1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 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 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")
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)
1290 (supported-systems '("x86_64-linux"))
1291 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1292 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1294 "@dfn{Bloom-filter-based error correction solution for high-throughput
1295 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1296 correction tool for genomic reads produced by @dfn{Next-generation
1297 sequencing} (NGS). BLESS produces accurate correction results with much less
1298 memory compared with previous solutions and is also able to tolerate a higher
1299 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1300 errors at the end of reads.")
1301 (license license:gpl3+)))
1303 (define-public bowtie
1310 (url "https://github.com/BenLangmead/bowtie2.git")
1311 (commit (string-append "v" version))))
1312 (file-name (git-file-name name version))
1315 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1316 (modules '((guix build utils)))
1319 (substitute* "Makefile"
1320 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1321 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1322 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1324 (build-system gnu-build-system)
1329 (string-append "prefix=" (assoc-ref %outputs "out")))
1331 (modify-phases %standard-phases
1336 "scripts/test/simple_tests.pl"
1337 "--bowtie2=./bowtie2"
1338 "--bowtie2-build=./bowtie2-build")
1343 ("python" ,python-wrapper)))
1346 ("perl-clone" ,perl-clone)
1347 ("perl-test-deep" ,perl-test-deep)
1348 ("perl-test-simple" ,perl-test-simple)))
1349 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1350 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1352 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1353 reads to long reference sequences. It is particularly good at aligning reads
1354 of about 50 up to 100s or 1,000s of characters, and particularly good at
1355 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1356 genome with an FM Index to keep its memory footprint small: for the human
1357 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1358 gapped, local, and paired-end alignment modes.")
1359 (supported-systems '("x86_64-linux"))
1360 (license license:gpl3+)))
1362 (define-public tophat
1369 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1373 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1374 (modules '((guix build utils)))
1377 ;; Remove bundled SeqAn and samtools
1378 (delete-file-recursively "src/SeqAn-1.4.2")
1379 (delete-file-recursively "src/samtools-0.1.18")
1381 (build-system gnu-build-system)
1383 '(#:parallel-build? #f ; not supported
1385 (modify-phases %standard-phases
1386 (add-after 'unpack 'use-system-samtools
1387 (lambda* (#:key inputs #:allow-other-keys)
1388 (substitute* "src/Makefile.in"
1389 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1390 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1391 (("SAMPROG = samtools_0\\.1\\.18") "")
1392 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1393 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1394 (substitute* '("src/common.cpp"
1396 (("samtools_0.1.18") (which "samtools")))
1397 (substitute* '("src/common.h"
1398 "src/bam2fastx.cpp")
1399 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1400 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1401 (substitute* '("src/bwt_map.h"
1403 "src/align_status.h")
1404 (("#include <bam.h>") "#include <samtools/bam.h>")
1405 (("#include <sam.h>") "#include <samtools/sam.h>"))
1410 ("samtools" ,samtools-0.1)
1411 ("ncurses" ,ncurses)
1412 ("python" ,python-2)
1415 ("seqan" ,seqan-1)))
1416 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1417 (synopsis "Spliced read mapper for RNA-Seq data")
1419 "TopHat is a fast splice junction mapper for nucleotide sequence
1420 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1421 mammalian-sized genomes using the ultra high-throughput short read
1422 aligner Bowtie, and then analyzes the mapping results to identify
1423 splice junctions between exons.")
1424 ;; TopHat is released under the Boost Software License, Version 1.0
1425 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1426 (license license:boost1.0)))
1435 "https://github.com/lh3/bwa/releases/download/v"
1436 version "/bwa-" version ".tar.bz2"))
1439 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1440 (build-system gnu-build-system)
1442 '(#:tests? #f ;no "check" target
1444 (modify-phases %standard-phases
1446 (lambda* (#:key outputs #:allow-other-keys)
1447 (let ((bin (string-append
1448 (assoc-ref outputs "out") "/bin"))
1450 (assoc-ref outputs "out") "/share/doc/bwa"))
1452 (assoc-ref outputs "out") "/share/man/man1")))
1453 (install-file "bwa" bin)
1454 (install-file "README.md" doc)
1455 (install-file "bwa.1" man))
1457 ;; no "configure" script
1458 (delete 'configure))))
1459 (inputs `(("zlib" ,zlib)))
1460 ;; Non-portable SSE instructions are used so building fails on platforms
1461 ;; other than x86_64.
1462 (supported-systems '("x86_64-linux"))
1463 (home-page "http://bio-bwa.sourceforge.net/")
1464 (synopsis "Burrows-Wheeler sequence aligner")
1466 "BWA is a software package for mapping low-divergent sequences against a
1467 large reference genome, such as the human genome. It consists of three
1468 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1469 designed for Illumina sequence reads up to 100bp, while the rest two for
1470 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1471 features such as long-read support and split alignment, but BWA-MEM, which is
1472 the latest, is generally recommended for high-quality queries as it is faster
1473 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1474 70-100bp Illumina reads.")
1475 (license license:gpl3+)))
1477 (define-public bwa-pssm
1478 (package (inherit bwa)
1484 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1486 (file-name (git-file-name name version))
1489 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1490 (build-system gnu-build-system)
1495 (home-page "http://bwa-pssm.binf.ku.dk/")
1496 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1498 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1499 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1500 existing aligners it is fast and sensitive. Unlike most other aligners,
1501 however, it is also adaptible in the sense that one can direct the alignment
1502 based on known biases within the data set. It is coded as a modification of
1503 the original BWA alignment program and shares the genome index structure as
1504 well as many of the command line options.")
1505 (license license:gpl3+)))
1507 (define-public python-bx-python
1509 (name "python-bx-python")
1513 (uri (pypi-uri "bx-python" version))
1516 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1517 (build-system python-build-system)
1518 ;; Tests fail because test data are not included
1519 (arguments '(#:tests? #f))
1521 `(("python-numpy" ,python-numpy)
1522 ("python-six" ,python-six)))
1526 `(("python-lzo" ,python-lzo)
1527 ("python-nose" ,python-nose)
1528 ("python-cython" ,python-cython)))
1529 (home-page "https://github.com/bxlab/bx-python")
1530 (synopsis "Tools for manipulating biological data")
1532 "bx-python provides tools for manipulating biological data, particularly
1533 multiple sequence alignments.")
1534 (license license:expat)))
1536 (define-public python2-bx-python
1537 (package-with-python2 python-bx-python))
1539 (define-public python-pysam
1541 (name "python-pysam")
1545 ;; Test data is missing on PyPi.
1547 (url "https://github.com/pysam-developers/pysam.git")
1548 (commit (string-append "v" version))))
1549 (file-name (git-file-name name version))
1552 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1553 (modules '((guix build utils)))
1555 ;; Drop bundled htslib. TODO: Also remove samtools
1557 (delete-file-recursively "htslib")
1559 (build-system python-build-system)
1561 `(#:modules ((ice-9 ftw)
1563 (guix build python-build-system)
1566 (modify-phases %standard-phases
1567 (add-before 'build 'set-flags
1568 (lambda* (#:key inputs #:allow-other-keys)
1569 (setenv "HTSLIB_MODE" "external")
1570 (setenv "HTSLIB_LIBRARY_DIR"
1571 (string-append (assoc-ref inputs "htslib") "/lib"))
1572 (setenv "HTSLIB_INCLUDE_DIR"
1573 (string-append (assoc-ref inputs "htslib") "/include"))
1574 (setenv "LDFLAGS" "-lncurses")
1575 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1578 (lambda* (#:key inputs outputs #:allow-other-keys)
1579 ;; This file contains tests that require a connection to the
1581 (delete-file "tests/tabix_test.py")
1582 ;; FIXME: This test fails
1583 (delete-file "tests/AlignmentFile_test.py")
1584 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1585 (setenv "PYTHONPATH"
1587 (getenv "PYTHONPATH")
1588 ":" (getcwd) "/build/"
1589 (car (scandir "build"
1590 (negate (cut string-prefix? "." <>))))))
1591 ;; Step out of source dir so python does not import from CWD.
1592 (with-directory-excursion "tests"
1593 (setenv "HOME" "/tmp")
1594 (invoke "make" "-C" "pysam_data")
1595 (invoke "make" "-C" "cbcf_data")
1596 ;; Running nosetests without explicitly asking for a single
1597 ;; process leads to a crash. Running with multiple processes
1598 ;; fails because the tests are not designed to run in parallel.
1600 ;; FIXME: tests keep timing out on some systems.
1601 (invoke "nosetests" "-v" "--processes" "1")))))))
1603 `(("htslib" ,htslib))) ; Included from installed header files.
1605 `(("ncurses" ,ncurses)
1609 `(("python-cython" ,python-cython)
1610 ;; Dependencies below are are for tests only.
1611 ("samtools" ,samtools)
1612 ("bcftools" ,bcftools)
1613 ("python-nose" ,python-nose)))
1614 (home-page "https://github.com/pysam-developers/pysam")
1615 (synopsis "Python bindings to the SAMtools C API")
1617 "Pysam is a Python module for reading and manipulating files in the
1618 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1619 also includes an interface for tabix.")
1620 (license license:expat)))
1622 (define-public python2-pysam
1623 (package-with-python2 python-pysam))
1625 (define-public python-twobitreader
1627 (name "python-twobitreader")
1632 (url "https://github.com/benjschiller/twobitreader")
1634 (file-name (git-file-name name version))
1637 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1638 (build-system python-build-system)
1639 ;; Tests are not included
1640 (arguments '(#:tests? #f))
1642 `(("python-sphinx" ,python-sphinx)))
1643 (home-page "https://github.com/benjschiller/twobitreader")
1644 (synopsis "Python library for reading .2bit files")
1646 "twobitreader is a Python library for reading .2bit files as used by the
1647 UCSC genome browser.")
1648 (license license:artistic2.0)))
1650 (define-public python2-twobitreader
1651 (package-with-python2 python-twobitreader))
1653 (define-public python-plastid
1655 (name "python-plastid")
1659 (uri (pypi-uri "plastid" version))
1662 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1663 (build-system python-build-system)
1665 ;; Some test files are not included.
1668 `(("python-numpy" ,python-numpy)
1669 ("python-scipy" ,python-scipy)
1670 ("python-pandas" ,python-pandas)
1671 ("python-pysam" ,python-pysam)
1672 ("python-matplotlib" ,python-matplotlib)
1673 ("python-biopython" ,python-biopython)
1674 ("python-twobitreader" ,python-twobitreader)
1675 ("python-termcolor" ,python-termcolor)))
1677 `(("python-cython" ,python-cython)
1678 ("python-nose" ,python-nose)))
1679 (home-page "https://github.com/joshuagryphon/plastid")
1680 (synopsis "Python library for genomic analysis")
1682 "plastid is a Python library for genomic analysis – in particular,
1683 high-throughput sequencing data – with an emphasis on simplicity.")
1684 (license license:bsd-3)))
1686 (define-public python2-plastid
1687 (package-with-python2 python-plastid))
1689 (define-public cd-hit
1695 (uri (string-append "https://github.com/weizhongli/cdhit"
1696 "/releases/download/V" version
1698 "-2017-0621-source.tar.gz"))
1701 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1702 (build-system gnu-build-system)
1704 `(#:tests? #f ; there are no tests
1706 ;; Executables are copied directly to the PREFIX.
1707 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1709 (modify-phases %standard-phases
1710 ;; No "configure" script
1712 ;; Remove sources of non-determinism
1713 (add-after 'unpack 'be-timeless
1715 (substitute* "cdhit-utility.c++"
1716 ((" \\(built on \" __DATE__ \"\\)") ""))
1717 (substitute* "cdhit-common.c++"
1718 (("__DATE__") "\"0\"")
1719 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1721 ;; The "install" target does not create the target directory.
1722 (add-before 'install 'create-target-dir
1723 (lambda* (#:key outputs #:allow-other-keys)
1724 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1728 (home-page "http://weizhongli-lab.org/cd-hit/")
1729 (synopsis "Cluster and compare protein or nucleotide sequences")
1731 "CD-HIT is a program for clustering and comparing protein or nucleotide
1732 sequences. CD-HIT is designed to be fast and handle extremely large
1734 ;; The manual says: "It can be copied under the GNU General Public License
1735 ;; version 2 (GPLv2)."
1736 (license license:gpl2)))
1738 (define-public clipper
1745 (url "https://github.com/YeoLab/clipper.git")
1747 (file-name (git-file-name name version))
1750 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1751 (modules '((guix build utils)))
1754 ;; remove unnecessary setup dependency
1755 (substitute* "setup.py"
1756 (("setup_requires = .*") ""))
1758 (build-system python-build-system)
1760 `(#:python ,python-2 ; only Python 2 is supported
1762 (modify-phases %standard-phases
1763 ;; This is fixed in upstream commit
1764 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1765 (add-after 'unpack 'fix-typo
1767 (substitute* "clipper/src/readsToWiggle.pyx"
1771 `(("htseq" ,python2-htseq)
1772 ("python-pybedtools" ,python2-pybedtools)
1773 ("python-cython" ,python2-cython)
1774 ("python-scikit-learn" ,python2-scikit-learn)
1775 ("python-matplotlib" ,python2-matplotlib)
1776 ("python-pandas" ,python2-pandas)
1777 ("python-pysam" ,python2-pysam)
1778 ("python-numpy" ,python2-numpy)
1779 ("python-scipy" ,python2-scipy)))
1781 `(("python-mock" ,python2-mock) ; for tests
1782 ("python-nose" ,python2-nose) ; for tests
1783 ("python-pytz" ,python2-pytz))) ; for tests
1784 (home-page "https://github.com/YeoLab/clipper")
1785 (synopsis "CLIP peak enrichment recognition")
1787 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1788 (license license:gpl2)))
1790 (define-public codingquarry
1792 (name "codingquarry")
1797 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1801 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1802 (build-system gnu-build-system)
1804 '(#:tests? #f ; no "check" target
1806 (modify-phases %standard-phases
1809 (lambda* (#:key outputs #:allow-other-keys)
1810 (let* ((out (assoc-ref outputs "out"))
1811 (bin (string-append out "/bin"))
1812 (doc (string-append out "/share/doc/codingquarry")))
1813 (install-file "INSTRUCTIONS.pdf" doc)
1814 (copy-recursively "QuarryFiles"
1815 (string-append out "/QuarryFiles"))
1816 (install-file "CodingQuarry" bin)
1817 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1819 (inputs `(("openmpi" ,openmpi)))
1820 (native-search-paths
1821 (list (search-path-specification
1822 (variable "QUARRY_PATH")
1823 (files '("QuarryFiles")))))
1824 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1825 (synopsis "Fungal gene predictor")
1826 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1827 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1828 (home-page "https://sourceforge.net/projects/codingquarry/")
1829 (license license:gpl3+)))
1831 (define-public couger
1838 "http://couger.oit.duke.edu/static/assets/COUGER"
1842 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1843 (build-system gnu-build-system)
1847 (modify-phases %standard-phases
1852 (lambda* (#:key outputs #:allow-other-keys)
1853 (let* ((out (assoc-ref outputs "out"))
1854 (bin (string-append out "/bin")))
1855 (copy-recursively "src" (string-append out "/src"))
1857 ;; Add "src" directory to module lookup path.
1858 (substitute* "couger"
1860 (string-append "import sys\nsys.path.append(\""
1861 out "\")\nfrom argparse")))
1862 (install-file "couger" bin))
1865 'install 'wrap-program
1866 (lambda* (#:key inputs outputs #:allow-other-keys)
1867 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1868 (let* ((out (assoc-ref outputs "out"))
1869 (path (getenv "PYTHONPATH")))
1870 (wrap-program (string-append out "/bin/couger")
1871 `("PYTHONPATH" ":" prefix (,path))))
1874 `(("python" ,python-2)
1875 ("python2-pillow" ,python2-pillow)
1876 ("python2-numpy" ,python2-numpy)
1877 ("python2-scipy" ,python2-scipy)
1878 ("python2-matplotlib" ,python2-matplotlib)))
1880 `(("r-minimal" ,r-minimal)
1882 ("randomjungle" ,randomjungle)))
1884 `(("unzip" ,unzip)))
1885 (home-page "http://couger.oit.duke.edu")
1886 (synopsis "Identify co-factors in sets of genomic regions")
1888 "COUGER can be applied to any two sets of genomic regions bound by
1889 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1890 putative co-factors that provide specificity to each TF. The framework
1891 determines the genomic targets uniquely-bound by each TF, and identifies a
1892 small set of co-factors that best explain the in vivo binding differences
1893 between the two TFs.
1895 COUGER uses classification algorithms (support vector machines and random
1896 forests) with features that reflect the DNA binding specificities of putative
1897 co-factors. The features are generated either from high-throughput TF-DNA
1898 binding data (from protein binding microarray experiments), or from large
1899 collections of DNA motifs.")
1900 (license license:gpl3+)))
1902 (define-public clustal-omega
1904 (name "clustal-omega")
1908 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1912 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1913 (build-system gnu-build-system)
1915 `(("argtable" ,argtable)))
1916 (home-page "http://www.clustal.org/omega/")
1917 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1919 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1920 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1921 of handling data-sets of hundreds of thousands of sequences in reasonable
1923 (license license:gpl2+)))
1925 (define-public crossmap
1931 (uri (pypi-uri "CrossMap" version))
1934 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1935 (build-system python-build-system)
1936 (arguments `(#:python ,python-2))
1938 `(("python-bx-python" ,python2-bx-python)
1939 ("python-numpy" ,python2-numpy)
1940 ("python-pysam" ,python2-pysam)
1943 `(("python-cython" ,python2-cython)
1944 ("python-nose" ,python2-nose)))
1945 (home-page "http://crossmap.sourceforge.net/")
1946 (synopsis "Convert genome coordinates between assemblies")
1948 "CrossMap is a program for conversion of genome coordinates or annotation
1949 files between different genome assemblies. It supports most commonly used
1950 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1951 (license license:gpl2+)))
1953 (define-public python-dnaio
1955 (name "python-dnaio")
1960 (uri (pypi-uri "dnaio" version))
1963 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1964 (build-system python-build-system)
1966 `(("python-cython" ,python-cython)
1967 ("python-pytest" ,python-pytest)
1968 ("python-xopen" ,python-xopen)))
1969 (home-page "https://github.com/marcelm/dnaio/")
1970 (synopsis "Read FASTA and FASTQ files efficiently")
1972 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1973 files. The code was previously part of the cutadapt tool.")
1974 (license license:expat)))
1976 (define-public cutadapt
1983 (url "https://github.com/marcelm/cutadapt.git")
1984 (commit (string-append "v" version))))
1985 (file-name (git-file-name name version))
1988 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1989 (build-system python-build-system)
1991 `(("python-dnaio" ,python-dnaio)
1992 ("python-xopen" ,python-xopen)))
1994 `(("python-cython" ,python-cython)
1995 ("python-pytest" ,python-pytest)))
1996 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1997 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1999 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2000 other types of unwanted sequence from high-throughput sequencing reads.")
2001 (license license:expat)))
2003 (define-public libbigwig
2010 (url "https://github.com/dpryan79/libBigWig.git")
2012 (file-name (string-append name "-" version "-checkout"))
2015 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2016 (build-system gnu-build-system)
2018 `(#:test-target "test"
2019 #:tests? #f ; tests require access to the web
2022 (string-append "prefix=" (assoc-ref %outputs "out")))
2024 (modify-phases %standard-phases
2025 (delete 'configure))))
2030 `(("doxygen" ,doxygen)
2032 ("python" ,python-2)))
2033 (home-page "https://github.com/dpryan79/libBigWig")
2034 (synopsis "C library for handling bigWig files")
2036 "This package provides a C library for parsing local and remote BigWig
2038 (license license:expat)))
2040 (define-public python-pybigwig
2042 (name "python-pybigwig")
2046 (uri (pypi-uri "pyBigWig" version))
2049 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2050 (modules '((guix build utils)))
2053 ;; Delete bundled libBigWig sources
2054 (delete-file-recursively "libBigWig")
2056 (build-system python-build-system)
2059 (modify-phases %standard-phases
2060 (add-after 'unpack 'link-with-libBigWig
2061 (lambda* (#:key inputs #:allow-other-keys)
2062 (substitute* "setup.py"
2063 (("libs=\\[") "libs=[\"BigWig\", "))
2066 `(("python-numpy" ,python-numpy)))
2068 `(("libbigwig" ,libbigwig)
2071 (home-page "https://github.com/dpryan79/pyBigWig")
2072 (synopsis "Access bigWig files in Python using libBigWig")
2074 "This package provides Python bindings to the libBigWig library for
2075 accessing bigWig files.")
