1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2016, 2017, 2018, 2020, 2021 Roel Janssen <roel@gnu.org>
4 ;;; Copyright © 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2016 Ben Woodcroft <donttrustben@gmail.com>
6 ;;; Copyright © 2017 Efraim Flashner <efraim@flashner.co.il>
7 ;;; Copyright © 2017, 2018, 2019, 2020, 2021 Tobias Geerinckx-Rice <me@tobias.gr>
8 ;;; Copyright © 2019, 2020, 2021, 2022 Simon Tournier <zimon.toutoune@gmail.com>
9 ;;; Copyright © 2020 Peter Lo <peterloleungyau@gmail.com>
10 ;;; Copyright © 2020, 2021, 2022 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
11 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
12 ;;; Copyright © 2021 Hong Li <hli@mdc-berlin.de>
13 ;;; Copyright © 2021 Tim Howes <timhowes@lavabit.com>
14 ;;; Copyright © 2021 Nicolas Vallet <nls.vallet@gmail.com>
16 ;;; This file is part of GNU Guix.
18 ;;; GNU Guix is free software; you can redistribute it and/or modify it
19 ;;; under the terms of the GNU General Public License as published by
20 ;;; the Free Software Foundation; either version 3 of the License, or (at
21 ;;; your option) any later version.
23 ;;; GNU Guix is distributed in the hope that it will be useful, but
24 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
25 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
26 ;;; GNU General Public License for more details.
28 ;;; You should have received a copy of the GNU General Public License
29 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
31 (define-module (gnu packages bioconductor)
32 #:use-module ((guix licenses) #:prefix license:)
33 #:use-module (guix packages)
34 #:use-module (guix download)
35 #:use-module (guix git-download)
36 #:use-module (guix build-system r)
37 #:use-module (gnu packages)
38 #:use-module (gnu packages base)
39 #:use-module (gnu packages bioinformatics)
40 #:use-module (gnu packages boost)
41 #:use-module (gnu packages cran)
42 #:use-module (gnu packages compression)
43 #:use-module (gnu packages curl)
44 #:use-module (gnu packages docker)
45 #:use-module (gnu packages gcc)
46 #:use-module (gnu packages graph)
47 #:use-module (gnu packages graphviz)
48 #:use-module (gnu packages haskell-xyz)
49 #:use-module (gnu packages image)
50 #:use-module (gnu packages maths)
51 #:use-module (gnu packages netpbm)
52 #:use-module (gnu packages perl)
53 #:use-module (gnu packages pkg-config)
54 #:use-module (gnu packages statistics)
55 #:use-module (gnu packages web)
56 #:use-module (gnu packages xml)
57 #:use-module (srfi srfi-1))
62 (define-public r-org-eck12-eg-db
64 (name "r-org-eck12-eg-db")
69 (uri (bioconductor-uri "org.EcK12.eg.db" version 'annotation))
71 (base32 "0c4p6jr83k0gm6pvn760yr8xf33wggrfcr6fg7a42a96bcf817gs"))))
73 `((upstream-name . "org.EcK12.eg.db")))
74 (build-system r-build-system)
76 (list r-annotationdbi))
77 (home-page "https://bioconductor.org/packages/org.EcK12.eg.db")
78 (synopsis "Genome wide annotation for E coli strain K12")
80 "This package provides genome wide annotation for E coli strain K12,
81 primarily based on mapping using Entrez Gene identifiers. Entrez Gene is
82 National Center for Biotechnology Information (NCBI)’s database for
83 gene-specific information. Entrez Gene maintains records from genomes which
84 have been completely sequenced, which have an active research community to
85 submit gene-specific information, or which are scheduled for intense sequence
87 (license license:artistic2.0)))
89 (define-public r-org-bt-eg-db
91 (name "r-org-bt-eg-db")
96 (uri (bioconductor-uri
102 "0pwvwyfah8fhvaxdc8zkp3lp1v4mchhzr84r3hb0jx97icdvhafi"))))
103 (properties `((upstream-name . "org.Bt.eg.db")))
104 (build-system r-build-system)
106 (list r-annotationdbi))
107 (home-page "https://bioconductor.org/packages/org.Bt.eg.db")
108 (synopsis "Genome wide annotation for Bovine")
110 "This package provides genome wide annotations for Bovine, primarily
111 based on mapping using Entrez Gene identifiers.")
112 (license license:artistic2.0)))
114 (define-public r-reactome-db
116 (name "r-reactome-db")
121 (uri (bioconductor-uri "reactome.db" version 'annotation))
124 "05wc4fp0faq6h3kq5rwafnips043as31yq11mrjngfxvf5i10srg"))))
125 (properties `((upstream-name . "reactome.db")))
126 (build-system r-build-system)
128 (list r-annotationdbi))
129 (home-page "https://bioconductor.org/packages/reactome.db/")
130 (synopsis "Annotation maps for reactome")
132 "This package provides a set of annotation maps for the REACTOME
133 database, assembled using data from REACTOME.")
134 (license license:cc-by4.0)))
136 (define-public r-bsgenome-btaurus-ucsc-bostau8
138 (name "r-bsgenome-btaurus-ucsc-bostau8")
142 (uri (bioconductor-uri "BSgenome.Btaurus.UCSC.bosTau8"
143 version 'annotation))
146 "16wjy1aw9nvx03r7w8yh5w7sw3pn8i9nczd0n0728l6nnyqxlsz6"))))
148 `((upstream-name . "BSgenome.Btaurus.UCSC.bosTau8")))
149 (build-system r-build-system)
153 "https://www.bioconductor.org/packages/BSgenome.Btaurus.UCSC.bosTau8/")
154 (synopsis "Full genome sequences for Bos taurus (UCSC version bosTau8)")
155 (description "This package provides the full genome sequences for Bos
156 taurus (UCSC version bosTau8).")
157 (license license:artistic2.0)))
159 (define-public r-bsgenome-celegans-ucsc-ce6
161 (name "r-bsgenome-celegans-ucsc-ce6")
165 (uri (bioconductor-uri "BSgenome.Celegans.UCSC.ce6"
166 version 'annotation))
169 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
171 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
172 (build-system r-build-system)
176 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
177 (synopsis "Full genome sequences for Worm")
179 "This package provides full genome sequences for Caenorhabditis
180 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
182 (license license:artistic2.0)))
184 (define-public r-bsgenome-celegans-ucsc-ce10
186 (name "r-bsgenome-celegans-ucsc-ce10")
190 (uri (bioconductor-uri "BSgenome.Celegans.UCSC.ce10"
191 version 'annotation))
194 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
196 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
197 (build-system r-build-system)
201 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
202 (synopsis "Full genome sequences for Worm")
204 "This package provides full genome sequences for Caenorhabditis
205 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
207 (license license:artistic2.0)))
209 (define-public r-bsgenome-dmelanogaster-ucsc-dm6
211 (name "r-bsgenome-dmelanogaster-ucsc-dm6")
215 (uri (bioconductor-uri "BSgenome.Dmelanogaster.UCSC.dm6"
216 version 'annotation))
219 "1bhj0rdgf7lspw4xby9y9mf7v7jxxz8001bc8vw8kf04rjsx6060"))))
221 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm6")))
222 (build-system r-build-system)
226 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm6/")
227 (synopsis "Full genome sequences for Fly")
229 "This package provides full genome sequences for Drosophila
230 melanogaster (Fly) as provided by UCSC (dm6) and stored in Biostrings
232 (license license:artistic2.0)))
234 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
236 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
240 (uri (bioconductor-uri "BSgenome.Dmelanogaster.UCSC.dm3"
241 version 'annotation))
244 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
246 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
247 (build-system r-build-system)
251 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
252 (synopsis "Full genome sequences for Fly")
254 "This package provides full genome sequences for Drosophila
255 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
256 Biostrings objects.")
257 (license license:artistic2.0)))
259 (define-public r-bsgenome-dmelanogaster-ucsc-dm3-masked
261 (name "r-bsgenome-dmelanogaster-ucsc-dm3-masked")
265 (uri (bioconductor-uri "BSgenome.Dmelanogaster.UCSC.dm3.masked"
266 version 'annotation))
269 "1756csb09f1br9rj1l3f08qyh4hlymdbd0cfn8x3fq39dn45m5ap"))))
271 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3.masked")))
272 (build-system r-build-system)
274 (list r-bsgenome r-bsgenome-dmelanogaster-ucsc-dm3))
275 (home-page "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3.masked/")
276 (synopsis "Full masked genome sequences for Fly")
278 "This package provides full masked genome sequences for Drosophila
279 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
280 Biostrings objects. The sequences are the same as in
281 BSgenome.Dmelanogaster.UCSC.dm3, except that each of them has the 4 following
282 masks on top: (1) the mask of assembly gaps (AGAPS mask), (2) the mask of
283 intra-contig ambiguities (AMB mask), (3) the mask of repeats from
284 RepeatMasker (RM mask), and (4) the mask of repeats from Tandem Repeats
285 Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by default.")
286 (license license:artistic2.0)))
288 (define-public r-bsgenome-drerio-ucsc-danrer11
290 (name "r-bsgenome-drerio-ucsc-danrer11")
295 (uri (bioconductor-uri "BSgenome.Drerio.UCSC.danRer11"
296 version 'annotation))
298 (base32 "08a928mqzv2jxngjcs4yr6ni1b9z9al6jdngwi438j8hm41cwk4v"))))
299 (properties `((upstream-name . "BSgenome.Drerio.UCSC.danRer11")))
300 (build-system r-build-system)
303 (home-page "https://bioconductor.org/packages/BSgenome.Drerio.UCSC.danRer11")
304 (synopsis "Full genome sequences for Danio rerio (UCSC version danRer11)")
306 "This package provides full genome sequences for Danio rerio (Zebrafish)
307 as provided by UCSC (danRer11, May 2017) and stored in Biostrings objects.")
308 (license license:artistic2.0)))
310 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
312 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
316 (uri (bioconductor-uri "BSgenome.Hsapiens.1000genomes.hs37d5"
317 version 'annotation))
320 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
322 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
323 (build-system r-build-system)
327 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
328 (synopsis "Full genome sequences for Homo sapiens")
330 "This package provides full genome sequences for Homo sapiens from
331 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
332 (license license:artistic2.0)))
334 (define-public r-bsgenome-hsapiens-ncbi-grch38
336 (name "r-bsgenome-hsapiens-ncbi-grch38")
341 (uri (bioconductor-uri "BSgenome.Hsapiens.NCBI.GRCh38"
342 version 'annotation))
345 "0y75qdq578fh6420vbvsbwmdw8jvr3g06qli2h3vj3pxmjykh9c1"))))
346 (properties `((upstream-name . "BSgenome.Hsapiens.NCBI.GRCh38")))
347 (build-system r-build-system)
348 (propagated-inputs (list r-bsgenome))
350 "https://bioconductor.org/packages/release/data/annotation/html/\
351 BSgenome.Hsapiens.NCBI.GRCh38.html")
352 (synopsis "Full genome sequences for Homo sapiens (GRCh38)")
354 "This package provides full genome sequences for Homo sapiens (Human) as
355 provided by NCBI (GRCh38, 2013-12-17) and stored in Biostrings objects.")
356 (license license:artistic2.0)))
358 (define-public r-bsgenome-hsapiens-ucsc-hg19-masked
360 (name "r-bsgenome-hsapiens-ucsc-hg19-masked")
365 (uri (bioconductor-uri "BSgenome.Hsapiens.UCSC.hg19.masked"
366 version 'annotation))
368 (base32 "19533ihgad67bzhavycv6z708012ylz9cw1qdfmk2b7ikf3kiaz9"))))
370 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19.masked")))
371 (build-system r-build-system)
373 (list r-bsgenome r-bsgenome-hsapiens-ucsc-hg19))
374 (home-page "https://bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19.masked/")
375 (synopsis "Full masked genome sequences for Homo sapiens")
377 "This package provides full genome sequences for Homo sapiens (Human) as
378 provided by UCSC (hg19, Feb. 2009) and stored in Biostrings objects. The
379 sequences are the same as in BSgenome.Hsapiens.UCSC.hg19, except that each of
380 them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS
381 mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of
382 repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem
383 Repeats Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by
385 (license license:artistic2.0)))
387 (define-public r-bsgenome-mmusculus-ucsc-mm9
389 (name "r-bsgenome-mmusculus-ucsc-mm9")
393 (uri (bioconductor-uri "BSgenome.Mmusculus.UCSC.mm9"
394 version 'annotation))
397 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
399 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
400 (build-system r-build-system)
404 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
405 (synopsis "Full genome sequences for Mouse")
407 "This package provides full genome sequences for Mus musculus (Mouse) as
408 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
409 (license license:artistic2.0)))
411 (define-public r-bsgenome-mmusculus-ucsc-mm9-masked
413 (name "r-bsgenome-mmusculus-ucsc-mm9-masked")
417 (uri (bioconductor-uri "BSgenome.Mmusculus.UCSC.mm9.masked"
418 version 'annotation))
421 "00bpbm3havqcxr4g63zhllsbpd9q6svgihks7qp7x73nm4gvq7fn"))))
423 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9.masked")))
424 (build-system r-build-system)
426 (list r-bsgenome r-bsgenome-mmusculus-ucsc-mm9))
427 (home-page "https://bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9.masked/")
428 (synopsis "Full masked genome sequences for Mouse")
430 "This package provides full genome sequences for Mus musculus (Mouse) as
431 provided by UCSC (mm9, Jul. 2007) and stored in Biostrings objects. The
432 sequences are the same as in BSgenome.Mmusculus.UCSC.mm9, except that each of
433 them has the 4 following masks on top: (1) the mask of assembly gaps (AGAPS
434 mask), (2) the mask of intra-contig ambiguities (AMB mask), (3) the mask of
435 repeats from RepeatMasker (RM mask), and (4) the mask of repeats from Tandem
436 Repeats Finder (TRF mask). Only the AGAPS and AMB masks are \"active\" by
438 (license license:artistic2.0)))
440 (define-public r-bsgenome-mmusculus-ucsc-mm10
442 (name "r-bsgenome-mmusculus-ucsc-mm10")
446 (uri (bioconductor-uri "BSgenome.Mmusculus.UCSC.mm10"
447 version 'annotation))
450 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
452 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
453 (build-system r-build-system)
457 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
458 (synopsis "Full genome sequences for Mouse")
460 "This package provides full genome sequences for Mus
461 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
462 in Biostrings objects.")
463 (license license:artistic2.0)))
465 (define-public r-genomeinfodbdata
467 (name "r-genomeinfodbdata")
471 (uri (bioconductor-uri "GenomeInfoDbData" version 'annotation))
474 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
476 `((upstream-name . "GenomeInfoDbData")))
477 (build-system r-build-system)
478 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
479 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
480 (description "This package contains data for mapping between NCBI taxonomy
481 ID and species. It is used by functions in the GenomeInfoDb package.")
482 (license license:artistic2.0)))
484 (define-public r-go-db
490 (uri (bioconductor-uri "GO.db" version 'annotation))
493 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
495 `((upstream-name . "GO.db")))
496 (build-system r-build-system)
498 (list r-annotationdbi))
499 (home-page "https://bioconductor.org/packages/GO.db")
500 (synopsis "Annotation maps describing the entire Gene Ontology")
502 "The purpose of this GO.db annotation package is to provide detailed
503 information about the latest version of the Gene Ontologies.")
504 (license license:artistic2.0)))
506 (define-public r-homo-sapiens
508 (name "r-homo-sapiens")
512 (uri (bioconductor-uri "Homo.sapiens" version 'annotation))
515 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
517 `((upstream-name . "Homo.sapiens")))
518 (build-system r-build-system)
520 (list r-genomicfeatures
523 r-txdb-hsapiens-ucsc-hg19-knowngene
526 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
527 (synopsis "Annotation package for the Homo.sapiens object")
529 "This package contains the Homo.sapiens object to access data from
530 several related annotation packages.")
531 (license license:artistic2.0)))
533 (define-public r-mus-musculus
535 (name "r-mus-musculus")
540 (uri (bioconductor-uri "Mus.musculus" version 'annotation))
543 "143zdf83gbfqhy8jm9df7gzhw5q3a64jrjrxrzjf0zd76j8s8j6y"))))
544 (properties `((upstream-name . "Mus.musculus")))
545 (build-system r-build-system)
547 (list r-annotationdbi
552 r-txdb-mmusculus-ucsc-mm10-knowngene))
553 (home-page "https://bioconductor.org/packages/Mus.musculus")
554 (synopsis "Annotation package for the Mus.musculus object")
556 "This package contains the @code{Mus.musculus} object to access data
557 from several related annotation packages.")
558 (license license:artistic2.0)))
560 (define-public r-illuminahumanmethylation450kanno-ilmn12-hg19
562 (name "r-illuminahumanmethylation450kanno-ilmn12-hg19")
567 (uri (bioconductor-uri
568 "IlluminaHumanMethylation450kanno.ilmn12.hg19"
569 version 'annotation))
572 "059vlxsx3p3fcnywwirahsc6mlk813zpqnbv0jsrag6x5bb8z6r4"))))
575 . "IlluminaHumanMethylation450kanno.ilmn12.hg19")))
576 (build-system r-build-system)
577 (propagated-inputs (list r-minfi))
579 "https://bioconductor.org/packages/IlluminaHumanMethylation450kanno.ilmn12.hg19/")
580 (synopsis "Annotation for Illumina's 450k methylation arrays")
582 "This package provides manifests and annotation for Illumina's 450k array
584 (license license:artistic2.0)))
586 (define-public r-org-ce-eg-db
588 (name "r-org-ce-eg-db")
592 (uri (bioconductor-uri "org.Ce.eg.db" version 'annotation))
595 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
597 `((upstream-name . "org.Ce.eg.db")))
598 (build-system r-build-system)
600 (list r-annotationdbi))
601 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
602 (synopsis "Genome wide annotation for Worm")
604 "This package provides mappings from Entrez gene identifiers to various
605 annotations for the genome of the model worm Caenorhabditis elegans.")
606 (license license:artistic2.0)))
608 (define-public r-org-dm-eg-db
610 (name "r-org-dm-eg-db")
614 (uri (bioconductor-uri "org.Dm.eg.db" version 'annotation))
617 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
619 `((upstream-name . "org.Dm.eg.db")))
620 (build-system r-build-system)
622 (list r-annotationdbi))
623 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
624 (synopsis "Genome wide annotation for Fly")
626 "This package provides mappings from Entrez gene identifiers to various
627 annotations for the genome of the model fruit fly Drosophila melanogaster.")
628 (license license:artistic2.0)))
630 (define-public r-org-dr-eg-db
632 (name "r-org-dr-eg-db")
636 (uri (bioconductor-uri "org.Dr.eg.db" version 'annotation))
639 "1xs5wsbcpy0iwbjyiv7fax57djqc529ai5fk1qfsdcvlja3cpglx"))))
641 `((upstream-name . "org.Dr.eg.db")))
642 (build-system r-build-system)
644 (list r-annotationdbi))
645 (home-page "https://www.bioconductor.org/packages/org.Dr.eg.db/")
646 (synopsis "Annotation for Zebrafish")
648 "This package provides genome wide annotations for Zebrafish, primarily
649 based on mapping using Entrez Gene identifiers.")
650 (license license:artistic2.0)))
652 (define-public r-org-hs-eg-db
654 (name "r-org-hs-eg-db")
658 (uri (bioconductor-uri "org.Hs.eg.db" version 'annotation))
661 "0mnddv42ll0sc0zxf7hkgilslykbvfn7xgxg1g8qi57q2dmpwb6j"))))
663 `((upstream-name . "org.Hs.eg.db")))
664 (build-system r-build-system)
666 (list r-annotationdbi))
667 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
668 (synopsis "Genome wide annotation for Human")
670 "This package contains genome-wide annotations for Human, primarily based
671 on mapping using Entrez Gene identifiers.")
672 (license license:artistic2.0)))
674 (define-public r-org-mm-eg-db
676 (name "r-org-mm-eg-db")
680 (uri (bioconductor-uri "org.Mm.eg.db" version 'annotation))
683 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
685 `((upstream-name . "org.Mm.eg.db")))
686 (build-system r-build-system)
688 (list r-annotationdbi))
689 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
690 (synopsis "Genome wide annotation for Mouse")
692 "This package provides mappings from Entrez gene identifiers to various
693 annotations for the genome of the model mouse Mus musculus.")
694 (license license:artistic2.0)))
696 (define-public r-bsgenome-hsapiens-ucsc-hg19
698 (name "r-bsgenome-hsapiens-ucsc-hg19")
702 (uri (bioconductor-uri "BSgenome.Hsapiens.UCSC.hg19"
703 version 'annotation))
706 "06lx7q7i52lg3vkjkqy492z9ianzgi4nhs9m1jrxjjb4hgbnbyjv"))))
708 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
709 (build-system r-build-system)
713 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
714 (synopsis "Full genome sequences for Homo sapiens")
716 "This package provides full genome sequences for Homo sapiens as provided
717 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
718 (license license:artistic2.0)))
720 (define-public r-bsgenome-hsapiens-ucsc-hg38
722 (name "r-bsgenome-hsapiens-ucsc-hg38")
726 (uri (bioconductor-uri "BSgenome.Hsapiens.UCSC.hg38"
727 version 'annotation))
729 (base32 "03xmh6q99nqjxz29m6j0ymxlk22jq0nlvpf4a2yhg3hgnxqkakh2"))))
731 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg38")))
732 (build-system r-build-system)
736 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg38/")
737 (synopsis "Full genome sequences for Homo sapiens")
739 "This package provides full genome sequences for Homo sapiens (Human)
740 as provided by UCSC (hg38, Dec. 2013) and stored in Biostrings objects.")
741 (license license:artistic2.0)))
743 (define-public r-ensdb-hsapiens-v75
745 (name "r-ensdb-hsapiens-v75")
750 (uri (bioconductor-uri "EnsDb.Hsapiens.v75" version 'annotation))
753 "0jx6rf6v0j8yr07q3c1h7s121901dc400nm6xaiv4i7kb5czjn9c"))))
755 `((upstream-name . "EnsDb.Hsapiens.v75")))
756 (build-system r-build-system)
759 (home-page "https://bioconductor.org/packages/EnsDb.Hsapiens.v75")
760 (synopsis "Ensembl based annotation package")
762 "This package exposes an annotation database generated from Ensembl.")
763 (license license:artistic2.0)))
765 (define-public r-ensdb-hsapiens-v86
767 (name "r-ensdb-hsapiens-v86")
772 (uri (bioconductor-uri "EnsDb.Hsapiens.v86" version 'annotation))
774 (base32 "1gp7xrzddpvmh2vrcp571wyy00skxgxfl39ksj4h0hm1qay0fb2m"))))
775 (properties `((upstream-name . "EnsDb.Hsapiens.v86")))
776 (build-system r-build-system)
777 (propagated-inputs (list r-ensembldb))
778 (home-page "https://bioconductor.org/packages/EnsDb.Hsapiens.v86")
779 (synopsis "Ensembl based annotation package")
780 (description "This package exposes an annotation database generated from
782 (license license:artistic2.0)))
784 (define-public r-ensdb-mmusculus-v79
786 (name "r-ensdb-mmusculus-v79")
791 (uri (bioconductor-uri "EnsDb.Mmusculus.v79" version 'annotation))
793 (base32 "1zpmq7v55if6q9r0h883q9k8l70ym20b01m9hxf121wb256rl9f7"))))
794 (properties `((upstream-name . "EnsDb.Mmusculus.v79")))
795 (build-system r-build-system)
796 (propagated-inputs (list r-ensembldb))
797 (home-page "https://bioconductor.org/packages/EnsDb.Mmusculus.v79")
798 (synopsis "Ensembl based annotation package")
799 (description "This package exposes an annotation database generated from
801 (license license:artistic2.0)))
803 (define-public r-snplocs-hsapiens-dbsnp144-grch37
805 (name "r-snplocs-hsapiens-dbsnp144-grch37")
809 (uri (bioconductor-uri "SNPlocs.Hsapiens.dbSNP144.GRCh37"
810 version 'annotation))
813 "1z8kx43ki1jvj7ms7pcybakcdimfwr6zpjvspkjmma97bdz093iz"))))
814 (build-system r-build-system)
815 ;; As this package provides little more than a very large data file it
816 ;; doesn't make sense to build substitutes.
817 (arguments `(#:substitutable? #f))
827 "https://bioconductor.org/packages/SNPlocs.Hsapiens.dbSNP144.GRCh37/")
828 (synopsis "SNP locations for Homo sapiens (dbSNP Build 144)")
829 (description "This package provides SNP locations and alleles for Homo
830 sapiens extracted from NCBI dbSNP Build 144. The source data files used for
831 this package were created by NCBI on May 29-30, 2015, and contain SNPs mapped
832 to reference genome GRCh37.p13. Note that the GRCh37.p13 genome is a
833 patched version of GRCh37. However the patch doesn't alter chromosomes 1-22,
834 X, Y, MT. GRCh37 itself is the same as the hg19 genome from UCSC *except* for
835 the mitochondrion chromosome. Therefore, the SNPs in this package can be
836 injected in @code{BSgenome.Hsapiens.UCSC.hg19} and they will land at the
837 correct position but this injection will exclude chrM (i.e. nothing will be
838 injected in that sequence).")
839 (license license:artistic2.0)))
841 (define-public r-txdb-dmelanogaster-ucsc-dm6-ensgene
843 (name "r-txdb-dmelanogaster-ucsc-dm6-ensgene")
848 (uri (bioconductor-uri "TxDb.Dmelanogaster.UCSC.dm6.ensGene"
849 version 'annotation))
852 "0yij7zyqkmmr13389rs2gfa5anvvw648nnl1kjbsgvyxkggif8q4"))))
854 `((upstream-name . "TxDb.Dmelanogaster.UCSC.dm6.ensGene")))
855 (build-system r-build-system)
857 (list r-annotationdbi r-genomicfeatures))
859 "https://bioconductor.org/packages/TxDb.Dmelanogaster.UCSC.dm6.ensGene")
860 (synopsis "Annotation package for TxDb object(s)")
862 "This package exposes an annotation databases generated from UCSC by
863 exposing these as TxDb objects.")
864 (license license:artistic2.0)))
866 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
868 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
872 (uri (bioconductor-uri "TxDb.Hsapiens.UCSC.hg19.knownGene"
873 version 'annotation))
876 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
878 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
879 (build-system r-build-system)
881 (list r-genomicfeatures))
883 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
884 (synopsis "Annotation package for human genome in TxDb format")
886 "This package provides an annotation database of Homo sapiens genome
887 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
888 track. The database is exposed as a @code{TxDb} object.")
889 (license license:artistic2.0)))
891 (define-public r-txdb-hsapiens-ucsc-hg38-knowngene
893 (name "r-txdb-hsapiens-ucsc-hg38-knowngene")
897 (uri (bioconductor-uri "TxDb.Hsapiens.UCSC.hg38.knownGene"
898 version 'annotation))
900 (base32 "1y9fqhkk5wgny43bxc0j82afy49vz34rblcmcfmwavngdkpnj879"))))
902 `((upstream-name . "TxDb.Hsapiens.UCSC.hg38.knownGene")))
903 (build-system r-build-system)
905 (list r-annotationdbi r-genomicfeatures))
907 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg38.knownGene/")
908 (synopsis "Annotation package for human genome in TxDb format")
910 "This package provides an annotation database of Homo sapiens genome
911 data. It is derived from the UCSC hg38 genome and based on the \"knownGene\"
912 track. The database is exposed as a @code{TxDb} object.")
913 (license license:artistic2.0)))
915 (define-public r-txdb-mmusculus-ucsc-mm9-knowngene
917 (name "r-txdb-mmusculus-ucsc-mm9-knowngene")
921 (uri (bioconductor-uri "TxDb.Mmusculus.UCSC.mm9.knownGene"
922 version 'annotation))
925 "16bjxy00363hf91ik2mqlqls86i07gia72qh92xc3l1ncch61mx2"))))
927 `((upstream-name . "TxDb.Mmusculus.UCSC.mm9.knownGene")))
928 (build-system r-build-system)
930 (list r-genomicfeatures r-annotationdbi))
932 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm9.knownGene/")
933 (synopsis "Annotation package for mouse genome in TxDb format")
935 "This package provides an annotation database of Mouse genome data. It
936 is derived from the UCSC mm9 genome and based on the \"knownGene\" track. The
937 database is exposed as a @code{TxDb} object.")
938 (license license:artistic2.0)))
940 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
942 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
946 (uri (bioconductor-uri "TxDb.Mmusculus.UCSC.mm10.knownGene"
947 version 'annotation))
950 "0xs9npnhbwll7p62hibs02y4ac23jchdcr25i6a7qwq1kms82qk9"))))
952 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
953 (build-system r-build-system)
955 (list r-bsgenome r-genomicfeatures r-annotationdbi))
957 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
958 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
960 "This package loads a TxDb object, which is an R interface to
961 prefabricated databases contained in this package. This package provides
962 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
963 based on the knownGene track.")
964 (license license:artistic2.0)))
966 (define-public r-txdb-celegans-ucsc-ce6-ensgene
968 (name "r-txdb-celegans-ucsc-ce6-ensgene")
973 (uri (bioconductor-uri "TxDb.Celegans.UCSC.ce6.ensGene"
974 version 'annotation))
977 "1sgppva33cdy4isj2is8mfalj5gmmkpbkq9w1d83a4agcq31mi90"))))
979 `((upstream-name . "TxDb.Celegans.UCSC.ce6.ensGene")))
980 (build-system r-build-system)
982 (list r-annotationdbi r-genomicfeatures))
983 (home-page "https://bioconductor.org/packages/TxDb.Celegans.UCSC.ce6.ensGene/")
984 (synopsis "Annotation package for C elegans TxDb objects")
986 "This package exposes a C elegans annotation database generated from UCSC
987 by exposing these as TxDb objects.")
988 (license license:artistic2.0)))
990 (define-public r-fdb-infiniummethylation-hg19
992 (name "r-fdb-infiniummethylation-hg19")
996 (uri (bioconductor-uri "FDb.InfiniumMethylation.hg19"
997 version 'annotation))
1000 "0gq90fvph6kgrpjb89nvzq6hl1k24swn19rgjh5g98l86mja6nk0"))))
1002 `((upstream-name . "FDb.InfiniumMethylation.hg19")))
1003 (build-system r-build-system)
1005 (list r-biostrings r-genomicfeatures r-annotationdbi r-org-hs-eg-db
1006 r-txdb-hsapiens-ucsc-hg19-knowngene))
1007 (home-page "https://bioconductor.org/packages/FDb.InfiniumMethylation.hg19/")
1008 (synopsis "Compiled HumanMethylation27 and HumanMethylation450 annotations")
1010 "This is an annotation package for Illumina Infinium DNA methylation
1011 probes. It contains the compiled HumanMethylation27 and HumanMethylation450
1013 (license license:artistic2.0)))
1015 (define-public r-illuminahumanmethylationepicmanifest
1017 (name "r-illuminahumanmethylationepicmanifest")
1021 (uri (bioconductor-uri "IlluminaHumanMethylationEPICmanifest"
1022 version 'annotation))
1025 "0alhjda5g186z8b1nsmnpfswrlj7prdz8mkwx60wkkl6hkcnk6p3"))))
1027 `((upstream-name . "IlluminaHumanMethylationEPICmanifest")))
1028 (build-system r-build-system)
1031 (home-page "https://bioconductor.org/packages/IlluminaHumanMethylationEPICmanifest/")
1032 (synopsis "Manifest for Illumina's EPIC methylation arrays")
1034 "This is a manifest package for Illumina's EPIC methylation arrays.")
1035 (license license:artistic2.0)))
1037 (define-public r-do-db
1043 (uri (bioconductor-uri "DO.db" version 'annotation))
1046 "10bqqa124l61ivzy4mdd3z3ar9a6537qbxw23pc4y9w8a6dwnavn"))))
1048 `((upstream-name . "DO.db")))
1049 (build-system r-build-system)
1051 (list r-annotationdbi))
1052 (home-page "https://www.bioconductor.org/packages/DO.db/")
1053 (synopsis "Annotation maps describing the entire Disease Ontology")
1055 "This package provides a set of annotation maps describing the entire
1057 (license license:artistic2.0)))
1059 (define-public r-hgu133plus2-db
1061 (name "r-hgu133plus2-db")
1066 (uri (bioconductor-uri "hgu133plus2.db" version 'annotation))
1068 (base32 "0i6cfk7ahql4fcgrq0dai9gkjbsahyzd9iv4lqv1ad58fzkmipnx"))))
1069 (properties `((upstream-name . "hgu133plus2.db")))
1070 (build-system r-build-system)
1071 (propagated-inputs (list r-annotationdbi r-org-hs-eg-db))
1072 (home-page "https://bioconductor.org/packages/hgu133plus2.db")
1073 (synopsis "Affymetrix Affymetrix HG-U133_Plus_2 Array annotation data")
1075 "This package provides Affymetrix HG-U133_Plus_2 array annotation
1076 data (chip hgu133plus2) assembled using data from public repositories.")
1077 (license license:artistic2.0)))
1079 (define-public r-pfam-db
1086 (uri (bioconductor-uri "PFAM.db" version 'annotation))
1088 (base32 "03vjfb9vx1gxrw1jkq6y4i46qhjj9z2mkdiflglbd6kpfrgnl0z7"))))
1089 (properties `((upstream-name . "PFAM.db")))
1090 (build-system r-build-system)
1092 (list r-annotationdbi))
1093 (home-page "https://bioconductor.org/packages/PFAM.db")
1094 (synopsis "Set of protein ID mappings for PFAM")
1096 "This package provides a set of protein ID mappings for PFAM, assembled
1097 using data from public repositories.")
1098 (license license:artistic2.0)))
1100 (define-public r-phastcons100way-ucsc-hg19
1102 (name "r-phastcons100way-ucsc-hg19")
1107 (uri (bioconductor-uri "phastCons100way.UCSC.hg19"
1108 version 'annotation))
1111 "1jmc4k4zgkx5vr2plnidnd9bidlwlb0kr7mjg60cqjw7dq7jl1fa"))))
1113 `((upstream-name . "phastCons100way.UCSC.hg19")))
1114 (build-system r-build-system)
1122 (home-page "https://bioconductor.org/packages/phastCons100way.UCSC.hg19")
1123 (synopsis "UCSC phastCons conservation scores for hg19")
1125 "This package provides UCSC phastCons conservation scores for the human
1126 genome (hg19) calculated from multiple alignments with other 99 vertebrate
1128 (license license:artistic2.0)))
1133 (define-public r-abadata
1139 (uri (bioconductor-uri "ABAData" version 'experiment))
1142 "1bmj341xcymlrk02gss5vvrqc4ddas0rdw39lnpsj98hq6n11p5z"))))
1144 `((upstream-name . "ABAData")))
1145 (build-system r-build-system)
1147 (list r-annotationdbi))
1148 (home-page "https://www.bioconductor.org/packages/ABAData/")
1149 (synopsis "Gene expression in human brain regions from Allen Brain Atlas")
1151 "This package provides the data for the gene expression enrichment
1152 analysis conducted in the package ABAEnrichment. The package includes three
1153 datasets which are derived from the Allen Brain Atlas:
1156 @item Gene expression data from Human Brain (adults) averaged across donors,
1157 @item Gene expression data from the Developing Human Brain pooled into five
1158 age categories and averaged across donors, and
1159 @item a developmental effect score based on the Developing Human Brain
1163 All datasets are restricted to protein coding genes.")
1164 (license license:gpl2+)))
1166 (define-public r-adductdata
1168 (name "r-adductdata")
1172 (uri (bioconductor-uri "adductData" version 'experiment))
1174 (base32 "02r7p1645vhhf7wn5x0aklmf7l97h6fjb8v9mldim4waccmpyg48"))))
1175 (properties `((upstream-name . "adductData")))
1176 (build-system r-build-system)
1177 (propagated-inputs (list r-annotationhub r-experimenthub))
1178 (native-inputs (list r-knitr))
1179 (home-page "https://bioconductor.org/packages/adductData")
1180 (synopsis "Data from untargeted mass spectrometry of modifications to Cys34")
1182 "This package contains data from untargeted @dfn{mass spectrometry} (MS)
1183 of modifications to @dfn{oxidized cysteine} (Cys) 34 in @dfn{human serum
1185 (license license:artistic2.0)))
1187 (define-public r-aneufinderdata
1189 (name "r-aneufinderdata")
1193 (uri (bioconductor-uri "AneuFinderData" version 'experiment))
1195 (base32 "0cncb8km0sc2xh95rgnnm38kys5ml0n8gh8cl6x7ls1xh9sm83f7"))))
1196 (build-system r-build-system)
1197 (home-page "https://bioconductor.org/packages/AneuFinderData/")
1198 (synopsis "Data package for @code{AneuFinder}")
1199 (description "This package contains whole-genome single cell sequencing data for
1200 demonstration purposes in the @code{AneuFinder} package.")
1201 (license license:artistic2.0)))
1203 (define-public r-arrmdata
1209 (uri (bioconductor-uri "ARRmData" version 'experiment))
1211 (base32 "1cjzr58426s9z2bwjz3wzlkh52fv0q85cw4gbjnhwakh9sr3dd5p"))))
1213 `((upstream-name . "ARRmData")))
1214 (build-system r-build-system)
1215 (home-page "https://www.bioconductor.org/packages/ARRmData/")
1216 (synopsis "Example dataset for normalization of Illumina 450k methylation data")
1218 "This package provides raw beta values from 36 samples across 3 groups
1219 from Illumina 450k methylation arrays.")
1220 (license license:artistic2.0)))
1222 (define-public r-biscuiteerdata
1224 (name "r-biscuiteerdata")
1229 (uri (bioconductor-uri "biscuiteerData" version 'experiment))
1231 (base32 "0nda6b8mkv93s513y0xfgxvi7zn8v07jx323ii709rknlncm6qqw"))))
1233 `((upstream-name . "biscuiteerData")))
1234 (build-system r-build-system)
1236 (list r-annotationhub r-curl r-experimenthub))
1237 (native-inputs (list r-knitr))
1238 (home-page "https://bioconductor.org/packages/biscuiteerData")
1239 (synopsis "Data package for Biscuiteer")
1241 "This package contains default datasets used by the Bioconductor package
1243 (license license:gpl3)))
1245 (define-public r-celldex
1252 (uri (bioconductor-uri "celldex" version 'experiment))
1254 (base32 "1fjldmhb9yg6yr3aq5ldvc8xwqw71ix4cdlr53xxckgwljjq7x10"))))
1255 (properties `((upstream-name . "celldex")))
1256 (build-system r-build-system)
1258 (list r-annotationdbi
1261 r-delayedmatrixstats
1264 r-summarizedexperiment))
1265 (native-inputs (list r-knitr))
1266 (home-page "https://github.com/LTLA/celldex")
1267 (synopsis "Reference index for cell types")
1269 "This package provides a collection of reference expression datasets with
1270 curated cell type labels, for use in procedures like automated annotation of
1271 single-cell data or deconvolution of bulk RNA-seq.")
1272 (license license:gpl3)))
1274 (define-public r-chromstardata
1276 (name "r-chromstardata")
1281 (uri (bioconductor-uri "chromstaRData" version 'experiment))
1283 (base32 "1ajwnkibpi01c93nrplxhy6grw8jj5219g4pii4rkan4k5815kv1"))))
1284 (properties `((upstream-name . "chromstaRData")))
1285 (build-system r-build-system)
1286 (home-page "https://bioconductor.org/packages/chromstaRData/")
1287 (synopsis "ChIP-seq data for demonstration purposes")
1289 "This package provides ChIP-seq data for demonstration purposes in the
1290 chromstaR package.")
1291 (license license:gpl3)))
1293 (define-public r-copyhelper
1295 (name "r-copyhelper")
1300 (uri (bioconductor-uri "CopyhelpeR" version 'experiment))
1302 (base32 "0klrnxck0q14birnpwzkiwmj77hwdn6gazvdg0lqn9y6j5mbkyx1"))))
1303 (properties `((upstream-name . "CopyhelpeR")))
1304 (build-system r-build-system)
1305 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
1306 (synopsis "Helper files for CopywriteR")
1308 "This package contains the helper files that are required to run the
1309 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
1310 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
1311 mm10. In addition, it contains a blacklist filter to remove regions that
1312 display copy number variation. Files are stored as GRanges objects from the
1313 GenomicRanges Bioconductor package.")
1314 (license license:gpl2)))
1316 (define-public r-genelendatabase
1318 (name "r-genelendatabase")
1323 (uri (bioconductor-uri "geneLenDataBase" version 'experiment))
1325 (base32 "0p4rmd3qszsnyn47mfbk96zfa0bhpyyvsh4ma1ligjrsnmkicsaz"))))
1327 `((upstream-name . "geneLenDataBase")))
1328 (build-system r-build-system)
1330 (list r-rtracklayer r-genomicfeatures))
1331 (home-page "https://bioconductor.org/packages/geneLenDataBase/")
1332 (synopsis "Lengths of mRNA transcripts for a number of genomes")
1334 "This package provides the lengths of mRNA transcripts for a number of
1335 genomes and gene ID formats, largely based on the UCSC table browser.")
1336 (license license:lgpl2.0+)))
1338 (define-public r-genomationdata
1340 (name "r-genomationdata")
1345 (uri (bioconductor-uri "genomationData" version 'experiment))
1347 (base32 "0ckdgmarndpz6r0y9sd4nmypzjgivj32w2890yl15xmxkx4397fh"))))
1349 `((upstream-name . "genomationData")))
1350 (build-system r-build-system)
1351 ;; As this package provides little more than large data files, it doesn't
1352 ;; make sense to build substitutes.
1353 (arguments `(#:substitutable? #f))
1356 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
1357 (synopsis "Experimental data for use with the genomation package")
1359 "This package contains experimental genetic data for use with the
1360 genomation package. Included are Chip Seq, Methylation and Cage data,
1361 downloaded from Encode.")
1362 (license license:gpl3+)))
1364 (define-public r-msdata
1371 (uri (bioconductor-uri "msdata" version 'experiment))
1373 (base32 "0nqb7d7fa9l15bxy3s9wmy2h79jb6ldwww0hzk5mifabacmzx691"))))
1374 (properties `((upstream-name . "msdata")))
1375 (build-system r-build-system)
1376 (home-page "https://bioconductor.org/packages/msdata")
1377 (synopsis "Various Mass Spectrometry raw data example files")
1379 "This package provides Ion Trap positive ionization mode data in mzML file
1380 format. It includes a subset from 500-850 m/z and 1190-1310 seconds,
1381 including MS2 and MS3, intensity threshold 100.000; extracts from FTICR Apex
1382 III, m/z 400-450; a subset of UPLC - Bruker micrOTOFq data, both mzML and mz5;
1383 LC-MSMS and MRM files from proteomics experiments; and PSI mzIdentML example
1384 files for various search engines.")
1385 (license license:gpl2+)))
1387 (define-public r-pasilla
1394 (uri (bioconductor-uri "pasilla" version 'experiment))
1396 (base32 "1vsxh7mv2krkbdqs5gsgjsxarjbll0bpyk94syrwh56z67n7jyib"))))
1397 (build-system r-build-system)
1398 (propagated-inputs (list r-dexseq))
1399 (native-inputs (list r-knitr))
1400 (home-page "https://www.bioconductor.org/packages/pasilla/")
1401 (synopsis "Data package with per-exon and per-gene read counts")
1402 (description "This package provides per-exon and per-gene read counts
1403 computed for selected genes from RNA-seq data that were presented in the
1404 article 'Conservation of an RNA regulatory map between Drosophila and mammals'
1405 by Brooks et al., Genome Research 2011.")
1406 (license license:lgpl2.1+)))
1408 (define-public r-hsmmsinglecell
1410 (name "r-hsmmsinglecell")
1415 (uri (bioconductor-uri "HSMMSingleCell" version 'experiment))
1417 (base32 "12whx0pl9461xbak5r9zi6ggx5is8sk6mgrbjwlmx3mbr9am116v"))))
1419 `((upstream-name . "HSMMSingleCell")))
1420 (build-system r-build-system)
1421 (home-page "https://www.bioconductor.org/packages/HSMMSingleCell/")
1422 (synopsis "Single-cell RNA-Seq for differentiating human skeletal muscle myoblasts (HSMM)")
1424 "Skeletal myoblasts undergo a well-characterized sequence of
1425 morphological and transcriptional changes during differentiation. In this
1426 experiment, primary @dfn{human skeletal muscle myoblasts} (HSMM) were expanded
1427 under high mitogen conditions (GM) and then differentiated by switching to
1428 low-mitogen media (DM). RNA-Seq libraries were sequenced from each of several
1429 hundred cells taken over a time-course of serum-induced differentiation.
1430 Between 49 and 77 cells were captured at each of four time points (0, 24, 48,
1431 72 hours) following serum switch using the Fluidigm C1 microfluidic system.
1432 RNA from each cell was isolated and used to construct mRNA-Seq libraries,
1433 which were then sequenced to a depth of ~4 million reads per library,
1434 resulting in a complete gene expression profile for each cell.")
1435 (license license:artistic2.0)))
1437 (define-public r-all
1444 (uri (bioconductor-uri "ALL" version 'experiment))
1446 (base32 "0410045x327wmfkksshd8yishw4yxij08vn8p65cdj7hb3qy3p0z"))))
1447 (properties `((upstream-name . "ALL")))
1448 (build-system r-build-system)
1451 (home-page "https://bioconductor.org/packages/ALL")
1452 (synopsis "Acute Lymphoblastic Leukemia data from the Ritz laboratory")
1454 "The data consist of microarrays from 128 different individuals with
1455 @dfn{acute lymphoblastic leukemia} (ALL). A number of additional covariates
1456 are available. The data have been normalized (using rma) and it is the
1457 jointly normalized data that are available here. The data are presented in
1458 the form of an @code{exprSet} object.")
1459 (license license:artistic2.0)))
1461 (define-public r-affydata
1468 (uri (bioconductor-uri "affydata" version 'experiment))
1470 (base32 "1d8ims7hks536v739r5hhfkkzyzqrf398aqal3hzyfm0psv15jbp"))))
1471 (properties `((upstream-name . "affydata")))
1472 (build-system r-build-system)
1475 (home-page "https://bioconductor.org/packages/affydata/")
1476 (synopsis "Affymetrix data for demonstration purposes")
1478 "This package provides example datasets that represent 'real world
1479 examples' of Affymetrix data, unlike the artificial examples included in the
1480 package @code{affy}.")
1481 (license license:gpl2+)))
1483 (define-public r-gagedata
1490 (uri (bioconductor-uri "gageData" version 'experiment))
1492 (base32 "00s2aig9r0bvk45brc0shildrgl2z0i0k8xlvqc9h1s274nnslk9"))))
1493 (properties `((upstream-name . "gageData")))
1494 (build-system r-build-system)
1495 (home-page "https://bioconductor.org/packages/gageData")
1496 (synopsis "Auxiliary data for the gage package")
1498 "This is a supportive data package for the software package @code{gage}.
1499 However, the data supplied here are also useful for gene set or pathway
1500 analysis or microarray data analysis in general. In this package, we provide
1501 two demo microarray dataset: GSE16873 (a breast cancer dataset from GEO) and
1502 BMP6 (originally published as an demo dataset for GAGE, also registered as
1503 GSE13604 in GEO). This package also includes commonly used gene set data based
1504 on KEGG pathways and GO terms for major research species, including human,
1505 mouse, rat and budding yeast. Mapping data between common gene IDs for budding
1506 yeast are also included.")
1507 (license license:gpl2+)))
1509 (define-public r-curatedtcgadata
1511 (name "r-curatedtcgadata")
1516 (uri (bioconductor-uri "curatedTCGAData" version 'experiment))
1518 (base32 "0h3mpwy6lhyn8hfry13sdjgb35gqyi3g26igfjqzshc5wvsniwpr"))))
1520 `((upstream-name . "curatedTCGAData")))
1521 (build-system r-build-system)
1523 (list r-annotationhub
1526 r-multiassayexperiment
1528 r-summarizedexperiment))
1529 (native-inputs (list r-knitr))
1530 (home-page "https://bioconductor.org/packages/curatedTCGAData/")
1531 (synopsis "Curated data from The Cancer Genome Atlas")
1533 "This package provides publicly available data from The Cancer Genome
1534 Atlas (TCGA) as @code{MultiAssayExperiment} objects.
1535 @code{MultiAssayExperiment} integrates multiple assays (e.g., RNA-seq, copy
1536 number, mutation, microRNA, protein, and others) with clinical / pathological
1537 data. It also links assay barcodes with patient identifiers, enabling
1538 harmonized subsetting of rows (features) and columns (patients / samples)
1539 across the entire multi-'omics experiment.")
1540 (license license:artistic2.0)))
1542 (define-public r-tcgabiolinksgui-data
1544 (name "r-tcgabiolinksgui-data")
1549 (uri (bioconductor-uri "TCGAbiolinksGUI.data" version 'experiment))
1551 (base32 "1mb2z59acs1pi1gqvgjyh62wnmbxskc5l0p42gpjajsjip5x1x7g"))))
1552 (properties `((upstream-name . "TCGAbiolinksGUI.data")))
1553 (build-system r-build-system)
1554 (native-inputs (list r-knitr))
1555 (home-page "https://github.com/BioinformaticsFMRP/TCGAbiolinksGUI.data")
1556 (synopsis "Data for the TCGAbiolinksGUI package")
1557 (description "This package provides supporting data for the
1558 TCGAbiolinksGUI package.")
1559 (license license:gpl3)))
1564 (define-public r-abarray
1570 (uri (bioconductor-uri "ABarray" version))
1573 "0kjq00i2mb21xyjjs3jy09ps80f11cy37wywzjvmxyjxzbsk4d7r"))))
1574 (properties `((upstream-name . "ABarray")))
1575 (build-system r-build-system)
1576 (propagated-inputs (list r-biobase r-multtest))
1577 (home-page "https://bioconductor.org/packages/ABarray")
1579 "Gene expression analysis for Applied Biosystems Genome Survey Microarray")
1581 "The package @code{ABarray} is designed to work with Applied Biosystems
1582 whole genome microarray platform, as well as any other platform whose data can
1583 be transformed into expression data matrix. Functions include data
1584 preprocessing, filtering, control probe analysis, statistical analysis in one
1585 single function. A @dfn{graphical user interface} (GUI) is also provided. The
1586 raw data, processed data, graphics output and statistical results are organized
1587 into folders according to the analysis settings used.")
1588 (license license:gpl2+)))
1590 (define-public r-absseq
1596 (uri (bioconductor-uri "ABSSeq" version))
1599 "1kwl0gcqwbgblwvpbvqlgnsi91km77j11f0q1f0gd6hhnv38mmlv"))))
1600 (properties `((upstream-name . "ABSSeq")))
1601 (build-system r-build-system)
1602 (propagated-inputs (list r-limma r-locfit))
1603 (home-page "https://bioconductor.org/packages/ABSSeq")
1605 "RNA-Seq analysis based on modelling absolute expression differences")
1607 "This package implements a new RNA-Seq analysis method and integrates two
1608 modules: a basic model for pairwise comparison and a linear model for complex
1609 design. RNA-Seq quantifies gene expression with reads count, which usually
1610 consists of conditions (or treatments) and several replicates for each
1611 condition. This software infers differential expression directly by the
1612 counts difference between conditions. It assumes that the sum counts
1613 difference between conditions follow a negative binomial distribution. In
1614 addition, @code{ABSSeq} moderates the fold-changes by two steps: the
1615 expression level and gene-specific dispersion, that might facilitate the gene
1616 ranking by fold-change and visualization.")
1617 (license license:gpl3+)))
1619 (define-public r-adam
1625 (uri (bioconductor-uri "ADAM" version))
1628 "1cgcjykik9hjrwlvvgaccprcrimgq5kwh9cj6367yk9m574a4gmn"))))
1629 (properties `((upstream-name . "ADAM")))
1630 (build-system r-build-system)
1631 (propagated-inputs (list r-dplyr
1639 r-summarizedexperiment))
1640 (native-inputs (list r-knitr))
1641 (home-page "https://bioconductor.org/packages/ADAM")
1642 (synopsis "Gene activity and diversity analysis module")
1644 "This software @code{ADAM} is a @dfn{Gene set enrichment analysis} (GSEA)
1645 package created to group a set of genes from comparative samples (control
1646 versus experiment) belonging to different species according to their respective
1647 functions. The corresponding roles are extracted from the default collections
1648 like Gene ontology and @dfn{Kyoto encyclopedia of genes and genomes} (KEGG).
1649 @code{ADAM} show their significance by calculating the p-values referring to
1650 gene diversity and activity. Each group of genes is called @dfn{Group of
1651 functionally associated genes} (GFAG).")
1652 (license license:gpl2+)))
1654 (define-public r-adamgui
1660 (uri (bioconductor-uri "ADAMgui" version))
1663 "0vvd5qdwkfcr7zg7z63x3vvrcg63r6c9p383yvcg2lp8zmx8hsbs"))))
1664 (properties `((upstream-name . "ADAMgui")))
1665 (build-system r-build-system)
1687 (native-inputs (list r-knitr))
1688 (home-page "https://bioconductor.org/packages/ADAMgui/")
1689 (synopsis "GUI for gene activity and diversity analysis")
1691 "This package @code{ADAMgui} is a @dfn{graphical user interface} (GUI)
1692 for the @code{ADAM} package. The @code{ADAMgui} package provides two
1693 shiny-based applications that allows the user to study the output of the
1694 @code{ADAM} package files through different plots. It's possible, for
1695 example, to choose a specific @dfn{group of functionally associated
1696 genes} (GFAG) and observe the gene expression behavior with the plots created
1697 with the @code{GFAGtargetUi} function. Features such as differential
1698 expression and fold change can be easily seen with aid of the plots made with
1699 the @code{GFAGpathUi} function.")
