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 jemalloc)
82 #:use-module (gnu packages dlang)
83 #:use-module (gnu packages linux)
84 #:use-module (gnu packages logging)
85 #:use-module (gnu packages machine-learning)
86 #:use-module (gnu packages man)
87 #:use-module (gnu packages maths)
88 #:use-module (gnu packages mpi)
89 #:use-module (gnu packages ncurses)
90 #:use-module (gnu packages ocaml)
91 #:use-module (gnu packages pcre)
92 #:use-module (gnu packages parallel)
93 #:use-module (gnu packages pdf)
94 #:use-module (gnu packages perl)
95 #:use-module (gnu packages perl-check)
96 #:use-module (gnu packages pkg-config)
97 #:use-module (gnu packages popt)
98 #:use-module (gnu packages protobuf)
99 #:use-module (gnu packages python)
100 #:use-module (gnu packages python-web)
101 #:use-module (gnu packages readline)
102 #:use-module (gnu packages ruby)
103 #:use-module (gnu packages serialization)
104 #:use-module (gnu packages shells)
105 #:use-module (gnu packages statistics)
106 #:use-module (gnu packages swig)
107 #:use-module (gnu packages tbb)
108 #:use-module (gnu packages tex)
109 #:use-module (gnu packages texinfo)
110 #:use-module (gnu packages textutils)
111 #:use-module (gnu packages time)
112 #:use-module (gnu packages tls)
113 #:use-module (gnu packages vim)
114 #:use-module (gnu packages web)
115 #:use-module (gnu packages xml)
116 #:use-module (gnu packages xorg)
117 #:use-module (srfi srfi-1)
118 #:use-module (ice-9 match))
120 (define-public aragorn
127 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
131 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
132 (build-system gnu-build-system)
134 `(#:tests? #f ; there are no tests
136 (modify-phases %standard-phases
146 (string-append "aragorn" ,version ".c"))
149 (lambda* (#:key outputs #:allow-other-keys)
150 (let* ((out (assoc-ref outputs "out"))
151 (bin (string-append out "/bin"))
152 (man (string-append out "/share/man/man1")))
153 (install-file "aragorn" bin)
154 (install-file "aragorn.1" man))
156 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
157 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
159 "Aragorn identifies transfer RNA, mitochondrial RNA and
160 transfer-messenger RNA from nucleotide sequences, based on homology to known
161 tRNA consensus sequences and RNA structure. It also outputs the secondary
162 structure of the predicted RNA.")
163 (license license:gpl2)))
171 ;; BamM is not available on pypi.
173 (url "https://github.com/Ecogenomics/BamM.git")
176 (file-name (git-file-name name version))
179 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
180 (modules '((guix build utils)))
183 ;; Delete bundled htslib.
184 (delete-file-recursively "c/htslib-1.3.1")
186 (build-system python-build-system)
188 `(#:python ,python-2 ; BamM is Python 2 only.
189 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
190 ;; been modified from its original form.
192 (let ((htslib (assoc-ref %build-inputs "htslib")))
193 (list "--with-libhts-lib" (string-append htslib "/lib")
194 "--with-libhts-inc" (string-append htslib "/include/htslib")))
196 (modify-phases %standard-phases
197 (add-after 'unpack 'autogen
199 (with-directory-excursion "c"
200 (let ((sh (which "sh")))
201 (for-each make-file-writable (find-files "." ".*"))
202 ;; Use autogen so that 'configure' works.
203 (substitute* "autogen.sh" (("/bin/sh") sh))
204 (setenv "CONFIG_SHELL" sh)
205 (invoke "./autogen.sh")))
208 ;; Run tests after installation so compilation only happens once.
210 (add-after 'install 'wrap-executable
211 (lambda* (#:key outputs #:allow-other-keys)
212 (let* ((out (assoc-ref outputs "out"))
213 (path (getenv "PATH")))
214 (wrap-program (string-append out "/bin/bamm")
215 `("PATH" ":" prefix (,path))))
217 (add-after 'wrap-executable 'post-install-check
218 (lambda* (#:key inputs outputs #:allow-other-keys)
220 (string-append (assoc-ref outputs "out")
225 (assoc-ref outputs "out")
227 (string-take (string-take-right
228 (assoc-ref inputs "python") 5) 3)
230 (getenv "PYTHONPATH")))
231 ;; There are 2 errors printed, but they are safe to ignore:
232 ;; 1) [E::hts_open_format] fail to open file ...
233 ;; 2) samtools view: failed to open ...
237 `(("autoconf" ,autoconf)
238 ("automake" ,automake)
241 ("python-nose" ,python2-nose)
242 ("python-pysam" ,python2-pysam)))
244 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
245 ("samtools" ,samtools)
249 ("coreutils" ,coreutils)))
251 `(("python-numpy" ,python2-numpy)))
252 (home-page "http://ecogenomics.github.io/BamM/")
253 (synopsis "Metagenomics-focused BAM file manipulator")
255 "BamM is a C library, wrapped in python, to efficiently generate and
256 parse BAM files, specifically for the analysis of metagenomic data. For
257 instance, it implements several methods to assess contig-wise read coverage.")
258 (license license:lgpl3+)))
260 (define-public bamtools
267 (url "https://github.com/pezmaster31/bamtools.git")
268 (commit (string-append "v" version))))
269 (file-name (git-file-name name version))
272 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
273 (build-system cmake-build-system)
275 `(#:tests? #f ;no "check" target
277 (modify-phases %standard-phases
279 'configure 'set-ldflags
280 (lambda* (#:key outputs #:allow-other-keys)
284 (assoc-ref outputs "out") "/lib/bamtools"))
286 (inputs `(("zlib" ,zlib)))
287 (home-page "https://github.com/pezmaster31/bamtools")
288 (synopsis "C++ API and command-line toolkit for working with BAM data")
290 "BamTools provides both a C++ API and a command-line toolkit for handling
292 (license license:expat)))
294 (define-public bcftools
300 (uri (string-append "https://github.com/samtools/bcftools/"
302 version "/bcftools-" version ".tar.bz2"))
305 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
306 (modules '((guix build utils)))
308 ;; Delete bundled htslib.
309 (delete-file-recursively "htslib-1.9")
311 (build-system gnu-build-system)
314 (list "--enable-libgsl")
317 (modify-phases %standard-phases
318 (add-before 'check 'patch-tests
320 (substitute* "test/test.pl"
321 (("/bin/bash") (which "bash")))
329 (home-page "https://samtools.github.io/bcftools/")
330 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
332 "BCFtools is a set of utilities that manipulate variant calls in the
333 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
334 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
335 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
336 (license (list license:gpl3+ license:expat))))
338 (define-public bedops
345 (url "https://github.com/bedops/bedops.git")
346 (commit (string-append "v" version))))
347 (file-name (git-file-name name version))
350 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
351 (build-system gnu-build-system)
354 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
356 (modify-phases %standard-phases
357 (add-after 'unpack 'unpack-tarballs
359 ;; FIXME: Bedops includes tarballs of minimally patched upstream
360 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
361 ;; libraries because at least one of the libraries (zlib) is
362 ;; patched to add a C++ function definition (deflateInit2cpp).
363 ;; Until the Bedops developers offer a way to link against system
364 ;; libraries we have to build the in-tree copies of these three
367 ;; See upstream discussion:
368 ;; https://github.com/bedops/bedops/issues/124
370 ;; Unpack the tarballs to benefit from shebang patching.
371 (with-directory-excursion "third-party"
372 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
373 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
374 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
375 ;; Disable unpacking of tarballs in Makefile.
376 (substitute* "system.mk/Makefile.linux"
377 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
378 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
379 (substitute* "third-party/zlib-1.2.7/Makefile.in"
380 (("^SHELL=.*$") "SHELL=bash\n"))
382 (delete 'configure))))
383 (home-page "https://github.com/bedops/bedops")
384 (synopsis "Tools for high-performance genomic feature operations")
386 "BEDOPS is a suite of tools to address common questions raised in genomic
387 studies---mostly with regard to overlap and proximity relationships between
388 data sets. It aims to be scalable and flexible, facilitating the efficient
389 and accurate analysis and management of large-scale genomic data.
391 BEDOPS provides tools that perform highly efficient and scalable Boolean and
392 other set operations, statistical calculations, archiving, conversion and
393 other management of genomic data of arbitrary scale. Tasks can be easily
394 split by chromosome for distributing whole-genome analyses across a
395 computational cluster.")
396 (license license:gpl2+)))
398 (define-public bedtools
404 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
405 "download/v" version "/"
406 "bedtools-" version ".tar.gz"))
409 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
410 (build-system gnu-build-system)
412 '(#:test-target "test"
414 (list (string-append "prefix=" (assoc-ref %outputs "out")))
416 (modify-phases %standard-phases
417 (delete 'configure))))
418 (native-inputs `(("python" ,python-2)))
420 `(("samtools" ,samtools)
422 (home-page "https://github.com/arq5x/bedtools2")
423 (synopsis "Tools for genome analysis and arithmetic")
425 "Collectively, the bedtools utilities are a swiss-army knife of tools for
426 a wide-range of genomics analysis tasks. The most widely-used tools enable
427 genome arithmetic: that is, set theory on the genome. For example, bedtools
428 allows one to intersect, merge, count, complement, and shuffle genomic
429 intervals from multiple files in widely-used genomic file formats such as BAM,
431 (license license:gpl2)))
433 ;; Later releases of bedtools produce files with more columns than
434 ;; what Ribotaper expects.
435 (define-public bedtools-2.18
436 (package (inherit bedtools)
441 (uri (string-append "https://github.com/arq5x/bedtools2/"
442 "releases/download/v" version
443 "/bedtools-" version ".tar.gz"))
446 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
448 '(#:test-target "test"
450 (modify-phases %standard-phases
453 (lambda* (#:key outputs #:allow-other-keys)
454 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
455 (for-each (lambda (file)
456 (install-file file bin))
457 (find-files "bin" ".*")))
460 ;; Needed for pybedtools.
461 (define-public bedtools-2.26
462 (package (inherit bedtools)
467 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
468 "download/v" version "/"
469 "bedtools-" version ".tar.gz"))
472 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
474 (define-public ribotaper
480 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
481 "files/RiboTaper/RiboTaper_Version_"
485 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
486 (build-system gnu-build-system)
489 (modify-phases %standard-phases
490 (add-after 'install 'wrap-executables
491 (lambda* (#:key inputs outputs #:allow-other-keys)
492 (let* ((out (assoc-ref outputs "out")))
495 (wrap-program (string-append out "/bin/" script)
496 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
497 '("create_annotations_files.bash"
498 "create_metaplots.bash"
499 "Ribotaper_ORF_find.sh"
503 `(("bedtools" ,bedtools-2.18)
504 ("samtools" ,samtools-0.1)
505 ("r-minimal" ,r-minimal)
506 ("r-foreach" ,r-foreach)
507 ("r-xnomial" ,r-xnomial)
509 ("r-multitaper" ,r-multitaper)
510 ("r-seqinr" ,r-seqinr)))
511 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
512 (synopsis "Define translated ORFs using ribosome profiling data")
514 "Ribotaper is a method for defining translated @dfn{open reading
515 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
516 provides the Ribotaper pipeline.")
517 (license license:gpl3+)))
519 (define-public ribodiff
527 (url "https://github.com/ratschlab/RiboDiff.git")
528 (commit (string-append "v" version))))
529 (file-name (git-file-name name version))
532 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
533 (build-system python-build-system)
537 (modify-phases %standard-phases
538 ;; Generate an installable executable script wrapper.
539 (add-after 'unpack 'patch-setup.py
541 (substitute* "setup.py"
542 (("^(.*)packages=.*" line prefix)
543 (string-append line "\n"
544 prefix "scripts=['scripts/TE.py'],\n")))
547 `(("python-numpy" ,python2-numpy)
548 ("python-matplotlib" ,python2-matplotlib)
549 ("python-scipy" ,python2-scipy)
550 ("python-statsmodels" ,python2-statsmodels)))
552 `(("python-mock" ,python2-mock)
553 ("python-nose" ,python2-nose)))
554 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
555 (synopsis "Detect translation efficiency changes from ribosome footprints")
556 (description "RiboDiff is a statistical tool that detects the protein
557 translational efficiency change from Ribo-Seq (ribosome footprinting) and
558 RNA-Seq data. It uses a generalized linear model to detect genes showing
559 difference in translational profile taking mRNA abundance into account. It
560 facilitates us to decipher the translational regulation that behave
561 independently with transcriptional regulation.")
562 (license license:gpl3+)))
564 (define-public bioawk
571 (url "https://github.com/lh3/bioawk.git")
572 (commit (string-append "v" version))))
573 (file-name (git-file-name name version))
576 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
577 (build-system gnu-build-system)
583 `(#:tests? #f ; There are no tests to run.
584 ;; Bison must generate files, before other targets can build.
587 (modify-phases %standard-phases
588 (delete 'configure) ; There is no configure phase.
590 (lambda* (#:key outputs #:allow-other-keys)
591 (let* ((out (assoc-ref outputs "out"))
592 (bin (string-append out "/bin"))
593 (man (string-append out "/share/man/man1")))
595 (copy-file "awk.1" (string-append man "/bioawk.1"))
596 (install-file "bioawk" bin))
598 (home-page "https://github.com/lh3/bioawk")
599 (synopsis "AWK with bioinformatics extensions")
600 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
601 support of several common biological data formats, including optionally gzip'ed
602 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
603 also adds a few built-in functions and a command line option to use TAB as the
604 input/output delimiter. When the new functionality is not used, bioawk is
605 intended to behave exactly the same as the original BWK awk.")
606 (license license:x11)))
608 (define-public python-pybedtools
610 (name "python-pybedtools")
614 (uri (pypi-uri "pybedtools" version))
617 "0l2b2wrnj85azfqgr0zwr60f7j58vlla1hcgxvr9rwikpl8j72ji"))))
618 (build-system python-build-system)
621 (modify-phases %standard-phases
622 ;; See https://github.com/daler/pybedtools/issues/261
623 (add-after 'unpack 'disable-broken-tests
625 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
626 ;; graphical environment.
627 (substitute* "pybedtools/test/test_scripts.py"
628 (("def test_venn_mpl")
629 "def _do_not_test_venn_mpl"))
630 ;; Requires internet access.
631 (substitute* "pybedtools/test/test_helpers.py"
632 (("def test_chromsizes")
633 "def _do_not_test_chromsizes"))
634 ;; FIXME: these two fail for no good reason.
635 (substitute* "pybedtools/test/test1.py"
636 (("def test_issue_157")
637 "def _do_not_test_issue_157")
638 (("def test_to_dataframe")
639 "def _do_not_test_to_dataframe"))
642 ;; Tests don't pass with Bedtools 2.27.1.
643 ;; See https://github.com/daler/pybedtools/issues/260
644 `(("bedtools" ,bedtools-2.26)
645 ("samtools" ,samtools)
646 ("python-matplotlib" ,python-matplotlib)
647 ("python-pysam" ,python-pysam)
648 ("python-pyyaml" ,python-pyyaml)))
650 `(("python-numpy" ,python-numpy)
651 ("python-pandas" ,python-pandas)
652 ("python-cython" ,python-cython)
653 ("python-nose" ,python-nose)
654 ("kentutils" ,kentutils) ; for bedGraphToBigWig
655 ("python-six" ,python-six)))
656 (home-page "https://pythonhosted.org/pybedtools/")
657 (synopsis "Python wrapper for BEDtools programs")
659 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
660 which are widely used for genomic interval manipulation or \"genome algebra\".
661 pybedtools extends BEDTools by offering feature-level manipulations from with
663 (license license:gpl2+)))
665 (define-public python2-pybedtools
666 (let ((pkg (package-with-python2 python-pybedtools)))
667 (package (inherit pkg)
669 `(#:modules ((ice-9 ftw)
673 (guix build python-build-system))
674 ;; See https://github.com/daler/pybedtools/issues/192
675 ,@(substitute-keyword-arguments (package-arguments pkg)
677 `(modify-phases ,phases
680 (let ((cwd (getcwd)))
682 (string-append cwd "/build/"
683 (find (cut string-prefix? "lib" <>)
684 (scandir (string-append cwd "/build")))
685 ":" (getenv "PYTHONPATH"))))
686 ;; The tests need to be run from elsewhere...
687 (mkdir-p "/tmp/test")
688 (copy-recursively "pybedtools/test" "/tmp/test")
689 (with-directory-excursion "/tmp/test"
691 ;; This test fails for unknown reasons
692 "--exclude=.*test_getting_example_beds"))
695 (define-public python-biom-format
697 (name "python-biom-format")
702 ;; Use GitHub as source because PyPI distribution does not contain
703 ;; test data: https://github.com/biocore/biom-format/issues/693
705 (url "https://github.com/biocore/biom-format.git")
707 (file-name (git-file-name name version))
710 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
711 (build-system python-build-system)
714 (modify-phases %standard-phases
715 (add-after 'unpack 'use-cython
716 (lambda _ (setenv "USE_CYTHON" "1") #t))
717 (add-after 'unpack 'disable-broken-test
719 (substitute* "biom/tests/test_cli/test_validate_table.py"
720 (("^(.+)def test_invalid_hdf5" m indent)
721 (string-append indent
722 "@npt.dec.skipif(True, msg='Guix')\n"
725 (add-before 'reset-gzip-timestamps 'make-files-writable
726 (lambda* (#:key outputs #:allow-other-keys)
727 (let ((out (assoc-ref outputs "out")))
728 (for-each (lambda (file) (chmod file #o644))
729 (find-files out "\\.gz"))
732 `(("python-numpy" ,python-numpy)
733 ("python-scipy" ,python-scipy)
734 ("python-flake8" ,python-flake8)
735 ("python-future" ,python-future)
736 ("python-click" ,python-click)
737 ("python-h5py" ,python-h5py)
738 ("python-pandas" ,python-pandas)))
740 `(("python-cython" ,python-cython)
741 ("python-pytest" ,python-pytest)
742 ("python-pytest-cov" ,python-pytest-cov)
743 ("python-nose" ,python-nose)))
744 (home-page "http://www.biom-format.org")
745 (synopsis "Biological Observation Matrix (BIOM) format utilities")
747 "The BIOM file format is designed to be a general-use format for
748 representing counts of observations e.g. operational taxonomic units, KEGG
749 orthology groups or lipid types, in one or more biological samples
750 e.g. microbiome samples, genomes, metagenomes.")
751 (license license:bsd-3)
752 (properties `((python2-variant . ,(delay python2-biom-format))))))
754 (define-public python2-biom-format
755 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
759 (substitute-keyword-arguments (package-arguments base)
761 `(modify-phases ,phases
762 ;; Do not require the unmaintained pyqi library.
763 (add-after 'unpack 'remove-pyqi
765 (substitute* "setup.py"
766 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
769 (define-public bioperl-minimal
770 (let* ((inputs `(("perl-module-build" ,perl-module-build)
771 ("perl-data-stag" ,perl-data-stag)
772 ("perl-libwww" ,perl-libwww)
773 ("perl-uri" ,perl-uri)))
775 (map (compose package-name cadr)
778 (map (compose package-transitive-target-inputs cadr) inputs))))))
780 (name "bioperl-minimal")
785 (uri (string-append "https://github.com/bioperl/bioperl-live/"
787 (string-map (lambda (c)
793 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
794 (build-system perl-build-system)
797 (modify-phases %standard-phases
799 'install 'wrap-programs
800 (lambda* (#:key outputs #:allow-other-keys)
801 ;; Make sure all executables in "bin" find the required Perl
802 ;; modules at runtime. As the PERL5LIB variable contains also
803 ;; the paths of native inputs, we pick the transitive target
804 ;; inputs from %build-inputs.
805 (let* ((out (assoc-ref outputs "out"))
806 (bin (string-append out "/bin/"))
808 (cons (string-append out "/lib/perl5/site_perl")
810 (assoc-ref %build-inputs name))
811 ',transitive-inputs))
813 (for-each (lambda (file)
815 `("PERL5LIB" ":" prefix (,path))))
816 (find-files bin "\\.pl$"))
820 `(("perl-test-most" ,perl-test-most)))
821 (home-page "https://metacpan.org/release/BioPerl")
822 (synopsis "Bioinformatics toolkit")
824 "BioPerl is the product of a community effort to produce Perl code which
825 is useful in biology. Examples include Sequence objects, Alignment objects
826 and database searching objects. These objects not only do what they are
827 advertised to do in the documentation, but they also interact - Alignment
828 objects are made from the Sequence objects, Sequence objects have access to
829 Annotation and SeqFeature objects and databases, Blast objects can be
830 converted to Alignment objects, and so on. This means that the objects
831 provide a coordinated and extensible framework to do computational biology.")
832 (license license:perl-license))))
834 (define-public python-biopython
836 (name "python-biopython")
840 ;; use PyPi rather than biopython.org to ease updating
841 (uri (pypi-uri "biopython" version))
844 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
845 (build-system python-build-system)
848 (modify-phases %standard-phases
849 (add-before 'check 'set-home
850 ;; Some tests require a home directory to be set.
851 (lambda _ (setenv "HOME" "/tmp") #t)))))
853 `(("python-numpy" ,python-numpy)))
854 (home-page "http://biopython.org/")
855 (synopsis "Tools for biological computation in Python")
857 "Biopython is a set of tools for biological computation including parsers
858 for bioinformatics files into Python data structures; interfaces to common
859 bioinformatics programs; a standard sequence class and tools for performing
860 common operations on them; code to perform data classification; code for
861 dealing with alignments; code making it easy to split up parallelizable tasks
862 into separate processes; and more.")
863 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
865 (define-public python2-biopython
866 (package-with-python2 python-biopython))
868 (define-public python-fastalite
870 (name "python-fastalite")
875 (uri (pypi-uri "fastalite" version))
878 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
879 (build-system python-build-system)
881 `(#:tests? #f)) ; Test data is not distributed.
882 (home-page "https://github.com/nhoffman/fastalite")
883 (synopsis "Simplest possible FASTA parser")
884 (description "This library implements a FASTA and a FASTQ parser without
885 relying on a complex dependency tree.")
886 (license license:expat)))
888 (define-public python2-fastalite
889 (package-with-python2 python-fastalite))
891 (define-public bpp-core
892 ;; The last release was in 2014 and the recommended way to install from source
893 ;; is to clone the git repository, so we do this.
894 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
895 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
898 (version (string-append "2.2.0-1." (string-take commit 7)))
902 (url "http://biopp.univ-montp2.fr/git/bpp-core")
904 (file-name (string-append name "-" version "-checkout"))
907 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
908 (build-system cmake-build-system)
910 `(#:parallel-build? #f))
912 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
913 ; compile all of the bpp packages with GCC 5.
914 (home-page "http://biopp.univ-montp2.fr")
915 (synopsis "C++ libraries for Bioinformatics")
917 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
918 analysis, phylogenetics, molecular evolution and population genetics. It is
919 Object Oriented and is designed to be both easy to use and computer efficient.
920 Bio++ intends to help programmers to write computer expensive programs, by
921 providing them a set of re-usable tools.")
922 (license license:cecill-c))))
924 (define-public bpp-phyl
925 ;; The last release was in 2014 and the recommended way to install from source
926 ;; is to clone the git repository, so we do this.
927 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
928 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
931 (version (string-append "2.2.0-1." (string-take commit 7)))
935 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
937 (file-name (string-append name "-" version "-checkout"))
940 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
941 (build-system cmake-build-system)
943 `(#:parallel-build? #f
944 ;; If out-of-source, test data is not copied into the build directory
945 ;; so the tests fail.
946 #:out-of-source? #f))
948 `(("bpp-core" ,bpp-core)
950 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
953 (home-page "http://biopp.univ-montp2.fr")
954 (synopsis "Bio++ phylogenetic Library")
956 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
957 analysis, phylogenetics, molecular evolution and population genetics. This
958 library provides phylogenetics-related modules.")
959 (license license:cecill-c))))
961 (define-public bpp-popgen
962 ;; The last release was in 2014 and the recommended way to install from source
963 ;; is to clone the git repository, so we do this.
964 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
965 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
968 (version (string-append "2.2.0-1." (string-take commit 7)))
972 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
974 (file-name (string-append name "-" version "-checkout"))
977 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
978 (build-system cmake-build-system)
980 `(#:parallel-build? #f
981 #:tests? #f)) ; There are no tests.
983 `(("bpp-core" ,bpp-core)
986 (home-page "http://biopp.univ-montp2.fr")
987 (synopsis "Bio++ population genetics library")
989 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
990 analysis, phylogenetics, molecular evolution and population genetics. This
991 library provides population genetics-related modules.")
992 (license license:cecill-c))))
994 (define-public bpp-seq
995 ;; The last release was in 2014 and the recommended way to install from source
996 ;; is to clone the git repository, so we do this.
997 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
998 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1001 (version (string-append "2.2.0-1." (string-take commit 7)))
1005 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1007 (file-name (string-append name "-" version "-checkout"))
1010 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1011 (build-system cmake-build-system)
1013 `(#:parallel-build? #f
1014 ;; If out-of-source, test data is not copied into the build directory
1015 ;; so the tests fail.
1016 #:out-of-source? #f))
1018 `(("bpp-core" ,bpp-core)
1019 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1020 (home-page "http://biopp.univ-montp2.fr")
1021 (synopsis "Bio++ sequence library")
1023 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1024 analysis, phylogenetics, molecular evolution and population genetics. This
1025 library provides sequence-related modules.")
1026 (license license:cecill-c))))
1028 (define-public bppsuite
1029 ;; The last release was in 2014 and the recommended way to install from source
1030 ;; is to clone the git repository, so we do this.
1031 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1032 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1035 (version (string-append "2.2.0-1." (string-take commit 7)))
1039 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1041 (file-name (string-append name "-" version "-checkout"))
1044 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1045 (build-system cmake-build-system)
1047 `(#:parallel-build? #f
1048 #:tests? #f)) ; There are no tests.
1052 ("texinfo" ,texinfo)))
1054 `(("bpp-core" ,bpp-core)
1055 ("bpp-seq" ,bpp-seq)
1056 ("bpp-phyl" ,bpp-phyl)
1057 ("bpp-phyl" ,bpp-popgen)
1059 (home-page "http://biopp.univ-montp2.fr")
1060 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1062 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1063 analysis, phylogenetics, molecular evolution and population genetics. This
1064 package provides command line tools using the Bio++ library.")
1065 (license license:cecill-c))))
1067 (define-public blast+
1074 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1075 version "/ncbi-blast-" version "+-src.tar.gz"))
1078 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1079 (patches (search-patches "blast+-fix-makefile.patch"))
1080 (modules '((guix build utils)))
1083 ;; Remove bundled bzip2, zlib and pcre.
1084 (delete-file-recursively "c++/src/util/compress/bzip2")
1085 (delete-file-recursively "c++/src/util/compress/zlib")
1086 (delete-file-recursively "c++/src/util/regexp")
1087 (substitute* "c++/src/util/compress/Makefile.in"
1088 (("bzip2 zlib api") "api"))
1089 ;; Remove useless msbuild directory
1090 (delete-file-recursively
1091 "c++/src/build-system/project_tree_builder/msbuild")
1093 (build-system gnu-build-system)
1095 `(;; There are two(!) tests for this massive library, and both fail with
1096 ;; "unparsable timing stats".
1097 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1098 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1101 #:parallel-build? #f ; not supported
1103 (modify-phases %standard-phases
1104 (add-before 'configure 'set-HOME
1105 ;; $HOME needs to be set at some point during the configure phase
1106 (lambda _ (setenv "HOME" "/tmp") #t))
1107 (add-after 'unpack 'enter-dir
1108 (lambda _ (chdir "c++") #t))
1109 (add-after 'enter-dir 'fix-build-system
1111 (define (which* cmd)
1112 (cond ((string=? cmd "date")
1113 ;; make call to "date" deterministic
1118 (format (current-error-port)
1119 "WARNING: Unable to find absolute path for ~s~%"
1123 ;; Rewrite hardcoded paths to various tools
1124 (substitute* (append '("src/build-system/configure.ac"
1125 "src/build-system/configure"
1126 "src/build-system/helpers/run_with_lock.c"
1127 "scripts/common/impl/if_diff.sh"
1128 "scripts/common/impl/run_with_lock.sh"
1129 "src/build-system/Makefile.configurables.real"
1130 "src/build-system/Makefile.in.top"
1131 "src/build-system/Makefile.meta.gmake=no"
1132 "src/build-system/Makefile.meta.in"
1133 "src/build-system/Makefile.meta_l"
1134 "src/build-system/Makefile.meta_p"
1135 "src/build-system/Makefile.meta_r"
1136 "src/build-system/Makefile.mk.in"
1137 "src/build-system/Makefile.requirements"
1138 "src/build-system/Makefile.rules_with_autodep.in")
1139 (find-files "scripts/common/check" "\\.sh$"))
1140 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1141 (or (which* cmd) all)))
1143 (substitute* (find-files "src/build-system" "^config.*")
1144 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1147 ;; rewrite "/var/tmp" in check script
1148 (substitute* "scripts/common/check/check_make_unix.sh"
1149 (("/var/tmp") "/tmp"))
1151 ;; do not reset PATH
1152 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1154 (("action=/bin/") "action=")
1155 (("export PATH") ":"))
1158 (lambda* (#:key inputs outputs #:allow-other-keys)
1159 (let ((out (assoc-ref outputs "out"))
1160 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1161 (include (string-append (assoc-ref outputs "include")
1162 "/include/ncbi-tools++")))
1163 ;; The 'configure' script doesn't recognize things like
1164 ;; '--enable-fast-install'.
1165 (invoke "./configure.orig"
1166 (string-append "--with-build-root=" (getcwd) "/build")
1167 (string-append "--prefix=" out)
1168 (string-append "--libdir=" lib)
1169 (string-append "--includedir=" include)
1170 (string-append "--with-bz2="
1171 (assoc-ref inputs "bzip2"))
1172 (string-append "--with-z="
1173 (assoc-ref inputs "zlib"))
1174 (string-append "--with-pcre="
1175 (assoc-ref inputs "pcre"))
1176 ;; Each library is built twice by default, once
1177 ;; with "-static" in its name, and again
1182 (outputs '("out" ; 21 MB
1190 ("python" ,python-wrapper)))
1193 (home-page "http://blast.ncbi.nlm.nih.gov")
1194 (synopsis "Basic local alignment search tool")
1196 "BLAST is a popular method of performing a DNA or protein sequence
1197 similarity search, using heuristics to produce results quickly. It also
1198 calculates an “expect value” that estimates how many matches would have
1199 occurred at a given score by chance, which can aid a user in judging how much
1200 confidence to have in an alignment.")
1201 ;; Most of the sources are in the public domain, with the following
1204 ;; * ./c++/include/util/bitset/
1205 ;; * ./c++/src/html/ncbi_menu*.js
1207 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1209 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1211 ;; * ./c++/src/corelib/teamcity_*
1212 (license (list license:public-domain
1218 (define-public bless
1224 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1228 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1229 (modules '((guix build utils)))
1232 ;; Remove bundled boost, pigz, zlib, and .git directory
1233 ;; FIXME: also remove bundled sources for murmurhash3 and
1234 ;; kmc once packaged.
1235 (delete-file-recursively "boost")
1236 (delete-file-recursively "pigz")
1237 (delete-file-recursively "google-sparsehash")
1238 (delete-file-recursively "zlib")
1239 (delete-file-recursively ".git")
1241 (build-system gnu-build-system)
1243 '(#:tests? #f ;no "check" target
1245 (list (string-append "ZLIB="
1246 (assoc-ref %build-inputs "zlib:static")
1248 (string-append "LDFLAGS="
1249 (string-join '("-lboost_filesystem"
1256 (modify-phases %standard-phases
1257 (add-after 'unpack 'do-not-build-bundled-pigz
1258 (lambda* (#:key inputs outputs #:allow-other-keys)
1259 (substitute* "Makefile"
1260 (("cd pigz/pigz-2.3.3; make") ""))
1262 (add-after 'unpack 'patch-paths-to-executables
1263 (lambda* (#:key inputs outputs #:allow-other-keys)
1264 (substitute* "parse_args.cpp"
1265 (("kmc_binary = .*")
1266 (string-append "kmc_binary = \""
1267 (assoc-ref outputs "out")
1269 (("pigz_binary = .*")
1270 (string-append "pigz_binary = \""
1271 (assoc-ref inputs "pigz")
1275 (lambda* (#:key outputs #:allow-other-keys)
1276 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1277 (for-each (lambda (file)
1278 (install-file file bin))
1279 '("bless" "kmc/bin/kmc"))
1281 (delete 'configure))))
1285 `(("openmpi" ,openmpi)
1287 ("sparsehash" ,sparsehash)
1289 ("zlib:static" ,zlib "static")
1291 (supported-systems '("x86_64-linux"))
1292 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1293 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1295 "@dfn{Bloom-filter-based error correction solution for high-throughput
1296 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1297 correction tool for genomic reads produced by @dfn{Next-generation
1298 sequencing} (NGS). BLESS produces accurate correction results with much less
1299 memory compared with previous solutions and is also able to tolerate a higher
1300 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1301 errors at the end of reads.")
1302 (license license:gpl3+)))
1304 (define-public bowtie
1311 (url "https://github.com/BenLangmead/bowtie2.git")
1312 (commit (string-append "v" version))))
1313 (file-name (git-file-name name version))
1316 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1317 (modules '((guix build utils)))
1320 (substitute* "Makefile"
1321 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1322 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1323 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1325 (build-system gnu-build-system)
1330 (string-append "prefix=" (assoc-ref %outputs "out")))
1332 (modify-phases %standard-phases
1337 "scripts/test/simple_tests.pl"
1338 "--bowtie2=./bowtie2"
1339 "--bowtie2-build=./bowtie2-build")
1344 ("python" ,python-wrapper)))
1347 ("perl-clone" ,perl-clone)
1348 ("perl-test-deep" ,perl-test-deep)
1349 ("perl-test-simple" ,perl-test-simple)))
1350 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1351 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1353 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1354 reads to long reference sequences. It is particularly good at aligning reads
1355 of about 50 up to 100s or 1,000s of characters, and particularly good at
1356 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1357 genome with an FM Index to keep its memory footprint small: for the human
1358 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1359 gapped, local, and paired-end alignment modes.")
1360 (supported-systems '("x86_64-linux"))
1361 (license license:gpl3+)))
1363 (define-public tophat
1370 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1374 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1375 (modules '((guix build utils)))
1378 ;; Remove bundled SeqAn and samtools
1379 (delete-file-recursively "src/SeqAn-1.4.2")
1380 (delete-file-recursively "src/samtools-0.1.18")
1382 (build-system gnu-build-system)
1384 '(#:parallel-build? #f ; not supported
1386 (modify-phases %standard-phases
1387 (add-after 'unpack 'use-system-samtools
1388 (lambda* (#:key inputs #:allow-other-keys)
1389 (substitute* "src/Makefile.in"
1390 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1391 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1392 (("SAMPROG = samtools_0\\.1\\.18") "")
1393 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1394 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1395 (substitute* '("src/common.cpp"
1397 (("samtools_0.1.18") (which "samtools")))
1398 (substitute* '("src/common.h"
1399 "src/bam2fastx.cpp")
1400 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1401 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1402 (substitute* '("src/bwt_map.h"
1404 "src/align_status.h")
1405 (("#include <bam.h>") "#include <samtools/bam.h>")
1406 (("#include <sam.h>") "#include <samtools/sam.h>"))
1411 ("samtools" ,samtools-0.1)
1412 ("ncurses" ,ncurses)
1413 ("python" ,python-2)
1416 ("seqan" ,seqan-1)))
1417 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1418 (synopsis "Spliced read mapper for RNA-Seq data")
1420 "TopHat is a fast splice junction mapper for nucleotide sequence
1421 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1422 mammalian-sized genomes using the ultra high-throughput short read
1423 aligner Bowtie, and then analyzes the mapping results to identify
1424 splice junctions between exons.")
1425 ;; TopHat is released under the Boost Software License, Version 1.0
1426 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1427 (license license:boost1.0)))
1436 "https://github.com/lh3/bwa/releases/download/v"
1437 version "/bwa-" version ".tar.bz2"))
1440 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1441 (build-system gnu-build-system)
1443 '(#:tests? #f ;no "check" target
1445 (modify-phases %standard-phases
1447 (lambda* (#:key outputs #:allow-other-keys)
1448 (let ((bin (string-append
1449 (assoc-ref outputs "out") "/bin"))
1451 (assoc-ref outputs "out") "/share/doc/bwa"))
1453 (assoc-ref outputs "out") "/share/man/man1")))
1454 (install-file "bwa" bin)
1455 (install-file "README.md" doc)
1456 (install-file "bwa.1" man))
1458 ;; no "configure" script
1459 (delete 'configure))))
1460 (inputs `(("zlib" ,zlib)))
1461 ;; Non-portable SSE instructions are used so building fails on platforms
1462 ;; other than x86_64.
1463 (supported-systems '("x86_64-linux"))
1464 (home-page "http://bio-bwa.sourceforge.net/")
1465 (synopsis "Burrows-Wheeler sequence aligner")
1467 "BWA is a software package for mapping low-divergent sequences against a
1468 large reference genome, such as the human genome. It consists of three
1469 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1470 designed for Illumina sequence reads up to 100bp, while the rest two for
1471 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1472 features such as long-read support and split alignment, but BWA-MEM, which is
1473 the latest, is generally recommended for high-quality queries as it is faster
1474 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1475 70-100bp Illumina reads.")
1476 (license license:gpl3+)))
1478 (define-public bwa-pssm
1479 (package (inherit bwa)
1485 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1487 (file-name (git-file-name name version))
1490 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1491 (build-system gnu-build-system)
1496 (home-page "http://bwa-pssm.binf.ku.dk/")
1497 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1499 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1500 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1501 existing aligners it is fast and sensitive. Unlike most other aligners,
1502 however, it is also adaptible in the sense that one can direct the alignment
1503 based on known biases within the data set. It is coded as a modification of
1504 the original BWA alignment program and shares the genome index structure as
1505 well as many of the command line options.")
1506 (license license:gpl3+)))
1508 (define-public python-bx-python
1510 (name "python-bx-python")
1514 (uri (pypi-uri "bx-python" version))
1517 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1518 (build-system python-build-system)
1519 ;; Tests fail because test data are not included
1520 (arguments '(#:tests? #f))
1522 `(("python-numpy" ,python-numpy)
1523 ("python-six" ,python-six)))
1527 `(("python-lzo" ,python-lzo)
1528 ("python-nose" ,python-nose)
1529 ("python-cython" ,python-cython)))
1530 (home-page "https://github.com/bxlab/bx-python")
1531 (synopsis "Tools for manipulating biological data")
1533 "bx-python provides tools for manipulating biological data, particularly
1534 multiple sequence alignments.")
1535 (license license:expat)))
1537 (define-public python2-bx-python
1538 (package-with-python2 python-bx-python))
1540 (define-public python-pysam
1542 (name "python-pysam")
1546 ;; Test data is missing on PyPi.
1548 (url "https://github.com/pysam-developers/pysam.git")
1549 (commit (string-append "v" version))))
1550 (file-name (git-file-name name version))
1553 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1554 (modules '((guix build utils)))
1556 ;; Drop bundled htslib. TODO: Also remove samtools
1558 (delete-file-recursively "htslib")
1560 (build-system python-build-system)
1562 `(#:modules ((ice-9 ftw)
1564 (guix build python-build-system)
1567 (modify-phases %standard-phases
1568 (add-before 'build 'set-flags
1569 (lambda* (#:key inputs #:allow-other-keys)
1570 (setenv "HTSLIB_MODE" "external")
1571 (setenv "HTSLIB_LIBRARY_DIR"
1572 (string-append (assoc-ref inputs "htslib") "/lib"))
1573 (setenv "HTSLIB_INCLUDE_DIR"
1574 (string-append (assoc-ref inputs "htslib") "/include"))
1575 (setenv "LDFLAGS" "-lncurses")
1576 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1579 (lambda* (#:key inputs outputs #:allow-other-keys)
1580 ;; This file contains tests that require a connection to the
1582 (delete-file "tests/tabix_test.py")
1583 ;; FIXME: This test fails
1584 (delete-file "tests/AlignmentFile_test.py")
1585 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1586 (setenv "PYTHONPATH"
1588 (getenv "PYTHONPATH")
1589 ":" (getcwd) "/build/"
1590 (car (scandir "build"
1591 (negate (cut string-prefix? "." <>))))))
1592 ;; Step out of source dir so python does not import from CWD.
1593 (with-directory-excursion "tests"
1594 (setenv "HOME" "/tmp")
1595 (invoke "make" "-C" "pysam_data")
1596 (invoke "make" "-C" "cbcf_data")
1597 ;; Running nosetests without explicitly asking for a single
1598 ;; process leads to a crash. Running with multiple processes
1599 ;; fails because the tests are not designed to run in parallel.
1601 ;; FIXME: tests keep timing out on some systems.
1602 (invoke "nosetests" "-v" "--processes" "1")))))))
1604 `(("htslib" ,htslib))) ; Included from installed header files.
1606 `(("ncurses" ,ncurses)
1610 `(("python-cython" ,python-cython)
1611 ;; Dependencies below are are for tests only.
1612 ("samtools" ,samtools)
1613 ("bcftools" ,bcftools)
1614 ("python-nose" ,python-nose)))
1615 (home-page "https://github.com/pysam-developers/pysam")
1616 (synopsis "Python bindings to the SAMtools C API")
1618 "Pysam is a Python module for reading and manipulating files in the
1619 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1620 also includes an interface for tabix.")
1621 (license license:expat)))
1623 (define-public python2-pysam
1624 (package-with-python2 python-pysam))
1626 (define-public python-twobitreader
1628 (name "python-twobitreader")
1633 (url "https://github.com/benjschiller/twobitreader")
1635 (file-name (git-file-name name version))
1638 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1639 (build-system python-build-system)
1640 ;; Tests are not included
1641 (arguments '(#:tests? #f))
1643 `(("python-sphinx" ,python-sphinx)))
1644 (home-page "https://github.com/benjschiller/twobitreader")
1645 (synopsis "Python library for reading .2bit files")
1647 "twobitreader is a Python library for reading .2bit files as used by the
1648 UCSC genome browser.")
1649 (license license:artistic2.0)))
1651 (define-public python2-twobitreader
1652 (package-with-python2 python-twobitreader))
1654 (define-public python-plastid
1656 (name "python-plastid")
1660 (uri (pypi-uri "plastid" version))
1663 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1664 (build-system python-build-system)
1666 ;; Some test files are not included.
1669 `(("python-numpy" ,python-numpy)
1670 ("python-scipy" ,python-scipy)
1671 ("python-pandas" ,python-pandas)
1672 ("python-pysam" ,python-pysam)
1673 ("python-matplotlib" ,python-matplotlib)
1674 ("python-biopython" ,python-biopython)
1675 ("python-twobitreader" ,python-twobitreader)
1676 ("python-termcolor" ,python-termcolor)))
1678 `(("python-cython" ,python-cython)
1679 ("python-nose" ,python-nose)))
1680 (home-page "https://github.com/joshuagryphon/plastid")
1681 (synopsis "Python library for genomic analysis")
1683 "plastid is a Python library for genomic analysis – in particular,
1684 high-throughput sequencing data – with an emphasis on simplicity.")
1685 (license license:bsd-3)))
1687 (define-public python2-plastid
1688 (package-with-python2 python-plastid))
1690 (define-public cd-hit
1696 (uri (string-append "https://github.com/weizhongli/cdhit"
1697 "/releases/download/V" version
1699 "-2017-0621-source.tar.gz"))
1702 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1703 (build-system gnu-build-system)
1705 `(#:tests? #f ; there are no tests
1707 ;; Executables are copied directly to the PREFIX.
1708 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1710 (modify-phases %standard-phases
1711 ;; No "configure" script
1713 ;; Remove sources of non-determinism
1714 (add-after 'unpack 'be-timeless
1716 (substitute* "cdhit-utility.c++"
1717 ((" \\(built on \" __DATE__ \"\\)") ""))
1718 (substitute* "cdhit-common.c++"
1719 (("__DATE__") "\"0\"")
1720 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1722 ;; The "install" target does not create the target directory.
1723 (add-before 'install 'create-target-dir
1724 (lambda* (#:key outputs #:allow-other-keys)
1725 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1729 (home-page "http://weizhongli-lab.org/cd-hit/")
1730 (synopsis "Cluster and compare protein or nucleotide sequences")
1732 "CD-HIT is a program for clustering and comparing protein or nucleotide
1733 sequences. CD-HIT is designed to be fast and handle extremely large
1735 ;; The manual says: "It can be copied under the GNU General Public License
1736 ;; version 2 (GPLv2)."
1737 (license license:gpl2)))
1739 (define-public clipper
1746 (url "https://github.com/YeoLab/clipper.git")
1748 (file-name (git-file-name name version))
1751 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1752 (modules '((guix build utils)))
1755 ;; remove unnecessary setup dependency
1756 (substitute* "setup.py"
1757 (("setup_requires = .*") ""))
1759 (build-system python-build-system)
1761 `(#:python ,python-2 ; only Python 2 is supported
1763 (modify-phases %standard-phases
1764 ;; This is fixed in upstream commit
1765 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1766 (add-after 'unpack 'fix-typo
1768 (substitute* "clipper/src/readsToWiggle.pyx"
1772 `(("htseq" ,python2-htseq)
1773 ("python-pybedtools" ,python2-pybedtools)
1774 ("python-cython" ,python2-cython)
1775 ("python-scikit-learn" ,python2-scikit-learn)
1776 ("python-matplotlib" ,python2-matplotlib)
1777 ("python-pandas" ,python2-pandas)
1778 ("python-pysam" ,python2-pysam)
1779 ("python-numpy" ,python2-numpy)
1780 ("python-scipy" ,python2-scipy)))
1782 `(("python-mock" ,python2-mock) ; for tests
1783 ("python-nose" ,python2-nose) ; for tests
1784 ("python-pytz" ,python2-pytz))) ; for tests
1785 (home-page "https://github.com/YeoLab/clipper")
1786 (synopsis "CLIP peak enrichment recognition")
1788 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1789 (license license:gpl2)))
1791 (define-public codingquarry
1793 (name "codingquarry")
1798 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1802 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1803 (build-system gnu-build-system)
1805 '(#:tests? #f ; no "check" target
1807 (modify-phases %standard-phases
1810 (lambda* (#:key outputs #:allow-other-keys)
1811 (let* ((out (assoc-ref outputs "out"))
1812 (bin (string-append out "/bin"))
1813 (doc (string-append out "/share/doc/codingquarry")))
1814 (install-file "INSTRUCTIONS.pdf" doc)
1815 (copy-recursively "QuarryFiles"
1816 (string-append out "/QuarryFiles"))
1817 (install-file "CodingQuarry" bin)
1818 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1820 (inputs `(("openmpi" ,openmpi)))
1821 (native-search-paths
1822 (list (search-path-specification
1823 (variable "QUARRY_PATH")
1824 (files '("QuarryFiles")))))
1825 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1826 (synopsis "Fungal gene predictor")
1827 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1828 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1829 (home-page "https://sourceforge.net/projects/codingquarry/")
1830 (license license:gpl3+)))
1832 (define-public couger
1839 "http://couger.oit.duke.edu/static/assets/COUGER"
1843 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1844 (build-system gnu-build-system)
1848 (modify-phases %standard-phases
1853 (lambda* (#:key outputs #:allow-other-keys)
1854 (let* ((out (assoc-ref outputs "out"))
1855 (bin (string-append out "/bin")))
1856 (copy-recursively "src" (string-append out "/src"))
1858 ;; Add "src" directory to module lookup path.
1859 (substitute* "couger"
1861 (string-append "import sys\nsys.path.append(\""
1862 out "\")\nfrom argparse")))
1863 (install-file "couger" bin))
1866 'install 'wrap-program
1867 (lambda* (#:key inputs outputs #:allow-other-keys)
1868 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1869 (let* ((out (assoc-ref outputs "out"))
1870 (path (getenv "PYTHONPATH")))
1871 (wrap-program (string-append out "/bin/couger")
1872 `("PYTHONPATH" ":" prefix (,path))))
1875 `(("python" ,python-2)
1876 ("python2-pillow" ,python2-pillow)
1877 ("python2-numpy" ,python2-numpy)
1878 ("python2-scipy" ,python2-scipy)
1879 ("python2-matplotlib" ,python2-matplotlib)))
1881 `(("r-minimal" ,r-minimal)
1883 ("randomjungle" ,randomjungle)))
1885 `(("unzip" ,unzip)))
1886 (home-page "http://couger.oit.duke.edu")
1887 (synopsis "Identify co-factors in sets of genomic regions")
1889 "COUGER can be applied to any two sets of genomic regions bound by
1890 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1891 putative co-factors that provide specificity to each TF. The framework
1892 determines the genomic targets uniquely-bound by each TF, and identifies a
1893 small set of co-factors that best explain the in vivo binding differences
1894 between the two TFs.
1896 COUGER uses classification algorithms (support vector machines and random
1897 forests) with features that reflect the DNA binding specificities of putative
1898 co-factors. The features are generated either from high-throughput TF-DNA
1899 binding data (from protein binding microarray experiments), or from large
1900 collections of DNA motifs.")
1901 (license license:gpl3+)))
1903 (define-public clustal-omega
1905 (name "clustal-omega")
1909 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1913 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1914 (build-system gnu-build-system)
1916 `(("argtable" ,argtable)))
1917 (home-page "http://www.clustal.org/omega/")
1918 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1920 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1921 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1922 of handling data-sets of hundreds of thousands of sequences in reasonable
1924 (license license:gpl2+)))
1926 (define-public crossmap
1932 (uri (pypi-uri "CrossMap" version))
1935 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1936 (build-system python-build-system)
1937 (arguments `(#:python ,python-2))
1939 `(("python-bx-python" ,python2-bx-python)
1940 ("python-numpy" ,python2-numpy)
1941 ("python-pysam" ,python2-pysam)
1944 `(("python-cython" ,python2-cython)
1945 ("python-nose" ,python2-nose)))
1946 (home-page "http://crossmap.sourceforge.net/")
1947 (synopsis "Convert genome coordinates between assemblies")
1949 "CrossMap is a program for conversion of genome coordinates or annotation
1950 files between different genome assemblies. It supports most commonly used
1951 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1952 (license license:gpl2+)))
1954 (define-public python-dnaio
1956 (name "python-dnaio")
1961 (uri (pypi-uri "dnaio" version))
1964 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1965 (build-system python-build-system)
1967 `(("python-cython" ,python-cython)
1968 ("python-pytest" ,python-pytest)
1969 ("python-xopen" ,python-xopen)))
1970 (home-page "https://github.com/marcelm/dnaio/")
1971 (synopsis "Read FASTA and FASTQ files efficiently")
1973 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1974 files. The code was previously part of the cutadapt tool.")
1975 (license license:expat)))
1977 (define-public cutadapt
1984 (url "https://github.com/marcelm/cutadapt.git")
1985 (commit (string-append "v" version))))
1986 (file-name (git-file-name name version))
1989 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1990 (build-system python-build-system)
1992 `(("python-dnaio" ,python-dnaio)
1993 ("python-xopen" ,python-xopen)))
1995 `(("python-cython" ,python-cython)
1996 ("python-pytest" ,python-pytest)))
1997 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1998 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2000 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2001 other types of unwanted sequence from high-throughput sequencing reads.")