2076 (license license:expat)))
2078 (define-public python2-pybigwig
2079 (package-with-python2 python-pybigwig))
2081 (define-public python-dendropy
2083 (name "python-dendropy")
2088 ;; Source from GitHub so that tests are included.
2090 (url "https://github.com/jeetsukumaran/DendroPy.git")
2091 (commit (string-append "v" version))))
2092 (file-name (git-file-name name version))
2095 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2096 (build-system python-build-system)
2097 (home-page "http://packages.python.org/DendroPy/")
2098 (synopsis "Library for phylogenetics and phylogenetic computing")
2100 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2101 writing, simulation, processing and manipulation of phylogenetic
2102 trees (phylogenies) and characters.")
2103 (license license:bsd-3)))
2105 (define-public python2-dendropy
2106 (let ((base (package-with-python2 python-dendropy)))
2111 (modify-phases %standard-phases
2112 (add-after 'unpack 'remove-failing-test
2114 ;; This test fails when the full test suite is run, as documented
2115 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2116 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2117 (("test_collection_comments_and_annotations")
2118 "do_not_test_collection_comments_and_annotations"))
2120 ,@(package-arguments base))))))
2122 (define-public python-py2bit
2124 (name "python-py2bit")
2129 (uri (pypi-uri "py2bit" version))
2132 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2133 (build-system python-build-system)
2134 (home-page "https://github.com/dpryan79/py2bit")
2135 (synopsis "Access 2bit files using lib2bit")
2137 "This package provides Python bindings for lib2bit to access 2bit files
2139 (license license:expat)))
2141 (define-public deeptools
2148 (url "https://github.com/deeptools/deepTools.git")
2150 (file-name (git-file-name name version))
2153 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2154 (build-system python-build-system)
2157 (modify-phases %standard-phases
2158 ;; This phase fails, but it's not needed.
2159 (delete 'reset-gzip-timestamps))))
2161 `(("python-plotly" ,python-plotly)
2162 ("python-scipy" ,python-scipy)
2163 ("python-numpy" ,python-numpy)
2164 ("python-numpydoc" ,python-numpydoc)
2165 ("python-matplotlib" ,python-matplotlib)
2166 ("python-pysam" ,python-pysam)
2167 ("python-py2bit" ,python-py2bit)
2168 ("python-pybigwig" ,python-pybigwig)))
2170 `(("python-mock" ,python-mock) ;for tests
2171 ("python-nose" ,python-nose) ;for tests
2172 ("python-pytz" ,python-pytz))) ;for tests
2173 (home-page "https://github.com/deeptools/deepTools")
2174 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2176 "DeepTools addresses the challenge of handling the large amounts of data
2177 that are now routinely generated from DNA sequencing centers. To do so,
2178 deepTools contains useful modules to process the mapped reads data to create
2179 coverage files in standard bedGraph and bigWig file formats. By doing so,
2180 deepTools allows the creation of normalized coverage files or the comparison
2181 between two files (for example, treatment and control). Finally, using such
2182 normalized and standardized files, multiple visualizations can be created to
2183 identify enrichments with functional annotations of the genome.")
2184 (license license:gpl3+)))
2186 (define-public delly
2193 (url "https://github.com/dellytools/delly.git")
2194 (commit (string-append "v" version))))
2195 (file-name (git-file-name name version))
2197 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2198 (modules '((guix build utils)))
2201 (delete-file-recursively "src/htslib")
2203 (build-system gnu-build-system)
2205 `(#:tests? #f ; There are no tests to run.
2207 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2208 (string-append "prefix=" (assoc-ref %outputs "out")))
2210 (modify-phases %standard-phases
2211 (delete 'configure) ; There is no configure phase.
2212 (add-after 'install 'install-templates
2213 (lambda* (#:key outputs #:allow-other-keys)
2214 (let ((templates (string-append (assoc-ref outputs "out")
2215 "/share/delly/templates")))
2217 (copy-recursively "excludeTemplates" templates)
2224 (home-page "https://github.com/dellytools/delly")
2225 (synopsis "Integrated structural variant prediction method")
2226 (description "Delly is an integrated structural variant prediction method
2227 that can discover and genotype deletions, tandem duplications, inversions and
2228 translocations at single-nucleotide resolution in short-read massively parallel
2229 sequencing data. It uses paired-ends and split-reads to sensitively and
2230 accurately delineate genomic rearrangements throughout the genome.")
2231 (license license:gpl3+)))
2233 (define-public diamond
2240 (url "https://github.com/bbuchfink/diamond.git")
2241 (commit (string-append "v" version))))
2242 (file-name (git-file-name name version))
2245 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2246 (build-system cmake-build-system)
2248 '(#:tests? #f ; no "check" target
2250 (modify-phases %standard-phases
2251 (add-after 'unpack 'remove-native-compilation
2253 (substitute* "CMakeLists.txt" (("-march=native") ""))
2257 (home-page "https://github.com/bbuchfink/diamond")
2258 (synopsis "Accelerated BLAST compatible local sequence aligner")
2260 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2261 translated DNA query sequences against a protein reference database (BLASTP
2262 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2263 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2264 data and settings.")
2265 (license license:agpl3+)))
2267 (define-public discrover
2275 (url "https://github.com/maaskola/discrover.git")
2277 (file-name (git-file-name name version))
2280 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2281 (build-system cmake-build-system)
2283 `(#:tests? #f ; there are no tests
2285 (modify-phases %standard-phases
2286 (add-after 'unpack 'add-missing-includes
2288 (substitute* "src/executioninformation.hpp"
2289 (("#define EXECUTIONINFORMATION_HPP" line)
2290 (string-append line "\n#include <random>")))
2291 (substitute* "src/plasma/fasta.hpp"
2292 (("#define FASTA_HPP" line)
2293 (string-append line "\n#include <random>")))
2299 `(("texlive" ,texlive)
2300 ("imagemagick" ,imagemagick)))
2301 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2302 (synopsis "Discover discriminative nucleotide sequence motifs")
2303 (description "Discrover is a motif discovery method to find binding sites
2304 of nucleic acid binding proteins.")
2305 (license license:gpl3+)))
2307 (define-public eigensoft
2315 (url "https://github.com/DReichLab/EIG.git")
2316 (commit (string-append "v" version))))
2317 (file-name (git-file-name name version))
2320 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2321 (modules '((guix build utils)))
2322 ;; Remove pre-built binaries.
2324 (delete-file-recursively "bin")
2327 (build-system gnu-build-system)
2329 `(#:tests? #f ; There are no tests.
2330 #:make-flags '("CC=gcc")
2332 (modify-phases %standard-phases
2333 ;; There is no configure phase, but the Makefile is in a
2336 (lambda _ (chdir "src") #t))
2337 ;; The provided install target only copies executables to
2338 ;; the "bin" directory in the build root.
2339 (add-after 'install 'actually-install
2340 (lambda* (#:key outputs #:allow-other-keys)
2341 (let* ((out (assoc-ref outputs "out"))
2342 (bin (string-append out "/bin")))
2343 (for-each (lambda (file)
2344 (install-file file bin))
2345 (find-files "../bin" ".*"))
2350 ("openblas" ,openblas)
2352 ("gfortran" ,gfortran "lib")))
2353 (home-page "https://github.com/DReichLab/EIG")
2354 (synopsis "Tools for population genetics")
2355 (description "The EIGENSOFT package provides tools for population
2356 genetics and stratification correction. EIGENSOFT implements methods commonly
2357 used in population genetics analyses such as PCA, computation of Tracy-Widom
2358 statistics, and finding related individuals in structured populations. It
2359 comes with a built-in plotting script and supports multiple file formats and
2360 quantitative phenotypes.")
2361 ;; The license of the eigensoft tools is Expat, but since it's
2362 ;; linking with the GNU Scientific Library (GSL) the effective
2363 ;; license is the GPL.
2364 (license license:gpl3+)))
2366 (define-public edirect
2369 (version "10.2.20181018")
2372 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2373 "/versions/" version
2374 "/edirect-" version ".tar.gz"))
2377 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2378 (build-system perl-build-system)
2381 (modify-phases %standard-phases
2384 (delete 'check) ; simple check after install
2386 (lambda* (#:key outputs #:allow-other-keys)
2387 (install-file "edirect.pl"
2388 (string-append (assoc-ref outputs "out") "/bin"))
2390 (add-after 'install 'wrap-program
2391 (lambda* (#:key outputs #:allow-other-keys)
2392 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2393 (let* ((out (assoc-ref outputs "out"))
2394 (path (getenv "PERL5LIB")))
2395 (wrap-program (string-append out "/bin/edirect.pl")
2396 `("PERL5LIB" ":" prefix (,path))))
2398 (add-after 'wrap-program 'check
2399 (lambda* (#:key outputs #:allow-other-keys)
2400 (invoke (string-append (assoc-ref outputs "out")
2405 `(("perl-html-parser" ,perl-html-parser)
2406 ("perl-encode-locale" ,perl-encode-locale)
2407 ("perl-file-listing" ,perl-file-listing)
2408 ("perl-html-tagset" ,perl-html-tagset)
2409 ("perl-html-tree" ,perl-html-tree)
2410 ("perl-http-cookies" ,perl-http-cookies)
2411 ("perl-http-date" ,perl-http-date)
2412 ("perl-http-message" ,perl-http-message)
2413 ("perl-http-negotiate" ,perl-http-negotiate)
2414 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2415 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2416 ("perl-net-http" ,perl-net-http)
2417 ("perl-uri" ,perl-uri)
2418 ("perl-www-robotrules" ,perl-www-robotrules)
2419 ("perl-xml-simple" ,perl-xml-simple)
2421 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2422 (synopsis "Tools for accessing the NCBI's set of databases")
2424 "Entrez Direct (EDirect) is a method for accessing the National Center
2425 for Biotechnology Information's (NCBI) set of interconnected
2426 databases (publication, sequence, structure, gene, variation, expression,
2427 etc.) from a terminal. Functions take search terms from command-line
2428 arguments. Individual operations are combined to build multi-step queries.
2429 Record retrieval and formatting normally complete the process.
2431 EDirect also provides an argument-driven function that simplifies the
2432 extraction of data from document summaries or other results that are returned
2433 in structured XML format. This can eliminate the need for writing custom
2434 software to answer ad hoc questions.")
2435 (license license:public-domain)))
2437 (define-public exonerate
2446 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2447 "exonerate-" version ".tar.gz"))
2450 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2451 (build-system gnu-build-system)
2453 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2455 `(("pkg-config" ,pkg-config)))
2459 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2460 (synopsis "Generic tool for biological sequence alignment")
2462 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2463 the alignment of sequences using a many alignment models, either exhaustive
2464 dynamic programming or a variety of heuristics.")
2465 (license license:gpl3)))
2467 (define-public express
2475 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2476 version "/express-" version "-src.tgz"))
2479 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2480 (build-system cmake-build-system)
2482 `(#:tests? #f ;no "check" target
2484 (modify-phases %standard-phases
2485 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2486 (lambda* (#:key inputs #:allow-other-keys)
2487 (substitute* "CMakeLists.txt"
2488 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2489 "set(Boost_USE_STATIC_LIBS OFF)")
2490 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2491 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2492 (substitute* "src/CMakeLists.txt"
2493 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2494 (string-append (assoc-ref inputs "bamtools") "/lib"))
2495 (("libprotobuf.a") "libprotobuf.so"))
2499 ("bamtools" ,bamtools)
2500 ("protobuf" ,protobuf)
2502 (home-page "http://bio.math.berkeley.edu/eXpress")
2503 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2505 "eXpress is a streaming tool for quantifying the abundances of a set of
2506 target sequences from sampled subsequences. Example applications include
2507 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2508 analysis (from RNA-Seq), transcription factor binding quantification in
2509 ChIP-Seq, and analysis of metagenomic data.")
2510 (license license:artistic2.0)))
2512 (define-public express-beta-diversity
2514 (name "express-beta-diversity")
2519 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2520 (commit (string-append "v" version))))
2521 (file-name (git-file-name name version))
2524 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2525 (build-system gnu-build-system)
2528 (modify-phases %standard-phases
2530 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2532 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2534 (lambda* (#:key outputs #:allow-other-keys)
2535 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2536 (install-file "../scripts/convertToEBD.py" bin)
2537 (install-file "../bin/ExpressBetaDiversity" bin)
2540 `(("python" ,python-2)))
2541 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2542 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2544 "Express Beta Diversity (EBD) calculates ecological beta diversity
2545 (dissimilarity) measures between biological communities. EBD implements a
2546 variety of diversity measures including those that make use of phylogenetic
2547 similarity of community members.")
2548 (license license:gpl3+)))
2550 (define-public fasttree
2557 "http://www.microbesonline.org/fasttree/FastTree-"
2561 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2562 (build-system gnu-build-system)
2564 `(#:tests? #f ; no "check" target
2566 (modify-phases %standard-phases
2570 (lambda* (#:key source #:allow-other-keys)
2573 "-finline-functions"
2584 "-finline-functions"
2593 (lambda* (#:key outputs #:allow-other-keys)
2594 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2595 (install-file "FastTree" bin)
2596 (install-file "FastTreeMP" bin)
2598 (home-page "http://www.microbesonline.org/fasttree")
2599 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2601 "FastTree can handle alignments with up to a million of sequences in a
2602 reasonable amount of time and memory. For large alignments, FastTree is
2603 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2604 (license license:gpl2+)))
2606 (define-public fastx-toolkit
2608 (name "fastx-toolkit")
2614 "https://github.com/agordon/fastx_toolkit/releases/download/"
2615 version "/fastx_toolkit-" version ".tar.bz2"))
2618 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2619 (build-system gnu-build-system)
2621 `(("libgtextutils" ,libgtextutils)))
2623 `(("pkg-config" ,pkg-config)))
2624 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2625 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2627 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2628 FASTA/FASTQ files preprocessing.
2630 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2631 containing multiple short-reads sequences. The main processing of such
2632 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2633 is sometimes more productive to preprocess the files before mapping the
2634 sequences to the genome---manipulating the sequences to produce better mapping
2635 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2636 (license license:agpl3+)))
2638 (define-public flexbar
2645 (url "https://github.com/seqan/flexbar.git")
2646 (commit (string-append "v" version))))
2647 (file-name (git-file-name name version))
2650 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2651 (build-system cmake-build-system)
2654 (modify-phases %standard-phases
2656 (lambda* (#:key outputs #:allow-other-keys)
2657 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2658 (with-directory-excursion "../source/test"
2659 (invoke "bash" "flexbar_test.sh"))
2662 (lambda* (#:key outputs #:allow-other-keys)
2663 (let* ((out (string-append (assoc-ref outputs "out")))
2664 (bin (string-append out "/bin/")))
2665 (install-file "flexbar" bin))
2671 `(("pkg-config" ,pkg-config)
2673 (home-page "https://github.com/seqan/flexbar")
2674 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2676 "Flexbar preprocesses high-throughput nucleotide sequencing data
2677 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2678 Moreover, trimming and filtering features are provided. Flexbar increases
2679 read mapping rates and improves genome and transcriptome assemblies. It
2680 supports next-generation sequencing data in fasta/q and csfasta/q format from
2681 Illumina, Roche 454, and the SOLiD platform.")
2682 (license license:bsd-3)))
2684 (define-public fraggenescan
2686 (name "fraggenescan")
2692 (string-append "mirror://sourceforge/fraggenescan/"
2693 "FragGeneScan" version ".tar.gz"))
2695 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2696 (build-system gnu-build-system)
2699 (modify-phases %standard-phases
2701 (add-before 'build 'patch-paths
2702 (lambda* (#:key outputs #:allow-other-keys)
2703 (let* ((out (string-append (assoc-ref outputs "out")))
2704 (share (string-append out "/share/fraggenescan/")))
2705 (substitute* "run_FragGeneScan.pl"
2707 (string-append "system(\"" (which "rm")))
2709 (string-append "system(\"" (which "mv")))
2710 (("\\\"awk") (string-append "\"" (which "awk")))
2711 ;; This script and other programs expect the training files
2712 ;; to be in the non-standard location bin/train/XXX. Change
2713 ;; this to be share/fraggenescan/train/XXX instead.
2714 (("^\\$train.file = \\$dir.*")
2715 (string-append "$train_file = \""
2717 "train/\".$FGS_train_file;")))
2718 (substitute* "run_hmm.c"
2719 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2720 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2724 (invoke "make" "clean")
2725 (invoke "make" "fgs")
2728 (lambda* (#:key outputs #:allow-other-keys)
2729 (let* ((out (string-append (assoc-ref outputs "out")))
2730 (bin (string-append out "/bin/"))
2731 (share (string-append out "/share/fraggenescan/train")))
2732 (install-file "run_FragGeneScan.pl" bin)
2733 (install-file "FragGeneScan" bin)
2734 (copy-recursively "train" share))
2737 (add-after 'install 'post-install-check
2738 ;; In lieu of 'make check', run one of the examples and check the
2739 ;; output files gets created.
2740 (lambda* (#:key outputs #:allow-other-keys)
2741 (let* ((out (string-append (assoc-ref outputs "out")))
2742 (bin (string-append out "/bin/"))
2743 (frag (string-append bin "run_FragGeneScan.pl")))
2744 ;; Test complete genome.
2746 "-genome=./example/NC_000913.fna"
2750 (unless (and (file-exists? "test2.faa")
2751 (file-exists? "test2.ffn")
2752 (file-exists? "test2.gff")
2753 (file-exists? "test2.out"))
2754 (error "Expected files do not exist."))
2755 ;; Test incomplete sequences.
2757 "-genome=./example/NC_000913-fgs.ffn"
2764 ("python" ,python-2))) ;not compatible with python 3.
2765 (home-page "https://sourceforge.net/projects/fraggenescan/")
2766 (synopsis "Finds potentially fragmented genes in short reads")
2768 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2769 short and error-prone DNA sequencing reads. It can also be applied to predict
2770 genes in incomplete assemblies or complete genomes.")
2771 ;; GPL3+ according to private correspondense with the authors.
2772 (license license:gpl3+)))
2774 (define-public fxtract
2775 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2783 (url "https://github.com/ctSkennerton/fxtract.git")
2785 (file-name (git-file-name name version))
2788 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2789 (build-system gnu-build-system)
2791 `(#:make-flags (list
2792 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2794 #:test-target "fxtract_test"
2796 (modify-phases %standard-phases
2798 (add-before 'build 'copy-util
2799 (lambda* (#:key inputs #:allow-other-keys)
2801 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2803 ;; Do not use make install as this requires additional dependencies.
2805 (lambda* (#:key outputs #:allow-other-keys)
2806 (let* ((out (assoc-ref outputs "out"))
2807 (bin (string-append out"/bin")))
2808 (install-file "fxtract" bin)
2814 ;; ctskennerton-util is licensed under GPL2.
2815 `(("ctskennerton-util"
2819 (url "https://github.com/ctSkennerton/util.git")
2820 (commit util-commit)))
2821 (file-name (string-append
2822 "ctstennerton-util-" util-commit "-checkout"))
2825 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2826 (home-page "https://github.com/ctSkennerton/fxtract")
2827 (synopsis "Extract sequences from FASTA and FASTQ files")
2829 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2830 or FASTQ) file given a subsequence. It uses a simple substring search for
2831 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2832 lookups or multi-pattern searching as required. By default fxtract looks in
2833 the sequence of each record but can also be told to look in the header,
2834 comment or quality sections.")
2835 ;; 'util' requires SSE instructions.