1700 (license license:gpl2+)))
1702 (define-public r-adimpute
1708 (uri (bioconductor-uri "ADImpute" version))
1711 "0885kd8mpmwjpzpx14pi6l3mqcvsixk10vkf5h4sqb7di0nnna4w"))))
1712 (properties `((upstream-name . "ADImpute")))
1713 (build-system r-build-system)
1715 (list r-biocparallel
1725 r-singlecellexperiment
1726 r-summarizedexperiment))
1727 (native-inputs (list r-knitr))
1728 (home-page "https://bioconductor.org/packages/ADImpute")
1729 (synopsis "Adaptive computational prediction for dropout imputations")
1731 "@dfn{Single-cell RNA sequencing} (scRNA-seq) methods are typically
1732 unable to quantify the expression levels of all genes in a cell, creating a
1733 need for the computational prediction of missing values (dropout imputation).
1734 Most existing dropout imputation methods are limited in the sense that they
1735 exclusively use the scRNA-seq dataset at hand and do not exploit external
1736 gene-gene relationship information. The @code{ADImpute} package proposes two
1737 methods to address this issue:
1740 @item a gene regulatory network-based approach using gene-gene relationships
1741 learnt from external data;
1742 @item a baseline approach corresponding to a sample-wide average.
1745 @code{ADImpute} implements these novel methods and also combines them with
1746 existing imputation methods like @code{DrImpute} and @code{SAVER}.
1747 @code{ADImpute} can learn the best performing method per gene and combine the
1748 results from different methods into an ensemble.")
1749 (license license:gpl3+)))
1751 (define-public r-adsplit
1757 (uri (bioconductor-uri "adSplit" version))
1760 "1wl2gd0b7krf485clw67cxayp0g9argklkzn8nw1vrkil0vvr4jm"))))
1761 (properties `((upstream-name . "adSplit")))
1762 (build-system r-build-system)
1764 (list r-annotationdbi
1770 (home-page "https://compdiag.molgen.mpg.de/software/adSplit.shtml")
1771 (synopsis "Annotation-driven splits in microarray data")
1773 "This package implements clustering of microarray gene expression
1774 profiles according to functional annotations. For each term genes are
1775 annotated to, splits into two subclasses are computed and a significance of
1776 the supporting gene set is determined.")
1777 (license license:gpl2+)))
1779 (define-public r-affixcan
1785 (uri (bioconductor-uri "AffiXcan" version))
1788 "0wj9shzmlxpksbxny571xzfcmmqqzjlk1vq4mx1is2r6ma7jkblq"))))
1789 (properties `((upstream-name . "AffiXcan")))
1790 (build-system r-build-system)
1792 (list r-biocparallel
1794 r-multiassayexperiment
1795 r-summarizedexperiment))
1796 (native-inputs (list r-knitr))
1797 (home-page "https://bioconductor.org/packages/AffiXcan")
1798 (synopsis "Functional approach to impute genetically regulated expression")
1800 "The @code{AffiXcan} package imputes a @dfn{genetically regulated
1801 expression} (GReX) for a set of genes in a sample of individuals, using a
1802 method based on the @dfn{total binding affinity} (TBA). Statistical models to
1803 impute GReX can be trained with a training dataset where the real total
1804 expression values are known.")
1805 (license license:gpl3)))
1807 (define-public r-affyrnadegradation
1809 (name "r-affyrnadegradation")
1813 (uri (bioconductor-uri "AffyRNADegradation" version))
1816 "16akwmpzwxai7ks5bvc1yyb9sx2scv9b9gas5avb0sk5fk0h3nsf"))))
1817 (properties `((upstream-name . "AffyRNADegradation")))
1818 (build-system r-build-system)
1819 (propagated-inputs (list r-affy))
1820 (home-page "https://bioconductor.org/packages/AffyRNADegradation")
1822 "Analyze and correct probe positional bias in data due to RNA degradation")
1824 "The @code{AffyRNADegradation} package helps with the assessment and
1825 correction of RNA degradation effects in Affymetrix 3 expression arrays. The
1826 parameter @code{d} gives a robust and accurate measure of RNA integrity. The
1827 correction removes the probe positional bias, and thus improves comparability
1828 of samples that are affected by RNA degradation.")
1829 ;; the R file header specifies GPL2 or later
1830 (license license:gpl2+)))
1832 (define-public r-agdex
1838 (uri (bioconductor-uri "AGDEX" version))
1841 "0c44fw5ajdjc13409rn3lsv0jhlqa2qcak9b1k8hpig486xxzsr9"))))
1842 (properties `((upstream-name . "AGDEX")))
1843 (build-system r-build-system)
1844 (propagated-inputs (list r-biobase r-gseabase))
1845 (home-page "https://bioconductor.org/packages/AGDEX")
1847 "Evaluate agreement of differential expression for cross-species genomics")
1849 "The objective of @code{AGDEX} is to evaluate whether the results of a
1850 pair of two-group differential expression analysis comparisons show a level of
1851 agreement that is greater than expected if the group labels for each two-group
1852 comparison are randomly assigned. The agreement is evaluated for the entire
1853 transcriptome and (optionally) for a collection of pre-defined gene-sets.
1854 Additionally, the procedure performs permutation-based differential expression
1855 and meta analysis at both gene and gene-set levels of the data from each
1857 (license license:gpl2+)))
1859 (define-public r-aggregatebiovar
1861 (name "r-aggregatebiovar")
1865 (uri (bioconductor-uri "aggregateBioVar" version))
1868 "0ngg12bgr95m4wm12scmrb55dgy4909c6qrg169l6dkng99v4nx1"))))
1869 (properties `((upstream-name . "aggregateBioVar")))
1870 (build-system r-build-system)
1875 r-singlecellexperiment
1876 r-summarizedexperiment
1878 (native-inputs (list r-knitr))
1879 (home-page "https://github.com/jasonratcliff/aggregateBioVar")
1880 (synopsis "Differential gene expression analysis for multi-subject scRNA-seq")
1882 "This package @code{aggregateBioVar} contains tools to summarize single
1883 cell gene expression profiles at the level of subject for single cell RNA-seq
1884 data collected from more than one subject (e.g. biological sample or technical
1885 replicates). A @code{SingleCellExperiment} object is taken as input and
1886 converted to a list of @code{SummarizedExperiment} objects, where each list
1887 element corresponds to an assigned cell type. The @code{SummarizedExperiment}
1888 objects contain aggregate gene-by-subject count matrices and inter-subject
1889 column metadata for individual subjects that can be processed using downstream
1890 bulk RNA-seq tools.")
1891 (license license:gpl3)))
1893 (define-public r-agilp
1899 (uri (bioconductor-uri "agilp" version))
1902 "1pm329y2nfcnx98ggxq0prdd5pxfcl5iylvsjjnhw5lyz1awg1yf"))))
1903 (properties `((upstream-name . "agilp")))
1904 (build-system r-build-system)
1905 (home-page "https://bioconductor.org/packages/agilp")
1906 (synopsis "Processing of Agilent expression array")
1908 "This package aims to provide a pipeline for the low-level analysis of
1909 gene expression microarray data, primarily focused on the Agilent platform,
1910 but which also provides utilities which may be useful for other platforms.")
1911 ;; Some files are under GPLv2+ but the combined work is released under the
1913 (license license:gpl3)))
1915 (define-public r-adductomicsr
1917 (name "r-adductomicsr")
1921 (uri (bioconductor-uri "adductomicsR" version))
1924 "0623qf06xgdsyz0in2wnxwvpdw8kj6cnwf8vlqmgp7g0n3w701ys"))))
1925 (properties `((upstream-name . "adductomicsR")))
1926 (build-system r-build-system)
1949 (native-inputs (list r-knitr))
1950 (home-page "https://bioconductor.org/packages/adductomicsR")
1951 (synopsis "Processing of adductomic mass spectral datasets")
1953 "This package @code{adductomicsR} processes data generated by the
1954 @dfn{second stage of mass spectrometry} (MS2) to identify potentially adducted
1955 peptides from spectra that has been corrected for mass drift and retention
1956 time drift and quantifies level mass spectral peaks from @dfn{first stage of
1957 mass spectrometry} (MS1) data.")
1958 (license license:artistic2.0)))
1960 (define-public r-agimicrorna
1962 (name "r-agimicrorna")
1966 (uri (bioconductor-uri "AgiMicroRna" version))
1969 "0jic89gyphbv7jzlfgm9bh1aq48lp86rq6hr34gsg9z0pa1192xa"))))
1970 (properties `((upstream-name . "AgiMicroRna")))
1971 (build-system r-build-system)
1978 (home-page "https://git.bioconductor.org/packages/AgiMicroRna")
1980 "Processing and differential expression analysis of Agilent microRNA chips")
1982 "@code{AgiMicroRna} provides useful functionality for the processing,
1983 quality assessment and differential expression analysis of Agilent microRNA
1984 array data. The package uses a limma-like structure to generate the processed
1985 data in order to make statistical inferences about differential expression
1986 using the linear model features implemented in limma. Standard Bioconductor
1987 objects are used so that other packages could be used as well.")
1988 (license license:gpl3)))
1990 (define-public r-amountain
1992 (name "r-amountain")
1996 (uri (bioconductor-uri "AMOUNTAIN" version))
1999 "0vdfabsrisdd7qq28f5ivd0v8zz49szqn677i5lhwnlaix220c54"))))
2000 (properties `((upstream-name . "AMOUNTAIN")))
2001 (build-system r-build-system)
2003 (native-inputs (list r-knitr))
2004 (home-page "https://bioconductor.org/packages/AMOUNTAIN")
2005 (synopsis "Modules for multilayer weighted gene co-expression networks")
2007 "This package provides a pure data-driven gene network, @dfn{WGCN}(weighted
2008 gene co-expression network) could be constructed only from expression profile.
2009 Different layers in such networks may represent different time points, multiple
2010 conditions or various species. @code{AMOUNTAIN} aims to search active modules
2011 in multi-layer WGCN using a continuous optimization approach.")
2012 (license license:gpl2+)))
2014 (define-public r-amaretto
2020 (uri (bioconductor-uri "AMARETTO" version))
2023 "111dk19b9910icksyr592cvhc5gwvgknr5q4887j9yxbajd7hcmx"))))
2024 (properties `((upstream-name . "AMARETTO")))
2025 (build-system r-build-system)
2027 (list r-biocfilecache
2045 r-multiassayexperiment
2051 (native-inputs (list r-knitr))
2052 (home-page "https://bioconductor.org/packages/AMARETTO")
2053 (synopsis "Regulatory network inference and driver gene evaluation")
2055 "This package @code{AMARETTO} represents an algorithm that integrates copy
2056 number, DNA methylation and gene expression data to identify a set of driver
2057 genes by analyzing cancer samples and connects them to clusters of co-expressed
2058 genes, which we define as modules. @code{AMARETTO} can be applied in a pancancer
2059 setting to identify cancer driver genes and their modules on multiple cancer
2060 sites. @code{AMARETTO} captures modules enriched in angiogenesis, cell cycle
2061 and EMT, and modules that accurately predict survival and molecular subtypes.
2062 This allows @code{AMARETTO} to identify novel cancer driver genes directing
2063 canonical cancer pathways.")
2064 (license license:asl2.0)))
2066 (define-public r-anaquin
2072 (uri (bioconductor-uri "Anaquin" version))
2075 "1jgpnls2djl1yzvnk64qc83mljmlci7wflwkza3wr0sv6r47b0dd"))))
2076 (properties `((upstream-name . "Anaquin")))
2077 (build-system r-build-system)
2086 (native-inputs (list r-knitr))
2087 (home-page "https://www.sequinstandards.com/")
2088 (synopsis "Statistical analysis of sequins")
2090 "The project is intended to support the use of @dfn{sequins}(synthetic
2091 sequencing spike-in controls) owned and made available by the Garvan Institute
2092 of Medical Research. The goal is to provide a standard open source library for
2093 quantitative analysis, modelling and visualization of spike-in controls.")
2094 (license license:bsd-3)))
2096 (define-public r-aneufinder
2098 (name "r-aneufinder")
2102 (uri (bioconductor-uri "AneuFinder" version))
2105 "1acsp987jv2x4qwbgy3y7ff4r2qz7680b0nbr37m4lmncqfgh8yl"))))
2106 (build-system r-build-system)
2110 (list r-genomicranges
2131 (home-page "https://bioconductor.org/packages/AneuFinder/")
2132 (synopsis "Copy number variation analysis in single-cell-sequencing data")
2133 (description "This package implements functions for copy number variant
2134 calling, plotting, export and analysis from whole-genome single cell
2136 (license license:artistic2.0)))
2138 (define-public r-anf
2144 (uri (bioconductor-uri "ANF" version))
2147 "1fa2pbdapymrpz01ws0m2fbzf11d723x6rbsys29v06is57f5lpj"))))
2148 (properties `((upstream-name . "ANF")))
2149 (build-system r-build-system)
2156 (native-inputs (list r-knitr))
2157 (home-page "https://bioconductor.org/packages/ANF")
2158 (synopsis "Affinity network fusion for complex patient clustering")
2160 "The package @dfn{ANF}(Affinity Network Fusion) provides methods for affinity
2161 matrix construction and fusion as well as spectral clustering. This package is
2162 used for complex patient clustering by integrating multi-omic data through affinity
2164 (license license:gpl3)))
2166 (define-public r-annmap
2172 (uri (bioconductor-uri "annmap" version))
2175 "0ywqbb8jia7rrkzcsf6a11kqf8dnx96z8n8xw7067mahycykbixv"))))
2176 (properties `((upstream-name . "annmap")))
2177 (build-system r-build-system)
2189 (home-page "https://github.com/cruk-mi/annmap")
2191 "Genome annotation and visualisation for Affymetrix arrays and NGS analysis")
2193 "This package @code{annmap} provides annotation mappings for Affymetrix exon
2194 arrays and coordinate based queries to support deep sequencing data analysis.
2195 Database access is hidden behind the API which provides a set of functions such
2196 as @code{genesInRange()}, @code{geneToExon()}, @code{exonDetails()}, etc.
2197 Functions to plot gene architecture and BAM file data are also provided.")
2198 (license license:gpl2)))
2200 (define-public r-antiprofiles
2202 (name "r-antiprofiles")
2206 (uri (bioconductor-uri "antiProfiles" version))
2209 "1277kg5xpyb2yriyjy18p437q5lj22h4al7z7pygkzxzywxv9g40"))))
2210 (properties `((upstream-name . "antiProfiles")))
2211 (build-system r-build-system)
2215 (home-page "https://github.com/HCBravoLab/antiProfiles")
2216 (synopsis "Implementation of gene expression anti-profiles")
2218 "This package implements the gene expression anti-profiles method.
2219 Anti-profiles are a new approach for developing cancer genomic signatures that
2220 specifically take advantage of gene expression heterogeneity. They explicitly
2221 model increased gene expression variability in cancer to define robust and
2222 reproducible gene expression signatures capable of accurately distinguishing
2223 tumor samples from healthy controls.")
2224 (license license:artistic2.0)))
2226 (define-public r-biocversion
2228 (name "r-biocversion")
2233 (uri (bioconductor-uri "BiocVersion" version))
2236 "0rs4nyza4hqqk204d037gi013135wgfhx5asq2dsdjc9vk5nwzfn"))))
2237 (properties `((upstream-name . "BiocVersion")))
2238 (build-system r-build-system)
2239 (home-page "https://bioconductor.org/packages/BiocVersion/")
2240 (synopsis "Set the appropriate version of Bioconductor packages")
2242 "This package provides repository information for the appropriate version
2244 (license license:artistic2.0)))
2246 (define-public r-biocgenerics
2248 (name "r-biocgenerics")
2252 (uri (bioconductor-uri "BiocGenerics" version))
2255 "0iv9bnpw2hycndwbmjsszqfwrksz6dfr6qcz78jkssc9ldsgmdhc"))))
2257 `((upstream-name . "BiocGenerics")))
2258 (build-system r-build-system)
2259 (home-page "https://bioconductor.org/packages/BiocGenerics")
2260 (synopsis "S4 generic functions for Bioconductor")
2262 "This package provides S4 generic functions needed by many Bioconductor
2264 (license license:artistic2.0)))
2266 (define-public r-coverageview
2268 (name "r-coverageview")
2272 (uri (bioconductor-uri "CoverageView" version))
2275 "0mh66l4yh6rpd1r7qbqwh5jkklqyvpfiap0zcqhz9kimssm2pbbp"))))
2276 (build-system r-build-system)
2284 (home-page "https://bioconductor.org/packages/CoverageView/")
2285 (synopsis "Coverage visualization package for R")
2286 (description "This package provides a framework for the visualization of
2287 genome coverage profiles. It can be used for ChIP-seq experiments, but it can
2288 be also used for genome-wide nucleosome positioning experiments or other
2289 experiment types where it is important to have a framework in order to inspect
2290 how the coverage distributed across the genome.")
2291 (license license:artistic2.0)))
2293 (define-public r-cummerbund
2295 (name "r-cummerbund")
2299 (uri (bioconductor-uri "cummeRbund" version))
2302 "1p4anmi436zykp0ir307g75g23kj8b7shxg4r65qq6zdwflphm0q"))))
2303 (build-system r-build-system)
2315 (home-page "https://bioconductor.org/packages/cummeRbund/")
2316 (synopsis "Analyze Cufflinks high-throughput sequencing data")
2317 (description "This package allows for persistent storage, access,
2318 exploration, and manipulation of Cufflinks high-throughput sequencing
2319 data. In addition, provides numerous plotting functions for commonly
2320 used visualizations.")
2321 (license license:artistic2.0)))
2323 (define-public r-dearseq
2330 (uri (bioconductor-uri "dearseq" version))
2333 "1f144k5gsclcmsnlsbisr2mivk91dbkci83wx1kznw6i15p4cpj1"))))
2334 (build-system r-build-system)
2336 (list r-compquadform
2352 (home-page "https://github.com/borishejblum/dearseq")
2353 (synopsis "DEA for RNA-seq data through a robust variance component test")
2355 "This is a package for Differential Expression Analysis of RNA-seq data.
2356 It features a variance component score test accounting for data
2357 heteroscedasticity through precision weights. Perform both gene-wise and gene
2358 set analyses, and can deal with repeated or longitudinal data.")
2359 (license license:gpl2)))
2361 (define-public r-decipher
2367 (uri (bioconductor-uri "DECIPHER" version))
2370 "045q2bfzgq1yzhyrzvrhrnmlpka4gikrajxxwv05szksy5nvp7q5"))))
2371 (build-system r-build-system)
2379 (home-page "https://www.bioconductor.org/packages/DECIPHER/")
2380 (synopsis "Tools for deciphering and managing biological sequences")
2381 (description "This package provides a toolset for deciphering and managing
2382 biological sequences.")
2383 (license license:gpl3)))
2385 (define-public r-deconvr
2391 (uri (bioconductor-uri "deconvR" version))
2394 "091z3lncamscsvzj63zzbw7dr7vnkn0jwfkm5ljq4112w4rxgrm3"))))
2395 (properties `((upstream-name . "deconvR")))
2396 (build-system r-build-system)
2415 (native-inputs (list r-knitr))
2416 (home-page "https://github.com/BIMSBbioinfo/deconvR")
2417 (synopsis "Simulation and deconvolution of omic profiles")
2419 "This package provides a collection of functions designed for analyzing
2420 deconvolution of the bulk sample(s) using an atlas of reference omic signature
2421 profiles and a user-selected model. Users are given the option to create or
2422 extend a reference atlas and,also simulate the desired size of the bulk
2423 signature profile of the reference cell types. The package includes the
2424 cell-type-specific methylation atlas and, Illumina Epic B5 probe ids that can
2425 be used in deconvolution. Additionally, we included @code{BSmeth2Probe}, to
2426 make mapping WGBS data to their probe IDs easier.")
2427 (license license:artistic2.0)))
2429 (define-public r-decoupler
2431 (name "r-decoupler")
2436 (uri (bioconductor-uri "decoupleR" version))
2438 (base32 "0q1w8yw3bwx8ai5z8rw8lz97w4cplxijq93634hza2vgkig1ck9m"))))
2439 (properties `((upstream-name . "decoupleR")))
2440 (build-system r-build-system)
2453 (native-inputs (list r-knitr))
2454 (home-page "https://saezlab.github.io/decoupleR/")
2455 (synopsis "Computational methods to infer biological activities from omics data")
2457 "Many methods allow us to extract biological activities from omics data using
2458 information from prior knowledge resources, reducing the dimensionality for
2459 increased statistical power and better interpretability. decoupleR is a
2460 Bioconductor package containing different statistical methods to extract these
2461 signatures within a unified framework. decoupleR allows the user to flexibly
2462 test any method with any resource. It incorporates methods that take into
2463 account the sign and weight of network interactions. decoupleR can be used
2464 with any omic, as long as its features can be linked to a biological process
2465 based on prior knowledge. For example, in transcriptomics gene sets regulated
2466 by a transcription factor, or in phospho-proteomics phosphosites that are
2467 targeted by a kinase.")
2468 (license license:gpl3)))
2470 (define-public r-deepsnv
2476 (uri (bioconductor-uri "deepSNV" version))
2479 "0bgj1grv3a5bqhcdsw445x49kl3pz367svy6fnrzfsk9bmj46kgn"))))
2480 (properties `((upstream-name . "deepSNV")))
2481 (build-system r-build-system)
2487 r-summarizedexperiment
2492 (home-page "https://github.com/gerstung-lab/deepSNV/")
2493 (synopsis "Detection of subclonal SNVs in deep sequencing data")
2495 "This package provides quantitative variant callers for detecting
2496 subclonal mutations in ultra-deep (>=100x coverage) sequencing experiments.
2497 The deepSNV algorithm is used for a comparative setup with a control experiment
2498 of the same loci and uses a beta-binomial model and a likelihood ratio test to
2499 discriminate sequencing errors and subclonal SNVs. The shearwater algorithm
2500 computes a Bayes classifier based on a beta-binomial model for variant calling
2501 with multiple samples for precisely estimating model parameters - such as local
2502 error rates and dispersion - and prior knowledge, e.g. from variation data
2503 bases such as COSMIC.")
2504 (license license:gpl3)))
2506 (define-public r-delayedarray
2508 (name "r-delayedarray")
2512 (uri (bioconductor-uri "DelayedArray" version))
2515 "11id63qza9dxl1364gllqafxmx25a0q22jv5q8h709bgc3f0grqy"))))
2517 `((upstream-name . "DelayedArray")))
2518 (build-system r-build-system)
2520 (list r-biocgenerics r-s4vectors r-iranges r-matrix
2524 (home-page "https://bioconductor.org/packages/DelayedArray")
2525 (synopsis "Delayed operations on array-like objects")
2527 "Wrapping an array-like object (typically an on-disk object) in a
2528 @code{DelayedArray} object allows one to perform common array operations on it
2529 without loading the object in memory. In order to reduce memory usage and
2530 optimize performance, operations on the object are either delayed or executed
2531 using a block processing mechanism. Note that this also works on in-memory
2532 array-like objects like @code{DataFrame} objects (typically with Rle columns),
2533 @code{Matrix} objects, and ordinary arrays and data frames.")
2534 (license license:artistic2.0)))
2536 (define-public r-derfinderhelper
2538 (name "r-derfinderhelper")
2543 (uri (bioconductor-uri "derfinderHelper" version))
2545 (base32 "0r7zbx5bfmh5cjs12y8d9qwz53nz340gdy3sx7zcn4rzn7rpslp5"))))
2546 (properties `((upstream-name . "derfinderHelper")))
2547 (build-system r-build-system)
2549 (list r-iranges r-matrix r-s4vectors))
2552 (home-page "https://github.com/leekgroup/derfinderHelper")
2553 (synopsis "Helper for derfinder")
2555 "This package speeds up the derfinder package when using multiple cores.
2556 It is particularly useful when using BiocParallel and it helps reduce the time
2557 spent loading the full derfinder package when running the F-statistics
2558 calculation in parallel.")
2559 (license license:artistic2.0)))
2561 (define-public r-drimseq
2568 (uri (bioconductor-uri "DRIMSeq" version))
2570 (base32 "1dph483ij43ayw0z5dbnp6gwp53ka7k5si1hp3miac7z8dqzv94l"))))
2571 (properties `((upstream-name . "DRIMSeq")))
2572 (build-system r-build-system)
2574 (list r-biocgenerics
2584 (native-inputs (list r-knitr))
2585 (home-page "https://bioconductor.org/packages/DRIMSeq")
2586 (synopsis "Differential transcript usage and tuQTL analyses with Dirichlet-multinomial model in RNA-seq")
2588 "The package provides two frameworks. One for the differential
2589 transcript usage analysis between different conditions and one for the tuQTL
2590 analysis. Both are based on modeling the counts of genomic features (i.e.,
2591 transcripts) with the Dirichlet-multinomial distribution. The package also
2592 makes available functions for visualization and exploration of the data and
2594 (license license:gpl3+)))
2596 (define-public r-bluster
2602 (uri (bioconductor-uri "bluster" version))
2605 "1g496yc7mdhshf6r0n8xhj7ax936ia5z2cx72lqyk2vzzzl5c4v8"))))
2606 (properties `((upstream-name . "bluster")))
2607 (build-system r-build-system)
2609 (list r-biocneighbors
2618 (home-page "https://bioconductor.org/packages/bluster")
2619 (synopsis "Clustering algorithms for Bioconductor")
2620 (description"This package wraps common clustering algorithms in an easily
2621 extended S4 framework. Backends are implemented for hierarchical, k-means
2622 and graph-based clustering. Several utilities are also provided to compare
2623 and evaluate clustering results.")
2624 (license license:gpl3)))
2626 (define-public r-ideoviz
2632 (uri (bioconductor-uri "IdeoViz" version))
2635 "1wwh3ifdijhpm58lw7cmnx084xwfxnc7i0206w8rhrjnvnq6ljh3"))))
2636 (build-system r-build-system)
2644 (home-page "https://bioconductor.org/packages/IdeoViz/")
2645 (synopsis "Plots data along a chromosomal ideogram")
2646 (description "This package provides functions to plot data associated with
2647 arbitrary genomic intervals along chromosomal ideogram.")
2648 (license license:gpl2)))
2650 (define-public r-iranges
2656 (uri (bioconductor-uri "IRanges" version))
2659 "0hfx5n0b4pqrrc1w2dik596803ly8ffnxfs768iy5l5kr8wwyc8k"))))
2661 `((upstream-name . "IRanges")))
2662 (build-system r-build-system)
2664 (list r-biocgenerics r-s4vectors))
2665 (home-page "https://bioconductor.org/packages/IRanges")
2666 (synopsis "Infrastructure for manipulating intervals on sequences")
2668 "This package provides efficient low-level and highly reusable S4 classes
2669 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
2670 generally, data that can be organized sequentially (formally defined as
2671 @code{Vector} objects), as well as views on these @code{Vector} objects.
2672 Efficient list-like classes are also provided for storing big collections of
2673 instances of the basic classes. All classes in the package use consistent
2674 naming and share the same rich and consistent \"Vector API\" as much as
2676 (license license:artistic2.0)))
2678 (define-public r-isoformswitchanalyzer
2680 (name "r-isoformswitchanalyzer")
2685 (uri (bioconductor-uri "IsoformSwitchAnalyzeR" version))
2687 (base32 "0n1gb9azxa1mxpsqvw3i3kf72f45nyjj1kgwwrzhd88n3g63lvkd"))))
2688 (properties `((upstream-name . "IsoformSwitchAnalyzeR")))
2689 (build-system r-build-system)
2722 (home-page "https://bioconductor.org/packages/IsoformSwitchAnalyzeR/")
2723 (synopsis "Analyze alternative splicing in RNA-seq data")
2725 "This is a package for the analysis of alternative splicing and isoform
2726 switches with predicted functional consequences (e.g. gain/loss of protein
2727 domains etc.) from quantification of all types of RNASeq by tools such as
2728 Kallisto, Salmon, StringTie, Cufflinks/Cuffdiff etc.")
2729 (license license:gpl2+)))
2731 ;; This is a CRAN package, but it depends on r-biobase and r-limma from Bioconductor.
2732 (define-public r-absfiltergsea
2734 (name "r-absfiltergsea")
2739 (uri (cran-uri "AbsFilterGSEA" version))
2741 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
2742 (properties `((upstream-name . "AbsFilterGSEA")))
2743 (build-system r-build-system)
2745 (list r-biobase r-deseq r-limma r-rcpp r-rcpparmadillo))
2746 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
2747 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
2749 "This package provides a function that performs gene-permuting of a gene-set
2750 enrichment analysis (GSEA) calculation with or without the absolute filtering.
2751 Without filtering, users can perform (original) two-tailed or one-tailed
2753 (license license:gpl2)))
2755 ;; This is a CRAN package, but it depends on r-biobase from Bioconductor.
2756 (define-public r-bisquerna
2758 (name "r-bisquerna")
2762 (uri (cran-uri "BisqueRNA" version))
2765 "0p3p5lp69gri7vs6qfpm7br4ksbs4l7clm4nj8ki99wpqiqni23n"))))
2766 (properties `((upstream-name . "BisqueRNA")))
2767 (build-system r-build-system)
2769 (list r-biobase r-limsolve))
2772 (home-page "https://www.biorxiv.org/content/10.1101/669911v1")
2773 (synopsis "Decomposition of bulk expression with single-cell sequencing")
2774 (description "This package provides tools to accurately estimate cell type
2775 abundances from heterogeneous bulk expression. A reference-based method
2776 utilizes single-cell information to generate a signature matrix and
2777 transformation of bulk expression for accurate regression based estimates.
2778 A marker-based method utilizes known cell-specific marker genes to measure
2779 relative abundances across samples.")
2780 (license license:gpl3)))
2782 ;; This is a CRAN package, but it depends on r-bsgenome-hsapiens-ucsc-hg19
2783 ;; from Bioconductor.
2784 (define-public r-deconstructsigs
2786 (name "r-deconstructsigs")
2790 (uri (cran-uri "deconstructSigs" version))
2793 "014x0nb23jb98666kaav2phkvmkr38pi38jv0dqd4jv7zp0gdf1a"))))
2795 `((upstream-name . "deconstructSigs")))
2796 (build-system r-build-system)
2798 (list r-bsgenome r-bsgenome-hsapiens-ucsc-hg19 r-genomeinfodb
2800 (home-page "https://github.com/raerose01/deconstructSigs")
2801 (synopsis "Identifies signatures present in a tumor sample")
2802 (description "This package takes sample information in the form of the
2803 fraction of mutations in each of 96 trinucleotide contexts and identifies
2804 the weighted combination of published signatures that, when summed, most
2805 closely reconstructs the mutational profile.")
2806 (license license:gpl2+)))
2808 ;; This is a CRAN package, but it depends on Bioconductor packages.
2809 (define-public r-jetset
2816 (uri (cran-uri "jetset" version))
2818 (base32 "0c99h5npsv2gf5d59s4qhkaqmjhbwa3prcykk24wzhnpfq6y6xhp"))))
2819 (properties `((upstream-name . "jetset")))
2820 (build-system r-build-system)
2821 (propagated-inputs (list r-annotationdbi r-org-hs-eg-db))
2822 (home-page "http://www.cbs.dtu.dk/biotools/jetset/")
2823 (synopsis "One-to-one gene-probeset mapping for Affymetrix human microarrays")
2825 "This package provides a one-to-one mapping from gene to \"best\" probe
2826 set for four Affymetrix human gene expression microarrays: hgu95av2, hgu133a,
2827 hgu133plus2, and u133x3p. On Affymetrix gene expression microarrays, a single
2828 gene may be measured by multiple probe sets. This can present a mild
2829 conundrum when attempting to evaluate a gene \"signature\" that is defined by
2830 gene names rather than by specific probe sets. This package also includes the
2831 pre-calculated probe set quality scores that were used to define the
2833 (license license:artistic2.0)))
2835 ;; This is a CRAN package, but it depends on Bioconductor packages.
2836 (define-public r-nmf
2843 (uri (cran-uri "NMF" version))
2846 "14yxra6in5c1md5nr75y8cdmh9pg0lxqabqflvlhgg1vbg9i2628"))))
2847 (properties `((upstream-name . "NMF")))
2848 (build-system r-build-system)
2853 r-bigmemory ; suggested
2854 r-synchronicity ; suggested
2869 (home-page "http://renozao.github.io/NMF")
2870 (synopsis "Algorithms and framework for nonnegative matrix factorization")
2872 "This package provides a framework to perform Non-negative Matrix
2873 Factorization (NMF). The package implements a set of already published
2874 algorithms and seeding methods, and provides a framework to test, develop and
2875 plug new or custom algorithms. Most of the built-in algorithms have been
2876 optimized in C++, and the main interface function provides an easy way of
2877 performing parallel computations on multicore machines.")
2878 (license license:gpl2+)))
2880 (define-public r-affy
2887 (uri (bioconductor-uri "affy" version))
2890 "02l77y4d4m4jwgkb3jdaskv6shmba5292whp0i29mg9asxv4rdc7"))))
2891 (build-system r-build-system)
2901 (home-page "https://bioconductor.org/packages/affy")
2902 (synopsis "Methods for affymetrix oligonucleotide arrays")
2904 "This package contains functions for exploratory oligonucleotide array
2906 (license license:lgpl2.0+)))
2908 (define-public r-affycomp
2915 (uri (bioconductor-uri "affycomp" version))
2918 "0aq5p56sqpvba0yhgd75302s9bazchh1izgymng6cpb78y5wfpj0"))))
2919 (properties `((upstream-name . "affycomp")))
2920 (build-system r-build-system)
2921 (propagated-inputs (list r-biobase))
2922 (home-page "https://bioconductor.org/packages/affycomp/")
2923 (synopsis "Graphics toolbox for assessment of Affymetrix expression measures")
2925 "The package contains functions that can be used to compare expression
2926 measures for Affymetrix Oligonucleotide Arrays.")
2927 (license license:gpl2+)))
2929 (define-public r-affycompatible
2931 (name "r-affycompatible")
2936 (uri (bioconductor-uri "AffyCompatible" version))
2939 "0x3lj1jgqq67389rzfklah5p878ns9b4fpdpz455m2gq9sk7qsda"))))
2941 `((upstream-name . "AffyCompatible")))
2942 (build-system r-build-system)
2946 `(modify-phases %standard-phases
2947 (add-after 'unpack 'make-reproducible
2949 ;; Order DTD elements before generating R code from them.
2950 (substitute* "R/methods-AffyCompatible.R"
2953 elements <- dtd$elements
2954 ordered <- elements[order(names(elements))]\n"))
2955 (("elt in dtd\\$elements")
2957 ;; Use a predictable directory name for code generation.
2958 (mkdir-p "/tmp/NetAffxResourcePrototype")
2959 (substitute* "R/DataClasses.R"
2960 (("directory=tempdir\\(\\)")
2961 "directory=\"/tmp/NetAffxResourcePrototype\"")))))))
2963 (list r-biostrings r-rcurl r-xml))
2964 (home-page "https://bioconductor.org/packages/AffyCompatible/")
2965 (synopsis "Work with Affymetrix GeneChip files")
2967 "This package provides an interface to Affymetrix chip annotation and
2968 sample attribute files. The package allows an easy way for users to download
2969 and manage local data bases of Affynmetrix NetAffx annotation files. It also
2970 provides access to @dfn{GeneChip Operating System} (GCOS) and @dfn{GeneChip
2971 Command Console} (AGCC)-compatible sample annotation files.")
2972 (license license:artistic2.0)))
2974 (define-public r-affycontam
2976 (name "r-affycontam")
2981 (uri (bioconductor-uri "affyContam" version))
2984 "1pyd4rj6pp139kvhh97whi4afvx029w5lglr4mnscw7m3f618v0p"))))
2985 (properties `((upstream-name . "affyContam")))
2986 (build-system r-build-system)
2988 (list r-affy r-affydata r-biobase))
2989 (home-page "https://bioconductor.org/packages/affyContam/")
2990 (synopsis "Structured corruption of Affymetrix CEL file data")
2992 "Microarray quality assessment is a major concern of microarray analysts.
2993 This package provides some simple approaches to in silico creation of quality
2994 problems in CEL-level data to help evaluate performance of quality metrics.")
2995 (license license:artistic2.0)))
2997 (define-public r-affycoretools
2999 (name "r-affycoretools")
3004 (uri (bioconductor-uri "affycoretools" version))
3007 "05x64hy5jpmg973biwq4q9gzy1n0iqc0pxrix1f6bri1w6vil3ww"))))
3008 (properties `((upstream-name . "affycoretools")))
3009 (build-system r-build-system)
3032 (home-page "https://bioconductor.org/packages/affycoretools/")
3033 (synopsis "Functions for analyses with Affymetrix GeneChips")
3035 "This package provides various wrapper functions that have been written
3036 to streamline the more common analyses that a Biostatistician might see.")
3037 (license license:artistic2.0)))
3039 (define-public r-affyio
3046 (uri (bioconductor-uri "affyio" version))
3049 "19cw82qvzkz6vh2gm302y7digsf6xif7c9l2q9s6lkx2yflqpgfp"))))
3050 (build-system r-build-system)
3055 (home-page "https://github.com/bmbolstad/affyio")
3056 (synopsis "Tools for parsing Affymetrix data files")
3058 "This package provides routines for parsing Affymetrix data files based
3059 upon file format information. The primary focus is on accessing the CEL and
3061 (license license:lgpl2.0+)))
3063 (define-public r-affxparser
3065 (name "r-affxparser")
3070 (uri (bioconductor-uri "affxparser" version))
3073 "16x92gwsy7zdyz4md4cw847xn2ymqd6gqsn0rlr2nnf3qmnjnils"))))
3074 (properties `((upstream-name . "affxparser")))
3075 (build-system r-build-system)
3076 (home-page "https://github.com/HenrikBengtsson/affxparser")
3077 (synopsis "Affymetrix File Parsing SDK")
3079 "This is a package for parsing Affymetrix files (CDF, CEL, CHP, BPMAP,
3080 BAR). It provides methods for fast and memory efficient parsing of Affymetrix
3081 files using the Affymetrix' Fusion SDK. Both ASCII- and binary-based files
3082 are supported. Currently, there are methods for reading @dfn{chip definition
3083 file} (CDF) and a @dfn{cell intensity file} (CEL). These files can be read
3084 either in full or in part. For example, probe signals from a few probesets
3085 can be extracted very quickly from a set of CEL files into a convenient list
3087 ;; The Fusion SDK contains files under GPLv2 and LGPLv2.1. The R code is
3089 (license (list license:lgpl2.0+ license:lgpl2.1 license:gpl2))))
3091 (define-public r-annotate
3098 (uri (bioconductor-uri "annotate" version))
3101 "0x6vddpiw2g713vicf70198x8dlrwf36p8jjygdsfnl56ls5bh2g"))))
3102 (build-system r-build-system)
3104 (list r-annotationdbi
3112 "https://bioconductor.org/packages/annotate")
3113 (synopsis "Annotation for microarrays")
3114 (description "This package provides R environments for the annotation of
3116 (license license:artistic2.0)))
3118 (define-public r-annotationdbi
3120 (name "r-annotationdbi")
3124 (uri (bioconductor-uri "AnnotationDbi" version))
3127 "15cwy7lic89jwl3dr7j4pb5bx457jdpvzvylr71624s0p0j9rgwn"))))
3129 `((upstream-name . "AnnotationDbi")))
3130 (build-system r-build-system)
3141 (home-page "https://bioconductor.org/packages/AnnotationDbi")
3142 (synopsis "Annotation database interface")
3144 "This package provides user interface and database connection code for
3145 annotation data packages using SQLite data storage.")
3146 (license license:artistic2.0)))
3148 (define-public r-annotationfilter
3150 (name "r-annotationfilter")
3154 (uri (bioconductor-uri "AnnotationFilter" version))
3157 "082lpcd6yr2nkxndlck2wqqd3nfdx7lnpw8barxgv41q4l7v4ald"))))
3159 `((upstream-name . "AnnotationFilter")))
3160 (build-system r-build-system)
3162 (list r-genomicranges r-lazyeval))
3165 (home-page "https://github.com/Bioconductor/AnnotationFilter")
3166 (synopsis "Facilities for filtering Bioconductor annotation resources")
3168 "This package provides classes and other infrastructure to implement
3169 filters for manipulating Bioconductor annotation resources. The filters are
3170 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
3171 (license license:artistic2.0)))
3173 (define-public r-annotationforge
3175 (name "r-annotationforge")
3180 (uri (bioconductor-uri "AnnotationForge" version))
3183 "18rcfadxdaggyjj3rj17nbvgddlqs6zlr5jmq9a02kin59czvzz8"))))
3185 `((upstream-name . "AnnotationForge")))
3186 (build-system r-build-system)
3188 (list r-annotationdbi
3198 (home-page "https://bioconductor.org/packages/AnnotationForge")
3199 (synopsis "Code for building annotation database packages")
3201 "This package provides code for generating Annotation packages and their
3202 databases. Packages produced are intended to be used with AnnotationDbi.")
3203 (license license:artistic2.0)))
3205 (define-public r-annotationhub
3207 (name "r-annotationhub")
3212 (uri (bioconductor-uri "AnnotationHub" version))
3215 "03dmbx43rsv9xv94lk12gpraq47ryc13jijwma3q05hl9wn8xjxs"))))
3216 (properties `((upstream-name . "AnnotationHub")))
3217 (build-system r-build-system)
3219 (list r-annotationdbi
3227 r-interactivedisplaybase
3234 (home-page "https://bioconductor.org/packages/AnnotationHub")
3235 (synopsis "Client to access AnnotationHub resources")
3237 "This package provides a client for the Bioconductor AnnotationHub web
3238 resource. The AnnotationHub web resource provides a central location where
3239 genomic files (e.g. VCF, bed, wig) and other resources from standard
3240 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
3241 metadata about each resource, e.g., a textual description, tags, and date of
3242 modification. The client creates and manages a local cache of files retrieved
3243 by the user, helping with quick and reproducible access.")
3244 (license license:artistic2.0)))
3246 (define-public r-aroma-light
3248 (name "r-aroma-light")
3253 (uri (bioconductor-uri "aroma.light" version))
3256 "1240v9wvsf205g998ms19hncki8g6shidg09dy5np9pqpiix4vys"))))
3257 (properties `((upstream-name . "aroma.light")))
3258 (build-system r-build-system)
3260 (list r-matrixstats r-r-methodss3 r-r-oo r-r-utils))
3261 (home-page "https://github.com/HenrikBengtsson/aroma.light")
3262 (synopsis "Methods for normalization and visualization of microarray data")
3264 "This package provides methods for microarray analysis that take basic
3265 data types such as matrices and lists of vectors. These methods can be used
3266 standalone, be utilized in other packages, or be wrapped up in higher-level
3268 (license license:gpl2+)))
3270 (define-public r-bamsignals
3272 (name "r-bamsignals")
3277 (uri (bioconductor-uri "bamsignals" version))
3280 "0ywbxq829hclhr5bb6p77rspxvfs580zlwd2f5kr3an6rdgyx9ky"))))
3281 (build-system r-build-system)
3283 (list r-biocgenerics
3291 (home-page "https://bioconductor.org/packages/bamsignals")
3292 (synopsis "Extract read count signals from bam files")
3294 "This package efficiently obtains count vectors from indexed bam
3295 files. It counts the number of nucleotide sequence reads in given genomic
3296 ranges and it computes reads profiles and coverage profiles. It also handles
3298 (license license:gpl2+)))
3300 (define-public r-biobase
3306 (uri (bioconductor-uri "Biobase" version))
3309 "1mnxky78an079p60427cjvk4fzilp0xzy6b85fq274qvdcrz8jbv"))))
3311 `((upstream-name . "Biobase")))
3312 (build-system r-build-system)
3314 (list r-biocgenerics))
3315 (home-page "https://bioconductor.org/packages/Biobase")
3316 (synopsis "Base functions for Bioconductor")
3318 "This package provides functions that are needed by many other packages
3319 on Bioconductor or which replace R functions.")
3320 (license license:artistic2.0)))
3322 (define-public r-biomart
3328 (uri (bioconductor-uri "biomaRt" version))
3331 "0yn3kanyrplc89a900xiz33nw1v23mkljvd5isizgs8gzvwzf8xg"))))
3333 `((upstream-name . "biomaRt")))
3334 (build-system r-build-system)
3336 (list r-annotationdbi
3347 (home-page "https://bioconductor.org/packages/biomaRt")
3348 (synopsis "Interface to BioMart databases")
3350 "biomaRt provides an interface to a growing collection of databases
3351 implementing the @url{BioMart software suite, http://www.biomart.org}. The
3352 package enables retrieval of large amounts of data in a uniform way without
3353 the need to know the underlying database schemas or write complex SQL queries.
3354 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
3355 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
3356 users direct access to a diverse set of data and enable a wide range of
3357 powerful online queries from gene annotation to database mining.")
3358 (license license:artistic2.0)))
3360 (define-public r-biocparallel
3362 (name "r-biocparallel")
3366 (uri (bioconductor-uri "BiocParallel" version))
3369 "1rs3wmasl9mx7f399iclvm0bnvggvjj2a88zbi294r5m8wxqlc92"))))
3371 `((upstream-name . "BiocParallel")))
3372 (build-system r-build-system)
3375 (modify-phases %standard-phases
3376 (add-after 'unpack 'make-reproducible
3378 ;; Remove generated documentation.
3379 (for-each delete-file
3380 '("inst/doc/BiocParallel_BatchtoolsParam.pdf"
3381 "inst/doc/Introduction_To_BiocParallel.pdf"
3382 "inst/doc/Errors_Logs_And_Debugging.pdf"
3383 "inst/doc/BiocParallel_BatchtoolsParam.R"
3384 "inst/doc/Introduction_To_BiocParallel.R"
3385 "inst/doc/Errors_Logs_And_Debugging.R"))
3387 ;; Remove time-dependent macro
3388 (substitute* '("inst/doc/BiocParallel_BatchtoolsParam.Rnw"
3389 "inst/doc/Introduction_To_BiocParallel.Rnw"
3390 "inst/doc/Errors_Logs_And_Debugging.Rnw"
3391 "vignettes/BiocParallel_BatchtoolsParam.Rnw"
3392 "vignettes/Introduction_To_BiocParallel.Rnw"
3393 "vignettes/Errors_Logs_And_Debugging.Rnw")
3394 (("\\today") "later"))
3396 ;; Initialize the random number generator seed when building.
3397 (substitute* "R/rng.R"
3398 (("\"L'Ecuyer-CMRG\"\\)" m)
3400 m "; if (!is.na(Sys.getenv(\"SOURCE_DATE_EPOCH\"))) {set.seed(100)}\n"))))))))
3402 (list r-bh r-codetools r-futile-logger r-snow))
3405 (home-page "https://bioconductor.org/packages/BiocParallel")
3406 (synopsis "Bioconductor facilities for parallel evaluation")
3408 "This package provides modified versions and novel implementation of
3409 functions for parallel evaluation, tailored to use with Bioconductor
3411 (license (list license:gpl2+ license:gpl3+))))
3413 (define-public r-biostrings
3415 (name "r-biostrings")
3419 (uri (bioconductor-uri "Biostrings" version))
3422 "1sz52hz89l9w2y2bvyis7kczslk1xnskls9l2bn1s3dhnjzdzhg8"))))
3424 `((upstream-name . "Biostrings")))
3425 (build-system r-build-system)
3427 (list r-biocgenerics
3433 (home-page "https://bioconductor.org/packages/Biostrings")
3434 (synopsis "String objects and algorithms for biological sequences")
3436 "This package provides memory efficient string containers, string
3437 matching algorithms, and other utilities, for fast manipulation of large
3438 biological sequences or sets of sequences.")
3439 (license license:artistic2.0)))
3441 (define-public r-biovizbase
3443 (name "r-biovizbase")
3448 (uri (bioconductor-uri "biovizBase" version))
3451 "1ffzf7yvl47l8v8a50m8g9q33hgwvxg4fcm8ld2yy8hd2zl86zyd"))))
3452 (properties `((upstream-name . "biovizBase")))
3453 (build-system r-build-system)
3455 (list r-annotationdbi
3472 r-summarizedexperiment
3473 r-variantannotation))
3474 (home-page "https://bioconductor.org/packages/biovizBase")
3475 (synopsis "Basic graphic utilities for visualization of genomic data")
3477 "The biovizBase package is designed to provide a set of utilities, color
3478 schemes and conventions for genomic data. It serves as the base for various
3479 high-level packages for biological data visualization. This saves development
3480 effort and encourages consistency.")
3481 (license license:artistic2.0)))
3483 (define-public r-bsgenome
3489 (uri (bioconductor-uri "BSgenome" version))
3492 "17gqrmaf6xxghgrzcansl9gfw3ghkrqp87swlnwgyghqvflr5qxc"))))
3494 `((upstream-name . "BSgenome")))
3495 (build-system r-build-system)
3497 (list r-biocgenerics
3507 (home-page "https://bioconductor.org/packages/BSgenome")
3508 (synopsis "Infrastructure for Biostrings-based genome data packages")
3510 "This package provides infrastructure shared by all Biostrings-based
3511 genome data packages and support for efficient SNP representation.")
3512 (license license:artistic2.0)))
3514 (define-public r-category
3521 (uri (bioconductor-uri "Category" version))
3524 "07js03cfdd6gzbzw14iavlqxynfcqszh988v6k1a3h074wxiivqd"))))
3525 (properties `((upstream-name . "Category")))
3526 (build-system r-build-system)
3538 (home-page "https://bioconductor.org/packages/Category")
3539 (synopsis "Category analysis")
3541 "This package provides a collection of tools for performing category
3543 (license license:artistic2.0)))
3545 (define-public r-chipseeker
3547 (name "r-chipseeker")
3551 (uri (bioconductor-uri "ChIPseeker" version))
3554 "001f85nk4myk9vgs05inlj2dfby4802p1iyzkfqg332yk52gsbl7"))))
3555 (build-system r-build-system)
3559 (list r-annotationdbi
3577 r-txdb-hsapiens-ucsc-hg19-knowngene))
3578 (home-page "https://www.bioconductor.org/packages/ChIPseeker/")
3579 (synopsis "ChIPseeker for ChIP peak annotation, comparison, and visualization")
3580 (description "This package implements functions to retrieve the nearest
3581 genes around the peak, annotate genomic region of the peak, statstical methods
3582 for estimate the significance of overlap among ChIP peak data sets, and
3583 incorporate GEO database for user to compare the own dataset with those
3584 deposited in database. The comparison can be used to infer cooperative
3585 regulation and thus can be used to generate hypotheses. Several visualization
3586 functions are implemented to summarize the coverage of the peak experiment,
3587 average profile and heatmap of peaks binding to TSS regions, genomic
3588 annotation, distance to TSS, and overlap of peaks or genes.")
3589 (license license:artistic2.0)))
3591 (define-public r-chipseq
3598 (uri (bioconductor-uri "chipseq" version))
3601 "1vh0hvgnw7ykj401v1q807sl14s4nixp1d8xbm41n01q6w8x834i"))))
3602 (build-system r-build-system)
3604 (list r-biocgenerics
3610 (home-page "https://bioconductor.org/packages/chipseq")
3611 (synopsis "Package for analyzing ChIPseq data")
3613 "This package provides tools for processing short read data from ChIPseq
3615 (license license:artistic2.0)))
3617 (define-public r-complexheatmap
3619 (name "r-complexheatmap")
3624 (uri (bioconductor-uri "ComplexHeatmap" version))
3627 "15b49vlkl89prcw70mlw066z0gxhs26x8dpfn6qr3gz7hihygs65"))))
3629 `((upstream-name . "ComplexHeatmap")))
3630 (build-system r-build-system)
3648 "https://github.com/jokergoo/ComplexHeatmap")
3649 (synopsis "Making Complex Heatmaps")
3651 "Complex heatmaps are efficient to visualize associations between
3652 different sources of data sets and reveal potential structures. This package
3653 provides a highly flexible way to arrange multiple heatmaps and supports
3654 self-defined annotation graphics.")
3655 (license license:gpl2+)))
3657 (define-public r-copywriter
3659 (name "r-copywriter")
3664 (uri (bioconductor-uri "CopywriteR" version))
3667 "1k11kvam96hpg71hz2n9cfzizmb7d1bmq5zfvm34s7fn09is60xb"))))
3668 (properties `((upstream-name . "CopywriteR")))
3669 (build-system r-build-system)
3671 (list r-biocparallel
3685 (home-page "https://github.com/PeeperLab/CopywriteR")
3686 (synopsis "Copy number information from targeted sequencing")
3688 "CopywriteR extracts DNA copy number information from targeted sequencing
3689 by utilizing off-target reads. It allows for extracting uniformly distributed
3690 copy number information, can be used without reference, and can be applied to
3691 sequencing data obtained from various techniques including chromatin
3692 immunoprecipitation and target enrichment on small gene panels. Thereby,
3693 CopywriteR constitutes a widely applicable alternative to available copy
3694 number detection tools.")
