1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2017, 2018 Roel Janssen <roel@gnu.org>
4 ;;; Copyright © 2018 Tobias Geerinckx-Rice <me@tobias.gr>
6 ;;; This file is part of GNU Guix.
8 ;;; GNU Guix is free software; you can redistribute it and/or modify it
9 ;;; under the terms of the GNU General Public License as published by
10 ;;; the Free Software Foundation; either version 3 of the License, or (at
11 ;;; your option) any later version.
13 ;;; GNU Guix is distributed in the hope that it will be useful, but
14 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
15 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 ;;; GNU General Public License for more details.
18 ;;; You should have received a copy of the GNU General Public License
19 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
21 (define-module (gnu packages bioconductor)
22 #:use-module ((guix licenses) #:prefix license:)
23 #:use-module (guix packages)
24 #:use-module (guix download)
25 #:use-module (guix build-system r)
26 #:use-module (gnu packages)
27 #:use-module (gnu packages bioinformatics)
28 #:use-module (gnu packages cran)
29 #:use-module (gnu packages compression)
30 #:use-module (gnu packages gcc)
31 #:use-module (gnu packages graph)
32 #:use-module (gnu packages maths)
33 #:use-module (gnu packages statistics)
34 #:use-module (gnu packages web))
36 (define-public r-bsgenome-dmelanogaster-ucsc-dm6
38 (name "r-bsgenome-dmelanogaster-ucsc-dm6")
42 ;; We cannot use bioconductor-uri here because this tarball is
43 ;; located under "data/annotation/" instead of "bioc/".
44 (uri (string-append "https://www.bioconductor.org/packages/"
45 "release/data/annotation/src/contrib/"
46 "BSgenome.Dmelanogaster.UCSC.dm6_"
50 "1bhj0rdgf7lspw4xby9y9mf7v7jxxz8001bc8vw8kf04rjsx6060"))))
52 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm6")))
53 (build-system r-build-system)
54 ;; As this package provides little more than a very large data file it
55 ;; doesn't make sense to build substitutes.
56 (arguments `(#:substitutable? #f))
58 `(("r-bsgenome" ,r-bsgenome)))
60 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm6/")
61 (synopsis "Full genome sequences for Fly")
63 "This package provides full genome sequences for Drosophila
64 melanogaster (Fly) as provided by UCSC (dm6) and stored in Biostrings
66 (license license:artistic2.0)))
68 (define-public r-bsgenome-dmelanogaster-ucsc-dm3-masked
70 (name "r-bsgenome-dmelanogaster-ucsc-dm3-masked")
74 ;; We cannot use bioconductor-uri here because this tarball is
75 ;; located under "data/annotation/" instead of "bioc/".
76 (uri (string-append "http://www.bioconductor.org/packages/"
77 "release/data/annotation/src/contrib/"
78 "BSgenome.Dmelanogaster.UCSC.dm3.masked_"
82 "1756csb09f1br9rj1l3f08qyh4hlymdbd0cfn8x3fq39dn45m5ap"))))
84 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3.masked")))
85 (build-system r-build-system)
87 `(("r-bsgenome" ,r-bsgenome)
88 ("r-bsgenome-dmelanogaster-ucsc-dm3"
89 ,r-bsgenome-dmelanogaster-ucsc-dm3)))
90 (home-page "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3.masked/")
91 (synopsis "Full masked genome sequences for Fly")
93 "This package provides full masked genome sequences for Drosophila
94 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
95 Biostrings objects. The sequences are the same as in
96 BSgenome.Dmelanogaster.UCSC.dm3, except that each of them has the 4 following
97 masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of
98 intra-contig ambiguities (AMB mask), (3) the mask of repeats from
99 RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats
100 Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by default.")
101 (license license:artistic2.0)))
103 (define-public r-bsgenome-hsapiens-ucsc-hg19-masked
105 (name "r-bsgenome-hsapiens-ucsc-hg19-masked")
109 ;; We cannot use bioconductor-uri here because this tarball is
110 ;; located under "data/annotation/" instead of "bioc/".
111 (uri (string-append "http://www.bioconductor.org/packages/"
112 "release/data/annotation/src/contrib/"
113 "BSgenome.Hsapiens.UCSC.hg19.masked_"
117 "0452pyah0kv1vsrsjbrqw4k2rm8lc2vc771dzib45gnnfz86qxrr"))))
119 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19.masked")))
120 (build-system r-build-system)
122 `(("r-bsgenome" ,r-bsgenome)
123 ("r-bsgenome-hsapiens-ucsc-hg19"
124 ,r-bsgenome-hsapiens-ucsc-hg19)))
125 (home-page "https://bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19.masked/")
126 (synopsis "Full masked genome sequences for Homo sapiens")
128 "This package provides full genome sequences for Homo sapiens (Human) as
129 provided by UCSC (hg19, Feb. 2009) and stored in Biostrings objects. The
130 sequences are the same as in BSgenome.Hsapiens.UCSC.hg19, except that each of
131 them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS
132 mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of
133 repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem
134 Repeats Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by
136 (license license:artistic2.0)))
138 (define-public r-bsgenome-mmusculus-ucsc-mm9-masked
140 (name "r-bsgenome-mmusculus-ucsc-mm9-masked")
144 ;; We cannot use bioconductor-uri here because this tarball is
145 ;; located under "data/annotation/" instead of "bioc/".
