1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
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 bioinformatics)
32 #:use-module ((guix licenses) #:prefix license:)
33 #:use-module (guix packages)
34 #:use-module (guix utils)
35 #:use-module (guix download)
36 #:use-module (guix git-download)
37 #:use-module (guix hg-download)
38 #:use-module (guix build-system ant)
39 #:use-module (guix build-system gnu)
40 #:use-module (guix build-system cmake)
41 #:use-module (guix build-system haskell)
42 #:use-module (guix build-system ocaml)
43 #:use-module (guix build-system perl)
44 #:use-module (guix build-system python)
45 #:use-module (guix build-system r)
46 #:use-module (guix build-system ruby)
47 #:use-module (guix build-system scons)
48 #:use-module (guix build-system trivial)
49 #:use-module (gnu packages)
50 #:use-module (gnu packages autotools)
51 #:use-module (gnu packages algebra)
52 #:use-module (gnu packages base)
53 #:use-module (gnu packages bash)
54 #:use-module (gnu packages bison)
55 #:use-module (gnu packages bioconductor)
56 #:use-module (gnu packages boost)
57 #:use-module (gnu packages check)
58 #:use-module (gnu packages compression)
59 #:use-module (gnu packages cpio)
60 #:use-module (gnu packages cran)
61 #:use-module (gnu packages curl)
62 #:use-module (gnu packages documentation)
63 #:use-module (gnu packages databases)
64 #:use-module (gnu packages datastructures)
65 #:use-module (gnu packages file)
66 #:use-module (gnu packages flex)
67 #:use-module (gnu packages gawk)
68 #:use-module (gnu packages gcc)
69 #:use-module (gnu packages gd)
70 #:use-module (gnu packages gtk)
71 #:use-module (gnu packages glib)
72 #:use-module (gnu packages graph)
73 #:use-module (gnu packages groff)
74 #:use-module (gnu packages guile)
75 #:use-module (gnu packages haskell)
76 #:use-module (gnu packages haskell-check)
77 #:use-module (gnu packages haskell-web)
78 #:use-module (gnu packages image)
79 #:use-module (gnu packages imagemagick)
80 #:use-module (gnu packages java)
81 #:use-module (gnu packages java-compression)
82 #:use-module (gnu packages jemalloc)
83 #:use-module (gnu packages dlang)
84 #:use-module (gnu packages linux)
85 #:use-module (gnu packages logging)
86 #:use-module (gnu packages machine-learning)
87 #:use-module (gnu packages man)
88 #:use-module (gnu packages maths)
89 #:use-module (gnu packages mpi)
90 #:use-module (gnu packages ncurses)
91 #:use-module (gnu packages ocaml)
92 #:use-module (gnu packages pcre)
93 #:use-module (gnu packages parallel)
94 #:use-module (gnu packages pdf)
95 #:use-module (gnu packages perl)
96 #:use-module (gnu packages perl-check)
97 #:use-module (gnu packages pkg-config)
98 #:use-module (gnu packages popt)
99 #:use-module (gnu packages protobuf)
100 #:use-module (gnu packages python)
101 #:use-module (gnu packages python-compression)
102 #:use-module (gnu packages python-web)
103 #:use-module (gnu packages python-xyz)
104 #:use-module (gnu packages readline)
105 #:use-module (gnu packages ruby)
106 #:use-module (gnu packages serialization)
107 #:use-module (gnu packages shells)
108 #:use-module (gnu packages statistics)
109 #:use-module (gnu packages swig)
110 #:use-module (gnu packages tbb)
111 #:use-module (gnu packages tex)
112 #:use-module (gnu packages texinfo)
113 #:use-module (gnu packages textutils)
114 #:use-module (gnu packages time)
115 #:use-module (gnu packages tls)
116 #:use-module (gnu packages vim)
117 #:use-module (gnu packages web)
118 #:use-module (gnu packages xml)
119 #:use-module (gnu packages xorg)
120 #:use-module (srfi srfi-1)
121 #:use-module (ice-9 match))
123 (define-public aragorn
130 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
134 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
135 (build-system gnu-build-system)
137 `(#:tests? #f ; there are no tests
139 (modify-phases %standard-phases
149 (string-append "aragorn" ,version ".c"))
152 (lambda* (#:key outputs #:allow-other-keys)
153 (let* ((out (assoc-ref outputs "out"))
154 (bin (string-append out "/bin"))
155 (man (string-append out "/share/man/man1")))
156 (install-file "aragorn" bin)
157 (install-file "aragorn.1" man))
159 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
160 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
162 "Aragorn identifies transfer RNA, mitochondrial RNA and
163 transfer-messenger RNA from nucleotide sequences, based on homology to known
164 tRNA consensus sequences and RNA structure. It also outputs the secondary
165 structure of the predicted RNA.")
166 (license license:gpl2)))
174 ;; BamM is not available on pypi.
176 (url "https://github.com/Ecogenomics/BamM.git")
179 (file-name (git-file-name name version))
182 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
183 (modules '((guix build utils)))
186 ;; Delete bundled htslib.
187 (delete-file-recursively "c/htslib-1.3.1")
189 (build-system python-build-system)
191 `(#:python ,python-2 ; BamM is Python 2 only.
192 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
193 ;; been modified from its original form.
195 (let ((htslib (assoc-ref %build-inputs "htslib")))
196 (list "--with-libhts-lib" (string-append htslib "/lib")
197 "--with-libhts-inc" (string-append htslib "/include/htslib")))
199 (modify-phases %standard-phases
200 (add-after 'unpack 'autogen
202 (with-directory-excursion "c"
203 (let ((sh (which "sh")))
204 (for-each make-file-writable (find-files "." ".*"))
205 ;; Use autogen so that 'configure' works.
206 (substitute* "autogen.sh" (("/bin/sh") sh))
207 (setenv "CONFIG_SHELL" sh)
208 (invoke "./autogen.sh")))
211 ;; Run tests after installation so compilation only happens once.
213 (add-after 'install 'wrap-executable
214 (lambda* (#:key outputs #:allow-other-keys)
215 (let* ((out (assoc-ref outputs "out"))
216 (path (getenv "PATH")))
217 (wrap-program (string-append out "/bin/bamm")
218 `("PATH" ":" prefix (,path))))
220 (add-after 'wrap-executable 'post-install-check
221 (lambda* (#:key inputs outputs #:allow-other-keys)
223 (string-append (assoc-ref outputs "out")
228 (assoc-ref outputs "out")
230 (string-take (string-take-right
231 (assoc-ref inputs "python") 5) 3)
233 (getenv "PYTHONPATH")))
234 ;; There are 2 errors printed, but they are safe to ignore:
235 ;; 1) [E::hts_open_format] fail to open file ...
236 ;; 2) samtools view: failed to open ...
240 `(("autoconf" ,autoconf)
241 ("automake" ,automake)
244 ("python-nose" ,python2-nose)
245 ("python-pysam" ,python2-pysam)))
247 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
248 ("samtools" ,samtools)
252 ("coreutils" ,coreutils)))
254 `(("python-numpy" ,python2-numpy)))
255 (home-page "http://ecogenomics.github.io/BamM/")
256 (synopsis "Metagenomics-focused BAM file manipulator")
258 "BamM is a C library, wrapped in python, to efficiently generate and
259 parse BAM files, specifically for the analysis of metagenomic data. For
260 instance, it implements several methods to assess contig-wise read coverage.")
261 (license license:lgpl3+)))
263 (define-public bamtools
270 (url "https://github.com/pezmaster31/bamtools.git")
271 (commit (string-append "v" version))))
272 (file-name (git-file-name name version))
275 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
276 (build-system cmake-build-system)
278 `(#:tests? #f ;no "check" target
280 (modify-phases %standard-phases
282 'configure 'set-ldflags
283 (lambda* (#:key outputs #:allow-other-keys)
287 (assoc-ref outputs "out") "/lib/bamtools"))
289 (inputs `(("zlib" ,zlib)))
290 (home-page "https://github.com/pezmaster31/bamtools")
291 (synopsis "C++ API and command-line toolkit for working with BAM data")
293 "BamTools provides both a C++ API and a command-line toolkit for handling
295 (license license:expat)))
297 (define-public bcftools
303 (uri (string-append "https://github.com/samtools/bcftools/"
305 version "/bcftools-" version ".tar.bz2"))
308 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
309 (modules '((guix build utils)))
311 ;; Delete bundled htslib.
312 (delete-file-recursively "htslib-1.9")
314 (build-system gnu-build-system)
317 (list "--enable-libgsl")
320 (modify-phases %standard-phases
321 (add-before 'check 'patch-tests
323 (substitute* "test/test.pl"
324 (("/bin/bash") (which "bash")))
332 (home-page "https://samtools.github.io/bcftools/")
333 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
335 "BCFtools is a set of utilities that manipulate variant calls in the
336 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
337 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
338 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
339 (license (list license:gpl3+ license:expat))))
341 (define-public bedops
348 (url "https://github.com/bedops/bedops.git")
349 (commit (string-append "v" version))))
350 (file-name (git-file-name name version))
353 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
354 (build-system gnu-build-system)
357 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
359 (modify-phases %standard-phases
360 (add-after 'unpack 'unpack-tarballs
362 ;; FIXME: Bedops includes tarballs of minimally patched upstream
363 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
364 ;; libraries because at least one of the libraries (zlib) is
365 ;; patched to add a C++ function definition (deflateInit2cpp).
366 ;; Until the Bedops developers offer a way to link against system
367 ;; libraries we have to build the in-tree copies of these three
370 ;; See upstream discussion:
371 ;; https://github.com/bedops/bedops/issues/124
373 ;; Unpack the tarballs to benefit from shebang patching.
374 (with-directory-excursion "third-party"
375 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
376 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
377 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
378 ;; Disable unpacking of tarballs in Makefile.
379 (substitute* "system.mk/Makefile.linux"
380 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
381 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
382 (substitute* "third-party/zlib-1.2.7/Makefile.in"
383 (("^SHELL=.*$") "SHELL=bash\n"))
385 (delete 'configure))))
386 (home-page "https://github.com/bedops/bedops")
387 (synopsis "Tools for high-performance genomic feature operations")
389 "BEDOPS is a suite of tools to address common questions raised in genomic
390 studies---mostly with regard to overlap and proximity relationships between
391 data sets. It aims to be scalable and flexible, facilitating the efficient
392 and accurate analysis and management of large-scale genomic data.
394 BEDOPS provides tools that perform highly efficient and scalable Boolean and
395 other set operations, statistical calculations, archiving, conversion and
396 other management of genomic data of arbitrary scale. Tasks can be easily
397 split by chromosome for distributing whole-genome analyses across a
398 computational cluster.")
399 (license license:gpl2+)))
401 (define-public bedtools
407 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
408 "download/v" version "/"
409 "bedtools-" version ".tar.gz"))
412 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
413 (build-system gnu-build-system)
415 '(#:test-target "test"
417 (list (string-append "prefix=" (assoc-ref %outputs "out")))
419 (modify-phases %standard-phases
420 (delete 'configure))))
421 (native-inputs `(("python" ,python-2)))
423 `(("samtools" ,samtools)
425 (home-page "https://github.com/arq5x/bedtools2")
426 (synopsis "Tools for genome analysis and arithmetic")
428 "Collectively, the bedtools utilities are a swiss-army knife of tools for
429 a wide-range of genomics analysis tasks. The most widely-used tools enable
430 genome arithmetic: that is, set theory on the genome. For example, bedtools
431 allows one to intersect, merge, count, complement, and shuffle genomic
432 intervals from multiple files in widely-used genomic file formats such as BAM,
434 (license license:gpl2)))
436 ;; Later releases of bedtools produce files with more columns than
437 ;; what Ribotaper expects.
438 (define-public bedtools-2.18
439 (package (inherit bedtools)
444 (uri (string-append "https://github.com/arq5x/bedtools2/"
445 "releases/download/v" version
446 "/bedtools-" version ".tar.gz"))
449 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
451 '(#:test-target "test"
453 (modify-phases %standard-phases
456 (lambda* (#:key outputs #:allow-other-keys)
457 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
458 (for-each (lambda (file)
459 (install-file file bin))
460 (find-files "bin" ".*")))
463 ;; Needed for pybedtools.
464 (define-public bedtools-2.26
465 (package (inherit bedtools)
470 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
471 "download/v" version "/"
472 "bedtools-" version ".tar.gz"))
475 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
477 (define-public ribotaper
483 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
484 "files/RiboTaper/RiboTaper_Version_"
488 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
489 (build-system gnu-build-system)
492 (modify-phases %standard-phases
493 (add-after 'install 'wrap-executables
494 (lambda* (#:key inputs outputs #:allow-other-keys)
495 (let* ((out (assoc-ref outputs "out")))
498 (wrap-program (string-append out "/bin/" script)
499 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
500 '("create_annotations_files.bash"
501 "create_metaplots.bash"
502 "Ribotaper_ORF_find.sh"
506 `(("bedtools" ,bedtools-2.18)
507 ("samtools" ,samtools-0.1)
508 ("r-minimal" ,r-minimal)
509 ("r-foreach" ,r-foreach)
510 ("r-xnomial" ,r-xnomial)
512 ("r-multitaper" ,r-multitaper)
513 ("r-seqinr" ,r-seqinr)))
514 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
515 (synopsis "Define translated ORFs using ribosome profiling data")
517 "Ribotaper is a method for defining translated @dfn{open reading
518 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
519 provides the Ribotaper pipeline.")
520 (license license:gpl3+)))
522 (define-public ribodiff
530 (url "https://github.com/ratschlab/RiboDiff.git")
531 (commit (string-append "v" version))))
532 (file-name (git-file-name name version))
535 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
536 (build-system python-build-system)
540 (modify-phases %standard-phases
541 ;; Generate an installable executable script wrapper.
542 (add-after 'unpack 'patch-setup.py
544 (substitute* "setup.py"
545 (("^(.*)packages=.*" line prefix)
546 (string-append line "\n"
547 prefix "scripts=['scripts/TE.py'],\n")))
550 `(("python-numpy" ,python2-numpy)
551 ("python-matplotlib" ,python2-matplotlib)
552 ("python-scipy" ,python2-scipy)
553 ("python-statsmodels" ,python2-statsmodels)))
555 `(("python-mock" ,python2-mock)
556 ("python-nose" ,python2-nose)))
557 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
558 (synopsis "Detect translation efficiency changes from ribosome footprints")
559 (description "RiboDiff is a statistical tool that detects the protein
560 translational efficiency change from Ribo-Seq (ribosome footprinting) and
561 RNA-Seq data. It uses a generalized linear model to detect genes showing
562 difference in translational profile taking mRNA abundance into account. It
563 facilitates us to decipher the translational regulation that behave
564 independently with transcriptional regulation.")
565 (license license:gpl3+)))
567 (define-public bioawk
574 (url "https://github.com/lh3/bioawk.git")
575 (commit (string-append "v" version))))
576 (file-name (git-file-name name version))
579 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
580 (build-system gnu-build-system)
586 `(#:tests? #f ; There are no tests to run.
587 ;; Bison must generate files, before other targets can build.
590 (modify-phases %standard-phases
591 (delete 'configure) ; There is no configure phase.
593 (lambda* (#:key outputs #:allow-other-keys)
594 (let* ((out (assoc-ref outputs "out"))
595 (bin (string-append out "/bin"))
596 (man (string-append out "/share/man/man1")))
598 (copy-file "awk.1" (string-append man "/bioawk.1"))
599 (install-file "bioawk" bin))
601 (home-page "https://github.com/lh3/bioawk")
602 (synopsis "AWK with bioinformatics extensions")
603 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
604 support of several common biological data formats, including optionally gzip'ed
605 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
606 also adds a few built-in functions and a command line option to use TAB as the
607 input/output delimiter. When the new functionality is not used, bioawk is
608 intended to behave exactly the same as the original BWK awk.")
609 (license license:x11)))
611 (define-public python-pybedtools
613 (name "python-pybedtools")
617 (uri (pypi-uri "pybedtools" version))
620 "0l2b2wrnj85azfqgr0zwr60f7j58vlla1hcgxvr9rwikpl8j72ji"))))
621 (build-system python-build-system)
624 (modify-phases %standard-phases
625 ;; See https://github.com/daler/pybedtools/issues/261
626 (add-after 'unpack 'disable-broken-tests
628 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
629 ;; graphical environment.
630 (substitute* "pybedtools/test/test_scripts.py"
631 (("def test_venn_mpl")
632 "def _do_not_test_venn_mpl"))
633 ;; Requires internet access.
634 (substitute* "pybedtools/test/test_helpers.py"
635 (("def test_chromsizes")
636 "def _do_not_test_chromsizes"))
637 ;; FIXME: these two fail for no good reason.
638 (substitute* "pybedtools/test/test1.py"
639 (("def test_issue_157")
640 "def _do_not_test_issue_157")
641 (("def test_to_dataframe")
642 "def _do_not_test_to_dataframe"))
645 ;; Tests don't pass with Bedtools 2.27.1.
646 ;; See https://github.com/daler/pybedtools/issues/260
647 `(("bedtools" ,bedtools-2.26)
648 ("samtools" ,samtools)
649 ("python-matplotlib" ,python-matplotlib)
650 ("python-pysam" ,python-pysam)
651 ("python-pyyaml" ,python-pyyaml)))
653 `(("python-numpy" ,python-numpy)
654 ("python-pandas" ,python-pandas)
655 ("python-cython" ,python-cython)
656 ("python-nose" ,python-nose)
657 ("kentutils" ,kentutils) ; for bedGraphToBigWig
658 ("python-six" ,python-six)))
659 (home-page "https://pythonhosted.org/pybedtools/")
660 (synopsis "Python wrapper for BEDtools programs")
662 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
663 which are widely used for genomic interval manipulation or \"genome algebra\".
664 pybedtools extends BEDTools by offering feature-level manipulations from with
666 (license license:gpl2+)))
668 (define-public python2-pybedtools
669 (let ((pkg (package-with-python2 python-pybedtools)))
670 (package (inherit pkg)
672 `(#:modules ((ice-9 ftw)
676 (guix build python-build-system))
677 ;; See https://github.com/daler/pybedtools/issues/192
678 ,@(substitute-keyword-arguments (package-arguments pkg)
680 `(modify-phases ,phases
683 (let ((cwd (getcwd)))
685 (string-append cwd "/build/"
686 (find (cut string-prefix? "lib" <>)
687 (scandir (string-append cwd "/build")))
688 ":" (getenv "PYTHONPATH"))))
689 ;; The tests need to be run from elsewhere...
690 (mkdir-p "/tmp/test")
691 (copy-recursively "pybedtools/test" "/tmp/test")
692 (with-directory-excursion "/tmp/test"
694 ;; This test fails for unknown reasons
695 "--exclude=.*test_getting_example_beds"))
698 (define-public python-biom-format
700 (name "python-biom-format")
705 ;; Use GitHub as source because PyPI distribution does not contain
706 ;; test data: https://github.com/biocore/biom-format/issues/693
708 (url "https://github.com/biocore/biom-format.git")
710 (file-name (git-file-name name version))
713 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
714 (build-system python-build-system)
717 (modify-phases %standard-phases
718 (add-after 'unpack 'use-cython
719 (lambda _ (setenv "USE_CYTHON" "1") #t))
720 (add-after 'unpack 'disable-broken-test
722 (substitute* "biom/tests/test_cli/test_validate_table.py"
723 (("^(.+)def test_invalid_hdf5" m indent)
724 (string-append indent
725 "@npt.dec.skipif(True, msg='Guix')\n"
728 (add-before 'reset-gzip-timestamps 'make-files-writable
729 (lambda* (#:key outputs #:allow-other-keys)
730 (let ((out (assoc-ref outputs "out")))
731 (for-each (lambda (file) (chmod file #o644))
732 (find-files out "\\.gz"))
735 `(("python-numpy" ,python-numpy)
736 ("python-scipy" ,python-scipy)
737 ("python-flake8" ,python-flake8)
738 ("python-future" ,python-future)
739 ("python-click" ,python-click)
740 ("python-h5py" ,python-h5py)
741 ("python-pandas" ,python-pandas)))
743 `(("python-cython" ,python-cython)
744 ("python-pytest" ,python-pytest)
745 ("python-pytest-cov" ,python-pytest-cov)
746 ("python-nose" ,python-nose)))
747 (home-page "http://www.biom-format.org")
748 (synopsis "Biological Observation Matrix (BIOM) format utilities")
750 "The BIOM file format is designed to be a general-use format for
751 representing counts of observations e.g. operational taxonomic units, KEGG
752 orthology groups or lipid types, in one or more biological samples
753 e.g. microbiome samples, genomes, metagenomes.")
754 (license license:bsd-3)
755 (properties `((python2-variant . ,(delay python2-biom-format))))))
757 (define-public python2-biom-format
758 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
762 (substitute-keyword-arguments (package-arguments base)
764 `(modify-phases ,phases
765 ;; Do not require the unmaintained pyqi library.
766 (add-after 'unpack 'remove-pyqi
768 (substitute* "setup.py"
769 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
772 (define-public bioperl-minimal
773 (let* ((inputs `(("perl-module-build" ,perl-module-build)
774 ("perl-data-stag" ,perl-data-stag)
775 ("perl-libwww" ,perl-libwww)
776 ("perl-uri" ,perl-uri)))
778 (map (compose package-name cadr)
781 (map (compose package-transitive-target-inputs cadr) inputs))))))
783 (name "bioperl-minimal")
788 (uri (string-append "https://github.com/bioperl/bioperl-live/"
790 (string-map (lambda (c)
796 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
797 (build-system perl-build-system)
800 (modify-phases %standard-phases
802 'install 'wrap-programs
803 (lambda* (#:key outputs #:allow-other-keys)
804 ;; Make sure all executables in "bin" find the required Perl
805 ;; modules at runtime. As the PERL5LIB variable contains also
806 ;; the paths of native inputs, we pick the transitive target
807 ;; inputs from %build-inputs.
808 (let* ((out (assoc-ref outputs "out"))
809 (bin (string-append out "/bin/"))
811 (cons (string-append out "/lib/perl5/site_perl")
813 (assoc-ref %build-inputs name))
814 ',transitive-inputs))
816 (for-each (lambda (file)
818 `("PERL5LIB" ":" prefix (,path))))
819 (find-files bin "\\.pl$"))
823 `(("perl-test-most" ,perl-test-most)))
824 (home-page "https://metacpan.org/release/BioPerl")
825 (synopsis "Bioinformatics toolkit")
827 "BioPerl is the product of a community effort to produce Perl code which
828 is useful in biology. Examples include Sequence objects, Alignment objects
829 and database searching objects. These objects not only do what they are
830 advertised to do in the documentation, but they also interact - Alignment
831 objects are made from the Sequence objects, Sequence objects have access to
832 Annotation and SeqFeature objects and databases, Blast objects can be
833 converted to Alignment objects, and so on. This means that the objects
834 provide a coordinated and extensible framework to do computational biology.")
835 (license license:perl-license))))
837 (define-public python-biopython
839 (name "python-biopython")
843 ;; use PyPi rather than biopython.org to ease updating
844 (uri (pypi-uri "biopython" version))
847 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
848 (build-system python-build-system)
851 (modify-phases %standard-phases
852 (add-before 'check 'set-home
853 ;; Some tests require a home directory to be set.
854 (lambda _ (setenv "HOME" "/tmp") #t)))))
856 `(("python-numpy" ,python-numpy)))
857 (home-page "http://biopython.org/")
858 (synopsis "Tools for biological computation in Python")
860 "Biopython is a set of tools for biological computation including parsers
861 for bioinformatics files into Python data structures; interfaces to common
862 bioinformatics programs; a standard sequence class and tools for performing
863 common operations on them; code to perform data classification; code for
864 dealing with alignments; code making it easy to split up parallelizable tasks
865 into separate processes; and more.")
866 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
868 (define-public python2-biopython
869 (package-with-python2 python-biopython))
871 (define-public python-fastalite
873 (name "python-fastalite")
878 (uri (pypi-uri "fastalite" version))
881 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
882 (build-system python-build-system)
884 `(#:tests? #f)) ; Test data is not distributed.
885 (home-page "https://github.com/nhoffman/fastalite")
886 (synopsis "Simplest possible FASTA parser")
887 (description "This library implements a FASTA and a FASTQ parser without
888 relying on a complex dependency tree.")
889 (license license:expat)))
891 (define-public python2-fastalite
892 (package-with-python2 python-fastalite))
894 (define-public bpp-core
895 ;; The last release was in 2014 and the recommended way to install from source
896 ;; is to clone the git repository, so we do this.
897 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
898 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
901 (version (string-append "2.2.0-1." (string-take commit 7)))
905 (url "http://biopp.univ-montp2.fr/git/bpp-core")
907 (file-name (string-append name "-" version "-checkout"))
910 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
911 (build-system cmake-build-system)
913 `(#:parallel-build? #f))
915 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
916 ; compile all of the bpp packages with GCC 5.
917 (home-page "http://biopp.univ-montp2.fr")
918 (synopsis "C++ libraries for Bioinformatics")
920 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
921 analysis, phylogenetics, molecular evolution and population genetics. It is
922 Object Oriented and is designed to be both easy to use and computer efficient.
923 Bio++ intends to help programmers to write computer expensive programs, by
924 providing them a set of re-usable tools.")
925 (license license:cecill-c))))
927 (define-public bpp-phyl
928 ;; The last release was in 2014 and the recommended way to install from source
929 ;; is to clone the git repository, so we do this.
930 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
931 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
934 (version (string-append "2.2.0-1." (string-take commit 7)))
938 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
940 (file-name (string-append name "-" version "-checkout"))
943 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
944 (build-system cmake-build-system)
946 `(#:parallel-build? #f
947 ;; If out-of-source, test data is not copied into the build directory
948 ;; so the tests fail.
949 #:out-of-source? #f))
951 `(("bpp-core" ,bpp-core)
953 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
956 (home-page "http://biopp.univ-montp2.fr")
957 (synopsis "Bio++ phylogenetic Library")
959 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
960 analysis, phylogenetics, molecular evolution and population genetics. This
961 library provides phylogenetics-related modules.")
962 (license license:cecill-c))))
964 (define-public bpp-popgen
965 ;; The last release was in 2014 and the recommended way to install from source
966 ;; is to clone the git repository, so we do this.
967 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
968 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
971 (version (string-append "2.2.0-1." (string-take commit 7)))
975 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
977 (file-name (string-append name "-" version "-checkout"))
980 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
981 (build-system cmake-build-system)
983 `(#:parallel-build? #f
984 #:tests? #f)) ; There are no tests.
986 `(("bpp-core" ,bpp-core)
989 (home-page "http://biopp.univ-montp2.fr")
990 (synopsis "Bio++ population genetics library")
992 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
993 analysis, phylogenetics, molecular evolution and population genetics. This
994 library provides population genetics-related modules.")
995 (license license:cecill-c))))
997 (define-public bpp-seq
998 ;; The last release was in 2014 and the recommended way to install from source
999 ;; is to clone the git repository, so we do this.
1000 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1001 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1004 (version (string-append "2.2.0-1." (string-take commit 7)))
1008 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1010 (file-name (string-append name "-" version "-checkout"))
1013 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1014 (build-system cmake-build-system)
1016 `(#:parallel-build? #f
1017 ;; If out-of-source, test data is not copied into the build directory
1018 ;; so the tests fail.
1019 #:out-of-source? #f))
1021 `(("bpp-core" ,bpp-core)
1022 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1023 (home-page "http://biopp.univ-montp2.fr")
1024 (synopsis "Bio++ sequence library")
1026 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1027 analysis, phylogenetics, molecular evolution and population genetics. This
1028 library provides sequence-related modules.")
1029 (license license:cecill-c))))
1031 (define-public bppsuite
1032 ;; The last release was in 2014 and the recommended way to install from source
1033 ;; is to clone the git repository, so we do this.
1034 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1035 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1038 (version (string-append "2.2.0-1." (string-take commit 7)))
1042 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1044 (file-name (string-append name "-" version "-checkout"))
1047 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1048 (build-system cmake-build-system)
1050 `(#:parallel-build? #f
1051 #:tests? #f)) ; There are no tests.
1055 ("texinfo" ,texinfo)))
1057 `(("bpp-core" ,bpp-core)
1058 ("bpp-seq" ,bpp-seq)
1059 ("bpp-phyl" ,bpp-phyl)
1060 ("bpp-phyl" ,bpp-popgen)
1062 (home-page "http://biopp.univ-montp2.fr")
1063 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1065 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1066 analysis, phylogenetics, molecular evolution and population genetics. This
1067 package provides command line tools using the Bio++ library.")
1068 (license license:cecill-c))))
1070 (define-public blast+
1077 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1078 version "/ncbi-blast-" version "+-src.tar.gz"))
1081 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1082 (patches (search-patches "blast+-fix-makefile.patch"))
1083 (modules '((guix build utils)))
1086 ;; Remove bundled bzip2, zlib and pcre.
1087 (delete-file-recursively "c++/src/util/compress/bzip2")
1088 (delete-file-recursively "c++/src/util/compress/zlib")
1089 (delete-file-recursively "c++/src/util/regexp")
1090 (substitute* "c++/src/util/compress/Makefile.in"
1091 (("bzip2 zlib api") "api"))
1092 ;; Remove useless msbuild directory
1093 (delete-file-recursively
1094 "c++/src/build-system/project_tree_builder/msbuild")
1096 (build-system gnu-build-system)
1098 `(;; There are two(!) tests for this massive library, and both fail with
1099 ;; "unparsable timing stats".
1100 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1101 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1104 #:parallel-build? #f ; not supported
1106 (modify-phases %standard-phases
1107 (add-before 'configure 'set-HOME
1108 ;; $HOME needs to be set at some point during the configure phase
1109 (lambda _ (setenv "HOME" "/tmp") #t))
1110 (add-after 'unpack 'enter-dir
1111 (lambda _ (chdir "c++") #t))
1112 (add-after 'enter-dir 'fix-build-system
1114 (define (which* cmd)
1115 (cond ((string=? cmd "date")
1116 ;; make call to "date" deterministic
1121 (format (current-error-port)
1122 "WARNING: Unable to find absolute path for ~s~%"
1126 ;; Rewrite hardcoded paths to various tools
1127 (substitute* (append '("src/build-system/configure.ac"
1128 "src/build-system/configure"
1129 "src/build-system/helpers/run_with_lock.c"
1130 "scripts/common/impl/if_diff.sh"
1131 "scripts/common/impl/run_with_lock.sh"
1132 "src/build-system/Makefile.configurables.real"
1133 "src/build-system/Makefile.in.top"
1134 "src/build-system/Makefile.meta.gmake=no"
1135 "src/build-system/Makefile.meta.in"
1136 "src/build-system/Makefile.meta_l"
1137 "src/build-system/Makefile.meta_p"
1138 "src/build-system/Makefile.meta_r"
1139 "src/build-system/Makefile.mk.in"
1140 "src/build-system/Makefile.requirements"
1141 "src/build-system/Makefile.rules_with_autodep.in")
1142 (find-files "scripts/common/check" "\\.sh$"))
1143 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1144 (or (which* cmd) all)))
1146 (substitute* (find-files "src/build-system" "^config.*")
1147 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1150 ;; rewrite "/var/tmp" in check script
1151 (substitute* "scripts/common/check/check_make_unix.sh"
1152 (("/var/tmp") "/tmp"))
1154 ;; do not reset PATH
1155 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1157 (("action=/bin/") "action=")
1158 (("export PATH") ":"))
1161 (lambda* (#:key inputs outputs #:allow-other-keys)
1162 (let ((out (assoc-ref outputs "out"))
1163 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1164 (include (string-append (assoc-ref outputs "include")
1165 "/include/ncbi-tools++")))
1166 ;; The 'configure' script doesn't recognize things like
1167 ;; '--enable-fast-install'.
1168 (invoke "./configure.orig"
1169 (string-append "--with-build-root=" (getcwd) "/build")
1170 (string-append "--prefix=" out)
1171 (string-append "--libdir=" lib)
1172 (string-append "--includedir=" include)
1173 (string-append "--with-bz2="
1174 (assoc-ref inputs "bzip2"))
1175 (string-append "--with-z="
1176 (assoc-ref inputs "zlib"))
1177 (string-append "--with-pcre="
1178 (assoc-ref inputs "pcre"))
1179 ;; Each library is built twice by default, once
1180 ;; with "-static" in its name, and again
1185 (outputs '("out" ; 21 MB
1193 ("python" ,python-wrapper)))
1196 (home-page "http://blast.ncbi.nlm.nih.gov")
1197 (synopsis "Basic local alignment search tool")
1199 "BLAST is a popular method of performing a DNA or protein sequence
1200 similarity search, using heuristics to produce results quickly. It also
1201 calculates an “expect value” that estimates how many matches would have
1202 occurred at a given score by chance, which can aid a user in judging how much
1203 confidence to have in an alignment.")
1204 ;; Most of the sources are in the public domain, with the following
1207 ;; * ./c++/include/util/bitset/
1208 ;; * ./c++/src/html/ncbi_menu*.js
1210 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1212 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1214 ;; * ./c++/src/corelib/teamcity_*
1215 (license (list license:public-domain
1221 (define-public bless
1227 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1231 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1232 (modules '((guix build utils)))
1235 ;; Remove bundled boost, pigz, zlib, and .git directory
1236 ;; FIXME: also remove bundled sources for murmurhash3 and
1237 ;; kmc once packaged.
1238 (delete-file-recursively "boost")
1239 (delete-file-recursively "pigz")
1240 (delete-file-recursively "google-sparsehash")
1241 (delete-file-recursively "zlib")
1242 (delete-file-recursively ".git")
1244 (build-system gnu-build-system)
1246 '(#:tests? #f ;no "check" target
1248 (list (string-append "ZLIB="
1249 (assoc-ref %build-inputs "zlib:static")
1251 (string-append "LDFLAGS="
1252 (string-join '("-lboost_filesystem"
1259 (modify-phases %standard-phases
1260 (add-after 'unpack 'do-not-build-bundled-pigz
1261 (lambda* (#:key inputs outputs #:allow-other-keys)
1262 (substitute* "Makefile"
1263 (("cd pigz/pigz-2.3.3; make") ""))
1265 (add-after 'unpack 'patch-paths-to-executables
1266 (lambda* (#:key inputs outputs #:allow-other-keys)
1267 (substitute* "parse_args.cpp"
1268 (("kmc_binary = .*")
1269 (string-append "kmc_binary = \""
1270 (assoc-ref outputs "out")
1272 (("pigz_binary = .*")
1273 (string-append "pigz_binary = \""
1274 (assoc-ref inputs "pigz")
1278 (lambda* (#:key outputs #:allow-other-keys)
1279 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1280 (for-each (lambda (file)
1281 (install-file file bin))
1282 '("bless" "kmc/bin/kmc"))
1284 (delete 'configure))))
1288 `(("openmpi" ,openmpi)
1290 ("sparsehash" ,sparsehash)
1292 ("zlib:static" ,zlib "static")
1294 (supported-systems '("x86_64-linux"))
1295 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1296 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1298 "@dfn{Bloom-filter-based error correction solution for high-throughput
1299 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1300 correction tool for genomic reads produced by @dfn{Next-generation
1301 sequencing} (NGS). BLESS produces accurate correction results with much less
1302 memory compared with previous solutions and is also able to tolerate a higher
1303 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1304 errors at the end of reads.")
1305 (license license:gpl3+)))
1307 (define-public bowtie
1314 (url "https://github.com/BenLangmead/bowtie2.git")
1315 (commit (string-append "v" version))))
1316 (file-name (git-file-name name version))
1319 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1320 (modules '((guix build utils)))
1323 (substitute* "Makefile"
1324 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1325 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1326 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1328 (build-system gnu-build-system)
1333 (string-append "prefix=" (assoc-ref %outputs "out")))
1335 (modify-phases %standard-phases
1340 "scripts/test/simple_tests.pl"
1341 "--bowtie2=./bowtie2"
1342 "--bowtie2-build=./bowtie2-build")
1347 ("python" ,python-wrapper)))
1350 ("perl-clone" ,perl-clone)
1351 ("perl-test-deep" ,perl-test-deep)
1352 ("perl-test-simple" ,perl-test-simple)))
1353 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1354 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1356 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1357 reads to long reference sequences. It is particularly good at aligning reads
1358 of about 50 up to 100s or 1,000s of characters, and particularly good at
1359 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1360 genome with an FM Index to keep its memory footprint small: for the human
1361 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1362 gapped, local, and paired-end alignment modes.")
1363 (supported-systems '("x86_64-linux"))
1364 (license license:gpl3+)))
1366 (define-public tophat
1373 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1377 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1378 (modules '((guix build utils)))
1381 ;; Remove bundled SeqAn and samtools
1382 (delete-file-recursively "src/SeqAn-1.4.2")
1383 (delete-file-recursively "src/samtools-0.1.18")
1385 (build-system gnu-build-system)
1387 '(#:parallel-build? #f ; not supported
1389 (modify-phases %standard-phases
1390 (add-after 'unpack 'use-system-samtools
1391 (lambda* (#:key inputs #:allow-other-keys)
1392 (substitute* "src/Makefile.in"
1393 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1394 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1395 (("SAMPROG = samtools_0\\.1\\.18") "")
1396 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1397 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1398 (substitute* '("src/common.cpp"
1400 (("samtools_0.1.18") (which "samtools")))
1401 (substitute* '("src/common.h"
1402 "src/bam2fastx.cpp")
1403 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1404 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1405 (substitute* '("src/bwt_map.h"
1407 "src/align_status.h")
1408 (("#include <bam.h>") "#include <samtools/bam.h>")
1409 (("#include <sam.h>") "#include <samtools/sam.h>"))
1414 ("samtools" ,samtools-0.1)
1415 ("ncurses" ,ncurses)
1416 ("python" ,python-2)
1419 ("seqan" ,seqan-1)))
1420 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1421 (synopsis "Spliced read mapper for RNA-Seq data")
1423 "TopHat is a fast splice junction mapper for nucleotide sequence
1424 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1425 mammalian-sized genomes using the ultra high-throughput short read
1426 aligner Bowtie, and then analyzes the mapping results to identify
1427 splice junctions between exons.")
1428 ;; TopHat is released under the Boost Software License, Version 1.0
1429 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1430 (license license:boost1.0)))
1439 "https://github.com/lh3/bwa/releases/download/v"
1440 version "/bwa-" version ".tar.bz2"))
1443 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1444 (build-system gnu-build-system)
1446 '(#:tests? #f ;no "check" target
1448 (modify-phases %standard-phases
1450 (lambda* (#:key outputs #:allow-other-keys)
1451 (let ((bin (string-append
1452 (assoc-ref outputs "out") "/bin"))
1454 (assoc-ref outputs "out") "/share/doc/bwa"))
1456 (assoc-ref outputs "out") "/share/man/man1")))
1457 (install-file "bwa" bin)
1458 (install-file "README.md" doc)
1459 (install-file "bwa.1" man))
1461 ;; no "configure" script
1462 (delete 'configure))))
1463 (inputs `(("zlib" ,zlib)))
1464 ;; Non-portable SSE instructions are used so building fails on platforms
1465 ;; other than x86_64.
1466 (supported-systems '("x86_64-linux"))
1467 (home-page "http://bio-bwa.sourceforge.net/")
1468 (synopsis "Burrows-Wheeler sequence aligner")
1470 "BWA is a software package for mapping low-divergent sequences against a
1471 large reference genome, such as the human genome. It consists of three
1472 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1473 designed for Illumina sequence reads up to 100bp, while the rest two for
1474 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1475 features such as long-read support and split alignment, but BWA-MEM, which is
1476 the latest, is generally recommended for high-quality queries as it is faster
1477 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1478 70-100bp Illumina reads.")
1479 (license license:gpl3+)))
1481 (define-public bwa-pssm
1482 (package (inherit bwa)
1488 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1490 (file-name (git-file-name name version))
1493 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1494 (build-system gnu-build-system)
1499 (home-page "http://bwa-pssm.binf.ku.dk/")
1500 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1502 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1503 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1504 existing aligners it is fast and sensitive. Unlike most other aligners,
1505 however, it is also adaptible in the sense that one can direct the alignment
1506 based on known biases within the data set. It is coded as a modification of
1507 the original BWA alignment program and shares the genome index structure as
1508 well as many of the command line options.")
1509 (license license:gpl3+)))
1511 (define-public python-bx-python
1513 (name "python-bx-python")
1517 (uri (pypi-uri "bx-python" version))
1520 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1521 (build-system python-build-system)
1522 ;; Tests fail because test data are not included
1523 (arguments '(#:tests? #f))
1525 `(("python-numpy" ,python-numpy)
1526 ("python-six" ,python-six)))
1530 `(("python-lzo" ,python-lzo)
1531 ("python-nose" ,python-nose)
1532 ("python-cython" ,python-cython)))
1533 (home-page "https://github.com/bxlab/bx-python")
1534 (synopsis "Tools for manipulating biological data")
1536 "bx-python provides tools for manipulating biological data, particularly
1537 multiple sequence alignments.")
1538 (license license:expat)))
1540 (define-public python2-bx-python
1541 (package-with-python2 python-bx-python))
1543 (define-public python-pysam
1545 (name "python-pysam")
1549 ;; Test data is missing on PyPi.
1551 (url "https://github.com/pysam-developers/pysam.git")
1552 (commit (string-append "v" version))))
1553 (file-name (git-file-name name version))
1556 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1557 (modules '((guix build utils)))
1559 ;; Drop bundled htslib. TODO: Also remove samtools
1561 (delete-file-recursively "htslib")
1563 (build-system python-build-system)
1565 `(#:modules ((ice-9 ftw)
1567 (guix build python-build-system)
1570 (modify-phases %standard-phases
1571 (add-before 'build 'set-flags
1572 (lambda* (#:key inputs #:allow-other-keys)
1573 (setenv "HTSLIB_MODE" "external")
1574 (setenv "HTSLIB_LIBRARY_DIR"
1575 (string-append (assoc-ref inputs "htslib") "/lib"))
1576 (setenv "HTSLIB_INCLUDE_DIR"
1577 (string-append (assoc-ref inputs "htslib") "/include"))
1578 (setenv "LDFLAGS" "-lncurses")
1579 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1582 (lambda* (#:key inputs outputs #:allow-other-keys)
1583 ;; This file contains tests that require a connection to the
1585 (delete-file "tests/tabix_test.py")
1586 ;; FIXME: This test fails
1587 (delete-file "tests/AlignmentFile_test.py")
1588 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1589 (setenv "PYTHONPATH"
1591 (getenv "PYTHONPATH")
1592 ":" (getcwd) "/build/"
1593 (car (scandir "build"
1594 (negate (cut string-prefix? "." <>))))))
1595 ;; Step out of source dir so python does not import from CWD.
1596 (with-directory-excursion "tests"
1597 (setenv "HOME" "/tmp")
1598 (invoke "make" "-C" "pysam_data")
1599 (invoke "make" "-C" "cbcf_data")
1600 ;; Running nosetests without explicitly asking for a single
1601 ;; process leads to a crash. Running with multiple processes
1602 ;; fails because the tests are not designed to run in parallel.
1604 ;; FIXME: tests keep timing out on some systems.
1605 (invoke "nosetests" "-v" "--processes" "1")))))))
1607 `(("htslib" ,htslib))) ; Included from installed header files.
1609 `(("ncurses" ,ncurses)
1613 `(("python-cython" ,python-cython)
1614 ;; Dependencies below are are for tests only.
1615 ("samtools" ,samtools)
1616 ("bcftools" ,bcftools)
1617 ("python-nose" ,python-nose)))
1618 (home-page "https://github.com/pysam-developers/pysam")
1619 (synopsis "Python bindings to the SAMtools C API")
1621 "Pysam is a Python module for reading and manipulating files in the
1622 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1623 also includes an interface for tabix.")
1624 (license license:expat)))
1626 (define-public python2-pysam
1627 (package-with-python2 python-pysam))
1629 (define-public python-twobitreader
1631 (name "python-twobitreader")
1636 (url "https://github.com/benjschiller/twobitreader")
1638 (file-name (git-file-name name version))
1641 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1642 (build-system python-build-system)
1643 ;; Tests are not included
1644 (arguments '(#:tests? #f))
1646 `(("python-sphinx" ,python-sphinx)))
1647 (home-page "https://github.com/benjschiller/twobitreader")
1648 (synopsis "Python library for reading .2bit files")
1650 "twobitreader is a Python library for reading .2bit files as used by the
1651 UCSC genome browser.")
1652 (license license:artistic2.0)))
1654 (define-public python2-twobitreader
1655 (package-with-python2 python-twobitreader))
1657 (define-public python-plastid
1659 (name "python-plastid")
1663 (uri (pypi-uri "plastid" version))
1666 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1667 (build-system python-build-system)
1669 ;; Some test files are not included.
1672 `(("python-numpy" ,python-numpy)
1673 ("python-scipy" ,python-scipy)
1674 ("python-pandas" ,python-pandas)
1675 ("python-pysam" ,python-pysam)
1676 ("python-matplotlib" ,python-matplotlib)
1677 ("python-biopython" ,python-biopython)
1678 ("python-twobitreader" ,python-twobitreader)
1679 ("python-termcolor" ,python-termcolor)))
1681 `(("python-cython" ,python-cython)
1682 ("python-nose" ,python-nose)))
1683 (home-page "https://github.com/joshuagryphon/plastid")
1684 (synopsis "Python library for genomic analysis")
1686 "plastid is a Python library for genomic analysis – in particular,
1687 high-throughput sequencing data – with an emphasis on simplicity.")
1688 (license license:bsd-3)))
1690 (define-public python2-plastid
1691 (package-with-python2 python-plastid))
1693 (define-public cd-hit
1699 (uri (string-append "https://github.com/weizhongli/cdhit"
1700 "/releases/download/V" version
1702 "-2017-0621-source.tar.gz"))
1705 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1706 (build-system gnu-build-system)
1708 `(#:tests? #f ; there are no tests
1710 ;; Executables are copied directly to the PREFIX.
1711 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1713 (modify-phases %standard-phases
1714 ;; No "configure" script
1716 ;; Remove sources of non-determinism
1717 (add-after 'unpack 'be-timeless
1719 (substitute* "cdhit-utility.c++"
1720 ((" \\(built on \" __DATE__ \"\\)") ""))
1721 (substitute* "cdhit-common.c++"
1722 (("__DATE__") "\"0\"")
1723 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1725 ;; The "install" target does not create the target directory.
1726 (add-before 'install 'create-target-dir
1727 (lambda* (#:key outputs #:allow-other-keys)
1728 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1732 (home-page "http://weizhongli-lab.org/cd-hit/")
1733 (synopsis "Cluster and compare protein or nucleotide sequences")
1735 "CD-HIT is a program for clustering and comparing protein or nucleotide
1736 sequences. CD-HIT is designed to be fast and handle extremely large
1738 ;; The manual says: "It can be copied under the GNU General Public License
1739 ;; version 2 (GPLv2)."
1740 (license license:gpl2)))
1742 (define-public clipper
1749 (url "https://github.com/YeoLab/clipper.git")
1751 (file-name (git-file-name name version))
1754 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1755 (modules '((guix build utils)))
1758 ;; remove unnecessary setup dependency
1759 (substitute* "setup.py"
1760 (("setup_requires = .*") ""))
1762 (build-system python-build-system)
1764 `(#:python ,python-2 ; only Python 2 is supported
1766 (modify-phases %standard-phases
1767 ;; This is fixed in upstream commit
1768 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1769 (add-after 'unpack 'fix-typo
1771 (substitute* "clipper/src/readsToWiggle.pyx"
1775 `(("htseq" ,python2-htseq)
1776 ("python-pybedtools" ,python2-pybedtools)
1777 ("python-cython" ,python2-cython)
1778 ("python-scikit-learn" ,python2-scikit-learn)
1779 ("python-matplotlib" ,python2-matplotlib)
1780 ("python-pandas" ,python2-pandas)
1781 ("python-pysam" ,python2-pysam)
1782 ("python-numpy" ,python2-numpy)
1783 ("python-scipy" ,python2-scipy)))
1785 `(("python-mock" ,python2-mock) ; for tests
1786 ("python-nose" ,python2-nose) ; for tests
1787 ("python-pytz" ,python2-pytz))) ; for tests
1788 (home-page "https://github.com/YeoLab/clipper")
1789 (synopsis "CLIP peak enrichment recognition")
1791 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1792 (license license:gpl2)))
1794 (define-public codingquarry
1796 (name "codingquarry")
1801 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1805 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1806 (build-system gnu-build-system)
1808 '(#:tests? #f ; no "check" target
1810 (modify-phases %standard-phases
1813 (lambda* (#:key outputs #:allow-other-keys)
1814 (let* ((out (assoc-ref outputs "out"))
1815 (bin (string-append out "/bin"))
1816 (doc (string-append out "/share/doc/codingquarry")))
1817 (install-file "INSTRUCTIONS.pdf" doc)
1818 (copy-recursively "QuarryFiles"
1819 (string-append out "/QuarryFiles"))
1820 (install-file "CodingQuarry" bin)
1821 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1823 (inputs `(("openmpi" ,openmpi)))
1824 (native-search-paths
1825 (list (search-path-specification
1826 (variable "QUARRY_PATH")
1827 (files '("QuarryFiles")))))
1828 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1829 (synopsis "Fungal gene predictor")
1830 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1831 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1832 (home-page "https://sourceforge.net/projects/codingquarry/")
1833 (license license:gpl3+)))
1835 (define-public couger
1842 "http://couger.oit.duke.edu/static/assets/COUGER"
1846 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1847 (build-system gnu-build-system)
1851 (modify-phases %standard-phases
1856 (lambda* (#:key outputs #:allow-other-keys)
1857 (let* ((out (assoc-ref outputs "out"))
1858 (bin (string-append out "/bin")))
1859 (copy-recursively "src" (string-append out "/src"))
1861 ;; Add "src" directory to module lookup path.
1862 (substitute* "couger"
1864 (string-append "import sys\nsys.path.append(\""
1865 out "\")\nfrom argparse")))
1866 (install-file "couger" bin))
1869 'install 'wrap-program
1870 (lambda* (#:key inputs outputs #:allow-other-keys)
1871 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1872 (let* ((out (assoc-ref outputs "out"))
1873 (path (getenv "PYTHONPATH")))
1874 (wrap-program (string-append out "/bin/couger")
1875 `("PYTHONPATH" ":" prefix (,path))))
1878 `(("python" ,python-2)
1879 ("python2-pillow" ,python2-pillow)
1880 ("python2-numpy" ,python2-numpy)
1881 ("python2-scipy" ,python2-scipy)
1882 ("python2-matplotlib" ,python2-matplotlib)))
1884 `(("r-minimal" ,r-minimal)
1886 ("randomjungle" ,randomjungle)))
1888 `(("unzip" ,unzip)))
1889 (home-page "http://couger.oit.duke.edu")
1890 (synopsis "Identify co-factors in sets of genomic regions")
1892 "COUGER can be applied to any two sets of genomic regions bound by
1893 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1894 putative co-factors that provide specificity to each TF. The framework
1895 determines the genomic targets uniquely-bound by each TF, and identifies a
1896 small set of co-factors that best explain the in vivo binding differences
1897 between the two TFs.
1899 COUGER uses classification algorithms (support vector machines and random
1900 forests) with features that reflect the DNA binding specificities of putative
1901 co-factors. The features are generated either from high-throughput TF-DNA
1902 binding data (from protein binding microarray experiments), or from large
1903 collections of DNA motifs.")