3695 (license license:gpl2)))
3697 (define-public r-deseq
3704 (uri (bioconductor-uri "DESeq" version))
3707 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
3708 (properties `((upstream-name . "DESeq")))
3709 (build-system r-build-system)
3719 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
3720 (synopsis "Differential gene expression analysis")
3722 "This package provides tools for estimating variance-mean dependence in
3723 count data from high-throughput genetic sequencing assays and for testing for
3724 differential expression based on a model using the negative binomial
3726 (license license:gpl3+)))
3728 (define-public r-deseq2
3735 (uri (bioconductor-uri "DESeq2" version))
3738 "06mvb0jqn2fg96wfwspv0kzpa8xpimzaldrcy8m2d4yk76xwsdr7"))))
3739 (properties `((upstream-name . "DESeq2")))
3740 (build-system r-build-system)
3754 r-summarizedexperiment))
3757 (home-page "https://bioconductor.org/packages/DESeq2")
3758 (synopsis "Differential gene expression analysis")
3760 "This package provides functions to estimate variance-mean dependence in
3761 count data from high-throughput nucleotide sequencing assays and test for
3762 differential expression based on a model using the negative binomial
3764 (license license:lgpl3+)))
3766 (define-public r-dexseq
3773 (uri (bioconductor-uri "DEXSeq" version))
3776 "1dzx9mvm8pvcrwr88rin3flnpmzp3vq8mvspx9s8virqhv1102am"))))
3777 (properties `((upstream-name . "DEXSeq")))
3778 (build-system r-build-system)
3780 (list r-annotationdbi
3796 r-summarizedexperiment))
3799 (home-page "https://bioconductor.org/packages/DEXSeq")
3800 (synopsis "Inference of differential exon usage in RNA-Seq")
3802 "This package is focused on finding differential exon usage using RNA-seq
3803 exon counts between samples with different experimental designs. It provides
3804 functions that allows the user to make the necessary statistical tests based
3805 on a model that uses the negative binomial distribution to estimate the
3806 variance between biological replicates and generalized linear models for
3807 testing. The package also provides functions for the visualization and
3808 exploration of the results.")
3809 (license license:gpl3+)))
3811 (define-public r-diffcyt
3818 (uri (bioconductor-uri "diffcyt" version))
3820 (base32 "0mysylzmg24g7lm1xan4yklzqmskfgh53j6vjcz2gzakz5rq3rdb"))))
3821 (properties `((upstream-name . "diffcyt")))
3822 (build-system r-build-system)
3836 r-summarizedexperiment
3838 (native-inputs (list r-knitr))
3839 (home-page "https://github.com/lmweber/diffcyt")
3840 (synopsis "Differential discovery in high-dimensional cytometry")
3842 "This package provides statistical methods for differential discovery
3843 analyses in high-dimensional cytometry data (including flow cytometry, mass
3844 cytometry or CyTOF, and oligonucleotide-tagged cytometry), based on a
3845 combination of high-resolution clustering and empirical Bayes moderated tests
3846 adapted from transcriptomics.")
3847 (license license:expat)))
3849 (define-public r-dirichletmultinomial
3851 (name "r-dirichletmultinomial")
3856 (uri (bioconductor-uri "DirichletMultinomial" version))
3859 "15l0h2qz80lmrm5rva3v7lkgddn42igyxxwims57zwpwyhrk9bmx"))))
3861 `((upstream-name . "DirichletMultinomial")))
3862 (build-system r-build-system)
3866 (list r-biocgenerics r-iranges r-s4vectors))
3867 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
3868 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
3870 "Dirichlet-multinomial mixture models can be used to describe variability
3871 in microbial metagenomic data. This package is an interface to code
3872 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
3874 (license license:lgpl3)))
3876 (define-public r-dittoseq
3882 (uri (bioconductor-uri "dittoSeq" version))
3885 "0vi0hcyffaxp6yxsrq95bdlrhr85dvbqm9c7rg6a6blkfgwhlzb4"))))
3886 (properties `((upstream-name . "dittoSeq")))
3887 (build-system r-build-system)
3898 r-singlecellexperiment
3899 r-summarizedexperiment))
3900 (native-inputs (list r-knitr))
3901 (home-page "https://bioconductor.org/packages/dittoSeq")
3902 (synopsis "Single-cell and bulk RNA sequencing visualization")
3904 "This package provides a universal, user friendly, single-cell and bulk RNA
3905 sequencing visualization toolkit that allows highly customizable creation of
3906 color blindness friendly, publication-quality figures. dittoSeq accepts both
3907 SingleCellExperiment (SCE) and Seurat objects, as well as the import and
3908 usage, via conversion to an SCE, of SummarizedExperiment or DGEList bulk data.
3909 Visualizations include dimensionality reduction plots, heatmaps, scatterplots,
3910 percent composition or expression across groups, and more. Customizations
3911 range from size and title adjustments to automatic generation of annotations
3912 for heatmaps, overlay of trajectory analysis onto any dimensionality reduciton
3913 plot, hidden data overlay upon cursor hovering via ggplotly conversion, and
3914 many more. All with simple, discrete inputs. Color blindness friendliness is
3915 powered by legend adjustments (enlarged keys), and by allowing the use of
3916 shapes or letter-overlay in addition to the carefully selected
3917 code{dittoColors()}.")
3918 (license license:expat)))
3920 (define-public r-edaseq
3927 (uri (bioconductor-uri "EDASeq" version))
3930 "1qnpbmhxvqsma7ihi6yp3ad962xcanlxald84k2szh011ipxj7ws"))))
3931 (properties `((upstream-name . "EDASeq")))
3932 (build-system r-build-system)
3934 (list r-annotationdbi
3948 (home-page "https://github.com/drisso/EDASeq")
3949 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
3951 "This package provides support for numerical and graphical summaries of
3952 RNA-Seq genomic read data. Provided within-lane normalization procedures to
3953 adjust for GC-content effect (or other gene-level effects) on read counts:
3954 loess robust local regression, global-scaling, and full-quantile
3955 normalization. Between-lane normalization procedures to adjust for
3956 distributional differences between lanes (e.g., sequencing depth):
3957 global-scaling and full-quantile normalization.")
3958 (license license:artistic2.0)))
3960 (define-public r-edger
3966 (uri (bioconductor-uri "edgeR" version))
3969 "1q933m76155gy30wgps2gdd8pxzsfhppydjqn0fhjrwj6kqz8mik"))))
3970 (properties `((upstream-name . "edgeR")))
3971 (build-system r-build-system)
3973 (list r-limma r-locfit r-rcpp r-statmod)) ;for estimateDisp
3974 (home-page "http://bioinf.wehi.edu.au/edgeR")
3975 (synopsis "EdgeR does empirical analysis of digital gene expression data")
3976 (description "This package can do differential expression analysis of
3977 RNA-seq expression profiles with biological replication. It implements a range
3978 of statistical methodology based on the negative binomial distributions,
3979 including empirical Bayes estimation, exact tests, generalized linear models
3980 and quasi-likelihood tests. It be applied to differential signal analysis of
3981 other types of genomic data that produce counts, including ChIP-seq, SAGE and
3983 (license license:gpl2+)))
3985 (define-public r-ensembldb
3987 (name "r-ensembldb")
3992 (uri (bioconductor-uri "ensembldb" version))
3995 "12n21dcimdhgyjzk33m6xbv0m9ihgyzcf66vr1jr5ycv3rq2s7xc"))))
3996 (build-system r-build-system)
3998 (list r-annotationdbi
4016 (home-page "https://github.com/jotsetung/ensembldb")
4017 (synopsis "Utilities to create and use Ensembl-based annotation databases")
4019 "The package provides functions to create and use transcript-centric
4020 annotation databases/packages. The annotation for the databases are directly
4021 fetched from Ensembl using their Perl API. The functionality and data is
4022 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
4023 but, in addition to retrieve all gene/transcript models and annotations from
4024 the database, the @code{ensembldb} package also provides a filter framework
4025 allowing to retrieve annotations for specific entries like genes encoded on a
4026 chromosome region or transcript models of lincRNA genes.")
4027 ;; No version specified
4028 (license license:lgpl3+)))
4030 (define-public r-fastseg
4037 (uri (bioconductor-uri "fastseg" version))
4040 "1cr1b1jbgp1z1zpf71kl7mljbm2jpi6b97bf3bll3gnagfm489hy"))))
4041 (build-system r-build-system)
4043 (list r-biobase r-biocgenerics r-genomicranges r-iranges
4045 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
4046 (synopsis "Fast segmentation algorithm for genetic sequencing data")
4048 "Fastseg implements a very fast and efficient segmentation algorithm.
4049 It can segment data from DNA microarrays and data from next generation
4050 sequencing for example to detect copy number segments. Further it can segment
4051 data from RNA microarrays like tiling arrays to identify transcripts. Most
4052 generally, it can segment data given as a matrix or as a vector. Various data
4053 formats can be used as input to fastseg like expression set objects for
4054 microarrays or GRanges for sequencing data.")
4055 (license license:lgpl2.0+)))
4057 (define-public r-gage
4064 (uri (bioconductor-uri "gage" version))
4067 "03hx188h98qrbpjlf8v9sg2vqyfv49rp4c18ir11pg6hwqqrxh7b"))))
4068 (build-system r-build-system)
4070 (list r-annotationdbi r-go-db r-graph r-keggrest))
4071 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
4072 "articles/10.1186/1471-2105-10-161"))
4073 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
4075 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
4076 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
4077 data attributes including sample sizes, experimental designs, assay platforms,
4078 and other types of heterogeneity. The gage package provides functions for
4079 basic GAGE analysis, result processing and presentation. In addition, it
4080 provides demo microarray data and commonly used gene set data based on KEGG
4081 pathways and GO terms. These functions and data are also useful for gene set
4082 analysis using other methods.")
4083 (license license:gpl2+)))
4085 (define-public r-genefilter
4087 (name "r-genefilter")
4092 (uri (bioconductor-uri "genefilter" version))
4095 "1lp3alnljhsil8zylf8rvf8ik4wmsyciy3ij4rr9l4191dkkp4aq"))))
4096 (build-system r-build-system)
4098 (list gfortran r-knitr))
4100 (list r-annotate r-annotationdbi r-biobase r-biocgenerics
4102 (home-page "https://bioconductor.org/packages/genefilter")
4103 (synopsis "Filter genes from high-throughput experiments")
4105 "This package provides basic functions for filtering genes from
4106 high-throughput sequencing experiments.")
4107 (license license:artistic2.0)))
4109 (define-public r-geneoverlap
4111 (name "r-geneoverlap")
4115 (uri (bioconductor-uri "GeneOverlap" version))
4118 "0nqwa3x9q1hl9nm06hqzzrn00rirc9kj6s320csjlf7x6rcidr93"))))
4119 (build-system r-build-system)
4121 (list r-rcolorbrewer r-gplots))
4122 (home-page "https://www.bioconductor.org/packages/GeneOverlap/")
4123 (synopsis "Test and visualize gene overlaps")
4124 (description "This package can be used to test two sets of gene lists
4125 and visualize the results.")
4126 (license license:gpl3)))
4128 (define-public r-genomation
4130 (name "r-genomation")
4134 (uri (bioconductor-uri "genomation" version))
4137 "0rvay7gs4g2wi6h42kln8xwy9b05axj1x8mkfayl6pnnlva6xj79"))))
4138 (build-system r-build-system)
4162 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
4163 (synopsis "Summary, annotation and visualization of genomic data")
4165 "This package provides a package for summary and annotation of genomic
4166 intervals. Users can visualize and quantify genomic intervals over
4167 pre-defined functional regions, such as promoters, exons, introns, etc. The
4168 genomic intervals represent regions with a defined chromosome position, which
4169 may be associated with a score, such as aligned reads from HT-seq experiments,
4170 TF binding sites, methylation scores, etc. The package can use any tabular
4171 genomic feature data as long as it has minimal information on the locations of
4172 genomic intervals. In addition, it can use BAM or BigWig files as input.")
4173 (license license:artistic2.0)))
4175 (define-public r-genomeinfodb
4177 (name "r-genomeinfodb")
4181 (uri (bioconductor-uri "GenomeInfoDb" version))
4184 "1n37bwb2fqmdgqbn19rgsd2qn8vbdhv6khdwjr7v12bwabcbx9xh"))))
4186 `((upstream-name . "GenomeInfoDb")))
4187 (build-system r-build-system)
4189 (list r-biocgenerics r-genomeinfodbdata r-iranges r-rcurl
4193 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
4194 (synopsis "Utilities for manipulating chromosome identifiers")
4196 "This package contains data and functions that define and allow
4197 translation between different chromosome sequence naming conventions (e.g.,
4198 \"chr1\" versus \"1\"), including a function that attempts to place sequence
4199 names in their natural, rather than lexicographic, order.")
4200 (license license:artistic2.0)))
4202 (define-public r-genomicalignments
4204 (name "r-genomicalignments")
4208 (uri (bioconductor-uri "GenomicAlignments" version))
4211 "1ifmlc0488f5yzcf4p92dmdc7psxl5c0aa7qpxjk0a07gf7lldbi"))))
4213 `((upstream-name . "GenomicAlignments")))
4214 (build-system r-build-system)
4216 (list r-biocgenerics
4224 r-summarizedexperiment))
4225 (home-page "https://bioconductor.org/packages/GenomicAlignments")
4226 (synopsis "Representation and manipulation of short genomic alignments")
4228 "This package provides efficient containers for storing and manipulating
4229 short genomic alignments (typically obtained by aligning short reads to a
4230 reference genome). This includes read counting, computing the coverage,
4231 junction detection, and working with the nucleotide content of the
4233 (license license:artistic2.0)))
4235 (define-public r-genomicfeatures
4237 (name "r-genomicfeatures")
4241 (uri (bioconductor-uri "GenomicFeatures" version))
4244 "0f14p1ma2y8l60p9sxmh5j0axws9by1cznczb2jxipphpb4slpl1"))))
4246 `((upstream-name . "GenomicFeatures")))
4247 (build-system r-build-system)
4249 (list r-annotationdbi
4266 (home-page "https://bioconductor.org/packages/GenomicFeatures")
4267 (synopsis "Tools for working with transcript centric annotations")
4269 "This package provides a set of tools and methods for making and
4270 manipulating transcript centric annotations. With these tools the user can
4271 easily download the genomic locations of the transcripts, exons and cds of a
4272 given organism, from either the UCSC Genome Browser or a BioMart
4273 database (more sources will be supported in the future). This information is
4274 then stored in a local database that keeps track of the relationship between
4275 transcripts, exons, cds and genes. Flexible methods are provided for
4276 extracting the desired features in a convenient format.")
4277 (license license:artistic2.0)))
4279 (define-public r-genomicfiles
4281 (name "r-genomicfiles")
4286 (uri (bioconductor-uri "GenomicFiles" version))
4289 "06ycfna26klx27vvsnlpgv46bymfrc8z0zkpag7nm4m23153ivkz"))))
4290 (properties `((upstream-name . "GenomicFiles")))
4291 (build-system r-build-system)
4293 (list r-biocgenerics
4303 r-summarizedexperiment
4304 r-variantannotation))
4305 (home-page "https://bioconductor.org/packages/GenomicFiles")
4306 (synopsis "Distributed computing by file or by range")
4308 "This package provides infrastructure for parallel computations
4309 distributed by file or by range. User defined mapper and reducer functions
4310 provide added flexibility for data combination and manipulation.")
4311 (license license:artistic2.0)))
4313 (define-public r-genomicranges
4315 (name "r-genomicranges")
4319 (uri (bioconductor-uri "GenomicRanges" version))
4322 "088rv1aclwq265pdg4hmks73nl0125vk0vigyi44n3djkrdx48yn"))))
4324 `((upstream-name . "GenomicRanges")))
4325 (build-system r-build-system)
4327 (list r-biocgenerics r-genomeinfodb r-iranges r-s4vectors r-xvector))
4330 (home-page "https://bioconductor.org/packages/GenomicRanges")
4331 (synopsis "Representation and manipulation of genomic intervals")
4333 "This package provides tools to efficiently represent and manipulate
4334 genomic annotations and alignments is playing a central role when it comes to
4335 analyzing high-throughput sequencing data (a.k.a. NGS data). The
4336 GenomicRanges package defines general purpose containers for storing and
4337 manipulating genomic intervals and variables defined along a genome.")
4338 (license license:artistic2.0)))
4340 (define-public r-gostats
4347 (uri (bioconductor-uri "GOstats" version))
4350 "121ly9vifarg8y7mc468571bbs0xv4sx6sflm5zcdqf0p83yvjrm"))))
4351 (properties `((upstream-name . "GOstats")))
4352 (build-system r-build-system)
4363 (home-page "https://bioconductor.org/packages/GOstats")
4364 (synopsis "Tools for manipulating GO and microarrays")
4366 "This package provides a set of tools for interacting with GO and
4367 microarray data. A variety of basic manipulation tools for graphs, hypothesis
4368 testing and other simple calculations.")
4369 (license license:artistic2.0)))
4371 (define-public r-gseabase
4378 (uri (bioconductor-uri "GSEABase" version))
4381 "1qhvgyg392fd98h2qnmfmhg7mil5hp9cy3qmkqs4x1bhpv1m978g"))))
4382 (properties `((upstream-name . "GSEABase")))
4383 (build-system r-build-system)
4393 (home-page "https://bioconductor.org/packages/GSEABase")
4394 (synopsis "Gene set enrichment data structures and methods")
4396 "This package provides classes and methods to support @dfn{Gene Set
4397 Enrichment Analysis} (GSEA).")
4398 (license license:artistic2.0)))
4400 (define-public r-hpar
4407 (uri (bioconductor-uri "hpar" version))
4410 "07c6r703d5xp7y9bqmqalxgna2qrbk1h5s0d992m7360k259mgrj"))))
4411 (build-system r-build-system)
4414 (home-page "https://bioconductor.org/packages/hpar/")
4415 (synopsis "Human Protein Atlas in R")
4416 (description "This package provides a simple interface to and data from
4417 the Human Protein Atlas project.")
4418 (license license:artistic2.0)))
4420 (define-public r-rhtslib
4427 (uri (bioconductor-uri "Rhtslib" version))
4430 "07kws6afkxbmxq4w357mwwl712pdd16alvz7iqijjd2x7rjchj2f"))))
4431 (properties `((upstream-name . "Rhtslib")))
4432 (build-system r-build-system)
4433 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
4434 ;; which makes R abort the build.
4435 (arguments '(#:configure-flags '("--no-staged-install")))
4437 (list curl zlib ; packages using rhtslib need to link with zlib
4440 (list pkg-config r-knitr))
4441 (home-page "https://github.com/nhayden/Rhtslib")
4442 (synopsis "High-throughput sequencing library as an R package")
4444 "This package provides the HTSlib C library for high-throughput
4445 nucleotide sequence analysis. The package is primarily useful to developers
4446 of other R packages who wish to make use of HTSlib.")
4447 (license license:lgpl2.0+)))
4449 (define-public r-impute
4455 (uri (bioconductor-uri "impute" version))
4458 "11b0z7py0im6y43k55xpzz5jnvc0ram9rk3n1n4mwhvs0vhy39r2"))))
4461 (build-system r-build-system)
4462 (home-page "https://bioconductor.org/packages/impute")
4463 (synopsis "Imputation for microarray data")
4465 "This package provides a function to impute missing gene expression
4466 microarray data, using nearest neighbor averaging.")
4467 (license license:gpl2+)))
4469 (define-public r-interactivedisplaybase
4471 (name "r-interactivedisplaybase")
4476 (uri (bioconductor-uri "interactiveDisplayBase" version))
4479 "0fdwx5ch0ch8axdkfiq7zzhhq5hwcvd6kf8fggw9nd3ah1yjwbdg"))))
4481 `((upstream-name . "interactiveDisplayBase")))
4482 (build-system r-build-system)
4484 (list r-biocgenerics r-dt r-shiny))
4487 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
4488 (synopsis "Base package for web displays of Bioconductor objects")
4490 "This package contains the basic methods needed to generate interactive
4491 Shiny-based display methods for Bioconductor objects.")
4492 (license license:artistic2.0)))
4494 (define-public r-keggrest
4501 (uri (bioconductor-uri "KEGGREST" version))
4504 "1rn03w8y80prbvzahkvf8275haiymnjj1ijcgn55p3d0sb54yzgw"))))
4505 (properties `((upstream-name . "KEGGREST")))
4506 (build-system r-build-system)
4508 (list r-biostrings r-httr r-png))
4511 (home-page "https://bioconductor.org/packages/KEGGREST")
4512 (synopsis "Client-side REST access to KEGG")
4514 "This package provides a package that provides a client interface to the
4515 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
4516 (license license:artistic2.0)))
4518 (define-public r-lfa
4525 (uri (bioconductor-uri "lfa" version))
4527 (base32 "044866h4fnxmzb3sh9vmrd2smgsbcqgvd19dgwxisi418cad577l"))))
4528 (properties `((upstream-name . "lfa")))
4529 (build-system r-build-system)
4530 (propagated-inputs (list r-corpcor))
4531 (native-inputs (list r-knitr))
4532 (home-page "https://github.com/StoreyLab/lfa")
4533 (synopsis "Logistic Factor Analysis for categorical data")
4535 "@dfn{Logistic Factor Analysis} (LFA) is a method for a PCA analogue on
4536 Binomial data via estimation of latent structure in the natural parameter.")
4537 (license license:gpl3)))
4539 (define-public r-limma
4545 (uri (bioconductor-uri "limma" version))
4548 "0m8p8pqmf48f2zdf3qs66hmychbc58g2hfg1wyxzsv180m6xkk65"))))
4549 (build-system r-build-system)
4550 (home-page "http://bioinf.wehi.edu.au/limma")
4551 (synopsis "Package for linear models for microarray and RNA-seq data")
4552 (description "This package can be used for the analysis of gene expression
4553 studies, especially the use of linear models for analysing designed experiments
4554 and the assessment of differential expression. The analysis methods apply to
4555 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
4556 (license license:gpl2+)))
4558 (define-public r-methylkit
4560 (name "r-methylkit")
4564 (uri (bioconductor-uri "methylKit" version))
4567 "00asjzv05avfg0rrkmfbdqd6xx8d18zi72n3b1kf9wj81z2d2a35"))))
4568 (properties `((upstream-name . "methylKit")))
4569 (build-system r-build-system)
4591 (list r-knitr)) ; for vignettes
4592 (home-page "https://github.com/al2na/methylKit")
4594 "DNA methylation analysis from high-throughput bisulfite sequencing results")
4596 "MethylKit is an R package for DNA methylation analysis and annotation
4597 from high-throughput bisulfite sequencing. The package is designed to deal
4598 with sequencing data from @dfn{Reduced representation bisulfite
4599 sequencing} (RRBS) and its variants, but also target-capture methods and whole
4600 genome bisulfite sequencing. It also has functions to analyze base-pair
4601 resolution 5hmC data from experimental protocols such as oxBS-Seq and
4603 (license license:artistic2.0)))
4605 (define-public r-motifrg
4612 (uri (bioconductor-uri "motifRG" version))
4615 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
4616 (properties `((upstream-name . "motifRG")))
4617 (build-system r-build-system)
4621 r-bsgenome-hsapiens-ucsc-hg19
4625 (home-page "https://bioconductor.org/packages/motifRG")
4626 (synopsis "Discover motifs in high throughput sequencing data")
4628 "This package provides tools for discriminative motif discovery in high
4629 throughput genetic sequencing data sets using regression methods.")
4630 (license license:artistic2.0)))
4632 (define-public r-mutationalpatterns
4634 (name "r-mutationalpatterns")
4639 (uri (bioconductor-uri "MutationalPatterns" version))
4642 "113b2hrc0n47qz144xhky93jcm6qh6flzadq5y0plga5jrz0rnwg"))))
4643 (build-system r-build-system)
4647 (list r-biocgenerics
4650 ;; These two packages are suggested packages
4651 r-bsgenome-hsapiens-1000genomes-hs37d5
4652 r-bsgenome-hsapiens-ucsc-hg19
4670 r-variantannotation))
4671 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
4672 (synopsis "Extract and visualize mutational patterns in genomic data")
4673 (description "This package provides an extensive toolset for the
4674 characterization and visualization of a wide range of mutational patterns
4675 in SNV base substitution data.")
4676 (license license:expat)))
4678 (define-public r-msnbase
4685 (uri (bioconductor-uri "MSnbase" version))
4688 "1xzn0k3c2wn6c6gv90hddy3c201sg927342zrw9ig2xap0r053x3"))))
4689 (properties `((upstream-name . "MSnbase")))
4690 (build-system r-build-system)
4716 (home-page "https://github.com/lgatto/MSnbase")
4717 (synopsis "Base functions and classes for MS-based proteomics")
4719 "This package provides basic plotting, data manipulation and processing
4720 of mass spectrometry based proteomics data.")
4721 (license license:artistic2.0)))
4723 (define-public r-msnid
4730 (uri (bioconductor-uri "MSnID" version))
4733 "1yiw95p40nz0pvq7s4i0xg02r9yqmnknak00z4lkw8jij3w3rkkq"))))
4734 (properties `((upstream-name . "MSnID")))
4735 (build-system r-build-system)
4738 (modify-phases %standard-phases
4739 (add-after 'unpack 'set-HOME
4740 (lambda _ (setenv "HOME" "/tmp"))))))
4742 (list r-annotationdbi
4768 (home-page "https://bioconductor.org/packages/MSnID")
4769 (synopsis "Utilities for LC-MSn proteomics identifications")
4771 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
4772 from mzIdentML (leveraging the mzID package) or text files. After collating
4773 the search results from multiple datasets it assesses their identification
4774 quality and optimize filtering criteria to achieve the maximum number of
4775 identifications while not exceeding a specified false discovery rate. It also
4776 contains a number of utilities to explore the MS/MS results and assess missed
4777 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
4778 (license license:artistic2.0)))
4780 (define-public r-mzid
4787 (uri (bioconductor-uri "mzID" version))
4790 "1q1aqyya9nd494s7m3rdaf3kixipdrwbj825g40kdljwrg85y961"))))
4791 (properties `((upstream-name . "mzID")))
4792 (build-system r-build-system)
4802 (home-page "https://bioconductor.org/packages/mzID")
4803 (synopsis "Parser for mzIdentML files")
4805 "This package provides a parser for mzIdentML files implemented using the
4806 XML package. The parser tries to be general and able to handle all types of
4807 mzIdentML files with the drawback of having less pretty output than a vendor
4809 (license license:gpl2+)))
4811 (define-public r-mzr
4818 (uri (bioconductor-uri "mzR" version))
4821 "1dqa03hb42kbqfg15ksijdkyf9pr54gcl3in4mzjkld5sdi8ncds"))
4822 (modules '((guix build utils)))
4824 '(delete-file-recursively "src/boost"))))
4825 (properties `((upstream-name . "mzR")))
4826 (build-system r-build-system)
4829 (modify-phases %standard-phases
4830 (add-after 'unpack 'use-system-boost
4832 (substitute* "src/Makevars"
4833 (("\\./boost/libs.*") "")
4834 (("PKG_LIBS=") "PKG_LIBS=$(BOOST_LIBS) ")
4835 (("\\ARCH_OBJS=" line)
4837 "\nBOOST_LIBS=-lboost_system -lboost_regex \
4838 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n"))))))))
4840 (list boost ; use this instead of the bundled boost sources
4851 (home-page "https://github.com/sneumann/mzR/")
4852 (synopsis "Parser for mass spectrometry data files")
4854 "The mzR package provides a unified API to the common file formats and
4855 parsers available for mass spectrometry data. It comes with a wrapper for the
4856 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
4857 The package contains the original code written by the ISB, and a subset of the
4858 proteowizard library for mzML and mzIdentML. The netCDF reading code has
4859 previously been used in XCMS.")
4860 (license license:artistic2.0)))
4862 (define-public r-organismdbi
4864 (name "r-organismdbi")
4869 (uri (bioconductor-uri "OrganismDbi" version))
4872 "0mxnxj8x4hc21psz39mf7qwvh1fsn6qyjgl5qffk1xxmasf69619"))))
4873 (properties `((upstream-name . "OrganismDbi")))
4874 (build-system r-build-system)
4876 (list r-annotationdbi
4887 (home-page "https://bioconductor.org/packages/OrganismDbi")
4888 (synopsis "Software to enable the smooth interfacing of database packages")
4889 (description "The package enables a simple unified interface to several
4890 annotation packages each of which has its own schema by taking advantage of
4891 the fact that each of these packages implements a select methods.")
4892 (license license:artistic2.0)))
4894 (define-public r-pcamethods
4896 (name "r-pcamethods")
4901 (uri (bioconductor-uri "pcaMethods" version))
4904 "1087sl7y707zld7zpf3ly51gnmdp93vn90dwa5440v7qawvg2h9b"))))
4905 (properties `((upstream-name . "pcaMethods")))
4906 (build-system r-build-system)
4908 (list r-biobase r-biocgenerics r-mass r-rcpp))
4909 (home-page "https://github.com/hredestig/pcamethods")
4910 (synopsis "Collection of PCA methods")
4912 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
4913 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
4914 for missing value estimation is included for comparison. BPCA, PPCA and
4915 NipalsPCA may be used to perform PCA on incomplete data as well as for
4916 accurate missing value estimation. A set of methods for printing and plotting
4917 the results is also provided. All PCA methods make use of the same data
4918 structure (pcaRes) to provide a common interface to the PCA results.")
4919 (license license:gpl3+)))
4921 ;; This is a CRAN package, but it depends on a Bioconductor package:
4922 ;; r-aroma-light, r-dnacopy..
4923 (define-public r-pscbs
4930 (uri (cran-uri "PSCBS" version))
4932 (base32 "14rs2wywipbkia3dbzfhpnkmfgdvm2bf586lggsx63sywlv5d02q"))))
4933 (properties `((upstream-name . "PSCBS")))
4934 (build-system r-build-system)
4937 (modify-phases %standard-phases
4938 (add-before 'install 'change-home-dir
4940 ;; Change from /homeless-shelter to /tmp for write permission.
4941 (setenv "HOME" "/tmp"))))))
4953 (list r-r-rsp ;used to build vignettes
4955 (home-page "https://github.com/HenrikBengtsson/PSCBS")
4956 (synopsis "Analysis of parent-specific DNA copy numbers")
4958 "This is a package for segmentation of allele-specific DNA copy number
4959 data and detection of regions with abnormal copy number within each parental
4960 chromosome. Both tumor-normal paired and tumor-only analyses are supported.")
4961 (license license:gpl2+)))
4963 (define-public r-protgenerics
4965 (name "r-protgenerics")
4970 (uri (bioconductor-uri "ProtGenerics" version))
4973 "04hcgj4q8dbzp1a29rbww2bxxrg679pgys3m09p0ydkpsx76rq05"))))
4974 (properties `((upstream-name . "ProtGenerics")))
4975 (build-system r-build-system)
4976 (home-page "https://github.com/lgatto/ProtGenerics")
4977 (synopsis "S4 generic functions for proteomics infrastructure")
4979 "This package provides S4 generic functions needed by Bioconductor
4980 proteomics packages.")
4981 (license license:artistic2.0)))
4983 (define-public r-rbgl
4990 (uri (bioconductor-uri "RBGL" version))
4993 "0ph089vxla49sng0pdwiyh9rpk9i96cbsx5q2jn46jj4x51ijc7y"))))
4994 (properties `((upstream-name . "RBGL")))
4995 (build-system r-build-system)
4997 (list r-bh r-graph))
4998 (home-page "https://www.bioconductor.org/packages/RBGL")
4999 (synopsis "Interface to the Boost graph library")
5001 "This package provides a fairly extensive and comprehensive interface to
5002 the graph algorithms contained in the Boost library.")
5003 (license license:artistic2.0)))
5005 (define-public r-rcas
5011 (uri (bioconductor-uri "RCAS" version))
5014 "05sj2ab7bxgf41gkmjaskhqm0198xlir1sw3f73x8rjg14rssmqf"))))
5015 (properties `((upstream-name . "RCAS")))
5016 (build-system r-build-system)
5018 (list r-biocgenerics
5021 r-bsgenome-hsapiens-ucsc-hg19
5047 (synopsis "RNA-centric annotation system")
5049 "RCAS aims to be a standalone RNA-centric annotation system that provides
5050 intuitive reports and publication-ready graphics. This package provides the R
5051 library implementing most of the pipeline's features.")
5052 (home-page "https://github.com/BIMSBbioinfo/RCAS")
5053 (license license:artistic2.0)))
5055 (define-public r-regioner
5062 (uri (bioconductor-uri "regioneR" version))
5065 "11whi2v211xiz9s7cjl14d8vavlry2fmhvx12rma25wkjmhrpa3f"))))
5066 (properties `((upstream-name . "regioneR")))
5067 (build-system r-build-system)
5079 (home-page "https://bioconductor.org/packages/regioneR/")
5080 (synopsis "Association analysis of genomic regions")
5081 (description "This package offers a statistical framework based on
5082 customizable permutation tests to assess the association between genomic
5083 region sets and other genomic features.")
5084 (license license:artistic2.0)))
5086 (define-public r-reportingtools
5088 (name "r-reportingtools")
5093 (uri (bioconductor-uri "ReportingTools" version))
5096 "0r8cdqzfh1jxkghhk3j8x3y9kkmdyg9ibfhsic15jqkmp1im6khh"))))
5098 `((upstream-name . "ReportingTools")))
5099 (build-system r-build-system)
5122 (home-page "https://bioconductor.org/packages/ReportingTools/")
5123 (synopsis "Tools for making reports in various formats")
5125 "The ReportingTools package enables users to easily display reports of
5126 analysis results generated from sources such as microarray and sequencing
5127 data. The package allows users to create HTML pages that may be viewed on a
5128 web browser, or in other formats. Users can generate tables with sortable and
5129 filterable columns, make and display plots, and link table entries to other
5130 data sources such as NCBI or larger plots within the HTML page. Using the
5131 package, users can also produce a table of contents page to link various
5132 reports together for a particular project that can be viewed in a web
5134 (license license:artistic2.0)))
5136 (define-public r-rhdf5
5142 (uri (bioconductor-uri "rhdf5" version))
5145 "00cp90mnb8p83jiflm6x4x0qf4p7gvgh47jk9jry6j3qyvfqaiff"))))
5146 (build-system r-build-system)
5148 (list r-rhdf5filters r-rhdf5lib))
5151 (home-page "https://bioconductor.org/packages/rhdf5")
5152 (synopsis "HDF5 interface to R")
5154 "This R/Bioconductor package provides an interface between HDF5 and R.
5155 HDF5's main features are the ability to store and access very large and/or
5156 complex datasets and a wide variety of metadata on mass storage (disk) through
5157 a completely portable file format. The rhdf5 package is thus suited for the
5158 exchange of large and/or complex datasets between R and other software
5159 package, and for letting R applications work on datasets that are larger than
5160 the available RAM.")
5161 (license license:artistic2.0)))
5163 (define-public r-rhdf5filters
5165 (name "r-rhdf5filters")
5170 (uri (bioconductor-uri "rhdf5filters" version))
5173 "1ipg0v8nqz1imj63scqmpiswcxbl4ankg3knfq4p06ic6ypbbmvs"))))
5174 (properties `((upstream-name . "rhdf5filters")))
5175 (build-system r-build-system)
5182 (home-page "https://github.com/grimbough/rhdf5filters")
5183 (synopsis "HDF5 compression filters")
5185 "This package provides a collection of compression filters for use with
5187 (license license:bsd-2)))
5189 (define-public r-rsamtools
5191 (name "r-rsamtools")
5195 (uri (bioconductor-uri "Rsamtools" version))
5198 "1wll703if12qrn0d11ljwf7rqhs4lb27fzyyz1hqwvzn3v361s10"))))
5200 `((upstream-name . "Rsamtools")))
5201 (build-system r-build-system)
5204 (modify-phases %standard-phases
5205 (add-after 'unpack 'use-system-zlib
5207 (substitute* "DESCRIPTION"
5208 (("zlibbioc, ") ""))
5209 (substitute* "NAMESPACE"
5210 (("import\\(zlibbioc\\)") "")))))))
5212 (list r-biocgenerics
5222 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
5223 (synopsis "Interface to samtools, bcftools, and tabix")
5225 "This package provides an interface to the @code{samtools},
5226 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
5227 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
5228 tab-delimited (tabix) files.")
5229 (license license:expat)))
5231 ;; This is a CRAN package, but it depends on a Bioconductor package:
5233 (define-public r-restfulr
5240 (uri (cran-uri "restfulr" version))
5243 "14p6h0gjknqy5z2fprxw7waf4p0cd2qmp18s7qig4ylqn8gqzzs0"))))
5244 (properties `((upstream-name . "restfulr")))
5245 (build-system r-build-system)
5247 (list r-rcurl r-rjson r-s4vectors r-xml r-yaml))
5248 (home-page "https://cran.r-project.org/package=restfulr")
5249 (synopsis "R interface to RESTful web services")
5251 "This package models a RESTful service as if it were a nested R list.")
5252 (license license:artistic2.0)))
5254 (define-public r-rtracklayer
5256 (name "r-rtracklayer")
5260 (uri (bioconductor-uri "rtracklayer" version))
5263 "10qy9s6253mgj871qfqn03i8yw10mz7id4cxfyf67qxczz2xmjls"))))
5264 (build-system r-build-system)
5267 (modify-phases %standard-phases
5268 (add-after 'unpack 'use-system-zlib
5270 (substitute* "DESCRIPTION"
5271 ((" zlibbioc,") ""))
5272 (substitute* "NAMESPACE"
5273 (("import\\(zlibbioc\\)") "")))))))
5279 (list r-biocgenerics
5293 (home-page "https://bioconductor.org/packages/rtracklayer")
5294 (synopsis "R interface to genome browsers and their annotation tracks")
5296 "rtracklayer is an extensible framework for interacting with multiple
5297 genome browsers (currently UCSC built-in) and manipulating annotation tracks
5298 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
5299 built-in). The user may export/import tracks to/from the supported browsers,
5300 as well as query and modify the browser state, such as the current viewport.")
5301 (license license:artistic2.0)))
5303 ;; This is a CRAN package, but it depends on a Bioconductor package.
5304 (define-public r-samr
5311 (uri (cran-uri "samr" version))
5314 "01km0f7qgm73x19vbvsxl083hs1dq4dj8qm5h64cxbf20b08my15"))))
5315 (properties `((upstream-name . "samr")))
5316 (build-system r-build-system)
5324 (native-inputs (list gfortran))
5325 (home-page "https://statweb.stanford.edu/~tibs/SAM/")
5326 (synopsis "Significance analysis of Microarrays")
5328 "This is a package for significance analysis of Microarrays for
5329 differential expression analysis, RNAseq data and related problems.")
5330 ;; Any version of the LGPL
5331 (license license:lgpl3+)))
5333 (define-public r-scannotatr
5335 (name "r-scannotatr")
5340 (uri (bioconductor-uri "scAnnotatR" version))
5342 (base32 "067q57kabhqd1z8l3d91fw74aaw89nb48gm6fll4hv00nqza3n5b"))))
5343 (properties `((upstream-name . "scAnnotatR")))
5344 (build-system r-build-system)
5346 (list r-annotationhub
5357 r-singlecellexperiment
5358 r-summarizedexperiment))
5359 (native-inputs (list r-knitr))
5360 (home-page "https://github.com/grisslab/scAnnotatR")
5361 (synopsis "Pretrained models for prediction on single cell RNA-sequencing data")
5363 "This package comprises a set of pretrained machine learning models to
5364 predict basic immune cell types. This enables to quickly get a first
5365 annotation of the cell types present in the dataset without requiring prior
5366 knowledge. The package also lets you train using own models to predict new
5367 cell types based on specific research needs.")
5368 (license license:expat)))
5370 (define-public r-scdblfinder
5372 (name "r-scdblfinder")
5377 (uri (bioconductor-uri "scDblFinder" version))
5379 (base32 "0y14dvdm16b3bvlrnz03adfylm1kj6jrp2fwciyldij2lfal90y0"))))
5380 (properties `((upstream-name . "scDblFinder")))
5381 (build-system r-build-system)
5383 (list r-biocgenerics
5401 r-singlecellexperiment
5402 r-summarizedexperiment
5404 (native-inputs (list r-knitr))
5405 (home-page "https://github.com/plger/scDblFinder")
5406 (synopsis "Detect multiplets in single-cell RNA sequencing data")
5408 "The scDblFinder package gathers various methods for the detection and
5409 handling of doublets/multiplets in single-cell RNA sequencing data (i.e.
5410 multiple cells captured within the same droplet or reaction volume). It
5411 includes methods formerly found in the scran package, and the new fast and
5412 comprehensive scDblFinder method.")
5413 (license license:gpl3)))
5415 (define-public r-scmap
5422 (uri (bioconductor-uri "scmap" version))
5424 (base32 "0pfwaa9pgml11b84rpf7afdkmg8kxb4srgpc56571vaz388xrv7l"))))
5425 (properties `((upstream-name . "scmap")))
5426 (build-system r-build-system)
5441 r-singlecellexperiment
5442 r-summarizedexperiment))
5443 (native-inputs (list r-knitr))
5444 (home-page "https://github.com/hemberg-lab/scmap")
5445 (synopsis "Tool for unsupervised projection of single cell RNA-seq data")
5447 "@dfn{Single-cell RNA-seq} (scRNA-seq) is widely used to investigate the
5448 composition of complex tissues since the technology allows researchers to
5449 define cell-types using unsupervised clustering of the transcriptome.
5450 However, due to differences in experimental methods and computational
5451 analyses, it is often challenging to directly compare the cells identified in
5452 two different experiments. @code{scmap} is a method for projecting cells from
5453 a scRNA-seq experiment onto the cell-types or individual cells identified in a
5454 different experiment.")
5455 (license license:gpl3)))
5457 (define-public r-seqlogo
5464 (uri (bioconductor-uri "seqLogo" version))
5467 "1lk3238m17acmd6lgjjbpscyxw8fm63wv34kbbr478wcih1wbwxr"))))
5468 (properties `((upstream-name . "seqLogo")))
5469 (build-system r-build-system)
5472 (home-page "https://bioconductor.org/packages/seqLogo")
5473 (synopsis "Sequence logos for DNA sequence alignments")
5475 "seqLogo takes the position weight matrix of a DNA sequence motif and
5476 plots the corresponding sequence logo as introduced by Schneider and
5478 (license license:lgpl2.0+)))
5480 (define-public r-seqpattern
5482 (name "r-seqpattern")
5486 (uri (bioconductor-uri "seqPattern" version))
5489 "0nrrlr1nl9zxmp88qq8jn7wgmda6jh0xvp4nph94w4nwjsyb7xqn"))))
5491 `((upstream-name . "seqPattern")))
5492 (build-system r-build-system)
5494 (list r-biostrings r-genomicranges r-iranges r-kernsmooth r-plotrix))
5495 (home-page "https://bioconductor.org/packages/seqPattern")
5496 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
5498 "This package provides tools to visualize oligonucleotide patterns and
5499 sequence motif occurrences across a large set of sequences centred at a common
5500 reference point and sorted by a user defined feature.")
5501 (license license:gpl3+)))
5503 (define-public r-shortread
5505 (name "r-shortread")
5510 (uri (bioconductor-uri "ShortRead" version))
5513 "0303198b4v2wjah9kc829kn01030996l6di4jpf8q5ccd212rjhq"))))
5514 (properties `((upstream-name . "ShortRead")))
5515 (build-system r-build-system)
5535 (home-page "https://bioconductor.org/packages/ShortRead")
5536 (synopsis "FASTQ input and manipulation tools")
5538 "This package implements sampling, iteration, and input of FASTQ files.
5539 It includes functions for filtering and trimming reads, and for generating a
5540 quality assessment report. Data are represented as
5541 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5542 purposes. The package also contains legacy support for early single-end,
5543 ungapped alignment formats.")
5544 (license license:artistic2.0)))
5546 (define-public r-simplifyenrichment
5548 (name "r-simplifyenrichment")
5553 (uri (bioconductor-uri "simplifyEnrichment" version))
5556 "0qblgdxmr7zc981529cca3ykakql618q1im6gaxw8pwws5jgpyk6"))))
5558 `((upstream-name . "simplifyEnrichment")))
5559 (build-system r-build-system)
5561 (list r-annotationdbi
5578 (native-inputs (list r-knitr))
5579 (home-page "https://github.com/jokergoo/simplifyEnrichment")
5580 (synopsis "Simplify functional enrichment results")
5581 (description "This package provides a new clustering algorithm, binary
5582 cut, for clustering similarity matrices of functional terms is implemented in
5583 this package. It also provides functionalities for visualizing, summarizing
5584 and comparing the clusterings.")
5585 (license license:expat)))
5587 (define-public r-transcriptr
5589 (name "r-transcriptr")
5594 (uri (bioconductor-uri "transcriptR" version))
5596 (base32 "1zc6aasd5nzwl9jxr0rdriiq85adqdbfi5b9m3jyf69pa71sgy03"))))
5597 (properties `((upstream-name . "transcriptR")))
5598 (build-system r-build-system)
5600 (list r-biocgenerics
5615 (native-inputs (list r-knitr))
5616 (home-page "https://bioconductor.org/packages/transcriptR")
5617 (synopsis "Primary transcripts detection and quantification")
5619 "The differences in the RNA types being sequenced have an impact on the
5620 resulting sequencing profiles. mRNA-seq data is enriched with reads derived
5621 from exons, while GRO-, nucRNA- and chrRNA-seq demonstrate a substantial
5622 broader coverage of both exonic and intronic regions. The presence of
5623 intronic reads in GRO-seq type of data makes it possible to use it to
5624 computationally identify and quantify all de novo continuous regions of
5625 transcription distributed across the genome. This type of data, however, is
5626 more challenging to interpret and less common practice compared to mRNA-seq.
5627 One of the challenges for primary transcript detection concerns the
5628 simultaneous transcription of closely spaced genes, which needs to be properly
5629 divided into individually transcribed units. The R package transcriptR
5630 combines RNA-seq data with ChIP-seq data of histone modifications that mark
5631 active Transcription Start Sites (TSSs), such as, H3K4me3 or H3K9/14Ac to
5632 overcome this challenge. The advantage of this approach over the use of, for
5633 example, gene annotations is that this approach is data driven and therefore
5634 able to deal also with novel and case specific events.")
5635 (license license:gpl3)))
5637 (define-public r-trajectoryutils
5639 (name "r-trajectoryutils")
5644 (uri (bioconductor-uri "TrajectoryUtils" version))
5647 "07hcr3zplxlzlwc13wh9006m5kaqm57cm1b2x74bpp857f2q93dj"))))
5649 `((upstream-name . "TrajectoryUtils")))
5650 (build-system r-build-system)
5652 (list r-igraph r-matrix r-s4vectors r-singlecellexperiment
5653 r-summarizedexperiment))
5654 (native-inputs (list r-knitr))
5655 (home-page "https://bioconductor.org/packages/TrajectoryUtils")
5656 (synopsis "Single-cell trajectory analysis utilities")
5658 "This package implements low-level utilities for single-cell trajectory
5659 analysis, primarily intended for re-use inside higher-level packages. It
5660 includes a function to create a cluster-level minimum spanning tree and data
5661 structures to hold pseudotime inference results.")
5662 (license license:gpl3)))
5664 (define-public r-slingshot
5666 (name "r-slingshot")
5670 (uri (bioconductor-uri "slingshot" version))
5673 "0xapi66l5z2qdqns3fcjqcjal6npqj7rxra60lwjvbrq49pq69p2"))))
5674 (build-system r-build-system)
5680 r-singlecellexperiment
5681 r-summarizedexperiment
5685 (home-page "https://bioconductor.org/packages/slingshot")
5686 (synopsis "Tools for ordering single-cell sequencing")
5687 (description "This package provides functions for inferring continuous,
5688 branching lineage structures in low-dimensional data. Slingshot was designed
5689 to model developmental trajectories in single-cell RNA sequencing data and
5690 serve as a component in an analysis pipeline after dimensionality reduction
5691 and clustering. It is flexible enough to handle arbitrarily many branching
5692 events and allows for the incorporation of prior knowledge through supervised
5693 graph construction.")
5694 (license license:artistic2.0)))
5696 (define-public r-stager
5703 (uri (bioconductor-uri "stageR" version))
5705 (base32 "0ns3ih6l4na6irshrc5iy4d9qf7hrnqq3ndnlcjb2i1cn38l2w9y"))))
5706 (properties `((upstream-name . "stageR")))
5707 (build-system r-build-system)
5708 (propagated-inputs (list r-summarizedexperiment))
5709 (native-inputs (list r-knitr))
5710 (home-page "https://bioconductor.org/packages/stageR")
5711 (synopsis "Stage-wise analysis of high throughput gene expression data")
5713 "The stageR package allows automated stage-wise analysis of
5714 high-throughput gene expression data. The method is published in Genome
5716 @url{https://genomebiology.biomedcentral.com/articles/10.1186/s13059-017-1277-0}.")
5717 (license license:gpl3)))
5719 (define-public r-stringdb
5726 (uri (bioconductor-uri "STRINGdb" version))
5728 (base32 "1jn6080v6097zpqsr4gfbx31gqqdhpzjrk63avk3v3xwawmf2379"))))
5729 (properties `((upstream-name . "STRINGdb")))
5730 (build-system r-build-system)
5741 (home-page "https://git.bioconductor.org/packages/STRINGdb")
5742 (synopsis "Search tool for the retrieval of interacting proteins database")
5744 "The @code{STRINGdb} package provides an R interface to the STRING
5745 protein-protein interactions database. @url{https://www.string-db.org,
5746 STRING} is a database of known and predicted protein-protein interactions.
5747 The interactions include direct (physical) and indirect (functional)
5748 associations. Each interaction is associated with a combined confidence score
5749 that integrates the various evidences.")
5750 (license license:gpl2)))
5752 (define-public r-structuralvariantannotation
5754 (name "r-structuralvariantannotation")
5759 (uri (bioconductor-uri "StructuralVariantAnnotation" version))
5761 (base32 "0f3x74ic3blg8nm5xlv79k0n8j3fpl98mmhfanqfzmdl0g3j6wx6"))))
5762 (build-system r-build-system)
5776 r-summarizedexperiment
5777 r-variantannotation))
5780 (home-page "https://bioconductor.org/packages/StructuralVariantAnnotation/")
5781 (synopsis "R package designed to simplify structural variant analysis")
5783 "This package contains useful helper functions for dealing with structural
5784 variants in VCF format. The packages contains functions for parsing VCFs from
5785 a number of popular callers as well as functions for dealing with breakpoints
5786 involving two separate genomic loci encoded as GRanges objects.")
5787 (license license:gpl3)))
5789 (define-public r-summarizedexperiment
5791 (name "r-summarizedexperiment")
5795 (uri (bioconductor-uri "SummarizedExperiment" version))
5798 "02vlqzmslyijs09jl0gdjxqjjnnl4yqbqqqlb4vb7nr0fspmyz39"))))
5800 `((upstream-name . "SummarizedExperiment")))
5801 (build-system r-build-system)
5814 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
5815 (synopsis "Container for representing genomic ranges by sample")
5817 "The SummarizedExperiment container contains one or more assays, each
5818 represented by a matrix-like object of numeric or other mode. The rows
5819 typically represent genomic ranges of interest and the columns represent
5821 (license license:artistic2.0)))
5823 (define-public r-sva
5830 (uri (bioconductor-uri "sva" version))
5833 "0ka259rn0la0hjslj7w24q1dyyh79h84nw6mxp7armqbfjb207a4"))))
5834 (build-system r-build-system)
5842 (home-page "https://bioconductor.org/packages/sva")
5843 (synopsis "Surrogate variable analysis")
5845 "This package contains functions for removing batch effects and other
5846 unwanted variation in high-throughput experiment. It also contains functions
5847 for identifying and building surrogate variables for high-dimensional data
5848 sets. Surrogate variables are covariates constructed directly from
5849 high-dimensional data like gene expression/RNA sequencing/methylation/brain
5850 imaging data that can be used in subsequent analyses to adjust for unknown,
5851 unmodeled, or latent sources of noise.")
5852 (license license:artistic2.0)))
5854 (define-public r-systempiper
5856 (name "r-systempiper")
5861 (uri (bioconductor-uri "systemPipeR" version))
5864 "1yybbff29gwv6rm0nw4yjw73bbl5prfj8gj4zky917smjfd459im"))))
5865 (properties `((upstream-name . "systemPipeR")))
5866 (build-system r-build-system)
5868 (list r-biocgenerics
5879 r-summarizedexperiment
5883 (home-page "https://github.com/tgirke/systemPipeR")
5884 (synopsis "Next generation sequencing workflow and reporting environment")
5886 "This R package provides tools for building and running automated
5887 end-to-end analysis workflows for a wide range of @dfn{next generation
5888 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5889 Important features include a uniform workflow interface across different NGS
5890 applications, automated report generation, and support for running both R and
5891 command-line software, such as NGS aligners or peak/variant callers, on local
5892 computers or compute clusters. Efficient handling of complex sample sets and
5893 experimental designs is facilitated by a consistently implemented sample
5894 annotation infrastructure.")
5895 (license license:artistic2.0)))
5897 (define-public r-topgo
5903 (uri (bioconductor-uri "topGO" version))
5906 "125r42ymk1irjmwk4sywjkcshs71s26p3zsvryfdvf56k5w162v6"))))
5908 `((upstream-name . "topGO")))
5909 (build-system r-build-system)
5911 (list r-annotationdbi
5920 (home-page "https://bioconductor.org/packages/topGO")
5921 (synopsis "Enrichment analysis for gene ontology")
5923 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
5924 terms while accounting for the topology of the GO graph. Different test
5925 statistics and different methods for eliminating local similarities and
5926 dependencies between GO terms can be implemented and applied.")
5927 ;; Any version of the LGPL applies.