146 (uri (string-append "http://www.bioconductor.org/packages/"
147 "release/data/annotation/src/contrib/"
148 "BSgenome.Mmusculus.UCSC.mm9.masked_"
152 "00bpbm3havqcxr4g63zhllsbpd9q6svgihks7qp7x73nm4gvq7fn"))))
154 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9.masked")))
155 (build-system r-build-system)
157 `(("r-bsgenome" ,r-bsgenome)
158 ("r-bsgenome-mmusculus-ucsc-mm9"
159 ,r-bsgenome-mmusculus-ucsc-mm9)))
160 (home-page "http://bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9.masked/")
161 (synopsis "Full masked genome sequences for Mouse")
163 "This package provides full genome sequences for Mus musculus (Mouse) as
164 provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects. The
165 sequences are the same as in BSgenome.Mmusculus.UCSC.mm9, except that each of
166 them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS
167 mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of
168 repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem
169 Repeats Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by
171 (license license:artistic2.0)))
173 (define-public r-genelendatabase
175 (name "r-genelendatabase")
180 ;; We cannot use bioconductor-uri here because this tarball is
181 ;; located under "data/experiment/" instead of "bioc/".
182 (uri (string-append "https://bioconductor.org/packages/"
183 "release/data/experiment/src/contrib"
184 "/geneLenDataBase_" version ".tar.gz"))
187 "07mmmn53kb7v14msc13dsbm8ghssbvwcrhifrk15hn37bw2p4ja5"))))
189 `((upstream-name . "geneLenDataBase")))
190 (build-system r-build-system)
192 `(("r-rtracklayer" ,r-rtracklayer)
193 ("r-genomicfeatures" ,r-genomicfeatures)))
194 (home-page "https://bioconductor.org/packages/geneLenDataBase/")
195 (synopsis "Lengths of mRNA transcripts for a number of genomes")
197 "This package provides the lengths of mRNA transcripts for a number of
198 genomes and gene ID formats, largely based on the UCSC table browser.")
199 (license license:lgpl2.0+)))
201 (define-public r-txdb-mmusculus-ucsc-mm9-knowngene
203 (name "r-txdb-mmusculus-ucsc-mm9-knowngene")
207 ;; We cannot use bioconductor-uri here because this tarball is
208 ;; located under "data/annotation/" instead of "bioc/".
209 (uri (string-append "https://bioconductor.org/packages/"
210 "release/data/annotation/src/contrib"
211 "/TxDb.Mmusculus.UCSC.mm9.knownGene_"
215 "16bjxy00363hf91ik2mqlqls86i07gia72qh92xc3l1ncch61mx2"))))
217 `((upstream-name . "TxDb.Mmusculus.UCSC.mm9.knownGene")))
218 (build-system r-build-system)
220 `(("r-genomicfeatures" ,r-genomicfeatures)
221 ("r-annotationdbi" ,r-annotationdbi)))
223 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm9.knownGene/")
224 (synopsis "Annotation package for mouse genome in TxDb format")
226 "This package provides an annotation database of Mouse genome data. It
227 is derived from the UCSC mm9 genome and based on the \"knownGene\" track. The
228 database is exposed as a @code{TxDb} object.")
229 (license license:artistic2.0)))
232 (define-public r-biocgenerics
234 (name "r-biocgenerics")
238 (uri (bioconductor-uri "BiocGenerics" version))
241 "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
243 `((upstream-name . "BiocGenerics")))
244 (build-system r-build-system)
245 (home-page "https://bioconductor.org/packages/BiocGenerics")
246 (synopsis "S4 generic functions for Bioconductor")
248 "This package provides S4 generic functions needed by many Bioconductor
250 (license license:artistic2.0)))
252 (define-public r-annotate
259 (uri (bioconductor-uri "annotate" version))
262 "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
263 (build-system r-build-system)
265 `(("r-annotationdbi" ,r-annotationdbi)
266 ("r-biobase" ,r-biobase)
267 ("r-biocgenerics" ,r-biocgenerics)
271 ("r-xtable" ,r-xtable)))
273 "https://bioconductor.org/packages/annotate")
274 (synopsis "Annotation for microarrays")
275 (description "This package provides R environments for the annotation of
277 (license license:artistic2.0)))
279 (define-public r-hpar
286 (uri (bioconductor-uri "hpar" version))
289 "1pm3k8apgynmdzv2d0chca3b636kcai3b1x861fyv1m3xs6msgxn"))))
290 (build-system r-build-system)
291 (home-page "https://bioconductor.org/packages/hpar/")
292 (synopsis "Human Protein Atlas in R")
293 (description "This package provides a simple interface to and data from
294 the Human Protein Atlas project.")
295 (license license:artistic2.0)))
297 (define-public r-regioner
304 (uri (bioconductor-uri "regioneR" version))
307 "19la74swgzxp90z2nr3pzsgkxd7wp70zl6i2ipv3plg841f6k5zd"))))
308 (properties `((upstream-name . "regioneR")))
309 (build-system r-build-system)
311 `(("r-biostrings" ,r-biostrings)
312 ("r-bsgenome" ,r-bsgenome)
313 ("r-genomeinfodb" ,r-genomeinfodb)
314 ("r-genomicranges" ,r-genomicranges)
315 ("r-iranges" ,r-iranges)
316 ("r-memoise" ,r-memoise)
317 ("r-rtracklayer" ,r-rtracklayer)
318 ("r-s4vectors" ,r-s4vectors)))
319 (home-page "https://bioconductor.org/packages/regioneR/")
320 (synopsis "Association analysis of genomic regions")
321 (description "This package offers a statistical framework based on
322 customizable permutation tests to assess the association between genomic
323 region sets and other genomic features.")