1904 (license license:gpl3+)))
1906 (define-public clustal-omega
1908 (name "clustal-omega")
1912 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1916 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1917 (build-system gnu-build-system)
1919 `(("argtable" ,argtable)))
1920 (home-page "http://www.clustal.org/omega/")
1921 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1923 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1924 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1925 of handling data-sets of hundreds of thousands of sequences in reasonable
1927 (license license:gpl2+)))
1929 (define-public crossmap
1935 (uri (pypi-uri "CrossMap" version))
1938 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1939 (build-system python-build-system)
1940 (arguments `(#:python ,python-2))
1942 `(("python-bx-python" ,python2-bx-python)
1943 ("python-numpy" ,python2-numpy)
1944 ("python-pysam" ,python2-pysam)
1947 `(("python-cython" ,python2-cython)
1948 ("python-nose" ,python2-nose)))
1949 (home-page "http://crossmap.sourceforge.net/")
1950 (synopsis "Convert genome coordinates between assemblies")
1952 "CrossMap is a program for conversion of genome coordinates or annotation
1953 files between different genome assemblies. It supports most commonly used
1954 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1955 (license license:gpl2+)))
1957 (define-public python-dnaio
1959 (name "python-dnaio")
1964 (uri (pypi-uri "dnaio" version))
1967 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1968 (build-system python-build-system)
1970 `(("python-cython" ,python-cython)
1971 ("python-pytest" ,python-pytest)
1972 ("python-xopen" ,python-xopen)))
1973 (home-page "https://github.com/marcelm/dnaio/")
1974 (synopsis "Read FASTA and FASTQ files efficiently")
1976 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1977 files. The code was previously part of the cutadapt tool.")
1978 (license license:expat)))
1980 (define-public cutadapt
1987 (url "https://github.com/marcelm/cutadapt.git")
1988 (commit (string-append "v" version))))
1989 (file-name (git-file-name name version))
1992 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1993 (build-system python-build-system)
1995 `(("python-dnaio" ,python-dnaio)
1996 ("python-xopen" ,python-xopen)))
1998 `(("python-cython" ,python-cython)
1999 ("python-pytest" ,python-pytest)))
2000 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2001 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2003 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2004 other types of unwanted sequence from high-throughput sequencing reads.")
2005 (license license:expat)))
2007 (define-public libbigwig
2014 (url "https://github.com/dpryan79/libBigWig.git")
2016 (file-name (string-append name "-" version "-checkout"))
2019 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2020 (build-system gnu-build-system)
2022 `(#:test-target "test"
2023 #:tests? #f ; tests require access to the web
2026 (string-append "prefix=" (assoc-ref %outputs "out")))
2028 (modify-phases %standard-phases
2029 (delete 'configure))))
2034 `(("doxygen" ,doxygen)
2036 ("python" ,python-2)))
2037 (home-page "https://github.com/dpryan79/libBigWig")
2038 (synopsis "C library for handling bigWig files")
2040 "This package provides a C library for parsing local and remote BigWig
2042 (license license:expat)))
2044 (define-public python-pybigwig
2046 (name "python-pybigwig")
2050 (uri (pypi-uri "pyBigWig" version))
2053 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2054 (modules '((guix build utils)))
2057 ;; Delete bundled libBigWig sources
2058 (delete-file-recursively "libBigWig")
2060 (build-system python-build-system)
2063 (modify-phases %standard-phases
2064 (add-after 'unpack 'link-with-libBigWig
2065 (lambda* (#:key inputs #:allow-other-keys)
2066 (substitute* "setup.py"
2067 (("libs=\\[") "libs=[\"BigWig\", "))
2070 `(("python-numpy" ,python-numpy)))
2072 `(("libbigwig" ,libbigwig)
2075 (home-page "https://github.com/dpryan79/pyBigWig")
2076 (synopsis "Access bigWig files in Python using libBigWig")
2078 "This package provides Python bindings to the libBigWig library for
2079 accessing bigWig files.")
2080 (license license:expat)))
2082 (define-public python2-pybigwig
2083 (package-with-python2 python-pybigwig))
2085 (define-public python-dendropy
2087 (name "python-dendropy")
2092 ;; Source from GitHub so that tests are included.
2094 (url "https://github.com/jeetsukumaran/DendroPy.git")
2095 (commit (string-append "v" version))))
2096 (file-name (git-file-name name version))
2099 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2100 (build-system python-build-system)
2101 (home-page "http://packages.python.org/DendroPy/")
2102 (synopsis "Library for phylogenetics and phylogenetic computing")
2104 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2105 writing, simulation, processing and manipulation of phylogenetic
2106 trees (phylogenies) and characters.")
2107 (license license:bsd-3)))
2109 (define-public python2-dendropy
2110 (let ((base (package-with-python2 python-dendropy)))
2115 (modify-phases %standard-phases
2116 (add-after 'unpack 'remove-failing-test
2118 ;; This test fails when the full test suite is run, as documented
2119 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2120 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2121 (("test_collection_comments_and_annotations")
2122 "do_not_test_collection_comments_and_annotations"))
2124 ,@(package-arguments base))))))
2126 (define-public python-py2bit
2128 (name "python-py2bit")
2133 (uri (pypi-uri "py2bit" version))
2136 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2137 (build-system python-build-system)
2138 (home-page "https://github.com/dpryan79/py2bit")
2139 (synopsis "Access 2bit files using lib2bit")
2141 "This package provides Python bindings for lib2bit to access 2bit files
2143 (license license:expat)))
2145 (define-public deeptools
2152 (url "https://github.com/deeptools/deepTools.git")
2154 (file-name (git-file-name name version))
2157 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2158 (build-system python-build-system)
2161 (modify-phases %standard-phases
2162 ;; This phase fails, but it's not needed.
2163 (delete 'reset-gzip-timestamps))))
2165 `(("python-plotly" ,python-plotly)
2166 ("python-scipy" ,python-scipy)
2167 ("python-numpy" ,python-numpy)
2168 ("python-numpydoc" ,python-numpydoc)
2169 ("python-matplotlib" ,python-matplotlib)
2170 ("python-pysam" ,python-pysam)
2171 ("python-py2bit" ,python-py2bit)
2172 ("python-pybigwig" ,python-pybigwig)))
2174 `(("python-mock" ,python-mock) ;for tests
2175 ("python-nose" ,python-nose) ;for tests
2176 ("python-pytz" ,python-pytz))) ;for tests
2177 (home-page "https://github.com/deeptools/deepTools")
2178 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2180 "DeepTools addresses the challenge of handling the large amounts of data
2181 that are now routinely generated from DNA sequencing centers. To do so,
2182 deepTools contains useful modules to process the mapped reads data to create
2183 coverage files in standard bedGraph and bigWig file formats. By doing so,
2184 deepTools allows the creation of normalized coverage files or the comparison
2185 between two files (for example, treatment and control). Finally, using such
2186 normalized and standardized files, multiple visualizations can be created to
2187 identify enrichments with functional annotations of the genome.")
2188 (license license:gpl3+)))
2190 (define-public delly
2197 (url "https://github.com/dellytools/delly.git")
2198 (commit (string-append "v" version))))
2199 (file-name (git-file-name name version))
2201 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2202 (modules '((guix build utils)))
2205 (delete-file-recursively "src/htslib")
2207 (build-system gnu-build-system)
2209 `(#:tests? #f ; There are no tests to run.
2211 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2212 (string-append "prefix=" (assoc-ref %outputs "out")))
2214 (modify-phases %standard-phases
2215 (delete 'configure) ; There is no configure phase.
2216 (add-after 'install 'install-templates
2217 (lambda* (#:key outputs #:allow-other-keys)
2218 (let ((templates (string-append (assoc-ref outputs "out")
2219 "/share/delly/templates")))
2221 (copy-recursively "excludeTemplates" templates)
2228 (home-page "https://github.com/dellytools/delly")
2229 (synopsis "Integrated structural variant prediction method")
2230 (description "Delly is an integrated structural variant prediction method
2231 that can discover and genotype deletions, tandem duplications, inversions and
2232 translocations at single-nucleotide resolution in short-read massively parallel
2233 sequencing data. It uses paired-ends and split-reads to sensitively and
2234 accurately delineate genomic rearrangements throughout the genome.")
2235 (license license:gpl3+)))
2237 (define-public diamond
2244 (url "https://github.com/bbuchfink/diamond.git")
2245 (commit (string-append "v" version))))
2246 (file-name (git-file-name name version))
2249 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2250 (build-system cmake-build-system)
2252 '(#:tests? #f ; no "check" target
2254 (modify-phases %standard-phases
2255 (add-after 'unpack 'remove-native-compilation
2257 (substitute* "CMakeLists.txt" (("-march=native") ""))
2261 (home-page "https://github.com/bbuchfink/diamond")
2262 (synopsis "Accelerated BLAST compatible local sequence aligner")
2264 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2265 translated DNA query sequences against a protein reference database (BLASTP
2266 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2267 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2268 data and settings.")
2269 (license license:agpl3+)))
2271 (define-public discrover
2279 (url "https://github.com/maaskola/discrover.git")
2281 (file-name (git-file-name name version))
2284 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2285 (build-system cmake-build-system)
2287 `(#:tests? #f ; there are no tests
2289 (modify-phases %standard-phases
2290 (add-after 'unpack 'add-missing-includes
2292 (substitute* "src/executioninformation.hpp"
2293 (("#define EXECUTIONINFORMATION_HPP" line)
2294 (string-append line "\n#include <random>")))
2295 (substitute* "src/plasma/fasta.hpp"
2296 (("#define FASTA_HPP" line)
2297 (string-append line "\n#include <random>")))
2303 `(("texlive" ,texlive)
2304 ;; TODO: Replace texlive with minimal texlive-union.
2305 ;; ("texlive" ,(texlive-union (list texlive-latex-doi
2306 ;; texlive-latex-hyperref
2307 ;; texlive-latex-oberdiek
2308 ;; texlive-generic-ifxetex
2309 ;; texlive-latex-url
2310 ;; texlive-latex-pgf
2311 ;; texlive-latex-examplep
2312 ;; texlive-latex-natbib
2313 ;; texlive-latex-verbatimbox
2315 ;; texlive-latex-xcolor
2316 ;; texlive-fonts-amsfonts
2317 ;; texlive-latex-amsfonts
2320 ("imagemagick" ,imagemagick)))
2321 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2322 (synopsis "Discover discriminative nucleotide sequence motifs")
2323 (description "Discrover is a motif discovery method to find binding sites
2324 of nucleic acid binding proteins.")
2325 (license license:gpl3+)))
2327 (define-public eigensoft
2335 (url "https://github.com/DReichLab/EIG.git")
2336 (commit (string-append "v" version))))
2337 (file-name (git-file-name name version))
2340 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2341 (modules '((guix build utils)))
2342 ;; Remove pre-built binaries.
2344 (delete-file-recursively "bin")
2347 (build-system gnu-build-system)
2349 `(#:tests? #f ; There are no tests.
2350 #:make-flags '("CC=gcc")
2352 (modify-phases %standard-phases
2353 ;; There is no configure phase, but the Makefile is in a
2356 (lambda _ (chdir "src") #t))
2357 ;; The provided install target only copies executables to
2358 ;; the "bin" directory in the build root.
2359 (add-after 'install 'actually-install
2360 (lambda* (#:key outputs #:allow-other-keys)
2361 (let* ((out (assoc-ref outputs "out"))
2362 (bin (string-append out "/bin")))
2363 (for-each (lambda (file)
2364 (install-file file bin))
2365 (find-files "../bin" ".*"))
2370 ("openblas" ,openblas)
2372 ("gfortran" ,gfortran "lib")))
2373 (home-page "https://github.com/DReichLab/EIG")
2374 (synopsis "Tools for population genetics")
2375 (description "The EIGENSOFT package provides tools for population
2376 genetics and stratification correction. EIGENSOFT implements methods commonly
2377 used in population genetics analyses such as PCA, computation of Tracy-Widom
2378 statistics, and finding related individuals in structured populations. It
2379 comes with a built-in plotting script and supports multiple file formats and
2380 quantitative phenotypes.")
2381 ;; The license of the eigensoft tools is Expat, but since it's
2382 ;; linking with the GNU Scientific Library (GSL) the effective
2383 ;; license is the GPL.
2384 (license license:gpl3+)))
2386 (define-public edirect
2389 (version "10.2.20181018")
2392 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2393 "/versions/" version
2394 "/edirect-" version ".tar.gz"))
2397 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2398 (build-system perl-build-system)
2401 (modify-phases %standard-phases
2404 (delete 'check) ; simple check after install
2406 (lambda* (#:key outputs #:allow-other-keys)
2407 (install-file "edirect.pl"
2408 (string-append (assoc-ref outputs "out") "/bin"))
2410 (add-after 'install 'wrap-program
2411 (lambda* (#:key outputs #:allow-other-keys)
2412 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2413 (let* ((out (assoc-ref outputs "out"))
2414 (path (getenv "PERL5LIB")))
2415 (wrap-program (string-append out "/bin/edirect.pl")
2416 `("PERL5LIB" ":" prefix (,path))))
2418 (add-after 'wrap-program 'check
2419 (lambda* (#:key outputs #:allow-other-keys)
2420 (invoke (string-append (assoc-ref outputs "out")
2425 `(("perl-html-parser" ,perl-html-parser)
2426 ("perl-encode-locale" ,perl-encode-locale)
2427 ("perl-file-listing" ,perl-file-listing)
2428 ("perl-html-tagset" ,perl-html-tagset)
2429 ("perl-html-tree" ,perl-html-tree)
2430 ("perl-http-cookies" ,perl-http-cookies)
2431 ("perl-http-date" ,perl-http-date)
2432 ("perl-http-message" ,perl-http-message)
2433 ("perl-http-negotiate" ,perl-http-negotiate)
2434 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2435 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2436 ("perl-net-http" ,perl-net-http)
2437 ("perl-uri" ,perl-uri)
2438 ("perl-www-robotrules" ,perl-www-robotrules)
2439 ("perl-xml-simple" ,perl-xml-simple)
2441 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2442 (synopsis "Tools for accessing the NCBI's set of databases")
2444 "Entrez Direct (EDirect) is a method for accessing the National Center
2445 for Biotechnology Information's (NCBI) set of interconnected
2446 databases (publication, sequence, structure, gene, variation, expression,
2447 etc.) from a terminal. Functions take search terms from command-line
2448 arguments. Individual operations are combined to build multi-step queries.
2449 Record retrieval and formatting normally complete the process.
2451 EDirect also provides an argument-driven function that simplifies the
2452 extraction of data from document summaries or other results that are returned
2453 in structured XML format. This can eliminate the need for writing custom
2454 software to answer ad hoc questions.")
2455 (license license:public-domain)))
2457 (define-public exonerate
2466 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2467 "exonerate-" version ".tar.gz"))
2470 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2471 (build-system gnu-build-system)
2473 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2475 `(("pkg-config" ,pkg-config)))
2479 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2480 (synopsis "Generic tool for biological sequence alignment")
2482 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2483 the alignment of sequences using a many alignment models, either exhaustive
2484 dynamic programming or a variety of heuristics.")
2485 (license license:gpl3)))
2487 (define-public express
2495 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2496 version "/express-" version "-src.tgz"))
2499 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2500 (build-system cmake-build-system)
2502 `(#:tests? #f ;no "check" target
2504 (modify-phases %standard-phases
2505 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2506 (lambda* (#:key inputs #:allow-other-keys)
2507 (substitute* "CMakeLists.txt"
2508 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2509 "set(Boost_USE_STATIC_LIBS OFF)")
2510 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2511 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2512 (substitute* "src/CMakeLists.txt"
2513 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2514 (string-append (assoc-ref inputs "bamtools") "/lib"))
2515 (("libprotobuf.a") "libprotobuf.so"))
2519 ("bamtools" ,bamtools)
2520 ("protobuf" ,protobuf)
2522 (home-page "http://bio.math.berkeley.edu/eXpress")
2523 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2525 "eXpress is a streaming tool for quantifying the abundances of a set of
2526 target sequences from sampled subsequences. Example applications include
2527 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2528 analysis (from RNA-Seq), transcription factor binding quantification in
2529 ChIP-Seq, and analysis of metagenomic data.")
2530 (license license:artistic2.0)))
2532 (define-public express-beta-diversity
2534 (name "express-beta-diversity")
2539 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2540 (commit (string-append "v" version))))
2541 (file-name (git-file-name name version))
2544 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2545 (build-system gnu-build-system)
2548 (modify-phases %standard-phases
2550 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2552 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2554 (lambda* (#:key outputs #:allow-other-keys)
2555 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2556 (install-file "../scripts/convertToEBD.py" bin)
2557 (install-file "../bin/ExpressBetaDiversity" bin)
2560 `(("python" ,python-2)))
2561 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2562 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2564 "Express Beta Diversity (EBD) calculates ecological beta diversity
2565 (dissimilarity) measures between biological communities. EBD implements a
2566 variety of diversity measures including those that make use of phylogenetic
2567 similarity of community members.")
2568 (license license:gpl3+)))
2570 (define-public fasttree
2577 "http://www.microbesonline.org/fasttree/FastTree-"
2581 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2582 (build-system gnu-build-system)
2584 `(#:tests? #f ; no "check" target
2586 (modify-phases %standard-phases
2590 (lambda* (#:key source #:allow-other-keys)
2593 "-finline-functions"
2604 "-finline-functions"
2613 (lambda* (#:key outputs #:allow-other-keys)
2614 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2615 (install-file "FastTree" bin)
2616 (install-file "FastTreeMP" bin)
2618 (home-page "http://www.microbesonline.org/fasttree")
2619 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2621 "FastTree can handle alignments with up to a million of sequences in a
2622 reasonable amount of time and memory. For large alignments, FastTree is
2623 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2624 (license license:gpl2+)))
2626 (define-public fastx-toolkit
2628 (name "fastx-toolkit")
2634 "https://github.com/agordon/fastx_toolkit/releases/download/"
2635 version "/fastx_toolkit-" version ".tar.bz2"))
2638 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2639 (build-system gnu-build-system)
2641 `(("libgtextutils" ,libgtextutils)))
2643 `(("pkg-config" ,pkg-config)))
2644 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2645 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2647 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2648 FASTA/FASTQ files preprocessing.
2650 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2651 containing multiple short-reads sequences. The main processing of such
2652 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2653 is sometimes more productive to preprocess the files before mapping the
2654 sequences to the genome---manipulating the sequences to produce better mapping
2655 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2656 (license license:agpl3+)))
2658 (define-public flexbar
2665 (url "https://github.com/seqan/flexbar.git")
2666 (commit (string-append "v" version))))
2667 (file-name (git-file-name name version))
2670 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2671 (build-system cmake-build-system)
2674 (modify-phases %standard-phases
2676 (lambda* (#:key outputs #:allow-other-keys)
2677 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2678 (with-directory-excursion "../source/test"
2679 (invoke "bash" "flexbar_test.sh"))
2682 (lambda* (#:key outputs #:allow-other-keys)
2683 (let* ((out (string-append (assoc-ref outputs "out")))
2684 (bin (string-append out "/bin/")))
2685 (install-file "flexbar" bin))
2691 `(("pkg-config" ,pkg-config)
2693 (home-page "https://github.com/seqan/flexbar")
2694 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2696 "Flexbar preprocesses high-throughput nucleotide sequencing data
2697 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2698 Moreover, trimming and filtering features are provided. Flexbar increases
2699 read mapping rates and improves genome and transcriptome assemblies. It
2700 supports next-generation sequencing data in fasta/q and csfasta/q format from
2701 Illumina, Roche 454, and the SOLiD platform.")
2702 (license license:bsd-3)))
2704 (define-public fraggenescan
2706 (name "fraggenescan")
2712 (string-append "mirror://sourceforge/fraggenescan/"
2713 "FragGeneScan" version ".tar.gz"))
2715 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2716 (build-system gnu-build-system)
2719 (modify-phases %standard-phases
2721 (add-before 'build 'patch-paths
2722 (lambda* (#:key outputs #:allow-other-keys)
2723 (let* ((out (string-append (assoc-ref outputs "out")))
2724 (share (string-append out "/share/fraggenescan/")))
2725 (substitute* "run_FragGeneScan.pl"
2727 (string-append "system(\"" (which "rm")))
2729 (string-append "system(\"" (which "mv")))
2730 (("\\\"awk") (string-append "\"" (which "awk")))
2731 ;; This script and other programs expect the training files
2732 ;; to be in the non-standard location bin/train/XXX. Change
2733 ;; this to be share/fraggenescan/train/XXX instead.
2734 (("^\\$train.file = \\$dir.*")
2735 (string-append "$train_file = \""
2737 "train/\".$FGS_train_file;")))
2738 (substitute* "run_hmm.c"
2739 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2740 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2744 (invoke "make" "clean")
2745 (invoke "make" "fgs")
2748 (lambda* (#:key outputs #:allow-other-keys)
2749 (let* ((out (string-append (assoc-ref outputs "out")))
2750 (bin (string-append out "/bin/"))
2751 (share (string-append out "/share/fraggenescan/train")))
2752 (install-file "run_FragGeneScan.pl" bin)
2753 (install-file "FragGeneScan" bin)
2754 (copy-recursively "train" share))
2757 (add-after 'install 'post-install-check
2758 ;; In lieu of 'make check', run one of the examples and check the
2759 ;; output files gets created.
2760 (lambda* (#:key outputs #:allow-other-keys)
2761 (let* ((out (string-append (assoc-ref outputs "out")))
2762 (bin (string-append out "/bin/"))
2763 (frag (string-append bin "run_FragGeneScan.pl")))
2764 ;; Test complete genome.
2766 "-genome=./example/NC_000913.fna"
2770 (unless (and (file-exists? "test2.faa")
2771 (file-exists? "test2.ffn")
2772 (file-exists? "test2.gff")
2773 (file-exists? "test2.out"))
2774 (error "Expected files do not exist."))
2775 ;; Test incomplete sequences.
2777 "-genome=./example/NC_000913-fgs.ffn"
2784 ("python" ,python-2))) ;not compatible with python 3.
2785 (home-page "https://sourceforge.net/projects/fraggenescan/")
2786 (synopsis "Finds potentially fragmented genes in short reads")
2788 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2789 short and error-prone DNA sequencing reads. It can also be applied to predict
2790 genes in incomplete assemblies or complete genomes.")
2791 ;; GPL3+ according to private correspondense with the authors.
2792 (license license:gpl3+)))
2794 (define-public fxtract
2795 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2803 (url "https://github.com/ctSkennerton/fxtract.git")
2805 (file-name (git-file-name name version))
2808 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2809 (build-system gnu-build-system)
2811 `(#:make-flags (list
2812 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2814 #:test-target "fxtract_test"
2816 (modify-phases %standard-phases
2818 (add-before 'build 'copy-util
2819 (lambda* (#:key inputs #:allow-other-keys)
2821 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2823 ;; Do not use make install as this requires additional dependencies.
2825 (lambda* (#:key outputs #:allow-other-keys)
2826 (let* ((out (assoc-ref outputs "out"))
2827 (bin (string-append out"/bin")))
2828 (install-file "fxtract" bin)
2834 ;; ctskennerton-util is licensed under GPL2.
2835 `(("ctskennerton-util"
2839 (url "https://github.com/ctSkennerton/util.git")
2840 (commit util-commit)))
2841 (file-name (string-append
2842 "ctstennerton-util-" util-commit "-checkout"))
2845 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2846 (home-page "https://github.com/ctSkennerton/fxtract")
2847 (synopsis "Extract sequences from FASTA and FASTQ files")
2849 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2850 or FASTQ) file given a subsequence. It uses a simple substring search for
2851 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2852 lookups or multi-pattern searching as required. By default fxtract looks in
2853 the sequence of each record but can also be told to look in the header,
2854 comment or quality sections.")
2855 ;; 'util' requires SSE instructions.
2856 (supported-systems '("x86_64-linux"))
2857 (license license:expat))))
2859 (define-public gemma
2866 (url "https://github.com/xiangzhou/GEMMA.git")
2867 (commit (string-append "v" version))))
2868 (file-name (git-file-name name version))
2871 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2874 ("gfortran" ,gfortran "lib")
2877 ("openblas" ,openblas)
2879 (build-system gnu-build-system)
2882 '(,@(match (%current-system)
2884 '("FORCE_DYNAMIC=1"))
2886 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2888 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2890 (modify-phases %standard-phases
2892 (add-after 'unpack 'find-eigen
2893 (lambda* (#:key inputs #:allow-other-keys)
2894 ;; Ensure that Eigen headers can be found
2895 (setenv "CPLUS_INCLUDE_PATH"
2896 (string-append (getenv "CPLUS_INCLUDE_PATH")
2898 (assoc-ref inputs "eigen")
2901 (add-before 'build 'bin-mkdir
2906 (lambda* (#:key outputs #:allow-other-keys)
2907 (let ((out (assoc-ref outputs "out")))
2908 (install-file "bin/gemma"
2912 #:tests? #f)) ; no tests included yet
2913 (home-page "https://github.com/xiangzhou/GEMMA")
2914 (synopsis "Tool for genome-wide efficient mixed model association")
2916 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2917 standard linear mixed model resolver with application in genome-wide
2918 association studies (GWAS).")
2919 (license license:gpl3)))
2928 (url "https://github.com/nboley/grit.git")
2930 (file-name (git-file-name name version))
2933 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
2934 (build-system python-build-system)
2936 `(#:python ,python-2
2938 (modify-phases %standard-phases
2939 (add-after 'unpack 'generate-from-cython-sources
2940 (lambda* (#:key inputs outputs #:allow-other-keys)
2941 ;; Delete these C files to force fresh generation from pyx sources.
2942 (delete-file "grit/sparsify_support_fns.c")
2943 (delete-file "grit/call_peaks_support_fns.c")
2944 (substitute* "setup.py"
2945 (("Cython.Setup") "Cython.Build"))
2948 `(("python-scipy" ,python2-scipy)
2949 ("python-numpy" ,python2-numpy)
2950 ("python-pysam" ,python2-pysam)
2951 ("python-networkx" ,python2-networkx)))
2953 `(("python-cython" ,python2-cython)))
2954 (home-page "http://grit-bio.org")
2955 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2957 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2958 full length transcript models. When none of these data sources are available,
2959 GRIT can be run by providing a candidate set of TES or TSS sites. In
2960 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2961 also be run in quantification mode, where it uses a provided GTF file and just
2962 estimates transcript expression.")
2963 (license license:gpl3+)))
2965 (define-public hisat
2972 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2973 version "-beta-source.zip"))
2976 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2977 (build-system gnu-build-system)
2979 `(#:tests? #f ;no check target
2980 #:make-flags '("allall"
2981 ;; Disable unsupported `popcnt' instructions on
2982 ;; architectures other than x86_64
2983 ,@(if (string-prefix? "x86_64"
2984 (or (%current-target-system)
2987 '("POPCNT_CAPABILITY=0")))
2989 (modify-phases %standard-phases
2990 (add-after 'unpack 'patch-sources
2992 ;; XXX Cannot use snippet because zip files are not supported
2993 (substitute* "Makefile"
2994 (("^CC = .*$") "CC = gcc")
2995 (("^CPP = .*$") "CPP = g++")
2996 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2997 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2998 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2999 (substitute* '("hisat-build" "hisat-inspect")
3000 (("/usr/bin/env") (which "env")))
3003 (lambda* (#:key outputs #:allow-other-keys)
3004 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3005 (for-each (lambda (file)
3006 (install-file file bin))
3009 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3011 (delete 'configure))))
3013 `(("unzip" ,unzip)))
3018 ;; Non-portable SSE instructions are used so building fails on platforms
3019 ;; other than x86_64.
3020 (supported-systems '("x86_64-linux"))
3021 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3022 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3024 "HISAT is a fast and sensitive spliced alignment program for mapping
3025 RNA-seq reads. In addition to one global FM index that represents a whole
3026 genome, HISAT uses a large set of small FM indexes that collectively cover the
3027 whole genome. These small indexes (called local indexes) combined with
3028 several alignment strategies enable effective alignment of RNA-seq reads, in
3029 particular, reads spanning multiple exons.")
3030 (license license:gpl3+)))
3032 (define-public hisat2
3039 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3040 "/downloads/hisat2-" version "-source.zip"))
3043 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3044 (build-system gnu-build-system)
3046 `(#:tests? #f ; no check target
3047 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3048 #:modules ((guix build gnu-build-system)
3052 (modify-phases %standard-phases
3053 (add-after 'unpack 'make-deterministic
3055 (substitute* "Makefile"
3060 (lambda* (#:key outputs #:allow-other-keys)
3061 (let* ((out (assoc-ref outputs "out"))
3062 (bin (string-append out "/bin/"))
3063 (doc (string-append out "/share/doc/hisat2/")))
3065 (cut install-file <> bin)
3067 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3069 (install-file "doc/manual.inc.html" doc))
3072 `(("unzip" ,unzip) ; needed for archive from ftp
3074 ("pandoc" ,ghc-pandoc))) ; for documentation
3075 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3076 (synopsis "Graph-based alignment of genomic sequencing reads")
3077 (description "HISAT2 is a fast and sensitive alignment program for mapping
3078 next-generation sequencing reads (both DNA and RNA) to a population of human
3079 genomes (as well as to a single reference genome). In addition to using one
3080 global @dfn{graph FM} (GFM) index that represents a population of human
3081 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3082 the whole genome. These small indexes, combined with several alignment
3083 strategies, enable rapid and accurate alignment of sequencing reads. This new
3084 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3085 ;; HISAT2 contains files from Bowtie2, which is released under
3086 ;; GPLv2 or later. The HISAT2 source files are released under
3088 (license license:gpl3+)))
3090 (define-public hmmer
3098 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3101 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3102 (build-system gnu-build-system)
3103 (native-inputs `(("perl" ,perl)))
3104 (home-page "http://hmmer.org/")
3105 (synopsis "Biosequence analysis using profile hidden Markov models")
3107 "HMMER is used for searching sequence databases for homologs of protein
3108 sequences, and for making protein sequence alignments. It implements methods
3109 using probabilistic models called profile hidden Markov models (profile
3111 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3113 (supported-systems '("x86_64-linux" "i686-linux"))
3114 (license license:bsd-3)))
3116 (define-public htseq
3122 (uri (pypi-uri "HTSeq" version))
3125 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3126 (build-system python-build-system)
3128 `(("python-cython" ,python-cython)))
3129 ;; Numpy needs to be propagated when htseq is used as a Python library.
3131 `(("python-numpy" ,python-numpy)))
3133 `(("python-pysam" ,python-pysam)
3134 ("python-matplotlib" ,python-matplotlib)))
3135 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3136 (synopsis "Analysing high-throughput sequencing data with Python")
3138 "HTSeq is a Python package that provides infrastructure to process data
3139 from high-throughput sequencing assays.")
3140 (license license:gpl3+)))
3142 (define-public python2-htseq
3143 (package-with-python2 htseq))
3145 (define-public java-htsjdk
3147 (name "java-htsjdk")
3148 (version "2.3.0") ; last version without build dependency on gradle
3152 (url "https://github.com/samtools/htsjdk.git")
3154 (file-name (git-file-name name version))
3157 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3158 (modules '((guix build utils)))
3160 ;; Delete pre-built binaries
3162 (delete-file-recursively "lib")
3165 (build-system ant-build-system)
3167 `(#:tests? #f ; test require Internet access
3170 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3171 "/share/java/htsjdk/"))
3172 #:build-target "all"
3174 (modify-phases %standard-phases
3175 ;; The build phase also installs the jars
3176 (delete 'install))))
3178 `(("java-ngs" ,java-ngs)
3179 ("java-snappy-1" ,java-snappy-1)
3180 ("java-commons-compress" ,java-commons-compress)
3181 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3182 ("java-commons-jexl-2" ,java-commons-jexl-2)
3183 ("java-xz" ,java-xz)))
3185 `(("java-testng" ,java-testng)))
3186 (home-page "http://samtools.github.io/htsjdk/")
3187 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3189 "HTSJDK is an implementation of a unified Java library for accessing
3190 common file formats, such as SAM and VCF, used for high-throughput
3191 sequencing (HTS) data. There are also an number of useful utilities for
3192 manipulating HTS data.")
3193 (license license:expat)))
3195 (define-public java-htsjdk-latest
3197 (name "java-htsjdk")
3202 (url "https://github.com/samtools/htsjdk.git")
3204 (file-name (string-append name "-" version "-checkout"))
3207 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3208 (build-system ant-build-system)
3210 `(#:tests? #f ; test require Scala
3212 #:jar-name "htsjdk.jar"
3214 (modify-phases %standard-phases
3215 (add-after 'unpack 'remove-useless-build.xml
3216 (lambda _ (delete-file "build.xml") #t))
3217 ;; The tests require the scalatest package.
3218 (add-after 'unpack 'remove-tests
3219 (lambda _ (delete-file-recursively "src/test") #t)))))
3221 `(("java-ngs" ,java-ngs)
3222 ("java-snappy-1" ,java-snappy-1)
3223 ("java-commons-compress" ,java-commons-compress)
3224 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3225 ("java-commons-jexl-2" ,java-commons-jexl-2)
3226 ("java-xz" ,java-xz)))
3228 `(("java-junit" ,java-junit)))
3229 (home-page "http://samtools.github.io/htsjdk/")
3230 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3232 "HTSJDK is an implementation of a unified Java library for accessing
3233 common file formats, such as SAM and VCF, used for high-throughput
3234 sequencing (HTS) data. There are also an number of useful utilities for
3235 manipulating HTS data.")
3236 (license license:expat)))
3238 ;; This is needed for picard 2.10.3
3239 (define-public java-htsjdk-2.10.1
3240 (package (inherit java-htsjdk-latest)
3241 (name "java-htsjdk")
3246 (url "https://github.com/samtools/htsjdk.git")
3248 (file-name (string-append name "-" version "-checkout"))
3251 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3252 (build-system ant-build-system)
3254 `(#:tests? #f ; tests require Scala
3256 #:jar-name "htsjdk.jar"
3258 (modify-phases %standard-phases
3259 (add-after 'unpack 'remove-useless-build.xml
3260 (lambda _ (delete-file "build.xml") #t))
3261 ;; The tests require the scalatest package.
3262 (add-after 'unpack 'remove-tests
3263 (lambda _ (delete-file-recursively "src/test") #t)))))))
3265 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3266 ;; recent version of java-htsjdk, which depends on gradle.
3267 (define-public java-picard
3269 (name "java-picard")
3274 (url "https://github.com/broadinstitute/picard.git")
3276 (file-name (string-append "java-picard-" version "-checkout"))
3279 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3280 (modules '((guix build utils)))
3283 ;; Delete pre-built binaries.
3284 (delete-file-recursively "lib")
3286 (substitute* "build.xml"
3287 ;; Remove build-time dependency on git.
3288 (("failifexecutionfails=\"true\"")
3289 "failifexecutionfails=\"false\"")
3291 (("depends=\"compile-htsjdk, ")
3293 (("depends=\"compile-htsjdk-tests, ")
3295 ;; Build picard-lib.jar before building picard.jar
3296 (("name=\"picard-jar\" depends=\"" line)
3297 (string-append line "picard-lib-jar, ")))
3299 (build-system ant-build-system)
3301 `(#:build-target "picard-jar"
3302 #:test-target "test"
3303 ;; Tests require jacoco:coverage.
3306 (list (string-append "-Dhtsjdk_lib_dir="
3307 (assoc-ref %build-inputs "java-htsjdk")
3308 "/share/java/htsjdk/")
3309 "-Dhtsjdk-classes=dist/tmp"
3310 (string-append "-Dhtsjdk-version="
3311 ,(package-version java-htsjdk)))
3314 (modify-phases %standard-phases
3315 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3316 (delete 'generate-jar-indices)
3317 (add-after 'unpack 'use-our-htsjdk
3318 (lambda* (#:key inputs #:allow-other-keys)
3319 (substitute* "build.xml"
3320 (("\\$\\{htsjdk\\}/lib")
3321 (string-append (assoc-ref inputs "java-htsjdk")
3322 "/share/java/htsjdk/")))
3324 (add-after 'unpack 'make-test-target-independent
3325 (lambda* (#:key inputs #:allow-other-keys)
3326 (substitute* "build.xml"
3327 (("name=\"test\" depends=\"compile, ")
3328 "name=\"test\" depends=\""))
3330 (replace 'install (install-jars "dist")))))
3332 `(("java-htsjdk" ,java-htsjdk)
3333 ("java-guava" ,java-guava)))
3335 `(("java-testng" ,java-testng)))
3336 (home-page "http://broadinstitute.github.io/picard/")
3337 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3338 (description "Picard is a set of Java command line tools for manipulating
3339 high-throughput sequencing (HTS) data and formats. Picard is implemented
3340 using the HTSJDK Java library to support accessing file formats that are
3341 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3343 (license license:expat)))
3345 ;; This is needed for dropseq-tools
3346 (define-public java-picard-2.10.3
3348 (name "java-picard")
3353 (url "https://github.com/broadinstitute/picard.git")
3355 (file-name (string-append "java-picard-" version "-checkout"))
3358 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3359 (build-system ant-build-system)
3361 `(#:jar-name "picard.jar"
3362 ;; Tests require jacoco:coverage.
3365 #:main-class "picard.cmdline.PicardCommandLine"
3366 #:modules ((guix build ant-build-system)
3368 (guix build java-utils)
3373 (modify-phases %standard-phases
3374 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3375 (delete 'generate-jar-indices)
3376 (add-after 'unpack 'remove-useless-build.xml
3377 (lambda _ (delete-file "build.xml") #t))
3378 ;; This is necessary to ensure that htsjdk is found when using
3379 ;; picard.jar as an executable.
3380 (add-before 'build 'edit-classpath-in-manifest
3381 (lambda* (#:key inputs #:allow-other-keys)
3382 (chmod "build.xml" #o664)
3383 (call-with-output-file "build.xml.new"
3387 (with-input-from-file "build.xml"
3388 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3389 `((target . ,(lambda (tag . kids)
3390 (let ((name ((sxpath '(name *text*))
3392 ;; FIXME: We're breaking the line
3393 ;; early with a dummy path to
3394 ;; ensure that the store reference
3395 ;; isn't broken apart and can still
3396 ;; be found by the reference
3401 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3402 ;; maximum line length is 70
3403 (string-tabulate (const #\b) 57)
3404 (assoc-ref inputs "java-htsjdk"))))
3405 (if (member "manifest" name)
3408 (@ (file "${manifest.file}")
3409 (match "\\r\\n\\r\\n")
3410 (replace "${line.separator}")))
3413 (file "${manifest.file}")
3416 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3417 (*text* . ,(lambda (_ txt) txt))))
3419 (rename-file "build.xml.new" "build.xml")
3422 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3424 `(("java-testng" ,java-testng)
3425 ("java-guava" ,java-guava)))
3426 (home-page "http://broadinstitute.github.io/picard/")
3427 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3428 (description "Picard is a set of Java command line tools for manipulating
3429 high-throughput sequencing (HTS) data and formats. Picard is implemented
3430 using the HTSJDK Java library to support accessing file formats that are
3431 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3433 (license license:expat)))
3435 ;; This is the last version of Picard to provide net.sf.samtools
3436 (define-public java-picard-1.113
3437 (package (inherit java-picard)
3438 (name "java-picard")
3443 (url "https://github.com/broadinstitute/picard.git")
3445 (file-name (string-append "java-picard-" version "-checkout"))
3448 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3449 (modules '((guix build utils)))
3452 ;; Delete pre-built binaries.
3453 (delete-file-recursively "lib")
3456 (build-system ant-build-system)
3458 `(#:build-target "picard-jar"
3459 #:test-target "test"
3460 ;; FIXME: the class path at test time is wrong.
3461 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3462 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3465 ;; This is only used for tests.
3467 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3469 (modify-phases %standard-phases
3470 ;; FIXME: This phase fails.
3471 (delete 'generate-jar-indices)
3472 ;; Do not use bundled ant bzip2.
3473 (add-after 'unpack 'use-ant-bzip
3474 (lambda* (#:key inputs #:allow-other-keys)
3475 (substitute* "build.xml"
3476 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3477 (string-append (assoc-ref inputs "ant")
3480 (add-after 'unpack 'make-test-target-independent
3481 (lambda* (#:key inputs #:allow-other-keys)
3482 (substitute* "build.xml"
3483 (("name=\"test\" depends=\"compile, ")
3484 "name=\"test\" depends=\"compile-tests, ")
3485 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3486 "name=\"compile\" depends=\"compile-src\""))
3488 (add-after 'unpack 'fix-deflater-path
3489 (lambda* (#:key outputs #:allow-other-keys)
3490 (substitute* "src/java/net/sf/samtools/Defaults.java"
3491 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3492 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3493 (assoc-ref outputs "out")
3494 "/lib/jni/libIntelDeflater.so"
3497 ;; Build the deflater library, because we've previously deleted the
3498 ;; pre-built one. This can only be built with access to the JDK
3500 (add-after 'build 'build-jni
3501 (lambda* (#:key inputs #:allow-other-keys)
3504 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3505 "-xf" (assoc-ref inputs "jdk-src"))
3506 (invoke "javah" "-jni"
3507 "-classpath" "classes"
3509 "net.sf.samtools.util.zip.IntelDeflater")
3510 (with-directory-excursion "src/c/inteldeflater"
3511 (invoke "gcc" "-I../../../lib" "-I."
3512 (string-append "-I" (assoc-ref inputs "jdk")
3514 "-I../../../jdk-src/src/share/native/common/"
3515 "-I../../../jdk-src/src/solaris/native/common/"
3516 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3517 (invoke "gcc" "-shared"
3518 "-o" "../../../lib/jni/libIntelDeflater.so"
3519 "IntelDeflater.o" "-lz" "-lstdc++"))
3521 ;; We can only build everything else after building the JNI library.
3522 (add-after 'build-jni 'build-rest
3523 (lambda* (#:key make-flags #:allow-other-keys)
3524 (apply invoke `("ant" "all" ,@make-flags))
3526 (add-before 'build 'set-JAVA6_HOME
3528 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3530 (replace 'install (install-jars "dist"))
3531 (add-after 'install 'install-jni-lib
3532 (lambda* (#:key outputs #:allow-other-keys)
3533 (let ((jni (string-append (assoc-ref outputs "out")
3536 (install-file "lib/jni/libIntelDeflater.so" jni)
3539 `(("java-snappy-1" ,java-snappy-1)
3540 ("java-commons-jexl-2" ,java-commons-jexl-2)
3541 ("java-cofoja" ,java-cofoja)
3542 ("ant" ,ant) ; for bzip2 support at runtime
3545 `(("ant-apache-bcel" ,ant-apache-bcel)
3546 ("ant-junit" ,ant-junit)
3547 ("java-testng" ,java-testng)
3548 ("java-commons-bcel" ,java-commons-bcel)
3549 ("java-jcommander" ,java-jcommander)
3550 ("jdk" ,icedtea-8 "jdk")
3551 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3553 (define-public fastqc
3560 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3561 "projects/fastqc/fastqc_v"
3562 version "_source.zip"))
3565 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3566 (build-system ant-build-system)
3568 `(#:tests? #f ; there are no tests
3569 #:build-target "build"
3571 (modify-phases %standard-phases
3572 (add-after 'unpack 'fix-dependencies
3573 (lambda* (#:key inputs #:allow-other-keys)
3574 (substitute* "build.xml"
3576 (string-append (assoc-ref inputs "java-jbzip2")
3577 "/share/java/jbzip2.jar"))
3579 (string-append (assoc-ref inputs "java-picard-1.113")
3580 "/share/java/sam-1.112.jar"))
3582 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3583 "/share/java/sis-jhdf5.jar")))
3585 ;; There is no installation target
3587 (lambda* (#:key inputs outputs #:allow-other-keys)
3588 (let* ((out (assoc-ref outputs "out"))
3589 (bin (string-append out "/bin"))
3590 (share (string-append out "/share/fastqc/"))
3591 (exe (string-append share "/fastqc")))
3592 (for-each mkdir-p (list bin share))
3593 (copy-recursively "bin" share)
3595 (("my \\$java_bin = 'java';")
3596 (string-append "my $java_bin = '"
3597 (assoc-ref inputs "java")
3600 (symlink exe (string-append bin "/fastqc"))
3604 ("perl" ,perl) ; needed for the wrapper script
3605 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3606 ("java-picard-1.113" ,java-picard-1.113)
3607 ("java-jbzip2" ,java-jbzip2)))
3609 `(("unzip" ,unzip)))
3610 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3611 (synopsis "Quality control tool for high throughput sequence data")
3613 "FastQC aims to provide a simple way to do some quality control
3614 checks on raw sequence data coming from high throughput sequencing
3615 pipelines. It provides a modular set of analyses which you can use to
3616 give a quick impression of whether your data has any problems of which
3617 you should be aware before doing any further analysis.
3619 The main functions of FastQC are:
3622 @item Import of data from BAM, SAM or FastQ files (any variant);
3623 @item Providing a quick overview to tell you in which areas there may
3625 @item Summary graphs and tables to quickly assess your data;
3626 @item Export of results to an HTML based permanent report;
3627 @item Offline operation to allow automated generation of reports
3628 without running the interactive application.
3630 (license license:gpl3+)))
3632 (define-public fastp
3640 (url "https://github.com/OpenGene/fastp.git")
3641 (commit (string-append "v" version))))
3642 (file-name (git-file-name name version))
3645 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3646 (build-system gnu-build-system)
3648 `(#:tests? #f ; there are none
3650 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3652 (modify-phases %standard-phases
3654 (add-before 'install 'create-target-dir
3655 (lambda* (#:key outputs #:allow-other-keys)
3656 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3660 (home-page "https://github.com/OpenGene/fastp/")
3661 (synopsis "All-in-one FastQ preprocessor")
3663 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3664 FastQ files. This tool has multi-threading support to afford high
3666 (license license:expat)))
3668 (define-public htslib
3675 "https://github.com/samtools/htslib/releases/download/"
3676 version "/htslib-" version ".tar.bz2"))
3679 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3680 (build-system gnu-build-system)
3682 `(("openssl" ,openssl)
3687 (home-page "http://www.htslib.org")
3688 (synopsis "C library for reading/writing high-throughput sequencing data")
3690 "HTSlib is a C library for reading/writing high-throughput sequencing
3691 data. It also provides the @command{bgzip}, @command{htsfile}, and
3692 @command{tabix} utilities.")
3693 ;; Files under cram/ are released under the modified BSD license;
3694 ;; the rest is released under the Expat license
3695 (license (list license:expat license:bsd-3))))
3697 ;; This package should be removed once no packages rely upon it.
3705 "https://github.com/samtools/htslib/releases/download/"
3706 version "/htslib-" version ".tar.bz2"))
3709 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3718 (url "https://github.com/nboley/idr.git")
3720 (file-name (git-file-name name version))
3723 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3724 ;; Delete generated C code.
3726 '(begin (delete-file "idr/inv_cdf.c") #t))))
3727 (build-system python-build-system)
3728 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3729 ;; are no longer part of this package. It also asserts False, which
3730 ;; causes the tests to always fail.
3731 (arguments `(#:tests? #f))
3733 `(("python-scipy" ,python-scipy)
3734 ("python-sympy" ,python-sympy)
3735 ("python-numpy" ,python-numpy)
3736 ("python-matplotlib" ,python-matplotlib)))
3738 `(("python-cython" ,python-cython)))
3739 (home-page "https://github.com/nboley/idr")
3740 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3742 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3743 to measure the reproducibility of findings identified from replicate
3744 experiments and provide highly stable thresholds based on reproducibility.")
3745 (license license:gpl2+)))
3747 (define-public jellyfish
3753 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3754 "releases/download/v" version
3755 "/jellyfish-" version ".tar.gz"))
3758 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3759 (build-system gnu-build-system)
3760 (outputs '("out" ;for library
3761 "ruby" ;for Ruby bindings
3762 "python")) ;for Python bindings
3765 (list (string-append "--enable-ruby-binding="
3766 (assoc-ref %outputs "ruby"))
3767 (string-append "--enable-python-binding="
3768 (assoc-ref %outputs "python")))
3770 (modify-phases %standard-phases
3771 (add-before 'check 'set-SHELL-variable
3773 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3775 (setenv "SHELL" (which "bash"))
3781 ("python" ,python-2)
3782 ("pkg-config" ,pkg-config)))
3784 `(("htslib" ,htslib)))
3785 (synopsis "Tool for fast counting of k-mers in DNA")
3787 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3788 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3789 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3790 is a command-line program that reads FASTA and multi-FASTA files containing
3791 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3792 translated into a human-readable text format using the @code{jellyfish dump}
3793 command, or queried for specific k-mers with @code{jellyfish query}.")
3794 (home-page "http://www.genome.umd.edu/jellyfish.html")
3795 ;; JELLYFISH seems to be 64-bit only.
3796 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3797 ;; The combined work is published under the GPLv3 or later. Individual
3798 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3799 (license (list license:gpl3+ license:expat))))
3801 (define-public khmer
3809 (url "https://github.com/dib-lab/khmer.git")
3810 (commit (string-append "v" version))))
3811 (file-name (git-file-name name version))
3814 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3815 (patches (search-patches "khmer-use-libraries.patch"))
3816 (modules '((guix build utils)))
3819 ;; Delete bundled libraries. We do not replace the bundled seqan
3820 ;; as it is a modified subset of the old version 1.4.1.
3822 ;; We do not replace the bundled MurmurHash as the canonical
3823 ;; repository for this code 'SMHasher' is unsuitable for providing
3825 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3826 (delete-file-recursively "third-party/zlib")
3827 (delete-file-recursively "third-party/bzip2")
3829 (build-system python-build-system)
3832 (modify-phases %standard-phases
3833 (add-after 'unpack 'set-cc
3834 (lambda _ (setenv "CC" "gcc") #t))
3835 ;; FIXME: This fails with "permission denied".
3836 (delete 'reset-gzip-timestamps))))
3838 `(("python-cython" ,python-cython)
3839 ("python-pytest" ,python-pytest)
3840 ("python-pytest-runner" ,python-pytest-runner)))
3844 ("python-screed" ,python-screed)
3845 ("python-bz2file" ,python-bz2file)))
3846 (home-page "https://khmer.readthedocs.org/")
3847 (synopsis "K-mer counting, filtering and graph traversal library")
3848 (description "The khmer software is a set of command-line tools for
3849 working with DNA shotgun sequencing data from genomes, transcriptomes,
3850 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3851 sometimes better. Khmer can also identify and fix problems with shotgun
3853 ;; When building on i686, armhf and mips64el, we get the following error:
3854 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3855 (supported-systems '("x86_64-linux" "aarch64-linux"))
3856 (license license:bsd-3)))
3858 (define-public kaiju
3865 (url "https://github.com/bioinformatics-centre/kaiju")
3866 (commit (string-append "v" version))))
3867 (file-name (git-file-name name version))
3870 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3871 (build-system gnu-build-system)
3873 `(#:tests? #f ; There are no tests.
3875 (modify-phases %standard-phases
3877 (add-before 'build 'move-to-src-dir
3878 (lambda _ (chdir "src") #t))
3880 (lambda* (#:key inputs outputs #:allow-other-keys)
3881 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3884 (copy-recursively "bin" bin))
3889 (home-page "http://kaiju.binf.ku.dk/")
3890 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3891 (description "Kaiju is a program for sensitive taxonomic classification
3892 of high-throughput sequencing reads from metagenomic whole genome sequencing
3894 (license license:gpl3+)))
3899 (version "2.1.1.20160309")
3902 (uri (pypi-uri "MACS2" version))
3905 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3906 (build-system python-build-system)
3908 `(#:python ,python-2 ; only compatible with Python 2.7
3909 #:tests? #f)) ; no test target
3911 `(("python-numpy" ,python2-numpy)))
3912 (home-page "https://github.com/taoliu/MACS/")
3913 (synopsis "Model based analysis for ChIP-Seq data")
3915 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3916 identifying transcript factor binding sites named Model-based Analysis of
3917 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3918 the significance of enriched ChIP regions and it improves the spatial
3919 resolution of binding sites through combining the information of both
3920 sequencing tag position and orientation.")