2002 (license license:expat)))
2004 (define-public libbigwig
2011 (url "https://github.com/dpryan79/libBigWig.git")
2013 (file-name (string-append name "-" version "-checkout"))
2016 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2017 (build-system gnu-build-system)
2019 `(#:test-target "test"
2020 #:tests? #f ; tests require access to the web
2023 (string-append "prefix=" (assoc-ref %outputs "out")))
2025 (modify-phases %standard-phases
2026 (delete 'configure))))
2031 `(("doxygen" ,doxygen)
2033 ("python" ,python-2)))
2034 (home-page "https://github.com/dpryan79/libBigWig")
2035 (synopsis "C library for handling bigWig files")
2037 "This package provides a C library for parsing local and remote BigWig
2039 (license license:expat)))
2041 (define-public python-pybigwig
2043 (name "python-pybigwig")
2047 (uri (pypi-uri "pyBigWig" version))
2050 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2051 (modules '((guix build utils)))
2054 ;; Delete bundled libBigWig sources
2055 (delete-file-recursively "libBigWig")
2057 (build-system python-build-system)
2060 (modify-phases %standard-phases
2061 (add-after 'unpack 'link-with-libBigWig
2062 (lambda* (#:key inputs #:allow-other-keys)
2063 (substitute* "setup.py"
2064 (("libs=\\[") "libs=[\"BigWig\", "))
2067 `(("python-numpy" ,python-numpy)))
2069 `(("libbigwig" ,libbigwig)
2072 (home-page "https://github.com/dpryan79/pyBigWig")
2073 (synopsis "Access bigWig files in Python using libBigWig")
2075 "This package provides Python bindings to the libBigWig library for
2076 accessing bigWig files.")
2077 (license license:expat)))
2079 (define-public python2-pybigwig
2080 (package-with-python2 python-pybigwig))
2082 (define-public python-dendropy
2084 (name "python-dendropy")
2089 ;; Source from GitHub so that tests are included.
2091 (url "https://github.com/jeetsukumaran/DendroPy.git")
2092 (commit (string-append "v" version))))
2093 (file-name (git-file-name name version))
2096 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2097 (build-system python-build-system)
2098 (home-page "http://packages.python.org/DendroPy/")
2099 (synopsis "Library for phylogenetics and phylogenetic computing")
2101 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2102 writing, simulation, processing and manipulation of phylogenetic
2103 trees (phylogenies) and characters.")
2104 (license license:bsd-3)))
2106 (define-public python2-dendropy
2107 (let ((base (package-with-python2 python-dendropy)))
2112 (modify-phases %standard-phases
2113 (add-after 'unpack 'remove-failing-test
2115 ;; This test fails when the full test suite is run, as documented
2116 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2117 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2118 (("test_collection_comments_and_annotations")
2119 "do_not_test_collection_comments_and_annotations"))
2121 ,@(package-arguments base))))))
2123 (define-public python-py2bit
2125 (name "python-py2bit")
2130 (uri (pypi-uri "py2bit" version))
2133 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2134 (build-system python-build-system)
2135 (home-page "https://github.com/dpryan79/py2bit")
2136 (synopsis "Access 2bit files using lib2bit")
2138 "This package provides Python bindings for lib2bit to access 2bit files
2140 (license license:expat)))
2142 (define-public deeptools
2149 (url "https://github.com/deeptools/deepTools.git")
2151 (file-name (git-file-name name version))
2154 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2155 (build-system python-build-system)
2158 (modify-phases %standard-phases
2159 ;; This phase fails, but it's not needed.
2160 (delete 'reset-gzip-timestamps))))
2162 `(("python-plotly" ,python-plotly)
2163 ("python-scipy" ,python-scipy)
2164 ("python-numpy" ,python-numpy)
2165 ("python-numpydoc" ,python-numpydoc)
2166 ("python-matplotlib" ,python-matplotlib)
2167 ("python-pysam" ,python-pysam)
2168 ("python-py2bit" ,python-py2bit)
2169 ("python-pybigwig" ,python-pybigwig)))
2171 `(("python-mock" ,python-mock) ;for tests
2172 ("python-nose" ,python-nose) ;for tests
2173 ("python-pytz" ,python-pytz))) ;for tests
2174 (home-page "https://github.com/deeptools/deepTools")
2175 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2177 "DeepTools addresses the challenge of handling the large amounts of data
2178 that are now routinely generated from DNA sequencing centers. To do so,
2179 deepTools contains useful modules to process the mapped reads data to create
2180 coverage files in standard bedGraph and bigWig file formats. By doing so,
2181 deepTools allows the creation of normalized coverage files or the comparison
2182 between two files (for example, treatment and control). Finally, using such
2183 normalized and standardized files, multiple visualizations can be created to
2184 identify enrichments with functional annotations of the genome.")
2185 (license license:gpl3+)))
2187 (define-public delly
2194 (url "https://github.com/dellytools/delly.git")
2195 (commit (string-append "v" version))))
2196 (file-name (git-file-name name version))
2198 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2199 (modules '((guix build utils)))
2202 (delete-file-recursively "src/htslib")
2204 (build-system gnu-build-system)
2206 `(#:tests? #f ; There are no tests to run.
2208 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2209 (string-append "prefix=" (assoc-ref %outputs "out")))
2211 (modify-phases %standard-phases
2212 (delete 'configure) ; There is no configure phase.
2213 (add-after 'install 'install-templates
2214 (lambda* (#:key outputs #:allow-other-keys)
2215 (let ((templates (string-append (assoc-ref outputs "out")
2216 "/share/delly/templates")))
2218 (copy-recursively "excludeTemplates" templates)
2225 (home-page "https://github.com/dellytools/delly")
2226 (synopsis "Integrated structural variant prediction method")
2227 (description "Delly is an integrated structural variant prediction method
2228 that can discover and genotype deletions, tandem duplications, inversions and
2229 translocations at single-nucleotide resolution in short-read massively parallel
2230 sequencing data. It uses paired-ends and split-reads to sensitively and
2231 accurately delineate genomic rearrangements throughout the genome.")
2232 (license license:gpl3+)))
2234 (define-public diamond
2241 (url "https://github.com/bbuchfink/diamond.git")
2242 (commit (string-append "v" version))))
2243 (file-name (git-file-name name version))
2246 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2247 (build-system cmake-build-system)
2249 '(#:tests? #f ; no "check" target
2251 (modify-phases %standard-phases
2252 (add-after 'unpack 'remove-native-compilation
2254 (substitute* "CMakeLists.txt" (("-march=native") ""))
2258 (home-page "https://github.com/bbuchfink/diamond")
2259 (synopsis "Accelerated BLAST compatible local sequence aligner")
2261 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2262 translated DNA query sequences against a protein reference database (BLASTP
2263 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2264 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2265 data and settings.")
2266 (license license:agpl3+)))
2268 (define-public discrover
2276 (url "https://github.com/maaskola/discrover.git")
2278 (file-name (git-file-name name version))
2281 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2282 (build-system cmake-build-system)
2284 `(#:tests? #f ; there are no tests
2286 (modify-phases %standard-phases
2287 (add-after 'unpack 'add-missing-includes
2289 (substitute* "src/executioninformation.hpp"
2290 (("#define EXECUTIONINFORMATION_HPP" line)
2291 (string-append line "\n#include <random>")))
2292 (substitute* "src/plasma/fasta.hpp"
2293 (("#define FASTA_HPP" line)
2294 (string-append line "\n#include <random>")))
2300 `(("texlive" ,texlive)
2301 ;; TODO: Replace texlive with minimal texlive-union.
2302 ;; ("texlive" ,(texlive-union (list texlive-latex-doi
2303 ;; texlive-latex-hyperref
2304 ;; texlive-latex-oberdiek
2305 ;; texlive-generic-ifxetex
2306 ;; texlive-latex-url
2307 ;; texlive-latex-pgf
2308 ;; texlive-latex-examplep
2309 ;; texlive-latex-natbib
2310 ;; texlive-latex-verbatimbox
2312 ;; texlive-latex-xcolor
2313 ;; texlive-fonts-amsfonts
2314 ;; texlive-latex-amsfonts
2317 ("imagemagick" ,imagemagick)))
2318 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2319 (synopsis "Discover discriminative nucleotide sequence motifs")
2320 (description "Discrover is a motif discovery method to find binding sites
2321 of nucleic acid binding proteins.")
2322 (license license:gpl3+)))
2324 (define-public eigensoft
2332 (url "https://github.com/DReichLab/EIG.git")
2333 (commit (string-append "v" version))))
2334 (file-name (git-file-name name version))
2337 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2338 (modules '((guix build utils)))
2339 ;; Remove pre-built binaries.
2341 (delete-file-recursively "bin")
2344 (build-system gnu-build-system)
2346 `(#:tests? #f ; There are no tests.
2347 #:make-flags '("CC=gcc")
2349 (modify-phases %standard-phases
2350 ;; There is no configure phase, but the Makefile is in a
2353 (lambda _ (chdir "src") #t))
2354 ;; The provided install target only copies executables to
2355 ;; the "bin" directory in the build root.
2356 (add-after 'install 'actually-install
2357 (lambda* (#:key outputs #:allow-other-keys)
2358 (let* ((out (assoc-ref outputs "out"))
2359 (bin (string-append out "/bin")))
2360 (for-each (lambda (file)
2361 (install-file file bin))
2362 (find-files "../bin" ".*"))
2367 ("openblas" ,openblas)
2369 ("gfortran" ,gfortran "lib")))
2370 (home-page "https://github.com/DReichLab/EIG")
2371 (synopsis "Tools for population genetics")
2372 (description "The EIGENSOFT package provides tools for population
2373 genetics and stratification correction. EIGENSOFT implements methods commonly
2374 used in population genetics analyses such as PCA, computation of Tracy-Widom
2375 statistics, and finding related individuals in structured populations. It
2376 comes with a built-in plotting script and supports multiple file formats and
2377 quantitative phenotypes.")
2378 ;; The license of the eigensoft tools is Expat, but since it's
2379 ;; linking with the GNU Scientific Library (GSL) the effective
2380 ;; license is the GPL.
2381 (license license:gpl3+)))
2383 (define-public edirect
2386 (version "10.2.20181018")
2389 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2390 "/versions/" version
2391 "/edirect-" version ".tar.gz"))
2394 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2395 (build-system perl-build-system)
2398 (modify-phases %standard-phases
2401 (delete 'check) ; simple check after install
2403 (lambda* (#:key outputs #:allow-other-keys)
2404 (install-file "edirect.pl"
2405 (string-append (assoc-ref outputs "out") "/bin"))
2407 (add-after 'install 'wrap-program
2408 (lambda* (#:key outputs #:allow-other-keys)
2409 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2410 (let* ((out (assoc-ref outputs "out"))
2411 (path (getenv "PERL5LIB")))
2412 (wrap-program (string-append out "/bin/edirect.pl")
2413 `("PERL5LIB" ":" prefix (,path))))
2415 (add-after 'wrap-program 'check
2416 (lambda* (#:key outputs #:allow-other-keys)
2417 (invoke (string-append (assoc-ref outputs "out")
2422 `(("perl-html-parser" ,perl-html-parser)
2423 ("perl-encode-locale" ,perl-encode-locale)
2424 ("perl-file-listing" ,perl-file-listing)
2425 ("perl-html-tagset" ,perl-html-tagset)
2426 ("perl-html-tree" ,perl-html-tree)
2427 ("perl-http-cookies" ,perl-http-cookies)
2428 ("perl-http-date" ,perl-http-date)
2429 ("perl-http-message" ,perl-http-message)
2430 ("perl-http-negotiate" ,perl-http-negotiate)
2431 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2432 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2433 ("perl-net-http" ,perl-net-http)
2434 ("perl-uri" ,perl-uri)
2435 ("perl-www-robotrules" ,perl-www-robotrules)
2436 ("perl-xml-simple" ,perl-xml-simple)
2438 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2439 (synopsis "Tools for accessing the NCBI's set of databases")
2441 "Entrez Direct (EDirect) is a method for accessing the National Center
2442 for Biotechnology Information's (NCBI) set of interconnected
2443 databases (publication, sequence, structure, gene, variation, expression,
2444 etc.) from a terminal. Functions take search terms from command-line
2445 arguments. Individual operations are combined to build multi-step queries.
2446 Record retrieval and formatting normally complete the process.
2448 EDirect also provides an argument-driven function that simplifies the
2449 extraction of data from document summaries or other results that are returned
2450 in structured XML format. This can eliminate the need for writing custom
2451 software to answer ad hoc questions.")
2452 (license license:public-domain)))
2454 (define-public exonerate
2463 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2464 "exonerate-" version ".tar.gz"))
2467 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2468 (build-system gnu-build-system)
2470 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2472 `(("pkg-config" ,pkg-config)))
2476 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2477 (synopsis "Generic tool for biological sequence alignment")
2479 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2480 the alignment of sequences using a many alignment models, either exhaustive
2481 dynamic programming or a variety of heuristics.")
2482 (license license:gpl3)))
2484 (define-public express
2492 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2493 version "/express-" version "-src.tgz"))
2496 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2497 (build-system cmake-build-system)
2499 `(#:tests? #f ;no "check" target
2501 (modify-phases %standard-phases
2502 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2503 (lambda* (#:key inputs #:allow-other-keys)
2504 (substitute* "CMakeLists.txt"
2505 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2506 "set(Boost_USE_STATIC_LIBS OFF)")
2507 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2508 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2509 (substitute* "src/CMakeLists.txt"
2510 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2511 (string-append (assoc-ref inputs "bamtools") "/lib"))
2512 (("libprotobuf.a") "libprotobuf.so"))
2516 ("bamtools" ,bamtools)
2517 ("protobuf" ,protobuf)
2519 (home-page "http://bio.math.berkeley.edu/eXpress")
2520 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2522 "eXpress is a streaming tool for quantifying the abundances of a set of
2523 target sequences from sampled subsequences. Example applications include
2524 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2525 analysis (from RNA-Seq), transcription factor binding quantification in
2526 ChIP-Seq, and analysis of metagenomic data.")
2527 (license license:artistic2.0)))
2529 (define-public express-beta-diversity
2531 (name "express-beta-diversity")
2536 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2537 (commit (string-append "v" version))))
2538 (file-name (git-file-name name version))
2541 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2542 (build-system gnu-build-system)
2545 (modify-phases %standard-phases
2547 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2549 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2551 (lambda* (#:key outputs #:allow-other-keys)
2552 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2553 (install-file "../scripts/convertToEBD.py" bin)
2554 (install-file "../bin/ExpressBetaDiversity" bin)
2557 `(("python" ,python-2)))
2558 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2559 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2561 "Express Beta Diversity (EBD) calculates ecological beta diversity
2562 (dissimilarity) measures between biological communities. EBD implements a
2563 variety of diversity measures including those that make use of phylogenetic
2564 similarity of community members.")
2565 (license license:gpl3+)))
2567 (define-public fasttree
2574 "http://www.microbesonline.org/fasttree/FastTree-"
2578 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2579 (build-system gnu-build-system)
2581 `(#:tests? #f ; no "check" target
2583 (modify-phases %standard-phases
2587 (lambda* (#:key source #:allow-other-keys)
2590 "-finline-functions"
2601 "-finline-functions"
2610 (lambda* (#:key outputs #:allow-other-keys)
2611 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2612 (install-file "FastTree" bin)
2613 (install-file "FastTreeMP" bin)
2615 (home-page "http://www.microbesonline.org/fasttree")
2616 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2618 "FastTree can handle alignments with up to a million of sequences in a
2619 reasonable amount of time and memory. For large alignments, FastTree is
2620 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2621 (license license:gpl2+)))
2623 (define-public fastx-toolkit
2625 (name "fastx-toolkit")
2631 "https://github.com/agordon/fastx_toolkit/releases/download/"
2632 version "/fastx_toolkit-" version ".tar.bz2"))
2635 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2636 (build-system gnu-build-system)
2638 `(("libgtextutils" ,libgtextutils)))
2640 `(("pkg-config" ,pkg-config)))
2641 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2642 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2644 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2645 FASTA/FASTQ files preprocessing.
2647 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2648 containing multiple short-reads sequences. The main processing of such
2649 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2650 is sometimes more productive to preprocess the files before mapping the
2651 sequences to the genome---manipulating the sequences to produce better mapping
2652 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2653 (license license:agpl3+)))
2655 (define-public flexbar
2662 (url "https://github.com/seqan/flexbar.git")
2663 (commit (string-append "v" version))))
2664 (file-name (git-file-name name version))
2667 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2668 (build-system cmake-build-system)
2671 (modify-phases %standard-phases
2673 (lambda* (#:key outputs #:allow-other-keys)
2674 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2675 (with-directory-excursion "../source/test"
2676 (invoke "bash" "flexbar_test.sh"))
2679 (lambda* (#:key outputs #:allow-other-keys)
2680 (let* ((out (string-append (assoc-ref outputs "out")))
2681 (bin (string-append out "/bin/")))
2682 (install-file "flexbar" bin))
2688 `(("pkg-config" ,pkg-config)
2690 (home-page "https://github.com/seqan/flexbar")
2691 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2693 "Flexbar preprocesses high-throughput nucleotide sequencing data
2694 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2695 Moreover, trimming and filtering features are provided. Flexbar increases
2696 read mapping rates and improves genome and transcriptome assemblies. It
2697 supports next-generation sequencing data in fasta/q and csfasta/q format from
2698 Illumina, Roche 454, and the SOLiD platform.")
2699 (license license:bsd-3)))
2701 (define-public fraggenescan
2703 (name "fraggenescan")
2709 (string-append "mirror://sourceforge/fraggenescan/"
2710 "FragGeneScan" version ".tar.gz"))
2712 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2713 (build-system gnu-build-system)
2716 (modify-phases %standard-phases
2718 (add-before 'build 'patch-paths
2719 (lambda* (#:key outputs #:allow-other-keys)
2720 (let* ((out (string-append (assoc-ref outputs "out")))
2721 (share (string-append out "/share/fraggenescan/")))
2722 (substitute* "run_FragGeneScan.pl"
2724 (string-append "system(\"" (which "rm")))
2726 (string-append "system(\"" (which "mv")))
2727 (("\\\"awk") (string-append "\"" (which "awk")))
2728 ;; This script and other programs expect the training files
2729 ;; to be in the non-standard location bin/train/XXX. Change
2730 ;; this to be share/fraggenescan/train/XXX instead.
2731 (("^\\$train.file = \\$dir.*")
2732 (string-append "$train_file = \""
2734 "train/\".$FGS_train_file;")))
2735 (substitute* "run_hmm.c"
2736 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2737 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2741 (invoke "make" "clean")
2742 (invoke "make" "fgs")
2745 (lambda* (#:key outputs #:allow-other-keys)
2746 (let* ((out (string-append (assoc-ref outputs "out")))
2747 (bin (string-append out "/bin/"))
2748 (share (string-append out "/share/fraggenescan/train")))
2749 (install-file "run_FragGeneScan.pl" bin)
2750 (install-file "FragGeneScan" bin)
2751 (copy-recursively "train" share))
2754 (add-after 'install 'post-install-check
2755 ;; In lieu of 'make check', run one of the examples and check the
2756 ;; output files gets created.
2757 (lambda* (#:key outputs #:allow-other-keys)
2758 (let* ((out (string-append (assoc-ref outputs "out")))
2759 (bin (string-append out "/bin/"))
2760 (frag (string-append bin "run_FragGeneScan.pl")))
2761 ;; Test complete genome.
2763 "-genome=./example/NC_000913.fna"
2767 (unless (and (file-exists? "test2.faa")
2768 (file-exists? "test2.ffn")
2769 (file-exists? "test2.gff")
2770 (file-exists? "test2.out"))
2771 (error "Expected files do not exist."))
2772 ;; Test incomplete sequences.
2774 "-genome=./example/NC_000913-fgs.ffn"
2781 ("python" ,python-2))) ;not compatible with python 3.
2782 (home-page "https://sourceforge.net/projects/fraggenescan/")
2783 (synopsis "Finds potentially fragmented genes in short reads")
2785 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2786 short and error-prone DNA sequencing reads. It can also be applied to predict
2787 genes in incomplete assemblies or complete genomes.")
2788 ;; GPL3+ according to private correspondense with the authors.
2789 (license license:gpl3+)))
2791 (define-public fxtract
2792 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2800 (url "https://github.com/ctSkennerton/fxtract.git")
2802 (file-name (git-file-name name version))
2805 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2806 (build-system gnu-build-system)
2808 `(#:make-flags (list
2809 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2811 #:test-target "fxtract_test"
2813 (modify-phases %standard-phases
2815 (add-before 'build 'copy-util
2816 (lambda* (#:key inputs #:allow-other-keys)
2818 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2820 ;; Do not use make install as this requires additional dependencies.
2822 (lambda* (#:key outputs #:allow-other-keys)
2823 (let* ((out (assoc-ref outputs "out"))
2824 (bin (string-append out"/bin")))
2825 (install-file "fxtract" bin)
2831 ;; ctskennerton-util is licensed under GPL2.
2832 `(("ctskennerton-util"
2836 (url "https://github.com/ctSkennerton/util.git")
2837 (commit util-commit)))
2838 (file-name (string-append
2839 "ctstennerton-util-" util-commit "-checkout"))
2842 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2843 (home-page "https://github.com/ctSkennerton/fxtract")
2844 (synopsis "Extract sequences from FASTA and FASTQ files")
2846 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2847 or FASTQ) file given a subsequence. It uses a simple substring search for
2848 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2849 lookups or multi-pattern searching as required. By default fxtract looks in
2850 the sequence of each record but can also be told to look in the header,
2851 comment or quality sections.")
2852 ;; 'util' requires SSE instructions.
2853 (supported-systems '("x86_64-linux"))
2854 (license license:expat))))
2856 (define-public gemma
2863 (url "https://github.com/xiangzhou/GEMMA.git")
2864 (commit (string-append "v" version))))
2865 (file-name (git-file-name name version))
2868 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2871 ("gfortran" ,gfortran "lib")
2874 ("openblas" ,openblas)
2876 (build-system gnu-build-system)
2879 '(,@(match (%current-system)
2881 '("FORCE_DYNAMIC=1"))
2883 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2885 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2887 (modify-phases %standard-phases
2889 (add-after 'unpack 'find-eigen
2890 (lambda* (#:key inputs #:allow-other-keys)
2891 ;; Ensure that Eigen headers can be found
2892 (setenv "CPLUS_INCLUDE_PATH"
2893 (string-append (getenv "CPLUS_INCLUDE_PATH")
2895 (assoc-ref inputs "eigen")
2898 (add-before 'build 'bin-mkdir
2903 (lambda* (#:key outputs #:allow-other-keys)
2904 (let ((out (assoc-ref outputs "out")))
2905 (install-file "bin/gemma"
2909 #:tests? #f)) ; no tests included yet
2910 (home-page "https://github.com/xiangzhou/GEMMA")
2911 (synopsis "Tool for genome-wide efficient mixed model association")
2913 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2914 standard linear mixed model resolver with application in genome-wide
2915 association studies (GWAS).")
2916 (license license:gpl3)))
2925 (url "https://github.com/nboley/grit.git")
2927 (file-name (git-file-name name version))
2930 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
2931 (build-system python-build-system)
2933 `(#:python ,python-2
2935 (modify-phases %standard-phases
2936 (add-after 'unpack 'generate-from-cython-sources
2937 (lambda* (#:key inputs outputs #:allow-other-keys)
2938 ;; Delete these C files to force fresh generation from pyx sources.
2939 (delete-file "grit/sparsify_support_fns.c")
2940 (delete-file "grit/call_peaks_support_fns.c")
2941 (substitute* "setup.py"
2942 (("Cython.Setup") "Cython.Build"))
2945 `(("python-scipy" ,python2-scipy)
2946 ("python-numpy" ,python2-numpy)
2947 ("python-pysam" ,python2-pysam)
2948 ("python-networkx" ,python2-networkx)))
2950 `(("python-cython" ,python2-cython)))
2951 (home-page "http://grit-bio.org")
2952 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2954 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2955 full length transcript models. When none of these data sources are available,
2956 GRIT can be run by providing a candidate set of TES or TSS sites. In
2957 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2958 also be run in quantification mode, where it uses a provided GTF file and just
2959 estimates transcript expression.")
2960 (license license:gpl3+)))
2962 (define-public hisat
2969 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2970 version "-beta-source.zip"))
2973 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2974 (build-system gnu-build-system)
2976 `(#:tests? #f ;no check target
2977 #:make-flags '("allall"
2978 ;; Disable unsupported `popcnt' instructions on
2979 ;; architectures other than x86_64
2980 ,@(if (string-prefix? "x86_64"
2981 (or (%current-target-system)
2984 '("POPCNT_CAPABILITY=0")))
2986 (modify-phases %standard-phases
2987 (add-after 'unpack 'patch-sources
2989 ;; XXX Cannot use snippet because zip files are not supported
2990 (substitute* "Makefile"
2991 (("^CC = .*$") "CC = gcc")
2992 (("^CPP = .*$") "CPP = g++")
2993 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2994 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2995 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2996 (substitute* '("hisat-build" "hisat-inspect")
2997 (("/usr/bin/env") (which "env")))
3000 (lambda* (#:key outputs #:allow-other-keys)
3001 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3002 (for-each (lambda (file)
3003 (install-file file bin))
3006 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3008 (delete 'configure))))
3010 `(("unzip" ,unzip)))
3015 ;; Non-portable SSE instructions are used so building fails on platforms
3016 ;; other than x86_64.
3017 (supported-systems '("x86_64-linux"))
3018 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3019 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3021 "HISAT is a fast and sensitive spliced alignment program for mapping
3022 RNA-seq reads. In addition to one global FM index that represents a whole
3023 genome, HISAT uses a large set of small FM indexes that collectively cover the
3024 whole genome. These small indexes (called local indexes) combined with
3025 several alignment strategies enable effective alignment of RNA-seq reads, in
3026 particular, reads spanning multiple exons.")
3027 (license license:gpl3+)))
3029 (define-public hisat2
3036 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3037 "/downloads/hisat2-" version "-source.zip"))
3040 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3041 (build-system gnu-build-system)
3043 `(#:tests? #f ; no check target
3044 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3045 #:modules ((guix build gnu-build-system)
3049 (modify-phases %standard-phases
3050 (add-after 'unpack 'make-deterministic
3052 (substitute* "Makefile"
3057 (lambda* (#:key outputs #:allow-other-keys)
3058 (let* ((out (assoc-ref outputs "out"))
3059 (bin (string-append out "/bin/"))
3060 (doc (string-append out "/share/doc/hisat2/")))
3062 (cut install-file <> bin)
3064 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3066 (install-file "doc/manual.inc.html" doc))
3069 `(("unzip" ,unzip) ; needed for archive from ftp
3071 ("pandoc" ,ghc-pandoc))) ; for documentation
3072 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3073 (synopsis "Graph-based alignment of genomic sequencing reads")
3074 (description "HISAT2 is a fast and sensitive alignment program for mapping
3075 next-generation sequencing reads (both DNA and RNA) to a population of human
3076 genomes (as well as to a single reference genome). In addition to using one
3077 global @dfn{graph FM} (GFM) index that represents a population of human
3078 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3079 the whole genome. These small indexes, combined with several alignment
3080 strategies, enable rapid and accurate alignment of sequencing reads. This new
3081 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3082 ;; HISAT2 contains files from Bowtie2, which is released under
3083 ;; GPLv2 or later. The HISAT2 source files are released under
3085 (license license:gpl3+)))
3087 (define-public hmmer
3095 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3098 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3099 (build-system gnu-build-system)
3100 (native-inputs `(("perl" ,perl)))
3101 (home-page "http://hmmer.org/")
3102 (synopsis "Biosequence analysis using profile hidden Markov models")
3104 "HMMER is used for searching sequence databases for homologs of protein
3105 sequences, and for making protein sequence alignments. It implements methods
3106 using probabilistic models called profile hidden Markov models (profile
3108 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3110 (supported-systems '("x86_64-linux" "i686-linux"))
3111 (license license:bsd-3)))
3113 (define-public htseq
3119 (uri (pypi-uri "HTSeq" version))
3122 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3123 (build-system python-build-system)
3125 `(("python-cython" ,python-cython)))
3126 ;; Numpy needs to be propagated when htseq is used as a Python library.
3128 `(("python-numpy" ,python-numpy)))
3130 `(("python-pysam" ,python-pysam)
3131 ("python-matplotlib" ,python-matplotlib)))
3132 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3133 (synopsis "Analysing high-throughput sequencing data with Python")
3135 "HTSeq is a Python package that provides infrastructure to process data
3136 from high-throughput sequencing assays.")
3137 (license license:gpl3+)))
3139 (define-public python2-htseq
3140 (package-with-python2 htseq))
3142 (define-public java-htsjdk
3144 (name "java-htsjdk")
3145 (version "2.3.0") ; last version without build dependency on gradle
3149 (url "https://github.com/samtools/htsjdk.git")
3151 (file-name (git-file-name name version))
3154 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3155 (modules '((guix build utils)))
3157 ;; Delete pre-built binaries
3159 (delete-file-recursively "lib")
3162 (build-system ant-build-system)
3164 `(#:tests? #f ; test require Internet access
3167 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3168 "/share/java/htsjdk/"))
3169 #:build-target "all"
3171 (modify-phases %standard-phases
3172 ;; The build phase also installs the jars
3173 (delete 'install))))
3175 `(("java-ngs" ,java-ngs)
3176 ("java-snappy-1" ,java-snappy-1)
3177 ("java-commons-compress" ,java-commons-compress)
3178 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3179 ("java-commons-jexl-2" ,java-commons-jexl-2)
3180 ("java-xz" ,java-xz)))
3182 `(("java-testng" ,java-testng)))
3183 (home-page "http://samtools.github.io/htsjdk/")
3184 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3186 "HTSJDK is an implementation of a unified Java library for accessing
3187 common file formats, such as SAM and VCF, used for high-throughput
3188 sequencing (HTS) data. There are also an number of useful utilities for
3189 manipulating HTS data.")
3190 (license license:expat)))
3192 (define-public java-htsjdk-latest
3194 (name "java-htsjdk")
3199 (url "https://github.com/samtools/htsjdk.git")
3201 (file-name (string-append name "-" version "-checkout"))
3204 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3205 (build-system ant-build-system)
3207 `(#:tests? #f ; test require Scala
3209 #:jar-name "htsjdk.jar"
3211 (modify-phases %standard-phases
3212 (add-after 'unpack 'remove-useless-build.xml
3213 (lambda _ (delete-file "build.xml") #t))
3214 ;; The tests require the scalatest package.
3215 (add-after 'unpack 'remove-tests
3216 (lambda _ (delete-file-recursively "src/test") #t)))))
3218 `(("java-ngs" ,java-ngs)
3219 ("java-snappy-1" ,java-snappy-1)
3220 ("java-commons-compress" ,java-commons-compress)
3221 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3222 ("java-commons-jexl-2" ,java-commons-jexl-2)
3223 ("java-xz" ,java-xz)))
3225 `(("java-junit" ,java-junit)))
3226 (home-page "http://samtools.github.io/htsjdk/")
3227 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3229 "HTSJDK is an implementation of a unified Java library for accessing
3230 common file formats, such as SAM and VCF, used for high-throughput
3231 sequencing (HTS) data. There are also an number of useful utilities for
3232 manipulating HTS data.")
3233 (license license:expat)))
3235 ;; This is needed for picard 2.10.3
3236 (define-public java-htsjdk-2.10.1
3237 (package (inherit java-htsjdk-latest)
3238 (name "java-htsjdk")
3243 (url "https://github.com/samtools/htsjdk.git")
3245 (file-name (string-append name "-" version "-checkout"))
3248 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3249 (build-system ant-build-system)
3251 `(#:tests? #f ; tests require Scala
3253 #:jar-name "htsjdk.jar"
3255 (modify-phases %standard-phases
3256 (add-after 'unpack 'remove-useless-build.xml
3257 (lambda _ (delete-file "build.xml") #t))
3258 ;; The tests require the scalatest package.
3259 (add-after 'unpack 'remove-tests
3260 (lambda _ (delete-file-recursively "src/test") #t)))))))
3262 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3263 ;; recent version of java-htsjdk, which depends on gradle.
3264 (define-public java-picard
3266 (name "java-picard")
3271 (url "https://github.com/broadinstitute/picard.git")
3273 (file-name (string-append "java-picard-" version "-checkout"))
3276 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3277 (modules '((guix build utils)))
3280 ;; Delete pre-built binaries.
3281 (delete-file-recursively "lib")
3283 (substitute* "build.xml"
3284 ;; Remove build-time dependency on git.
3285 (("failifexecutionfails=\"true\"")
3286 "failifexecutionfails=\"false\"")
3288 (("depends=\"compile-htsjdk, ")
3290 (("depends=\"compile-htsjdk-tests, ")
3292 ;; Build picard-lib.jar before building picard.jar
3293 (("name=\"picard-jar\" depends=\"" line)
3294 (string-append line "picard-lib-jar, ")))
3296 (build-system ant-build-system)
3298 `(#:build-target "picard-jar"
3299 #:test-target "test"
3300 ;; Tests require jacoco:coverage.
3303 (list (string-append "-Dhtsjdk_lib_dir="
3304 (assoc-ref %build-inputs "java-htsjdk")
3305 "/share/java/htsjdk/")
3306 "-Dhtsjdk-classes=dist/tmp"
3307 (string-append "-Dhtsjdk-version="
3308 ,(package-version java-htsjdk)))
3311 (modify-phases %standard-phases
3312 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3313 (delete 'generate-jar-indices)
3314 (add-after 'unpack 'use-our-htsjdk
3315 (lambda* (#:key inputs #:allow-other-keys)
3316 (substitute* "build.xml"
3317 (("\\$\\{htsjdk\\}/lib")
3318 (string-append (assoc-ref inputs "java-htsjdk")
3319 "/share/java/htsjdk/")))
3321 (add-after 'unpack 'make-test-target-independent
3322 (lambda* (#:key inputs #:allow-other-keys)
3323 (substitute* "build.xml"
3324 (("name=\"test\" depends=\"compile, ")
3325 "name=\"test\" depends=\""))
3327 (replace 'install (install-jars "dist")))))
3329 `(("java-htsjdk" ,java-htsjdk)
3330 ("java-guava" ,java-guava)))
3332 `(("java-testng" ,java-testng)))
3333 (home-page "http://broadinstitute.github.io/picard/")
3334 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3335 (description "Picard is a set of Java command line tools for manipulating
3336 high-throughput sequencing (HTS) data and formats. Picard is implemented
3337 using the HTSJDK Java library to support accessing file formats that are
3338 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3340 (license license:expat)))
3342 ;; This is needed for dropseq-tools
3343 (define-public java-picard-2.10.3
3345 (name "java-picard")
3350 (url "https://github.com/broadinstitute/picard.git")
3352 (file-name (string-append "java-picard-" version "-checkout"))
3355 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3356 (build-system ant-build-system)
3358 `(#:jar-name "picard.jar"
3359 ;; Tests require jacoco:coverage.
3362 #:main-class "picard.cmdline.PicardCommandLine"
3363 #:modules ((guix build ant-build-system)
3365 (guix build java-utils)
3370 (modify-phases %standard-phases
3371 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3372 (delete 'generate-jar-indices)
3373 (add-after 'unpack 'remove-useless-build.xml
3374 (lambda _ (delete-file "build.xml") #t))
3375 ;; This is necessary to ensure that htsjdk is found when using
3376 ;; picard.jar as an executable.
3377 (add-before 'build 'edit-classpath-in-manifest
3378 (lambda* (#:key inputs #:allow-other-keys)
3379 (chmod "build.xml" #o664)
3380 (call-with-output-file "build.xml.new"
3384 (with-input-from-file "build.xml"
3385 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3386 `((target . ,(lambda (tag . kids)
3387 (let ((name ((sxpath '(name *text*))
3389 ;; FIXME: We're breaking the line
3390 ;; early with a dummy path to
3391 ;; ensure that the store reference
3392 ;; isn't broken apart and can still
3393 ;; be found by the reference
3398 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3399 ;; maximum line length is 70
3400 (string-tabulate (const #\b) 57)
3401 (assoc-ref inputs "java-htsjdk"))))
3402 (if (member "manifest" name)
3405 (@ (file "${manifest.file}")
3406 (match "\\r\\n\\r\\n")
3407 (replace "${line.separator}")))
3410 (file "${manifest.file}")
3413 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3414 (*text* . ,(lambda (_ txt) txt))))
3416 (rename-file "build.xml.new" "build.xml")
3419 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3421 `(("java-testng" ,java-testng)
3422 ("java-guava" ,java-guava)))
3423 (home-page "http://broadinstitute.github.io/picard/")
3424 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3425 (description "Picard is a set of Java command line tools for manipulating
3426 high-throughput sequencing (HTS) data and formats. Picard is implemented
3427 using the HTSJDK Java library to support accessing file formats that are
3428 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3430 (license license:expat)))
3432 ;; This is the last version of Picard to provide net.sf.samtools
3433 (define-public java-picard-1.113
3434 (package (inherit java-picard)
3435 (name "java-picard")
3440 (url "https://github.com/broadinstitute/picard.git")
3442 (file-name (string-append "java-picard-" version "-checkout"))
3445 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3446 (modules '((guix build utils)))
3449 ;; Delete pre-built binaries.
3450 (delete-file-recursively "lib")
3453 (build-system ant-build-system)
3455 `(#:build-target "picard-jar"
3456 #:test-target "test"
3457 ;; FIXME: the class path at test time is wrong.
3458 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3459 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3462 ;; This is only used for tests.
3464 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3466 (modify-phases %standard-phases
3467 ;; FIXME: This phase fails.
3468 (delete 'generate-jar-indices)
3469 ;; Do not use bundled ant bzip2.
3470 (add-after 'unpack 'use-ant-bzip
3471 (lambda* (#:key inputs #:allow-other-keys)
3472 (substitute* "build.xml"
3473 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3474 (string-append (assoc-ref inputs "ant")
3477 (add-after 'unpack 'make-test-target-independent
3478 (lambda* (#:key inputs #:allow-other-keys)
3479 (substitute* "build.xml"
3480 (("name=\"test\" depends=\"compile, ")
3481 "name=\"test\" depends=\"compile-tests, ")
3482 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3483 "name=\"compile\" depends=\"compile-src\""))
3485 (add-after 'unpack 'fix-deflater-path
3486 (lambda* (#:key outputs #:allow-other-keys)
3487 (substitute* "src/java/net/sf/samtools/Defaults.java"
3488 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3489 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3490 (assoc-ref outputs "out")
3491 "/lib/jni/libIntelDeflater.so"
3494 ;; Build the deflater library, because we've previously deleted the
3495 ;; pre-built one. This can only be built with access to the JDK
3497 (add-after 'build 'build-jni
3498 (lambda* (#:key inputs #:allow-other-keys)
3501 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3502 "-xf" (assoc-ref inputs "jdk-src"))
3503 (invoke "javah" "-jni"
3504 "-classpath" "classes"
3506 "net.sf.samtools.util.zip.IntelDeflater")
3507 (with-directory-excursion "src/c/inteldeflater"
3508 (invoke "gcc" "-I../../../lib" "-I."
3509 (string-append "-I" (assoc-ref inputs "jdk")
3511 "-I../../../jdk-src/src/share/native/common/"
3512 "-I../../../jdk-src/src/solaris/native/common/"
3513 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3514 (invoke "gcc" "-shared"
3515 "-o" "../../../lib/jni/libIntelDeflater.so"
3516 "IntelDeflater.o" "-lz" "-lstdc++"))
3518 ;; We can only build everything else after building the JNI library.
3519 (add-after 'build-jni 'build-rest
3520 (lambda* (#:key make-flags #:allow-other-keys)
3521 (apply invoke `("ant" "all" ,@make-flags))
3523 (add-before 'build 'set-JAVA6_HOME
3525 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3527 (replace 'install (install-jars "dist"))
3528 (add-after 'install 'install-jni-lib
3529 (lambda* (#:key outputs #:allow-other-keys)
3530 (let ((jni (string-append (assoc-ref outputs "out")
3533 (install-file "lib/jni/libIntelDeflater.so" jni)
3536 `(("java-snappy-1" ,java-snappy-1)
3537 ("java-commons-jexl-2" ,java-commons-jexl-2)
3538 ("java-cofoja" ,java-cofoja)
3539 ("ant" ,ant) ; for bzip2 support at runtime
3542 `(("ant-apache-bcel" ,ant-apache-bcel)
3543 ("ant-junit" ,ant-junit)
3544 ("java-testng" ,java-testng)
3545 ("java-commons-bcel" ,java-commons-bcel)
3546 ("java-jcommander" ,java-jcommander)
3547 ("jdk" ,icedtea-8 "jdk")
3548 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3550 (define-public fastqc
3557 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3558 "projects/fastqc/fastqc_v"
3559 version "_source.zip"))
3562 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3563 (build-system ant-build-system)
3565 `(#:tests? #f ; there are no tests
3566 #:build-target "build"
3568 (modify-phases %standard-phases
3569 (add-after 'unpack 'fix-dependencies
3570 (lambda* (#:key inputs #:allow-other-keys)
3571 (substitute* "build.xml"
3573 (string-append (assoc-ref inputs "java-jbzip2")
3574 "/share/java/jbzip2.jar"))
3576 (string-append (assoc-ref inputs "java-picard-1.113")
3577 "/share/java/sam-1.112.jar"))
3579 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3580 "/share/java/sis-jhdf5.jar")))
3582 ;; There is no installation target
3584 (lambda* (#:key inputs outputs #:allow-other-keys)
3585 (let* ((out (assoc-ref outputs "out"))
3586 (bin (string-append out "/bin"))
3587 (share (string-append out "/share/fastqc/"))
3588 (exe (string-append share "/fastqc")))
3589 (for-each mkdir-p (list bin share))
3590 (copy-recursively "bin" share)
3592 (("my \\$java_bin = 'java';")
3593 (string-append "my $java_bin = '"
3594 (assoc-ref inputs "java")
3597 (symlink exe (string-append bin "/fastqc"))
3601 ("perl" ,perl) ; needed for the wrapper script
3602 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3603 ("java-picard-1.113" ,java-picard-1.113)
3604 ("java-jbzip2" ,java-jbzip2)))
3606 `(("unzip" ,unzip)))
3607 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3608 (synopsis "Quality control tool for high throughput sequence data")
3610 "FastQC aims to provide a simple way to do some quality control
3611 checks on raw sequence data coming from high throughput sequencing
3612 pipelines. It provides a modular set of analyses which you can use to
3613 give a quick impression of whether your data has any problems of which
3614 you should be aware before doing any further analysis.
3616 The main functions of FastQC are:
3619 @item Import of data from BAM, SAM or FastQ files (any variant);
3620 @item Providing a quick overview to tell you in which areas there may
3622 @item Summary graphs and tables to quickly assess your data;
3623 @item Export of results to an HTML based permanent report;
3624 @item Offline operation to allow automated generation of reports
3625 without running the interactive application.
3627 (license license:gpl3+)))
3629 (define-public fastp
3637 (url "https://github.com/OpenGene/fastp.git")
3638 (commit (string-append "v" version))))
3639 (file-name (git-file-name name version))
3642 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3643 (build-system gnu-build-system)
3645 `(#:tests? #f ; there are none
3647 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3649 (modify-phases %standard-phases
3651 (add-before 'install 'create-target-dir
3652 (lambda* (#:key outputs #:allow-other-keys)
3653 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3657 (home-page "https://github.com/OpenGene/fastp/")
3658 (synopsis "All-in-one FastQ preprocessor")
3660 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3661 FastQ files. This tool has multi-threading support to afford high
3663 (license license:expat)))
3665 (define-public htslib
3672 "https://github.com/samtools/htslib/releases/download/"
3673 version "/htslib-" version ".tar.bz2"))
3676 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3677 (build-system gnu-build-system)
3679 `(("openssl" ,openssl)
3684 (home-page "http://www.htslib.org")
3685 (synopsis "C library for reading/writing high-throughput sequencing data")
3687 "HTSlib is a C library for reading/writing high-throughput sequencing
3688 data. It also provides the @command{bgzip}, @command{htsfile}, and
3689 @command{tabix} utilities.")
3690 ;; Files under cram/ are released under the modified BSD license;
3691 ;; the rest is released under the Expat license
3692 (license (list license:expat license:bsd-3))))
3694 ;; This package should be removed once no packages rely upon it.
3702 "https://github.com/samtools/htslib/releases/download/"
3703 version "/htslib-" version ".tar.bz2"))
3706 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3715 (url "https://github.com/nboley/idr.git")
3717 (file-name (git-file-name name version))
3720 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3721 ;; Delete generated C code.
3723 '(begin (delete-file "idr/inv_cdf.c") #t))))
3724 (build-system python-build-system)
3725 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3726 ;; are no longer part of this package. It also asserts False, which
3727 ;; causes the tests to always fail.
3728 (arguments `(#:tests? #f))
3730 `(("python-scipy" ,python-scipy)
3731 ("python-sympy" ,python-sympy)
3732 ("python-numpy" ,python-numpy)
3733 ("python-matplotlib" ,python-matplotlib)))
3735 `(("python-cython" ,python-cython)))
3736 (home-page "https://github.com/nboley/idr")
3737 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3739 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3740 to measure the reproducibility of findings identified from replicate
3741 experiments and provide highly stable thresholds based on reproducibility.")
3742 (license license:gpl2+)))
3744 (define-public jellyfish
3750 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3751 "releases/download/v" version
3752 "/jellyfish-" version ".tar.gz"))
3755 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3756 (build-system gnu-build-system)
3757 (outputs '("out" ;for library
3758 "ruby" ;for Ruby bindings
3759 "python")) ;for Python bindings
3762 (list (string-append "--enable-ruby-binding="
3763 (assoc-ref %outputs "ruby"))
3764 (string-append "--enable-python-binding="
3765 (assoc-ref %outputs "python")))
3767 (modify-phases %standard-phases
3768 (add-before 'check 'set-SHELL-variable
3770 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3772 (setenv "SHELL" (which "bash"))
3778 ("python" ,python-2)
3779 ("pkg-config" ,pkg-config)))
3781 `(("htslib" ,htslib)))
3782 (synopsis "Tool for fast counting of k-mers in DNA")
3784 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3785 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3786 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3787 is a command-line program that reads FASTA and multi-FASTA files containing
3788 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3789 translated into a human-readable text format using the @code{jellyfish dump}
3790 command, or queried for specific k-mers with @code{jellyfish query}.")
3791 (home-page "http://www.genome.umd.edu/jellyfish.html")
3792 ;; JELLYFISH seems to be 64-bit only.
3793 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3794 ;; The combined work is published under the GPLv3 or later. Individual
3795 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3796 (license (list license:gpl3+ license:expat))))
3798 (define-public khmer
3806 (url "https://github.com/dib-lab/khmer.git")
3807 (commit (string-append "v" version))))
3808 (file-name (git-file-name name version))
3811 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3812 (patches (search-patches "khmer-use-libraries.patch"))
3813 (modules '((guix build utils)))
3816 ;; Delete bundled libraries. We do not replace the bundled seqan
3817 ;; as it is a modified subset of the old version 1.4.1.
3819 ;; We do not replace the bundled MurmurHash as the canonical
3820 ;; repository for this code 'SMHasher' is unsuitable for providing
3822 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3823 (delete-file-recursively "third-party/zlib")
3824 (delete-file-recursively "third-party/bzip2")
3826 (build-system python-build-system)
3829 (modify-phases %standard-phases
3830 (add-after 'unpack 'set-cc
3831 (lambda _ (setenv "CC" "gcc") #t))
3832 ;; FIXME: This fails with "permission denied".
3833 (delete 'reset-gzip-timestamps))))
3835 `(("python-cython" ,python-cython)
3836 ("python-pytest" ,python-pytest)
3837 ("python-pytest-runner" ,python-pytest-runner)))
3841 ("python-screed" ,python-screed)
3842 ("python-bz2file" ,python-bz2file)))
3843 (home-page "https://khmer.readthedocs.org/")
3844 (synopsis "K-mer counting, filtering and graph traversal library")
3845 (description "The khmer software is a set of command-line tools for
3846 working with DNA shotgun sequencing data from genomes, transcriptomes,
3847 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3848 sometimes better. Khmer can also identify and fix problems with shotgun
3850 ;; When building on i686, armhf and mips64el, we get the following error:
3851 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3852 (supported-systems '("x86_64-linux" "aarch64-linux"))
3853 (license license:bsd-3)))
3855 (define-public kaiju
3862 (url "https://github.com/bioinformatics-centre/kaiju")
3863 (commit (string-append "v" version))))
3864 (file-name (git-file-name name version))
3867 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3868 (build-system gnu-build-system)
3870 `(#:tests? #f ; There are no tests.
3872 (modify-phases %standard-phases
3874 (add-before 'build 'move-to-src-dir
3875 (lambda _ (chdir "src") #t))
3877 (lambda* (#:key inputs outputs #:allow-other-keys)
3878 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3881 (copy-recursively "bin" bin))
3886 (home-page "http://kaiju.binf.ku.dk/")
3887 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3888 (description "Kaiju is a program for sensitive taxonomic classification
3889 of high-throughput sequencing reads from metagenomic whole genome sequencing
3891 (license license:gpl3+)))
3896 (version "2.1.1.20160309")
3899 (uri (pypi-uri "MACS2" version))
3902 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3903 (build-system python-build-system)
3905 `(#:python ,python-2 ; only compatible with Python 2.7
3906 #:tests? #f)) ; no test target
3908 `(("python-numpy" ,python2-numpy)))
3909 (home-page "https://github.com/taoliu/MACS/")
3910 (synopsis "Model based analysis for ChIP-Seq data")
3912 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3913 identifying transcript factor binding sites named Model-based Analysis of
3914 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3915 the significance of enriched ChIP regions and it improves the spatial
3916 resolution of binding sites through combining the information of both
3917 sequencing tag position and orientation.")
3918 (license license:bsd-3)))
3920 (define-public mafft
3927 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3928 "-without-extensions-src.tgz"))
3929 (file-name (string-append name "-" version ".tgz"))
3932 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3933 (build-system gnu-build-system)
3935 `(#:tests? #f ; no automated tests, though there are tests in the read me
3936 #:make-flags (let ((out (assoc-ref %outputs "out")))
3937 (list (string-append "PREFIX=" out)
3938 (string-append "BINDIR="
3939 (string-append out "/bin"))))
3941 (modify-phases %standard-phases
3942 (add-after 'unpack 'enter-dir
3943 (lambda _ (chdir "core") #t))
3944 (add-after 'enter-dir 'patch-makefile
3946 ;; on advice from the MAFFT authors, there is no need to
3947 ;; distribute mafft-profile, mafft-distance, or
3948 ;; mafft-homologs.rb as they are too "specialised".
3949 (substitute* "Makefile"
3950 ;; remove mafft-homologs.rb from SCRIPTS
3951 (("^SCRIPTS = mafft mafft-homologs.rb")
3953 ;; remove mafft-homologs from MANPAGES
3954 (("^MANPAGES = mafft.1 mafft-homologs.1")
3955 "MANPAGES = mafft.1")
3956 ;; remove mafft-distance from PROGS
3957 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3958 "PROGS = dvtditr dndfast7 dndblast sextet5")
3959 ;; remove mafft-profile from PROGS
3960 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3961 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3962 (("^rm -f mafft-profile mafft-profile.exe") "#")
3963 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3964 ;; do not install MAN pages in libexec folder
3965 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3966 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3968 (add-after 'enter-dir 'patch-paths
3969 (lambda* (#:key inputs #:allow-other-keys)
3970 (substitute* '("pairash.c"
3972 (("perl") (which "perl"))
3973 (("([\"`| ])awk" _ prefix)
3974 (string-append prefix (which "awk")))
3975 (("grep") (which "grep")))
3978 (add-after 'install 'wrap-programs
3979 (lambda* (#:key outputs #:allow-other-keys)
3980 (let* ((out (assoc-ref outputs "out"))
3981 (bin (string-append out "/bin"))
3982 (path (string-append
3983 (assoc-ref %build-inputs "coreutils") "/bin:")))
3984 (for-each (lambda (file)
3986 `("PATH" ":" prefix (,path))))
3994 ("coreutils" ,coreutils)))
3995 (home-page "http://mafft.cbrc.jp/alignment/software/")
3996 (synopsis "Multiple sequence alignment program")
3998 "MAFFT offers a range of multiple alignment methods for nucleotide and
3999 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4000 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4002 (license (license:non-copyleft
4003 "http://mafft.cbrc.jp/alignment/software/license.txt"
4004 "BSD-3 with different formatting"))))
4013 (url "https://github.com/marbl/mash.git")
4014 (commit (string-append "v" version))))
4015 (file-name (git-file-name name version))
4018 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4019 (modules '((guix build utils)))
4022 ;; Delete bundled kseq.