5928 (license license:lgpl2.1+)))
5930 (define-public r-tximport
5936 (uri (bioconductor-uri "tximport" version))
5939 "1cnra82pvwz79a1hkw0phc6aa3v43r5p4nx8xyx5wzmkd7rjkc8x"))))
5940 (build-system r-build-system)
5943 (home-page "https://bioconductor.org/packages/tximport")
5944 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
5946 "This package provides tools to import transcript-level abundance,
5947 estimated counts and transcript lengths, and to summarize them into matrices
5948 for use with downstream gene-level analysis packages. Average transcript
5949 length, weighted by sample-specific transcript abundance estimates, is
5950 provided as a matrix which can be used as an offset for different expression
5951 of gene-level counts.")
5952 (license license:gpl2+)))
5954 ;; This is a CRAN package, but it depends on a Bioconductor package.
5955 (define-public r-valr
5962 (uri (cran-uri "valr" version))
5965 "0dd41irvibh6rwi52bw4zg4m7wpyihlp1kdkb8fdji3csw2fiz4k"))))
5966 (build-system r-build-system)
5974 r-rtracklayer ;bioconductor package
5979 (home-page "https://github.com/rnabioco/valr")
5980 (synopsis "Genome interval arithmetic in R")
5982 "This package enables you to read and manipulate genome intervals and
5983 signals. It provides functionality similar to command-line tool suites within
5984 R, enabling interactive analysis and visualization of genome-scale data.")
5985 (license license:expat)))
5987 (define-public r-variantannotation
5989 (name "r-variantannotation")
5993 (uri (bioconductor-uri "VariantAnnotation" version))
5996 "12d5hkx6pby6l2asyg4jp4jb2x17ybwhqd55rl64h37mwcndbdg1"))))
5998 `((upstream-name . "VariantAnnotation")))
6000 (list r-annotationdbi
6011 r-summarizedexperiment
6018 (build-system r-build-system)
6019 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6020 (synopsis "Package for annotation of genetic variants")
6021 (description "This R package can annotate variants, compute amino acid
6022 coding changes and predict coding outcomes.")
6023 (license license:artistic2.0)))
6025 (define-public r-vsn
6032 (uri (bioconductor-uri "vsn" version))
6035 "1ja7vdjvgx671l57f9fzfn4vc6q7xzfmqs4krg2rdyfaaf531gqf"))))
6036 (build-system r-build-system)
6038 (list r-affy r-biobase r-ggplot2 r-lattice r-limma))
6040 (list r-knitr)) ; for vignettes
6041 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
6042 (synopsis "Variance stabilization and calibration for microarray data")
6044 "The package implements a method for normalising microarray intensities,
6045 and works for single- and multiple-color arrays. It can also be used for data
6046 from other technologies, as long as they have similar format. The method uses
6047 a robust variant of the maximum-likelihood estimator for an
6048 additive-multiplicative error model and affine calibration. The model
6049 incorporates data calibration step (a.k.a. normalization), a model for the
6050 dependence of the variance on the mean intensity and a variance stabilizing
6051 data transformation. Differences between transformed intensities are
6052 analogous to \"normalized log-ratios\". However, in contrast to the latter,
6053 their variance is independent of the mean, and they are usually more sensitive
6054 and specific in detecting differential transcription.")
6055 (license license:artistic2.0)))
6057 ;; There is no source tarball, so we fetch the code from the Bioconductor git
6059 (define-public r-xcir
6060 (let ((commit "3b59d456f2ad7f70285915b036b1dc4279687277")
6064 (version (git-version "1.8.0" revision commit))
6068 (url "https://git.bioconductor.org/packages/XCIR")
6070 (file-name (git-file-name name version))
6073 "1xxw5ady5j2p7z7zjxgx7lhm85x7fxbljiv49lc2ghsvh9wm937p"))))
6074 (properties `((upstream-name . "XCIR")))
6075 (build-system r-build-system)
6076 (propagated-inputs (list r-biomart
6084 r-variantannotation))
6085 (native-inputs (list r-knitr))
6086 (home-page "https://github.com/SRenan/XCIR")
6087 (synopsis "Analysis of X chromosome inactivation")
6089 "This package is an R package that offers models and tools for subject
6090 level analysis of @dfn{X chromosome inactivation} (XCI) and XCI-escape
6092 (license license:gpl2))))
6094 (define-public r-xina
6101 (uri (bioconductor-uri "XINA" version))
6103 (base32 "03gf7mqpnwx12kny9fsaskgrw83b0wi2cf1j4dbq46pfxjx34v1g"))))
6104 (properties `((upstream-name . "XINA")))
6105 (build-system r-build-system)
6114 (native-inputs (list r-knitr))
6115 (home-page "https://git.bioconductor.org/packages/XINA")
6116 (synopsis "Identifying proteins that exhibit similar patterns")
6118 "The aim of @code{XINA} is to determine which proteins exhibit similar
6119 patterns within and across experimental conditions, since proteins with
6120 co-abundance patterns may have common molecular functions. @code{XINA} imports
6121 multiple datasets, tags dataset in silico, and combines the data for subsequent
6122 subgrouping into multiple clusters. The result is a single output depicting
6123 the variation across all conditions. @code{XINA} not only extracts
6124 coabundance profiles within and across experiments, but also incorporates
6125 protein-protein interaction databases and integrative resources such as
6126 @dfn{Kyoto encyclopedia of genes and genomes} (KEGG) to infer interactors and
6127 molecular functions, respectively, and produces intuitive graphical outputs.")
6128 (license license:gpl3)))
6130 (define-public r-xmapbridge
6132 (name "r-xmapbridge")
6137 (uri (bioconductor-uri "xmapbridge" version))
6139 (base32 "1n3nxc4jwxf5z32i70sza52nyk29adhp8vc3hac7r5b8mbi6gg10"))))
6140 (properties `((upstream-name . "xmapbridge")))
6141 (build-system r-build-system)
6142 (home-page "https://git.bioconductor.org/packages/xmapbridge")
6143 (synopsis "Display numeric data in the web based genome browser X:MAP")
6145 "The package @code{xmapbridge} can plot graphs in the X:Map genome
6146 browser. X:Map uses the Google Maps API to provide a scrollable view of the
6147 genome. It supports a number of species, and can be accessed at
6148 @url{http://xmap.picr.man.ac.uk}. This package exports plotting files in a
6149 suitable format. Graph plotting in R is done using calls to the functions
6150 @code{xmap.plot} and @code{xmap.points}, which have parameters that aim to be
6151 similar to those used by the standard plot methods in R. These result in data
6152 being written to a set of files (in a specific directory structure) that
6153 contain the data to be displayed, as well as some additional meta-data
6154 describing each of the graphs.")
6155 (license license:lgpl3)))
6157 (define-public r-xvector
6163 (uri (bioconductor-uri "XVector" version))
6166 "1f3sbqy279gb9k13l73j00ixywa1havlqy81zx766r1xkz15nvhk"))))
6168 `((upstream-name . "XVector")))
6169 (build-system r-build-system)
6172 (modify-phases %standard-phases
6173 (add-after 'unpack 'use-system-zlib
6175 (substitute* "DESCRIPTION"
6176 (("zlibbioc, ") ""))
6177 (substitute* "NAMESPACE"
6178 (("import\\(zlibbioc\\)") ""))
6183 (list r-biocgenerics r-iranges r-s4vectors))
6184 (home-page "https://bioconductor.org/packages/XVector")
6185 (synopsis "Representation and manpulation of external sequences")
6187 "This package provides memory efficient S4 classes for storing sequences
6188 \"externally\" (behind an R external pointer, or on disk).")
6189 (license license:artistic2.0)))
6191 (define-public r-zlibbioc
6197 (uri (bioconductor-uri "zlibbioc" version))
6200 "0w0y9jixdk6akmasn55g9g0nhlh93hbca5bwx5w1fypnvqrqpxzv"))))
6202 `((upstream-name . "zlibbioc")))
6203 (build-system r-build-system)
6204 (home-page "https://bioconductor.org/packages/zlibbioc")
6205 (synopsis "Provider for zlib-1.2.5 to R packages")
6206 (description "This package uses the source code of zlib-1.2.5 to create
6207 libraries for systems that do not have these available via other means.")
6208 (license license:artistic2.0)))
6210 (define-public r-zellkonverter
6212 (name "r-zellkonverter")
6217 (uri (bioconductor-uri "zellkonverter" version))
6219 (base32 "0l6v7a2zyxpq2w3vm85z439ldi3ld3pkc3wx95a1vxzbr31cpdzz"))))
6220 (properties `((upstream-name . "zellkonverter")))
6221 (build-system r-build-system)
6229 r-singlecellexperiment
6230 r-summarizedexperiment))
6231 (native-inputs (list r-knitr))
6232 (home-page "https://github.com/theislab/zellkonverter")
6233 (synopsis "Conversion between AnnData and single-cell experiments objects")
6235 "This package provides methods to convert between Python AnnData objects
6236 and SingleCellExperiment objects. These are primarily intended for use by
6237 downstream Bioconductor packages that wrap Python methods for single-cell data
6238 analysis. It also includes functions to read and write H5AD files used for
6239 saving AnnData objects to disk.")
6240 (license license:expat)))
6242 (define-public r-geneplotter
6244 (name "r-geneplotter")
6249 (uri (bioconductor-uri "geneplotter" version))
6252 "13230mzrdralnvf9jp032s16a8mk3kx5476nnvpa4pvcgp1i1ijc"))))
6253 (build-system r-build-system)
6261 (home-page "https://bioconductor.org/packages/geneplotter")
6262 (synopsis "Graphics functions for genomic data")
6264 "This package provides functions for plotting genomic data.")
6265 (license license:artistic2.0)))
6267 (define-public r-oligoclasses
6269 (name "r-oligoclasses")
6274 (uri (bioconductor-uri "oligoClasses" version))
6277 "1m4x50gl1fm5waa531v7ml0q229q65qn9cgiwnvjg721fvra7mdk"))))
6278 (properties `((upstream-name . "oligoClasses")))
6279 (build-system r-build-system)
6293 r-summarizedexperiment))
6294 (home-page "https://bioconductor.org/packages/oligoClasses/")
6295 (synopsis "Classes for high-throughput arrays")
6297 "This package contains class definitions, validity checks, and
6298 initialization methods for classes used by the @code{oligo} and @code{crlmm}
6300 (license license:gpl2+)))
6302 (define-public r-oligo
6309 (uri (bioconductor-uri "oligo" version))
6312 "0y7j96rafm9b85sxq2483i73685i3j67lk33fn8nfcav6lmsv5vy"))))
6313 (properties `((upstream-name . "oligo")))
6314 (build-system r-build-system)
6315 (inputs (list zlib))
6330 (home-page "https://bioconductor.org/packages/oligo/")
6331 (synopsis "Preprocessing tools for oligonucleotide arrays")
6333 "This package provides a package to analyze oligonucleotide
6334 arrays (expression/SNP/tiling/exon) at probe-level. It currently supports
6335 Affymetrix (CEL files) and NimbleGen arrays (XYS files).")
6336 (license license:lgpl2.0+)))
6338 (define-public r-qvalue
6345 (uri (bioconductor-uri "qvalue" version))
6348 "0cvhm5cldcnnxwa293dig1pj9lvj2hnz9zh4gfr25sw0xlcjzmyw"))))
6349 (build-system r-build-system)
6351 (list r-ggplot2 r-reshape2))
6354 (home-page "https://github.com/StoreyLab/qvalue")
6355 (synopsis "Q-value estimation for false discovery rate control")
6357 "This package takes a list of p-values resulting from the simultaneous
6358 testing of many hypotheses and estimates their q-values and local @dfn{false
6359 discovery rate} (FDR) values. The q-value of a test measures the proportion
6360 of false positives incurred when that particular test is called significant.
6361 The local FDR measures the posterior probability the null hypothesis is true
6362 given the test's p-value. Various plots are automatically generated, allowing
6363 one to make sensible significance cut-offs. The software can be applied to
6364 problems in genomics, brain imaging, astrophysics, and data mining.")
6365 ;; Any version of the LGPL.
6366 (license license:lgpl3+)))
6368 (define r-rcppnumerical
6370 (name "r-rcppnumerical")
6374 (uri (cran-uri "RcppNumerical" version))
6377 "1a92fql6mijhnr1kxkcxwivf95pk9lhgmhzkshs51h0ybfv5krik"))))
6378 (properties `((upstream-name . "RcppNumerical")))
6379 (build-system r-build-system)
6381 `(("r-rcpp" ,r-rcpp)
6382 ("r-rcppeigen" ,r-rcppeigen)))
6384 `(("r-knitr" ,r-knitr)))
6385 (home-page "https://github.com/yixuan/RcppNumerical")
6386 (synopsis "Rcpp integration for numerical computing libraries")
6387 (description "This package provides a collection of open source libraries
6388 for numerical computing (numerical integration, optimization, etc.) and their
6389 integration with @code{Rcpp}.")
6390 (license license:gpl2+)))
6392 (define-public r-apeglm
6398 (uri (bioconductor-uri "apeglm" version))
6401 "1ppwk4g66x46hpqsfsvhl12398d1srqr47nmp0y2gz212kff0rby"))))
6402 (properties `((upstream-name . "apeglm")))
6403 (build-system r-build-system)
6410 r-summarizedexperiment))
6411 (native-inputs (list r-knitr))
6412 (home-page "https://bioconductor.org/packages/apeglm")
6413 (synopsis "Approximate posterior estimation for GLM coefficients")
6414 (description "This package provides Bayesian shrinkage estimators for
6415 effect sizes for a variety of GLM models, using approximation of the
6416 posterior for individual coefficients.")
6417 (license license:gpl2)))
6419 (define-public r-greylistchip
6421 (name "r-greylistchip")
6425 (uri (bioconductor-uri "GreyListChIP" version))
6428 "0w52vwvjarql19bsv40b80yn701qx8c9d0clsjhj85wmzj2p6dhg"))))
6429 (properties `((upstream-name . "GreyListChIP")))
6430 (build-system r-build-system)
6439 r-summarizedexperiment))
6440 (home-page "https://bioconductor.org/packages/GreyListChIP")
6441 (synopsis "Greylist artefact regions based on ChIP inputs")
6442 (description "This package identifies regions of ChIP experiments with high
6443 signal in the input, that lead to spurious peaks during peak calling.")
6444 (license license:artistic2.0)))
6446 (define-public r-diffbind
6453 (uri (bioconductor-uri "DiffBind" version))
6456 "0izlk8vmmal4dj0bjxhgzr25arfa9zgdv06rm70w7ylr0gl84pzr"))))
6457 (properties `((upstream-name . "DiffBind")))
6458 (build-system r-build-system)
6481 r-summarizedexperiment
6483 (home-page "https://bioconductor.org/packages/DiffBind")
6484 (synopsis "Differential binding analysis of ChIP-Seq peak data")
6486 "This package computes differentially bound sites from multiple
6487 ChIP-seq experiments using affinity (quantitative) data. Also enables
6488 occupancy (overlap) analysis and plotting functions.")
6489 (license license:artistic2.0)))
6491 (define-public r-ripseeker
6493 (name "r-ripseeker")
6498 (uri (bioconductor-uri "RIPSeeker" version))
6501 "1wyv9mfrbxzklysfjcnwb8yils71janyyxa982jn0zxx4p9cl3vs"))))
6502 (properties `((upstream-name . "RIPSeeker")))
6503 (build-system r-build-system)
6508 r-summarizedexperiment
6512 (home-page "https://bioconductor.org/packages/RIPSeeker")
6514 "Identifying protein-associated transcripts from RIP-seq experiments")
6516 "This package infers and discriminates RIP peaks from RIP-seq alignments
6517 using two-state HMM with negative binomial emission probability. While
6518 RIPSeeker is specifically tailored for RIP-seq data analysis, it also provides
6519 a suite of bioinformatics tools integrated within this self-contained software
6520 package comprehensively addressing issues ranging from post-alignments
6521 processing to visualization and annotation.")
6522 (license license:gpl2)))
6524 (define-public r-mbkmeans
6530 (uri (bioconductor-uri "mbkmeans" version))
6533 "1f5krzlyqljz763vkp1a50danjn78xhn35s8qqdvzrmwyx0fzphg"))))
6534 (build-system r-build-system)
6548 r-singlecellexperiment
6549 r-summarizedexperiment))
6550 (home-page "https://bioconductor.org/packages/mbkmeans")
6551 (synopsis "Mini-batch k-means clustering for single-cell RNA-seq")
6552 (description "This package implements the mini-batch k-means algorithm for
6553 large datasets, including support for on-disk data representation.")
6554 (license license:expat)))
6556 (define-public r-multtest
6563 (uri (bioconductor-uri "multtest" version))
6566 "037wcmwk1wvhjxgmlvnk289pkwishi1753ajkmy9x14xlmldix82"))))
6567 (build-system r-build-system)
6569 (list r-survival r-biocgenerics r-biobase r-mass))
6570 (home-page "https://bioconductor.org/packages/multtest")
6571 (synopsis "Resampling-based multiple hypothesis testing")
6573 "This package can do non-parametric bootstrap and permutation
6574 resampling-based multiple testing procedures (including empirical Bayes
6575 methods) for controlling the family-wise error rate (FWER), generalized
6576 family-wise error rate (gFWER), tail probability of the proportion of
6577 false positives (TPPFP), and false discovery rate (FDR). Several choices
6578 of bootstrap-based null distribution are implemented (centered, centered
6579 and scaled, quantile-transformed). Single-step and step-wise methods are
6580 available. Tests based on a variety of T- and F-statistics (including
6581 T-statistics based on regression parameters from linear and survival models
6582 as well as those based on correlation parameters) are included. When probing
6583 hypotheses with T-statistics, users may also select a potentially faster null
6584 distribution which is multivariate normal with mean zero and variance
6585 covariance matrix derived from the vector influence function. Results are
6586 reported in terms of adjusted P-values, confidence regions and test statistic
6587 cutoffs. The procedures are directly applicable to identifying differentially
6588 expressed genes in DNA microarray experiments.")
6589 (license license:lgpl3)))
6591 (define-public r-graph
6597 (uri (bioconductor-uri "graph" version))
6600 "1b8hrjwjg82kicls1496fxfzv75xjvq2k6r9apzsd3qlbyg3ilg4"))))
6601 (build-system r-build-system)
6603 (list r-biocgenerics))
6604 (home-page "https://bioconductor.org/packages/graph")
6605 (synopsis "Handle graph data structures in R")
6607 "This package implements some simple graph handling capabilities for R.")
6608 (license license:artistic2.0)))
6610 ;; This is a CRAN package, but it depends on a Bioconductor package.
6611 (define-public r-ggm
6618 (uri (cran-uri "ggm" version))
6621 "11wc6k2kj2ydy0dyks5mbvbhxm1r43id87anl1jg6dn0yv4m78di"))))
6622 (properties `((upstream-name . "ggm")))
6623 (build-system r-build-system)
6625 (list r-graph r-igraph))
6626 (home-page "https://cran.r-project.org/package=ggm")
6627 (synopsis "Functions for graphical Markov models")
6629 "This package provides functions and datasets for maximum likelihood
6630 fitting of some classes of graphical Markov models.")
6631 (license license:gpl2+)))
6633 ;; This is a CRAN package, but it depends on a Bioconductor package, r-graph.
6634 (define-public r-perfmeas
6641 (uri (cran-uri "PerfMeas" version))
6644 "1x7ancmb41zd1js24rx94plgbssyc71z2bvpic6mg34xjkwdjw93"))))
6645 (properties `((upstream-name . "PerfMeas")))
6646 (build-system r-build-system)
6648 (list r-graph r-limma r-rbgl))
6649 (home-page "https://cran.r-project.org/web/packages/PerfMeas/")
6650 (synopsis "Performance measures for ranking and classification tasks")
6652 "This package implements different performance measures for
6653 classification and ranking tasks. @dfn{Area under curve} (AUC), precision at
6654 a given recall, F-score for single and multiple classes are available.")
6655 (license license:gpl2+)))
6657 ;; This is a CRAN package, but it depends on a Bioconductor package.
6658 (define-public r-codedepends
6660 (name "r-codedepends")
6665 (uri (cran-uri "CodeDepends" version))
6668 "0l7kiv3awx50glf5cs841b4zzsff1ml90f0zr868ygvwsr4ps1hq"))))
6669 (properties `((upstream-name . "CodeDepends")))
6670 (build-system r-build-system)
6672 (list r-codetools r-graph r-xml))
6673 (home-page "https://cran.r-project.org/web/packages/CodeDepends")
6674 (synopsis "Analysis of R code for reproducible research and code comprehension")
6676 "This package provides tools for analyzing R expressions or blocks of
6677 code and determining the dependencies between them. It focuses on R scripts,
6678 but can be used on the bodies of functions. There are many facilities
6679 including the ability to summarize or get a high-level view of code,
6680 determining dependencies between variables, code improvement suggestions.")
6681 ;; Any version of the GPL
6682 (license (list license:gpl2+ license:gpl3+))))
6684 (define-public r-chippeakanno
6686 (name "r-chippeakanno")
6691 (uri (bioconductor-uri "ChIPpeakAnno" version))
6694 "0a26glldxczcfymjvd45gv5m4hympziivm6wwx4ab9wld7n43l8y"))))
6695 (properties `((upstream-name . "ChIPpeakAnno")))
6696 (build-system r-build-system)
6698 (list r-annotationdbi
6721 r-summarizedexperiment
6725 (home-page "https://bioconductor.org/packages/ChIPpeakAnno")
6726 (synopsis "Peaks annotation from ChIP-seq and ChIP-chip experiments")
6728 "The package includes functions to retrieve the sequences around the peak,
6729 obtain enriched Gene Ontology (GO) terms, find the nearest gene, exon, miRNA or
6730 custom features such as most conserved elements and other transcription factor
6731 binding sites supplied by users. Starting 2.0.5, new functions have been added
6732 for finding the peaks with bi-directional promoters with summary statistics
6733 (peaksNearBDP), for summarizing the occurrence of motifs in peaks
6734 (summarizePatternInPeaks) and for adding other IDs to annotated peaks or
6735 enrichedGO (addGeneIDs).")
6736 (license license:gpl2+)))
6738 (define-public r-matrixgenerics
6740 (name "r-matrixgenerics")
6744 (uri (bioconductor-uri "MatrixGenerics" version))
6747 "1liblnpziyyjxzrhdd5d89ilvfqqhbl87h3hsmdm0kwnmc73r37f"))))
6749 `((upstream-name . "MatrixGenerics")))
6750 (build-system r-build-system)
6752 (list r-matrixstats))
6753 (home-page "https://bioconductor.org/packages/MatrixGenerics")
6754 (synopsis "S4 generic summary statistic functions for matrix-like objects")
6756 "This package provides S4 generic functions modeled after the
6757 @code{matrixStats} API for alternative matrix implementations. Packages with
6758 alternative matrix implementation can depend on this package and implement the
6759 generic functions that are defined here for a useful set of row and column
6760 summary statistics. Other package developers can import this package and
6761 handle a different matrix implementations without worrying about
6762 incompatibilities.")
6763 (license license:artistic2.0)))
6765 (define-public r-marray
6771 (uri (bioconductor-uri "marray" version))
6773 (base32 "0awfz0akz3sylyw1jxhxgadv1rqdzvy9v11933yxkl9a8m9ngm8i"))))
6774 (build-system r-build-system)
6777 (home-page "https://bioconductor.org/packages/marray")
6778 (synopsis "Exploratory analysis for two-color spotted microarray data")
6779 (description "This package contains class definitions for two-color spotted
6780 microarray data. It also includes functions for data input, diagnostic plots,
6781 normalization and quality checking.")
6782 (license license:lgpl2.0+)))
6784 (define-public r-cghbase
6790 (uri (bioconductor-uri "CGHbase" version))
6792 (base32 "1q8yy60r4g5nyv2gbfdgk192xd73c0rrjr668d5616ddb7sx8wcr"))))
6793 (properties `((upstream-name . "CGHbase")))
6794 (build-system r-build-system)
6796 (list r-biobase r-marray))
6797 (home-page "https://bioconductor.org/packages/CGHbase")
6798 (synopsis "Base functions and classes for arrayCGH data analysis")
6799 (description "This package contains functions and classes that are needed by
6800 the @code{arrayCGH} packages.")
6801 (license license:gpl2+)))
6803 (define-public r-cghcall
6809 (uri (bioconductor-uri "CGHcall" version))
6811 (base32 "1qpsibp4gb09sn6fkwwrdjkh3a28lqfbk18c6fvn4m386j96ps65"))))
6812 (properties `((upstream-name . "CGHcall")))
6813 (build-system r-build-system)
6815 (list r-biobase r-cghbase r-impute r-dnacopy r-snowfall))
6816 (home-page "https://bioconductor.org/packages/CGHcall")
6817 (synopsis "Base functions and classes for arrayCGH data analysis")
6818 (description "This package contains functions and classes that are needed by
6819 @code{arrayCGH} packages.")
6820 (license license:gpl2+)))
6822 (define-public r-qdnaseq
6828 (uri (bioconductor-uri "QDNAseq" version))
6830 (base32 "0s360s72lfn9vjml88gg1m40n61s0dc66ilzgfjdcp65djdxxfvm"))))
6831 (properties `((upstream-name . "QDNAseq")))
6832 (build-system r-build-system)
6844 (home-page "https://bioconductor.org/packages/QDNAseq")
6845 (synopsis "Quantitative DNA sequencing for chromosomal aberrations")
6846 (description "The genome is divided into non-overlapping fixed-sized bins,
6847 number of sequence reads in each counted, adjusted with a simultaneous
6848 two-dimensional loess correction for sequence mappability and GC content, and
6849 filtered to remove spurious regions in the genome. Downstream steps of
6850 segmentation and calling are also implemented via packages DNAcopy and CGHcall,
6852 (license license:gpl2+)))
6854 (define-public r-bayseq
6861 (uri (bioconductor-uri "baySeq" version))
6864 "1yqykndyv32s2rk7x86qf410qr0pigc8z4gdkl8vhj4dgyr47n2j"))))
6865 (properties `((upstream-name . "baySeq")))
6866 (build-system r-build-system)
6868 (list r-abind r-edger r-genomicranges))
6869 (home-page "https://bioconductor.org/packages/baySeq/")
6870 (synopsis "Bayesian analysis of differential expression patterns in count data")
6872 "This package identifies differential expression in high-throughput count
6873 data, such as that derived from next-generation sequencing machines,
6874 calculating estimated posterior likelihoods of differential expression (or
6875 more complex hypotheses) via empirical Bayesian methods.")
6876 (license license:gpl3)))
6878 (define-public r-chipcomp
6885 (uri (bioconductor-uri "ChIPComp" version))
6888 "06q34y59gf1iz0rs7y5x8ndy1wa95j65rfmz37aym5c46ijqsnq0"))))
6889 (properties `((upstream-name . "ChIPComp")))
6890 (build-system r-build-system)
6892 (list r-biocgenerics
6893 r-bsgenome-hsapiens-ucsc-hg19
6894 r-bsgenome-mmusculus-ucsc-mm9
6902 (home-page "https://bioconductor.org/packages/ChIPComp")
6903 (synopsis "Quantitative comparison of multiple ChIP-seq datasets")
6905 "ChIPComp implements a statistical method for quantitative comparison of
6906 multiple ChIP-seq datasets. It detects differentially bound sharp binding
6907 sites across multiple conditions considering matching control in ChIP-seq
6909 ;; Any version of the GPL.
6910 (license license:gpl3+)))
6912 (define-public r-riboprofiling
6914 (name "r-riboprofiling")
6919 (uri (bioconductor-uri "RiboProfiling" version))
6922 "08m4rc530bkzcc43iwzg2fw9cjlf4wc2d8akv5vblsb42xdn8sqp"))))
6923 (properties `((upstream-name . "RiboProfiling")))
6924 (build-system r-build-system)
6926 (list r-biocgenerics
6944 (home-page "https://bioconductor.org/packages/RiboProfiling/")
6945 (synopsis "Ribosome profiling data analysis")
6946 (description "Starting with a BAM file, this package provides the
6947 necessary functions for quality assessment, read start position recalibration,
6948 the counting of genomic sequence reads on CDS, 3'UTR, and 5'UTR, and plotting
6949 of count data: pairs, log fold-change, codon frequency and coverage
6950 assessment, principal component analysis on codon coverage.")
6951 (license license:gpl3)))
6953 (define-public r-riboseqr
6960 (uri (bioconductor-uri "riboSeqR" version))
6963 "1zs3y0icsqrndjp9wwqz3jxysvyc9pch45y49j6g9b5b2l44ma26"))))
6964 (properties `((upstream-name . "riboSeqR")))
6965 (build-system r-build-system)
6974 (home-page "https://bioconductor.org/packages/riboSeqR/")
6975 (synopsis "Analysis of sequencing data from ribosome profiling experiments")
6977 "This package provides plotting functions, frameshift detection and
6978 parsing of genetic sequencing data from ribosome profiling experiments.")
6979 (license license:gpl3)))
6981 (define-public r-interactionset
6983 (name "r-interactionset")
6988 (uri (bioconductor-uri "InteractionSet" version))
6991 "0qjimx25jvm8siq8hmlbf2z6mknzpbq945p06fsj826k57bpcsm5"))))
6993 `((upstream-name . "InteractionSet")))
6994 (build-system r-build-system)
6996 (list r-biocgenerics
7003 r-summarizedexperiment))
7006 (home-page "https://bioconductor.org/packages/InteractionSet")
7007 (synopsis "Base classes for storing genomic interaction data")
7009 "This package provides the @code{GInteractions},
7010 @code{InteractionSet} and @code{ContactMatrix} objects and associated methods
7011 for storing and manipulating genomic interaction data from Hi-C and ChIA-PET
7013 (license license:gpl3)))
7015 (define-public r-genomicinteractions
7017 (name "r-genomicinteractions")
7022 (uri (bioconductor-uri "GenomicInteractions" version))
7025 "0aph1hja5vfprxs3jl4zd1inhvih6m3v1p3jkm6w7xpj3jzvmgbx"))))
7027 `((upstream-name . "GenomicInteractions")))
7028 (build-system r-build-system)
7048 (home-page "https://github.com/ComputationalRegulatoryGenomicsICL/GenomicInteractions/")
7049 (synopsis "R package for handling genomic interaction data")
7051 "This R package provides tools for handling genomic interaction data,
7052 such as ChIA-PET/Hi-C, annotating genomic features with interaction
7053 information and producing various plots and statistics.")
7054 (license license:gpl3)))
7056 (define-public r-ctc
7063 (uri (bioconductor-uri "ctc" version))
7066 "0c9pgp25dqx12fmi4cqm7xyxjmy6g7wv9vbljgdjghaij2lrc4pb"))))
7067 (build-system r-build-system)
7068 (propagated-inputs (list r-amap))
7069 (home-page "https://bioconductor.org/packages/ctc/")
7070 (synopsis "Cluster and tree conversion")
7072 "This package provides tools for exporting and importing classification
7073 trees and clusters to other programs.")
7074 (license license:gpl2)))
7076 (define-public r-goseq
7083 (uri (bioconductor-uri "goseq" version))
7086 "1w0rwzhqkvp2x7y5v0qcyjbss0p95gb1jrnx5sdkqginbvrmrd48"))))
7087 (build-system r-build-system)
7089 (list r-annotationdbi
7095 (home-page "https://bioconductor.org/packages/goseq/")
7096 (synopsis "Gene Ontology analyser for RNA-seq and other length biased data")
7098 "This package provides tools to detect Gene Ontology and/or other user
7099 defined categories which are over/under represented in RNA-seq data.")
7100 (license license:lgpl2.0+)))
7102 (define-public r-glimma
7109 (uri (bioconductor-uri "Glimma" version))
7112 "1k17ay09vhb2hakg1vrgvpp1zliavlj7cdkxaal162bc3v8pyvyz"))))
7113 (properties `((upstream-name . "Glimma")))
7114 (build-system r-build-system)
7122 r-summarizedexperiment))
7125 (home-page "https://github.com/Shians/Glimma")
7126 (synopsis "Interactive HTML graphics")
7128 "This package generates interactive visualisations for analysis of
7129 RNA-sequencing data using output from limma, edgeR or DESeq2 packages in an
7130 HTML page. The interactions are built on top of the popular static
7131 representations of analysis results in order to provide additional
7133 (license license:lgpl3)))
7135 (define-public r-rots
7142 (uri (bioconductor-uri "ROTS" version))
7145 "021a578p8kcl5yd9myiy0h2qp10r30ggnip2kp6xs7dx8nzic96r"))))
7146 (properties `((upstream-name . "ROTS")))
7147 (build-system r-build-system)
7149 (list r-biobase r-rcpp))
7150 (home-page "https://bioconductor.org/packages/ROTS/")
7151 (synopsis "Reproducibility-Optimized Test Statistic")
7153 "This package provides tools for calculating the
7154 @dfn{Reproducibility-Optimized Test Statistic} (ROTS) for differential testing
7156 (license license:gpl2+)))
7158 (define-public r-plgem
7165 (uri (bioconductor-uri "plgem" version))
7168 "07zxflxcay17hxjw3wh5kfdwl2x8537csb18p1qzmyrkvscnja77"))))
7169 (build-system r-build-system)
7171 (list r-biobase r-mass))
7172 (home-page "http://www.genopolis.it")
7173 (synopsis "Detect differential expression in microarray and proteomics datasets")
7175 "The Power Law Global Error Model (PLGEM) has been shown to faithfully
7176 model the variance-versus-mean dependence that exists in a variety of
7177 genome-wide datasets, including microarray and proteomics data. The use of
7178 PLGEM has been shown to improve the detection of differentially expressed
7179 genes or proteins in these datasets.")
7180 (license license:gpl2)))
7182 (define-public r-inspect
7189 (uri (bioconductor-uri "INSPEcT" version))
7192 "0jx887vhxwd8zlqajr9czvn9nx88ryyxlnl58hxrlajjpcjkz9ax"))))
7193 (properties `((upstream-name . "INSPEcT")))
7194 (build-system r-build-system)
7215 r-summarizedexperiment
7216 r-txdb-mmusculus-ucsc-mm9-knowngene))
7219 (home-page "https://bioconductor.org/packages/INSPEcT")
7220 (synopsis "Analysis of 4sU-seq and RNA-seq time-course data")
7222 "INSPEcT (INference of Synthesis, Processing and dEgradation rates in
7223 Time-Course experiments) analyses 4sU-seq and RNA-seq time-course data in
7224 order to evaluate synthesis, processing and degradation rates and assess via
7225 modeling the rates that determines changes in mature mRNA levels.")
7226 (license license:gpl2)))
7228 (define-public r-dnabarcodes
7230 (name "r-dnabarcodes")
7235 (uri (bioconductor-uri "DNABarcodes" version))
7238 "0n2qlvpcjhrxr3br27gz9vhwcpf7sn6g4xdjazvvi3gqcgk90xc6"))))
7239 (properties `((upstream-name . "DNABarcodes")))
7240 (build-system r-build-system)
7242 (list r-bh r-matrix r-rcpp))
7245 (home-page "https://bioconductor.org/packages/DNABarcodes")
7246 (synopsis "Create and analyze DNA barcodes")
7248 "This package offers tools to create DNA barcode sets capable of
7249 correcting insertion, deletion, and substitution errors. Existing barcodes
7250 can be analyzed regarding their minimal, maximal and average distances between
7251 barcodes. Finally, reads that start with a (possibly mutated) barcode can be
7252 demultiplexed, i.e. assigned to their original reference barcode.")
7253 (license license:gpl2)))
7255 (define-public r-ruvseq
7262 (uri (bioconductor-uri "RUVSeq" version))
7265 "001h07b074hvj16bjdp9llb9psphw7r6kpwhq61bj4519y6lpg7x"))))
7266 (properties `((upstream-name . "RUVSeq")))
7267 (build-system r-build-system)
7269 (list r-biobase r-edaseq r-edger r-mass))
7272 (home-page "https://github.com/drisso/RUVSeq")
7273 (synopsis "Remove unwanted variation from RNA-Seq data")
7275 "This package implements methods to @dfn{remove unwanted variation} (RUV)
7276 of Risso et al. (2014) for the normalization of RNA-Seq read counts between
7278 (license license:artistic2.0)))
7280 (define-public r-biocneighbors
7282 (name "r-biocneighbors")
7287 (uri (bioconductor-uri "BiocNeighbors" version))
7290 "1a43hzmcpxviqa9723hkafr6gm358amfpqj9d56imclkkfkdz95x"))))
7291 (properties `((upstream-name . "BiocNeighbors")))
7292 (build-system r-build-system)
7294 (list r-biocparallel r-matrix r-rcpp r-rcpphnsw r-s4vectors))
7297 (home-page "https://bioconductor.org/packages/BiocNeighbors")
7298 (synopsis "Nearest Neighbor Detection for Bioconductor packages")
7300 "This package implements exact and approximate methods for nearest
7301 neighbor detection, in a framework that allows them to be easily switched
7302 within Bioconductor packages or workflows. The exact algorithm is implemented
7303 using pre-clustering with the k-means algorithm. Functions are also provided
7304 to search for all neighbors within a given distance. Parallelization is
7305 achieved for all methods using the BiocParallel framework.")
7306 (license license:gpl3)))
7308 (define-public r-scaledmatrix
7310 (name "r-scaledmatrix")
7315 (uri (bioconductor-uri "ScaledMatrix" version))
7318 "0p6065mbn77hphpjfchz3r3raspl127f11n39mwh9bih4zg375cl"))))
7319 (properties `((upstream-name . "ScaledMatrix")))
7320 (build-system r-build-system)
7322 (list r-delayedarray r-matrix r-s4vectors))
7323 (native-inputs (list r-knitr))
7324 (home-page "https://github.com/LTLA/ScaledMatrix")
7325 (synopsis "Create a DelayedMatrix of scaled and centered values")
7327 "This package provides delayed computation of a matrix of scaled and
7328 centered values. The result is equivalent to using the @code{scale} function
7329 but avoids explicit realization of a dense matrix during block processing.
7330 This permits greater efficiency in common operations, most notably matrix
7332 (license license:gpl3)))
7334 (define-public r-treeio
7341 (uri (bioconductor-uri "treeio" version))
7344 "1hc5m0b2qqxrh3z0inny2jizrpn9d4yn9pn3k1h18xb4ggyijyla"))))
7345 (properties `((upstream-name . "treeio")))
7346 (build-system r-build-system)
7355 (native-inputs (list r-knitr))
7356 (home-page "https://github.com/YuLab-SMU/treeio")
7357 (synopsis "Base classes and functions for Phylogenetic tree input and output")
7359 "This is an R package to make it easier to import and store phylogenetic
7360 trees with associated data; and to link external data from different sources
7361 to phylogeny. It also supports exporting phylogenetic trees with
7362 heterogeneous associated data to a single tree file and can be served as a
7363 platform for merging tree with associated data and converting file formats.")
7364 (license license:artistic2.0)))
7366 (define-public r-ggtree
7373 (uri (bioconductor-uri "ggtree" version))
7376 "033r748npv0l72yb9sk6lqnj0l7cd36ykf788145qv8ck5i2gyk4"))))
7377 (properties `((upstream-name . "ggtree")))
7378 (build-system r-build-system)
7393 (native-inputs (list r-knitr))
7394 (home-page "https://yulab-smu.top/treedata-book/")
7395 (synopsis "R package for visualization of trees and annotation data")
7397 "This package extends the ggplot2 plotting system which implements a
7398 grammar of graphics. ggtree is designed for visualization and annotation of
7399 phylogenetic trees and other tree-like structures with their annotation
7401 (license license:artistic2.0)))
7403 (define-public r-metapod
7410 (uri (bioconductor-uri "metapod" version))
7413 "19g9c08alg4qqr710si465wlb5dy759m5d8wn91zwj24077dds7b"))))
7414 (properties `((upstream-name . "metapod")))
7415 (build-system r-build-system)
7420 (home-page "https://bioconductor.org/packages/metapod")
7421 (synopsis "Meta-analyses on p-values of differential analyses")
7423 "This package implements a variety of methods for combining p-values in
7424 differential analyses of genome-scale datasets. Functions can combine
7425 p-values across different tests in the same analysis (e.g., genomic windows in
7426 ChIP-seq, exons in RNA-seq) or for corresponding tests across separate
7427 analyses (e.g., replicated comparisons, effect of different treatment
7428 conditions). Support is provided for handling log-transformed input p-values,
7429 missing values and weighting where appropriate.")
7430 (license license:gpl3)))
7432 (define-public r-biocsingular
7434 (name "r-biocsingular")
7439 (uri (bioconductor-uri "BiocSingular" version))
7442 "1sraycnn0jahpi8kni1y8ik00ga89fvwqjmbr8388968q22mvm3x"))))
7443 (properties `((upstream-name . "BiocSingular")))
7444 (build-system r-build-system)
7458 (home-page "https://github.com/LTLA/BiocSingular")
7459 (synopsis "Singular value decomposition for Bioconductor packages")
7461 "This package implements exact and approximate methods for singular value
7462 decomposition and principal components analysis, in a framework that allows
7463 them to be easily switched within Bioconductor packages or workflows. Where
7464 possible, parallelization is achieved using the BiocParallel framework.")
7465 (license license:gpl3)))
7467 (define-public r-destiny
7474 (uri (bioconductor-uri "destiny" version))
7477 "1c85ky5ggdsi0ab1l4ipl85gc1kj1zv3wp08qrvslax3z0yw0ljy"))))
7478 (build-system r-build-system)
7496 r-singlecellexperiment
7498 r-summarizedexperiment
7503 (list r-knitr r-nbconvertr)) ; for vignettes
7504 (home-page "https://bioconductor.org/packages/destiny/")
7505 (synopsis "Create and plot diffusion maps")
7506 (description "This package provides tools to create and plot diffusion
7508 ;; Any version of the GPL
7509 (license license:gpl3+)))
7511 (define-public r-savr
7518 (uri (bioconductor-uri "savR" version))
7521 "04zlf3lyr6vnpj80m6fd2is2f7302sxwih8nzzjnc4ss972jid2k"))))
7522 (properties `((upstream-name . "savR")))
7523 (build-system r-build-system)
7525 (list r-ggplot2 r-gridextra r-reshape2 r-scales r-xml))
7526 (home-page "https://github.com/bcalder/savR")
7527 (synopsis "Parse and analyze Illumina SAV files")
7529 "This package provides tools to parse Illumina Sequence Analysis
7530 Viewer (SAV) files, access data, and generate QC plots.")
7531 (license license:agpl3+)))
7533 (define-public r-chipexoqual
7535 (name "r-chipexoqual")
7540 (uri (bioconductor-uri "ChIPexoQual" version))
7543 "1r4s8awvwwj1g33jpnzfxji23mfy0chkhi14i0ml5sh090xijpaz"))))
7544 (properties `((upstream-name . "ChIPexoQual")))
7545 (build-system r-build-system)
7547 (list r-biocparallel
7566 (home-page "https://github.com/keleslab/ChIPexoQual")
7567 (synopsis "Quality control pipeline for ChIP-exo/nexus data")
7569 "This package provides a quality control pipeline for ChIP-exo/nexus
7571 (license license:gpl2+)))
7573 (define-public r-copynumber
7575 (name "r-copynumber")
7579 (uri (bioconductor-uri "copynumber" version))
7582 "1gr8q9ri49x8qlmbsi6k6wcak1w9v48wr1qy7axc86brzx6z6mhd"))))
7583 (build-system r-build-system)
7585 (list r-s4vectors r-iranges r-genomicranges r-biocgenerics))
7586 (home-page "https://bioconductor.org/packages/copynumber")
7587 (synopsis "Segmentation of single- and multi-track copy number data")
7589 "This package segments single- and multi-track copy number data by a
7590 penalized least squares regression method.")
7591 (license license:artistic2.0)))
7593 (define-public r-dnacopy
7600 (uri (bioconductor-uri "DNAcopy" version))
7603 "10bh4p8nbl84rfngsm3bi9w542m159kff95f8c2hvjcxv5yw7iwc"))))
7604 (properties `((upstream-name . "DNAcopy")))
7605 (build-system r-build-system)
7606 (native-inputs (list gfortran))
7607 (home-page "https://bioconductor.org/packages/DNAcopy")
7608 (synopsis "DNA copy number data analysis")
7610 "This package implements the @dfn{circular binary segmentation} (CBS)
7611 algorithm to segment DNA copy number data and identify genomic regions with
7612 abnormal copy number.")
7613 (license license:gpl2+)))
7615 ;; This is a CRAN package, but it uncharacteristically depends on a
7616 ;; Bioconductor package.
7617 (define-public r-htscluster
7619 (name "r-htscluster")
7624 (uri (cran-uri "HTSCluster" version))
7627 "0wnbfh6hdx8692jilgmv8sys1zm6fqc6mim7vvjhyqlmpm8gm0kg"))))
7628 (properties `((upstream-name . "HTSCluster")))
7629 (build-system r-build-system)
7631 (list r-capushe r-edger r-plotrix))
7632 (home-page "https://cran.r-project.org/web/packages/HTSCluster")
7633 (synopsis "Clustering high-throughput transcriptome sequencing (HTS) data")
7635 "This package provides a Poisson mixture model is implemented to cluster
7636 genes from high-throughput transcriptome sequencing (RNA-seq) data. Parameter
7637 estimation is performed using either the EM or CEM algorithm, and the slope
7638 heuristics are used for model selection (i.e., to choose the number of
7640 (license license:gpl3+)))
7642 (define-public r-deds
7649 (uri (bioconductor-uri "DEDS" version))
7652 "0vzsmah2lhxf8k6n4d0i4j609sbvygmb6ii2ridg9z3nskwkrhp8"))))
7653 (properties `((upstream-name . "DEDS")))
7654 (build-system r-build-system)
7655 (home-page "https://bioconductor.org/packages/DEDS/")
7656 (synopsis "Differential expression via distance summary for microarray data")
7658 "This library contains functions that calculate various statistics of
7659 differential expression for microarray data, including t statistics, fold
7660 change, F statistics, SAM, moderated t and F statistics and B statistics. It
7661 also implements a new methodology called DEDS (Differential Expression via
7662 Distance Summary), which selects differentially expressed genes by integrating
7663 and summarizing a set of statistics using a weighted distance approach.")
7664 ;; Any version of the LGPL.
7665 (license license:lgpl3+)))
7667 ;; This is a CRAN package, but since it depends on a Bioconductor package we
7669 (define-public r-nbpseq
7676 (uri (cran-uri "NBPSeq" version))
7679 "07mnnk4n0cyksp1mw36y6369is62kxsfg3wb8d3dwswycdmj8m14"))))
7680 (properties `((upstream-name . "NBPSeq")))
7681 (build-system r-build-system)
7684 (home-page "https://cran.r-project.org/web/packages/NBPSeq")
7685 (synopsis "Negative binomial models for RNA-Seq data")
7687 "This package provides negative binomial models for two-group comparisons
7688 and regression inferences from RNA-sequencing data.")
7689 (license license:gpl2)))
7691 (define-public r-ebseq
7698 (uri (bioconductor-uri "EBSeq" version))
7701 "192xl9fwsh04w563yk33mfl303d1kqby2ssbqkckqsdr4jb7d57y"))))
7702 (properties `((upstream-name . "EBSeq")))
7703 (build-system r-build-system)
7705 (list r-blockmodeling r-gplots r-testthat))
7706 (home-page "https://bioconductor.org/packages/EBSeq")
7707 (synopsis "Differential expression analysis of RNA-seq data")
7709 "This package provides tools for differential expression analysis at both
7710 gene and isoform level using RNA-seq data")
7711 (license license:artistic2.0)))
7713 (define-public r-karyoploter
7715 (name "r-karyoploter")
7719 (uri (bioconductor-uri "karyoploteR" version))
7722 "0hawq9wi3ikvlcdgnjfy5fiiwfq22zwx1p8xf5h4bpypp96pknsk"))))
7723 (build-system r-build-system)
7725 (list r-annotationdbi
7739 r-variantannotation))
7742 (home-page "https://bioconductor.org/packages/karyoploteR/")
7743 (synopsis "Plot customizable linear genomes displaying arbitrary data")
7744 (description "This package creates karyotype plots of arbitrary genomes and
7745 offers a complete set of functions to plot arbitrary data on them. It mimics
7746 many R base graphics functions coupling them with a coordinate change function
7747 automatically mapping the chromosome and data coordinates into the plot
7749 (license license:artistic2.0)))
7751 (define-public r-lpsymphony
7753 (name "r-lpsymphony")
7758 (uri (bioconductor-uri "lpsymphony" version))
7761 "0kc708ss5byzw8qh439mb4nq6hsfmz73gfamiznw3lv352brd33g"))))
7762 (build-system r-build-system)
7766 (list pkg-config r-knitr))
7767 (home-page "https://r-forge.r-project.org/projects/rsymphony")
7768 (synopsis "Symphony integer linear programming solver in R")
7770 "This package was derived from Rsymphony. The package provides an R
7771 interface to SYMPHONY, a linear programming solver written in C++. The main
7772 difference between this package and Rsymphony is that it includes the solver
7773 source code, while Rsymphony expects to find header and library files on the
7774 users' system. Thus the intention of @code{lpsymphony} is to provide an easy
7775 to install interface to SYMPHONY.")
7776 ;; Symphony 5.4 or later is distributed under the terms of the EPL 1.0.
7777 ;; lpsimphony is released under the same terms.
7778 (license license:epl1.0)))
7780 (define-public r-ihw
7787 (uri (bioconductor-uri "IHW" version))
7790 "1gsfy75dz7xh16z844llcmjnp0a0ridszmrbbv2bdaa43na5msmf"))))
7791 (properties `((upstream-name . "IHW")))
7792 (build-system r-build-system)
7794 (list r-biocgenerics r-fdrtool r-lpsymphony r-slam))
7797 (home-page "https://bioconductor.org/packages/IHW")
7798 (synopsis "Independent hypothesis weighting")
7800 "@dfn{Independent hypothesis weighting} (IHW) is a multiple testing
7801 procedure that increases power compared to the method of Benjamini and
7802 Hochberg by assigning data-driven weights to each hypothesis. The input to
7803 IHW is a two-column table of p-values and covariates. The covariate can be
7804 any continuous-valued or categorical variable that is thought to be
7805 informative on the statistical properties of each hypothesis test, while it is
7806 independent of the p-value under the null hypothesis.")
7807 (license license:artistic2.0)))
7809 (define-public r-icobra
7816 (uri (bioconductor-uri "iCOBRA" version))
7819 "1gvra5bgsf6lvs4f2md3xx7xxsx4j8079c2nr8vz9lvy2sfyl6s9"))))
7820 (properties `((upstream-name . "iCOBRA")))
7821 (build-system r-build-system)
7837 (home-page "https://bioconductor.org/packages/iCOBRA")
7838 (synopsis "Comparison and visualization of ranking and assignment methods")
7840 "This package provides functions for calculation and visualization of
7841 performance metrics for evaluation of ranking and binary
7842 classification (assignment) methods. It also contains a Shiny application for
7843 interactive exploration of results.")
7844 (license license:gpl2+)))
7846 (define-public r-residualmatrix
7848 (name "r-residualmatrix")
7853 (uri (bioconductor-uri "ResidualMatrix" version))
7856 "1pjr3gva0jwj2pgqr4k4nl1ir1153hhrk1d400r30w0di472hns4"))))
7858 `((upstream-name . "ResidualMatrix")))
7859 (build-system r-build-system)
7861 (list r-delayedarray r-matrix r-s4vectors))
7864 (home-page "https://github.com/LTLA/ResidualMatrix")
7865 (synopsis "Create a DelayedMatrix of regression residuals")
7867 "This package implements tools for delayed computation of a matrix of
7868 residuals after fitting a linear model to each column of an input matrix. It
7869 also supports partial computation of residuals where selected factors are to
7870 be preserved in the output matrix. It implements a number of efficient
7871 methods for operating on the delayed matrix of residuals, most notably matrix
7872 multiplication and calculation of row/column sums or means.")
7873 (license license:gpl3)))
7875 (define-public r-batchelor
7877 (name "r-batchelor")
7882 (uri (bioconductor-uri "batchelor" version))
7885 "00ix3hvhgalxg63qnynv2waa273jk336lg47k72qwxfzimsxfjxc"))))
7886 (properties `((upstream-name . "batchelor")))
7887 (build-system r-build-system)
7895 r-delayedmatrixstats
7903 r-singlecellexperiment
7904 r-summarizedexperiment))
7905 (native-inputs (list r-knitr))
7906 (home-page "https://bioconductor.org/packages/batchelor")
7907 (synopsis "Single-Cell Batch Correction Methods")
7909 "This package implements a variety of methods for batch correction of
7910 single-cell (RNA sequencing) data. This includes methods based on detecting
7911 mutually nearest neighbors, as well as several efficient variants of linear
7912 regression of the log-expression values. Functions are also provided to
7913 perform global rescaling to remove differences in depth between batches, and
7914 to perform a principal components analysis that is robust to differences in
7915 the numbers of cells across batches.")
7916 (license license:gpl3)))
7918 (define-public r-mast
7925 (uri (bioconductor-uri "MAST" version))
7928 "1kmrqxcfzzcs8l33n9qn0vahc6wxq6ks3cjx95vg96maf2qzhzzi"))))
7929 (properties `((upstream-name . "MAST")))
7930 (build-system r-build-system)
7941 r-singlecellexperiment
7943 r-summarizedexperiment))
7946 (home-page "https://github.com/RGLab/MAST/")
7947 (synopsis "Model-based analysis of single cell transcriptomics")
7949 "This package provides methods and models for handling zero-inflated
7950 single cell assay data.")