3921 (license license:bsd-3)))
3923 (define-public mafft
3930 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3931 "-without-extensions-src.tgz"))
3932 (file-name (string-append name "-" version ".tgz"))
3935 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3936 (build-system gnu-build-system)
3938 `(#:tests? #f ; no automated tests, though there are tests in the read me
3939 #:make-flags (let ((out (assoc-ref %outputs "out")))
3940 (list (string-append "PREFIX=" out)
3941 (string-append "BINDIR="
3942 (string-append out "/bin"))))
3944 (modify-phases %standard-phases
3945 (add-after 'unpack 'enter-dir
3946 (lambda _ (chdir "core") #t))
3947 (add-after 'enter-dir 'patch-makefile
3949 ;; on advice from the MAFFT authors, there is no need to
3950 ;; distribute mafft-profile, mafft-distance, or
3951 ;; mafft-homologs.rb as they are too "specialised".
3952 (substitute* "Makefile"
3953 ;; remove mafft-homologs.rb from SCRIPTS
3954 (("^SCRIPTS = mafft mafft-homologs.rb")
3956 ;; remove mafft-homologs from MANPAGES
3957 (("^MANPAGES = mafft.1 mafft-homologs.1")
3958 "MANPAGES = mafft.1")
3959 ;; remove mafft-distance from PROGS
3960 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3961 "PROGS = dvtditr dndfast7 dndblast sextet5")
3962 ;; remove mafft-profile from PROGS
3963 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3964 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3965 (("^rm -f mafft-profile mafft-profile.exe") "#")
3966 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3967 ;; do not install MAN pages in libexec folder
3968 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3969 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3971 (add-after 'enter-dir 'patch-paths
3972 (lambda* (#:key inputs #:allow-other-keys)
3973 (substitute* '("pairash.c"
3975 (("perl") (which "perl"))
3976 (("([\"`| ])awk" _ prefix)
3977 (string-append prefix (which "awk")))
3978 (("grep") (which "grep")))
3981 (add-after 'install 'wrap-programs
3982 (lambda* (#:key outputs #:allow-other-keys)
3983 (let* ((out (assoc-ref outputs "out"))
3984 (bin (string-append out "/bin"))
3985 (path (string-append
3986 (assoc-ref %build-inputs "coreutils") "/bin:")))
3987 (for-each (lambda (file)
3989 `("PATH" ":" prefix (,path))))
3997 ("coreutils" ,coreutils)))
3998 (home-page "http://mafft.cbrc.jp/alignment/software/")
3999 (synopsis "Multiple sequence alignment program")
4001 "MAFFT offers a range of multiple alignment methods for nucleotide and
4002 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4003 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4005 (license (license:non-copyleft
4006 "http://mafft.cbrc.jp/alignment/software/license.txt"
4007 "BSD-3 with different formatting"))))
4016 (url "https://github.com/marbl/mash.git")
4017 (commit (string-append "v" version))))
4018 (file-name (git-file-name name version))
4021 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4022 (modules '((guix build utils)))
4025 ;; Delete bundled kseq.
4026 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4027 (delete-file "src/mash/kseq.h")
4029 (build-system gnu-build-system)
4031 `(#:tests? #f ; No tests.
4034 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4035 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4036 #:make-flags (list "CC=gcc")
4038 (modify-phases %standard-phases
4039 (add-after 'unpack 'fix-includes
4041 (substitute* '("src/mash/Sketch.cpp"
4042 "src/mash/CommandFind.cpp"
4043 "src/mash/CommandScreen.cpp")
4044 (("^#include \"kseq\\.h\"")
4045 "#include \"htslib/kseq.h\""))
4047 (add-after 'fix-includes 'use-c++14
4049 ;; capnproto 0.7 requires c++14 to build
4050 (substitute* "configure.ac"
4051 (("c\\+\\+11") "c++14"))
4052 (substitute* "Makefile.in"
4053 (("c\\+\\+11") "c++14"))
4056 `(("autoconf" ,autoconf)
4057 ;; Capnproto and htslib are statically embedded in the final
4058 ;; application. Therefore we also list their licenses, below.
4059 ("capnproto" ,capnproto)
4060 ("htslib" ,htslib)))
4064 (supported-systems '("x86_64-linux"))
4065 (home-page "https://mash.readthedocs.io")
4066 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4067 (description "Mash is a fast sequence distance estimator that uses the
4068 MinHash algorithm and is designed to work with genomes and metagenomes in the
4069 form of assemblies or reads.")
4070 (license (list license:bsd-3 ; Mash
4071 license:expat ; HTSlib and capnproto
4072 license:public-domain ; MurmurHash 3
4073 license:cpl1.0)))) ; Open Bloom Filter
4075 (define-public metabat
4083 (url "https://bitbucket.org/berkeleylab/metabat.git")
4084 (commit (string-append "v" version))))
4085 (file-name (git-file-name name version))
4088 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4089 (patches (search-patches "metabat-fix-compilation.patch"))))
4090 (build-system scons-build-system)
4092 `(#:scons ,scons-python2
4094 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4095 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4096 #:tests? #f ;; Tests are run during the build phase.
4098 (modify-phases %standard-phases
4099 (add-after 'unpack 'fix-includes
4101 (substitute* "src/BamUtils.h"
4102 (("^#include \"bam/bam\\.h\"")
4103 "#include \"samtools/bam.h\"")
4104 (("^#include \"bam/sam\\.h\"")
4105 "#include \"samtools/sam.h\""))
4106 (substitute* "src/KseqReader.h"
4107 (("^#include \"bam/kseq\\.h\"")
4108 "#include \"htslib/kseq.h\""))
4110 (add-after 'unpack 'fix-scons
4111 (lambda* (#:key inputs #:allow-other-keys)
4112 (substitute* "SConstruct"
4113 (("^htslib_dir += 'samtools'")
4114 (string-append "htslib_dir = '"
4115 (assoc-ref inputs "htslib")
4117 (("^samtools_dir = 'samtools'")
4118 (string-append "samtools_dir = '"
4119 (assoc-ref inputs "samtools")
4121 (("^findStaticOrShared\\('bam', hts_lib")
4122 (string-append "findStaticOrShared('bam', '"
4123 (assoc-ref inputs "samtools")
4125 ;; Do not distribute README.
4126 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4131 ("samtools" ,samtools)
4134 (home-page "https://bitbucket.org/berkeleylab/metabat")
4136 "Reconstruction of single genomes from complex microbial communities")
4138 "Grouping large genomic fragments assembled from shotgun metagenomic
4139 sequences to deconvolute complex microbial communities, or metagenome binning,
4140 enables the study of individual organisms and their interactions. MetaBAT is
4141 an automated metagenome binning software, which integrates empirical
4142 probabilistic distances of genome abundance and tetranucleotide frequency.")
4143 ;; The source code contains inline assembly.
4144 (supported-systems '("x86_64-linux" "i686-linux"))
4145 (license (license:non-copyleft "file://license.txt"
4146 "See license.txt in the distribution."))))
4148 (define-public minced
4155 (url "https://github.com/ctSkennerton/minced.git")
4157 (file-name (git-file-name name version))
4160 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4161 (build-system gnu-build-system)
4163 `(#:test-target "test"
4165 (modify-phases %standard-phases
4167 (add-before 'check 'fix-test
4169 ;; Fix test for latest version.
4170 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4171 (("minced:0.1.6") "minced:0.2.0"))
4173 (replace 'install ; No install target.
4174 (lambda* (#:key inputs outputs #:allow-other-keys)
4175 (let* ((out (assoc-ref outputs "out"))
4176 (bin (string-append out "/bin"))
4177 (wrapper (string-append bin "/minced")))
4178 ;; Minced comes with a wrapper script that tries to figure out where
4179 ;; it is located before running the JAR. Since these paths are known
4180 ;; to us, we build our own wrapper to avoid coreutils dependency.
4181 (install-file "minced.jar" bin)
4182 (with-output-to-file wrapper
4186 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4187 (assoc-ref inputs "jre") "/bin/java -jar "
4188 bin "/minced.jar \"$@\"\n"))))
4189 (chmod wrapper #o555))
4192 `(("jdk" ,icedtea "jdk")))
4195 ("jre" ,icedtea "out")))
4196 (home-page "https://github.com/ctSkennerton/minced")
4197 (synopsis "Mining CRISPRs in Environmental Datasets")
4199 "MinCED is a program to find Clustered Regularly Interspaced Short
4200 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4201 unassembled metagenomic reads, but is mainly designed for full genomes and
4202 assembled metagenomic sequence.")
4203 (license license:gpl3+)))
4211 (uri (pypi-uri "misopy" version))
4214 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4215 (modules '((guix build utils)))
4217 (substitute* "setup.py"
4218 ;; Use setuptools, or else the executables are not
4220 (("distutils.core") "setuptools")
4221 ;; use "gcc" instead of "cc" for compilation
4223 "cc.set_executables(
4227 linker_so='gcc -shared'); defines"))
4229 (build-system python-build-system)
4231 `(#:python ,python-2 ; only Python 2 is supported
4232 #:tests? #f)) ; no "test" target
4234 `(("samtools" ,samtools)
4235 ("python-numpy" ,python2-numpy)
4236 ("python-pysam" ,python2-pysam)
4237 ("python-scipy" ,python2-scipy)
4238 ("python-matplotlib" ,python2-matplotlib)))
4240 `(("python-mock" ,python2-mock) ;for tests
4241 ("python-pytz" ,python2-pytz))) ;for tests
4242 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4243 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4245 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4246 the expression level of alternatively spliced genes from RNA-Seq data, and
4247 identifies differentially regulated isoforms or exons across samples. By
4248 modeling the generative process by which reads are produced from isoforms in
4249 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4250 that a read originated from a particular isoform.")
4251 (license license:gpl2)))
4253 (define-public muscle
4256 (version "3.8.1551")
4258 (method url-fetch/tarbomb)
4260 "http://www.drive5.com/muscle/muscle_src_"
4264 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4265 (build-system gnu-build-system)
4267 `(#:make-flags (list "LDLIBS = -lm")
4269 (modify-phases %standard-phases
4272 ;; There are no tests, so just test if it runs.
4273 (lambda _ (invoke "./muscle" "-version") #t))
4275 (lambda* (#:key outputs #:allow-other-keys)
4276 (let* ((out (assoc-ref outputs "out"))
4277 (bin (string-append out "/bin")))
4278 (install-file "muscle" bin)
4280 (home-page "http://www.drive5.com/muscle")
4281 (synopsis "Multiple sequence alignment program")
4283 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4284 program for nucleotide and protein sequences.")
4285 ;; License information found in 'muscle -h' and usage.cpp.
4286 (license license:public-domain)))
4288 (define-public newick-utils
4289 ;; There are no recent releases so we package from git.
4290 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4292 (name "newick-utils")
4293 (version (string-append "1.6-1." (string-take commit 8)))
4297 (url "https://github.com/tjunier/newick_utils.git")
4299 (file-name (string-append name "-" version "-checkout"))
4302 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4303 (build-system gnu-build-system)
4305 ;; XXX: TODO: Enable Lua and Guile bindings.
4306 ;; https://github.com/tjunier/newick_utils/issues/13
4307 `(("libxml2" ,libxml2)
4311 `(("autoconf" ,autoconf)
4312 ("automake" ,automake)
4313 ("libtool" ,libtool)))
4314 (synopsis "Programs for working with newick format phylogenetic trees")
4316 "Newick-utils is a suite of utilities for processing phylogenetic trees
4317 in Newick format. Functions include re-rooting, extracting subtrees,
4318 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4319 (home-page "https://github.com/tjunier/newick_utils")
4320 (license license:bsd-3))))
4329 "https://github.com/wwood/OrfM/releases/download/v"
4330 version "/orfm-" version ".tar.gz"))
4333 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4334 (build-system gnu-build-system)
4335 (inputs `(("zlib" ,zlib)))
4337 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4338 ("ruby-rspec" ,ruby-rspec)
4340 (synopsis "Simple and not slow open reading frame (ORF) caller")
4342 "An ORF caller finds stretches of DNA that, when translated, are not
4343 interrupted by stop codons. OrfM finds and prints these ORFs.")
4344 (home-page "https://github.com/wwood/OrfM")
4345 (license license:lgpl3+)))
4347 (define-public pplacer
4348 (let ((commit "807f6f3"))
4351 ;; The commit should be updated with each version change.
4352 (version "1.1.alpha19")
4357 (url "https://github.com/matsen/pplacer.git")
4358 (commit (string-append "v" version))))
4359 (file-name (git-file-name name version))
4361 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
4362 (build-system ocaml-build-system)
4364 `(#:ocaml ,ocaml-4.01
4365 #:findlib ,ocaml4.01-findlib
4366 #:modules ((guix build ocaml-build-system)
4370 (modify-phases %standard-phases
4372 (add-after 'unpack 'replace-bundled-cddlib
4373 (lambda* (#:key inputs #:allow-other-keys)
4374 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4375 (local-dir "cddlib_guix"))
4377 (with-directory-excursion local-dir
4378 (invoke "tar" "xvf" cddlib-src))
4379 (let ((cddlib-src-folder
4380 (string-append local-dir "/"
4381 (list-ref (scandir local-dir) 2)
4383 (for-each make-file-writable (find-files "cdd_src" ".*"))
4387 (string-append "cdd_src/" (basename file))))
4388 (find-files cddlib-src-folder ".*[ch]$")))
4390 (add-after 'unpack 'fix-makefile
4392 ;; Remove system calls to 'git'.
4393 (substitute* "Makefile"
4394 (("^DESCRIPT:=pplacer-.*")
4396 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4397 (substitute* "myocamlbuild.ml"
4398 (("git describe --tags --long .*\\\" with")
4400 "echo -n v" ,version "-" ,commit "\" with")))
4403 (lambda* (#:key outputs #:allow-other-keys)
4404 (let* ((out (assoc-ref outputs "out"))
4405 (bin (string-append out "/bin")))
4406 (copy-recursively "bin" bin))
4411 ("ocaml-ounit" ,ocaml4.01-ounit)
4412 ("ocaml-batteries" ,ocaml4.01-batteries)
4413 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4414 ("ocaml-csv" ,ocaml4.01-csv)
4415 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4416 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4417 ("ocaml-mcl" ,ocaml4.01-mcl)
4418 ("ocaml-gsl" ,ocaml4.01-gsl)
4419 ("cddlib-src" ,(package-source cddlib))))
4421 `(("pplacer-scripts" ,pplacer-scripts)))
4422 (synopsis "Phylogenetic placement of biological sequences")
4424 "Pplacer places query sequences on a fixed reference phylogenetic tree
4425 to maximize phylogenetic likelihood or posterior probability according to a
4426 reference alignment. Pplacer is designed to be fast, to give useful
4427 information about uncertainty, and to offer advanced visualization and
4428 downstream analysis.")
4429 (home-page "http://matsen.fhcrc.org/pplacer")
4430 (license license:gpl3))))
4432 ;; This package is installed alongside 'pplacer'. It is a separate package so
4433 ;; that it can use the python-build-system for the scripts that are
4434 ;; distributed alongside the main OCaml binaries.
4435 (define pplacer-scripts
4438 (name "pplacer-scripts")
4439 (build-system python-build-system)
4441 `(#:python ,python-2
4443 (modify-phases %standard-phases
4444 (add-after 'unpack 'enter-scripts-dir
4445 (lambda _ (chdir "scripts") #t))
4447 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
4448 (add-after 'install 'wrap-executables
4449 (lambda* (#:key inputs outputs #:allow-other-keys)
4450 (let* ((out (assoc-ref outputs "out"))
4451 (bin (string-append out "/bin")))
4452 (let ((path (string-append
4453 (assoc-ref inputs "hmmer") "/bin:"
4454 (assoc-ref inputs "infernal") "/bin")))
4456 (wrap-program (string-append bin "/refpkg_align.py")
4457 `("PATH" ":" prefix (,path))))
4458 (let ((path (string-append
4459 (assoc-ref inputs "hmmer") "/bin")))
4460 (wrap-program (string-append bin "/hrefpkg_query.py")
4461 `("PATH" ":" prefix (,path)))))
4464 `(("infernal" ,infernal)
4467 `(("python-biopython" ,python2-biopython)
4468 ("taxtastic" ,taxtastic)))
4469 (synopsis "Pplacer Python scripts")))
4471 (define-public python2-pbcore
4473 (name "python2-pbcore")
4477 (uri (pypi-uri "pbcore" version))
4480 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4481 (build-system python-build-system)
4482 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4484 `(("python-cython" ,python2-cython)
4485 ("python-numpy" ,python2-numpy)
4486 ("python-pysam" ,python2-pysam)
4487 ("python-h5py" ,python2-h5py)))
4489 `(("python-nose" ,python2-nose)
4490 ("python-sphinx" ,python2-sphinx)
4491 ("python-pyxb" ,python2-pyxb)))
4492 (home-page "http://pacificbiosciences.github.io/pbcore/")
4493 (synopsis "Library for reading and writing PacBio data files")
4495 "The pbcore package provides Python APIs for interacting with PacBio data
4496 files and writing bioinformatics applications.")
4497 (license license:bsd-3)))
4499 (define-public python2-warpedlmm
4501 (name "python2-warpedlmm")
4507 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4511 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4512 (build-system python-build-system)
4514 `(#:python ,python-2)) ; requires Python 2.7
4516 `(("python-scipy" ,python2-scipy)
4517 ("python-numpy" ,python2-numpy)
4518 ("python-matplotlib" ,python2-matplotlib)
4519 ("python-fastlmm" ,python2-fastlmm)
4520 ("python-pandas" ,python2-pandas)
4521 ("python-pysnptools" ,python2-pysnptools)))
4523 `(("python-mock" ,python2-mock)
4524 ("python-nose" ,python2-nose)
4526 (home-page "https://github.com/PMBio/warpedLMM")
4527 (synopsis "Implementation of warped linear mixed models")
4529 "WarpedLMM is a Python implementation of the warped linear mixed model,
4530 which automatically learns an optimal warping function (or transformation) for
4531 the phenotype as it models the data.")
4532 (license license:asl2.0)))
4534 (define-public pbtranscript-tofu
4535 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4537 (name "pbtranscript-tofu")
4538 (version (string-append "2.2.3." (string-take commit 7)))
4542 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4544 (file-name (string-append name "-" version "-checkout"))
4547 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4548 (modules '((guix build utils)))
4551 ;; remove bundled Cython sources
4552 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4554 (build-system python-build-system)
4556 `(#:python ,python-2
4557 ;; FIXME: Tests fail with "No such file or directory:
4558 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4561 (modify-phases %standard-phases
4562 (add-after 'unpack 'enter-directory
4564 (chdir "pbtranscript-tofu/pbtranscript/")
4566 ;; With setuptools version 18.0 and later this setup.py hack causes
4567 ;; a build error, so we disable it.
4568 (add-after 'enter-directory 'patch-setuppy
4570 (substitute* "setup.py"
4571 (("if 'setuptools.extension' in sys.modules:")
4575 `(("python-numpy" ,python2-numpy)
4576 ("python-bx-python" ,python2-bx-python)
4577 ("python-networkx" ,python2-networkx)
4578 ("python-scipy" ,python2-scipy)
4579 ("python-pbcore" ,python2-pbcore)
4580 ("python-h5py" ,python2-h5py)))
4582 `(("python-cython" ,python2-cython)
4583 ("python-nose" ,python2-nose)))
4584 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4585 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4587 "pbtranscript-tofu contains scripts to analyze transcriptome data
4588 generated using the PacBio Iso-Seq protocol.")
4589 (license license:bsd-3))))
4591 (define-public prank
4598 "http://wasabiapp.org/download/prank/prank.source."
4602 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4603 (build-system gnu-build-system)
4606 (modify-phases %standard-phases
4607 (add-after 'unpack 'enter-src-dir
4611 (add-after 'unpack 'remove-m64-flag
4612 ;; Prank will build with the correct 'bit-ness' without this flag
4613 ;; and this allows building on 32-bit machines.
4614 (lambda _ (substitute* "src/Makefile"
4619 (lambda* (#:key outputs #:allow-other-keys)
4620 (let* ((out (assoc-ref outputs "out"))
4621 (bin (string-append out "/bin"))
4622 (man (string-append out "/share/man/man1"))
4623 (path (string-append
4624 (assoc-ref %build-inputs "mafft") "/bin:"
4625 (assoc-ref %build-inputs "exonerate") "/bin:"
4626 (assoc-ref %build-inputs "bppsuite") "/bin")))
4627 (install-file "prank" bin)
4628 (wrap-program (string-append bin "/prank")
4629 `("PATH" ":" prefix (,path)))
4630 (install-file "prank.1" man))
4634 ("exonerate" ,exonerate)
4635 ("bppsuite" ,bppsuite)))
4636 (home-page "http://wasabiapp.org/software/prank/")
4637 (synopsis "Probabilistic multiple sequence alignment program")
4639 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4640 codon and amino-acid sequences. It is based on a novel algorithm that treats
4641 insertions correctly and avoids over-estimation of the number of deletion
4642 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4643 in phylogenetics and correctly takes into account the evolutionary distances
4644 between sequences. Lastly, PRANK allows for defining a potential structure
4645 for sequences to be aligned and then, simultaneously with the alignment,
4646 predicts the locations of structural units in the sequences.")
4647 (license license:gpl2+)))
4649 (define-public proteinortho
4651 (name "proteinortho")
4658 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4659 version "_src.tar.gz"))
4662 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4663 (build-system gnu-build-system)
4665 `(#:test-target "test"
4667 (modify-phases %standard-phases
4669 ;; There is no configure script, so we modify the Makefile directly.
4670 (lambda* (#:key outputs #:allow-other-keys)
4671 (substitute* "Makefile"
4674 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4676 (add-before 'install 'make-install-directory
4677 ;; The install directory is not created during 'make install'.
4678 (lambda* (#:key outputs #:allow-other-keys)
4679 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4681 (add-after 'install 'wrap-programs
4682 (lambda* (#:key inputs outputs #:allow-other-keys)
4683 (let* ((path (getenv "PATH"))
4684 (out (assoc-ref outputs "out"))
4685 (binary (string-append out "/bin/proteinortho5.pl")))
4686 (wrap-program binary `("PATH" ":" prefix (,path))))
4690 ("python" ,python-2)
4691 ("blast+" ,blast+)))
4692 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4693 (synopsis "Detect orthologous genes across species")
4695 "Proteinortho is a tool to detect orthologous genes across different
4696 species. For doing so, it compares similarities of given gene sequences and
4697 clusters them to find significant groups. The algorithm was designed to handle
4698 large-scale data and can be applied to hundreds of species at once.")
4699 (license license:gpl2+)))
4701 (define-public pyicoteo
4709 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4710 (commit (string-append "v" version))))
4711 (file-name (git-file-name name version))
4714 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4715 (build-system python-build-system)
4717 `(#:python ,python-2 ; does not work with Python 3
4718 #:tests? #f)) ; there are no tests
4720 `(("python2-matplotlib" ,python2-matplotlib)))
4721 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4722 (synopsis "Analyze high-throughput genetic sequencing data")
4724 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4725 sequencing data. It works with genomic coordinates. There are currently six
4726 different command-line tools:
4729 @item pyicoregion: for generating exploratory regions automatically;
4730 @item pyicoenrich: for differential enrichment between two conditions;
4731 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4732 @item pyicos: for genomic coordinates manipulation;
4733 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4734 @item pyicount: to count how many reads from N experiment files overlap in a
4736 @item pyicotrocol: to combine operations from pyicoteo.
4738 (license license:gpl3+)))
4740 (define-public prodigal
4747 (url "https://github.com/hyattpd/Prodigal.git")
4748 (commit (string-append "v" version))))
4749 (file-name (git-file-name name version))
4752 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4753 (build-system gnu-build-system)
4755 `(#:tests? #f ;no check target
4756 #:make-flags (list (string-append "INSTALLDIR="
4757 (assoc-ref %outputs "out")
4760 (modify-phases %standard-phases
4761 (delete 'configure))))
4762 (home-page "http://prodigal.ornl.gov")
4763 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4765 "Prodigal runs smoothly on finished genomes, draft genomes, and
4766 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4767 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4768 partial genes, and identifies translation initiation sites.")
4769 (license license:gpl3+)))
4771 (define-public roary
4779 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4783 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4784 (build-system perl-build-system)
4787 (modify-phases %standard-phases
4792 ;; The tests are not run by default, so we run each test file
4794 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4796 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4797 (getenv "PERL5LIB")))
4798 (for-each (lambda (file)
4799 (display file)(display "\n")
4800 (invoke "perl" file))
4801 (find-files "t" ".*\\.t$"))
4804 ;; There is no 'install' target in the Makefile.
4805 (lambda* (#:key outputs #:allow-other-keys)
4806 (let* ((out (assoc-ref outputs "out"))
4807 (bin (string-append out "/bin"))
4808 (perl (string-append out "/lib/perl5/site_perl"))
4809 (roary-plots "contrib/roary_plots"))
4812 (copy-recursively "bin" bin)
4813 (copy-recursively "lib" perl)
4815 (add-after 'install 'wrap-programs
4816 (lambda* (#:key inputs outputs #:allow-other-keys)
4817 (let* ((out (assoc-ref outputs "out"))
4818 (perl5lib (getenv "PERL5LIB"))
4819 (path (getenv "PATH")))
4820 (for-each (lambda (prog)
4821 (let ((binary (string-append out "/" prog)))
4822 (wrap-program binary
4823 `("PERL5LIB" ":" prefix
4824 (,(string-append perl5lib ":" out
4825 "/lib/perl5/site_perl"))))
4826 (wrap-program binary
4828 (,(string-append path ":" out "/bin"))))))
4829 (find-files "bin" ".*[^R]$"))
4831 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4832 (r-site-lib (getenv "R_LIBS_SITE"))
4834 (string-append (assoc-ref inputs "coreutils") "/bin")))
4836 `("R_LIBS_SITE" ":" prefix
4837 (,(string-append r-site-lib ":" out "/site-library/"))))
4840 (,(string-append coreutils-path ":" out "/bin"))))))
4843 `(("perl-env-path" ,perl-env-path)
4844 ("perl-test-files" ,perl-test-files)
4845 ("perl-test-most" ,perl-test-most)
4846 ("perl-test-output" ,perl-test-output)))
4848 `(("perl-array-utils" ,perl-array-utils)
4849 ("bioperl" ,bioperl-minimal)
4850 ("perl-digest-md5-file" ,perl-digest-md5-file)
4851 ("perl-exception-class" ,perl-exception-class)
4852 ("perl-file-find-rule" ,perl-file-find-rule)
4853 ("perl-file-grep" ,perl-file-grep)
4854 ("perl-file-slurper" ,perl-file-slurper)
4855 ("perl-file-which" ,perl-file-which)
4856 ("perl-graph" ,perl-graph)
4857 ("perl-graph-readwrite" ,perl-graph-readwrite)
4858 ("perl-log-log4perl" ,perl-log-log4perl)
4859 ("perl-moose" ,perl-moose)
4860 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4861 ("perl-text-csv" ,perl-text-csv)
4862 ("bedtools" ,bedtools)
4866 ("parallel" ,parallel)
4869 ("fasttree" ,fasttree)
4873 ("r-minimal" ,r-minimal)
4874 ("r-ggplot2" ,r-ggplot2)
4875 ("coreutils" ,coreutils)))
4876 (home-page "http://sanger-pathogens.github.io/Roary")
4877 (synopsis "High speed stand-alone pan genome pipeline")
4879 "Roary is a high speed stand alone pan genome pipeline, which takes
4880 annotated assemblies in GFF3 format (produced by the Prokka program) and
4881 calculates the pan genome. Using a standard desktop PC, it can analyse
4882 datasets with thousands of samples, without compromising the quality of the
4883 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4884 single processor. Roary is not intended for metagenomics or for comparing
4885 extremely diverse sets of genomes.")
4886 (license license:gpl3)))
4888 (define-public raxml
4896 (url "https://github.com/stamatak/standard-RAxML.git")
4897 (commit (string-append "v" version))))
4898 (file-name (git-file-name name version))
4901 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4902 (build-system gnu-build-system)
4904 `(#:tests? #f ; There are no tests.
4905 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4906 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4908 (modify-phases %standard-phases
4911 (lambda* (#:key outputs #:allow-other-keys)
4912 (let* ((out (assoc-ref outputs "out"))
4913 (bin (string-append out "/bin"))
4914 (executable "raxmlHPC-HYBRID"))
4915 (install-file executable bin)
4916 (symlink (string-append bin "/" executable) "raxml"))
4919 `(("openmpi" ,openmpi)))
4920 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4921 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4923 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4925 ;; The source includes x86 specific code
4926 (supported-systems '("x86_64-linux" "i686-linux"))
4927 (license license:gpl2+)))
4937 (url "https://github.com/deweylab/RSEM.git")
4938 (commit (string-append "v" version))))
4940 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4941 (file-name (git-file-name name version))
4942 (modules '((guix build utils)))
4945 ;; remove bundled copy of boost and samtools
4946 (delete-file-recursively "boost")
4947 (delete-file-recursively "samtools-1.3")
4949 (build-system gnu-build-system)
4951 `(#:tests? #f ;no "check" target
4953 (list (string-append "BOOST="
4954 (assoc-ref %build-inputs "boost")
4956 (string-append "SAMHEADERS="
4957 (assoc-ref %build-inputs "htslib")
4958 "/include/htslib/sam.h")
4959 (string-append "SAMLIBS="
4960 (assoc-ref %build-inputs "htslib")
4963 (modify-phases %standard-phases
4964 ;; No "configure" script.
4965 ;; Do not build bundled samtools library.
4968 (substitute* "Makefile"
4969 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4970 (("^\\$\\(SAMLIBS\\).*") ""))
4973 (lambda* (#:key outputs #:allow-other-keys)
4974 (let* ((out (string-append (assoc-ref outputs "out")))
4975 (bin (string-append out "/bin/"))
4976 (perl (string-append out "/lib/perl5/site_perl")))
4979 (for-each (lambda (file)
4980 (install-file file bin))
4981 (find-files "." "rsem-.*"))
4982 (install-file "rsem_perl_utils.pm" perl))
4984 (add-after 'install 'wrap-program
4985 (lambda* (#:key outputs #:allow-other-keys)
4986 (let ((out (assoc-ref outputs "out")))
4987 (for-each (lambda (prog)
4988 (wrap-program (string-append out "/bin/" prog)
4989 `("PERL5LIB" ":" prefix
4990 (,(string-append out "/lib/perl5/site_perl")))))
4991 '("rsem-calculate-expression"
4993 "rsem-generate-data-matrix"
4994 "rsem-generate-ngvector"
4995 "rsem-plot-transcript-wiggles"
4996 "rsem-prepare-reference"
4998 "rsem-run-prsem-testing-procedure")))
5002 ("r-minimal" ,r-minimal)
5004 ("htslib" ,htslib-1.3)
5006 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5007 (synopsis "Estimate gene expression levels from RNA-Seq data")
5009 "RSEM is a software package for estimating gene and isoform expression
5010 levels from RNA-Seq data. The RSEM package provides a user-friendly
5011 interface, supports threads for parallel computation of the EM algorithm,
5012 single-end and paired-end read data, quality scores, variable-length reads and
5013 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5014 interval estimates for expression levels. For visualization, it can generate
5015 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5016 (license license:gpl3+)))
5018 (define-public rseqc
5026 (string-append "mirror://sourceforge/rseqc/"
5027 "RSeQC-" version ".tar.gz"))
5029 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5030 (modules '((guix build utils)))
5033 ;; remove bundled copy of pysam
5034 (delete-file-recursively "lib/pysam")
5035 (substitute* "setup.py"
5036 ;; remove dependency on outdated "distribute" module
5037 (("^from distribute_setup import use_setuptools") "")
5038 (("^use_setuptools\\(\\)") "")
5039 ;; do not use bundled copy of pysam
5040 (("^have_pysam = False") "have_pysam = True"))
5042 (build-system python-build-system)
5043 (arguments `(#:python ,python-2))
5045 `(("python-cython" ,python2-cython)
5046 ("python-pysam" ,python2-pysam)
5047 ("python-numpy" ,python2-numpy)
5050 `(("python-nose" ,python2-nose)))
5051 (home-page "http://rseqc.sourceforge.net/")
5052 (synopsis "RNA-seq quality control package")
5054 "RSeQC provides a number of modules that can comprehensively evaluate
5055 high throughput sequence data, especially RNA-seq data. Some basic modules
5056 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5057 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5058 distribution, coverage uniformity, strand specificity, etc.")
5059 (license license:gpl3+)))
5062 ;; There are no release tarballs. According to the installation
5063 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5064 ;; stable release is identified by this changeset ID.
5065 (let ((changeset "2329130")
5069 (version (string-append "0-" revision "." changeset))
5073 (url "https://bitbucket.org/libsleipnir/sleipnir")
5074 (changeset changeset)))
5075 (file-name (string-append name "-" version "-checkout"))
5078 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5079 (build-system gnu-build-system)
5081 `(#:modules ((srfi srfi-1)
5082 (guix build gnu-build-system)
5085 (let ((dirs '("SeekMiner"
5091 (modify-phases %standard-phases
5094 (substitute* "gen_tools_am"
5095 (("/usr/bin/env.*") (which "perl")))
5096 (invoke "bash" "gen_auto")
5098 (add-after 'build 'build-additional-tools
5099 (lambda* (#:key make-flags #:allow-other-keys)
5100 (for-each (lambda (dir)
5101 (with-directory-excursion (string-append "tools/" dir)
5102 (apply invoke "make" make-flags)))
5105 (add-after 'install 'install-additional-tools
5106 (lambda* (#:key make-flags #:allow-other-keys)
5107 (for-each (lambda (dir)
5108 (with-directory-excursion (string-append "tools/" dir)
5109 (apply invoke `("make" ,@make-flags "install"))))
5116 ("readline" ,readline)
5117 ("gengetopt" ,gengetopt)
5118 ("log4cpp" ,log4cpp)))
5120 `(("autoconf" ,autoconf)
5121 ("automake" ,automake)
5123 (home-page "http://seek.princeton.edu")
5124 (synopsis "Gene co-expression search engine")
5126 "SEEK is a computational gene co-expression search engine. SEEK provides
5127 biologists with a way to navigate the massive human expression compendium that
5128 now contains thousands of expression datasets. SEEK returns a robust ranking
5129 of co-expressed genes in the biological area of interest defined by the user's
5130 query genes. It also prioritizes thousands of expression datasets according
5131 to the user's query of interest.")
5132 (license license:cc-by3.0))))
5134 (define-public samtools
5142 (string-append "mirror://sourceforge/samtools/samtools/"
5143 version "/samtools-" version ".tar.bz2"))
5146 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5147 (modules '((guix build utils)))
5149 ;; Delete bundled htslib.
5150 (delete-file-recursively "htslib-1.9")
5152 (build-system gnu-build-system)
5154 `(#:modules ((ice-9 ftw)
5156 (guix build gnu-build-system)
5158 #:configure-flags (list "--with-ncurses")
5160 (modify-phases %standard-phases
5161 (add-after 'unpack 'patch-tests
5163 (substitute* "test/test.pl"
5164 ;; The test script calls out to /bin/bash
5165 (("/bin/bash") (which "bash")))
5167 (add-after 'install 'install-library
5168 (lambda* (#:key outputs #:allow-other-keys)
5169 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5170 (install-file "libbam.a" lib)
5172 (add-after 'install 'install-headers
5173 (lambda* (#:key outputs #:allow-other-keys)
5174 (let ((include (string-append (assoc-ref outputs "out")
5175 "/include/samtools/")))
5176 (for-each (lambda (file)
5177 (install-file file include))
5178 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5180 (native-inputs `(("pkg-config" ,pkg-config)))
5182 `(("htslib" ,htslib)
5183 ("ncurses" ,ncurses)
5187 (home-page "http://samtools.sourceforge.net")
5188 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5190 "Samtools implements various utilities for post-processing nucleotide
5191 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5192 variant calling (in conjunction with bcftools), and a simple alignment
5194 (license license:expat)))
5196 (define-public samtools-0.1
5197 ;; This is the most recent version of the 0.1 line of samtools. The input
5198 ;; and output formats differ greatly from that used and produced by samtools
5199 ;; 1.x and is still used in many bioinformatics pipelines.
5200 (package (inherit samtools)
5206 (string-append "mirror://sourceforge/samtools/samtools/"
5207 version "/samtools-" version ".tar.bz2"))
5209 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5211 `(#:tests? #f ;no "check" target
5213 (list "LIBCURSES=-lncurses")
5214 ,@(substitute-keyword-arguments (package-arguments samtools)
5216 `(modify-phases ,phases
5218 (lambda* (#:key outputs #:allow-other-keys)
5219 (let ((bin (string-append
5220 (assoc-ref outputs "out") "/bin")))
5222 (install-file "samtools" bin)
5224 (delete 'patch-tests)
5225 (delete 'configure))))))))
5227 (define-public mosaik
5228 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5233 ;; There are no release tarballs nor tags.
5236 (url "https://github.com/wanpinglee/MOSAIK.git")
5238 (file-name (string-append name "-" version))
5241 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5242 (build-system gnu-build-system)
5244 `(#:tests? #f ; no tests
5245 #:make-flags (list "CC=gcc")
5247 (modify-phases %standard-phases
5249 (lambda _ (chdir "src") #t))
5251 (lambda* (#:key outputs #:allow-other-keys)
5252 (let ((bin (string-append (assoc-ref outputs "out")
5255 (copy-recursively "../bin" bin)
5259 ("zlib:static" ,zlib "static")
5261 (supported-systems '("x86_64-linux"))
5262 (home-page "https://github.com/wanpinglee/MOSAIK")
5263 (synopsis "Map nucleotide sequence reads to reference genomes")
5265 "MOSAIK is a program for mapping second and third-generation sequencing
5266 reads to a reference genome. MOSAIK can align reads generated by all the
5267 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5268 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5269 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5270 ;; code released into the public domain:
5271 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5272 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5273 (license (list license:gpl2+ license:public-domain)))))
5275 (define-public ngs-sdk
5282 (url "https://github.com/ncbi/ngs.git")
5284 (file-name (git-file-name name version))
5287 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5288 (build-system gnu-build-system)
5290 `(#:parallel-build? #f ; not supported
5291 #:tests? #f ; no "check" target
5293 (modify-phases %standard-phases
5295 (lambda* (#:key outputs #:allow-other-keys)
5296 (let ((out (assoc-ref outputs "out")))
5297 ;; Allow 'konfigure.perl' to find 'package.prl'.
5299 (string-append ".:" (getenv "PERL5LIB")))
5301 ;; The 'configure' script doesn't recognize things like
5302 ;; '--enable-fast-install'.
5303 (invoke "./configure"
5304 (string-append "--build-prefix=" (getcwd) "/build")
5305 (string-append "--prefix=" out))
5307 (add-after 'unpack 'enter-dir
5308 (lambda _ (chdir "ngs-sdk") #t)))))
5309 (native-inputs `(("perl" ,perl)))
5310 ;; According to the test
5311 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5312 ;; in ngs-sdk/setup/konfigure.perl
5313 (supported-systems '("i686-linux" "x86_64-linux"))
5314 (home-page "https://github.com/ncbi/ngs")
5315 (synopsis "API for accessing Next Generation Sequencing data")
5317 "NGS is a domain-specific API for accessing reads, alignments and pileups
5318 produced from Next Generation Sequencing. The API itself is independent from
5319 any particular back-end implementation, and supports use of multiple back-ends
5321 (license license:public-domain)))
5323 (define-public java-ngs
5324 (package (inherit ngs-sdk)
5327 `(,@(substitute-keyword-arguments
5328 `(#:modules ((guix build gnu-build-system)
5332 ,@(package-arguments ngs-sdk))
5334 `(modify-phases ,phases
5335 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5337 `(("jdk" ,icedtea "jdk")
5338 ("ngs-sdk" ,ngs-sdk)))
5339 (synopsis "Java bindings for NGS SDK")))
5341 (define-public ncbi-vdb
5348 (url "https://github.com/ncbi/ncbi-vdb.git")
5350 (file-name (git-file-name name version))
5353 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5354 (build-system gnu-build-system)
5356 `(#:parallel-build? #f ; not supported
5357 #:tests? #f ; no "check" target
5359 (modify-phases %standard-phases
5360 (add-after 'unpack 'make-files-writable
5361 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5362 (add-before 'configure 'set-perl-search-path
5364 ;; Work around "dotless @INC" build failure.
5366 (string-append (getcwd) "/setup:"
5367 (getenv "PERL5LIB")))
5370 (lambda* (#:key inputs outputs #:allow-other-keys)
5371 (let ((out (assoc-ref outputs "out")))
5372 ;; Override include path for libmagic
5373 (substitute* "setup/package.prl"
5374 (("name => 'magic', Include => '/usr/include'")
5375 (string-append "name=> 'magic', Include => '"
5376 (assoc-ref inputs "libmagic")
5379 ;; Install kdf5 library (needed by sra-tools)
5380 (substitute* "build/Makefile.install"
5381 (("LIBRARIES_TO_INSTALL =")
5382 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5384 (substitute* "build/Makefile.env"
5385 (("CFLAGS =" prefix)
5386 (string-append prefix "-msse2 ")))
5388 ;; Override search path for ngs-java
5389 (substitute* "setup/package.prl"
5390 (("/usr/local/ngs/ngs-java")
5391 (assoc-ref inputs "java-ngs")))
5393 ;; The 'configure' script doesn't recognize things like
5394 ;; '--enable-fast-install'.
5395 (invoke "./configure"
5396 (string-append "--build-prefix=" (getcwd) "/build")
5397 (string-append "--prefix=" (assoc-ref outputs "out"))
5398 (string-append "--debug")
5399 (string-append "--with-xml2-prefix="
5400 (assoc-ref inputs "libxml2"))
5401 (string-append "--with-ngs-sdk-prefix="
5402 (assoc-ref inputs "ngs-sdk"))
5403 (string-append "--with-hdf5-prefix="
5404 (assoc-ref inputs "hdf5")))
5406 (add-after 'install 'install-interfaces
5407 (lambda* (#:key outputs #:allow-other-keys)
5408 ;; Install interface libraries. On i686 the interface libraries
5409 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5410 ;; architecture name ("i386") instead of the target system prefix
5412 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5413 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5414 ,(system->linux-architecture
5415 (or (%current-target-system)
5418 (string-append (assoc-ref outputs "out")
5420 ;; Install interface headers
5421 (copy-recursively "interfaces"
5422 (string-append (assoc-ref outputs "out")
5425 ;; These files are needed by sra-tools.
5426 (add-after 'install 'install-configuration-files
5427 (lambda* (#:key outputs #:allow-other-keys)
5428 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5430 (install-file "libs/kfg/default.kfg" target)
5431 (install-file "libs/kfg/certs.kfg" target))
5434 `(("libxml2" ,libxml2)
5435 ("ngs-sdk" ,ngs-sdk)
5436 ("java-ngs" ,java-ngs)
5439 (native-inputs `(("perl" ,perl)))
5440 ;; NCBI-VDB requires SSE capability.
5441 (supported-systems '("i686-linux" "x86_64-linux"))
5442 (home-page "https://github.com/ncbi/ncbi-vdb")
5443 (synopsis "Database engine for genetic information")
5445 "The NCBI-VDB library implements a highly compressed columnar data
5446 warehousing engine that is most often used to store genetic information.
5447 Databases are stored in a portable image within the file system, and can be
5448 accessed/downloaded on demand across HTTP.")
5449 (license license:public-domain)))
5451 (define-public plink
5459 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5460 version "-src.zip"))
5462 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5463 (patches (search-patches "plink-1.07-unclobber-i.patch"
5464 "plink-endian-detection.patch"))))
5465 (build-system gnu-build-system)
5467 '(#:tests? #f ;no "check" target
5468 #:make-flags (list (string-append "LIB_LAPACK="
5469 (assoc-ref %build-inputs "lapack")
5470 "/lib/liblapack.so")
5473 ;; disable phoning home
5476 (modify-phases %standard-phases
5477 ;; no "configure" script
5480 (lambda* (#:key outputs #:allow-other-keys)
5481 (let ((bin (string-append (assoc-ref outputs "out")
5483 (install-file "plink" bin)
5487 ("lapack" ,lapack)))
5489 `(("unzip" ,unzip)))
5490 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5491 (synopsis "Whole genome association analysis toolset")
5493 "PLINK is a whole genome association analysis toolset, designed to
5494 perform a range of basic, large-scale analyses in a computationally efficient
5495 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5496 so there is no support for steps prior to this (e.g. study design and
5497 planning, generating genotype or CNV calls from raw data). Through
5498 integration with gPLINK and Haploview, there is some support for the
5499 subsequent visualization, annotation and storage of results.")
5500 ;; Code is released under GPLv2, except for fisher.h, which is under
5502 (license (list license:gpl2 license:lgpl2.1+))))
5504 (define-public plink-ng
5505 (package (inherit plink)
5512 (url "https://github.com/chrchang/plink-ng.git")
5513 (commit (string-append "v" version))))
5514 (file-name (git-file-name name version))
5516 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5517 (build-system gnu-build-system)
5519 '(#:tests? #f ;no "check" target
5520 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5521 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5523 "-f" "Makefile.std")
5525 (modify-phases %standard-phases
5526 (add-after 'unpack 'chdir
5527 (lambda _ (chdir "1.9") #t))
5528 (delete 'configure) ; no "configure" script
5530 (lambda* (#:key outputs #:allow-other-keys)
5531 (let ((bin (string-append (assoc-ref outputs "out")
5533 (install-file "plink" bin)
5538 ("openblas" ,openblas)))
5539 (home-page "https://www.cog-genomics.org/plink/")
5540 (license license:gpl3+)))
5542 (define-public smithlab-cpp
5543 (let ((revision "1")
5544 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5546 (name "smithlab-cpp")
5547 (version (string-append "0." revision "." (string-take commit 7)))
5551 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5553 (file-name (string-append name "-" version "-checkout"))
5556 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5557 (build-system gnu-build-system)
5559 `(#:modules ((guix build gnu-build-system)
5562 #:tests? #f ;no "check" target
5564 (modify-phases %standard-phases
5565 (add-after 'unpack 'use-samtools-headers
5567 (substitute* '("SAM.cpp"
5569 (("sam.h") "samtools/sam.h"))
5572 (lambda* (#:key outputs #:allow-other-keys)
5573 (let* ((out (assoc-ref outputs "out"))
5574 (lib (string-append out "/lib"))
5575 (include (string-append out "/include/smithlab-cpp")))
5578 (for-each (cut install-file <> lib)
5579 (find-files "." "\\.o$"))
5580 (for-each (cut install-file <> include)
5581 (find-files "." "\\.hpp$")))
5583 (delete 'configure))))
5585 `(("samtools" ,samtools-0.1)
5587 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5588 (synopsis "C++ helper library for functions used in Smith lab projects")
5590 "Smithlab CPP is a C++ library that includes functions used in many of
5591 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5592 structures, classes for genomic regions, mapped sequencing reads, etc.")
5593 (license license:gpl3+))))
5595 (define-public preseq
5601 (uri (string-append "https://github.com/smithlabcode/preseq/"
5602 "releases/download/v" version
5603 "/preseq_v" version ".tar.bz2"))
5605 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5606 (modules '((guix build utils)))
5608 ;; Remove bundled samtools.
5609 (delete-file-recursively "samtools")
5611 (build-system gnu-build-system)
5613 `(#:tests? #f ;no "check" target
5615 (modify-phases %standard-phases
5616 (delete 'configure))
5618 (list (string-append "PREFIX="
5619 (assoc-ref %outputs "out"))
5620 (string-append "LIBBAM="
5621 (assoc-ref %build-inputs "samtools")
5623 (string-append "SMITHLAB_CPP="
5624 (assoc-ref %build-inputs "smithlab-cpp")
5627 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5630 ("samtools" ,samtools-0.1)
5631 ("smithlab-cpp" ,smithlab-cpp)
5633 (home-page "http://smithlabresearch.org/software/preseq/")
5634 (synopsis "Program for analyzing library complexity")
5636 "The preseq package is aimed at predicting and estimating the complexity
5637 of a genomic sequencing library, equivalent to predicting and estimating the
5638 number of redundant reads from a given sequencing depth and how many will be
5639 expected from additional sequencing using an initial sequencing experiment.
5640 The estimates can then be used to examine the utility of further sequencing,
5641 optimize the sequencing depth, or to screen multiple libraries to avoid low
5642 complexity samples.")
5643 (license license:gpl3+)))
5645 (define-public python-screed
5647 (name "python-screed")
5652 (uri (pypi-uri "screed" version))
5655 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5656 (build-system python-build-system)
5659 (modify-phases %standard-phases
5660 ;; Tests must be run after installation, as the "screed" command does
5661 ;; not exist right after building.
5663 (add-after 'install 'check
5664 (lambda* (#:key inputs outputs #:allow-other-keys)
5665 (let ((out (assoc-ref outputs "out")))
5666 (setenv "PYTHONPATH"
5667 (string-append out "/lib/python"
5668 (string-take (string-take-right
5669 (assoc-ref inputs "python")
5672 (getenv "PYTHONPATH")))
5673 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5674 (invoke "python" "setup.py" "test")
5677 `(("python-pytest" ,python-pytest)
5678 ("python-pytest-cov" ,python-pytest-cov)
5679 ("python-pytest-runner" ,python-pytest-runner)))
5681 `(("python-bz2file" ,python-bz2file)))
5682 (home-page "https://github.com/dib-lab/screed/")
5683 (synopsis "Short read sequence database utilities")
5684 (description "Screed parses FASTA and FASTQ files and generates databases.
5685 Values such as sequence name, sequence description, sequence quality and the
5686 sequence itself can be retrieved from these databases.")
5687 (license license:bsd-3)))
5689 (define-public python2-screed
5690 (package-with-python2 python-screed))
5692 (define-public sra-tools
5700 (url "https://github.com/ncbi/sra-tools.git")
5702 (file-name (git-file-name name version))
5705 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5706 (build-system gnu-build-system)
5708 `(#:parallel-build? #f ; not supported
5709 #:tests? #f ; no "check" target
5711 (list (string-append "DEFAULT_CRT="
5712 (assoc-ref %build-inputs "ncbi-vdb")
5714 (string-append "DEFAULT_KFG="
5715 (assoc-ref %build-inputs "ncbi-vdb")
5717 (string-append "VDB_LIBDIR="
5718 (assoc-ref %build-inputs "ncbi-vdb")
5719 ,(if (string-prefix? "x86_64"
5720 (or (%current-target-system)
5725 (modify-phases %standard-phases
5726 (add-before 'configure 'set-perl-search-path
5728 ;; Work around "dotless @INC" build failure.
5730 (string-append (getcwd) "/setup:"
5731 (getenv "PERL5LIB")))
5734 (lambda* (#:key inputs outputs #:allow-other-keys)
5735 ;; The build system expects a directory containing the sources and
5736 ;; raw build output of ncbi-vdb, including files that are not
5737 ;; installed. Since we are building against an installed version of
5738 ;; ncbi-vdb, the following modifications are needed.