324 (license license:artistic2.0)))
326 (define-public r-diffbind
333 (uri (bioconductor-uri "DiffBind" version))
336 "0j8pal40lr1gv8sss96hhkj7l1qn9sy4q4l2kqd4rfwl7qrcnfw5"))))
337 (properties `((upstream-name . "DiffBind")))
338 (build-system r-build-system)
343 ("r-biocparallel" ,r-biocparallel)
344 ("r-deseq2" ,r-deseq2)
347 ("r-genomicalignments" ,r-genomicalignments)
348 ("r-genomicranges" ,r-genomicranges)
349 ("r-ggplot2" ,r-ggplot2)
350 ("r-ggrepel" ,r-ggrepel)
351 ("r-gplots" ,r-gplots)
352 ("r-iranges" ,r-iranges)
353 ("r-lattice" ,r-lattice)
355 ("r-locfit" ,r-locfit)
356 ("r-rcolorbrewer" , r-rcolorbrewer)
358 ("r-rsamtools" ,r-rsamtools)
359 ("r-s4vectors" ,r-s4vectors)
360 ("r-summarizedexperiment" ,r-summarizedexperiment)
361 ("r-systempiper" ,r-systempiper)
362 ("r-zlibbioc" ,r-zlibbioc)))
363 (home-page "http://bioconductor.org/packages/DiffBind")
364 (synopsis "Differential binding analysis of ChIP-Seq peak data")
366 "This package computes differentially bound sites from multiple
367 ChIP-seq experiments using affinity (quantitative) data. Also enables
368 occupancy (overlap) analysis and plotting functions.")
369 (license license:artistic2.0)))
371 (define-public r-ripseeker
378 (uri (bioconductor-uri "RIPSeeker" version))
381 "1x2n1iyik4s67bxq0fl6fpf602k51g4pxjpjpxkgx1a5fsk61f2i"))))
382 (properties `((upstream-name . "RIPSeeker")))
383 (build-system r-build-system)
385 `(("r-s4vectors" ,r-s4vectors)
386 ("r-iranges" ,r-iranges)
387 ("r-genomicranges" ,r-genomicranges)
388 ("r-summarizedexperiment" ,r-summarizedexperiment)
389 ("r-rsamtools" ,r-rsamtools)
390 ("r-genomicalignments" ,r-genomicalignments)
391 ("r-rtracklayer" ,r-rtracklayer)))
392 (home-page "http://bioconductor.org/packages/RIPSeeker")
394 "Identifying protein-associated transcripts from RIP-seq experiments")
396 "This package infers and discriminates RIP peaks from RIP-seq alignments
397 using two-state HMM with negative binomial emission probability. While
398 RIPSeeker is specifically tailored for RIP-seq data analysis, it also provides
399 a suite of bioinformatics tools integrated within this self-contained software
400 package comprehensively addressing issues ranging from post-alignments
401 processing to visualization and annotation.")
402 (license license:gpl2)))
404 (define-public r-multtest
411 (uri (bioconductor-uri "multtest" version))
414 "0lq62jw81hz9k840969n5byj57pwd0jqga3hqvhb6abb3g10yz7k"))))
415 (build-system r-build-system)
417 `(("r-survival" ,r-survival)
418 ("r-biocgenerics" ,r-biocgenerics)
419 ("r-biobase" ,r-biobase)
421 (home-page "http://bioconductor.org/packages/multtest")
422 (synopsis "Resampling-based multiple hypothesis testing")
424 "This package can do non-parametric bootstrap and permutation
425 resampling-based multiple testing procedures (including empirical Bayes
426 methods) for controlling the family-wise error rate (FWER), generalized
427 family-wise error rate (gFWER), tail probability of the proportion of
428 false positives (TPPFP), and false discovery rate (FDR). Several choices
429 of bootstrap-based null distribution are implemented (centered, centered
430 and scaled, quantile-transformed). Single-step and step-wise methods are
431 available. Tests based on a variety of T- and F-statistics (including
432 T-statistics based on regression parameters from linear and survival models
433 as well as those based on correlation parameters) are included. When probing
434 hypotheses with T-statistics, users may also select a potentially faster null
435 distribution which is multivariate normal with mean zero and variance
436 covariance matrix derived from the vector influence function. Results are
437 reported in terms of adjusted P-values, confidence regions and test statistic
438 cutoffs. The procedures are directly applicable to identifying differentially
439 expressed genes in DNA microarray experiments.")
440 (license license:lgpl3)))
442 (define-public r-graph
448 (uri (bioconductor-uri "graph" version))
451 "1kgnsm6f0vmb9qbkmmrnvxbwqc0gar17dq5gv1v10hrksw6mh64i"))))
452 (build-system r-build-system)
454 `(("r-biocgenerics" ,r-biocgenerics)))
455 (home-page "https://bioconductor.org/packages/graph")
456 (synopsis "Handle graph data structures in R")
458 "This package implements some simple graph handling capabilities for R.")
459 (license license:artistic2.0)))
461 (define-public r-codedepends
463 (name "r-codedepends")
468 (uri (cran-uri "CodeDepends" version))
471 "0l7kiv3awx50glf5cs841b4zzsff1ml90f0zr868ygvwsr4ps1hq"))))
472 (properties `((upstream-name . "CodeDepends")))
473 (build-system r-build-system)
475 `(("r-codetools" ,r-codetools)
478 (home-page "http://cran.r-project.org/web/packages/CodeDepends")
479 (synopsis "Analysis of R code for reproducible research and code comprehension")
481 "This package provides tools for analyzing R expressions or blocks of
482 code and determining the dependencies between them. It focuses on R scripts,
483 but can be used on the bodies of functions. There are many facilities
484 including the ability to summarize or get a high-level view of code,
485 determining dependencies between variables, code improvement suggestions.")