7951 (license license:gpl2+)))
7953 (define-public r-monocle
7960 (uri (bioconductor-uri "monocle" version))
7963 "11g1wx0f1yzhg3x1aa3d5l7pqlzxj16s0gha21skxkgld8k2x8xn"))))
7964 (build-system r-build-system)
7998 (home-page "https://bioconductor.org/packages/monocle")
7999 (synopsis "Clustering, differential expression, and trajectory analysis for single-cell RNA-Seq")
8001 "Monocle performs differential expression and time-series analysis for
8002 single-cell expression experiments. It orders individual cells according to
8003 progress through a biological process, without knowing ahead of time which
8004 genes define progress through that process. Monocle also performs
8005 differential expression analysis, clustering, visualization, and other useful
8006 tasks on single cell expression data. It is designed to work with RNA-Seq and
8007 qPCR data, but could be used with other types as well.")
8008 (license license:artistic2.0)))
8010 (define-public r-leidenbase
8011 (let ((commit "a11b8455fa3307d9e3ac4e3a5accddf3c83b9a96")
8014 (name "r-leidenbase")
8015 (version (git-version "0.1.9" revision commit))
8020 (url "https://github.com/cole-trapnell-lab/leidenbase")
8022 (file-name (git-file-name name version))
8025 "1f54mycsffvzmblz5pzgs3v4jygnbvz0c9d3x710gw5mxkq2p84f"))))
8026 (properties `((upstream-name . "leidenbase")))
8027 (build-system r-build-system)
8034 (home-page "https://github.com/cole-trapnell-lab/leidenbase")
8035 (synopsis "R and C wrappers to run the Leiden find_partition function")
8037 "This package provides an R to C interface that runs the Leiden
8038 community detection algorithm to find a basic partition. It runs the
8039 equivalent of the @code{find_partition} function. This package includes the
8040 required source code files from the official Leidenalg distribution and
8041 several functions from the R igraph package.")
8042 (license license:gpl3+))))
8044 (define-public r-sanssouci
8045 ;; sansscouci doesn't have a (versioned) release yet.
8046 ;; This is the latest commit as of packaging for Guix.
8047 (let ((commit "5fe20a9aaf4ac637fa83d9cc73ff1c22de97ca6f")
8050 (name "r-sanssouci")
8051 (version (git-version "0" revision commit))
8055 (url "https://github.com/pneuvial/sanssouci.git")
8057 (file-name (git-file-name name version))
8060 "13ycdd790qw64qy2zdvcrpj3fc8as628rsly32438d3rifnlc5sk"))))
8061 (build-system r-build-system)
8063 (list r-generics r-matrix r-matrixstats r-rcpp r-rcpparmadillo))
8064 (home-page "https://pneuvial.github.io/sanssouci")
8065 (synopsis "Post Hoc multiple testing inference")
8067 "The goal of sansSouci is to perform post hoc inference: in a multiple
8068 testing context, sansSouci provides statistical guarantees on possibly
8069 user-defined and/or data-driven sets of hypotheses.")
8070 (license license:gpl3))))
8072 (define-public r-monocle3
8080 (url "https://github.com/cole-trapnell-lab/monocle3")
8082 (file-name (git-file-name name version))
8085 "16vpvlbms8fdvpfwzcig0rkg2mxnsq1h80d2l7q3953wm91qc9x4"))))
8086 (build-system r-build-system)
8092 r-delayedmatrixstats
8127 r-singlecellexperiment
8132 (home-page "https://github.com/cole-trapnell-lab/monocle3")
8133 (synopsis "Analysis toolkit for single-cell RNA-Seq data")
8135 "Monocle 3 is an analysis toolkit for single-cell RNA-Seq experiments.")
8136 (license license:expat)))
8138 (define-public r-noiseq
8145 (uri (bioconductor-uri "NOISeq" version))
8148 "0ah6adlhv4254jkssinn2ik8n811hd1nw85bnzqk2kwhl49nrk27"))))
8149 (properties `((upstream-name . "NOISeq")))
8150 (build-system r-build-system)
8152 (list r-biobase r-matrix))
8153 (home-page "https://bioconductor.org/packages/NOISeq")
8154 (synopsis "Exploratory analysis and differential expression for RNA-seq data")
8156 "This package provides tools to support the analysis of RNA-seq
8157 expression data or other similar kind of data. It provides exploratory plots
8158 to evaluate saturation, count distribution, expression per chromosome, type of
8159 detected features, features length, etc. It also supports the analysis of
8160 differential expression between two experimental conditions with no parametric
8162 (license license:artistic2.0)))
8164 (define-public r-scdd
8171 (uri (bioconductor-uri "scDD" version))
8174 "0bjww338z5qf2g97kbh85h9kpagjr59ff9f4alm33h16xz5mb7k0"))))
8175 (properties `((upstream-name . "scDD")))
8176 (build-system r-build-system)
8187 r-singlecellexperiment
8188 r-summarizedexperiment))
8191 (home-page "https://github.com/kdkorthauer/scDD")
8192 (synopsis "Mixture modeling of single-cell RNA-seq data")
8194 "This package implements a method to analyze single-cell RNA-seq data
8195 utilizing flexible Dirichlet Process mixture models. Genes with differential
8196 distributions of expression are classified into several interesting patterns
8197 of differences between two conditions. The package also includes functions
8198 for simulating data with these patterns from negative binomial
8200 (license license:gpl2)))
8202 (define-public r-scone
8209 (uri (bioconductor-uri "scone" version))
8212 "05id34n6min03ha1chg5mrvx399qm2mby9kxkaz5w8fbidp97851"))))
8213 (build-system r-build-system)
8234 r-singlecellexperiment
8235 r-summarizedexperiment))
8238 (home-page "https://bioconductor.org/packages/scone")
8239 (synopsis "Single cell overview of normalized expression data")
8241 "SCONE is an R package for comparing and ranking the performance of
8242 different normalization schemes for single-cell RNA-seq and other
8243 high-throughput analyses.")
8244 (license license:artistic2.0)))
8246 (define-public r-geoquery
8253 (uri (bioconductor-uri "GEOquery" version))
8256 "1cvkvq2haz831qi8w0gd3ayvxfxsl0z5klhki4gkfi9xqdv1gi9x"))))
8257 (properties `((upstream-name . "GEOquery")))
8258 (build-system r-build-system)
8272 (home-page "https://github.com/seandavi/GEOquery/")
8273 (synopsis "Get data from NCBI Gene Expression Omnibus (GEO)")
8275 "The NCBI Gene Expression Omnibus (GEO) is a public repository of
8276 microarray data. Given the rich and varied nature of this resource, it is
8277 only natural to want to apply BioConductor tools to these data. GEOquery is
8278 the bridge between GEO and BioConductor.")
8279 (license license:gpl2)))
8281 (define-public r-illuminaio
8283 (name "r-illuminaio")
8288 (uri (bioconductor-uri "illuminaio" version))
8291 "1xk057a9w4ps8xi8jyw8imkjcicfmzns8g92grn4af7yiip68h62"))))
8292 (build-system r-build-system)
8295 (home-page "https://github.com/HenrikBengtsson/illuminaio/")
8296 (synopsis "Parse Illumina microarray output files")
8298 "This package provides tools for parsing Illumina's microarray output
8299 files, including IDAT.")
8300 (license license:gpl2)))
8302 (define-public r-siggenes
8309 (uri (bioconductor-uri "siggenes" version))
8312 "0amjqm2c8p1vjzx109p7n81wbsbx8rljwn6mbkl7dpi834im9d7l"))))
8313 (build-system r-build-system)
8315 (list r-biobase r-multtest r-scrime))
8316 (home-page "https://bioconductor.org/packages/siggenes/")
8318 "Multiple testing using SAM and Efron's empirical Bayes approaches")
8320 "This package provides tools for the identification of differentially
8321 expressed genes and estimation of the @dfn{False Discovery Rate} (FDR) using
8322 both the Significance Analysis of Microarrays (SAM) and the @dfn{Empirical
8323 Bayes Analyses of Microarrays} (EBAM).")
8324 (license license:lgpl2.0+)))
8326 (define-public r-bumphunter
8328 (name "r-bumphunter")
8333 (uri (bioconductor-uri "bumphunter" version))
8336 "0k92ps9chqsimbc7vsr8swg679zfv8nfn5zahbqq4nknhhy7hwxw"))))
8337 (build-system r-build-system)
8339 (list r-annotationdbi
8352 (home-page "https://github.com/ririzarr/bumphunter")
8353 (synopsis "Find bumps in genomic data")
8355 "This package provides tools for finding bumps in genomic data in order
8356 to identify differentially methylated regions in epigenetic epidemiology
8358 (license license:artistic2.0)))
8360 (define-public r-minfi
8367 (uri (bioconductor-uri "minfi" version))
8370 "0255z7w5i5k01w8wn7jkb37h3q7m7vg0szqgk76h330yydnmkrq6"))))
8371 (build-system r-build-system)
8381 r-delayedmatrixstats
8401 r-summarizedexperiment))
8404 (home-page "https://github.com/hansenlab/minfi")
8405 (synopsis "Analyze Illumina Infinium DNA methylation arrays")
8407 "This package provides tools to analyze and visualize Illumina Infinium
8408 methylation arrays.")
8409 (license license:artistic2.0)))
8411 (define-public r-methylumi
8413 (name "r-methylumi")
8418 (uri (bioconductor-uri "methylumi" version))
8421 "0klkinq55lfj1d4z8gkrv98849079x1l5gd15habw7jq9xxvhjww"))))
8422 (build-system r-build-system)
8428 r-fdb-infiniummethylation-hg19
8442 r-summarizedexperiment))
8445 (home-page "https://bioconductor.org/packages/methylumi")
8446 (synopsis "Handle Illumina methylation data")
8448 "This package provides classes for holding and manipulating Illumina
8449 methylation data. Based on eSet, it can contain MIAME information, sample
8450 information, feature information, and multiple matrices of data. An
8451 \"intelligent\" import function, methylumiR can read the Illumina text files
8452 and create a MethyLumiSet. methylumIDAT can directly read raw IDAT files from
8453 HumanMethylation27 and HumanMethylation450 microarrays. Normalization,
8454 background correction, and quality control features for GoldenGate, Infinium,
8455 and Infinium HD arrays are also included.")
8456 (license license:gpl2)))
8458 (define-public r-lumi
8465 (uri (bioconductor-uri "lumi" version))
8468 "06zmll5j1yymsm3byarhllrz4q1w5mzv267a9g6visn73wan8y9d"))))
8469 (build-system r-build-system)
8486 (home-page "https://bioconductor.org/packages/lumi")
8487 (synopsis "BeadArray-specific methods for Illumina methylation and expression microarrays")
8489 "The lumi package provides an integrated solution for the Illumina
8490 microarray data analysis. It includes functions of Illumina
8491 BeadStudio (GenomeStudio) data input, quality control, BeadArray-specific
8492 variance stabilization, normalization and gene annotation at the probe level.
8493 It also includes the functions of processing Illumina methylation microarrays,
8494 especially Illumina Infinium methylation microarrays.")
8495 (license license:lgpl2.0+)))
8497 (define-public r-linnorm
8504 (uri (bioconductor-uri "Linnorm" version))
8507 "1002lllgns5klv3q2wsikkbypa2bafpka7a8mri0y5bfxncfr2zb"))))
8508 (properties `((upstream-name . "Linnorm")))
8509 (build-system r-build-system)
8531 (home-page "http://www.jjwanglab.org/Linnorm/")
8532 (synopsis "Linear model and normality based transformation method")
8534 "Linnorm is an R package for the analysis of RNA-seq, scRNA-seq, ChIP-seq
8535 count data or any large scale count data. It transforms such datasets for
8536 parametric tests. In addition to the transformtion function (@code{Linnorm}),
8537 the following pipelines are implemented:
8540 @item Library size/batch effect normalization (@code{Linnorm.Norm})
8541 @item Cell subpopluation analysis and visualization using t-SNE or PCA K-means
8542 clustering or hierarchical clustering (@code{Linnorm.tSNE},
8543 @code{Linnorm.PCA}, @code{Linnorm.HClust})
8544 @item Differential expression analysis or differential peak detection using
8545 limma (@code{Linnorm.limma})
8546 @item Highly variable gene discovery and visualization (@code{Linnorm.HVar})
8547 @item Gene correlation network analysis and visualization (@code{Linnorm.Cor})
8548 @item Stable gene selection for scRNA-seq data; for users without or who do
8549 not want to rely on spike-in genes (@code{Linnorm.SGenes})
8550 @item Data imputation (@code{Linnorm.DataImput}).
8553 Linnorm can work with raw count, CPM, RPKM, FPKM and TPM. Additionally, the
8554 @code{RnaXSim} function is included for simulating RNA-seq data for the
8555 evaluation of DEG analysis methods.")
8556 (license license:expat)))
8558 (define-public r-ioniser
8565 (uri (bioconductor-uri "IONiseR" version))
8568 "0cgx1dcfh617l9vr4r3ky8w7f0snl0vpavfd9n1h5n68p0p42dwi"))))
8569 (properties `((upstream-name . "IONiseR")))
8570 (build-system r-build-system)
8572 (list r-biocgenerics
8587 (home-page "https://bioconductor.org/packages/IONiseR/")
8588 (synopsis "Quality assessment tools for Oxford Nanopore MinION data")
8590 "IONiseR provides tools for the quality assessment of Oxford Nanopore
8591 MinION data. It extracts summary statistics from a set of fast5 files and can
8592 be used either before or after base calling. In addition to standard
8593 summaries of the read-types produced, it provides a number of plots for
8594 visualising metrics relative to experiment run time or spatially over the
8595 surface of a flowcell.")
8596 (license license:expat)))
8598 ;; This is a CRAN package, but it depends on multtest from Bioconductor.
8599 (define-public r-mutoss
8606 (uri (cran-uri "mutoss" version))
8609 "1yk7p7pb2xm38d3j19ysgwmix48lvimbhkhjjwk5jmr1a0ysx298"))))
8610 (properties `((upstream-name . "mutoss")))
8611 (build-system r-build-system)
8613 (list r-multcomp r-multtest r-mvtnorm r-plotrix))
8614 (home-page "https://github.com/kornl/mutoss/")
8615 (synopsis "Unified multiple testing procedures")
8617 "This package is designed to ease the application and comparison of
8618 multiple hypothesis testing procedures for FWER, gFWER, FDR and FDX. Methods
8619 are standardized and usable by the accompanying mutossGUI package.")
8620 ;; Any version of the GPL.
8621 (license (list license:gpl2+ license:gpl3+))))
8623 ;; This is a CRAN package, but it depends on mutoss, which depends on multtest
8624 ;; from Bioconductor, so we put it here.
8625 (define-public r-metap
8632 (uri (cran-uri "metap" version))
8635 "0asmypxfxly4xmcjf3yzid5zqlzg88z0brij2splfk4avsl035gf"))))
8636 (build-system r-build-system)
8644 (home-page "http://www.dewey.myzen.co.uk/meta/meta.html")
8645 (synopsis "Meta-analysis of significance values")
8647 "The canonical way to perform meta-analysis involves using effect sizes.
8648 When they are not available this package provides a number of methods for
8649 meta-analysis of significance values including the methods of Edgington,
8650 Fisher, Stouffer, Tippett, and Wilkinson; a number of data-sets to replicate
8651 published results; and a routine for graphical display.")
8652 (license license:gpl2)))
8654 (define-public r-tradeseq
8660 (uri (bioconductor-uri "tradeSeq" version))
8663 "0v9nqxrwa69qhmyaicn2vvs8haha4kzs93iqim306331vadp9qm0"))))
8664 (build-system r-build-system)
8680 r-singlecellexperiment
8682 r-summarizedexperiment
8688 (home-page "https://statomics.github.io/tradeSeq/index.html")
8689 (synopsis "Trajectory-based differential expression analysis")
8691 "This package provides a flexible method for fitting regression models that
8692 can be used to find genes that are differentially expressed along one or
8693 multiple lineages in a trajectory. Based on the fitted models, it uses a
8694 variety of tests suited to answer different questions of interest, e.g. the
8695 discovery of genes for which expression is associated with pseudotime, or which
8696 are differentially expressed (in a specific region) along the trajectory. It
8697 fits a negative binomial generalized additive model (GAM) for each gene, and
8698 performs inference on the parameters of the GAM.")
8699 (license license:expat)))
8701 (define-public r-triform
8708 (uri (bioconductor-uri "triform" version))
8711 "089b7f6dwpi9abj0ncswbi4s30k45996zb99sh43avw6jcb6qj60"))))
8712 (build-system r-build-system)
8714 (list r-biocgenerics r-iranges r-yaml))
8715 (home-page "https://bioconductor.org/packages/triform/")
8716 (synopsis "Find enriched regions in transcription factor ChIP-sequencing data")
8718 "The Triform algorithm uses model-free statistics to identify peak-like
8719 distributions of TF ChIP sequencing reads, taking advantage of an improved
8720 peak definition in combination with known profile characteristics.")
8721 (license license:gpl2)))
8723 (define-public r-varianttools
8725 (name "r-varianttools")
8730 (uri (bioconductor-uri "VariantTools" version))
8733 "18nxcamfgnw4n2ab0czxglw0sqc9wzdqzpjv43lcyyal23lzzsix"))))
8734 (properties `((upstream-name . "VariantTools")))
8735 (build-system r-build-system)
8750 r-variantannotation))
8751 (home-page "https://bioconductor.org/packages/VariantTools/")
8752 (synopsis "Tools for exploratory analysis of variant calls")
8754 "Explore, diagnose, and compare variant calls using filters. The
8755 VariantTools package supports a workflow for loading data, calling single
8756 sample variants and tumor-specific somatic mutations or other sample-specific
8757 variant types (e.g., RNA editing). Most of the functions operate on
8758 alignments (BAM files) or datasets of called variants. The user is expected
8759 to have already aligned the reads with a separate tool, e.g., GSNAP via
8761 (license license:artistic2.0)))
8763 (define-public r-heatplus
8770 (uri (bioconductor-uri "Heatplus" version))
8773 "0b1mzxysmrqinp93p587apna8p0llmawblwj93icydqxxm2jkhb1"))))
8774 (properties `((upstream-name . "Heatplus")))
8775 (build-system r-build-system)
8777 (list r-rcolorbrewer))
8778 (home-page "https://github.com/alexploner/Heatplus")
8779 (synopsis "Heatmaps with row and/or column covariates and colored clusters")
8781 "This package provides tools to display a rectangular heatmap (intensity
8782 plot) of a data matrix. By default, both samples (columns) and features (row)
8783 of the matrix are sorted according to a hierarchical clustering, and the
8784 corresponding dendrogram is plotted. Optionally, panels with additional
8785 information about samples and features can be added to the plot.")
8786 (license license:gpl2+)))
8788 (define-public r-gosemsim
8795 (uri (bioconductor-uri "GOSemSim" version))
8798 "1hp15pzd0m0g9f8kglyfsgjqxnvxcmm9022xnsrkzfvmj2yw14vd"))))
8799 (properties `((upstream-name . "GOSemSim")))
8800 (build-system r-build-system)
8802 (list r-annotationdbi r-go-db r-rcpp))
8805 (home-page "https://guangchuangyu.github.io/software/GOSemSim")
8806 (synopsis "GO-terms semantic similarity measures")
8808 "The semantic comparisons of @dfn{Gene Ontology} (GO) annotations provide
8809 quantitative ways to compute similarities between genes and gene groups, and
8810 have became important basis for many bioinformatics analysis approaches.
8811 GOSemSim is an R package for semantic similarity computation among GO terms,
8812 sets of GO terms, gene products and gene clusters.")
8813 (license license:artistic2.0)))
8815 (define-public r-anota
8822 (uri (bioconductor-uri "anota" version))
8825 "1x75r5znl8jllqsgzpxsqj62ch11bpwhmyzmbjmb8sz8f8ww923c"))))
8826 (build-system r-build-system)
8828 (list r-multtest r-qvalue))
8829 (home-page "https://bioconductor.org/packages/anota/")
8830 (synopsis "Analysis of translational activity")
8832 "Genome wide studies of translational control is emerging as a tool to
8833 study various biological conditions. The output from such analysis is both
8834 the mRNA level (e.g. cytosolic mRNA level) and the level of mRNA actively
8835 involved in translation (the actively translating mRNA level) for each mRNA.
8836 The standard analysis of such data strives towards identifying differential
8837 translational between two or more sample classes - i.e. differences in
8838 actively translated mRNA levels that are independent of underlying differences
8839 in cytosolic mRNA levels. This package allows for such analysis using partial
8840 variances and the random variance model. As 10s of thousands of mRNAs are
8841 analyzed in parallel the library performs a number of tests to assure that
8842 the data set is suitable for such analysis.")
8843 (license license:gpl3)))
8845 (define-public r-sigpathway
8847 (name "r-sigpathway")
8852 (uri (bioconductor-uri "sigPathway" version))
8855 "1c2kwhbxgf66az7ssm2mab9n5x59zy4kxq8vblz5r9636xqaysif"))))
8856 (properties `((upstream-name . "sigPathway")))
8857 (build-system r-build-system)
8858 (home-page "https://www.pnas.org/cgi/doi/10.1073/pnas.0506577102")
8859 (synopsis "Pathway analysis")
8861 "This package is used to conduct pathway analysis by calculating the NT_k
8862 and NE_k statistics in a statistical framework for determining whether a
8863 specified group of genes for a pathway has a coordinated association with a
8864 phenotype of interest.")
8865 (license license:gpl2)))
8867 (define-public r-fcscan
8874 (uri (bioconductor-uri "fcScan" version))
8876 (base32 "0yv7ifw0xxx1v9z8dxszv0cb72q3frd74dyxfbvrcs6x9y9v3jzp"))))
8877 (properties `((upstream-name . "fcScan")))
8878 (build-system r-build-system)
8886 r-summarizedexperiment
8887 r-variantannotation))
8888 (native-inputs (list r-knitr))
8889 (home-page "https://bioconductor.org/packages/fcScan")
8890 (synopsis "Detect clusters of coordinates with user defined options")
8892 "This package is used to detect combination of genomic coordinates
8893 falling within a user defined window size along with user defined overlap
8894 between identified neighboring clusters. It can be used for genomic data
8895 where the clusters are built on a specific chromosome or specific strand.
8896 Clustering can be performed with a \"greedy\" option allowing thus the
8897 presence of additional sites within the allowed window size.")
8898 (license license:artistic2.0)))
8900 (define-public r-fgsea
8907 (uri (bioconductor-uri "fgsea" version))
8910 "0innyggai6l4fpl4qrblzdc52vqw9jaszmip0yr1lv7rzwyl6mpg"))))
8911 (build-system r-build-system)
8923 (home-page "https://github.com/ctlab/fgsea/")
8924 (synopsis "Fast gene set enrichment analysis")
8926 "The package implements an algorithm for fast gene set enrichment
8927 analysis. Using the fast algorithm makes more permutations and gets
8928 more fine grained p-values, which allows using accurate standard approaches
8929 to multiple hypothesis correction.")
8930 (license license:expat)))
8932 (define-public r-dose
8939 (uri (bioconductor-uri "DOSE" version))
8942 "11lg4ql0bi54p2wg3z1dw9rwqai37khgcqbs4cb7zf67ml8jadwp"))))
8943 (properties `((upstream-name . "DOSE")))
8944 (build-system r-build-system)
8946 (list r-annotationdbi
8956 (home-page "https://guangchuangyu.github.io/software/DOSE/")
8957 (synopsis "Disease ontology semantic and enrichment analysis")
8959 "This package implements five methods proposed by Resnik, Schlicker,
8960 Jiang, Lin and Wang, respectively, for measuring semantic similarities among
8961 @dfn{Disease ontology} (DO) terms and gene products. Enrichment analyses
8962 including hypergeometric model and gene set enrichment analysis are also
8963 implemented for discovering disease associations of high-throughput biological
8965 (license license:artistic2.0)))
8967 (define-public r-enrichplot
8969 (name "r-enrichplot")
8974 (uri (bioconductor-uri "enrichplot" version))
8977 "17ln1wbkq8sp7jw0dpkccj5qcsl382sgd7zic04dk99z9ag3mh02"))))
8978 (build-system r-build-system)
8997 (home-page "https://github.com/GuangchuangYu/enrichplot")
8998 (synopsis "Visualization of functional enrichment result")
9000 "The enrichplot package implements several visualization methods for
9001 interpreting functional enrichment results obtained from ORA or GSEA analyses.
9002 All the visualization methods are developed based on ggplot2 graphics.")
9003 (license license:artistic2.0)))
9005 (define-public r-clusterprofiler
9007 (name "r-clusterprofiler")
9012 (uri (bioconductor-uri "clusterProfiler" version))
9015 "0k5jhry0j6wa7779n3hrw4ld4bvyahpgpbwi2a0g704m3dd3mqp5"))))
9017 `((upstream-name . "clusterProfiler")))
9018 (build-system r-build-system)
9020 (list r-annotationdbi
9035 (home-page "https://guangchuangyu.github.io/software/clusterProfiler/")
9036 (synopsis "Analysis and visualization of functional profiles for gene clusters")
9038 "This package implements methods to analyze and visualize functional
9039 profiles (GO and KEGG) of gene and gene clusters.")
9040 (license license:artistic2.0)))
9042 (define-public r-clusterexperiment
9044 (name "r-clusterexperiment")
9048 (uri (bioconductor-uri "clusterExperiment" version))
9051 "1xd2kxmdg51hhj0zvz7pxmpdvb1sya7prsf9ny2wj2y8ivrqgn4f"))))
9052 (build-system r-build-system)
9077 r-singlecellexperiment
9079 r-summarizedexperiment
9081 (home-page "https://bioconductor.org/packages/clusterExperiment/")
9082 (synopsis "Compare clusterings for single-cell sequencing")
9083 (description "This package provides functionality for running and comparing
9084 many different clusterings of single-cell sequencing data or other large mRNA
9085 expression data sets.")
9086 (license license:artistic2.0)))
9088 (define-public r-mlinterfaces
9090 (name "r-mlinterfaces")
9095 (uri (bioconductor-uri "MLInterfaces" version))
9098 "179d19kxjipfkc40z15337x1vzqd7vz3gbmr2lw5w7x9l857ngs5"))))
9099 (properties `((upstream-name . "MLInterfaces")))
9100 (build-system r-build-system)
9122 (home-page "https://bioconductor.org/packages/MLInterfaces/")
9123 (synopsis "Interfaces to R machine learning procedures")
9125 "This package provides uniform interfaces to machine learning code for
9126 data in R and Bioconductor containers.")
9127 ;; Any version of the LGPL.
9128 (license license:lgpl2.1+)))
9130 (define-public r-annaffy
9137 (uri (bioconductor-uri "annaffy" version))
9140 "1fbqknwbl4534h66xrhcryg9pavm9fkja47gqbsxf8bd5yhk5mgq"))))
9141 (build-system r-build-system)
9144 (modify-phases %standard-phases
9145 (add-after 'unpack 'remove-reference-to-non-free-data
9147 (substitute* "DESCRIPTION"
9148 ((", KEGG.db") "")))))))
9150 (list r-annotationdbi r-biobase r-biocmanager r-dbi r-go-db))
9151 (home-page "https://bioconductor.org/packages/annaffy/")
9152 (synopsis "Annotation tools for Affymetrix biological metadata")
9154 "This package provides functions for handling data from Bioconductor
9155 Affymetrix annotation data packages. It produces compact HTML and text
9156 reports including experimental data and URL links to many online databases.
9157 It allows searching of biological metadata using various criteria.")
9158 ;; Any version of the LGPL according to the DESCRIPTION file. A copy of
9159 ;; the LGPL 2.1 is included.
9160 (license license:lgpl2.1+)))
9162 (define-public r-a4core
9169 (uri (bioconductor-uri "a4Core" version))
9172 "1ky1lphq6bqxj6h12pg06cvs451fziqam8gd56wmpk6r5pbg4390"))))
9173 (properties `((upstream-name . "a4Core")))
9174 (build-system r-build-system)
9176 (list r-biobase r-glmnet))
9179 (home-page "https://bioconductor.org/packages/a4Core")
9180 (synopsis "Automated Affymetrix array analysis core package")
9182 "This is the core package for the automated analysis of Affymetrix
9184 (license license:gpl3)))
9186 (define-public r-a4classif
9188 (name "r-a4classif")
9193 (uri (bioconductor-uri "a4Classif" version))
9196 "1v61vgpqrf7bhk44n2gkxb8dm5d0rr8c9rd6fdcjs50nhij0lbiw"))))
9197 (properties `((upstream-name . "a4Classif")))
9198 (build-system r-build-system)
9209 (home-page "https://bioconductor.org/packages/a4Classif/")
9210 (synopsis "Automated Affymetrix array analysis classification package")
9212 "This is the classification package for the automated analysis of
9213 Affymetrix arrays.")
9214 (license license:gpl3)))
9216 (define-public r-a4preproc
9218 (name "r-a4preproc")
9223 (uri (bioconductor-uri "a4Preproc" version))
9226 "098yzy7x5536bj76iavismdsdn7x6x07aw0j3knj6i9www9y8yz9"))))
9227 (properties `((upstream-name . "a4Preproc")))
9228 (build-system r-build-system)
9230 (list r-biobase r-biocgenerics))
9233 (home-page "https://bioconductor.org/packages/a4Preproc/")
9234 (synopsis "Automated Affymetrix array analysis preprocessing package")
9236 "This is a package for the automated analysis of Affymetrix arrays. It
9237 is used for preprocessing the arrays.")
9238 (license license:gpl3)))
9240 (define-public r-a4reporting
9242 (name "r-a4reporting")
9247 (uri (bioconductor-uri "a4Reporting" version))
9250 "03sypayh187gqc6hykkqr1g0vb3zxc2c3xyp00jfbn12b35acnb0"))))
9251 (properties `((upstream-name . "a4Reporting")))
9252 (build-system r-build-system)
9257 (home-page "https://bioconductor.org/packages/a4Reporting/")
9258 (synopsis "Automated Affymetrix array analysis reporting package")
9260 "This is a package for the automated analysis of Affymetrix arrays. It
9261 provides reporting features.")
9262 (license license:gpl3)))
9264 (define-public r-a4base
9271 (uri (bioconductor-uri "a4Base" version))
9274 "15zqirz16gpks9f5d3d76h85b936za2jih74vfr55l5arqrrvvsn"))))
9275 (properties `((upstream-name . "a4Base")))
9276 (build-system r-build-system)
9288 (home-page "https://bioconductor.org/packages/a4Base/")
9289 (synopsis "Automated Affymetrix array analysis base package")
9291 "This package provides basic features for the automated analysis of
9292 Affymetrix arrays.")
9293 (license license:gpl3)))
9302 (uri (bioconductor-uri "a4" version))
9305 "1zs8fs6mdd7fhsmx4k824mid0jk400cm6dwfhl8z5lg85y8y2n0r"))))
9306 (build-system r-build-system)
9308 (list r-a4base r-a4classif r-a4core r-a4preproc r-a4reporting))
9309 (home-page "https://bioconductor.org/packages/a4/")
9310 (synopsis "Automated Affymetrix array analysis umbrella package")
9312 "This package provides a software suite for the automated analysis of
9313 Affymetrix arrays.")
9314 (license license:gpl3)))
9316 (define-public r-abseqr
9323 (uri (bioconductor-uri "abseqR" version))
9326 "0jh3rj6ag07vpw6fymqm6m4jkrm9mgf50zkjncahxdf52mna8a9b"))))
9327 (properties `((upstream-name . "abseqR")))
9328 (build-system r-build-system)
9332 (list r-biocparallel
9352 (home-page "https://github.com/malhamdoosh/abseqR")
9353 (synopsis "Reporting and data analysis for Rep-Seq datasets of antibody libraries")
9355 "AbSeq is a comprehensive bioinformatic pipeline for the analysis of
9356 sequencing datasets generated from antibody libraries and abseqR is one of its
9357 packages. AbseqR empowers the users of abseqPy with plotting and reporting
9358 capabilities and allows them to generate interactive HTML reports for the
9359 convenience of viewing and sharing with other researchers. Additionally,
9360 abseqR extends abseqPy to compare multiple repertoire analyses and perform
9361 further downstream analysis on its output.")
9362 (license license:gpl3)))
9364 (define-public r-bacon
9371 (uri (bioconductor-uri "bacon" version))
9374 "1zvcxdj3r892898ik5gq3jdbfig1438qws4bwd465ik8vi7g39v8"))))
9375 (build-system r-build-system)
9377 (list r-biocparallel r-ellipse r-ggplot2))
9380 (home-page "https://bioconductor.org/packages/bacon/")
9381 (synopsis "Controlling bias and inflation in association studies")
9383 "Bacon can be used to remove inflation and bias often observed in
9384 epigenome- and transcriptome-wide association studies. To this end bacon
9385 constructs an empirical null distribution using a Gibbs Sampling algorithm by
9386 fitting a three-component normal mixture on z-scores.")
9387 (license license:gpl2+)))
9389 (define-public r-rgadem
9396 (uri (bioconductor-uri "rGADEM" version))
9399 "013xdwz0c3n0n9hxf8kkx570qry961pgdjsp023531pl5ww2ing4"))))
9400 (properties `((upstream-name . "rGADEM")))
9401 (build-system r-build-system)
9403 (list r-biostrings r-bsgenome r-genomicranges r-iranges r-seqlogo))
9404 (home-page "https://bioconductor.org/packages/rGADEM/")
9405 (synopsis "De novo sequence motif discovery")
9407 "rGADEM is an efficient de novo motif discovery tool for large-scale
9408 genomic sequence data.")
9409 (license license:artistic2.0)))
9411 (define-public r-motiv
9418 (uri (bioconductor-uri "MotIV" version))
9421 "1yqqymcrnwlpv6h3w80yliv19922g32xqlqszaqjk6zp853qilh6"))))
9422 (properties `((upstream-name . "MotIV")))
9423 (build-system r-build-system)
9427 (list r-biocgenerics
9434 (home-page "https://bioconductor.org/packages/MotIV/")
9435 (synopsis "Motif identification and validation")
9437 "This package is used for the identification and validation of sequence
9438 motifs. It makes use of STAMP for comparing a set of motifs to a given
9439 database (e.g. JASPAR). It can also be used to visualize motifs, motif
9440 distributions, modules and filter motifs.")
9441 (license license:gpl2)))
9443 (define-public r-motifdb
9449 (uri (bioconductor-uri "MotifDb" version))
9451 (base32 "1cyfz0l0yvdii3idaiq5w39yzxlzfpifa4v5pv7hdjfjj83a8rbi"))))
9452 (properties `((upstream-name . "MotifDb")))
9453 (build-system r-build-system)
9455 (list r-biocgenerics
9464 (home-page "https://www.bioconductor.org/packages/MotifDb/")
9465 (synopsis "Annotated collection of protein-DNA binding sequence motifs")
9466 (description "This package provides more than 2000 annotated position
9467 frequency matrices from nine public sources, for multiple organisms.")
9468 (license license:artistic2.0)))
9470 (define-public r-motifbreakr
9472 (name "r-motifbreakr")
9476 (uri (bioconductor-uri "motifbreakR" version))
9478 (base32 "0sad73jjx52qzp1fmygp6xqvaxwl5szi69f00f94i1pdyq70qhlg"))))
9479 (properties `((upstream-name . "motifbreakR")))
9480 (build-system r-build-system)
9482 (list r-biocgenerics
9496 r-summarizedexperiment
9498 r-variantannotation))
9501 (home-page "https://www.bioconductor.org/packages/motifbreakR/")
9502 (synopsis "Predicting disruptiveness of single nucleotide polymorphisms")
9503 (description "This package allows biologists to judge in the first place
9504 whether the sequence surrounding the polymorphism is a good match, and in
9505 the second place how much information is gained or lost in one allele of
9506 the polymorphism relative to another. This package gives a choice of
9507 algorithms for interrogation of genomes with motifs from public sources:
9509 @item a weighted-sum probability matrix;
9510 @item log-probabilities;
9511 @item weighted by relative entropy.
9514 This package can predict effects for novel or previously described variants in
9515 public databases, making it suitable for tasks beyond the scope of its original
9516 design. Lastly, it can be used to interrogate any genome curated within
9518 (license license:gpl2+)))
9520 (define-public r-motifstack
9522 (name "r-motifstack")
9527 (uri (bioconductor-uri "motifStack" version))
9530 "0d2ihx73chczbv6f91n04qb372plrdv7k4qws8shyw1fmvb1rq0z"))))
9531 (properties `((upstream-name . "motifStack")))
9532 (build-system r-build-system)
9542 (home-page "https://bioconductor.org/packages/motifStack/")
9543 (synopsis "Plot stacked logos for DNA, RNA and amino acid sequences")
9545 "The motifStack package is designed for graphic representation of
9546 multiple motifs with different similarity scores. It works with both DNA/RNA
9547 sequence motifs and amino acid sequence motifs. In addition, it provides the
9548 flexibility for users to customize the graphic parameters such as the font
9549 type and symbol colors.")
9550 (license license:gpl2+)))
9552 (define-public r-genomicscores
9554 (name "r-genomicscores")
9559 (uri (bioconductor-uri "GenomicScores" version))
9562 "12rcxw69an1d5q7ar58xy8s871l47imw2nm08j054ivxslx8597j"))))
9563 (properties `((upstream-name . "GenomicScores")))
9564 (build-system r-build-system)
9566 (list r-annotationhub
9583 (home-page "https://github.com/rcastelo/GenomicScores/")
9584 (synopsis "Work with genome-wide position-specific scores")
9586 "This package provides infrastructure to store and access genome-wide
9587 position-specific scores within R and Bioconductor.")
9588 (license license:artistic2.0)))
9590 (define-public r-atacseqqc
9592 (name "r-atacseqqc")
9597 (uri (bioconductor-uri "ATACseqQC" version))
9600 "0jj7n0mcj0gciw0ksazlksgmwzp51a40pwqhf0c7la0cc4bnrkqp"))))
9601 (properties `((upstream-name . "ATACseqQC")))
9602 (build-system r-build-system)
9604 (list r-biocgenerics
9624 (home-page "https://bioconductor.org/packages/ATACseqQC/")
9625 (synopsis "ATAC-seq quality control")
9627 "ATAC-seq, an assay for Transposase-Accessible Chromatin using
9628 sequencing, is a rapid and sensitive method for chromatin accessibility
9629 analysis. It was developed as an alternative method to MNase-seq, FAIRE-seq
9630 and DNAse-seq. The ATACseqQC package was developed to help users to quickly
9631 assess whether their ATAC-seq experiment is successful. It includes
9632 diagnostic plots of fragment size distribution, proportion of mitochondria
9633 reads, nucleosome positioning pattern, and CTCF or other Transcript Factor
9635 (license license:gpl2+)))
9637 (define-public r-gofuncr
9644 (uri (bioconductor-uri "GOfuncR" version))
9647 "02vdfsjrqp0m06mfbspwkxjyqxfca0w1idgygpi1a9i5m4fqhwpk"))))
9648 (properties `((upstream-name . "GOfuncR")))
9649 (build-system r-build-system)
9651 (list r-annotationdbi
9660 (home-page "https://bioconductor.org/packages/GOfuncR/")
9661 (synopsis "Gene ontology enrichment using FUNC")
9663 "GOfuncR performs a gene ontology enrichment analysis based on the
9664 ontology enrichment software FUNC. GO-annotations are obtained from
9665 OrganismDb or OrgDb packages (@code{Homo.sapiens} by default); the GO-graph is
9666 included in the package and updated regularly. GOfuncR provides the standard
9667 candidate vs background enrichment analysis using the hypergeometric test, as
9668 well as three additional tests:
9671 @item the Wilcoxon rank-sum test that is used when genes are ranked,
9672 @item a binomial test that is used when genes are associated with two counts,
9674 @item a Chi-square or Fisher's exact test that is used in cases when genes are
9675 associated with four counts.
9678 To correct for multiple testing and interdependency of the tests, family-wise
9679 error rates are computed based on random permutations of the gene-associated
9680 variables. GOfuncR also provides tools for exploring the ontology graph and
9681 the annotations, and options to take gene-length or spatial clustering of
9682 genes into account. It is also possible to provide custom gene coordinates,
9683 annotations and ontologies.")
9684 (license license:gpl2+)))
9686 (define-public r-abaenrichment
9688 (name "r-abaenrichment")
9693 (uri (bioconductor-uri "ABAEnrichment" version))
9696 "1sp3f72rzlr822dxx42bswynrwwfx6f520hdhfdikqp13p2y4044"))))
9697 (properties `((upstream-name . "ABAEnrichment")))
9698 (build-system r-build-system)
9708 (home-page "https://bioconductor.org/packages/ABAEnrichment/")
9709 (synopsis "Gene expression enrichment in human brain regions")
9711 "The package ABAEnrichment is designed to test for enrichment of user
9712 defined candidate genes in the set of expressed genes in different human brain
9713 regions. The core function @code{aba_enrich} integrates the expression of the
9714 candidate gene set (averaged across donors) and the structural information of
9715 the brain using an ontology, both provided by the Allen Brain Atlas project.")
9716 (license license:gpl2+)))
9718 (define-public r-annotationfuncs
9720 (name "r-annotationfuncs")
9725 (uri (bioconductor-uri "AnnotationFuncs" version))
9728 "0xsm7741zm81bi4c9hy0zaacnk8a6bahdpc6srqzrbsz0pfzdyhr"))))
9730 `((upstream-name . "AnnotationFuncs")))
9731 (build-system r-build-system)
9733 (list r-annotationdbi r-dbi))
9734 (home-page "https://www.iysik.com/r/annotationfuncs")
9735 (synopsis "Annotation translation functions")
9737 "This package provides functions for handling translating between
9738 different identifieres using the Biocore Data Team data-packages (e.g.
9739 @code{org.Bt.eg.db}).")
9740 (license license:gpl2)))
9742 (define-public r-annotationtools
9744 (name "r-annotationtools")
9749 (uri (bioconductor-uri "annotationTools" version))
9752 "122b424zida3j0vqkn8d06sg3jpc3ngsgidr8kgg00n4cjngkc51"))))
9754 `((upstream-name . "annotationTools")))
9755 (build-system r-build-system)
9756 (propagated-inputs (list r-biobase))
9757 (home-page "https://bioconductor.org/packages/annotationTools/")
9758 (synopsis "Annotate microarrays and perform gene expression analyses")
9760 "This package provides functions to annotate microarrays, find orthologs,
9761 and integrate heterogeneous gene expression profiles using annotation and
9762 other molecular biology information available as flat file database (plain
9764 ;; Any version of the GPL.
9765 (license (list license:gpl2+))))
9767 (define-public r-allelicimbalance
9769 (name "r-allelicimbalance")
9774 (uri (bioconductor-uri "AllelicImbalance" version))
9777 "0w4xd0xzkwx7bbhrgqligpahlhg85rginknx520z891r8v0bim2z"))))
9779 `((upstream-name . "AllelicImbalance")))
9780 (build-system r-build-system)
9782 (list r-annotationdbi
9799 r-summarizedexperiment
9800 r-variantannotation))
9803 (home-page "https://github.com/pappewaio/AllelicImbalance")
9804 (synopsis "Investigate allele-specific expression")
9806 "This package provides a framework for allele-specific expression
9807 investigation using RNA-seq data.")
9808 (license license:gpl3)))
9810 (define-public r-aucell
9817 (uri (bioconductor-uri "AUCell" version))
9820 "17wr7dycll0l1gax4w268qw7is163bs51rj6p1qnx1dgc9ibnsgr"))))
9821 (properties `((upstream-name . "AUCell")))
9822 (build-system r-build-system)
9824 (list r-biocgenerics
9827 r-delayedmatrixstats
9832 r-summarizedexperiment))
9835 (home-page "https://bioconductor.org/packages/AUCell/")
9836 (synopsis "Analysis of gene set activity in single-cell RNA-seq data")
9838 "AUCell identifies cells with active gene sets (e.g. signatures,
9839 gene modules, etc) in single-cell RNA-seq data. AUCell uses the @dfn{Area
9840 Under the Curve} (AUC) to calculate whether a critical subset of the input
9841 gene set is enriched within the expressed genes for each cell. The
9842 distribution of AUC scores across all the cells allows exploring the relative
9843 expression of the signature. Since the scoring method is ranking-based,
9844 AUCell is independent of the gene expression units and the normalization
9845 procedure. In addition, since the cells are evaluated individually, it can
9846 easily be applied to bigger datasets, subsetting the expression matrix if
9848 (license license:gpl3)))
9850 (define-public r-ebimage
9857 (uri (bioconductor-uri "EBImage" version))
9860 "1vcx45bw36k9daw9dywj5bz77jmqk4gjfwsym8ajjnc1jmlq20si"))))
9861 (properties `((upstream-name . "EBImage")))
9862 (build-system r-build-system)
9875 (list r-knitr)) ; for vignettes
9876 (home-page "https://github.com/aoles/EBImage")
9877 (synopsis "Image processing and analysis toolbox for R")
9879 "EBImage provides general purpose functionality for image processing and
9880 analysis. In the context of (high-throughput) microscopy-based cellular
9881 assays, EBImage offers tools to segment cells and extract quantitative
9882 cellular descriptors. This allows the automation of such tasks using the R
9883 programming language and facilitates the use of other tools in the R
9884 environment for signal processing, statistical modeling, machine learning and
9885 visualization with image data.")
9886 ;; Any version of the LGPL.
9887 (license license:lgpl2.1+)))
9889 (define-public r-yamss
9896 (uri (bioconductor-uri "yamss" version))
9899 "1lcfxw73cxvpy3bnq28pxdy5128mpq5xklsa0mzxdjyqc4g55hy8"))))
9900 (build-system r-build-system)
9902 (list r-biocgenerics
9910 r-summarizedexperiment))
9913 (home-page "https://github.com/hansenlab/yamss")
9914 (synopsis "Tools for high-throughput metabolomics")
9916 "This package provides tools to analyze and visualize high-throughput
9917 metabolomics data acquired using chromatography-mass spectrometry. These tools
9918 preprocess data in a way that enables reliable and powerful differential
9920 (license license:artistic2.0)))
9922 (define-public r-gtrellis
9929 (uri (bioconductor-uri "gtrellis" version))
9932 "1s4xczzv6hz2kyv32xgcq84540w75qr3f644w1s4c3kwxgyq2gff"))))
9933 (build-system r-build-system)
9935 (list r-circlize r-genomicranges r-getoptlong r-iranges))
9938 (home-page "https://github.com/jokergoo/gtrellis")
9939 (synopsis "Genome level Trellis layout")
9941 "Genome level Trellis graph visualizes genomic data conditioned by
9942 genomic categories (e.g. chromosomes). For each genomic category, multiple
9943 dimensional data which are represented as tracks describe different features
9944 from different aspects. This package provides high flexibility to arrange
9945 genomic categories and to add self-defined graphics in the plot.")
9946 (license license:expat)))
9948 (define-public r-somaticsignatures
9950 (name "r-somaticsignatures")
9955 (uri (bioconductor-uri "SomaticSignatures" version))
9958 "1ydnp54laznzpi08s403kxhnr5nqhvm3iilaxlcdlz0ngxhm6vx6"))))
9960 `((upstream-name . "SomaticSignatures")))
9961 (build-system r-build-system)
9975 r-variantannotation))
9978 (home-page "https://github.com/juliangehring/SomaticSignatures")
9979 (synopsis "Somatic signatures")
9981 "This package identifies mutational signatures of @dfn{single nucleotide
9982 variants} (SNVs). It provides a infrastructure related to the methodology
9983 described in Nik-Zainal (2012, Cell), with flexibility in the matrix
9984 decomposition algorithms.")
9985 (license license:expat)))
9987 (define-public r-yapsa
9994 (uri (bioconductor-uri "YAPSA" version))
9997 "1klqfif4sadkxw7agywk2ncvcdqsnfb1d6adnacdfdasr8abvhid"))))
9998 (properties `((upstream-name . "YAPSA")))
9999 (build-system r-build-system)
10002 r-bsgenome-hsapiens-ucsc-hg19
10022 r-somaticsignatures
10023 r-variantannotation))
10026 (home-page "https://bioconductor.org/packages/YAPSA/")
10027 (synopsis "Yet another package for signature analysis")
10029 "This package provides functions and routines useful in the analysis of
10030 somatic signatures (cf. L. Alexandrov et al., Nature 2013). In particular,
10031 functions to perform a signature analysis with known signatures and a
10032 signature analysis on @dfn{stratified mutational catalogue} (SMC) are
10034 (license license:gpl3)))
10036 (define-public r-gcrma
10043 (uri (bioconductor-uri "gcrma" version))
10046 "13a8igr2b02gsa6n3437kb33wg6h7si82fmqi35dzpfzhvx0qf6d"))))
10047 (build-system r-build-system)
10055 (home-page "https://bioconductor.org/packages/gcrma/")
10056 (synopsis "Background adjustment using sequence information")
10058 "Gcrma adjusts for background intensities in Affymetrix array data which
10059 include optical noise and @dfn{non-specific binding} (NSB). The main function
10060 @code{gcrma} converts background adjusted probe intensities to expression
10061 measures using the same normalization and summarization methods as a
10062 @dfn{Robust Multiarray Average} (RMA). Gcrma uses probe sequence information
10063 to estimate probe affinity to NSB. The sequence information is summarized in
10064 a more complex way than the simple GC content. Instead, the base types (A, T,
10065 G or C) at each position along the probe determine the affinity of each probe.
10066 The parameters of the position-specific base contributions to the probe
10067 affinity is estimated in an NSB experiment in which only NSB but no
10068 gene-specific binding is expected.")
10069 ;; Any version of the LGPL
10070 (license license:lgpl2.1+)))
10072 (define-public r-simpleaffy
10074 (name "r-simpleaffy")
10079 (uri (bioconductor-uri "simpleaffy" version))
10082 "04a11dsqd5y4b39nny94acnh0qhdazjc6d1803izza4vrgmw2csb"))))
10083 (build-system r-build-system)
10085 (list r-affy r-biobase r-biocgenerics r-gcrma r-genefilter))
10086 (home-page "https://bioconductor.org/packages/simpleaffy/")
10087 (synopsis "Very simple high level analysis of Affymetrix data")
10089 "This package provides high level functions for reading Affy @file{.CEL}
10090 files, phenotypic data, and then computing simple things with it, such as
10091 t-tests, fold changes and the like. It makes heavy use of the @code{affy}
10092 library. It also has some basic scatter plot functions and mechanisms for
10093 generating high resolution journal figures.")
10094 (license license:gpl2+)))
10096 (define-public r-yaqcaffy
10098 (name "r-yaqcaffy")
10103 (uri (bioconductor-uri "yaqcaffy" version))
10106 "18gphcjj15iivrahp52186bvdg07yd2dvrykfjdd4r1vyf33im96"))))
10107 (build-system r-build-system)
10109 (list r-simpleaffy))
10110 (home-page "https://bioconductor.org/packages/yaqcaffy/")
10111 (synopsis "Affymetrix quality control and reproducibility analysis")
10113 "This is a package that can be used for quality control of Affymetrix
10114 GeneChip expression data and reproducibility analysis of human whole genome
10115 chips with the MAQC reference datasets.")
10116 (license license:artistic2.0)))
10118 (define-public r-quantro
10125 (uri (bioconductor-uri "quantro" version))
10128 "1zfrz7lxyrbf0c8d277npzj1h4six9whkqplvcjmn3li0xj5qng3"))))
10129 (build-system r-build-system)
10140 (home-page "https://bioconductor.org/packages/quantro/")
10141 (synopsis "Test for when to use quantile normalization")
10143 "This package provides a data-driven test for the assumptions of quantile
10144 normalization using raw data such as objects that inherit eSets (e.g.
10145 ExpressionSet, MethylSet). Group level information about each sample (such as
10146 Tumor / Normal status) must also be provided because the test assesses if
10147 there are global differences in the distributions between the user-defined
10149 (license license:gpl3+)))
10151 (define-public r-yarn
10158 (uri (bioconductor-uri "yarn" version))
10161 "0z5202pqq02fwm8qf1g36004k7sv668s1xacbpr1cvw5sl452lbg"))))
10162 (build-system r-build-system)
10177 (home-page "https://bioconductor.org/packages/yarn/")
10178 (synopsis "Robust multi-condition RNA-Seq preprocessing and normalization")
10180 "Expedite large RNA-Seq analyses using a combination of previously
10181 developed tools. YARN is meant to make it easier for the user in performing
10182 basic mis-annotation quality control, filtering, and condition-aware
10183 normalization. YARN leverages many Bioconductor tools and statistical
10184 techniques to account for the large heterogeneity and sparsity found in very
10185 large RNA-seq experiments.")
10186 (license license:artistic2.0)))
10188 (define-public r-roar
10195 (uri (bioconductor-uri "roar" version))
10198 "0zq1praf5h9294cvmrb06l3chx8v40xw2sfvhlnh1516x9sjkwfc"))))
10199 (build-system r-build-system)
10201 (list r-biocgenerics
10203 r-genomicalignments
10208 r-summarizedexperiment))
10209 (home-page "https://github.com/vodkatad/roar/")
10210 (synopsis "Identify differential APA usage from RNA-seq alignments")
10212 "This package provides tools for identifying preferential usage of APA
10213 sites, comparing two biological conditions, starting from known alternative
10214 sites and alignments obtained from standard RNA-seq experiments.")