5739 (substitute* "setup/konfigure.perl"
5740 ;; Make the configure script look for the "ilib" directory of
5741 ;; "ncbi-vdb" without first checking for the existence of a
5742 ;; matching library in its "lib" directory.
5743 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5744 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5745 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5746 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5747 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5750 (substitute* "tools/copycat/Makefile"
5751 (("smagic-static") "lmagic"))
5753 ;; The 'configure' script doesn't recognize things like
5754 ;; '--enable-fast-install'.
5755 (invoke "./configure"
5756 (string-append "--build-prefix=" (getcwd) "/build")
5757 (string-append "--prefix=" (assoc-ref outputs "out"))
5758 (string-append "--debug")
5759 (string-append "--with-fuse-prefix="
5760 (assoc-ref inputs "fuse"))
5761 (string-append "--with-magic-prefix="
5762 (assoc-ref inputs "libmagic"))
5763 ;; TODO: building with libxml2 fails with linker errors
5764 ;; (string-append "--with-xml2-prefix="
5765 ;; (assoc-ref inputs "libxml2"))
5766 (string-append "--with-ncbi-vdb-sources="
5767 (assoc-ref inputs "ncbi-vdb"))
5768 (string-append "--with-ncbi-vdb-build="
5769 (assoc-ref inputs "ncbi-vdb"))
5770 (string-append "--with-ngs-sdk-prefix="
5771 (assoc-ref inputs "ngs-sdk"))
5772 (string-append "--with-hdf5-prefix="
5773 (assoc-ref inputs "hdf5")))
5775 (native-inputs `(("perl" ,perl)))
5777 `(("ngs-sdk" ,ngs-sdk)
5778 ("ncbi-vdb" ,ncbi-vdb)
5783 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5784 (synopsis "Tools and libraries for reading and writing sequencing data")
5786 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5787 reading of sequencing files from the Sequence Read Archive (SRA) database and
5788 writing files into the .sra format.")
5789 (license license:public-domain)))
5791 (define-public seqan
5797 (uri (string-append "https://github.com/seqan/seqan/releases/"
5798 "download/seqan-v" version
5799 "/seqan-library-" version ".tar.xz"))
5802 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5803 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5804 ;; makes sense to split the outputs.
5805 (outputs '("out" "doc"))
5806 (build-system trivial-build-system)
5808 `(#:modules ((guix build utils))
5811 (use-modules (guix build utils))
5812 (let ((tar (assoc-ref %build-inputs "tar"))
5813 (xz (assoc-ref %build-inputs "xz"))
5814 (out (assoc-ref %outputs "out"))
5815 (doc (assoc-ref %outputs "doc")))
5816 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5817 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5818 (chdir (string-append "seqan-library-" ,version))
5819 (copy-recursively "include" (string-append out "/include"))
5820 (copy-recursively "share" (string-append doc "/share"))
5823 `(("source" ,source)
5826 (home-page "http://www.seqan.de")
5827 (synopsis "Library for nucleotide sequence analysis")
5829 "SeqAn is a C++ library of efficient algorithms and data structures for
5830 the analysis of sequences with the focus on biological data. It contains
5831 algorithms and data structures for string representation and their
5832 manipulation, online and indexed string search, efficient I/O of
5833 bioinformatics file formats, sequence alignment, and more.")
5834 (license license:bsd-3)))
5836 (define-public seqan-1
5837 (package (inherit seqan)
5842 (uri (string-append "http://packages.seqan.de/seqan-library/"
5843 "seqan-library-" version ".tar.bz2"))
5846 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5847 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5848 ;; makes sense to split the outputs.
5849 (outputs '("out" "doc"))
5850 (build-system trivial-build-system)
5852 `(#:modules ((guix build utils))
5855 (use-modules (guix build utils))
5856 (let ((tar (assoc-ref %build-inputs "tar"))
5857 (bzip (assoc-ref %build-inputs "bzip2"))
5858 (out (assoc-ref %outputs "out"))
5859 (doc (assoc-ref %outputs "doc")))
5860 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5861 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5862 (chdir (string-append "seqan-library-" ,version))
5863 (copy-recursively "include" (string-append out "/include"))
5864 (copy-recursively "share" (string-append doc "/share"))
5867 `(("source" ,source)
5869 ("bzip2" ,bzip2)))))
5871 (define-public seqmagick
5878 (uri (pypi-uri "seqmagick" version))
5881 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5882 (build-system python-build-system)
5884 `(("python-biopython" ,python-biopython)))
5886 `(("python-nose" ,python-nose)))
5887 (home-page "https://github.com/fhcrc/seqmagick")
5888 (synopsis "Tools for converting and modifying sequence files")
5890 "Bioinformaticians often have to convert sequence files between formats
5891 and do little manipulations on them, and it's not worth writing scripts for
5892 that. Seqmagick is a utility to expose the file format conversion in
5893 BioPython in a convenient way. Instead of having a big mess of scripts, there
5894 is one that takes arguments.")
5895 (license license:gpl3)))
5897 (define-public seqtk
5904 (url "https://github.com/lh3/seqtk.git")
5905 (commit (string-append "v" version))))
5906 (file-name (git-file-name name version))
5909 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5910 (build-system gnu-build-system)
5913 (modify-phases %standard-phases
5916 ;; There are no tests, so we just run a sanity check.
5917 (lambda _ (invoke "./seqtk" "seq") #t))
5919 (lambda* (#:key outputs #:allow-other-keys)
5920 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5921 (install-file "seqtk" bin)
5925 (home-page "https://github.com/lh3/seqtk")
5926 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5928 "Seqtk is a fast and lightweight tool for processing sequences in the
5929 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5930 optionally compressed by gzip.")
5931 (license license:expat)))
5933 (define-public snap-aligner
5935 (name "snap-aligner")
5936 (version "1.0beta.18")
5940 (url "https://github.com/amplab/snap.git")
5941 (commit (string-append "v" version))))
5942 (file-name (git-file-name name version))
5945 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5946 (build-system gnu-build-system)
5949 (modify-phases %standard-phases
5951 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5953 (lambda* (#:key outputs #:allow-other-keys)
5954 (let* ((out (assoc-ref outputs "out"))
5955 (bin (string-append out "/bin")))
5956 (install-file "snap-aligner" bin)
5957 (install-file "SNAPCommand" bin)
5961 (home-page "http://snap.cs.berkeley.edu/")
5962 (synopsis "Short read DNA sequence aligner")
5964 "SNAP is a fast and accurate aligner for short DNA reads. It is
5965 optimized for modern read lengths of 100 bases or higher, and takes advantage
5966 of these reads to align data quickly through a hash-based indexing scheme.")
5967 ;; 32-bit systems are not supported by the unpatched code.
5968 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5969 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5970 ;; systems without a lot of memory cannot make good use of this program.
5971 (supported-systems '("x86_64-linux"))
5972 (license license:asl2.0)))
5974 (define-public sortmerna
5982 (url "https://github.com/biocore/sortmerna.git")
5984 (file-name (git-file-name name version))
5987 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5988 (build-system gnu-build-system)
5989 (outputs '("out" ;for binaries
5990 "db")) ;for sequence databases
5993 (modify-phases %standard-phases
5995 (lambda* (#:key outputs #:allow-other-keys)
5996 (let* ((out (assoc-ref outputs "out"))
5997 (bin (string-append out "/bin"))
5998 (db (assoc-ref outputs "db"))
6000 (string-append db "/share/sortmerna/rRNA_databases")))
6001 (install-file "sortmerna" bin)
6002 (install-file "indexdb_rna" bin)
6003 (for-each (lambda (file)
6004 (install-file file share))
6005 (find-files "rRNA_databases" ".*fasta"))
6009 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6010 (synopsis "Biological sequence analysis tool for NGS reads")
6012 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6013 and operational taxonomic unit (OTU) picking of next generation
6014 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6015 allows for fast and sensitive analyses of nucleotide sequences. The main
6016 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6017 ;; The source includes x86 specific code
6018 (supported-systems '("x86_64-linux" "i686-linux"))
6019 (license license:lgpl3)))
6028 (url "https://github.com/alexdobin/STAR.git")
6030 (file-name (string-append name "-" version "-checkout"))
6033 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
6034 (modules '((guix build utils)))
6037 (substitute* "source/Makefile"
6039 ;; Remove pre-built binaries and bundled htslib sources.
6040 (delete-file-recursively "bin/MacOSX_x86_64")
6041 (delete-file-recursively "bin/Linux_x86_64")
6042 (delete-file-recursively "bin/Linux_x86_64_static")
6043 (delete-file-recursively "source/htslib")
6045 (build-system gnu-build-system)
6047 '(#:tests? #f ;no check target
6048 #:make-flags '("STAR")
6050 (modify-phases %standard-phases
6051 (add-after 'unpack 'enter-source-dir
6052 (lambda _ (chdir "source") #t))
6053 (add-after 'enter-source-dir 'make-reproducible
6055 (substitute* "Makefile"
6056 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6057 (string-append pre "Built with Guix" post)))
6059 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6061 (substitute* "Makefile"
6062 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6064 (substitute* '("BAMfunctions.cpp"
6069 "bamRemoveDuplicates.cpp")
6070 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6071 (string-append "#include <" header ">")))
6072 (substitute* "IncludeDefine.h"
6073 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6074 (string-append "<" header ">")))
6077 (lambda* (#:key outputs #:allow-other-keys)
6078 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6079 (install-file "STAR" bin))
6081 (delete 'configure))))
6085 `(("htslib" ,htslib)
6087 (home-page "https://github.com/alexdobin/STAR")
6088 (synopsis "Universal RNA-seq aligner")
6090 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6091 based on a previously undescribed RNA-seq alignment algorithm that uses
6092 sequential maximum mappable seed search in uncompressed suffix arrays followed
6093 by seed clustering and stitching procedure. In addition to unbiased de novo
6094 detection of canonical junctions, STAR can discover non-canonical splices and
6095 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6097 ;; Only 64-bit systems are supported according to the README.
6098 (supported-systems '("x86_64-linux" "mips64el-linux"))
6099 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6100 (license license:gpl3+)))
6102 (define-public subread
6108 (uri (string-append "mirror://sourceforge/subread/subread-"
6109 version "/subread-" version "-source.tar.gz"))
6112 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6113 (build-system gnu-build-system)
6115 `(#:tests? #f ;no "check" target
6116 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6117 ;; optimizations by default, so we override these flags such that x86_64
6118 ;; flags are only added when the build target is an x86_64 system.
6120 (list (let ((system ,(or (%current-target-system)
6122 (flags '("-ggdb" "-fomit-frame-pointer"
6123 "-ffast-math" "-funroll-loops"
6124 "-fmessage-length=0"
6125 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6127 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6128 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6129 (if (string-prefix? "x86_64" system)
6130 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6131 (string-append "CCFLAGS=" (string-join flags))))
6132 "-f" "Makefile.Linux"
6133 "CC=gcc ${CCFLAGS}")
6135 (modify-phases %standard-phases
6136 (add-after 'unpack 'enter-dir
6137 (lambda _ (chdir "src") #t))
6139 (lambda* (#:key outputs #:allow-other-keys)
6140 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6142 (copy-recursively "../bin" bin))
6144 ;; no "configure" script
6145 (delete 'configure))))
6146 (inputs `(("zlib" ,zlib)))
6147 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6148 (synopsis "Tool kit for processing next-gen sequencing data")
6150 "The subread package contains the following tools: subread aligner, a
6151 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6152 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6153 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6154 against local background noises.")
6155 (license license:gpl3+)))
6157 (define-public stringtie
6163 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6164 "stringtie-" version ".tar.gz"))
6167 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6168 (modules '((guix build utils)))
6171 (delete-file-recursively "samtools-0.1.18")
6173 (build-system gnu-build-system)
6175 `(#:tests? #f ;no test suite
6177 (modify-phases %standard-phases
6178 ;; no configure script
6180 (add-before 'build 'use-system-samtools
6182 (substitute* "Makefile"
6183 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6185 (substitute* '("gclib/GBam.h"
6187 (("#include \"(bam|sam|kstring).h\"" _ header)
6188 (string-append "#include <samtools/" header ".h>")))
6190 (add-after 'unpack 'remove-duplicate-typedef
6192 ;; This typedef conflicts with the typedef in
6193 ;; glibc-2.25/include/bits/types.h
6194 (substitute* "gclib/GThreads.h"
6195 (("typedef long long __intmax_t;") ""))
6198 (lambda* (#:key outputs #:allow-other-keys)
6199 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6200 (install-file "stringtie" bin)
6203 `(("samtools" ,samtools-0.1)
6205 (home-page "http://ccb.jhu.edu/software/stringtie/")
6206 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6208 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6209 alignments into potential transcripts. It uses a novel network flow algorithm
6210 as well as an optional de novo assembly step to assemble and quantitate
6211 full-length transcripts representing multiple splice variants for each gene
6212 locus. Its input can include not only the alignments of raw reads used by
6213 other transcript assemblers, but also alignments of longer sequences that have
6214 been assembled from those reads. To identify differentially expressed genes
6215 between experiments, StringTie's output can be processed either by the
6216 Cuffdiff or Ballgown programs.")
6217 (license license:artistic2.0)))
6219 (define-public taxtastic
6225 (uri (pypi-uri "taxtastic" version))
6228 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6229 (build-system python-build-system)
6231 `(#:python ,python-2
6233 (modify-phases %standard-phases
6235 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6237 `(("python-sqlalchemy" ,python2-sqlalchemy)
6238 ("python-decorator" ,python2-decorator)
6239 ("python-biopython" ,python2-biopython)
6240 ("python-pandas" ,python2-pandas)
6241 ("python-psycopg2" ,python2-psycopg2)
6242 ("python-fastalite" ,python2-fastalite)
6243 ("python-pyyaml" ,python2-pyyaml)
6244 ("python-six" ,python2-six)
6245 ("python-jinja2" ,python2-jinja2)
6246 ("python-dendropy" ,python2-dendropy)))
6247 (home-page "https://github.com/fhcrc/taxtastic")
6248 (synopsis "Tools for taxonomic naming and annotation")
6250 "Taxtastic is software written in python used to build and maintain
6251 reference packages i.e. collections of reference trees, reference alignments,
6252 profiles, and associated taxonomic information.")
6253 (license license:gpl3+)))
6255 (define-public vcftools
6262 "https://github.com/vcftools/vcftools/releases/download/v"
6263 version "/vcftools-" version ".tar.gz"))
6266 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6267 (build-system gnu-build-system)
6269 `(#:tests? #f ; no "check" target
6271 "CFLAGS=-O2" ; override "-m64" flag
6272 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6273 (string-append "MANDIR=" (assoc-ref %outputs "out")
6274 "/share/man/man1"))))
6276 `(("pkg-config" ,pkg-config)))
6280 (home-page "https://vcftools.github.io/")
6281 (synopsis "Tools for working with VCF files")
6283 "VCFtools is a program package designed for working with VCF files, such
6284 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6285 provide easily accessible methods for working with complex genetic variation
6286 data in the form of VCF files.")
6287 ;; The license is declared as LGPLv3 in the README and
6288 ;; at https://vcftools.github.io/license.html
6289 (license license:lgpl3)))
6291 (define-public infernal
6297 (uri (string-append "http://eddylab.org/software/infernal/"
6298 "infernal-" version ".tar.gz"))
6301 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6302 (build-system gnu-build-system)
6304 `(("perl" ,perl))) ; for tests
6305 (home-page "http://eddylab.org/infernal/")
6306 (synopsis "Inference of RNA alignments")
6307 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6308 searching DNA sequence databases for RNA structure and sequence similarities.
6309 It is an implementation of a special case of profile stochastic context-free
6310 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6311 profile, but it scores a combination of sequence consensus and RNA secondary
6312 structure consensus, so in many cases, it is more capable of identifying RNA
6313 homologs that conserve their secondary structure more than their primary
6315 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6316 (supported-systems '("i686-linux" "x86_64-linux"))
6317 (license license:bsd-3)))
6319 (define-public r-centipede
6321 (name "r-centipede")
6325 (uri (string-append "http://download.r-forge.r-project.org/"
6326 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6329 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6330 (build-system r-build-system)
6331 (home-page "http://centipede.uchicago.edu/")
6332 (synopsis "Predict transcription factor binding sites")
6334 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6335 of the genome that are bound by particular transcription factors. It starts
6336 by identifying a set of candidate binding sites, and then aims to classify the
6337 sites according to whether each site is bound or not bound by a transcription
6338 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6339 between two different types of motif instances using as much relevant
6340 information as possible.")
6341 (license (list license:gpl2+ license:gpl3+))))
6343 (define-public r-copynumber
6345 (name "r-copynumber")
6349 (uri (bioconductor-uri "copynumber" version))
6352 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6353 (build-system r-build-system)
6355 `(("r-s4vectors" ,r-s4vectors)
6356 ("r-iranges" ,r-iranges)
6357 ("r-genomicranges" ,r-genomicranges)
6358 ("r-biocgenerics" ,r-biocgenerics)))
6359 (home-page "https://bioconductor.org/packages/copynumber")
6360 (synopsis "Segmentation of single- and multi-track copy number data")
6362 "This package segments single- and multi-track copy number data by a
6363 penalized least squares regression method.")
6364 (license license:artistic2.0)))
6366 (define-public r-geneplotter
6368 (name "r-geneplotter")
6373 (uri (bioconductor-uri "geneplotter" version))
6376 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6377 (build-system r-build-system)
6379 `(("r-annotate" ,r-annotate)
6380 ("r-annotationdbi" ,r-annotationdbi)
6381 ("r-biobase" ,r-biobase)
6382 ("r-biocgenerics" ,r-biocgenerics)
6383 ("r-lattice" ,r-lattice)
6384 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6385 (home-page "https://bioconductor.org/packages/geneplotter")
6386 (synopsis "Graphics functions for genomic data")
6388 "This package provides functions for plotting genomic data.")
6389 (license license:artistic2.0)))
6391 (define-public r-genefilter
6393 (name "r-genefilter")
6398 (uri (bioconductor-uri "genefilter" version))
6401 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6402 (build-system r-build-system)
6404 `(("gfortran" ,gfortran)))
6406 `(("r-annotate" ,r-annotate)
6407 ("r-annotationdbi" ,r-annotationdbi)
6408 ("r-biobase" ,r-biobase)
6409 ("r-s4vectors" ,r-s4vectors)
6410 ("r-survival" ,r-survival)))
6411 (home-page "https://bioconductor.org/packages/genefilter")
6412 (synopsis "Filter genes from high-throughput experiments")
6414 "This package provides basic functions for filtering genes from
6415 high-throughput sequencing experiments.")
6416 (license license:artistic2.0)))
6418 (define-public r-deseq2
6425 (uri (bioconductor-uri "DESeq2" version))
6428 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6429 (properties `((upstream-name . "DESeq2")))
6430 (build-system r-build-system)
6432 `(("r-biobase" ,r-biobase)
6433 ("r-biocgenerics" ,r-biocgenerics)
6434 ("r-biocparallel" ,r-biocparallel)
6435 ("r-genefilter" ,r-genefilter)
6436 ("r-geneplotter" ,r-geneplotter)
6437 ("r-genomicranges" ,r-genomicranges)
6438 ("r-ggplot2" ,r-ggplot2)
6439 ("r-hmisc" ,r-hmisc)
6440 ("r-iranges" ,r-iranges)
6441 ("r-locfit" ,r-locfit)
6443 ("r-rcpparmadillo" ,r-rcpparmadillo)
6444 ("r-s4vectors" ,r-s4vectors)
6445 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6446 (home-page "https://bioconductor.org/packages/DESeq2")
6447 (synopsis "Differential gene expression analysis")
6449 "This package provides functions to estimate variance-mean dependence in
6450 count data from high-throughput nucleotide sequencing assays and test for
6451 differential expression based on a model using the negative binomial
6453 (license license:lgpl3+)))
6455 (define-public r-dexseq
6462 (uri (bioconductor-uri "DEXSeq" version))
6465 "0g5w9bn2nb3m670hkcsnhfvvkza2318z9irlhhwhb3n8rdzlsdym"))))
6466 (properties `((upstream-name . "DEXSeq")))
6467 (build-system r-build-system)
6469 `(("r-annotationdbi" ,r-annotationdbi)
6470 ("r-biobase" ,r-biobase)
6471 ("r-biocgenerics" ,r-biocgenerics)
6472 ("r-biocparallel" ,r-biocparallel)
6473 ("r-biomart" ,r-biomart)
6474 ("r-deseq2" ,r-deseq2)
6475 ("r-genefilter" ,r-genefilter)
6476 ("r-geneplotter" ,r-geneplotter)
6477 ("r-genomicranges" ,r-genomicranges)
6478 ("r-hwriter" ,r-hwriter)
6479 ("r-iranges" ,r-iranges)
6480 ("r-rcolorbrewer" ,r-rcolorbrewer)
6481 ("r-rsamtools" ,r-rsamtools)
6482 ("r-s4vectors" ,r-s4vectors)
6483 ("r-statmod" ,r-statmod)
6484 ("r-stringr" ,r-stringr)
6485 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6486 (home-page "https://bioconductor.org/packages/DEXSeq")
6487 (synopsis "Inference of differential exon usage in RNA-Seq")
6489 "This package is focused on finding differential exon usage using RNA-seq
6490 exon counts between samples with different experimental designs. It provides
6491 functions that allows the user to make the necessary statistical tests based
6492 on a model that uses the negative binomial distribution to estimate the
6493 variance between biological replicates and generalized linear models for
6494 testing. The package also provides functions for the visualization and
6495 exploration of the results.")
6496 (license license:gpl3+)))
6498 (define-public r-annotationforge
6500 (name "r-annotationforge")
6505 (uri (bioconductor-uri "AnnotationForge" version))
6508 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6510 `((upstream-name . "AnnotationForge")))
6511 (build-system r-build-system)
6513 `(("r-annotationdbi" ,r-annotationdbi)
6514 ("r-biobase" ,r-biobase)
6515 ("r-biocgenerics" ,r-biocgenerics)
6517 ("r-rcurl" ,r-rcurl)
6518 ("r-rsqlite" ,r-rsqlite)
6519 ("r-s4vectors" ,r-s4vectors)
6521 (home-page "https://bioconductor.org/packages/AnnotationForge")
6522 (synopsis "Code for building annotation database packages")
6524 "This package provides code for generating Annotation packages and their
6525 databases. Packages produced are intended to be used with AnnotationDbi.")
6526 (license license:artistic2.0)))
6528 (define-public r-rbgl
6535 (uri (bioconductor-uri "RBGL" version))
6538 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6539 (properties `((upstream-name . "RBGL")))
6540 (build-system r-build-system)
6541 (propagated-inputs `(("r-graph" ,r-graph)))
6542 (home-page "https://www.bioconductor.org/packages/RBGL")
6543 (synopsis "Interface to the Boost graph library")
6545 "This package provides a fairly extensive and comprehensive interface to
6546 the graph algorithms contained in the Boost library.")
6547 (license license:artistic2.0)))
6549 (define-public r-gseabase
6556 (uri (bioconductor-uri "GSEABase" version))
6559 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6560 (properties `((upstream-name . "GSEABase")))
6561 (build-system r-build-system)
6563 `(("r-annotate" ,r-annotate)
6564 ("r-annotationdbi" ,r-annotationdbi)
6565 ("r-biobase" ,r-biobase)
6566 ("r-biocgenerics" ,r-biocgenerics)
6567 ("r-graph" ,r-graph)
6569 (home-page "https://bioconductor.org/packages/GSEABase")
6570 (synopsis "Gene set enrichment data structures and methods")
6572 "This package provides classes and methods to support @dfn{Gene Set
6573 Enrichment Analysis} (GSEA).")
6574 (license license:artistic2.0)))
6576 (define-public r-category
6583 (uri (bioconductor-uri "Category" version))
6586 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6587 (properties `((upstream-name . "Category")))
6588 (build-system r-build-system)
6590 `(("r-annotate" ,r-annotate)
6591 ("r-annotationdbi" ,r-annotationdbi)
6592 ("r-biobase" ,r-biobase)
6593 ("r-biocgenerics" ,r-biocgenerics)
6594 ("r-genefilter" ,r-genefilter)
6595 ("r-graph" ,r-graph)
6596 ("r-gseabase" ,r-gseabase)
6597 ("r-matrix" ,r-matrix)
6600 (home-page "https://bioconductor.org/packages/Category")
6601 (synopsis "Category analysis")
6603 "This package provides a collection of tools for performing category
6605 (license license:artistic2.0)))
6607 (define-public r-gostats
6614 (uri (bioconductor-uri "GOstats" version))
6617 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6618 (properties `((upstream-name . "GOstats")))
6619 (build-system r-build-system)
6621 `(("r-annotate" ,r-annotate)
6622 ("r-annotationdbi" ,r-annotationdbi)
6623 ("r-annotationforge" ,r-annotationforge)
6624 ("r-biobase" ,r-biobase)
6625 ("r-category" ,r-category)
6626 ("r-go-db" ,r-go-db)
6627 ("r-graph" ,r-graph)
6628 ("r-rgraphviz" ,r-rgraphviz)
6629 ("r-rbgl" ,r-rbgl)))
6630 (home-page "https://bioconductor.org/packages/GOstats")
6631 (synopsis "Tools for manipulating GO and microarrays")
6633 "This package provides a set of tools for interacting with GO and
6634 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6635 testing and other simple calculations.")
6636 (license license:artistic2.0)))
6638 (define-public r-shortread
6640 (name "r-shortread")
6645 (uri (bioconductor-uri "ShortRead" version))
6648 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6649 (properties `((upstream-name . "ShortRead")))
6650 (build-system r-build-system)
6654 `(("r-biobase" ,r-biobase)
6655 ("r-biocgenerics" ,r-biocgenerics)
6656 ("r-biocparallel" ,r-biocparallel)
6657 ("r-biostrings" ,r-biostrings)
6658 ("r-genomeinfodb" ,r-genomeinfodb)
6659 ("r-genomicalignments" ,r-genomicalignments)
6660 ("r-genomicranges" ,r-genomicranges)
6661 ("r-hwriter" ,r-hwriter)
6662 ("r-iranges" ,r-iranges)
6663 ("r-lattice" ,r-lattice)
6664 ("r-latticeextra" ,r-latticeextra)
6665 ("r-rsamtools" ,r-rsamtools)
6666 ("r-s4vectors" ,r-s4vectors)
6667 ("r-xvector" ,r-xvector)
6668 ("r-zlibbioc" ,r-zlibbioc)))
6669 (home-page "https://bioconductor.org/packages/ShortRead")
6670 (synopsis "FASTQ input and manipulation tools")
6672 "This package implements sampling, iteration, and input of FASTQ files.
6673 It includes functions for filtering and trimming reads, and for generating a
6674 quality assessment report. Data are represented as
6675 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6676 purposes. The package also contains legacy support for early single-end,
6677 ungapped alignment formats.")
6678 (license license:artistic2.0)))
6680 (define-public r-systempiper
6682 (name "r-systempiper")
6687 (uri (bioconductor-uri "systemPipeR" version))
6690 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6691 (properties `((upstream-name . "systemPipeR")))
6692 (build-system r-build-system)
6694 `(("r-annotate" ,r-annotate)
6695 ("r-batchjobs" ,r-batchjobs)
6696 ("r-biocgenerics" ,r-biocgenerics)
6697 ("r-biostrings" ,r-biostrings)
6698 ("r-deseq2" ,r-deseq2)
6699 ("r-edger" ,r-edger)
6700 ("r-genomicfeatures" ,r-genomicfeatures)
6701 ("r-genomicranges" ,r-genomicranges)
6702 ("r-ggplot2" ,r-ggplot2)
6703 ("r-go-db" ,r-go-db)
6704 ("r-gostats" ,r-gostats)
6705 ("r-limma" ,r-limma)
6706 ("r-pheatmap" ,r-pheatmap)
6707 ("r-rjson" ,r-rjson)
6708 ("r-rsamtools" ,r-rsamtools)
6709 ("r-shortread" ,r-shortread)
6710 ("r-summarizedexperiment" ,r-summarizedexperiment)
6711 ("r-variantannotation" ,r-variantannotation)))
6712 (home-page "https://github.com/tgirke/systemPipeR")
6713 (synopsis "Next generation sequencing workflow and reporting environment")
6715 "This R package provides tools for building and running automated
6716 end-to-end analysis workflows for a wide range of @dfn{next generation
6717 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6718 Important features include a uniform workflow interface across different NGS
6719 applications, automated report generation, and support for running both R and
6720 command-line software, such as NGS aligners or peak/variant callers, on local
6721 computers or compute clusters. Efficient handling of complex sample sets and
6722 experimental designs is facilitated by a consistently implemented sample
6723 annotation infrastructure.")
6724 (license license:artistic2.0)))
6726 (define-public r-grohmm
6733 (uri (bioconductor-uri "groHMM" version))
6736 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6737 (properties `((upstream-name . "groHMM")))
6738 (build-system r-build-system)
6740 `(("r-genomeinfodb" ,r-genomeinfodb)
6741 ("r-genomicalignments" ,r-genomicalignments)
6742 ("r-genomicranges" ,r-genomicranges)
6743 ("r-iranges" ,r-iranges)
6745 ("r-rtracklayer" ,r-rtracklayer)
6746 ("r-s4vectors" ,r-s4vectors)))
6747 (home-page "https://github.com/Kraus-Lab/groHMM")
6748 (synopsis "GRO-seq analysis pipeline")
6750 "This package provides a pipeline for the analysis of GRO-seq data.")
6751 (license license:gpl3+)))
6753 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6755 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6759 ;; We cannot use bioconductor-uri here because this tarball is
6760 ;; located under "data/annotation/" instead of "bioc/".
6761 (uri (string-append "https://bioconductor.org/packages/"
6762 "release/data/annotation/src/contrib"
6763 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6767 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6769 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6770 (build-system r-build-system)
6771 ;; As this package provides little more than a very large data file it
6772 ;; doesn't make sense to build substitutes.
6773 (arguments `(#:substitutable? #f))
6775 `(("r-genomicfeatures" ,r-genomicfeatures)))
6777 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6778 (synopsis "Annotation package for human genome in TxDb format")
6780 "This package provides an annotation database of Homo sapiens genome
6781 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6782 track. The database is exposed as a @code{TxDb} object.")
6783 (license license:artistic2.0)))
6785 (define-public r-sparql
6791 (uri (cran-uri "SPARQL" version))
6794 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6795 (properties `((upstream-name . "SPARQL")))
6796 (build-system r-build-system)
6798 `(("r-rcurl" ,r-rcurl)
6800 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6801 (synopsis "SPARQL client for R")
6802 (description "This package provides an interface to use SPARQL to pose
6803 SELECT or UPDATE queries to an end-point.")
6804 ;; The only license indication is found in the DESCRIPTION file,
6805 ;; which states GPL-3. So we cannot assume GPLv3+.
6806 (license license:gpl3)))
6808 (define-public vsearch
6816 (url "https://github.com/torognes/vsearch.git")
6817 (commit (string-append "v" version))))
6818 (file-name (git-file-name name version))
6821 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6822 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6825 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6826 ;; for this in the patch.
6827 (delete-file "src/city.h")
6828 (delete-file "src/citycrc.h")
6829 (delete-file "src/city.cc")
6831 (build-system gnu-build-system)
6835 ("cityhash" ,cityhash)))
6837 `(("autoconf" ,autoconf)
6838 ("automake" ,automake)))
6839 (synopsis "Sequence search tools for metagenomics")
6841 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6842 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6843 masking. The tool takes advantage of parallelism in the form of SIMD
6844 vectorization as well as multiple threads to perform accurate alignments at
6845 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6846 Needleman-Wunsch).")
6847 (home-page "https://github.com/torognes/vsearch")
6848 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6850 (supported-systems '("x86_64-linux"))
6851 ;; Dual licensed; also includes public domain source.
6852 (license (list license:gpl3 license:bsd-2))))
6854 (define-public pardre
6857 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6862 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6866 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6867 (build-system gnu-build-system)
6869 `(#:tests? #f ; no tests included
6871 (modify-phases %standard-phases
6874 (lambda* (#:key outputs #:allow-other-keys)
6875 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6876 (install-file "ParDRe" bin)
6879 `(("openmpi" ,openmpi)
6881 (synopsis "Parallel tool to remove duplicate DNA reads")
6883 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6884 Duplicate reads can be seen as identical or nearly identical sequences with
6885 some mismatches. This tool lets users avoid the analysis of unnecessary
6886 reads, reducing the time of subsequent procedures with the
6887 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6888 in order to exploit the parallel capabilities of multicore clusters. It is
6889 faster than multithreaded counterparts (end of 2015) for the same number of
6890 cores and, thanks to the message-passing technology, it can be executed on
6892 (home-page "https://sourceforge.net/projects/pardre/")
6893 (license license:gpl3+)))
6895 (define-public ruby-bio-kseq
6897 (name "ruby-bio-kseq")
6902 (uri (rubygems-uri "bio-kseq" version))
6905 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6906 (build-system ruby-build-system)
6908 `(#:test-target "spec"))
6910 `(("bundler" ,bundler)
6911 ("ruby-rspec" ,ruby-rspec)
6912 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6915 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6917 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6918 FASTQ parsing code. It provides a fast iterator over sequences and their
6920 (home-page "https://github.com/gusevfe/bio-kseq")
6921 (license license:expat)))
6923 (define-public bio-locus
6930 (uri (rubygems-uri "bio-locus" version))
6933 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6934 (build-system ruby-build-system)
6936 `(("ruby-rspec" ,ruby-rspec)))
6937 (synopsis "Tool for fast querying of genome locations")
6939 "Bio-locus is a tabix-like tool for fast querying of genome
6940 locations. Many file formats in bioinformatics contain records that
6941 start with a chromosome name and a position for a SNP, or a start-end
6942 position for indels. Bio-locus allows users to store this chr+pos or
6943 chr+pos+alt information in a database.")
6944 (home-page "https://github.com/pjotrp/bio-locus")
6945 (license license:expat)))
6947 (define-public bio-blastxmlparser
6949 (name "bio-blastxmlparser")
6953 (uri (rubygems-uri "bio-blastxmlparser" version))
6956 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6957 (build-system ruby-build-system)
6959 `(("ruby-bio-logger" ,ruby-bio-logger)
6960 ("ruby-nokogiri" ,ruby-nokogiri)))
6962 `(("ruby-rspec" ,ruby-rspec)))
6963 (synopsis "Fast big data BLAST XML parser and library")
6965 "Very fast parallel big-data BLAST XML file parser which can be used as
6966 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6967 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6968 (home-page "https://github.com/pjotrp/blastxmlparser")
6969 (license license:expat)))
6971 (define-public bioruby
6978 (uri (rubygems-uri "bio" version))
6981 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
6982 (build-system ruby-build-system)
6984 `(("ruby-libxml" ,ruby-libxml)))
6986 `(("which" ,which))) ; required for test phase
6989 (modify-phases %standard-phases
6990 (add-before 'build 'patch-test-command
6992 (substitute* '("test/functional/bio/test_command.rb")
6993 (("/bin/sh") (which "sh")))
6994 (substitute* '("test/functional/bio/test_command.rb")
6995 (("/bin/ls") (which "ls")))
6996 (substitute* '("test/functional/bio/test_command.rb")
6997 (("which") (which "which")))
6998 (substitute* '("test/functional/bio/test_command.rb",
6999 "test/data/command/echoarg2.sh")
7000 (("/bin/echo") (which "echo")))
7002 (synopsis "Ruby library, shell and utilities for bioinformatics")
7003 (description "BioRuby comes with a comprehensive set of Ruby development
7004 tools and libraries for bioinformatics and molecular biology. BioRuby has
7005 components for sequence analysis, pathway analysis, protein modelling and
7006 phylogenetic analysis; it supports many widely used data formats and provides
7007 easy access to databases, external programs and public web services, including
7008 BLAST, KEGG, GenBank, MEDLINE and GO.")
7009 (home-page "http://bioruby.org/")
7010 ;; Code is released under Ruby license, except for setup
7011 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7012 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7014 (define-public r-acsnminer
7016 (name "r-acsnminer")
7017 (version "0.16.8.25")
7020 (uri (cran-uri "ACSNMineR" version))
7023 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7024 (properties `((upstream-name . "ACSNMineR")))
7025 (build-system r-build-system)
7027 `(("r-ggplot2" ,r-ggplot2)
7028 ("r-gridextra" ,r-gridextra)))
7029 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7030 (synopsis "Gene enrichment analysis")
7032 "This package provides tools to compute and represent gene set enrichment
7033 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7034 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7035 enrichment can be run with hypergeometric test or Fisher exact test, and can
7036 use multiple corrections. Visualization of data can be done either by
7037 barplots or heatmaps.")
7038 (license license:gpl2+)))
7040 (define-public r-biocinstaller
7042 (name "r-biocinstaller")
7046 (uri (bioconductor-uri "BiocInstaller" version))
7049 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7051 `((upstream-name . "BiocInstaller")))
7052 (build-system r-build-system)
7053 (home-page "https://bioconductor.org/packages/BiocInstaller")
7054 (synopsis "Install Bioconductor packages")
7055 (description "This package is used to install and update R packages from
7056 Bioconductor, CRAN, and Github.")
7057 (license license:artistic2.0)))
7059 (define-public r-biocviews
7061 (name "r-biocviews")
7065 (uri (bioconductor-uri "biocViews" version))
7068 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
7070 `((upstream-name . "biocViews")))
7071 (build-system r-build-system)
7073 `(("r-biobase" ,r-biobase)
7074 ("r-graph" ,r-graph)
7076 ("r-rcurl" ,r-rcurl)
7078 ("r-runit" ,r-runit)))
7079 (home-page "https://bioconductor.org/packages/biocViews")
7080 (synopsis "Bioconductor package categorization helper")
7081 (description "The purpose of biocViews is to create HTML pages that
7082 categorize packages in a Bioconductor package repository according to keywords,
7083 also known as views, in a controlled vocabulary.")
7084 (license license:artistic2.0)))
7086 (define-public r-bookdown
7092 (uri (cran-uri "bookdown" version))
7095 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7096 (build-system r-build-system)
7098 `(("r-htmltools" ,r-htmltools)
7099 ("r-knitr" ,r-knitr)
7100 ("r-rmarkdown" ,r-rmarkdown)
7101 ("r-tinytex" ,r-tinytex)
7103 ("r-xfun" ,r-xfun)))
7104 (home-page "https://github.com/rstudio/bookdown")
7105 (synopsis "Authoring books and technical documents with R markdown")
7106 (description "This package provides output formats and utilities for
7107 authoring books and technical documents with R Markdown.")
7108 (license license:gpl3)))
7110 (define-public r-biocstyle
7112 (name "r-biocstyle")
7116 (uri (bioconductor-uri "BiocStyle" version))
7119 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7121 `((upstream-name . "BiocStyle")))
7122 (build-system r-build-system)
7124 `(("r-biocmanager" ,r-biocmanager)
7125 ("r-bookdown" ,r-bookdown)
7126 ("r-knitr" ,r-knitr)
7127 ("r-rmarkdown" ,r-rmarkdown)
7128 ("r-yaml" ,r-yaml)))
7129 (home-page "https://bioconductor.org/packages/BiocStyle")
7130 (synopsis "Bioconductor formatting styles")
7131 (description "This package provides standard formatting styles for
7132 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7134 (license license:artistic2.0)))
7136 (define-public r-bioccheck
7138 (name "r-bioccheck")
7142 (uri (bioconductor-uri "BiocCheck" version))
7145 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7147 `((upstream-name . "BiocCheck")))
7148 (build-system r-build-system)
7151 (modify-phases %standard-phases
7152 ;; This package can be used by calling BiocCheck(<package>) from
7153 ;; within R, or by running R CMD BiocCheck <package>. This phase
7154 ;; makes sure the latter works. For this to work, the BiocCheck
7155 ;; script must be somewhere on the PATH (not the R bin directory).
7156 (add-after 'install 'install-bioccheck-subcommand
7157 (lambda* (#:key outputs #:allow-other-keys)
7158 (let* ((out (assoc-ref outputs "out"))
7159 (dest-dir (string-append out "/bin"))
7161 (string-append out "/site-library/BiocCheck/script/")))
7163 (symlink (string-append script-dir "/checkBadDeps.R")
7164 (string-append dest-dir "/checkBadDeps.R"))
7165 (symlink (string-append script-dir "/BiocCheck")
7166 (string-append dest-dir "/BiocCheck")))
7169 `(("r-codetools" ,r-codetools)
7170 ("r-graph" ,r-graph)
7172 ("r-knitr" ,r-knitr)
7173 ("r-optparse" ,r-optparse)
7174 ("r-biocmanager" ,r-biocmanager)
7175 ("r-biocviews" ,r-biocviews)
7176 ("r-stringdist" ,r-stringdist)))
7177 (home-page "https://bioconductor.org/packages/BiocCheck")
7178 (synopsis "Executes Bioconductor-specific package checks")
7179 (description "This package contains tools to perform additional quality
7180 checks on R packages that are to be submitted to the Bioconductor repository.")
7181 (license license:artistic2.0)))
7183 (define-public r-optparse
7190 (uri (cran-uri "optparse" version))
7193 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7194 (build-system r-build-system)
7196 `(("r-getopt" ,r-getopt)))
7198 "https://github.com/trevorld/optparse")
7199 (synopsis "Command line option parser")
7201 "This package provides a command line parser inspired by Python's
7202 @code{optparse} library to be used with Rscript to write shebang scripts
7203 that accept short and long options.")
7204 (license license:gpl2+)))
7206 (define-public r-dnacopy
7212 (uri (bioconductor-uri "DNAcopy" version))
7215 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7217 `((upstream-name . "DNAcopy")))
7218 (build-system r-build-system)
7220 `(("gfortran" ,gfortran)))
7221 (home-page "https://bioconductor.org/packages/DNAcopy")
7222 (synopsis "Implementation of a circular binary segmentation algorithm")
7223 (description "This package implements the circular binary segmentation (CBS)
7224 algorithm to segment DNA copy number data and identify genomic regions with
7225 abnormal copy number.")
7226 (license license:gpl2+)))
7228 (define-public r-s4vectors
7230 (name "r-s4vectors")
7234 (uri (bioconductor-uri "S4Vectors" version))
7237 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7239 `((upstream-name . "S4Vectors")))
7240 (build-system r-build-system)
7242 `(("r-biocgenerics" ,r-biocgenerics)))
7243 (home-page "https://bioconductor.org/packages/S4Vectors")
7244 (synopsis "S4 implementation of vectors and lists")
7246 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7247 classes and a set of generic functions that extend the semantic of ordinary
7248 vectors and lists in R. Package developers can easily implement vector-like
7249 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7250 In addition, a few low-level concrete subclasses of general interest (e.g.
7251 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7252 S4Vectors package itself.")
7253 (license license:artistic2.0)))
7255 (define-public r-seqinr
7262 (uri (cran-uri "seqinr" version))
7265 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7266 (build-system r-build-system)
7268 `(("r-ade4" ,r-ade4)
7269 ("r-segmented" ,r-segmented)))
7272 (home-page "http://seqinr.r-forge.r-project.org/")
7273 (synopsis "Biological sequences retrieval and analysis")
7275 "This package provides tools for exploratory data analysis and data
7276 visualization of biological sequence (DNA and protein) data. It also includes
7277 utilities for sequence data management under the ACNUC system.")
7278 (license license:gpl2+)))
7280 (define-public r-iranges
7286 (uri (bioconductor-uri "IRanges" version))
7289 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7291 `((upstream-name . "IRanges")))
7292 (build-system r-build-system)
7294 `(("r-biocgenerics" ,r-biocgenerics)
7295 ("r-s4vectors" ,r-s4vectors)))
7296 (home-page "https://bioconductor.org/packages/IRanges")
7297 (synopsis "Infrastructure for manipulating intervals on sequences")
7299 "This package provides efficient low-level and highly reusable S4 classes
7300 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7301 generally, data that can be organized sequentially (formally defined as
7302 @code{Vector} objects), as well as views on these @code{Vector} objects.
7303 Efficient list-like classes are also provided for storing big collections of
7304 instances of the basic classes. All classes in the package use consistent
7305 naming and share the same rich and consistent \"Vector API\" as much as
7307 (license license:artistic2.0)))
7309 (define-public r-genomeinfodbdata
7311 (name "r-genomeinfodbdata")
7315 ;; We cannot use bioconductor-uri here because this tarball is
7316 ;; located under "data/annotation/" instead of "bioc/".
7317 (uri (string-append "https://bioconductor.org/packages/release/"
7318 "data/annotation/src/contrib/GenomeInfoDbData_"
7322 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7324 `((upstream-name . "GenomeInfoDbData")))
7325 (build-system r-build-system)
7326 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7327 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7328 (description "This package contains data for mapping between NCBI taxonomy
7329 ID and species. It is used by functions in the GenomeInfoDb package.")
7330 (license license:artistic2.0)))
7332 (define-public r-genomeinfodb
7334 (name "r-genomeinfodb")
7338 (uri (bioconductor-uri "GenomeInfoDb" version))
7341 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7343 `((upstream-name . "GenomeInfoDb")))
7344 (build-system r-build-system)
7346 `(("r-biocgenerics" ,r-biocgenerics)
7347 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7348 ("r-iranges" ,r-iranges)
7349 ("r-rcurl" ,r-rcurl)
7350 ("r-s4vectors" ,r-s4vectors)))
7351 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7352 (synopsis "Utilities for manipulating chromosome identifiers")
7354 "This package contains data and functions that define and allow
7355 translation between different chromosome sequence naming conventions (e.g.,
7356 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7357 names in their natural, rather than lexicographic, order.")
7358 (license license:artistic2.0)))
7360 (define-public r-edger
7366 (uri (bioconductor-uri "edgeR" version))
7369 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7370 (properties `((upstream-name . "edgeR")))
7371 (build-system r-build-system)
7373 `(("r-limma" ,r-limma)
7374 ("r-locfit" ,r-locfit)
7376 ("r-statmod" ,r-statmod))) ;for estimateDisp
7377 (home-page "http://bioinf.wehi.edu.au/edgeR")
7378 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7379 (description "This package can do differential expression analysis of
7380 RNA-seq expression profiles with biological replication. It implements a range
7381 of statistical methodology based on the negative binomial distributions,
7382 including empirical Bayes estimation, exact tests, generalized linear models
7383 and quasi-likelihood tests. It be applied to differential signal analysis of
7384 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7386 (license license:gpl2+)))
7388 (define-public r-variantannotation
7390 (name "r-variantannotation")
7394 (uri (bioconductor-uri "VariantAnnotation" version))
7397 "0gf36lr9xy3zmcc4rxs5bi2ccrrc7b6wqp6p3cvnclgif4i0l66k"))))
7399 `((upstream-name . "VariantAnnotation")))
7403 `(("r-annotationdbi" ,r-annotationdbi)
7404 ("r-biobase" ,r-biobase)
7405 ("r-biocgenerics" ,r-biocgenerics)
7406 ("r-biostrings" ,r-biostrings)
7407 ("r-bsgenome" ,r-bsgenome)
7409 ("r-genomeinfodb" ,r-genomeinfodb)
7410 ("r-genomicfeatures" ,r-genomicfeatures)
7411 ("r-genomicranges" ,r-genomicranges)
7412 ("r-iranges" ,r-iranges)
7413 ("r-summarizedexperiment" ,r-summarizedexperiment)
7414 ("r-rsamtools" ,r-rsamtools)
7415 ("r-rtracklayer" ,r-rtracklayer)
7416 ("r-s4vectors" ,r-s4vectors)
7417 ("r-xvector" ,r-xvector)
7418 ("r-zlibbioc" ,r-zlibbioc)))
7419 (build-system r-build-system)
7420 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7421 (synopsis "Package for annotation of genetic variants")
7422 (description "This R package can annotate variants, compute amino acid
7423 coding changes and predict coding outcomes.")
7424 (license license:artistic2.0)))
7426 (define-public r-limma
7432 (uri (bioconductor-uri "limma" version))
7435 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7436 (build-system r-build-system)
7437 (home-page "http://bioinf.wehi.edu.au/limma")
7438 (synopsis "Package for linear models for microarray and RNA-seq data")
7439 (description "This package can be used for the analysis of gene expression
7440 studies, especially the use of linear models for analysing designed experiments
7441 and the assessment of differential expression. The analysis methods apply to
7442 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7443 (license license:gpl2+)))
7445 (define-public r-xvector
7451 (uri (bioconductor-uri "XVector" version))
7454 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7456 `((upstream-name . "XVector")))
7457 (build-system r-build-system)
7460 (modify-phases %standard-phases
7461 (add-after 'unpack 'use-system-zlib
7463 (substitute* "DESCRIPTION"
7464 (("zlibbioc, ") ""))
7465 (substitute* "NAMESPACE"
7466 (("import\\(zlibbioc\\)") ""))
7471 `(("r-biocgenerics" ,r-biocgenerics)
7472 ("r-iranges" ,r-iranges)
7473 ("r-s4vectors" ,r-s4vectors)))
7474 (home-page "https://bioconductor.org/packages/XVector")
7475 (synopsis "Representation and manpulation of external sequences")
7477 "This package provides memory efficient S4 classes for storing sequences
7478 \"externally\" (behind an R external pointer, or on disk).")
7479 (license license:artistic2.0)))
7481 (define-public r-genomicranges
7483 (name "r-genomicranges")
7487 (uri (bioconductor-uri "GenomicRanges" version))
7490 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7492 `((upstream-name . "GenomicRanges")))
7493 (build-system r-build-system)
7495 `(("r-biocgenerics" ,r-biocgenerics)
7496 ("r-genomeinfodb" ,r-genomeinfodb)
7497 ("r-iranges" ,r-iranges)
7498 ("r-s4vectors" ,r-s4vectors)
7499 ("r-xvector" ,r-xvector)))
7500 (home-page "https://bioconductor.org/packages/GenomicRanges")
7501 (synopsis "Representation and manipulation of genomic intervals")
7503 "This package provides tools to efficiently represent and manipulate
7504 genomic annotations and alignments is playing a central role when it comes to
7505 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7506 GenomicRanges package defines general purpose containers for storing and
7507 manipulating genomic intervals and variables defined along a genome.")
7508 (license license:artistic2.0)))
7510 (define-public r-biobase
7516 (uri (bioconductor-uri "Biobase" version))
7519 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7521 `((upstream-name . "Biobase")))
7522 (build-system r-build-system)
7524 `(("r-biocgenerics" ,r-biocgenerics)))
7525 (home-page "https://bioconductor.org/packages/Biobase")
7526 (synopsis "Base functions for Bioconductor")
7528 "This package provides functions that are needed by many other packages
7529 on Bioconductor or which replace R functions.")
7530 (license license:artistic2.0)))
7532 (define-public r-annotationdbi
7534 (name "r-annotationdbi")
7538 (uri (bioconductor-uri "AnnotationDbi" version))
7541 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7543 `((upstream-name . "AnnotationDbi")))
7544 (build-system r-build-system)
7546 `(("r-biobase" ,r-biobase)
7547 ("r-biocgenerics" ,r-biocgenerics)
7549 ("r-iranges" ,r-iranges)
7550 ("r-rsqlite" ,r-rsqlite)
7551 ("r-s4vectors" ,r-s4vectors)))
7552 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7553 (synopsis "Annotation database interface")
7555 "This package provides user interface and database connection code for
7556 annotation data packages using SQLite data storage.")