486 ;; Any version of the GPL
487 (license (list license:gpl2+ license:gpl3+))))
489 (define-public r-chippeakanno
491 (name "r-chippeakanno")
496 (uri (bioconductor-uri "ChIPpeakAnno" version))
499 "1x98d8iwrxjwdz1s5cnvi6flynw9gdkmara9gwf205qxgmy7j3a3"))))
500 (properties `((upstream-name . "ChIPpeakAnno")))
501 (build-system r-build-system)
503 `(("r-biocgenerics" ,r-biocgenerics)
504 ("r-biocmanager" ,r-biocmanager)
505 ("r-biostrings" ,r-biostrings)
506 ("r-delayedarray" ,r-delayedarray)
508 ("r-biomart" ,r-biomart)
509 ("r-bsgenome" ,r-bsgenome)
510 ("r-genomicfeatures" ,r-genomicfeatures)
511 ("r-genomicranges" ,r-genomicranges)
512 ("r-genomeinfodb" ,r-genomeinfodb)
513 ("r-iranges" ,r-iranges)
514 ("r-matrixstats" ,r-matrixstats)
515 ("r-annotationdbi" ,r-annotationdbi)
517 ("r-multtest" ,r-multtest)
520 ("r-regioner" ,r-regioner)
522 ("r-ensembldb" ,r-ensembldb)
523 ("r-biobase" ,r-biobase)
524 ("r-s4vectors" ,r-s4vectors)
525 ("r-seqinr" ,r-seqinr)
527 ("r-genomicalignments" ,r-genomicalignments)
528 ("r-summarizedexperiment" ,r-summarizedexperiment)
529 ("r-rsamtools" ,r-rsamtools)
530 ("r-venndiagram" ,r-venndiagram)))
531 (home-page "http://bioconductor.org/packages/ChIPpeakAnno")
532 (synopsis "Peaks annotation from ChIP-seq and ChIP-chip experiments")
534 "The package includes functions to retrieve the sequences around the peak,
535 obtain enriched Gene Ontology (GO) terms, find the nearest gene, exon, miRNA or
536 custom features such as most conserved elements and other transcription factor
537 binding sites supplied by users. Starting 2.0.5, new functions have been added
538 for finding the peaks with bi-directional promoters with summary statistics
539 (peaksNearBDP), for summarizing the occurrence of motifs in peaks
540 (summarizePatternInPeaks) and for adding other IDs to annotated peaks or
541 enrichedGO (addGeneIDs).")
542 (license license:gpl2+)))
544 (define-public r-marray
550 (uri (bioconductor-uri "marray" version))
552 (base32 "1sh7l3c28x6zhdv99c9x05ii2yxmh9alkazp98kdi4fdb23rlzky"))))
553 (build-system r-build-system)
555 `(("r-limma" ,r-limma)))
556 (home-page "http://bioconductor.org/packages/marray")
557 (synopsis "Exploratory analysis for two-color spotted microarray data")
558 (description "This package contains class definitions for two-color spotted
559 microarray data. It also includes fuctions for data input, diagnostic plots,
560 normalization and quality checking.")
561 (license license:lgpl2.0+)))
563 (define-public r-cghbase
569 (uri (bioconductor-uri "CGHbase" version))
571 (base32 "0ghxp49xdi09p3f2qwrdrq2p4qjafj4z1rr08ycgbf11gb22h1sc"))))
572 (properties `((upstream-name . "CGHbase")))
573 (build-system r-build-system)
575 `(("r-biobase" ,r-biobase)
576 ("r-marray" ,r-marray)))
577 (home-page "http://bioconductor.org/packages/CGHbase")
578 (synopsis "Base functions and classes for arrayCGH data analysis")
579 (description "This package contains functions and classes that are needed by
580 the @code{arrayCGH} packages.")
581 (license license:gpl2+)))
583 (define-public r-cghcall
589 (uri (bioconductor-uri "CGHcall" version))
591 (base32 "1k65kaiqvjyllzbpa2367n6f6kkmsy463kpflzs66hqhx2fshsmi"))))
592 (properties `((upstream-name . "CGHcall")))
593 (build-system r-build-system)
595 `(("r-biobase" ,r-biobase)
596 ("r-cghbase" ,r-cghbase)
597 ("r-impute" ,r-impute)
598 ("r-dnacopy" ,r-dnacopy)
599 ("r-snowfall" ,r-snowfall)))
600 (home-page "http://bioconductor.org/packages/CGHcall")
601 (synopsis "Base functions and classes for arrayCGH data analysis")
602 (description "This package contains functions and classes that are needed by
603 @code{arrayCGH} packages.")
