013av41wq8bfm3cx6f9zr")))) + (properties `((upstream-name . "a4Core"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biobase" ,r-biobase) + ("r-glmnet" ,r-glmnet))) + (home-page "https://bioconductor.org/packages/a4Core") + (synopsis "Automated Affymetrix array analysis core package") + (description + "This is the core package for the automated analysis of Affymetrix +arrays.") + (license license:gpl3))) + +(define-public r-a4classif + (package + (name "r-a4classif") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4Classif" version)) + (sha256 + (base32 + "02l77a59865ly3bydv74ff2l2wfb0x5s283g1nx6g1qrw3ly982j")))) + (properties `((upstream-name . "a4Classif"))) + (build-system r-build-system) + (propagated-inputs + `(("r-a4core" ,r-a4core) + ("r-a4preproc" ,r-a4preproc) + ("r-glmnet" ,r-glmnet) + ("r-mlinterfaces" ,r-mlinterfaces) + ("r-pamr" ,r-pamr) + ("r-rocr" ,r-rocr) + ("r-varselrf" ,r-varselrf))) + (home-page "https://bioconductor.org/packages/a4Classif/") + (synopsis "Automated Affymetrix array analysis classification package") + (description + "This is the classification package for the automated analysis of +Affymetrix arrays.") + (license license:gpl3))) + +(define-public r-a4preproc + (package + (name "r-a4preproc") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4Preproc" version)) + (sha256 + (base32 + "1dd3fqcc7nr2zbi46k0mnqkh42mfxk894ixfpqg7i9np2523p5gp")))) + (properties `((upstream-name . "a4Preproc"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annotationdbi" ,r-annotationdbi))) + (home-page "https://bioconductor.org/packages/a4Preproc/") + (synopsis "Automated Affymetrix array analysis preprocessing package") + (description + "This is a package for the automated analysis of Affymetrix arrays. It +is used for preprocessing the arrays.") + (license license:gpl3))) + +(define-public r-a4reporting + (package + (name "r-a4reporting") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4Reporting" version)) + (sha256 + (base32 + "124774z3bfdjgxx2ad40795h92aam21yfx0rw0n01nk2wf6k7xc4")))) + (properties `((upstream-name . "a4Reporting"))) + (build-system r-build-system) + (propagated-inputs + `(("r-annaffy" ,r-annaffy) + ("r-xtable" ,r-xtable))) + (home-page "https://bioconductor.org/packages/a4Reporting/") + (synopsis "Automated Affymetrix array analysis reporting package") + (description + "This is a package for the automated analysis of Affymetrix arrays. It +provides reporting features.") + (license license:gpl3))) + +(define-public r-a4base + (package + (name "r-a4base") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4Base" version)) + (sha256 + (base32 + "0k9k3bv99msbwf2y416cz316ssaha2dxvmaddbl7z9037p8mjr70")))) + (properties `((upstream-name . "a4Base"))) + (build-system r-build-system) + (propagated-inputs + `(("r-a4core" ,r-a4core) + ("r-a4preproc" ,r-a4preproc) + ("r-annaffy" ,r-annaffy) + ("r-annotationdbi" ,r-annotationdbi) + ("r-biobase" ,r-biobase) + ("r-genefilter" ,r-genefilter) + ("r-glmnet" ,r-glmnet) + ("r-gplots" ,r-gplots) + ("r-limma" ,r-limma) + ("r-mpm" ,r-mpm) + ("r-multtest" ,r-multtest))) + (home-page "https://bioconductor.org/packages/a4Base/") + (synopsis "Automated Affymetrix array analysis base package") + (description + "This package provides basic features for the automated analysis of +Affymetrix arrays.") + (license license:gpl3))) + +(define-public r-a4 + (package + (name "r-a4") + (version "1.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "a4" version)) + (sha256 + (base32 + "1iqjy35rqx3m2y0dm2bk4cnzdm1qvbi608bfmrid88w6wmwz3qlk")))) + (build-system r-build-system) + (propagated-inputs + `(("r-a4base" ,r-a4base) + ("r-a4classif" ,r-a4classif) + ("r-a4core" ,r-a4core) + ("r-a4preproc" ,r-a4preproc) + ("r-a4reporting" ,r-a4reporting))) + (home-page "https://bioconductor.org/packages/a4/") + (synopsis "Automated Affymetrix array analysis umbrella package") + (description + "This package provides a software suite for the automated analysis of +Affymetrix arrays.") + (license license:gpl3))) + +(define-public r-abseqr + (package + (name "r-abseqr") + (version "1.0.