7557 (license license:artistic2.0)))
7559 (define-public r-biomart
7565 (uri (bioconductor-uri "biomaRt" version))
7568 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7570 `((upstream-name . "biomaRt")))
7571 (build-system r-build-system)
7573 `(("r-annotationdbi" ,r-annotationdbi)
7575 ("r-progress" ,r-progress)
7576 ("r-rcurl" ,r-rcurl)
7577 ("r-stringr" ,r-stringr)
7579 (home-page "https://bioconductor.org/packages/biomaRt")
7580 (synopsis "Interface to BioMart databases")
7582 "biomaRt provides an interface to a growing collection of databases
7583 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7584 package enables retrieval of large amounts of data in a uniform way without
7585 the need to know the underlying database schemas or write complex SQL queries.
7586 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7587 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7588 users direct access to a diverse set of data and enable a wide range of
7589 powerful online queries from gene annotation to database mining.")
7590 (license license:artistic2.0)))
7592 (define-public r-biocparallel
7594 (name "r-biocparallel")
7598 (uri (bioconductor-uri "BiocParallel" version))
7601 "1164dk0fajb2vrkfpcjs11055qf1cs4vvbnq0aqdaaf2p4lyx41l"))))
7603 `((upstream-name . "BiocParallel")))
7604 (build-system r-build-system)
7606 `(("r-futile-logger" ,r-futile-logger)
7609 (home-page "https://bioconductor.org/packages/BiocParallel")
7610 (synopsis "Bioconductor facilities for parallel evaluation")
7612 "This package provides modified versions and novel implementation of
7613 functions for parallel evaluation, tailored to use with Bioconductor
7615 (license (list license:gpl2+ license:gpl3+))))
7617 (define-public r-biostrings
7619 (name "r-biostrings")
7623 (uri (bioconductor-uri "Biostrings" version))
7626 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7628 `((upstream-name . "Biostrings")))
7629 (build-system r-build-system)
7631 `(("r-biocgenerics" ,r-biocgenerics)
7632 ("r-iranges" ,r-iranges)
7633 ("r-s4vectors" ,r-s4vectors)
7634 ("r-xvector" ,r-xvector)))
7635 (home-page "https://bioconductor.org/packages/Biostrings")
7636 (synopsis "String objects and algorithms for biological sequences")
7638 "This package provides memory efficient string containers, string
7639 matching algorithms, and other utilities, for fast manipulation of large
7640 biological sequences or sets of sequences.")
7641 (license license:artistic2.0)))
7643 (define-public r-rsamtools
7645 (name "r-rsamtools")
7649 (uri (bioconductor-uri "Rsamtools" version))
7652 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7654 `((upstream-name . "Rsamtools")))
7655 (build-system r-build-system)
7658 (modify-phases %standard-phases
7659 (add-after 'unpack 'use-system-zlib
7661 (substitute* "DESCRIPTION"
7662 (("zlibbioc, ") ""))
7663 (substitute* "NAMESPACE"
7664 (("import\\(zlibbioc\\)") ""))
7669 `(("r-biocgenerics" ,r-biocgenerics)
7670 ("r-biocparallel" ,r-biocparallel)
7671 ("r-biostrings" ,r-biostrings)
7672 ("r-bitops" ,r-bitops)
7673 ("r-genomeinfodb" ,r-genomeinfodb)
7674 ("r-genomicranges" ,r-genomicranges)
7675 ("r-iranges" ,r-iranges)
7676 ("r-s4vectors" ,r-s4vectors)
7677 ("r-xvector" ,r-xvector)))
7678 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7679 (synopsis "Interface to samtools, bcftools, and tabix")
7681 "This package provides an interface to the 'samtools', 'bcftools', and
7682 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7683 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7685 (license license:expat)))
7687 (define-public r-delayedarray
7689 (name "r-delayedarray")
7693 (uri (bioconductor-uri "DelayedArray" version))
7696 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7698 `((upstream-name . "DelayedArray")))
7699 (build-system r-build-system)
7701 `(("r-biocgenerics" ,r-biocgenerics)
7702 ("r-biocparallel" ,r-biocparallel)
7703 ("r-s4vectors" ,r-s4vectors)
7704 ("r-iranges" ,r-iranges)
7705 ("r-matrixstats" ,r-matrixstats)))
7706 (home-page "https://bioconductor.org/packages/DelayedArray")
7707 (synopsis "Delayed operations on array-like objects")
7709 "Wrapping an array-like object (typically an on-disk object) in a
7710 @code{DelayedArray} object allows one to perform common array operations on it
7711 without loading the object in memory. In order to reduce memory usage and
7712 optimize performance, operations on the object are either delayed or executed
7713 using a block processing mechanism. Note that this also works on in-memory
7714 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7715 @code{Matrix} objects, and ordinary arrays and data frames.")
7716 (license license:artistic2.0)))
7718 (define-public r-summarizedexperiment
7720 (name "r-summarizedexperiment")
7724 (uri (bioconductor-uri "SummarizedExperiment" version))
7727 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7729 `((upstream-name . "SummarizedExperiment")))
7730 (build-system r-build-system)
7732 `(("r-biobase" ,r-biobase)
7733 ("r-biocgenerics" ,r-biocgenerics)
7734 ("r-delayedarray" ,r-delayedarray)
7735 ("r-genomeinfodb" ,r-genomeinfodb)
7736 ("r-genomicranges" ,r-genomicranges)
7737 ("r-iranges" ,r-iranges)
7738 ("r-matrix" ,r-matrix)
7739 ("r-s4vectors" ,r-s4vectors)))
7740 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7741 (synopsis "Container for representing genomic ranges by sample")
7743 "The SummarizedExperiment container contains one or more assays, each
7744 represented by a matrix-like object of numeric or other mode. The rows
7745 typically represent genomic ranges of interest and the columns represent
7747 (license license:artistic2.0)))
7749 (define-public r-genomicalignments
7751 (name "r-genomicalignments")
7755 (uri (bioconductor-uri "GenomicAlignments" version))
7758 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7760 `((upstream-name . "GenomicAlignments")))
7761 (build-system r-build-system)
7763 `(("r-biocgenerics" ,r-biocgenerics)
7764 ("r-biocparallel" ,r-biocparallel)
7765 ("r-biostrings" ,r-biostrings)
7766 ("r-genomeinfodb" ,r-genomeinfodb)
7767 ("r-genomicranges" ,r-genomicranges)
7768 ("r-iranges" ,r-iranges)
7769 ("r-rsamtools" ,r-rsamtools)
7770 ("r-s4vectors" ,r-s4vectors)
7771 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7772 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7773 (synopsis "Representation and manipulation of short genomic alignments")
7775 "This package provides efficient containers for storing and manipulating
7776 short genomic alignments (typically obtained by aligning short reads to a
7777 reference genome). This includes read counting, computing the coverage,
7778 junction detection, and working with the nucleotide content of the
7780 (license license:artistic2.0)))
7782 (define-public r-rtracklayer
7784 (name "r-rtracklayer")
7788 (uri (bioconductor-uri "rtracklayer" version))
7791 "1ycmcxvgvszvjv75hlmg0i6pq8i7r8720vgmfayb905s9l6j82x6"))))
7792 (build-system r-build-system)
7795 (modify-phases %standard-phases
7796 (add-after 'unpack 'use-system-zlib
7798 (substitute* "DESCRIPTION"
7799 ((" zlibbioc,") ""))
7800 (substitute* "NAMESPACE"
7801 (("import\\(zlibbioc\\)") ""))
7804 `(("pkg-config" ,pkg-config)))
7808 `(("r-biocgenerics" ,r-biocgenerics)
7809 ("r-biostrings" ,r-biostrings)
7810 ("r-genomeinfodb" ,r-genomeinfodb)
7811 ("r-genomicalignments" ,r-genomicalignments)
7812 ("r-genomicranges" ,r-genomicranges)
7813 ("r-iranges" ,r-iranges)
7814 ("r-rcurl" ,r-rcurl)
7815 ("r-rsamtools" ,r-rsamtools)
7816 ("r-s4vectors" ,r-s4vectors)
7818 ("r-xvector" ,r-xvector)))
7819 (home-page "https://bioconductor.org/packages/rtracklayer")
7820 (synopsis "R interface to genome browsers and their annotation tracks")
7822 "rtracklayer is an extensible framework for interacting with multiple
7823 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7824 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7825 built-in). The user may export/import tracks to/from the supported browsers,
7826 as well as query and modify the browser state, such as the current viewport.")
7827 (license license:artistic2.0)))
7829 (define-public r-genomicfeatures
7831 (name "r-genomicfeatures")
7835 (uri (bioconductor-uri "GenomicFeatures" version))
7838 "0slq6hv5bmc3bgrl824jzmr6db3fvaj6b7ihwmdn76pgqqbq2fq6"))))
7840 `((upstream-name . "GenomicFeatures")))
7841 (build-system r-build-system)
7843 `(("r-annotationdbi" ,r-annotationdbi)
7844 ("r-biobase" ,r-biobase)
7845 ("r-biocgenerics" ,r-biocgenerics)
7846 ("r-biomart" ,r-biomart)
7847 ("r-biostrings" ,r-biostrings)
7849 ("r-genomeinfodb" ,r-genomeinfodb)
7850 ("r-genomicranges" ,r-genomicranges)
7851 ("r-iranges" ,r-iranges)
7852 ("r-rcurl" ,r-rcurl)
7853 ("r-rsqlite" ,r-rsqlite)
7854 ("r-rtracklayer" ,r-rtracklayer)
7855 ("r-s4vectors" ,r-s4vectors)
7856 ("r-xvector" ,r-xvector)))
7857 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7858 (synopsis "Tools for working with transcript centric annotations")
7860 "This package provides a set of tools and methods for making and
7861 manipulating transcript centric annotations. With these tools the user can
7862 easily download the genomic locations of the transcripts, exons and cds of a
7863 given organism, from either the UCSC Genome Browser or a BioMart
7864 database (more sources will be supported in the future). This information is
7865 then stored in a local database that keeps track of the relationship between
7866 transcripts, exons, cds and genes. Flexible methods are provided for
7867 extracting the desired features in a convenient format.")
7868 (license license:artistic2.0)))
7870 (define-public r-go-db
7876 (uri (string-append "https://www.bioconductor.org/packages/"
7877 "release/data/annotation/src/contrib/GO.db_"
7881 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7883 `((upstream-name . "GO.db")))
7884 (build-system r-build-system)
7886 `(("r-annotationdbi" ,r-annotationdbi)))
7887 (home-page "https://bioconductor.org/packages/GO.db")
7888 (synopsis "Annotation maps describing the entire Gene Ontology")
7890 "The purpose of this GO.db annotation package is to provide detailed
7891 information about the latest version of the Gene Ontologies.")
7892 (license license:artistic2.0)))
7894 (define-public r-topgo
7900 (uri (bioconductor-uri "topGO" version))
7903 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7905 `((upstream-name . "topGO")))
7906 (build-system r-build-system)
7908 `(("r-annotationdbi" ,r-annotationdbi)
7910 ("r-biobase" ,r-biobase)
7911 ("r-biocgenerics" ,r-biocgenerics)
7912 ("r-go-db" ,r-go-db)
7913 ("r-graph" ,r-graph)
7914 ("r-lattice" ,r-lattice)
7915 ("r-matrixstats" ,r-matrixstats)
7916 ("r-sparsem" ,r-sparsem)))
7917 (home-page "https://bioconductor.org/packages/topGO")
7918 (synopsis "Enrichment analysis for gene ontology")
7920 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7921 terms while accounting for the topology of the GO graph. Different test
7922 statistics and different methods for eliminating local similarities and
7923 dependencies between GO terms can be implemented and applied.")
7924 ;; Any version of the LGPL applies.
7925 (license license:lgpl2.1+)))
7927 (define-public r-bsgenome
7933 (uri (bioconductor-uri "BSgenome" version))
7936 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7938 `((upstream-name . "BSgenome")))
7939 (build-system r-build-system)
7941 `(("r-biocgenerics" ,r-biocgenerics)
7942 ("r-biostrings" ,r-biostrings)
7943 ("r-genomeinfodb" ,r-genomeinfodb)
7944 ("r-genomicranges" ,r-genomicranges)
7945 ("r-iranges" ,r-iranges)
7946 ("r-rsamtools" ,r-rsamtools)
7947 ("r-rtracklayer" ,r-rtracklayer)
7948 ("r-s4vectors" ,r-s4vectors)
7949 ("r-xvector" ,r-xvector)))
7950 (home-page "https://bioconductor.org/packages/BSgenome")
7951 (synopsis "Infrastructure for Biostrings-based genome data packages")
7953 "This package provides infrastructure shared by all Biostrings-based
7954 genome data packages and support for efficient SNP representation.")
7955 (license license:artistic2.0)))
7957 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7959 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7963 ;; We cannot use bioconductor-uri here because this tarball is
7964 ;; located under "data/annotation/" instead of "bioc/".
7965 (uri (string-append "https://www.bioconductor.org/packages/"
7966 "release/data/annotation/src/contrib/"
7967 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7971 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7973 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7974 (build-system r-build-system)
7975 ;; As this package provides little more than a very large data file it
7976 ;; doesn't make sense to build substitutes.
7977 (arguments `(#:substitutable? #f))
7979 `(("r-bsgenome" ,r-bsgenome)))
7981 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7982 (synopsis "Full genome sequences for Homo sapiens")
7984 "This package provides full genome sequences for Homo sapiens from
7985 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7986 (license license:artistic2.0)))
7988 (define-public r-impute
7994 (uri (bioconductor-uri "impute" version))
7997 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
7999 `(("gfortran" ,gfortran)))
8000 (build-system r-build-system)
8001 (home-page "https://bioconductor.org/packages/impute")
8002 (synopsis "Imputation for microarray data")
8004 "This package provides a function to impute missing gene expression
8005 microarray data, using nearest neighbor averaging.")
8006 (license license:gpl2+)))
8008 (define-public r-seqpattern
8010 (name "r-seqpattern")
8014 (uri (bioconductor-uri "seqPattern" version))
8017 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8019 `((upstream-name . "seqPattern")))
8020 (build-system r-build-system)
8022 `(("r-biostrings" ,r-biostrings)
8023 ("r-genomicranges" ,r-genomicranges)
8024 ("r-iranges" ,r-iranges)
8025 ("r-kernsmooth" ,r-kernsmooth)
8026 ("r-plotrix" ,r-plotrix)))
8027 (home-page "https://bioconductor.org/packages/seqPattern")
8028 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8030 "This package provides tools to visualize oligonucleotide patterns and
8031 sequence motif occurrences across a large set of sequences centred at a common
8032 reference point and sorted by a user defined feature.")
8033 (license license:gpl3+)))
8035 (define-public r-genomation
8037 (name "r-genomation")
8041 (uri (bioconductor-uri "genomation" version))
8044 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8045 (build-system r-build-system)
8047 `(("r-biostrings" ,r-biostrings)
8048 ("r-bsgenome" ,r-bsgenome)
8049 ("r-data-table" ,r-data-table)
8050 ("r-genomeinfodb" ,r-genomeinfodb)
8051 ("r-genomicalignments" ,r-genomicalignments)
8052 ("r-genomicranges" ,r-genomicranges)
8053 ("r-ggplot2" ,r-ggplot2)
8054 ("r-gridbase" ,r-gridbase)
8055 ("r-impute" ,r-impute)
8056 ("r-iranges" ,r-iranges)
8057 ("r-matrixstats" ,r-matrixstats)
8058 ("r-plotrix" ,r-plotrix)
8061 ("r-readr" ,r-readr)
8062 ("r-reshape2" ,r-reshape2)
8063 ("r-rsamtools" ,r-rsamtools)
8064 ("r-rtracklayer" ,r-rtracklayer)
8065 ("r-runit" ,r-runit)
8066 ("r-s4vectors" ,r-s4vectors)
8067 ("r-seqpattern" ,r-seqpattern)))
8068 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8069 (synopsis "Summary, annotation and visualization of genomic data")
8071 "This package provides a package for summary and annotation of genomic
8072 intervals. Users can visualize and quantify genomic intervals over
8073 pre-defined functional regions, such as promoters, exons, introns, etc. The
8074 genomic intervals represent regions with a defined chromosome position, which
8075 may be associated with a score, such as aligned reads from HT-seq experiments,
8076 TF binding sites, methylation scores, etc. The package can use any tabular
8077 genomic feature data as long as it has minimal information on the locations of
8078 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8079 (license license:artistic2.0)))
8081 (define-public r-genomationdata
8083 (name "r-genomationdata")
8087 ;; We cannot use bioconductor-uri here because this tarball is
8088 ;; located under "data/annotation/" instead of "bioc/".
8089 (uri (string-append "https://bioconductor.org/packages/"
8090 "release/data/experiment/src/contrib/"
8091 "genomationData_" version ".tar.gz"))
8094 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8095 (build-system r-build-system)
8096 ;; As this package provides little more than large data files, it doesn't
8097 ;; make sense to build substitutes.
8098 (arguments `(#:substitutable? #f))
8100 `(("r-knitr" ,r-knitr)))
8101 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8102 (synopsis "Experimental data for use with the genomation package")
8104 "This package contains experimental genetic data for use with the
8105 genomation package. Included are Chip Seq, Methylation and Cage data,
8106 downloaded from Encode.")
8107 (license license:gpl3+)))
8109 (define-public r-org-hs-eg-db
8111 (name "r-org-hs-eg-db")
8115 ;; We cannot use bioconductor-uri here because this tarball is
8116 ;; located under "data/annotation/" instead of "bioc/".
8117 (uri (string-append "https://www.bioconductor.org/packages/"
8118 "release/data/annotation/src/contrib/"
8119 "org.Hs.eg.db_" version ".tar.gz"))
8122 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
8124 `((upstream-name . "org.Hs.eg.db")))
8125 (build-system r-build-system)
8127 `(("r-annotationdbi" ,r-annotationdbi)))
8128 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8129 (synopsis "Genome wide annotation for Human")
8131 "This package contains genome-wide annotations for Human, primarily based
8132 on mapping using Entrez Gene identifiers.")
8133 (license license:artistic2.0)))
8135 (define-public r-org-ce-eg-db
8137 (name "r-org-ce-eg-db")
8141 ;; We cannot use bioconductor-uri here because this tarball is
8142 ;; located under "data/annotation/" instead of "bioc/".
8143 (uri (string-append "https://www.bioconductor.org/packages/"
8144 "release/data/annotation/src/contrib/"
8145 "org.Ce.eg.db_" version ".tar.gz"))
8148 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8150 `((upstream-name . "org.Ce.eg.db")))
8151 (build-system r-build-system)
8153 `(("r-annotationdbi" ,r-annotationdbi)))
8154 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8155 (synopsis "Genome wide annotation for Worm")
8157 "This package provides mappings from Entrez gene identifiers to various
8158 annotations for the genome of the model worm Caenorhabditis elegans.")
8159 (license license:artistic2.0)))
8161 (define-public r-org-dm-eg-db
8163 (name "r-org-dm-eg-db")
8167 ;; We cannot use bioconductor-uri here because this tarball is
8168 ;; located under "data/annotation/" instead of "bioc/".
8169 (uri (string-append "https://www.bioconductor.org/packages/"
8170 "release/data/annotation/src/contrib/"
8171 "org.Dm.eg.db_" version ".tar.gz"))
8174 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8176 `((upstream-name . "org.Dm.eg.db")))
8177 (build-system r-build-system)
8179 `(("r-annotationdbi" ,r-annotationdbi)))
8180 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8181 (synopsis "Genome wide annotation for Fly")
8183 "This package provides mappings from Entrez gene identifiers to various
8184 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8185 (license license:artistic2.0)))
8187 (define-public r-org-mm-eg-db
8189 (name "r-org-mm-eg-db")
8193 ;; We cannot use bioconductor-uri here because this tarball is
8194 ;; located under "data/annotation/" instead of "bioc/".
8195 (uri (string-append "https://www.bioconductor.org/packages/"
8196 "release/data/annotation/src/contrib/"
8197 "org.Mm.eg.db_" version ".tar.gz"))
8200 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8202 `((upstream-name . "org.Mm.eg.db")))
8203 (build-system r-build-system)
8205 `(("r-annotationdbi" ,r-annotationdbi)))
8206 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8207 (synopsis "Genome wide annotation for Mouse")
8209 "This package provides mappings from Entrez gene identifiers to various
8210 annotations for the genome of the model mouse Mus musculus.")
8211 (license license:artistic2.0)))
8213 (define-public r-seqlogo
8220 (uri (bioconductor-uri "seqLogo" version))
8223 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8224 (properties `((upstream-name . "seqLogo")))
8225 (build-system r-build-system)
8226 (home-page "https://bioconductor.org/packages/seqLogo")
8227 (synopsis "Sequence logos for DNA sequence alignments")
8229 "seqLogo takes the position weight matrix of a DNA sequence motif and
8230 plots the corresponding sequence logo as introduced by Schneider and
8232 (license license:lgpl2.0+)))
8234 (define-public r-bsgenome-hsapiens-ucsc-hg19
8236 (name "r-bsgenome-hsapiens-ucsc-hg19")
8240 ;; We cannot use bioconductor-uri here because this tarball is
8241 ;; located under "data/annotation/" instead of "bioc/".
8242 (uri (string-append "https://www.bioconductor.org/packages/"
8243 "release/data/annotation/src/contrib/"
8244 "BSgenome.Hsapiens.UCSC.hg19_"
8248 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8250 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8251 (build-system r-build-system)
8252 ;; As this package provides little more than a very large data file it
8253 ;; doesn't make sense to build substitutes.
8254 (arguments `(#:substitutable? #f))
8256 `(("r-bsgenome" ,r-bsgenome)))
8258 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8259 (synopsis "Full genome sequences for Homo sapiens")
8261 "This package provides full genome sequences for Homo sapiens as provided
8262 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8263 (license license:artistic2.0)))
8265 (define-public r-bsgenome-mmusculus-ucsc-mm9
8267 (name "r-bsgenome-mmusculus-ucsc-mm9")
8271 ;; We cannot use bioconductor-uri here because this tarball is
8272 ;; located under "data/annotation/" instead of "bioc/".
8273 (uri (string-append "https://www.bioconductor.org/packages/"
8274 "release/data/annotation/src/contrib/"
8275 "BSgenome.Mmusculus.UCSC.mm9_"
8279 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8281 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8282 (build-system r-build-system)
8283 ;; As this package provides little more than a very large data file it
8284 ;; doesn't make sense to build substitutes.
8285 (arguments `(#:substitutable? #f))
8287 `(("r-bsgenome" ,r-bsgenome)))
8289 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8290 (synopsis "Full genome sequences for Mouse")
8292 "This package provides full genome sequences for Mus musculus (Mouse) as
8293 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8294 (license license:artistic2.0)))
8296 (define-public r-bsgenome-mmusculus-ucsc-mm10
8298 (name "r-bsgenome-mmusculus-ucsc-mm10")
8302 ;; We cannot use bioconductor-uri here because this tarball is
8303 ;; located under "data/annotation/" instead of "bioc/".
8304 (uri (string-append "https://www.bioconductor.org/packages/"
8305 "release/data/annotation/src/contrib/"
8306 "BSgenome.Mmusculus.UCSC.mm10_"
8310 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8312 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8313 (build-system r-build-system)
8314 ;; As this package provides little more than a very large data file it
8315 ;; doesn't make sense to build substitutes.
8316 (arguments `(#:substitutable? #f))
8318 `(("r-bsgenome" ,r-bsgenome)))
8320 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8321 (synopsis "Full genome sequences for Mouse")
8323 "This package provides full genome sequences for Mus
8324 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8325 in Biostrings objects.")
8326 (license license:artistic2.0)))
8328 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8330 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8334 ;; We cannot use bioconductor-uri here because this tarball is
8335 ;; located under "data/annotation/" instead of "bioc/".
8336 (uri (string-append "https://www.bioconductor.org/packages/"
8337 "release/data/annotation/src/contrib/"
8338 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8342 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8344 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8345 (build-system r-build-system)
8346 ;; As this package provides little more than a very large data file it
8347 ;; doesn't make sense to build substitutes.
8348 (arguments `(#:substitutable? #f))
8350 `(("r-bsgenome" ,r-bsgenome)
8351 ("r-genomicfeatures" ,r-genomicfeatures)
8352 ("r-annotationdbi" ,r-annotationdbi)))
8354 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8355 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8357 "This package loads a TxDb object, which is an R interface to
8358 prefabricated databases contained in this package. This package provides
8359 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8360 based on the knownGene track.")
8361 (license license:artistic2.0)))
8363 (define-public r-bsgenome-celegans-ucsc-ce6
8365 (name "r-bsgenome-celegans-ucsc-ce6")
8369 ;; We cannot use bioconductor-uri here because this tarball is
8370 ;; located under "data/annotation/" instead of "bioc/".
8371 (uri (string-append "https://www.bioconductor.org/packages/"
8372 "release/data/annotation/src/contrib/"
8373 "BSgenome.Celegans.UCSC.ce6_"
8377 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8379 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8380 (build-system r-build-system)
8381 ;; As this package provides little more than a very large data file it
8382 ;; doesn't make sense to build substitutes.
8383 (arguments `(#:substitutable? #f))
8385 `(("r-bsgenome" ,r-bsgenome)))
8387 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8388 (synopsis "Full genome sequences for Worm")
8390 "This package provides full genome sequences for Caenorhabditis
8391 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8393 (license license:artistic2.0)))
8395 (define-public r-bsgenome-celegans-ucsc-ce10
8397 (name "r-bsgenome-celegans-ucsc-ce10")
8401 ;; We cannot use bioconductor-uri here because this tarball is
8402 ;; located under "data/annotation/" instead of "bioc/".
8403 (uri (string-append "https://www.bioconductor.org/packages/"
8404 "release/data/annotation/src/contrib/"
8405 "BSgenome.Celegans.UCSC.ce10_"
8409 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8411 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8412 (build-system r-build-system)
8413 ;; As this package provides little more than a very large data file it
8414 ;; doesn't make sense to build substitutes.
8415 (arguments `(#:substitutable? #f))
8417 `(("r-bsgenome" ,r-bsgenome)))
8419 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8420 (synopsis "Full genome sequences for Worm")
8422 "This package provides full genome sequences for Caenorhabditis
8423 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8425 (license license:artistic2.0)))
8427 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8429 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8433 ;; We cannot use bioconductor-uri here because this tarball is
8434 ;; located under "data/annotation/" instead of "bioc/".
8435 (uri (string-append "https://www.bioconductor.org/packages/"
8436 "release/data/annotation/src/contrib/"
8437 "BSgenome.Dmelanogaster.UCSC.dm3_"
8441 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8443 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8444 (build-system r-build-system)
8445 ;; As this package provides little more than a very large data file it
8446 ;; doesn't make sense to build substitutes.
8447 (arguments `(#:substitutable? #f))
8449 `(("r-bsgenome" ,r-bsgenome)))
8451 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8452 (synopsis "Full genome sequences for Fly")
8454 "This package provides full genome sequences for Drosophila
8455 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8456 Biostrings objects.")
8457 (license license:artistic2.0)))
8459 (define-public r-motifrg
8466 (uri (bioconductor-uri "motifRG" version))
8469 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8470 (properties `((upstream-name . "motifRG")))
8471 (build-system r-build-system)
8473 `(("r-biostrings" ,r-biostrings)
8474 ("r-bsgenome" ,r-bsgenome)
8475 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8476 ("r-iranges" ,r-iranges)
8477 ("r-seqlogo" ,r-seqlogo)
8478 ("r-xvector" ,r-xvector)))
8479 (home-page "https://bioconductor.org/packages/motifRG")
8480 (synopsis "Discover motifs in high throughput sequencing data")
8482 "This package provides tools for discriminative motif discovery in high
8483 throughput genetic sequencing data sets using regression methods.")
8484 (license license:artistic2.0)))
8486 (define-public r-qtl
8493 (uri (string-append "mirror://cran/src/contrib/qtl_"
8497 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8498 (build-system r-build-system)
8499 (home-page "http://rqtl.org/")
8500 (synopsis "R package for analyzing QTL experiments in genetics")
8501 (description "R/qtl is an extension library for the R statistics
8502 system. It is used to analyze experimental crosses for identifying
8503 genes contributing to variation in quantitative traits (so-called
8504 quantitative trait loci, QTLs).
8506 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8507 identify genotyping errors, and to perform single-QTL and two-QTL,
8508 two-dimensional genome scans.")
8509 (license license:gpl3)))
8511 (define-public r-zlibbioc
8517 (uri (bioconductor-uri "zlibbioc" version))
8520 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8522 `((upstream-name . "zlibbioc")))
8523 (build-system r-build-system)
8524 (home-page "https://bioconductor.org/packages/zlibbioc")
8525 (synopsis "Provider for zlib-1.2.5 to R packages")
8526 (description "This package uses the source code of zlib-1.2.5 to create
8527 libraries for systems that do not have these available via other means.")
8528 (license license:artistic2.0)))
8530 (define-public r-r4rna
8537 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8541 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8542 (build-system r-build-system)
8544 `(("r-optparse" ,r-optparse)
8545 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8546 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8547 (synopsis "Analysis framework for RNA secondary structure")
8549 "The R4RNA package aims to be a general framework for the analysis of RNA
8550 secondary structure and comparative analysis in R.")
8551 (license license:gpl3+)))
8553 (define-public r-rhtslib
8560 (uri (bioconductor-uri "Rhtslib" version))
8563 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8564 (properties `((upstream-name . "Rhtslib")))
8565 (build-system r-build-system)
8567 `(("r-zlibbioc" ,r-zlibbioc)))
8571 `(("pkg-config" ,pkg-config)))
8572 (home-page "https://github.com/nhayden/Rhtslib")
8573 (synopsis "High-throughput sequencing library as an R package")
8575 "This package provides the HTSlib C library for high-throughput
8576 nucleotide sequence analysis. The package is primarily useful to developers
8577 of other R packages who wish to make use of HTSlib.")
8578 (license license:lgpl2.0+)))
8580 (define-public r-bamsignals
8582 (name "r-bamsignals")
8587 (uri (bioconductor-uri "bamsignals" version))
8590 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8591 (build-system r-build-system)
8593 `(("r-biocgenerics" ,r-biocgenerics)
8594 ("r-genomicranges" ,r-genomicranges)
8595 ("r-iranges" ,r-iranges)
8597 ("r-rhtslib" ,r-rhtslib)
8598 ("r-zlibbioc" ,r-zlibbioc)))
8601 (home-page "https://bioconductor.org/packages/bamsignals")
8602 (synopsis "Extract read count signals from bam files")
8604 "This package allows to efficiently obtain count vectors from indexed bam
8605 files. It counts the number of nucleotide sequence reads in given genomic
8606 ranges and it computes reads profiles and coverage profiles. It also handles
8608 (license license:gpl2+)))
8610 (define-public r-rcas
8616 (uri (bioconductor-uri "RCAS" version))
8619 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8620 (build-system r-build-system)
8622 `(("r-annotationdbi" ,r-annotationdbi)
8623 ("r-biocgenerics" ,r-biocgenerics)
8624 ("r-biomart" ,r-biomart)
8625 ("r-biostrings" ,r-biostrings)
8626 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8627 ("r-cowplot" ,r-cowplot)
8628 ("r-data-table" ,r-data-table)
8631 ("r-genomation" ,r-genomation)
8632 ("r-genomeinfodb" ,r-genomeinfodb)
8633 ("r-genomicfeatures" ,r-genomicfeatures)
8634 ("r-genomicranges" ,r-genomicranges)
8635 ("r-ggplot2" ,r-ggplot2)
8636 ("r-ggseqlogo" ,r-ggseqlogo)
8637 ("r-knitr" ,r-knitr)
8638 ("r-motifrg" ,r-motifrg)
8639 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8640 ("r-pbapply" ,r-pbapply)
8641 ("r-pheatmap" ,r-pheatmap)
8642 ("r-plotly" ,r-plotly)
8643 ("r-plotrix" ,r-plotrix)
8644 ("r-proxy" ,r-proxy)
8645 ("r-rsqlite" ,r-rsqlite)
8646 ("r-rtracklayer" ,r-rtracklayer)
8647 ("r-rmarkdown" ,r-rmarkdown)
8648 ("r-s4vectors" ,r-s4vectors)
8649 ("r-topgo" ,r-topgo)))
8650 (synopsis "RNA-centric annotation system")
8652 "RCAS aims to be a standalone RNA-centric annotation system that provides
8653 intuitive reports and publication-ready graphics. This package provides the R
8654 library implementing most of the pipeline's features.")
8655 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8656 (license license:artistic2.0)))
8658 (define-public rcas-web
8665 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8666 "releases/download/v" version
8667 "/rcas-web-" version ".tar.gz"))
8670 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8671 (build-system gnu-build-system)
8674 (modify-phases %standard-phases
8675 (add-after 'install 'wrap-executable
8676 (lambda* (#:key inputs outputs #:allow-other-keys)
8677 (let* ((out (assoc-ref outputs "out"))
8678 (json (assoc-ref inputs "guile-json"))
8679 (redis (assoc-ref inputs "guile-redis"))
8680 (path (string-append
8681 json "/share/guile/site/2.2:"
8682 redis "/share/guile/site/2.2")))
8683 (wrap-program (string-append out "/bin/rcas-web")
8684 `("GUILE_LOAD_PATH" ":" = (,path))
8685 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8686 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8689 `(("r-minimal" ,r-minimal)
8691 ("guile-next" ,guile-2.2)
8692 ("guile-json" ,guile-json)
8693 ("guile-redis" ,guile2.2-redis)))
8695 `(("pkg-config" ,pkg-config)))
8696 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8697 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8698 (description "This package provides a simple web interface for the
8699 @dfn{RNA-centric annotation system} (RCAS).")
8700 (license license:agpl3+)))
8702 (define-public r-mutationalpatterns
8704 (name "r-mutationalpatterns")
8709 (uri (bioconductor-uri "MutationalPatterns" version))
8712 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8713 (build-system r-build-system)
8715 `(("r-biocgenerics" ,r-biocgenerics)
8716 ("r-biostrings" ,r-biostrings)
8717 ;; These two packages are suggested packages
8718 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8719 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8720 ("r-genomicranges" ,r-genomicranges)
8721 ("r-genomeinfodb" ,r-genomeinfodb)
8722 ("r-ggplot2" ,r-ggplot2)
8723 ("r-iranges" ,r-iranges)
8726 ("r-pracma" ,r-pracma)
8727 ("r-reshape2" ,r-reshape2)
8728 ("r-cowplot" ,r-cowplot)
8729 ("r-ggdendro" ,r-ggdendro)
8730 ("r-s4vectors" ,r-s4vectors)
8731 ("r-summarizedexperiment" ,r-summarizedexperiment)
8732 ("r-variantannotation" ,r-variantannotation)))
8733 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8734 (synopsis "Extract and visualize mutational patterns in genomic data")
8735 (description "This package provides an extensive toolset for the
8736 characterization and visualization of a wide range of mutational patterns
8737 in SNV base substitution data.")
8738 (license license:expat)))
8740 (define-public r-wgcna
8747 (uri (cran-uri "WGCNA" version))
8750 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8751 (properties `((upstream-name . "WGCNA")))
8752 (build-system r-build-system)
8754 `(("r-annotationdbi" ,r-annotationdbi)
8755 ("r-doparallel" ,r-doparallel)
8756 ("r-dynamictreecut" ,r-dynamictreecut)
8757 ("r-fastcluster" ,r-fastcluster)
8758 ("r-foreach" ,r-foreach)
8759 ("r-go-db" ,r-go-db)
8760 ("r-hmisc" ,r-hmisc)
8761 ("r-impute" ,r-impute)
8763 ("r-robust" ,r-robust)
8764 ("r-survival" ,r-survival)
8765 ("r-matrixstats" ,r-matrixstats)
8766 ("r-preprocesscore" ,r-preprocesscore)))
8768 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8769 (synopsis "Weighted correlation network analysis")
8771 "This package provides functions necessary to perform Weighted
8772 Correlation Network Analysis on high-dimensional data. It includes functions
8773 for rudimentary data cleaning, construction and summarization of correlation
8774 networks, module identification and functions for relating both variables and
8775 modules to sample traits. It also includes a number of utility functions for
8776 data manipulation and visualization.")
8777 (license license:gpl2+)))
8779 (define-public r-chipkernels
8780 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8783 (name "r-chipkernels")
8784 (version (string-append "1.1-" revision "." (string-take commit 9)))
8789 (url "https://github.com/ManuSetty/ChIPKernels.git")
8791 (file-name (string-append name "-" version))
8794 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8795 (build-system r-build-system)
8797 `(("r-iranges" ,r-iranges)
8798 ("r-xvector" ,r-xvector)
8799 ("r-biostrings" ,r-biostrings)
8800 ("r-bsgenome" ,r-bsgenome)
8801 ("r-gtools" ,r-gtools)
8802 ("r-genomicranges" ,r-genomicranges)
8803 ("r-sfsmisc" ,r-sfsmisc)
8804 ("r-kernlab" ,r-kernlab)
8805 ("r-s4vectors" ,r-s4vectors)
8806 ("r-biocgenerics" ,r-biocgenerics)))
8807 (home-page "https://github.com/ManuSetty/ChIPKernels")
8808 (synopsis "Build string kernels for DNA Sequence analysis")
8809 (description "ChIPKernels is an R package for building different string
8810 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8811 must be built and this dictionary can be used for determining kernels for DNA
8813 (license license:gpl2+))))
8815 (define-public r-seqgl
8823 (url "https://github.com/ManuSetty/SeqGL.git")
8825 (file-name (git-file-name name version))
8828 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8829 (build-system r-build-system)
8831 `(("r-biostrings" ,r-biostrings)
8832 ("r-chipkernels" ,r-chipkernels)
8833 ("r-genomicranges" ,r-genomicranges)
8834 ("r-spams" ,r-spams)
8835 ("r-wgcna" ,r-wgcna)
8836 ("r-fastcluster" ,r-fastcluster)))
8837 (home-page "https://github.com/ManuSetty/SeqGL")
8838 (synopsis "Group lasso for Dnase/ChIP-seq data")
8839 (description "SeqGL is a group lasso based algorithm to extract
8840 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8841 This package presents a method which uses group lasso to discriminate between
8842 bound and non bound genomic regions to accurately identify transcription
8843 factors bound at the specific regions.")
8844 (license license:gpl2+)))
8846 (define-public r-gkmsvm
8853 (uri (cran-uri "gkmSVM" version))
8856 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8857 (properties `((upstream-name . "gkmSVM")))
8858 (build-system r-build-system)
8860 `(("r-biocgenerics" ,r-biocgenerics)
8861 ("r-biostrings" ,r-biostrings)
8862 ("r-genomeinfodb" ,r-genomeinfodb)
8863 ("r-genomicranges" ,r-genomicranges)
8864 ("r-iranges" ,r-iranges)
8865 ("r-kernlab" ,r-kernlab)
8868 ("r-rtracklayer" ,r-rtracklayer)
8869 ("r-s4vectors" ,r-s4vectors)
8870 ("r-seqinr" ,r-seqinr)))
8871 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8872 (synopsis "Gapped-kmer support vector machine")
8874 "This R package provides tools for training gapped-kmer SVM classifiers
8875 for DNA and protein sequences. This package supports several sequence
8876 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8877 (license license:gpl2+)))
8879 (define-public r-tximport
8885 (uri (bioconductor-uri "tximport" version))
8888 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8889 (build-system r-build-system)
8890 (home-page "https://bioconductor.org/packages/tximport")
8891 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8893 "This package provides tools to import transcript-level abundance,
8894 estimated counts and transcript lengths, and to summarize them into matrices
8895 for use with downstream gene-level analysis packages. Average transcript
8896 length, weighted by sample-specific transcript abundance estimates, is
8897 provided as a matrix which can be used as an offset for different expression
8898 of gene-level counts.")
8899 (license license:gpl2+)))
8901 (define-public r-rhdf5
8907 (uri (bioconductor-uri "rhdf5" version))
8910 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8911 (build-system r-build-system)
8913 `(("r-rhdf5lib" ,r-rhdf5lib)))
8916 (home-page "https://bioconductor.org/packages/rhdf5")
8917 (synopsis "HDF5 interface to R")
8919 "This R/Bioconductor package provides an interface between HDF5 and R.
8920 HDF5's main features are the ability to store and access very large and/or
8921 complex datasets and a wide variety of metadata on mass storage (disk) through
8922 a completely portable file format. The rhdf5 package is thus suited for the
8923 exchange of large and/or complex datasets between R and other software
8924 package, and for letting R applications work on datasets that are larger than
8925 the available RAM.")
8926 (license license:artistic2.0)))
8928 (define-public r-annotationfilter
8930 (name "r-annotationfilter")
8934 (uri (bioconductor-uri "AnnotationFilter" version))
8937 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8939 `((upstream-name . "AnnotationFilter")))
8940 (build-system r-build-system)
8942 `(("r-genomicranges" ,r-genomicranges)
8943 ("r-lazyeval" ,r-lazyeval)))
8944 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8945 (synopsis "Facilities for filtering Bioconductor annotation resources")
8947 "This package provides classes and other infrastructure to implement
8948 filters for manipulating Bioconductor annotation resources. The filters are
8949 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8950 (license license:artistic2.0)))
8952 (define-public emboss
8958 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8959 (version-major+minor version) ".0/"
8960 "EMBOSS-" version ".tar.gz"))
8963 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8964 (build-system gnu-build-system)
8967 (list (string-append "--with-hpdf="
8968 (assoc-ref %build-inputs "libharu")))
8970 (modify-phases %standard-phases
8971 (add-after 'unpack 'fix-checks
8973 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8974 ;; and zlib, but assume that they are all found at the same
8976 (substitute* "configure.in"
8977 (("CHECK_PNGDRIVER")
8978 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8979 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8980 AM_CONDITIONAL(AMPNG, true)"))
8982 (add-after 'fix-checks 'disable-update-check
8984 ;; At build time there is no connection to the Internet, so
8985 ;; looking for updates will not work.
8986 (substitute* "Makefile.am"
8987 (("\\$\\(bindir\\)/embossupdate") ""))
8989 (add-after 'disable-update-check 'autogen
8990 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8996 ("libharu" ,libharu)
8999 `(("autoconf" ,autoconf)
9000 ("automake" ,automake)
9001 ("libtool" ,libtool)
9002 ("pkg-config" ,pkg-config)))
9003 (home-page "http://emboss.sourceforge.net")
9004 (synopsis "Molecular biology analysis suite")
9005 (description "EMBOSS is the \"European Molecular Biology Open Software
9006 Suite\". EMBOSS is an analysis package specially developed for the needs of
9007 the molecular biology (e.g. EMBnet) user community. The software
9008 automatically copes with data in a variety of formats and even allows
9009 transparent retrieval of sequence data from the web. It also provides a
9010 number of libraries for the development of software in the field of molecular
9011 biology. EMBOSS also integrates a range of currently available packages and
9012 tools for sequence analysis into a seamless whole.")
9013 (license license:gpl2+)))
9016 (let ((revision "1")
9017 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9020 ;; The version is 2.13.0 even though no release archives have been
9021 ;; published as yet.
9022 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9026 (url "https://github.com/arq5x/bits.git")
9028 (file-name (string-append name "-" version "-checkout"))
9031 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9032 (build-system gnu-build-system)
9034 `(#:tests? #f ;no tests included
9036 (modify-phases %standard-phases
9038 (add-after 'unpack 'remove-cuda
9040 (substitute* "Makefile"
9042 (("(bits_test_intersections) \\\\" _ match) match))
9045 (lambda* (#:key outputs #:allow-other-keys)
9047 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9052 (home-page "https://github.com/arq5x/bits")
9053 (synopsis "Implementation of binary interval search algorithm")
9054 (description "This package provides an implementation of the
9055 BITS (Binary Interval Search) algorithm, an approach to interval set
9056 intersection. It is especially suited for the comparison of diverse genomic
9057 datasets and the exploration of large datasets of genome
9058 intervals (e.g. genes, sequence alignments).")
9059 (license license:gpl2))))
9061 (define-public piranha
9062 ;; There is no release tarball for the latest version. The latest commit is
9063 ;; older than one year at the time of this writing.
9064 (let ((revision "1")
9065 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9068 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9072 (url "https://github.com/smithlabcode/piranha.git")
9074 (file-name (git-file-name name version))
9077 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9078 (build-system gnu-build-system)
9080 `(#:test-target "test"
9082 (modify-phases %standard-phases
9083 (add-after 'unpack 'copy-smithlab-cpp
9084 (lambda* (#:key inputs #:allow-other-keys)
9085 (for-each (lambda (file)
9086 (install-file file "./src/smithlab_cpp/"))
9087 (find-files (assoc-ref inputs "smithlab-cpp")))
9089 (add-after 'install 'install-to-store
9090 (lambda* (#:key outputs #:allow-other-keys)
9091 (let* ((out (assoc-ref outputs "out"))
9092 (bin (string-append out "/bin")))
9093 (for-each (lambda (file)
9094 (install-file file bin))
9095 (find-files "bin" ".*")))
9098 (list (string-append "--with-bam_tools_headers="
9099 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9100 (string-append "--with-bam_tools_library="
9101 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9103 `(("bamtools" ,bamtools)
9104 ("samtools" ,samtools-0.1)
9107 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9111 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9113 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9116 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9118 `(("python" ,python-2)))
9119 (home-page "https://github.com/smithlabcode/piranha")
9120 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9122 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9123 RIP-seq experiments. It takes input in BED or BAM format and identifies
9124 regions of statistically significant read enrichment. Additional covariates
9125 may optionally be provided to further inform the peak-calling process.")
9126 (license license:gpl3+))))
9134 (uri (string-append "https://pypi.python.org/packages/source/P"
9135 "/PePr/PePr-" version ".tar.gz"))
9138 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9139 (build-system python-build-system)
9141 `(#:python ,python-2 ; python2 only
9142 #:tests? #f)) ; no tests included
9144 `(("python2-numpy" ,python2-numpy)
9145 ("python2-scipy" ,python2-scipy)
9146 ("python2-pysam" ,python2-pysam)))
9147 (home-page "https://github.com/shawnzhangyx/PePr")
9148 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9150 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9151 that is primarily designed for data with biological replicates. It uses a
9152 negative binomial distribution to model the read counts among the samples in
9153 the same group, and look for consistent differences between ChIP and control
9154 group or two ChIP groups run under different conditions.")
9155 (license license:gpl3+)))
9157 (define-public filevercmp
9158 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9161 (version (string-append "0-1." (string-take commit 7)))
9165 (url "https://github.com/ekg/filevercmp.git")
9167 (file-name (git-file-name name commit))
9170 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9171 (build-system gnu-build-system)
9173 `(#:tests? #f ; There are no tests to run.
9175 (modify-phases %standard-phases
9176 (delete 'configure) ; There is no configure phase.
9178 (lambda* (#:key outputs #:allow-other-keys)
9179 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9180 (install-file "filevercmp" bin)
9182 (home-page "https://github.com/ekg/filevercmp")
9183 (synopsis "This program compares version strings")
9184 (description "This program compares version strings. It intends to be a
9185 replacement for strverscmp.")
9186 (license license:gpl3+))))
9188 (define-public multiqc
9195 (uri (pypi-uri "multiqc" version))
9198 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9199 (build-system python-build-system)
9201 `(("python-jinja2" ,python-jinja2)
9202 ("python-simplejson" ,python-simplejson)
9203 ("python-pyyaml" ,python-pyyaml)
9204 ("python-click" ,python-click)
9205 ("python-spectra" ,python-spectra)
9206 ("python-requests" ,python-requests)
9207 ("python-markdown" ,python-markdown)
9208 ("python-lzstring" ,python-lzstring)
9209 ("python-matplotlib" ,python-matplotlib)
9210 ("python-numpy" ,python-numpy)
9211 ;; MultQC checks for the presence of nose at runtime.
9212 ("python-nose" ,python-nose)))
9215 (modify-phases %standard-phases
9216 (add-after 'unpack 'relax-requirements
9218 (substitute* "setup.py"
9219 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9220 ;; than the one in Guix, but should work fine with 2.2.2.
9221 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9222 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9223 (("['\"]matplotlib.*?['\"]")
9226 (home-page "http://multiqc.info")
9227 (synopsis "Aggregate bioinformatics analysis reports")
9229 "MultiQC is a tool to aggregate bioinformatics results across many
9230 samples into a single report. It contains modules for a large number of
9231 common bioinformatics tools.")
9232 (license license:gpl3+)))
9234 (define-public r-chipseq
9241 (uri (bioconductor-uri "chipseq" version))
9244 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9245 (build-system r-build-system)
9247 `(("r-biocgenerics" ,r-biocgenerics)
9248 ("r-genomicranges" ,r-genomicranges)
9249 ("r-iranges" ,r-iranges)
9250 ("r-lattice" ,r-lattice)
9251 ("r-s4vectors" ,r-s4vectors)
9252 ("r-shortread" ,r-shortread)))
9253 (home-page "https://bioconductor.org/packages/chipseq")
9254 (synopsis "Package for analyzing ChIPseq data")
9256 "This package provides tools for processing short read data from ChIPseq
9258 (license license:artistic2.0)))
9260 (define-public r-copyhelper
9262 (name "r-copyhelper")
9267 (uri (string-append "https://bioconductor.org/packages/release/"
9268 "data/experiment/src/contrib/CopyhelpeR_"
9272 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9273 (properties `((upstream-name . "CopyhelpeR")))
9274 (build-system r-build-system)
9275 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9276 (synopsis "Helper files for CopywriteR")
9278 "This package contains the helper files that are required to run the
9279 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9280 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9281 mm10. In addition, it contains a blacklist filter to remove regions that
9282 display copy number variation. Files are stored as GRanges objects from the
9283 GenomicRanges Bioconductor package.")
9284 (license license:gpl2)))
9286 (define-public r-copywriter
9288 (name "r-copywriter")
9293 (uri (bioconductor-uri "CopywriteR" version))
9296 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
9297 (properties `((upstream-name . "CopywriteR")))
9298 (build-system r-build-system)
9300 `(("r-biocparallel" ,r-biocparallel)
9301 ("r-chipseq" ,r-chipseq)
9302 ("r-copyhelper" ,r-copyhelper)
9303 ("r-data-table" ,r-data-table)
9304 ("r-dnacopy" ,r-dnacopy)
9305 ("r-futile-logger" ,r-futile-logger)
9306 ("r-genomeinfodb" ,r-genomeinfodb)
9307 ("r-genomicalignments" ,r-genomicalignments)
9308 ("r-genomicranges" ,r-genomicranges)
9309 ("r-gtools" ,r-gtools)
9310 ("r-iranges" ,r-iranges)
9311 ("r-matrixstats" ,r-matrixstats)
9312 ("r-rsamtools" ,r-rsamtools)
9313 ("r-s4vectors" ,r-s4vectors)))
9314 (home-page "https://github.com/PeeperLab/CopywriteR")
9315 (synopsis "Copy number information from targeted sequencing")
9317 "CopywriteR extracts DNA copy number information from targeted sequencing
9318 by utilizing off-target reads. It allows for extracting uniformly distributed
9319 copy number information, can be used without reference, and can be applied to
9320 sequencing data obtained from various techniques including chromatin
9321 immunoprecipitation and target enrichment on small gene panels. Thereby,
9322 CopywriteR constitutes a widely applicable alternative to available copy
9323 number detection tools.")