604 (license license:gpl2+)))
606 (define-public r-qdnaseq
612 (uri (bioconductor-uri "QDNAseq" version))
614 (base32 "04ff9nbckzrlb45mr2j0c3mlh1wcggq5bbl81zklhq203c5x1wc2"))))
615 (properties `((upstream-name . "QDNAseq")))
616 (build-system r-build-system)
618 `(("r-biobase" ,r-biobase)
619 ("r-biocparallel" ,r-biocparallel)
620 ("r-cghbase" ,r-cghbase)
621 ("r-cghcall" ,r-cghcall)
622 ("r-dnacopy" ,r-dnacopy)
623 ("r-genomicranges" ,r-genomicranges)
624 ("r-iranges" ,r-iranges)
625 ("r-matrixstats" ,r-matrixstats)
626 ("r-r-utils" ,r-r-utils)
627 ("r-rsamtools" ,r-rsamtools)))
628 (home-page "http://bioconductor.org/packages/QDNAseq")
629 (synopsis "Quantitative DNA sequencing for chromosomal aberrations")
630 (description "The genome is divided into non-overlapping fixed-sized bins,
631 number of sequence reads in each counted, adjusted with a simultaneous
632 two-dimensional loess correction for sequence mappability and GC content, and
633 filtered to remove spurious regions in the genome. Downstream steps of
634 segmentation and calling are also implemented via packages DNAcopy and CGHcall,
636 (license license:gpl2+)))
638 (define-public r-bayseq
645 (uri (bioconductor-uri "baySeq" version))
648 "0f6yckihm5cwh3dycv2g54hf7nddhcqya4yrqwbir96y5k1d1km5"))))
649 (properties `((upstream-name . "baySeq")))
650 (build-system r-build-system)
652 `(("r-abind" ,r-abind)
654 ("r-genomicranges" ,r-genomicranges)))
655 (home-page "https://bioconductor.org/packages/baySeq/")
656 (synopsis "Bayesian analysis of differential expression patterns in count data")
658 "This package identifies differential expression in high-throughput count
659 data, such as that derived from next-generation sequencing machines,
660 calculating estimated posterior likelihoods of differential expression (or
661 more complex hypotheses) via empirical Bayesian methods.")
662 (license license:gpl3)))
664 (define-public r-chipcomp
671 (uri (bioconductor-uri "ChIPComp" version))
674 "1sypdsvwzssraanlhddhzpf9p0xs3qlflc0hp7yfbp0aplsifx85"))))
675 (properties `((upstream-name . "ChIPComp")))
676 (build-system r-build-system)
678 `(("r-biocgenerics" ,r-biocgenerics)
679 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
680 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
681 ("r-genomeinfodb" ,r-genomeinfodb)
682 ("r-genomicranges" ,r-genomicranges)
683 ("r-iranges" ,r-iranges)
685 ("r-rsamtools" ,r-rsamtools)
686 ("r-rtracklayer" ,r-rtracklayer)
687 ("r-s4vectors" ,r-s4vectors)))
688 (home-page "https://bioconductor.org/packages/ChIPComp")
689 (synopsis "Quantitative comparison of multiple ChIP-seq datasets")
691 "ChIPComp implements a statistical method for quantitative comparison of
692 multiple ChIP-seq datasets. It detects differentially bound sharp binding
693 sites across multiple conditions considering matching control in ChIP-seq
695 ;; Any version of the GPL.
696 (license license:gpl3+)))
698 (define-public r-riboprofiling
700 (name "r-riboprofiling")
705 (uri (bioconductor-uri "RiboProfiling" version))
708 "1njvkd1khmf3rbp3dkz5z63wp79z4wmk4kzd3p3amky3w5by070z"))))
709 (properties `((upstream-name . "RiboProfiling")))
710 (build-system r-build-system)
712 `(("r-biocgenerics" ,r-biocgenerics)
713 ("r-biostrings" ,r-biostrings)
714 ("r-data-table" ,r-data-table)
715 ("r-genomeinfodb" ,r-genomeinfodb)
716 ("r-genomicalignments" ,r-genomicalignments)
717 ("r-genomicfeatures" ,r-genomicfeatures)
718 ("r-genomicranges" ,r-genomicranges)
720 ("r-ggplot2" ,r-ggplot2)
721 ("r-iranges" ,r-iranges)
723 ("r-reshape2" ,r-reshape2)
724 ("r-rsamtools" ,r-rsamtools)
725 ("r-rtracklayer" ,r-rtracklayer)
726 ("r-s4vectors" ,r-s4vectors)
727 ("r-sqldf" ,r-sqldf)))
728 (home-page "https://bioconductor.org/packages/RiboProfiling/")
729 (synopsis "Ribosome profiling data analysis")
730 (description "Starting with a BAM file, this package provides the
731 necessary functions for quality assessment, read start position recalibration,
732 the counting of genomic sequence reads on CDS, 3'UTR, and 5'UTR, and plotting
733 of count data: pairs, log fold-change, codon frequency and coverage
734 assessment, principal component analysis on codon coverage.")
735 (license license:gpl3)))
737 (define-public r-riboseqr
744 (uri (bioconductor-uri "riboSeqR" version))
747 "1nacsbsz77fw4a10nqj2ncsf25q3aaa0gd5w1q0ray2prx7qmlqb"))))
748 (properties `((upstream-name . "riboSeqR")))
749 (build-system r-build-system)
751 `(("r-abind" ,r-abind)
752 ("r-bayseq" ,r-bayseq)
753 ("r-genomeinfodb" ,r-genomeinfodb)
754 ("r-genomicranges" ,r-genomicranges)
755 ("r-iranges" ,r-iranges)
756 ("r-rsamtools" ,r-rsamtools)
757 ("r-seqlogo" ,r-seqlogo)))
758 (home-page "https://bioconductor.org/packages/riboSeqR/")
759 (synopsis "Analysis of sequencing data from ribosome profiling experiments")
761 "This package provides plotting functions, frameshift detection and
762 parsing of genetic sequencing data from ribosome profiling experiments.")