10215 (license license:gpl3)))
10217 (define-public r-xbseq
10224 (uri (bioconductor-uri "XBSeq" version))
10227 "1dvk2jpsdynqw5071z54yd5j0ddprhc1ppk834cz9liibd72d7vz"))))
10228 (properties `((upstream-name . "XBSeq")))
10229 (build-system r-build-system)
10242 (home-page "https://github.com/Liuy12/XBSeq")
10243 (synopsis "Test for differential expression for RNA-seq data")
10245 "XBSeq is a novel algorithm for testing RNA-seq @dfn{differential
10246 expression} (DE), where a statistical model was established based on the
10247 assumption that observed signals are the convolution of true expression
10248 signals and sequencing noises. The mapped reads in non-exonic regions are
10249 considered as sequencing noises, which follows a Poisson distribution. Given
10250 measurable observed signal and background noise from RNA-seq data, true
10251 expression signals, assuming governed by the negative binomial distribution,
10252 can be delineated and thus the accurate detection of differential expressed
10254 (license license:gpl3+)))
10256 (define-public r-massspecwavelet
10258 (name "r-massspecwavelet")
10263 (uri (bioconductor-uri "MassSpecWavelet" version))
10266 "0g9izdy3f7h1zmsfbq45ahdz0ak5013rp3vxc4ijb1mpqx8ldd39"))))
10268 `((upstream-name . "MassSpecWavelet")))
10269 (build-system r-build-system)
10272 (home-page "https://bioconductor.org/packages/MassSpecWavelet/")
10273 (synopsis "Mass spectrum processing by wavelet-based algorithms")
10275 "The MassSpecWavelet package aims to process @dfn{Mass Spectrometry} (MS)
10276 data mainly through the use of wavelet transforms. It supports peak detection
10277 based on @dfn{Continuous Wavelet Transform} (CWT).")
10278 (license license:lgpl2.0+)))
10280 (define-public r-xcms
10287 (uri (bioconductor-uri "xcms" version))
10290 "0p2zd2728lj5q8y24gdfvsjijd6zl2i73hrcf017n32jq7vn71xm"))))
10291 (build-system r-build-system)
10309 r-summarizedexperiment))
10312 (home-page "https://bioconductor.org/packages/xcms/")
10313 (synopsis "LC/MS and GC/MS mass spectrometry data analysis")
10315 "This package provides a framework for processing and visualization of
10316 chromatographically separated and single-spectra mass spectral data. It
10317 imports from AIA/ANDI NetCDF, mzXML, mzData and mzML files. It preprocesses
10318 data for high-throughput, untargeted analyte profiling.")
10319 (license license:gpl2+)))
10321 (define-public r-wppi
10327 (uri (bioconductor-uri "wppi" version))
10330 "1008s39bb7sd261cy1vfgdah7bmhfw9qq322fh7g4wvpfw63ii9f"))))
10331 (properties `((upstream-name . "wppi")))
10332 (build-system r-build-system)
10333 ;; This is necessary because omnipathr attempts to write a configuration
10337 (modify-phases %standard-phases
10338 (add-after 'unpack 'set-HOME
10339 (lambda _ (setenv "HOME" "/tmp"))))))
10340 (propagated-inputs (list r-dplyr
10352 (native-inputs (list r-knitr))
10353 (home-page "https://github.com/AnaGalhoz37/wppi")
10354 (synopsis "Weighting protein-protein interactions")
10356 "This package predicts functional relevance of protein-protein
10357 interactions based on functional annotations such as Human Protein Ontology
10358 and Gene Ontology, and prioritizes genes based on network topology, functional
10359 scores and a path search algorithm.")
10360 (license license:expat)))
10362 (define-public r-wrench
10369 (uri (bioconductor-uri "Wrench" version))
10372 "1zx65s4m71wj85s2sq8ip54pq12r4sxfv8b2rxc41gfc5aj0zzca"))))
10373 (properties `((upstream-name . "Wrench")))
10374 (build-system r-build-system)
10376 (list r-limma r-locfit r-matrixstats))
10379 (home-page "https://github.com/HCBravoLab/Wrench")
10380 (synopsis "Wrench normalization for sparse count data")
10382 "Wrench is a package for normalization sparse genomic count data, like
10383 that arising from 16s metagenomic surveys.")
10384 (license license:artistic2.0)))
10386 (define-public r-wiggleplotr
10388 (name "r-wiggleplotr")
10393 (uri (bioconductor-uri "wiggleplotr" version))
10396 "0s128mm5w8n072k6j0fv1mxnxjpwisjp5lpz8a9z96cnn69bnr0i"))))
10397 (build-system r-build-system)
10411 (home-page "https://bioconductor.org/packages/wiggleplotr/")
10412 (synopsis "Make read coverage plots from BigWig files")
10414 "This package provides tools to visualize read coverage from sequencing
10415 experiments together with genomic annotations (genes, transcripts, peaks).
10416 Introns of long transcripts can be rescaled to a fixed length for better
10417 visualization of exonic read coverage.")
10418 (license license:asl2.0)))
10420 (define-public r-widgettools
10422 (name "r-widgettools")
10427 (uri (bioconductor-uri "widgetTools" version))
10430 "10w1s5h4za6ibmphvj145ir3lp22qgah2z8fvmipmf8ciq1jf86d"))))
10431 (properties `((upstream-name . "widgetTools")))
10432 (build-system r-build-system)
10433 (home-page "https://bioconductor.org/packages/widgetTools/")
10434 (synopsis "Tools for creating interactive tcltk widgets")
10436 "This package contains tools to support the construction of tcltk
10438 ;; Any version of the LGPL.
10439 (license license:lgpl3+)))
10441 (define-public r-webbioc
10448 (uri (bioconductor-uri "webbioc" version))
10451 "1g3srxsa2fqcn3r4wz4y19fwjmw3vawlcvdw6lbjdnvbgcafq1ah"))))
10452 (build-system r-build-system)
10454 (list netpbm perl))
10464 (home-page "https://www.bioconductor.org/")
10465 (synopsis "Bioconductor web interface")
10467 "This package provides an integrated web interface for doing microarray
10468 analysis using several of the Bioconductor packages. It is intended to be
10469 deployed as a centralized bioinformatics resource for use by many users.
10470 Currently only Affymetrix oligonucleotide analysis is supported.")
10471 (license license:gpl2+)))
10473 (define-public r-zinbwave
10475 (name "r-zinbwave")
10480 (uri (bioconductor-uri "zinbwave" version))
10483 "0vpz721sciw5b4ypxj5lj8p53gwkpfwlwkn6k3y8i65zg80p1g6i"))))
10484 (build-system r-build-system)
10486 (list r-biocparallel
10490 r-singlecellexperiment
10492 r-summarizedexperiment))
10495 (home-page "https://bioconductor.org/packages/zinbwave")
10496 (synopsis "Zero-inflated negative binomial model for RNA-seq data")
10497 (description "This package implements a general and flexible zero-inflated
10498 negative binomial model that can be used to provide a low-dimensional
10499 representations of single-cell RNA-seq data. The model accounts for zero
10500 inflation (dropouts), over-dispersion, and the count nature of the data.
10501 The model also accounts for the difference in library sizes and optionally
10502 for batch effects and/or other covariates, avoiding the need for pre-normalize
10504 (license license:artistic2.0)))
10506 (define-public r-zfpkm
10513 (uri (bioconductor-uri "zFPKM" version))
10516 "1h7g553rgb5mkmmsp8dyqqs9n9x17xmmcg3iijhb54nyrr2j1mji"))))
10517 (properties `((upstream-name . "zFPKM")))
10518 (build-system r-build-system)
10520 (list r-checkmate r-dplyr r-ggplot2 r-summarizedexperiment r-tidyr))
10523 (home-page "https://github.com/ronammar/zFPKM/")
10524 (synopsis "Functions to facilitate zFPKM transformations")
10526 "This is a package to perform the zFPKM transform on RNA-seq FPKM data.
10527 This algorithm is based on the publication by Hart et al., 2013 (Pubmed ID
10529 (license license:gpl3)))
10531 (define-public r-rbowtie2
10533 (name "r-rbowtie2")
10538 (uri (bioconductor-uri "Rbowtie2" version))
10541 "0dhdx27vrkhd4fak0qb5q9amlcpi97xhf3ry39zk0ifx5zpjynkg"))))
10542 (properties `((upstream-name . "Rbowtie2")))
10543 (build-system r-build-system)
10545 (list r-magrittr r-rsamtools))
10547 (list samtools zlib))
10550 (home-page "https://bioconductor.org/packages/Rbowtie2/")
10551 (synopsis "R wrapper for Bowtie2 and AdapterRemoval")
10553 "This package provides an R wrapper of the popular @code{bowtie2}
10554 sequencing reads aligner and @code{AdapterRemoval}, a convenient tool for
10555 rapid adapter trimming, identification, and read merging.")
10556 (license license:gpl3+)))
10558 (define-public r-progeny
10565 (uri (bioconductor-uri "progeny" version))
10568 "1rhy2l2yf9ndxlvff8756s6n8qyi42nz7a75lgygj5aqqckkj21b"))))
10569 (build-system r-build-system)
10581 (home-page "https://github.com/saezlab/progeny")
10582 (synopsis "Pathway responsive gene activity inference")
10584 "This package provides a function to infer pathway activity from gene
10585 expression. It contains the linear model inferred in the publication
10586 \"Perturbation-response genes reveal signaling footprints in cancer gene
10588 (license license:asl2.0)))
10590 (define-public r-arrmnormalization
10592 (name "r-arrmnormalization")
10597 (uri (bioconductor-uri "ARRmNormalization" version))
10600 "1pnvw8psbql787m8lrmhd9xbmgkc3dbc70yfds1aggv50dk3yjk1"))))
10602 `((upstream-name . "ARRmNormalization")))
10603 (build-system r-build-system)
10604 (propagated-inputs (list r-arrmdata))
10605 (home-page "https://bioconductor.org/packages/ARRmNormalization/")
10606 (synopsis "Adaptive robust regression normalization for methylation data")
10608 "This is a package to perform the @dfn{Adaptive Robust Regression
10609 method} (ARRm) for the normalization of methylation data from the Illumina
10610 Infinium HumanMethylation 450k assay.")
10611 (license license:artistic2.0)))
10613 (define-public r-biocfilecache
10615 (name "r-biocfilecache")
10620 (uri (bioconductor-uri "BiocFileCache" version))
10623 "1bdbmlixrd8wvs25nmzdksq5hwnsxf8b6ds9qwx01h284vky5vsw"))))
10624 (properties `((upstream-name . "BiocFileCache")))
10625 (build-system r-build-system)
10637 (home-page "https://bioconductor.org/packages/BiocFileCache/")
10638 (synopsis "Manage files across sessions")
10640 "This package creates a persistent on-disk cache of files that the user
10641 can add, update, and retrieve. It is useful for managing resources (such as
10642 custom Txdb objects) that are costly or difficult to create, web resources,
10643 and data files used across sessions.")
10644 (license license:artistic2.0)))
10646 (define-public r-iclusterplus
10648 (name "r-iclusterplus")
10653 (uri (bioconductor-uri "iClusterPlus" version))
10656 "0xzx3vly3p99zc5a69pra4jjp8d3bdhx7dl1l76w459cs58zy0sm"))))
10657 (properties `((upstream-name . "iClusterPlus")))
10658 (build-system r-build-system)
10659 (native-inputs (list gfortran))
10660 (home-page "https://bioconductor.org/packages/iClusterPlus/")
10661 (synopsis "Integrative clustering of multi-type genomic data")
10663 "iClusterPlus is developed for integrative clustering analysis of
10664 multi-type genomic data and is an enhanced version of iCluster proposed and
10665 developed by Shen, Olshen and Ladanyi (2009). Multi-type genomic data arise
10666 from the experiments where biological samples (e.g. tumor samples) are
10667 analyzed by multiple techniques, for instance, @dfn{array comparative genomic
10668 hybridization} (aCGH), gene expression microarray, RNA-seq and DNA-seq, and so
10669 on. In the iClusterPlus model, binary observations such as somatic mutation
10670 are modeled as Binomial processes; categorical observations such as copy
10671 number states are realizations of Multinomial random variables; counts are
10672 modeled as Poisson random processes; and continuous measures are modeled by
10673 Gaussian distributions.")
10674 (license license:gpl2+)))
10676 (define-public r-rbowtie
10683 (uri (bioconductor-uri "Rbowtie" version))
10686 "1ya1irwshsyy9l1fj51b04nv1ahq7a47ck7q19h2cly6yskc4x1q"))))
10687 (properties `((upstream-name . "Rbowtie")))
10688 (build-system r-build-system)
10691 ;; Disable unsupported `popcnt' instructions on
10692 ;; architectures other than x86_64
10693 ,(if (string-prefix? "x86_64"
10694 (or (%current-target-system)
10695 (%current-system)))
10697 '(modify-phases %standard-phases
10698 (add-after 'unpack 'patch-sources
10700 (setenv "POPCNT_CAPABILITY" "0")))))))
10701 (inputs (list zlib))
10704 (home-page "https://bioconductor.org/packages/Rbowtie/")
10705 (synopsis "R bowtie wrapper")
10707 "This package provides an R wrapper around the popular bowtie short read
10708 aligner and around SpliceMap, a de novo splice junction discovery and
10710 (license license:artistic2.0)))
10712 (define-public r-sgseq
10719 (uri (bioconductor-uri "SGSeq" version))
10722 "0hz45367i70wl97silnimicdvs3g41zyf8syc6igz6471wbwkxwp"))))
10723 (properties `((upstream-name . "SGSeq")))
10724 (build-system r-build-system)
10726 (list r-annotationdbi
10730 r-genomicalignments
10739 r-summarizedexperiment))
10742 (home-page "https://bioconductor.org/packages/SGSeq/")
10743 (synopsis "Splice event prediction and quantification from RNA-seq data")
10745 "SGSeq is a package for analyzing splice events from RNA-seq data. Input
10746 data are RNA-seq reads mapped to a reference genome in BAM format. Genes are
10747 represented as a splice graph, which can be obtained from existing annotation
10748 or predicted from the mapped sequence reads. Splice events are identified
10749 from the graph and are quantified locally using structurally compatible reads
10750 at the start or end of each splice variant. The software includes functions
10751 for splice event prediction, quantification, visualization and
10753 (license license:artistic2.0)))
10755 (define-public r-rhisat2
10762 (uri (bioconductor-uri "Rhisat2" version))
10765 "0hzair41l47kzykymd169a34pfhb98vrjgkgdf15m17csyz7pnv7"))))
10766 (properties `((upstream-name . "Rhisat2")))
10767 (build-system r-build-system)
10770 (modify-phases %standard-phases
10771 (add-after 'unpack 'make-reproducible
10773 (substitute* "src/Makefile"
10774 (("`hostname`") "guix")
10776 ;; Avoid shelling out to "which".
10777 (("^CC =.*") (which "gcc"))
10778 (("^CPP =.*") (which "g++")))
10781 (list r-genomicfeatures r-genomicranges r-sgseq))
10784 (home-page "https://github.com/fmicompbio/Rhisat2")
10785 (synopsis "R Wrapper for HISAT2 sequence aligner")
10787 "This package provides an R interface to the HISAT2 spliced short-read
10788 aligner by Kim et al. (2015). The package contains wrapper functions to
10789 create a genome index and to perform the read alignment to the generated
10791 (license license:gpl3)))
10793 (define-public r-quasr
10800 (uri (bioconductor-uri "QuasR" version))
10803 "1m0c0rdakkdn4rr6dh51c6rs40cbxkvz93n6s0m2kc6fqjv9zplf"))))
10804 (properties `((upstream-name . "QuasR")))
10805 (build-system r-build-system)
10807 (list r-annotationdbi
10826 (home-page "https://bioconductor.org/packages/QuasR/")
10827 (synopsis "Quantify and annotate short reads in R")
10829 "This package provides a framework for the quantification and analysis of
10830 short genomic reads. It covers a complete workflow starting from raw sequence
10831 reads, over creation of alignments and quality control plots, to the
10832 quantification of genomic regions of interest.")
10833 (license license:gpl2)))
10835 (define-public r-rqc
10842 (uri (bioconductor-uri "Rqc" version))
10845 "11j8m69zdcmpjb3xzr4s8sqmv8aqgl8q7k81gnd09l3nyjzy0h1k"))))
10846 (properties `((upstream-name . "Rqc")))
10847 (build-system r-build-system)
10849 (list r-biocgenerics
10854 r-genomicalignments
10869 (home-page "https://github.com/labbcb/Rqc")
10870 (synopsis "Quality control tool for high-throughput sequencing data")
10872 "Rqc is an optimized tool designed for quality control and assessment of
10873 high-throughput sequencing data. It performs parallel processing of entire
10874 files and produces a report which contains a set of high-resolution
10876 (license license:gpl2+)))
10878 (define-public r-birewire
10880 (name "r-birewire")
10885 (uri (bioconductor-uri "BiRewire" version))
10888 "0r3i7n45qgj8wzdsx8wmfk0lc4xbcvxvmfziiqzig7r706q2c2hm"))))
10889 (properties `((upstream-name . "BiRewire")))
10890 (build-system r-build-system)
10892 (list r-igraph r-matrix r-rtsne r-slam))
10893 (home-page "https://bioconductor.org/packages/release/bioc/html/BiRewire.html")
10894 (synopsis "Tools for randomization of bipartite graphs")
10896 "This package provides functions for bipartite network rewiring through N
10897 consecutive switching steps and for the computation of the minimal number of
10898 switching steps to be performed in order to maximise the dissimilarity with
10899 respect to the original network. It includes functions for the analysis of
10900 the introduced randomness across the switching steps and several other
10901 routines to analyse the resulting networks and their natural projections.")
10902 (license license:gpl3)))
10904 (define-public r-birta
10911 (uri (bioconductor-uri "birta" version))
10914 "00a1kcfmcgdbx6wpnhk45wm45bynhry5m93l9hm75j2rwyc4lnca"))))
10915 (build-system r-build-system)
10917 (list r-biobase r-limma r-mass))
10918 (home-page "https://bioconductor.org/packages/birta")
10919 (synopsis "Bayesian inference of regulation of transcriptional activity")
10921 "Expression levels of mRNA molecules are regulated by different
10922 processes, comprising inhibition or activation by transcription factors and
10923 post-transcriptional degradation by microRNAs. @dfn{birta} (Bayesian
10924 Inference of Regulation of Transcriptional Activity) uses the regulatory
10925 networks of transcription factors and miRNAs together with mRNA and miRNA
10926 expression data to predict switches in regulatory activity between two
10927 conditions. A Bayesian network is used to model the regulatory structure and
10928 Markov-Chain-Monte-Carlo is applied to sample the activity states.")
10929 (license license:gpl2+)))
10931 (define-public r-multidataset
10933 (name "r-multidataset")
10938 (uri (bioconductor-uri "MultiDataSet" version))
10941 "0rfs6jkzh1i4mj1pgfk4lwzmcl8pcwizra3q3282x3d8h2g98qnf"))))
10942 (properties `((upstream-name . "MultiDataSet")))
10943 (build-system r-build-system)
10954 r-summarizedexperiment))
10957 (home-page "https://bioconductor.org/packages/MultiDataSet/")
10958 (synopsis "Implementation of MultiDataSet and ResultSet")
10960 "This package provides an implementation of the BRGE's (Bioinformatic
10961 Research Group in Epidemiology from Center for Research in Environmental
10962 Epidemiology) MultiDataSet and ResultSet. MultiDataSet is designed for
10963 integrating multi omics data sets and ResultSet is a container for omics
10964 results. This package contains base classes for MEAL and rexposome
10966 (license license:expat)))
10968 (define-public r-ropls
10975 (uri (bioconductor-uri "ropls" version))
10978 "07gpx15r8c3wljiwxnff2zp7wxbhzz9r7njk8zg8hpy2q5qm3i6c"))))
10979 (build-system r-build-system)
10982 r-multiassayexperiment
10984 r-summarizedexperiment))
10986 (list r-knitr)) ; for vignettes
10987 (home-page "https://dx.doi.org/10.1021/acs.jproteome.5b00354")
10988 (synopsis "Multivariate analysis and feature selection of omics data")
10990 "Latent variable modeling with @dfn{Principal Component Analysis} (PCA)
10991 and @dfn{Partial Least Squares} (PLS) are powerful methods for visualization,
10992 regression, classification, and feature selection of omics data where the
10993 number of variables exceeds the number of samples and with multicollinearity
10994 among variables. @dfn{Orthogonal Partial Least Squares} (OPLS) enables to
10995 separately model the variation correlated (predictive) to the factor of
10996 interest and the uncorrelated (orthogonal) variation. While performing
10997 similarly to PLS, OPLS facilitates interpretation.
10999 This package provides imlementations of PCA, PLS, and OPLS for multivariate
11000 analysis and feature selection of omics data. In addition to scores, loadings
11001 and weights plots, the package provides metrics and graphics to determine the
11002 optimal number of components (e.g. with the R2 and Q2 coefficients), check the
11003 validity of the model by permutation testing, detect outliers, and perform
11004 feature selection (e.g. with Variable Importance in Projection or regression
11006 (license license:cecill)))
11008 (define-public r-biosigner
11010 (name "r-biosigner")
11015 (uri (bioconductor-uri "biosigner" version))
11018 "0vdv2by3qv7y8vzr8qgg7apwwgsa0fhlfrhzns7g3nas7883c89m"))))
11019 (build-system r-build-system)
11023 r-multiassayexperiment
11027 r-summarizedexperiment))
11030 (home-page "https://bioconductor.org/packages/biosigner/")
11031 (synopsis "Signature discovery from omics data")
11033 "Feature selection is critical in omics data analysis to extract
11034 restricted and meaningful molecular signatures from complex and high-dimension
11035 data, and to build robust classifiers. This package implements a method to
11036 assess the relevance of the variables for the prediction performances of the
11037 classifier. The approach can be run in parallel with the PLS-DA, Random
11038 Forest, and SVM binary classifiers. The signatures and the corresponding
11039 'restricted' models are returned, enabling future predictions on new
11041 (license license:cecill)))
11043 (define-public r-annotatr
11045 (name "r-annotatr")
11050 (uri (bioconductor-uri "annotatr" version))
11053 "1fbax9v3d486c8lwf3yfjbf4w7zf53wmdpxk2clwm8ngm7w0pqm0"))))
11054 (build-system r-build-system)
11056 (list r-annotationdbi
11071 (home-page "https://bioconductor.org/packages/annotatr/")
11072 (synopsis "Annotation of genomic regions to genomic annotations")
11074 "Given a set of genomic sites/regions (e.g. ChIP-seq peaks, CpGs,
11075 differentially methylated CpGs or regions, SNPs, etc.) it is often of interest
11076 to investigate the intersecting genomic annotations. Such annotations include
11077 those relating to gene models (promoters, 5'UTRs, exons, introns, and 3'UTRs),
11078 CpGs (CpG islands, CpG shores, CpG shelves), or regulatory sequences such as
11079 enhancers. The annotatr package provides an easy way to summarize and
11080 visualize the intersection of genomic sites/regions with genomic
11082 (license license:gpl3)))
11084 (define-public r-rsubread
11086 (name "r-rsubread")
11091 (uri (bioconductor-uri "Rsubread" version))
11094 "155h25gbagqns7wpriil17li0jkdd1z1pcz0dlnikdqj4saf97rl"))))
11095 (properties `((upstream-name . "Rsubread")))
11096 (build-system r-build-system)
11097 (inputs (list zlib))
11100 (home-page "https://bioconductor.org/packages/Rsubread/")
11101 (synopsis "Subread sequence alignment and counting for R")
11103 "This package provides tools for alignment, quantification and analysis
11104 of second and third generation sequencing data. It includes functionality for
11105 read mapping, read counting, SNP calling, structural variant detection and
11106 gene fusion discovery. It can be applied to all major sequencing techologies
11107 and to both short and long sequence reads.")
11108 (license license:gpl3)))
11110 (define-public r-flowutils
11112 (name "r-flowutils")
11117 (uri (bioconductor-uri "flowUtils" version))
11120 "11x362dqb9mjlsbq6g1qkb8hhnkvm22z5s3wkgmpyy9kyifjkm26"))))
11121 (properties `((upstream-name . "flowUtils")))
11122 (build-system r-build-system)
11130 (home-page "https://github.com/jspidlen/flowUtils")
11131 (synopsis "Utilities for flow cytometry")
11133 "This package provides utilities for flow cytometry data.")
11134 (license license:artistic2.0)))
11136 (define-public r-consensusclusterplus
11138 (name "r-consensusclusterplus")
11143 (uri (bioconductor-uri "ConsensusClusterPlus" version))
11146 "1021cix4mr9qsafskw4kk1l3wdzx9pk2gcwjifz6f4zqxss9v07p"))))
11148 `((upstream-name . "ConsensusClusterPlus")))
11149 (build-system r-build-system)
11151 (list r-all r-biobase r-cluster))
11152 (home-page "https://bioconductor.org/packages/ConsensusClusterPlus")
11153 (synopsis "Clustering algorithm")
11155 "This package provides an implementation of an algorithm for determining
11156 cluster count and membership by stability evidence in unsupervised analysis.")
11157 (license license:gpl2)))
11159 ;; This is the latest commit and it solves a bug from the latest release.
11160 (define-public r-cycombine
11161 (let ((commit "f18504bc83ff5daee2b5eb4b28f09abdaaa66698") (revision "1"))
11163 (name "r-cycombine")
11164 (version (git-version "0.2.6" revision commit))
11167 (uri (git-reference
11168 (url "https://github.com/biosurf/cyCombine")
11170 (file-name (git-file-name name version))
11173 "1fiwnik8iahg01732fik85xhz359x32f1xc59h443pdf7jancskm"))))
11174 (properties `((upstream-name . "cyCombine")))
11175 (build-system r-build-system)
11193 (native-inputs (list r-knitr))
11194 (home-page "https://github.com/biosurf/cyCombine")
11195 (synopsis "Integration of single-cell cytometry datasets")
11197 "This package provides a method for combining single-cell cytometry
11198 datasets, which increases the analytical flexibility and the statistical power
11199 of the analyses while minimizing technical noise.")
11200 (license license:expat))))
11202 (define-public r-cytolib
11209 (uri (bioconductor-uri "cytolib" version))
11212 "18b532sicca5l8sn334prrm7g1z1cakiwydccz4i833168pnsjyg"))))
11213 (properties `((upstream-name . "cytolib")))
11214 (build-system r-build-system)
11224 (home-page "https://bioconductor.org/packages/cytolib/")
11225 (synopsis "C++ infrastructure for working with gated cytometry")
11227 "This package provides the core data structure and API to represent and
11228 interact with gated cytometry data.")
11229 (license license:artistic2.0)))
11231 (define-public r-flowcore
11233 (name "r-flowcore")
11238 (uri (bioconductor-uri "flowCore" version))
11241 "17nci6rc4i0vs0ibw5q8zy30ap7q4550qpq4ifkbblqbyzxlzkhr"))))
11242 (properties `((upstream-name . "flowCore")))
11243 (build-system r-build-system)
11256 (home-page "https://bioconductor.org/packages/flowCore")
11257 (synopsis "Basic structures for flow cytometry data")
11259 "This package provides S4 data structures and basic functions to deal
11260 with flow cytometry data.")
11261 (license license:artistic2.0)))
11263 (define-public r-flowmeans
11265 (name "r-flowmeans")
11270 (uri (bioconductor-uri "flowMeans" version))
11273 "1n4li43ydwwf5gvgmdml4ba28cxymybg5wnz6jvp35n959fwxv6y"))))
11274 (properties `((upstream-name . "flowMeans")))
11275 (build-system r-build-system)
11277 (list r-biobase r-feature r-flowcore r-rrcov))
11278 (home-page "https://bioconductor.org/packages/flowMeans")
11279 (synopsis "Non-parametric flow cytometry data gating")
11281 "This package provides tools to identify cell populations in Flow
11282 Cytometry data using non-parametric clustering and segmented-regression-based
11283 change point detection.")
11284 (license license:artistic2.0)))
11286 (define-public r-ncdfflow
11288 (name "r-ncdfflow")
11293 (uri (bioconductor-uri "ncdfFlow" version))
11296 "18ba8rygcd1ys150pk38r4w5lxwm6sl76zkd294yg847dygsqa4m"))))
11297 (properties `((upstream-name . "ncdfFlow")))
11298 (build-system r-build-system)
11310 (home-page "https://bioconductor.org/packages/ncdfFlow/")
11311 (synopsis "HDF5 based storage for flow cytometry data")
11313 "This package provides HDF5 storage based methods and functions for
11314 manipulation of flow cytometry data.")
11315 (license license:artistic2.0)))
11317 (define-public r-ggcyto
11324 (uri (bioconductor-uri "ggcyto" version))
11327 "0sycyvdpa77mykzr709a7padh6478zmnzapibbq90qkc7bxnj359"))))
11328 (properties `((upstream-name . "ggcyto")))
11329 (build-system r-build-system)
11344 (home-page "https://github.com/RGLab/ggcyto/issues")
11345 (synopsis "Visualize Cytometry data with ggplot")
11347 "With the dedicated fortify method implemented for @code{flowSet},
11348 @code{ncdfFlowSet} and @code{GatingSet} classes, both raw and gated flow
11349 cytometry data can be plotted directly with ggplot. The @code{ggcyto} wrapper
11350 and some custom layers also make it easy to add gates and population
11351 statistics to the plot.")
11352 (license license:artistic2.0)))
11354 (define-public r-flowviz
11361 (uri (bioconductor-uri "flowViz" version))
11364 "175ygncrv6q6mb8pahixs89m9wm6hdpzx489gc9s8lgad2vrvz8f"))))
11365 (properties `((upstream-name . "flowViz")))
11366 (build-system r-build-system)
11379 (home-page "https://bioconductor.org/packages/flowViz/")
11380 (synopsis "Visualization for flow cytometry")
11382 "This package provides visualization tools for flow cytometry data.")
11383 (license license:artistic2.0)))
11385 (define-public r-flowclust
11387 (name "r-flowclust")
11392 (uri (bioconductor-uri "flowClust" version))
11395 "055vm9s8aha92znhpjqkipzprw8bkrinwjaik4ygmhym7w6vbblk"))))
11396 (properties `((upstream-name . "flowClust")))
11397 (build-system r-build-system)
11399 `(#:configure-flags
11400 (list "--configure-args=--enable-bundled-gsl=no")))
11409 (list pkg-config r-knitr))
11410 (home-page "https://bioconductor.org/packages/flowClust")
11411 (synopsis "Clustering for flow cytometry")
11413 "This package provides robust model-based clustering using a t-mixture
11414 model with Box-Cox transformation.")
11415 (license license:artistic2.0)))
11417 ;; TODO: this package bundles an old version of protobuf. It's not easy to
11418 ;; make it use our protobuf package instead.
11419 (define-public r-rprotobuflib
11421 (name "r-rprotobuflib")
11426 (uri (bioconductor-uri "RProtoBufLib" version))
11429 "1mvqwrm1y0vij66gdwgpf5l1h660wsi9jzjfs4ihw3zm4cb0q5pp"))))
11430 (properties `((upstream-name . "RProtoBufLib")))
11431 (build-system r-build-system)
11434 (modify-phases %standard-phases
11435 (add-after 'unpack 'unpack-bundled-sources
11437 (with-directory-excursion "src"
11438 (invoke "tar" "xf" "protobuf-3.8.0.tar.gz")))))))
11441 (home-page "https://bioconductor.org/packages/RProtoBufLib/")
11442 (synopsis "C++ headers and static libraries of Protocol buffers")
11444 "This package provides the headers and static library of Protocol buffers
11445 for other R packages to compile and link against.")
11446 (license license:bsd-3)))
11448 (define-public r-flowworkspace
11450 (name "r-flowworkspace")
11455 (uri (bioconductor-uri "flowWorkspace" version))
11458 "0riyi9628cx1j5x6hmdd28yq75xh25j8ckcdz8dnb94dpvnhaqss"))))
11459 (properties `((upstream-name . "flowWorkspace")))
11460 (build-system r-build-system)
11491 (home-page "https://bioconductor.org/packages/flowWorkspace/")
11492 (synopsis "Infrastructure for working with cytometry data")
11494 "This package is designed to facilitate comparison of automated gating
11495 methods against manual gating done in flowJo. This package allows you to
11496 import basic flowJo workspaces into BioConductor and replicate the gating from
11497 flowJo using the @code{flowCore} functionality. Gating hierarchies, groups of
11498 samples, compensation, and transformation are performed so that the output
11499 matches the flowJo analysis.")
11500 (license license:artistic2.0)))
11502 (define-public r-flowstats
11504 (name "r-flowstats")
11509 (uri (bioconductor-uri "flowStats" version))
11512 "1jbc92ah2mlpnd7v3k0207v4qz3rg9g9yy6r6y0s0cc5nifdyhwj"))))
11513 (properties `((upstream-name . "flowStats")))
11514 (build-system r-build-system)
11532 (home-page "http://www.github.com/RGLab/flowStats")
11533 (synopsis "Statistical methods for the analysis of flow cytometry data")
11535 "This package provides methods and functionality to analyze flow data
11536 that is beyond the basic infrastructure provided by the @code{flowCore}
11538 (license license:artistic2.0)))
11540 (define-public r-opencyto
11542 (name "r-opencyto")
11547 (uri (bioconductor-uri "openCyto" version))
11550 "1nz5fra0jf70jwyfbcz5ksnz5xb62vfnfwfasr0zwwvjvmmvrs1y"))))
11551 (properties `((upstream-name . "openCyto")))
11552 (build-system r-build-system)
11577 (home-page "https://bioconductor.org/packages/openCyto")
11578 (synopsis "Hierarchical gating pipeline for flow cytometry data")
11580 "This package is designed to facilitate the automated gating methods in a
11581 sequential way to mimic the manual gating strategy.")
11582 (license license:artistic2.0)))
11584 (define-public r-cytoml
11591 (uri (bioconductor-uri "CytoML" version))
11594 "0vp7advfh1d8596hjpzayasjhga4mx0l104sgz2asscbrjm4v7rr"))))
11595 (properties `((upstream-name . "CytoML")))
11596 (build-system r-build-system)
11598 (list libxml2 zlib))
11629 (home-page "https://github.com/RGLab/CytoML")
11630 (synopsis "GatingML interface for cross platform cytometry data sharing")
11632 "This package provides an interface to implementations of the GatingML2.0
11633 standard to exchange gated cytometry data with other software platforms.")
11634 (license license:artistic2.0)))
11636 (define-public r-flowsom
11643 (uri (bioconductor-uri "FlowSOM" version))
11646 "0balsds5mm981cqamdjv3ndq1y9arharisd6f2lrpkzgvwawa645"))))
11647 (properties `((upstream-name . "FlowSOM")))
11648 (build-system r-build-system)
11650 (list r-biocgenerics
11652 r-consensusclusterplus
11672 (home-page "https://bioconductor.org/packages/FlowSOM/")
11673 (synopsis "Visualize and interpret cytometry data")
11675 "FlowSOM offers visualization options for cytometry data, by using
11676 self-organizing map clustering and minimal spanning trees.")
11677 (license license:gpl2+)))
11679 (define-public r-mixomics
11681 (name "r-mixomics")
11686 (uri (bioconductor-uri "mixOmics" version))
11689 "0fwc2w7frj0bjijzfckkxf7ipx1z13gw7907q4zr5qfl9mh127w7"))))
11690 (properties `((upstream-name . "mixOmics")))
11691 (build-system r-build-system)
11693 (list r-biocparallel
11710 (home-page "http://www.mixOmics.org")
11711 (synopsis "Multivariate methods for exploration of biological datasets")
11713 "mixOmics offers a wide range of multivariate methods for the exploration
11714 and integration of biological datasets with a particular focus on variable
11715 selection. The package proposes several sparse multivariate models we have
11716 developed to identify the key variables that are highly correlated, and/or
11717 explain the biological outcome of interest. The data that can be analysed
11718 with mixOmics may come from high throughput sequencing technologies, such as
11719 omics data (transcriptomics, metabolomics, proteomics, metagenomics etc) but
11720 also beyond the realm of omics (e.g. spectral imaging). The methods
11721 implemented in mixOmics can also handle missing values without having to
11722 delete entire rows with missing data.")
11723 (license license:gpl2+)))
11725 (define-public r-depecher
11726 (package ;Source/Weave error
11727 (name "r-depecher")
11732 (uri (bioconductor-uri "DepecheR" version))
11735 "0rixczdds5gpac50wap6s68kmpdj4208l38gcihkrysz5frbvqjp"))))
11736 (properties `((upstream-name . "DepecheR")))
11737 (build-system r-build-system)
11758 (home-page "https://bioconductor.org/packages/DepecheR/")
11759 (synopsis "Identify traits of clusters in high-dimensional entities")
11761 "The purpose of this package is to identify traits in a dataset that can
11762 separate groups. This is done on two levels. First, clustering is performed,
11763 using an implementation of sparse K-means. Secondly, the generated clusters
11764 are used to predict outcomes of groups of individuals based on their
11765 distribution of observations in the different clusters. As certain clusters
11766 with separating information will be identified, and these clusters are defined
11767 by a sparse number of variables, this method can reduce the complexity of
11768 data, to only emphasize the data that actually matters.")
11769 (license license:expat)))
11771 (define-public r-rcistarget
11773 (name "r-rcistarget")
11778 (uri (bioconductor-uri "RcisTarget" version))
11781 "17fnjkg6rjqj33v7slg81skqag10y6dc14g5iv69gqshjal4w4im"))))
11782 (properties `((upstream-name . "RcisTarget")))
11783 (build-system r-build-system)
11795 r-summarizedexperiment
11799 (home-page "https://aertslab.org/#scenic")
11800 (synopsis "Identify transcription factor binding motifs enriched on a gene list")
11802 "RcisTarget identifies @dfn{transcription factor binding motifs} (TFBS)
11803 over-represented on a gene list. In a first step, RcisTarget selects DNA
11804 motifs that are significantly over-represented in the surroundings of the
11805 @dfn{transcription start site} (TSS) of the genes in the gene-set. This is
11806 achieved by using a database that contains genome-wide cross-species rankings
11807 for each motif. The motifs that are then annotated to TFs and those that have
11808 a high @dfn{Normalized Enrichment Score} (NES) are retained. Finally, for
11809 each motif and gene-set, RcisTarget predicts the candidate target genes (i.e.
11810 genes in the gene-set that are ranked above the leading edge).")
11811 (license license:gpl3)))
11813 (define-public r-chicago
11820 (uri (bioconductor-uri "Chicago" version))
11823 "13vzxmvxpc3r9gii37zvhhr5nbnaggrva97g6m2n02qn9daf6vmm"))))
11824 (properties `((upstream-name . "Chicago")))
11825 (build-system r-build-system)
11827 (list r-data-table r-delaporte r-hmisc r-mass r-matrixstats))
11828 (native-inputs (list r-knitr))
11829 (home-page "https://bioconductor.org/packages/Chicago")
11830 (synopsis "Capture Hi-C analysis of genomic organization")
11832 "This package provides a pipeline for analysing Capture Hi-C data.")
11833 (license license:artistic2.0)))
11835 (define-public r-cicero
11842 (uri (bioconductor-uri "cicero" version))
11845 "1ip12ijazlmcfbym078slxykpkz7d1zwvs8l8aqdnqpxjfk1ipx5"))))
11846 (build-system r-build-system)
11872 (home-page "https://bioconductor.org/packages/cicero/")
11873 (synopsis "Predict cis-co-accessibility from single-cell data")
11875 "Cicero computes putative cis-regulatory maps from single-cell chromatin
11876 accessibility data. It also extends the monocle package for use in chromatin
11877 accessibility data.")
11878 (license license:expat)))
11880 ;; This is the latest commit on the "monocle3" branch.
11881 (define-public r-cicero-monocle3
11882 (let ((commit "fa2fb6515857a8cfc88bc9af044f34de1bcd2b7b")
11884 (package (inherit r-cicero)
11885 (name "r-cicero-monocle3")
11886 (version (git-version "1.3.2" revision commit))
11890 (uri (git-reference
11891 (url "https://github.com/cole-trapnell-lab/cicero-release")
11893 (file-name (git-file-name name version))
11896 "077yza93wdhi08n40md20jwk55k9lw1f3y0063qkk90cpz60wi0c"))))
11898 (modify-inputs (package-propagated-inputs r-cicero)
11899 (delete "r-monocle")
11900 (prepend r-monocle3))))))
11902 (define-public r-circrnaprofiler
11904 (name "r-circrnaprofiler")
11909 (uri (bioconductor-uri "circRNAprofiler" version))
11912 "1gwm416shhv2p3gh1n6kv1rvx0n0imy25b7z62z4s8b3gs3nfp5j"))))
11914 `((upstream-name . "circRNAprofiler")))
11915 (build-system r-build-system)
11917 (list r-annotationhub
11920 r-bsgenome-hsapiens-ucsc-hg19
11943 "https://github.com/Aufiero/circRNAprofiler")
11945 "Computational framework for the downstream analysis of circular RNA's")
11947 "@code{r-circrnaprofiler} is a computational framework for a comprehensive
11948 in silico analysis of @dfn{circular RNA} (circRNAs). This computational
11949 framework allows combining and analyzing circRNAs previously detected by
11950 multiple publicly available annotation-based circRNA detection tools. It
11951 covers different aspects of circRNAs analysis from differential expression
11952 analysis, evolutionary conservation, biogenesis to functional analysis.")
11953 (license license:gpl3)))
11955 (define-public r-cistopic
11957 (name "r-cistopic")
11962 (uri (git-reference
11963 (url "https://github.com/aertslab/cisTopic")
11964 (commit (string-append "v" version))))
11965 (file-name (git-file-name name version))
11968 "0c4553rnxq7b1w451kcc3iwvak4qa5h2b43xmfw6ii8096zd1gbf"))))
11969 (build-system r-build-system)
11986 (home-page "https://github.com/aertslab/cisTopic")
11987 (synopsis "Modelling of cis-regulatory topics from single cell epigenomics data")
11989 "The sparse nature of single cell epigenomics data can be overruled using
11990 probabilistic modelling methods such as @dfn{Latent Dirichlet
11991 Allocation} (LDA). This package allows the probabilistic modelling of
11992 cis-regulatory topics (cisTopics) from single cell epigenomics data, and
11993 includes functionalities to identify cell states based on the contribution of
11994 cisTopics and explore the nature and regulatory proteins driving them.")
11995 (license license:gpl3)))
11997 (define-public r-cistopic-next
11998 (let ((commit "04cecbb9d1112fcc1a6edc28b5a506bcb49f2803")
12001 (inherit r-cistopic)
12002 (name "r-cistopic-next")
12003 ;; The DESCRIPTION file says this is version 0.3.0, which is a bit odd
12004 ;; since the previous release is 2.1.0. Oh well.
12005 (version (git-version "0.3.0" revision commit))
12009 (uri (git-reference
12010 (url "https://github.com/aertslab/cisTopic")
12012 (file-name (git-file-name name version))
12015 "11cg9szlysnsjiaahda4k5v2vh4rxx27zhz53hafgaq9mdz0kgi2"))))
12016 (properties `((upstream-name . "cisTopic")))
12037 (define-public r-genie3
12044 (uri (bioconductor-uri "GENIE3" version))
12047 "0h3vnpnznb9rda8gfwp4cnd2mqsvs1vzmfx90dchn5pqaphz1k2l"))))
12048 (properties `((upstream-name . "GENIE3")))
12049 (build-system r-build-system)
12051 (list r-dplyr r-reshape2))
12054 (home-page "https://bioconductor.org/packages/GENIE3")
12055 (synopsis "Gene network inference with ensemble of trees")
12057 "This package implements the GENIE3 algorithm for inferring gene
12058 regulatory networks from expression data.")
12059 (license license:gpl2+)))
12061 (define-public r-roc
12068 (uri (bioconductor-uri "ROC" version))
12071 "0yfq0d0j2bzqdnjs6l2h6p48kmv9wfphlqym3brgndlnadipq1v2"))))
12072 (properties `((upstream-name . "ROC")))
12073 (build-system r-build-system)
12076 (home-page "https://www.bioconductor.org/packages/ROC/")
12077 (synopsis "Utilities for ROC curves")
12079 "This package provides utilities for @dfn{Receiver Operating
12080 Characteristic} (ROC) curves, with a focus on micro arrays.")
12081 (license license:artistic2.0)))
12083 (define-public r-watermelon
12085 (name "r-watermelon")
12090 (uri (bioconductor-uri "wateRmelon" version))
12093 "0adqyfabrvfcaj3mwp0rbqlcgpj92yb205cyhibbrs5gdr5ri4pv"))))
12094 (properties `((upstream-name . "wateRmelon")))
12095 (build-system r-build-system)
12098 r-illuminahumanmethylation450kanno-ilmn12-hg19
12107 (home-page "https://bioconductor.org/packages/wateRmelon/")
12108 (synopsis "Illumina 450 methylation array normalization and metrics")
12110 "The standard index of DNA methylation (beta) is computed from methylated
12111 and unmethylated signal intensities. Betas calculated from raw signal
12112 intensities perform well, but using 11 methylomic datasets we demonstrate that
12113 quantile normalization methods produce marked improvement. The commonly used
12114 procedure of normalizing betas is inferior to the separate normalization of M
12115 and U, and it is also advantageous to normalize Type I and Type II assays
12116 separately. This package provides 15 flavours of betas and three performance
12117 metrics, with methods for objects produced by the @code{methylumi} and
12118 @code{minfi} packages.")
12119 (license license:gpl3)))
12121 (define-public r-gdsfmt
12128 (uri (bioconductor-uri "gdsfmt" version))
12131 "1cdwyivgfc6yw5hj9b3j57wx55gckwhx6fwx2lvqynrjzjyzf3q0"))
12132 (modules '((guix build utils)))
12133 ;; Remove bundled sources of zlib, lz4, and xz. Don't attempt to build
12134 ;; them and link with system libraries instead.
12137 (for-each delete-file-recursively
12141 (substitute* "src/Makevars"
12142 (("all: \\$\\(SHLIB\\)") "all:")
12143 (("\\$\\(SHLIB\\): liblzma.a") "")
12144 (("^ (ZLIB|LZ4)/.*") "")
12145 (("CoreArray/dVLIntGDS.cpp.*")
12146 "CoreArray/dVLIntGDS.cpp")
12147 (("CoreArray/dVLIntGDS.o.*")
12148 "CoreArray/dVLIntGDS.o")
12149 (("PKG_LIBS = ./liblzma.a")
12150 "PKG_LIBS = -llz4"))
12151 (substitute* "src/CoreArray/dStream.h"
12152 (("include \"../(ZLIB|LZ4|XZ/api)/(.*)\"" _ _ header)
12153 (string-append "include <" header ">")))))))
12154 (properties `((upstream-name . "gdsfmt")))
12155 (build-system r-build-system)
12157 (list lz4 xz zlib))
12160 (home-page "http://corearray.sourceforge.net/")
12162 "R Interface to CoreArray Genomic Data Structure (GDS) Files")
12164 "This package provides a high-level R interface to CoreArray @dfn{Genomic
12165 Data Structure} (GDS) data files, which are portable across platforms with
12166 hierarchical structure to store multiple scalable array-oriented data sets
12167 with metadata information. It is suited for large-scale datasets, especially
12168 for data which are much larger than the available random-access memory. The
12169 @code{gdsfmt} package offers efficient operations specifically designed for
12170 integers of less than 8 bits, since a diploid genotype, like
12171 @dfn{single-nucleotide polymorphism} (SNP), usually occupies fewer bits than a
12172 byte. Data compression and decompression are available with relatively
12173 efficient random access. It is also allowed to read a GDS file in parallel
12174 with multiple R processes supported by the package @code{parallel}.")
12175 (license license:lgpl3)))
12177 (define-public r-bigmelon
12179 (name "r-bigmelon")
12184 (uri (bioconductor-uri "bigmelon" version))
12187 "1msch4qbifkdqv0bbw03xj6d9w28z91mf4ki41rqg6048cq17h2k"))))
12188 (properties `((upstream-name . "bigmelon")))
12189 (build-system r-build-system)
12201 (home-page "https://bioconductor.org/packages/bigmelon/")
12202 (synopsis "Illumina methylation array analysis for large experiments")
12204 "This package provides methods for working with Illumina arrays using the
12205 @code{gdsfmt} package.")
12206 (license license:gpl3)))
12208 (define-public r-seqbias
12215 (uri (bioconductor-uri "seqbias" version))
12218 "085nq6pf0bdn17wsbr5jnyy512v7rf67xff9rp5wz47mcifbv6rg"))))
12219 (properties `((upstream-name . "seqbias")))
12220 (build-system r-build-system)
12222 (list r-biostrings r-genomicranges r-rhtslib))
12223 (home-page "https://bioconductor.org/packages/seqbias/")
12224 (synopsis "Estimation of per-position bias in high-throughput sequencing data")
12226 "This package implements a model of per-position sequencing bias in
12227 high-throughput sequencing data using a simple Bayesian network, the structure
12228 and parameters of which are trained on a set of aligned reads and a reference
12230 (license license:lgpl3)))
12232 (define-public r-reqon
12239 (uri (bioconductor-uri "ReQON" version))
12242 "1f5pplm8fy3wvl0b6n18gph4dq9i9x5qiyjrj0bk0kwlkbpba74r"))))
12243 (properties `((upstream-name . "ReQON")))
12244 (build-system r-build-system)
12246 (list r-rjava r-rsamtools r-seqbias))
12247 (home-page "https://bioconductor.org/packages/ReQON/")
12248 (synopsis "Recalibrating quality of nucleotides")
12250 "This package provides an implementation of an algorithm for
12251 recalibrating the base quality scores for aligned sequencing data in BAM
12253 (license license:gpl2)))
12255 (define-public r-wavcluster
12257 (name "r-wavcluster")
12262 (uri (bioconductor-uri "wavClusteR" version))
12265 "04di095i9i19j9ppx8gdsk7n18vd02d4rjdi9d4a3p0xv05ihnb6"))))
12266 (properties `((upstream-name . "wavClusteR")))
12267 (build-system r-build-system)
12269 (list r-biocgenerics
12285 (home-page "https://bioconductor.org/packages/wavClusteR/")
12286 (synopsis "Identification of RNA-protein interaction sites in PAR-CLIP data")
12288 "This package provides an integrated pipeline for the analysis of
12289 PAR-CLIP data. PAR-CLIP-induced transitions are first discriminated from
12290 sequencing errors, SNPs and additional non-experimental sources by a non-
12291 parametric mixture model. The protein binding sites (clusters) are then
12292 resolved at high resolution and cluster statistics are estimated using a
12293 rigorous Bayesian framework. Post-processing of the results, data export for
12294 UCSC genome browser visualization and motif search analysis are provided. In
12295 addition, the package integrates RNA-Seq data to estimate the False
12296 Discovery Rate of cluster detection. Key functions support parallel multicore
12297 computing. While wavClusteR was designed for PAR-CLIP data analysis, it can
12298 be applied to the analysis of other NGS data obtained from experimental
12299 procedures that induce nucleotide substitutions (e.g. BisSeq).")
12300 (license license:gpl2)))
12302 (define-public r-timeseriesexperiment
12304 (name "r-timeseriesexperiment")
12309 (uri (bioconductor-uri "TimeSeriesExperiment" version))
12312 "0bdpxxr739qdg92qabfx122k9f43vw2hyxp4yxqlbp37vzgcdf2c"))))
12314 `((upstream-name . "TimeSeriesExperiment")))
12315 (build-system r-build-system)
12327 r-summarizedexperiment
12334 (home-page "https://github.com/nlhuong/TimeSeriesExperiment/")
12335 (synopsis "Analysis for short time-series data")
12337 "This package is a visualization and analysis toolbox for short time
12338 course data which includes dimensionality reduction, clustering, two-sample
12339 differential expression testing and gene ranking techniques. The package also
12340 provides methods for retrieving enriched pathways.")
12341 (license license:lgpl3+)))
12343 (define-public r-variantfiltering
12345 (name "r-variantfiltering")
12350 (uri (bioconductor-uri "VariantFiltering" version))
12353 "1bjqn8qik221x0bqvgd99p87v45iihwp6cxckh4ks964pd0c1xk8"))))
12355 `((upstream-name . "VariantFiltering")))
12356 (build-system r-build-system)
12358 (list r-annotationdbi
12379 r-summarizedexperiment
12380 r-variantannotation
12382 (home-page "https://github.com/rcastelo/VariantFiltering")
12383 (synopsis "Filtering of coding and non-coding genetic variants")
12385 "Filter genetic variants using different criteria such as inheritance
12386 model, amino acid change consequence, minor allele frequencies across human
12387 populations, splice site strength, conservation, etc.")
12388 (license license:artistic2.0)))
12390 (define-public r-genomegraphs
12392 (name "r-genomegraphs")
12397 (uri (bioconductor-uri "GenomeGraphs" version))
12400 "05vavhz936v7cknig2f2mn3fd9fiy54r3swlvifpawramblp1ags"))))
12401 (properties `((upstream-name . "GenomeGraphs")))
12402 (build-system r-build-system)
12405 (home-page "https://bioconductor.org/packages/GenomeGraphs/")
12406 (synopsis "Plotting genomic information from Ensembl")
12408 "Genomic data analyses requires integrated visualization of known genomic
12409 information and new experimental data. GenomeGraphs uses the biomaRt package
12410 to perform live annotation queries to Ensembl and translates this to e.g.
12411 gene/transcript structures in viewports of the grid graphics package. This
12412 results in genomic information plotted together with your data. Another
12413 strength of GenomeGraphs is to plot different data types such as array CGH,
12414 gene expression, sequencing and other data, together in one plot using the
12415 same genome coordinate system.")