4023 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4024 (delete-file "src/mash/kseq.h")
4026 (build-system gnu-build-system)
4028 `(#:tests? #f ; No tests.
4031 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4032 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4033 #:make-flags (list "CC=gcc")
4035 (modify-phases %standard-phases
4036 (add-after 'unpack 'fix-includes
4038 (substitute* '("src/mash/Sketch.cpp"
4039 "src/mash/CommandFind.cpp"
4040 "src/mash/CommandScreen.cpp")
4041 (("^#include \"kseq\\.h\"")
4042 "#include \"htslib/kseq.h\""))
4044 (add-after 'fix-includes 'use-c++14
4046 ;; capnproto 0.7 requires c++14 to build
4047 (substitute* "configure.ac"
4048 (("c\\+\\+11") "c++14"))
4049 (substitute* "Makefile.in"
4050 (("c\\+\\+11") "c++14"))
4053 `(("autoconf" ,autoconf)
4054 ;; Capnproto and htslib are statically embedded in the final
4055 ;; application. Therefore we also list their licenses, below.
4056 ("capnproto" ,capnproto)
4057 ("htslib" ,htslib)))
4061 (supported-systems '("x86_64-linux"))
4062 (home-page "https://mash.readthedocs.io")
4063 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4064 (description "Mash is a fast sequence distance estimator that uses the
4065 MinHash algorithm and is designed to work with genomes and metagenomes in the
4066 form of assemblies or reads.")
4067 (license (list license:bsd-3 ; Mash
4068 license:expat ; HTSlib and capnproto
4069 license:public-domain ; MurmurHash 3
4070 license:cpl1.0)))) ; Open Bloom Filter
4072 (define-public metabat
4080 (url "https://bitbucket.org/berkeleylab/metabat.git")
4081 (commit (string-append "v" version))))
4082 (file-name (git-file-name name version))
4085 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4086 (patches (search-patches "metabat-fix-compilation.patch"))))
4087 (build-system scons-build-system)
4089 `(#:scons ,scons-python2
4091 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4092 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4093 #:tests? #f ;; Tests are run during the build phase.
4095 (modify-phases %standard-phases
4096 (add-after 'unpack 'fix-includes
4098 (substitute* "src/BamUtils.h"
4099 (("^#include \"bam/bam\\.h\"")
4100 "#include \"samtools/bam.h\"")
4101 (("^#include \"bam/sam\\.h\"")
4102 "#include \"samtools/sam.h\""))
4103 (substitute* "src/KseqReader.h"
4104 (("^#include \"bam/kseq\\.h\"")
4105 "#include \"htslib/kseq.h\""))
4107 (add-after 'unpack 'fix-scons
4108 (lambda* (#:key inputs #:allow-other-keys)
4109 (substitute* "SConstruct"
4110 (("^htslib_dir += 'samtools'")
4111 (string-append "htslib_dir = '"
4112 (assoc-ref inputs "htslib")
4114 (("^samtools_dir = 'samtools'")
4115 (string-append "samtools_dir = '"
4116 (assoc-ref inputs "samtools")
4118 (("^findStaticOrShared\\('bam', hts_lib")
4119 (string-append "findStaticOrShared('bam', '"
4120 (assoc-ref inputs "samtools")
4122 ;; Do not distribute README.
4123 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4128 ("samtools" ,samtools)
4131 (home-page "https://bitbucket.org/berkeleylab/metabat")
4133 "Reconstruction of single genomes from complex microbial communities")
4135 "Grouping large genomic fragments assembled from shotgun metagenomic
4136 sequences to deconvolute complex microbial communities, or metagenome binning,
4137 enables the study of individual organisms and their interactions. MetaBAT is
4138 an automated metagenome binning software, which integrates empirical
4139 probabilistic distances of genome abundance and tetranucleotide frequency.")
4140 ;; The source code contains inline assembly.
4141 (supported-systems '("x86_64-linux" "i686-linux"))
4142 (license (license:non-copyleft "file://license.txt"
4143 "See license.txt in the distribution."))))
4145 (define-public minced
4152 (url "https://github.com/ctSkennerton/minced.git")
4154 (file-name (git-file-name name version))
4157 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4158 (build-system gnu-build-system)
4160 `(#:test-target "test"
4162 (modify-phases %standard-phases
4164 (add-before 'check 'fix-test
4166 ;; Fix test for latest version.
4167 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4168 (("minced:0.1.6") "minced:0.2.0"))
4170 (replace 'install ; No install target.
4171 (lambda* (#:key inputs outputs #:allow-other-keys)
4172 (let* ((out (assoc-ref outputs "out"))
4173 (bin (string-append out "/bin"))
4174 (wrapper (string-append bin "/minced")))
4175 ;; Minced comes with a wrapper script that tries to figure out where
4176 ;; it is located before running the JAR. Since these paths are known
4177 ;; to us, we build our own wrapper to avoid coreutils dependency.
4178 (install-file "minced.jar" bin)
4179 (with-output-to-file wrapper
4183 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4184 (assoc-ref inputs "jre") "/bin/java -jar "
4185 bin "/minced.jar \"$@\"\n"))))
4186 (chmod wrapper #o555))
4189 `(("jdk" ,icedtea "jdk")))
4192 ("jre" ,icedtea "out")))
4193 (home-page "https://github.com/ctSkennerton/minced")
4194 (synopsis "Mining CRISPRs in Environmental Datasets")
4196 "MinCED is a program to find Clustered Regularly Interspaced Short
4197 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4198 unassembled metagenomic reads, but is mainly designed for full genomes and
4199 assembled metagenomic sequence.")
4200 (license license:gpl3+)))
4208 (uri (pypi-uri "misopy" version))
4211 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4212 (modules '((guix build utils)))
4214 (substitute* "setup.py"
4215 ;; Use setuptools, or else the executables are not
4217 (("distutils.core") "setuptools")
4218 ;; use "gcc" instead of "cc" for compilation
4220 "cc.set_executables(
4224 linker_so='gcc -shared'); defines"))
4226 (build-system python-build-system)
4228 `(#:python ,python-2 ; only Python 2 is supported
4229 #:tests? #f)) ; no "test" target
4231 `(("samtools" ,samtools)
4232 ("python-numpy" ,python2-numpy)
4233 ("python-pysam" ,python2-pysam)
4234 ("python-scipy" ,python2-scipy)
4235 ("python-matplotlib" ,python2-matplotlib)))
4237 `(("python-mock" ,python2-mock) ;for tests
4238 ("python-pytz" ,python2-pytz))) ;for tests
4239 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4240 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4242 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4243 the expression level of alternatively spliced genes from RNA-Seq data, and
4244 identifies differentially regulated isoforms or exons across samples. By
4245 modeling the generative process by which reads are produced from isoforms in
4246 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4247 that a read originated from a particular isoform.")
4248 (license license:gpl2)))
4250 (define-public muscle
4253 (version "3.8.1551")
4255 (method url-fetch/tarbomb)
4257 "http://www.drive5.com/muscle/muscle_src_"
4261 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4262 (build-system gnu-build-system)
4264 `(#:make-flags (list "LDLIBS = -lm")
4266 (modify-phases %standard-phases
4269 ;; There are no tests, so just test if it runs.
4270 (lambda _ (invoke "./muscle" "-version") #t))
4272 (lambda* (#:key outputs #:allow-other-keys)
4273 (let* ((out (assoc-ref outputs "out"))
4274 (bin (string-append out "/bin")))
4275 (install-file "muscle" bin)
4277 (home-page "http://www.drive5.com/muscle")
4278 (synopsis "Multiple sequence alignment program")
4280 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4281 program for nucleotide and protein sequences.")
4282 ;; License information found in 'muscle -h' and usage.cpp.
4283 (license license:public-domain)))
4285 (define-public newick-utils
4286 ;; There are no recent releases so we package from git.
4287 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4289 (name "newick-utils")
4290 (version (string-append "1.6-1." (string-take commit 8)))
4294 (url "https://github.com/tjunier/newick_utils.git")
4296 (file-name (string-append name "-" version "-checkout"))
4299 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4300 (build-system gnu-build-system)
4302 ;; XXX: TODO: Enable Lua and Guile bindings.
4303 ;; https://github.com/tjunier/newick_utils/issues/13
4304 `(("libxml2" ,libxml2)
4308 `(("autoconf" ,autoconf)
4309 ("automake" ,automake)
4310 ("libtool" ,libtool)))
4311 (synopsis "Programs for working with newick format phylogenetic trees")
4313 "Newick-utils is a suite of utilities for processing phylogenetic trees
4314 in Newick format. Functions include re-rooting, extracting subtrees,
4315 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4316 (home-page "https://github.com/tjunier/newick_utils")
4317 (license license:bsd-3))))
4326 "https://github.com/wwood/OrfM/releases/download/v"
4327 version "/orfm-" version ".tar.gz"))
4330 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4331 (build-system gnu-build-system)
4332 (inputs `(("zlib" ,zlib)))
4334 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4335 ("ruby-rspec" ,ruby-rspec)
4337 (synopsis "Simple and not slow open reading frame (ORF) caller")
4339 "An ORF caller finds stretches of DNA that, when translated, are not
4340 interrupted by stop codons. OrfM finds and prints these ORFs.")
4341 (home-page "https://github.com/wwood/OrfM")
4342 (license license:lgpl3+)))
4344 (define-public pplacer
4345 (let ((commit "807f6f3"))
4348 ;; The commit should be updated with each version change.
4349 (version "1.1.alpha19")
4354 (url "https://github.com/matsen/pplacer.git")
4355 (commit (string-append "v" version))))
4356 (file-name (git-file-name name version))
4358 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
4359 (build-system ocaml-build-system)
4361 `(#:ocaml ,ocaml-4.01
4362 #:findlib ,ocaml4.01-findlib
4363 #:modules ((guix build ocaml-build-system)
4367 (modify-phases %standard-phases
4369 (add-after 'unpack 'replace-bundled-cddlib
4370 (lambda* (#:key inputs #:allow-other-keys)
4371 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4372 (local-dir "cddlib_guix"))
4374 (with-directory-excursion local-dir
4375 (invoke "tar" "xvf" cddlib-src))
4376 (let ((cddlib-src-folder
4377 (string-append local-dir "/"
4378 (list-ref (scandir local-dir) 2)
4380 (for-each make-file-writable (find-files "cdd_src" ".*"))
4384 (string-append "cdd_src/" (basename file))))
4385 (find-files cddlib-src-folder ".*[ch]$")))
4387 (add-after 'unpack 'fix-makefile
4389 ;; Remove system calls to 'git'.
4390 (substitute* "Makefile"
4391 (("^DESCRIPT:=pplacer-.*")
4393 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4394 (substitute* "myocamlbuild.ml"
4395 (("git describe --tags --long .*\\\" with")
4397 "echo -n v" ,version "-" ,commit "\" with")))
4400 (lambda* (#:key outputs #:allow-other-keys)
4401 (let* ((out (assoc-ref outputs "out"))
4402 (bin (string-append out "/bin")))
4403 (copy-recursively "bin" bin))
4408 ("ocaml-ounit" ,ocaml4.01-ounit)
4409 ("ocaml-batteries" ,ocaml4.01-batteries)
4410 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4411 ("ocaml-csv" ,ocaml4.01-csv)
4412 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4413 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4414 ("ocaml-mcl" ,ocaml4.01-mcl)
4415 ("ocaml-gsl" ,ocaml4.01-gsl)
4416 ("cddlib-src" ,(package-source cddlib))))
4418 `(("pplacer-scripts" ,pplacer-scripts)))
4419 (synopsis "Phylogenetic placement of biological sequences")
4421 "Pplacer places query sequences on a fixed reference phylogenetic tree
4422 to maximize phylogenetic likelihood or posterior probability according to a
4423 reference alignment. Pplacer is designed to be fast, to give useful
4424 information about uncertainty, and to offer advanced visualization and
4425 downstream analysis.")
4426 (home-page "http://matsen.fhcrc.org/pplacer")
4427 (license license:gpl3))))
4429 ;; This package is installed alongside 'pplacer'. It is a separate package so
4430 ;; that it can use the python-build-system for the scripts that are
4431 ;; distributed alongside the main OCaml binaries.
4432 (define pplacer-scripts
4435 (name "pplacer-scripts")
4436 (build-system python-build-system)
4438 `(#:python ,python-2
4440 (modify-phases %standard-phases
4441 (add-after 'unpack 'enter-scripts-dir
4442 (lambda _ (chdir "scripts") #t))
4444 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
4445 (add-after 'install 'wrap-executables
4446 (lambda* (#:key inputs outputs #:allow-other-keys)
4447 (let* ((out (assoc-ref outputs "out"))
4448 (bin (string-append out "/bin")))
4449 (let ((path (string-append
4450 (assoc-ref inputs "hmmer") "/bin:"
4451 (assoc-ref inputs "infernal") "/bin")))
4453 (wrap-program (string-append bin "/refpkg_align.py")
4454 `("PATH" ":" prefix (,path))))
4455 (let ((path (string-append
4456 (assoc-ref inputs "hmmer") "/bin")))
4457 (wrap-program (string-append bin "/hrefpkg_query.py")
4458 `("PATH" ":" prefix (,path)))))
4461 `(("infernal" ,infernal)
4464 `(("python-biopython" ,python2-biopython)
4465 ("taxtastic" ,taxtastic)))
4466 (synopsis "Pplacer Python scripts")))
4468 (define-public python2-pbcore
4470 (name "python2-pbcore")
4474 (uri (pypi-uri "pbcore" version))
4477 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4478 (build-system python-build-system)
4479 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4481 `(("python-cython" ,python2-cython)
4482 ("python-numpy" ,python2-numpy)
4483 ("python-pysam" ,python2-pysam)
4484 ("python-h5py" ,python2-h5py)))
4486 `(("python-nose" ,python2-nose)
4487 ("python-sphinx" ,python2-sphinx)
4488 ("python-pyxb" ,python2-pyxb)))
4489 (home-page "http://pacificbiosciences.github.io/pbcore/")
4490 (synopsis "Library for reading and writing PacBio data files")
4492 "The pbcore package provides Python APIs for interacting with PacBio data
4493 files and writing bioinformatics applications.")
4494 (license license:bsd-3)))
4496 (define-public python2-warpedlmm
4498 (name "python2-warpedlmm")
4504 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4508 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4509 (build-system python-build-system)
4511 `(#:python ,python-2)) ; requires Python 2.7
4513 `(("python-scipy" ,python2-scipy)
4514 ("python-numpy" ,python2-numpy)
4515 ("python-matplotlib" ,python2-matplotlib)
4516 ("python-fastlmm" ,python2-fastlmm)
4517 ("python-pandas" ,python2-pandas)
4518 ("python-pysnptools" ,python2-pysnptools)))
4520 `(("python-mock" ,python2-mock)
4521 ("python-nose" ,python2-nose)
4523 (home-page "https://github.com/PMBio/warpedLMM")
4524 (synopsis "Implementation of warped linear mixed models")
4526 "WarpedLMM is a Python implementation of the warped linear mixed model,
4527 which automatically learns an optimal warping function (or transformation) for
4528 the phenotype as it models the data.")
4529 (license license:asl2.0)))
4531 (define-public pbtranscript-tofu
4532 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4534 (name "pbtranscript-tofu")
4535 (version (string-append "2.2.3." (string-take commit 7)))
4539 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4541 (file-name (string-append name "-" version "-checkout"))
4544 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4545 (modules '((guix build utils)))
4548 ;; remove bundled Cython sources
4549 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4551 (build-system python-build-system)
4553 `(#:python ,python-2
4554 ;; FIXME: Tests fail with "No such file or directory:
4555 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4558 (modify-phases %standard-phases
4559 (add-after 'unpack 'enter-directory
4561 (chdir "pbtranscript-tofu/pbtranscript/")
4563 ;; With setuptools version 18.0 and later this setup.py hack causes
4564 ;; a build error, so we disable it.
4565 (add-after 'enter-directory 'patch-setuppy
4567 (substitute* "setup.py"
4568 (("if 'setuptools.extension' in sys.modules:")
4572 `(("python-numpy" ,python2-numpy)
4573 ("python-bx-python" ,python2-bx-python)
4574 ("python-networkx" ,python2-networkx)
4575 ("python-scipy" ,python2-scipy)
4576 ("python-pbcore" ,python2-pbcore)
4577 ("python-h5py" ,python2-h5py)))
4579 `(("python-cython" ,python2-cython)
4580 ("python-nose" ,python2-nose)))
4581 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4582 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4584 "pbtranscript-tofu contains scripts to analyze transcriptome data
4585 generated using the PacBio Iso-Seq protocol.")
4586 (license license:bsd-3))))
4588 (define-public prank
4595 "http://wasabiapp.org/download/prank/prank.source."
4599 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4600 (build-system gnu-build-system)
4603 (modify-phases %standard-phases
4604 (add-after 'unpack 'enter-src-dir
4608 (add-after 'unpack 'remove-m64-flag
4609 ;; Prank will build with the correct 'bit-ness' without this flag
4610 ;; and this allows building on 32-bit machines.
4611 (lambda _ (substitute* "src/Makefile"
4616 (lambda* (#:key outputs #:allow-other-keys)
4617 (let* ((out (assoc-ref outputs "out"))
4618 (bin (string-append out "/bin"))
4619 (man (string-append out "/share/man/man1"))
4620 (path (string-append
4621 (assoc-ref %build-inputs "mafft") "/bin:"
4622 (assoc-ref %build-inputs "exonerate") "/bin:"
4623 (assoc-ref %build-inputs "bppsuite") "/bin")))
4624 (install-file "prank" bin)
4625 (wrap-program (string-append bin "/prank")
4626 `("PATH" ":" prefix (,path)))
4627 (install-file "prank.1" man))
4631 ("exonerate" ,exonerate)
4632 ("bppsuite" ,bppsuite)))
4633 (home-page "http://wasabiapp.org/software/prank/")
4634 (synopsis "Probabilistic multiple sequence alignment program")
4636 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4637 codon and amino-acid sequences. It is based on a novel algorithm that treats
4638 insertions correctly and avoids over-estimation of the number of deletion
4639 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4640 in phylogenetics and correctly takes into account the evolutionary distances
4641 between sequences. Lastly, PRANK allows for defining a potential structure
4642 for sequences to be aligned and then, simultaneously with the alignment,
4643 predicts the locations of structural units in the sequences.")
4644 (license license:gpl2+)))
4646 (define-public proteinortho
4648 (name "proteinortho")
4655 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4656 version "_src.tar.gz"))
4659 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4660 (build-system gnu-build-system)
4662 `(#:test-target "test"
4664 (modify-phases %standard-phases
4666 ;; There is no configure script, so we modify the Makefile directly.
4667 (lambda* (#:key outputs #:allow-other-keys)
4668 (substitute* "Makefile"
4671 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4673 (add-before 'install 'make-install-directory
4674 ;; The install directory is not created during 'make install'.
4675 (lambda* (#:key outputs #:allow-other-keys)
4676 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4678 (add-after 'install 'wrap-programs
4679 (lambda* (#:key inputs outputs #:allow-other-keys)
4680 (let* ((path (getenv "PATH"))
4681 (out (assoc-ref outputs "out"))
4682 (binary (string-append out "/bin/proteinortho5.pl")))
4683 (wrap-program binary `("PATH" ":" prefix (,path))))
4687 ("python" ,python-2)
4688 ("blast+" ,blast+)))
4689 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4690 (synopsis "Detect orthologous genes across species")
4692 "Proteinortho is a tool to detect orthologous genes across different
4693 species. For doing so, it compares similarities of given gene sequences and
4694 clusters them to find significant groups. The algorithm was designed to handle
4695 large-scale data and can be applied to hundreds of species at once.")
4696 (license license:gpl2+)))
4698 (define-public pyicoteo
4706 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4707 (commit (string-append "v" version))))
4708 (file-name (git-file-name name version))
4711 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4712 (build-system python-build-system)
4714 `(#:python ,python-2 ; does not work with Python 3
4715 #:tests? #f)) ; there are no tests
4717 `(("python2-matplotlib" ,python2-matplotlib)))
4718 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4719 (synopsis "Analyze high-throughput genetic sequencing data")
4721 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4722 sequencing data. It works with genomic coordinates. There are currently six
4723 different command-line tools:
4726 @item pyicoregion: for generating exploratory regions automatically;
4727 @item pyicoenrich: for differential enrichment between two conditions;
4728 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4729 @item pyicos: for genomic coordinates manipulation;
4730 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4731 @item pyicount: to count how many reads from N experiment files overlap in a
4733 @item pyicotrocol: to combine operations from pyicoteo.
4735 (license license:gpl3+)))
4737 (define-public prodigal
4744 (url "https://github.com/hyattpd/Prodigal.git")
4745 (commit (string-append "v" version))))
4746 (file-name (git-file-name name version))
4749 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4750 (build-system gnu-build-system)
4752 `(#:tests? #f ;no check target
4753 #:make-flags (list (string-append "INSTALLDIR="
4754 (assoc-ref %outputs "out")
4757 (modify-phases %standard-phases
4758 (delete 'configure))))
4759 (home-page "http://prodigal.ornl.gov")
4760 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4762 "Prodigal runs smoothly on finished genomes, draft genomes, and
4763 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4764 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4765 partial genes, and identifies translation initiation sites.")
4766 (license license:gpl3+)))
4768 (define-public roary
4776 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4780 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4781 (build-system perl-build-system)
4784 (modify-phases %standard-phases
4789 ;; The tests are not run by default, so we run each test file
4791 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4793 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4794 (getenv "PERL5LIB")))
4795 (for-each (lambda (file)
4796 (display file)(display "\n")
4797 (invoke "perl" file))
4798 (find-files "t" ".*\\.t$"))
4801 ;; There is no 'install' target in the Makefile.
4802 (lambda* (#:key outputs #:allow-other-keys)
4803 (let* ((out (assoc-ref outputs "out"))
4804 (bin (string-append out "/bin"))
4805 (perl (string-append out "/lib/perl5/site_perl"))
4806 (roary-plots "contrib/roary_plots"))
4809 (copy-recursively "bin" bin)
4810 (copy-recursively "lib" perl)
4812 (add-after 'install 'wrap-programs
4813 (lambda* (#:key inputs outputs #:allow-other-keys)
4814 (let* ((out (assoc-ref outputs "out"))
4815 (perl5lib (getenv "PERL5LIB"))
4816 (path (getenv "PATH")))
4817 (for-each (lambda (prog)
4818 (let ((binary (string-append out "/" prog)))
4819 (wrap-program binary
4820 `("PERL5LIB" ":" prefix
4821 (,(string-append perl5lib ":" out
4822 "/lib/perl5/site_perl"))))
4823 (wrap-program binary
4825 (,(string-append path ":" out "/bin"))))))
4826 (find-files "bin" ".*[^R]$"))
4828 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4829 (r-site-lib (getenv "R_LIBS_SITE"))
4831 (string-append (assoc-ref inputs "coreutils") "/bin")))
4833 `("R_LIBS_SITE" ":" prefix
4834 (,(string-append r-site-lib ":" out "/site-library/"))))
4837 (,(string-append coreutils-path ":" out "/bin"))))))
4840 `(("perl-env-path" ,perl-env-path)
4841 ("perl-test-files" ,perl-test-files)
4842 ("perl-test-most" ,perl-test-most)
4843 ("perl-test-output" ,perl-test-output)))
4845 `(("perl-array-utils" ,perl-array-utils)
4846 ("bioperl" ,bioperl-minimal)
4847 ("perl-digest-md5-file" ,perl-digest-md5-file)
4848 ("perl-exception-class" ,perl-exception-class)
4849 ("perl-file-find-rule" ,perl-file-find-rule)
4850 ("perl-file-grep" ,perl-file-grep)
4851 ("perl-file-slurper" ,perl-file-slurper)
4852 ("perl-file-which" ,perl-file-which)
4853 ("perl-graph" ,perl-graph)
4854 ("perl-graph-readwrite" ,perl-graph-readwrite)
4855 ("perl-log-log4perl" ,perl-log-log4perl)
4856 ("perl-moose" ,perl-moose)
4857 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4858 ("perl-text-csv" ,perl-text-csv)
4859 ("bedtools" ,bedtools)
4863 ("parallel" ,parallel)
4866 ("fasttree" ,fasttree)
4870 ("r-minimal" ,r-minimal)
4871 ("r-ggplot2" ,r-ggplot2)
4872 ("coreutils" ,coreutils)))
4873 (home-page "http://sanger-pathogens.github.io/Roary")
4874 (synopsis "High speed stand-alone pan genome pipeline")
4876 "Roary is a high speed stand alone pan genome pipeline, which takes
4877 annotated assemblies in GFF3 format (produced by the Prokka program) and
4878 calculates the pan genome. Using a standard desktop PC, it can analyse
4879 datasets with thousands of samples, without compromising the quality of the
4880 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4881 single processor. Roary is not intended for metagenomics or for comparing
4882 extremely diverse sets of genomes.")
4883 (license license:gpl3)))
4885 (define-public raxml
4893 (url "https://github.com/stamatak/standard-RAxML.git")
4894 (commit (string-append "v" version))))
4895 (file-name (git-file-name name version))
4898 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4899 (build-system gnu-build-system)
4901 `(#:tests? #f ; There are no tests.
4902 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4903 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4905 (modify-phases %standard-phases
4908 (lambda* (#:key outputs #:allow-other-keys)
4909 (let* ((out (assoc-ref outputs "out"))
4910 (bin (string-append out "/bin"))
4911 (executable "raxmlHPC-HYBRID"))
4912 (install-file executable bin)
4913 (symlink (string-append bin "/" executable) "raxml"))
4916 `(("openmpi" ,openmpi)))
4917 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4918 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4920 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4922 ;; The source includes x86 specific code
4923 (supported-systems '("x86_64-linux" "i686-linux"))
4924 (license license:gpl2+)))
4934 (url "https://github.com/deweylab/RSEM.git")
4935 (commit (string-append "v" version))))
4937 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4938 (file-name (git-file-name name version))
4939 (modules '((guix build utils)))
4942 ;; remove bundled copy of boost and samtools
4943 (delete-file-recursively "boost")
4944 (delete-file-recursively "samtools-1.3")
4946 (build-system gnu-build-system)
4948 `(#:tests? #f ;no "check" target
4950 (list (string-append "BOOST="
4951 (assoc-ref %build-inputs "boost")
4953 (string-append "SAMHEADERS="
4954 (assoc-ref %build-inputs "htslib")
4955 "/include/htslib/sam.h")
4956 (string-append "SAMLIBS="
4957 (assoc-ref %build-inputs "htslib")
4960 (modify-phases %standard-phases
4961 ;; No "configure" script.
4962 ;; Do not build bundled samtools library.
4965 (substitute* "Makefile"
4966 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4967 (("^\\$\\(SAMLIBS\\).*") ""))
4970 (lambda* (#:key outputs #:allow-other-keys)
4971 (let* ((out (string-append (assoc-ref outputs "out")))
4972 (bin (string-append out "/bin/"))
4973 (perl (string-append out "/lib/perl5/site_perl")))
4976 (for-each (lambda (file)
4977 (install-file file bin))
4978 (find-files "." "rsem-.*"))
4979 (install-file "rsem_perl_utils.pm" perl))
4981 (add-after 'install 'wrap-program
4982 (lambda* (#:key outputs #:allow-other-keys)
4983 (let ((out (assoc-ref outputs "out")))
4984 (for-each (lambda (prog)
4985 (wrap-program (string-append out "/bin/" prog)
4986 `("PERL5LIB" ":" prefix
4987 (,(string-append out "/lib/perl5/site_perl")))))
4988 '("rsem-calculate-expression"
4990 "rsem-generate-data-matrix"
4991 "rsem-generate-ngvector"
4992 "rsem-plot-transcript-wiggles"
4993 "rsem-prepare-reference"
4995 "rsem-run-prsem-testing-procedure")))
4999 ("r-minimal" ,r-minimal)
5001 ("htslib" ,htslib-1.3)
5003 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5004 (synopsis "Estimate gene expression levels from RNA-Seq data")
5006 "RSEM is a software package for estimating gene and isoform expression
5007 levels from RNA-Seq data. The RSEM package provides a user-friendly
5008 interface, supports threads for parallel computation of the EM algorithm,
5009 single-end and paired-end read data, quality scores, variable-length reads and
5010 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5011 interval estimates for expression levels. For visualization, it can generate
5012 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5013 (license license:gpl3+)))
5015 (define-public rseqc
5023 (string-append "mirror://sourceforge/rseqc/"
5024 "RSeQC-" version ".tar.gz"))
5026 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5027 (modules '((guix build utils)))
5030 ;; remove bundled copy of pysam
5031 (delete-file-recursively "lib/pysam")
5032 (substitute* "setup.py"
5033 ;; remove dependency on outdated "distribute" module
5034 (("^from distribute_setup import use_setuptools") "")
5035 (("^use_setuptools\\(\\)") "")
5036 ;; do not use bundled copy of pysam
5037 (("^have_pysam = False") "have_pysam = True"))
5039 (build-system python-build-system)
5040 (arguments `(#:python ,python-2))
5042 `(("python-cython" ,python2-cython)
5043 ("python-pysam" ,python2-pysam)
5044 ("python-numpy" ,python2-numpy)
5047 `(("python-nose" ,python2-nose)))
5048 (home-page "http://rseqc.sourceforge.net/")
5049 (synopsis "RNA-seq quality control package")
5051 "RSeQC provides a number of modules that can comprehensively evaluate
5052 high throughput sequence data, especially RNA-seq data. Some basic modules
5053 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5054 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5055 distribution, coverage uniformity, strand specificity, etc.")
5056 (license license:gpl3+)))
5059 ;; There are no release tarballs. According to the installation
5060 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5061 ;; stable release is identified by this changeset ID.
5062 (let ((changeset "2329130")
5066 (version (string-append "0-" revision "." changeset))
5070 (url "https://bitbucket.org/libsleipnir/sleipnir")
5071 (changeset changeset)))
5072 (file-name (string-append name "-" version "-checkout"))
5075 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5076 (build-system gnu-build-system)
5078 `(#:modules ((srfi srfi-1)
5079 (guix build gnu-build-system)
5082 (let ((dirs '("SeekMiner"
5088 (modify-phases %standard-phases
5091 (substitute* "gen_tools_am"
5092 (("/usr/bin/env.*") (which "perl")))
5093 (invoke "bash" "gen_auto")
5095 (add-after 'build 'build-additional-tools
5096 (lambda* (#:key make-flags #:allow-other-keys)
5097 (for-each (lambda (dir)
5098 (with-directory-excursion (string-append "tools/" dir)
5099 (apply invoke "make" make-flags)))
5102 (add-after 'install 'install-additional-tools
5103 (lambda* (#:key make-flags #:allow-other-keys)
5104 (for-each (lambda (dir)
5105 (with-directory-excursion (string-append "tools/" dir)
5106 (apply invoke `("make" ,@make-flags "install"))))
5113 ("readline" ,readline)
5114 ("gengetopt" ,gengetopt)
5115 ("log4cpp" ,log4cpp)))
5117 `(("autoconf" ,autoconf)
5118 ("automake" ,automake)
5120 (home-page "http://seek.princeton.edu")
5121 (synopsis "Gene co-expression search engine")
5123 "SEEK is a computational gene co-expression search engine. SEEK provides
5124 biologists with a way to navigate the massive human expression compendium that
5125 now contains thousands of expression datasets. SEEK returns a robust ranking
5126 of co-expressed genes in the biological area of interest defined by the user's
5127 query genes. It also prioritizes thousands of expression datasets according
5128 to the user's query of interest.")
5129 (license license:cc-by3.0))))
5131 (define-public samtools
5139 (string-append "mirror://sourceforge/samtools/samtools/"
5140 version "/samtools-" version ".tar.bz2"))
5143 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5144 (modules '((guix build utils)))
5146 ;; Delete bundled htslib.
5147 (delete-file-recursively "htslib-1.9")
5149 (build-system gnu-build-system)
5151 `(#:modules ((ice-9 ftw)
5153 (guix build gnu-build-system)
5155 #:configure-flags (list "--with-ncurses")
5157 (modify-phases %standard-phases
5158 (add-after 'unpack 'patch-tests
5160 (substitute* "test/test.pl"
5161 ;; The test script calls out to /bin/bash
5162 (("/bin/bash") (which "bash")))
5164 (add-after 'install 'install-library
5165 (lambda* (#:key outputs #:allow-other-keys)
5166 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5167 (install-file "libbam.a" lib)
5169 (add-after 'install 'install-headers
5170 (lambda* (#:key outputs #:allow-other-keys)
5171 (let ((include (string-append (assoc-ref outputs "out")
5172 "/include/samtools/")))
5173 (for-each (lambda (file)
5174 (install-file file include))
5175 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5177 (native-inputs `(("pkg-config" ,pkg-config)))
5179 `(("htslib" ,htslib)
5180 ("ncurses" ,ncurses)
5184 (home-page "http://samtools.sourceforge.net")
5185 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5187 "Samtools implements various utilities for post-processing nucleotide
5188 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5189 variant calling (in conjunction with bcftools), and a simple alignment
5191 (license license:expat)))
5193 (define-public samtools-0.1
5194 ;; This is the most recent version of the 0.1 line of samtools. The input
5195 ;; and output formats differ greatly from that used and produced by samtools
5196 ;; 1.x and is still used in many bioinformatics pipelines.
5197 (package (inherit samtools)
5203 (string-append "mirror://sourceforge/samtools/samtools/"
5204 version "/samtools-" version ".tar.bz2"))
5206 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5208 `(#:tests? #f ;no "check" target
5210 (list "LIBCURSES=-lncurses")
5211 ,@(substitute-keyword-arguments (package-arguments samtools)
5213 `(modify-phases ,phases
5215 (lambda* (#:key outputs #:allow-other-keys)
5216 (let ((bin (string-append
5217 (assoc-ref outputs "out") "/bin")))
5219 (install-file "samtools" bin)
5221 (delete 'patch-tests)
5222 (delete 'configure))))))))
5224 (define-public mosaik
5225 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5230 ;; There are no release tarballs nor tags.
5233 (url "https://github.com/wanpinglee/MOSAIK.git")
5235 (file-name (string-append name "-" version))
5238 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5239 (build-system gnu-build-system)
5241 `(#:tests? #f ; no tests
5242 #:make-flags (list "CC=gcc")
5244 (modify-phases %standard-phases
5246 (lambda _ (chdir "src") #t))
5248 (lambda* (#:key outputs #:allow-other-keys)
5249 (let ((bin (string-append (assoc-ref outputs "out")
5252 (copy-recursively "../bin" bin)
5256 ("zlib:static" ,zlib "static")
5258 (supported-systems '("x86_64-linux"))
5259 (home-page "https://github.com/wanpinglee/MOSAIK")
5260 (synopsis "Map nucleotide sequence reads to reference genomes")
5262 "MOSAIK is a program for mapping second and third-generation sequencing
5263 reads to a reference genome. MOSAIK can align reads generated by all the
5264 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5265 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5266 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5267 ;; code released into the public domain:
5268 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5269 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5270 (license (list license:gpl2+ license:public-domain)))))
5272 (define-public ngs-sdk
5279 (url "https://github.com/ncbi/ngs.git")
5281 (file-name (git-file-name name version))
5284 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5285 (build-system gnu-build-system)
5287 `(#:parallel-build? #f ; not supported
5288 #:tests? #f ; no "check" target
5290 (modify-phases %standard-phases
5292 (lambda* (#:key outputs #:allow-other-keys)
5293 (let ((out (assoc-ref outputs "out")))
5294 ;; Allow 'konfigure.perl' to find 'package.prl'.
5296 (string-append ".:" (getenv "PERL5LIB")))
5298 ;; The 'configure' script doesn't recognize things like
5299 ;; '--enable-fast-install'.
5300 (invoke "./configure"
5301 (string-append "--build-prefix=" (getcwd) "/build")
5302 (string-append "--prefix=" out))
5304 (add-after 'unpack 'enter-dir
5305 (lambda _ (chdir "ngs-sdk") #t)))))
5306 (native-inputs `(("perl" ,perl)))
5307 ;; According to the test
5308 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5309 ;; in ngs-sdk/setup/konfigure.perl
5310 (supported-systems '("i686-linux" "x86_64-linux"))
5311 (home-page "https://github.com/ncbi/ngs")
5312 (synopsis "API for accessing Next Generation Sequencing data")
5314 "NGS is a domain-specific API for accessing reads, alignments and pileups
5315 produced from Next Generation Sequencing. The API itself is independent from
5316 any particular back-end implementation, and supports use of multiple back-ends
5318 (license license:public-domain)))
5320 (define-public java-ngs
5321 (package (inherit ngs-sdk)
5324 `(,@(substitute-keyword-arguments
5325 `(#:modules ((guix build gnu-build-system)
5329 ,@(package-arguments ngs-sdk))
5331 `(modify-phases ,phases
5332 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5334 `(("jdk" ,icedtea "jdk")
5335 ("ngs-sdk" ,ngs-sdk)))
5336 (synopsis "Java bindings for NGS SDK")))
5338 (define-public ncbi-vdb
5345 (url "https://github.com/ncbi/ncbi-vdb.git")
5347 (file-name (git-file-name name version))
5350 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5351 (build-system gnu-build-system)
5353 `(#:parallel-build? #f ; not supported
5354 #:tests? #f ; no "check" target
5356 (modify-phases %standard-phases
5357 (add-after 'unpack 'make-files-writable
5358 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5359 (add-before 'configure 'set-perl-search-path
5361 ;; Work around "dotless @INC" build failure.
5363 (string-append (getcwd) "/setup:"
5364 (getenv "PERL5LIB")))
5367 (lambda* (#:key inputs outputs #:allow-other-keys)
5368 (let ((out (assoc-ref outputs "out")))
5369 ;; Override include path for libmagic
5370 (substitute* "setup/package.prl"
5371 (("name => 'magic', Include => '/usr/include'")
5372 (string-append "name=> 'magic', Include => '"
5373 (assoc-ref inputs "libmagic")
5376 ;; Install kdf5 library (needed by sra-tools)
5377 (substitute* "build/Makefile.install"
5378 (("LIBRARIES_TO_INSTALL =")
5379 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5381 (substitute* "build/Makefile.env"
5382 (("CFLAGS =" prefix)
5383 (string-append prefix "-msse2 ")))
5385 ;; Override search path for ngs-java
5386 (substitute* "setup/package.prl"
5387 (("/usr/local/ngs/ngs-java")
5388 (assoc-ref inputs "java-ngs")))
5390 ;; The 'configure' script doesn't recognize things like
5391 ;; '--enable-fast-install'.
5392 (invoke "./configure"
5393 (string-append "--build-prefix=" (getcwd) "/build")
5394 (string-append "--prefix=" (assoc-ref outputs "out"))
5395 (string-append "--debug")
5396 (string-append "--with-xml2-prefix="
5397 (assoc-ref inputs "libxml2"))
5398 (string-append "--with-ngs-sdk-prefix="
5399 (assoc-ref inputs "ngs-sdk"))
5400 (string-append "--with-hdf5-prefix="
5401 (assoc-ref inputs "hdf5")))
5403 (add-after 'install 'install-interfaces
5404 (lambda* (#:key outputs #:allow-other-keys)
5405 ;; Install interface libraries. On i686 the interface libraries
5406 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5407 ;; architecture name ("i386") instead of the target system prefix
5409 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5410 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5411 ,(system->linux-architecture
5412 (or (%current-target-system)
5415 (string-append (assoc-ref outputs "out")
5417 ;; Install interface headers
5418 (copy-recursively "interfaces"
5419 (string-append (assoc-ref outputs "out")
5422 ;; These files are needed by sra-tools.
5423 (add-after 'install 'install-configuration-files
5424 (lambda* (#:key outputs #:allow-other-keys)
5425 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5427 (install-file "libs/kfg/default.kfg" target)
5428 (install-file "libs/kfg/certs.kfg" target))
5431 `(("libxml2" ,libxml2)
5432 ("ngs-sdk" ,ngs-sdk)
5433 ("java-ngs" ,java-ngs)
5436 (native-inputs `(("perl" ,perl)))
5437 ;; NCBI-VDB requires SSE capability.
5438 (supported-systems '("i686-linux" "x86_64-linux"))
5439 (home-page "https://github.com/ncbi/ncbi-vdb")
5440 (synopsis "Database engine for genetic information")
5442 "The NCBI-VDB library implements a highly compressed columnar data
5443 warehousing engine that is most often used to store genetic information.
5444 Databases are stored in a portable image within the file system, and can be
5445 accessed/downloaded on demand across HTTP.")
5446 (license license:public-domain)))
5448 (define-public plink
5456 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5457 version "-src.zip"))
5459 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5460 (patches (search-patches "plink-1.07-unclobber-i.patch"
5461 "plink-endian-detection.patch"))))
5462 (build-system gnu-build-system)
5464 '(#:tests? #f ;no "check" target
5465 #:make-flags (list (string-append "LIB_LAPACK="
5466 (assoc-ref %build-inputs "lapack")
5467 "/lib/liblapack.so")
5470 ;; disable phoning home
5473 (modify-phases %standard-phases
5474 ;; no "configure" script
5477 (lambda* (#:key outputs #:allow-other-keys)
5478 (let ((bin (string-append (assoc-ref outputs "out")
5480 (install-file "plink" bin)
5484 ("lapack" ,lapack)))
5486 `(("unzip" ,unzip)))
5487 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5488 (synopsis "Whole genome association analysis toolset")
5490 "PLINK is a whole genome association analysis toolset, designed to
5491 perform a range of basic, large-scale analyses in a computationally efficient
5492 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5493 so there is no support for steps prior to this (e.g. study design and
5494 planning, generating genotype or CNV calls from raw data). Through
5495 integration with gPLINK and Haploview, there is some support for the
5496 subsequent visualization, annotation and storage of results.")
5497 ;; Code is released under GPLv2, except for fisher.h, which is under
5499 (license (list license:gpl2 license:lgpl2.1+))))
5501 (define-public plink-ng
5502 (package (inherit plink)
5509 (url "https://github.com/chrchang/plink-ng.git")
5510 (commit (string-append "v" version))))
5511 (file-name (git-file-name name version))
5513 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5514 (build-system gnu-build-system)
5516 '(#:tests? #f ;no "check" target
5517 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5518 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5520 "-f" "Makefile.std")
5522 (modify-phases %standard-phases
5523 (add-after 'unpack 'chdir
5524 (lambda _ (chdir "1.9") #t))
5525 (delete 'configure) ; no "configure" script
5527 (lambda* (#:key outputs #:allow-other-keys)
5528 (let ((bin (string-append (assoc-ref outputs "out")
5530 (install-file "plink" bin)
5535 ("openblas" ,openblas)))
5536 (home-page "https://www.cog-genomics.org/plink/")
5537 (license license:gpl3+)))
5539 (define-public smithlab-cpp
5540 (let ((revision "1")
5541 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5543 (name "smithlab-cpp")
5544 (version (string-append "0." revision "." (string-take commit 7)))
5548 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5550 (file-name (string-append name "-" version "-checkout"))
5553 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5554 (build-system gnu-build-system)
5556 `(#:modules ((guix build gnu-build-system)
5559 #:tests? #f ;no "check" target
5561 (modify-phases %standard-phases
5562 (add-after 'unpack 'use-samtools-headers
5564 (substitute* '("SAM.cpp"
5566 (("sam.h") "samtools/sam.h"))
5569 (lambda* (#:key outputs #:allow-other-keys)
5570 (let* ((out (assoc-ref outputs "out"))
5571 (lib (string-append out "/lib"))
5572 (include (string-append out "/include/smithlab-cpp")))
5575 (for-each (cut install-file <> lib)
5576 (find-files "." "\\.o$"))
5577 (for-each (cut install-file <> include)
5578 (find-files "." "\\.hpp$")))
5580 (delete 'configure))))
5582 `(("samtools" ,samtools-0.1)
5584 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5585 (synopsis "C++ helper library for functions used in Smith lab projects")
5587 "Smithlab CPP is a C++ library that includes functions used in many of
5588 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5589 structures, classes for genomic regions, mapped sequencing reads, etc.")
5590 (license license:gpl3+))))
5592 (define-public preseq
5598 (uri (string-append "https://github.com/smithlabcode/preseq/"
5599 "releases/download/v" version
5600 "/preseq_v" version ".tar.bz2"))
5602 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5603 (modules '((guix build utils)))
5605 ;; Remove bundled samtools.
5606 (delete-file-recursively "samtools")
5608 (build-system gnu-build-system)
5610 `(#:tests? #f ;no "check" target
5612 (modify-phases %standard-phases
5613 (delete 'configure))
5615 (list (string-append "PREFIX="
5616 (assoc-ref %outputs "out"))
5617 (string-append "LIBBAM="
5618 (assoc-ref %build-inputs "samtools")
5620 (string-append "SMITHLAB_CPP="
5621 (assoc-ref %build-inputs "smithlab-cpp")
5624 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5627 ("samtools" ,samtools-0.1)
5628 ("smithlab-cpp" ,smithlab-cpp)
5630 (home-page "http://smithlabresearch.org/software/preseq/")
5631 (synopsis "Program for analyzing library complexity")
5633 "The preseq package is aimed at predicting and estimating the complexity
5634 of a genomic sequencing library, equivalent to predicting and estimating the
5635 number of redundant reads from a given sequencing depth and how many will be
5636 expected from additional sequencing using an initial sequencing experiment.
5637 The estimates can then be used to examine the utility of further sequencing,
5638 optimize the sequencing depth, or to screen multiple libraries to avoid low
5639 complexity samples.")
5640 (license license:gpl3+)))
5642 (define-public python-screed
5644 (name "python-screed")
5649 (uri (pypi-uri "screed" version))
5652 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5653 (build-system python-build-system)
5656 (modify-phases %standard-phases
5657 ;; Tests must be run after installation, as the "screed" command does
5658 ;; not exist right after building.
5660 (add-after 'install 'check
5661 (lambda* (#:key inputs outputs #:allow-other-keys)
5662 (let ((out (assoc-ref outputs "out")))
5663 (setenv "PYTHONPATH"
5664 (string-append out "/lib/python"
5665 (string-take (string-take-right
5666 (assoc-ref inputs "python")
5669 (getenv "PYTHONPATH")))
5670 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5671 (invoke "python" "setup.py" "test")
5674 `(("python-pytest" ,python-pytest)
5675 ("python-pytest-cov" ,python-pytest-cov)
5676 ("python-pytest-runner" ,python-pytest-runner)))
5678 `(("python-bz2file" ,python-bz2file)))
5679 (home-page "https://github.com/dib-lab/screed/")
5680 (synopsis "Short read sequence database utilities")
5681 (description "Screed parses FASTA and FASTQ files and generates databases.
5682 Values such as sequence name, sequence description, sequence quality and the
5683 sequence itself can be retrieved from these databases.")
5684 (license license:bsd-3)))
5686 (define-public python2-screed
5687 (package-with-python2 python-screed))
5689 (define-public sra-tools
5697 (url "https://github.com/ncbi/sra-tools.git")
5699 (file-name (git-file-name name version))
5702 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5703 (build-system gnu-build-system)
5705 `(#:parallel-build? #f ; not supported
5706 #:tests? #f ; no "check" target
5708 (list (string-append "DEFAULT_CRT="
5709 (assoc-ref %build-inputs "ncbi-vdb")
5711 (string-append "DEFAULT_KFG="
5712 (assoc-ref %build-inputs "ncbi-vdb")
5714 (string-append "VDB_LIBDIR="
5715 (assoc-ref %build-inputs "ncbi-vdb")
5716 ,(if (string-prefix? "x86_64"
5717 (or (%current-target-system)
5722 (modify-phases %standard-phases
5723 (add-before 'configure 'set-perl-search-path
5725 ;; Work around "dotless @INC" build failure.
5727 (string-append (getcwd) "/setup:"
5728 (getenv "PERL5LIB")))
5731 (lambda* (#:key inputs outputs #:allow-other-keys)
5732 ;; The build system expects a directory containing the sources and
5733 ;; raw build output of ncbi-vdb, including files that are not
5734 ;; installed. Since we are building against an installed version of
5735 ;; ncbi-vdb, the following modifications are needed.
5736 (substitute* "setup/konfigure.perl"
5737 ;; Make the configure script look for the "ilib" directory of
5738 ;; "ncbi-vdb" without first checking for the existence of a
5739 ;; matching library in its "lib" directory.
5740 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5741 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5742 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5743 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5744 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5747 (substitute* "tools/copycat/Makefile"
5748 (("smagic-static") "lmagic"))
5750 ;; The 'configure' script doesn't recognize things like
5751 ;; '--enable-fast-install'.
5752 (invoke "./configure"
5753 (string-append "--build-prefix=" (getcwd) "/build")
5754 (string-append "--prefix=" (assoc-ref outputs "out"))
5755 (string-append "--debug")
5756 (string-append "--with-fuse-prefix="
5757 (assoc-ref inputs "fuse"))
5758 (string-append "--with-magic-prefix="
5759 (assoc-ref inputs "libmagic"))
5760 ;; TODO: building with libxml2 fails with linker errors
5761 ;; (string-append "--with-xml2-prefix="
5762 ;; (assoc-ref inputs "libxml2"))
5763 (string-append "--with-ncbi-vdb-sources="
5764 (assoc-ref inputs "ncbi-vdb"))
5765 (string-append "--with-ncbi-vdb-build="
5766 (assoc-ref inputs "ncbi-vdb"))
5767 (string-append "--with-ngs-sdk-prefix="
5768 (assoc-ref inputs "ngs-sdk"))
5769 (string-append "--with-hdf5-prefix="
5770 (assoc-ref inputs "hdf5")))
5772 (native-inputs `(("perl" ,perl)))
5774 `(("ngs-sdk" ,ngs-sdk)
5775 ("ncbi-vdb" ,ncbi-vdb)
5780 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5781 (synopsis "Tools and libraries for reading and writing sequencing data")
5783 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5784 reading of sequencing files from the Sequence Read Archive (SRA) database and
5785 writing files into the .sra format.")
5786 (license license:public-domain)))
5788 (define-public seqan
5794 (uri (string-append "https://github.com/seqan/seqan/releases/"
5795 "download/seqan-v" version
5796 "/seqan-library-" version ".tar.xz"))
5799 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5800 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5801 ;; makes sense to split the outputs.
5802 (outputs '("out" "doc"))
5803 (build-system trivial-build-system)
5805 `(#:modules ((guix build utils))
5808 (use-modules (guix build utils))
5809 (let ((tar (assoc-ref %build-inputs "tar"))
5810 (xz (assoc-ref %build-inputs "xz"))
5811 (out (assoc-ref %outputs "out"))
5812 (doc (assoc-ref %outputs "doc")))
5813 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5814 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5815 (chdir (string-append "seqan-library-" ,version))
5816 (copy-recursively "include" (string-append out "/include"))
5817 (copy-recursively "share" (string-append doc "/share"))
5820 `(("source" ,source)
5823 (home-page "http://www.seqan.de")
5824 (synopsis "Library for nucleotide sequence analysis")
5826 "SeqAn is a C++ library of efficient algorithms and data structures for
5827 the analysis of sequences with the focus on biological data. It contains
5828 algorithms and data structures for string representation and their
5829 manipulation, online and indexed string search, efficient I/O of
5830 bioinformatics file formats, sequence alignment, and more.")