9324 (license license:gpl2)))
9326 (define-public r-methylkit
9328 (name "r-methylkit")
9332 (uri (bioconductor-uri "methylKit" version))
9335 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
9336 (properties `((upstream-name . "methylKit")))
9337 (build-system r-build-system)
9339 `(("r-data-table" ,r-data-table)
9340 ("r-emdbook" ,r-emdbook)
9341 ("r-fastseg" ,r-fastseg)
9342 ("r-genomeinfodb" ,r-genomeinfodb)
9343 ("r-genomicranges" ,r-genomicranges)
9344 ("r-gtools" ,r-gtools)
9345 ("r-iranges" ,r-iranges)
9346 ("r-kernsmooth" ,r-kernsmooth)
9347 ("r-limma" ,r-limma)
9348 ("r-mclust" ,r-mclust)
9349 ("r-qvalue" ,r-qvalue)
9350 ("r-r-utils" ,r-r-utils)
9352 ("r-rhtslib" ,r-rhtslib)
9353 ("r-rsamtools" ,r-rsamtools)
9354 ("r-rtracklayer" ,r-rtracklayer)
9355 ("r-s4vectors" ,r-s4vectors)
9356 ("r-zlibbioc" ,r-zlibbioc)))
9359 (home-page "https://github.com/al2na/methylKit")
9361 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9363 "MethylKit is an R package for DNA methylation analysis and annotation
9364 from high-throughput bisulfite sequencing. The package is designed to deal
9365 with sequencing data from @dfn{Reduced representation bisulfite
9366 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9367 genome bisulfite sequencing. It also has functions to analyze base-pair
9368 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9370 (license license:artistic2.0)))
9372 (define-public r-sva
9379 (uri (bioconductor-uri "sva" version))
9382 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
9383 (build-system r-build-system)
9385 `(("r-genefilter" ,r-genefilter)
9387 ("r-biocparallel" ,r-biocparallel)
9388 ("r-matrixstats" ,r-matrixstats)
9389 ("r-limma" ,r-limma)))
9390 (home-page "https://bioconductor.org/packages/sva")
9391 (synopsis "Surrogate variable analysis")
9393 "This package contains functions for removing batch effects and other
9394 unwanted variation in high-throughput experiment. It also contains functions
9395 for identifying and building surrogate variables for high-dimensional data
9396 sets. Surrogate variables are covariates constructed directly from
9397 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9398 imaging data that can be used in subsequent analyses to adjust for unknown,
9399 unmodeled, or latent sources of noise.")
9400 (license license:artistic2.0)))
9402 (define-public r-seqminer
9409 (uri (cran-uri "seqminer" version))
9412 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9413 (build-system r-build-system)
9416 (home-page "http://seqminer.genomic.codes")
9417 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9419 "This package provides tools to integrate nucleotide sequencing
9420 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9421 ;; Any version of the GPL is acceptable
9422 (license (list license:gpl2+ license:gpl3+))))
9424 (define-public r-raremetals2
9426 (name "r-raremetals2")
9431 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9432 "b/b7/RareMETALS2_" version ".tar.gz"))
9435 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9436 (properties `((upstream-name . "RareMETALS2")))
9437 (build-system r-build-system)
9439 `(("r-seqminer" ,r-seqminer)
9440 ("r-mvtnorm" ,r-mvtnorm)
9442 ("r-compquadform" ,r-compquadform)
9443 ("r-getopt" ,r-getopt)))
9444 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9445 (synopsis "Analyze gene-level association tests for binary trait")
9447 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9448 It was designed to meta-analyze gene-level association tests for binary trait.
9449 While rareMETALS offers a near-complete solution for meta-analysis of
9450 gene-level tests for quantitative trait, it does not offer the optimal
9451 solution for binary trait. The package rareMETALS2 offers improved features
9452 for analyzing gene-level association tests in meta-analyses for binary
9454 (license license:gpl3)))
9456 (define-public r-maldiquant
9458 (name "r-maldiquant")
9463 (uri (cran-uri "MALDIquant" version))
9466 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9467 (properties `((upstream-name . "MALDIquant")))
9468 (build-system r-build-system)
9469 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9470 (synopsis "Quantitative analysis of mass spectrometry data")
9472 "This package provides a complete analysis pipeline for matrix-assisted
9473 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9474 two-dimensional mass spectrometry data. In addition to commonly used plotting
9475 and processing methods it includes distinctive features, namely baseline
9476 subtraction methods such as morphological filters (TopHat) or the
9477 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9478 alignment using warping functions, handling of replicated measurements as well
9479 as allowing spectra with different resolutions.")
9480 (license license:gpl3+)))
9482 (define-public r-protgenerics
9484 (name "r-protgenerics")
9489 (uri (bioconductor-uri "ProtGenerics" version))
9492 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9493 (properties `((upstream-name . "ProtGenerics")))
9494 (build-system r-build-system)
9495 (home-page "https://github.com/lgatto/ProtGenerics")
9496 (synopsis "S4 generic functions for proteomics infrastructure")
9498 "This package provides S4 generic functions needed by Bioconductor
9499 proteomics packages.")
9500 (license license:artistic2.0)))
9502 (define-public r-mzr
9509 (uri (bioconductor-uri "mzR" version))
9512 "0mlwg646k49klxrznckzfv54a9mz6irj42fqpaaa0xjm6cw2lwaa"))
9513 (modules '((guix build utils)))
9516 (delete-file-recursively "src/boost")
9518 (properties `((upstream-name . "mzR")))
9519 (build-system r-build-system)
9522 (modify-phases %standard-phases
9523 (add-after 'unpack 'use-system-boost
9525 (substitute* "src/Makevars"
9526 (("\\./boost/libs.*") "")
9527 (("ARCH_OBJS=" line)
9529 "\nARCH_LIBS=-lboost_system -lboost_regex \
9530 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9533 `(("boost" ,boost) ; use this instead of the bundled boost sources
9536 `(("r-biobase" ,r-biobase)
9537 ("r-biocgenerics" ,r-biocgenerics)
9538 ("r-ncdf4" ,r-ncdf4)
9539 ("r-protgenerics" ,r-protgenerics)
9541 ("r-rhdf5lib" ,r-rhdf5lib)
9542 ("r-zlibbioc" ,r-zlibbioc)))
9543 (home-page "https://github.com/sneumann/mzR/")
9544 (synopsis "Parser for mass spectrometry data files")
9546 "The mzR package provides a unified API to the common file formats and
9547 parsers available for mass spectrometry data. It comes with a wrapper for the
9548 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9549 The package contains the original code written by the ISB, and a subset of the
9550 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9551 previously been used in XCMS.")
9552 (license license:artistic2.0)))
9554 (define-public r-affyio
9561 (uri (bioconductor-uri "affyio" version))
9564 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9565 (build-system r-build-system)
9567 `(("r-zlibbioc" ,r-zlibbioc)))
9570 (home-page "https://github.com/bmbolstad/affyio")
9571 (synopsis "Tools for parsing Affymetrix data files")
9573 "This package provides routines for parsing Affymetrix data files based
9574 upon file format information. The primary focus is on accessing the CEL and
9576 (license license:lgpl2.0+)))
9578 (define-public r-affy
9585 (uri (bioconductor-uri "affy" version))
9588 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9589 (build-system r-build-system)
9591 `(("r-affyio" ,r-affyio)
9592 ("r-biobase" ,r-biobase)
9593 ("r-biocgenerics" ,r-biocgenerics)
9594 ("r-biocmanager" ,r-biocmanager)
9595 ("r-preprocesscore" ,r-preprocesscore)
9596 ("r-zlibbioc" ,r-zlibbioc)))
9599 (home-page "https://bioconductor.org/packages/affy")
9600 (synopsis "Methods for affymetrix oligonucleotide arrays")
9602 "This package contains functions for exploratory oligonucleotide array
9604 (license license:lgpl2.0+)))
9606 (define-public r-vsn
9613 (uri (bioconductor-uri "vsn" version))
9616 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9617 (build-system r-build-system)
9619 `(("r-affy" ,r-affy)
9620 ("r-biobase" ,r-biobase)
9621 ("r-ggplot2" ,r-ggplot2)
9622 ("r-lattice" ,r-lattice)
9623 ("r-limma" ,r-limma)))
9624 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9625 (synopsis "Variance stabilization and calibration for microarray data")
9627 "The package implements a method for normalising microarray intensities,
9628 and works for single- and multiple-color arrays. It can also be used for data
9629 from other technologies, as long as they have similar format. The method uses
9630 a robust variant of the maximum-likelihood estimator for an
9631 additive-multiplicative error model and affine calibration. The model
9632 incorporates data calibration step (a.k.a. normalization), a model for the
9633 dependence of the variance on the mean intensity and a variance stabilizing
9634 data transformation. Differences between transformed intensities are
9635 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9636 their variance is independent of the mean, and they are usually more sensitive
9637 and specific in detecting differential transcription.")
9638 (license license:artistic2.0)))
9640 (define-public r-mzid
9647 (uri (bioconductor-uri "mzID" version))
9650 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9651 (properties `((upstream-name . "mzID")))
9652 (build-system r-build-system)
9654 `(("r-doparallel" ,r-doparallel)
9655 ("r-foreach" ,r-foreach)
9656 ("r-iterators" ,r-iterators)
9658 ("r-protgenerics" ,r-protgenerics)
9661 (home-page "https://bioconductor.org/packages/mzID")
9662 (synopsis "Parser for mzIdentML files")
9664 "This package provides a parser for mzIdentML files implemented using the
9665 XML package. The parser tries to be general and able to handle all types of
9666 mzIdentML files with the drawback of having less pretty output than a vendor
9668 (license license:gpl2+)))
9670 (define-public r-pcamethods
9672 (name "r-pcamethods")
9677 (uri (bioconductor-uri "pcaMethods" version))
9680 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9681 (properties `((upstream-name . "pcaMethods")))
9682 (build-system r-build-system)
9684 `(("r-biobase" ,r-biobase)
9685 ("r-biocgenerics" ,r-biocgenerics)
9687 ("r-rcpp" ,r-rcpp)))
9688 (home-page "https://github.com/hredestig/pcamethods")
9689 (synopsis "Collection of PCA methods")
9691 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9692 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9693 for missing value estimation is included for comparison. BPCA, PPCA and
9694 NipalsPCA may be used to perform PCA on incomplete data as well as for
9695 accurate missing value estimation. A set of methods for printing and plotting
9696 the results is also provided. All PCA methods make use of the same data
9697 structure (pcaRes) to provide a common interface to the PCA results.")
9698 (license license:gpl3+)))
9700 (define-public r-msnbase
9707 (uri (bioconductor-uri "MSnbase" version))
9710 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9711 (properties `((upstream-name . "MSnbase")))
9712 (build-system r-build-system)
9714 `(("r-affy" ,r-affy)
9715 ("r-biobase" ,r-biobase)
9716 ("r-biocgenerics" ,r-biocgenerics)
9717 ("r-biocparallel" ,r-biocparallel)
9718 ("r-digest" ,r-digest)
9719 ("r-ggplot2" ,r-ggplot2)
9720 ("r-impute" ,r-impute)
9721 ("r-iranges" ,r-iranges)
9722 ("r-lattice" ,r-lattice)
9723 ("r-maldiquant" ,r-maldiquant)
9727 ("r-pcamethods" ,r-pcamethods)
9729 ("r-preprocesscore" ,r-preprocesscore)
9730 ("r-protgenerics" ,r-protgenerics)
9732 ("r-s4vectors" ,r-s4vectors)
9733 ("r-scales" ,r-scales)
9736 (home-page "https://github.com/lgatto/MSnbase")
9737 (synopsis "Base functions and classes for MS-based proteomics")
9739 "This package provides basic plotting, data manipulation and processing
9740 of mass spectrometry based proteomics data.")
9741 (license license:artistic2.0)))
9743 (define-public r-msnid
9750 (uri (bioconductor-uri "MSnID" version))
9753 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9754 (properties `((upstream-name . "MSnID")))
9755 (build-system r-build-system)
9757 `(("r-biobase" ,r-biobase)
9758 ("r-data-table" ,r-data-table)
9759 ("r-doparallel" ,r-doparallel)
9760 ("r-dplyr" ,r-dplyr)
9761 ("r-foreach" ,r-foreach)
9762 ("r-iterators" ,r-iterators)
9763 ("r-msnbase" ,r-msnbase)
9766 ("r-protgenerics" ,r-protgenerics)
9767 ("r-r-cache" ,r-r-cache)
9769 ("r-reshape2" ,r-reshape2)))
9770 (home-page "https://bioconductor.org/packages/MSnID")
9771 (synopsis "Utilities for LC-MSn proteomics identifications")
9773 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9774 from mzIdentML (leveraging the mzID package) or text files. After collating
9775 the search results from multiple datasets it assesses their identification
9776 quality and optimize filtering criteria to achieve the maximum number of
9777 identifications while not exceeding a specified false discovery rate. It also
9778 contains a number of utilities to explore the MS/MS results and assess missed
9779 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9780 (license license:artistic2.0)))
9782 (define-public r-seurat
9788 (uri (cran-uri "Seurat" version))
9791 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9792 (properties `((upstream-name . "Seurat")))
9793 (build-system r-build-system)
9796 ("r-cluster" ,r-cluster)
9797 ("r-cowplot" ,r-cowplot)
9798 ("r-dosnow" ,r-dosnow)
9799 ("r-dplyr" ,r-dplyr)
9801 ("r-fitdistrplus" ,r-fitdistrplus)
9802 ("r-foreach" ,r-foreach)
9804 ("r-ggplot2" ,r-ggplot2)
9805 ("r-ggridges" ,r-ggridges)
9806 ("r-gplots" ,r-gplots)
9807 ("r-hdf5r" ,r-hdf5r)
9808 ("r-hmisc" ,r-hmisc)
9811 ("r-igraph" ,r-igraph)
9812 ("r-irlba" ,r-irlba)
9814 ("r-lmtest" ,r-lmtest)
9816 ("r-matrix" ,r-matrix)
9817 ("r-metap" ,r-metap)
9818 ("r-mixtools" ,r-mixtools)
9819 ("r-pbapply" ,r-pbapply)
9820 ("r-plotly" ,r-plotly)
9823 ("r-rcolorbrewer" ,r-rcolorbrewer)
9825 ("r-rcppeigen" ,r-rcppeigen)
9826 ("r-rcppprogress" ,r-rcppprogress)
9827 ("r-reshape2" ,r-reshape2)
9828 ("r-reticulate" ,r-reticulate)
9830 ("r-rtsne" ,r-rtsne)
9831 ("r-sdmtools" ,r-sdmtools)
9832 ("r-tidyr" ,r-tidyr)
9833 ("r-tsne" ,r-tsne)))
9834 (home-page "http://www.satijalab.org/seurat")
9835 (synopsis "Seurat is an R toolkit for single cell genomics")
9837 "This package is an R package designed for QC, analysis, and
9838 exploration of single cell RNA-seq data. It easily enables widely-used
9839 analytical techniques, including the identification of highly variable genes,
9840 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9841 algorithms; density clustering, hierarchical clustering, k-means, and the
9842 discovery of differentially expressed genes and markers.")
9843 (license license:gpl3)))
9845 (define-public r-aroma-light
9847 (name "r-aroma-light")
9852 (uri (bioconductor-uri "aroma.light" version))
9855 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9856 (properties `((upstream-name . "aroma.light")))
9857 (build-system r-build-system)
9859 `(("r-matrixstats" ,r-matrixstats)
9860 ("r-r-methodss3" ,r-r-methodss3)
9862 ("r-r-utils" ,r-r-utils)))
9863 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9864 (synopsis "Methods for normalization and visualization of microarray data")
9866 "This package provides methods for microarray analysis that take basic
9867 data types such as matrices and lists of vectors. These methods can be used
9868 standalone, be utilized in other packages, or be wrapped up in higher-level
9870 (license license:gpl2+)))
9872 (define-public r-deseq
9879 (uri (bioconductor-uri "DESeq" version))
9882 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9883 (properties `((upstream-name . "DESeq")))
9884 (build-system r-build-system)
9886 `(("r-biobase" ,r-biobase)
9887 ("r-biocgenerics" ,r-biocgenerics)
9888 ("r-genefilter" ,r-genefilter)
9889 ("r-geneplotter" ,r-geneplotter)
9890 ("r-lattice" ,r-lattice)
9891 ("r-locfit" ,r-locfit)
9893 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9894 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9895 (synopsis "Differential gene expression analysis")
9897 "This package provides tools for estimating variance-mean dependence in
9898 count data from high-throughput genetic sequencing assays and for testing for
9899 differential expression based on a model using the negative binomial
9901 (license license:gpl3+)))
9903 (define-public r-edaseq
9910 (uri (bioconductor-uri "EDASeq" version))
9913 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9914 (properties `((upstream-name . "EDASeq")))
9915 (build-system r-build-system)
9917 `(("r-annotationdbi" ,r-annotationdbi)
9918 ("r-aroma-light" ,r-aroma-light)
9919 ("r-biobase" ,r-biobase)
9920 ("r-biocgenerics" ,r-biocgenerics)
9921 ("r-biocmanager" ,r-biocmanager)
9922 ("r-biomart" ,r-biomart)
9923 ("r-biostrings" ,r-biostrings)
9924 ("r-deseq" ,r-deseq)
9925 ("r-genomicfeatures" ,r-genomicfeatures)
9926 ("r-genomicranges" ,r-genomicranges)
9927 ("r-iranges" ,r-iranges)
9928 ("r-rsamtools" ,r-rsamtools)
9929 ("r-shortread" ,r-shortread)))
9930 (home-page "https://github.com/drisso/EDASeq")
9931 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9933 "This package provides support for numerical and graphical summaries of
9934 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9935 adjust for GC-content effect (or other gene-level effects) on read counts:
9936 loess robust local regression, global-scaling, and full-quantile
9937 normalization. Between-lane normalization procedures to adjust for
9938 distributional differences between lanes (e.g., sequencing depth):
9939 global-scaling and full-quantile normalization.")
9940 (license license:artistic2.0)))
9942 (define-public r-interactivedisplaybase
9944 (name "r-interactivedisplaybase")
9949 (uri (bioconductor-uri "interactiveDisplayBase" version))
9952 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9954 `((upstream-name . "interactiveDisplayBase")))
9955 (build-system r-build-system)
9957 `(("r-biocgenerics" ,r-biocgenerics)
9958 ("r-shiny" ,r-shiny)))
9959 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9960 (synopsis "Base package for web displays of Bioconductor objects")
9962 "This package contains the basic methods needed to generate interactive
9963 Shiny-based display methods for Bioconductor objects.")
9964 (license license:artistic2.0)))
9966 (define-public r-annotationhub
9968 (name "r-annotationhub")
9973 (uri (bioconductor-uri "AnnotationHub" version))
9976 "17fgrvcnbii9siv5rq5j09bxhqffx47f6jf10418qvr7hh61ic1g"))))
9977 (properties `((upstream-name . "AnnotationHub")))
9978 (build-system r-build-system)
9980 `(("r-annotationdbi" ,r-annotationdbi)
9981 ("r-biocgenerics" ,r-biocgenerics)
9982 ("r-biocmanager" ,r-biocmanager)
9985 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9986 ("r-rsqlite" ,r-rsqlite)
9987 ("r-s4vectors" ,r-s4vectors)
9988 ("r-yaml" ,r-yaml)))
9989 (home-page "https://bioconductor.org/packages/AnnotationHub")
9990 (synopsis "Client to access AnnotationHub resources")
9992 "This package provides a client for the Bioconductor AnnotationHub web
9993 resource. The AnnotationHub web resource provides a central location where
9994 genomic files (e.g. VCF, bed, wig) and other resources from standard
9995 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9996 metadata about each resource, e.g., a textual description, tags, and date of
9997 modification. The client creates and manages a local cache of files retrieved
9998 by the user, helping with quick and reproducible access.")
9999 (license license:artistic2.0)))
10001 (define-public r-fastseg
10008 (uri (bioconductor-uri "fastseg" version))
10011 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10012 (build-system r-build-system)
10014 `(("r-biobase" ,r-biobase)
10015 ("r-biocgenerics" ,r-biocgenerics)
10016 ("r-genomicranges" ,r-genomicranges)
10017 ("r-iranges" ,r-iranges)
10018 ("r-s4vectors" ,r-s4vectors)))
10019 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10020 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10022 "Fastseg implements a very fast and efficient segmentation algorithm.
10023 It can segment data from DNA microarrays and data from next generation
10024 sequencing for example to detect copy number segments. Further it can segment
10025 data from RNA microarrays like tiling arrays to identify transcripts. Most
10026 generally, it can segment data given as a matrix or as a vector. Various data
10027 formats can be used as input to fastseg like expression set objects for
10028 microarrays or GRanges for sequencing data.")
10029 (license license:lgpl2.0+)))
10031 (define-public r-keggrest
10033 (name "r-keggrest")
10038 (uri (bioconductor-uri "KEGGREST" version))
10041 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10042 (properties `((upstream-name . "KEGGREST")))
10043 (build-system r-build-system)
10045 `(("r-biostrings" ,r-biostrings)
10048 (home-page "https://bioconductor.org/packages/KEGGREST")
10049 (synopsis "Client-side REST access to KEGG")
10051 "This package provides a package that provides a client interface to the
10052 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10053 (license license:artistic2.0)))
10055 (define-public r-gage
10062 (uri (bioconductor-uri "gage" version))
10065 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
10066 (build-system r-build-system)
10068 `(("r-annotationdbi" ,r-annotationdbi)
10069 ("r-graph" ,r-graph)
10070 ("r-keggrest" ,r-keggrest)))
10071 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10072 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10074 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10075 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10076 data attributes including sample sizes, experimental designs, assay platforms,
10077 and other types of heterogeneity. The gage package provides functions for
10078 basic GAGE analysis, result processing and presentation. In addition, it
10079 provides demo microarray data and commonly used gene set data based on KEGG
10080 pathways and GO terms. These funtions and data are also useful for gene set
10081 analysis using other methods.")
10082 (license license:gpl2+)))
10084 (define-public r-genomicfiles
10086 (name "r-genomicfiles")
10091 (uri (bioconductor-uri "GenomicFiles" version))
10094 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10095 (properties `((upstream-name . "GenomicFiles")))
10096 (build-system r-build-system)
10098 `(("r-biocgenerics" ,r-biocgenerics)
10099 ("r-biocparallel" ,r-biocparallel)
10100 ("r-genomeinfodb" ,r-genomeinfodb)
10101 ("r-genomicalignments" ,r-genomicalignments)
10102 ("r-genomicranges" ,r-genomicranges)
10103 ("r-iranges" ,r-iranges)
10104 ("r-rsamtools" ,r-rsamtools)
10105 ("r-rtracklayer" ,r-rtracklayer)
10106 ("r-s4vectors" ,r-s4vectors)
10107 ("r-summarizedexperiment" ,r-summarizedexperiment)
10108 ("r-variantannotation" ,r-variantannotation)))
10109 (home-page "https://bioconductor.org/packages/GenomicFiles")
10110 (synopsis "Distributed computing by file or by range")
10112 "This package provides infrastructure for parallel computations
10113 distributed by file or by range. User defined mapper and reducer functions
10114 provide added flexibility for data combination and manipulation.")
10115 (license license:artistic2.0)))
10117 (define-public r-complexheatmap
10119 (name "r-complexheatmap")
10124 (uri (bioconductor-uri "ComplexHeatmap" version))
10127 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10129 `((upstream-name . "ComplexHeatmap")))
10130 (build-system r-build-system)
10132 `(("r-circlize" ,r-circlize)
10133 ("r-colorspace" ,r-colorspace)
10134 ("r-getoptlong" ,r-getoptlong)
10135 ("r-globaloptions" ,r-globaloptions)
10136 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10138 "https://github.com/jokergoo/ComplexHeatmap")
10139 (synopsis "Making Complex Heatmaps")
10141 "Complex heatmaps are efficient to visualize associations between
10142 different sources of data sets and reveal potential structures. This package
10143 provides a highly flexible way to arrange multiple heatmaps and supports
10144 self-defined annotation graphics.")
10145 (license license:gpl2+)))
10147 (define-public r-dirichletmultinomial
10149 (name "r-dirichletmultinomial")
10154 (uri (bioconductor-uri "DirichletMultinomial" version))
10157 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
10159 `((upstream-name . "DirichletMultinomial")))
10160 (build-system r-build-system)
10164 `(("r-biocgenerics" ,r-biocgenerics)
10165 ("r-iranges" ,r-iranges)
10166 ("r-s4vectors" ,r-s4vectors)))
10167 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10168 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10170 "Dirichlet-multinomial mixture models can be used to describe variability
10171 in microbial metagenomic data. This package is an interface to code
10172 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10174 (license license:lgpl3)))
10176 (define-public r-ensembldb
10178 (name "r-ensembldb")
10183 (uri (bioconductor-uri "ensembldb" version))
10186 "0kzdsfk6mdwlp57sw4j2cf7lx5nc67v5j0xr3iag9kzmgikaq1lb"))))
10187 (build-system r-build-system)
10189 `(("r-annotationdbi" ,r-annotationdbi)
10190 ("r-annotationfilter" ,r-annotationfilter)
10191 ("r-biobase" ,r-biobase)
10192 ("r-biocgenerics" ,r-biocgenerics)
10193 ("r-biostrings" ,r-biostrings)
10196 ("r-genomeinfodb" ,r-genomeinfodb)
10197 ("r-genomicfeatures" ,r-genomicfeatures)
10198 ("r-genomicranges" ,r-genomicranges)
10199 ("r-iranges" ,r-iranges)
10200 ("r-protgenerics" ,r-protgenerics)
10201 ("r-rsamtools" ,r-rsamtools)
10202 ("r-rsqlite" ,r-rsqlite)
10203 ("r-rtracklayer" ,r-rtracklayer)
10204 ("r-s4vectors" ,r-s4vectors)))
10205 (home-page "https://github.com/jotsetung/ensembldb")
10206 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10208 "The package provides functions to create and use transcript-centric
10209 annotation databases/packages. The annotation for the databases are directly
10210 fetched from Ensembl using their Perl API. The functionality and data is
10211 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10212 but, in addition to retrieve all gene/transcript models and annotations from
10213 the database, the @code{ensembldb} package also provides a filter framework
10214 allowing to retrieve annotations for specific entries like genes encoded on a
10215 chromosome region or transcript models of lincRNA genes.")
10216 ;; No version specified
10217 (license license:lgpl3+)))
10219 (define-public r-organismdbi
10221 (name "r-organismdbi")
10226 (uri (bioconductor-uri "OrganismDbi" version))
10229 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10230 (properties `((upstream-name . "OrganismDbi")))
10231 (build-system r-build-system)
10233 `(("r-annotationdbi" ,r-annotationdbi)
10234 ("r-biobase" ,r-biobase)
10235 ("r-biocgenerics" ,r-biocgenerics)
10236 ("r-biocmanager" ,r-biocmanager)
10238 ("r-genomicfeatures" ,r-genomicfeatures)
10239 ("r-genomicranges" ,r-genomicranges)
10240 ("r-graph" ,r-graph)
10241 ("r-iranges" ,r-iranges)
10243 ("r-s4vectors" ,r-s4vectors)))
10244 (home-page "https://bioconductor.org/packages/OrganismDbi")
10245 (synopsis "Software to enable the smooth interfacing of database packages")
10246 (description "The package enables a simple unified interface to several
10247 annotation packages each of which has its own schema by taking advantage of
10248 the fact that each of these packages implements a select methods.")
10249 (license license:artistic2.0)))
10251 (define-public r-biovizbase
10253 (name "r-biovizbase")
10258 (uri (bioconductor-uri "biovizBase" version))
10261 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
10262 (properties `((upstream-name . "biovizBase")))
10263 (build-system r-build-system)
10265 `(("r-annotationdbi" ,r-annotationdbi)
10266 ("r-annotationfilter" ,r-annotationfilter)
10267 ("r-biocgenerics" ,r-biocgenerics)
10268 ("r-biostrings" ,r-biostrings)
10269 ("r-dichromat" ,r-dichromat)
10270 ("r-ensembldb" ,r-ensembldb)
10271 ("r-genomeinfodb" ,r-genomeinfodb)
10272 ("r-genomicalignments" ,r-genomicalignments)
10273 ("r-genomicfeatures" ,r-genomicfeatures)
10274 ("r-genomicranges" ,r-genomicranges)
10275 ("r-hmisc" ,r-hmisc)
10276 ("r-iranges" ,r-iranges)
10277 ("r-rcolorbrewer" ,r-rcolorbrewer)
10278 ("r-rlang" ,r-rlang)
10279 ("r-rsamtools" ,r-rsamtools)
10280 ("r-s4vectors" ,r-s4vectors)
10281 ("r-scales" ,r-scales)
10282 ("r-summarizedexperiment" ,r-summarizedexperiment)
10283 ("r-variantannotation" ,r-variantannotation)))
10284 (home-page "https://bioconductor.org/packages/biovizBase")
10285 (synopsis "Basic graphic utilities for visualization of genomic data")
10287 "The biovizBase package is designed to provide a set of utilities, color
10288 schemes and conventions for genomic data. It serves as the base for various
10289 high-level packages for biological data visualization. This saves development
10290 effort and encourages consistency.")
10291 (license license:artistic2.0)))
10293 (define-public r-ggbio
10300 (uri (bioconductor-uri "ggbio" version))
10303 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10304 (build-system r-build-system)
10306 `(("r-annotationdbi" ,r-annotationdbi)
10307 ("r-annotationfilter" ,r-annotationfilter)
10308 ("r-biobase" ,r-biobase)
10309 ("r-biocgenerics" ,r-biocgenerics)
10310 ("r-biostrings" ,r-biostrings)
10311 ("r-biovizbase" ,r-biovizbase)
10312 ("r-bsgenome" ,r-bsgenome)
10313 ("r-ensembldb" ,r-ensembldb)
10314 ("r-genomeinfodb" ,r-genomeinfodb)
10315 ("r-genomicalignments" ,r-genomicalignments)
10316 ("r-genomicfeatures" ,r-genomicfeatures)
10317 ("r-genomicranges" ,r-genomicranges)
10318 ("r-ggally" ,r-ggally)
10319 ("r-ggplot2" ,r-ggplot2)
10320 ("r-gridextra" ,r-gridextra)
10321 ("r-gtable" ,r-gtable)
10322 ("r-hmisc" ,r-hmisc)
10323 ("r-iranges" ,r-iranges)
10324 ("r-organismdbi" ,r-organismdbi)
10325 ("r-reshape2" ,r-reshape2)
10326 ("r-rlang" ,r-rlang)
10327 ("r-rsamtools" ,r-rsamtools)
10328 ("r-rtracklayer" ,r-rtracklayer)
10329 ("r-s4vectors" ,r-s4vectors)
10330 ("r-scales" ,r-scales)
10331 ("r-summarizedexperiment" ,r-summarizedexperiment)
10332 ("r-variantannotation" ,r-variantannotation)))
10333 (home-page "http://www.tengfei.name/ggbio/")
10334 (synopsis "Visualization tools for genomic data")
10336 "The ggbio package extends and specializes the grammar of graphics for
10337 biological data. The graphics are designed to answer common scientific
10338 questions, in particular those often asked of high throughput genomics data.
10339 All core Bioconductor data structures are supported, where appropriate. The
10340 package supports detailed views of particular genomic regions, as well as
10341 genome-wide overviews. Supported overviews include ideograms and grand linear
10342 views. High-level plots include sequence fragment length, edge-linked
10343 interval to data view, mismatch pileup, and several splicing summaries.")
10344 (license license:artistic2.0)))
10346 (define-public r-gprofiler
10348 (name "r-gprofiler")
10353 (uri (cran-uri "gProfileR" version))
10356 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10357 (properties `((upstream-name . "gProfileR")))
10358 (build-system r-build-system)
10360 `(("r-plyr" ,r-plyr)
10361 ("r-rcurl" ,r-rcurl)))
10362 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10363 (synopsis "Interface to the g:Profiler toolkit")
10365 "This package provides tools for functional enrichment analysis,
10366 gene identifier conversion and mapping homologous genes across related
10367 organisms via the @code{g:Profiler} toolkit.")
10368 (license license:gpl2+)))
10370 (define-public r-gqtlbase
10372 (name "r-gqtlbase")
10377 (uri (bioconductor-uri "gQTLBase" version))
10380 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10381 (properties `((upstream-name . "gQTLBase")))
10382 (build-system r-build-system)
10384 `(("r-batchjobs" ,r-batchjobs)
10385 ("r-bbmisc" ,r-bbmisc)
10386 ("r-biocgenerics" ,r-biocgenerics)
10388 ("r-doparallel" ,r-doparallel)
10390 ("r-ffbase" ,r-ffbase)
10391 ("r-foreach" ,r-foreach)
10392 ("r-genomicfiles" ,r-genomicfiles)
10393 ("r-genomicranges" ,r-genomicranges)
10394 ("r-rtracklayer" ,r-rtracklayer)
10395 ("r-s4vectors" ,r-s4vectors)
10396 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10397 (home-page "https://bioconductor.org/packages/gQTLBase")
10398 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10400 "The purpose of this package is to simplify the storage and interrogation
10401 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10403 (license license:artistic2.0)))
10405 (define-public r-snpstats
10407 (name "r-snpstats")
10412 (uri (bioconductor-uri "snpStats" version))
10415 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10416 (properties `((upstream-name . "snpStats")))
10417 (build-system r-build-system)
10418 (inputs `(("zlib" ,zlib)))
10420 `(("r-biocgenerics" ,r-biocgenerics)
10421 ("r-matrix" ,r-matrix)
10422 ("r-survival" ,r-survival)
10423 ("r-zlibbioc" ,r-zlibbioc)))
10424 (home-page "https://bioconductor.org/packages/snpStats")
10425 (synopsis "Methods for SNP association studies")
10427 "This package provides classes and statistical methods for large
10428 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10429 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10430 (license license:gpl3)))
10432 (define-public r-homo-sapiens
10434 (name "r-homo-sapiens")
10438 ;; We cannot use bioconductor-uri here because this tarball is
10439 ;; located under "data/annotation/" instead of "bioc/".
10440 (uri (string-append "http://www.bioconductor.org/packages/"
10441 "release/data/annotation/src/contrib/"
10443 version ".tar.gz"))
10446 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10448 `((upstream-name . "Homo.sapiens")))
10449 (build-system r-build-system)
10451 `(("r-genomicfeatures" ,r-genomicfeatures)
10452 ("r-go-db" ,r-go-db)
10453 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10454 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10455 ("r-organismdbi" ,r-organismdbi)
10456 ("r-annotationdbi" ,r-annotationdbi)))
10457 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10458 (synopsis "Annotation package for the Homo.sapiens object")
10460 "This package contains the Homo.sapiens object to access data from
10461 several related annotation packages.")
10462 (license license:artistic2.0)))
10464 (define-public r-erma
10471 (uri (bioconductor-uri "erma" version))
10474 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10475 (build-system r-build-system)
10477 `(("r-annotationdbi" ,r-annotationdbi)
10478 ("r-biobase" ,r-biobase)
10479 ("r-biocgenerics" ,r-biocgenerics)
10480 ("r-biocparallel" ,r-biocparallel)
10481 ("r-genomeinfodb" ,r-genomeinfodb)
10482 ("r-genomicfiles" ,r-genomicfiles)
10483 ("r-genomicranges" ,r-genomicranges)
10484 ("r-ggplot2" ,r-ggplot2)
10485 ("r-homo-sapiens" ,r-homo-sapiens)
10486 ("r-iranges" ,r-iranges)
10487 ("r-rtracklayer" ,r-rtracklayer)
10488 ("r-s4vectors" ,r-s4vectors)
10489 ("r-shiny" ,r-shiny)
10490 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10491 (home-page "https://bioconductor.org/packages/erma")
10492 (synopsis "Epigenomic road map adventures")
10494 "The epigenomics road map describes locations of epigenetic marks in DNA
10495 from a variety of cell types. Of interest are locations of histone
10496 modifications, sites of DNA methylation, and regions of accessible chromatin.
10497 This package presents a selection of elements of the road map including
10498 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10499 by Ernst and Kellis.")
10500 (license license:artistic2.0)))
10502 (define-public r-ldblock
10509 (uri (bioconductor-uri "ldblock" version))
10512 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10513 (build-system r-build-system)
10515 `(("r-biocgenerics" ,r-biocgenerics)
10517 ("r-genomeinfodb" ,r-genomeinfodb)
10518 ("r-genomicfiles" ,r-genomicfiles)
10519 ("r-go-db" ,r-go-db)
10520 ("r-homo-sapiens" ,r-homo-sapiens)
10521 ("r-matrix" ,r-matrix)
10522 ("r-rsamtools" ,r-rsamtools)
10523 ("r-snpstats" ,r-snpstats)
10524 ("r-variantannotation" ,r-variantannotation)))
10525 (home-page "https://bioconductor.org/packages/ldblock")
10526 (synopsis "Data structures for linkage disequilibrium measures in populations")
10528 "This package defines data structures for @dfn{linkage
10529 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10530 handling of existing population-level data for the purpose of flexibly
10531 defining LD blocks.")
10532 (license license:artistic2.0)))
10534 (define-public r-gqtlstats
10536 (name "r-gqtlstats")
10541 (uri (bioconductor-uri "gQTLstats" version))
10544 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10545 (properties `((upstream-name . "gQTLstats")))
10546 (build-system r-build-system)
10548 `(("r-annotationdbi" ,r-annotationdbi)
10549 ("r-batchjobs" ,r-batchjobs)
10550 ("r-bbmisc" ,r-bbmisc)
10551 ("r-beeswarm" ,r-beeswarm)
10552 ("r-biobase" ,r-biobase)
10553 ("r-biocgenerics" ,r-biocgenerics)
10554 ("r-doparallel" ,r-doparallel)
10555 ("r-dplyr" ,r-dplyr)
10557 ("r-ffbase" ,r-ffbase)
10558 ("r-foreach" ,r-foreach)
10559 ("r-genomeinfodb" ,r-genomeinfodb)
10560 ("r-genomicfeatures" ,r-genomicfeatures)
10561 ("r-genomicfiles" ,r-genomicfiles)
10562 ("r-genomicranges" ,r-genomicranges)
10563 ("r-ggbeeswarm" ,r-ggbeeswarm)
10564 ("r-ggplot2" ,r-ggplot2)
10565 ("r-gqtlbase" ,r-gqtlbase)
10566 ("r-hardyweinberg" ,r-hardyweinberg)
10567 ("r-homo-sapiens" ,r-homo-sapiens)
10568 ("r-iranges" ,r-iranges)
10569 ("r-limma" ,r-limma)
10571 ("r-plotly" ,r-plotly)
10572 ("r-reshape2" ,r-reshape2)
10573 ("r-s4vectors" ,r-s4vectors)
10574 ("r-shiny" ,r-shiny)
10575 ("r-snpstats" ,r-snpstats)
10576 ("r-summarizedexperiment" ,r-summarizedexperiment)
10577 ("r-variantannotation" ,r-variantannotation)))
10578 (home-page "https://bioconductor.org/packages/gQTLstats")
10579 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10581 "This package provides tools for the computationally efficient analysis
10582 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10583 The software in this package aims to support refinements and functional
10584 interpretation of members of a collection of association statistics on a
10585 family of feature/genome hypotheses.")
10586 (license license:artistic2.0)))
10588 (define-public r-gviz
10595 (uri (bioconductor-uri "Gviz" version))
10598 "0jvcivgw0ahv2rjadxmrww76xambhf7silczmh38nn4yn4qw6w9y"))))
10599 (properties `((upstream-name . "Gviz")))
10600 (build-system r-build-system)
10602 `(("r-annotationdbi" ,r-annotationdbi)
10603 ("r-biobase" ,r-biobase)
10604 ("r-biocgenerics" ,r-biocgenerics)
10605 ("r-biomart" ,r-biomart)
10606 ("r-biostrings" ,r-biostrings)
10607 ("r-biovizbase" ,r-biovizbase)
10608 ("r-bsgenome" ,r-bsgenome)
10609 ("r-digest" ,r-digest)
10610 ("r-genomeinfodb" ,r-genomeinfodb)
10611 ("r-genomicalignments" ,r-genomicalignments)
10612 ("r-genomicfeatures" ,r-genomicfeatures)
10613 ("r-genomicranges" ,r-genomicranges)
10614 ("r-iranges" ,r-iranges)
10615 ("r-lattice" ,r-lattice)
10616 ("r-latticeextra" ,r-latticeextra)
10617 ("r-matrixstats" ,r-matrixstats)
10618 ("r-rcolorbrewer" ,r-rcolorbrewer)
10619 ("r-rsamtools" ,r-rsamtools)
10620 ("r-rtracklayer" ,r-rtracklayer)
10621 ("r-s4vectors" ,r-s4vectors)
10622 ("r-xvector" ,r-xvector)))
10623 (home-page "https://bioconductor.org/packages/Gviz")
10624 (synopsis "Plotting data and annotation information along genomic coordinates")
10626 "Genomic data analyses requires integrated visualization of known genomic
10627 information and new experimental data. Gviz uses the biomaRt and the
10628 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10629 and translates this to e.g. gene/transcript structures in viewports of the
10630 grid graphics package. This results in genomic information plotted together
10632 (license license:artistic2.0)))
10634 (define-public r-gwascat
10641 (uri (bioconductor-uri "gwascat" version))
10644 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10645 (build-system r-build-system)
10647 `(("r-annotationdbi" ,r-annotationdbi)
10648 ("r-annotationhub" ,r-annotationhub)
10649 ("r-biocgenerics" ,r-biocgenerics)
10650 ("r-biostrings" ,r-biostrings)
10651 ("r-genomeinfodb" ,r-genomeinfodb)
10652 ("r-genomicfeatures" ,r-genomicfeatures)
10653 ("r-genomicranges" ,r-genomicranges)
10654 ("r-ggbio" ,r-ggbio)
10655 ("r-ggplot2" ,r-ggplot2)
10656 ("r-gqtlstats" ,r-gqtlstats)
10657 ("r-graph" ,r-graph)
10659 ("r-homo-sapiens" ,r-homo-sapiens)
10660 ("r-iranges" ,r-iranges)
10661 ("r-rsamtools" ,r-rsamtools)
10662 ("r-rtracklayer" ,r-rtracklayer)
10663 ("r-s4vectors" ,r-s4vectors)
10664 ("r-snpstats" ,r-snpstats)
10665 ("r-summarizedexperiment" ,r-summarizedexperiment)
10666 ("r-variantannotation" ,r-variantannotation)))
10667 (home-page "https://bioconductor.org/packages/gwascat")
10668 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10670 "This package provides tools for representing and modeling data in the
10671 EMBL-EBI GWAS catalog.")
10672 (license license:artistic2.0)))
10674 (define-public r-sushi
10680 (uri (bioconductor-uri "Sushi" version))
10683 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10684 (properties `((upstream-name . "Sushi")))
10685 (build-system r-build-system)
10687 `(("r-biomart" ,r-biomart)
10689 (home-page "https://bioconductor.org/packages/Sushi")
10690 (synopsis "Tools for visualizing genomics data")
10692 "This package provides flexible, quantitative, and integrative genomic
10693 visualizations for publication-quality multi-panel figures.")
10694 (license license:gpl2+)))
10696 (define-public r-fithic
10702 (uri (bioconductor-uri "FitHiC" version))
10705 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10706 (properties `((upstream-name . "FitHiC")))
10707 (build-system r-build-system)
10709 `(("r-data-table" ,r-data-table)
10710 ("r-fdrtool" ,r-fdrtool)
10711 ("r-rcpp" ,r-rcpp)))
10712 (home-page "https://bioconductor.org/packages/FitHiC")
10713 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10715 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10716 intra-chromosomal contact maps produced by genome-wide genome architecture
10717 assays such as Hi-C.")
10718 (license license:gpl2+)))
10720 (define-public r-hitc
10726 (uri (bioconductor-uri "HiTC" version))
10729 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10730 (properties `((upstream-name . "HiTC")))
10731 (build-system r-build-system)
10733 `(("r-biostrings" ,r-biostrings)
10734 ("r-genomeinfodb" ,r-genomeinfodb)
10735 ("r-genomicranges" ,r-genomicranges)
10736 ("r-iranges" ,r-iranges)
10737 ("r-matrix" ,r-matrix)
10738 ("r-rcolorbrewer" ,r-rcolorbrewer)
10739 ("r-rtracklayer" ,r-rtracklayer)))
10740 (home-page "https://bioconductor.org/packages/HiTC")
10741 (synopsis "High throughput chromosome conformation capture analysis")
10743 "The HiTC package was developed to explore high-throughput \"C\" data
10744 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10745 quality controls, normalization, visualization, and further analysis are also
10747 (license license:artistic2.0)))
10749 (define-public r-qvalue
10756 (uri (bioconductor-uri "qvalue" version))
10759 "0kxavzm1j2mk26qicmjm90nxx4w5h3dxighzks7wzihay3k8cysc"))))
10760 (build-system r-build-system)
10762 `(("r-ggplot2" ,r-ggplot2)
10763 ("r-reshape2" ,r-reshape2)))
10764 (home-page "http://github.com/jdstorey/qvalue")
10765 (synopsis "Q-value estimation for false discovery rate control")
10767 "This package takes a list of p-values resulting from the simultaneous
10768 testing of many hypotheses and estimates their q-values and local @dfn{false
10769 discovery rate} (FDR) values. The q-value of a test measures the proportion
10770 of false positives incurred when that particular test is called significant.
10771 The local FDR measures the posterior probability the null hypothesis is true
10772 given the test's p-value. Various plots are automatically generated, allowing
10773 one to make sensible significance cut-offs. The software can be applied to
10774 problems in genomics, brain imaging, astrophysics, and data mining.")
10775 ;; Any version of the LGPL.
10776 (license license:lgpl3+)))
10778 (define-public r-hdf5array
10780 (name "r-hdf5array")
10785 (uri (bioconductor-uri "HDF5Array" version))
10788 "1qwdsygcadl58qj598hfyvs8hp0hqcl9ghnhknahrlhmb7k2bd2d"))))
10789 (properties `((upstream-name . "HDF5Array")))
10790 (build-system r-build-system)
10792 `(("r-biocgenerics" ,r-biocgenerics)
10793 ("r-delayedarray" ,r-delayedarray)
10794 ("r-iranges" ,r-iranges)
10795 ("r-rhdf5" ,r-rhdf5)
10796 ("r-s4vectors" ,r-s4vectors)))
10797 (home-page "https://bioconductor.org/packages/HDF5Array")
10798 (synopsis "HDF5 back end for DelayedArray objects")
10799 (description "This package provides an array-like container for convenient
10800 access and manipulation of HDF5 datasets. It supports delayed operations and
10801 block processing.")
10802 (license license:artistic2.0)))
10804 (define-public r-rhdf5lib
10806 (name "r-rhdf5lib")
10811 (uri (bioconductor-uri "Rhdf5lib" version))
10814 "06bxd3wz8lrvh2hzvmjpdv4lvzj5lz9353bw5b3zb98cb8w9r2j5"))
10815 (modules '((guix build utils)))
10818 ;; Delete bundled binaries
10819 (delete-file-recursively "src/winlib/")
10821 (properties `((upstream-name . "Rhdf5lib")))
10822 (build-system r-build-system)
10825 (modify-phases %standard-phases
10826 (add-after 'unpack 'do-not-use-bundled-hdf5
10827 (lambda* (#:key inputs #:allow-other-keys)
10828 (for-each delete-file '("configure" "configure.ac"))
10829 ;; Do not make other packages link with the proprietary libsz.
10830 (substitute* "R/zzz.R"
10831 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10832 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10833 (("'%s/libhdf5.a %s/libsz.a -lz'")
10834 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10835 (with-directory-excursion "src"
10836 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10837 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10839 ;; Remove timestamp and host system information to make
10840 ;; the build reproducible.
10841 (substitute* "hdf5/src/libhdf5.settings.in"
10842 (("Configured on: @CONFIG_DATE@")
10843 "Configured on: Guix")
10844 (("Uname information:.*")
10845 "Uname information: Linux\n")
10846 ;; Remove unnecessary store reference.
10848 "C Compiler: GCC\n"))
10849 (rename-file "Makevars.in" "Makevars")
10850 (substitute* "Makevars"
10851 (("HDF5_CXX_LIB=.*")
10852 (string-append "HDF5_CXX_LIB="
10853 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10855 (string-append "HDF5_LIB="
10856 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10857 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10858 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10859 ;; szip is non-free software
10860 (("cp \\$\\{SZIP_LIB\\}.*") "")
10861 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10866 `(("hdf5" ,hdf5-1.10)))
10868 `(("hdf5-source" ,(package-source hdf5-1.10))))
10869 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10870 (synopsis "HDF5 library as an R package")
10871 (description "This package provides C and C++ HDF5 libraries for use in R
10873 (license license:artistic2.0)))
10875 (define-public r-beachmat
10877 (name "r-beachmat")
10882 (uri (bioconductor-uri "beachmat" version))
10885 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10886 (build-system r-build-system)
10891 `(("r-biocgenerics" ,r-biocgenerics)
10892 ("r-delayedarray" ,r-delayedarray)
10893 ("r-hdf5array" ,r-hdf5array)
10895 ("r-rhdf5" ,r-rhdf5)
10896 ("r-rhdf5lib" ,r-rhdf5lib)))
10897 (home-page "https://bioconductor.org/packages/beachmat")
10898 (synopsis "Compiling Bioconductor to handle each matrix type")
10899 (description "This package provides a consistent C++ class interface for a
10900 variety of commonly used matrix types, including sparse and HDF5-backed
10902 (license license:gpl3)))
10904 (define-public r-singlecellexperiment
10906 (name "r-singlecellexperiment")
10911 (uri (bioconductor-uri "SingleCellExperiment" version))
10914 "12139kk9cqgzpm6f3cwdsq31gj5lxamz2q939dy9fa0fa54gdaq4"))))
10916 `((upstream-name . "SingleCellExperiment")))
10917 (build-system r-build-system)
10919 `(("r-biocgenerics" ,r-biocgenerics)
10920 ("r-s4vectors" ,r-s4vectors)
10921 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10922 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10923 (synopsis "S4 classes for single cell data")
10924 (description "This package defines an S4 class for storing data from
10925 single-cell experiments. This includes specialized methods to store and
10926 retrieve spike-in information, dimensionality reduction coordinates and size
10927 factors for each cell, along with the usual metadata for genes and
10929 (license license:gpl3)))
10931 (define-public r-scater
10937 (uri (bioconductor-uri "scater" version))
10940 "0rijhy7g5qmcn927y1wyd63la1fhyar9fv1hccsqd23jd98yc55a"))))
10941 (build-system r-build-system)
10943 `(("r-beachmat" ,r-beachmat)
10944 ("r-biocgenerics" ,r-biocgenerics)
10945 ("r-biocparallel" ,r-biocparallel)
10946 ("r-delayedarray" ,r-delayedarray)
10947 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10948 ("r-dplyr" ,r-dplyr)
10949 ("r-ggbeeswarm" ,r-ggbeeswarm)
10950 ("r-ggplot2" ,r-ggplot2)
10951 ("r-matrix" ,r-matrix)
10954 ("r-reshape2" ,r-reshape2)
10955 ("r-rhdf5lib" ,r-rhdf5lib)
10956 ("r-s4vectors" ,r-s4vectors)
10957 ("r-singlecellexperiment" ,r-singlecellexperiment)
10958 ("r-summarizedexperiment" ,r-summarizedexperiment)
10959 ("r-viridis" ,r-viridis)))
10960 (home-page "https://github.com/davismcc/scater")
10961 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10962 (description "This package provides a collection of tools for doing
10963 various analyses of single-cell RNA-seq gene expression data, with a focus on
10965 (license license:gpl2+)))
10967 (define-public r-scran
10974 (uri (bioconductor-uri "scran" version))
10977 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
10978 (build-system r-build-system)
10980 `(("r-beachmat" ,r-beachmat)
10981 ("r-biocgenerics" ,r-biocgenerics)
10982 ("r-biocneighbors" ,r-biocneighbors)
10983 ("r-biocparallel" ,r-biocparallel)
10984 ("r-delayedarray" ,r-delayedarray)
10985 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10986 ("r-dynamictreecut" ,r-dynamictreecut)
10987 ("r-edger" ,r-edger)
10988 ("r-igraph" ,r-igraph)
10989 ("r-limma" ,r-limma)
10990 ("r-matrix" ,r-matrix)
10992 ("r-rhdf5lib" ,r-rhdf5lib)
10993 ("r-s4vectors" ,r-s4vectors)
10994 ("r-scater" ,r-scater)
10995 ("r-singlecellexperiment" ,r-singlecellexperiment)
10996 ("r-statmod" ,r-statmod)
10997 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10998 (home-page "https://bioconductor.org/packages/scran")
10999 (synopsis "Methods for single-cell RNA-Seq data analysis")
11000 (description "This package implements a variety of low-level analyses of
11001 single-cell RNA-seq data. Methods are provided for normalization of
11002 cell-specific biases, assignment of cell cycle phase, and detection of highly
11003 variable and significantly correlated genes.")