12416 (license license:artistic2.0)))
12418 (define-public r-wavetiling
12420 (name "r-wavetiling")
12425 (uri (bioconductor-uri "waveTiling" version))
12428 "0d7l559zlmly8mncmh1zhkqmsml0bwwfpm7ccp8l26y852vwf7hf"))))
12429 (properties `((upstream-name . "waveTiling")))
12430 (build-system r-build-system)
12442 (home-page "https://r-forge.r-project.org/projects/wavetiling/")
12443 (synopsis "Wavelet-based models for tiling array transcriptome analysis")
12445 "This package is designed to conduct transcriptome analysis for tiling
12446 arrays based on fast wavelet-based functional models.")
12447 (license license:gpl2+)))
12449 (define-public r-variancepartition
12451 (name "r-variancepartition")
12456 (uri (bioconductor-uri "variancePartition" version))
12459 "0wk1xql8b0gxyrqz9hs54xvmp7qdw9b8jnv88p4vgv061iwyk7wv"))))
12461 `((upstream-name . "variancePartition")))
12462 (build-system r-build-system)
12486 (home-page "https://bioconductor.org/packages/variancePartition/")
12487 (synopsis "Analyze variation in gene expression experiments")
12489 "This is a package providing tools to quantify and interpret multiple
12490 sources of biological and technical variation in gene expression experiments.
12491 It uses a linear mixed model to quantify variation in gene expression
12492 attributable to individual, tissue, time point, or technical variables. The
12493 package includes dream differential expression analysis for repeated
12495 (license license:gpl2+)))
12497 (define-public r-htqpcr
12504 (uri (bioconductor-uri "HTqPCR" version))
12507 "0am98rzwpi3kybq1l27c5qn3n1pg5aqwmh6jq9q0lzbjjin3haqc"))))
12508 (properties `((upstream-name . "HTqPCR")))
12509 (build-system r-build-system)
12511 (list r-affy r-biobase r-gplots r-limma r-rcolorbrewer))
12512 (home-page (string-append "https://www.ebi.ac.uk/sites/ebi.ac.uk/files/"
12513 "groups/bertone/software/HTqPCR.pdf"))
12514 (synopsis "Automated analysis of high-throughput qPCR data")
12516 "Analysis of Ct values from high throughput quantitative real-time
12517 PCR (qPCR) assays across multiple conditions or replicates. The input data
12518 can be from spatially-defined formats such ABI TaqMan Low Density Arrays or
12519 OpenArray; LightCycler from Roche Applied Science; the CFX plates from Bio-Rad
12520 Laboratories; conventional 96- or 384-well plates; or microfluidic devices
12521 such as the Dynamic Arrays from Fluidigm Corporation. HTqPCR handles data
12522 loading, quality assessment, normalization, visualization and parametric or
12523 non-parametric testing for statistical significance in Ct values between
12524 features (e.g. genes, microRNAs).")
12525 (license license:artistic2.0)))
12527 (define-public r-unifiedwmwqpcr
12529 (name "r-unifiedwmwqpcr")
12534 (uri (bioconductor-uri "unifiedWMWqPCR" version))
12537 "1skfs94a6bv05c844zf5vfqw1fbgxyppgdnckdbhxg2a2470a4wh"))))
12539 `((upstream-name . "unifiedWMWqPCR")))
12540 (build-system r-build-system)
12542 (list r-biocgenerics r-htqpcr))
12543 (home-page "https://bioconductor.org/packages/unifiedWMWqPCR")
12544 (synopsis "Unified Wilcoxon-Mann Whitney Test for differential expression in qPCR data")
12546 "This package implements the unified Wilcoxon-Mann-Whitney Test for qPCR
12547 data. This modified test allows for testing differential expression in qPCR
12549 (license license:gpl2+)))
12551 (define-public r-universalmotif
12553 (name "r-universalmotif")
12558 (uri (bioconductor-uri "universalmotif" version))
12561 "1sm54z8aq3534qjsa19wychhwcvwnjlkydmiqqvidiiwcxwqpjsr"))))
12563 `((upstream-name . "universalmotif")))
12564 (build-system r-build-system)
12567 (modify-phases %standard-phases
12568 (add-after 'unpack 'fix-reference-to-strip
12570 (substitute* "src/Makevars"
12571 (("/usr/bin/strip") (which "strip"))))))))
12573 (list r-biocgenerics
12586 "https://bioconductor.org/packages/universalmotif/")
12588 "Specific structures importer, modifier, and exporter for R")
12590 "This package allows importing most common @dfn{specific structure}
12591 (motif) types into R for use by functions provided by other Bioconductor
12592 motif-related packages. Motifs can be exported into most major motif formats
12593 from various classes as defined by other Bioconductor packages. A suite of
12594 motif and sequence manipulation and analysis functions are included, including
12595 enrichment, comparison, P-value calculation, shuffling, trimming, higher-order
12596 motifs, and others.")
12597 (license license:gpl3)))
12599 (define-public r-ace
12605 (uri (bioconductor-uri "ACE" version))
12608 "1xnw288vz810vjkidar5h218wyc0q2hx0k4zi3r88vaz5rfhc05m"))))
12609 (properties `((upstream-name . "ACE")))
12610 (build-system r-build-system)
12611 (propagated-inputs (list r-biobase r-genomicranges r-ggplot2 r-qdnaseq))
12612 (native-inputs (list r-knitr))
12613 (home-page "https://github.com/tgac-vumc/ACE")
12615 "Absolute copy number estimation from low-coverage whole genome sequencing")
12617 "This package uses segmented copy number data to estimate tumor cell
12618 percentage and produce copy number plots displaying absolute copy numbers. For
12619 this it uses segmented data from the @code{QDNAseq} package, which in turn uses
12620 a number of dependencies to turn mapped reads into segmented data. @code{ACE}
12621 will run @code{QDNAseq} or use its output rds-file of segmented data. It will
12622 subsequently run through all samples in the object(s), for which it will create
12623 individual subdirectories. For each sample, it will calculate how well the
12624 segments fit (the relative error) to integer copy numbers for each percentage
12625 of @dfn{tumor cells} (cells with divergent segments).")
12626 (license license:gpl2)))
12628 (define-public r-acgh
12634 (uri (bioconductor-uri "aCGH" version))
12637 "00ni0kwy68v33ggfi8g5vffirhmbhaxg4l54hcqhx75m535z1x7d"))))
12638 (properties `((upstream-name . "aCGH")))
12639 (build-system r-build-system)
12640 (propagated-inputs (list r-biobase r-cluster r-multtest r-survival))
12641 (home-page "https://bioconductor.org/packages/aCGH")
12643 "Classes and functions for array comparative genomic hybridization data")
12645 "This package provides functions for reading
12646 @dfn{array comparative genomic hybridization} (aCGH) data from image analysis
12647 output files and clone information files, creation of @code{aCGH} objects for
12648 storing these data. Basic methods are accessing/replacing, subsetting,
12649 printing and plotting @code{aCGH} objects.")
12650 (license license:gpl2)))
12652 (define-public r-acme
12658 (uri (bioconductor-uri "ACME" version))
12661 "0ilcsgpc4m47gifxc0yzx2xi3g4day515mncnnjvfdj3iq8xwk25"))))
12662 (properties `((upstream-name . "ACME")))
12663 (build-system r-build-system)
12664 (propagated-inputs (list r-biobase r-biocgenerics))
12665 (home-page "https://bioconductor.org/packages/aCGH/")
12666 (synopsis "Calculating microarray enrichment")
12668 "This package implements @dfn{algorithms for calculating microarray
12669 enrichment} (ACME), and it is a set of tools for analysing tiling array of
12670 @dfn{combined chromatin immunoprecipitation with DNA microarray} (ChIP/chip),
12671 DNAse hypersensitivity, or other experiments that result in regions of the
12672 genome showing enrichment. It does not rely on a specific array technology
12673 (although the array should be a tiling array), is very general (can be applied
12674 in experiments resulting in regions of enrichment), and is very insensitive to
12675 array noise or normalization methods. It is also very fast and can be applied
12676 on whole-genome tiling array experiments quite easily with enough memory.")
12677 (license license:gpl2+)))
12679 (define-public r-acde
12685 (uri (bioconductor-uri "acde" version))
12688 "0lgq546y4qklfzbc6fjr3d656hn76p6dn4694qfiafql2nlsjbj2"))))
12689 (properties `((upstream-name . "acde")))
12690 (build-system r-build-system)
12691 (propagated-inputs (list r-boot))
12692 (home-page "https://bioconductor.org/packages/acde")
12694 "Identification of differentially expressed genes with artificial components")
12696 "This package provides a multivariate inferential analysis method for
12697 detecting differentially expressed genes in gene expression data. It uses
12698 artificial components, close to the data's principal components but with an
12699 exact interpretation in terms of differential genetic expression, to identify
12700 differentially expressed genes while controlling the @dfn{false discovery
12702 (license license:gpl3)))
12704 ;; This is a CRAN package, but it depends on Bioconductor packages, so we put
12706 (define-public r-activedriverwgs
12708 (name "r-activedriverwgs")
12713 (uri (cran-uri "ActiveDriverWGS" version))
12716 "13b5yazgv9kckcp6gck183mh1m0q8lc5ixagmcy9s8kv2wz7wq45"))))
12718 `((upstream-name . "ActiveDriverWGS")))
12719 (build-system r-build-system)
12723 r-bsgenome-hsapiens-ucsc-hg19
12724 r-bsgenome-hsapiens-ucsc-hg38
12725 r-bsgenome-mmusculus-ucsc-mm9
12726 r-bsgenome-mmusculus-ucsc-mm10
12733 (home-page "https://cran.r-project.org/web/packages/ActiveDriverWGS/")
12734 (synopsis "Driver discovery tool for cancer whole genomes")
12736 "This package provides a method for finding an enrichment of cancer
12737 simple somatic mutations (SNVs and Indels) in functional elements across the
12738 human genome. ActiveDriverWGS detects coding and noncoding driver elements
12739 using whole genome sequencing data.")
12740 (license license:gpl3)))
12742 ;; This is a CRAN package, but it depends on Bioconductor packages, so we put
12744 (define-public r-activepathways
12746 (name "r-activepathways")
12751 (uri (cran-uri "ActivePathways" version))
12754 "0zbrgz91mlik7j8j11wsdswqqqfsijj8jkgd5fx1ar3mc6rqsmbg"))))
12756 `((upstream-name . "ActivePathways")))
12757 (build-system r-build-system)
12759 (list r-data-table r-ggplot2))
12762 (home-page "https://cran.r-project.org/web/packages/ActivePathways/")
12763 (synopsis "Multivariate pathway enrichment analysis")
12765 "This package represents an integrative method of analyzing multi omics
12766 data that conducts enrichment analysis of annotated gene sets. ActivePathways
12767 uses a statistical data fusion approach, rationalizes contributing evidence
12768 and highlights associated genes, improving systems-level understanding of
12769 cellular organization in health and disease.")
12770 (license license:gpl3)))
12772 (define-public r-bgmix
12779 (uri (bioconductor-uri "BGmix" version))
12782 "03f6nknp3n49yvg2d9qsmds676rva70pr4wjz0md228jczgjk0vj"))))
12783 (properties `((upstream-name . "BGmix")))
12784 (build-system r-build-system)
12786 (list r-kernsmooth))
12787 (home-page "https://bioconductor.org/packages/BGmix/")
12788 (synopsis "Bayesian models for differential gene expression")
12790 "This package provides fully Bayesian mixture models for differential
12792 (license license:gpl2)))
12794 (define-public r-bgx
12801 (uri (bioconductor-uri "bgx" version))
12804 "0q2y4n6bcc9pvz5sgfkw1lrb00rrp7q29i1vh7srdfmfhgpyz6bk"))))
12805 (properties `((upstream-name . "bgx")))
12806 (build-system r-build-system)
12808 (list r-affy r-biobase r-gcrma r-rcpp))
12809 (home-page "https://bioconductor.org/packages/bgx/")
12810 (synopsis "Bayesian gene expression")
12812 "This package provides tools for Bayesian integrated analysis of
12813 Affymetrix GeneChips.")
12814 (license license:gpl2)))
12816 (define-public r-bhc
12823 (uri (bioconductor-uri "BHC" version))
12826 "1kqajd16981y5yaak2imaq1i7pilgqdr3nbhggsakh787j1d9rc5"))))
12827 (properties `((upstream-name . "BHC")))
12828 (build-system r-build-system)
12829 (home-page "https://bioconductor.org/packages/BHC/")
12830 (synopsis "Bayesian hierarchical clustering")
12832 "The method implemented in this package performs bottom-up hierarchical
12833 clustering, using a Dirichlet Process (infinite mixture) to model uncertainty
12834 in the data and Bayesian model selection to decide at each step which clusters
12835 to merge. This avoids several limitations of traditional methods, for example
12836 how many clusters there should be and how to choose a principled distance
12837 metric. This implementation accepts multinomial (i.e. discrete, with 2+
12838 categories) or time-series data. This version also includes a randomised
12839 algorithm which is more efficient for larger data sets.")
12840 (license license:gpl3)))
12842 (define-public r-bicare
12849 (uri (bioconductor-uri "BicARE" version))
12852 "0qjh5bsjcjry6k1vzdaascwy2shjrkc2bw0w57w0qa458cbi89z2"))))
12853 (properties `((upstream-name . "BicARE")))
12854 (build-system r-build-system)
12856 (list r-biobase r-gseabase r-multtest))
12857 (home-page "http://bioinfo.curie.fr")
12858 (synopsis "Biclustering analysis and results exploration")
12860 "This is a package for biclustering analysis and exploration of
12862 (license license:gpl2)))
12864 (define-public r-bifet
12871 (uri (bioconductor-uri "BiFET" version))
12874 "03ypbbn8i0f4bl4m6wfdcv702jydniak56wqjb1vlrckd9aphwzq"))))
12875 (properties `((upstream-name . "BiFET")))
12876 (build-system r-build-system)
12878 (list r-genomicranges r-poibin))
12881 (home-page "https://bioconductor.org/packages/BiFET")
12882 (synopsis "Bias-free footprint enrichment test")
12884 "BiFET identifies @dfn{transcription factors} (TFs) whose footprints are
12885 over-represented in target regions compared to background regions after
12886 correcting for the bias arising from the imbalance in read counts and GC
12887 contents between the target and background regions. For a given TF k, BiFET
12888 tests the null hypothesis that the target regions have the same probability of
12889 having footprints for the TF k as the background regions while correcting for
12890 the read count and GC content bias.")
12891 (license license:gpl3)))
12893 (define-public r-rsbml
12900 (uri (bioconductor-uri "rsbml" version))
12903 "1v11pspkml6xdsacgwxw8r4qdhbnn2h2sqgpm9aidaq9p2085b0v"))))
12904 (properties `((upstream-name . "rsbml")))
12905 (build-system r-build-system)
12909 (list r-biocgenerics r-graph))
12912 (home-page "http://www.sbml.org")
12913 (synopsis "R support for SBML")
12915 "This package provides an R interface to libsbml for SBML parsing,
12916 validating output, provides an S4 SBML DOM, converts SBML to R graph objects.")
12917 (license license:artistic2.0)))
12919 (define-public r-hypergraph
12921 (name "r-hypergraph")
12926 (uri (bioconductor-uri "hypergraph" version))
12929 "0xmryqj5yw1ns6wbhjqbb6h14jlj89zrznzvqnvd4n03ci20kzzp"))))
12930 (properties `((upstream-name . "hypergraph")))
12931 (build-system r-build-system)
12934 (home-page "https://bioconductor.org/packages/hypergraph")
12935 (synopsis "Hypergraph data structures")
12937 "This package implements some simple capabilities for representing and
12938 manipulating hypergraphs.")
12939 (license license:artistic2.0)))
12941 (define-public r-hyperdraw
12943 (name "r-hyperdraw")
12948 (uri (bioconductor-uri "hyperdraw" version))
12951 "0ndw4y6b15jy4w86vfkahmdc81d3ycjsvqy1mxi55dwvd8xq0ap6"))))
12952 (properties `((upstream-name . "hyperdraw")))
12953 (build-system r-build-system)
12954 (inputs (list graphviz))
12956 (list r-graph r-hypergraph r-rgraphviz))
12957 (home-page "https://bioconductor.org/packages/hyperdraw")
12958 (synopsis "Visualizing hypergraphs")
12960 "This package provides functions for visualizing hypergraphs.")
12961 (license license:gpl2+)))
12963 (define-public r-biggr
12970 (uri (bioconductor-uri "BiGGR" version))
12973 "0n57bgl6xz5b1gpw4isimq2pqxmlabn7jzhbjg2fbxcklabdvrcw"))))
12974 (properties `((upstream-name . "BiGGR")))
12975 (build-system r-build-system)
12983 (home-page "https://bioconductor.org/packages/BiGGR/")
12984 (synopsis "Constraint based modeling using metabolic reconstruction databases")
12986 "This package provides an interface to simulate metabolic reconstruction
12987 from the @url{http://bigg.ucsd.edu/, BiGG database} and other metabolic
12988 reconstruction databases. The package facilitates @dfn{flux balance
12989 analysis} (FBA) and the sampling of feasible flux distributions. Metabolic
12990 networks and estimated fluxes can be visualized with hypergraphs.")
12991 (license license:gpl3+)))
12993 (define-public r-bigmemoryextras
12995 (name "r-bigmemoryextras")
13000 (uri (bioconductor-uri "bigmemoryExtras" version))
13003 "1k31h746j8r3f92vj62s38fw12qjkv5814ipcqfbswnxgaan17zj"))))
13005 `((upstream-name . "bigmemoryExtras")))
13006 (build-system r-build-system)
13008 (list r-bigmemory))
13011 (home-page "https://github.com/phaverty/bigmemoryExtras")
13012 (synopsis "Extension of the bigmemory package")
13014 "This package defines a @code{BigMatrix} @code{ReferenceClass} which adds
13015 safety and convenience features to the @code{filebacked.big.matrix} class from
13016 the @code{bigmemory} package. @code{BigMatrix} protects against segfaults by
13017 monitoring and gracefully restoring the connection to on-disk data and it also
13018 protects against accidental data modification with a file-system-based
13019 permissions system. Utilities are provided for using @code{BigMatrix}-derived
13020 classes as @code{assayData} matrices within the @code{Biobase} package's
13021 @code{eSet} family of classes. @code{BigMatrix} provides some optimizations
13022 related to attaching to, and indexing into, file-backed matrices with
13023 dimnames. Additionally, the package provides a @code{BigMatrixFactor} class,
13024 a file-backed matrix with factor properties.")
13025 (license license:artistic2.0)))
13027 (define-public r-bigpint
13034 (uri (bioconductor-uri "bigPint" version))
13037 "1hp69j2qcidrxqs3dxjjngb09nbzp5x2yy4jz1rjmv6ghif9ccfj"))))
13038 (properties `((upstream-name . "bigPint")))
13039 (build-system r-build-system)
13041 (list r-delayedarray
13057 r-summarizedexperiment
13061 (home-page "https://github.com/lindsayrutter/bigPint")
13062 (synopsis "Big multivariate data plotted interactively")
13064 "This package provides methods for visualizing large multivariate
13065 datasets using static and interactive scatterplot matrices, parallel
13066 coordinate plots, volcano plots, and litre plots. It includes examples for
13067 visualizing RNA-sequencing datasets and differentially expressed genes.")
13068 (license license:gpl3)))
13070 (define-public r-chemminer
13072 (name "r-chemminer")
13077 (uri (bioconductor-uri "ChemmineR" version))
13080 "1nri4zkc9lp1mqgsi0h58486vixwiv2989b6pmx2aj5c3575i0ma"))))
13081 (properties `((upstream-name . "ChemmineR")))
13082 (build-system r-build-system)
13101 (home-page "https://github.com/girke-lab/ChemmineR")
13102 (synopsis "Cheminformatics toolkit for R")
13104 "ChemmineR is a cheminformatics package for analyzing drug-like small
13105 molecule data in R. It contains functions for efficient processing of large
13106 numbers of molecules, physicochemical/structural property predictions,
13107 structural similarity searching, classification and clustering of compound
13108 libraries with a wide spectrum of algorithms. In addition, it offers
13109 visualization functions for compound clustering results and chemical
13111 (license license:artistic2.0)))
13113 (define-public r-fmcsr
13120 (uri (bioconductor-uri "fmcsR" version))
13122 (base32 "1mblmk21dxc9v2fikhvfg2njwgl190gkysppl6msxizwcmxsmh30"))))
13123 (properties `((upstream-name . "fmcsR")))
13124 (build-system r-build-system)
13126 (list r-biocgenerics r-chemminer r-runit))
13127 (native-inputs (list r-knitr))
13128 (home-page "https://github.com/girke-lab/fmcsR")
13129 (synopsis "Mismatch tolerant maximum common substructure searching")
13131 "The fmcsR package introduces an efficient @dfn{maximum common
13132 substructure} (MCS) algorithms combined with a novel matching strategy that
13133 allows for atom and/or bond mismatches in the substructures shared among two
13134 small molecules. The resulting flexible MCSs (FMCSs) are often larger than
13135 strict MCSs, resulting in the identification of more common features in their
13136 source structures, as well as a higher sensitivity in finding compounds with
13137 weak structural similarities. The fmcsR package provides several utilities to
13138 use the FMCS algorithm for pairwise compound comparisons, structure similarity
13139 searching and clustering.")
13140 (license license:artistic2.0)))
13142 (define-public r-bioassayr
13144 (name "r-bioassayr")
13149 (uri (bioconductor-uri "bioassayR" version))
13152 "0zbrci0vgk4qca28i0qb2izhyrz3r95l1w54h9h3zj9f3vd61wrz"))))
13153 (properties `((upstream-name . "bioassayR")))
13154 (build-system r-build-system)
13156 (list r-biocgenerics
13165 (home-page "https://github.com/girke-lab/bioassayR")
13166 (synopsis "Cross-target analysis of small molecule bioactivity")
13168 "bioassayR is a computational tool that enables simultaneous analysis of
13169 thousands of bioassay experiments performed over a diverse set of compounds
13170 and biological targets. Unique features include support for large-scale
13171 cross-target analyses of both public and custom bioassays, generation of
13172 @dfn{high throughput screening fingerprints} (HTSFPs), and an optional
13173 preloaded database that provides access to a substantial portion of publicly
13174 available bioactivity data.")
13175 (license license:artistic2.0)))
13177 (define-public r-biobroom
13179 (name "r-biobroom")
13184 (uri (bioconductor-uri "biobroom" version))
13187 "04x1z9nchm4mbhqr31011zdprc4md156j4zf003s7xx0n278xsgh"))))
13188 (properties `((upstream-name . "biobroom")))
13189 (build-system r-build-system)
13191 (list r-biobase r-broom r-dplyr r-tidyr))
13194 (home-page "https://github.com/StoreyLab/biobroom")
13195 (synopsis "Turn Bioconductor objects into tidy data frames")
13197 "This package contains methods for converting standard objects
13198 constructed by bioinformatics packages, especially those in Bioconductor, and
13199 converting them to @code{tidy} data. It thus serves as a complement to the
13200 @code{broom} package, and follows the same tidy, augment, glance division of
13201 tidying methods. Tidying data makes it easy to recombine, reshape and
13202 visualize bioinformatics analyses.")
13203 ;; Any version of the LGPL.
13204 (license license:lgpl3+)))
13206 (define-public r-graphite
13208 (name "r-graphite")
13213 (uri (bioconductor-uri "graphite" version))
13216 "0nl5mkgrvf7vsqjy48ij9b1dmxfvp9lf8cpay55h93c4qz4x606g"))))
13217 (properties `((upstream-name . "graphite")))
13218 (build-system r-build-system)
13220 (list r-annotationdbi r-graph r-httr r-rappdirs r-rlang))
13221 (home-page "https://bioconductor.org/packages/graphite/")
13222 (synopsis "Networks from pathway databases")
13224 "Graphite provides networks derived from eight public pathway databases,
13225 and automates the conversion of node identifiers (e.g. from Entrez IDs to gene
13227 (license license:agpl3+)))
13229 (define-public r-reactomepa
13231 (name "r-reactomepa")
13236 (uri (bioconductor-uri "ReactomePA" version))
13239 "1fd72m2afxbbvbgwy8knp6fiq1h561plmsh4r8a08w21ngmkz2s5"))))
13240 (properties `((upstream-name . "ReactomePA")))
13241 (build-system r-build-system)
13243 (list r-annotationdbi
13253 (home-page "https://guangchuangyu.github.io/software/ReactomePA")
13254 (synopsis "Reactome pathway analysis")
13256 "This package provides functions for pathway analysis based on the
13257 REACTOME pathway database. It implements enrichment analysis, gene set
13258 enrichment analysis and several functions for visualization.")
13259 (license license:gpl2)))
13261 (define-public r-ebarrays
13263 (name "r-ebarrays")
13268 (uri (bioconductor-uri "EBarrays" version))
13271 "027zarnpxpdnyl877swp5ypxj7zvq0cjp2q2xs6g6yn5dpqjvxxk"))))
13272 (properties `((upstream-name . "EBarrays")))
13273 (build-system r-build-system)
13275 (list r-biobase r-cluster r-lattice))
13276 (home-page "https://bioconductor.org/packages/EBarrays/")
13277 (synopsis "Gene clustering and differential expression identification")
13279 "EBarrays provides tools for the analysis of replicated/unreplicated
13281 (license license:gpl2+)))
13283 (define-public r-bioccasestudies
13285 (name "r-bioccasestudies")
13290 (uri (bioconductor-uri "BiocCaseStudies" version))
13293 "03n49b6fvyyzmvdy4yif3cl7yv21c09c8xdx4cvvax5zz4v4sab1"))))
13295 `((upstream-name . "BiocCaseStudies")))
13296 (build-system r-build-system)
13297 (propagated-inputs (list r-biobase))
13298 (home-page "https://bioconductor.org/packages/BiocCaseStudies")
13299 (synopsis "Support for the case studies monograph")
13301 "This package provides software and data to support the case studies
13303 (license license:artistic2.0)))
13305 (define-public r-bioccheck
13307 (name "r-bioccheck")
13311 (uri (bioconductor-uri "BiocCheck" version))
13314 "1k1gxzmxx26hmwdxgagv93mv4jwyygkk8703ds6nvryzhqffzkbc"))))
13316 `((upstream-name . "BiocCheck")))
13317 (build-system r-build-system)
13328 (home-page "https://bioconductor.org/packages/BiocCheck")
13329 (synopsis "Executes Bioconductor-specific package checks")
13330 (description "This package contains tools to perform additional quality
13331 checks on R packages that are to be submitted to the Bioconductor repository.")
13332 (license license:artistic2.0)))
13334 (define-public r-biocgraph
13336 (name "r-biocgraph")
13341 (uri (bioconductor-uri "biocGraph" version))
13344 "1y59a7c4ahhn1g2wz2hkx83izfn8i85mmxxp63jdd0rg7zwhr6nn"))))
13345 (properties `((upstream-name . "biocGraph")))
13346 (build-system r-build-system)
13348 (list r-biocgenerics r-geneplotter r-graph r-rgraphviz))
13349 (home-page "https://bioconductor.org/packages/biocGraph/")
13350 (synopsis "Graph examples and use cases in Bioinformatics")
13352 "This package provides examples and code that make use of the
13353 different graph related packages produced by Bioconductor.")
13354 (license license:artistic2.0)))
13356 (define-public r-biocstyle
13358 (name "r-biocstyle")
13362 (uri (bioconductor-uri "BiocStyle" version))
13365 "1nwiib201b9q1x19ihqjqr5jl0vnid8wfgpi8sa3y02bn722g5a5"))))
13367 `((upstream-name . "BiocStyle")))
13368 (build-system r-build-system)
13370 (list r-biocmanager r-bookdown r-knitr r-rmarkdown r-yaml))
13373 (home-page "https://bioconductor.org/packages/BiocStyle")
13374 (synopsis "Bioconductor formatting styles")
13375 (description "This package provides standard formatting styles for
13376 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
13378 (license license:artistic2.0)))
13380 (define-public r-biocviews
13382 (name "r-biocviews")
13386 (uri (bioconductor-uri "biocViews" version))
13389 "1lahla53awdqiglfiygbxg5pkzfabym7n5abgyp1nvqsvsj0g126"))))
13391 `((upstream-name . "biocViews")))
13392 (build-system r-build-system)
13401 (home-page "https://bioconductor.org/packages/biocViews")
13402 (synopsis "Bioconductor package categorization helper")
13403 (description "The purpose of biocViews is to create HTML pages that
13404 categorize packages in a Bioconductor package repository according to keywords,
13405 also known as views, in a controlled vocabulary.")
13406 (license license:artistic2.0)))
13408 (define-public r-experimenthub
13410 (name "r-experimenthub")
13415 (uri (bioconductor-uri "ExperimentHub" version))
13418 "11hna8vrm1az1zk7pw2dv0wh84sd0hw2bi55w40hqvs36csb7lkl"))))
13419 (properties `((upstream-name . "ExperimentHub")))
13420 (build-system r-build-system)
13422 (list r-annotationhub
13431 (home-page "https://bioconductor.org/packages/ExperimentHub/")
13432 (synopsis "Client to access ExperimentHub resources")
13434 "This package provides a client for the Bioconductor ExperimentHub web
13435 resource. ExperimentHub provides a central location where curated data from
13436 experiments, publications or training courses can be accessed. Each resource
13437 has associated metadata, tags and date of modification. The client creates
13438 and manages a local cache of files retrieved enabling quick and reproducible
13440 (license license:artistic2.0)))
13442 (define-public r-grohmm
13449 (uri (bioconductor-uri "groHMM" version))
13452 "0v2mk7xcy483w2nygpmyjp73kj3v5pkk1kf1wr41n33dxqlddqai"))))
13453 (properties `((upstream-name . "groHMM")))
13454 (build-system r-build-system)
13456 (list r-genomeinfodb
13457 r-genomicalignments
13463 (home-page "https://github.com/Kraus-Lab/groHMM")
13464 (synopsis "GRO-seq analysis pipeline")
13466 "This package provides a pipeline for the analysis of GRO-seq data.")
13467 (license license:gpl3+)))
13469 (define-public r-multiassayexperiment
13471 (name "r-multiassayexperiment")
13476 (uri (bioconductor-uri "MultiAssayExperiment" version))
13479 "1wnp52l9vifxn1wzqgndzp9b6ih0s1cflxx1fhw32k32d05cw9q1"))))
13481 `((upstream-name . "MultiAssayExperiment")))
13482 (build-system r-build-system)
13489 r-summarizedexperiment
13493 (home-page "https://waldronlab.io/MultiAssayExperiment/")
13494 (synopsis "Integration of multi-omics experiments in Bioconductor")
13496 "MultiAssayExperiment harmonizes data management of multiple assays
13497 performed on an overlapping set of specimens. It provides a familiar
13498 Bioconductor user experience by extending concepts from
13499 @code{SummarizedExperiment}, supporting an open-ended mix of standard data
13500 classes for individual assays, and allowing subsetting by genomic ranges or
13502 (license license:artistic2.0)))
13504 (define-public r-bioconcotk
13506 (name "r-bioconcotk")
13511 (uri (bioconductor-uri "BiocOncoTK" version))
13514 "1alplszw84vqa1mvzp996f94s40scmh4qwbrqhg43hrnyvbnq7pi"))))
13515 (properties `((upstream-name . "BiocOncoTK")))
13516 (build-system r-build-system)
13539 r-summarizedexperiment))
13542 (home-page "https://bioconductor.org/packages/BiocOncoTK")
13543 (synopsis "Bioconductor components for general cancer genomics")
13545 "The purpose of this package is to provide a central interface to various
13546 tools for genome-scale analysis of cancer studies.")
13547 (license license:artistic2.0)))
13549 (define-public r-biocor
13556 (uri (bioconductor-uri "BioCor" version))
13559 "004mksswampwisljcdz6fswwbgdjdii3y86gjzib0gf8v4w7w4q3"))))
13560 (properties `((upstream-name . "BioCor")))
13561 (build-system r-build-system)
13563 (list r-biocparallel r-gseabase r-matrix))
13566 (home-page "https://llrs.github.io/BioCor/")
13567 (synopsis "Functional similarities")
13569 "This package provides tools to calculate functional similarities based
13570 on the pathways described on KEGG and REACTOME or in gene sets. These
13571 similarities can be calculated for pathways or gene sets, genes, or clusters
13572 and combined with other similarities. They can be used to improve networks,
13573 gene selection, testing relationships, and so on.")
13574 (license license:expat)))
13576 (define-public r-biocpkgtools
13578 (name "r-biocpkgtools")
13583 (uri (bioconductor-uri "BiocPkgTools" version))
13586 "1v0824vmg49q9lh0igdyniryyknw6vmh462rn25kmg9hdna0w99h"))))
13587 (properties `((upstream-name . "BiocPkgTools")))
13588 (build-system r-build-system)
13590 (list r-biocfilecache
13614 (home-page "https://github.com/seandavi/BiocPkgTools")
13615 (synopsis "Collection of tools for learning about Bioconductor packages")
13617 "Bioconductor has a rich ecosystem of metadata around packages, usage,
13618 and build status. This package is a simple collection of functions to access
13619 that metadata from R. The goal is to expose metadata for data mining and
13620 value-added functionality such as package searching, text mining, and
13621 analytics on packages.")
13622 (license license:expat)))
13624 (define-public r-biocset
13631 (uri (bioconductor-uri "BiocSet" version))
13634 "1ghba7020inrdxlbrrgds9gjymjxjma2p89b9lgkjin89zalqglh"))))
13635 (properties `((upstream-name . "BiocSet")))
13636 (build-system r-build-system)
13638 (list r-annotationdbi
13651 "https://bioconductor.org/packages/BiocSet")
13653 "Representing Different Biological Sets")
13655 "BiocSet displays different biological sets in a triple tibble format.
13656 These three tibbles are @code{element}, @code{set}, and @code{elementset}.
13657 The user has the ability to activate one of these three tibbles to perform
13658 common functions from the @code{dplyr} package. Mapping functionality and
13659 accessing web references for elements/sets are also available in BiocSet.")
13660 (license license:artistic2.0)))
13662 (define-public r-biocworkflowtools
13664 (name "r-biocworkflowtools")
13669 (uri (bioconductor-uri "BiocWorkflowTools" version))
13672 "1jj4icpkhrv9f6yx3vghkpdil1pfghf3yvc9756wmndvhs100r5l"))))
13674 `((upstream-name . "BiocWorkflowTools")))
13675 (build-system r-build-system)
13688 (home-page "https://bioconductor.org/packages/BiocWorkflowTools/")
13689 (synopsis "Tools to aid the development of Bioconductor Workflow packages")
13691 "This package provides functions to ease the transition between
13692 Rmarkdown and LaTeX documents when authoring a Bioconductor Workflow.")
13693 (license license:expat)))
13695 (define-public r-biodist
13702 (uri (bioconductor-uri "bioDist" version))
13705 "04nrvrcvpj0sn8p2i8n3ggsl2s7r4na576174i7bn1sj21vr0yb0"))))
13706 (properties `((upstream-name . "bioDist")))
13707 (build-system r-build-system)
13709 (list r-biobase r-kernsmooth))
13710 (home-page "https://bioconductor.org/packages/bioDist/")
13711 (synopsis "Different distance measures")
13713 "This package provides a collection of software tools for calculating
13714 distance measures.")
13715 (license license:artistic2.0)))
13717 (define-public r-pcatools
13719 (name "r-pcatools")
13724 (uri (bioconductor-uri "PCAtools" version))
13727 "03s4dh008fys2rrcpzanc0892p63f6jyyvzc9m42jbi1dlkyx26v"))))
13728 (properties `((upstream-name . "PCAtools")))
13729 (build-system r-build-system)
13737 r-delayedmatrixstats
13745 (native-inputs (list r-knitr))
13746 (home-page "https://github.com/kevinblighe/PCAtools")
13747 (synopsis "PCAtools: everything Principal Components Analysis")
13749 "@dfn{Principal Component Analysis} (PCA) extracts the fundamental
13750 structure of the data without the need to build any model to represent it.
13751 This \"summary\" of the data is arrived at through a process of reduction that
13752 can transform the large number of variables into a lesser number that are
13753 uncorrelated (i.e. the 'principal components'), while at the same time being
13754 capable of easy interpretation on the original data. PCAtools provides
13755 functions for data exploration via PCA, and allows the user to generate
13756 publication-ready figures. PCA is performed via @code{BiocSingular}; users
13757 can also identify an optimal number of principal components via different
13758 metrics, such as the elbow method and Horn's parallel analysis, which has
13759 relevance for data reduction in single-cell RNA-seq (scRNA-seq) and high
13760 dimensional mass cytometry data.")
13761 (license license:gpl3)))
13763 (define-public r-rgreat
13770 (uri (bioconductor-uri "rGREAT" version))
13773 "0px72r8mjimf5mxfwb9qz46kqpgjw5gaqq41hy0212ymjd8whaky"))))
13774 (properties `((upstream-name . "rGREAT")))
13775 (build-system r-build-system)
13777 (list r-genomicranges r-getoptlong r-iranges r-rcurl r-rjson))
13778 (native-inputs (list r-knitr))
13779 (home-page "https://github.com/jokergoo/rGREAT")
13780 (synopsis "Client for GREAT analysis")
13782 "This package makes GREAT (Genomic Regions Enrichment of Annotations
13783 Tool) analysis automatic by constructing a HTTP POST request according to
13784 user's input and automatically retrieving results from GREAT web server.")
13785 (license license:expat)))
13787 (define-public r-m3c
13794 (uri (bioconductor-uri "M3C" version))
13797 "120gd7gkgc98d1l6hl2ij799b3jksdnga5iyb44ps9mbc79hl012"))))
13798 (properties `((upstream-name . "M3C")))
13799 (build-system r-build-system)
13811 (native-inputs (list r-knitr))
13812 (home-page "https://bioconductor.org/packages/M3C")
13813 (synopsis "Monte Carlo reference-based consensus clustering")
13815 "M3C is a consensus clustering algorithm that uses a Monte Carlo
13816 simulation to eliminate overestimation of @code{K} and can reject the null
13817 hypothesis @code{K=1}.")
13818 (license license:agpl3+)))
13820 (define-public r-icens
13827 (uri (bioconductor-uri "Icens" version))
13830 "0jnbfv7js8bw0ginql90krrpk0p54whj9igw0zk3jc45jqvj2vyc"))))
13831 (properties `((upstream-name . "Icens")))
13832 (build-system r-build-system)
13835 (home-page "https://bioconductor.org/packages/Icens")
13836 (synopsis "NPMLE for censored and truncated data")
13838 "This package provides many functions for computing the
13839 @dfn{nonparametric maximum likelihood estimator} (NPMLE) for censored and
13841 (license license:artistic2.0)))
13843 ;; This is a CRAN package but it depends on r-icens, which is published on
13845 (define-public r-interval
13847 (name "r-interval")
13848 (version "1.1-0.8")
13852 (uri (cran-uri "interval" version))
13855 "0g0k9nri19p3y3s70ic1w3i3sxq8fbsxaikd7c4d6afqzr8hk2nl"))))
13856 (properties `((upstream-name . "interval")))
13857 (build-system r-build-system)
13859 (list r-icens r-mlecens r-perm r-survival))
13860 (home-page "https://cran.r-project.org/web/packages/interval/")
13861 (synopsis "Weighted Logrank tests and NPMLE for interval censored data")
13863 "This package provides functions to fit nonparametric survival curves,
13864 plot them, and perform logrank or Wilcoxon type tests.")
13865 (license license:gpl2+)))
13867 ;; This is a CRAN package, but it depends on r-interval, which depends on a
13868 ;; Bioconductor package.
13869 (define-public r-fhtest
13876 (uri (cran-uri "FHtest" version))
13879 "00mql2r4f5hxhdqf27q3x9s5rz2zzakx2myym97b1w1s7c5znl4q"))))
13880 (properties `((upstream-name . "FHtest")))
13881 (build-system r-build-system)
13883 (list r-interval r-kmsurv r-mass r-perm r-survival))
13884 (home-page "https://cran.r-project.org/web/packages/FHtest/")
13885 (synopsis "Tests for survival data based on the Fleming-Harrington class")
13887 "This package provides functions to compare two or more survival curves
13891 @item The Fleming-Harrington test for right-censored data based on
13892 permutations and on counting processes.
13893 @item An extension of the Fleming-Harrington test for interval-censored data
13894 based on a permutation distribution and on a score vector distribution.
13897 (license license:gpl2+)))
13899 (define-public r-fourcseq
13901 (name "r-fourcseq")
13906 (uri (bioconductor-uri "FourCSeq" version))
13908 (base32 "1rwdphcj26xis47n8j1fiyc3k3qbsgn0bhf5bhgy5vm11yqyvicb"))))
13909 (properties `((upstream-name . "FourCSeq")))
13910 (build-system r-build-system)
13916 r-genomicalignments
13926 r-summarizedexperiment))
13930 "https://bioconductor.org/packages/release/bioc/html/FourCSeq.html")
13931 (synopsis "Analysis of multiplexed 4C sequencing data")
13933 "This package is an R package dedicated to the analysis of (multiplexed)
13934 4C sequencing data. @code{r-fourcseq} provides a pipeline to detect specific
13935 interactions between DNA elements and identify differential interactions
13936 between conditions. The statistical analysis in R starts with individual bam
13937 files for each sample as inputs. To obtain these files, the package contains
13938 a Python script to demultiplex libraries and trim off primer sequences. With
13939 a standard alignment software the required bam files can be then be
13941 (license license:gpl3+)))
13943 (define-public r-preprocesscore
13945 (name "r-preprocesscore")
13950 (uri (bioconductor-uri "preprocessCore" version))
13953 "1sqpp00hhv6gypflrjw8qpqyqgdcp29m86gmi1di1574x8casdkf"))))
13955 `((upstream-name . "preprocessCore")))
13956 (build-system r-build-system)
13957 (home-page "https://github.com/bmbolstad/preprocessCore")
13958 (synopsis "Collection of pre-processing functions")
13960 "This package provides a library of core pre-processing and normalization
13962 (license license:lgpl2.0+)))
13964 (define-public r-s4vectors
13966 (name "r-s4vectors")
13970 (uri (bioconductor-uri "S4Vectors" version))
13973 "0j3ybhzdhlhw8527nks3mjja28asjya2n0m0rjkh4bw66rkfys4k"))))
13975 `((upstream-name . "S4Vectors")))
13976 (build-system r-build-system)
13978 (list r-biocgenerics))
13979 (home-page "https://bioconductor.org/packages/S4Vectors")
13980 (synopsis "S4 implementation of vectors and lists")
13982 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
13983 classes and a set of generic functions that extend the semantic of ordinary
13984 vectors and lists in R. Package developers can easily implement vector-like
13985 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
13986 In addition, a few low-level concrete subclasses of general interest (e.g.
13987 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
13988 S4Vectors package itself.")
13989 (license license:artistic2.0)))
13991 ;; This is a CRAN package, but it depends on preprocessorcore, which is a
13992 ;; Bioconductor package.
13993 (define-public r-wgcna
14000 (uri (cran-uri "WGCNA" version))
14003 "027pkc4pyn9bifqbjs05318gvlm06mffw016j50n59wfi2g39x91"))))
14004 (properties `((upstream-name . "WGCNA")))
14005 (build-system r-build-system)
14007 (list r-annotationdbi
14020 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
14021 (synopsis "Weighted correlation network analysis")
14023 "This package provides functions necessary to perform Weighted
14024 Correlation Network Analysis on high-dimensional data. It includes functions
14025 for rudimentary data cleaning, construction and summarization of correlation
14026 networks, module identification and functions for relating both variables and
14027 modules to sample traits. It also includes a number of utility functions for
14028 data manipulation and visualization.")
14029 (license license:gpl2+)))
14031 (define-public r-rgraphviz
14033 (name "r-rgraphviz")
14038 (uri (bioconductor-uri "Rgraphviz" version))
14041 "1r6ff7w2bmyfl1vzjvpgnhb8f5arwjlpab8fw5ph8fgyiqbcx94l"))))
14042 (properties `((upstream-name . "Rgraphviz")))
14043 (build-system r-build-system)
14046 (modify-phases %standard-phases
14047 (add-after 'unpack 'make-reproducible
14049 ;; The replacement value is taken from src/graphviz/builddate.h
14050 (substitute* "src/graphviz/configure"
14051 (("VERSION_DATE=.*")
14052 "VERSION_DATE=20200427.2341\n"))
14054 ;; FIXME: Rgraphviz bundles the sources of an older variant of
14055 ;; graphviz. It does not build with the latest version of graphviz, so
14056 ;; we do not add graphviz to the inputs.
14057 (inputs (list zlib))
14062 (home-page "https://bioconductor.org/packages/Rgraphviz")
14063 (synopsis "Plotting capabilities for R graph objects")
14065 "This package interfaces R with the graphviz library for plotting R graph
14066 objects from the @code{graph} package.")
14067 (license license:epl1.0)))
14069 (define-public r-fithic
14075 (uri (bioconductor-uri "FitHiC" version))
14078 "0iv14yx3g7shzl8qrjknyxbmiylj51sbd1wzr1ff9lc5shgl55kq"))))
14079 (properties `((upstream-name . "FitHiC")))
14080 (build-system r-build-system)
14082 (list r-data-table r-fdrtool r-rcpp))
14085 (home-page "https://bioconductor.org/packages/FitHiC")
14086 (synopsis "Confidence estimation for intra-chromosomal contact maps")
14088 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
14089 intra-chromosomal contact maps produced by genome-wide genome architecture
14090 assays such as Hi-C.")
14091 (license license:gpl2+)))
14093 (define-public r-hitc
14099 (uri (bioconductor-uri "HiTC" version))
14102 "1pkshlrra26cad0hf8a54brlkazni6rsvrplh36azxapx5rpps4s"))))
14103 (properties `((upstream-name . "HiTC")))
14104 (build-system r-build-system)
14113 (home-page "https://bioconductor.org/packages/HiTC")
14114 (synopsis "High throughput chromosome conformation capture analysis")
14116 "The HiTC package was developed to explore high-throughput \"C\" data
14117 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
14118 quality controls, normalization, visualization, and further analysis are also
14120 (license license:artistic2.0)))
14122 (define-public r-hdf5array
14124 (name "r-hdf5array")
14129 (uri (bioconductor-uri "HDF5Array" version))
14132 "1r1lg7k60qgb489xkypd4gvm1fmdlihvylb5va6xj58ipndbfday"))))
14133 (properties `((upstream-name . "HDF5Array")))
14134 (build-system r-build-system)
14138 (list r-biocgenerics
14146 (home-page "https://bioconductor.org/packages/HDF5Array")
14147 (synopsis "HDF5 back end for DelayedArray objects")
14148 (description "This package provides an array-like container for convenient
14149 access and manipulation of HDF5 datasets. It supports delayed operations and
14150 block processing.")
14151 (license license:artistic2.0)))
14153 (define-public r-rhdf5lib
14155 (name "r-rhdf5lib")
14160 (uri (bioconductor-uri "Rhdf5lib" version))
14163 "1jpb8h7c724yz51zjfqs90bsqxgmy1rry2ra9qamsgqpr2j9764g"))
14164 (modules '((guix build utils)))
14167 ;; Delete bundled binaries
14168 (delete-file-recursively "src/wininclude/")
14169 (delete-file-recursively "src/winlib/")
14170 (delete-file "src/hdf5small_cxx_hl_1.10.7.tar.gz")))))
14171 (properties `((upstream-name . "Rhdf5lib")))
14172 (build-system r-build-system)
14175 (modify-phases %standard-phases
14176 (add-after 'unpack 'do-not-use-bundled-hdf5
14177 (lambda* (#:key inputs #:allow-other-keys)
14178 (for-each delete-file '("configure" "configure.ac"))
14179 (substitute* "R/zzz.R"
14180 (("return\\(links\\)") "return(\" -lz\")"))
14181 (with-directory-excursion "src"
14182 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
14183 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
14185 ;; Remove timestamp and host system information to make
14186 ;; the build reproducible.
14187 (substitute* "hdf5/src/libhdf5.settings.in"
14188 (("Configured on: @CONFIG_DATE@")
14189 "Configured on: Guix")
14190 (("Uname information:.*")
14191 "Uname information: Linux\n")
14192 ;; Remove unnecessary store reference.
14194 "C Compiler: GCC\n"))
14195 (rename-file "hdf5/src/libhdf5.settings.in"
14196 "hdf5/src/libhdf5.settings")
14197 (rename-file "Makevars.in" "Makevars")
14198 (substitute* "Makevars"
14199 (("@BUILD_HDF5@") "")
14200 (("@COPY_SZIP@") "")
14201 (("@ZLIB_LIB@") "-lz")
14202 (("@ZLIB_INCLUDE@") "")
14203 (("HDF5_CXX_LIB=.*")
14204 (string-append "HDF5_CXX_LIB="
14205 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
14207 (string-append "HDF5_LIB="
14208 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
14209 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
14210 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
14211 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
14212 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
14213 (("HDF5_HL_LIB=.*")
14214 (string-append "HDF5_HL_LIB="
14215 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
14216 (("HDF5_HL_CXX_LIB=.*")
14217 (string-append "HDF5_HL_CXX_LIB="
14218 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
14219 ;; szip is non-free software
14220 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
14221 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n"))))))))
14223 (list hdf5-1.10 zlib))
14225 `(("hdf5-source" ,(package-source hdf5-1.10))
14226 ("r-knitr" ,r-knitr)))
14227 (home-page "https://bioconductor.org/packages/Rhdf5lib")
14228 (synopsis "HDF5 library as an R package")
14229 (description "This package provides C and C++ HDF5 libraries for use in R
14231 (license license:artistic2.0)))
14233 (define-public r-beachmat
14235 (name "r-beachmat")
14240 (uri (bioconductor-uri "beachmat" version))
14243 "0fc6vvjjq1mfjfj2zqkap3rwvinnfqjs0cpk1447sspvd1rjya8c"))))
14244 (build-system r-build-system)
14246 (list r-biocgenerics r-delayedarray r-matrix r-rcpp))
14249 (home-page "https://bioconductor.org/packages/beachmat")
14250 (synopsis "Compiling Bioconductor to handle each matrix type")
14251 (description "This package provides a consistent C++ class interface for a
14252 variety of commonly used matrix types, including sparse and HDF5-backed
14254 (license license:gpl3)))
14256 ;; This package includes files that have been taken from kentutils. Some
14257 ;; parts of kentutils are not released under a free license, but this package
14258 ;; only uses files that are also found in the free parts of kentutils.
14259 (define-public r-cner
14266 (uri (bioconductor-uri "CNEr" version))
14268 (base32 "05zvr5fv8nprxqh2wvvrlf737dq242i20p1rpyqjaxihl6xl62kq"))))
14269 (properties `((upstream-name . "CNEr")))
14270 (build-system r-build-system)
14271 (inputs (list zlib))
14278 r-genomicalignments
14294 (home-page "https://github.com/ge11232002/CNEr")
14295 (synopsis "CNE Detection and Visualization")
14297 "This package provides tools for large-scale identification and
14298 advanced visualization of sets of conserved noncoding elements.")
14299 ;; For all files in src/ucsc "license is hereby granted for all use -
14300 ;; public, private or commercial"; this includes those files that don't
14301 ;; have a license header, because they are included in the free parts of
14302 ;; the kentutils package.
14303 (license (list license:gpl2
14304 (license:non-copyleft
14305 "https://raw.githubusercontent.com/ucscGenomeBrowser/kent/v410_base/src/lib/LICENSE")))))
14307 (define-public r-tfbstools
14309 (name "r-tfbstools")
14314 (uri (bioconductor-uri "TFBSTools" version))
14317 "0l6j1r2cx7jfd39qzbyynk4jvzd81ys6yypzxjc97js4kkyrx29w"))))
14318 (properties `((upstream-name . "TFBSTools")))
14319 (build-system r-build-system)
14329 r-dirichletmultinomial
14341 (native-inputs (list r-knitr))
14342 (home-page "https://github.com/ge11232002/TFBSTools")
14343 (synopsis "Transcription factor binding site (TFBS) analysis")
14345 "TFBSTools is a package for the analysis and manipulation of
14346 transcription factor binding sites. It includes matrices conversion
14347 between @dfn{Position Frequency Matrix} (PFM), @dfn{Position Weight
14348 Matrix} (PWM) and @dfn{Information Content Matrix} (ICM). It can also
14349 scan putative TFBS from sequence/alignment, query JASPAR database and
14350 provides a wrapper of de novo motif discovery software.")
14351 (license license:gpl2)))
14353 (define-public r-maftools
14355 (name "r-maftools")
14360 (uri (bioconductor-uri "maftools" version))
14362 (base32 "1gqfi95v4fs64n4walij0g2kds3fbbwp6lih5yakmgf6kj8fpkk6"))))
14363 (properties `((upstream-name . "maftools")))
14364 (build-system r-build-system)
14372 (native-inputs (list r-knitr))
14373 (home-page "https://github.com/PoisonAlien/maftools")
14374 (synopsis "Summarize, analyze and visualize MAF files")
14376 "Analyze and visualize Mutation Annotation Format (MAF) files from large
14377 scale sequencing studies. This package provides various functions to perform
14378 most commonly used analyses in cancer genomics and to create feature rich
14379 customizable visualzations with minimal effort.")
14380 (license license:expat)))
14382 (define-public r-motifmatchr
14384 (name "r-motifmatchr")
14389 (uri (bioconductor-uri "motifmatchr" version))
14392 "1ssn00mxwk23zr5na0vcmxvm69i68f0ga0wqlv1nk2isg0wpv878"))))
14393 (properties `((upstream-name . "motifmatchr")))
14394 (build-system r-build-system)
14406 r-summarizedexperiment
14408 (native-inputs (list r-knitr))
14409 (home-page "https://bioconductor.org/packages/motifmatchr")
14410 (synopsis "Fast motif matching in R")
14412 "Quickly find motif matches for many motifs and many sequences.