5831 (license license:bsd-3)))
5833 (define-public seqan-1
5834 (package (inherit seqan)
5839 (uri (string-append "http://packages.seqan.de/seqan-library/"
5840 "seqan-library-" version ".tar.bz2"))
5843 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5844 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5845 ;; makes sense to split the outputs.
5846 (outputs '("out" "doc"))
5847 (build-system trivial-build-system)
5849 `(#:modules ((guix build utils))
5852 (use-modules (guix build utils))
5853 (let ((tar (assoc-ref %build-inputs "tar"))
5854 (bzip (assoc-ref %build-inputs "bzip2"))
5855 (out (assoc-ref %outputs "out"))
5856 (doc (assoc-ref %outputs "doc")))
5857 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5858 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5859 (chdir (string-append "seqan-library-" ,version))
5860 (copy-recursively "include" (string-append out "/include"))
5861 (copy-recursively "share" (string-append doc "/share"))
5864 `(("source" ,source)
5866 ("bzip2" ,bzip2)))))
5868 (define-public seqmagick
5875 (uri (pypi-uri "seqmagick" version))
5878 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5879 (build-system python-build-system)
5881 `(("python-biopython" ,python-biopython)))
5883 `(("python-nose" ,python-nose)))
5884 (home-page "https://github.com/fhcrc/seqmagick")
5885 (synopsis "Tools for converting and modifying sequence files")
5887 "Bioinformaticians often have to convert sequence files between formats
5888 and do little manipulations on them, and it's not worth writing scripts for
5889 that. Seqmagick is a utility to expose the file format conversion in
5890 BioPython in a convenient way. Instead of having a big mess of scripts, there
5891 is one that takes arguments.")
5892 (license license:gpl3)))
5894 (define-public seqtk
5901 (url "https://github.com/lh3/seqtk.git")
5902 (commit (string-append "v" version))))
5903 (file-name (git-file-name name version))
5906 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5907 (build-system gnu-build-system)
5910 (modify-phases %standard-phases
5913 ;; There are no tests, so we just run a sanity check.
5914 (lambda _ (invoke "./seqtk" "seq") #t))
5916 (lambda* (#:key outputs #:allow-other-keys)
5917 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5918 (install-file "seqtk" bin)
5922 (home-page "https://github.com/lh3/seqtk")
5923 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5925 "Seqtk is a fast and lightweight tool for processing sequences in the
5926 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5927 optionally compressed by gzip.")
5928 (license license:expat)))
5930 (define-public snap-aligner
5932 (name "snap-aligner")
5933 (version "1.0beta.18")
5937 (url "https://github.com/amplab/snap.git")
5938 (commit (string-append "v" version))))
5939 (file-name (git-file-name name version))
5942 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5943 (build-system gnu-build-system)
5946 (modify-phases %standard-phases
5948 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5950 (lambda* (#:key outputs #:allow-other-keys)
5951 (let* ((out (assoc-ref outputs "out"))
5952 (bin (string-append out "/bin")))
5953 (install-file "snap-aligner" bin)
5954 (install-file "SNAPCommand" bin)
5958 (home-page "http://snap.cs.berkeley.edu/")
5959 (synopsis "Short read DNA sequence aligner")
5961 "SNAP is a fast and accurate aligner for short DNA reads. It is
5962 optimized for modern read lengths of 100 bases or higher, and takes advantage
5963 of these reads to align data quickly through a hash-based indexing scheme.")
5964 ;; 32-bit systems are not supported by the unpatched code.
5965 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5966 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5967 ;; systems without a lot of memory cannot make good use of this program.
5968 (supported-systems '("x86_64-linux"))
5969 (license license:asl2.0)))
5971 (define-public sortmerna
5979 (url "https://github.com/biocore/sortmerna.git")
5981 (file-name (git-file-name name version))
5984 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5985 (build-system gnu-build-system)
5986 (outputs '("out" ;for binaries
5987 "db")) ;for sequence databases
5990 (modify-phases %standard-phases
5992 (lambda* (#:key outputs #:allow-other-keys)
5993 (let* ((out (assoc-ref outputs "out"))
5994 (bin (string-append out "/bin"))
5995 (db (assoc-ref outputs "db"))
5997 (string-append db "/share/sortmerna/rRNA_databases")))
5998 (install-file "sortmerna" bin)
5999 (install-file "indexdb_rna" bin)
6000 (for-each (lambda (file)
6001 (install-file file share))
6002 (find-files "rRNA_databases" ".*fasta"))
6006 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6007 (synopsis "Biological sequence analysis tool for NGS reads")
6009 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6010 and operational taxonomic unit (OTU) picking of next generation
6011 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6012 allows for fast and sensitive analyses of nucleotide sequences. The main
6013 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6014 ;; The source includes x86 specific code
6015 (supported-systems '("x86_64-linux" "i686-linux"))
6016 (license license:lgpl3)))
6025 (url "https://github.com/alexdobin/STAR.git")
6027 (file-name (string-append name "-" version "-checkout"))
6030 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
6031 (modules '((guix build utils)))
6034 (substitute* "source/Makefile"
6036 ;; Remove pre-built binaries and bundled htslib sources.
6037 (delete-file-recursively "bin/MacOSX_x86_64")
6038 (delete-file-recursively "bin/Linux_x86_64")
6039 (delete-file-recursively "bin/Linux_x86_64_static")
6040 (delete-file-recursively "source/htslib")
6042 (build-system gnu-build-system)
6044 '(#:tests? #f ;no check target
6045 #:make-flags '("STAR")
6047 (modify-phases %standard-phases
6048 (add-after 'unpack 'enter-source-dir
6049 (lambda _ (chdir "source") #t))
6050 (add-after 'enter-source-dir 'make-reproducible
6052 (substitute* "Makefile"
6053 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6054 (string-append pre "Built with Guix" post)))
6056 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6058 (substitute* "Makefile"
6059 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6061 (substitute* '("BAMfunctions.cpp"
6066 "bamRemoveDuplicates.cpp")
6067 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6068 (string-append "#include <" header ">")))
6069 (substitute* "IncludeDefine.h"
6070 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6071 (string-append "<" header ">")))
6074 (lambda* (#:key outputs #:allow-other-keys)
6075 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6076 (install-file "STAR" bin))
6078 (delete 'configure))))
6082 `(("htslib" ,htslib)
6084 (home-page "https://github.com/alexdobin/STAR")
6085 (synopsis "Universal RNA-seq aligner")
6087 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6088 based on a previously undescribed RNA-seq alignment algorithm that uses
6089 sequential maximum mappable seed search in uncompressed suffix arrays followed
6090 by seed clustering and stitching procedure. In addition to unbiased de novo
6091 detection of canonical junctions, STAR can discover non-canonical splices and
6092 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6094 ;; Only 64-bit systems are supported according to the README.
6095 (supported-systems '("x86_64-linux" "mips64el-linux"))
6096 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6097 (license license:gpl3+)))
6099 (define-public subread
6105 (uri (string-append "mirror://sourceforge/subread/subread-"
6106 version "/subread-" version "-source.tar.gz"))
6109 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6110 (build-system gnu-build-system)
6112 `(#:tests? #f ;no "check" target
6113 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6114 ;; optimizations by default, so we override these flags such that x86_64
6115 ;; flags are only added when the build target is an x86_64 system.
6117 (list (let ((system ,(or (%current-target-system)
6119 (flags '("-ggdb" "-fomit-frame-pointer"
6120 "-ffast-math" "-funroll-loops"
6121 "-fmessage-length=0"
6122 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6124 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6125 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6126 (if (string-prefix? "x86_64" system)
6127 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6128 (string-append "CCFLAGS=" (string-join flags))))
6129 "-f" "Makefile.Linux"
6130 "CC=gcc ${CCFLAGS}")
6132 (modify-phases %standard-phases
6133 (add-after 'unpack 'enter-dir
6134 (lambda _ (chdir "src") #t))
6136 (lambda* (#:key outputs #:allow-other-keys)
6137 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6139 (copy-recursively "../bin" bin))
6141 ;; no "configure" script
6142 (delete 'configure))))
6143 (inputs `(("zlib" ,zlib)))
6144 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6145 (synopsis "Tool kit for processing next-gen sequencing data")
6147 "The subread package contains the following tools: subread aligner, a
6148 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6149 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6150 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6151 against local background noises.")
6152 (license license:gpl3+)))
6154 (define-public stringtie
6160 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6161 "stringtie-" version ".tar.gz"))
6164 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6165 (modules '((guix build utils)))
6168 (delete-file-recursively "samtools-0.1.18")
6170 (build-system gnu-build-system)
6172 `(#:tests? #f ;no test suite
6174 (modify-phases %standard-phases
6175 ;; no configure script
6177 (add-before 'build 'use-system-samtools
6179 (substitute* "Makefile"
6180 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6182 (substitute* '("gclib/GBam.h"
6184 (("#include \"(bam|sam|kstring).h\"" _ header)
6185 (string-append "#include <samtools/" header ".h>")))
6187 (add-after 'unpack 'remove-duplicate-typedef
6189 ;; This typedef conflicts with the typedef in
6190 ;; glibc-2.25/include/bits/types.h
6191 (substitute* "gclib/GThreads.h"
6192 (("typedef long long __intmax_t;") ""))
6195 (lambda* (#:key outputs #:allow-other-keys)
6196 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6197 (install-file "stringtie" bin)
6200 `(("samtools" ,samtools-0.1)
6202 (home-page "http://ccb.jhu.edu/software/stringtie/")
6203 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6205 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6206 alignments into potential transcripts. It uses a novel network flow algorithm
6207 as well as an optional de novo assembly step to assemble and quantitate
6208 full-length transcripts representing multiple splice variants for each gene
6209 locus. Its input can include not only the alignments of raw reads used by
6210 other transcript assemblers, but also alignments of longer sequences that have
6211 been assembled from those reads. To identify differentially expressed genes
6212 between experiments, StringTie's output can be processed either by the
6213 Cuffdiff or Ballgown programs.")
6214 (license license:artistic2.0)))
6216 (define-public taxtastic
6222 (uri (pypi-uri "taxtastic" version))
6225 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6226 (build-system python-build-system)
6228 `(#:python ,python-2
6230 (modify-phases %standard-phases
6232 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6234 `(("python-sqlalchemy" ,python2-sqlalchemy)
6235 ("python-decorator" ,python2-decorator)
6236 ("python-biopython" ,python2-biopython)
6237 ("python-pandas" ,python2-pandas)
6238 ("python-psycopg2" ,python2-psycopg2)
6239 ("python-fastalite" ,python2-fastalite)
6240 ("python-pyyaml" ,python2-pyyaml)
6241 ("python-six" ,python2-six)
6242 ("python-jinja2" ,python2-jinja2)
6243 ("python-dendropy" ,python2-dendropy)))
6244 (home-page "https://github.com/fhcrc/taxtastic")
6245 (synopsis "Tools for taxonomic naming and annotation")
6247 "Taxtastic is software written in python used to build and maintain
6248 reference packages i.e. collections of reference trees, reference alignments,
6249 profiles, and associated taxonomic information.")
6250 (license license:gpl3+)))
6252 (define-public vcftools
6259 "https://github.com/vcftools/vcftools/releases/download/v"
6260 version "/vcftools-" version ".tar.gz"))
6263 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6264 (build-system gnu-build-system)
6266 `(#:tests? #f ; no "check" target
6268 "CFLAGS=-O2" ; override "-m64" flag
6269 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6270 (string-append "MANDIR=" (assoc-ref %outputs "out")
6271 "/share/man/man1"))))
6273 `(("pkg-config" ,pkg-config)))
6277 (home-page "https://vcftools.github.io/")
6278 (synopsis "Tools for working with VCF files")
6280 "VCFtools is a program package designed for working with VCF files, such
6281 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6282 provide easily accessible methods for working with complex genetic variation
6283 data in the form of VCF files.")
6284 ;; The license is declared as LGPLv3 in the README and
6285 ;; at https://vcftools.github.io/license.html
6286 (license license:lgpl3)))
6288 (define-public infernal
6294 (uri (string-append "http://eddylab.org/software/infernal/"
6295 "infernal-" version ".tar.gz"))
6298 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6299 (build-system gnu-build-system)
6301 `(("perl" ,perl))) ; for tests
6302 (home-page "http://eddylab.org/infernal/")
6303 (synopsis "Inference of RNA alignments")
6304 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6305 searching DNA sequence databases for RNA structure and sequence similarities.
6306 It is an implementation of a special case of profile stochastic context-free
6307 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6308 profile, but it scores a combination of sequence consensus and RNA secondary
6309 structure consensus, so in many cases, it is more capable of identifying RNA
6310 homologs that conserve their secondary structure more than their primary
6312 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6313 (supported-systems '("i686-linux" "x86_64-linux"))
6314 (license license:bsd-3)))
6316 (define-public r-centipede
6318 (name "r-centipede")
6322 (uri (string-append "http://download.r-forge.r-project.org/"
6323 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6326 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6327 (build-system r-build-system)
6328 (home-page "http://centipede.uchicago.edu/")
6329 (synopsis "Predict transcription factor binding sites")
6331 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6332 of the genome that are bound by particular transcription factors. It starts
6333 by identifying a set of candidate binding sites, and then aims to classify the
6334 sites according to whether each site is bound or not bound by a transcription
6335 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6336 between two different types of motif instances using as much relevant
6337 information as possible.")
6338 (license (list license:gpl2+ license:gpl3+))))
6340 (define-public r-vegan
6347 (uri (cran-uri "vegan" version))
6350 "023xznh0iy0496icpchadmp7a3rk3nj9s48fvwlvp3dssw58yp3c"))))
6351 (build-system r-build-system)
6353 `(("gfortran" ,gfortran)))
6355 `(("r-cluster" ,r-cluster)
6356 ("r-knitr" ,r-knitr) ; needed for vignettes
6357 ("r-lattice" ,r-lattice)
6360 ("r-permute" ,r-permute)))
6361 (home-page "https://cran.r-project.org/web/packages/vegan")
6362 (synopsis "Functions for community ecology")
6364 "The vegan package provides tools for descriptive community ecology. It
6365 has most basic functions of diversity analysis, community ordination and
6366 dissimilarity analysis. Most of its multivariate tools can be used for other
6367 data types as well.")
6368 (license license:gpl2+)))
6370 (define-public r-annotate
6377 (uri (bioconductor-uri "annotate" version))
6380 "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
6381 (build-system r-build-system)
6383 `(("r-annotationdbi" ,r-annotationdbi)
6384 ("r-biobase" ,r-biobase)
6385 ("r-biocgenerics" ,r-biocgenerics)
6387 ("r-rcurl" ,r-rcurl)
6389 ("r-xtable" ,r-xtable)))
6391 "https://bioconductor.org/packages/annotate")
6392 (synopsis "Annotation for microarrays")
6393 (description "This package provides R environments for the annotation of
6395 (license license:artistic2.0)))
6397 (define-public r-copynumber
6399 (name "r-copynumber")
6403 (uri (bioconductor-uri "copynumber" version))
6406 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6407 (build-system r-build-system)
6409 `(("r-s4vectors" ,r-s4vectors)
6410 ("r-iranges" ,r-iranges)
6411 ("r-genomicranges" ,r-genomicranges)
6412 ("r-biocgenerics" ,r-biocgenerics)))
6413 (home-page "https://bioconductor.org/packages/copynumber")
6414 (synopsis "Segmentation of single- and multi-track copy number data")
6416 "This package segments single- and multi-track copy number data by a
6417 penalized least squares regression method.")
6418 (license license:artistic2.0)))
6420 (define-public r-geneplotter
6422 (name "r-geneplotter")
6427 (uri (bioconductor-uri "geneplotter" version))
6430 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6431 (build-system r-build-system)
6433 `(("r-annotate" ,r-annotate)
6434 ("r-annotationdbi" ,r-annotationdbi)
6435 ("r-biobase" ,r-biobase)
6436 ("r-biocgenerics" ,r-biocgenerics)
6437 ("r-lattice" ,r-lattice)
6438 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6439 (home-page "https://bioconductor.org/packages/geneplotter")
6440 (synopsis "Graphics functions for genomic data")
6442 "This package provides functions for plotting genomic data.")
6443 (license license:artistic2.0)))
6445 (define-public r-genefilter
6447 (name "r-genefilter")
6452 (uri (bioconductor-uri "genefilter" version))
6455 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6456 (build-system r-build-system)
6458 `(("gfortran" ,gfortran)))
6460 `(("r-annotate" ,r-annotate)
6461 ("r-annotationdbi" ,r-annotationdbi)
6462 ("r-biobase" ,r-biobase)
6463 ("r-s4vectors" ,r-s4vectors)
6464 ("r-survival" ,r-survival)))
6465 (home-page "https://bioconductor.org/packages/genefilter")
6466 (synopsis "Filter genes from high-throughput experiments")
6468 "This package provides basic functions for filtering genes from
6469 high-throughput sequencing experiments.")
6470 (license license:artistic2.0)))
6472 (define-public r-deseq2
6479 (uri (bioconductor-uri "DESeq2" version))
6482 "1b2bmvcsfzvks47d7w46zplcwz0kgcdhx5xmx3x9lp2gvx2p84r5"))))
6483 (properties `((upstream-name . "DESeq2")))
6484 (build-system r-build-system)
6486 `(("r-biobase" ,r-biobase)
6487 ("r-biocgenerics" ,r-biocgenerics)
6488 ("r-biocparallel" ,r-biocparallel)
6489 ("r-genefilter" ,r-genefilter)
6490 ("r-geneplotter" ,r-geneplotter)
6491 ("r-genomicranges" ,r-genomicranges)
6492 ("r-ggplot2" ,r-ggplot2)
6493 ("r-hmisc" ,r-hmisc)
6494 ("r-iranges" ,r-iranges)
6495 ("r-locfit" ,r-locfit)
6497 ("r-rcpparmadillo" ,r-rcpparmadillo)
6498 ("r-s4vectors" ,r-s4vectors)
6499 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6500 (home-page "https://bioconductor.org/packages/DESeq2")
6501 (synopsis "Differential gene expression analysis")
6503 "This package provides functions to estimate variance-mean dependence in
6504 count data from high-throughput nucleotide sequencing assays and test for
6505 differential expression based on a model using the negative binomial
6507 (license license:lgpl3+)))
6509 (define-public r-dexseq
6516 (uri (bioconductor-uri "DEXSeq" version))
6519 "0jh1640cnzpk8x3155cqc8dvrs1rciw3d6nv2k70baw96bhrynp8"))))
6520 (properties `((upstream-name . "DEXSeq")))
6521 (build-system r-build-system)
6523 `(("r-annotationdbi" ,r-annotationdbi)
6524 ("r-biobase" ,r-biobase)
6525 ("r-biocgenerics" ,r-biocgenerics)
6526 ("r-biocparallel" ,r-biocparallel)
6527 ("r-biomart" ,r-biomart)
6528 ("r-deseq2" ,r-deseq2)
6529 ("r-genefilter" ,r-genefilter)
6530 ("r-geneplotter" ,r-geneplotter)
6531 ("r-genomicranges" ,r-genomicranges)
6532 ("r-hwriter" ,r-hwriter)
6533 ("r-iranges" ,r-iranges)
6534 ("r-rcolorbrewer" ,r-rcolorbrewer)
6535 ("r-rsamtools" ,r-rsamtools)
6536 ("r-s4vectors" ,r-s4vectors)
6537 ("r-statmod" ,r-statmod)
6538 ("r-stringr" ,r-stringr)
6539 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6540 (home-page "https://bioconductor.org/packages/DEXSeq")
6541 (synopsis "Inference of differential exon usage in RNA-Seq")
6543 "This package is focused on finding differential exon usage using RNA-seq
6544 exon counts between samples with different experimental designs. It provides
6545 functions that allows the user to make the necessary statistical tests based
6546 on a model that uses the negative binomial distribution to estimate the
6547 variance between biological replicates and generalized linear models for
6548 testing. The package also provides functions for the visualization and
6549 exploration of the results.")
6550 (license license:gpl3+)))
6552 (define-public r-annotationforge
6554 (name "r-annotationforge")
6559 (uri (bioconductor-uri "AnnotationForge" version))
6562 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6564 `((upstream-name . "AnnotationForge")))
6565 (build-system r-build-system)
6567 `(("r-annotationdbi" ,r-annotationdbi)
6568 ("r-biobase" ,r-biobase)
6569 ("r-biocgenerics" ,r-biocgenerics)
6571 ("r-rcurl" ,r-rcurl)
6572 ("r-rsqlite" ,r-rsqlite)
6573 ("r-s4vectors" ,r-s4vectors)
6575 (home-page "https://bioconductor.org/packages/AnnotationForge")
6576 (synopsis "Code for building annotation database packages")
6578 "This package provides code for generating Annotation packages and their
6579 databases. Packages produced are intended to be used with AnnotationDbi.")
6580 (license license:artistic2.0)))
6582 (define-public r-rbgl
6589 (uri (bioconductor-uri "RBGL" version))
6592 "0jy95m38c4qp0a12097hhm2gg63k96k6ydhb11dy379h3ziapcar"))))
6593 (properties `((upstream-name . "RBGL")))
6594 (build-system r-build-system)
6595 (propagated-inputs `(("r-graph" ,r-graph)))
6596 (home-page "https://www.bioconductor.org/packages/RBGL")
6597 (synopsis "Interface to the Boost graph library")
6599 "This package provides a fairly extensive and comprehensive interface to
6600 the graph algorithms contained in the Boost library.")
6601 (license license:artistic2.0)))
6603 (define-public r-gseabase
6610 (uri (bioconductor-uri "GSEABase" version))
6613 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6614 (properties `((upstream-name . "GSEABase")))
6615 (build-system r-build-system)
6617 `(("r-annotate" ,r-annotate)
6618 ("r-annotationdbi" ,r-annotationdbi)
6619 ("r-biobase" ,r-biobase)
6620 ("r-biocgenerics" ,r-biocgenerics)
6621 ("r-graph" ,r-graph)
6623 (home-page "https://bioconductor.org/packages/GSEABase")
6624 (synopsis "Gene set enrichment data structures and methods")
6626 "This package provides classes and methods to support @dfn{Gene Set
6627 Enrichment Analysis} (GSEA).")
6628 (license license:artistic2.0)))
6630 (define-public r-category
6637 (uri (bioconductor-uri "Category" version))
6640 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6641 (properties `((upstream-name . "Category")))
6642 (build-system r-build-system)
6644 `(("r-annotate" ,r-annotate)
6645 ("r-annotationdbi" ,r-annotationdbi)
6646 ("r-biobase" ,r-biobase)
6647 ("r-biocgenerics" ,r-biocgenerics)
6648 ("r-genefilter" ,r-genefilter)
6649 ("r-graph" ,r-graph)
6650 ("r-gseabase" ,r-gseabase)
6651 ("r-matrix" ,r-matrix)
6654 (home-page "https://bioconductor.org/packages/Category")
6655 (synopsis "Category analysis")
6657 "This package provides a collection of tools for performing category
6659 (license license:artistic2.0)))
6661 (define-public r-gostats
6668 (uri (bioconductor-uri "GOstats" version))
6671 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6672 (properties `((upstream-name . "GOstats")))
6673 (build-system r-build-system)
6675 `(("r-annotate" ,r-annotate)
6676 ("r-annotationdbi" ,r-annotationdbi)
6677 ("r-annotationforge" ,r-annotationforge)
6678 ("r-biobase" ,r-biobase)
6679 ("r-category" ,r-category)
6680 ("r-go-db" ,r-go-db)
6681 ("r-graph" ,r-graph)
6682 ("r-rgraphviz" ,r-rgraphviz)
6683 ("r-rbgl" ,r-rbgl)))
6684 (home-page "https://bioconductor.org/packages/GOstats")
6685 (synopsis "Tools for manipulating GO and microarrays")
6687 "This package provides a set of tools for interacting with GO and
6688 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6689 testing and other simple calculations.")
6690 (license license:artistic2.0)))
6692 (define-public r-shortread
6694 (name "r-shortread")
6699 (uri (bioconductor-uri "ShortRead" version))
6702 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6703 (properties `((upstream-name . "ShortRead")))
6704 (build-system r-build-system)
6708 `(("r-biobase" ,r-biobase)
6709 ("r-biocgenerics" ,r-biocgenerics)
6710 ("r-biocparallel" ,r-biocparallel)
6711 ("r-biostrings" ,r-biostrings)
6712 ("r-genomeinfodb" ,r-genomeinfodb)
6713 ("r-genomicalignments" ,r-genomicalignments)
6714 ("r-genomicranges" ,r-genomicranges)
6715 ("r-hwriter" ,r-hwriter)
6716 ("r-iranges" ,r-iranges)
6717 ("r-lattice" ,r-lattice)
6718 ("r-latticeextra" ,r-latticeextra)
6719 ("r-rsamtools" ,r-rsamtools)
6720 ("r-s4vectors" ,r-s4vectors)
6721 ("r-xvector" ,r-xvector)
6722 ("r-zlibbioc" ,r-zlibbioc)))
6723 (home-page "https://bioconductor.org/packages/ShortRead")
6724 (synopsis "FASTQ input and manipulation tools")
6726 "This package implements sampling, iteration, and input of FASTQ files.
6727 It includes functions for filtering and trimming reads, and for generating a
6728 quality assessment report. Data are represented as
6729 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6730 purposes. The package also contains legacy support for early single-end,
6731 ungapped alignment formats.")
6732 (license license:artistic2.0)))
6734 (define-public r-systempiper
6736 (name "r-systempiper")
6741 (uri (bioconductor-uri "systemPipeR" version))
6744 "0l26q8zjdmzg84g7f25gv9z60sykybahlpg5bg9bmpbg5lzcsx04"))))
6745 (properties `((upstream-name . "systemPipeR")))
6746 (build-system r-build-system)
6748 `(("r-annotate" ,r-annotate)
6749 ("r-batchjobs" ,r-batchjobs)
6750 ("r-biocgenerics" ,r-biocgenerics)
6751 ("r-biostrings" ,r-biostrings)
6752 ("r-deseq2" ,r-deseq2)
6753 ("r-edger" ,r-edger)
6754 ("r-genomicfeatures" ,r-genomicfeatures)
6755 ("r-genomicranges" ,r-genomicranges)
6756 ("r-ggplot2" ,r-ggplot2)
6757 ("r-go-db" ,r-go-db)
6758 ("r-gostats" ,r-gostats)
6759 ("r-limma" ,r-limma)
6760 ("r-pheatmap" ,r-pheatmap)
6761 ("r-rjson" ,r-rjson)
6762 ("r-rsamtools" ,r-rsamtools)
6763 ("r-shortread" ,r-shortread)
6764 ("r-summarizedexperiment" ,r-summarizedexperiment)
6765 ("r-variantannotation" ,r-variantannotation)))
6766 (home-page "https://github.com/tgirke/systemPipeR")
6767 (synopsis "Next generation sequencing workflow and reporting environment")
6769 "This R package provides tools for building and running automated
6770 end-to-end analysis workflows for a wide range of @dfn{next generation
6771 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6772 Important features include a uniform workflow interface across different NGS
6773 applications, automated report generation, and support for running both R and
6774 command-line software, such as NGS aligners or peak/variant callers, on local
6775 computers or compute clusters. Efficient handling of complex sample sets and
6776 experimental designs is facilitated by a consistently implemented sample
6777 annotation infrastructure.")
6778 (license license:artistic2.0)))
6780 (define-public r-grohmm
6787 (uri (bioconductor-uri "groHMM" version))
6790 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6791 (properties `((upstream-name . "groHMM")))
6792 (build-system r-build-system)
6794 `(("r-genomeinfodb" ,r-genomeinfodb)
6795 ("r-genomicalignments" ,r-genomicalignments)
6796 ("r-genomicranges" ,r-genomicranges)
6797 ("r-iranges" ,r-iranges)
6799 ("r-rtracklayer" ,r-rtracklayer)
6800 ("r-s4vectors" ,r-s4vectors)))
6801 (home-page "https://github.com/Kraus-Lab/groHMM")
6802 (synopsis "GRO-seq analysis pipeline")
6804 "This package provides a pipeline for the analysis of GRO-seq data.")
6805 (license license:gpl3+)))
6807 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6809 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6813 ;; We cannot use bioconductor-uri here because this tarball is
6814 ;; located under "data/annotation/" instead of "bioc/".
6815 (uri (string-append "https://bioconductor.org/packages/"
6816 "release/data/annotation/src/contrib"
6817 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6821 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6823 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6824 (build-system r-build-system)
6825 ;; As this package provides little more than a very large data file it
6826 ;; doesn't make sense to build substitutes.
6827 (arguments `(#:substitutable? #f))
6829 `(("r-genomicfeatures" ,r-genomicfeatures)))
6831 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6832 (synopsis "Annotation package for human genome in TxDb format")
6834 "This package provides an annotation database of Homo sapiens genome
6835 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6836 track. The database is exposed as a @code{TxDb} object.")
6837 (license license:artistic2.0)))
6839 (define-public r-sparql
6845 (uri (cran-uri "SPARQL" version))
6848 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6849 (properties `((upstream-name . "SPARQL")))
6850 (build-system r-build-system)
6852 `(("r-rcurl" ,r-rcurl)
6854 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6855 (synopsis "SPARQL client for R")
6856 (description "This package provides an interface to use SPARQL to pose
6857 SELECT or UPDATE queries to an end-point.")
6858 ;; The only license indication is found in the DESCRIPTION file,
6859 ;; which states GPL-3. So we cannot assume GPLv3+.
6860 (license license:gpl3)))
6862 (define-public vsearch
6870 (url "https://github.com/torognes/vsearch.git")
6871 (commit (string-append "v" version))))
6872 (file-name (git-file-name name version))
6875 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6876 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6879 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6880 ;; for this in the patch.
6881 (delete-file "src/city.h")
6882 (delete-file "src/citycrc.h")
6883 (delete-file "src/city.cc")
6885 (build-system gnu-build-system)
6889 ("cityhash" ,cityhash)))
6891 `(("autoconf" ,autoconf)
6892 ("automake" ,automake)))
6893 (synopsis "Sequence search tools for metagenomics")
6895 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6896 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6897 masking. The tool takes advantage of parallelism in the form of SIMD
6898 vectorization as well as multiple threads to perform accurate alignments at
6899 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6900 Needleman-Wunsch).")
6901 (home-page "https://github.com/torognes/vsearch")
6902 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6904 (supported-systems '("x86_64-linux"))
6905 ;; Dual licensed; also includes public domain source.
6906 (license (list license:gpl3 license:bsd-2))))
6908 (define-public pardre
6911 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6916 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6920 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6921 (build-system gnu-build-system)
6923 `(#:tests? #f ; no tests included
6925 (modify-phases %standard-phases
6928 (lambda* (#:key outputs #:allow-other-keys)
6929 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6930 (install-file "ParDRe" bin)
6933 `(("openmpi" ,openmpi)
6935 (synopsis "Parallel tool to remove duplicate DNA reads")
6937 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6938 Duplicate reads can be seen as identical or nearly identical sequences with
6939 some mismatches. This tool lets users avoid the analysis of unnecessary
6940 reads, reducing the time of subsequent procedures with the
6941 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6942 in order to exploit the parallel capabilities of multicore clusters. It is
6943 faster than multithreaded counterparts (end of 2015) for the same number of
6944 cores and, thanks to the message-passing technology, it can be executed on
6946 (home-page "https://sourceforge.net/projects/pardre/")
6947 (license license:gpl3+)))
6949 (define-public ruby-bio-kseq
6951 (name "ruby-bio-kseq")
6956 (uri (rubygems-uri "bio-kseq" version))
6959 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6960 (build-system ruby-build-system)
6962 `(#:test-target "spec"))
6964 `(("bundler" ,bundler)
6965 ("ruby-rspec" ,ruby-rspec)
6966 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6969 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6971 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6972 FASTQ parsing code. It provides a fast iterator over sequences and their
6974 (home-page "https://github.com/gusevfe/bio-kseq")
6975 (license license:expat)))
6977 (define-public bio-locus
6984 (uri (rubygems-uri "bio-locus" version))
6987 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6988 (build-system ruby-build-system)
6990 `(("ruby-rspec" ,ruby-rspec)))
6991 (synopsis "Tool for fast querying of genome locations")
6993 "Bio-locus is a tabix-like tool for fast querying of genome
6994 locations. Many file formats in bioinformatics contain records that
6995 start with a chromosome name and a position for a SNP, or a start-end
6996 position for indels. Bio-locus allows users to store this chr+pos or
6997 chr+pos+alt information in a database.")
6998 (home-page "https://github.com/pjotrp/bio-locus")
6999 (license license:expat)))
7001 (define-public bio-blastxmlparser
7003 (name "bio-blastxmlparser")
7007 (uri (rubygems-uri "bio-blastxmlparser" version))
7010 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7011 (build-system ruby-build-system)
7013 `(("ruby-bio-logger" ,ruby-bio-logger)
7014 ("ruby-nokogiri" ,ruby-nokogiri)))
7016 `(("ruby-rspec" ,ruby-rspec)))
7017 (synopsis "Fast big data BLAST XML parser and library")
7019 "Very fast parallel big-data BLAST XML file parser which can be used as
7020 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7021 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7022 (home-page "https://github.com/pjotrp/blastxmlparser")
7023 (license license:expat)))
7025 (define-public bioruby
7032 (uri (rubygems-uri "bio" version))
7035 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7036 (build-system ruby-build-system)
7038 `(("ruby-libxml" ,ruby-libxml)))
7040 `(("which" ,which))) ; required for test phase
7043 (modify-phases %standard-phases
7044 (add-before 'build 'patch-test-command
7046 (substitute* '("test/functional/bio/test_command.rb")
7047 (("/bin/sh") (which "sh")))
7048 (substitute* '("test/functional/bio/test_command.rb")
7049 (("/bin/ls") (which "ls")))
7050 (substitute* '("test/functional/bio/test_command.rb")
7051 (("which") (which "which")))
7052 (substitute* '("test/functional/bio/test_command.rb",
7053 "test/data/command/echoarg2.sh")
7054 (("/bin/echo") (which "echo")))
7056 (synopsis "Ruby library, shell and utilities for bioinformatics")
7057 (description "BioRuby comes with a comprehensive set of Ruby development
7058 tools and libraries for bioinformatics and molecular biology. BioRuby has
7059 components for sequence analysis, pathway analysis, protein modelling and
7060 phylogenetic analysis; it supports many widely used data formats and provides
7061 easy access to databases, external programs and public web services, including
7062 BLAST, KEGG, GenBank, MEDLINE and GO.")
7063 (home-page "http://bioruby.org/")
7064 ;; Code is released under Ruby license, except for setup
7065 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7066 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7068 (define-public r-acsnminer
7070 (name "r-acsnminer")
7071 (version "0.16.8.25")
7074 (uri (cran-uri "ACSNMineR" version))
7077 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7078 (properties `((upstream-name . "ACSNMineR")))
7079 (build-system r-build-system)
7081 `(("r-ggplot2" ,r-ggplot2)
7082 ("r-gridextra" ,r-gridextra)))
7083 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7084 (synopsis "Gene enrichment analysis")
7086 "This package provides tools to compute and represent gene set enrichment
7087 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7088 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7089 enrichment can be run with hypergeometric test or Fisher exact test, and can
7090 use multiple corrections. Visualization of data can be done either by
7091 barplots or heatmaps.")
7092 (license license:gpl2+)))
7094 (define-public r-biocgenerics
7096 (name "r-biocgenerics")
7100 (uri (bioconductor-uri "BiocGenerics" version))
7103 "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
7105 `((upstream-name . "BiocGenerics")))
7106 (build-system r-build-system)
7107 (home-page "https://bioconductor.org/packages/BiocGenerics")
7108 (synopsis "S4 generic functions for Bioconductor")
7110 "This package provides S4 generic functions needed by many Bioconductor
7112 (license license:artistic2.0)))
7114 (define-public r-biocinstaller
7116 (name "r-biocinstaller")
7120 (uri (bioconductor-uri "BiocInstaller" version))
7123 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7125 `((upstream-name . "BiocInstaller")))
7126 (build-system r-build-system)
7127 (home-page "https://bioconductor.org/packages/BiocInstaller")
7128 (synopsis "Install Bioconductor packages")
7129 (description "This package is used to install and update R packages from
7130 Bioconductor, CRAN, and Github.")
7131 (license license:artistic2.0)))
7133 (define-public r-biocviews
7135 (name "r-biocviews")
7139 (uri (bioconductor-uri "biocViews" version))
7142 "0rc1n89n04ylvy9gvsgvizcs77bh70jg1nkjjsjs7rqbr3zzdysz"))))
7144 `((upstream-name . "biocViews")))
7145 (build-system r-build-system)
7147 `(("r-biobase" ,r-biobase)
7148 ("r-graph" ,r-graph)
7150 ("r-rcurl" ,r-rcurl)
7152 ("r-runit" ,r-runit)))
7153 (home-page "https://bioconductor.org/packages/biocViews")
7154 (synopsis "Bioconductor package categorization helper")
7155 (description "The purpose of biocViews is to create HTML pages that
7156 categorize packages in a Bioconductor package repository according to keywords,
7157 also known as views, in a controlled vocabulary.")
7158 (license license:artistic2.0)))
7160 (define-public r-bookdown
7166 (uri (cran-uri "bookdown" version))
7169 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
7170 (build-system r-build-system)
7172 `(("r-htmltools" ,r-htmltools)
7173 ("r-knitr" ,r-knitr)
7174 ("r-rmarkdown" ,r-rmarkdown)
7175 ("r-tinytex" ,r-tinytex)
7177 ("r-xfun" ,r-xfun)))
7178 (home-page "https://github.com/rstudio/bookdown")
7179 (synopsis "Authoring books and technical documents with R markdown")
7180 (description "This package provides output formats and utilities for
7181 authoring books and technical documents with R Markdown.")
7182 (license license:gpl3)))
7184 (define-public r-biocstyle
7186 (name "r-biocstyle")
7190 (uri (bioconductor-uri "BiocStyle" version))
7193 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7195 `((upstream-name . "BiocStyle")))
7196 (build-system r-build-system)
7198 `(("r-biocmanager" ,r-biocmanager)
7199 ("r-bookdown" ,r-bookdown)
7200 ("r-knitr" ,r-knitr)
7201 ("r-rmarkdown" ,r-rmarkdown)
7202 ("r-yaml" ,r-yaml)))
7203 (home-page "https://bioconductor.org/packages/BiocStyle")
7204 (synopsis "Bioconductor formatting styles")
7205 (description "This package provides standard formatting styles for
7206 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7208 (license license:artistic2.0)))
7210 (define-public r-bioccheck
7212 (name "r-bioccheck")
7216 (uri (bioconductor-uri "BiocCheck" version))
7219 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7221 `((upstream-name . "BiocCheck")))
7222 (build-system r-build-system)
7225 (modify-phases %standard-phases
7226 ;; This package can be used by calling BiocCheck(<package>) from
7227 ;; within R, or by running R CMD BiocCheck <package>. This phase
7228 ;; makes sure the latter works. For this to work, the BiocCheck
7229 ;; script must be somewhere on the PATH (not the R bin directory).
7230 (add-after 'install 'install-bioccheck-subcommand
7231 (lambda* (#:key outputs #:allow-other-keys)
7232 (let* ((out (assoc-ref outputs "out"))
7233 (dest-dir (string-append out "/bin"))
7235 (string-append out "/site-library/BiocCheck/script/")))
7237 (symlink (string-append script-dir "/checkBadDeps.R")
7238 (string-append dest-dir "/checkBadDeps.R"))
7239 (symlink (string-append script-dir "/BiocCheck")
7240 (string-append dest-dir "/BiocCheck")))
7243 `(("r-codetools" ,r-codetools)
7244 ("r-graph" ,r-graph)
7246 ("r-knitr" ,r-knitr)
7247 ("r-optparse" ,r-optparse)
7248 ("r-biocmanager" ,r-biocmanager)
7249 ("r-biocviews" ,r-biocviews)
7250 ("r-stringdist" ,r-stringdist)))
7251 (home-page "https://bioconductor.org/packages/BiocCheck")
7252 (synopsis "Executes Bioconductor-specific package checks")
7253 (description "This package contains tools to perform additional quality
7254 checks on R packages that are to be submitted to the Bioconductor repository.")
7255 (license license:artistic2.0)))
7257 (define-public r-optparse
7264 (uri (cran-uri "optparse" version))
7267 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7268 (build-system r-build-system)
7270 `(("r-getopt" ,r-getopt)))
7272 "https://github.com/trevorld/optparse")
7273 (synopsis "Command line option parser")
7275 "This package provides a command line parser inspired by Python's
7276 @code{optparse} library to be used with Rscript to write shebang scripts
7277 that accept short and long options.")
7278 (license license:gpl2+)))
7280 (define-public r-dnacopy
7286 (uri (bioconductor-uri "DNAcopy" version))
7289 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7291 `((upstream-name . "DNAcopy")))
7292 (build-system r-build-system)
7294 `(("gfortran" ,gfortran)))
7295 (home-page "https://bioconductor.org/packages/DNAcopy")
7296 (synopsis "Implementation of a circular binary segmentation algorithm")
7297 (description "This package implements the circular binary segmentation (CBS)
7298 algorithm to segment DNA copy number data and identify genomic regions with
7299 abnormal copy number.")
7300 (license license:gpl2+)))
7302 (define-public r-s4vectors
7304 (name "r-s4vectors")
7308 (uri (bioconductor-uri "S4Vectors" version))
7311 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7313 `((upstream-name . "S4Vectors")))
7314 (build-system r-build-system)
7316 `(("r-biocgenerics" ,r-biocgenerics)))
7317 (home-page "https://bioconductor.org/packages/S4Vectors")
7318 (synopsis "S4 implementation of vectors and lists")
7320 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7321 classes and a set of generic functions that extend the semantic of ordinary
7322 vectors and lists in R. Package developers can easily implement vector-like
7323 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7324 In addition, a few low-level concrete subclasses of general interest (e.g.
7325 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7326 S4Vectors package itself.")
7327 (license license:artistic2.0)))
7329 (define-public r-seqinr
7336 (uri (cran-uri "seqinr" version))
7339 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7340 (build-system r-build-system)
7342 `(("r-ade4" ,r-ade4)
7343 ("r-segmented" ,r-segmented)))
7346 (home-page "http://seqinr.r-forge.r-project.org/")
7347 (synopsis "Biological sequences retrieval and analysis")
7349 "This package provides tools for exploratory data analysis and data
7350 visualization of biological sequence (DNA and protein) data. It also includes
7351 utilities for sequence data management under the ACNUC system.")
7352 (license license:gpl2+)))
7354 (define-public r-iranges
7360 (uri (bioconductor-uri "IRanges" version))
7363 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7365 `((upstream-name . "IRanges")))
7366 (build-system r-build-system)
7368 `(("r-biocgenerics" ,r-biocgenerics)
7369 ("r-s4vectors" ,r-s4vectors)))
7370 (home-page "https://bioconductor.org/packages/IRanges")
7371 (synopsis "Infrastructure for manipulating intervals on sequences")
7373 "This package provides efficient low-level and highly reusable S4 classes
7374 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7375 generally, data that can be organized sequentially (formally defined as
7376 @code{Vector} objects), as well as views on these @code{Vector} objects.
7377 Efficient list-like classes are also provided for storing big collections of
7378 instances of the basic classes. All classes in the package use consistent
7379 naming and share the same rich and consistent \"Vector API\" as much as
7381 (license license:artistic2.0)))
7383 (define-public r-genomeinfodbdata
7385 (name "r-genomeinfodbdata")
7389 ;; We cannot use bioconductor-uri here because this tarball is
7390 ;; located under "data/annotation/" instead of "bioc/".
7391 (uri (string-append "https://bioconductor.org/packages/release/"
7392 "data/annotation/src/contrib/GenomeInfoDbData_"
7396 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7398 `((upstream-name . "GenomeInfoDbData")))
7399 (build-system r-build-system)
7400 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7401 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7402 (description "This package contains data for mapping between NCBI taxonomy
7403 ID and species. It is used by functions in the GenomeInfoDb package.")
7404 (license license:artistic2.0)))
7406 (define-public r-genomeinfodb
7408 (name "r-genomeinfodb")
7412 (uri (bioconductor-uri "GenomeInfoDb" version))
7415 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7417 `((upstream-name . "GenomeInfoDb")))
7418 (build-system r-build-system)
7420 `(("r-biocgenerics" ,r-biocgenerics)
7421 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7422 ("r-iranges" ,r-iranges)
7423 ("r-rcurl" ,r-rcurl)
7424 ("r-s4vectors" ,r-s4vectors)))
7425 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7426 (synopsis "Utilities for manipulating chromosome identifiers")
7428 "This package contains data and functions that define and allow
7429 translation between different chromosome sequence naming conventions (e.g.,
7430 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7431 names in their natural, rather than lexicographic, order.")
7432 (license license:artistic2.0)))
7434 (define-public r-edger
7440 (uri (bioconductor-uri "edgeR" version))
7443 "0ihihgzrgb4q3xc8xkzp1v76ndgihrj4gas00fa25vggfs1v6hvg"))))
7444 (properties `((upstream-name . "edgeR")))
7445 (build-system r-build-system)
7447 `(("r-limma" ,r-limma)
7448 ("r-locfit" ,r-locfit)
7450 ("r-statmod" ,r-statmod))) ;for estimateDisp
7451 (home-page "http://bioinf.wehi.edu.au/edgeR")
7452 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7453 (description "This package can do differential expression analysis of
7454 RNA-seq expression profiles with biological replication. It implements a range
7455 of statistical methodology based on the negative binomial distributions,
7456 including empirical Bayes estimation, exact tests, generalized linear models
7457 and quasi-likelihood tests. It be applied to differential signal analysis of
7458 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7460 (license license:gpl2+)))
7462 (define-public r-variantannotation
7464 (name "r-variantannotation")
7468 (uri (bioconductor-uri "VariantAnnotation" version))
7471 "0gvah258mkaafhbna81zwknx8qr3lidbcx5qvwk39q3yswr9mi49"))))
7473 `((upstream-name . "VariantAnnotation")))
7477 `(("r-annotationdbi" ,r-annotationdbi)
7478 ("r-biobase" ,r-biobase)
7479 ("r-biocgenerics" ,r-biocgenerics)
7480 ("r-biostrings" ,r-biostrings)
7481 ("r-bsgenome" ,r-bsgenome)
7483 ("r-genomeinfodb" ,r-genomeinfodb)
7484 ("r-genomicfeatures" ,r-genomicfeatures)
7485 ("r-genomicranges" ,r-genomicranges)
7486 ("r-iranges" ,r-iranges)
7487 ("r-summarizedexperiment" ,r-summarizedexperiment)
7488 ("r-rsamtools" ,r-rsamtools)
7489 ("r-rtracklayer" ,r-rtracklayer)
7490 ("r-s4vectors" ,r-s4vectors)
7491 ("r-xvector" ,r-xvector)
7492 ("r-zlibbioc" ,r-zlibbioc)))
7493 (build-system r-build-system)
7494 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7495 (synopsis "Package for annotation of genetic variants")
7496 (description "This R package can annotate variants, compute amino acid
7497 coding changes and predict coding outcomes.")
7498 (license license:artistic2.0)))
7500 (define-public r-limma
7506 (uri (bioconductor-uri "limma" version))
7509 "1wkh362rmn24q7bkinb6nx62a31wl3r3myg5l326gx65wpwdnx97"))))
7510 (build-system r-build-system)
7511 (home-page "http://bioinf.wehi.edu.au/limma")
7512 (synopsis "Package for linear models for microarray and RNA-seq data")
7513 (description "This package can be used for the analysis of gene expression
7514 studies, especially the use of linear models for analysing designed experiments
7515 and the assessment of differential expression. The analysis methods apply to
7516 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7517 (license license:gpl2+)))
7519 (define-public r-xvector
7525 (uri (bioconductor-uri "XVector" version))
7528 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7530 `((upstream-name . "XVector")))
7531 (build-system r-build-system)
7534 (modify-phases %standard-phases
7535 (add-after 'unpack 'use-system-zlib
7537 (substitute* "DESCRIPTION"
7538 (("zlibbioc, ") ""))
7539 (substitute* "NAMESPACE"
7540 (("import\\(zlibbioc\\)") ""))
7545 `(("r-biocgenerics" ,r-biocgenerics)
7546 ("r-iranges" ,r-iranges)
7547 ("r-s4vectors" ,r-s4vectors)))
7548 (home-page "https://bioconductor.org/packages/XVector")
7549 (synopsis "Representation and manpulation of external sequences")
7551 "This package provides memory efficient S4 classes for storing sequences
7552 \"externally\" (behind an R external pointer, or on disk).")
7553 (license license:artistic2.0)))
7555 (define-public r-genomicranges
7557 (name "r-genomicranges")
7561 (uri (bioconductor-uri "GenomicRanges" version))
7564 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7566 `((upstream-name . "GenomicRanges")))
7567 (build-system r-build-system)
7569 `(("r-biocgenerics" ,r-biocgenerics)
7570 ("r-genomeinfodb" ,r-genomeinfodb)
7571 ("r-iranges" ,r-iranges)
7572 ("r-s4vectors" ,r-s4vectors)
7573 ("r-xvector" ,r-xvector)))
7574 (home-page "https://bioconductor.org/packages/GenomicRanges")
7575 (synopsis "Representation and manipulation of genomic intervals")
7577 "This package provides tools to efficiently represent and manipulate
7578 genomic annotations and alignments is playing a central role when it comes to
7579 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7580 GenomicRanges package defines general purpose containers for storing and
7581 manipulating genomic intervals and variables defined along a genome.")
7582 (license license:artistic2.0)))
7584 (define-public r-biobase
7590 (uri (bioconductor-uri "Biobase" version))
7593 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7595 `((upstream-name . "Biobase")))
7596 (build-system r-build-system)
7598 `(("r-biocgenerics" ,r-biocgenerics)))
7599 (home-page "https://bioconductor.org/packages/Biobase")
7600 (synopsis "Base functions for Bioconductor")
7602 "This package provides functions that are needed by many other packages
7603 on Bioconductor or which replace R functions.")
7604 (license license:artistic2.0)))
7606 (define-public r-annotationdbi
7608 (name "r-annotationdbi")
7612 (uri (bioconductor-uri "AnnotationDbi" version))
7615 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7617 `((upstream-name . "AnnotationDbi")))
7618 (build-system r-build-system)
7620 `(("r-biobase" ,r-biobase)
7621 ("r-biocgenerics" ,r-biocgenerics)
7623 ("r-iranges" ,r-iranges)
7624 ("r-rsqlite" ,r-rsqlite)
7625 ("r-s4vectors" ,r-s4vectors)))
7626 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7627 (synopsis "Annotation database interface")
7629 "This package provides user interface and database connection code for
7630 annotation data packages using SQLite data storage.")
7631 (license license:artistic2.0)))
7633 (define-public r-biomart
7639 (uri (bioconductor-uri "biomaRt" version))
7642 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7644 `((upstream-name . "biomaRt")))
7645 (build-system r-build-system)
7647 `(("r-annotationdbi" ,r-annotationdbi)
7649 ("r-progress" ,r-progress)
7650 ("r-rcurl" ,r-rcurl)
7651 ("r-stringr" ,r-stringr)
7653 (home-page "https://bioconductor.org/packages/biomaRt")
7654 (synopsis "Interface to BioMart databases")
7656 "biomaRt provides an interface to a growing collection of databases
7657 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7658 package enables retrieval of large amounts of data in a uniform way without
7659 the need to know the underlying database schemas or write complex SQL queries.
7660 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7661 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7662 users direct access to a diverse set of data and enable a wide range of
7663 powerful online queries from gene annotation to database mining.")