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "abseqR" version)) + (sha256 + (base32 + "0w0ngxnilcrxlixsz7ls3zm99gyabxwn7w1r3r45n96d4aj075ry")))) + (properties `((upstream-name . "abseqR"))) + (build-system r-build-system) + (inputs + `(("pandoc" ,ghc-pandoc))) + (propagated-inputs + `(("r-biocparallel" ,r-biocparallel) + ("r-biocstyle" ,r-biocstyle) + ("r-circlize" ,r-circlize) + ("r-flexdashboard" ,r-flexdashboard) + ("r-ggcorrplot" ,r-ggcorrplot) + ("r-ggdendro" ,r-ggdendro) + ("r-ggplot2" ,r-ggplot2) + ("r-gridextra" ,r-gridextra) + ("r-knitr" ,r-knitr) + ("r-plotly" ,r-plotly) + ("r-plyr" ,r-plyr) + ("r-png" ,r-png) + ("r-rcolorbrewer" ,r-rcolorbrewer) + ("r-reshape2" ,r-reshape2) + ("r-rmarkdown" ,r-rmarkdown) + ("r-stringr" ,r-stringr) + ("r-vegan" ,r-vegan) + ("r-venndiagram" ,r-venndiagram))) + (home-page "https://github.com/malhamdoosh/abseqR") + (synopsis "Reporting and data analysis for Rep-Seq datasets of antibody libraries") + (description + "AbSeq is a comprehensive bioinformatic pipeline for the analysis of +sequencing datasets generated from antibody libraries and abseqR is one of its +packages. AbseqR empowers the users of abseqPy with plotting and reporting +capabilities and allows them to generate interactive HTML reports for the +convenience of viewing and sharing with other researchers. Additionally, +abseqR extends abseqPy to compare multiple repertoire analyses and perform +further downstream analysis on its output.") + (license license:gpl3))) + +(define-public r-bacon + (package + (name "r-bacon") + (version "1.10.1") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "bacon" version)) + (sha256 + (base32 + "1pd3p1cfggiy08458vplsy3s1zm5jqqcwrv4fks8ra2kf97j38df")))) + (build-system r-build-system) + (propagated-inputs + `(("r-biocparallel" ,r-biocparallel) + ("r-ellipse" ,r-ellipse) + ("r-ggplot2" ,r-ggplot2))) + (home-page "https://bioconductor.org/packages/bacon/") + (synopsis "Controlling bias and inflation in association studies") + (description + "Bacon can be used to remove inflation and bias often observed in +epigenome- and transcriptome-wide association studies. To this end bacon +constructs an empirical null distribution using a Gibbs Sampling algorithm by +fitting a three-component normal mixture on z-scores.") + (license license:gpl2+))) + +(define-public r-rgadem + (package + (name "r-rgadem") + (version "2.30.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "rGADEM" version)) + (sha256 + (base32 + "1a3mvxabp7yb275cv1wr0rzyvjhnsaysk2hnmll4z4cci171z2j2")))) + (properties `((upstream-name . "rGADEM"))) + (build-system r-build-system) + (propagated-inputs + `(("r-biostrings" ,r-biostrings) + ("r-bsgenome" ,r-bsgenome) + ("r-iranges" ,r-iranges) + ("r-seqlogo" ,r-seqlogo))) + (home-page "https://bioconductor.org/packages/rGADEM/") + (synopsis "De novo sequence motif discovery") + (description + "rGADEM is an efficient de novo motif discovery tool for large-scale +genomic sequence data.") + (license license:artistic2.0))) + +(define-public r-motiv + (package + (name "r-motiv") + (version "1.38.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "MotIV" version)) + (sha256 + (base32 + "1qrpydwc5bn8f0843qkyhw6920xk8kvq452ird0ij96g6faiv9a8")))) + (properties `((upstream-name . "MotIV"))) + (build-system r-build-system) + (inputs + `(("gsl" ,gsl))) + (propagated-inputs + `(("r-biocgenerics" ,r-biocgenerics) + ("r-biostrings" ,r-biostrings) + ("r-iranges" ,r-iranges) + ("r-lattice" ,r-lattice) + ("r-rgadem" ,r-rgadem) + ("r-s4vectors" ,r-s4vectors))) + (home-page "https://bioconductor.org/packages/MotIV/") + (synopsis "Motif identification and validation") + (description + "This package is used for the identification and validation of sequence +motifs. It makes use of STAMP for comparing a set of motifs to a given +database (e.g. JASPAR). It can also be used to visualize motifs, motif +distributions, modules and filter motifs.") + (license license:gpl2))) + +(define-public r-motifstack + (package + (name "r-motifstack") + (version "1.26.0") + (source + (origin + (method url-fetch) + (uri (bioconductor-uri "motifStack" version)) + (sha256 + (base32 + "1c4w39ilc4ca4wgi1b6iypadkbxvqjw7k2br0d7q03niw9qjkhxf")))) + (properties `((upstream-name . "motifStack"))) + (build-system r-build-system) + (propagated-inputs + `(("r-ade4" ,r-ade4) + ("r-biostrings" ,r-biostrings) + ("r-grimport" ,r-grimport) + ("r-htmlwidgets" ,r-htmlwidgets) + ("r-motiv" ,r-motiv) + ("r-scales" ,r-scales) + ("r-xml" ,r-xml))) + (home-page "https://bioconductor.org/packages/motifStack/") + (synopsis "Plot stacked logos for DNA, RNA and amino acid sequences") + (description + "The motifStack package is designed for graphic representation of +multiple motifs with different similarity scores. It works with both DNA/RNA +sequence motifs and amino acid sequence motifs. In addition, it provides the +flexibility for users to customize the graphic parameters such as the font +type and symbol colors.") + (license license:gpl2+)))