2836 (supported-systems '("x86_64-linux"))
2837 (license license:expat))))
2839 (define-public gemma
2846 (url "https://github.com/xiangzhou/GEMMA.git")
2847 (commit (string-append "v" version))))
2848 (file-name (git-file-name name version))
2851 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2854 ("gfortran" ,gfortran "lib")
2857 ("openblas" ,openblas)
2859 (build-system gnu-build-system)
2862 '(,@(match (%current-system)
2864 '("FORCE_DYNAMIC=1"))
2866 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2868 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2870 (modify-phases %standard-phases
2872 (add-after 'unpack 'find-eigen
2873 (lambda* (#:key inputs #:allow-other-keys)
2874 ;; Ensure that Eigen headers can be found
2875 (setenv "CPLUS_INCLUDE_PATH"
2876 (string-append (getenv "CPLUS_INCLUDE_PATH")
2878 (assoc-ref inputs "eigen")
2881 (add-before 'build 'bin-mkdir
2886 (lambda* (#:key outputs #:allow-other-keys)
2887 (let ((out (assoc-ref outputs "out")))
2888 (install-file "bin/gemma"
2892 #:tests? #f)) ; no tests included yet
2893 (home-page "https://github.com/xiangzhou/GEMMA")
2894 (synopsis "Tool for genome-wide efficient mixed model association")
2896 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2897 standard linear mixed model resolver with application in genome-wide
2898 association studies (GWAS).")
2899 (license license:gpl3)))
2908 (url "https://github.com/nboley/grit.git")
2910 (file-name (git-file-name name version))
2913 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
2914 (build-system python-build-system)
2916 `(#:python ,python-2
2918 (modify-phases %standard-phases
2919 (add-after 'unpack 'generate-from-cython-sources
2920 (lambda* (#:key inputs outputs #:allow-other-keys)
2921 ;; Delete these C files to force fresh generation from pyx sources.
2922 (delete-file "grit/sparsify_support_fns.c")
2923 (delete-file "grit/call_peaks_support_fns.c")
2924 (substitute* "setup.py"
2925 (("Cython.Setup") "Cython.Build"))
2928 `(("python-scipy" ,python2-scipy)
2929 ("python-numpy" ,python2-numpy)
2930 ("python-pysam" ,python2-pysam)
2931 ("python-networkx" ,python2-networkx)))
2933 `(("python-cython" ,python2-cython)))
2934 (home-page "http://grit-bio.org")
2935 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2937 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2938 full length transcript models. When none of these data sources are available,
2939 GRIT can be run by providing a candidate set of TES or TSS sites. In
2940 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2941 also be run in quantification mode, where it uses a provided GTF file and just
2942 estimates transcript expression.")
2943 (license license:gpl3+)))
2945 (define-public hisat
2952 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2953 version "-beta-source.zip"))
2956 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2957 (build-system gnu-build-system)
2959 `(#:tests? #f ;no check target
2960 #:make-flags '("allall"
2961 ;; Disable unsupported `popcnt' instructions on
2962 ;; architectures other than x86_64
2963 ,@(if (string-prefix? "x86_64"
2964 (or (%current-target-system)
2967 '("POPCNT_CAPABILITY=0")))
2969 (modify-phases %standard-phases
2970 (add-after 'unpack 'patch-sources
2972 ;; XXX Cannot use snippet because zip files are not supported
2973 (substitute* "Makefile"
2974 (("^CC = .*$") "CC = gcc")
2975 (("^CPP = .*$") "CPP = g++")
2976 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2977 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2978 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2979 (substitute* '("hisat-build" "hisat-inspect")
2980 (("/usr/bin/env") (which "env")))
2983 (lambda* (#:key outputs #:allow-other-keys)
2984 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2985 (for-each (lambda (file)
2986 (install-file file bin))
2989 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2991 (delete 'configure))))
2993 `(("unzip" ,unzip)))
2998 ;; Non-portable SSE instructions are used so building fails on platforms
2999 ;; other than x86_64.
3000 (supported-systems '("x86_64-linux"))
3001 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3002 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3004 "HISAT is a fast and sensitive spliced alignment program for mapping
3005 RNA-seq reads. In addition to one global FM index that represents a whole
3006 genome, HISAT uses a large set of small FM indexes that collectively cover the
3007 whole genome. These small indexes (called local indexes) combined with
3008 several alignment strategies enable effective alignment of RNA-seq reads, in
3009 particular, reads spanning multiple exons.")
3010 (license license:gpl3+)))
3012 (define-public hisat2
3019 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3020 "/downloads/hisat2-" version "-source.zip"))
3023 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3024 (build-system gnu-build-system)
3026 `(#:tests? #f ; no check target
3027 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3028 #:modules ((guix build gnu-build-system)
3032 (modify-phases %standard-phases
3033 (add-after 'unpack 'make-deterministic
3035 (substitute* "Makefile"
3040 (lambda* (#:key outputs #:allow-other-keys)
3041 (let* ((out (assoc-ref outputs "out"))
3042 (bin (string-append out "/bin/"))
3043 (doc (string-append out "/share/doc/hisat2/")))
3045 (cut install-file <> bin)
3047 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3049 (install-file "doc/manual.inc.html" doc))
3052 `(("unzip" ,unzip) ; needed for archive from ftp
3054 ("pandoc" ,ghc-pandoc))) ; for documentation
3055 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3056 (synopsis "Graph-based alignment of genomic sequencing reads")
3057 (description "HISAT2 is a fast and sensitive alignment program for mapping
3058 next-generation sequencing reads (both DNA and RNA) to a population of human
3059 genomes (as well as to a single reference genome). In addition to using one
3060 global @dfn{graph FM} (GFM) index that represents a population of human
3061 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3062 the whole genome. These small indexes, combined with several alignment
3063 strategies, enable rapid and accurate alignment of sequencing reads. This new
3064 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3065 ;; HISAT2 contains files from Bowtie2, which is released under
3066 ;; GPLv2 or later. The HISAT2 source files are released under
3068 (license license:gpl3+)))
3070 (define-public hmmer
3078 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3081 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3082 (build-system gnu-build-system)
3083 (native-inputs `(("perl" ,perl)))
3084 (home-page "http://hmmer.org/")
3085 (synopsis "Biosequence analysis using profile hidden Markov models")
3087 "HMMER is used for searching sequence databases for homologs of protein
3088 sequences, and for making protein sequence alignments. It implements methods
3089 using probabilistic models called profile hidden Markov models (profile
3091 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3093 (supported-systems '("x86_64-linux" "i686-linux"))
3094 (license license:bsd-3)))
3096 (define-public htseq
3102 (uri (pypi-uri "HTSeq" version))
3105 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3106 (build-system python-build-system)
3108 `(("python-cython" ,python-cython)))
3109 ;; Numpy needs to be propagated when htseq is used as a Python library.
3111 `(("python-numpy" ,python-numpy)))
3113 `(("python-pysam" ,python-pysam)
3114 ("python-matplotlib" ,python-matplotlib)))
3115 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3116 (synopsis "Analysing high-throughput sequencing data with Python")
3118 "HTSeq is a Python package that provides infrastructure to process data
3119 from high-throughput sequencing assays.")
3120 (license license:gpl3+)))
3122 (define-public python2-htseq
3123 (package-with-python2 htseq))
3125 (define-public java-htsjdk
3127 (name "java-htsjdk")
3128 (version "2.3.0") ; last version without build dependency on gradle
3132 (url "https://github.com/samtools/htsjdk.git")
3134 (file-name (git-file-name name version))
3137 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3138 (modules '((guix build utils)))
3140 ;; Delete pre-built binaries
3142 (delete-file-recursively "lib")
3145 (build-system ant-build-system)
3147 `(#:tests? #f ; test require Internet access
3150 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3151 "/share/java/htsjdk/"))
3152 #:build-target "all"
3154 (modify-phases %standard-phases
3155 ;; The build phase also installs the jars
3156 (delete 'install))))
3158 `(("java-ngs" ,java-ngs)
3159 ("java-snappy-1" ,java-snappy-1)
3160 ("java-commons-compress" ,java-commons-compress)
3161 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3162 ("java-commons-jexl-2" ,java-commons-jexl-2)
3163 ("java-xz" ,java-xz)))
3165 `(("java-testng" ,java-testng)))
3166 (home-page "http://samtools.github.io/htsjdk/")
3167 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3169 "HTSJDK is an implementation of a unified Java library for accessing
3170 common file formats, such as SAM and VCF, used for high-throughput
3171 sequencing (HTS) data. There are also an number of useful utilities for
3172 manipulating HTS data.")
3173 (license license:expat)))
3175 (define-public java-htsjdk-latest
3177 (name "java-htsjdk")
3182 (url "https://github.com/samtools/htsjdk.git")
3184 (file-name (string-append name "-" version "-checkout"))
3187 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3188 (build-system ant-build-system)
3190 `(#:tests? #f ; test require Scala
3192 #:jar-name "htsjdk.jar"
3194 (modify-phases %standard-phases
3195 (add-after 'unpack 'remove-useless-build.xml
3196 (lambda _ (delete-file "build.xml") #t))
3197 ;; The tests require the scalatest package.
3198 (add-after 'unpack 'remove-tests
3199 (lambda _ (delete-file-recursively "src/test") #t)))))
3201 `(("java-ngs" ,java-ngs)
3202 ("java-snappy-1" ,java-snappy-1)
3203 ("java-commons-compress" ,java-commons-compress)
3204 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3205 ("java-commons-jexl-2" ,java-commons-jexl-2)
3206 ("java-xz" ,java-xz)))
3208 `(("java-junit" ,java-junit)))
3209 (home-page "http://samtools.github.io/htsjdk/")
3210 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3212 "HTSJDK is an implementation of a unified Java library for accessing
3213 common file formats, such as SAM and VCF, used for high-throughput
3214 sequencing (HTS) data. There are also an number of useful utilities for
3215 manipulating HTS data.")
3216 (license license:expat)))
3218 ;; This is needed for picard 2.10.3
3219 (define-public java-htsjdk-2.10.1
3220 (package (inherit java-htsjdk-latest)
3221 (name "java-htsjdk")
3226 (url "https://github.com/samtools/htsjdk.git")
3228 (file-name (string-append name "-" version "-checkout"))
3231 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3232 (build-system ant-build-system)
3234 `(#:tests? #f ; tests require Scala
3236 #:jar-name "htsjdk.jar"
3238 (modify-phases %standard-phases
3239 (add-after 'unpack 'remove-useless-build.xml
3240 (lambda _ (delete-file "build.xml") #t))
3241 ;; The tests require the scalatest package.
3242 (add-after 'unpack 'remove-tests
3243 (lambda _ (delete-file-recursively "src/test") #t)))))))
3245 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3246 ;; recent version of java-htsjdk, which depends on gradle.
3247 (define-public java-picard
3249 (name "java-picard")
3254 (url "https://github.com/broadinstitute/picard.git")
3256 (file-name (string-append "java-picard-" version "-checkout"))
3259 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3260 (modules '((guix build utils)))
3263 ;; Delete pre-built binaries.
3264 (delete-file-recursively "lib")
3266 (substitute* "build.xml"
3267 ;; Remove build-time dependency on git.
3268 (("failifexecutionfails=\"true\"")
3269 "failifexecutionfails=\"false\"")
3271 (("depends=\"compile-htsjdk, ")
3273 (("depends=\"compile-htsjdk-tests, ")
3275 ;; Build picard-lib.jar before building picard.jar
3276 (("name=\"picard-jar\" depends=\"" line)
3277 (string-append line "picard-lib-jar, ")))
3279 (build-system ant-build-system)
3281 `(#:build-target "picard-jar"
3282 #:test-target "test"
3283 ;; Tests require jacoco:coverage.
3286 (list (string-append "-Dhtsjdk_lib_dir="
3287 (assoc-ref %build-inputs "java-htsjdk")
3288 "/share/java/htsjdk/")
3289 "-Dhtsjdk-classes=dist/tmp"
3290 (string-append "-Dhtsjdk-version="
3291 ,(package-version java-htsjdk)))
3294 (modify-phases %standard-phases
3295 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3296 (delete 'generate-jar-indices)
3297 (add-after 'unpack 'use-our-htsjdk
3298 (lambda* (#:key inputs #:allow-other-keys)
3299 (substitute* "build.xml"
3300 (("\\$\\{htsjdk\\}/lib")
3301 (string-append (assoc-ref inputs "java-htsjdk")
3302 "/share/java/htsjdk/")))
3304 (add-after 'unpack 'make-test-target-independent
3305 (lambda* (#:key inputs #:allow-other-keys)
3306 (substitute* "build.xml"
3307 (("name=\"test\" depends=\"compile, ")
3308 "name=\"test\" depends=\""))
3310 (replace 'install (install-jars "dist")))))
3312 `(("java-htsjdk" ,java-htsjdk)
3313 ("java-guava" ,java-guava)))
3315 `(("java-testng" ,java-testng)))
3316 (home-page "http://broadinstitute.github.io/picard/")
3317 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3318 (description "Picard is a set of Java command line tools for manipulating
3319 high-throughput sequencing (HTS) data and formats. Picard is implemented
3320 using the HTSJDK Java library to support accessing file formats that are
3321 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3323 (license license:expat)))
3325 ;; This is needed for dropseq-tools
3326 (define-public java-picard-2.10.3
3328 (name "java-picard")
3333 (url "https://github.com/broadinstitute/picard.git")
3335 (file-name (string-append "java-picard-" version "-checkout"))
3338 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3339 (build-system ant-build-system)
3341 `(#:jar-name "picard.jar"
3342 ;; Tests require jacoco:coverage.
3345 #:main-class "picard.cmdline.PicardCommandLine"
3346 #:modules ((guix build ant-build-system)
3348 (guix build java-utils)
3353 (modify-phases %standard-phases
3354 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3355 (delete 'generate-jar-indices)
3356 (add-after 'unpack 'remove-useless-build.xml
3357 (lambda _ (delete-file "build.xml") #t))
3358 ;; This is necessary to ensure that htsjdk is found when using
3359 ;; picard.jar as an executable.
3360 (add-before 'build 'edit-classpath-in-manifest
3361 (lambda* (#:key inputs #:allow-other-keys)
3362 (chmod "build.xml" #o664)
3363 (call-with-output-file "build.xml.new"
3367 (with-input-from-file "build.xml"
3368 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3369 `((target . ,(lambda (tag . kids)
3370 (let ((name ((sxpath '(name *text*))
3372 ;; FIXME: We're breaking the line
3373 ;; early with a dummy path to
3374 ;; ensure that the store reference
3375 ;; isn't broken apart and can still
3376 ;; be found by the reference
3381 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3382 ;; maximum line length is 70
3383 (string-tabulate (const #\b) 57)
3384 (assoc-ref inputs "java-htsjdk"))))
3385 (if (member "manifest" name)
3388 (@ (file "${manifest.file}")
3389 (match "\\r\\n\\r\\n")
3390 (replace "${line.separator}")))
3393 (file "${manifest.file}")
3396 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3397 (*text* . ,(lambda (_ txt) txt))))
3399 (rename-file "build.xml.new" "build.xml")
3402 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3404 `(("java-testng" ,java-testng)
3405 ("java-guava" ,java-guava)))
3406 (home-page "http://broadinstitute.github.io/picard/")
3407 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3408 (description "Picard is a set of Java command line tools for manipulating
3409 high-throughput sequencing (HTS) data and formats. Picard is implemented
3410 using the HTSJDK Java library to support accessing file formats that are
3411 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3413 (license license:expat)))
3415 ;; This is the last version of Picard to provide net.sf.samtools
3416 (define-public java-picard-1.113
3417 (package (inherit java-picard)
3418 (name "java-picard")
3423 (url "https://github.com/broadinstitute/picard.git")
3425 (file-name (string-append "java-picard-" version "-checkout"))
3428 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3429 (modules '((guix build utils)))
3432 ;; Delete pre-built binaries.
3433 (delete-file-recursively "lib")
3436 (build-system ant-build-system)
3438 `(#:build-target "picard-jar"
3439 #:test-target "test"
3440 ;; FIXME: the class path at test time is wrong.
3441 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3442 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3445 ;; This is only used for tests.
3447 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3449 (modify-phases %standard-phases
3450 ;; FIXME: This phase fails.
3451 (delete 'generate-jar-indices)
3452 ;; Do not use bundled ant bzip2.
3453 (add-after 'unpack 'use-ant-bzip
3454 (lambda* (#:key inputs #:allow-other-keys)
3455 (substitute* "build.xml"
3456 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3457 (string-append (assoc-ref inputs "ant")
3460 (add-after 'unpack 'make-test-target-independent
3461 (lambda* (#:key inputs #:allow-other-keys)
3462 (substitute* "build.xml"
3463 (("name=\"test\" depends=\"compile, ")
3464 "name=\"test\" depends=\"compile-tests, ")
3465 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3466 "name=\"compile\" depends=\"compile-src\""))
3468 (add-after 'unpack 'fix-deflater-path
3469 (lambda* (#:key outputs #:allow-other-keys)
3470 (substitute* "src/java/net/sf/samtools/Defaults.java"
3471 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3472 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3473 (assoc-ref outputs "out")
3474 "/lib/jni/libIntelDeflater.so"
3477 ;; Build the deflater library, because we've previously deleted the
3478 ;; pre-built one. This can only be built with access to the JDK
3480 (add-after 'build 'build-jni
3481 (lambda* (#:key inputs #:allow-other-keys)
3484 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3485 "-xf" (assoc-ref inputs "jdk-src"))
3486 (invoke "javah" "-jni"
3487 "-classpath" "classes"
3489 "net.sf.samtools.util.zip.IntelDeflater")
3490 (with-directory-excursion "src/c/inteldeflater"
3491 (invoke "gcc" "-I../../../lib" "-I."
3492 (string-append "-I" (assoc-ref inputs "jdk")
3494 "-I../../../jdk-src/src/share/native/common/"
3495 "-I../../../jdk-src/src/solaris/native/common/"
3496 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3497 (invoke "gcc" "-shared"
3498 "-o" "../../../lib/jni/libIntelDeflater.so"
3499 "IntelDeflater.o" "-lz" "-lstdc++"))
3501 ;; We can only build everything else after building the JNI library.
3502 (add-after 'build-jni 'build-rest
3503 (lambda* (#:key make-flags #:allow-other-keys)
3504 (apply invoke `("ant" "all" ,@make-flags))
3506 (add-before 'build 'set-JAVA6_HOME
3508 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3510 (replace 'install (install-jars "dist"))
3511 (add-after 'install 'install-jni-lib
3512 (lambda* (#:key outputs #:allow-other-keys)
3513 (let ((jni (string-append (assoc-ref outputs "out")
3516 (install-file "lib/jni/libIntelDeflater.so" jni)
3519 `(("java-snappy-1" ,java-snappy-1)
3520 ("java-commons-jexl-2" ,java-commons-jexl-2)
3521 ("java-cofoja" ,java-cofoja)
3522 ("ant" ,ant) ; for bzip2 support at runtime
3525 `(("ant-apache-bcel" ,ant-apache-bcel)
3526 ("ant-junit" ,ant-junit)
3527 ("java-testng" ,java-testng)
3528 ("java-commons-bcel" ,java-commons-bcel)
3529 ("java-jcommander" ,java-jcommander)
3530 ("jdk" ,icedtea-8 "jdk")
3531 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3533 (define-public fastqc
3540 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3541 "projects/fastqc/fastqc_v"
3542 version "_source.zip"))
3545 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3546 (build-system ant-build-system)
3548 `(#:tests? #f ; there are no tests
3549 #:build-target "build"
3551 (modify-phases %standard-phases
3552 (add-after 'unpack 'fix-dependencies
3553 (lambda* (#:key inputs #:allow-other-keys)
3554 (substitute* "build.xml"
3556 (string-append (assoc-ref inputs "java-jbzip2")
3557 "/share/java/jbzip2.jar"))
3559 (string-append (assoc-ref inputs "java-picard-1.113")
3560 "/share/java/sam-1.112.jar"))
3562 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3563 "/share/java/sis-jhdf5.jar")))
3565 ;; There is no installation target
3567 (lambda* (#:key inputs outputs #:allow-other-keys)
3568 (let* ((out (assoc-ref outputs "out"))
3569 (bin (string-append out "/bin"))
3570 (share (string-append out "/share/fastqc/"))
3571 (exe (string-append share "/fastqc")))
3572 (for-each mkdir-p (list bin share))
3573 (copy-recursively "bin" share)
3575 (("my \\$java_bin = 'java';")
3576 (string-append "my $java_bin = '"
3577 (assoc-ref inputs "java")
3580 (symlink exe (string-append bin "/fastqc"))
3584 ("perl" ,perl) ; needed for the wrapper script
3585 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3586 ("java-picard-1.113" ,java-picard-1.113)
3587 ("java-jbzip2" ,java-jbzip2)))
3589 `(("unzip" ,unzip)))
3590 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3591 (synopsis "Quality control tool for high throughput sequence data")
3593 "FastQC aims to provide a simple way to do some quality control
3594 checks on raw sequence data coming from high throughput sequencing
3595 pipelines. It provides a modular set of analyses which you can use to
3596 give a quick impression of whether your data has any problems of which
3597 you should be aware before doing any further analysis.