7664 (license license:artistic2.0)))
7666 (define-public r-biocparallel
7668 (name "r-biocparallel")
7672 (uri (bioconductor-uri "BiocParallel" version))
7675 "0g16cy0vjapqkb188z63r1b6y96m9g8vx0a3v2qavzxc177k0cja"))))
7677 `((upstream-name . "BiocParallel")))
7678 (build-system r-build-system)
7680 `(("r-futile-logger" ,r-futile-logger)
7683 (home-page "https://bioconductor.org/packages/BiocParallel")
7684 (synopsis "Bioconductor facilities for parallel evaluation")
7686 "This package provides modified versions and novel implementation of
7687 functions for parallel evaluation, tailored to use with Bioconductor
7689 (license (list license:gpl2+ license:gpl3+))))
7691 (define-public r-biostrings
7693 (name "r-biostrings")
7697 (uri (bioconductor-uri "Biostrings" version))
7700 "1qyv1ps7vy6gy78pm2rcikg0bgf1mv7falahjp3pkwqq1272hrl8"))))
7702 `((upstream-name . "Biostrings")))
7703 (build-system r-build-system)
7705 `(("r-biocgenerics" ,r-biocgenerics)
7706 ("r-iranges" ,r-iranges)
7707 ("r-s4vectors" ,r-s4vectors)
7708 ("r-xvector" ,r-xvector)))
7709 (home-page "https://bioconductor.org/packages/Biostrings")
7710 (synopsis "String objects and algorithms for biological sequences")
7712 "This package provides memory efficient string containers, string
7713 matching algorithms, and other utilities, for fast manipulation of large
7714 biological sequences or sets of sequences.")
7715 (license license:artistic2.0)))
7717 (define-public r-rsamtools
7719 (name "r-rsamtools")
7723 (uri (bioconductor-uri "Rsamtools" version))
7726 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7728 `((upstream-name . "Rsamtools")))
7729 (build-system r-build-system)
7732 (modify-phases %standard-phases
7733 (add-after 'unpack 'use-system-zlib
7735 (substitute* "DESCRIPTION"
7736 (("zlibbioc, ") ""))
7737 (substitute* "NAMESPACE"
7738 (("import\\(zlibbioc\\)") ""))
7743 `(("r-biocgenerics" ,r-biocgenerics)
7744 ("r-biocparallel" ,r-biocparallel)
7745 ("r-biostrings" ,r-biostrings)
7746 ("r-bitops" ,r-bitops)
7747 ("r-genomeinfodb" ,r-genomeinfodb)
7748 ("r-genomicranges" ,r-genomicranges)
7749 ("r-iranges" ,r-iranges)
7750 ("r-s4vectors" ,r-s4vectors)
7751 ("r-xvector" ,r-xvector)))
7752 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7753 (synopsis "Interface to samtools, bcftools, and tabix")
7755 "This package provides an interface to the 'samtools', 'bcftools', and
7756 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7757 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7759 (license license:expat)))
7761 (define-public r-delayedarray
7763 (name "r-delayedarray")
7767 (uri (bioconductor-uri "DelayedArray" version))
7770 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7772 `((upstream-name . "DelayedArray")))
7773 (build-system r-build-system)
7775 `(("r-biocgenerics" ,r-biocgenerics)
7776 ("r-biocparallel" ,r-biocparallel)
7777 ("r-s4vectors" ,r-s4vectors)
7778 ("r-iranges" ,r-iranges)
7779 ("r-matrixstats" ,r-matrixstats)))
7780 (home-page "https://bioconductor.org/packages/DelayedArray")
7781 (synopsis "Delayed operations on array-like objects")
7783 "Wrapping an array-like object (typically an on-disk object) in a
7784 @code{DelayedArray} object allows one to perform common array operations on it
7785 without loading the object in memory. In order to reduce memory usage and
7786 optimize performance, operations on the object are either delayed or executed
7787 using a block processing mechanism. Note that this also works on in-memory
7788 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7789 @code{Matrix} objects, and ordinary arrays and data frames.")
7790 (license license:artistic2.0)))
7792 (define-public r-summarizedexperiment
7794 (name "r-summarizedexperiment")
7798 (uri (bioconductor-uri "SummarizedExperiment" version))
7801 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7803 `((upstream-name . "SummarizedExperiment")))
7804 (build-system r-build-system)
7806 `(("r-biobase" ,r-biobase)
7807 ("r-biocgenerics" ,r-biocgenerics)
7808 ("r-delayedarray" ,r-delayedarray)
7809 ("r-genomeinfodb" ,r-genomeinfodb)
7810 ("r-genomicranges" ,r-genomicranges)
7811 ("r-iranges" ,r-iranges)
7812 ("r-matrix" ,r-matrix)
7813 ("r-s4vectors" ,r-s4vectors)))
7814 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7815 (synopsis "Container for representing genomic ranges by sample")
7817 "The SummarizedExperiment container contains one or more assays, each
7818 represented by a matrix-like object of numeric or other mode. The rows
7819 typically represent genomic ranges of interest and the columns represent
7821 (license license:artistic2.0)))
7823 (define-public r-genomicalignments
7825 (name "r-genomicalignments")
7829 (uri (bioconductor-uri "GenomicAlignments" version))
7832 "0a3zhwripfw2508fvgx3wzqa8nq8vnslg97a911znpwvxh53jl24"))))
7834 `((upstream-name . "GenomicAlignments")))
7835 (build-system r-build-system)
7837 `(("r-biocgenerics" ,r-biocgenerics)
7838 ("r-biocparallel" ,r-biocparallel)
7839 ("r-biostrings" ,r-biostrings)
7840 ("r-genomeinfodb" ,r-genomeinfodb)
7841 ("r-genomicranges" ,r-genomicranges)
7842 ("r-iranges" ,r-iranges)
7843 ("r-rsamtools" ,r-rsamtools)
7844 ("r-s4vectors" ,r-s4vectors)
7845 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7846 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7847 (synopsis "Representation and manipulation of short genomic alignments")
7849 "This package provides efficient containers for storing and manipulating
7850 short genomic alignments (typically obtained by aligning short reads to a
7851 reference genome). This includes read counting, computing the coverage,
7852 junction detection, and working with the nucleotide content of the
7854 (license license:artistic2.0)))
7856 (define-public r-rtracklayer
7858 (name "r-rtracklayer")
7862 (uri (bioconductor-uri "rtracklayer" version))
7865 "0a4mhd926w9slkfil5xgngjsfdj024a4w57w2bm3d4r0pj8y5da7"))))
7866 (build-system r-build-system)
7869 (modify-phases %standard-phases
7870 (add-after 'unpack 'use-system-zlib
7872 (substitute* "DESCRIPTION"
7873 ((" zlibbioc,") ""))
7874 (substitute* "NAMESPACE"
7875 (("import\\(zlibbioc\\)") ""))
7878 `(("pkg-config" ,pkg-config)))
7882 `(("r-biocgenerics" ,r-biocgenerics)
7883 ("r-biostrings" ,r-biostrings)
7884 ("r-genomeinfodb" ,r-genomeinfodb)
7885 ("r-genomicalignments" ,r-genomicalignments)
7886 ("r-genomicranges" ,r-genomicranges)
7887 ("r-iranges" ,r-iranges)
7888 ("r-rcurl" ,r-rcurl)
7889 ("r-rsamtools" ,r-rsamtools)
7890 ("r-s4vectors" ,r-s4vectors)
7892 ("r-xvector" ,r-xvector)))
7893 (home-page "https://bioconductor.org/packages/rtracklayer")
7894 (synopsis "R interface to genome browsers and their annotation tracks")
7896 "rtracklayer is an extensible framework for interacting with multiple
7897 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7898 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7899 built-in). The user may export/import tracks to/from the supported browsers,
7900 as well as query and modify the browser state, such as the current viewport.")
7901 (license license:artistic2.0)))
7903 (define-public r-genomicfeatures
7905 (name "r-genomicfeatures")
7909 (uri (bioconductor-uri "GenomicFeatures" version))
7912 "0slq6hv5bmc3bgrl824jzmr6db3fvaj6b7ihwmdn76pgqqbq2fq6"))))
7914 `((upstream-name . "GenomicFeatures")))
7915 (build-system r-build-system)
7917 `(("r-annotationdbi" ,r-annotationdbi)
7918 ("r-biobase" ,r-biobase)
7919 ("r-biocgenerics" ,r-biocgenerics)
7920 ("r-biomart" ,r-biomart)
7921 ("r-biostrings" ,r-biostrings)
7923 ("r-genomeinfodb" ,r-genomeinfodb)
7924 ("r-genomicranges" ,r-genomicranges)
7925 ("r-iranges" ,r-iranges)
7926 ("r-rcurl" ,r-rcurl)
7927 ("r-rsqlite" ,r-rsqlite)
7928 ("r-rtracklayer" ,r-rtracklayer)
7929 ("r-s4vectors" ,r-s4vectors)
7930 ("r-xvector" ,r-xvector)))
7931 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7932 (synopsis "Tools for working with transcript centric annotations")
7934 "This package provides a set of tools and methods for making and
7935 manipulating transcript centric annotations. With these tools the user can
7936 easily download the genomic locations of the transcripts, exons and cds of a
7937 given organism, from either the UCSC Genome Browser or a BioMart
7938 database (more sources will be supported in the future). This information is
7939 then stored in a local database that keeps track of the relationship between
7940 transcripts, exons, cds and genes. Flexible methods are provided for
7941 extracting the desired features in a convenient format.")
7942 (license license:artistic2.0)))
7944 (define-public r-go-db
7950 (uri (string-append "https://www.bioconductor.org/packages/"
7951 "release/data/annotation/src/contrib/GO.db_"
7955 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7957 `((upstream-name . "GO.db")))
7958 (build-system r-build-system)
7960 `(("r-annotationdbi" ,r-annotationdbi)))
7961 (home-page "https://bioconductor.org/packages/GO.db")
7962 (synopsis "Annotation maps describing the entire Gene Ontology")
7964 "The purpose of this GO.db annotation package is to provide detailed
7965 information about the latest version of the Gene Ontologies.")
7966 (license license:artistic2.0)))
7968 (define-public r-topgo
7974 (uri (bioconductor-uri "topGO" version))
7977 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7979 `((upstream-name . "topGO")))
7980 (build-system r-build-system)
7982 `(("r-annotationdbi" ,r-annotationdbi)
7984 ("r-biobase" ,r-biobase)
7985 ("r-biocgenerics" ,r-biocgenerics)
7986 ("r-go-db" ,r-go-db)
7987 ("r-graph" ,r-graph)
7988 ("r-lattice" ,r-lattice)
7989 ("r-matrixstats" ,r-matrixstats)
7990 ("r-sparsem" ,r-sparsem)))
7991 (home-page "https://bioconductor.org/packages/topGO")
7992 (synopsis "Enrichment analysis for gene ontology")
7994 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7995 terms while accounting for the topology of the GO graph. Different test
7996 statistics and different methods for eliminating local similarities and
7997 dependencies between GO terms can be implemented and applied.")
7998 ;; Any version of the LGPL applies.
7999 (license license:lgpl2.1+)))
8001 (define-public r-bsgenome
8007 (uri (bioconductor-uri "BSgenome" version))
8010 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
8012 `((upstream-name . "BSgenome")))
8013 (build-system r-build-system)
8015 `(("r-biocgenerics" ,r-biocgenerics)
8016 ("r-biostrings" ,r-biostrings)
8017 ("r-genomeinfodb" ,r-genomeinfodb)
8018 ("r-genomicranges" ,r-genomicranges)
8019 ("r-iranges" ,r-iranges)
8020 ("r-rsamtools" ,r-rsamtools)
8021 ("r-rtracklayer" ,r-rtracklayer)
8022 ("r-s4vectors" ,r-s4vectors)
8023 ("r-xvector" ,r-xvector)))
8024 (home-page "https://bioconductor.org/packages/BSgenome")
8025 (synopsis "Infrastructure for Biostrings-based genome data packages")
8027 "This package provides infrastructure shared by all Biostrings-based
8028 genome data packages and support for efficient SNP representation.")
8029 (license license:artistic2.0)))
8031 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
8033 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
8037 ;; We cannot use bioconductor-uri here because this tarball is
8038 ;; located under "data/annotation/" instead of "bioc/".
8039 (uri (string-append "https://www.bioconductor.org/packages/"
8040 "release/data/annotation/src/contrib/"
8041 "BSgenome.Hsapiens.1000genomes.hs37d5_"
8045 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
8047 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
8048 (build-system r-build-system)
8049 ;; As this package provides little more than a very large data file it
8050 ;; doesn't make sense to build substitutes.
8051 (arguments `(#:substitutable? #f))
8053 `(("r-bsgenome" ,r-bsgenome)))
8055 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
8056 (synopsis "Full genome sequences for Homo sapiens")
8058 "This package provides full genome sequences for Homo sapiens from
8059 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
8060 (license license:artistic2.0)))
8062 (define-public r-impute
8068 (uri (bioconductor-uri "impute" version))
8071 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8073 `(("gfortran" ,gfortran)))
8074 (build-system r-build-system)
8075 (home-page "https://bioconductor.org/packages/impute")
8076 (synopsis "Imputation for microarray data")
8078 "This package provides a function to impute missing gene expression
8079 microarray data, using nearest neighbor averaging.")
8080 (license license:gpl2+)))
8082 (define-public r-seqpattern
8084 (name "r-seqpattern")
8088 (uri (bioconductor-uri "seqPattern" version))
8091 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8093 `((upstream-name . "seqPattern")))
8094 (build-system r-build-system)
8096 `(("r-biostrings" ,r-biostrings)
8097 ("r-genomicranges" ,r-genomicranges)
8098 ("r-iranges" ,r-iranges)
8099 ("r-kernsmooth" ,r-kernsmooth)
8100 ("r-plotrix" ,r-plotrix)))
8101 (home-page "https://bioconductor.org/packages/seqPattern")
8102 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8104 "This package provides tools to visualize oligonucleotide patterns and
8105 sequence motif occurrences across a large set of sequences centred at a common
8106 reference point and sorted by a user defined feature.")
8107 (license license:gpl3+)))
8109 (define-public r-genomation
8111 (name "r-genomation")
8115 (uri (bioconductor-uri "genomation" version))
8118 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8119 (build-system r-build-system)
8121 `(("r-biostrings" ,r-biostrings)
8122 ("r-bsgenome" ,r-bsgenome)
8123 ("r-data-table" ,r-data-table)
8124 ("r-genomeinfodb" ,r-genomeinfodb)
8125 ("r-genomicalignments" ,r-genomicalignments)
8126 ("r-genomicranges" ,r-genomicranges)
8127 ("r-ggplot2" ,r-ggplot2)
8128 ("r-gridbase" ,r-gridbase)
8129 ("r-impute" ,r-impute)
8130 ("r-iranges" ,r-iranges)
8131 ("r-matrixstats" ,r-matrixstats)
8132 ("r-plotrix" ,r-plotrix)
8135 ("r-readr" ,r-readr)
8136 ("r-reshape2" ,r-reshape2)
8137 ("r-rsamtools" ,r-rsamtools)
8138 ("r-rtracklayer" ,r-rtracklayer)
8139 ("r-runit" ,r-runit)
8140 ("r-s4vectors" ,r-s4vectors)
8141 ("r-seqpattern" ,r-seqpattern)))
8142 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8143 (synopsis "Summary, annotation and visualization of genomic data")
8145 "This package provides a package for summary and annotation of genomic
8146 intervals. Users can visualize and quantify genomic intervals over
8147 pre-defined functional regions, such as promoters, exons, introns, etc. The
8148 genomic intervals represent regions with a defined chromosome position, which
8149 may be associated with a score, such as aligned reads from HT-seq experiments,
8150 TF binding sites, methylation scores, etc. The package can use any tabular
8151 genomic feature data as long as it has minimal information on the locations of
8152 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8153 (license license:artistic2.0)))
8155 (define-public r-genomationdata
8157 (name "r-genomationdata")
8161 ;; We cannot use bioconductor-uri here because this tarball is
8162 ;; located under "data/annotation/" instead of "bioc/".
8163 (uri (string-append "https://bioconductor.org/packages/"
8164 "release/data/experiment/src/contrib/"
8165 "genomationData_" version ".tar.gz"))
8168 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8169 (build-system r-build-system)
8170 ;; As this package provides little more than large data files, it doesn't
8171 ;; make sense to build substitutes.
8172 (arguments `(#:substitutable? #f))
8174 `(("r-knitr" ,r-knitr)))
8175 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8176 (synopsis "Experimental data for use with the genomation package")
8178 "This package contains experimental genetic data for use with the
8179 genomation package. Included are Chip Seq, Methylation and Cage data,
8180 downloaded from Encode.")
8181 (license license:gpl3+)))
8183 (define-public r-org-hs-eg-db
8185 (name "r-org-hs-eg-db")
8189 ;; We cannot use bioconductor-uri here because this tarball is
8190 ;; located under "data/annotation/" instead of "bioc/".
8191 (uri (string-append "https://www.bioconductor.org/packages/"
8192 "release/data/annotation/src/contrib/"
8193 "org.Hs.eg.db_" version ".tar.gz"))
8196 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
8198 `((upstream-name . "org.Hs.eg.db")))
8199 (build-system r-build-system)
8201 `(("r-annotationdbi" ,r-annotationdbi)))
8202 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8203 (synopsis "Genome wide annotation for Human")
8205 "This package contains genome-wide annotations for Human, primarily based
8206 on mapping using Entrez Gene identifiers.")
8207 (license license:artistic2.0)))
8209 (define-public r-org-ce-eg-db
8211 (name "r-org-ce-eg-db")
8215 ;; We cannot use bioconductor-uri here because this tarball is
8216 ;; located under "data/annotation/" instead of "bioc/".
8217 (uri (string-append "https://www.bioconductor.org/packages/"
8218 "release/data/annotation/src/contrib/"
8219 "org.Ce.eg.db_" version ".tar.gz"))
8222 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8224 `((upstream-name . "org.Ce.eg.db")))
8225 (build-system r-build-system)
8227 `(("r-annotationdbi" ,r-annotationdbi)))
8228 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8229 (synopsis "Genome wide annotation for Worm")
8231 "This package provides mappings from Entrez gene identifiers to various
8232 annotations for the genome of the model worm Caenorhabditis elegans.")
8233 (license license:artistic2.0)))
8235 (define-public r-org-dm-eg-db
8237 (name "r-org-dm-eg-db")
8241 ;; We cannot use bioconductor-uri here because this tarball is
8242 ;; located under "data/annotation/" instead of "bioc/".
8243 (uri (string-append "https://www.bioconductor.org/packages/"
8244 "release/data/annotation/src/contrib/"
8245 "org.Dm.eg.db_" version ".tar.gz"))
8248 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8250 `((upstream-name . "org.Dm.eg.db")))
8251 (build-system r-build-system)
8253 `(("r-annotationdbi" ,r-annotationdbi)))
8254 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8255 (synopsis "Genome wide annotation for Fly")
8257 "This package provides mappings from Entrez gene identifiers to various
8258 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8259 (license license:artistic2.0)))
8261 (define-public r-org-mm-eg-db
8263 (name "r-org-mm-eg-db")
8267 ;; We cannot use bioconductor-uri here because this tarball is
8268 ;; located under "data/annotation/" instead of "bioc/".
8269 (uri (string-append "https://www.bioconductor.org/packages/"
8270 "release/data/annotation/src/contrib/"
8271 "org.Mm.eg.db_" version ".tar.gz"))
8274 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8276 `((upstream-name . "org.Mm.eg.db")))
8277 (build-system r-build-system)
8279 `(("r-annotationdbi" ,r-annotationdbi)))
8280 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8281 (synopsis "Genome wide annotation for Mouse")
8283 "This package provides mappings from Entrez gene identifiers to various
8284 annotations for the genome of the model mouse Mus musculus.")
8285 (license license:artistic2.0)))
8287 (define-public r-seqlogo
8294 (uri (bioconductor-uri "seqLogo" version))
8297 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8298 (properties `((upstream-name . "seqLogo")))
8299 (build-system r-build-system)
8300 (home-page "https://bioconductor.org/packages/seqLogo")
8301 (synopsis "Sequence logos for DNA sequence alignments")
8303 "seqLogo takes the position weight matrix of a DNA sequence motif and
8304 plots the corresponding sequence logo as introduced by Schneider and
8306 (license license:lgpl2.0+)))
8308 (define-public r-bsgenome-hsapiens-ucsc-hg19
8310 (name "r-bsgenome-hsapiens-ucsc-hg19")
8314 ;; We cannot use bioconductor-uri here because this tarball is
8315 ;; located under "data/annotation/" instead of "bioc/".
8316 (uri (string-append "https://www.bioconductor.org/packages/"
8317 "release/data/annotation/src/contrib/"
8318 "BSgenome.Hsapiens.UCSC.hg19_"
8322 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8324 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8325 (build-system r-build-system)
8326 ;; As this package provides little more than a very large data file it
8327 ;; doesn't make sense to build substitutes.
8328 (arguments `(#:substitutable? #f))
8330 `(("r-bsgenome" ,r-bsgenome)))
8332 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8333 (synopsis "Full genome sequences for Homo sapiens")
8335 "This package provides full genome sequences for Homo sapiens as provided
8336 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8337 (license license:artistic2.0)))
8339 (define-public r-bsgenome-mmusculus-ucsc-mm9
8341 (name "r-bsgenome-mmusculus-ucsc-mm9")
8345 ;; We cannot use bioconductor-uri here because this tarball is
8346 ;; located under "data/annotation/" instead of "bioc/".
8347 (uri (string-append "https://www.bioconductor.org/packages/"
8348 "release/data/annotation/src/contrib/"
8349 "BSgenome.Mmusculus.UCSC.mm9_"
8353 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8355 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8356 (build-system r-build-system)
8357 ;; As this package provides little more than a very large data file it
8358 ;; doesn't make sense to build substitutes.
8359 (arguments `(#:substitutable? #f))
8361 `(("r-bsgenome" ,r-bsgenome)))
8363 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8364 (synopsis "Full genome sequences for Mouse")
8366 "This package provides full genome sequences for Mus musculus (Mouse) as
8367 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8368 (license license:artistic2.0)))
8370 (define-public r-bsgenome-mmusculus-ucsc-mm10
8372 (name "r-bsgenome-mmusculus-ucsc-mm10")
8376 ;; We cannot use bioconductor-uri here because this tarball is
8377 ;; located under "data/annotation/" instead of "bioc/".
8378 (uri (string-append "https://www.bioconductor.org/packages/"
8379 "release/data/annotation/src/contrib/"
8380 "BSgenome.Mmusculus.UCSC.mm10_"
8384 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8386 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8387 (build-system r-build-system)
8388 ;; As this package provides little more than a very large data file it
8389 ;; doesn't make sense to build substitutes.
8390 (arguments `(#:substitutable? #f))
8392 `(("r-bsgenome" ,r-bsgenome)))
8394 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8395 (synopsis "Full genome sequences for Mouse")
8397 "This package provides full genome sequences for Mus
8398 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8399 in Biostrings objects.")
8400 (license license:artistic2.0)))
8402 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8404 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8408 ;; We cannot use bioconductor-uri here because this tarball is
8409 ;; located under "data/annotation/" instead of "bioc/".
8410 (uri (string-append "https://www.bioconductor.org/packages/"
8411 "release/data/annotation/src/contrib/"
8412 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8416 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8418 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8419 (build-system r-build-system)
8420 ;; As this package provides little more than a very large data file it
8421 ;; doesn't make sense to build substitutes.
8422 (arguments `(#:substitutable? #f))
8424 `(("r-bsgenome" ,r-bsgenome)
8425 ("r-genomicfeatures" ,r-genomicfeatures)
8426 ("r-annotationdbi" ,r-annotationdbi)))
8428 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8429 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8431 "This package loads a TxDb object, which is an R interface to
8432 prefabricated databases contained in this package. This package provides
8433 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8434 based on the knownGene track.")
8435 (license license:artistic2.0)))
8437 (define-public r-bsgenome-celegans-ucsc-ce6
8439 (name "r-bsgenome-celegans-ucsc-ce6")
8443 ;; We cannot use bioconductor-uri here because this tarball is
8444 ;; located under "data/annotation/" instead of "bioc/".
8445 (uri (string-append "https://www.bioconductor.org/packages/"
8446 "release/data/annotation/src/contrib/"
8447 "BSgenome.Celegans.UCSC.ce6_"
8451 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8453 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8454 (build-system r-build-system)
8455 ;; As this package provides little more than a very large data file it
8456 ;; doesn't make sense to build substitutes.
8457 (arguments `(#:substitutable? #f))
8459 `(("r-bsgenome" ,r-bsgenome)))
8461 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8462 (synopsis "Full genome sequences for Worm")
8464 "This package provides full genome sequences for Caenorhabditis
8465 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8467 (license license:artistic2.0)))
8469 (define-public r-bsgenome-celegans-ucsc-ce10
8471 (name "r-bsgenome-celegans-ucsc-ce10")
8475 ;; We cannot use bioconductor-uri here because this tarball is
8476 ;; located under "data/annotation/" instead of "bioc/".
8477 (uri (string-append "https://www.bioconductor.org/packages/"
8478 "release/data/annotation/src/contrib/"
8479 "BSgenome.Celegans.UCSC.ce10_"
8483 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8485 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8486 (build-system r-build-system)
8487 ;; As this package provides little more than a very large data file it
8488 ;; doesn't make sense to build substitutes.
8489 (arguments `(#:substitutable? #f))
8491 `(("r-bsgenome" ,r-bsgenome)))
8493 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8494 (synopsis "Full genome sequences for Worm")
8496 "This package provides full genome sequences for Caenorhabditis
8497 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8499 (license license:artistic2.0)))
8501 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8503 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8507 ;; We cannot use bioconductor-uri here because this tarball is
8508 ;; located under "data/annotation/" instead of "bioc/".
8509 (uri (string-append "https://www.bioconductor.org/packages/"
8510 "release/data/annotation/src/contrib/"
8511 "BSgenome.Dmelanogaster.UCSC.dm3_"
8515 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8517 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8518 (build-system r-build-system)
8519 ;; As this package provides little more than a very large data file it
8520 ;; doesn't make sense to build substitutes.
8521 (arguments `(#:substitutable? #f))
8523 `(("r-bsgenome" ,r-bsgenome)))
8525 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8526 (synopsis "Full genome sequences for Fly")
8528 "This package provides full genome sequences for Drosophila
8529 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8530 Biostrings objects.")
8531 (license license:artistic2.0)))
8533 (define-public r-motifrg
8540 (uri (bioconductor-uri "motifRG" version))
8543 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8544 (properties `((upstream-name . "motifRG")))
8545 (build-system r-build-system)
8547 `(("r-biostrings" ,r-biostrings)
8548 ("r-bsgenome" ,r-bsgenome)
8549 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8550 ("r-iranges" ,r-iranges)
8551 ("r-seqlogo" ,r-seqlogo)
8552 ("r-xvector" ,r-xvector)))
8553 (home-page "https://bioconductor.org/packages/motifRG")
8554 (synopsis "Discover motifs in high throughput sequencing data")
8556 "This package provides tools for discriminative motif discovery in high
8557 throughput genetic sequencing data sets using regression methods.")
8558 (license license:artistic2.0)))
8560 (define-public r-qtl
8567 (uri (string-append "mirror://cran/src/contrib/qtl_"
8571 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8572 (build-system r-build-system)
8573 (home-page "http://rqtl.org/")
8574 (synopsis "R package for analyzing QTL experiments in genetics")
8575 (description "R/qtl is an extension library for the R statistics
8576 system. It is used to analyze experimental crosses for identifying
8577 genes contributing to variation in quantitative traits (so-called
8578 quantitative trait loci, QTLs).
8580 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8581 identify genotyping errors, and to perform single-QTL and two-QTL,
8582 two-dimensional genome scans.")
8583 (license license:gpl3)))
8585 (define-public r-zlibbioc
8591 (uri (bioconductor-uri "zlibbioc" version))
8594 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8596 `((upstream-name . "zlibbioc")))
8597 (build-system r-build-system)
8598 (home-page "https://bioconductor.org/packages/zlibbioc")
8599 (synopsis "Provider for zlib-1.2.5 to R packages")
8600 (description "This package uses the source code of zlib-1.2.5 to create
8601 libraries for systems that do not have these available via other means.")
8602 (license license:artistic2.0)))
8604 (define-public r-r4rna
8611 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8615 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8616 (build-system r-build-system)
8618 `(("r-optparse" ,r-optparse)
8619 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8620 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8621 (synopsis "Analysis framework for RNA secondary structure")
8623 "The R4RNA package aims to be a general framework for the analysis of RNA
8624 secondary structure and comparative analysis in R.")
8625 (license license:gpl3+)))
8627 (define-public r-rhtslib
8634 (uri (bioconductor-uri "Rhtslib" version))
8637 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8638 (properties `((upstream-name . "Rhtslib")))
8639 (build-system r-build-system)
8641 `(("r-zlibbioc" ,r-zlibbioc)))
8645 `(("pkg-config" ,pkg-config)))
8646 (home-page "https://github.com/nhayden/Rhtslib")
8647 (synopsis "High-throughput sequencing library as an R package")
8649 "This package provides the HTSlib C library for high-throughput
8650 nucleotide sequence analysis. The package is primarily useful to developers
8651 of other R packages who wish to make use of HTSlib.")
8652 (license license:lgpl2.0+)))
8654 (define-public r-bamsignals
8656 (name "r-bamsignals")
8661 (uri (bioconductor-uri "bamsignals" version))
8664 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8665 (build-system r-build-system)
8667 `(("r-biocgenerics" ,r-biocgenerics)
8668 ("r-genomicranges" ,r-genomicranges)
8669 ("r-iranges" ,r-iranges)
8671 ("r-rhtslib" ,r-rhtslib)
8672 ("r-zlibbioc" ,r-zlibbioc)))
8675 (home-page "https://bioconductor.org/packages/bamsignals")
8676 (synopsis "Extract read count signals from bam files")
8678 "This package allows to efficiently obtain count vectors from indexed bam
8679 files. It counts the number of nucleotide sequence reads in given genomic
8680 ranges and it computes reads profiles and coverage profiles. It also handles
8682 (license license:gpl2+)))
8684 (define-public r-rcas
8690 (uri (bioconductor-uri "RCAS" version))
8693 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8694 (build-system r-build-system)
8696 `(("r-annotationdbi" ,r-annotationdbi)
8697 ("r-biocgenerics" ,r-biocgenerics)
8698 ("r-biomart" ,r-biomart)
8699 ("r-biostrings" ,r-biostrings)
8700 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8701 ("r-cowplot" ,r-cowplot)
8702 ("r-data-table" ,r-data-table)
8705 ("r-genomation" ,r-genomation)
8706 ("r-genomeinfodb" ,r-genomeinfodb)
8707 ("r-genomicfeatures" ,r-genomicfeatures)
8708 ("r-genomicranges" ,r-genomicranges)
8709 ("r-ggplot2" ,r-ggplot2)
8710 ("r-ggseqlogo" ,r-ggseqlogo)
8711 ("r-knitr" ,r-knitr)
8712 ("r-motifrg" ,r-motifrg)
8713 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8714 ("r-pbapply" ,r-pbapply)
8715 ("r-pheatmap" ,r-pheatmap)
8716 ("r-plotly" ,r-plotly)
8717 ("r-plotrix" ,r-plotrix)
8718 ("r-proxy" ,r-proxy)
8719 ("r-rsqlite" ,r-rsqlite)
8720 ("r-rtracklayer" ,r-rtracklayer)
8721 ("r-rmarkdown" ,r-rmarkdown)
8722 ("r-s4vectors" ,r-s4vectors)
8723 ("r-topgo" ,r-topgo)))
8724 (synopsis "RNA-centric annotation system")
8726 "RCAS aims to be a standalone RNA-centric annotation system that provides
8727 intuitive reports and publication-ready graphics. This package provides the R
8728 library implementing most of the pipeline's features.")
8729 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8730 (license license:artistic2.0)))
8732 (define-public rcas-web
8739 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8740 "releases/download/v" version
8741 "/rcas-web-" version ".tar.gz"))
8744 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8745 (build-system gnu-build-system)
8748 (modify-phases %standard-phases
8749 (add-after 'install 'wrap-executable
8750 (lambda* (#:key inputs outputs #:allow-other-keys)
8751 (let* ((out (assoc-ref outputs "out"))
8752 (json (assoc-ref inputs "guile-json"))
8753 (redis (assoc-ref inputs "guile-redis"))
8754 (path (string-append
8755 json "/share/guile/site/2.2:"
8756 redis "/share/guile/site/2.2")))
8757 (wrap-program (string-append out "/bin/rcas-web")
8758 `("GUILE_LOAD_PATH" ":" = (,path))
8759 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8760 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8763 `(("r-minimal" ,r-minimal)
8765 ("guile-next" ,guile-2.2)
8766 ("guile-json" ,guile-json)
8767 ("guile-redis" ,guile2.2-redis)))
8769 `(("pkg-config" ,pkg-config)))
8770 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8771 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8772 (description "This package provides a simple web interface for the
8773 @dfn{RNA-centric annotation system} (RCAS).")
8774 (license license:agpl3+)))
8776 (define-public r-mutationalpatterns
8778 (name "r-mutationalpatterns")
8783 (uri (bioconductor-uri "MutationalPatterns" version))
8786 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8787 (build-system r-build-system)
8789 `(("r-biocgenerics" ,r-biocgenerics)
8790 ("r-biostrings" ,r-biostrings)
8791 ;; These two packages are suggested packages
8792 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8793 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8794 ("r-genomicranges" ,r-genomicranges)
8795 ("r-genomeinfodb" ,r-genomeinfodb)
8796 ("r-ggplot2" ,r-ggplot2)
8797 ("r-iranges" ,r-iranges)
8800 ("r-pracma" ,r-pracma)
8801 ("r-reshape2" ,r-reshape2)
8802 ("r-cowplot" ,r-cowplot)
8803 ("r-ggdendro" ,r-ggdendro)
8804 ("r-s4vectors" ,r-s4vectors)
8805 ("r-summarizedexperiment" ,r-summarizedexperiment)
8806 ("r-variantannotation" ,r-variantannotation)))
8807 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8808 (synopsis "Extract and visualize mutational patterns in genomic data")
8809 (description "This package provides an extensive toolset for the
8810 characterization and visualization of a wide range of mutational patterns
8811 in SNV base substitution data.")
8812 (license license:expat)))
8814 (define-public r-wgcna
8821 (uri (cran-uri "WGCNA" version))
8824 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8825 (properties `((upstream-name . "WGCNA")))
8826 (build-system r-build-system)
8828 `(("r-annotationdbi" ,r-annotationdbi)
8829 ("r-doparallel" ,r-doparallel)
8830 ("r-dynamictreecut" ,r-dynamictreecut)
8831 ("r-fastcluster" ,r-fastcluster)
8832 ("r-foreach" ,r-foreach)
8833 ("r-go-db" ,r-go-db)
8834 ("r-hmisc" ,r-hmisc)
8835 ("r-impute" ,r-impute)
8837 ("r-robust" ,r-robust)
8838 ("r-survival" ,r-survival)
8839 ("r-matrixstats" ,r-matrixstats)
8840 ("r-preprocesscore" ,r-preprocesscore)))
8842 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8843 (synopsis "Weighted correlation network analysis")
8845 "This package provides functions necessary to perform Weighted
8846 Correlation Network Analysis on high-dimensional data. It includes functions
8847 for rudimentary data cleaning, construction and summarization of correlation
8848 networks, module identification and functions for relating both variables and
8849 modules to sample traits. It also includes a number of utility functions for
8850 data manipulation and visualization.")
8851 (license license:gpl2+)))
8853 (define-public r-chipkernels
8854 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8857 (name "r-chipkernels")
8858 (version (string-append "1.1-" revision "." (string-take commit 9)))
8863 (url "https://github.com/ManuSetty/ChIPKernels.git")
8865 (file-name (string-append name "-" version))
8868 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8869 (build-system r-build-system)
8871 `(("r-iranges" ,r-iranges)
8872 ("r-xvector" ,r-xvector)
8873 ("r-biostrings" ,r-biostrings)
8874 ("r-bsgenome" ,r-bsgenome)
8875 ("r-gtools" ,r-gtools)
8876 ("r-genomicranges" ,r-genomicranges)
8877 ("r-sfsmisc" ,r-sfsmisc)
8878 ("r-kernlab" ,r-kernlab)
8879 ("r-s4vectors" ,r-s4vectors)
8880 ("r-biocgenerics" ,r-biocgenerics)))
8881 (home-page "https://github.com/ManuSetty/ChIPKernels")
8882 (synopsis "Build string kernels for DNA Sequence analysis")
8883 (description "ChIPKernels is an R package for building different string
8884 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8885 must be built and this dictionary can be used for determining kernels for DNA
8887 (license license:gpl2+))))
8889 (define-public r-seqgl
8897 (url "https://github.com/ManuSetty/SeqGL.git")
8899 (file-name (git-file-name name version))
8902 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8903 (build-system r-build-system)
8905 `(("r-biostrings" ,r-biostrings)
8906 ("r-chipkernels" ,r-chipkernels)
8907 ("r-genomicranges" ,r-genomicranges)
8908 ("r-spams" ,r-spams)
8909 ("r-wgcna" ,r-wgcna)
8910 ("r-fastcluster" ,r-fastcluster)))
8911 (home-page "https://github.com/ManuSetty/SeqGL")
8912 (synopsis "Group lasso for Dnase/ChIP-seq data")
8913 (description "SeqGL is a group lasso based algorithm to extract
8914 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8915 This package presents a method which uses group lasso to discriminate between
8916 bound and non bound genomic regions to accurately identify transcription
8917 factors bound at the specific regions.")
8918 (license license:gpl2+)))
8920 (define-public r-gkmsvm
8927 (uri (cran-uri "gkmSVM" version))
8930 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8931 (properties `((upstream-name . "gkmSVM")))
8932 (build-system r-build-system)
8934 `(("r-biocgenerics" ,r-biocgenerics)
8935 ("r-biostrings" ,r-biostrings)
8936 ("r-genomeinfodb" ,r-genomeinfodb)
8937 ("r-genomicranges" ,r-genomicranges)
8938 ("r-iranges" ,r-iranges)
8939 ("r-kernlab" ,r-kernlab)
8942 ("r-rtracklayer" ,r-rtracklayer)
8943 ("r-s4vectors" ,r-s4vectors)
8944 ("r-seqinr" ,r-seqinr)))
8945 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8946 (synopsis "Gapped-kmer support vector machine")
8948 "This R package provides tools for training gapped-kmer SVM classifiers
8949 for DNA and protein sequences. This package supports several sequence
8950 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8951 (license license:gpl2+)))
8953 (define-public r-tximport
8959 (uri (bioconductor-uri "tximport" version))
8962 "0za2js8hqjgz8ria09cglynffj4w9vrzg85nmn1xgpvmc1xk813h"))))
8963 (build-system r-build-system)
8964 (home-page "https://bioconductor.org/packages/tximport")
8965 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8967 "This package provides tools to import transcript-level abundance,
8968 estimated counts and transcript lengths, and to summarize them into matrices
8969 for use with downstream gene-level analysis packages. Average transcript
8970 length, weighted by sample-specific transcript abundance estimates, is
8971 provided as a matrix which can be used as an offset for different expression
8972 of gene-level counts.")
8973 (license license:gpl2+)))
8975 (define-public r-rhdf5
8981 (uri (bioconductor-uri "rhdf5" version))
8984 "0xmpkfdsmgl79ffffj7cf9fx3zxki2rk0xn25k778kr3s0sbmhis"))))
8985 (build-system r-build-system)
8987 `(("r-rhdf5lib" ,r-rhdf5lib)))
8990 (home-page "https://bioconductor.org/packages/rhdf5")
8991 (synopsis "HDF5 interface to R")
8993 "This R/Bioconductor package provides an interface between HDF5 and R.
8994 HDF5's main features are the ability to store and access very large and/or
8995 complex datasets and a wide variety of metadata on mass storage (disk) through
8996 a completely portable file format. The rhdf5 package is thus suited for the
8997 exchange of large and/or complex datasets between R and other software
8998 package, and for letting R applications work on datasets that are larger than
8999 the available RAM.")
9000 (license license:artistic2.0)))
9002 (define-public r-annotationfilter
9004 (name "r-annotationfilter")
9008 (uri (bioconductor-uri "AnnotationFilter" version))
9011 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
9013 `((upstream-name . "AnnotationFilter")))
9014 (build-system r-build-system)
9016 `(("r-genomicranges" ,r-genomicranges)
9017 ("r-lazyeval" ,r-lazyeval)))
9018 (home-page "https://github.com/Bioconductor/AnnotationFilter")
9019 (synopsis "Facilities for filtering Bioconductor annotation resources")
9021 "This package provides classes and other infrastructure to implement
9022 filters for manipulating Bioconductor annotation resources. The filters are
9023 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
9024 (license license:artistic2.0)))
9026 (define-public emboss
9032 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
9033 (version-major+minor version) ".0/"
9034 "EMBOSS-" version ".tar.gz"))
9037 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
9038 (build-system gnu-build-system)
9041 (list (string-append "--with-hpdf="
9042 (assoc-ref %build-inputs "libharu")))
9044 (modify-phases %standard-phases
9045 (add-after 'unpack 'fix-checks
9047 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9048 ;; and zlib, but assume that they are all found at the same
9050 (substitute* "configure.in"
9051 (("CHECK_PNGDRIVER")
9052 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9053 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9054 AM_CONDITIONAL(AMPNG, true)"))
9056 (add-after 'fix-checks 'disable-update-check
9058 ;; At build time there is no connection to the Internet, so
9059 ;; looking for updates will not work.
9060 (substitute* "Makefile.am"
9061 (("\\$\\(bindir\\)/embossupdate") ""))
9063 (add-after 'disable-update-check 'autogen
9064 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9070 ("libharu" ,libharu)
9073 `(("autoconf" ,autoconf)
9074 ("automake" ,automake)
9075 ("libtool" ,libtool)
9076 ("pkg-config" ,pkg-config)))
9077 (home-page "http://emboss.sourceforge.net")
9078 (synopsis "Molecular biology analysis suite")
9079 (description "EMBOSS is the \"European Molecular Biology Open Software
9080 Suite\". EMBOSS is an analysis package specially developed for the needs of
9081 the molecular biology (e.g. EMBnet) user community. The software
9082 automatically copes with data in a variety of formats and even allows
9083 transparent retrieval of sequence data from the web. It also provides a
9084 number of libraries for the development of software in the field of molecular
9085 biology. EMBOSS also integrates a range of currently available packages and
9086 tools for sequence analysis into a seamless whole.")
9087 (license license:gpl2+)))
9090 (let ((revision "1")
9091 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9094 ;; The version is 2.13.0 even though no release archives have been
9095 ;; published as yet.
9096 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9100 (url "https://github.com/arq5x/bits.git")
9102 (file-name (string-append name "-" version "-checkout"))
9105 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9106 (build-system gnu-build-system)
9108 `(#:tests? #f ;no tests included
9110 (modify-phases %standard-phases
9112 (add-after 'unpack 'remove-cuda
9114 (substitute* "Makefile"
9116 (("(bits_test_intersections) \\\\" _ match) match))
9119 (lambda* (#:key outputs #:allow-other-keys)
9121 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9126 (home-page "https://github.com/arq5x/bits")
9127 (synopsis "Implementation of binary interval search algorithm")
9128 (description "This package provides an implementation of the
9129 BITS (Binary Interval Search) algorithm, an approach to interval set
9130 intersection. It is especially suited for the comparison of diverse genomic
9131 datasets and the exploration of large datasets of genome
9132 intervals (e.g. genes, sequence alignments).")
9133 (license license:gpl2))))
9135 (define-public piranha
9136 ;; There is no release tarball for the latest version. The latest commit is
9137 ;; older than one year at the time of this writing.
9138 (let ((revision "1")
9139 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9142 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9146 (url "https://github.com/smithlabcode/piranha.git")
9148 (file-name (git-file-name name version))
9151 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9152 (build-system gnu-build-system)
9154 `(#:test-target "test"
9156 (modify-phases %standard-phases
9157 (add-after 'unpack 'copy-smithlab-cpp
9158 (lambda* (#:key inputs #:allow-other-keys)
9159 (for-each (lambda (file)
9160 (install-file file "./src/smithlab_cpp/"))
9161 (find-files (assoc-ref inputs "smithlab-cpp")))
9163 (add-after 'install 'install-to-store
9164 (lambda* (#:key outputs #:allow-other-keys)
9165 (let* ((out (assoc-ref outputs "out"))
9166 (bin (string-append out "/bin")))
9167 (for-each (lambda (file)
9168 (install-file file bin))
9169 (find-files "bin" ".*")))
9172 (list (string-append "--with-bam_tools_headers="
9173 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9174 (string-append "--with-bam_tools_library="
9175 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9177 `(("bamtools" ,bamtools)
9178 ("samtools" ,samtools-0.1)
9181 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9185 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9187 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9190 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9192 `(("python" ,python-2)))
9193 (home-page "https://github.com/smithlabcode/piranha")
9194 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9196 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9197 RIP-seq experiments. It takes input in BED or BAM format and identifies
9198 regions of statistically significant read enrichment. Additional covariates
9199 may optionally be provided to further inform the peak-calling process.")
9200 (license license:gpl3+))))
9208 (uri (string-append "https://pypi.python.org/packages/source/P"
9209 "/PePr/PePr-" version ".tar.gz"))
9212 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9213 (build-system python-build-system)
9215 `(#:python ,python-2 ; python2 only
9216 #:tests? #f)) ; no tests included
9218 `(("python2-numpy" ,python2-numpy)
9219 ("python2-scipy" ,python2-scipy)
9220 ("python2-pysam" ,python2-pysam)))
9221 (home-page "https://github.com/shawnzhangyx/PePr")
9222 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9224 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9225 that is primarily designed for data with biological replicates. It uses a
9226 negative binomial distribution to model the read counts among the samples in
9227 the same group, and look for consistent differences between ChIP and control
9228 group or two ChIP groups run under different conditions.")
9229 (license license:gpl3+)))
9231 (define-public filevercmp
9232 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9235 (version (string-append "0-1." (string-take commit 7)))
9239 (url "https://github.com/ekg/filevercmp.git")
9241 (file-name (git-file-name name commit))
9244 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9245 (build-system gnu-build-system)
9247 `(#:tests? #f ; There are no tests to run.
9249 (modify-phases %standard-phases
9250 (delete 'configure) ; There is no configure phase.
9252 (lambda* (#:key outputs #:allow-other-keys)
9253 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9254 (install-file "filevercmp" bin)
9256 (home-page "https://github.com/ekg/filevercmp")
9257 (synopsis "This program compares version strings")
9258 (description "This program compares version strings. It intends to be a
9259 replacement for strverscmp.")
9260 (license license:gpl3+))))
9262 (define-public multiqc
9269 (uri (pypi-uri "multiqc" version))
9272 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9273 (build-system python-build-system)
9275 `(("python-jinja2" ,python-jinja2)
9276 ("python-simplejson" ,python-simplejson)
9277 ("python-pyyaml" ,python-pyyaml)
9278 ("python-click" ,python-click)
9279 ("python-spectra" ,python-spectra)
9280 ("python-requests" ,python-requests)
9281 ("python-markdown" ,python-markdown)
9282 ("python-lzstring" ,python-lzstring)
9283 ("python-matplotlib" ,python-matplotlib)
9284 ("python-numpy" ,python-numpy)
9285 ;; MultQC checks for the presence of nose at runtime.
9286 ("python-nose" ,python-nose)))
9289 (modify-phases %standard-phases
9290 (add-after 'unpack 'relax-requirements
9292 (substitute* "setup.py"
9293 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9294 ;; than the one in Guix, but should work fine with 2.2.2.
9295 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9296 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9297 (("['\"]matplotlib.*?['\"]")
9300 (home-page "http://multiqc.info")
9301 (synopsis "Aggregate bioinformatics analysis reports")
9303 "MultiQC is a tool to aggregate bioinformatics results across many
9304 samples into a single report. It contains modules for a large number of
9305 common bioinformatics tools.")
9306 (license license:gpl3+)))
9308 (define-public r-chipseq
9315 (uri (bioconductor-uri "chipseq" version))
9318 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9319 (build-system r-build-system)
9321 `(("r-biocgenerics" ,r-biocgenerics)
9322 ("r-genomicranges" ,r-genomicranges)
9323 ("r-iranges" ,r-iranges)
9324 ("r-lattice" ,r-lattice)
9325 ("r-s4vectors" ,r-s4vectors)
9326 ("r-shortread" ,r-shortread)))
9327 (home-page "https://bioconductor.org/packages/chipseq")
9328 (synopsis "Package for analyzing ChIPseq data")
9330 "This package provides tools for processing short read data from ChIPseq
9332 (license license:artistic2.0)))
9334 (define-public r-copyhelper
9336 (name "r-copyhelper")
9341 (uri (string-append "https://bioconductor.org/packages/release/"
9342 "data/experiment/src/contrib/CopyhelpeR_"
9346 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9347 (properties `((upstream-name . "CopyhelpeR")))
9348 (build-system r-build-system)
9349 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9350 (synopsis "Helper files for CopywriteR")
9352 "This package contains the helper files that are required to run the
9353 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9354 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9355 mm10. In addition, it contains a blacklist filter to remove regions that
9356 display copy number variation. Files are stored as GRanges objects from the
9357 GenomicRanges Bioconductor package.")
9358 (license license:gpl2)))
9360 (define-public r-copywriter
9362 (name "r-copywriter")
9367 (uri (bioconductor-uri "CopywriteR" version))
9370 "0aamxafdk98n7s92jyqs65d6ljpnc2463vanvsw80p44qn6l6awn"))))
9371 (properties `((upstream-name . "CopywriteR")))
9372 (build-system r-build-system)
9374 `(("r-biocparallel" ,r-biocparallel)
9375 ("r-chipseq" ,r-chipseq)
9376 ("r-copyhelper" ,r-copyhelper)
9377 ("r-data-table" ,r-data-table)
9378 ("r-dnacopy" ,r-dnacopy)
9379 ("r-futile-logger" ,r-futile-logger)
9380 ("r-genomeinfodb" ,r-genomeinfodb)
9381 ("r-genomicalignments" ,r-genomicalignments)
9382 ("r-genomicranges" ,r-genomicranges)
9383 ("r-gtools" ,r-gtools)
9384 ("r-iranges" ,r-iranges)
9385 ("r-matrixstats" ,r-matrixstats)
9386 ("r-rsamtools" ,r-rsamtools)
9387 ("r-s4vectors" ,r-s4vectors)))
9388 (home-page "https://github.com/PeeperLab/CopywriteR")
9389 (synopsis "Copy number information from targeted sequencing")
9391 "CopywriteR extracts DNA copy number information from targeted sequencing
9392 by utilizing off-target reads. It allows for extracting uniformly distributed
9393 copy number information, can be used without reference, and can be applied to
9394 sequencing data obtained from various techniques including chromatin
9395 immunoprecipitation and target enrichment on small gene panels. Thereby,
9396 CopywriteR constitutes a widely applicable alternative to available copy
9397 number detection tools.")