763 (license license:gpl3)))
765 (define-public r-interactionset
767 (name "r-interactionset")
772 (uri (bioconductor-uri "InteractionSet" version))
775 "0wirfhmpmkmnmhbqslw4bzvi2msqyqpjy1rrwr5qbd9k5rhx3bzb"))))
777 `((upstream-name . "InteractionSet")))
778 (build-system r-build-system)
780 `(("r-biocgenerics" ,r-biocgenerics)
781 ("r-genomeinfodb" ,r-genomeinfodb)
782 ("r-genomicranges" ,r-genomicranges)
783 ("r-iranges" ,r-iranges)
784 ("r-matrix" ,r-matrix)
786 ("r-s4vectors" ,r-s4vectors)
787 ("r-summarizedexperiment" ,r-summarizedexperiment)))
788 (home-page "https://bioconductor.org/packages/InteractionSet")
789 (synopsis "Base classes for storing genomic interaction data")
791 "This packages provides the @code{GInteractions},
792 @code{InteractionSet} and @code{ContactMatrix} objects and associated methods
793 for storing and manipulating genomic interaction data from Hi-C and ChIA-PET
795 (license license:gpl3)))
797 (define-public r-genomicinteractions
799 (name "r-genomicinteractions")
804 (uri (bioconductor-uri "GenomicInteractions" version))
807 "0zy5isp2lqpjm0n0n1gly5bs4izn22yciibyqrnlrr60rmn5s67q"))))
809 `((upstream-name . "GenomicInteractions")))
810 (build-system r-build-system)
812 `(("r-biobase" ,r-biobase)
813 ("r-biocgenerics" ,r-biocgenerics)
814 ("r-data-table" ,r-data-table)
816 ("r-genomeinfodb" ,r-genomeinfodb)
817 ("r-genomicranges" ,r-genomicranges)
818 ("r-ggplot2" ,r-ggplot2)
819 ("r-gridextra" ,r-gridextra)
821 ("r-igraph" ,r-igraph)
822 ("r-interactionset" ,r-interactionset)
823 ("r-iranges" ,r-iranges)
824 ("r-rsamtools" ,r-rsamtools)
825 ("r-rtracklayer" ,r-rtracklayer)
826 ("r-s4vectors" ,r-s4vectors)
827 ("r-stringr" ,r-stringr)))
828 (home-page "https://github.com/ComputationalRegulatoryGenomicsICL/GenomicInteractions/")
829 (synopsis "R package for handling genomic interaction data")
831 "This R package provides tools for handling genomic interaction data,
832 such as ChIA-PET/Hi-C, annotating genomic features with interaction
833 information and producing various plots and statistics.")
834 (license license:gpl3)))
843 (uri (bioconductor-uri "ctc" version))
846 "0yp7c0abk48jx1wf8n1gawh7dm15idahqc8va24v8cm0bzxgnmh2"))))
847 (build-system r-build-system)
848 (propagated-inputs `(("r-amap" ,r-amap)))
849 (home-page "https://bioconductor.org/packages/ctc/")
850 (synopsis "Cluster and tree conversion")
852 "This package provides tools for exporting and importing classification
853 trees and clusters to other programs.")
854 (license license:gpl2)))
856 (define-public r-goseq
863 (uri (bioconductor-uri "goseq" version))
866 "1j87j98cajcjqabv6rb6zmcqxsqxxhbb3w60w1iink4rhsh8m3mn"))))
867 (build-system r-build-system)
869 `(("r-annotationdbi" ,r-annotationdbi)
870 ("r-biasedurn" ,r-biasedurn)
871 ("r-biocgenerics" ,r-biocgenerics)
872 ("r-genelendatabase" ,r-genelendatabase)
875 (home-page "https://bioconductor.org/packages/goseq/")
876 (synopsis "Gene Ontology analyser for RNA-seq and other length biased data")
878 "This package provides tools to detect Gene Ontology and/or other user
879 defined categories which are over/under represented in RNA-seq data.")
880 (license license:lgpl2.0+)))
882 (define-public r-glimma
889 (uri (bioconductor-uri "Glimma" version))
892 "1ihrww55sa7ipi1rpp0rmn081sbqdwdmm5mz30zfrjr1xxqcdbcv"))))
893 (properties `((upstream-name . "Glimma")))
894 (build-system r-build-system)
896 `(("r-edger" ,r-edger)
897 ("r-jsonlite" ,r-jsonlite)
898 ("r-s4vectors" ,r-s4vectors)))
899 (home-page "https://github.com/Shians/Glimma")
900 (synopsis "Interactive HTML graphics")
902 "This package generates interactive visualisations for analysis of
903 RNA-sequencing data using output from limma, edgeR or DESeq2 packages in an
904 HTML page. The interactions are built on top of the popular static
905 representations of analysis results in order to provide additional
907 (license license:lgpl3)))
909 (define-public r-rots
916 (uri (bioconductor-uri "ROTS" version))
919 "1d5ggkk47xybcaizfy756qimbf2falg9cld46mhqjp3xfbfvzsg6"))))
920 (properties `((upstream-name . "ROTS")))
921 (build-system r-build-system)
923 `(("r-biobase" ,r-biobase)
925 (home-page "https://bioconductor.org/packages/ROTS/")
926 (synopsis "Reproducibility-Optimized Test Statistic")
928 "This package provides tools for calculating the
929 @dfn{Reproducibility-Optimized Test Statistic} (ROTS) for differential testing
931 (license license:gpl2+)))
933 (define-public r-plgem
940 (uri (bioconductor-uri "plgem" version))
943 "1330635db3p8xm5y8fwrk1l37r6bgypsq70s3rx954i775zp6szg"))))
944 (build-system r-build-system)
946 `(("r-biobase" ,r-biobase)
948 (home-page "http://www.genopolis.it")
949 (synopsis "Detect differential expression in microarray and proteomics datasets")
951 "The Power Law Global Error Model (PLGEM) has been shown to faithfully
952 model the variance-versus-mean dependence that exists in a variety of
953 genome-wide datasets, including microarray and proteomics data. The use of
954 PLGEM has been shown to improve the detection of differentially expressed
955 genes or proteins in these datasets.")