3599 The main functions of FastQC are:
3602 @item Import of data from BAM, SAM or FastQ files (any variant);
3603 @item Providing a quick overview to tell you in which areas there may
3605 @item Summary graphs and tables to quickly assess your data;
3606 @item Export of results to an HTML based permanent report;
3607 @item Offline operation to allow automated generation of reports
3608 without running the interactive application.
3610 (license license:gpl3+)))
3612 (define-public fastp
3620 (url "https://github.com/OpenGene/fastp.git")
3621 (commit (string-append "v" version))))
3622 (file-name (git-file-name name version))
3625 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3626 (build-system gnu-build-system)
3628 `(#:tests? #f ; there are none
3630 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3632 (modify-phases %standard-phases
3634 (add-before 'install 'create-target-dir
3635 (lambda* (#:key outputs #:allow-other-keys)
3636 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3640 (home-page "https://github.com/OpenGene/fastp/")
3641 (synopsis "All-in-one FastQ preprocessor")
3643 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3644 FastQ files. This tool has multi-threading support to afford high
3646 (license license:expat)))
3648 (define-public htslib
3655 "https://github.com/samtools/htslib/releases/download/"
3656 version "/htslib-" version ".tar.bz2"))
3659 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3660 (build-system gnu-build-system)
3662 `(("openssl" ,openssl)
3667 (home-page "http://www.htslib.org")
3668 (synopsis "C library for reading/writing high-throughput sequencing data")
3670 "HTSlib is a C library for reading/writing high-throughput sequencing
3671 data. It also provides the @command{bgzip}, @command{htsfile}, and
3672 @command{tabix} utilities.")
3673 ;; Files under cram/ are released under the modified BSD license;
3674 ;; the rest is released under the Expat license
3675 (license (list license:expat license:bsd-3))))
3677 ;; This package should be removed once no packages rely upon it.
3685 "https://github.com/samtools/htslib/releases/download/"
3686 version "/htslib-" version ".tar.bz2"))
3689 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3698 (url "https://github.com/nboley/idr.git")
3700 (file-name (git-file-name name version))
3703 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3704 ;; Delete generated C code.
3706 '(begin (delete-file "idr/inv_cdf.c") #t))))
3707 (build-system python-build-system)
3708 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3709 ;; are no longer part of this package. It also asserts False, which
3710 ;; causes the tests to always fail.
3711 (arguments `(#:tests? #f))
3713 `(("python-scipy" ,python-scipy)
3714 ("python-sympy" ,python-sympy)
3715 ("python-numpy" ,python-numpy)
3716 ("python-matplotlib" ,python-matplotlib)))
3718 `(("python-cython" ,python-cython)))
3719 (home-page "https://github.com/nboley/idr")
3720 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3722 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3723 to measure the reproducibility of findings identified from replicate
3724 experiments and provide highly stable thresholds based on reproducibility.")
3725 (license license:gpl2+)))
3727 (define-public jellyfish
3733 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3734 "releases/download/v" version
3735 "/jellyfish-" version ".tar.gz"))
3738 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3739 (build-system gnu-build-system)
3740 (outputs '("out" ;for library
3741 "ruby" ;for Ruby bindings
3742 "python")) ;for Python bindings
3745 (list (string-append "--enable-ruby-binding="
3746 (assoc-ref %outputs "ruby"))
3747 (string-append "--enable-python-binding="
3748 (assoc-ref %outputs "python")))
3750 (modify-phases %standard-phases
3751 (add-before 'check 'set-SHELL-variable
3753 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3755 (setenv "SHELL" (which "bash"))
3761 ("python" ,python-2)
3762 ("pkg-config" ,pkg-config)))
3764 `(("htslib" ,htslib)))
3765 (synopsis "Tool for fast counting of k-mers in DNA")
3767 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3768 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3769 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3770 is a command-line program that reads FASTA and multi-FASTA files containing
3771 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3772 translated into a human-readable text format using the @code{jellyfish dump}
3773 command, or queried for specific k-mers with @code{jellyfish query}.")
3774 (home-page "http://www.genome.umd.edu/jellyfish.html")
3775 ;; JELLYFISH seems to be 64-bit only.
3776 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3777 ;; The combined work is published under the GPLv3 or later. Individual
3778 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3779 (license (list license:gpl3+ license:expat))))
3781 (define-public khmer
3789 (url "https://github.com/dib-lab/khmer.git")
3790 (commit (string-append "v" version))))
3791 (file-name (git-file-name name version))
3794 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3795 (patches (search-patches "khmer-use-libraries.patch"))
3796 (modules '((guix build utils)))
3799 ;; Delete bundled libraries. We do not replace the bundled seqan
3800 ;; as it is a modified subset of the old version 1.4.1.
3802 ;; We do not replace the bundled MurmurHash as the canonical
3803 ;; repository for this code 'SMHasher' is unsuitable for providing
3805 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3806 (delete-file-recursively "third-party/zlib")
3807 (delete-file-recursively "third-party/bzip2")
3809 (build-system python-build-system)
3812 (modify-phases %standard-phases
3813 (add-after 'unpack 'set-cc
3814 (lambda _ (setenv "CC" "gcc") #t))
3815 ;; FIXME: This fails with "permission denied".
3816 (delete 'reset-gzip-timestamps))))
3818 `(("python-cython" ,python-cython)
3819 ("python-pytest" ,python-pytest)
3820 ("python-pytest-runner" ,python-pytest-runner)))
3824 ("python-screed" ,python-screed)
3825 ("python-bz2file" ,python-bz2file)))
3826 (home-page "https://khmer.readthedocs.org/")
3827 (synopsis "K-mer counting, filtering and graph traversal library")
3828 (description "The khmer software is a set of command-line tools for
3829 working with DNA shotgun sequencing data from genomes, transcriptomes,
3830 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3831 sometimes better. Khmer can also identify and fix problems with shotgun
3833 ;; When building on i686, armhf and mips64el, we get the following error:
3834 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3835 (supported-systems '("x86_64-linux" "aarch64-linux"))
3836 (license license:bsd-3)))
3838 (define-public kaiju
3845 (url "https://github.com/bioinformatics-centre/kaiju")
3846 (commit (string-append "v" version))))
3847 (file-name (git-file-name name version))
3850 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3851 (build-system gnu-build-system)
3853 `(#:tests? #f ; There are no tests.
3855 (modify-phases %standard-phases
3857 (add-before 'build 'move-to-src-dir
3858 (lambda _ (chdir "src") #t))
3860 (lambda* (#:key inputs outputs #:allow-other-keys)
3861 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3864 (copy-recursively "bin" bin))
3869 (home-page "http://kaiju.binf.ku.dk/")
3870 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3871 (description "Kaiju is a program for sensitive taxonomic classification
3872 of high-throughput sequencing reads from metagenomic whole genome sequencing
3874 (license license:gpl3+)))
3879 (version "2.1.1.20160309")
3882 (uri (pypi-uri "MACS2" version))
3885 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3886 (build-system python-build-system)
3888 `(#:python ,python-2 ; only compatible with Python 2.7
3889 #:tests? #f)) ; no test target
3891 `(("python-numpy" ,python2-numpy)))
3892 (home-page "https://github.com/taoliu/MACS/")
3893 (synopsis "Model based analysis for ChIP-Seq data")
3895 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3896 identifying transcript factor binding sites named Model-based Analysis of
3897 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3898 the significance of enriched ChIP regions and it improves the spatial
3899 resolution of binding sites through combining the information of both
3900 sequencing tag position and orientation.")
3901 (license license:bsd-3)))
3903 (define-public mafft
3910 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3911 "-without-extensions-src.tgz"))
3912 (file-name (string-append name "-" version ".tgz"))
3915 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3916 (build-system gnu-build-system)
3918 `(#:tests? #f ; no automated tests, though there are tests in the read me
3919 #:make-flags (let ((out (assoc-ref %outputs "out")))
3920 (list (string-append "PREFIX=" out)
3921 (string-append "BINDIR="
3922 (string-append out "/bin"))))
3924 (modify-phases %standard-phases
3925 (add-after 'unpack 'enter-dir
3926 (lambda _ (chdir "core") #t))
3927 (add-after 'enter-dir 'patch-makefile
3929 ;; on advice from the MAFFT authors, there is no need to
3930 ;; distribute mafft-profile, mafft-distance, or
3931 ;; mafft-homologs.rb as they are too "specialised".
3932 (substitute* "Makefile"
3933 ;; remove mafft-homologs.rb from SCRIPTS
3934 (("^SCRIPTS = mafft mafft-homologs.rb")
3936 ;; remove mafft-homologs from MANPAGES
3937 (("^MANPAGES = mafft.1 mafft-homologs.1")
3938 "MANPAGES = mafft.1")
3939 ;; remove mafft-distance from PROGS
3940 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3941 "PROGS = dvtditr dndfast7 dndblast sextet5")
3942 ;; remove mafft-profile from PROGS
3943 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3944 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3945 (("^rm -f mafft-profile mafft-profile.exe") "#")
3946 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3947 ;; do not install MAN pages in libexec folder
3948 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3949 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3951 (add-after 'enter-dir 'patch-paths
3952 (lambda* (#:key inputs #:allow-other-keys)
3953 (substitute* '("pairash.c"
3955 (("perl") (which "perl"))
3956 (("([\"`| ])awk" _ prefix)
3957 (string-append prefix (which "awk")))
3958 (("grep") (which "grep")))
3961 (add-after 'install 'wrap-programs
3962 (lambda* (#:key outputs #:allow-other-keys)
3963 (let* ((out (assoc-ref outputs "out"))
3964 (bin (string-append out "/bin"))
3965 (path (string-append
3966 (assoc-ref %build-inputs "coreutils") "/bin:")))
3967 (for-each (lambda (file)
3969 `("PATH" ":" prefix (,path))))
3977 ("coreutils" ,coreutils)))
3978 (home-page "http://mafft.cbrc.jp/alignment/software/")
3979 (synopsis "Multiple sequence alignment program")
3981 "MAFFT offers a range of multiple alignment methods for nucleotide and
3982 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3983 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3985 (license (license:non-copyleft
3986 "http://mafft.cbrc.jp/alignment/software/license.txt"
3987 "BSD-3 with different formatting"))))
3996 (url "https://github.com/marbl/mash.git")
3997 (commit (string-append "v" version))))
3998 (file-name (git-file-name name version))
4001 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4002 (modules '((guix build utils)))
4005 ;; Delete bundled kseq.
4006 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4007 (delete-file "src/mash/kseq.h")
4009 (build-system gnu-build-system)
4011 `(#:tests? #f ; No tests.
4014 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4015 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4016 #:make-flags (list "CC=gcc")
4018 (modify-phases %standard-phases
4019 (add-after 'unpack 'fix-includes
4021 (substitute* '("src/mash/Sketch.cpp"
4022 "src/mash/CommandFind.cpp"
4023 "src/mash/CommandScreen.cpp")
4024 (("^#include \"kseq\\.h\"")
4025 "#include \"htslib/kseq.h\""))
4028 `(("autoconf" ,autoconf)
4029 ;; Capnproto and htslib are statically embedded in the final
4030 ;; application. Therefore we also list their licenses, below.
4031 ("capnproto" ,capnproto)
4032 ("htslib" ,htslib)))
4036 (supported-systems '("x86_64-linux"))
4037 (home-page "https://mash.readthedocs.io")
4038 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4039 (description "Mash is a fast sequence distance estimator that uses the
4040 MinHash algorithm and is designed to work with genomes and metagenomes in the
4041 form of assemblies or reads.")
4042 (license (list license:bsd-3 ; Mash
4043 license:expat ; HTSlib and capnproto
4044 license:public-domain ; MurmurHash 3
4045 license:cpl1.0)))) ; Open Bloom Filter
4047 (define-public metabat
4055 (url "https://bitbucket.org/berkeleylab/metabat.git")
4056 (commit (string-append "v" version))))
4057 (file-name (git-file-name name version))
4060 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4061 (patches (search-patches "metabat-fix-compilation.patch"))))
4062 (build-system scons-build-system)
4064 `(#:scons ,scons-python2
4066 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4067 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4068 #:tests? #f ;; Tests are run during the build phase.
4070 (modify-phases %standard-phases
4071 (add-after 'unpack 'fix-includes
4073 (substitute* "src/BamUtils.h"
4074 (("^#include \"bam/bam\\.h\"")
4075 "#include \"samtools/bam.h\"")
4076 (("^#include \"bam/sam\\.h\"")
4077 "#include \"samtools/sam.h\""))
4078 (substitute* "src/KseqReader.h"
4079 (("^#include \"bam/kseq\\.h\"")
4080 "#include \"htslib/kseq.h\""))
4082 (add-after 'unpack 'fix-scons
4083 (lambda* (#:key inputs #:allow-other-keys)
4084 (substitute* "SConstruct"
4085 (("^htslib_dir += 'samtools'")
4086 (string-append "htslib_dir = '"
4087 (assoc-ref inputs "htslib")
4089 (("^samtools_dir = 'samtools'")
4090 (string-append "samtools_dir = '"
4091 (assoc-ref inputs "samtools")
4093 (("^findStaticOrShared\\('bam', hts_lib")
4094 (string-append "findStaticOrShared('bam', '"
4095 (assoc-ref inputs "samtools")
4097 ;; Do not distribute README.
4098 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4103 ("samtools" ,samtools)
4106 (home-page "https://bitbucket.org/berkeleylab/metabat")
4108 "Reconstruction of single genomes from complex microbial communities")
4110 "Grouping large genomic fragments assembled from shotgun metagenomic
4111 sequences to deconvolute complex microbial communities, or metagenome binning,
4112 enables the study of individual organisms and their interactions. MetaBAT is
4113 an automated metagenome binning software, which integrates empirical
4114 probabilistic distances of genome abundance and tetranucleotide frequency.")
4115 ;; The source code contains inline assembly.
4116 (supported-systems '("x86_64-linux" "i686-linux"))
4117 (license (license:non-copyleft "file://license.txt"
4118 "See license.txt in the distribution."))))
4120 (define-public minced
4127 (url "https://github.com/ctSkennerton/minced.git")
4129 (file-name (git-file-name name version))
4132 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4133 (build-system gnu-build-system)
4135 `(#:test-target "test"
4137 (modify-phases %standard-phases
4139 (add-before 'check 'fix-test
4141 ;; Fix test for latest version.
4142 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4143 (("minced:0.1.6") "minced:0.2.0"))
4145 (replace 'install ; No install target.
4146 (lambda* (#:key inputs outputs #:allow-other-keys)
4147 (let* ((out (assoc-ref outputs "out"))
4148 (bin (string-append out "/bin"))
4149 (wrapper (string-append bin "/minced")))
4150 ;; Minced comes with a wrapper script that tries to figure out where
4151 ;; it is located before running the JAR. Since these paths are known
4152 ;; to us, we build our own wrapper to avoid coreutils dependency.
4153 (install-file "minced.jar" bin)
4154 (with-output-to-file wrapper
4158 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4159 (assoc-ref inputs "jre") "/bin/java -jar "
4160 bin "/minced.jar \"$@\"\n"))))
4161 (chmod wrapper #o555))
4164 `(("jdk" ,icedtea "jdk")))
4167 ("jre" ,icedtea "out")))
4168 (home-page "https://github.com/ctSkennerton/minced")
4169 (synopsis "Mining CRISPRs in Environmental Datasets")
4171 "MinCED is a program to find Clustered Regularly Interspaced Short
4172 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4173 unassembled metagenomic reads, but is mainly designed for full genomes and
4174 assembled metagenomic sequence.")
4175 (license license:gpl3+)))
4183 (uri (pypi-uri "misopy" version))
4186 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4187 (modules '((guix build utils)))
4189 (substitute* "setup.py"
4190 ;; Use setuptools, or else the executables are not
4192 (("distutils.core") "setuptools")
4193 ;; use "gcc" instead of "cc" for compilation
4195 "cc.set_executables(
4199 linker_so='gcc -shared'); defines"))
4201 (build-system python-build-system)
4203 `(#:python ,python-2 ; only Python 2 is supported
4204 #:tests? #f)) ; no "test" target
4206 `(("samtools" ,samtools)
4207 ("python-numpy" ,python2-numpy)
4208 ("python-pysam" ,python2-pysam)
4209 ("python-scipy" ,python2-scipy)
4210 ("python-matplotlib" ,python2-matplotlib)))
4212 `(("python-mock" ,python2-mock) ;for tests
4213 ("python-pytz" ,python2-pytz))) ;for tests
4214 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4215 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4217 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4218 the expression level of alternatively spliced genes from RNA-Seq data, and
4219 identifies differentially regulated isoforms or exons across samples. By
4220 modeling the generative process by which reads are produced from isoforms in
4221 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4222 that a read originated from a particular isoform.")
4223 (license license:gpl2)))
4225 (define-public muscle
4228 (version "3.8.1551")
4230 (method url-fetch/tarbomb)
4232 "http://www.drive5.com/muscle/muscle_src_"
4236 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4237 (build-system gnu-build-system)
4239 `(#:make-flags (list "LDLIBS = -lm")
4241 (modify-phases %standard-phases
4244 ;; There are no tests, so just test if it runs.
4245 (lambda _ (invoke "./muscle" "-version") #t))
4247 (lambda* (#:key outputs #:allow-other-keys)
4248 (let* ((out (assoc-ref outputs "out"))
4249 (bin (string-append out "/bin")))
4250 (install-file "muscle" bin)
4252 (home-page "http://www.drive5.com/muscle")
4253 (synopsis "Multiple sequence alignment program")
4255 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4256 program for nucleotide and protein sequences.")
4257 ;; License information found in 'muscle -h' and usage.cpp.
4258 (license license:public-domain)))
4260 (define-public newick-utils
4261 ;; There are no recent releases so we package from git.
4262 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4264 (name "newick-utils")
4265 (version (string-append "1.6-1." (string-take commit 8)))
4269 (url "https://github.com/tjunier/newick_utils.git")
4271 (file-name (string-append name "-" version "-checkout"))
4274 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4275 (build-system gnu-build-system)
4277 ;; XXX: TODO: Enable Lua and Guile bindings.
4278 ;; https://github.com/tjunier/newick_utils/issues/13
4279 `(("libxml2" ,libxml2)
4283 `(("autoconf" ,autoconf)
4284 ("automake" ,automake)
4285 ("libtool" ,libtool)))
4286 (synopsis "Programs for working with newick format phylogenetic trees")
4288 "Newick-utils is a suite of utilities for processing phylogenetic trees
4289 in Newick format. Functions include re-rooting, extracting subtrees,
4290 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4291 (home-page "https://github.com/tjunier/newick_utils")
4292 (license license:bsd-3))))
4301 "https://github.com/wwood/OrfM/releases/download/v"
4302 version "/orfm-" version ".tar.gz"))
4305 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4306 (build-system gnu-build-system)
4307 (inputs `(("zlib" ,zlib)))
4309 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4310 ("ruby-rspec" ,ruby-rspec)
4312 (synopsis "Simple and not slow open reading frame (ORF) caller")
4314 "An ORF caller finds stretches of DNA that, when translated, are not
4315 interrupted by stop codons. OrfM finds and prints these ORFs.")