9398 (license license:gpl2)))
9400 (define-public r-methylkit
9402 (name "r-methylkit")
9406 (uri (bioconductor-uri "methylKit" version))
9409 "0mz6lil1wax931incnw5byx0v9i8ryhwq9mv0nv8s48ai33ch3x6"))))
9410 (properties `((upstream-name . "methylKit")))
9411 (build-system r-build-system)
9413 `(("r-data-table" ,r-data-table)
9414 ("r-emdbook" ,r-emdbook)
9415 ("r-fastseg" ,r-fastseg)
9416 ("r-genomeinfodb" ,r-genomeinfodb)
9417 ("r-genomicranges" ,r-genomicranges)
9418 ("r-gtools" ,r-gtools)
9419 ("r-iranges" ,r-iranges)
9420 ("r-kernsmooth" ,r-kernsmooth)
9421 ("r-limma" ,r-limma)
9422 ("r-mclust" ,r-mclust)
9423 ("r-qvalue" ,r-qvalue)
9424 ("r-r-utils" ,r-r-utils)
9426 ("r-rhtslib" ,r-rhtslib)
9427 ("r-rsamtools" ,r-rsamtools)
9428 ("r-rtracklayer" ,r-rtracklayer)
9429 ("r-s4vectors" ,r-s4vectors)
9430 ("r-zlibbioc" ,r-zlibbioc)))
9433 (home-page "https://github.com/al2na/methylKit")
9435 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9437 "MethylKit is an R package for DNA methylation analysis and annotation
9438 from high-throughput bisulfite sequencing. The package is designed to deal
9439 with sequencing data from @dfn{Reduced representation bisulfite
9440 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9441 genome bisulfite sequencing. It also has functions to analyze base-pair
9442 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9444 (license license:artistic2.0)))
9446 (define-public r-sva
9453 (uri (bioconductor-uri "sva" version))
9456 "1xf0hlrqjxl0y3x13mrkxghiv39fd9v2g8gq3qzbf1wj7il6bph3"))))
9457 (build-system r-build-system)
9459 `(("r-genefilter" ,r-genefilter)
9461 ("r-biocparallel" ,r-biocparallel)
9462 ("r-matrixstats" ,r-matrixstats)
9463 ("r-limma" ,r-limma)))
9464 (home-page "https://bioconductor.org/packages/sva")
9465 (synopsis "Surrogate variable analysis")
9467 "This package contains functions for removing batch effects and other
9468 unwanted variation in high-throughput experiment. It also contains functions
9469 for identifying and building surrogate variables for high-dimensional data
9470 sets. Surrogate variables are covariates constructed directly from
9471 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9472 imaging data that can be used in subsequent analyses to adjust for unknown,
9473 unmodeled, or latent sources of noise.")
9474 (license license:artistic2.0)))
9476 (define-public r-seqminer
9483 (uri (cran-uri "seqminer" version))
9486 "15yhg4vfc7jg1jnqb3371j00pgbmbyc9l1xx63hq1l3p34lazq2l"))))
9487 (build-system r-build-system)
9490 (home-page "http://seqminer.genomic.codes")
9491 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9493 "This package provides tools to integrate nucleotide sequencing
9494 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9495 ;; Any version of the GPL is acceptable
9496 (license (list license:gpl2+ license:gpl3+))))
9498 (define-public r-raremetals2
9500 (name "r-raremetals2")
9505 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9506 "b/b7/RareMETALS2_" version ".tar.gz"))
9509 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9510 (properties `((upstream-name . "RareMETALS2")))
9511 (build-system r-build-system)
9513 `(("r-seqminer" ,r-seqminer)
9514 ("r-mvtnorm" ,r-mvtnorm)
9516 ("r-compquadform" ,r-compquadform)
9517 ("r-getopt" ,r-getopt)))
9518 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9519 (synopsis "Analyze gene-level association tests for binary trait")
9521 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9522 It was designed to meta-analyze gene-level association tests for binary trait.
9523 While rareMETALS offers a near-complete solution for meta-analysis of
9524 gene-level tests for quantitative trait, it does not offer the optimal
9525 solution for binary trait. The package rareMETALS2 offers improved features
9526 for analyzing gene-level association tests in meta-analyses for binary
9528 (license license:gpl3)))
9530 (define-public r-maldiquant
9532 (name "r-maldiquant")
9537 (uri (cran-uri "MALDIquant" version))
9540 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9541 (properties `((upstream-name . "MALDIquant")))
9542 (build-system r-build-system)
9543 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9544 (synopsis "Quantitative analysis of mass spectrometry data")
9546 "This package provides a complete analysis pipeline for matrix-assisted
9547 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9548 two-dimensional mass spectrometry data. In addition to commonly used plotting
9549 and processing methods it includes distinctive features, namely baseline
9550 subtraction methods such as morphological filters (TopHat) or the
9551 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9552 alignment using warping functions, handling of replicated measurements as well
9553 as allowing spectra with different resolutions.")
9554 (license license:gpl3+)))
9556 (define-public r-protgenerics
9558 (name "r-protgenerics")
9563 (uri (bioconductor-uri "ProtGenerics" version))
9566 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9567 (properties `((upstream-name . "ProtGenerics")))
9568 (build-system r-build-system)
9569 (home-page "https://github.com/lgatto/ProtGenerics")
9570 (synopsis "S4 generic functions for proteomics infrastructure")
9572 "This package provides S4 generic functions needed by Bioconductor
9573 proteomics packages.")
9574 (license license:artistic2.0)))
9576 (define-public r-mzr
9583 (uri (bioconductor-uri "mzR" version))
9586 "0li1y6p95ljiva4lvfmql9sipn4dq42sknbh60b36ycjppnf8lj5"))
9587 (modules '((guix build utils)))
9590 (delete-file-recursively "src/boost")
9592 (properties `((upstream-name . "mzR")))
9593 (build-system r-build-system)
9596 (modify-phases %standard-phases
9597 (add-after 'unpack 'use-system-boost
9599 (substitute* "src/Makevars"
9600 (("\\./boost/libs.*") "")
9601 (("ARCH_OBJS=" line)
9603 "\nARCH_LIBS=-lboost_system -lboost_regex \
9604 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9607 `(("boost" ,boost) ; use this instead of the bundled boost sources
9610 `(("r-biobase" ,r-biobase)
9611 ("r-biocgenerics" ,r-biocgenerics)
9612 ("r-ncdf4" ,r-ncdf4)
9613 ("r-protgenerics" ,r-protgenerics)
9615 ("r-rhdf5lib" ,r-rhdf5lib)
9616 ("r-zlibbioc" ,r-zlibbioc)))
9617 (home-page "https://github.com/sneumann/mzR/")
9618 (synopsis "Parser for mass spectrometry data files")
9620 "The mzR package provides a unified API to the common file formats and
9621 parsers available for mass spectrometry data. It comes with a wrapper for the
9622 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9623 The package contains the original code written by the ISB, and a subset of the
9624 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9625 previously been used in XCMS.")
9626 (license license:artistic2.0)))
9628 (define-public r-affyio
9635 (uri (bioconductor-uri "affyio" version))
9638 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9639 (build-system r-build-system)
9641 `(("r-zlibbioc" ,r-zlibbioc)))
9644 (home-page "https://github.com/bmbolstad/affyio")
9645 (synopsis "Tools for parsing Affymetrix data files")
9647 "This package provides routines for parsing Affymetrix data files based
9648 upon file format information. The primary focus is on accessing the CEL and
9650 (license license:lgpl2.0+)))
9652 (define-public r-affy
9659 (uri (bioconductor-uri "affy" version))
9662 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9663 (build-system r-build-system)
9665 `(("r-affyio" ,r-affyio)
9666 ("r-biobase" ,r-biobase)
9667 ("r-biocgenerics" ,r-biocgenerics)
9668 ("r-biocmanager" ,r-biocmanager)
9669 ("r-preprocesscore" ,r-preprocesscore)
9670 ("r-zlibbioc" ,r-zlibbioc)))
9673 (home-page "https://bioconductor.org/packages/affy")
9674 (synopsis "Methods for affymetrix oligonucleotide arrays")
9676 "This package contains functions for exploratory oligonucleotide array
9678 (license license:lgpl2.0+)))
9680 (define-public r-vsn
9687 (uri (bioconductor-uri "vsn" version))
9690 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9691 (build-system r-build-system)
9693 `(("r-affy" ,r-affy)
9694 ("r-biobase" ,r-biobase)
9695 ("r-ggplot2" ,r-ggplot2)
9696 ("r-lattice" ,r-lattice)
9697 ("r-limma" ,r-limma)))
9698 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9699 (synopsis "Variance stabilization and calibration for microarray data")
9701 "The package implements a method for normalising microarray intensities,
9702 and works for single- and multiple-color arrays. It can also be used for data
9703 from other technologies, as long as they have similar format. The method uses
9704 a robust variant of the maximum-likelihood estimator for an
9705 additive-multiplicative error model and affine calibration. The model
9706 incorporates data calibration step (a.k.a. normalization), a model for the
9707 dependence of the variance on the mean intensity and a variance stabilizing
9708 data transformation. Differences between transformed intensities are
9709 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9710 their variance is independent of the mean, and they are usually more sensitive
9711 and specific in detecting differential transcription.")
9712 (license license:artistic2.0)))
9714 (define-public r-mzid
9721 (uri (bioconductor-uri "mzID" version))
9724 "08jbq223viwknsmsi30hyxyxslvmb0l4wx3vmqlkl6qk4vfmxzjz"))))
9725 (properties `((upstream-name . "mzID")))
9726 (build-system r-build-system)
9728 `(("r-doparallel" ,r-doparallel)
9729 ("r-foreach" ,r-foreach)
9730 ("r-iterators" ,r-iterators)
9732 ("r-protgenerics" ,r-protgenerics)
9735 (home-page "https://bioconductor.org/packages/mzID")
9736 (synopsis "Parser for mzIdentML files")
9738 "This package provides a parser for mzIdentML files implemented using the
9739 XML package. The parser tries to be general and able to handle all types of
9740 mzIdentML files with the drawback of having less pretty output than a vendor
9742 (license license:gpl2+)))
9744 (define-public r-pcamethods
9746 (name "r-pcamethods")
9751 (uri (bioconductor-uri "pcaMethods" version))
9754 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9755 (properties `((upstream-name . "pcaMethods")))
9756 (build-system r-build-system)
9758 `(("r-biobase" ,r-biobase)
9759 ("r-biocgenerics" ,r-biocgenerics)
9761 ("r-rcpp" ,r-rcpp)))
9762 (home-page "https://github.com/hredestig/pcamethods")
9763 (synopsis "Collection of PCA methods")
9765 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9766 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9767 for missing value estimation is included for comparison. BPCA, PPCA and
9768 NipalsPCA may be used to perform PCA on incomplete data as well as for
9769 accurate missing value estimation. A set of methods for printing and plotting
9770 the results is also provided. All PCA methods make use of the same data
9771 structure (pcaRes) to provide a common interface to the PCA results.")
9772 (license license:gpl3+)))
9774 (define-public r-msnbase
9781 (uri (bioconductor-uri "MSnbase" version))
9784 "0y658anh06vnvbkfs7r8q40gqgyqr2r8kj7jlpnp33fy1lvp1nv7"))))
9785 (properties `((upstream-name . "MSnbase")))
9786 (build-system r-build-system)
9788 `(("r-affy" ,r-affy)
9789 ("r-biobase" ,r-biobase)
9790 ("r-biocgenerics" ,r-biocgenerics)
9791 ("r-biocparallel" ,r-biocparallel)
9792 ("r-digest" ,r-digest)
9793 ("r-ggplot2" ,r-ggplot2)
9794 ("r-impute" ,r-impute)
9795 ("r-iranges" ,r-iranges)
9796 ("r-lattice" ,r-lattice)
9797 ("r-maldiquant" ,r-maldiquant)
9801 ("r-pcamethods" ,r-pcamethods)
9803 ("r-preprocesscore" ,r-preprocesscore)
9804 ("r-protgenerics" ,r-protgenerics)
9806 ("r-s4vectors" ,r-s4vectors)
9807 ("r-scales" ,r-scales)
9810 (home-page "https://github.com/lgatto/MSnbase")
9811 (synopsis "Base functions and classes for MS-based proteomics")
9813 "This package provides basic plotting, data manipulation and processing
9814 of mass spectrometry based proteomics data.")
9815 (license license:artistic2.0)))
9817 (define-public r-msnid
9824 (uri (bioconductor-uri "MSnID" version))
9827 "0hgq4argllhh5hvxqi8vkf1blc3nibsslhx4zsv2mcv4yj75bv4n"))))
9828 (properties `((upstream-name . "MSnID")))
9829 (build-system r-build-system)
9831 `(("r-biobase" ,r-biobase)
9832 ("r-data-table" ,r-data-table)
9833 ("r-doparallel" ,r-doparallel)
9834 ("r-dplyr" ,r-dplyr)
9835 ("r-foreach" ,r-foreach)
9836 ("r-iterators" ,r-iterators)
9837 ("r-msnbase" ,r-msnbase)
9840 ("r-protgenerics" ,r-protgenerics)
9841 ("r-r-cache" ,r-r-cache)
9843 ("r-reshape2" ,r-reshape2)))
9844 (home-page "https://bioconductor.org/packages/MSnID")
9845 (synopsis "Utilities for LC-MSn proteomics identifications")
9847 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9848 from mzIdentML (leveraging the mzID package) or text files. After collating
9849 the search results from multiple datasets it assesses their identification
9850 quality and optimize filtering criteria to achieve the maximum number of
9851 identifications while not exceeding a specified false discovery rate. It also
9852 contains a number of utilities to explore the MS/MS results and assess missed
9853 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9854 (license license:artistic2.0)))
9856 (define-public r-seurat
9862 (uri (cran-uri "Seurat" version))
9865 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9866 (properties `((upstream-name . "Seurat")))
9867 (build-system r-build-system)
9870 ("r-cluster" ,r-cluster)
9871 ("r-cowplot" ,r-cowplot)
9872 ("r-dosnow" ,r-dosnow)
9873 ("r-dplyr" ,r-dplyr)
9875 ("r-fitdistrplus" ,r-fitdistrplus)
9876 ("r-foreach" ,r-foreach)
9878 ("r-ggplot2" ,r-ggplot2)
9879 ("r-ggridges" ,r-ggridges)
9880 ("r-gplots" ,r-gplots)
9881 ("r-hdf5r" ,r-hdf5r)
9882 ("r-hmisc" ,r-hmisc)
9885 ("r-igraph" ,r-igraph)
9886 ("r-irlba" ,r-irlba)
9888 ("r-lmtest" ,r-lmtest)
9890 ("r-matrix" ,r-matrix)
9891 ("r-metap" ,r-metap)
9892 ("r-mixtools" ,r-mixtools)
9893 ("r-pbapply" ,r-pbapply)
9894 ("r-plotly" ,r-plotly)
9897 ("r-rcolorbrewer" ,r-rcolorbrewer)
9899 ("r-rcppeigen" ,r-rcppeigen)
9900 ("r-rcppprogress" ,r-rcppprogress)
9901 ("r-reshape2" ,r-reshape2)
9902 ("r-reticulate" ,r-reticulate)
9904 ("r-rtsne" ,r-rtsne)
9905 ("r-sdmtools" ,r-sdmtools)
9906 ("r-tidyr" ,r-tidyr)
9907 ("r-tsne" ,r-tsne)))
9908 (home-page "http://www.satijalab.org/seurat")
9909 (synopsis "Seurat is an R toolkit for single cell genomics")
9911 "This package is an R package designed for QC, analysis, and
9912 exploration of single cell RNA-seq data. It easily enables widely-used
9913 analytical techniques, including the identification of highly variable genes,
9914 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9915 algorithms; density clustering, hierarchical clustering, k-means, and the
9916 discovery of differentially expressed genes and markers.")
9917 (license license:gpl3)))
9919 (define-public r-aroma-light
9921 (name "r-aroma-light")
9926 (uri (bioconductor-uri "aroma.light" version))
9929 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9930 (properties `((upstream-name . "aroma.light")))
9931 (build-system r-build-system)
9933 `(("r-matrixstats" ,r-matrixstats)
9934 ("r-r-methodss3" ,r-r-methodss3)
9936 ("r-r-utils" ,r-r-utils)))
9937 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9938 (synopsis "Methods for normalization and visualization of microarray data")
9940 "This package provides methods for microarray analysis that take basic
9941 data types such as matrices and lists of vectors. These methods can be used
9942 standalone, be utilized in other packages, or be wrapped up in higher-level
9944 (license license:gpl2+)))
9946 (define-public r-deseq
9953 (uri (bioconductor-uri "DESeq" version))
9956 "1klv1xrh3173srywr6dnq6i7m9djn4gc9aflr1p3a6yjlqcq6fya"))))
9957 (properties `((upstream-name . "DESeq")))
9958 (build-system r-build-system)
9960 `(("r-biobase" ,r-biobase)
9961 ("r-biocgenerics" ,r-biocgenerics)
9962 ("r-genefilter" ,r-genefilter)
9963 ("r-geneplotter" ,r-geneplotter)
9964 ("r-lattice" ,r-lattice)
9965 ("r-locfit" ,r-locfit)
9967 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9968 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9969 (synopsis "Differential gene expression analysis")
9971 "This package provides tools for estimating variance-mean dependence in
9972 count data from high-throughput genetic sequencing assays and for testing for
9973 differential expression based on a model using the negative binomial
9975 (license license:gpl3+)))
9977 (define-public r-edaseq
9984 (uri (bioconductor-uri "EDASeq" version))
9987 "1gjqzn1kg9qwyz2gwjyy9xzzr1lnc7xd5zwdyvzkadz97gckzxwf"))))
9988 (properties `((upstream-name . "EDASeq")))
9989 (build-system r-build-system)
9991 `(("r-annotationdbi" ,r-annotationdbi)
9992 ("r-aroma-light" ,r-aroma-light)
9993 ("r-biobase" ,r-biobase)
9994 ("r-biocgenerics" ,r-biocgenerics)
9995 ("r-biomart" ,r-biomart)
9996 ("r-biostrings" ,r-biostrings)
9997 ("r-deseq" ,r-deseq)
9998 ("r-genomicfeatures" ,r-genomicfeatures)
9999 ("r-genomicranges" ,r-genomicranges)
10000 ("r-iranges" ,r-iranges)
10001 ("r-rsamtools" ,r-rsamtools)
10002 ("r-shortread" ,r-shortread)))
10003 (home-page "https://github.com/drisso/EDASeq")
10004 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
10006 "This package provides support for numerical and graphical summaries of
10007 RNA-Seq genomic read data. Provided within-lane normalization procedures to
10008 adjust for GC-content effect (or other gene-level effects) on read counts:
10009 loess robust local regression, global-scaling, and full-quantile
10010 normalization. Between-lane normalization procedures to adjust for
10011 distributional differences between lanes (e.g., sequencing depth):
10012 global-scaling and full-quantile normalization.")
10013 (license license:artistic2.0)))
10015 (define-public r-interactivedisplaybase
10017 (name "r-interactivedisplaybase")
10022 (uri (bioconductor-uri "interactiveDisplayBase" version))
10025 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
10027 `((upstream-name . "interactiveDisplayBase")))
10028 (build-system r-build-system)
10030 `(("r-biocgenerics" ,r-biocgenerics)
10031 ("r-shiny" ,r-shiny)))
10032 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10033 (synopsis "Base package for web displays of Bioconductor objects")
10035 "This package contains the basic methods needed to generate interactive
10036 Shiny-based display methods for Bioconductor objects.")
10037 (license license:artistic2.0)))
10039 (define-public r-annotationhub
10041 (name "r-annotationhub")
10046 (uri (bioconductor-uri "AnnotationHub" version))
10049 "00288x3na0izpmbcvsqac1br1qwry86vwc2slj1l47crdfb7za6c"))))
10050 (properties `((upstream-name . "AnnotationHub")))
10051 (build-system r-build-system)
10053 `(("r-annotationdbi" ,r-annotationdbi)
10054 ("r-biocgenerics" ,r-biocgenerics)
10055 ("r-biocmanager" ,r-biocmanager)
10058 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10059 ("r-rsqlite" ,r-rsqlite)
10060 ("r-s4vectors" ,r-s4vectors)
10061 ("r-yaml" ,r-yaml)))
10062 (home-page "https://bioconductor.org/packages/AnnotationHub")
10063 (synopsis "Client to access AnnotationHub resources")
10065 "This package provides a client for the Bioconductor AnnotationHub web
10066 resource. The AnnotationHub web resource provides a central location where
10067 genomic files (e.g. VCF, bed, wig) and other resources from standard
10068 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10069 metadata about each resource, e.g., a textual description, tags, and date of
10070 modification. The client creates and manages a local cache of files retrieved
10071 by the user, helping with quick and reproducible access.")
10072 (license license:artistic2.0)))
10074 (define-public r-fastseg
10081 (uri (bioconductor-uri "fastseg" version))
10084 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10085 (build-system r-build-system)
10087 `(("r-biobase" ,r-biobase)
10088 ("r-biocgenerics" ,r-biocgenerics)
10089 ("r-genomicranges" ,r-genomicranges)
10090 ("r-iranges" ,r-iranges)
10091 ("r-s4vectors" ,r-s4vectors)))
10092 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10093 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10095 "Fastseg implements a very fast and efficient segmentation algorithm.
10096 It can segment data from DNA microarrays and data from next generation
10097 sequencing for example to detect copy number segments. Further it can segment
10098 data from RNA microarrays like tiling arrays to identify transcripts. Most
10099 generally, it can segment data given as a matrix or as a vector. Various data
10100 formats can be used as input to fastseg like expression set objects for
10101 microarrays or GRanges for sequencing data.")
10102 (license license:lgpl2.0+)))
10104 (define-public r-keggrest
10106 (name "r-keggrest")
10111 (uri (bioconductor-uri "KEGGREST" version))
10114 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10115 (properties `((upstream-name . "KEGGREST")))
10116 (build-system r-build-system)
10118 `(("r-biostrings" ,r-biostrings)
10121 (home-page "https://bioconductor.org/packages/KEGGREST")
10122 (synopsis "Client-side REST access to KEGG")
10124 "This package provides a package that provides a client interface to the
10125 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10126 (license license:artistic2.0)))
10128 (define-public r-gage
10135 (uri (bioconductor-uri "gage" version))
10138 "07b098wvryxf0zd423nk6h52s3gyngwjcx2vplqybpbpgl8h2931"))))
10139 (build-system r-build-system)
10141 `(("r-annotationdbi" ,r-annotationdbi)
10142 ("r-graph" ,r-graph)
10143 ("r-keggrest" ,r-keggrest)))
10144 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10145 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10147 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10148 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10149 data attributes including sample sizes, experimental designs, assay platforms,
10150 and other types of heterogeneity. The gage package provides functions for
10151 basic GAGE analysis, result processing and presentation. In addition, it
10152 provides demo microarray data and commonly used gene set data based on KEGG
10153 pathways and GO terms. These funtions and data are also useful for gene set
10154 analysis using other methods.")
10155 (license license:gpl2+)))
10157 (define-public r-genomicfiles
10159 (name "r-genomicfiles")
10164 (uri (bioconductor-uri "GenomicFiles" version))
10167 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10168 (properties `((upstream-name . "GenomicFiles")))
10169 (build-system r-build-system)
10171 `(("r-biocgenerics" ,r-biocgenerics)
10172 ("r-biocparallel" ,r-biocparallel)
10173 ("r-genomeinfodb" ,r-genomeinfodb)
10174 ("r-genomicalignments" ,r-genomicalignments)
10175 ("r-genomicranges" ,r-genomicranges)
10176 ("r-iranges" ,r-iranges)
10177 ("r-rsamtools" ,r-rsamtools)
10178 ("r-rtracklayer" ,r-rtracklayer)
10179 ("r-s4vectors" ,r-s4vectors)
10180 ("r-summarizedexperiment" ,r-summarizedexperiment)
10181 ("r-variantannotation" ,r-variantannotation)))
10182 (home-page "https://bioconductor.org/packages/GenomicFiles")
10183 (synopsis "Distributed computing by file or by range")
10185 "This package provides infrastructure for parallel computations
10186 distributed by file or by range. User defined mapper and reducer functions
10187 provide added flexibility for data combination and manipulation.")
10188 (license license:artistic2.0)))
10190 (define-public r-complexheatmap
10192 (name "r-complexheatmap")
10197 (uri (bioconductor-uri "ComplexHeatmap" version))
10200 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10202 `((upstream-name . "ComplexHeatmap")))
10203 (build-system r-build-system)
10205 `(("r-circlize" ,r-circlize)
10206 ("r-colorspace" ,r-colorspace)
10207 ("r-getoptlong" ,r-getoptlong)
10208 ("r-globaloptions" ,r-globaloptions)
10209 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10211 "https://github.com/jokergoo/ComplexHeatmap")
10212 (synopsis "Making Complex Heatmaps")
10214 "Complex heatmaps are efficient to visualize associations between
10215 different sources of data sets and reveal potential structures. This package
10216 provides a highly flexible way to arrange multiple heatmaps and supports
10217 self-defined annotation graphics.")
10218 (license license:gpl2+)))
10220 (define-public r-dirichletmultinomial
10222 (name "r-dirichletmultinomial")
10227 (uri (bioconductor-uri "DirichletMultinomial" version))
10230 "19bzn0a5jal1xv0ad6wikxc7wrk582hczqamlln0vb2ffwkj1z3f"))))
10232 `((upstream-name . "DirichletMultinomial")))
10233 (build-system r-build-system)
10237 `(("r-biocgenerics" ,r-biocgenerics)
10238 ("r-iranges" ,r-iranges)
10239 ("r-s4vectors" ,r-s4vectors)))
10240 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10241 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10243 "Dirichlet-multinomial mixture models can be used to describe variability
10244 in microbial metagenomic data. This package is an interface to code
10245 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10247 (license license:lgpl3)))
10249 (define-public r-ensembldb
10251 (name "r-ensembldb")
10256 (uri (bioconductor-uri "ensembldb" version))
10259 "0hdz1f34v7sas2v4225icwl3wd4sf17ykpd5dkbx1hc7wcy4w3np"))))
10260 (build-system r-build-system)
10262 `(("r-annotationdbi" ,r-annotationdbi)
10263 ("r-annotationfilter" ,r-annotationfilter)
10264 ("r-biobase" ,r-biobase)
10265 ("r-biocgenerics" ,r-biocgenerics)
10266 ("r-biostrings" ,r-biostrings)
10269 ("r-genomeinfodb" ,r-genomeinfodb)
10270 ("r-genomicfeatures" ,r-genomicfeatures)
10271 ("r-genomicranges" ,r-genomicranges)
10272 ("r-iranges" ,r-iranges)
10273 ("r-protgenerics" ,r-protgenerics)
10274 ("r-rsamtools" ,r-rsamtools)
10275 ("r-rsqlite" ,r-rsqlite)
10276 ("r-rtracklayer" ,r-rtracklayer)
10277 ("r-s4vectors" ,r-s4vectors)))
10278 (home-page "https://github.com/jotsetung/ensembldb")
10279 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10281 "The package provides functions to create and use transcript-centric
10282 annotation databases/packages. The annotation for the databases are directly
10283 fetched from Ensembl using their Perl API. The functionality and data is
10284 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10285 but, in addition to retrieve all gene/transcript models and annotations from
10286 the database, the @code{ensembldb} package also provides a filter framework
10287 allowing to retrieve annotations for specific entries like genes encoded on a
10288 chromosome region or transcript models of lincRNA genes.")
10289 ;; No version specified
10290 (license license:lgpl3+)))
10292 (define-public r-organismdbi
10294 (name "r-organismdbi")
10299 (uri (bioconductor-uri "OrganismDbi" version))
10302 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10303 (properties `((upstream-name . "OrganismDbi")))
10304 (build-system r-build-system)
10306 `(("r-annotationdbi" ,r-annotationdbi)
10307 ("r-biobase" ,r-biobase)
10308 ("r-biocgenerics" ,r-biocgenerics)
10309 ("r-biocmanager" ,r-biocmanager)
10311 ("r-genomicfeatures" ,r-genomicfeatures)
10312 ("r-genomicranges" ,r-genomicranges)
10313 ("r-graph" ,r-graph)
10314 ("r-iranges" ,r-iranges)
10316 ("r-s4vectors" ,r-s4vectors)))
10317 (home-page "https://bioconductor.org/packages/OrganismDbi")
10318 (synopsis "Software to enable the smooth interfacing of database packages")
10319 (description "The package enables a simple unified interface to several
10320 annotation packages each of which has its own schema by taking advantage of
10321 the fact that each of these packages implements a select methods.")
10322 (license license:artistic2.0)))
10324 (define-public r-biovizbase
10326 (name "r-biovizbase")
10331 (uri (bioconductor-uri "biovizBase" version))
10334 "0v54mcn3rnnfx8dmcrms5z3rgq19n3hp4r23azlgzwq6hjw7cccx"))))
10335 (properties `((upstream-name . "biovizBase")))
10336 (build-system r-build-system)
10338 `(("r-annotationdbi" ,r-annotationdbi)
10339 ("r-annotationfilter" ,r-annotationfilter)
10340 ("r-biocgenerics" ,r-biocgenerics)
10341 ("r-biostrings" ,r-biostrings)
10342 ("r-dichromat" ,r-dichromat)
10343 ("r-ensembldb" ,r-ensembldb)
10344 ("r-genomeinfodb" ,r-genomeinfodb)
10345 ("r-genomicalignments" ,r-genomicalignments)
10346 ("r-genomicfeatures" ,r-genomicfeatures)
10347 ("r-genomicranges" ,r-genomicranges)
10348 ("r-hmisc" ,r-hmisc)
10349 ("r-iranges" ,r-iranges)
10350 ("r-rcolorbrewer" ,r-rcolorbrewer)
10351 ("r-rlang" ,r-rlang)
10352 ("r-rsamtools" ,r-rsamtools)
10353 ("r-s4vectors" ,r-s4vectors)
10354 ("r-scales" ,r-scales)
10355 ("r-summarizedexperiment" ,r-summarizedexperiment)
10356 ("r-variantannotation" ,r-variantannotation)))
10357 (home-page "https://bioconductor.org/packages/biovizBase")
10358 (synopsis "Basic graphic utilities for visualization of genomic data")
10360 "The biovizBase package is designed to provide a set of utilities, color
10361 schemes and conventions for genomic data. It serves as the base for various
10362 high-level packages for biological data visualization. This saves development
10363 effort and encourages consistency.")
10364 (license license:artistic2.0)))
10366 (define-public r-ggbio
10373 (uri (bioconductor-uri "ggbio" version))
10376 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10377 (build-system r-build-system)
10379 `(("r-annotationdbi" ,r-annotationdbi)
10380 ("r-annotationfilter" ,r-annotationfilter)
10381 ("r-biobase" ,r-biobase)
10382 ("r-biocgenerics" ,r-biocgenerics)
10383 ("r-biostrings" ,r-biostrings)
10384 ("r-biovizbase" ,r-biovizbase)
10385 ("r-bsgenome" ,r-bsgenome)
10386 ("r-ensembldb" ,r-ensembldb)
10387 ("r-genomeinfodb" ,r-genomeinfodb)
10388 ("r-genomicalignments" ,r-genomicalignments)
10389 ("r-genomicfeatures" ,r-genomicfeatures)
10390 ("r-genomicranges" ,r-genomicranges)
10391 ("r-ggally" ,r-ggally)
10392 ("r-ggplot2" ,r-ggplot2)
10393 ("r-gridextra" ,r-gridextra)
10394 ("r-gtable" ,r-gtable)
10395 ("r-hmisc" ,r-hmisc)
10396 ("r-iranges" ,r-iranges)
10397 ("r-organismdbi" ,r-organismdbi)
10398 ("r-reshape2" ,r-reshape2)
10399 ("r-rlang" ,r-rlang)
10400 ("r-rsamtools" ,r-rsamtools)
10401 ("r-rtracklayer" ,r-rtracklayer)
10402 ("r-s4vectors" ,r-s4vectors)
10403 ("r-scales" ,r-scales)
10404 ("r-summarizedexperiment" ,r-summarizedexperiment)
10405 ("r-variantannotation" ,r-variantannotation)))
10406 (home-page "http://www.tengfei.name/ggbio/")
10407 (synopsis "Visualization tools for genomic data")
10409 "The ggbio package extends and specializes the grammar of graphics for
10410 biological data. The graphics are designed to answer common scientific
10411 questions, in particular those often asked of high throughput genomics data.
10412 All core Bioconductor data structures are supported, where appropriate. The
10413 package supports detailed views of particular genomic regions, as well as
10414 genome-wide overviews. Supported overviews include ideograms and grand linear
10415 views. High-level plots include sequence fragment length, edge-linked
10416 interval to data view, mismatch pileup, and several splicing summaries.")
10417 (license license:artistic2.0)))
10419 (define-public r-gprofiler
10421 (name "r-gprofiler")
10426 (uri (cran-uri "gProfileR" version))
10429 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10430 (properties `((upstream-name . "gProfileR")))
10431 (build-system r-build-system)
10433 `(("r-plyr" ,r-plyr)
10434 ("r-rcurl" ,r-rcurl)))
10435 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10436 (synopsis "Interface to the g:Profiler toolkit")
10438 "This package provides tools for functional enrichment analysis,
10439 gene identifier conversion and mapping homologous genes across related
10440 organisms via the @code{g:Profiler} toolkit.")
10441 (license license:gpl2+)))
10443 (define-public r-gqtlbase
10445 (name "r-gqtlbase")
10450 (uri (bioconductor-uri "gQTLBase" version))
10453 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10454 (properties `((upstream-name . "gQTLBase")))
10455 (build-system r-build-system)
10457 `(("r-batchjobs" ,r-batchjobs)
10458 ("r-bbmisc" ,r-bbmisc)
10459 ("r-biocgenerics" ,r-biocgenerics)
10461 ("r-doparallel" ,r-doparallel)
10463 ("r-ffbase" ,r-ffbase)
10464 ("r-foreach" ,r-foreach)
10465 ("r-genomicfiles" ,r-genomicfiles)
10466 ("r-genomicranges" ,r-genomicranges)
10467 ("r-rtracklayer" ,r-rtracklayer)
10468 ("r-s4vectors" ,r-s4vectors)
10469 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10470 (home-page "https://bioconductor.org/packages/gQTLBase")
10471 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10473 "The purpose of this package is to simplify the storage and interrogation
10474 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10476 (license license:artistic2.0)))
10478 (define-public r-snpstats
10480 (name "r-snpstats")
10485 (uri (bioconductor-uri "snpStats" version))
10488 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10489 (properties `((upstream-name . "snpStats")))
10490 (build-system r-build-system)
10491 (inputs `(("zlib" ,zlib)))
10493 `(("r-biocgenerics" ,r-biocgenerics)
10494 ("r-matrix" ,r-matrix)
10495 ("r-survival" ,r-survival)
10496 ("r-zlibbioc" ,r-zlibbioc)))
10497 (home-page "https://bioconductor.org/packages/snpStats")
10498 (synopsis "Methods for SNP association studies")
10500 "This package provides classes and statistical methods for large
10501 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10502 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10503 (license license:gpl3)))
10505 (define-public r-homo-sapiens
10507 (name "r-homo-sapiens")
10511 ;; We cannot use bioconductor-uri here because this tarball is
10512 ;; located under "data/annotation/" instead of "bioc/".
10513 (uri (string-append "http://www.bioconductor.org/packages/"
10514 "release/data/annotation/src/contrib/"
10516 version ".tar.gz"))
10519 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10521 `((upstream-name . "Homo.sapiens")))
10522 (build-system r-build-system)
10524 `(("r-genomicfeatures" ,r-genomicfeatures)
10525 ("r-go-db" ,r-go-db)
10526 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10527 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10528 ("r-organismdbi" ,r-organismdbi)
10529 ("r-annotationdbi" ,r-annotationdbi)))
10530 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10531 (synopsis "Annotation package for the Homo.sapiens object")
10533 "This package contains the Homo.sapiens object to access data from
10534 several related annotation packages.")
10535 (license license:artistic2.0)))
10537 (define-public r-erma
10544 (uri (bioconductor-uri "erma" version))
10547 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10548 (build-system r-build-system)
10550 `(("r-annotationdbi" ,r-annotationdbi)
10551 ("r-biobase" ,r-biobase)
10552 ("r-biocgenerics" ,r-biocgenerics)
10553 ("r-biocparallel" ,r-biocparallel)
10554 ("r-genomeinfodb" ,r-genomeinfodb)
10555 ("r-genomicfiles" ,r-genomicfiles)
10556 ("r-genomicranges" ,r-genomicranges)
10557 ("r-ggplot2" ,r-ggplot2)
10558 ("r-homo-sapiens" ,r-homo-sapiens)
10559 ("r-iranges" ,r-iranges)
10560 ("r-rtracklayer" ,r-rtracklayer)
10561 ("r-s4vectors" ,r-s4vectors)
10562 ("r-shiny" ,r-shiny)
10563 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10564 (home-page "https://bioconductor.org/packages/erma")
10565 (synopsis "Epigenomic road map adventures")
10567 "The epigenomics road map describes locations of epigenetic marks in DNA
10568 from a variety of cell types. Of interest are locations of histone
10569 modifications, sites of DNA methylation, and regions of accessible chromatin.
10570 This package presents a selection of elements of the road map including
10571 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10572 by Ernst and Kellis.")
10573 (license license:artistic2.0)))
10575 (define-public r-ldblock
10582 (uri (bioconductor-uri "ldblock" version))
10585 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10586 (build-system r-build-system)
10588 `(("r-biocgenerics" ,r-biocgenerics)
10590 ("r-genomeinfodb" ,r-genomeinfodb)
10591 ("r-genomicfiles" ,r-genomicfiles)
10592 ("r-go-db" ,r-go-db)
10593 ("r-homo-sapiens" ,r-homo-sapiens)
10594 ("r-matrix" ,r-matrix)
10595 ("r-rsamtools" ,r-rsamtools)
10596 ("r-snpstats" ,r-snpstats)
10597 ("r-variantannotation" ,r-variantannotation)))
10598 (home-page "https://bioconductor.org/packages/ldblock")
10599 (synopsis "Data structures for linkage disequilibrium measures in populations")
10601 "This package defines data structures for @dfn{linkage
10602 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10603 handling of existing population-level data for the purpose of flexibly
10604 defining LD blocks.")
10605 (license license:artistic2.0)))
10607 (define-public r-gqtlstats
10609 (name "r-gqtlstats")
10614 (uri (bioconductor-uri "gQTLstats" version))
10617 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10618 (properties `((upstream-name . "gQTLstats")))
10619 (build-system r-build-system)
10621 `(("r-annotationdbi" ,r-annotationdbi)
10622 ("r-batchjobs" ,r-batchjobs)
10623 ("r-bbmisc" ,r-bbmisc)
10624 ("r-beeswarm" ,r-beeswarm)
10625 ("r-biobase" ,r-biobase)
10626 ("r-biocgenerics" ,r-biocgenerics)
10627 ("r-doparallel" ,r-doparallel)
10628 ("r-dplyr" ,r-dplyr)
10630 ("r-ffbase" ,r-ffbase)
10631 ("r-foreach" ,r-foreach)
10632 ("r-genomeinfodb" ,r-genomeinfodb)
10633 ("r-genomicfeatures" ,r-genomicfeatures)
10634 ("r-genomicfiles" ,r-genomicfiles)
10635 ("r-genomicranges" ,r-genomicranges)
10636 ("r-ggbeeswarm" ,r-ggbeeswarm)
10637 ("r-ggplot2" ,r-ggplot2)
10638 ("r-gqtlbase" ,r-gqtlbase)
10639 ("r-hardyweinberg" ,r-hardyweinberg)
10640 ("r-homo-sapiens" ,r-homo-sapiens)
10641 ("r-iranges" ,r-iranges)
10642 ("r-limma" ,r-limma)
10644 ("r-plotly" ,r-plotly)
10645 ("r-reshape2" ,r-reshape2)
10646 ("r-s4vectors" ,r-s4vectors)
10647 ("r-shiny" ,r-shiny)
10648 ("r-snpstats" ,r-snpstats)
10649 ("r-summarizedexperiment" ,r-summarizedexperiment)
10650 ("r-variantannotation" ,r-variantannotation)))
10651 (home-page "https://bioconductor.org/packages/gQTLstats")
10652 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10654 "This package provides tools for the computationally efficient analysis
10655 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10656 The software in this package aims to support refinements and functional
10657 interpretation of members of a collection of association statistics on a
10658 family of feature/genome hypotheses.")
10659 (license license:artistic2.0)))
10661 (define-public r-gviz
10668 (uri (bioconductor-uri "Gviz" version))
10671 "05zk9hf30afg6rjg97lzn5v8xij90v8zm09y9vcz0asmc3c8xs0a"))))
10672 (properties `((upstream-name . "Gviz")))
10673 (build-system r-build-system)
10675 `(("r-annotationdbi" ,r-annotationdbi)
10676 ("r-biobase" ,r-biobase)
10677 ("r-biocgenerics" ,r-biocgenerics)
10678 ("r-biomart" ,r-biomart)
10679 ("r-biostrings" ,r-biostrings)
10680 ("r-biovizbase" ,r-biovizbase)
10681 ("r-bsgenome" ,r-bsgenome)
10682 ("r-digest" ,r-digest)
10683 ("r-genomeinfodb" ,r-genomeinfodb)
10684 ("r-genomicalignments" ,r-genomicalignments)
10685 ("r-genomicfeatures" ,r-genomicfeatures)
10686 ("r-genomicranges" ,r-genomicranges)
10687 ("r-iranges" ,r-iranges)
10688 ("r-lattice" ,r-lattice)
10689 ("r-latticeextra" ,r-latticeextra)
10690 ("r-matrixstats" ,r-matrixstats)
10691 ("r-rcolorbrewer" ,r-rcolorbrewer)
10692 ("r-rsamtools" ,r-rsamtools)
10693 ("r-rtracklayer" ,r-rtracklayer)
10694 ("r-s4vectors" ,r-s4vectors)
10695 ("r-xvector" ,r-xvector)))
10696 (home-page "https://bioconductor.org/packages/Gviz")
10697 (synopsis "Plotting data and annotation information along genomic coordinates")
10699 "Genomic data analyses requires integrated visualization of known genomic
10700 information and new experimental data. Gviz uses the biomaRt and the
10701 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10702 and translates this to e.g. gene/transcript structures in viewports of the
10703 grid graphics package. This results in genomic information plotted together
10705 (license license:artistic2.0)))
10707 (define-public r-gwascat
10714 (uri (bioconductor-uri "gwascat" version))
10717 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10718 (build-system r-build-system)
10720 `(("r-annotationdbi" ,r-annotationdbi)
10721 ("r-annotationhub" ,r-annotationhub)
10722 ("r-biocgenerics" ,r-biocgenerics)
10723 ("r-biostrings" ,r-biostrings)
10724 ("r-genomeinfodb" ,r-genomeinfodb)
10725 ("r-genomicfeatures" ,r-genomicfeatures)
10726 ("r-genomicranges" ,r-genomicranges)
10727 ("r-ggbio" ,r-ggbio)
10728 ("r-ggplot2" ,r-ggplot2)
10729 ("r-gqtlstats" ,r-gqtlstats)
10730 ("r-graph" ,r-graph)
10732 ("r-homo-sapiens" ,r-homo-sapiens)
10733 ("r-iranges" ,r-iranges)
10734 ("r-rsamtools" ,r-rsamtools)
10735 ("r-rtracklayer" ,r-rtracklayer)
10736 ("r-s4vectors" ,r-s4vectors)
10737 ("r-snpstats" ,r-snpstats)
10738 ("r-summarizedexperiment" ,r-summarizedexperiment)
10739 ("r-variantannotation" ,r-variantannotation)))
10740 (home-page "https://bioconductor.org/packages/gwascat")
10741 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10743 "This package provides tools for representing and modeling data in the
10744 EMBL-EBI GWAS catalog.")
10745 (license license:artistic2.0)))
10747 (define-public r-sushi
10753 (uri (bioconductor-uri "Sushi" version))
10756 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10757 (properties `((upstream-name . "Sushi")))
10758 (build-system r-build-system)
10760 `(("r-biomart" ,r-biomart)
10762 (home-page "https://bioconductor.org/packages/Sushi")
10763 (synopsis "Tools for visualizing genomics data")
10765 "This package provides flexible, quantitative, and integrative genomic
10766 visualizations for publication-quality multi-panel figures.")
10767 (license license:gpl2+)))
10769 (define-public r-fithic
10775 (uri (bioconductor-uri "FitHiC" version))
10778 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10779 (properties `((upstream-name . "FitHiC")))
10780 (build-system r-build-system)
10782 `(("r-data-table" ,r-data-table)
10783 ("r-fdrtool" ,r-fdrtool)
10784 ("r-rcpp" ,r-rcpp)))
10785 (home-page "https://bioconductor.org/packages/FitHiC")
10786 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10788 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10789 intra-chromosomal contact maps produced by genome-wide genome architecture
10790 assays such as Hi-C.")
10791 (license license:gpl2+)))
10793 (define-public r-hitc
10799 (uri (bioconductor-uri "HiTC" version))
10802 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10803 (properties `((upstream-name . "HiTC")))
10804 (build-system r-build-system)
10806 `(("r-biostrings" ,r-biostrings)
10807 ("r-genomeinfodb" ,r-genomeinfodb)
10808 ("r-genomicranges" ,r-genomicranges)
10809 ("r-iranges" ,r-iranges)
10810 ("r-matrix" ,r-matrix)
10811 ("r-rcolorbrewer" ,r-rcolorbrewer)
10812 ("r-rtracklayer" ,r-rtracklayer)))
10813 (home-page "https://bioconductor.org/packages/HiTC")
10814 (synopsis "High throughput chromosome conformation capture analysis")
10816 "The HiTC package was developed to explore high-throughput \"C\" data
10817 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10818 quality controls, normalization, visualization, and further analysis are also
10820 (license license:artistic2.0)))
10822 (define-public r-qvalue
10829 (uri (bioconductor-uri "qvalue" version))
10832 "03qxshqwwq1rj23p6pjrz08jm3ziikvy9badi4mz2rcwy2nz783a"))))
10833 (build-system r-build-system)
10835 `(("r-ggplot2" ,r-ggplot2)
10836 ("r-reshape2" ,r-reshape2)))
10837 (home-page "http://github.com/jdstorey/qvalue")
10838 (synopsis "Q-value estimation for false discovery rate control")
10840 "This package takes a list of p-values resulting from the simultaneous
10841 testing of many hypotheses and estimates their q-values and local @dfn{false
10842 discovery rate} (FDR) values. The q-value of a test measures the proportion
10843 of false positives incurred when that particular test is called significant.
10844 The local FDR measures the posterior probability the null hypothesis is true
10845 given the test's p-value. Various plots are automatically generated, allowing
10846 one to make sensible significance cut-offs. The software can be applied to
10847 problems in genomics, brain imaging, astrophysics, and data mining.")
10848 ;; Any version of the LGPL.
10849 (license license:lgpl3+)))
10851 (define-public r-hdf5array
10853 (name "r-hdf5array")
10858 (uri (bioconductor-uri "HDF5Array" version))
10861 "1w7ad8cfsbh5xx82m3l4lc0vbmj9lcsqxxpiy3ana2ycgn1bqv3g"))))
10862 (properties `((upstream-name . "HDF5Array")))
10863 (build-system r-build-system)
10865 `(("r-biocgenerics" ,r-biocgenerics)
10866 ("r-delayedarray" ,r-delayedarray)
10867 ("r-iranges" ,r-iranges)
10868 ("r-rhdf5" ,r-rhdf5)
10869 ("r-s4vectors" ,r-s4vectors)))
10870 (home-page "https://bioconductor.org/packages/HDF5Array")
10871 (synopsis "HDF5 back end for DelayedArray objects")
10872 (description "This package provides an array-like container for convenient
10873 access and manipulation of HDF5 datasets. It supports delayed operations and
10874 block processing.")
10875 (license license:artistic2.0)))
10877 (define-public r-rhdf5lib
10879 (name "r-rhdf5lib")
10884 (uri (bioconductor-uri "Rhdf5lib" version))
10887 "01gpz780g850ql20b2ql6pvr678ydk4nq4sn5iiih94a4crb9lz1"))
10888 (modules '((guix build utils)))
10891 ;; Delete bundled binaries
10892 (delete-file-recursively "src/winlib/")
10894 (properties `((upstream-name . "Rhdf5lib")))
10895 (build-system r-build-system)
10898 (modify-phases %standard-phases
10899 (add-after 'unpack 'do-not-use-bundled-hdf5
10900 (lambda* (#:key inputs #:allow-other-keys)
10901 (for-each delete-file '("configure" "configure.ac"))
10902 ;; Do not make other packages link with the proprietary libsz.
10903 (substitute* "R/zzz.R"
10904 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10905 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10906 (("'%s/libhdf5.a %s/libsz.a -lz'")
10907 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10908 (with-directory-excursion "src"
10909 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10910 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10912 ;; Remove timestamp and host system information to make
10913 ;; the build reproducible.
10914 (substitute* "hdf5/src/libhdf5.settings.in"
10915 (("Configured on: @CONFIG_DATE@")
10916 "Configured on: Guix")
10917 (("Uname information:.*")
10918 "Uname information: Linux\n")
10919 ;; Remove unnecessary store reference.
10921 "C Compiler: GCC\n"))
10922 (rename-file "Makevars.in" "Makevars")
10923 (substitute* "Makevars"
10924 (("HDF5_CXX_LIB=.*")
10925 (string-append "HDF5_CXX_LIB="
10926 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10928 (string-append "HDF5_LIB="
10929 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10930 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10931 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10932 ;; szip is non-free software
10933 (("cp \\$\\{SZIP_LIB\\}.*") "")
10934 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10939 `(("hdf5" ,hdf5-1.10)))
10941 `(("hdf5-source" ,(package-source hdf5-1.10))))
10942 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10943 (synopsis "HDF5 library as an R package")
10944 (description "This package provides C and C++ HDF5 libraries for use in R
10946 (license license:artistic2.0)))
10948 (define-public r-beachmat
10950 (name "r-beachmat")
10955 (uri (bioconductor-uri "beachmat" version))
10958 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10959 (build-system r-build-system)
10964 `(("r-biocgenerics" ,r-biocgenerics)
10965 ("r-delayedarray" ,r-delayedarray)
10966 ("r-hdf5array" ,r-hdf5array)
10968 ("r-rhdf5" ,r-rhdf5)
10969 ("r-rhdf5lib" ,r-rhdf5lib)))
10970 (home-page "https://bioconductor.org/packages/beachmat")
10971 (synopsis "Compiling Bioconductor to handle each matrix type")
10972 (description "This package provides a consistent C++ class interface for a
10973 variety of commonly used matrix types, including sparse and HDF5-backed
10975 (license license:gpl3)))
10977 (define-public r-singlecellexperiment
10979 (name "r-singlecellexperiment")
10984 (uri (bioconductor-uri "SingleCellExperiment" version))
10987 "19r4r7djrn46qlijkj1g926vcklxzcrxjlxv6cg43m9j9jgfs3dj"))))
10989 `((upstream-name . "SingleCellExperiment")))
10990 (build-system r-build-system)
10992 `(("r-biocgenerics" ,r-biocgenerics)
10993 ("r-s4vectors" ,r-s4vectors)
10994 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10995 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10996 (synopsis "S4 classes for single cell data")
10997 (description "This package defines an S4 class for storing data from
10998 single-cell experiments. This includes specialized methods to store and
10999 retrieve spike-in information, dimensionality reduction coordinates and size
11000 factors for each cell, along with the usual metadata for genes and
11002 (license license:gpl3)))
11004 (define-public r-scater
11010 (uri (bioconductor-uri "scater" version))
11013 "1kwa9n70c5j0xcj6nkmlkzjr63cnj78mp8nhg58n07fq1ijm4ns3"))))
11014 (build-system r-build-system)
11016 `(("r-beachmat" ,r-beachmat)
11017 ("r-biocgenerics" ,r-biocgenerics)
11018 ("r-biocparallel" ,r-biocparallel)
11019 ("r-delayedarray" ,r-delayedarray)
11020 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11021 ("r-dplyr" ,r-dplyr)
11022 ("r-ggbeeswarm" ,r-ggbeeswarm)
11023 ("r-ggplot2" ,r-ggplot2)
11024 ("r-matrix" ,r-matrix)
11027 ("r-reshape2" ,r-reshape2)
11028 ("r-rhdf5lib" ,r-rhdf5lib)
11029 ("r-s4vectors" ,r-s4vectors)
11030 ("r-singlecellexperiment" ,r-singlecellexperiment)
11031 ("r-summarizedexperiment" ,r-summarizedexperiment)
11032 ("r-viridis" ,r-viridis)))
11033 (home-page "https://github.com/davismcc/scater")
11034 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11035 (description "This package provides a collection of tools for doing
11036 various analyses of single-cell RNA-seq gene expression data, with a focus on
11038 (license license:gpl2+)))
11040 (define-public r-scran
11047 (uri (bioconductor-uri "scran" version))
11050 "1viyzrwfm9vccsf54c6g7k1dn7skkfx4ml1jy12q67wa20sx8l03"))))
11051 (build-system r-build-system)
11053 `(("r-beachmat" ,r-beachmat)
11054 ("r-biocgenerics" ,r-biocgenerics)
11055 ("r-biocneighbors" ,r-biocneighbors)
11056 ("r-biocparallel" ,r-biocparallel)
11057 ("r-delayedarray" ,r-delayedarray)
11058 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11059 ("r-dynamictreecut" ,r-dynamictreecut)
11060 ("r-edger" ,r-edger)
11061 ("r-igraph" ,r-igraph)
11062 ("r-limma" ,r-limma)
11063 ("r-matrix" ,r-matrix)
11065 ("r-rhdf5lib" ,r-rhdf5lib)
11066 ("r-s4vectors" ,r-s4vectors)
11067 ("r-scater" ,r-scater)
11068 ("r-singlecellexperiment" ,r-singlecellexperiment)
11069 ("r-statmod" ,r-statmod)
11070 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11071 (home-page "https://bioconductor.org/packages/scran")
11072 (synopsis "Methods for single-cell RNA-Seq data analysis")
11073 (description "This package implements a variety of low-level analyses of
11074 single-cell RNA-seq data. Methods are provided for normalization of
11075 cell-specific biases, assignment of cell cycle phase, and detection of highly
11076 variable and significantly correlated genes.")