956 (license license:gpl2)))
958 (define-public r-inspect
965 (uri (bioconductor-uri "INSPEcT" version))
968 "07q5msw9rnamx957mbiawnv3p9kr5ahwawzvv9xzla7d3lkk62xp"))))
969 (properties `((upstream-name . "INSPEcT")))
970 (build-system r-build-system)
972 `(("r-biobase" ,r-biobase)
973 ("r-biocgenerics" ,r-biocgenerics)
974 ("r-biocparallel" ,r-biocparallel)
975 ("r-deseq2" ,r-deseq2)
976 ("r-desolve" ,r-desolve)
977 ("r-genomicalignments" ,r-genomicalignments)
978 ("r-genomicfeatures" ,r-genomicfeatures)
979 ("r-genomicranges" ,r-genomicranges)
980 ("r-iranges" ,r-iranges)
982 ("r-preprocesscore" ,r-preprocesscore)
984 ("r-rootsolve" ,r-rootsolve)
985 ("r-rsamtools" ,r-rsamtools)
986 ("r-s4vectors" ,r-s4vectors)
988 ("r-summarizedexperiment" ,r-summarizedexperiment)
989 ("r-txdb-mmusculus-ucsc-mm9-knowngene"
990 ,r-txdb-mmusculus-ucsc-mm9-knowngene)))
991 (home-page "https://bioconductor.org/packages/INSPEcT")
992 (synopsis "Analysis of 4sU-seq and RNA-seq time-course data")
994 "INSPEcT (INference of Synthesis, Processing and dEgradation rates in
995 Time-Course experiments) analyses 4sU-seq and RNA-seq time-course data in
996 order to evaluate synthesis, processing and degradation rates and assess via
997 modeling the rates that determines changes in mature mRNA levels.")
998 (license license:gpl2)))
1000 (define-public r-dnabarcodes
1002 (name "r-dnabarcodes")
1007 (uri (bioconductor-uri "DNABarcodes" version))
1010 "0g6j7ish0fk9jcib94wssjgp1m8ldcp42hyyg1ypr945fa3xghx0"))))
1011 (properties `((upstream-name . "DNABarcodes")))
1012 (build-system r-build-system)
1015 ("r-matrix" ,r-matrix)
1016 ("r-rcpp" ,r-rcpp)))
1017 (home-page "https://bioconductor.org/packages/DNABarcodes")
1018 (synopsis "Create and analyze DNA barcodes")
1020 "This package offers tools to create DNA barcode sets capable of
1021 correcting insertion, deletion, and substitution errors. Existing barcodes
1022 can be analyzed regarding their minimal, maximal and average distances between
1023 barcodes. Finally, reads that start with a (possibly mutated) barcode can be
1024 demultiplexed, i.e. assigned to their original reference barcode.")
1025 (license license:gpl2)))
1027 (define-public r-ruvseq
1034 (uri (bioconductor-uri "RUVSeq" version))
1037 "0qk7q3ab7k133divfkp54zsmvsmb9p8r09pkh2caswrzrn8achzv"))))
1038 (properties `((upstream-name . "RUVSeq")))
1039 (build-system r-build-system)
1041 `(("r-biobase" ,r-biobase)
1042 ("r-edaseq" ,r-edaseq)
1043 ("r-edger" ,r-edger)
1044 ("r-mass" ,r-mass)))
1045 (home-page "https://github.com/drisso/RUVSeq")
1046 (synopsis "Remove unwanted variation from RNA-Seq data")
1048 "This package implements methods to @dfn{remove unwanted variation} (RUV)
1049 of Risso et al. (2014) for the normalization of RNA-Seq read counts between
1051 (license license:artistic2.0)))
1053 (define-public r-biocneighbors
1055 (name "r-biocneighbors")
1060 (uri (bioconductor-uri "BiocNeighbors" version))
1063 "1fsb96acidlxwf0h65xv7fnwdi58ckmq00gmwykrlawh88wgn1ll"))))
1064 (properties `((upstream-name . "BiocNeighbors")))
1065 (build-system r-build-system)
1067 `(("r-biocparallel" ,r-biocparallel)
1069 ("r-rcppannoy" ,r-rcppannoy)
1070 ("r-s4vectors" ,r-s4vectors)))
1071 (home-page "https://bioconductor.org/packages/BiocNeighbors")
1072 (synopsis "Nearest Neighbor Detection for Bioconductor packages")
1074 "This package implements exact and approximate methods for nearest
1075 neighbor detection, in a framework that allows them to be easily switched
1076 within Bioconductor packages or workflows. The exact algorithm is implemented
1077 using pre-clustering with the k-means algorithm. Functions are also provided
1078 to search for all neighbors within a given distance. Parallelization is
1079 achieved for all methods using the BiocParallel framework.")