4316 (home-page "https://github.com/wwood/OrfM")
4317 (license license:lgpl3+)))
4319 (define-public pplacer
4320 (let ((commit "807f6f3"))
4323 ;; The commit should be updated with each version change.
4324 (version "1.1.alpha19")
4329 (url "https://github.com/matsen/pplacer.git")
4330 (commit (string-append "v" version))))
4331 (file-name (git-file-name name version))
4333 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
4334 (build-system ocaml-build-system)
4336 `(#:ocaml ,ocaml-4.01
4337 #:findlib ,ocaml4.01-findlib
4338 #:modules ((guix build ocaml-build-system)
4342 (modify-phases %standard-phases
4344 (add-after 'unpack 'replace-bundled-cddlib
4345 (lambda* (#:key inputs #:allow-other-keys)
4346 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4347 (local-dir "cddlib_guix"))
4349 (with-directory-excursion local-dir
4350 (invoke "tar" "xvf" cddlib-src))
4351 (let ((cddlib-src-folder
4352 (string-append local-dir "/"
4353 (list-ref (scandir local-dir) 2)
4355 (for-each make-file-writable (find-files "cdd_src" ".*"))
4359 (string-append "cdd_src/" (basename file))))
4360 (find-files cddlib-src-folder ".*[ch]$")))
4362 (add-after 'unpack 'fix-makefile
4364 ;; Remove system calls to 'git'.
4365 (substitute* "Makefile"
4366 (("^DESCRIPT:=pplacer-.*")
4368 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4369 (substitute* "myocamlbuild.ml"
4370 (("git describe --tags --long .*\\\" with")
4372 "echo -n v" ,version "-" ,commit "\" with")))
4375 (lambda* (#:key outputs #:allow-other-keys)
4376 (let* ((out (assoc-ref outputs "out"))
4377 (bin (string-append out "/bin")))
4378 (copy-recursively "bin" bin))
4383 ("ocaml-ounit" ,ocaml4.01-ounit)
4384 ("ocaml-batteries" ,ocaml4.01-batteries)
4385 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4386 ("ocaml-csv" ,ocaml4.01-csv)
4387 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4388 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4389 ("ocaml-mcl" ,ocaml4.01-mcl)
4390 ("ocaml-gsl" ,ocaml4.01-gsl)
4391 ("cddlib-src" ,(package-source cddlib))))
4393 `(("pplacer-scripts" ,pplacer-scripts)))
4394 (synopsis "Phylogenetic placement of biological sequences")
4396 "Pplacer places query sequences on a fixed reference phylogenetic tree
4397 to maximize phylogenetic likelihood or posterior probability according to a
4398 reference alignment. Pplacer is designed to be fast, to give useful
4399 information about uncertainty, and to offer advanced visualization and
4400 downstream analysis.")
4401 (home-page "http://matsen.fhcrc.org/pplacer")
4402 (license license:gpl3))))
4404 ;; This package is installed alongside 'pplacer'. It is a separate package so
4405 ;; that it can use the python-build-system for the scripts that are
4406 ;; distributed alongside the main OCaml binaries.
4407 (define pplacer-scripts
4410 (name "pplacer-scripts")
4411 (build-system python-build-system)
4413 `(#:python ,python-2
4415 (modify-phases %standard-phases
4416 (add-after 'unpack 'enter-scripts-dir
4417 (lambda _ (chdir "scripts") #t))
4419 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
4420 (add-after 'install 'wrap-executables
4421 (lambda* (#:key inputs outputs #:allow-other-keys)
4422 (let* ((out (assoc-ref outputs "out"))
4423 (bin (string-append out "/bin")))
4424 (let ((path (string-append
4425 (assoc-ref inputs "hmmer") "/bin:"
4426 (assoc-ref inputs "infernal") "/bin")))
4428 (wrap-program (string-append bin "/refpkg_align.py")
4429 `("PATH" ":" prefix (,path))))
4430 (let ((path (string-append
4431 (assoc-ref inputs "hmmer") "/bin")))
4432 (wrap-program (string-append bin "/hrefpkg_query.py")
4433 `("PATH" ":" prefix (,path)))))
4436 `(("infernal" ,infernal)
4439 `(("python-biopython" ,python2-biopython)
4440 ("taxtastic" ,taxtastic)))
4441 (synopsis "Pplacer Python scripts")))
4443 (define-public python2-pbcore
4445 (name "python2-pbcore")
4449 (uri (pypi-uri "pbcore" version))
4452 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4453 (build-system python-build-system)
4454 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4456 `(("python-cython" ,python2-cython)
4457 ("python-numpy" ,python2-numpy)
4458 ("python-pysam" ,python2-pysam)
4459 ("python-h5py" ,python2-h5py)))
4461 `(("python-nose" ,python2-nose)
4462 ("python-sphinx" ,python2-sphinx)
4463 ("python-pyxb" ,python2-pyxb)))
4464 (home-page "http://pacificbiosciences.github.io/pbcore/")
4465 (synopsis "Library for reading and writing PacBio data files")
4467 "The pbcore package provides Python APIs for interacting with PacBio data
4468 files and writing bioinformatics applications.")
4469 (license license:bsd-3)))
4471 (define-public python2-warpedlmm
4473 (name "python2-warpedlmm")
4479 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4483 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4484 (build-system python-build-system)
4486 `(#:python ,python-2)) ; requires Python 2.7
4488 `(("python-scipy" ,python2-scipy)
4489 ("python-numpy" ,python2-numpy)
4490 ("python-matplotlib" ,python2-matplotlib)
4491 ("python-fastlmm" ,python2-fastlmm)
4492 ("python-pandas" ,python2-pandas)
4493 ("python-pysnptools" ,python2-pysnptools)))
4495 `(("python-mock" ,python2-mock)
4496 ("python-nose" ,python2-nose)
4498 (home-page "https://github.com/PMBio/warpedLMM")
4499 (synopsis "Implementation of warped linear mixed models")
4501 "WarpedLMM is a Python implementation of the warped linear mixed model,
4502 which automatically learns an optimal warping function (or transformation) for
4503 the phenotype as it models the data.")
4504 (license license:asl2.0)))
4506 (define-public pbtranscript-tofu
4507 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4509 (name "pbtranscript-tofu")
4510 (version (string-append "2.2.3." (string-take commit 7)))
4514 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4516 (file-name (string-append name "-" version "-checkout"))
4519 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4520 (modules '((guix build utils)))
4523 ;; remove bundled Cython sources
4524 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4526 (build-system python-build-system)
4528 `(#:python ,python-2
4529 ;; FIXME: Tests fail with "No such file or directory:
4530 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4533 (modify-phases %standard-phases
4534 (add-after 'unpack 'enter-directory
4536 (chdir "pbtranscript-tofu/pbtranscript/")
4538 ;; With setuptools version 18.0 and later this setup.py hack causes
4539 ;; a build error, so we disable it.
4540 (add-after 'enter-directory 'patch-setuppy
4542 (substitute* "setup.py"
4543 (("if 'setuptools.extension' in sys.modules:")
4547 `(("python-numpy" ,python2-numpy)
4548 ("python-bx-python" ,python2-bx-python)
4549 ("python-networkx" ,python2-networkx)
4550 ("python-scipy" ,python2-scipy)
4551 ("python-pbcore" ,python2-pbcore)
4552 ("python-h5py" ,python2-h5py)))
4554 `(("python-cython" ,python2-cython)
4555 ("python-nose" ,python2-nose)))
4556 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4557 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4559 "pbtranscript-tofu contains scripts to analyze transcriptome data
4560 generated using the PacBio Iso-Seq protocol.")
4561 (license license:bsd-3))))
4563 (define-public prank
4570 "http://wasabiapp.org/download/prank/prank.source."
4574 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4575 (build-system gnu-build-system)
4578 (modify-phases %standard-phases
4579 (add-after 'unpack 'enter-src-dir
4583 (add-after 'unpack 'remove-m64-flag
4584 ;; Prank will build with the correct 'bit-ness' without this flag
4585 ;; and this allows building on 32-bit machines.
4586 (lambda _ (substitute* "src/Makefile"
4591 (lambda* (#:key outputs #:allow-other-keys)
4592 (let* ((out (assoc-ref outputs "out"))
4593 (bin (string-append out "/bin"))
4594 (man (string-append out "/share/man/man1"))
4595 (path (string-append
4596 (assoc-ref %build-inputs "mafft") "/bin:"
4597 (assoc-ref %build-inputs "exonerate") "/bin:"
4598 (assoc-ref %build-inputs "bppsuite") "/bin")))
4599 (install-file "prank" bin)
4600 (wrap-program (string-append bin "/prank")
4601 `("PATH" ":" prefix (,path)))
4602 (install-file "prank.1" man))
4606 ("exonerate" ,exonerate)
4607 ("bppsuite" ,bppsuite)))
4608 (home-page "http://wasabiapp.org/software/prank/")
4609 (synopsis "Probabilistic multiple sequence alignment program")
4611 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4612 codon and amino-acid sequences. It is based on a novel algorithm that treats
4613 insertions correctly and avoids over-estimation of the number of deletion
4614 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4615 in phylogenetics and correctly takes into account the evolutionary distances
4616 between sequences. Lastly, PRANK allows for defining a potential structure
4617 for sequences to be aligned and then, simultaneously with the alignment,
4618 predicts the locations of structural units in the sequences.")
4619 (license license:gpl2+)))
4621 (define-public proteinortho
4623 (name "proteinortho")
4630 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4631 version "_src.tar.gz"))
4634 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4635 (build-system gnu-build-system)
4637 `(#:test-target "test"
4639 (modify-phases %standard-phases
4641 ;; There is no configure script, so we modify the Makefile directly.
4642 (lambda* (#:key outputs #:allow-other-keys)
4643 (substitute* "Makefile"
4646 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4648 (add-before 'install 'make-install-directory
4649 ;; The install directory is not created during 'make install'.
4650 (lambda* (#:key outputs #:allow-other-keys)
4651 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4653 (add-after 'install 'wrap-programs
4654 (lambda* (#:key inputs outputs #:allow-other-keys)
4655 (let* ((path (getenv "PATH"))
4656 (out (assoc-ref outputs "out"))
4657 (binary (string-append out "/bin/proteinortho5.pl")))
4658 (wrap-program binary `("PATH" ":" prefix (,path))))
4662 ("python" ,python-2)
4663 ("blast+" ,blast+)))
4664 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4665 (synopsis "Detect orthologous genes across species")
4667 "Proteinortho is a tool to detect orthologous genes across different
4668 species. For doing so, it compares similarities of given gene sequences and
4669 clusters them to find significant groups. The algorithm was designed to handle
4670 large-scale data and can be applied to hundreds of species at once.")
4671 (license license:gpl2+)))
4673 (define-public pyicoteo
4681 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4682 (commit (string-append "v" version))))
4683 (file-name (git-file-name name version))
4686 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4687 (build-system python-build-system)
4689 `(#:python ,python-2 ; does not work with Python 3
4690 #:tests? #f)) ; there are no tests
4692 `(("python2-matplotlib" ,python2-matplotlib)))
4693 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4694 (synopsis "Analyze high-throughput genetic sequencing data")
4696 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4697 sequencing data. It works with genomic coordinates. There are currently six
4698 different command-line tools:
4701 @item pyicoregion: for generating exploratory regions automatically;
4702 @item pyicoenrich: for differential enrichment between two conditions;
4703 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4704 @item pyicos: for genomic coordinates manipulation;
4705 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4706 @item pyicount: to count how many reads from N experiment files overlap in a
4708 @item pyicotrocol: to combine operations from pyicoteo.
4710 (license license:gpl3+)))
4712 (define-public prodigal
4719 (url "https://github.com/hyattpd/Prodigal.git")
4720 (commit (string-append "v" version))))
4721 (file-name (git-file-name name version))
4724 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4725 (build-system gnu-build-system)
4727 `(#:tests? #f ;no check target
4728 #:make-flags (list (string-append "INSTALLDIR="
4729 (assoc-ref %outputs "out")
4732 (modify-phases %standard-phases
4733 (delete 'configure))))
4734 (home-page "http://prodigal.ornl.gov")
4735 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4737 "Prodigal runs smoothly on finished genomes, draft genomes, and
4738 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4739 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4740 partial genes, and identifies translation initiation sites.")
4741 (license license:gpl3+)))
4743 (define-public roary
4751 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4755 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4756 (build-system perl-build-system)
4759 (modify-phases %standard-phases
4764 ;; The tests are not run by default, so we run each test file
4766 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4768 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4769 (getenv "PERL5LIB")))
4770 (for-each (lambda (file)
4771 (display file)(display "\n")
4772 (invoke "perl" file))
4773 (find-files "t" ".*\\.t$"))
4776 ;; There is no 'install' target in the Makefile.
4777 (lambda* (#:key outputs #:allow-other-keys)
4778 (let* ((out (assoc-ref outputs "out"))
4779 (bin (string-append out "/bin"))
4780 (perl (string-append out "/lib/perl5/site_perl"))
4781 (roary-plots "contrib/roary_plots"))
4784 (copy-recursively "bin" bin)
4785 (copy-recursively "lib" perl)
4787 (add-after 'install 'wrap-programs
4788 (lambda* (#:key inputs outputs #:allow-other-keys)
4789 (let* ((out (assoc-ref outputs "out"))
4790 (perl5lib (getenv "PERL5LIB"))
4791 (path (getenv "PATH")))
4792 (for-each (lambda (prog)
4793 (let ((binary (string-append out "/" prog)))
4794 (wrap-program binary
4795 `("PERL5LIB" ":" prefix
4796 (,(string-append perl5lib ":" out
4797 "/lib/perl5/site_perl"))))
4798 (wrap-program binary
4800 (,(string-append path ":" out "/bin"))))))
4801 (find-files "bin" ".*[^R]$"))
4803 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4804 (r-site-lib (getenv "R_LIBS_SITE"))
4806 (string-append (assoc-ref inputs "coreutils") "/bin")))
4808 `("R_LIBS_SITE" ":" prefix
4809 (,(string-append r-site-lib ":" out "/site-library/"))))
4812 (,(string-append coreutils-path ":" out "/bin"))))))
4815 `(("perl-env-path" ,perl-env-path)
4816 ("perl-test-files" ,perl-test-files)
4817 ("perl-test-most" ,perl-test-most)
4818 ("perl-test-output" ,perl-test-output)))
4820 `(("perl-array-utils" ,perl-array-utils)
4821 ("bioperl" ,bioperl-minimal)
4822 ("perl-digest-md5-file" ,perl-digest-md5-file)
4823 ("perl-exception-class" ,perl-exception-class)
4824 ("perl-file-find-rule" ,perl-file-find-rule)
4825 ("perl-file-grep" ,perl-file-grep)
4826 ("perl-file-slurper" ,perl-file-slurper)
4827 ("perl-file-which" ,perl-file-which)
4828 ("perl-graph" ,perl-graph)
4829 ("perl-graph-readwrite" ,perl-graph-readwrite)
4830 ("perl-log-log4perl" ,perl-log-log4perl)
4831 ("perl-moose" ,perl-moose)
4832 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4833 ("perl-text-csv" ,perl-text-csv)
4834 ("bedtools" ,bedtools)
4838 ("parallel" ,parallel)
4841 ("fasttree" ,fasttree)
4845 ("r-minimal" ,r-minimal)
4846 ("r-ggplot2" ,r-ggplot2)
4847 ("coreutils" ,coreutils)))
4848 (home-page "http://sanger-pathogens.github.io/Roary")
4849 (synopsis "High speed stand-alone pan genome pipeline")
4851 "Roary is a high speed stand alone pan genome pipeline, which takes
4852 annotated assemblies in GFF3 format (produced by the Prokka program) and
4853 calculates the pan genome. Using a standard desktop PC, it can analyse
4854 datasets with thousands of samples, without compromising the quality of the
4855 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4856 single processor. Roary is not intended for metagenomics or for comparing
4857 extremely diverse sets of genomes.")
4858 (license license:gpl3)))
4860 (define-public raxml
4868 (url "https://github.com/stamatak/standard-RAxML.git")
4869 (commit (string-append "v" version))))
4870 (file-name (git-file-name name version))
4873 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4874 (build-system gnu-build-system)
4876 `(#:tests? #f ; There are no tests.
4877 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4878 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4880 (modify-phases %standard-phases
4883 (lambda* (#:key outputs #:allow-other-keys)
4884 (let* ((out (assoc-ref outputs "out"))
4885 (bin (string-append out "/bin"))
4886 (executable "raxmlHPC-HYBRID"))
4887 (install-file executable bin)
4888 (symlink (string-append bin "/" executable) "raxml"))
4891 `(("openmpi" ,openmpi)))
4892 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4893 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4895 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4897 ;; The source includes x86 specific code
4898 (supported-systems '("x86_64-linux" "i686-linux"))
4899 (license license:gpl2+)))
4909 (url "https://github.com/deweylab/RSEM.git")
4910 (commit (string-append "v" version))))
4912 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4913 (file-name (git-file-name name version))
4914 (modules '((guix build utils)))
4917 ;; remove bundled copy of boost and samtools
4918 (delete-file-recursively "boost")
4919 (delete-file-recursively "samtools-1.3")
4921 (build-system gnu-build-system)
4923 `(#:tests? #f ;no "check" target
4925 (list (string-append "BOOST="
4926 (assoc-ref %build-inputs "boost")
4928 (string-append "SAMHEADERS="
4929 (assoc-ref %build-inputs "htslib")
4930 "/include/htslib/sam.h")
4931 (string-append "SAMLIBS="
4932 (assoc-ref %build-inputs "htslib")
4935 (modify-phases %standard-phases
4936 ;; No "configure" script.
4937 ;; Do not build bundled samtools library.
4940 (substitute* "Makefile"
4941 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4942 (("^\\$\\(SAMLIBS\\).*") ""))
4945 (lambda* (#:key outputs #:allow-other-keys)
4946 (let* ((out (string-append (assoc-ref outputs "out")))
4947 (bin (string-append out "/bin/"))
4948 (perl (string-append out "/lib/perl5/site_perl")))
4951 (for-each (lambda (file)
4952 (install-file file bin))
4953 (find-files "." "rsem-.*"))
4954 (install-file "rsem_perl_utils.pm" perl))
4956 (add-after 'install 'wrap-program
4957 (lambda* (#:key outputs #:allow-other-keys)
4958 (let ((out (assoc-ref outputs "out")))
4959 (for-each (lambda (prog)
4960 (wrap-program (string-append out "/bin/" prog)
4961 `("PERL5LIB" ":" prefix
4962 (,(string-append out "/lib/perl5/site_perl")))))
4963 '("rsem-calculate-expression"
4965 "rsem-generate-data-matrix"
4966 "rsem-generate-ngvector"
4967 "rsem-plot-transcript-wiggles"
4968 "rsem-prepare-reference"
4970 "rsem-run-prsem-testing-procedure")))
4974 ("r-minimal" ,r-minimal)
4976 ("htslib" ,htslib-1.3)
4978 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4979 (synopsis "Estimate gene expression levels from RNA-Seq data")
4981 "RSEM is a software package for estimating gene and isoform expression
4982 levels from RNA-Seq data. The RSEM package provides a user-friendly
4983 interface, supports threads for parallel computation of the EM algorithm,
4984 single-end and paired-end read data, quality scores, variable-length reads and
4985 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4986 interval estimates for expression levels. For visualization, it can generate
4987 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4988 (license license:gpl3+)))
4990 (define-public rseqc
4998 (string-append "mirror://sourceforge/rseqc/"
4999 "RSeQC-" version ".tar.gz"))
5001 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5002 (modules '((guix build utils)))
5005 ;; remove bundled copy of pysam
5006 (delete-file-recursively "lib/pysam")
5007 (substitute* "setup.py"
5008 ;; remove dependency on outdated "distribute" module
5009 (("^from distribute_setup import use_setuptools") "")
5010 (("^use_setuptools\\(\\)") "")
5011 ;; do not use bundled copy of pysam
5012 (("^have_pysam = False") "have_pysam = True"))
5014 (build-system python-build-system)
5015 (arguments `(#:python ,python-2))
5017 `(("python-cython" ,python2-cython)
5018 ("python-pysam" ,python2-pysam)
5019 ("python-numpy" ,python2-numpy)
5022 `(("python-nose" ,python2-nose)))
5023 (home-page "http://rseqc.sourceforge.net/")
5024 (synopsis "RNA-seq quality control package")
5026 "RSeQC provides a number of modules that can comprehensively evaluate
5027 high throughput sequence data, especially RNA-seq data. Some basic modules
5028 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5029 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5030 distribution, coverage uniformity, strand specificity, etc.")