11077 (license license:gpl3)))
11079 (define-public r-delayedmatrixstats
11081 (name "r-delayedmatrixstats")
11086 (uri (bioconductor-uri "DelayedMatrixStats" version))
11089 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11091 `((upstream-name . "DelayedMatrixStats")))
11092 (build-system r-build-system)
11094 `(("r-biocparallel" ,r-biocparallel)
11095 ("r-delayedarray" ,r-delayedarray)
11096 ("r-hdf5array" ,r-hdf5array)
11097 ("r-iranges" ,r-iranges)
11098 ("r-matrix" ,r-matrix)
11099 ("r-matrixstats" ,r-matrixstats)
11100 ("r-s4vectors" ,r-s4vectors)))
11101 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11102 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11104 "This package provides a port of the @code{matrixStats} API for use with
11105 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11106 contains high-performing functions operating on rows and columns of
11107 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11108 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11109 are optimized per data type and for subsetted calculations such that both
11110 memory usage and processing time is minimized.")
11111 (license license:expat)))
11113 (define-public r-phangorn
11115 (name "r-phangorn")
11120 (uri (cran-uri "phangorn" version))
11123 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11124 (build-system r-build-system)
11127 ("r-fastmatch" ,r-fastmatch)
11128 ("r-igraph" ,r-igraph)
11129 ("r-magrittr" ,r-magrittr)
11130 ("r-matrix" ,r-matrix)
11131 ("r-quadprog" ,r-quadprog)
11132 ("r-rcpp" ,r-rcpp)))
11133 (home-page "https://github.com/KlausVigo/phangorn")
11134 (synopsis "Phylogenetic analysis in R")
11136 "Phangorn is a package for phylogenetic analysis in R. It supports
11137 estimation of phylogenetic trees and networks using Maximum Likelihood,
11138 Maximum Parsimony, distance methods and Hadamard conjugation.")
11139 (license license:gpl2+)))
11141 (define-public r-dropbead
11142 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11145 (name "r-dropbead")
11146 (version (string-append "0-" revision "." (string-take commit 7)))
11150 (uri (git-reference
11151 (url "https://github.com/rajewsky-lab/dropbead.git")
11153 (file-name (git-file-name name version))
11156 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11157 (build-system r-build-system)
11159 `(("r-ggplot2" ,r-ggplot2)
11160 ("r-rcolorbrewer" ,r-rcolorbrewer)
11161 ("r-gridextra" ,r-gridextra)
11162 ("r-gplots" ,r-gplots)
11163 ("r-plyr" ,r-plyr)))
11164 (home-page "https://github.com/rajewsky-lab/dropbead")
11165 (synopsis "Basic exploration and analysis of Drop-seq data")
11166 (description "This package offers a quick and straight-forward way to
11167 explore and perform basic analysis of single cell sequencing data coming from
11168 droplet sequencing. It has been particularly tailored for Drop-seq.")
11169 (license license:gpl3))))
11171 (define htslib-for-sambamba
11172 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11175 (name "htslib-for-sambamba")
11176 (version (string-append "1.3.1-1." (string-take commit 9)))
11180 (uri (git-reference
11181 (url "https://github.com/lomereiter/htslib.git")
11183 (file-name (string-append "htslib-" version "-checkout"))
11186 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11188 `(("autoconf" ,autoconf)
11189 ("automake" ,automake)
11190 ,@(package-native-inputs htslib))))))
11192 (define-public sambamba
11199 (uri (git-reference
11200 (url "https://github.com/lomereiter/sambamba.git")
11201 (commit (string-append "v" version))))
11202 (file-name (string-append name "-" version "-checkout"))
11205 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
11206 (build-system gnu-build-system)
11208 `(#:tests? #f ; there is no test target
11209 #:parallel-build? #f ; not supported
11211 (modify-phases %standard-phases
11212 (delete 'configure)
11213 (add-after 'unpack 'fix-ldc-version
11215 (substitute* "gen_ldc_version_info.py"
11216 (("/usr/bin/env.*") (which "python3")))
11217 (substitute* "Makefile"
11218 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11219 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11221 (add-after 'unpack 'place-biod-and-undead
11222 (lambda* (#:key inputs #:allow-other-keys)
11223 (copy-recursively (assoc-ref inputs "biod") "BioD")
11224 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11226 (add-after 'unpack 'unbundle-prerequisites
11228 (substitute* "Makefile"
11229 (("htslib/libhts.a lz4/lib/liblz4.a")
11231 ((" lz4-static htslib-static") ""))
11234 (lambda* (#:key outputs #:allow-other-keys)
11235 (let* ((out (assoc-ref outputs "out"))
11236 (bin (string-append out "/bin")))
11238 (install-file "bin/sambamba" bin)
11243 ("python" ,python-minimal)
11245 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
11248 (uri (git-reference
11249 (url "https://github.com/biod/BioD.git")
11251 (file-name (string-append "biod-"
11252 (string-take commit 9)
11256 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
11258 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
11261 (uri (git-reference
11262 (url "https://github.com/biod/undeaD.git")
11264 (file-name (string-append "undead-"
11265 (string-take commit 9)
11269 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11272 ("htslib" ,htslib-for-sambamba)))
11273 (home-page "http://lomereiter.github.io/sambamba")
11274 (synopsis "Tools for working with SAM/BAM data")
11275 (description "Sambamba is a high performance modern robust and
11276 fast tool (and library), written in the D programming language, for
11277 working with SAM and BAM files. Current parallelised functionality is
11278 an important subset of samtools functionality, including view, index,
11279 sort, markdup, and depth.")
11280 (license license:gpl2+)))
11282 (define-public ritornello
11284 (name "ritornello")
11288 (uri (git-reference
11289 (url "https://github.com/KlugerLab/Ritornello.git")
11290 (commit (string-append "v" version))))
11291 (file-name (git-file-name name version))
11294 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11295 (build-system gnu-build-system)
11297 `(#:tests? #f ; there are no tests
11299 (modify-phases %standard-phases
11300 (add-after 'unpack 'patch-samtools-references
11301 (lambda* (#:key inputs #:allow-other-keys)
11302 (substitute* '("src/SamStream.h"
11304 (("<sam.h>") "<samtools/sam.h>"))
11306 (delete 'configure)
11308 (lambda* (#:key inputs outputs #:allow-other-keys)
11309 (let* ((out (assoc-ref outputs "out"))
11310 (bin (string-append out "/bin/")))
11312 (install-file "bin/Ritornello" bin)
11315 `(("samtools" ,samtools-0.1)
11319 (home-page "https://github.com/KlugerLab/Ritornello")
11320 (synopsis "Control-free peak caller for ChIP-seq data")
11321 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11322 signal processing that can accurately call binding events without the need to
11323 do a pair total DNA input or IgG control sample. It has been tested for use
11324 with narrow binding events such as transcription factor ChIP-seq.")
11325 (license license:gpl3+)))
11327 (define-public trim-galore
11329 (name "trim-galore")
11334 (uri (git-reference
11335 (url "https://github.com/FelixKrueger/TrimGalore.git")
11337 (file-name (string-append name "-" version "-checkout"))
11340 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11341 (build-system gnu-build-system)
11343 `(#:tests? #f ; no tests
11345 (modify-phases %standard-phases
11346 (delete 'configure)
11348 (add-after 'unpack 'hardcode-tool-references
11349 (lambda* (#:key inputs #:allow-other-keys)
11350 (substitute* "trim_galore"
11351 (("\\$path_to_cutadapt = 'cutadapt'")
11352 (string-append "$path_to_cutadapt = '"
11353 (assoc-ref inputs "cutadapt")
11356 (string-append "| "
11357 (assoc-ref inputs "gzip")
11360 (string-append "\""
11361 (assoc-ref inputs "gzip")
11365 (lambda* (#:key outputs #:allow-other-keys)
11366 (let ((bin (string-append (assoc-ref outputs "out")
11369 (install-file "trim_galore" bin)
11374 ("cutadapt" ,cutadapt)))
11376 `(("unzip" ,unzip)))
11377 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11378 (synopsis "Wrapper around Cutadapt and FastQC")
11379 (description "Trim Galore! is a wrapper script to automate quality and
11380 adapter trimming as well as quality control, with some added functionality to
11381 remove biased methylation positions for RRBS sequence files.")
11382 (license license:gpl3+)))
11384 (define-public gess
11390 (uri (string-append "http://compbio.uthscsa.edu/"
11392 "gess-" version ".src.tar.gz"))
11395 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11396 (build-system gnu-build-system)
11398 `(#:tests? #f ; no tests
11400 (modify-phases %standard-phases
11401 (delete 'configure)
11404 (lambda* (#:key inputs outputs #:allow-other-keys)
11405 (let* ((python (assoc-ref inputs "python"))
11406 (out (assoc-ref outputs "out"))
11407 (bin (string-append out "/bin/"))
11408 (target (string-append
11410 ,(version-major+minor
11411 (package-version python))
11412 "/site-packages/gess/")))
11414 (copy-recursively "." target)
11415 ;; Make GESS.py executable
11416 (chmod (string-append target "GESS.py") #o555)
11417 ;; Add Python shebang to the top and make Matplotlib
11419 (substitute* (string-append target "GESS.py")
11420 (("\"\"\"Description:" line)
11421 (string-append "#!" (which "python") "
11423 matplotlib.use('Agg')
11425 ;; Make sure GESS has all modules in its path
11426 (wrap-program (string-append target "GESS.py")
11427 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11429 (symlink (string-append target "GESS.py")
11430 (string-append bin "GESS.py"))
11433 `(("python" ,python-2)
11434 ("python2-pysam" ,python2-pysam)
11435 ("python2-scipy" ,python2-scipy)
11436 ("python2-numpy" ,python2-numpy)
11437 ("python2-networkx" ,python2-networkx)
11438 ("python2-biopython" ,python2-biopython)))
11439 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11440 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11442 "GESS is an implementation of a novel computational method to detect de
11443 novo exon-skipping events directly from raw RNA-seq data without the prior
11444 knowledge of gene annotation information. GESS stands for the graph-based
11445 exon-skipping scanner detection scheme.")
11446 (license license:bsd-3)))
11448 (define-public phylip
11455 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11456 "download/phylip-" version ".tar.gz"))
11459 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11460 (build-system gnu-build-system)
11462 `(#:tests? #f ; no check target
11463 #:make-flags (list "-f" "Makefile.unx" "install")
11464 #:parallel-build? #f ; not supported
11466 (modify-phases %standard-phases
11467 (add-after 'unpack 'enter-dir
11468 (lambda _ (chdir "src") #t))
11469 (delete 'configure)
11471 (lambda* (#:key inputs outputs #:allow-other-keys)
11472 (let ((target (string-append (assoc-ref outputs "out")
11475 (for-each (lambda (file)
11476 (install-file file target))
11477 (find-files "../exe" ".*")))
11479 (home-page "http://evolution.genetics.washington.edu/phylip/")
11480 (synopsis "Tools for inferring phylogenies")
11481 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11482 programs for inferring phylogenies (evolutionary trees).")
11483 (license license:bsd-2)))
11492 (uri (string-append "https://integrativemodeling.org/"
11493 version "/download/imp-" version ".tar.gz"))
11496 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11497 (build-system cmake-build-system)
11499 `(;; FIXME: Some tests fail because they produce warnings, others fail
11500 ;; because the PYTHONPATH does not include the modeller's directory.
11508 ("python" ,python-2)))
11510 `(("python2-numpy" ,python2-numpy)
11511 ("python2-scipy" ,python2-scipy)
11512 ("python2-pandas" ,python2-pandas)
11513 ("python2-scikit-learn" ,python2-scikit-learn)
11514 ("python2-networkx" ,python2-networkx)))
11515 (home-page "https://integrativemodeling.org")
11516 (synopsis "Integrative modeling platform")
11517 (description "IMP's broad goal is to contribute to a comprehensive
11518 structural characterization of biomolecules ranging in size and complexity
11519 from small peptides to large macromolecular assemblies, by integrating data
11520 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11521 Python toolbox for solving complex modeling problems, and a number of
11522 applications for tackling some common problems in a user-friendly way.")
11523 ;; IMP is largely available under the GNU Lesser GPL; see the file
11524 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11525 ;; available under the GNU GPL (see the file COPYING.GPL).
11526 (license (list license:lgpl2.1+
11529 (define-public tadbit
11535 (uri (git-reference
11536 (url "https://github.com/3DGenomes/TADbit.git")
11537 (commit (string-append "v" version))))
11538 (file-name (git-file-name name version))
11541 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11542 (build-system python-build-system)
11544 `(;; Tests are included and must be run after installation, but
11545 ;; they are incomplete and thus cannot be run.
11549 (modify-phases %standard-phases
11550 (add-after 'unpack 'fix-problems-with-setup.py
11551 (lambda* (#:key outputs #:allow-other-keys)
11552 ;; setup.py opens these files for writing
11553 (chmod "_pytadbit/_version.py" #o664)
11554 (chmod "README.rst" #o664)
11556 ;; Don't attempt to install the bash completions to
11557 ;; the home directory.
11558 (rename-file "extras/.bash_completion"
11560 (substitute* "setup.py"
11561 (("\\(path.expanduser\\('~'\\)")
11562 (string-append "(\""
11563 (assoc-ref outputs "out")
11564 "/etc/bash_completion.d\""))
11565 (("extras/\\.bash_completion")
11569 ;; TODO: add Chimera for visualization
11572 ("python2-scipy" ,python2-scipy)
11573 ("python2-numpy" ,python2-numpy)
11574 ("python2-matplotlib" ,python2-matplotlib)
11575 ("python2-pysam" ,python2-pysam)))
11576 (home-page "https://3dgenomes.github.io/TADbit/")
11577 (synopsis "Analyze, model, and explore 3C-based data")
11579 "TADbit is a complete Python library to deal with all steps to analyze,
11580 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11581 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11582 correct interaction matrices, identify and compare the so-called
11583 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11584 interaction matrices, and finally, extract structural properties from the
11585 models. TADbit is complemented by TADkit for visualizing 3D models.")
11586 (license license:gpl3+)))
11588 (define-public kentutils
11591 ;; 302.1.0 is out, but the only difference is the inclusion of
11592 ;; pre-built binaries.
11593 (version "302.0.0")
11597 (uri (git-reference
11598 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11599 (commit (string-append "v" version))))
11600 (file-name (git-file-name name version))
11603 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11604 (modules '((guix build utils)
11609 ;; Only the contents of the specified directories are free
11610 ;; for all uses, so we remove the rest. "hg/autoSql" and
11611 ;; "hg/autoXml" are nominally free, but they depend on a
11612 ;; library that is built from the sources in "hg/lib",
11613 ;; which is nonfree.
11614 (let ((free (list "." ".."
11615 "utils" "lib" "inc" "tagStorm"
11616 "parasol" "htslib"))
11617 (directory? (lambda (file)
11618 (eq? 'directory (stat:type (stat file))))))
11619 (for-each (lambda (file)
11620 (and (directory? file)
11621 (delete-file-recursively file)))
11622 (map (cut string-append "src/" <>)
11625 (not (member file free)))))))
11626 ;; Only make the utils target, not the userApps target,
11627 ;; because that requires libraries we won't build.
11628 (substitute* "Makefile"
11629 ((" userApps") " utils"))
11630 ;; Only build libraries that are free.
11631 (substitute* "src/makefile"
11632 (("DIRS =.*") "DIRS =\n")
11633 (("cd jkOwnLib.*") "")
11636 (substitute* "src/utils/makefile"
11637 ;; These tools depend on "jkhgap.a", which is part of the
11638 ;; nonfree "src/hg/lib" directory.
11639 (("raSqlQuery") "")
11640 (("pslLiftSubrangeBlat") "")
11642 ;; Do not build UCSC tools, which may require nonfree
11644 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11646 (build-system gnu-build-system)
11648 `( ;; There is no global test target and the test target for
11649 ;; individual tools depends on input files that are not
11653 (modify-phases %standard-phases
11654 (add-after 'unpack 'fix-permissions
11655 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11656 (add-after 'unpack 'fix-paths
11658 (substitute* "Makefile"
11659 (("/bin/echo") (which "echo")))
11661 (add-after 'unpack 'prepare-samtabix
11662 (lambda* (#:key inputs #:allow-other-keys)
11663 (copy-recursively (assoc-ref inputs "samtabix")
11666 (delete 'configure)
11668 (lambda* (#:key outputs #:allow-other-keys)
11669 (let ((bin (string-append (assoc-ref outputs "out")
11671 (copy-recursively "bin" bin))
11677 (uri (git-reference
11678 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11679 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11682 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11688 ("mariadb" ,mariadb)
11689 ("openssl" ,openssl)))
11690 (home-page "http://genome.cse.ucsc.edu/index.html")
11691 (synopsis "Assorted bioinformatics utilities")
11692 (description "This package provides the kentUtils, a selection of
11693 bioinformatics utilities used in combination with the UCSC genome
11695 ;; Only a subset of the sources are released under a non-copyleft
11696 ;; free software license. All other sources are removed in a
11697 ;; snippet. See this bug report for an explanation of how the
11698 ;; license statements apply:
11699 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11700 (license (license:non-copyleft
11701 "http://genome.ucsc.edu/license/"
11702 "The contents of this package are free for all uses."))))
11704 (define-public f-seq
11705 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11709 (version (string-append "1.1-" revision "." (string-take commit 7)))
11712 (uri (git-reference
11713 (url "https://github.com/aboyle/F-seq.git")
11715 (file-name (string-append name "-" version))
11718 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11719 (modules '((guix build utils)))
11720 ;; Remove bundled Java library archives.
11723 (for-each delete-file (find-files "lib" ".*"))
11725 (build-system ant-build-system)
11727 `(#:tests? #f ; no tests included
11729 (modify-phases %standard-phases
11731 (lambda* (#:key inputs outputs #:allow-other-keys)
11732 (let* ((target (assoc-ref outputs "out"))
11733 (bin (string-append target "/bin"))
11734 (doc (string-append target "/share/doc/f-seq"))
11735 (lib (string-append target "/lib")))
11738 (substitute* "bin/linux/fseq"
11739 (("java") (which "java"))
11740 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11741 (string-append (assoc-ref inputs "java-commons-cli")
11742 "/share/java/commons-cli.jar"))
11744 (string-append "REALDIR=" bin "\n")))
11745 (install-file "README.txt" doc)
11746 (install-file "bin/linux/fseq" bin)
11747 (install-file "build~/fseq.jar" lib)
11748 (copy-recursively "lib" lib)
11752 ("java-commons-cli" ,java-commons-cli)))
11753 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11754 (synopsis "Feature density estimator for high-throughput sequence tags")
11756 "F-Seq is a software package that generates a continuous tag sequence
11757 density estimation allowing identification of biologically meaningful sites
11758 such as transcription factor binding sites (ChIP-seq) or regions of open
11759 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11761 (license license:gpl3+))))
11763 (define-public bismark
11770 (uri (git-reference
11771 (url "https://github.com/FelixKrueger/Bismark.git")
11773 (file-name (string-append name "-" version "-checkout"))
11776 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11779 ;; highcharts.js is non-free software. The code is available under
11780 ;; CC-BY-NC or proprietary licenses only.
11781 (delete-file "bismark_sitrep/highcharts.js")
11783 (build-system perl-build-system)
11785 `(#:tests? #f ; there are no tests
11787 (modify-phases %standard-phases
11788 (delete 'configure)
11791 (lambda* (#:key inputs outputs #:allow-other-keys)
11792 (let* ((out (assoc-ref outputs "out"))
11793 (bin (string-append out "/bin"))
11794 (share (string-append out "/share/bismark"))
11795 (docdir (string-append out "/share/doc/bismark"))
11796 (docs '("Docs/Bismark_User_Guide.html"))
11797 (scripts '("bismark"
11798 "bismark_genome_preparation"
11799 "bismark_methylation_extractor"
11802 "coverage2cytosine"
11803 "deduplicate_bismark"
11804 "filter_non_conversion"
11806 "bismark2summary")))
11807 (substitute* "bismark2report"
11808 (("\\$RealBin/bismark_sitrep")
11809 (string-append share "/bismark_sitrep")))
11813 (for-each (lambda (file) (install-file file bin))
11815 (for-each (lambda (file) (install-file file docdir))
11817 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11818 (copy-recursively "bismark_sitrep"
11819 (string-append share "/bismark_sitrep"))
11821 ;; Fix references to gunzip
11822 (substitute* (map (lambda (file)
11823 (string-append bin "/" file))
11826 (string-append "\"" (assoc-ref inputs "gzip")
11827 "/bin/gunzip -c")))
11831 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11832 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11833 (description "Bismark is a program to map bisulfite treated sequencing
11834 reads to a genome of interest and perform methylation calls in a single step.
11835 The output can be easily imported into a genome viewer, such as SeqMonk, and
11836 enables a researcher to analyse the methylation levels of their samples
11837 straight away. Its main features are:
11840 @item Bisulfite mapping and methylation calling in one single step
11841 @item Supports single-end and paired-end read alignments
11842 @item Supports ungapped and gapped alignments
11843 @item Alignment seed length, number of mismatches etc are adjustable
11844 @item Output discriminates between cytosine methylation in CpG, CHG
11847 (license license:gpl3+)))
11849 (define-public paml
11855 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11856 "paml" version ".tgz"))
11859 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11860 (modules '((guix build utils)))
11861 ;; Remove Windows binaries
11864 (for-each delete-file (find-files "." "\\.exe$"))
11866 (build-system gnu-build-system)
11868 `(#:tests? #f ; there are no tests
11869 #:make-flags '("CC=gcc")
11871 (modify-phases %standard-phases
11872 (replace 'configure
11874 (substitute* "src/BFdriver.c"
11875 (("/bin/bash") (which "bash")))
11879 (lambda* (#:key outputs #:allow-other-keys)
11880 (let ((tools '("baseml" "basemlg" "codeml"
11881 "pamp" "evolver" "yn00" "chi2"))
11882 (bin (string-append (assoc-ref outputs "out") "/bin"))
11883 (docdir (string-append (assoc-ref outputs "out")
11884 "/share/doc/paml")))
11886 (for-each (lambda (file) (install-file file bin)) tools)
11887 (copy-recursively "../doc" docdir)
11889 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11890 (synopsis "Phylogentic analysis by maximum likelihood")
11891 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11892 contains a few programs for model fitting and phylogenetic tree reconstruction
11893 using nucleotide or amino-acid sequence data.")
11895 (license license:gpl3)))
11897 (define-public kallisto
11903 (uri (git-reference
11904 (url "https://github.com/pachterlab/kallisto.git")
11905 (commit (string-append "v" version))))
11906 (file-name (git-file-name name version))
11909 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11910 (build-system cmake-build-system)
11912 `(#:tests? #f ; no "check" target
11914 (modify-phases %standard-phases
11915 (add-after 'unpack 'do-not-use-bundled-htslib
11917 (substitute* "CMakeLists.txt"
11918 (("^ExternalProject_Add" m)
11919 (string-append "if (NEVER)\n" m))
11921 (string-append ")\nendif(NEVER)"))
11922 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11923 (string-append "# " m)))
11924 (substitute* "src/CMakeLists.txt"
11925 (("target_link_libraries\\(kallisto kallisto_core pthread \
11926 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11927 "target_link_libraries(kallisto kallisto_core pthread hts)")
11928 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11934 (home-page "http://pachterlab.github.io/kallisto/")
11935 (synopsis "Near-optimal RNA-Seq quantification")
11937 "Kallisto is a program for quantifying abundances of transcripts from
11938 RNA-Seq data, or more generally of target sequences using high-throughput
11939 sequencing reads. It is based on the novel idea of pseudoalignment for
11940 rapidly determining the compatibility of reads with targets, without the need
11941 for alignment. Pseudoalignment of reads preserves the key information needed
11942 for quantification, and kallisto is therefore not only fast, but also as
11943 accurate as existing quantification tools.")
11944 (license license:bsd-2)))
11946 (define-public libgff
11952 (uri (git-reference
11953 (url "https://github.com/Kingsford-Group/libgff.git")
11954 (commit (string-append "v" version))))
11955 (file-name (git-file-name name version))
11958 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11959 (build-system cmake-build-system)
11960 (arguments `(#:tests? #f)) ; no tests included
11961 (home-page "https://github.com/Kingsford-Group/libgff")
11962 (synopsis "Parser library for reading/writing GFF files")
11963 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11964 code that is used in the Cufflinks codebase. The goal of this library is to
11965 provide this functionality without the necessity of drawing in a heavy-weight
11966 dependency like SeqAn.")
11967 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11969 (define-public libdivsufsort
11971 (name "libdivsufsort")
11975 (uri (git-reference
11976 (url "https://github.com/y-256/libdivsufsort.git")
11978 (file-name (git-file-name name version))
11981 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11982 (build-system cmake-build-system)
11984 '(#:tests? #f ; there are no tests
11986 ;; Needed for rapmap and sailfish.
11987 '("-DBUILD_DIVSUFSORT64=ON")))
11988 (home-page "https://github.com/y-256/libdivsufsort")
11989 (synopsis "Lightweight suffix-sorting library")
11990 (description "libdivsufsort is a software library that implements a
11991 lightweight suffix array construction algorithm. This library provides a
11992 simple and an efficient C API to construct a suffix array and a
11993 Burrows-Wheeler transformed string from a given string over a constant-size
11994 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11995 bytes of memory space, where n is the length of the string.")
11996 (license license:expat)))
11998 (define-public sailfish
12004 (uri (git-reference
12005 (url "https://github.com/kingsfordgroup/sailfish.git")
12006 (commit (string-append "v" version))))
12007 (file-name (git-file-name name version))
12010 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
12011 (modules '((guix build utils)))
12014 ;; Delete bundled headers for eigen3.
12015 (delete-file-recursively "include/eigen3/")
12017 (build-system cmake-build-system)
12019 `(#:configure-flags
12020 (list (string-append "-DBOOST_INCLUDEDIR="
12021 (assoc-ref %build-inputs "boost")
12023 (string-append "-DBOOST_LIBRARYDIR="
12024 (assoc-ref %build-inputs "boost")
12026 (string-append "-DBoost_LIBRARIES="
12027 "-lboost_iostreams "
12028 "-lboost_filesystem "
12033 "-lboost_program_options")
12034 "-DBoost_FOUND=TRUE"
12035 ;; Don't download RapMap---we already have it!
12036 "-DFETCHED_RAPMAP=1")
12037 ;; Tests must be run after installation and the location of the test
12038 ;; data file must be overridden. But the tests fail. It looks like
12039 ;; they are not really meant to be run.
12042 (modify-phases %standard-phases
12043 ;; Boost cannot be found, even though it's right there.
12044 (add-after 'unpack 'do-not-look-for-boost
12045 (lambda* (#:key inputs #:allow-other-keys)
12046 (substitute* "CMakeLists.txt"
12047 (("find_package\\(Boost 1\\.53\\.0") "#"))
12049 (add-after 'unpack 'do-not-assign-to-macro
12051 (substitute* "include/spdlog/details/format.cc"
12052 (("const unsigned CHAR_WIDTH = 1;") ""))
12054 (add-after 'unpack 'prepare-rapmap
12055 (lambda* (#:key inputs #:allow-other-keys)
12056 (let ((src "external/install/src/rapmap/")
12057 (include "external/install/include/rapmap/")
12058 (rapmap (assoc-ref inputs "rapmap")))
12059 (mkdir-p "/tmp/rapmap")
12061 (assoc-ref inputs "rapmap")
12063 "--strip-components=1")
12066 (for-each (lambda (file)
12067 (install-file file src))
12068 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12069 (copy-recursively "/tmp/rapmap/include" include))
12071 (add-after 'unpack 'use-system-libraries
12072 (lambda* (#:key inputs #:allow-other-keys)
12073 (substitute* '("src/SailfishIndexer.cpp"
12074 "src/SailfishUtils.cpp"
12075 "src/SailfishQuantify.cpp"
12076 "src/FASTAParser.cpp"
12078 "include/SailfishUtils.hpp"
12079 "include/SailfishIndex.hpp"
12080 "include/CollapsedEMOptimizer.hpp"
12081 "src/CollapsedEMOptimizer.cpp")
12082 (("#include \"jellyfish/config.h\"") ""))
12083 (substitute* "src/CMakeLists.txt"
12084 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12085 (string-append (assoc-ref inputs "jellyfish")
12086 "/include/jellyfish-" ,(package-version jellyfish)))
12087 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12088 (string-append (assoc-ref inputs "jellyfish")
12089 "/lib/libjellyfish-2.0.a"))
12090 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12091 (string-append (assoc-ref inputs "libdivsufsort")
12092 "/lib/libdivsufsort.so"))
12093 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12094 (string-append (assoc-ref inputs "libdivsufsort")
12095 "/lib/libdivsufsort64.so")))
12096 (substitute* "CMakeLists.txt"
12097 ;; Don't prefer static libs
12098 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12099 (("find_package\\(Jellyfish.*") "")
12100 (("ExternalProject_Add\\(libjellyfish") "message(")
12101 (("ExternalProject_Add\\(libgff") "message(")
12102 (("ExternalProject_Add\\(libsparsehash") "message(")
12103 (("ExternalProject_Add\\(libdivsufsort") "message("))
12105 ;; Ensure that Eigen headers can be found
12106 (setenv "CPLUS_INCLUDE_PATH"
12107 (string-append (getenv "CPLUS_INCLUDE_PATH")
12109 (assoc-ref inputs "eigen")
12110 "/include/eigen3"))
12115 ("jemalloc" ,jemalloc)
12116 ("jellyfish" ,jellyfish)
12117 ("sparsehash" ,sparsehash)
12120 (uri (git-reference
12121 (url "https://github.com/COMBINE-lab/RapMap.git")
12122 (commit (string-append "sf-v" version))))
12123 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12126 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12127 (modules '((guix build utils)))
12128 ;; These files are expected to be excluded.
12130 '(begin (delete-file-recursively "include/spdlog")
12131 (for-each delete-file '("include/xxhash.h"
12134 ("libdivsufsort" ,libdivsufsort)
12139 `(("pkg-config" ,pkg-config)))
12140 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12141 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12142 (description "Sailfish is a tool for genomic transcript quantification
12143 from RNA-seq data. It requires a set of target transcripts (either from a
12144 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12145 fasta file containing your reference transcripts and a (set of) fasta/fastq
12146 file(s) containing your reads.")
12147 (license license:gpl3+)))
12149 (define libstadenio-for-salmon
12151 (name "libstadenio")
12155 (uri (git-reference
12156 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12157 (commit (string-append "v" version))))
12158 (file-name (string-append name "-" version "-checkout"))
12161 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12162 (build-system gnu-build-system)
12163 (arguments '(#:parallel-tests? #f)) ; not supported
12167 `(("perl" ,perl))) ; for tests
12168 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12169 (synopsis "General purpose trace and experiment file library")
12170 (description "This package provides a library of file reading and writing
12171 code to provide a general purpose Trace file (and Experiment File) reading
12174 The following file formats are supported:
12177 @item SCF trace files
12178 @item ABI trace files
12179 @item ALF trace files
12180 @item ZTR trace files
12181 @item SFF trace archives
12182 @item SRF trace archives
12183 @item Experiment files
12184 @item Plain text files
12185 @item SAM/BAM sequence files
12186 @item CRAM sequence files
12188 (license license:bsd-3)))
12190 (define spdlog-for-salmon
12196 (uri (git-reference
12197 (url "https://github.com/COMBINE-lab/spdlog.git")
12198 (commit (string-append "v" version))))
12199 (file-name (string-append name "-" version "-checkout"))
12202 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12203 (build-system cmake-build-system)
12204 (home-page "https://github.com/COMBINE-lab/spdlog")
12205 (synopsis "Very fast C++ logging library")
12206 (description "Spdlog is a very fast header-only C++ logging library with
12207 performance as its primary goal.")
12208 (license license:expat)))
12210 ;; This is a modified variant of bwa for use with Salmon. It installs a
12211 ;; library to avoid having to build this as part of Salmon.
12212 (define bwa-for-salmon
12213 (package (inherit bwa)
12215 (version "0.7.12.5")
12218 (uri (git-reference
12219 (url "https://github.com/COMBINE-lab/bwa.git")
12220 (commit (string-append "v" version))))
12221 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12224 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12225 (build-system gnu-build-system)
12227 '(#:tests? #f ;no "check" target
12229 (modify-phases %standard-phases
12231 (lambda* (#:key outputs #:allow-other-keys)
12232 (let* ((out (assoc-ref outputs "out"))
12233 (bin (string-append out "/bin"))
12234 (lib (string-append out "/lib"))
12235 (doc (string-append out "/share/doc/bwa"))
12236 (man (string-append out "/share/man/man1"))
12237 (inc (string-append out "/include/bwa")))
12238 (install-file "bwa" bin)
12239 (install-file "README.md" doc)
12240 (install-file "bwa.1" man)
12241 (install-file "libbwa.a" lib)
12244 (for-each (lambda (file)
12245 (install-file file inc))
12246 (find-files "." "\\.h$")))
12248 ;; no "configure" script
12249 (delete 'configure))))))
12251 (define-public salmon
12257 (uri (git-reference
12258 (url "https://github.com/COMBINE-lab/salmon.git")
12259 (commit (string-append "v" version))))
12260 (file-name (string-append name "-" version "-checkout"))
12263 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12264 (modules '((guix build utils)))
12267 ;; Delete bundled headers for eigen3.
12268 (delete-file-recursively "include/eigen3/")
12270 (build-system cmake-build-system)
12272 `(#:configure-flags
12273 (list (string-append "-DBOOST_INCLUDEDIR="
12274 (assoc-ref %build-inputs "boost")
12276 (string-append "-DBOOST_LIBRARYDIR="
12277 (assoc-ref %build-inputs "boost")
12279 (string-append "-DBoost_LIBRARIES="
12280 "-lboost_iostreams "
12281 "-lboost_filesystem "
12286 "-lboost_program_options")
12287 "-DBoost_FOUND=TRUE"
12288 "-DTBB_LIBRARIES=tbb tbbmalloc"
12289 ;; Don't download RapMap---we already have it!
12290 "-DFETCHED_RAPMAP=1")
12292 (modify-phases %standard-phases
12293 ;; Boost cannot be found, even though it's right there.
12294 (add-after 'unpack 'do-not-look-for-boost
12295 (lambda* (#:key inputs #:allow-other-keys)
12296 (substitute* "CMakeLists.txt"
12297 (("find_package\\(Boost 1\\.53\\.0") "#"))
12299 (add-after 'unpack 'do-not-phone-home
12301 (substitute* "src/Salmon.cpp"
12302 (("getVersionMessage\\(\\)") "\"\""))
12304 (add-after 'unpack 'prepare-rapmap
12305 (lambda* (#:key inputs #:allow-other-keys)
12306 (let ((src "external/install/src/rapmap/")
12307 (include "external/install/include/rapmap/")
12308 (rapmap (assoc-ref inputs "rapmap")))
12311 (for-each (lambda (file)
12312 (install-file file src))
12313 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12314 (copy-recursively (string-append rapmap "/include") include)
12315 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12316 "external/install/include/rapmap/FastxParser.hpp"
12317 "external/install/include/rapmap/concurrentqueue.h"
12318 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12319 "external/install/src/rapmap/FastxParser.cpp"
12320 "external/install/src/rapmap/xxhash.c")))
12322 (add-after 'unpack 'use-system-libraries
12323 (lambda* (#:key inputs #:allow-other-keys)
12324 (substitute* "src/CMakeLists.txt"
12325 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12326 (string-append (assoc-ref inputs "jellyfish")
12327 "/include/jellyfish-" ,(package-version jellyfish)))
12328 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12329 (string-append (assoc-ref inputs "jellyfish")
12330 "/lib/libjellyfish-2.0.a"))
12331 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12332 (string-append (assoc-ref inputs "libdivsufsort")
12333 "/lib/libdivsufsort.so"))
12334 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12335 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12336 "/lib/libstaden-read.a"))
12337 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12338 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12339 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12340 (string-append (assoc-ref inputs "libdivsufsort")
12341 "/lib/libdivsufsort64.so")))
12342 (substitute* "CMakeLists.txt"
12343 ;; Don't prefer static libs
12344 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12345 (("set\\(TBB_LIBRARIES") "message(")
12346 (("find_package\\(Jellyfish.*") "")
12347 (("ExternalProject_Add\\(libcereal") "message(")
12348 (("ExternalProject_Add\\(libbwa") "message(")
12349 (("ExternalProject_Add\\(libjellyfish") "message(")
12350 (("ExternalProject_Add\\(libgff") "message(")
12351 (("ExternalProject_Add\\(libtbb") "message(")
12352 (("ExternalProject_Add\\(libspdlog") "message(")
12353 (("ExternalProject_Add\\(libdivsufsort") "message(")
12354 (("ExternalProject_Add\\(libstadenio") "message(")
12355 (("ExternalProject_Add_Step\\(") "message("))
12357 ;; Ensure that all headers can be found
12358 (setenv "CPLUS_INCLUDE_PATH"
12359 (string-append (getenv "CPLUS_INCLUDE_PATH")
12361 (assoc-ref inputs "bwa")
12364 (assoc-ref inputs "eigen")
12365 "/include/eigen3"))
12367 (string-append (assoc-ref inputs "bwa")
12370 (assoc-ref inputs "eigen")
12371 "/include/eigen3"))
12373 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12374 ;; run. It only exists after the install phase.
12375 (add-after 'unpack 'fix-tests
12377 (substitute* "src/CMakeLists.txt"
12378 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12379 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12383 ("bwa" ,bwa-for-salmon)
12389 (uri (git-reference
12390 (url "https://github.com/COMBINE-lab/RapMap.git")
12391 (commit (string-append "salmon-v" version))))
12392 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12395 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12396 ("jemalloc" ,jemalloc)
12397 ("jellyfish" ,jellyfish)
12400 ("libdivsufsort" ,libdivsufsort)
12401 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12402 ("spdlog-for-salmon" ,spdlog-for-salmon)
12405 (home-page "https://github.com/COMBINE-lab/salmon")
12406 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12407 (description "Salmon is a program to produce highly-accurate,
12408 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12409 its accuracy and speed via a number of different innovations, including the
12410 use of lightweight alignments (accurate but fast-to-compute proxies for
12411 traditional read alignments) and massively-parallel stochastic collapsed
12412 variational inference.")
12413 (license license:gpl3+)))
12415 (define-public python-loompy
12417 (name "python-loompy")
12422 (uri (pypi-uri "loompy" version))
12425 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12426 (build-system python-build-system)
12427 ;; There are no tests
12428 (arguments '(#:tests? #f))
12430 `(("python-h5py" ,python-h5py)
12431 ("python-numpy" ,python-numpy)
12432 ("python-scipy" ,python-scipy)))
12433 (home-page "https://github.com/linnarsson-lab/loompy")
12434 (synopsis "Work with .loom files for single-cell RNA-seq data")
12435 (description "The loom file format is an efficient format for very large
12436 omics datasets, consisting of a main matrix, optional additional layers, a
12437 variable number of row and column annotations. Loom also supports sparse
12438 graphs. This library makes it easy to work with @file{.loom} files for
12439 single-cell RNA-seq data.")
12440 (license license:bsd-3)))
12442 ;; We cannot use the latest commit because it requires Java 9.
12443 (define-public java-forester
12444 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12447 (name "java-forester")
12448 (version (string-append "0-" revision "." (string-take commit 7)))
12451 (uri (git-reference
12452 (url "https://github.com/cmzmasek/forester.git")
12454 (file-name (string-append name "-" version "-checkout"))
12457 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12458 (modules '((guix build utils)))
12461 ;; Delete bundled jars and pre-built classes
12462 (delete-file-recursively "forester/java/resources")
12463 (delete-file-recursively "forester/java/classes")
12464 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12465 ;; Delete bundled applications
12466 (delete-file-recursively "forester_applications")
12468 (build-system ant-build-system)
12470 `(#:tests? #f ; there are none
12472 #:modules ((guix build ant-build-system)
12474 (guix build java-utils)
12478 (modify-phases %standard-phases
12479 (add-after 'unpack 'chdir
12480 (lambda _ (chdir "forester/java") #t))
12481 (add-after 'chdir 'fix-dependencies
12483 (chmod "build.xml" #o664)
12484 (call-with-output-file "build.xml.new"
12488 (with-input-from-file "build.xml"
12489 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12490 `(;; Remove all unjar tags to avoid repacking classes.
12491 (unjar . ,(lambda _ '()))
12492 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12493 (*text* . ,(lambda (_ txt) txt))))
12495 (rename-file "build.xml.new" "build.xml")
12497 ;; FIXME: itext is difficult to package as it depends on a few
12498 ;; unpackaged libraries.
12499 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12501 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12502 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12503 (("pdf_written_to = PdfExporter.*")
12504 "throw new IOException(\"PDF export is not available.\");"))
12506 ;; There is no install target
12507 (replace 'install (install-jars ".")))))
12509 `(("java-commons-codec" ,java-commons-codec)
12510 ("java-openchart2" ,java-openchart2)))
12511 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12512 (synopsis "Phylogenomics libraries for Java")
12513 (description "Forester is a collection of Java libraries for
12514 phylogenomics and evolutionary biology research. It includes support for
12515 reading, writing, and exporting phylogenetic trees.")
12516 (license license:lgpl2.1+))))
12518 (define-public java-forester-1.005
12520 (name "java-forester")
12524 (uri (string-append "http://search.maven.org/remotecontent?"
12525 "filepath=org/biojava/thirdparty/forester/"
12526 version "/forester-" version "-sources.jar"))
12527 (file-name (string-append name "-" version ".jar"))
12530 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12531 (build-system ant-build-system)
12533 `(#:tests? #f ; there are none
12535 #:modules ((guix build ant-build-system)
12537 (guix build java-utils)
12541 (modify-phases %standard-phases
12542 (add-after 'unpack 'fix-dependencies
12543 (lambda* (#:key inputs #:allow-other-keys)
12544 (call-with-output-file "build.xml"
12548 (with-input-from-file "src/build.xml"
12549 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12550 `(;; Remove all unjar tags to avoid repacking classes.
12551 (unjar . ,(lambda _ '()))
12552 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12553 (*text* . ,(lambda (_ txt) txt))))
12555 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12556 "synth_look_and_feel_1.xml")
12557 (copy-file (assoc-ref inputs "phyloxml.xsd")
12559 (substitute* "build.xml"
12560 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12561 "synth_look_and_feel_1.xml")
12562 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12565 ;; FIXME: itext is difficult to package as it depends on a few
12566 ;; unpackaged libraries.
12567 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12569 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12570 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12571 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12572 (("pdf_written_to = PdfExporter.*")
12573 "throw new IOException(\"PDF export is not available.\"); /*")
12574 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12575 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12577 (add-after 'unpack 'delete-pre-built-classes
12578 (lambda _ (delete-file-recursively "src/classes") #t))
12579 ;; There is no install target
12580 (replace 'install (install-jars ".")))))
12582 `(("java-commons-codec" ,java-commons-codec)
12583 ("java-openchart2" ,java-openchart2)))
12584 ;; The source archive does not contain the resources.
12589 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12590 "b61cc2dcede0bede317db362472333115756b8c6/"
12591 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12592 (file-name (string-append name "-phyloxml-" version ".xsd"))
12595 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12596 ("synth_look_and_feel_1.xml"
12599 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12600 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12601 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12602 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12605 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12606 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12607 (synopsis "Phylogenomics libraries for Java")
12608 (description "Forester is a collection of Java libraries for
12609 phylogenomics and evolutionary biology research. It includes support for
12610 reading, writing, and exporting phylogenetic trees.")
12611 (license license:lgpl2.1+)))
12613 (define-public java-biojava-core
12615 (name "java-biojava-core")
12619 (uri (git-reference
12620 (url "https://github.com/biojava/biojava")
12621 (commit (string-append "biojava-" version))))
12622 (file-name (string-append name "-" version "-checkout"))
12625 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12626 (build-system ant-build-system)
12629 #:jar-name "biojava-core.jar"
12630 #:source-dir "biojava-core/src/main/java/"
12631 #:test-dir "biojava-core/src/test"
12632 ;; These tests seem to require internet access.
12633 #:test-exclude (list "**/SearchIOTest.java"
12634 "**/BlastXMLParserTest.java"
12635 "**/GenbankCookbookTest.java"
12636 "**/GenbankProxySequenceReaderTest.java")
12638 (modify-phases %standard-phases
12639 (add-before 'build 'copy-resources
12641 (copy-recursively "biojava-core/src/main/resources"
12644 (add-before 'check 'copy-test-resources
12646 (copy-recursively "biojava-core/src/test/resources"
12647 "build/test-classes")
12650 `(("java-log4j-api" ,java-log4j-api)
12651 ("java-log4j-core" ,java-log4j-core)
12652 ("java-slf4j-api" ,java-slf4j-api)
12653 ("java-slf4j-simple" ,java-slf4j-simple)))
12655 `(("java-junit" ,java-junit)
12656 ("java-hamcrest-core" ,java-hamcrest-core)))
12657 (home-page "http://biojava.org")
12658 (synopsis "Core libraries of Java framework for processing biological data")
12659 (description "BioJava is a project dedicated to providing a Java framework
12660 for processing biological data. It provides analytical and statistical
12661 routines, parsers for common file formats, reference implementations of
12662 popular algorithms, and allows the manipulation of sequences and 3D
12663 structures. The goal of the biojava project is to facilitate rapid
12664 application development for bioinformatics.
12666 This package provides the core libraries.")
12667 (license license:lgpl2.1+)))
12669 (define-public java-biojava-phylo
12670 (package (inherit java-biojava-core)
12671 (name "java-biojava-phylo")
12672 (build-system ant-build-system)
12675 #:jar-name "biojava-phylo.jar"
12676 #:source-dir "biojava-phylo/src/main/java/"
12677 #:test-dir "biojava-phylo/src/test"
12679 (modify-phases %standard-phases
12680 (add-before 'build 'copy-resources
12682 (copy-recursively "biojava-phylo/src/main/resources"
12685 (add-before 'check 'copy-test-resources
12687 (copy-recursively "biojava-phylo/src/test/resources"
12688 "build/test-classes")
12691 `(("java-log4j-api" ,java-log4j-api)
12692 ("java-log4j-core" ,java-log4j-core)
12693 ("java-slf4j-api" ,java-slf4j-api)
12694 ("java-slf4j-simple" ,java-slf4j-simple)
12695 ("java-biojava-core" ,java-biojava-core)
12696 ("java-forester" ,java-forester)))
12698 `(("java-junit" ,java-junit)
12699 ("java-hamcrest-core" ,java-hamcrest-core)))
12700 (home-page "http://biojava.org")
12701 (synopsis "Biojava interface to the forester phylogenomics library")
12702 (description "The phylo module provides a biojava interface layer to the
12703 forester phylogenomics library for constructing phylogenetic trees.")))
12705 (define-public java-biojava-alignment
12706 (package (inherit java-biojava-core)
12707 (name "java-biojava-alignment")
12708 (build-system ant-build-system)
12711 #:jar-name "biojava-alignment.jar"
12712 #:source-dir "biojava-alignment/src/main/java/"
12713 #:test-dir "biojava-alignment/src/test"
12715 (modify-phases %standard-phases
12716 (add-before 'build 'copy-resources
12718 (copy-recursively "biojava-alignment/src/main/resources"
12721 (add-before 'check 'copy-test-resources
12723 (copy-recursively "biojava-alignment/src/test/resources"
12724 "build/test-classes")
12727 `(("java-log4j-api" ,java-log4j-api)
12728 ("java-log4j-core" ,java-log4j-core)
12729 ("java-slf4j-api" ,java-slf4j-api)
12730 ("java-slf4j-simple" ,java-slf4j-simple)
12731 ("java-biojava-core" ,java-biojava-core)
12732 ("java-biojava-phylo" ,java-biojava-phylo)
12733 ("java-forester" ,java-forester)))
12735 `(("java-junit" ,java-junit)
12736 ("java-hamcrest-core" ,java-hamcrest-core)))
12737 (home-page "http://biojava.org")
12738 (synopsis "Biojava API for genetic sequence alignment")
12739 (description "The alignment module of BioJava provides an API that
12743 @item implementations of dynamic programming algorithms for sequence
12745 @item reading and writing of popular alignment file formats;
12746 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12749 (define-public java-biojava-core-4.0
12750 (package (inherit java-biojava-core)
12751 (name "java-biojava-core")
12755 (uri (git-reference
12756 (url "https://github.com/biojava/biojava")
12757 (commit (string-append "biojava-" version))))
12758 (file-name (string-append name "-" version "-checkout"))
12761 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12763 (define-public java-biojava-phylo-4.0
12764 (package (inherit java-biojava-core-4.0)
12765 (name "java-biojava-phylo")
12766 (build-system ant-build-system)
12769 #:jar-name "biojava-phylo.jar"
12770 #:source-dir "biojava-phylo/src/main/java/"
12771 #:test-dir "biojava-phylo/src/test"
12773 (modify-phases %standard-phases
12774 (add-before 'build 'copy-resources
12776 (copy-recursively "biojava-phylo/src/main/resources"
12779 (add-before 'check 'copy-test-resources
12781 (copy-recursively "biojava-phylo/src/test/resources"
12782 "build/test-classes")
12785 `(("java-log4j-api" ,java-log4j-api)
12786 ("java-log4j-core" ,java-log4j-core)
12787 ("java-slf4j-api" ,java-slf4j-api)
12788 ("java-slf4j-simple" ,java-slf4j-simple)
12789 ("java-biojava-core" ,java-biojava-core-4.0)
12790 ("java-forester" ,java-forester-1.005)))
12792 `(("java-junit" ,java-junit)
12793 ("java-hamcrest-core" ,java-hamcrest-core)))
12794 (home-page "http://biojava.org")
12795 (synopsis "Biojava interface to the forester phylogenomics library")
12796 (description "The phylo module provides a biojava interface layer to the
12797 forester phylogenomics library for constructing phylogenetic trees.")))