1080 (license license:gpl3)))
1082 (define-public r-destiny
1089 (uri (bioconductor-uri "destiny" version))
1092 "1iay17mrhsfmpwl920rh1nip5b6ybva4h6bna0yld04paq5yva67"))))
1093 (build-system r-build-system)
1095 `(("r-biobase" ,r-biobase)
1096 ("r-biocgenerics" ,r-biocgenerics)
1098 ("r-ggthemes" ,r-ggthemes)
1099 ("r-hmisc" ,r-hmisc)
1100 ("r-igraph" ,r-igraph)
1101 ("r-matrix" ,r-matrix)
1102 ("r-proxy" ,r-proxy)
1104 ("r-rcppeigen" ,r-rcppeigen)
1105 ("r-scales" ,r-scales)
1106 ("r-scatterplot3d" ,r-scatterplot3d)
1107 ("r-smoother" ,r-smoother)
1108 ("r-summarizedexperiment" ,r-summarizedexperiment)
1110 (home-page "https://bioconductor.org/packages/destiny/")
1111 (synopsis "Create and plot diffusion maps")
1112 (description "This package provides tools to create and plot diffusion
1114 ;; Any version of the GPL
1115 (license license:gpl3+)))
1117 (define-public r-savr
1124 (uri (bioconductor-uri "savR" version))
1127 "13bwq2a2pygdkmhrcmvz525wsi5i01j911711zgs6x93wj20b2w7"))))
1128 (properties `((upstream-name . "savR")))
1129 (build-system r-build-system)
1131 `(("r-ggplot2" ,r-ggplot2)
1132 ("r-gridextra" ,r-gridextra)
1133 ("r-reshape2" ,r-reshape2)
1134 ("r-scales" ,r-scales)
1136 (home-page "https://github.com/bcalder/savR")
1137 (synopsis "Parse and analyze Illumina SAV files")
1139 "This package provides tools to parse Illumina Sequence Analysis
1140 Viewer (SAV) files, access data, and generate QC plots.")
1141 (license license:agpl3+)))
1143 (define-public r-chipexoqual
1145 (name "r-chipexoqual")
1150 (uri (bioconductor-uri "ChIPexoQual" version))
1153 "1773bpiybn4g9jlv46z29x19q4dpcvn7lairr3lq5pdqbqmz5hnp"))))
1154 (properties `((upstream-name . "ChIPexoQual")))
1155 (build-system r-build-system)
1157 `(("r-biocparallel" ,r-biocparallel)
1158 ("r-biovizbase" ,r-biovizbase)
1159 ("r-broom" ,r-broom)
1160 ("r-data-table" ,r-data-table)
1161 ("r-dplyr" ,r-dplyr)
1162 ("r-genomeinfodb" ,r-genomeinfodb)
1163 ("r-genomicalignments" ,r-genomicalignments)
1164 ("r-genomicranges" ,r-genomicranges)
1165 ("r-ggplot2" ,r-ggplot2)
1166 ("r-hexbin" ,r-hexbin)
1167 ("r-iranges" ,r-iranges)
1168 ("r-rcolorbrewer" ,r-rcolorbrewer)
1169 ("r-rmarkdown" ,r-rmarkdown)
1170 ("r-rsamtools" ,r-rsamtools)
1171 ("r-s4vectors" ,r-s4vectors)
1172 ("r-scales" ,r-scales)
1173 ("r-viridis" ,r-viridis)))
1174 (home-page "https://github.com/keleslab/ChIPexoQual")
1175 (synopsis "Quality control pipeline for ChIP-exo/nexus data")
1177 "This package provides a quality control pipeline for ChIP-exo/nexus
1179 (license license:gpl2+)))
1181 (define-public r-dnacopy
1188 (uri (bioconductor-uri "DNAcopy" version))
1191 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
1192 (properties `((upstream-name . "DNAcopy")))
1193 (build-system r-build-system)
1194 (native-inputs `(("gfortran" ,gfortran)))
1195 (home-page "https://bioconductor.org/packages/DNAcopy")
1196 (synopsis "DNA copy number data analysis")
1198 "This package implements the @dfn{circular binary segmentation} (CBS)
1199 algorithm to segment DNA copy number data and identify genomic regions with
1200 abnormal copy number.")
1201 (license license:gpl2+)))
1203 ;; This is a CRAN package, but it uncharacteristically depends on a
1204 ;; Bioconductor package.
1205 (define-public r-htscluster
1207 (name "r-htscluster")
1212 (uri (cran-uri "HTSCluster" version))
1215 "0wnbfh6hdx8692jilgmv8sys1zm6fqc6mim7vvjhyqlmpm8gm0kg"))))
1216 (properties `((upstream-name . "HTSCluster")))
1217 (build-system r-build-system)
1219 `(("r-capushe" ,r-capushe)
1220 ("r-edger" ,r-edger)
1221 ("r-plotrix" ,r-plotrix)))
1222 (home-page "https://cran.r-project.org/web/packages/HTSCluster")
1223 (synopsis "Clustering high-throughput transcriptome sequencing (HTS) data")
1225 "This package provides a Poisson mixture model is implemented to cluster
1226 genes from high-throughput transcriptome sequencing (RNA-seq) data. Parameter
1227 estimation is performed using either the EM or CEM algorithm, and the slope
1228 heuristics are used for model selection (i.e., to choose the number of
1230 (license license:gpl3+)))