5031 (license license:gpl3+)))
5034 ;; There are no release tarballs. According to the installation
5035 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5036 ;; stable release is identified by this changeset ID.
5037 (let ((changeset "2329130")
5041 (version (string-append "0-" revision "." changeset))
5045 (url "https://bitbucket.org/libsleipnir/sleipnir")
5046 (changeset changeset)))
5047 (file-name (string-append name "-" version "-checkout"))
5050 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5051 (build-system gnu-build-system)
5053 `(#:modules ((srfi srfi-1)
5054 (guix build gnu-build-system)
5057 (let ((dirs '("SeekMiner"
5063 (modify-phases %standard-phases
5066 (substitute* "gen_tools_am"
5067 (("/usr/bin/env.*") (which "perl")))
5068 (invoke "bash" "gen_auto")
5070 (add-after 'build 'build-additional-tools
5071 (lambda* (#:key make-flags #:allow-other-keys)
5072 (for-each (lambda (dir)
5073 (with-directory-excursion (string-append "tools/" dir)
5074 (apply invoke "make" make-flags)))
5077 (add-after 'install 'install-additional-tools
5078 (lambda* (#:key make-flags #:allow-other-keys)
5079 (for-each (lambda (dir)
5080 (with-directory-excursion (string-append "tools/" dir)
5081 (apply invoke `("make" ,@make-flags "install"))))
5088 ("readline" ,readline)
5089 ("gengetopt" ,gengetopt)
5090 ("log4cpp" ,log4cpp)))
5092 `(("autoconf" ,autoconf)
5093 ("automake" ,automake)
5095 (home-page "http://seek.princeton.edu")
5096 (synopsis "Gene co-expression search engine")
5098 "SEEK is a computational gene co-expression search engine. SEEK provides
5099 biologists with a way to navigate the massive human expression compendium that
5100 now contains thousands of expression datasets. SEEK returns a robust ranking
5101 of co-expressed genes in the biological area of interest defined by the user's
5102 query genes. It also prioritizes thousands of expression datasets according
5103 to the user's query of interest.")
5104 (license license:cc-by3.0))))
5106 (define-public samtools
5114 (string-append "mirror://sourceforge/samtools/samtools/"
5115 version "/samtools-" version ".tar.bz2"))
5118 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5119 (modules '((guix build utils)))
5121 ;; Delete bundled htslib.
5122 (delete-file-recursively "htslib-1.9")
5124 (build-system gnu-build-system)
5126 `(#:modules ((ice-9 ftw)
5128 (guix build gnu-build-system)
5130 #:configure-flags (list "--with-ncurses")
5132 (modify-phases %standard-phases
5133 (add-after 'unpack 'patch-tests
5135 (substitute* "test/test.pl"
5136 ;; The test script calls out to /bin/bash
5137 (("/bin/bash") (which "bash")))
5139 (add-after 'install 'install-library
5140 (lambda* (#:key outputs #:allow-other-keys)
5141 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5142 (install-file "libbam.a" lib)
5144 (add-after 'install 'install-headers
5145 (lambda* (#:key outputs #:allow-other-keys)
5146 (let ((include (string-append (assoc-ref outputs "out")
5147 "/include/samtools/")))
5148 (for-each (lambda (file)
5149 (install-file file include))
5150 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5152 (native-inputs `(("pkg-config" ,pkg-config)))
5154 `(("htslib" ,htslib)
5155 ("ncurses" ,ncurses)
5159 (home-page "http://samtools.sourceforge.net")
5160 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5162 "Samtools implements various utilities for post-processing nucleotide
5163 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5164 variant calling (in conjunction with bcftools), and a simple alignment
5166 (license license:expat)))
5168 (define-public samtools-0.1
5169 ;; This is the most recent version of the 0.1 line of samtools. The input
5170 ;; and output formats differ greatly from that used and produced by samtools
5171 ;; 1.x and is still used in many bioinformatics pipelines.
5172 (package (inherit samtools)
5178 (string-append "mirror://sourceforge/samtools/samtools/"
5179 version "/samtools-" version ".tar.bz2"))
5181 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5183 `(#:tests? #f ;no "check" target
5185 (list "LIBCURSES=-lncurses")
5186 ,@(substitute-keyword-arguments (package-arguments samtools)
5188 `(modify-phases ,phases
5190 (lambda* (#:key outputs #:allow-other-keys)
5191 (let ((bin (string-append
5192 (assoc-ref outputs "out") "/bin")))
5194 (install-file "samtools" bin)
5196 (delete 'patch-tests)
5197 (delete 'configure))))))))
5199 (define-public mosaik
5200 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5205 ;; There are no release tarballs nor tags.
5208 (url "https://github.com/wanpinglee/MOSAIK.git")
5210 (file-name (string-append name "-" version))
5213 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5214 (build-system gnu-build-system)
5216 `(#:tests? #f ; no tests
5217 #:make-flags (list "CC=gcc")
5219 (modify-phases %standard-phases
5221 (lambda _ (chdir "src") #t))
5223 (lambda* (#:key outputs #:allow-other-keys)
5224 (let ((bin (string-append (assoc-ref outputs "out")
5227 (copy-recursively "../bin" bin)
5232 (supported-systems '("x86_64-linux"))
5233 (home-page "https://github.com/wanpinglee/MOSAIK")
5234 (synopsis "Map nucleotide sequence reads to reference genomes")
5236 "MOSAIK is a program for mapping second and third-generation sequencing
5237 reads to a reference genome. MOSAIK can align reads generated by all the
5238 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5239 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5240 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5241 ;; code released into the public domain:
5242 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5243 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5244 (license (list license:gpl2+ license:public-domain)))))
5246 (define-public ngs-sdk
5253 (url "https://github.com/ncbi/ngs.git")
5255 (file-name (git-file-name name version))
5258 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5259 (build-system gnu-build-system)
5261 `(#:parallel-build? #f ; not supported
5262 #:tests? #f ; no "check" target
5264 (modify-phases %standard-phases
5266 (lambda* (#:key outputs #:allow-other-keys)
5267 (let ((out (assoc-ref outputs "out")))
5268 ;; Allow 'konfigure.perl' to find 'package.prl'.
5270 (string-append ".:" (getenv "PERL5LIB")))
5272 ;; The 'configure' script doesn't recognize things like
5273 ;; '--enable-fast-install'.
5274 (invoke "./configure"
5275 (string-append "--build-prefix=" (getcwd) "/build")
5276 (string-append "--prefix=" out))
5278 (add-after 'unpack 'enter-dir
5279 (lambda _ (chdir "ngs-sdk") #t)))))
5280 (native-inputs `(("perl" ,perl)))
5281 ;; According to the test
5282 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5283 ;; in ngs-sdk/setup/konfigure.perl
5284 (supported-systems '("i686-linux" "x86_64-linux"))
5285 (home-page "https://github.com/ncbi/ngs")
5286 (synopsis "API for accessing Next Generation Sequencing data")
5288 "NGS is a domain-specific API for accessing reads, alignments and pileups
5289 produced from Next Generation Sequencing. The API itself is independent from
5290 any particular back-end implementation, and supports use of multiple back-ends
5292 (license license:public-domain)))
5294 (define-public java-ngs
5295 (package (inherit ngs-sdk)
5298 `(,@(substitute-keyword-arguments
5299 `(#:modules ((guix build gnu-build-system)
5303 ,@(package-arguments ngs-sdk))
5305 `(modify-phases ,phases
5306 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5308 `(("jdk" ,icedtea "jdk")
5309 ("ngs-sdk" ,ngs-sdk)))
5310 (synopsis "Java bindings for NGS SDK")))
5312 (define-public ncbi-vdb
5319 (url "https://github.com/ncbi/ncbi-vdb.git")
5321 (file-name (git-file-name name version))
5324 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5325 (build-system gnu-build-system)
5327 `(#:parallel-build? #f ; not supported
5328 #:tests? #f ; no "check" target
5330 (modify-phases %standard-phases
5331 (add-after 'unpack 'make-files-writable
5332 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5333 (add-before 'configure 'set-perl-search-path
5335 ;; Work around "dotless @INC" build failure.
5337 (string-append (getcwd) "/setup:"
5338 (getenv "PERL5LIB")))
5341 (lambda* (#:key inputs outputs #:allow-other-keys)
5342 (let ((out (assoc-ref outputs "out")))
5343 ;; Override include path for libmagic
5344 (substitute* "setup/package.prl"
5345 (("name => 'magic', Include => '/usr/include'")
5346 (string-append "name=> 'magic', Include => '"
5347 (assoc-ref inputs "libmagic")
5350 ;; Install kdf5 library (needed by sra-tools)
5351 (substitute* "build/Makefile.install"
5352 (("LIBRARIES_TO_INSTALL =")
5353 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5355 (substitute* "build/Makefile.env"
5356 (("CFLAGS =" prefix)
5357 (string-append prefix "-msse2 ")))
5359 ;; Override search path for ngs-java
5360 (substitute* "setup/package.prl"
5361 (("/usr/local/ngs/ngs-java")
5362 (assoc-ref inputs "java-ngs")))
5364 ;; The 'configure' script doesn't recognize things like
5365 ;; '--enable-fast-install'.
5366 (invoke "./configure"
5367 (string-append "--build-prefix=" (getcwd) "/build")
5368 (string-append "--prefix=" (assoc-ref outputs "out"))
5369 (string-append "--debug")
5370 (string-append "--with-xml2-prefix="
5371 (assoc-ref inputs "libxml2"))
5372 (string-append "--with-ngs-sdk-prefix="
5373 (assoc-ref inputs "ngs-sdk"))
5374 (string-append "--with-hdf5-prefix="
5375 (assoc-ref inputs "hdf5")))
5377 (add-after 'install 'install-interfaces
5378 (lambda* (#:key outputs #:allow-other-keys)
5379 ;; Install interface libraries. On i686 the interface libraries
5380 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5381 ;; architecture name ("i386") instead of the target system prefix
5383 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5384 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5385 ,(system->linux-architecture
5386 (or (%current-target-system)
5389 (string-append (assoc-ref outputs "out")
5391 ;; Install interface headers
5392 (copy-recursively "interfaces"
5393 (string-append (assoc-ref outputs "out")
5396 ;; These files are needed by sra-tools.
5397 (add-after 'install 'install-configuration-files
5398 (lambda* (#:key outputs #:allow-other-keys)
5399 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5401 (install-file "libs/kfg/default.kfg" target)
5402 (install-file "libs/kfg/certs.kfg" target))
5405 `(("libxml2" ,libxml2)
5406 ("ngs-sdk" ,ngs-sdk)
5407 ("java-ngs" ,java-ngs)
5410 (native-inputs `(("perl" ,perl)))
5411 ;; NCBI-VDB requires SSE capability.
5412 (supported-systems '("i686-linux" "x86_64-linux"))
5413 (home-page "https://github.com/ncbi/ncbi-vdb")
5414 (synopsis "Database engine for genetic information")
5416 "The NCBI-VDB library implements a highly compressed columnar data
5417 warehousing engine that is most often used to store genetic information.
5418 Databases are stored in a portable image within the file system, and can be
5419 accessed/downloaded on demand across HTTP.")
5420 (license license:public-domain)))
5422 (define-public plink
5430 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5431 version "-src.zip"))
5433 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5434 (patches (search-patches "plink-1.07-unclobber-i.patch"
5435 "plink-endian-detection.patch"))))
5436 (build-system gnu-build-system)
5438 '(#:tests? #f ;no "check" target
5439 #:make-flags (list (string-append "LIB_LAPACK="
5440 (assoc-ref %build-inputs "lapack")
5441 "/lib/liblapack.so")
5444 ;; disable phoning home
5447 (modify-phases %standard-phases
5448 ;; no "configure" script
5451 (lambda* (#:key outputs #:allow-other-keys)
5452 (let ((bin (string-append (assoc-ref outputs "out")
5454 (install-file "plink" bin)
5458 ("lapack" ,lapack)))
5460 `(("unzip" ,unzip)))
5461 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5462 (synopsis "Whole genome association analysis toolset")
5464 "PLINK is a whole genome association analysis toolset, designed to
5465 perform a range of basic, large-scale analyses in a computationally efficient
5466 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5467 so there is no support for steps prior to this (e.g. study design and
5468 planning, generating genotype or CNV calls from raw data). Through
5469 integration with gPLINK and Haploview, there is some support for the
5470 subsequent visualization, annotation and storage of results.")
5471 ;; Code is released under GPLv2, except for fisher.h, which is under
5473 (license (list license:gpl2 license:lgpl2.1+))))
5475 (define-public plink-ng
5476 (package (inherit plink)
5483 (url "https://github.com/chrchang/plink-ng.git")
5484 (commit (string-append "v" version))))
5485 (file-name (git-file-name name version))
5487 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5488 (build-system gnu-build-system)
5490 '(#:tests? #f ;no "check" target
5491 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5492 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5494 "-f" "Makefile.std")
5496 (modify-phases %standard-phases
5497 (add-after 'unpack 'chdir
5498 (lambda _ (chdir "1.9") #t))
5499 (delete 'configure) ; no "configure" script
5501 (lambda* (#:key outputs #:allow-other-keys)
5502 (let ((bin (string-append (assoc-ref outputs "out")
5504 (install-file "plink" bin)
5509 ("openblas" ,openblas)))
5510 (home-page "https://www.cog-genomics.org/plink/")
5511 (license license:gpl3+)))
5513 (define-public smithlab-cpp
5514 (let ((revision "1")
5515 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5517 (name "smithlab-cpp")
5518 (version (string-append "0." revision "." (string-take commit 7)))
5522 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5524 (file-name (string-append name "-" version "-checkout"))
5527 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5528 (build-system gnu-build-system)
5530 `(#:modules ((guix build gnu-build-system)
5533 #:tests? #f ;no "check" target
5535 (modify-phases %standard-phases
5536 (add-after 'unpack 'use-samtools-headers
5538 (substitute* '("SAM.cpp"
5540 (("sam.h") "samtools/sam.h"))
5543 (lambda* (#:key outputs #:allow-other-keys)
5544 (let* ((out (assoc-ref outputs "out"))
5545 (lib (string-append out "/lib"))
5546 (include (string-append out "/include/smithlab-cpp")))
5549 (for-each (cut install-file <> lib)
5550 (find-files "." "\\.o$"))
5551 (for-each (cut install-file <> include)
5552 (find-files "." "\\.hpp$")))
5554 (delete 'configure))))
5556 `(("samtools" ,samtools-0.1)
5558 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5559 (synopsis "C++ helper library for functions used in Smith lab projects")
5561 "Smithlab CPP is a C++ library that includes functions used in many of
5562 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5563 structures, classes for genomic regions, mapped sequencing reads, etc.")
5564 (license license:gpl3+))))
5566 (define-public preseq
5572 (uri (string-append "https://github.com/smithlabcode/preseq/"
5573 "releases/download/v" version
5574 "/preseq_v" version ".tar.bz2"))
5576 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5577 (modules '((guix build utils)))
5579 ;; Remove bundled samtools.
5580 (delete-file-recursively "samtools")
5582 (build-system gnu-build-system)
5584 `(#:tests? #f ;no "check" target
5586 (modify-phases %standard-phases
5587 (delete 'configure))
5589 (list (string-append "PREFIX="
5590 (assoc-ref %outputs "out"))
5591 (string-append "LIBBAM="
5592 (assoc-ref %build-inputs "samtools")
5594 (string-append "SMITHLAB_CPP="
5595 (assoc-ref %build-inputs "smithlab-cpp")
5598 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5601 ("samtools" ,samtools-0.1)
5602 ("smithlab-cpp" ,smithlab-cpp)
5604 (home-page "http://smithlabresearch.org/software/preseq/")
5605 (synopsis "Program for analyzing library complexity")
5607 "The preseq package is aimed at predicting and estimating the complexity
5608 of a genomic sequencing library, equivalent to predicting and estimating the
5609 number of redundant reads from a given sequencing depth and how many will be
5610 expected from additional sequencing using an initial sequencing experiment.
5611 The estimates can then be used to examine the utility of further sequencing,
5612 optimize the sequencing depth, or to screen multiple libraries to avoid low
5613 complexity samples.")
5614 (license license:gpl3+)))
5616 (define-public python-screed
5618 (name "python-screed")
5623 (uri (pypi-uri "screed" version))
5626 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5627 (build-system python-build-system)
5630 (modify-phases %standard-phases
5631 ;; Tests must be run after installation, as the "screed" command does
5632 ;; not exist right after building.
5634 (add-after 'install 'check
5635 (lambda* (#:key inputs outputs #:allow-other-keys)
5636 (let ((out (assoc-ref outputs "out")))
5637 (setenv "PYTHONPATH"
5638 (string-append out "/lib/python"
5639 (string-take (string-take-right
5640 (assoc-ref inputs "python")
5643 (getenv "PYTHONPATH")))
5644 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5645 (invoke "python" "setup.py" "test")
5648 `(("python-pytest" ,python-pytest)
5649 ("python-pytest-cov" ,python-pytest-cov)
5650 ("python-pytest-runner" ,python-pytest-runner)))
5652 `(("python-bz2file" ,python-bz2file)))
5653 (home-page "https://github.com/dib-lab/screed/")
5654 (synopsis "Short read sequence database utilities")
5655 (description "Screed parses FASTA and FASTQ files and generates databases.
5656 Values such as sequence name, sequence description, sequence quality and the
5657 sequence itself can be retrieved from these databases.")
5658 (license license:bsd-3)))
5660 (define-public python2-screed
5661 (package-with-python2 python-screed))
5663 (define-public sra-tools
5671 (url "https://github.com/ncbi/sra-tools.git")
5673 (file-name (git-file-name name version))
5676 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5677 (build-system gnu-build-system)
5679 `(#:parallel-build? #f ; not supported
5680 #:tests? #f ; no "check" target
5682 (list (string-append "DEFAULT_CRT="
5683 (assoc-ref %build-inputs "ncbi-vdb")
5685 (string-append "DEFAULT_KFG="
5686 (assoc-ref %build-inputs "ncbi-vdb")
5688 (string-append "VDB_LIBDIR="
5689 (assoc-ref %build-inputs "ncbi-vdb")
5690 ,(if (string-prefix? "x86_64"
5691 (or (%current-target-system)
5696 (modify-phases %standard-phases
5697 (add-before 'configure 'set-perl-search-path
5699 ;; Work around "dotless @INC" build failure.
5701 (string-append (getcwd) "/setup:"
5702 (getenv "PERL5LIB")))
5705 (lambda* (#:key inputs outputs #:allow-other-keys)
5706 ;; The build system expects a directory containing the sources and
5707 ;; raw build output of ncbi-vdb, including files that are not
5708 ;; installed. Since we are building against an installed version of
5709 ;; ncbi-vdb, the following modifications are needed.
5710 (substitute* "setup/konfigure.perl"
5711 ;; Make the configure script look for the "ilib" directory of
5712 ;; "ncbi-vdb" without first checking for the existence of a
5713 ;; matching library in its "lib" directory.
5714 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5715 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5716 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5717 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5718 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5721 (substitute* "tools/copycat/Makefile"
5722 (("smagic-static") "lmagic"))
5724 ;; The 'configure' script doesn't recognize things like
5725 ;; '--enable-fast-install'.