14413 This package wraps C++ code from the MOODS motif calling library.")
14414 (license license:gpl3)))
14416 (define-public r-chromvar
14418 (name "r-chromvar")
14423 (uri (bioconductor-uri "chromVAR" version))
14425 (base32 "0vhsvkm4kvln0002f13ayk57f9fmiz1kw9vwpsm1vds1vahd656m"))))
14426 (properties `((upstream-name . "chromVAR")))
14427 (build-system r-build-system)
14429 (list r-biocgenerics
14449 r-summarizedexperiment
14451 (native-inputs (list r-knitr))
14452 (home-page "https://bioconductor.org/packages/release/bioc/html/chromVAR.html")
14453 (synopsis "Determine chromatin variation across regions")
14455 "This package @code{r-chromvar} determines variation in chromatin
14456 accessibility across sets of annotations or peaks. @code{r-chromvar} is
14457 designed primarily for single-cell or sparse chromatin accessibility data like
14458 single cell assay for transposase-accessible chromatin using
14459 sequencing (@code{scATAC-seq} or sparse bulk ATAC or deoxyribonuclease
14460 sequence (@code{DNAse-seq}) experiments.")
14461 (license license:expat)))
14463 (define-public r-singlecellexperiment
14465 (name "r-singlecellexperiment")
14470 (uri (bioconductor-uri "SingleCellExperiment" version))
14473 "0s1aqbvlfnzijzfywjfpinqmxqj269dq2d3zlgf4xw9c1nwwnv7p"))))
14475 `((upstream-name . "SingleCellExperiment")))
14476 (build-system r-build-system)
14478 (list r-biocgenerics r-delayedarray r-genomicranges r-s4vectors
14479 r-summarizedexperiment))
14482 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
14483 (synopsis "S4 classes for single cell data")
14484 (description "This package defines an S4 class for storing data from
14485 single-cell experiments. This includes specialized methods to store and
14486 retrieve spike-in information, dimensionality reduction coordinates and size
14487 factors for each cell, along with the usual metadata for genes and
14489 (license license:gpl3)))
14491 (define-public r-singler
14498 (uri (bioconductor-uri "SingleR" version))
14500 (base32 "0qbyc6ygw2xv3li9187i3axsw6ihwpa7pkvxvy9cagv7xck45c5y"))))
14501 (properties `((upstream-name . "SingleR")))
14502 (build-system r-build-system)
14509 r-delayedmatrixstats
14513 r-summarizedexperiment))
14514 (native-inputs (list r-knitr))
14515 (home-page "https://github.com/LTLA/SingleR")
14516 (synopsis "Reference-based single-cell RNA-seq annotation")
14518 "This package performs unbiased cell type recognition from single-cell
14519 RNA sequencing data, by leveraging reference transcriptomic datasets of pure
14520 cell types to infer the cell of origin of each single cell independently.")
14521 (license license:gpl3)))
14523 (define-public r-scuttle
14530 (uri (bioconductor-uri "scuttle" version))
14533 "0nnmq3wf436xaw4arc4y3ldvn6ilsg52xzbccmid0icb8z3y2kzn"))))
14534 (properties `((upstream-name . "scuttle")))
14535 (build-system r-build-system)
14541 r-delayedmatrixstats
14546 r-singlecellexperiment
14547 r-summarizedexperiment))
14548 (native-inputs (list r-knitr))
14549 (home-page "https://bioconductor.org/packages/scuttle")
14550 (synopsis "Single-cell RNA-Seq analysis utilities")
14552 "This package provides basic utility functions for performing single-cell
14553 analyses, focusing on simple normalization, quality control and data
14554 transformations. It also provides some helper functions to assist development
14555 of other packages.")
14556 (license license:gpl3)))
14558 (define-public r-scater
14564 (uri (bioconductor-uri "scater" version))
14567 "0dqirggw7my5nq4ln9q0ya18ciqplkz9gx318ffias9ag3yii5rw"))))
14568 (build-system r-build-system)
14576 r-delayedmatrixstats
14588 r-singlecellexperiment
14589 r-summarizedexperiment
14593 (home-page "https://github.com/davismcc/scater")
14594 (synopsis "Single-cell analysis toolkit for gene expression data in R")
14595 (description "This package provides a collection of tools for doing
14596 various analyses of single-cell RNA-seq gene expression data, with a focus on
14598 (license license:gpl2+)))
14600 (define-public r-scran
14607 (uri (bioconductor-uri "scran" version))
14610 "0xg7dl35915a65pmzkxdacsm4iqf97ayljdjljcvqx1ycmn7x68w"))))
14611 (build-system r-build-system)
14620 r-delayedmatrixstats
14630 r-singlecellexperiment
14632 r-summarizedexperiment))
14635 (home-page "https://bioconductor.org/packages/scran")
14636 (synopsis "Methods for single-cell RNA-Seq data analysis")
14637 (description "This package implements a variety of low-level analyses of
14638 single-cell RNA-seq data. Methods are provided for normalization of
14639 cell-specific biases, assignment of cell cycle phase, and detection of highly
14640 variable and significantly correlated genes.")
14641 (license license:gpl3)))
14643 (define-public r-sparsematrixstats
14645 (name "r-sparsematrixstats")
14650 (uri (bioconductor-uri "sparseMatrixStats" version))
14653 "0p12kay7p5zbfm2589wdx0n9jhgpf5fb2fsmkhn3p4ck4xcy13x2"))))
14655 `((upstream-name . "sparseMatrixStats")))
14656 (build-system r-build-system)
14658 (list r-matrix r-matrixgenerics r-matrixstats r-rcpp))
14659 (native-inputs (list r-knitr))
14660 (home-page "https://bioconductor.org/packages/sparseMatrixStats/")
14661 (synopsis "Summary statistics for rows and columns of sparse matrices")
14663 "This package provides high performance functions for row and column
14664 operations on sparse matrices. Currently, the optimizations are limited to
14665 data in the column sparse format.")
14666 (license license:expat)))
14668 (define-public r-delayedmatrixstats
14670 (name "r-delayedmatrixstats")
14675 (uri (bioconductor-uri "DelayedMatrixStats" version))
14678 "1qlwv69c0r2w3zkmsr8r7w6sr3hf1ha0sfcrsjx4ks8f0ww7aqsv"))))
14680 `((upstream-name . "DelayedMatrixStats")))
14681 (build-system r-build-system)
14683 (list r-delayedarray
14689 r-sparsematrixstats))
14692 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
14693 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
14695 "This package provides a port of the @code{matrixStats} API for use with
14696 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
14697 contains high-performing functions operating on rows and columns of
14698 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
14699 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
14700 are optimized per data type and for subsetted calculations such that both
14701 memory usage and processing time is minimized.")
14702 (license license:expat)))
14704 (define-public r-mscoreutils
14706 (name "r-mscoreutils")
14711 (uri (bioconductor-uri "MsCoreUtils" version))
14714 "077x1zcy27x8akmagjn75j97082cgnahrbfw0qx08q455m5x3xzh"))))
14715 (properties `((upstream-name . "MsCoreUtils")))
14716 (build-system r-build-system)
14718 (list r-clue r-mass r-rcpp r-s4vectors))
14721 (home-page "https://github.com/RforMassSpectrometry/MsCoreUtils")
14722 (synopsis "Core utils for mass spectrometry data")
14724 "This package defines low-level functions for mass spectrometry data and
14725 is independent of any high-level data structures. These functions include
14726 mass spectra processing functions (noise estimation, smoothing, binning),
14727 quantitative aggregation functions (median polish, robust summarisation,
14728 etc.), missing data imputation, data normalisation (quantiles, vsn, etc.) as
14729 well as misc helper functions, that are used across high-level data structure
14730 within the R for Mass Spectrometry packages.")
14731 (license license:artistic2.0)))
14733 (define-public r-msfeatures
14735 (name "r-msfeatures")
14740 (uri (bioconductor-uri "MsFeatures" version))
14742 (base32 "111iqcq4q315pb4j8z427shin9b00p179m2s9h6dd7imvbd68yq3"))))
14743 (properties `((upstream-name . "MsFeatures")))
14744 (build-system r-build-system)
14746 (list r-mscoreutils r-protgenerics r-summarizedexperiment))
14749 (home-page "https://github.com/RforMassSpectrometry/MsFeatures")
14750 (synopsis "Functionality for mass spectrometry features")
14752 "The MsFeature package defines functionality for Mass Spectrometry
14753 features. This includes functions to group (LC-MS) features based on some of
14754 their properties, such as retention time (coeluting features), or correlation
14755 of signals across samples. This package hence can be used to group features, and
14756 its results can be used as an input for the @code{QFeatures} package which
14757 allows aggregating abundance levels of features within each group. This
14758 package defines concepts and functions for base and common data types,
14759 implementations for more specific data types are expected to be implemented in
14760 the respective packages (such as e.g. @code{xcms}).")
14761 (license license:artistic2.0)))
14763 (define-public r-biocio
14770 (uri (bioconductor-uri "BiocIO" version))
14773 "16j826w4zrmbgpmq6nyglcrjailsfv48ih1rz1qn383g7v503ydp"))))
14774 (properties `((upstream-name . "BiocIO")))
14775 (build-system r-build-system)
14777 (list r-biocgenerics r-s4vectors))
14780 (home-page "https://bioconductor.org/packages/BiocIO")
14781 (synopsis "Standard input and output for Bioconductor packages")
14783 "This package implements `import()` and `export()` standard generics for
14784 importing and exporting biological data formats. `import()` supports
14785 whole-file as well as chunk-wise iterative import. The `import()` interface
14786 optionally provides a standard mechanism for 'lazy' access via `filter()` (on
14787 row or element-like components of the file resource), `select()` (on
14788 column-like components of the file resource) and `collect()`. The `import()`
14789 interface optionally provides transparent access to remote (e.g. via https)
14790 as well as local access. Developers can register a file extension, e.g.,
14791 `.loom` for dispatch from character-based URIs to specific `import()` /
14792 `export()` methods based on classes representing file types, e.g.,
14794 (license license:artistic2.0)))
14796 (define-public r-msmseda
14803 (uri (bioconductor-uri "msmsEDA" version))
14806 "0jnaq9ar4mnf3pfhka9hvk61p51ny9jws49xi8z29dq288b42b42"))))
14807 (properties `((upstream-name . "msmsEDA")))
14808 (build-system r-build-system)
14810 (list r-gplots r-mass r-msnbase r-rcolorbrewer))
14812 "https://bioconductor.org/packages/msmsEDA")
14813 (synopsis "Exploratory data analysis of LC-MS/MS data by spectral counts")
14815 "Exploratory data analysis to assess the quality of a set of LC-MS/MS
14816 experiments, and visualize de influence of the involved factors.")
14817 (license license:gpl2)))
14819 (define-public r-msmstests
14821 (name "r-msmstests")
14826 (uri (bioconductor-uri "msmsTests" version))
14829 "1wzdz0p9wmr243xkmymx9fwskafkyxgmlip4sd1fy2s06px7r0xi"))))
14830 (properties `((upstream-name . "msmsTests")))
14831 (build-system r-build-system)
14833 (list r-edger r-msmseda r-msnbase r-qvalue))
14835 "https://bioconductor.org/packages/msmsTests")
14836 (synopsis "Differential LC-MS/MS expression tests")
14838 "This package provides statistical tests for label-free LC-MS/MS data
14839 by spectral counts, to discover differentially expressed proteins between two
14840 biological conditions. Three tests are available: Poisson GLM regression,
14841 quasi-likelihood GLM regression, and the negative binomial of the edgeR
14842 package. The three models admit blocking factors to control for nuisance
14843 variables. To assure a good level of reproducibility a post-test filter is
14844 available, where we may set the minimum effect size considered biologicaly
14845 relevant, and the minimum expression of the most abundant condition.")
14846 (license license:gpl2)))
14848 (define-public r-catalyst
14850 (name "r-catalyst")
14855 (uri (bioconductor-uri "CATALYST" version))
14858 "05vfqwa9qsm16px77s9bzygs6zymcxshymmpvz86a9l1cy1yxbza"))))
14859 (properties `((upstream-name . "CATALYST")))
14860 (build-system r-build-system)
14864 r-consensusclusterplus
14886 r-singlecellexperiment
14887 r-summarizedexperiment))
14890 (home-page "https://github.com/HelenaLC/CATALYST")
14891 (synopsis "Cytometry data analysis tools")
14893 "This package is @dfn{Cytometry dATa anALYSis Tools} (CATALYST). Mass
14894 cytometry like @dfn{Cytometry by time of flight} (CyTOF) uses heavy metal
14895 isotopes rather than fluorescent tags as reporters to label antibodies,
14896 thereby substantially decreasing spectral overlap and allowing for examination
14897 of over 50 parameters at the single cell level. While spectral overlap is
14898 significantly less pronounced in CyTOF than flow cytometry, spillover due to
14899 detection sensitivity, isotopic impurities, and oxide formation can impede
14900 data interpretability. @code{CATALYST} was designed to provide a pipeline for
14901 preprocessing of cytometry data, including:
14904 @item normalization using bead standards;
14905 @item single-cell deconvolution;
14906 @item bead-based compensation.
14909 (license license:gpl2+)))
14911 (define-public r-erma
14918 (uri (bioconductor-uri "erma" version))
14921 "1ilq01cr2ipxpmp422fikiz6nj4nasjhj0ikcagjn2zmmarpgi1b"))))
14922 (build-system r-build-system)
14924 (list r-annotationdbi
14937 r-summarizedexperiment))
14940 (home-page "https://bioconductor.org/packages/erma")
14941 (synopsis "Epigenomic road map adventures")
14943 "The epigenomics road map describes locations of epigenetic marks in DNA
14944 from a variety of cell types. Of interest are locations of histone
14945 modifications, sites of DNA methylation, and regions of accessible chromatin.
14946 This package presents a selection of elements of the road map including
14947 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
14948 by Ernst and Kellis.")
14949 (license license:artistic2.0)))
14951 (define-public r-ggbio
14958 (uri (bioconductor-uri "ggbio" version))
14961 "0iyhjalwq1jmldpn20iv8l2kmz6sm20ddry2yz2zn7yq0wszp3vg"))))
14962 (build-system r-build-system)
14965 (modify-phases %standard-phases
14966 ;; See https://github.com/tengfei/ggbio/issues/117
14967 ;; This fix will be included in the next release.
14968 (add-after 'unpack 'fix-typo
14970 (substitute* "R/GGbio-class.R"
14971 (("fechable") "fetchable"))
14974 (list r-annotationdbi
14983 r-genomicalignments
14999 r-summarizedexperiment
15000 r-variantannotation))
15003 (home-page "http://www.tengfei.name/ggbio/")
15004 (synopsis "Visualization tools for genomic data")
15006 "The ggbio package extends and specializes the grammar of graphics for
15007 biological data. The graphics are designed to answer common scientific
15008 questions, in particular those often asked of high throughput genomics data.
15009 All core Bioconductor data structures are supported, where appropriate. The
15010 package supports detailed views of particular genomic regions, as well as
15011 genome-wide overviews. Supported overviews include ideograms and grand linear
15012 views. High-level plots include sequence fragment length, edge-linked
15013 interval to data view, mismatch pileup, and several splicing summaries.")
15014 (license license:artistic2.0)))
15016 (define-public r-gqtlbase
15018 (name "r-gqtlbase")
15023 (uri (bioconductor-uri "gQTLBase" version))
15026 "0nipibm1bk9k70ajbw1f6vjmz0dh7gk21l17q3m54bnawxsggrfh"))))
15027 (properties `((upstream-name . "gQTLBase")))
15028 (build-system r-build-system)
15031 (modify-phases %standard-phases
15032 ;; This is an upstream bug.
15033 (add-after 'unpack 'fix-imports
15035 (substitute* "NAMESPACE"
15036 ((".*maxffmode.*") "")
15037 (("importFrom\\(ff,.*") "import(ff)\n"))
15052 r-summarizedexperiment))
15055 (home-page "https://bioconductor.org/packages/gQTLBase")
15056 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
15058 "The purpose of this package is to simplify the storage and interrogation
15059 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
15061 (license license:artistic2.0)))
15063 (define-public r-gqtlstats
15065 (name "r-gqtlstats")
15070 (uri (bioconductor-uri "gQTLstats" version))
15073 "1h78l23idf867djmdk97b02jxgmz4vfr2dai01fp648d0lsx5mkl"))))
15074 (properties `((upstream-name . "gQTLstats")))
15075 (build-system r-build-system)
15077 (list r-annotationdbi
15105 r-summarizedexperiment
15106 r-variantannotation))
15109 (home-page "https://bioconductor.org/packages/gQTLstats")
15110 (synopsis "Computationally efficient analysis for eQTL and allied studies")
15112 "This package provides tools for the computationally efficient analysis
15113 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
15114 The software in this package aims to support refinements and functional
15115 interpretation of members of a collection of association statistics on a
15116 family of feature/genome hypotheses.")
15117 (license license:artistic2.0)))
15119 (define-public r-gviz
15126 (uri (bioconductor-uri "Gviz" version))
15129 "0as3sxhv21bqqrpvafcqim7798hhkzj3q40hy1rqyhv2lhj4rbvi"))))
15130 (properties `((upstream-name . "Gviz")))
15131 (build-system r-build-system)
15133 (list r-annotationdbi
15143 r-genomicalignments
15157 (home-page "https://bioconductor.org/packages/Gviz")
15158 (synopsis "Plotting data and annotation information along genomic coordinates")
15160 "Genomic data analyses requires integrated visualization of known genomic
15161 information and new experimental data. Gviz uses the biomaRt and the
15162 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
15163 and translates this to e.g. gene/transcript structures in viewports of the
15164 grid graphics package. This results in genomic information plotted together
15166 (license license:artistic2.0)))
15168 (define-public r-gwascat
15175 (uri (bioconductor-uri "gwascat" version))
15178 "19ymdxj8966i4yk0zalfw23938cpv4q7pywg4qb242p44na5y9sl"))))
15179 (build-system r-build-system)
15181 (list r-annotationdbi
15192 r-variantannotation))
15195 (home-page "https://bioconductor.org/packages/gwascat")
15196 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
15198 "This package provides tools for representing and modeling data in the
15199 EMBL-EBI GWAS catalog.")
15200 (license license:artistic2.0)))
15202 (define-public r-kegggraph
15204 (name "r-kegggraph")
15209 (uri (bioconductor-uri "KEGGgraph" version))
15211 (base32 "15pq040pcg8hr18xixmjp59xb7mgvygjv6kisqk8yv99l1611ndx"))))
15212 (properties `((upstream-name . "KEGGgraph")))
15213 (build-system r-build-system)
15215 (list r-graph r-rcurl r-rgraphviz r-xml))
15216 (home-page "https://bioconductor.org/packages/KEGGgraph")
15217 (synopsis "Graph approach to Kegg Pathway database in R and Bioconductor")
15219 "@code{r-kegggraph} is an interface between Kegg Pathway database and graph
15220 object as well as a collection of tools to analyze, dissect and visualize these
15221 graphs. It parses the regularly updated kgml (Kegg XML) files into graph models
15222 maintaining all essential pathway attributes. The package offers
15223 functionalities including parsing, graph operation, visualization and etc.")
15224 (license license:gpl2+)))
15226 (define-public r-ldblock
15233 (uri (bioconductor-uri "ldblock" version))
15236 "08ss03b93czwb4x60hsi30ad4lmamvq5mxa8nj0g18z68qcraijm"))))
15237 (build-system r-build-system)
15239 (list r-biocgenerics
15240 r-ensdb-hsapiens-v75
15248 r-variantannotation))
15251 (home-page "https://bioconductor.org/packages/ldblock")
15252 (synopsis "Data structures for linkage disequilibrium measures in populations")
15254 "This package defines data structures for @dfn{linkage
15255 disequilibrium} (LD) measures in populations. Its purpose is to simplify
15256 handling of existing population-level data for the purpose of flexibly
15257 defining LD blocks.")
15258 (license license:artistic2.0)))
15260 ;; This is a CRAN package, but it depends on r-snpstats, which is a
15261 ;; Bioconductor package.
15262 (define-public r-ldheatmap
15264 (name "r-ldheatmap")
15269 (uri (cran-uri "LDheatmap" version))
15272 "0gr99kys1ahyl8s6cbj6rmh4vwid8kn92lcbjnwh0ahb73m2xjjc"))))
15273 (properties `((upstream-name . "LDheatmap")))
15274 (build-system r-build-system)
15276 (list r-genetics r-rcpp r-snpstats))
15277 (home-page "https://stat.sfu.ca/statgen/research/ldheatmap.html")
15278 (synopsis "Graphical display of pairwise linkage disequilibria between SNPs")
15280 "This package provides tools to produce a graphical display, as a heat
15281 map, of measures of pairwise linkage disequilibria between SNPs. Users may
15282 optionally include the physical locations or genetic map distances of each SNP
15284 (license license:gpl3)))
15286 ;; This is a CRAN package, but it depends on r-rgraphviz, which is a
15287 ;; Bioconductor package.
15288 (define-public r-abn
15295 (uri (cran-uri "abn" version))
15298 "1w3jns96m8b9scvaa4hcla3i88a0cfh9qis2l04yixvda5q91gpr"))))
15299 (build-system r-build-system)
15312 (home-page "https://r-bayesian-networks.org/")
15313 (synopsis "Modelling multivariate data with additive bayesian networks")
15315 "Bayesian network analysis is a form of probabilistic graphical models
15316 which derives from empirical data a directed acyclic graph, DAG, describing
15317 the dependency structure between random variables. An additive Bayesian
15318 network model consists of a form of a DAG where each node comprises a
15319 @dfn{generalized linear model} (GLM). Additive Bayesian network models are
15320 equivalent to Bayesian multivariate regression using graphical modelling, they
15321 generalises the usual multivariable regression, GLM, to multiple dependent
15322 variables. This package provides routines to help determine optimal Bayesian
15323 network models for a given data set, where these models are used to identify
15324 statistical dependencies in messy, complex data.")
15325 (license license:gpl2+)))
15327 ;; This is a CRAN package, but it depends on r-rsamtools, which is a
15328 ;; Bioconductor package.
15329 (define-public r-spp
15335 (uri (cran-uri "spp" version))
15338 "08zxxgyp0h6733b08jmml7k4rhfd3mi5dda3jrzid0s184y0z29w"))))
15339 (build-system r-build-system)
15343 (list r-bh r-catools r-rcpp r-rsamtools))
15344 (home-page "https://cran.r-project.org/web/packages/spp/")
15345 (synopsis "ChIP-Seq processing pipeline")
15346 (description "This package provides tools for analysis of ChIP-seq and
15347 other functional sequencing data.")
15348 (license license:gpl2)))
15350 (define-public r-pathview
15352 (name "r-pathview")
15357 (uri (bioconductor-uri "pathview" version))
15359 (base32 "1472k107f21cflbx2fip92g8gl9wlwxgwfvgvl73ma0y0jzs0qdq"))))
15360 (properties `((upstream-name . "pathview")))
15361 (build-system r-build-system)
15363 (list r-annotationdbi
15371 (home-page "https://pathview.uncc.edu/")
15372 (synopsis "Tool set for pathway based data integration and visualization")
15374 "@code{r-pathview} is a tool set for pathway based data integration and
15375 visualization. It maps and renders a wide variety of biological data on
15376 relevant pathway graphs. All users need is to supply their data and specify
15377 the target pathway. This package automatically downloads the pathway graph
15378 data, parses the data file, maps user data to the pathway, and render pathway
15379 graph with the mapped data. In addition, @code{r-pathview} also seamlessly
15380 integrates with pathway and gene set (enrichment) analysis tools for
15381 large-scale and fully automated analysis.")
15382 (license license:gpl3+)))
15384 (define-public r-snpstats
15386 (name "r-snpstats")
15391 (uri (bioconductor-uri "snpStats" version))
15394 "0a5b5nqc7n965jk45ijwkzbn416ib4gfhp8xl39z8f2bdskip4a2"))))
15395 (properties `((upstream-name . "snpStats")))
15396 (build-system r-build-system)
15397 (inputs (list zlib))
15399 (list r-biocgenerics r-matrix r-survival r-zlibbioc))
15400 (home-page "https://bioconductor.org/packages/snpStats")
15401 (synopsis "Methods for SNP association studies")
15403 "This package provides classes and statistical methods for large
15404 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
15405 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
15406 (license license:gpl3)))
15408 (define-public r-chromstar
15410 (name "r-chromstar")
15415 (uri (bioconductor-uri "chromstaR" version))
15418 "1xjwmnr4hk8v3nwvhqd6ixk5qr2dv0n4mb9wd6nl7cgjfhjsdgj7"))))
15419 (properties `((upstream-name . "chromstaR")))
15420 (build-system r-build-system)
15428 r-genomicalignments
15436 (native-inputs (list r-knitr))
15437 (home-page "https://github.com/ataudt/chromstaR")
15438 (synopsis "Chromatin state analysis for ChIP-Seq data")
15440 "This package implements functions for combinatorial and differential
15441 analysis of ChIP-seq data. It includes uni- and multivariate peak-calling,
15442 export to genome browser viewable files, and functions for enrichment
15444 (license license:artistic2.0)))
15446 (define-public r-guitar
15453 (uri (bioconductor-uri "Guitar" version))
15456 "09grsasnnk7rmlzjh4lhas9r5spzcsrvmdqj6fx1dk22sckcqahh"))))
15457 (properties `((upstream-name . "Guitar")))
15458 (build-system r-build-system)
15460 (list r-annotationdbi
15470 (home-page "https://bioconductor.org/packages/Guitar")
15471 (synopsis "Visualize genomic features")
15473 "This package is designed for visualization of RNA-related genomic
15474 features with respect to the landmarks of RNA transcripts, i.e., transcription
15475 starting site, start codon, stop codon and transcription ending site.")
15476 (license license:gpl2)))
15478 (define-public r-sushi
15484 (uri (bioconductor-uri "Sushi" version))
15487 "0adswrbzd93rhy3q56ypwkrk6155vd4zxapvznswyjlxp8ha813q"))))
15488 (properties `((upstream-name . "Sushi")))
15489 (build-system r-build-system)
15491 (list r-biomart r-zoo))
15492 (home-page "https://bioconductor.org/packages/Sushi")
15493 (synopsis "Tools for visualizing genomics data")
15495 "This package provides flexible, quantitative, and integrative genomic
15496 visualizations for publication-quality multi-panel figures.")
15497 (license license:gpl2+)))
15499 (define-public r-ballgown
15501 (name "r-ballgown")
15506 (uri (bioconductor-uri "ballgown" version))
15509 "0l8q3fymskxmsi5jcikzjz5xi66lpzgv7bjymir4izah2v68z708"))))
15510 (properties `((upstream-name . "ballgown")))
15511 (build-system r-build-system)
15524 (home-page "https://bioconductor.org/packages/ballgown")
15525 (synopsis "Flexible, isoform-level differential expression analysis")
15527 "This package provides tools for statistical analysis of assembled
15528 transcriptomes, including flexible differential expression analysis,
15529 visualization of transcript structures, and matching of assembled transcripts
15531 (license license:artistic2.0)))
15533 (define-public r-megadepth
15535 (name "r-megadepth")
15540 (uri (bioconductor-uri "megadepth" version))
15543 "0qq82dmd3drr2bhn51bgbc6ml40klfmmhj6wdj72n9ya6n60lwy8"))))
15544 (properties `((upstream-name . "megadepth")))
15545 (build-system r-build-system)
15546 (inputs (list megadepth))
15557 (home-page "https://github.com/LieberInstitute/megadepth")
15558 (synopsis "BigWig and BAM related utilities")
15560 "This package provides an R interface to Megadepth. It is particularly
15561 useful for computing the coverage of a set of genomic regions across bigWig or
15562 BAM files. With this package, you can build base-pair coverage matrices for
15563 regions or annotations of your choice from BigWig files.")
15564 (license license:artistic2.0)))
15566 (define-public r-beclear
15573 (uri (bioconductor-uri "BEclear" version))
15576 "0x43yfnmb2d782g3g52nqdfs90i3zrrlqz8qy3ybmgv5f8n92p15"))))
15577 (properties `((upstream-name . "BEclear")))
15578 (build-system r-build-system)
15590 (home-page "https://github.com/uds-helms/BEclear")
15591 (synopsis "Correction of batch effects in DNA methylation data")
15593 "This package provides functions to detect and correct for batch effects
15594 in DNA methylation data. The core function is based on latent factor models
15595 and can also be used to predict missing values in any other matrix containing
15597 (license license:gpl3)))
15599 (define-public r-bgeecall
15601 (name "r-bgeecall")
15606 (uri (bioconductor-uri "BgeeCall" version))
15609 "1g12cms66zb45p347h3b358vjhnq76galvwqwq86xby4hnwpdzkh"))))
15610 (properties `((upstream-name . "BgeeCall")))
15611 (build-system r-build-system)
15625 (native-inputs (list r-knitr))
15626 (home-page "https://github.com/BgeeDB/BgeeCall")
15627 (synopsis "RNA-Seq present/absent gene expression calls generation")
15629 "BgeeCall allows generating present/absent gene expression calls without
15630 using an arbitrary cutoff like TPM<1. Calls are generated based on reference
15631 intergenic sequences. These sequences are generated based on expression of
15632 all RNA-Seq libraries of each species integrated in Bgee.")
15633 (license license:gpl3)))
15635 (define-public r-bgeedb
15642 (uri (bioconductor-uri "BgeeDB" version))
15645 "1f6lrazaibbz21sqvj59rq6ps9m1riw2y0kyidbn29mxf4ibwh3k"))))
15646 (properties `((upstream-name . "BgeeDB")))
15647 (build-system r-build-system)
15660 (native-inputs (list r-knitr))
15661 (home-page "https://github.com/BgeeDB/BgeeDB_R")
15662 (synopsis "Annotation and gene expression data retrieval from Bgee database")
15664 "This package provides a package for the annotation and gene expression
15665 data download from Bgee database, and TopAnat analysis: GO-like enrichment of
15666 anatomical terms, mapped to genes by expression patterns.")
15667 (license license:gpl3)))
15669 (define-public r-biobtreer
15671 (name "r-biobtreer")
15676 (uri (bioconductor-uri "biobtreeR" version))
15679 "0cx46hdqqm6mbj0vp4y86axv0qccd4sgk2jwwjvnqp5pynq9bbqa"))))
15680 (properties `((upstream-name . "biobtreeR")))
15681 (build-system r-build-system)
15683 (list r-httpuv r-httr r-jsonlite r-stringi))
15684 (native-inputs (list r-knitr))
15685 (home-page "https://github.com/tamerh/biobtreeR")
15686 (synopsis "Use biobtree tool from R")
15688 "The biobtreeR package provides an interface to biobtree, a tool which
15689 covers large sets of bioinformatics datasets and allows search and chain
15690 mappings functionalities.")
15691 (license license:expat)))
15693 (define-public r-minet
15700 (uri (bioconductor-uri "minet" version))
15703 "0q6jw2jqkl9qynjpzaygz45c7dmx1l5y2d8s1illpcf87siawcam"))))
15704 (properties `((upstream-name . "minet")))
15705 (build-system r-build-system)
15708 (home-page "http://minet.meyerp.com")
15709 (synopsis "Mutual information networks")
15711 "This package implements various algorithms for inferring mutual
15712 information networks from data.")
15713 (license license:artistic2.0)))
15715 (define-public r-genetclassifier
15717 (name "r-genetclassifier")
15722 (uri (bioconductor-uri "geNetClassifier" version))
15725 "1kh7mp5h0n7yd1klcd7w4v7i3fh9pkmvgf7189wangfzbcsr4f70"))))
15727 `((upstream-name . "geNetClassifier")))
15728 (build-system r-build-system)
15730 (list r-biobase r-e1071 r-ebarrays r-minet))
15731 (home-page "https://www.cicancer.org")
15732 (synopsis "Classify diseases and build gene networks using expression profiles")
15734 "This is a comprehensive package to automatically train and validate a
15735 multi-class SVM classifier based on gene expression data. It provides
15736 transparent selection of gene markers, their coexpression networks, and an
15737 interface to query the classifier.")
15738 (license license:gpl2+)))
15740 (define-public r-dir-expiry
15742 (name "r-dir-expiry")
15747 (uri (bioconductor-uri "dir.expiry" version))
15750 "098wzm8hlpy70c99k2sl4k8z2dllhw7rwdj8dhcskr7kaw71k3sq"))))
15751 (properties `((upstream-name . "dir.expiry")))
15752 (build-system r-build-system)
15753 (propagated-inputs (list r-filelock))
15754 (native-inputs (list r-knitr))
15755 (home-page "https://bioconductor.org/packages/dir.expiry")
15756 (synopsis "Managing expiration for cache directories")
15758 "This package implements an expiration system for access to versioned
15759 directories. Directories that have not been accessed by a registered function
15760 within a certain time frame are deleted. This aims to reduce disk usage by
15761 eliminating obsolete caches generated by old versions of packages.")
15762 (license license:gpl3)))
15764 (define-public r-basilisk-utils
15766 (name "r-basilisk-utils")
15771 (uri (bioconductor-uri "basilisk.utils" version))
15774 "1jnqv0rlljkq27rd4ixl763v335f2aanm4fzr386yc81fj4vnmhk"))))
15776 `((upstream-name . "basilisk.utils")))
15777 (build-system r-build-system)
15779 (list r-dir-expiry))
15780 (native-inputs (list r-knitr))
15781 (home-page "https://bioconductor.org/packages/basilisk.utils")
15782 (synopsis "Basilisk installation utilities")
15784 "This package implements utilities for installation of the basilisk
15785 package, primarily for creation of the underlying Conda instance.")
15786 (license license:gpl3)))
15788 (define-public r-basilisk
15790 (name "r-basilisk")
15795 (uri (bioconductor-uri "basilisk" version))
15798 "1p90wq8a9wrpqpgmcy4zgh5skdw65gg2gsb3lnx78zk9khq0yyzh"))))
15799 (properties `((upstream-name . "basilisk")))
15800 (build-system r-build-system)
15802 (list r-basilisk-utils r-dir-expiry r-reticulate))
15803 (native-inputs (list r-knitr))
15804 (home-page "https://bioconductor.org/packages/basilisk")
15805 (synopsis "Freeze Python dependencies inside Bioconductor packages")
15807 "This package installs a self-contained Conda instance that is managed by
15808 the R/Bioconductor installation machinery. This aims to provide a consistent
15809 Python environment that can be used reliably by Bioconductor packages.
15810 Functions are also provided to enable smooth interoperability of multiple
15811 Python environments in a single R session.")
15812 (license license:gpl3)))
15814 (define-public r-biocthis
15816 (name "r-biocthis")
15821 (uri (bioconductor-uri "biocthis" version))
15824 "1hdgjp00d2si3mr7m1d289i9wn7g927z6n8n27d5sm94lb91qln0"))))
15825 (properties `((upstream-name . "biocthis")))
15826 (build-system r-build-system)
15829 (modify-phases %standard-phases
15830 (add-after 'unpack 'set-HOME
15831 (lambda _ (setenv "HOME" "/tmp"))))))
15833 (list r-biocmanager
15839 (native-inputs (list r-knitr))
15840 (home-page "https://github.com/lcolladotor/biocthis")
15841 (synopsis "Automate package and project setup for Bioconductor packages")
15843 "This package expands the @code{usethis} package with the goal of helping
15844 automate the process of creating R packages for Bioconductor or making them
15845 Bioconductor-friendly.")
15846 (license license:artistic2.0)))
15848 (define-public r-biocdockermanager
15850 (name "r-biocdockermanager")
15855 (uri (bioconductor-uri "BiocDockerManager" version))
15858 "0kl6r8ad728a8dvqx0safj7v5gj1rxxcdiw44jkr1pd5ddv0xbi6"))))
15860 `((upstream-name . "BiocDockerManager")))
15861 (build-system r-build-system)
15869 (native-inputs (list r-knitr))
15870 (home-page "https://bioconductor.org/packages/BiocDockerManager")
15871 (synopsis "Access and manage Bioconductor Docker images")
15873 "This package works analogous to BiocManager but for Docker images. Use
15874 the BiocDockerManager package to install and manage Docker images provided by
15875 the Bioconductor project.")
15876 (license license:artistic2.0)))
15878 (define-public r-biodb
15885 (uri (bioconductor-uri "biodb" version))
15888 "02i0n29bp9d9p1ibslxca5m37qsgny2hlgg7d364lf7kc6y2bqni"))))
15889 (properties `((upstream-name . "biodb")))
15890 (build-system r-build-system)
15892 (list r-biocfilecache
15910 (native-inputs (list r-knitr))
15911 (home-page "https://bioconductor.org/packages/biodb")
15912 (synopsis "Library for connecting to chemical and biological databases")
15914 "The biodb package provides access to standard remote chemical and
15915 biological databases (ChEBI, KEGG, HMDB, ...), as well as to in-house local
15916 database files (CSV, SQLite), with easy retrieval of entries, access to web
15917 services, search of compounds by mass and/or name, and mass spectra matching
15918 for LCMS and MSMS. Its architecture as a development framework facilitates
15919 the development of new database connectors for local projects or inside
15920 separate published packages.")
15921 (license license:agpl3+)))
15923 (define-public r-biomformat
15925 (name "r-biomformat")
15930 (uri (bioconductor-uri "biomformat" version))
15933 "12wqjipxhngmlnrdmx329dqmkmy2wa4nkkrhwaqv2nwy90dncs9n"))))
15934 (properties `((upstream-name . "biomformat")))
15935 (build-system r-build-system)
15937 (list r-jsonlite r-matrix r-plyr r-rhdf5))
15938 (native-inputs (list r-knitr))
15939 (home-page "https://github.com/joey711/biomformat/")
15940 (synopsis "Interface package for the BIOM file format")
15942 "This is an R package for interfacing with the BIOM format. This package
15943 includes basic tools for reading biom-format files, accessing and subsetting
15944 data tables from a biom object (which is more complex than a single table), as
15945 well as limited support for writing a biom-object back to a biom-format file.
15946 The design of this API is intended to match the Python API and other tools
15947 included with the biom-format project, but with a decidedly \"R flavor\" that
15948 should be familiar to R users. This includes S4 classes and methods, as well
15949 as extensions of common core functions/methods.")
15950 (license license:gpl2)))
15952 (define-public r-mvcclass
15954 (name "r-mvcclass")
15959 (uri (bioconductor-uri "MVCClass" version))
15962 "0apcjlq4i2mg8mlfqgvlcsqkiy51whzid3nd0m830jff0ywgh47g"))))
15963 (properties `((upstream-name . "MVCClass")))
15964 (build-system r-build-system)
15965 (home-page "https://bioconductor.org/packages/MVCClass")
15966 (synopsis "Model-View-Controller (MVC) classes")
15968 "This package contains classes used in model-view-controller (MVC)
15970 (license license:lgpl2.1+)))
15972 (define-public r-biomvcclass
15974 (name "r-biomvcclass")
15979 (uri (bioconductor-uri "BioMVCClass" version))
15982 "078pnyygbvbfxziqspfr1nn78w67xyb4qmiwc34czga5psblvfwz"))))
15983 (properties `((upstream-name . "BioMVCClass")))
15984 (build-system r-build-system)
15986 (list r-biobase r-graph r-mvcclass r-rgraphviz))
15987 (home-page "https://bioconductor.org/packages/BioMVCClass")
15988 (synopsis "Model-View-Controller (MVC) classes that use Biobase")
15990 "This package contains classes used in model-view-controller (MVC)
15992 (license license:lgpl2.1+)))
15994 (define-public r-biomvrcns
15996 (name "r-biomvrcns")
16001 (uri (bioconductor-uri "biomvRCNS" version))
16004 "0i576g7pkivqaxff1pkb760mdpx8v9fh071aic1mwfnlfa7k87ln"))))
16005 (properties `((upstream-name . "biomvRCNS")))
16006 (build-system r-build-system)
16008 (list r-genomicranges r-gviz r-iranges r-mvtnorm))
16009 (home-page "https://bioconductor.org/packages/biomvRCNS")
16010 (synopsis "Copy number study and segmentation for multivariate biological data")
16012 "In this package, a @dfn{Hidden Semi Markov Model} (HSMM) and one
16013 homogeneous segmentation model are designed and implemented for segmentation
16014 genomic data, with the aim of assisting in transcripts detection using high
16015 throughput technology like RNA-seq or tiling array, and copy number analysis
16016 using aCGH or sequencing.")
16017 (license license:gpl2+)))
16019 (define-public r-bionero
16026 (uri (bioconductor-uri "BioNERO" version))
16029 "1nyzjbl0gcwvbj2nxfwykirikf8j3rsx5ny45bqjbcb4r23k65kj"))))
16030 (properties `((upstream-name . "BioNERO")))
16031 (build-system r-build-system)
16033 (list r-biocparallel
16050 r-summarizedexperiment
16055 (home-page "https://github.com/almeidasilvaf/BioNERO")
16056 (synopsis "Biological network reconstruction omnibus")
16058 "BioNERO aims to integrate all aspects of biological network inference in
16059 a single package, including data preprocessing, exploratory analyses, network
16060 inference, and analyses for biological interpretations. BioNERO can be used
16061 to infer gene coexpression networks (GCNs) and gene regulatory networks (GRNs)
16062 from gene expression data. Additionally, it can be used to explore
16063 topological properties of protein-protein interaction (PPI) networks. GCN
16064 inference relies on the popular WGCNA algorithm. GRN inference is based on
16065 the \"wisdom of the crowds\" principle, which consists in inferring GRNs with
16066 multiple algorithms (here, CLR, GENIE3 and ARACNE) and calculating the average
16067 rank for each interaction pair. As all steps of network analyses are included
16068 in this package, BioNERO makes users avoid having to learn the syntaxes of
16069 several packages and how to communicate between them. Finally, users can also
16070 identify consensus modules across independent expression sets and calculate
16071 intra and interspecies module preservation statistics between different
16073 (license license:gpl3)))
16075 (define-public r-bionet
16082 (uri (bioconductor-uri "BioNet" version))
16085 "0kcw71j4nmdkn373wk21ak6h0v4gycivnfrklb72kk1qcmsy1wrm"))))
16086 (properties `((upstream-name . "BioNet")))
16087 (build-system r-build-system)
16089 (list r-annotationdbi r-biobase r-graph r-igraph r-rbgl))
16090 (home-page "http://bioconductor.org/packages/release/bioc/html/BioNet.html")
16091 (synopsis "Functional analysis of biological networks")
16093 "This package provides functions for the integrated analysis of
16094 protein-protein interaction networks and the detection of functional modules.
16095 Different datasets can be integrated into the network by assigning p-values of
16096 statistical tests to the nodes of the network. E.g. p-values obtained from
16097 the differential expression of the genes from an Affymetrix array are assigned
16098 to the nodes of the network. By fitting a beta-uniform mixture model and
16099 calculating scores from the p-values, overall scores of network regions can be
16100 calculated and an integer linear programming algorithm identifies the maximum
16101 scoring subnetwork.")
16102 (license license:gpl2+)))
16104 (define-public r-bionetstat
16106 (name "r-bionetstat")
16111 (uri (bioconductor-uri "BioNetStat" version))
16114 "0zs6pymvxb95sji0rnnzaz3whj7hsvj2kl4n4gzj7w1q0prbfpb2"))))
16115 (properties `((upstream-name . "BioNetStat")))
16116 (build-system r-build-system)
16118 (list r-biocparallel
16138 (home-page "https://github.com/jardimViniciusC/BioNetStat")
16139 (synopsis "Biological network analysis")
16141 "This package provides a package to perform differential network
16142 analysis, differential node analysis (differential coexpression analysis),
16143 network and metabolic pathways view.")
16144 (license license:gpl3+)))
16146 (define-public r-bioqc
16153 (uri (bioconductor-uri "BioQC" version))
16156 "0vb2nnzqvyv25pw8qshcmijravswafg0858pkgqjgiv7wsr2mn3m"))))
16157 (properties `((upstream-name . "BioQC")))
16158 (build-system r-build-system)
16160 (list r-biobase r-edger r-rcpp))
16163 (home-page "https://accio.github.io/BioQC/")
16164 (synopsis "Detect tissue heterogeneity in expression profiles with gene sets")
16166 "BioQC performs quality control of high-throughput expression data based
16167 on tissue gene signatures. It can detect tissue heterogeneity in gene
16168 expression data. The core algorithm is a Wilcoxon-Mann-Whitney test that is
16169 optimised for high performance.")
16170 (license license:gpl3+)))
16172 (define-public r-biotip
16179 (uri (bioconductor-uri "BioTIP" version))
16182 "1sihi5zy7mlabh3ix1wvdqz8ibfq1avl8bnxjhvxyzq40zbcklh6"))))
16183 (properties `((upstream-name . "BioTIP")))
16184 (build-system r-build-system)
16195 (home-page "https://github.com/xyang2uchicago/BioTIP")
16196 (synopsis "R package for characterization of biological tipping-point")
16198 "This package adopts tipping-point theory to transcriptome profiles to
16199 help unravel disease regulatory trajectory.")
16200 (license license:gpl2)))
16202 (define-public r-biotmle
16209 (uri (bioconductor-uri "biotmle" version))
16212 "1frig90krvfdk6nwpmslpj0pvligyzwzfwwci7hzwcmbglk5jj22"))))
16213 (properties `((upstream-name . "biotmle")))
16214 (build-system r-build-system)
16225 r-summarizedexperiment
16230 (home-page "https://code.nimahejazi.org/biotmle/")
16231 (synopsis "Targeted learning with moderated statistics for biomarker discovery")
16233 "This package provides tools for differential expression biomarker
16234 discovery based on microarray and next-generation sequencing data that
16235 leverage efficient semiparametric estimators of the average treatment effect
16236 for variable importance analysis. Estimation and inference of the (marginal)
16237 average treatment effects of potential biomarkers are computed by targeted
16238 minimum loss-based estimation, with joint, stable inference constructed across
16239 all biomarkers using a generalization of moderated statistics for use with the
16240 estimated efficient influence function. The procedure accommodates the use of
16241 ensemble machine learning for the estimation of nuisance functions.")
16242 (license license:expat)))
16244 (define-public r-bsseq
16251 (uri (bioconductor-uri "bsseq" version))
16254 "1jpfib2vb6hd7pgh3d33jgch24lba175zmbalwsbgvlmmyyf1ki5"))))
16255 (properties `((upstream-name . "bsseq")))
16256 (build-system r-build-system)
16266 r-delayedmatrixstats
16280 r-summarizedexperiment))
16283 (home-page "https://github.com/hansenlab/bsseq")
16284 (synopsis "Analyze, manage and store bisulfite sequencing data")
16286 "This package provides a collection of tools for analyzing and
16287 visualizing bisulfite sequencing data.")
16288 (license license:artistic2.0)))
16290 (define-public r-dmrseq
16297 (uri (bioconductor-uri "dmrseq" version))
16300 "1c99l62fi26bnbvpzrlsvvs722za0l5vfhddcrhzzzasabhccb4n"))))
16301 (properties `((upstream-name . "dmrseq")))
16302 (build-system r-build-system)
16304 (list r-annotationhub
16309 r-delayedmatrixstats
16323 (home-page "https://bioconductor.org/packages/dmrseq")
16324 (synopsis "Detection and inference of differentially methylated regions")
16326 "This package implements an approach for scanning the genome to detect
16327 and perform accurate inference on differentially methylated regions from Whole
16328 Genome Bisulfite Sequencing data. The method is based on comparing detected
16329 regions to a pooled null distribution, that can be implemented even when as
16330 few as two samples per population are available. Region-level statistics are
16331 obtained by fitting a @dfn{generalized least squares} (GLS) regression model
16332 with a nested autoregressive correlated error structure for the effect of
16333 interest on transformed methylation proportions.")
16334 (license license:expat)))
16336 (define-public r-omnipathr
16338 (name "r-omnipathr")
16343 (uri (bioconductor-uri "OmnipathR" version))
16345 (base32 "0vk0fv09j3ql78mzzhdxwxb2b83qqdz2qfd8wpp1vydmcx2vvgni"))))
16346 (properties `((upstream-name . "OmnipathR")))
16347 (build-system r-build-system)
16350 (modify-phases %standard-phases
16351 (add-after 'unpack 'set-HOME
16352 (lambda _ (setenv "HOME" "/tmp"))))))
16378 (native-inputs (list r-knitr))
16379 (home-page "https://saezlab.github.io/OmnipathR/")
16380 (synopsis "OmniPath web service client and more")
16382 "This package provides a client for the OmniPath web service and many
16383 other resources. It also includes functions to transform and pretty print
16384 some of the downloaded data, functions to access a number of other resources.
16385 Furthermore, OmnipathR features a close integration with the NicheNet method
16386 for ligand activity prediction from transcriptomics data.")
16387 (license license:expat)))
16389 (define-public r-biscuiteer
16391 (name "r-biscuiteer")
16396 (uri (bioconductor-uri "biscuiteer" version))
16399 "0y7vbdaafiga16yr0d22w1v4p0jmczndcar0r0km06f5y1b74amr"))))
16400 (properties `((upstream-name . "biscuiteer")))
16401 (build-system r-build-system)
16409 r-delayedmatrixstats
16428 r-summarizedexperiment
16429 r-variantannotation))
16432 (home-page "https://github.com/trichelab/biscuiteer")
16433 (synopsis "Convenience functions for the Biscuit package")
16435 "This package provides a test harness for bsseq loading of Biscuit
16436 output, summarization of WGBS data over defined regions and in mappable
16437 samples, with or without imputation, dropping of mostly-NA rows, age
16439 (license license:gpl3)))
16441 (define-public r-tcgabiolinks
16443 (name "r-tcgabiolinks")
16448 (uri (bioconductor-uri "TCGAbiolinks" version))
16450 (base32 "0visvfhzaf0p1rb5vjkmw1c91zfxpks8nl9nbl9xlnpm8lkmmkms"))))
16451 (properties `((upstream-name . "TCGAbiolinks")))
16452 (build-system r-build-system)
16471 r-summarizedexperiment
16472 r-tcgabiolinksgui-data
16477 (native-inputs (list r-knitr))
16478 (home-page "https://github.com/BioinformaticsFMRP/TCGAbiolinks")
16479 (synopsis "Integrative analysis with GDC data")
16481 "The aim of TCGAbiolinks is:
16484 @item facilitate GDC open-access data retrieval;
16485 @item prepare the data using the appropriate pre-processing strategies;
16486 @item provide the means to carry out different standard analyses, and;
16487 @item to easily reproduce earlier research results.
16490 In more detail, the package provides multiple methods for analysis (e.g.,
16491 differential expression analysis, identifying differentially methylated
16492 regions) and methods for visualization (e.g., survival plots, volcano plots,
16493 starburst plots) in order to easily develop complete analysis pipelines.")
16494 (license license:gpl3+)))
16496 (define-public r-tricycle
16498 (name "r-tricycle")
16502 (uri (bioconductor-uri "tricycle" version))
16505 "0bjkajcz6xcfak6071d0ihakrvgf7s0pmkn6vqkjd6yxbfld7zln"))))
16506 (properties `((upstream-name . "tricycle")))
16507 (build-system r-build-system)
16509 (list r-annotationdbi
16520 r-singlecellexperiment
16521 r-summarizedexperiment))
16522 (native-inputs (list r-knitr))
16523 (home-page "https://github.com/hansenlab/tricycle")
16524 (synopsis "Transferable representation and inference of cell cycle")
16526 "The package contains functions to infer and visualize cell cycle process
16527 using Single-cell RNA-Seq data. It exploits the idea of transfer learning,
16528 projecting new data to the previous learned biologically interpretable space.
16529 The @code{tricycle} provides a pre-learned cell cycle space, which could be
16530 used to infer cell cycle time of human and mouse single cell samples. In
16531 addition, it also offer functions to visualize cell cycle time on different
16532 embeddings and functions to build new reference.")
16533 (license license:gpl3)))
16535 (define-public r-tximeta
16542 (uri (bioconductor-uri "tximeta" version))
16545 "1vq7x1sf5h8iwdalalbrybxzbq47s2ymb75himj5wkv77mgcivfl"))))
16546 (properties `((upstream-name . "tximeta")))
16547 (build-system r-build-system)
16549 (list r-annotationdbi
16561 r-summarizedexperiment
16566 (home-page "https://github.com/mikelove/tximeta")
16567 (synopsis "Transcript quantification import with automatic metadata")
16569 "This package implements transcript quantification import from Salmon and
16570 alevin with automatic attachment of transcript ranges and release information,
16571 and other associated metadata. De novo transcriptomes can be linked to the
16572 appropriate sources with linkedTxomes and shared for computational
16574 (license license:gpl2)))
16576 (define-public r-phyloseq
16578 (name "r-phyloseq")
16583 (uri (bioconductor-uri "phyloseq" version))
16585 (base32 "0hcyv4ziyaw74mc9vf7bad3q9izi9p0whg3hspbs6w8b3hp34y2k"))))
16586 (properties `((upstream-name . "phyloseq")))
16587 (build-system r-build-system)
16607 (home-page "https://github.com/joey711/phyloseq")
16608 (synopsis "Handling and analysis of high-throughput microbiome census data")
16610 "Phyloseq provides a set of classes and tools to facilitate the import,
16611 storage, analysis, and graphical display of microbiome census data.")
16612 (license license:agpl3)))
HCoop / jackhill / guix / guix.git / blob