11004 (license license:gpl3)))
11006 (define-public r-delayedmatrixstats
11008 (name "r-delayedmatrixstats")
11013 (uri (bioconductor-uri "DelayedMatrixStats" version))
11016 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11018 `((upstream-name . "DelayedMatrixStats")))
11019 (build-system r-build-system)
11021 `(("r-biocparallel" ,r-biocparallel)
11022 ("r-delayedarray" ,r-delayedarray)
11023 ("r-hdf5array" ,r-hdf5array)
11024 ("r-iranges" ,r-iranges)
11025 ("r-matrix" ,r-matrix)
11026 ("r-matrixstats" ,r-matrixstats)
11027 ("r-s4vectors" ,r-s4vectors)))
11028 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11029 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11031 "This package provides a port of the @code{matrixStats} API for use with
11032 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11033 contains high-performing functions operating on rows and columns of
11034 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11035 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11036 are optimized per data type and for subsetted calculations such that both
11037 memory usage and processing time is minimized.")
11038 (license license:expat)))
11040 (define-public r-phangorn
11042 (name "r-phangorn")
11047 (uri (cran-uri "phangorn" version))
11050 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11051 (build-system r-build-system)
11054 ("r-fastmatch" ,r-fastmatch)
11055 ("r-igraph" ,r-igraph)
11056 ("r-magrittr" ,r-magrittr)
11057 ("r-matrix" ,r-matrix)
11058 ("r-quadprog" ,r-quadprog)
11059 ("r-rcpp" ,r-rcpp)))
11060 (home-page "https://github.com/KlausVigo/phangorn")
11061 (synopsis "Phylogenetic analysis in R")
11063 "Phangorn is a package for phylogenetic analysis in R. It supports
11064 estimation of phylogenetic trees and networks using Maximum Likelihood,
11065 Maximum Parsimony, distance methods and Hadamard conjugation.")
11066 (license license:gpl2+)))
11068 (define-public r-dropbead
11069 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11072 (name "r-dropbead")
11073 (version (string-append "0-" revision "." (string-take commit 7)))
11077 (uri (git-reference
11078 (url "https://github.com/rajewsky-lab/dropbead.git")
11080 (file-name (git-file-name name version))
11083 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11084 (build-system r-build-system)
11086 `(("r-ggplot2" ,r-ggplot2)
11087 ("r-rcolorbrewer" ,r-rcolorbrewer)
11088 ("r-gridextra" ,r-gridextra)
11089 ("r-gplots" ,r-gplots)
11090 ("r-plyr" ,r-plyr)))
11091 (home-page "https://github.com/rajewsky-lab/dropbead")
11092 (synopsis "Basic exploration and analysis of Drop-seq data")
11093 (description "This package offers a quick and straight-forward way to
11094 explore and perform basic analysis of single cell sequencing data coming from
11095 droplet sequencing. It has been particularly tailored for Drop-seq.")
11096 (license license:gpl3))))
11098 (define htslib-for-sambamba
11099 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11102 (name "htslib-for-sambamba")
11103 (version (string-append "1.3.1-1." (string-take commit 9)))
11107 (uri (git-reference
11108 (url "https://github.com/lomereiter/htslib.git")
11110 (file-name (string-append "htslib-" version "-checkout"))
11113 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11115 `(("autoconf" ,autoconf)
11116 ("automake" ,automake)
11117 ,@(package-native-inputs htslib))))))
11119 (define-public sambamba
11126 (uri (git-reference
11127 (url "https://github.com/lomereiter/sambamba.git")
11128 (commit (string-append "v" version))))
11129 (file-name (string-append name "-" version "-checkout"))
11132 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
11133 (build-system gnu-build-system)
11135 `(#:tests? #f ; there is no test target
11136 #:parallel-build? #f ; not supported
11138 (modify-phases %standard-phases
11139 (delete 'configure)
11140 (add-after 'unpack 'fix-ldc-version
11142 (substitute* "gen_ldc_version_info.py"
11143 (("/usr/bin/env.*") (which "python3")))
11144 (substitute* "Makefile"
11145 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11146 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11148 (add-after 'unpack 'place-biod-and-undead
11149 (lambda* (#:key inputs #:allow-other-keys)
11150 (copy-recursively (assoc-ref inputs "biod") "BioD")
11151 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11153 (add-after 'unpack 'unbundle-prerequisites
11155 (substitute* "Makefile"
11156 (("htslib/libhts.a lz4/lib/liblz4.a")
11158 ((" lz4-static htslib-static") ""))
11161 (lambda* (#:key outputs #:allow-other-keys)
11162 (let* ((out (assoc-ref outputs "out"))
11163 (bin (string-append out "/bin")))
11165 (install-file "bin/sambamba" bin)
11170 ("python" ,python-minimal)
11172 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
11175 (uri (git-reference
11176 (url "https://github.com/biod/BioD.git")
11178 (file-name (string-append "biod-"
11179 (string-take commit 9)
11183 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
11185 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
11188 (uri (git-reference
11189 (url "https://github.com/biod/undeaD.git")
11191 (file-name (string-append "undead-"
11192 (string-take commit 9)
11196 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11199 ("htslib" ,htslib-for-sambamba)))
11200 (home-page "http://lomereiter.github.io/sambamba")
11201 (synopsis "Tools for working with SAM/BAM data")
11202 (description "Sambamba is a high performance modern robust and
11203 fast tool (and library), written in the D programming language, for
11204 working with SAM and BAM files. Current parallelised functionality is
11205 an important subset of samtools functionality, including view, index,
11206 sort, markdup, and depth.")
11207 (license license:gpl2+)))
11209 (define-public ritornello
11211 (name "ritornello")
11215 (uri (git-reference
11216 (url "https://github.com/KlugerLab/Ritornello.git")
11217 (commit (string-append "v" version))))
11218 (file-name (git-file-name name version))
11221 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11222 (build-system gnu-build-system)
11224 `(#:tests? #f ; there are no tests
11226 (modify-phases %standard-phases
11227 (add-after 'unpack 'patch-samtools-references
11228 (lambda* (#:key inputs #:allow-other-keys)
11229 (substitute* '("src/SamStream.h"
11231 (("<sam.h>") "<samtools/sam.h>"))
11233 (delete 'configure)
11235 (lambda* (#:key inputs outputs #:allow-other-keys)
11236 (let* ((out (assoc-ref outputs "out"))
11237 (bin (string-append out "/bin/")))
11239 (install-file "bin/Ritornello" bin)
11242 `(("samtools" ,samtools-0.1)
11246 (home-page "https://github.com/KlugerLab/Ritornello")
11247 (synopsis "Control-free peak caller for ChIP-seq data")
11248 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11249 signal processing that can accurately call binding events without the need to
11250 do a pair total DNA input or IgG control sample. It has been tested for use
11251 with narrow binding events such as transcription factor ChIP-seq.")
11252 (license license:gpl3+)))
11254 (define-public trim-galore
11256 (name "trim-galore")
11261 (uri (git-reference
11262 (url "https://github.com/FelixKrueger/TrimGalore.git")
11264 (file-name (string-append name "-" version "-checkout"))
11267 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11268 (build-system gnu-build-system)
11270 `(#:tests? #f ; no tests
11272 (modify-phases %standard-phases
11273 (delete 'configure)
11275 (add-after 'unpack 'hardcode-tool-references
11276 (lambda* (#:key inputs #:allow-other-keys)
11277 (substitute* "trim_galore"
11278 (("\\$path_to_cutadapt = 'cutadapt'")
11279 (string-append "$path_to_cutadapt = '"
11280 (assoc-ref inputs "cutadapt")
11283 (string-append "| "
11284 (assoc-ref inputs "gzip")
11287 (string-append "\""
11288 (assoc-ref inputs "gzip")
11292 (lambda* (#:key outputs #:allow-other-keys)
11293 (let ((bin (string-append (assoc-ref outputs "out")
11296 (install-file "trim_galore" bin)
11301 ("cutadapt" ,cutadapt)))
11303 `(("unzip" ,unzip)))
11304 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11305 (synopsis "Wrapper around Cutadapt and FastQC")
11306 (description "Trim Galore! is a wrapper script to automate quality and
11307 adapter trimming as well as quality control, with some added functionality to
11308 remove biased methylation positions for RRBS sequence files.")
11309 (license license:gpl3+)))
11311 (define-public gess
11317 (uri (string-append "http://compbio.uthscsa.edu/"
11319 "gess-" version ".src.tar.gz"))
11322 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11323 (build-system gnu-build-system)
11325 `(#:tests? #f ; no tests
11327 (modify-phases %standard-phases
11328 (delete 'configure)
11331 (lambda* (#:key inputs outputs #:allow-other-keys)
11332 (let* ((python (assoc-ref inputs "python"))
11333 (out (assoc-ref outputs "out"))
11334 (bin (string-append out "/bin/"))
11335 (target (string-append
11337 ,(version-major+minor
11338 (package-version python))
11339 "/site-packages/gess/")))
11341 (copy-recursively "." target)
11342 ;; Make GESS.py executable
11343 (chmod (string-append target "GESS.py") #o555)
11344 ;; Add Python shebang to the top and make Matplotlib
11346 (substitute* (string-append target "GESS.py")
11347 (("\"\"\"Description:" line)
11348 (string-append "#!" (which "python") "
11350 matplotlib.use('Agg')
11352 ;; Make sure GESS has all modules in its path
11353 (wrap-program (string-append target "GESS.py")
11354 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11356 (symlink (string-append target "GESS.py")
11357 (string-append bin "GESS.py"))
11360 `(("python" ,python-2)
11361 ("python2-pysam" ,python2-pysam)
11362 ("python2-scipy" ,python2-scipy)
11363 ("python2-numpy" ,python2-numpy)
11364 ("python2-networkx" ,python2-networkx)
11365 ("python2-biopython" ,python2-biopython)))
11366 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11367 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11369 "GESS is an implementation of a novel computational method to detect de
11370 novo exon-skipping events directly from raw RNA-seq data without the prior
11371 knowledge of gene annotation information. GESS stands for the graph-based
11372 exon-skipping scanner detection scheme.")
11373 (license license:bsd-3)))
11375 (define-public phylip
11382 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11383 "download/phylip-" version ".tar.gz"))
11386 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11387 (build-system gnu-build-system)
11389 `(#:tests? #f ; no check target
11390 #:make-flags (list "-f" "Makefile.unx" "install")
11391 #:parallel-build? #f ; not supported
11393 (modify-phases %standard-phases
11394 (add-after 'unpack 'enter-dir
11395 (lambda _ (chdir "src") #t))
11396 (delete 'configure)
11398 (lambda* (#:key inputs outputs #:allow-other-keys)
11399 (let ((target (string-append (assoc-ref outputs "out")
11402 (for-each (lambda (file)
11403 (install-file file target))
11404 (find-files "../exe" ".*")))
11406 (home-page "http://evolution.genetics.washington.edu/phylip/")
11407 (synopsis "Tools for inferring phylogenies")
11408 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11409 programs for inferring phylogenies (evolutionary trees).")
11410 (license license:bsd-2)))
11419 (uri (string-append "https://integrativemodeling.org/"
11420 version "/download/imp-" version ".tar.gz"))
11423 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11424 (build-system cmake-build-system)
11426 `(;; FIXME: Some tests fail because they produce warnings, others fail
11427 ;; because the PYTHONPATH does not include the modeller's directory.
11435 ("python" ,python-2)))
11437 `(("python2-numpy" ,python2-numpy)
11438 ("python2-scipy" ,python2-scipy)
11439 ("python2-pandas" ,python2-pandas)
11440 ("python2-scikit-learn" ,python2-scikit-learn)
11441 ("python2-networkx" ,python2-networkx)))
11442 (home-page "https://integrativemodeling.org")
11443 (synopsis "Integrative modeling platform")
11444 (description "IMP's broad goal is to contribute to a comprehensive
11445 structural characterization of biomolecules ranging in size and complexity
11446 from small peptides to large macromolecular assemblies, by integrating data
11447 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11448 Python toolbox for solving complex modeling problems, and a number of
11449 applications for tackling some common problems in a user-friendly way.")
11450 ;; IMP is largely available under the GNU Lesser GPL; see the file
11451 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11452 ;; available under the GNU GPL (see the file COPYING.GPL).
11453 (license (list license:lgpl2.1+
11456 (define-public tadbit
11462 (uri (git-reference
11463 (url "https://github.com/3DGenomes/TADbit.git")
11464 (commit (string-append "v" version))))
11465 (file-name (git-file-name name version))
11468 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11469 (build-system python-build-system)
11471 `(;; Tests are included and must be run after installation, but
11472 ;; they are incomplete and thus cannot be run.
11476 (modify-phases %standard-phases
11477 (add-after 'unpack 'fix-problems-with-setup.py
11478 (lambda* (#:key outputs #:allow-other-keys)
11479 ;; setup.py opens these files for writing
11480 (chmod "_pytadbit/_version.py" #o664)
11481 (chmod "README.rst" #o664)
11483 ;; Don't attempt to install the bash completions to
11484 ;; the home directory.
11485 (rename-file "extras/.bash_completion"
11487 (substitute* "setup.py"
11488 (("\\(path.expanduser\\('~'\\)")
11489 (string-append "(\""
11490 (assoc-ref outputs "out")
11491 "/etc/bash_completion.d\""))
11492 (("extras/\\.bash_completion")
11496 ;; TODO: add Chimera for visualization
11499 ("python2-scipy" ,python2-scipy)
11500 ("python2-numpy" ,python2-numpy)
11501 ("python2-matplotlib" ,python2-matplotlib)
11502 ("python2-pysam" ,python2-pysam)))
11503 (home-page "https://3dgenomes.github.io/TADbit/")
11504 (synopsis "Analyze, model, and explore 3C-based data")
11506 "TADbit is a complete Python library to deal with all steps to analyze,
11507 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11508 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11509 correct interaction matrices, identify and compare the so-called
11510 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11511 interaction matrices, and finally, extract structural properties from the
11512 models. TADbit is complemented by TADkit for visualizing 3D models.")
11513 (license license:gpl3+)))
11515 (define-public kentutils
11518 ;; 302.1.0 is out, but the only difference is the inclusion of
11519 ;; pre-built binaries.
11520 (version "302.0.0")
11524 (uri (git-reference
11525 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11526 (commit (string-append "v" version))))
11527 (file-name (git-file-name name version))
11530 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11531 (modules '((guix build utils)
11536 ;; Only the contents of the specified directories are free
11537 ;; for all uses, so we remove the rest. "hg/autoSql" and
11538 ;; "hg/autoXml" are nominally free, but they depend on a
11539 ;; library that is built from the sources in "hg/lib",
11540 ;; which is nonfree.
11541 (let ((free (list "." ".."
11542 "utils" "lib" "inc" "tagStorm"
11543 "parasol" "htslib"))
11544 (directory? (lambda (file)
11545 (eq? 'directory (stat:type (stat file))))))
11546 (for-each (lambda (file)
11547 (and (directory? file)
11548 (delete-file-recursively file)))
11549 (map (cut string-append "src/" <>)
11552 (not (member file free)))))))
11553 ;; Only make the utils target, not the userApps target,
11554 ;; because that requires libraries we won't build.
11555 (substitute* "Makefile"
11556 ((" userApps") " utils"))
11557 ;; Only build libraries that are free.
11558 (substitute* "src/makefile"
11559 (("DIRS =.*") "DIRS =\n")
11560 (("cd jkOwnLib.*") "")
11563 (substitute* "src/utils/makefile"
11564 ;; These tools depend on "jkhgap.a", which is part of the
11565 ;; nonfree "src/hg/lib" directory.
11566 (("raSqlQuery") "")
11567 (("pslLiftSubrangeBlat") "")
11569 ;; Do not build UCSC tools, which may require nonfree
11571 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11573 (build-system gnu-build-system)
11575 `( ;; There is no global test target and the test target for
11576 ;; individual tools depends on input files that are not
11580 (modify-phases %standard-phases
11581 (add-after 'unpack 'fix-permissions
11582 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11583 (add-after 'unpack 'fix-paths
11585 (substitute* "Makefile"
11586 (("/bin/echo") (which "echo")))
11588 (add-after 'unpack 'prepare-samtabix
11589 (lambda* (#:key inputs #:allow-other-keys)
11590 (copy-recursively (assoc-ref inputs "samtabix")
11593 (delete 'configure)
11595 (lambda* (#:key outputs #:allow-other-keys)
11596 (let ((bin (string-append (assoc-ref outputs "out")
11598 (copy-recursively "bin" bin))
11604 (uri (git-reference
11605 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11606 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11609 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11615 ("mariadb" ,mariadb)
11616 ("openssl" ,openssl)))
11617 (home-page "http://genome.cse.ucsc.edu/index.html")
11618 (synopsis "Assorted bioinformatics utilities")
11619 (description "This package provides the kentUtils, a selection of
11620 bioinformatics utilities used in combination with the UCSC genome
11622 ;; Only a subset of the sources are released under a non-copyleft
11623 ;; free software license. All other sources are removed in a
11624 ;; snippet. See this bug report for an explanation of how the
11625 ;; license statements apply:
11626 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11627 (license (license:non-copyleft
11628 "http://genome.ucsc.edu/license/"
11629 "The contents of this package are free for all uses."))))
11631 (define-public f-seq
11632 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11636 (version (string-append "1.1-" revision "." (string-take commit 7)))
11639 (uri (git-reference
11640 (url "https://github.com/aboyle/F-seq.git")
11642 (file-name (string-append name "-" version))
11645 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11646 (modules '((guix build utils)))
11647 ;; Remove bundled Java library archives.
11650 (for-each delete-file (find-files "lib" ".*"))
11652 (build-system ant-build-system)
11654 `(#:tests? #f ; no tests included
11656 (modify-phases %standard-phases
11658 (lambda* (#:key inputs outputs #:allow-other-keys)
11659 (let* ((target (assoc-ref outputs "out"))
11660 (bin (string-append target "/bin"))
11661 (doc (string-append target "/share/doc/f-seq"))
11662 (lib (string-append target "/lib")))
11665 (substitute* "bin/linux/fseq"
11666 (("java") (which "java"))
11667 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11668 (string-append (assoc-ref inputs "java-commons-cli")
11669 "/share/java/commons-cli.jar"))
11671 (string-append "REALDIR=" bin "\n")))
11672 (install-file "README.txt" doc)
11673 (install-file "bin/linux/fseq" bin)
11674 (install-file "build~/fseq.jar" lib)
11675 (copy-recursively "lib" lib)
11679 ("java-commons-cli" ,java-commons-cli)))
11680 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11681 (synopsis "Feature density estimator for high-throughput sequence tags")
11683 "F-Seq is a software package that generates a continuous tag sequence
11684 density estimation allowing identification of biologically meaningful sites
11685 such as transcription factor binding sites (ChIP-seq) or regions of open
11686 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11688 (license license:gpl3+))))
11690 (define-public bismark
11697 (uri (git-reference
11698 (url "https://github.com/FelixKrueger/Bismark.git")
11700 (file-name (string-append name "-" version "-checkout"))
11703 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11706 ;; highcharts.js is non-free software. The code is available under
11707 ;; CC-BY-NC or proprietary licenses only.
11708 (delete-file "bismark_sitrep/highcharts.js")
11710 (build-system perl-build-system)
11712 `(#:tests? #f ; there are no tests
11714 (modify-phases %standard-phases
11715 (delete 'configure)
11718 (lambda* (#:key inputs outputs #:allow-other-keys)
11719 (let* ((out (assoc-ref outputs "out"))
11720 (bin (string-append out "/bin"))
11721 (share (string-append out "/share/bismark"))
11722 (docdir (string-append out "/share/doc/bismark"))
11723 (docs '("Docs/Bismark_User_Guide.html"))
11724 (scripts '("bismark"
11725 "bismark_genome_preparation"
11726 "bismark_methylation_extractor"
11729 "coverage2cytosine"
11730 "deduplicate_bismark"
11731 "filter_non_conversion"
11733 "bismark2summary")))
11734 (substitute* "bismark2report"
11735 (("\\$RealBin/bismark_sitrep")
11736 (string-append share "/bismark_sitrep")))
11740 (for-each (lambda (file) (install-file file bin))
11742 (for-each (lambda (file) (install-file file docdir))
11744 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11745 (copy-recursively "bismark_sitrep"
11746 (string-append share "/bismark_sitrep"))
11748 ;; Fix references to gunzip
11749 (substitute* (map (lambda (file)
11750 (string-append bin "/" file))
11753 (string-append "\"" (assoc-ref inputs "gzip")
11754 "/bin/gunzip -c")))
11758 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11759 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11760 (description "Bismark is a program to map bisulfite treated sequencing
11761 reads to a genome of interest and perform methylation calls in a single step.
11762 The output can be easily imported into a genome viewer, such as SeqMonk, and
11763 enables a researcher to analyse the methylation levels of their samples
11764 straight away. Its main features are:
11767 @item Bisulfite mapping and methylation calling in one single step
11768 @item Supports single-end and paired-end read alignments
11769 @item Supports ungapped and gapped alignments
11770 @item Alignment seed length, number of mismatches etc are adjustable
11771 @item Output discriminates between cytosine methylation in CpG, CHG
11774 (license license:gpl3+)))
11776 (define-public paml
11782 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11783 "paml" version ".tgz"))
11786 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11787 (modules '((guix build utils)))
11788 ;; Remove Windows binaries
11791 (for-each delete-file (find-files "." "\\.exe$"))
11793 (build-system gnu-build-system)
11795 `(#:tests? #f ; there are no tests
11796 #:make-flags '("CC=gcc")
11798 (modify-phases %standard-phases
11799 (replace 'configure
11801 (substitute* "src/BFdriver.c"
11802 (("/bin/bash") (which "bash")))
11806 (lambda* (#:key outputs #:allow-other-keys)
11807 (let ((tools '("baseml" "basemlg" "codeml"
11808 "pamp" "evolver" "yn00" "chi2"))
11809 (bin (string-append (assoc-ref outputs "out") "/bin"))
11810 (docdir (string-append (assoc-ref outputs "out")
11811 "/share/doc/paml")))
11813 (for-each (lambda (file) (install-file file bin)) tools)
11814 (copy-recursively "../doc" docdir)
11816 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11817 (synopsis "Phylogentic analysis by maximum likelihood")
11818 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11819 contains a few programs for model fitting and phylogenetic tree reconstruction
11820 using nucleotide or amino-acid sequence data.")
11822 (license license:gpl3)))
11824 (define-public kallisto
11830 (uri (git-reference
11831 (url "https://github.com/pachterlab/kallisto.git")
11832 (commit (string-append "v" version))))
11833 (file-name (git-file-name name version))
11836 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11837 (build-system cmake-build-system)
11839 `(#:tests? #f ; no "check" target
11841 (modify-phases %standard-phases
11842 (add-after 'unpack 'do-not-use-bundled-htslib
11844 (substitute* "CMakeLists.txt"
11845 (("^ExternalProject_Add" m)
11846 (string-append "if (NEVER)\n" m))
11848 (string-append ")\nendif(NEVER)"))
11849 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11850 (string-append "# " m)))
11851 (substitute* "src/CMakeLists.txt"
11852 (("target_link_libraries\\(kallisto kallisto_core pthread \
11853 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11854 "target_link_libraries(kallisto kallisto_core pthread hts)")
11855 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11861 (home-page "http://pachterlab.github.io/kallisto/")
11862 (synopsis "Near-optimal RNA-Seq quantification")
11864 "Kallisto is a program for quantifying abundances of transcripts from
11865 RNA-Seq data, or more generally of target sequences using high-throughput
11866 sequencing reads. It is based on the novel idea of pseudoalignment for
11867 rapidly determining the compatibility of reads with targets, without the need
11868 for alignment. Pseudoalignment of reads preserves the key information needed
11869 for quantification, and kallisto is therefore not only fast, but also as
11870 accurate as existing quantification tools.")
11871 (license license:bsd-2)))
11873 (define-public libgff
11879 (uri (git-reference
11880 (url "https://github.com/Kingsford-Group/libgff.git")
11881 (commit (string-append "v" version))))
11882 (file-name (git-file-name name version))
11885 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11886 (build-system cmake-build-system)
11887 (arguments `(#:tests? #f)) ; no tests included
11888 (home-page "https://github.com/Kingsford-Group/libgff")
11889 (synopsis "Parser library for reading/writing GFF files")
11890 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11891 code that is used in the Cufflinks codebase. The goal of this library is to
11892 provide this functionality without the necessity of drawing in a heavy-weight
11893 dependency like SeqAn.")
11894 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11896 (define-public libdivsufsort
11898 (name "libdivsufsort")
11902 (uri (git-reference
11903 (url "https://github.com/y-256/libdivsufsort.git")
11905 (file-name (git-file-name name version))
11908 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11909 (build-system cmake-build-system)
11911 '(#:tests? #f ; there are no tests
11913 ;; Needed for rapmap and sailfish.
11914 '("-DBUILD_DIVSUFSORT64=ON")))
11915 (home-page "https://github.com/y-256/libdivsufsort")
11916 (synopsis "Lightweight suffix-sorting library")
11917 (description "libdivsufsort is a software library that implements a
11918 lightweight suffix array construction algorithm. This library provides a
11919 simple and an efficient C API to construct a suffix array and a
11920 Burrows-Wheeler transformed string from a given string over a constant-size
11921 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11922 bytes of memory space, where n is the length of the string.")
11923 (license license:expat)))
11925 (define-public sailfish
11931 (uri (git-reference
11932 (url "https://github.com/kingsfordgroup/sailfish.git")
11933 (commit (string-append "v" version))))
11934 (file-name (git-file-name name version))
11937 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11938 (modules '((guix build utils)))
11941 ;; Delete bundled headers for eigen3.
11942 (delete-file-recursively "include/eigen3/")
11944 (build-system cmake-build-system)
11946 `(#:configure-flags
11947 (list (string-append "-DBOOST_INCLUDEDIR="
11948 (assoc-ref %build-inputs "boost")
11950 (string-append "-DBOOST_LIBRARYDIR="
11951 (assoc-ref %build-inputs "boost")
11953 (string-append "-DBoost_LIBRARIES="
11954 "-lboost_iostreams "
11955 "-lboost_filesystem "
11960 "-lboost_program_options")
11961 "-DBoost_FOUND=TRUE"
11962 ;; Don't download RapMap---we already have it!
11963 "-DFETCHED_RAPMAP=1")
11964 ;; Tests must be run after installation and the location of the test
11965 ;; data file must be overridden. But the tests fail. It looks like
11966 ;; they are not really meant to be run.
11969 (modify-phases %standard-phases
11970 ;; Boost cannot be found, even though it's right there.
11971 (add-after 'unpack 'do-not-look-for-boost
11972 (lambda* (#:key inputs #:allow-other-keys)
11973 (substitute* "CMakeLists.txt"
11974 (("find_package\\(Boost 1\\.53\\.0") "#"))
11976 (add-after 'unpack 'do-not-assign-to-macro
11978 (substitute* "include/spdlog/details/format.cc"
11979 (("const unsigned CHAR_WIDTH = 1;") ""))
11981 (add-after 'unpack 'prepare-rapmap
11982 (lambda* (#:key inputs #:allow-other-keys)
11983 (let ((src "external/install/src/rapmap/")
11984 (include "external/install/include/rapmap/")
11985 (rapmap (assoc-ref inputs "rapmap")))
11986 (mkdir-p "/tmp/rapmap")
11988 (assoc-ref inputs "rapmap")
11990 "--strip-components=1")
11993 (for-each (lambda (file)
11994 (install-file file src))
11995 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11996 (copy-recursively "/tmp/rapmap/include" include))
11998 (add-after 'unpack 'use-system-libraries
11999 (lambda* (#:key inputs #:allow-other-keys)
12000 (substitute* '("src/SailfishIndexer.cpp"
12001 "src/SailfishUtils.cpp"
12002 "src/SailfishQuantify.cpp"
12003 "src/FASTAParser.cpp"
12005 "include/SailfishUtils.hpp"
12006 "include/SailfishIndex.hpp"
12007 "include/CollapsedEMOptimizer.hpp"
12008 "src/CollapsedEMOptimizer.cpp")
12009 (("#include \"jellyfish/config.h\"") ""))
12010 (substitute* "src/CMakeLists.txt"
12011 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12012 (string-append (assoc-ref inputs "jellyfish")
12013 "/include/jellyfish-" ,(package-version jellyfish)))
12014 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12015 (string-append (assoc-ref inputs "jellyfish")
12016 "/lib/libjellyfish-2.0.a"))
12017 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12018 (string-append (assoc-ref inputs "libdivsufsort")
12019 "/lib/libdivsufsort.so"))
12020 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12021 (string-append (assoc-ref inputs "libdivsufsort")
12022 "/lib/libdivsufsort64.so")))
12023 (substitute* "CMakeLists.txt"
12024 ;; Don't prefer static libs
12025 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12026 (("find_package\\(Jellyfish.*") "")
12027 (("ExternalProject_Add\\(libjellyfish") "message(")
12028 (("ExternalProject_Add\\(libgff") "message(")
12029 (("ExternalProject_Add\\(libsparsehash") "message(")
12030 (("ExternalProject_Add\\(libdivsufsort") "message("))
12032 ;; Ensure that Eigen headers can be found
12033 (setenv "CPLUS_INCLUDE_PATH"
12034 (string-append (getenv "CPLUS_INCLUDE_PATH")
12036 (assoc-ref inputs "eigen")
12037 "/include/eigen3"))
12042 ("jemalloc" ,jemalloc)
12043 ("jellyfish" ,jellyfish)
12044 ("sparsehash" ,sparsehash)
12047 (uri (git-reference
12048 (url "https://github.com/COMBINE-lab/RapMap.git")
12049 (commit (string-append "sf-v" version))))
12050 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12053 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12054 (modules '((guix build utils)))
12055 ;; These files are expected to be excluded.
12057 '(begin (delete-file-recursively "include/spdlog")
12058 (for-each delete-file '("include/xxhash.h"
12061 ("libdivsufsort" ,libdivsufsort)
12066 `(("pkg-config" ,pkg-config)))
12067 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12068 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12069 (description "Sailfish is a tool for genomic transcript quantification
12070 from RNA-seq data. It requires a set of target transcripts (either from a
12071 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12072 fasta file containing your reference transcripts and a (set of) fasta/fastq
12073 file(s) containing your reads.")
12074 (license license:gpl3+)))
12076 (define libstadenio-for-salmon
12078 (name "libstadenio")
12082 (uri (git-reference
12083 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12084 (commit (string-append "v" version))))
12085 (file-name (string-append name "-" version "-checkout"))
12088 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12089 (build-system gnu-build-system)
12090 (arguments '(#:parallel-tests? #f)) ; not supported
12094 `(("perl" ,perl))) ; for tests
12095 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12096 (synopsis "General purpose trace and experiment file library")
12097 (description "This package provides a library of file reading and writing
12098 code to provide a general purpose Trace file (and Experiment File) reading
12101 The following file formats are supported:
12104 @item SCF trace files
12105 @item ABI trace files
12106 @item ALF trace files
12107 @item ZTR trace files
12108 @item SFF trace archives
12109 @item SRF trace archives
12110 @item Experiment files
12111 @item Plain text files
12112 @item SAM/BAM sequence files
12113 @item CRAM sequence files
12115 (license license:bsd-3)))
12117 (define spdlog-for-salmon
12123 (uri (git-reference
12124 (url "https://github.com/COMBINE-lab/spdlog.git")
12125 (commit (string-append "v" version))))
12126 (file-name (string-append name "-" version "-checkout"))
12129 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12130 (build-system cmake-build-system)
12131 (home-page "https://github.com/COMBINE-lab/spdlog")
12132 (synopsis "Very fast C++ logging library")
12133 (description "Spdlog is a very fast header-only C++ logging library with
12134 performance as its primary goal.")
12135 (license license:expat)))
12137 ;; This is a modified variant of bwa for use with Salmon. It installs a
12138 ;; library to avoid having to build this as part of Salmon.
12139 (define bwa-for-salmon
12140 (package (inherit bwa)
12142 (version "0.7.12.5")
12145 (uri (git-reference
12146 (url "https://github.com/COMBINE-lab/bwa.git")
12147 (commit (string-append "v" version))))
12148 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12151 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12152 (build-system gnu-build-system)
12154 '(#:tests? #f ;no "check" target
12156 (modify-phases %standard-phases
12158 (lambda* (#:key outputs #:allow-other-keys)
12159 (let* ((out (assoc-ref outputs "out"))
12160 (bin (string-append out "/bin"))
12161 (lib (string-append out "/lib"))
12162 (doc (string-append out "/share/doc/bwa"))
12163 (man (string-append out "/share/man/man1"))
12164 (inc (string-append out "/include/bwa")))
12165 (install-file "bwa" bin)
12166 (install-file "README.md" doc)
12167 (install-file "bwa.1" man)
12168 (install-file "libbwa.a" lib)
12171 (for-each (lambda (file)
12172 (install-file file inc))
12173 (find-files "." "\\.h$")))
12175 ;; no "configure" script
12176 (delete 'configure))))))
12178 (define-public salmon
12184 (uri (git-reference
12185 (url "https://github.com/COMBINE-lab/salmon.git")
12186 (commit (string-append "v" version))))
12187 (file-name (string-append name "-" version "-checkout"))
12190 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12191 (modules '((guix build utils)))
12194 ;; Delete bundled headers for eigen3.
12195 (delete-file-recursively "include/eigen3/")
12197 (build-system cmake-build-system)
12199 `(#:configure-flags
12200 (list (string-append "-DBOOST_INCLUDEDIR="
12201 (assoc-ref %build-inputs "boost")
12203 (string-append "-DBOOST_LIBRARYDIR="
12204 (assoc-ref %build-inputs "boost")
12206 (string-append "-DBoost_LIBRARIES="
12207 "-lboost_iostreams "
12208 "-lboost_filesystem "
12213 "-lboost_program_options")
12214 "-DBoost_FOUND=TRUE"
12215 "-DTBB_LIBRARIES=tbb tbbmalloc"
12216 ;; Don't download RapMap---we already have it!
12217 "-DFETCHED_RAPMAP=1")
12219 (modify-phases %standard-phases
12220 ;; Boost cannot be found, even though it's right there.
12221 (add-after 'unpack 'do-not-look-for-boost
12222 (lambda* (#:key inputs #:allow-other-keys)
12223 (substitute* "CMakeLists.txt"
12224 (("find_package\\(Boost 1\\.53\\.0") "#"))
12226 (add-after 'unpack 'do-not-phone-home
12228 (substitute* "src/Salmon.cpp"
12229 (("getVersionMessage\\(\\)") "\"\""))
12231 (add-after 'unpack 'prepare-rapmap
12232 (lambda* (#:key inputs #:allow-other-keys)
12233 (let ((src "external/install/src/rapmap/")
12234 (include "external/install/include/rapmap/")
12235 (rapmap (assoc-ref inputs "rapmap")))
12238 (for-each (lambda (file)
12239 (install-file file src))
12240 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12241 (copy-recursively (string-append rapmap "/include") include)
12242 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12243 "external/install/include/rapmap/FastxParser.hpp"
12244 "external/install/include/rapmap/concurrentqueue.h"
12245 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12246 "external/install/src/rapmap/FastxParser.cpp"
12247 "external/install/src/rapmap/xxhash.c")))
12249 (add-after 'unpack 'use-system-libraries
12250 (lambda* (#:key inputs #:allow-other-keys)
12251 (substitute* "src/CMakeLists.txt"
12252 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12253 (string-append (assoc-ref inputs "jellyfish")
12254 "/include/jellyfish-" ,(package-version jellyfish)))
12255 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12256 (string-append (assoc-ref inputs "jellyfish")
12257 "/lib/libjellyfish-2.0.a"))
12258 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12259 (string-append (assoc-ref inputs "libdivsufsort")
12260 "/lib/libdivsufsort.so"))
12261 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12262 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12263 "/lib/libstaden-read.a"))
12264 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12265 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12266 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12267 (string-append (assoc-ref inputs "libdivsufsort")
12268 "/lib/libdivsufsort64.so")))
12269 (substitute* "CMakeLists.txt"
12270 ;; Don't prefer static libs
12271 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12272 (("set\\(TBB_LIBRARIES") "message(")
12273 (("find_package\\(Jellyfish.*") "")
12274 (("ExternalProject_Add\\(libcereal") "message(")
12275 (("ExternalProject_Add\\(libbwa") "message(")
12276 (("ExternalProject_Add\\(libjellyfish") "message(")
12277 (("ExternalProject_Add\\(libgff") "message(")
12278 (("ExternalProject_Add\\(libtbb") "message(")
12279 (("ExternalProject_Add\\(libspdlog") "message(")
12280 (("ExternalProject_Add\\(libdivsufsort") "message(")
12281 (("ExternalProject_Add\\(libstadenio") "message(")
12282 (("ExternalProject_Add_Step\\(") "message("))
12284 ;; Ensure that all headers can be found
12285 (setenv "CPLUS_INCLUDE_PATH"
12286 (string-append (getenv "CPLUS_INCLUDE_PATH")
12288 (assoc-ref inputs "bwa")
12291 (assoc-ref inputs "eigen")
12292 "/include/eigen3"))
12294 (string-append (assoc-ref inputs "bwa")
12297 (assoc-ref inputs "eigen")
12298 "/include/eigen3"))
12300 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12301 ;; run. It only exists after the install phase.
12302 (add-after 'unpack 'fix-tests
12304 (substitute* "src/CMakeLists.txt"
12305 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12306 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12310 ("bwa" ,bwa-for-salmon)
12316 (uri (git-reference
12317 (url "https://github.com/COMBINE-lab/RapMap.git")
12318 (commit (string-append "salmon-v" version))))
12319 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12322 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12323 ("jemalloc" ,jemalloc)
12324 ("jellyfish" ,jellyfish)
12327 ("libdivsufsort" ,libdivsufsort)
12328 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12329 ("spdlog-for-salmon" ,spdlog-for-salmon)
12332 (home-page "https://github.com/COMBINE-lab/salmon")
12333 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12334 (description "Salmon is a program to produce highly-accurate,
12335 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12336 its accuracy and speed via a number of different innovations, including the
12337 use of lightweight alignments (accurate but fast-to-compute proxies for
12338 traditional read alignments) and massively-parallel stochastic collapsed
12339 variational inference.")
12340 (license license:gpl3+)))
12342 (define-public python-loompy
12344 (name "python-loompy")
12349 (uri (pypi-uri "loompy" version))
12352 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12353 (build-system python-build-system)
12354 ;; There are no tests
12355 (arguments '(#:tests? #f))
12357 `(("python-h5py" ,python-h5py)
12358 ("python-numpy" ,python-numpy)
12359 ("python-scipy" ,python-scipy)))
12360 (home-page "https://github.com/linnarsson-lab/loompy")
12361 (synopsis "Work with .loom files for single-cell RNA-seq data")
12362 (description "The loom file format is an efficient format for very large
12363 omics datasets, consisting of a main matrix, optional additional layers, a
12364 variable number of row and column annotations. Loom also supports sparse
12365 graphs. This library makes it easy to work with @file{.loom} files for
12366 single-cell RNA-seq data.")
12367 (license license:bsd-3)))
12369 ;; We cannot use the latest commit because it requires Java 9.
12370 (define-public java-forester
12371 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12374 (name "java-forester")
12375 (version (string-append "0-" revision "." (string-take commit 7)))
12378 (uri (git-reference
12379 (url "https://github.com/cmzmasek/forester.git")
12381 (file-name (string-append name "-" version "-checkout"))
12384 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12385 (modules '((guix build utils)))
12388 ;; Delete bundled jars and pre-built classes
12389 (delete-file-recursively "forester/java/resources")
12390 (delete-file-recursively "forester/java/classes")
12391 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12392 ;; Delete bundled applications
12393 (delete-file-recursively "forester_applications")
12395 (build-system ant-build-system)
12397 `(#:tests? #f ; there are none
12399 #:modules ((guix build ant-build-system)
12401 (guix build java-utils)
12405 (modify-phases %standard-phases
12406 (add-after 'unpack 'chdir
12407 (lambda _ (chdir "forester/java") #t))
12408 (add-after 'chdir 'fix-dependencies
12410 (chmod "build.xml" #o664)
12411 (call-with-output-file "build.xml.new"
12415 (with-input-from-file "build.xml"
12416 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12417 `(;; Remove all unjar tags to avoid repacking classes.
12418 (unjar . ,(lambda _ '()))
12419 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12420 (*text* . ,(lambda (_ txt) txt))))
12422 (rename-file "build.xml.new" "build.xml")
12424 ;; FIXME: itext is difficult to package as it depends on a few
12425 ;; unpackaged libraries.
12426 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12428 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12429 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12430 (("pdf_written_to = PdfExporter.*")
12431 "throw new IOException(\"PDF export is not available.\");"))
12433 ;; There is no install target
12434 (replace 'install (install-jars ".")))))
12436 `(("java-commons-codec" ,java-commons-codec)
12437 ("java-openchart2" ,java-openchart2)))
12438 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12439 (synopsis "Phylogenomics libraries for Java")
12440 (description "Forester is a collection of Java libraries for
12441 phylogenomics and evolutionary biology research. It includes support for
12442 reading, writing, and exporting phylogenetic trees.")
12443 (license license:lgpl2.1+))))
12445 (define-public java-forester-1.005
12447 (name "java-forester")
12451 (uri (string-append "http://search.maven.org/remotecontent?"
12452 "filepath=org/biojava/thirdparty/forester/"
12453 version "/forester-" version "-sources.jar"))
12454 (file-name (string-append name "-" version ".jar"))
12457 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12458 (build-system ant-build-system)
12460 `(#:tests? #f ; there are none
12462 #:modules ((guix build ant-build-system)
12464 (guix build java-utils)
12468 (modify-phases %standard-phases
12469 (add-after 'unpack 'fix-dependencies
12470 (lambda* (#:key inputs #:allow-other-keys)
12471 (call-with-output-file "build.xml"
12475 (with-input-from-file "src/build.xml"
12476 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12477 `(;; Remove all unjar tags to avoid repacking classes.
12478 (unjar . ,(lambda _ '()))
12479 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12480 (*text* . ,(lambda (_ txt) txt))))
12482 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12483 "synth_look_and_feel_1.xml")
12484 (copy-file (assoc-ref inputs "phyloxml.xsd")
12486 (substitute* "build.xml"
12487 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12488 "synth_look_and_feel_1.xml")
12489 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12492 ;; FIXME: itext is difficult to package as it depends on a few
12493 ;; unpackaged libraries.
12494 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12496 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12497 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12498 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12499 (("pdf_written_to = PdfExporter.*")
12500 "throw new IOException(\"PDF export is not available.\"); /*")
12501 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12502 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12504 (add-after 'unpack 'delete-pre-built-classes
12505 (lambda _ (delete-file-recursively "src/classes") #t))
12506 ;; There is no install target
12507 (replace 'install (install-jars ".")))))
12509 `(("java-commons-codec" ,java-commons-codec)
12510 ("java-openchart2" ,java-openchart2)))
12511 ;; The source archive does not contain the resources.
12516 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12517 "b61cc2dcede0bede317db362472333115756b8c6/"
12518 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12519 (file-name (string-append name "-phyloxml-" version ".xsd"))
12522 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12523 ("synth_look_and_feel_1.xml"
12526 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12527 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12528 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12529 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12532 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12533 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12534 (synopsis "Phylogenomics libraries for Java")
12535 (description "Forester is a collection of Java libraries for
12536 phylogenomics and evolutionary biology research. It includes support for
12537 reading, writing, and exporting phylogenetic trees.")
12538 (license license:lgpl2.1+)))
12540 (define-public java-biojava-core
12542 (name "java-biojava-core")
12546 (uri (git-reference
12547 (url "https://github.com/biojava/biojava")
12548 (commit (string-append "biojava-" version))))
12549 (file-name (string-append name "-" version "-checkout"))
12552 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12553 (build-system ant-build-system)
12556 #:jar-name "biojava-core.jar"
12557 #:source-dir "biojava-core/src/main/java/"
12558 #:test-dir "biojava-core/src/test"
12559 ;; These tests seem to require internet access.
12560 #:test-exclude (list "**/SearchIOTest.java"
12561 "**/BlastXMLParserTest.java"
12562 "**/GenbankCookbookTest.java"
12563 "**/GenbankProxySequenceReaderTest.java")
12565 (modify-phases %standard-phases
12566 (add-before 'build 'copy-resources
12568 (copy-recursively "biojava-core/src/main/resources"
12571 (add-before 'check 'copy-test-resources
12573 (copy-recursively "biojava-core/src/test/resources"
12574 "build/test-classes")
12577 `(("java-log4j-api" ,java-log4j-api)
12578 ("java-log4j-core" ,java-log4j-core)
12579 ("java-slf4j-api" ,java-slf4j-api)
12580 ("java-slf4j-simple" ,java-slf4j-simple)))
12582 `(("java-junit" ,java-junit)
12583 ("java-hamcrest-core" ,java-hamcrest-core)))
12584 (home-page "http://biojava.org")
12585 (synopsis "Core libraries of Java framework for processing biological data")
12586 (description "BioJava is a project dedicated to providing a Java framework
12587 for processing biological data. It provides analytical and statistical
12588 routines, parsers for common file formats, reference implementations of
12589 popular algorithms, and allows the manipulation of sequences and 3D
12590 structures. The goal of the biojava project is to facilitate rapid
12591 application development for bioinformatics.
12593 This package provides the core libraries.")
12594 (license license:lgpl2.1+)))
12596 (define-public java-biojava-phylo
12597 (package (inherit java-biojava-core)
12598 (name "java-biojava-phylo")
12599 (build-system ant-build-system)
12602 #:jar-name "biojava-phylo.jar"
12603 #:source-dir "biojava-phylo/src/main/java/"
12604 #:test-dir "biojava-phylo/src/test"
12606 (modify-phases %standard-phases
12607 (add-before 'build 'copy-resources
12609 (copy-recursively "biojava-phylo/src/main/resources"
12612 (add-before 'check 'copy-test-resources
12614 (copy-recursively "biojava-phylo/src/test/resources"
12615 "build/test-classes")
12618 `(("java-log4j-api" ,java-log4j-api)
12619 ("java-log4j-core" ,java-log4j-core)
12620 ("java-slf4j-api" ,java-slf4j-api)
12621 ("java-slf4j-simple" ,java-slf4j-simple)
12622 ("java-biojava-core" ,java-biojava-core)
12623 ("java-forester" ,java-forester)))
12625 `(("java-junit" ,java-junit)
12626 ("java-hamcrest-core" ,java-hamcrest-core)))
12627 (home-page "http://biojava.org")
12628 (synopsis "Biojava interface to the forester phylogenomics library")
12629 (description "The phylo module provides a biojava interface layer to the
12630 forester phylogenomics library for constructing phylogenetic trees.")))
12632 (define-public java-biojava-alignment
12633 (package (inherit java-biojava-core)
12634 (name "java-biojava-alignment")
12635 (build-system ant-build-system)
12638 #:jar-name "biojava-alignment.jar"
12639 #:source-dir "biojava-alignment/src/main/java/"
12640 #:test-dir "biojava-alignment/src/test"
12642 (modify-phases %standard-phases
12643 (add-before 'build 'copy-resources
12645 (copy-recursively "biojava-alignment/src/main/resources"
12648 (add-before 'check 'copy-test-resources
12650 (copy-recursively "biojava-alignment/src/test/resources"
12651 "build/test-classes")
12654 `(("java-log4j-api" ,java-log4j-api)
12655 ("java-log4j-core" ,java-log4j-core)
12656 ("java-slf4j-api" ,java-slf4j-api)
12657 ("java-slf4j-simple" ,java-slf4j-simple)
12658 ("java-biojava-core" ,java-biojava-core)
12659 ("java-biojava-phylo" ,java-biojava-phylo)
12660 ("java-forester" ,java-forester)))
12662 `(("java-junit" ,java-junit)
12663 ("java-hamcrest-core" ,java-hamcrest-core)))
12664 (home-page "http://biojava.org")
12665 (synopsis "Biojava API for genetic sequence alignment")
12666 (description "The alignment module of BioJava provides an API that
12670 @item implementations of dynamic programming algorithms for sequence
12672 @item reading and writing of popular alignment file formats;
12673 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12676 (define-public java-biojava-core-4.0
12677 (package (inherit java-biojava-core)
12678 (name "java-biojava-core")
12682 (uri (git-reference
12683 (url "https://github.com/biojava/biojava")
12684 (commit (string-append "biojava-" version))))
12685 (file-name (string-append name "-" version "-checkout"))
12688 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12690 (define-public java-biojava-phylo-4.0
12691 (package (inherit java-biojava-core-4.0)
12692 (name "java-biojava-phylo")
12693 (build-system ant-build-system)
12696 #:jar-name "biojava-phylo.jar"
12697 #:source-dir "biojava-phylo/src/main/java/"
12698 #:test-dir "biojava-phylo/src/test"
12700 (modify-phases %standard-phases
12701 (add-before 'build 'copy-resources
12703 (copy-recursively "biojava-phylo/src/main/resources"
12706 (add-before 'check 'copy-test-resources
12708 (copy-recursively "biojava-phylo/src/test/resources"
12709 "build/test-classes")
12712 `(("java-log4j-api" ,java-log4j-api)
12713 ("java-log4j-core" ,java-log4j-core)
12714 ("java-slf4j-api" ,java-slf4j-api)
12715 ("java-slf4j-simple" ,java-slf4j-simple)
12716 ("java-biojava-core" ,java-biojava-core-4.0)
12717 ("java-forester" ,java-forester-1.005)))
12719 `(("java-junit" ,java-junit)
12720 ("java-hamcrest-core" ,java-hamcrest-core)))
12721 (home-page "http://biojava.org")
12722 (synopsis "Biojava interface to the forester phylogenomics library")
12723 (description "The phylo module provides a biojava interface layer to the
12724 forester phylogenomics library for constructing phylogenetic trees.")))