5726 (invoke "./configure"
5727 (string-append "--build-prefix=" (getcwd) "/build")
5728 (string-append "--prefix=" (assoc-ref outputs "out"))
5729 (string-append "--debug")
5730 (string-append "--with-fuse-prefix="
5731 (assoc-ref inputs "fuse"))
5732 (string-append "--with-magic-prefix="
5733 (assoc-ref inputs "libmagic"))
5734 ;; TODO: building with libxml2 fails with linker errors
5735 ;; (string-append "--with-xml2-prefix="
5736 ;; (assoc-ref inputs "libxml2"))
5737 (string-append "--with-ncbi-vdb-sources="
5738 (assoc-ref inputs "ncbi-vdb"))
5739 (string-append "--with-ncbi-vdb-build="
5740 (assoc-ref inputs "ncbi-vdb"))
5741 (string-append "--with-ngs-sdk-prefix="
5742 (assoc-ref inputs "ngs-sdk"))
5743 (string-append "--with-hdf5-prefix="
5744 (assoc-ref inputs "hdf5")))
5746 (native-inputs `(("perl" ,perl)))
5748 `(("ngs-sdk" ,ngs-sdk)
5749 ("ncbi-vdb" ,ncbi-vdb)
5754 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5755 (synopsis "Tools and libraries for reading and writing sequencing data")
5757 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5758 reading of sequencing files from the Sequence Read Archive (SRA) database and
5759 writing files into the .sra format.")
5760 (license license:public-domain)))
5762 (define-public seqan
5768 (uri (string-append "https://github.com/seqan/seqan/releases/"
5769 "download/seqan-v" version
5770 "/seqan-library-" version ".tar.xz"))
5773 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5774 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5775 ;; makes sense to split the outputs.
5776 (outputs '("out" "doc"))
5777 (build-system trivial-build-system)
5779 `(#:modules ((guix build utils))
5782 (use-modules (guix build utils))
5783 (let ((tar (assoc-ref %build-inputs "tar"))
5784 (xz (assoc-ref %build-inputs "xz"))
5785 (out (assoc-ref %outputs "out"))
5786 (doc (assoc-ref %outputs "doc")))
5787 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5788 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5789 (chdir (string-append "seqan-library-" ,version))
5790 (copy-recursively "include" (string-append out "/include"))
5791 (copy-recursively "share" (string-append doc "/share"))
5794 `(("source" ,source)
5797 (home-page "http://www.seqan.de")
5798 (synopsis "Library for nucleotide sequence analysis")
5800 "SeqAn is a C++ library of efficient algorithms and data structures for
5801 the analysis of sequences with the focus on biological data. It contains
5802 algorithms and data structures for string representation and their
5803 manipulation, online and indexed string search, efficient I/O of
5804 bioinformatics file formats, sequence alignment, and more.")
5805 (license license:bsd-3)))
5807 (define-public seqan-1
5808 (package (inherit seqan)
5813 (uri (string-append "http://packages.seqan.de/seqan-library/"
5814 "seqan-library-" version ".tar.bz2"))
5817 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5818 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5819 ;; makes sense to split the outputs.
5820 (outputs '("out" "doc"))
5821 (build-system trivial-build-system)
5823 `(#:modules ((guix build utils))
5826 (use-modules (guix build utils))
5827 (let ((tar (assoc-ref %build-inputs "tar"))
5828 (bzip (assoc-ref %build-inputs "bzip2"))
5829 (out (assoc-ref %outputs "out"))
5830 (doc (assoc-ref %outputs "doc")))
5831 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5832 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5833 (chdir (string-append "seqan-library-" ,version))
5834 (copy-recursively "include" (string-append out "/include"))
5835 (copy-recursively "share" (string-append doc "/share"))
5838 `(("source" ,source)
5840 ("bzip2" ,bzip2)))))
5842 (define-public seqmagick
5849 (uri (pypi-uri "seqmagick" version))
5852 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5853 (build-system python-build-system)
5855 `(("python-biopython" ,python-biopython)))
5857 `(("python-nose" ,python-nose)))
5858 (home-page "https://github.com/fhcrc/seqmagick")
5859 (synopsis "Tools for converting and modifying sequence files")
5861 "Bioinformaticians often have to convert sequence files between formats
5862 and do little manipulations on them, and it's not worth writing scripts for
5863 that. Seqmagick is a utility to expose the file format conversion in
5864 BioPython in a convenient way. Instead of having a big mess of scripts, there
5865 is one that takes arguments.")
5866 (license license:gpl3)))
5868 (define-public seqtk
5875 (url "https://github.com/lh3/seqtk.git")
5876 (commit (string-append "v" version))))
5877 (file-name (git-file-name name version))
5880 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5881 (build-system gnu-build-system)
5884 (modify-phases %standard-phases
5887 ;; There are no tests, so we just run a sanity check.
5888 (lambda _ (invoke "./seqtk" "seq") #t))
5890 (lambda* (#:key outputs #:allow-other-keys)
5891 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5892 (install-file "seqtk" bin)
5896 (home-page "https://github.com/lh3/seqtk")
5897 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5899 "Seqtk is a fast and lightweight tool for processing sequences in the
5900 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5901 optionally compressed by gzip.")
5902 (license license:expat)))
5904 (define-public snap-aligner
5906 (name "snap-aligner")
5907 (version "1.0beta.18")
5911 (url "https://github.com/amplab/snap.git")
5912 (commit (string-append "v" version))))
5913 (file-name (git-file-name name version))
5916 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5917 (build-system gnu-build-system)
5920 (modify-phases %standard-phases
5922 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5924 (lambda* (#:key outputs #:allow-other-keys)
5925 (let* ((out (assoc-ref outputs "out"))
5926 (bin (string-append out "/bin")))
5927 (install-file "snap-aligner" bin)
5928 (install-file "SNAPCommand" bin)
5932 (home-page "http://snap.cs.berkeley.edu/")
5933 (synopsis "Short read DNA sequence aligner")
5935 "SNAP is a fast and accurate aligner for short DNA reads. It is
5936 optimized for modern read lengths of 100 bases or higher, and takes advantage
5937 of these reads to align data quickly through a hash-based indexing scheme.")
5938 ;; 32-bit systems are not supported by the unpatched code.
5939 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5940 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5941 ;; systems without a lot of memory cannot make good use of this program.
5942 (supported-systems '("x86_64-linux"))
5943 (license license:asl2.0)))
5945 (define-public sortmerna
5953 (url "https://github.com/biocore/sortmerna.git")
5955 (file-name (git-file-name name version))
5958 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5959 (build-system gnu-build-system)
5960 (outputs '("out" ;for binaries
5961 "db")) ;for sequence databases
5964 (modify-phases %standard-phases
5966 (lambda* (#:key outputs #:allow-other-keys)
5967 (let* ((out (assoc-ref outputs "out"))
5968 (bin (string-append out "/bin"))
5969 (db (assoc-ref outputs "db"))
5971 (string-append db "/share/sortmerna/rRNA_databases")))
5972 (install-file "sortmerna" bin)
5973 (install-file "indexdb_rna" bin)
5974 (for-each (lambda (file)
5975 (install-file file share))
5976 (find-files "rRNA_databases" ".*fasta"))
5980 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5981 (synopsis "Biological sequence analysis tool for NGS reads")
5983 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5984 and operational taxonomic unit (OTU) picking of next generation
5985 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5986 allows for fast and sensitive analyses of nucleotide sequences. The main
5987 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5988 ;; The source includes x86 specific code
5989 (supported-systems '("x86_64-linux" "i686-linux"))
5990 (license license:lgpl3)))
5999 (url "https://github.com/alexdobin/STAR.git")
6001 (file-name (string-append name "-" version "-checkout"))
6004 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
6005 (modules '((guix build utils)))
6008 (substitute* "source/Makefile"
6010 ;; Remove pre-built binaries and bundled htslib sources.
6011 (delete-file-recursively "bin/MacOSX_x86_64")
6012 (delete-file-recursively "bin/Linux_x86_64")
6013 (delete-file-recursively "bin/Linux_x86_64_static")
6014 (delete-file-recursively "source/htslib")
6016 (build-system gnu-build-system)
6018 '(#:tests? #f ;no check target
6019 #:make-flags '("STAR")
6021 (modify-phases %standard-phases
6022 (add-after 'unpack 'enter-source-dir
6023 (lambda _ (chdir "source") #t))
6024 (add-after 'enter-source-dir 'make-reproducible
6026 (substitute* "Makefile"
6027 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6028 (string-append pre "Built with Guix" post)))
6030 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6032 (substitute* "Makefile"
6033 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6035 (substitute* '("BAMfunctions.cpp"
6040 "bamRemoveDuplicates.cpp")
6041 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6042 (string-append "#include <" header ">")))
6043 (substitute* "IncludeDefine.h"
6044 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6045 (string-append "<" header ">")))
6048 (lambda* (#:key outputs #:allow-other-keys)
6049 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6050 (install-file "STAR" bin))
6052 (delete 'configure))))
6056 `(("htslib" ,htslib)
6058 (home-page "https://github.com/alexdobin/STAR")
6059 (synopsis "Universal RNA-seq aligner")
6061 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6062 based on a previously undescribed RNA-seq alignment algorithm that uses
6063 sequential maximum mappable seed search in uncompressed suffix arrays followed
6064 by seed clustering and stitching procedure. In addition to unbiased de novo
6065 detection of canonical junctions, STAR can discover non-canonical splices and
6066 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6068 ;; Only 64-bit systems are supported according to the README.
6069 (supported-systems '("x86_64-linux" "mips64el-linux"))
6070 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6071 (license license:gpl3+)))
6073 (define-public subread
6079 (uri (string-append "mirror://sourceforge/subread/subread-"
6080 version "/subread-" version "-source.tar.gz"))
6083 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6084 (build-system gnu-build-system)
6086 `(#:tests? #f ;no "check" target
6087 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6088 ;; optimizations by default, so we override these flags such that x86_64
6089 ;; flags are only added when the build target is an x86_64 system.
6091 (list (let ((system ,(or (%current-target-system)
6093 (flags '("-ggdb" "-fomit-frame-pointer"
6094 "-ffast-math" "-funroll-loops"
6095 "-fmessage-length=0"
6096 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6098 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6099 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6100 (if (string-prefix? "x86_64" system)
6101 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6102 (string-append "CCFLAGS=" (string-join flags))))
6103 "-f" "Makefile.Linux"
6104 "CC=gcc ${CCFLAGS}")
6106 (modify-phases %standard-phases
6107 (add-after 'unpack 'enter-dir
6108 (lambda _ (chdir "src") #t))
6110 (lambda* (#:key outputs #:allow-other-keys)
6111 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6113 (copy-recursively "../bin" bin))
6115 ;; no "configure" script
6116 (delete 'configure))))
6117 (inputs `(("zlib" ,zlib)))
6118 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6119 (synopsis "Tool kit for processing next-gen sequencing data")
6121 "The subread package contains the following tools: subread aligner, a
6122 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6123 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6124 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6125 against local background noises.")
6126 (license license:gpl3+)))
6128 (define-public stringtie
6134 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6135 "stringtie-" version ".tar.gz"))
6138 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6139 (modules '((guix build utils)))
6142 (delete-file-recursively "samtools-0.1.18")
6144 (build-system gnu-build-system)
6146 `(#:tests? #f ;no test suite
6148 (modify-phases %standard-phases
6149 ;; no configure script
6151 (add-before 'build 'use-system-samtools
6153 (substitute* "Makefile"
6154 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6156 (substitute* '("gclib/GBam.h"
6158 (("#include \"(bam|sam|kstring).h\"" _ header)
6159 (string-append "#include <samtools/" header ".h>")))
6161 (add-after 'unpack 'remove-duplicate-typedef
6163 ;; This typedef conflicts with the typedef in
6164 ;; glibc-2.25/include/bits/types.h
6165 (substitute* "gclib/GThreads.h"
6166 (("typedef long long __intmax_t;") ""))
6169 (lambda* (#:key outputs #:allow-other-keys)
6170 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6171 (install-file "stringtie" bin)
6174 `(("samtools" ,samtools-0.1)
6176 (home-page "http://ccb.jhu.edu/software/stringtie/")
6177 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6179 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6180 alignments into potential transcripts. It uses a novel network flow algorithm
6181 as well as an optional de novo assembly step to assemble and quantitate
6182 full-length transcripts representing multiple splice variants for each gene
6183 locus. Its input can include not only the alignments of raw reads used by
6184 other transcript assemblers, but also alignments of longer sequences that have
6185 been assembled from those reads. To identify differentially expressed genes
6186 between experiments, StringTie's output can be processed either by the
6187 Cuffdiff or Ballgown programs.")
6188 (license license:artistic2.0)))
6190 (define-public taxtastic
6196 (uri (pypi-uri "taxtastic" version))
6199 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6200 (build-system python-build-system)
6202 `(#:python ,python-2
6204 (modify-phases %standard-phases
6206 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6208 `(("python-sqlalchemy" ,python2-sqlalchemy)
6209 ("python-decorator" ,python2-decorator)
6210 ("python-biopython" ,python2-biopython)
6211 ("python-pandas" ,python2-pandas)
6212 ("python-psycopg2" ,python2-psycopg2)
6213 ("python-fastalite" ,python2-fastalite)
6214 ("python-pyyaml" ,python2-pyyaml)
6215 ("python-six" ,python2-six)
6216 ("python-jinja2" ,python2-jinja2)
6217 ("python-dendropy" ,python2-dendropy)))
6218 (home-page "https://github.com/fhcrc/taxtastic")
6219 (synopsis "Tools for taxonomic naming and annotation")
6221 "Taxtastic is software written in python used to build and maintain
6222 reference packages i.e. collections of reference trees, reference alignments,
6223 profiles, and associated taxonomic information.")
6224 (license license:gpl3+)))
6226 (define-public vcftools
6233 "https://github.com/vcftools/vcftools/releases/download/v"
6234 version "/vcftools-" version ".tar.gz"))
6237 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6238 (build-system gnu-build-system)
6240 `(#:tests? #f ; no "check" target
6242 "CFLAGS=-O2" ; override "-m64" flag
6243 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6244 (string-append "MANDIR=" (assoc-ref %outputs "out")
6245 "/share/man/man1"))))
6247 `(("pkg-config" ,pkg-config)))
6251 (home-page "https://vcftools.github.io/")
6252 (synopsis "Tools for working with VCF files")
6254 "VCFtools is a program package designed for working with VCF files, such
6255 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6256 provide easily accessible methods for working with complex genetic variation
6257 data in the form of VCF files.")
6258 ;; The license is declared as LGPLv3 in the README and
6259 ;; at https://vcftools.github.io/license.html
6260 (license license:lgpl3)))
6262 (define-public infernal
6268 (uri (string-append "http://eddylab.org/software/infernal/"
6269 "infernal-" version ".tar.gz"))
6272 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6273 (build-system gnu-build-system)
6275 `(("perl" ,perl))) ; for tests
6276 (home-page "http://eddylab.org/infernal/")
6277 (synopsis "Inference of RNA alignments")
6278 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6279 searching DNA sequence databases for RNA structure and sequence similarities.
6280 It is an implementation of a special case of profile stochastic context-free
6281 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6282 profile, but it scores a combination of sequence consensus and RNA secondary
6283 structure consensus, so in many cases, it is more capable of identifying RNA
6284 homologs that conserve their secondary structure more than their primary
6286 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6287 (supported-systems '("i686-linux" "x86_64-linux"))
6288 (license license:bsd-3)))
6290 (define-public r-centipede
6292 (name "r-centipede")
6296 (uri (string-append "http://download.r-forge.r-project.org/"
6297 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6300 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6301 (build-system r-build-system)
6302 (home-page "http://centipede.uchicago.edu/")
6303 (synopsis "Predict transcription factor binding sites")
6305 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6306 of the genome that are bound by particular transcription factors. It starts
6307 by identifying a set of candidate binding sites, and then aims to classify the
6308 sites according to whether each site is bound or not bound by a transcription
6309 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6310 between two different types of motif instances using as much relevant
6311 information as possible.")
6312 (license (list license:gpl2+ license:gpl3+))))
6314 (define-public r-vegan
6321 (uri (cran-uri "vegan" version))
6324 "023xznh0iy0496icpchadmp7a3rk3nj9s48fvwlvp3dssw58yp3c"))))
6325 (build-system r-build-system)
6327 `(("gfortran" ,gfortran)))
6329 `(("r-cluster" ,r-cluster)
6330 ("r-knitr" ,r-knitr) ; needed for vignettes
6331 ("r-lattice" ,r-lattice)
6334 ("r-permute" ,r-permute)))
6335 (home-page "https://cran.r-project.org/web/packages/vegan")
6336 (synopsis "Functions for community ecology")
6338 "The vegan package provides tools for descriptive community ecology. It
6339 has most basic functions of diversity analysis, community ordination and
6340 dissimilarity analysis. Most of its multivariate tools can be used for other
6341 data types as well.")
6342 (license license:gpl2+)))
6344 (define-public r-annotate
6351 (uri (bioconductor-uri "annotate" version))
6354 "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
6355 (build-system r-build-system)
6357 `(("r-annotationdbi" ,r-annotationdbi)
6358 ("r-biobase" ,r-biobase)
6359 ("r-biocgenerics" ,r-biocgenerics)
6361 ("r-rcurl" ,r-rcurl)
6363 ("r-xtable" ,r-xtable)))
6365 "https://bioconductor.org/packages/annotate")
6366 (synopsis "Annotation for microarrays")
6367 (description "This package provides R environments for the annotation of
6369 (license license:artistic2.0)))
6371 (define-public r-copynumber
6373 (name "r-copynumber")
6377 (uri (bioconductor-uri "copynumber" version))
6380 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6381 (build-system r-build-system)
6383 `(("r-s4vectors" ,r-s4vectors)
6384 ("r-iranges" ,r-iranges)
6385 ("r-genomicranges" ,r-genomicranges)
6386 ("r-biocgenerics" ,r-biocgenerics)))
6387 (home-page "https://bioconductor.org/packages/copynumber")
6388 (synopsis "Segmentation of single- and multi-track copy number data")
6390 "This package segments single- and multi-track copy number data by a
6391 penalized least squares regression method.")
6392 (license license:artistic2.0)))
6394 (define-public r-geneplotter
6396 (name "r-geneplotter")
6401 (uri (bioconductor-uri "geneplotter" version))
6404 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6405 (build-system r-build-system)
6407 `(("r-annotate" ,r-annotate)
6408 ("r-annotationdbi" ,r-annotationdbi)
6409 ("r-biobase" ,r-biobase)
6410 ("r-biocgenerics" ,r-biocgenerics)
6411 ("r-lattice" ,r-lattice)
6412 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6413 (home-page "https://bioconductor.org/packages/geneplotter")
6414 (synopsis "Graphics functions for genomic data")
6416 "This package provides functions for plotting genomic data.")
6417 (license license:artistic2.0)))
6419 (define-public r-genefilter
6421 (name "r-genefilter")
6426 (uri (bioconductor-uri "genefilter" version))
6429 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6430 (build-system r-build-system)
6432 `(("gfortran" ,gfortran)))
6434 `(("r-annotate" ,r-annotate)
6435 ("r-annotationdbi" ,r-annotationdbi)
6436 ("r-biobase" ,r-biobase)
6437 ("r-s4vectors" ,r-s4vectors)
6438 ("r-survival" ,r-survival)))
6439 (home-page "https://bioconductor.org/packages/genefilter")
6440 (synopsis "Filter genes from high-throughput experiments")
6442 "This package provides basic functions for filtering genes from
6443 high-throughput sequencing experiments.")