12799 (define-public java-biojava-alignment-4.0
12800 (package (inherit java-biojava-core-4.0)
12801 (name "java-biojava-alignment")
12802 (build-system ant-build-system)
12805 #:jar-name "biojava-alignment.jar"
12806 #:source-dir "biojava-alignment/src/main/java/"
12807 #:test-dir "biojava-alignment/src/test"
12809 (modify-phases %standard-phases
12810 (add-before 'build 'copy-resources
12812 (copy-recursively "biojava-alignment/src/main/resources"
12815 (add-before 'check 'copy-test-resources
12817 (copy-recursively "biojava-alignment/src/test/resources"
12818 "build/test-classes")
12821 `(("java-log4j-api" ,java-log4j-api)
12822 ("java-log4j-core" ,java-log4j-core)
12823 ("java-slf4j-api" ,java-slf4j-api)
12824 ("java-slf4j-simple" ,java-slf4j-simple)
12825 ("java-biojava-core" ,java-biojava-core-4.0)
12826 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12827 ("java-forester" ,java-forester-1.005)))
12829 `(("java-junit" ,java-junit)
12830 ("java-hamcrest-core" ,java-hamcrest-core)))
12831 (home-page "http://biojava.org")
12832 (synopsis "Biojava API for genetic sequence alignment")
12833 (description "The alignment module of BioJava provides an API that
12837 @item implementations of dynamic programming algorithms for sequence
12839 @item reading and writing of popular alignment file formats;
12840 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12843 (define-public dropseq-tools
12845 (name "dropseq-tools")
12850 (uri "http://mccarrolllab.com/download/1276/")
12851 (file-name (string-append "dropseq-tools-" version ".zip"))
12854 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12855 ;; Delete bundled libraries
12856 (modules '((guix build utils)))
12859 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12860 (delete-file-recursively "3rdParty")
12862 (build-system ant-build-system)
12864 `(#:tests? #f ; test data are not included
12865 #:test-target "test"
12866 #:build-target "all"
12867 #:source-dir "public/src/"
12870 (list (string-append "-Dpicard.executable.dir="
12871 (assoc-ref %build-inputs "java-picard")
12873 #:modules ((ice-9 match)
12876 (guix build java-utils)
12877 (guix build ant-build-system))
12879 (modify-phases %standard-phases
12880 ;; FIXME: fails with "java.io.FileNotFoundException:
12881 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12882 (delete 'generate-jar-indices)
12883 ;; All dependencies must be linked to "lib", because that's where
12884 ;; they will be searched for when the Class-Path property of the
12885 ;; manifest is computed.
12886 (add-after 'unpack 'record-references
12887 (lambda* (#:key inputs #:allow-other-keys)
12888 (mkdir-p "jar/lib")
12889 (let ((dirs (filter-map (match-lambda
12891 (if (and (string-prefix? "java-" name)
12892 (not (string=? name "java-testng")))
12895 (for-each (lambda (jar)
12896 (symlink jar (string-append "jar/lib/" (basename jar))))
12897 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12900 ;; There is no installation target
12902 (lambda* (#:key inputs outputs #:allow-other-keys)
12903 (let* ((out (assoc-ref outputs "out"))
12904 (bin (string-append out "/bin"))
12905 (share (string-append out "/share/java/"))
12906 (lib (string-append share "/lib/"))
12907 (scripts (list "BAMTagHistogram"
12908 "BAMTagofTagCounts"
12909 "BaseDistributionAtReadPosition"
12910 "CollapseBarcodesInPlace"
12911 "CollapseTagWithContext"
12913 "CreateIntervalsFiles"
12914 "DetectBeadSynthesisErrors"
12915 "DigitalExpression"
12916 "Drop-seq_alignment.sh"
12919 "GatherGeneGCLength"
12920 "GatherMolecularBarcodeDistributionByGene"
12921 "GatherReadQualityMetrics"
12924 "SelectCellsByNumTranscripts"
12925 "SingleCellRnaSeqMetricsCollector"
12926 "TagBamWithReadSequenceExtended"
12927 "TagReadWithGeneExon"
12928 "TagReadWithInterval"
12929 "TrimStartingSequence"
12930 "ValidateReference")))
12931 (for-each mkdir-p (list bin share lib))
12932 (install-file "dist/dropseq.jar" share)
12933 (for-each (lambda (script)
12934 (chmod script #o555)
12935 (install-file script bin))
12937 (substitute* (map (lambda (script)
12938 (string-append bin "/" script))
12940 (("^java") (which "java"))
12941 (("jar_deploy_dir=.*")
12942 (string-append "jar_deploy_dir=" share "\n"))))
12944 ;; FIXME: We do this after stripping jars because we don't want it to
12945 ;; copy all these jars and strip them. We only want to install
12946 ;; links. Arguably, this is a problem with the ant-build-system.
12947 (add-after 'strip-jar-timestamps 'install-links
12948 (lambda* (#:key outputs #:allow-other-keys)
12949 (let* ((out (assoc-ref outputs "out"))
12950 (share (string-append out "/share/java/"))
12951 (lib (string-append share "/lib/")))
12952 (for-each (lambda (jar)
12953 (symlink (readlink jar)
12954 (string-append lib (basename jar))))
12955 (find-files "jar/lib" "\\.jar$")))
12958 `(("jdk" ,icedtea-8)
12959 ("java-picard" ,java-picard-2.10.3)
12960 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12961 ("java-commons-math3" ,java-commons-math3)
12962 ("java-commons-jexl2" ,java-commons-jexl-2)
12963 ("java-commons-collections4" ,java-commons-collections4)
12964 ("java-commons-lang2" ,java-commons-lang)
12965 ("java-commons-io" ,java-commons-io)
12966 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12967 ("java-guava" ,java-guava)
12968 ("java-la4j" ,java-la4j)
12969 ("java-biojava-core" ,java-biojava-core-4.0)
12970 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12971 ("java-jdistlib" ,java-jdistlib)
12972 ("java-simple-xml" ,java-simple-xml)
12973 ("java-snakeyaml" ,java-snakeyaml)))
12976 ("java-testng" ,java-testng)))
12977 (home-page "http://mccarrolllab.com/dropseq/")
12978 (synopsis "Tools for Drop-seq analyses")
12979 (description "Drop-seq is a technology to enable biologists to
12980 analyze RNA expression genome-wide in thousands of individual cells at
12981 once. This package provides tools to perform Drop-seq analyses.")
12982 (license license:expat)))
12984 (define-public pigx-rnaseq
12986 (name "pigx-rnaseq")
12990 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12991 "releases/download/v" version
12992 "/pigx_rnaseq-" version ".tar.gz"))
12995 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12996 (build-system gnu-build-system)
12998 `(#:parallel-tests? #f ; not supported
13000 (modify-phases %standard-phases
13001 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
13002 (add-after 'unpack 'disable-resource-intensive-test
13004 (substitute* "Makefile.in"
13005 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
13006 (("^ tests/test_multiqc/test.sh") "")
13007 (("^ test.sh") ""))
13011 ("snakemake" ,snakemake)
13013 ("multiqc" ,multiqc)
13015 ("trim-galore" ,trim-galore)
13017 ("samtools" ,samtools)
13018 ("bedtools" ,bedtools)
13019 ("r-minimal" ,r-minimal)
13020 ("r-rmarkdown" ,r-rmarkdown)
13021 ("r-ggplot2" ,r-ggplot2)
13022 ("r-ggrepel" ,r-ggrepel)
13023 ("r-gprofiler" ,r-gprofiler)
13024 ("r-deseq2" ,r-deseq2)
13026 ("r-knitr" ,r-knitr)
13027 ("r-pheatmap" ,r-pheatmap)
13028 ("r-corrplot" ,r-corrplot)
13029 ("r-reshape2" ,r-reshape2)
13030 ("r-plotly" ,r-plotly)
13031 ("r-scales" ,r-scales)
13032 ("r-summarizedexperiment" ,r-summarizedexperiment)
13033 ("r-crosstalk" ,r-crosstalk)
13034 ("r-tximport" ,r-tximport)
13035 ("r-rtracklayer" ,r-rtracklayer)
13036 ("r-rjson" ,r-rjson)
13038 ("ghc-pandoc" ,ghc-pandoc)
13039 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13040 ("python-wrapper" ,python-wrapper)
13041 ("python-pyyaml" ,python-pyyaml)))
13042 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13043 (synopsis "Analysis pipeline for RNA sequencing experiments")
13044 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
13045 reporting for RNA sequencing experiments. It is easy to use and produces high
13046 quality reports. The inputs are reads files from the sequencing experiment,
13047 and a configuration file which describes the experiment. In addition to
13048 quality control of the experiment, the pipeline produces a differential
13049 expression report comparing samples in an easily configurable manner.")
13050 (license license:gpl3+)))
13052 (define-public pigx-chipseq
13054 (name "pigx-chipseq")
13058 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
13059 "releases/download/v" version
13060 "/pigx_chipseq-" version ".tar.gz"))
13063 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
13064 (build-system gnu-build-system)
13065 ;; parts of the tests rely on access to the network
13066 (arguments '(#:tests? #f))
13069 ("coreutils" ,coreutils)
13070 ("r-minimal" ,r-minimal)
13071 ("r-argparser" ,r-argparser)
13072 ("r-biocparallel" ,r-biocparallel)
13073 ("r-biostrings" ,r-biostrings)
13074 ("r-chipseq" ,r-chipseq)
13075 ("r-data-table" ,r-data-table)
13076 ("r-dplyr" ,r-dplyr)
13077 ("r-genomation" ,r-genomation)
13078 ("r-genomicalignments" ,r-genomicalignments)
13079 ("r-genomicranges" ,r-genomicranges)
13080 ("r-rsamtools" ,r-rsamtools)
13081 ("r-rtracklayer" ,r-rtracklayer)
13082 ("r-s4vectors" ,r-s4vectors)
13083 ("r-stringr" ,r-stringr)
13084 ("r-tibble" ,r-tibble)
13085 ("r-tidyr" ,r-tidyr)
13086 ("r-jsonlite" ,r-jsonlite)
13087 ("r-heatmaply" ,r-heatmaply)
13088 ("r-htmlwidgets" ,r-htmlwidgets)
13089 ("r-ggplot2" ,r-ggplot2)
13090 ("r-plotly" ,r-plotly)
13091 ("r-rmarkdown" ,r-rmarkdown)
13092 ("python-wrapper" ,python-wrapper)
13093 ("python-pyyaml" ,python-pyyaml)
13094 ("python-magic" ,python-magic)
13095 ("python-xlrd" ,python-xlrd)
13096 ("trim-galore" ,trim-galore)
13098 ("multiqc" ,multiqc)
13100 ("ghc-pandoc" ,ghc-pandoc)
13101 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13105 ("snakemake" ,snakemake)
13106 ("samtools" ,samtools)
13107 ("bedtools" ,bedtools)
13108 ("kentutils" ,kentutils)))
13110 `(("python-pytest" ,python-pytest)))
13111 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13112 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13113 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13114 calling and reporting for ChIP sequencing experiments. It is easy to use and
13115 produces high quality reports. The inputs are reads files from the sequencing
13116 experiment, and a configuration file which describes the experiment. In
13117 addition to quality control of the experiment, the pipeline enables to set up
13118 multiple peak calling analysis and allows the generation of a UCSC track hub
13119 in an easily configurable manner.")
13120 (license license:gpl3+)))
13122 (define-public pigx-bsseq
13124 (name "pigx-bsseq")
13128 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13129 "releases/download/v" version
13130 "/pigx_bsseq-" version ".tar.gz"))
13133 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13134 (build-system gnu-build-system)
13137 (modify-phases %standard-phases
13138 (add-before 'check 'set-timezone
13139 ;; The readr package is picky about timezones.
13140 (lambda* (#:key inputs #:allow-other-keys)
13141 (setenv "TZ" "UTC+1")
13143 (string-append (assoc-ref inputs "tzdata")
13144 "/share/zoneinfo"))
13147 `(("tzdata" ,tzdata)))
13149 `(("coreutils" ,coreutils)
13152 ("r-minimal" ,r-minimal)
13153 ("r-annotationhub" ,r-annotationhub)
13155 ("r-genomation" ,r-genomation)
13156 ("r-methylkit" ,r-methylkit)
13157 ("r-rtracklayer" ,r-rtracklayer)
13158 ("r-rmarkdown" ,r-rmarkdown)
13159 ("r-bookdown" ,r-bookdown)
13160 ("r-ggplot2" ,r-ggplot2)
13161 ("r-ggbio" ,r-ggbio)
13162 ("ghc-pandoc" ,ghc-pandoc)
13163 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13164 ("python-wrapper" ,python-wrapper)
13165 ("python-pyyaml" ,python-pyyaml)
13166 ("snakemake" ,snakemake)
13167 ("bismark" ,bismark)
13170 ("trim-galore" ,trim-galore)
13171 ("cutadapt" ,cutadapt)
13172 ("samtools" ,samtools)))
13173 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13174 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13175 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13176 data of bisulfite experiments; it produces reports on aggregate methylation
13177 and coverage and can be used to produce information on differential
13178 methylation and segmentation.")
13179 (license license:gpl3+)))
13181 (define-public pigx-scrnaseq
13183 (name "pigx-scrnaseq")
13187 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13188 "releases/download/v" version
13189 "/pigx_scrnaseq-" version ".tar.gz"))
13192 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13193 (build-system gnu-build-system)
13195 `(#:configure-flags
13196 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13197 "/share/java/picard.jar")
13198 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13199 "/share/java/dropseq.jar"))))
13201 `(("coreutils" ,coreutils)
13203 ("dropseq-tools" ,dropseq-tools)
13205 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13206 ("java" ,icedtea-8)
13207 ("python-wrapper" ,python-wrapper)
13208 ("python-pyyaml" ,python-pyyaml)
13209 ("python-pandas" ,python-pandas)
13210 ("python-magic" ,python-magic)
13211 ("python-numpy" ,python-numpy)
13212 ("python-loompy" ,python-loompy)
13213 ("ghc-pandoc" ,ghc-pandoc)
13214 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13215 ("samtools" ,samtools)
13216 ("snakemake" ,snakemake)
13218 ("r-minimal" ,r-minimal)
13219 ("r-argparser" ,r-argparser)
13220 ("r-cowplot" ,r-cowplot)
13221 ("r-data-table" ,r-data-table)
13222 ("r-delayedarray" ,r-delayedarray)
13223 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13224 ("r-dplyr" ,r-dplyr)
13225 ("r-dropbead" ,r-dropbead)
13227 ("r-genomicalignments" ,r-genomicalignments)
13228 ("r-genomicfiles" ,r-genomicfiles)
13229 ("r-genomicranges" ,r-genomicranges)
13230 ("r-ggplot2" ,r-ggplot2)
13231 ("r-hdf5array" ,r-hdf5array)
13232 ("r-pheatmap" ,r-pheatmap)
13233 ("r-rmarkdown" ,r-rmarkdown)
13234 ("r-rsamtools" ,r-rsamtools)
13235 ("r-rtracklayer" ,r-rtracklayer)
13236 ("r-rtsne" ,r-rtsne)
13237 ("r-scater" ,r-scater)
13238 ("r-scran" ,r-scran)
13239 ("r-singlecellexperiment" ,r-singlecellexperiment)
13240 ("r-stringr" ,r-stringr)
13241 ("r-yaml" ,r-yaml)))
13242 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13243 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13244 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13245 quality control for single cell RNA sequencing experiments. The inputs are
13246 read files from the sequencing experiment, and a configuration file which
13247 describes the experiment. It produces processed files for downstream analysis
13248 and interactive quality reports. The pipeline is designed to work with UMI
13250 (license license:gpl3+)))
13252 (define-public pigx
13258 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13259 "releases/download/v" version
13260 "/pigx-" version ".tar.gz"))
13263 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13264 (build-system gnu-build-system)
13266 `(("python" ,python)
13267 ("pigx-bsseq" ,pigx-bsseq)
13268 ("pigx-chipseq" ,pigx-chipseq)
13269 ("pigx-rnaseq" ,pigx-rnaseq)
13270 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13271 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13272 (synopsis "Analysis pipelines for genomics")
13273 (description "PiGx is a collection of genomics pipelines. It includes the
13274 following pipelines:
13277 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13278 @item PiGx RNAseq for RNAseq samples
13279 @item PiGx scRNAseq for single cell dropseq analysis
13280 @item PiGx ChIPseq for reads from ChIPseq experiments
13283 All pipelines are easily configured with a simple sample sheet and a
13284 descriptive settings file. The result is a set of comprehensive, interactive
13285 HTML reports with interesting findings about your samples.")
13286 (license license:gpl3+)))
13288 (define-public mantis
13289 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13293 (version (git-version "0" revision commit))
13296 (uri (git-reference
13297 (url "https://github.com/splatlab/mantis.git")
13299 (file-name (git-file-name name version))
13302 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13303 (build-system cmake-build-system)
13304 (arguments '(#:tests? #f)) ; there are none
13306 `(("sdsl-lite" ,sdsl-lite)
13307 ("openssl" ,openssl)
13309 (home-page "https://github.com/splatlab/mantis")
13310 (synopsis "Large-scale sequence-search index data structure")
13311 (description "Mantis is a space-efficient data structure that can be
13312 used to index thousands of raw-read genomics experiments and facilitate
13313 large-scale sequence searches on those experiments. Mantis uses counting
13314 quotient filters instead of Bloom filters, enabling rapid index builds and
13315 queries, small indexes, and exact results, i.e., no false positives or
13316 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13317 representation, so it supports fast graph traversal and other topological
13318 analyses in addition to large-scale sequence-level searches.")
13319 ;; uses __uint128_t and inline assembly
13320 (supported-systems '("x86_64-linux"))
13321 (license license:bsd-3))))
13323 (define-public r-diversitree
13325 (name "r-diversitree")
13330 (uri (cran-uri "diversitree" version))
13333 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13334 (build-system r-build-system)
13336 `(("gfortran" ,gfortran)))
13337 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13340 ("r-desolve" ,r-desolve)
13342 ("r-suplex" ,r-subplex)))
13343 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13344 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13345 (description "This package contains a number of comparative \"phylogenetic\"
13346 methods, mostly focusing on analysing diversification and character evolution.
13347 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13348 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13349 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13350 include Markov models of discrete and continuous trait evolution and constant
13351 rate speciation and extinction.")
13352 (license license:gpl2+)))
13354 (define-public sjcount
13355 ;; There is no tag for version 3.2, nor is there a release archive.
13356 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13360 (version (git-version "3.2" revision commit))
13363 (uri (git-reference
13364 (url "https://github.com/pervouchine/sjcount-full.git")
13366 (file-name (string-append name "-" version "-checkout"))
13369 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13370 (build-system gnu-build-system)
13372 `(#:tests? #f ; requires a 1.4G test file
13374 (list (string-append "SAMTOOLS_DIR="
13375 (assoc-ref %build-inputs "samtools")
13378 (modify-phases %standard-phases
13379 (replace 'configure
13380 (lambda* (#:key inputs #:allow-other-keys)
13381 (substitute* "makefile"
13382 (("-I \\$\\{SAMTOOLS_DIR\\}")
13383 (string-append "-I" (assoc-ref inputs "samtools")
13384 "/include/samtools"))
13385 (("-lz ") "-lz -lpthread "))
13388 (lambda* (#:key outputs #:allow-other-keys)
13389 (for-each (lambda (tool)
13391 (string-append (assoc-ref outputs "out")
13393 '("j_count" "b_count" "sjcount"))
13396 `(("samtools" ,samtools-0.1)
13398 (home-page "https://github.com/pervouchine/sjcount-full/")
13399 (synopsis "Annotation-agnostic splice junction counting pipeline")
13400 (description "Sjcount is a utility for fast quantification of splice
13401 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13402 version does count multisplits.")
13403 (license license:gpl3+))))
13405 (define-public minimap2
13412 (uri (string-append "https://github.com/lh3/minimap2/"
13413 "releases/download/v" version "/"
13414 "minimap2-" version ".tar.bz2"))
13417 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13418 (build-system gnu-build-system)
13420 `(#:tests? #f ; there are none
13423 (let ((system ,(or (%current-target-system)
13424 (%current-system))))
13426 ((string-prefix? "x86_64" system)
13428 ((or (string-prefix? "armhf" system)
13429 (string-prefix? "aarch64" system))
13431 (_ "sse2only=1"))))
13433 (modify-phases %standard-phases
13434 (delete 'configure)
13436 (lambda* (#:key outputs #:allow-other-keys)
13437 (let* ((out (assoc-ref outputs "out"))
13438 (bin (string-append out "/bin"))
13439 (man (string-append out "/share/man/man1")))
13440 (install-file "minimap2" bin)
13442 (install-file "minimap2.1" man))
13446 (home-page "https://lh3.github.io/minimap2/")
13447 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13448 (description "Minimap2 is a versatile sequence alignment program that
13449 aligns DNA or mRNA sequences against a large reference database. Typical use
13453 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13454 @item finding overlaps between long reads with error rate up to ~15%;
13455 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13456 reads against a reference genome;
13457 @item aligning Illumina single- or paired-end reads;
13458 @item assembly-to-assembly alignment;
13459 @item full-genome alignment between two closely related species with
13460 divergence below ~15%.
13462 (license license:expat)))
13464 (define-public r-circus
13471 (uri (git-reference
13472 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13473 (commit (string-append "v" version))))
13474 (file-name (git-file-name name version))
13477 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13478 (build-system r-build-system)
13480 `(("r-annotationdbi" ,r-annotationdbi)
13481 ("r-annotationhub" ,r-annotationhub)
13482 ("r-biomart" ,r-biomart)
13483 ("r-data-table" ,r-data-table)
13485 ("r-genomicfeatures" ,r-genomicfeatures)
13486 ("r-genomicranges" ,r-genomicranges)
13487 ("r-ggplot2" ,r-ggplot2)
13489 ("r-iranges" ,r-iranges)
13490 ("r-rcolorbrewer" ,r-rcolorbrewer)
13491 ("r-rmysql" ,r-rmysql)
13492 ("r-s4vectors" ,r-s4vectors)
13493 ("r-stringr" ,r-stringr)
13494 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13496 `(("r-knitr" ,r-knitr)))
13497 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13498 (synopsis "Annotation, analysis and visualization of circRNA data")
13499 (description "Circus is an R package for annotation, analysis and
13500 visualization of circRNA data. Users can annotate their circRNA candidates
13501 with host genes, gene featrues they are spliced from, and discriminate between
13502 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13503 can be calculated, and a number of descriptive plots easily generated.")
13504 (license license:artistic2.0)))
13506 (define-public r-loomr
13507 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13511 (version (git-version "0.2.0" revision commit))
13515 (uri (git-reference
13516 (url "https://github.com/mojaveazure/loomR.git")
13518 (file-name (git-file-name name version))
13521 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13522 (build-system r-build-system)
13525 ("r-hdf5r" ,r-hdf5r)
13526 ("r-iterators" ,r-iterators)
13527 ("r-itertools" ,r-itertools)
13528 ("r-matrix" ,r-matrix)))
13529 (home-page "https://github.com/mojaveazure/loomR")
13530 (synopsis "R interface for loom files")
13531 (description "This package provides an R interface to access, create,
13532 and modify loom files. loomR aims to be completely compatible with loompy.")
13533 (license license:gpl3))))
13535 (define-public gffread
13536 ;; We cannot use the tagged release because it is not in sync with gclib.
13537 ;; See https://github.com/gpertea/gffread/issues/26
13538 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13542 (version (git-version "0.9.12" revision commit))
13546 (uri (git-reference
13547 (url "https://github.com/gpertea/gffread.git")
13549 (file-name (git-file-name name version))
13552 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13553 (build-system gnu-build-system)
13555 `(#:tests? #f ; no check target
13557 (list "GCLDIR=gclib")
13559 (modify-phases %standard-phases
13560 (delete 'configure)
13561 (add-after 'unpack 'copy-gclib-source
13562 (lambda* (#:key inputs #:allow-other-keys)
13564 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13566 ;; There is no install target
13568 (lambda* (#:key outputs #:allow-other-keys)
13569 (let* ((out (assoc-ref outputs "out"))
13570 (bin (string-append out "/bin")))
13571 (install-file "gffread" bin))
13575 ,(let ((version "0.10.3")
13576 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13580 (uri (git-reference
13581 (url "https://github.com/gpertea/gclib.git")
13583 (file-name (git-file-name "gclib" version))
13586 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13587 (home-page "https://github.com/gpertea/gffread/")
13588 (synopsis "Parse and convert GFF/GTF files")
13590 "This package provides a GFF/GTF file parsing utility providing format
13591 conversions, region filtering, FASTA sequence extraction and more.")
13592 ;; gffread is under Expat, but gclib is under Artistic 2.0
13593 (license (list license:expat
13594 license:artistic2.0)))))
13596 (define-public find-circ
13597 ;; The last release was in 2015. The license was clarified in 2017, so we
13598 ;; take the latest commit.
13599 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13603 (version (git-version "1.2" revision commit))
13607 (uri (git-reference
13608 (url "https://github.com/marvin-jens/find_circ.git")
13610 (file-name (git-file-name name version))
13613 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13614 (build-system gnu-build-system)
13616 `(#:tests? #f ; there are none
13618 ;; There is no actual build system.
13619 (modify-phases %standard-phases
13620 (delete 'configure)
13623 (lambda* (#:key outputs #:allow-other-keys)
13624 (let* ((out (assoc-ref outputs "out"))
13625 (bin (string-append out "/bin"))
13626 (path (getenv "PYTHONPATH")))
13627 (for-each (lambda (script)
13628 (install-file script bin)
13629 (wrap-program (string-append bin "/" script)
13630 `("PYTHONPATH" ":" prefix (,path))))
13635 "unmapped2anchors.py")))
13638 `(("python2" ,python-2)
13639 ("python2-pysam" ,python2-pysam)
13640 ("python2-numpy" ,python2-numpy)))
13641 (home-page "https://github.com/marvin-jens/find_circ")
13642 (synopsis "circRNA detection from RNA-seq reads")
13643 (description "This package provides tools to detect head-to-tail
13644 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13646 (license license:gpl3))))
13648 (define-public python-scanpy
13650 (name "python-scanpy")
13655 (uri (pypi-uri "scanpy" version))
13658 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13659 (build-system python-build-system)
13661 `(("python-anndata" ,python-anndata)
13662 ("python-igraph" ,python-igraph)
13663 ("python-numba" ,python-numba)
13664 ("python-joblib" ,python-joblib)
13665 ("python-natsort" ,python-natsort)
13666 ("python-networkx" ,python-networkx)
13667 ("python-statsmodels" ,python-statsmodels)
13668 ("python-scikit-learn" ,python-scikit-learn)
13669 ("python-matplotlib" ,python-matplotlib)
13670 ("python-pandas" ,python-pandas)
13671 ("python-scipy" ,python-scipy)
13672 ("python-seaborn" ,python-seaborn)
13673 ("python-h5py" ,python-h5py)
13674 ("python-tables" ,python-tables)))
13675 (home-page "http://github.com/theislab/scanpy")
13676 (synopsis "Single-Cell Analysis in Python.")
13677 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13678 expression data. It includes preprocessing, visualization, clustering,
13679 pseudotime and trajectory inference and differential expression testing. The
13680 Python-based implementation efficiently deals with datasets of more than one
13682 (license license:bsd-3)))
13684 (define-public gffcompare
13685 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13688 (name "gffcompare")
13689 (version (git-version "0.10.15" revision commit))
13693 (uri (git-reference
13694 (url "https://github.com/gpertea/gffcompare/")
13696 (file-name (git-file-name name version))
13698 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13699 (build-system gnu-build-system)
13701 `(#:tests? #f ; no check target
13703 (modify-phases %standard-phases
13704 (delete 'configure)
13705 (add-before 'build 'copy-gclib-source
13706 (lambda* (#:key inputs #:allow-other-keys)
13709 (assoc-ref inputs "gclib-source") "../gclib")
13712 (lambda* (#:key outputs #:allow-other-keys)
13713 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13714 (install-file "gffcompare" bin)
13717 `(("gclib-source" ; see 'README.md' of gffcompare
13718 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13721 (version (git-version "0.10.3" revision commit)))
13724 (uri (git-reference
13725 (url "https://github.com/gpertea/gclib/")
13727 (file-name (git-file-name name version))
13729 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13730 (home-page "https://github.com/gpertea/gffcompare/")
13731 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13733 "@code{gffcompare} is a tool that can:
13735 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13736 (Cufflinks, Stringtie);
13737 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13738 resulted from assembly of different samples);
13739 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13740 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13744 license:expat ;license for gffcompare
13745 license:artistic2.0))))) ;license for gclib
13747 (define-public python-intervaltree
13749 (name "python-intervaltree")
13754 (uri (pypi-uri "intervaltree" version))
13757 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13758 (build-system python-build-system)
13759 ;; FIXME: error when collecting tests
13760 (arguments '(#:tests? #f))
13762 `(("python-sortedcontainers" ,python-sortedcontainers)))
13764 `(("python-pytest" ,python-pytest)))
13765 (home-page "https://github.com/chaimleib/intervaltree")
13766 (synopsis "Editable interval tree data structure")
13768 "This package provides a mutable, self-balancing interval tree
13769 implementation for Python. Queries may be by point, by range overlap, or by
13770 range envelopment. This library was designed to allow tagging text and time
13771 intervals, where the intervals include the lower bound but not the upper
13773 (license license:asl2.0)))
13775 (define-public python-pypairix
13777 (name "python-pypairix")
13782 (uri (pypi-uri "pypairix" version))
13785 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13786 (build-system python-build-system)
13787 ;; FIXME: the tests fail because test.support cannot be loaded:
13788 ;; ImportError: cannot import name 'support'
13789 (arguments '(#:tests? #f))
13792 (home-page "https://github.com/4dn-dcic/pairix")
13793 (synopsis "Support for querying pairix-indexed bgzipped text files")
13795 "Pypairix is a Python module for fast querying on a pairix-indexed
13796 bgzipped text file that contains a pair of genomic coordinates per line.")
13797 (license license:expat)))
13799 (define-public python-pyfaidx
13801 (name "python-pyfaidx")
13802 (version "0.5.4.2")
13806 (uri (pypi-uri "pyfaidx" version))
13809 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13810 (build-system python-build-system)
13812 `(("python-setuptools" ,python-setuptools)
13813 ("python-six" ,python-six)))
13814 (home-page "http://mattshirley.com")
13815 (synopsis "Random access to fasta subsequences")
13817 "This package provides procedures for efficient pythonic random access to
13818 fasta subsequences.")
13819 (license license:bsd-3)))
13821 (define-public python-cooler
13823 (name "python-cooler")
13828 (uri (pypi-uri "cooler" version))
13831 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13832 (build-system python-build-system)
13834 `(("python-biopython" ,python-biopython)
13835 ("python-click" ,python-click)
13836 ("python-cytoolz" ,python-cytoolz)
13837 ("python-dask" ,python-dask)
13838 ("python-h5py" ,python-h5py)
13839 ("python-multiprocess" ,python-multiprocess)
13840 ("python-pandas" ,python-pandas)
13841 ("python-pyfaidx" ,python-pyfaidx)
13842 ("python-pypairix" ,python-pypairix)
13843 ("python-pysam" ,python-pysam)
13844 ("python-scipy" ,python-scipy)))
13846 `(("python-mock" ,python-mock)
13847 ("python-nose" ,python-nose)
13848 ("python-numpydoc" ,python-numpydoc)
13849 ("python-sphinx" ,python-sphinx)))
13850 (home-page "https://github.com/mirnylab/cooler")
13851 (synopsis "Sparse binary format for genomic interaction matrices")
13853 "Cooler is a support library for a sparse, compressed, binary persistent
13854 storage format, called @code{cool}, used to store genomic interaction data,
13855 such as Hi-C contact matrices.")
13856 (license license:bsd-3)))
13858 (define-public python-hicexplorer
13860 (name "python-hicexplorer")
13864 ;; The latest version is not available on Pypi.
13866 (uri (git-reference
13867 (url "https://github.com/deeptools/HiCExplorer.git")
13869 (file-name (git-file-name name version))
13872 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13873 (build-system python-build-system)
13876 (modify-phases %standard-phases
13877 (add-after 'unpack 'loosen-up-requirements
13879 (substitute* "setup.py"
13883 `(("python-biopython" ,python-biopython)
13884 ("python-configparser" ,python-configparser)
13885 ("python-cooler" ,python-cooler)
13886 ("python-future" ,python-future)
13887 ("python-intervaltree" ,python-intervaltree)
13888 ("python-jinja2" ,python-jinja2)
13889 ("python-matplotlib" ,python-matplotlib)
13890 ("python-numpy" ,python-numpy)
13891 ("python-pandas" ,python-pandas)
13892 ("python-pybigwig" ,python-pybigwig)
13893 ("python-pysam" ,python-pysam)
13894 ("python-scipy" ,python-scipy)
13895 ("python-six" ,python-six)
13896 ("python-tables" ,python-tables)
13897 ("python-unidecode" ,python-unidecode)))
13898 (home-page "http://hicexplorer.readthedocs.io")
13899 (synopsis "Process, analyze and visualize Hi-C data")
13901 "HiCExplorer is a powerful and easy to use set of tools to process,
13902 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13903 contact matrices, correction of contacts, TAD detection, A/B compartments,
13904 merging, reordering or chromosomes, conversion from different formats
13905 including cooler and detection of long-range contacts. Moreover, it allows
13906 the visualization of multiple contact matrices along with other types of data
13907 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13908 genomic scores), long range contacts and the visualization of viewpoints.")
13909 (license license:gpl3)))
13911 (define-public python-pygenometracks
13913 (name "python-pygenometracks")
13918 (uri (pypi-uri "pyGenomeTracks" version))
13921 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13922 (build-system python-build-system)
13924 `(("python-configparser" ,python-configparser)
13925 ("python-future" ,python-future)
13926 ("python-hicexplorer" ,python-hicexplorer)
13927 ("python-intervaltree" ,python-intervaltree)
13928 ("python-matplotlib" ,python-matplotlib)
13929 ("python-numpy" ,python-numpy)
13930 ("python-pybigwig" ,python-pybigwig)))
13932 `(("python-pytest" ,python-pytest)))
13933 (home-page "https://pygenometracks.readthedocs.io")
13934 (synopsis "Program and library to plot beautiful genome browser tracks")
13936 "This package aims to produce high-quality genome browser tracks that
13937 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13938 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13939 pyGenomeTracks can make plots with or without Hi-C data.")
13940 (license license:gpl3+)))
13942 (define-public python-hic2cool
13944 (name "python-hic2cool")
13949 (uri (pypi-uri "hic2cool" version))
13952 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13953 (build-system python-build-system)
13954 (arguments '(#:tests? #f)) ; no tests included
13956 `(("python-cooler" ,python-cooler)))
13957 (home-page "https://github.com/4dn-dcic/hic2cool")
13958 (synopsis "Converter for .hic and .cool files")
13960 "This package provides a converter between @code{.hic} files (from
13961 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13962 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13964 (license license:expat)))
13966 (define-public r-pore
13974 (string-append "mirror://sourceforge/rpore/" version
13975 "/poRe_" version ".tar.gz"))
13977 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13978 (properties `((upstream-name . "poRe")))
13979 (build-system r-build-system)
13981 `(("r-bit64" ,r-bit64)
13982 ("r-data-table" ,r-data-table)
13983 ("r-rhdf5" ,r-rhdf5)
13984 ("r-shiny" ,r-shiny)
13985 ("r-svdialogs" ,r-svdialogs)))
13986 (home-page "https://sourceforge.net/projects/rpore/")
13987 (synopsis "Visualize Nanopore sequencing data")
13989 "This package provides graphical user interfaces to organize and visualize Nanopore
13991 ;; This is free software but the license variant is unclear:
13992 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13993 (license license:bsd-3)))
13995 (define-public r-xbioc
13996 (let ((revision "1")
13997 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
14000 (version (git-version "0.1.15" revision commit))
14003 (uri (git-reference
14004 (url "https://github.com/renozao/xbioc.git")
14006 (file-name (git-file-name name version))
14009 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
14010 (build-system r-build-system)
14012 `(("r-annotationdbi" ,r-annotationdbi)
14013 ("r-assertthat" ,r-assertthat)
14014 ("r-biobase" ,r-biobase)
14015 ("r-biocinstaller" ,r-biocinstaller)
14016 ("r-digest" ,r-digest)
14017 ("r-pkgmaker" ,r-pkgmaker)
14019 ("r-reshape2" ,r-reshape2)
14020 ("r-stringr" ,r-stringr)))
14021 (home-page "https://github.com/renozao/xbioc/")
14022 (synopsis "Extra base functions for Bioconductor")
14023 (description "This package provides extra utility functions to perform
14024 common tasks in the analysis of omics data, leveraging and enhancing features
14025 provided by Bioconductor packages.")
14026 (license license:gpl3+))))
14028 (define-public r-cssam
14029 (let ((revision "1")
14030 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14033 (version (git-version "1.4" revision commit))
14036 (uri (git-reference
14037 (url "https://github.com/shenorrLab/csSAM.git")
14039 (file-name (git-file-name name version))
14042 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14043 (build-system r-build-system)
14045 `(("r-formula" ,r-formula)
14046 ("r-ggplot2" ,r-ggplot2)
14047 ("r-pkgmaker" ,r-pkgmaker)
14049 ("r-rngtools" ,r-rngtools)
14050 ("r-scales" ,r-scales)))
14051 (home-page "https://github.com/shenorrLab/csSAM/")
14052 (synopsis "Cell type-specific statistical analysis of microarray")
14053 (description "This package implements the method csSAM that computes
14054 cell-specific differential expression from measured cell proportions using
14057 (license license:lgpl2.1+))))
14059 (define-public r-bseqsc
14060 (let ((revision "1")
14061 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14064 (version (git-version "1.0" revision commit))
14067 (uri (git-reference
14068 (url "https://github.com/shenorrLab/bseqsc.git")
14070 (file-name (git-file-name name version))
14073 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14074 (build-system r-build-system)
14076 `(("r-abind" ,r-abind)
14077 ("r-annotationdbi" ,r-annotationdbi)
14078 ("r-biobase" ,r-biobase)
14079 ("r-cssam" ,r-cssam)
14080 ("r-dplyr" ,r-dplyr)
14081 ("r-e1071" ,r-e1071)
14082 ("r-edger" ,r-edger)
14083 ("r-ggplot2" ,r-ggplot2)
14085 ("r-openxlsx" ,r-openxlsx)
14086 ("r-pkgmaker" ,r-pkgmaker)
14088 ("r-preprocesscore" ,r-preprocesscore)
14089 ("r-rngtools" ,r-rngtools)
14090 ("r-scales" ,r-scales)
14091 ("r-stringr" ,r-stringr)
14092 ("r-xbioc" ,r-xbioc)))
14093 (home-page "https://github.com/shenorrLab/bseqsc")
14094 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14095 (description "BSeq-sc is a bioinformatics analysis pipeline that
14096 leverages single-cell sequencing data to estimate cell type proportion and
14097 cell type-specific gene expression differences from RNA-seq data from bulk
14098 tissue samples. This is a companion package to the publication \"A
14099 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14100 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14101 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14102 (license license:gpl2+))))
14104 (define-public porechop
14105 ;; The recommended way to install is to clone the git repository
14106 ;; https://github.com/rrwick/Porechop#installation
14107 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14111 (version (git-version "0.2.3" revision commit))
14115 (uri (git-reference
14116 (url "https://github.com/rrwick/Porechop.git")
14118 (file-name (git-file-name name version))
14120 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14121 (build-system python-build-system)
14122 (home-page "https://github.com/rrwick/porechop")
14123 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14125 "The porechop package is a tool for finding and removing adapters from Oxford
14126 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14127 has an adapter in its middle, it is treated as chimeric and chopped into
14128 separate reads. Porechop performs thorough alignments to effectively find
14129 adapters, even at low sequence identity. Porechop also supports demultiplexing
14130 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14131 Barcoding Kit or Rapid Barcoding Kit.")
14132 (license license:gpl3+))))
14134 (define-public poretools
14135 ;; The latest release was in 2016 and the latest commit is from 2017
14136 ;; the recommended way to install is to clone the git repository
14137 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14138 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14142 (version (git-version "0.6.0" revision commit))
14146 (uri (git-reference
14147 (url "https://github.com/arq5x/poretools.git")
14149 (file-name (git-file-name name version))
14151 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14152 (build-system python-build-system)
14153 ;; requires python >=2.7, <3.0, and the same for python dependencies
14154 (arguments `(#:python ,python-2))
14158 `(("python-dateutil" ,python2-dateutil)
14159 ("python-h5py" ,python2-h5py)
14160 ("python-matplotlib" ,python2-matplotlib)
14161 ("python-pandas" ,python2-pandas)
14162 ("python-seaborn" ,python2-seaborn)))
14163 (home-page "https://poretools.readthedocs.io")
14164 (synopsis "Toolkit for working with nanopore sequencing data")
14166 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14167 This @code{poretools} package is a flexible toolkit for exploring datasets
14168 generated by nanopore sequencing devices for the purposes of quality control and
14169 downstream analysis. Poretools operates directly on the native FAST5, a variant
14170 of the Hierarchical Data Format (HDF5) standard.")
14171 (license license:expat))))
14173 (define-public r-absfiltergsea
14175 (name "r-absfiltergsea")
14180 (uri (cran-uri "AbsFilterGSEA" version))
14182 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14183 (properties `((upstream-name . "AbsFilterGSEA")))
14184 (build-system r-build-system)
14186 `(("r-biobase" ,r-biobase)
14187 ("r-deseq" ,r-deseq)
14188 ("r-limma" ,r-limma)
14190 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14191 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14192 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14194 "This package provides a function that performs gene-permuting of a gene-set
14195 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14196 Without filtering, users can perform (original) two-tailed or one-tailed
14198 (license license:gpl2)))
14200 (define-public jamm
14203 (version "1.0.7.5")
14207 (uri (git-reference
14208 (url "https://github.com/mahmoudibrahim/JAMM.git")
14209 (commit (string-append "JAMMv" version))))
14210 (file-name (git-file-name name version))
14213 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14214 (build-system gnu-build-system)
14216 `(#:tests? #f ; there are none
14218 (modify-phases %standard-phases
14219 (delete 'configure)
14221 (lambda* (#:key inputs outputs #:allow-other-keys)
14222 (substitute* "JAMM.sh"
14224 (string-append "")))
14227 (lambda* (#:key inputs outputs #:allow-other-keys)
14228 (let* ((out (assoc-ref outputs "out"))
14229 (libexec (string-append out "/libexec/jamm"))
14230 (bin (string-append out "/bin")))
14231 (substitute* '("JAMM.sh"
14232 "SignalGenerator.sh")
14234 (string-append "sPath=\"" libexec "\"\n")))
14235 (for-each (lambda (file)
14236 (install-file file libexec))
14237 (list "bincalculator.r"
14249 (chmod script #o555)
14250 (install-file script bin)
14251 (wrap-program (string-append bin "/" script)
14252 `("PATH" ":" prefix
14253 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14254 ,(string-append (assoc-ref inputs "gawk") "/bin")
14255 ,(string-append (assoc-ref inputs "perl") "/bin")
14256 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14257 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14258 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14259 (list "JAMM.sh" "SignalGenerator.sh")))
14263 ("coreutils" ,coreutils)
14266 ("r-minimal" ,r-minimal)
14267 ;;("r-parallel" ,r-parallel)
14268 ("r-signal" ,r-signal)
14269 ("r-mclust" ,r-mclust)))
14270 (home-page "https://github.com/mahmoudibrahim/JAMM")
14271 (synopsis "Peak finder for NGS datasets")
14273 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14274 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14275 boundaries accurately. JAMM is applicable to both broad and narrow
14277 (license license:gpl3+)))
14279 (define-public ngless
14286 (uri (git-reference
14287 (url "https://gitlab.com/ngless/ngless.git")
14288 (commit (string-append "v" version))))
14289 (file-name (git-file-name name version))
14292 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14293 (build-system haskell-build-system)
14295 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14296 ; error: parse error on input import
14297 ; import Options.Applicative
14299 (modify-phases %standard-phases
14300 (add-after 'unpack 'create-cabal-file
14301 (lambda _ (invoke "hpack") #t))
14302 ;; These tools are expected to be installed alongside ngless.
14303 (add-after 'install 'link-tools
14304 (lambda* (#:key inputs outputs #:allow-other-keys)
14305 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14306 (symlink (string-append (assoc-ref inputs "prodigal")
14308 (string-append bin "ngless-" ,version "-prodigal"))
14309 (symlink (string-append (assoc-ref inputs "minimap2")
14311 (string-append bin "ngless-" ,version "-minimap2"))
14312 (symlink (string-append (assoc-ref inputs "samtools")
14314 (string-append bin "ngless-" ,version "-samtools"))
14315 (symlink (string-append (assoc-ref inputs "bwa")
14317 (string-append bin "ngless-" ,version "-bwa"))
14320 `(("prodigal" ,prodigal)
14322 ("samtools" ,samtools)
14323 ("minimap2" ,minimap2)
14324 ("ghc-aeson" ,ghc-aeson)
14325 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14326 ("ghc-async" ,ghc-async)
14327 ("ghc-atomic-write" ,ghc-atomic-write)
14328 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14329 ("ghc-chart" ,ghc-chart)
14330 ("ghc-chart-cairo" ,ghc-chart-cairo)
14331 ("ghc-conduit" ,ghc-conduit)
14332 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14333 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14334 ("ghc-conduit-extra" ,ghc-conduit-extra)
14335 ("ghc-configurator" ,ghc-configurator)
14336 ("ghc-convertible" ,ghc-convertible)
14337 ("ghc-data-default" ,ghc-data-default)
14338 ("ghc-double-conversion" ,ghc-double-conversion)
14339 ("ghc-edit-distance" ,ghc-edit-distance)
14340 ("ghc-either" ,ghc-either)
14341 ("ghc-errors" ,ghc-errors)
14342 ("ghc-extra" ,ghc-extra)
14343 ("ghc-filemanip" ,ghc-filemanip)
14344 ("ghc-file-embed" ,ghc-file-embed)
14345 ("ghc-gitrev" ,ghc-gitrev)
14346 ("ghc-hashtables" ,ghc-hashtables)
14347 ("ghc-http-conduit" ,ghc-http-conduit)
14348 ("ghc-inline-c" ,ghc-inline-c)
14349 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14350 ("ghc-intervalmap" ,ghc-intervalmap)
14351 ("ghc-missingh" ,ghc-missingh)
14352 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14353 ("ghc-parsec" ,ghc-parsec)
14354 ("ghc-regex" ,ghc-regex)
14355 ("ghc-safe" ,ghc-safe)
14356 ("ghc-safeio" ,ghc-safeio)
14357 ("ghc-strict" ,ghc-strict)
14358 ("ghc-tar" ,ghc-tar)
14359 ("ghc-text" ,ghc-text)
14360 ("ghc-unliftio" ,ghc-unliftio)
14361 ("ghc-unliftio-core" ,ghc-unliftio-core)
14362 ("ghc-vector" ,ghc-vector)
14363 ("ghc-yaml" ,ghc-yaml)
14364 ("ghc-zlib" ,ghc-zlib)))
14367 ("r-hdf5r" ,r-hdf5r)
14368 ("r-iterators" ,r-iterators)
14369 ("r-itertools" ,r-itertools)
14370 ("r-matrix" ,r-matrix)))
14372 `(("ghc-hpack" ,ghc-hpack)
14373 ("ghc-quickcheck" ,ghc-quickcheck)
14374 ("ghc-test-framework" ,ghc-test-framework)
14375 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14376 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14377 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14378 (home-page "https://gitlab.com/ngless/ngless")
14379 (synopsis "DSL for processing next-generation sequencing data")
14380 (description "Ngless is a domain-specific language for
14381 @dfn{next-generation sequencing} (NGS) data processing.")
14382 (license license:expat)))
14384 (define-public filtlong
14385 ;; The recommended way to install is to clone the git repository
14386 ;; https://github.com/rrwick/Filtlong#installation
14387 ;; and the lastest release is more than nine months old
14388 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14392 (version (git-version "0.2.0" revision commit))
14396 (uri (git-reference
14397 (url "https://github.com/rrwick/Filtlong.git")
14399 (file-name (git-file-name name version))
14401 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14402 (build-system gnu-build-system)
14404 `(#:tests? #f ; no check target
14406 (modify-phases %standard-phases
14407 (delete 'configure)
14409 (lambda* (#:key outputs #:allow-other-keys)
14410 (let* ((out (assoc-ref outputs "out"))
14411 (bin (string-append out "/bin"))
14412 (scripts (string-append out "/share/filtlong/scripts")))
14413 (install-file "bin/filtlong" bin)
14414 (install-file "scripts/histogram.py" scripts)
14415 (install-file "scripts/read_info_histograms.sh" scripts))
14417 (add-after 'install 'wrap-program
14418 (lambda* (#:key inputs outputs #:allow-other-keys)
14419 (let* ((out (assoc-ref outputs "out"))
14420 (path (getenv "PYTHONPATH")))
14421 (wrap-program (string-append out
14422 "/share/filtlong/scripts/histogram.py")
14423 `("PYTHONPATH" ":" prefix (,path))))
14425 (add-before 'check 'patch-tests
14427 (substitute* "scripts/read_info_histograms.sh"
14428 (("awk") (which "gawk")))
14431 `(("gawk" ,gawk) ;for read_info_histograms.sh
14432 ("python" ,python-2) ;required for histogram.py
14434 (home-page "https://github.com/rrwick/Filtlong/")
14435 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14437 "The Filtlong package is a tool for filtering long reads by quality.
14438 It can take a set of long reads and produce a smaller, better subset. It uses
14439 both read length (longer is better) and read identity (higher is better) when
14440 choosing which reads pass the filter.")
14441 (license (list license:gpl3 ;filtlong
14442 license:asl2.0))))) ;histogram.py
14444 (define-public nanopolish
14445 ;; The recommended way to install is to clone the git repository
14446 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14447 ;; Also, the differences between release and current version seem to be
14449 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14452 (name "nanopolish")
14453 (version (git-version "0.10.2" revision commit))
14457 (uri (git-reference
14458 (url "https://github.com/jts/nanopolish.git")
14461 (file-name (git-file-name name version))
14463 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14464 (build-system gnu-build-system)
14467 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14468 #:tests? #f ; no check target
14470 (modify-phases %standard-phases
14471 (add-after 'unpack 'find-eigen
14472 (lambda* (#:key inputs #:allow-other-keys)
14474 (string-append (assoc-ref inputs "eigen")
14475 "/include/eigen3"))
14477 (delete 'configure)
14479 (lambda* (#:key outputs #:allow-other-keys)
14480 (let* ((out (assoc-ref outputs "out"))
14481 (bin (string-append out "/bin"))
14482 (scripts (string-append out "/share/nanopolish/scripts")))
14484 (install-file "nanopolish" bin)
14485 (for-each (lambda (file) (install-file file scripts))
14486 (find-files "scripts" ".*"))
14488 (add-after 'install 'wrap-programs
14489 (lambda* (#:key outputs #:allow-other-keys)
14490 (for-each (lambda (file)
14491 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14492 (find-files "/share/nanopolish/scripts" "\\.py"))
14493 (for-each (lambda (file)
14494 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14495 (find-files "/share/nanopolish/scripts" "\\.pl"))
14503 ("python-biopython" ,python-biopython)
14504 ("python-numpy" ,python-numpy)
14505 ("python-pysam" ,python-pysam)
14506 ("python-scikit-learn" , python-scikit-learn)
14507 ("python-scipy" ,python-scipy)
14509 (home-page "https://github.com/jts/nanopolish")
14510 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14512 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14513 Nanopolish can calculate an improved consensus sequence for a draft genome
14514 assembly, detect base modifications, call SNPs (Single nucleotide
14515 polymorphisms) and indels with respect to a reference genome and more.")
14516 (license license:expat))))