12726 (define-public java-biojava-alignment-4.0
12727 (package (inherit java-biojava-core-4.0)
12728 (name "java-biojava-alignment")
12729 (build-system ant-build-system)
12732 #:jar-name "biojava-alignment.jar"
12733 #:source-dir "biojava-alignment/src/main/java/"
12734 #:test-dir "biojava-alignment/src/test"
12736 (modify-phases %standard-phases
12737 (add-before 'build 'copy-resources
12739 (copy-recursively "biojava-alignment/src/main/resources"
12742 (add-before 'check 'copy-test-resources
12744 (copy-recursively "biojava-alignment/src/test/resources"
12745 "build/test-classes")
12748 `(("java-log4j-api" ,java-log4j-api)
12749 ("java-log4j-core" ,java-log4j-core)
12750 ("java-slf4j-api" ,java-slf4j-api)
12751 ("java-slf4j-simple" ,java-slf4j-simple)
12752 ("java-biojava-core" ,java-biojava-core-4.0)
12753 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12754 ("java-forester" ,java-forester-1.005)))
12756 `(("java-junit" ,java-junit)
12757 ("java-hamcrest-core" ,java-hamcrest-core)))
12758 (home-page "http://biojava.org")
12759 (synopsis "Biojava API for genetic sequence alignment")
12760 (description "The alignment module of BioJava provides an API that
12764 @item implementations of dynamic programming algorithms for sequence
12766 @item reading and writing of popular alignment file formats;
12767 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12770 (define-public dropseq-tools
12772 (name "dropseq-tools")
12777 (uri "http://mccarrolllab.com/download/1276/")
12778 (file-name (string-append "dropseq-tools-" version ".zip"))
12781 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12782 ;; Delete bundled libraries
12783 (modules '((guix build utils)))
12786 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12787 (delete-file-recursively "3rdParty")
12789 (build-system ant-build-system)
12791 `(#:tests? #f ; test data are not included
12792 #:test-target "test"
12793 #:build-target "all"
12794 #:source-dir "public/src/"
12797 (list (string-append "-Dpicard.executable.dir="
12798 (assoc-ref %build-inputs "java-picard")
12800 #:modules ((ice-9 match)
12803 (guix build java-utils)
12804 (guix build ant-build-system))
12806 (modify-phases %standard-phases
12807 ;; FIXME: fails with "java.io.FileNotFoundException:
12808 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12809 (delete 'generate-jar-indices)
12810 ;; All dependencies must be linked to "lib", because that's where
12811 ;; they will be searched for when the Class-Path property of the
12812 ;; manifest is computed.
12813 (add-after 'unpack 'record-references
12814 (lambda* (#:key inputs #:allow-other-keys)
12815 (mkdir-p "jar/lib")
12816 (let ((dirs (filter-map (match-lambda
12818 (if (and (string-prefix? "java-" name)
12819 (not (string=? name "java-testng")))
12822 (for-each (lambda (jar)
12823 (symlink jar (string-append "jar/lib/" (basename jar))))
12824 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12827 ;; There is no installation target
12829 (lambda* (#:key inputs outputs #:allow-other-keys)
12830 (let* ((out (assoc-ref outputs "out"))
12831 (bin (string-append out "/bin"))
12832 (share (string-append out "/share/java/"))
12833 (lib (string-append share "/lib/"))
12834 (scripts (list "BAMTagHistogram"
12835 "BAMTagofTagCounts"
12836 "BaseDistributionAtReadPosition"
12837 "CollapseBarcodesInPlace"
12838 "CollapseTagWithContext"
12840 "CreateIntervalsFiles"
12841 "DetectBeadSynthesisErrors"
12842 "DigitalExpression"
12843 "Drop-seq_alignment.sh"
12846 "GatherGeneGCLength"
12847 "GatherMolecularBarcodeDistributionByGene"
12848 "GatherReadQualityMetrics"
12851 "SelectCellsByNumTranscripts"
12852 "SingleCellRnaSeqMetricsCollector"
12853 "TagBamWithReadSequenceExtended"
12854 "TagReadWithGeneExon"
12855 "TagReadWithInterval"
12856 "TrimStartingSequence"
12857 "ValidateReference")))
12858 (for-each mkdir-p (list bin share lib))
12859 (install-file "dist/dropseq.jar" share)
12860 (for-each (lambda (script)
12861 (chmod script #o555)
12862 (install-file script bin))
12864 (substitute* (map (lambda (script)
12865 (string-append bin "/" script))
12867 (("^java") (which "java"))
12868 (("jar_deploy_dir=.*")
12869 (string-append "jar_deploy_dir=" share "\n"))))
12871 ;; FIXME: We do this after stripping jars because we don't want it to
12872 ;; copy all these jars and strip them. We only want to install
12873 ;; links. Arguably, this is a problem with the ant-build-system.
12874 (add-after 'strip-jar-timestamps 'install-links
12875 (lambda* (#:key outputs #:allow-other-keys)
12876 (let* ((out (assoc-ref outputs "out"))
12877 (share (string-append out "/share/java/"))
12878 (lib (string-append share "/lib/")))
12879 (for-each (lambda (jar)
12880 (symlink (readlink jar)
12881 (string-append lib (basename jar))))
12882 (find-files "jar/lib" "\\.jar$")))
12885 `(("jdk" ,icedtea-8)
12886 ("java-picard" ,java-picard-2.10.3)
12887 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12888 ("java-commons-math3" ,java-commons-math3)
12889 ("java-commons-jexl2" ,java-commons-jexl-2)
12890 ("java-commons-collections4" ,java-commons-collections4)
12891 ("java-commons-lang2" ,java-commons-lang)
12892 ("java-commons-io" ,java-commons-io)
12893 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12894 ("java-guava" ,java-guava)
12895 ("java-la4j" ,java-la4j)
12896 ("java-biojava-core" ,java-biojava-core-4.0)
12897 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12898 ("java-jdistlib" ,java-jdistlib)
12899 ("java-simple-xml" ,java-simple-xml)
12900 ("java-snakeyaml" ,java-snakeyaml)))
12903 ("java-testng" ,java-testng)))
12904 (home-page "http://mccarrolllab.com/dropseq/")
12905 (synopsis "Tools for Drop-seq analyses")
12906 (description "Drop-seq is a technology to enable biologists to
12907 analyze RNA expression genome-wide in thousands of individual cells at
12908 once. This package provides tools to perform Drop-seq analyses.")
12909 (license license:expat)))
12911 (define-public pigx-rnaseq
12913 (name "pigx-rnaseq")
12917 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12918 "releases/download/v" version
12919 "/pigx_rnaseq-" version ".tar.gz"))
12922 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12923 (build-system gnu-build-system)
12925 `(#:parallel-tests? #f ; not supported
12927 (modify-phases %standard-phases
12928 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12929 (add-after 'unpack 'disable-resource-intensive-test
12931 (substitute* "Makefile.in"
12932 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12933 (("^ tests/test_multiqc/test.sh") "")
12934 (("^ test.sh") ""))
12938 ("snakemake" ,snakemake)
12940 ("multiqc" ,multiqc)
12942 ("trim-galore" ,trim-galore)
12944 ("samtools" ,samtools)
12945 ("bedtools" ,bedtools)
12946 ("r-minimal" ,r-minimal)
12947 ("r-rmarkdown" ,r-rmarkdown)
12948 ("r-ggplot2" ,r-ggplot2)
12949 ("r-ggrepel" ,r-ggrepel)
12950 ("r-gprofiler" ,r-gprofiler)
12951 ("r-deseq2" ,r-deseq2)
12953 ("r-knitr" ,r-knitr)
12954 ("r-pheatmap" ,r-pheatmap)
12955 ("r-corrplot" ,r-corrplot)
12956 ("r-reshape2" ,r-reshape2)
12957 ("r-plotly" ,r-plotly)
12958 ("r-scales" ,r-scales)
12959 ("r-summarizedexperiment" ,r-summarizedexperiment)
12960 ("r-crosstalk" ,r-crosstalk)
12961 ("r-tximport" ,r-tximport)
12962 ("r-rtracklayer" ,r-rtracklayer)
12963 ("r-rjson" ,r-rjson)
12965 ("ghc-pandoc" ,ghc-pandoc)
12966 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12967 ("python-wrapper" ,python-wrapper)
12968 ("python-pyyaml" ,python-pyyaml)))
12969 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12970 (synopsis "Analysis pipeline for RNA sequencing experiments")
12971 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12972 reporting for RNA sequencing experiments. It is easy to use and produces high
12973 quality reports. The inputs are reads files from the sequencing experiment,
12974 and a configuration file which describes the experiment. In addition to
12975 quality control of the experiment, the pipeline produces a differential
12976 expression report comparing samples in an easily configurable manner.")
12977 (license license:gpl3+)))
12979 (define-public pigx-chipseq
12981 (name "pigx-chipseq")
12985 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12986 "releases/download/v" version
12987 "/pigx_chipseq-" version ".tar.gz"))
12990 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
12991 (build-system gnu-build-system)
12992 ;; parts of the tests rely on access to the network
12993 (arguments '(#:tests? #f))
12996 ("coreutils" ,coreutils)
12997 ("r-minimal" ,r-minimal)
12998 ("r-argparser" ,r-argparser)
12999 ("r-biocparallel" ,r-biocparallel)
13000 ("r-biostrings" ,r-biostrings)
13001 ("r-chipseq" ,r-chipseq)
13002 ("r-data-table" ,r-data-table)
13003 ("r-dplyr" ,r-dplyr)
13004 ("r-genomation" ,r-genomation)
13005 ("r-genomicalignments" ,r-genomicalignments)
13006 ("r-genomicranges" ,r-genomicranges)
13007 ("r-rsamtools" ,r-rsamtools)
13008 ("r-rtracklayer" ,r-rtracklayer)
13009 ("r-s4vectors" ,r-s4vectors)
13010 ("r-stringr" ,r-stringr)
13011 ("r-tibble" ,r-tibble)
13012 ("r-tidyr" ,r-tidyr)
13013 ("r-jsonlite" ,r-jsonlite)
13014 ("r-heatmaply" ,r-heatmaply)
13015 ("r-htmlwidgets" ,r-htmlwidgets)
13016 ("r-ggplot2" ,r-ggplot2)
13017 ("r-plotly" ,r-plotly)
13018 ("r-rmarkdown" ,r-rmarkdown)
13019 ("python-wrapper" ,python-wrapper)
13020 ("python-pyyaml" ,python-pyyaml)
13021 ("python-magic" ,python-magic)
13022 ("python-xlrd" ,python-xlrd)
13023 ("trim-galore" ,trim-galore)
13025 ("multiqc" ,multiqc)
13027 ("ghc-pandoc" ,ghc-pandoc)
13028 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13032 ("snakemake" ,snakemake)
13033 ("samtools" ,samtools)
13034 ("bedtools" ,bedtools)
13035 ("kentutils" ,kentutils)))
13037 `(("python-pytest" ,python-pytest)))
13038 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13039 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13040 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13041 calling and reporting for ChIP sequencing experiments. It is easy to use and
13042 produces high quality reports. The inputs are reads files from the sequencing
13043 experiment, and a configuration file which describes the experiment. In
13044 addition to quality control of the experiment, the pipeline enables to set up
13045 multiple peak calling analysis and allows the generation of a UCSC track hub
13046 in an easily configurable manner.")
13047 (license license:gpl3+)))
13049 (define-public pigx-bsseq
13051 (name "pigx-bsseq")
13055 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13056 "releases/download/v" version
13057 "/pigx_bsseq-" version ".tar.gz"))
13060 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13061 (build-system gnu-build-system)
13064 (modify-phases %standard-phases
13065 (add-before 'check 'set-timezone
13066 ;; The readr package is picky about timezones.
13067 (lambda* (#:key inputs #:allow-other-keys)
13068 (setenv "TZ" "UTC+1")
13070 (string-append (assoc-ref inputs "tzdata")
13071 "/share/zoneinfo"))
13074 `(("tzdata" ,tzdata)))
13076 `(("coreutils" ,coreutils)
13079 ("r-minimal" ,r-minimal)
13080 ("r-annotationhub" ,r-annotationhub)
13082 ("r-genomation" ,r-genomation)
13083 ("r-methylkit" ,r-methylkit)
13084 ("r-rtracklayer" ,r-rtracklayer)
13085 ("r-rmarkdown" ,r-rmarkdown)
13086 ("r-bookdown" ,r-bookdown)
13087 ("r-ggplot2" ,r-ggplot2)
13088 ("r-ggbio" ,r-ggbio)
13089 ("ghc-pandoc" ,ghc-pandoc)
13090 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13091 ("python-wrapper" ,python-wrapper)
13092 ("python-pyyaml" ,python-pyyaml)
13093 ("snakemake" ,snakemake)
13094 ("bismark" ,bismark)
13097 ("trim-galore" ,trim-galore)
13098 ("cutadapt" ,cutadapt)
13099 ("samtools" ,samtools)))
13100 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13101 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13102 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13103 data of bisulfite experiments; it produces reports on aggregate methylation
13104 and coverage and can be used to produce information on differential
13105 methylation and segmentation.")
13106 (license license:gpl3+)))
13108 (define-public pigx-scrnaseq
13110 (name "pigx-scrnaseq")
13114 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13115 "releases/download/v" version
13116 "/pigx_scrnaseq-" version ".tar.gz"))
13119 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13120 (build-system gnu-build-system)
13122 `(#:configure-flags
13123 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13124 "/share/java/picard.jar")
13125 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13126 "/share/java/dropseq.jar"))))
13128 `(("coreutils" ,coreutils)
13130 ("dropseq-tools" ,dropseq-tools)
13132 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13133 ("java" ,icedtea-8)
13134 ("python-wrapper" ,python-wrapper)
13135 ("python-pyyaml" ,python-pyyaml)
13136 ("python-pandas" ,python-pandas)
13137 ("python-magic" ,python-magic)
13138 ("python-numpy" ,python-numpy)
13139 ("python-loompy" ,python-loompy)
13140 ("ghc-pandoc" ,ghc-pandoc)
13141 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13142 ("samtools" ,samtools)
13143 ("snakemake" ,snakemake)
13145 ("r-minimal" ,r-minimal)
13146 ("r-argparser" ,r-argparser)
13147 ("r-cowplot" ,r-cowplot)
13148 ("r-data-table" ,r-data-table)
13149 ("r-delayedarray" ,r-delayedarray)
13150 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13151 ("r-dplyr" ,r-dplyr)
13152 ("r-dropbead" ,r-dropbead)
13154 ("r-genomicalignments" ,r-genomicalignments)
13155 ("r-genomicfiles" ,r-genomicfiles)
13156 ("r-genomicranges" ,r-genomicranges)
13157 ("r-ggplot2" ,r-ggplot2)
13158 ("r-hdf5array" ,r-hdf5array)
13159 ("r-pheatmap" ,r-pheatmap)
13160 ("r-rmarkdown" ,r-rmarkdown)
13161 ("r-rsamtools" ,r-rsamtools)
13162 ("r-rtracklayer" ,r-rtracklayer)
13163 ("r-rtsne" ,r-rtsne)
13164 ("r-scater" ,r-scater)
13165 ("r-scran" ,r-scran)
13166 ("r-singlecellexperiment" ,r-singlecellexperiment)
13167 ("r-stringr" ,r-stringr)
13168 ("r-yaml" ,r-yaml)))
13169 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13170 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13171 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13172 quality control for single cell RNA sequencing experiments. The inputs are
13173 read files from the sequencing experiment, and a configuration file which
13174 describes the experiment. It produces processed files for downstream analysis
13175 and interactive quality reports. The pipeline is designed to work with UMI
13177 (license license:gpl3+)))
13179 (define-public pigx
13185 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13186 "releases/download/v" version
13187 "/pigx-" version ".tar.gz"))
13190 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13191 (build-system gnu-build-system)
13193 `(("python" ,python)
13194 ("pigx-bsseq" ,pigx-bsseq)
13195 ("pigx-chipseq" ,pigx-chipseq)
13196 ("pigx-rnaseq" ,pigx-rnaseq)
13197 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13198 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13199 (synopsis "Analysis pipelines for genomics")
13200 (description "PiGx is a collection of genomics pipelines. It includes the
13201 following pipelines:
13204 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13205 @item PiGx RNAseq for RNAseq samples
13206 @item PiGx scRNAseq for single cell dropseq analysis
13207 @item PiGx ChIPseq for reads from ChIPseq experiments
13210 All pipelines are easily configured with a simple sample sheet and a
13211 descriptive settings file. The result is a set of comprehensive, interactive
13212 HTML reports with interesting findings about your samples.")
13213 (license license:gpl3+)))
13215 (define-public mantis
13216 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13220 (version (git-version "0" revision commit))
13223 (uri (git-reference
13224 (url "https://github.com/splatlab/mantis.git")
13226 (file-name (git-file-name name version))
13229 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13230 (build-system cmake-build-system)
13231 (arguments '(#:tests? #f)) ; there are none
13233 `(("sdsl-lite" ,sdsl-lite)
13234 ("openssl" ,openssl)
13236 (home-page "https://github.com/splatlab/mantis")
13237 (synopsis "Large-scale sequence-search index data structure")
13238 (description "Mantis is a space-efficient data structure that can be
13239 used to index thousands of raw-read genomics experiments and facilitate
13240 large-scale sequence searches on those experiments. Mantis uses counting
13241 quotient filters instead of Bloom filters, enabling rapid index builds and
13242 queries, small indexes, and exact results, i.e., no false positives or
13243 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13244 representation, so it supports fast graph traversal and other topological
13245 analyses in addition to large-scale sequence-level searches.")
13246 ;; uses __uint128_t and inline assembly
13247 (supported-systems '("x86_64-linux"))
13248 (license license:bsd-3))))
13250 (define-public r-diversitree
13252 (name "r-diversitree")
13257 (uri (cran-uri "diversitree" version))
13260 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13261 (build-system r-build-system)
13263 `(("gfortran" ,gfortran)))
13264 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13267 ("r-desolve" ,r-desolve)
13269 ("r-suplex" ,r-subplex)))
13270 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13271 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13272 (description "This package contains a number of comparative \"phylogenetic\"
13273 methods, mostly focusing on analysing diversification and character evolution.
13274 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13275 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13276 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13277 include Markov models of discrete and continuous trait evolution and constant
13278 rate speciation and extinction.")
13279 (license license:gpl2+)))
13281 (define-public sjcount
13282 ;; There is no tag for version 3.2, nor is there a release archive.
13283 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13287 (version (git-version "3.2" revision commit))
13290 (uri (git-reference
13291 (url "https://github.com/pervouchine/sjcount-full.git")
13293 (file-name (string-append name "-" version "-checkout"))
13296 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13297 (build-system gnu-build-system)
13299 `(#:tests? #f ; requires a 1.4G test file
13301 (list (string-append "SAMTOOLS_DIR="
13302 (assoc-ref %build-inputs "samtools")
13305 (modify-phases %standard-phases
13306 (replace 'configure
13307 (lambda* (#:key inputs #:allow-other-keys)
13308 (substitute* "makefile"
13309 (("-I \\$\\{SAMTOOLS_DIR\\}")
13310 (string-append "-I" (assoc-ref inputs "samtools")
13311 "/include/samtools"))
13312 (("-lz ") "-lz -lpthread "))
13315 (lambda* (#:key outputs #:allow-other-keys)
13316 (for-each (lambda (tool)
13318 (string-append (assoc-ref outputs "out")
13320 '("j_count" "b_count" "sjcount"))
13323 `(("samtools" ,samtools-0.1)
13325 (home-page "https://github.com/pervouchine/sjcount-full/")
13326 (synopsis "Annotation-agnostic splice junction counting pipeline")
13327 (description "Sjcount is a utility for fast quantification of splice
13328 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13329 version does count multisplits.")
13330 (license license:gpl3+))))
13332 (define-public minimap2
13339 (uri (string-append "https://github.com/lh3/minimap2/"
13340 "releases/download/v" version "/"
13341 "minimap2-" version ".tar.bz2"))
13344 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13345 (build-system gnu-build-system)
13347 `(#:tests? #f ; there are none
13350 (let ((system ,(or (%current-target-system)
13351 (%current-system))))
13353 ((string-prefix? "x86_64" system)
13355 ((or (string-prefix? "armhf" system)
13356 (string-prefix? "aarch64" system))
13358 (_ "sse2only=1"))))
13360 (modify-phases %standard-phases
13361 (delete 'configure)
13363 (lambda* (#:key outputs #:allow-other-keys)
13364 (let* ((out (assoc-ref outputs "out"))
13365 (bin (string-append out "/bin"))
13366 (man (string-append out "/share/man/man1")))
13367 (install-file "minimap2" bin)
13369 (install-file "minimap2.1" man))
13373 (home-page "https://lh3.github.io/minimap2/")
13374 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13375 (description "Minimap2 is a versatile sequence alignment program that
13376 aligns DNA or mRNA sequences against a large reference database. Typical use
13380 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13381 @item finding overlaps between long reads with error rate up to ~15%;
13382 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13383 reads against a reference genome;
13384 @item aligning Illumina single- or paired-end reads;
13385 @item assembly-to-assembly alignment;
13386 @item full-genome alignment between two closely related species with
13387 divergence below ~15%.
13389 (license license:expat)))
13391 (define-public r-circus
13398 (uri (git-reference
13399 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13400 (commit (string-append "v" version))))
13401 (file-name (git-file-name name version))
13404 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13405 (build-system r-build-system)
13407 `(("r-annotationdbi" ,r-annotationdbi)
13408 ("r-annotationhub" ,r-annotationhub)
13409 ("r-biomart" ,r-biomart)
13410 ("r-data-table" ,r-data-table)
13412 ("r-genomicfeatures" ,r-genomicfeatures)
13413 ("r-genomicranges" ,r-genomicranges)
13414 ("r-ggplot2" ,r-ggplot2)
13416 ("r-iranges" ,r-iranges)
13417 ("r-rcolorbrewer" ,r-rcolorbrewer)
13418 ("r-rmysql" ,r-rmysql)
13419 ("r-s4vectors" ,r-s4vectors)
13420 ("r-stringr" ,r-stringr)
13421 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13423 `(("r-knitr" ,r-knitr)))
13424 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13425 (synopsis "Annotation, analysis and visualization of circRNA data")
13426 (description "Circus is an R package for annotation, analysis and
13427 visualization of circRNA data. Users can annotate their circRNA candidates
13428 with host genes, gene featrues they are spliced from, and discriminate between
13429 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13430 can be calculated, and a number of descriptive plots easily generated.")
13431 (license license:artistic2.0)))
13433 (define-public r-loomr
13434 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13438 (version (git-version "0.2.0" revision commit))
13442 (uri (git-reference
13443 (url "https://github.com/mojaveazure/loomR.git")
13445 (file-name (git-file-name name version))
13448 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13449 (build-system r-build-system)
13452 ("r-hdf5r" ,r-hdf5r)
13453 ("r-iterators" ,r-iterators)
13454 ("r-itertools" ,r-itertools)
13455 ("r-matrix" ,r-matrix)))
13456 (home-page "https://github.com/mojaveazure/loomR")
13457 (synopsis "R interface for loom files")
13458 (description "This package provides an R interface to access, create,
13459 and modify loom files. loomR aims to be completely compatible with loompy.")
13460 (license license:gpl3))))
13462 (define-public gffread
13463 ;; We cannot use the tagged release because it is not in sync with gclib.
13464 ;; See https://github.com/gpertea/gffread/issues/26
13465 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13469 (version (git-version "0.9.12" revision commit))
13473 (uri (git-reference
13474 (url "https://github.com/gpertea/gffread.git")
13476 (file-name (git-file-name name version))
13479 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13480 (build-system gnu-build-system)
13482 `(#:tests? #f ; no check target
13484 (list "GCLDIR=gclib")
13486 (modify-phases %standard-phases
13487 (delete 'configure)
13488 (add-after 'unpack 'copy-gclib-source
13489 (lambda* (#:key inputs #:allow-other-keys)
13491 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13493 ;; There is no install target
13495 (lambda* (#:key outputs #:allow-other-keys)
13496 (let* ((out (assoc-ref outputs "out"))
13497 (bin (string-append out "/bin")))
13498 (install-file "gffread" bin))
13502 ,(let ((version "0.10.3")
13503 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13507 (uri (git-reference
13508 (url "https://github.com/gpertea/gclib.git")
13510 (file-name (git-file-name "gclib" version))
13513 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13514 (home-page "https://github.com/gpertea/gffread/")
13515 (synopsis "Parse and convert GFF/GTF files")
13517 "This package provides a GFF/GTF file parsing utility providing format
13518 conversions, region filtering, FASTA sequence extraction and more.")
13519 ;; gffread is under Expat, but gclib is under Artistic 2.0
13520 (license (list license:expat
13521 license:artistic2.0)))))
13523 (define-public find-circ
13524 ;; The last release was in 2015. The license was clarified in 2017, so we
13525 ;; take the latest commit.
13526 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13530 (version (git-version "1.2" revision commit))
13534 (uri (git-reference
13535 (url "https://github.com/marvin-jens/find_circ.git")
13537 (file-name (git-file-name name version))
13540 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13541 (build-system gnu-build-system)
13543 `(#:tests? #f ; there are none
13545 ;; There is no actual build system.
13546 (modify-phases %standard-phases
13547 (delete 'configure)
13550 (lambda* (#:key outputs #:allow-other-keys)
13551 (let* ((out (assoc-ref outputs "out"))
13552 (bin (string-append out "/bin"))
13553 (path (getenv "PYTHONPATH")))
13554 (for-each (lambda (script)
13555 (install-file script bin)
13556 (wrap-program (string-append bin "/" script)
13557 `("PYTHONPATH" ":" prefix (,path))))
13562 "unmapped2anchors.py")))
13565 `(("python2" ,python-2)
13566 ("python2-pysam" ,python2-pysam)
13567 ("python2-numpy" ,python2-numpy)))
13568 (home-page "https://github.com/marvin-jens/find_circ")
13569 (synopsis "circRNA detection from RNA-seq reads")
13570 (description "This package provides tools to detect head-to-tail
13571 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13573 (license license:gpl3))))
13575 (define-public python-scanpy
13577 (name "python-scanpy")
13582 (uri (pypi-uri "scanpy" version))
13585 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13586 (build-system python-build-system)
13588 `(("python-anndata" ,python-anndata)
13589 ("python-igraph" ,python-igraph)
13590 ("python-numba" ,python-numba)
13591 ("python-joblib" ,python-joblib)
13592 ("python-natsort" ,python-natsort)
13593 ("python-networkx" ,python-networkx)
13594 ("python-statsmodels" ,python-statsmodels)
13595 ("python-scikit-learn" ,python-scikit-learn)
13596 ("python-matplotlib" ,python-matplotlib)
13597 ("python-pandas" ,python-pandas)
13598 ("python-scipy" ,python-scipy)
13599 ("python-seaborn" ,python-seaborn)
13600 ("python-h5py" ,python-h5py)
13601 ("python-tables" ,python-tables)))
13602 (home-page "http://github.com/theislab/scanpy")
13603 (synopsis "Single-Cell Analysis in Python.")
13604 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13605 expression data. It includes preprocessing, visualization, clustering,
13606 pseudotime and trajectory inference and differential expression testing. The
13607 Python-based implementation efficiently deals with datasets of more than one
13609 (license license:bsd-3)))
13611 (define-public gffcompare
13612 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13615 (name "gffcompare")
13616 (version (git-version "0.10.15" revision commit))
13620 (uri (git-reference
13621 (url "https://github.com/gpertea/gffcompare/")
13623 (file-name (git-file-name name version))
13625 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13626 (build-system gnu-build-system)
13628 `(#:tests? #f ; no check target
13630 (modify-phases %standard-phases
13631 (delete 'configure)
13632 (add-before 'build 'copy-gclib-source
13633 (lambda* (#:key inputs #:allow-other-keys)
13636 (assoc-ref inputs "gclib-source") "../gclib")
13639 (lambda* (#:key outputs #:allow-other-keys)
13640 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13641 (install-file "gffcompare" bin)
13644 `(("gclib-source" ; see 'README.md' of gffcompare
13645 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13648 (version (git-version "0.10.3" revision commit)))
13651 (uri (git-reference
13652 (url "https://github.com/gpertea/gclib/")
13654 (file-name (git-file-name name version))
13656 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13657 (home-page "https://github.com/gpertea/gffcompare/")
13658 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13660 "@code{gffcompare} is a tool that can:
13662 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13663 (Cufflinks, Stringtie);
13664 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13665 resulted from assembly of different samples);
13666 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13667 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13671 license:expat ;license for gffcompare
13672 license:artistic2.0))))) ;license for gclib
13674 (define-public python-intervaltree
13676 (name "python-intervaltree")
13681 (uri (pypi-uri "intervaltree" version))
13684 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13685 (build-system python-build-system)
13686 ;; FIXME: error when collecting tests
13687 (arguments '(#:tests? #f))
13689 `(("python-sortedcontainers" ,python-sortedcontainers)))
13691 `(("python-pytest" ,python-pytest)))
13692 (home-page "https://github.com/chaimleib/intervaltree")
13693 (synopsis "Editable interval tree data structure")
13695 "This package provides a mutable, self-balancing interval tree
13696 implementation for Python. Queries may be by point, by range overlap, or by
13697 range envelopment. This library was designed to allow tagging text and time
13698 intervals, where the intervals include the lower bound but not the upper
13700 (license license:asl2.0)))
13702 (define-public python-pypairix
13704 (name "python-pypairix")
13709 (uri (pypi-uri "pypairix" version))
13712 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13713 (build-system python-build-system)
13714 ;; FIXME: the tests fail because test.support cannot be loaded:
13715 ;; ImportError: cannot import name 'support'
13716 (arguments '(#:tests? #f))
13719 (home-page "https://github.com/4dn-dcic/pairix")
13720 (synopsis "Support for querying pairix-indexed bgzipped text files")
13722 "Pypairix is a Python module for fast querying on a pairix-indexed
13723 bgzipped text file that contains a pair of genomic coordinates per line.")
13724 (license license:expat)))
13726 (define-public python-pyfaidx
13728 (name "python-pyfaidx")
13729 (version "0.5.4.2")
13733 (uri (pypi-uri "pyfaidx" version))
13736 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13737 (build-system python-build-system)
13739 `(("python-setuptools" ,python-setuptools)
13740 ("python-six" ,python-six)))
13741 (home-page "http://mattshirley.com")
13742 (synopsis "Random access to fasta subsequences")
13744 "This package provides procedures for efficient pythonic random access to
13745 fasta subsequences.")
13746 (license license:bsd-3)))
13748 (define-public python-cooler
13750 (name "python-cooler")
13755 (uri (pypi-uri "cooler" version))
13758 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13759 (build-system python-build-system)
13761 `(("python-biopython" ,python-biopython)
13762 ("python-click" ,python-click)
13763 ("python-cytoolz" ,python-cytoolz)
13764 ("python-dask" ,python-dask)
13765 ("python-h5py" ,python-h5py)
13766 ("python-multiprocess" ,python-multiprocess)
13767 ("python-pandas" ,python-pandas)
13768 ("python-pyfaidx" ,python-pyfaidx)
13769 ("python-pypairix" ,python-pypairix)
13770 ("python-pysam" ,python-pysam)
13771 ("python-scipy" ,python-scipy)))
13773 `(("python-mock" ,python-mock)
13774 ("python-nose" ,python-nose)
13775 ("python-numpydoc" ,python-numpydoc)
13776 ("python-sphinx" ,python-sphinx)))
13777 (home-page "https://github.com/mirnylab/cooler")
13778 (synopsis "Sparse binary format for genomic interaction matrices")
13780 "Cooler is a support library for a sparse, compressed, binary persistent
13781 storage format, called @code{cool}, used to store genomic interaction data,
13782 such as Hi-C contact matrices.")
13783 (license license:bsd-3)))
13785 (define-public python-hicexplorer
13787 (name "python-hicexplorer")
13791 ;; The latest version is not available on Pypi.
13793 (uri (git-reference
13794 (url "https://github.com/deeptools/HiCExplorer.git")
13796 (file-name (git-file-name name version))
13799 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13800 (build-system python-build-system)
13803 (modify-phases %standard-phases
13804 (add-after 'unpack 'loosen-up-requirements
13806 (substitute* "setup.py"
13810 `(("python-biopython" ,python-biopython)
13811 ("python-configparser" ,python-configparser)
13812 ("python-cooler" ,python-cooler)
13813 ("python-future" ,python-future)
13814 ("python-intervaltree" ,python-intervaltree)
13815 ("python-jinja2" ,python-jinja2)
13816 ("python-matplotlib" ,python-matplotlib)
13817 ("python-numpy" ,python-numpy)
13818 ("python-pandas" ,python-pandas)
13819 ("python-pybigwig" ,python-pybigwig)
13820 ("python-pysam" ,python-pysam)
13821 ("python-scipy" ,python-scipy)
13822 ("python-six" ,python-six)
13823 ("python-tables" ,python-tables)
13824 ("python-unidecode" ,python-unidecode)))
13825 (home-page "http://hicexplorer.readthedocs.io")
13826 (synopsis "Process, analyze and visualize Hi-C data")
13828 "HiCExplorer is a powerful and easy to use set of tools to process,
13829 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13830 contact matrices, correction of contacts, TAD detection, A/B compartments,
13831 merging, reordering or chromosomes, conversion from different formats
13832 including cooler and detection of long-range contacts. Moreover, it allows
13833 the visualization of multiple contact matrices along with other types of data
13834 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13835 genomic scores), long range contacts and the visualization of viewpoints.")
13836 (license license:gpl3)))
13838 (define-public python-pygenometracks
13840 (name "python-pygenometracks")
13845 (uri (pypi-uri "pyGenomeTracks" version))
13848 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13849 (build-system python-build-system)
13851 `(("python-configparser" ,python-configparser)
13852 ("python-future" ,python-future)
13853 ("python-hicexplorer" ,python-hicexplorer)
13854 ("python-intervaltree" ,python-intervaltree)
13855 ("python-matplotlib" ,python-matplotlib)
13856 ("python-numpy" ,python-numpy)
13857 ("python-pybigwig" ,python-pybigwig)))
13859 `(("python-pytest" ,python-pytest)))
13860 (home-page "https://pygenometracks.readthedocs.io")
13861 (synopsis "Program and library to plot beautiful genome browser tracks")
13863 "This package aims to produce high-quality genome browser tracks that
13864 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13865 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13866 pyGenomeTracks can make plots with or without Hi-C data.")
13867 (license license:gpl3+)))
13869 (define-public python-hic2cool
13871 (name "python-hic2cool")
13876 (uri (pypi-uri "hic2cool" version))
13879 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13880 (build-system python-build-system)
13881 (arguments '(#:tests? #f)) ; no tests included
13883 `(("python-cooler" ,python-cooler)))
13884 (home-page "https://github.com/4dn-dcic/hic2cool")
13885 (synopsis "Converter for .hic and .cool files")
13887 "This package provides a converter between @code{.hic} files (from
13888 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13889 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13891 (license license:expat)))
13893 (define-public r-pore
13901 (string-append "mirror://sourceforge/rpore/" version
13902 "/poRe_" version ".tar.gz"))
13904 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13905 (properties `((upstream-name . "poRe")))
13906 (build-system r-build-system)
13908 `(("r-bit64" ,r-bit64)
13909 ("r-data-table" ,r-data-table)
13910 ("r-rhdf5" ,r-rhdf5)
13911 ("r-shiny" ,r-shiny)
13912 ("r-svdialogs" ,r-svdialogs)))
13913 (home-page "https://sourceforge.net/projects/rpore/")
13914 (synopsis "Visualize Nanopore sequencing data")
13916 "This package provides graphical user interfaces to organize and visualize Nanopore
13918 ;; This is free software but the license variant is unclear:
13919 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13920 (license license:bsd-3)))
13922 (define-public r-xbioc
13923 (let ((revision "1")
13924 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13927 (version (git-version "0.1.15" revision commit))
13930 (uri (git-reference
13931 (url "https://github.com/renozao/xbioc.git")
13933 (file-name (git-file-name name version))
13936 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13937 (build-system r-build-system)
13939 `(("r-annotationdbi" ,r-annotationdbi)
13940 ("r-assertthat" ,r-assertthat)
13941 ("r-biobase" ,r-biobase)
13942 ("r-biocinstaller" ,r-biocinstaller)
13943 ("r-digest" ,r-digest)
13944 ("r-pkgmaker" ,r-pkgmaker)
13946 ("r-reshape2" ,r-reshape2)
13947 ("r-stringr" ,r-stringr)))
13948 (home-page "https://github.com/renozao/xbioc/")
13949 (synopsis "Extra base functions for Bioconductor")
13950 (description "This package provides extra utility functions to perform
13951 common tasks in the analysis of omics data, leveraging and enhancing features
13952 provided by Bioconductor packages.")
13953 (license license:gpl3+))))
13955 (define-public r-cssam
13956 (let ((revision "1")
13957 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13960 (version (git-version "1.4" revision commit))
13963 (uri (git-reference
13964 (url "https://github.com/shenorrLab/csSAM.git")
13966 (file-name (git-file-name name version))
13969 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13970 (build-system r-build-system)
13972 `(("r-formula" ,r-formula)
13973 ("r-ggplot2" ,r-ggplot2)
13974 ("r-pkgmaker" ,r-pkgmaker)
13976 ("r-rngtools" ,r-rngtools)
13977 ("r-scales" ,r-scales)))
13978 (home-page "https://github.com/shenorrLab/csSAM/")
13979 (synopsis "Cell type-specific statistical analysis of microarray")
13980 (description "This package implements the method csSAM that computes
13981 cell-specific differential expression from measured cell proportions using
13984 (license license:lgpl2.1+))))
13986 (define-public r-bseqsc
13987 (let ((revision "1")
13988 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13991 (version (git-version "1.0" revision commit))
13994 (uri (git-reference
13995 (url "https://github.com/shenorrLab/bseqsc.git")
13997 (file-name (git-file-name name version))
14000 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14001 (build-system r-build-system)
14003 `(("r-abind" ,r-abind)
14004 ("r-annotationdbi" ,r-annotationdbi)
14005 ("r-biobase" ,r-biobase)
14006 ("r-cssam" ,r-cssam)
14007 ("r-dplyr" ,r-dplyr)
14008 ("r-e1071" ,r-e1071)
14009 ("r-edger" ,r-edger)
14010 ("r-ggplot2" ,r-ggplot2)
14012 ("r-openxlsx" ,r-openxlsx)
14013 ("r-pkgmaker" ,r-pkgmaker)
14015 ("r-preprocesscore" ,r-preprocesscore)
14016 ("r-rngtools" ,r-rngtools)
14017 ("r-scales" ,r-scales)
14018 ("r-stringr" ,r-stringr)
14019 ("r-xbioc" ,r-xbioc)))
14020 (home-page "https://github.com/shenorrLab/bseqsc")
14021 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14022 (description "BSeq-sc is a bioinformatics analysis pipeline that
14023 leverages single-cell sequencing data to estimate cell type proportion and
14024 cell type-specific gene expression differences from RNA-seq data from bulk
14025 tissue samples. This is a companion package to the publication \"A
14026 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14027 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14028 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14029 (license license:gpl2+))))
14031 (define-public porechop
14032 ;; The recommended way to install is to clone the git repository
14033 ;; https://github.com/rrwick/Porechop#installation
14034 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14038 (version (git-version "0.2.3" revision commit))
14042 (uri (git-reference
14043 (url "https://github.com/rrwick/Porechop.git")
14045 (file-name (git-file-name name version))
14047 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14048 (build-system python-build-system)
14049 (home-page "https://github.com/rrwick/porechop")
14050 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14052 "The porechop package is a tool for finding and removing adapters from Oxford
14053 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14054 has an adapter in its middle, it is treated as chimeric and chopped into
14055 separate reads. Porechop performs thorough alignments to effectively find
14056 adapters, even at low sequence identity. Porechop also supports demultiplexing
14057 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14058 Barcoding Kit or Rapid Barcoding Kit.")
14059 (license license:gpl3+))))
14061 (define-public poretools
14062 ;; The latest release was in 2016 and the latest commit is from 2017
14063 ;; the recommended way to install is to clone the git repository
14064 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14065 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14069 (version (git-version "0.6.0" revision commit))
14073 (uri (git-reference
14074 (url "https://github.com/arq5x/poretools.git")
14076 (file-name (git-file-name name version))
14078 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14079 (build-system python-build-system)
14080 ;; requires python >=2.7, <3.0, and the same for python dependencies
14081 (arguments `(#:python ,python-2))
14085 `(("python-dateutil" ,python2-dateutil)
14086 ("python-h5py" ,python2-h5py)
14087 ("python-matplotlib" ,python2-matplotlib)
14088 ("python-pandas" ,python2-pandas)
14089 ("python-seaborn" ,python2-seaborn)))
14090 (home-page "https://poretools.readthedocs.io")
14091 (synopsis "Toolkit for working with nanopore sequencing data")
14093 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14094 This @code{poretools} package is a flexible toolkit for exploring datasets
14095 generated by nanopore sequencing devices for the purposes of quality control and
14096 downstream analysis. Poretools operates directly on the native FAST5, a variant
14097 of the Hierarchical Data Format (HDF5) standard.")
14098 (license license:expat))))
14100 (define-public r-absfiltergsea
14102 (name "r-absfiltergsea")
14107 (uri (cran-uri "AbsFilterGSEA" version))
14109 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14110 (properties `((upstream-name . "AbsFilterGSEA")))
14111 (build-system r-build-system)
14113 `(("r-biobase" ,r-biobase)
14114 ("r-deseq" ,r-deseq)
14115 ("r-limma" ,r-limma)
14117 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14118 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14119 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14121 "This package provides a function that performs gene-permuting of a gene-set
14122 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14123 Without filtering, users can perform (original) two-tailed or one-tailed
14125 (license license:gpl2)))
14127 (define-public jamm
14130 (version "1.0.7.5")
14134 (uri (git-reference
14135 (url "https://github.com/mahmoudibrahim/JAMM.git")
14136 (commit (string-append "JAMMv" version))))
14137 (file-name (git-file-name name version))
14140 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14141 (build-system gnu-build-system)
14143 `(#:tests? #f ; there are none
14145 (modify-phases %standard-phases
14146 (delete 'configure)
14149 (lambda* (#:key inputs outputs #:allow-other-keys)
14150 (let* ((out (assoc-ref outputs "out"))
14151 (libexec (string-append out "/libexec/jamm"))
14152 (bin (string-append out "/bin")))
14153 (substitute* '("JAMM.sh"
14154 "SignalGenerator.sh")
14156 (string-append "sPath=\"" libexec "\"\n")))
14157 (for-each (lambda (file)
14158 (install-file file libexec))
14159 (list "bincalculator.r"
14171 (chmod script #o555)
14172 (install-file script bin)
14173 (wrap-program (string-append bin "/" script)
14174 `("PATH" ":" prefix
14175 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14176 ,(string-append (assoc-ref inputs "gawk") "/bin")
14177 ,(string-append (assoc-ref inputs "perl") "/bin")
14178 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14179 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14180 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14181 (list "JAMM.sh" "SignalGenerator.sh")))
14185 ("coreutils" ,coreutils)
14188 ("r-minimal" ,r-minimal)
14189 ;;("r-parallel" ,r-parallel)
14190 ("r-signal" ,r-signal)
14191 ("r-mclust" ,r-mclust)))
14192 (home-page "https://github.com/mahmoudibrahim/JAMM")
14193 (synopsis "Peak finder for NGS datasets")
14195 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14196 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14197 boundaries accurately. JAMM is applicable to both broad and narrow
14199 (license license:gpl3+)))
14201 (define-public ngless
14208 (uri (git-reference
14209 (url "https://gitlab.com/ngless/ngless.git")
14210 (commit (string-append "v" version))))
14211 (file-name (git-file-name name version))
14214 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14215 (build-system haskell-build-system)
14217 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14218 ; error: parse error on input import
14219 ; import Options.Applicative
14221 (modify-phases %standard-phases
14222 (add-after 'unpack 'create-cabal-file
14223 (lambda _ (invoke "hpack") #t))
14224 ;; These tools are expected to be installed alongside ngless.
14225 (add-after 'install 'link-tools
14226 (lambda* (#:key inputs outputs #:allow-other-keys)
14227 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14228 (symlink (string-append (assoc-ref inputs "prodigal")
14230 (string-append bin "ngless-" ,version "-prodigal"))
14231 (symlink (string-append (assoc-ref inputs "minimap2")
14233 (string-append bin "ngless-" ,version "-minimap2"))
14234 (symlink (string-append (assoc-ref inputs "samtools")
14236 (string-append bin "ngless-" ,version "-samtools"))
14237 (symlink (string-append (assoc-ref inputs "bwa")
14239 (string-append bin "ngless-" ,version "-bwa"))
14242 `(("prodigal" ,prodigal)
14244 ("samtools" ,samtools)
14245 ("minimap2" ,minimap2)
14246 ("ghc-aeson" ,ghc-aeson)
14247 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14248 ("ghc-async" ,ghc-async)
14249 ("ghc-atomic-write" ,ghc-atomic-write)
14250 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14251 ("ghc-chart" ,ghc-chart)
14252 ("ghc-chart-cairo" ,ghc-chart-cairo)
14253 ("ghc-conduit" ,ghc-conduit)
14254 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14255 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14256 ("ghc-conduit-extra" ,ghc-conduit-extra)
14257 ("ghc-configurator" ,ghc-configurator)
14258 ("ghc-convertible" ,ghc-convertible)
14259 ("ghc-data-default" ,ghc-data-default)
14260 ("ghc-double-conversion" ,ghc-double-conversion)
14261 ("ghc-edit-distance" ,ghc-edit-distance)
14262 ("ghc-either" ,ghc-either)
14263 ("ghc-errors" ,ghc-errors)
14264 ("ghc-extra" ,ghc-extra)
14265 ("ghc-filemanip" ,ghc-filemanip)
14266 ("ghc-file-embed" ,ghc-file-embed)
14267 ("ghc-gitrev" ,ghc-gitrev)
14268 ("ghc-hashtables" ,ghc-hashtables)
14269 ("ghc-http-conduit" ,ghc-http-conduit)
14270 ("ghc-inline-c" ,ghc-inline-c)
14271 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14272 ("ghc-intervalmap" ,ghc-intervalmap)
14273 ("ghc-missingh" ,ghc-missingh)
14274 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14275 ("ghc-parsec" ,ghc-parsec)
14276 ("ghc-regex" ,ghc-regex)
14277 ("ghc-safe" ,ghc-safe)
14278 ("ghc-safeio" ,ghc-safeio)
14279 ("ghc-strict" ,ghc-strict)
14280 ("ghc-tar" ,ghc-tar)
14281 ("ghc-text" ,ghc-text)
14282 ("ghc-unliftio" ,ghc-unliftio)
14283 ("ghc-unliftio-core" ,ghc-unliftio-core)
14284 ("ghc-vector" ,ghc-vector)
14285 ("ghc-yaml" ,ghc-yaml)
14286 ("ghc-zlib" ,ghc-zlib)))
14289 ("r-hdf5r" ,r-hdf5r)
14290 ("r-iterators" ,r-iterators)
14291 ("r-itertools" ,r-itertools)
14292 ("r-matrix" ,r-matrix)))
14294 `(("ghc-hpack" ,ghc-hpack)
14295 ("ghc-quickcheck" ,ghc-quickcheck)
14296 ("ghc-test-framework" ,ghc-test-framework)
14297 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14298 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14299 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14300 (home-page "https://gitlab.com/ngless/ngless")
14301 (synopsis "DSL for processing next-generation sequencing data")
14302 (description "Ngless is a domain-specific language for
14303 @dfn{next-generation sequencing} (NGS) data processing.")
14304 (license license:expat)))
14306 (define-public filtlong
14307 ;; The recommended way to install is to clone the git repository
14308 ;; https://github.com/rrwick/Filtlong#installation
14309 ;; and the lastest release is more than nine months old
14310 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14314 (version (git-version "0.2.0" revision commit))
14318 (uri (git-reference
14319 (url "https://github.com/rrwick/Filtlong.git")
14321 (file-name (git-file-name name version))
14323 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14324 (build-system gnu-build-system)
14326 `(#:tests? #f ; no check target
14328 (modify-phases %standard-phases
14329 (delete 'configure)
14331 (lambda* (#:key outputs #:allow-other-keys)
14332 (let* ((out (assoc-ref outputs "out"))
14333 (bin (string-append out "/bin"))
14334 (scripts (string-append out "/share/filtlong/scripts")))
14335 (install-file "bin/filtlong" bin)
14336 (install-file "scripts/histogram.py" scripts)
14337 (install-file "scripts/read_info_histograms.sh" scripts))
14339 (add-after 'install 'wrap-program
14340 (lambda* (#:key inputs outputs #:allow-other-keys)
14341 (let* ((out (assoc-ref outputs "out"))
14342 (path (getenv "PYTHONPATH")))
14343 (wrap-program (string-append out
14344 "/share/filtlong/scripts/histogram.py")
14345 `("PYTHONPATH" ":" prefix (,path))))
14347 (add-before 'check 'patch-tests
14349 (substitute* "scripts/read_info_histograms.sh"
14350 (("awk") (which "gawk")))
14353 `(("gawk" ,gawk) ;for read_info_histograms.sh
14354 ("python" ,python-2) ;required for histogram.py
14356 (home-page "https://github.com/rrwick/Filtlong/")
14357 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14359 "The Filtlong package is a tool for filtering long reads by quality.
14360 It can take a set of long reads and produce a smaller, better subset. It uses
14361 both read length (longer is better) and read identity (higher is better) when
14362 choosing which reads pass the filter.")
14363 (license (list license:gpl3 ;filtlong
14364 license:asl2.0))))) ;histogram.py
14366 (define-public nanopolish
14367 ;; The recommended way to install is to clone the git repository
14368 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14369 ;; Also, the differences between release and current version seem to be
14371 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14374 (name "nanopolish")
14375 (version (git-version "0.10.2" revision commit))
14379 (uri (git-reference
14380 (url "https://github.com/jts/nanopolish.git")
14383 (file-name (git-file-name name version))
14385 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14386 (build-system gnu-build-system)
14389 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14390 #:tests? #f ; no check target
14392 (modify-phases %standard-phases
14393 (add-after 'unpack 'find-eigen
14394 (lambda* (#:key inputs #:allow-other-keys)
14396 (string-append (assoc-ref inputs "eigen")
14397 "/include/eigen3"))
14399 (delete 'configure)
14401 (lambda* (#:key outputs #:allow-other-keys)
14402 (let* ((out (assoc-ref outputs "out"))
14403 (bin (string-append out "/bin"))
14404 (scripts (string-append out "/share/nanopolish/scripts")))
14406 (install-file "nanopolish" bin)
14407 (for-each (lambda (file) (install-file file scripts))
14408 (find-files "scripts" ".*"))
14410 (add-after 'install 'wrap-programs
14411 (lambda* (#:key outputs #:allow-other-keys)
14412 (for-each (lambda (file)
14413 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14414 (find-files "/share/nanopolish/scripts" "\\.py"))
14415 (for-each (lambda (file)
14416 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14417 (find-files "/share/nanopolish/scripts" "\\.pl"))
14425 ("python-biopython" ,python-biopython)
14426 ("python-numpy" ,python-numpy)
14427 ("python-pysam" ,python-pysam)
14428 ("python-scikit-learn" , python-scikit-learn)
14429 ("python-scipy" ,python-scipy)
14431 (home-page "https://github.com/jts/nanopolish")
14432 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14434 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14435 Nanopolish can calculate an improved consensus sequence for a draft genome
14436 assembly, detect base modifications, call SNPs (Single nucleotide
14437 polymorphisms) and indels with respect to a reference genome and more.")
14438 (license license:expat))))