6444 (license license:artistic2.0)))
6446 (define-public r-deseq2
6453 (uri (bioconductor-uri "DESeq2" version))
6456 "1b2bmvcsfzvks47d7w46zplcwz0kgcdhx5xmx3x9lp2gvx2p84r5"))))
6457 (properties `((upstream-name . "DESeq2")))
6458 (build-system r-build-system)
6460 `(("r-biobase" ,r-biobase)
6461 ("r-biocgenerics" ,r-biocgenerics)
6462 ("r-biocparallel" ,r-biocparallel)
6463 ("r-genefilter" ,r-genefilter)
6464 ("r-geneplotter" ,r-geneplotter)
6465 ("r-genomicranges" ,r-genomicranges)
6466 ("r-ggplot2" ,r-ggplot2)
6467 ("r-hmisc" ,r-hmisc)
6468 ("r-iranges" ,r-iranges)
6469 ("r-locfit" ,r-locfit)
6471 ("r-rcpparmadillo" ,r-rcpparmadillo)
6472 ("r-s4vectors" ,r-s4vectors)
6473 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6474 (home-page "https://bioconductor.org/packages/DESeq2")
6475 (synopsis "Differential gene expression analysis")
6477 "This package provides functions to estimate variance-mean dependence in
6478 count data from high-throughput nucleotide sequencing assays and test for
6479 differential expression based on a model using the negative binomial
6481 (license license:lgpl3+)))
6483 (define-public r-dexseq
6490 (uri (bioconductor-uri "DEXSeq" version))
6493 "0jh1640cnzpk8x3155cqc8dvrs1rciw3d6nv2k70baw96bhrynp8"))))
6494 (properties `((upstream-name . "DEXSeq")))
6495 (build-system r-build-system)
6497 `(("r-annotationdbi" ,r-annotationdbi)
6498 ("r-biobase" ,r-biobase)
6499 ("r-biocgenerics" ,r-biocgenerics)
6500 ("r-biocparallel" ,r-biocparallel)
6501 ("r-biomart" ,r-biomart)
6502 ("r-deseq2" ,r-deseq2)
6503 ("r-genefilter" ,r-genefilter)
6504 ("r-geneplotter" ,r-geneplotter)
6505 ("r-genomicranges" ,r-genomicranges)
6506 ("r-hwriter" ,r-hwriter)
6507 ("r-iranges" ,r-iranges)
6508 ("r-rcolorbrewer" ,r-rcolorbrewer)
6509 ("r-rsamtools" ,r-rsamtools)
6510 ("r-s4vectors" ,r-s4vectors)
6511 ("r-statmod" ,r-statmod)
6512 ("r-stringr" ,r-stringr)
6513 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6514 (home-page "https://bioconductor.org/packages/DEXSeq")
6515 (synopsis "Inference of differential exon usage in RNA-Seq")
6517 "This package is focused on finding differential exon usage using RNA-seq
6518 exon counts between samples with different experimental designs. It provides
6519 functions that allows the user to make the necessary statistical tests based
6520 on a model that uses the negative binomial distribution to estimate the
6521 variance between biological replicates and generalized linear models for
6522 testing. The package also provides functions for the visualization and
6523 exploration of the results.")
6524 (license license:gpl3+)))
6526 (define-public r-annotationforge
6528 (name "r-annotationforge")
6533 (uri (bioconductor-uri "AnnotationForge" version))
6536 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6538 `((upstream-name . "AnnotationForge")))
6539 (build-system r-build-system)
6541 `(("r-annotationdbi" ,r-annotationdbi)
6542 ("r-biobase" ,r-biobase)
6543 ("r-biocgenerics" ,r-biocgenerics)
6545 ("r-rcurl" ,r-rcurl)
6546 ("r-rsqlite" ,r-rsqlite)
6547 ("r-s4vectors" ,r-s4vectors)
6549 (home-page "https://bioconductor.org/packages/AnnotationForge")
6550 (synopsis "Code for building annotation database packages")
6552 "This package provides code for generating Annotation packages and their
6553 databases. Packages produced are intended to be used with AnnotationDbi.")
6554 (license license:artistic2.0)))
6556 (define-public r-rbgl
6563 (uri (bioconductor-uri "RBGL" version))
6566 "0jy95m38c4qp0a12097hhm2gg63k96k6ydhb11dy379h3ziapcar"))))
6567 (properties `((upstream-name . "RBGL")))
6568 (build-system r-build-system)
6569 (propagated-inputs `(("r-graph" ,r-graph)))
6570 (home-page "https://www.bioconductor.org/packages/RBGL")
6571 (synopsis "Interface to the Boost graph library")
6573 "This package provides a fairly extensive and comprehensive interface to
6574 the graph algorithms contained in the Boost library.")
6575 (license license:artistic2.0)))
6577 (define-public r-gseabase
6584 (uri (bioconductor-uri "GSEABase" version))
6587 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6588 (properties `((upstream-name . "GSEABase")))
6589 (build-system r-build-system)
6591 `(("r-annotate" ,r-annotate)
6592 ("r-annotationdbi" ,r-annotationdbi)
6593 ("r-biobase" ,r-biobase)
6594 ("r-biocgenerics" ,r-biocgenerics)
6595 ("r-graph" ,r-graph)
6597 (home-page "https://bioconductor.org/packages/GSEABase")
6598 (synopsis "Gene set enrichment data structures and methods")
6600 "This package provides classes and methods to support @dfn{Gene Set
6601 Enrichment Analysis} (GSEA).")
6602 (license license:artistic2.0)))
6604 (define-public r-category
6611 (uri (bioconductor-uri "Category" version))
6614 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6615 (properties `((upstream-name . "Category")))
6616 (build-system r-build-system)
6618 `(("r-annotate" ,r-annotate)
6619 ("r-annotationdbi" ,r-annotationdbi)
6620 ("r-biobase" ,r-biobase)
6621 ("r-biocgenerics" ,r-biocgenerics)
6622 ("r-genefilter" ,r-genefilter)
6623 ("r-graph" ,r-graph)
6624 ("r-gseabase" ,r-gseabase)
6625 ("r-matrix" ,r-matrix)
6628 (home-page "https://bioconductor.org/packages/Category")
6629 (synopsis "Category analysis")
6631 "This package provides a collection of tools for performing category
6633 (license license:artistic2.0)))
6635 (define-public r-gostats
6642 (uri (bioconductor-uri "GOstats" version))
6645 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6646 (properties `((upstream-name . "GOstats")))
6647 (build-system r-build-system)
6649 `(("r-annotate" ,r-annotate)
6650 ("r-annotationdbi" ,r-annotationdbi)
6651 ("r-annotationforge" ,r-annotationforge)
6652 ("r-biobase" ,r-biobase)
6653 ("r-category" ,r-category)
6654 ("r-go-db" ,r-go-db)
6655 ("r-graph" ,r-graph)
6656 ("r-rgraphviz" ,r-rgraphviz)
6657 ("r-rbgl" ,r-rbgl)))
6658 (home-page "https://bioconductor.org/packages/GOstats")
6659 (synopsis "Tools for manipulating GO and microarrays")
6661 "This package provides a set of tools for interacting with GO and
6662 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6663 testing and other simple calculations.")
6664 (license license:artistic2.0)))
6666 (define-public r-shortread
6668 (name "r-shortread")
6673 (uri (bioconductor-uri "ShortRead" version))
6676 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6677 (properties `((upstream-name . "ShortRead")))
6678 (build-system r-build-system)
6682 `(("r-biobase" ,r-biobase)
6683 ("r-biocgenerics" ,r-biocgenerics)
6684 ("r-biocparallel" ,r-biocparallel)
6685 ("r-biostrings" ,r-biostrings)
6686 ("r-genomeinfodb" ,r-genomeinfodb)
6687 ("r-genomicalignments" ,r-genomicalignments)
6688 ("r-genomicranges" ,r-genomicranges)
6689 ("r-hwriter" ,r-hwriter)
6690 ("r-iranges" ,r-iranges)
6691 ("r-lattice" ,r-lattice)
6692 ("r-latticeextra" ,r-latticeextra)
6693 ("r-rsamtools" ,r-rsamtools)
6694 ("r-s4vectors" ,r-s4vectors)
6695 ("r-xvector" ,r-xvector)
6696 ("r-zlibbioc" ,r-zlibbioc)))
6697 (home-page "https://bioconductor.org/packages/ShortRead")
6698 (synopsis "FASTQ input and manipulation tools")
6700 "This package implements sampling, iteration, and input of FASTQ files.
6701 It includes functions for filtering and trimming reads, and for generating a
6702 quality assessment report. Data are represented as
6703 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6704 purposes. The package also contains legacy support for early single-end,
6705 ungapped alignment formats.")
6706 (license license:artistic2.0)))
6708 (define-public r-systempiper
6710 (name "r-systempiper")
6715 (uri (bioconductor-uri "systemPipeR" version))
6718 "0l26q8zjdmzg84g7f25gv9z60sykybahlpg5bg9bmpbg5lzcsx04"))))
6719 (properties `((upstream-name . "systemPipeR")))
6720 (build-system r-build-system)
6722 `(("r-annotate" ,r-annotate)
6723 ("r-batchjobs" ,r-batchjobs)
6724 ("r-biocgenerics" ,r-biocgenerics)
6725 ("r-biostrings" ,r-biostrings)
6726 ("r-deseq2" ,r-deseq2)
6727 ("r-edger" ,r-edger)
6728 ("r-genomicfeatures" ,r-genomicfeatures)
6729 ("r-genomicranges" ,r-genomicranges)
6730 ("r-ggplot2" ,r-ggplot2)
6731 ("r-go-db" ,r-go-db)
6732 ("r-gostats" ,r-gostats)
6733 ("r-limma" ,r-limma)
6734 ("r-pheatmap" ,r-pheatmap)
6735 ("r-rjson" ,r-rjson)
6736 ("r-rsamtools" ,r-rsamtools)
6737 ("r-shortread" ,r-shortread)
6738 ("r-summarizedexperiment" ,r-summarizedexperiment)
6739 ("r-variantannotation" ,r-variantannotation)))
6740 (home-page "https://github.com/tgirke/systemPipeR")
6741 (synopsis "Next generation sequencing workflow and reporting environment")
6743 "This R package provides tools for building and running automated
6744 end-to-end analysis workflows for a wide range of @dfn{next generation
6745 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6746 Important features include a uniform workflow interface across different NGS
6747 applications, automated report generation, and support for running both R and
6748 command-line software, such as NGS aligners or peak/variant callers, on local
6749 computers or compute clusters. Efficient handling of complex sample sets and
6750 experimental designs is facilitated by a consistently implemented sample
6751 annotation infrastructure.")
6752 (license license:artistic2.0)))
6754 (define-public r-grohmm
6761 (uri (bioconductor-uri "groHMM" version))
6764 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6765 (properties `((upstream-name . "groHMM")))
6766 (build-system r-build-system)
6768 `(("r-genomeinfodb" ,r-genomeinfodb)
6769 ("r-genomicalignments" ,r-genomicalignments)
6770 ("r-genomicranges" ,r-genomicranges)
6771 ("r-iranges" ,r-iranges)
6773 ("r-rtracklayer" ,r-rtracklayer)
6774 ("r-s4vectors" ,r-s4vectors)))
6775 (home-page "https://github.com/Kraus-Lab/groHMM")
6776 (synopsis "GRO-seq analysis pipeline")
6778 "This package provides a pipeline for the analysis of GRO-seq data.")
6779 (license license:gpl3+)))
6781 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6783 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6787 ;; We cannot use bioconductor-uri here because this tarball is
6788 ;; located under "data/annotation/" instead of "bioc/".
6789 (uri (string-append "https://bioconductor.org/packages/"
6790 "release/data/annotation/src/contrib"
6791 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6795 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6797 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6798 (build-system r-build-system)
6799 ;; As this package provides little more than a very large data file it
6800 ;; doesn't make sense to build substitutes.
6801 (arguments `(#:substitutable? #f))
6803 `(("r-genomicfeatures" ,r-genomicfeatures)))
6805 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6806 (synopsis "Annotation package for human genome in TxDb format")
6808 "This package provides an annotation database of Homo sapiens genome
6809 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6810 track. The database is exposed as a @code{TxDb} object.")
6811 (license license:artistic2.0)))
6813 (define-public r-sparql
6819 (uri (cran-uri "SPARQL" version))
6822 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6823 (properties `((upstream-name . "SPARQL")))
6824 (build-system r-build-system)
6826 `(("r-rcurl" ,r-rcurl)
6828 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6829 (synopsis "SPARQL client for R")
6830 (description "This package provides an interface to use SPARQL to pose
6831 SELECT or UPDATE queries to an end-point.")
6832 ;; The only license indication is found in the DESCRIPTION file,
6833 ;; which states GPL-3. So we cannot assume GPLv3+.
6834 (license license:gpl3)))
6836 (define-public vsearch
6844 (url "https://github.com/torognes/vsearch.git")
6845 (commit (string-append "v" version))))
6846 (file-name (git-file-name name version))
6849 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6850 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6853 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6854 ;; for this in the patch.
6855 (delete-file "src/city.h")
6856 (delete-file "src/citycrc.h")
6857 (delete-file "src/city.cc")
6859 (build-system gnu-build-system)
6863 ("cityhash" ,cityhash)))
6865 `(("autoconf" ,autoconf)
6866 ("automake" ,automake)))
6867 (synopsis "Sequence search tools for metagenomics")
6869 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6870 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6871 masking. The tool takes advantage of parallelism in the form of SIMD
6872 vectorization as well as multiple threads to perform accurate alignments at
6873 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6874 Needleman-Wunsch).")
6875 (home-page "https://github.com/torognes/vsearch")
6876 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6878 (supported-systems '("x86_64-linux"))
6879 ;; Dual licensed; also includes public domain source.
6880 (license (list license:gpl3 license:bsd-2))))
6882 (define-public pardre
6885 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6890 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6894 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6895 (build-system gnu-build-system)
6897 `(#:tests? #f ; no tests included
6899 (modify-phases %standard-phases
6902 (lambda* (#:key outputs #:allow-other-keys)
6903 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6904 (install-file "ParDRe" bin)
6907 `(("openmpi" ,openmpi)
6909 (synopsis "Parallel tool to remove duplicate DNA reads")
6911 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6912 Duplicate reads can be seen as identical or nearly identical sequences with
6913 some mismatches. This tool lets users avoid the analysis of unnecessary
6914 reads, reducing the time of subsequent procedures with the
6915 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6916 in order to exploit the parallel capabilities of multicore clusters. It is
6917 faster than multithreaded counterparts (end of 2015) for the same number of
6918 cores and, thanks to the message-passing technology, it can be executed on
6920 (home-page "https://sourceforge.net/projects/pardre/")
6921 (license license:gpl3+)))
6923 (define-public ruby-bio-kseq
6925 (name "ruby-bio-kseq")
6930 (uri (rubygems-uri "bio-kseq" version))
6933 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6934 (build-system ruby-build-system)
6936 `(#:test-target "spec"))
6938 `(("bundler" ,bundler)
6939 ("ruby-rspec" ,ruby-rspec)
6940 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6943 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6945 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6946 FASTQ parsing code. It provides a fast iterator over sequences and their
6948 (home-page "https://github.com/gusevfe/bio-kseq")
6949 (license license:expat)))
6951 (define-public bio-locus
6958 (uri (rubygems-uri "bio-locus" version))
6961 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6962 (build-system ruby-build-system)
6964 `(("ruby-rspec" ,ruby-rspec)))
6965 (synopsis "Tool for fast querying of genome locations")
6967 "Bio-locus is a tabix-like tool for fast querying of genome
6968 locations. Many file formats in bioinformatics contain records that
6969 start with a chromosome name and a position for a SNP, or a start-end
6970 position for indels. Bio-locus allows users to store this chr+pos or
6971 chr+pos+alt information in a database.")
6972 (home-page "https://github.com/pjotrp/bio-locus")
6973 (license license:expat)))
6975 (define-public bio-blastxmlparser
6977 (name "bio-blastxmlparser")
6981 (uri (rubygems-uri "bio-blastxmlparser" version))
6984 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6985 (build-system ruby-build-system)
6987 `(("ruby-bio-logger" ,ruby-bio-logger)
6988 ("ruby-nokogiri" ,ruby-nokogiri)))
6990 `(("ruby-rspec" ,ruby-rspec)))
6991 (synopsis "Fast big data BLAST XML parser and library")
6993 "Very fast parallel big-data BLAST XML file parser which can be used as
6994 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6995 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6996 (home-page "https://github.com/pjotrp/blastxmlparser")
6997 (license license:expat)))
6999 (define-public bioruby
7006 (uri (rubygems-uri "bio" version))
7009 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7010 (build-system ruby-build-system)
7012 `(("ruby-libxml" ,ruby-libxml)))
7014 `(("which" ,which))) ; required for test phase
7017 (modify-phases %standard-phases
7018 (add-before 'build 'patch-test-command
7020 (substitute* '("test/functional/bio/test_command.rb")
7021 (("/bin/sh") (which "sh")))
7022 (substitute* '("test/functional/bio/test_command.rb")
7023 (("/bin/ls") (which "ls")))
7024 (substitute* '("test/functional/bio/test_command.rb")
7025 (("which") (which "which")))
7026 (substitute* '("test/functional/bio/test_command.rb",
7027 "test/data/command/echoarg2.sh")
7028 (("/bin/echo") (which "echo")))
7030 (synopsis "Ruby library, shell and utilities for bioinformatics")
7031 (description "BioRuby comes with a comprehensive set of Ruby development
7032 tools and libraries for bioinformatics and molecular biology. BioRuby has
7033 components for sequence analysis, pathway analysis, protein modelling and
7034 phylogenetic analysis; it supports many widely used data formats and provides
7035 easy access to databases, external programs and public web services, including
7036 BLAST, KEGG, GenBank, MEDLINE and GO.")
7037 (home-page "http://bioruby.org/")
7038 ;; Code is released under Ruby license, except for setup
7039 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7040 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7042 (define-public r-acsnminer
7044 (name "r-acsnminer")
7045 (version "0.16.8.25")
7048 (uri (cran-uri "ACSNMineR" version))
7051 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7052 (properties `((upstream-name . "ACSNMineR")))
7053 (build-system r-build-system)
7055 `(("r-ggplot2" ,r-ggplot2)
7056 ("r-gridextra" ,r-gridextra)))
7057 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7058 (synopsis "Gene enrichment analysis")
7060 "This package provides tools to compute and represent gene set enrichment
7061 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7062 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7063 enrichment can be run with hypergeometric test or Fisher exact test, and can
7064 use multiple corrections. Visualization of data can be done either by
7065 barplots or heatmaps.")
7066 (license license:gpl2+)))
7068 (define-public r-biocgenerics
7070 (name "r-biocgenerics")
7074 (uri (bioconductor-uri "BiocGenerics" version))
7077 "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
7079 `((upstream-name . "BiocGenerics")))
7080 (build-system r-build-system)
7081 (home-page "https://bioconductor.org/packages/BiocGenerics")
7082 (synopsis "S4 generic functions for Bioconductor")
7084 "This package provides S4 generic functions needed by many Bioconductor
7086 (license license:artistic2.0)))
7088 (define-public r-biocinstaller
7090 (name "r-biocinstaller")
7094 (uri (bioconductor-uri "BiocInstaller" version))
7097 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7099 `((upstream-name . "BiocInstaller")))
7100 (build-system r-build-system)
7101 (home-page "https://bioconductor.org/packages/BiocInstaller")
7102 (synopsis "Install Bioconductor packages")
7103 (description "This package is used to install and update R packages from
7104 Bioconductor, CRAN, and Github.")
7105 (license license:artistic2.0)))
7107 (define-public r-biocviews
7109 (name "r-biocviews")
7113 (uri (bioconductor-uri "biocViews" version))
7116 "0rc1n89n04ylvy9gvsgvizcs77bh70jg1nkjjsjs7rqbr3zzdysz"))))
7118 `((upstream-name . "biocViews")))
7119 (build-system r-build-system)
7121 `(("r-biobase" ,r-biobase)
7122 ("r-graph" ,r-graph)
7124 ("r-rcurl" ,r-rcurl)
7126 ("r-runit" ,r-runit)))
7127 (home-page "https://bioconductor.org/packages/biocViews")
7128 (synopsis "Bioconductor package categorization helper")
7129 (description "The purpose of biocViews is to create HTML pages that
7130 categorize packages in a Bioconductor package repository according to keywords,
7131 also known as views, in a controlled vocabulary.")
7132 (license license:artistic2.0)))
7134 (define-public r-bookdown
7140 (uri (cran-uri "bookdown" version))
7143 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
7144 (build-system r-build-system)
7146 `(("r-htmltools" ,r-htmltools)
7147 ("r-knitr" ,r-knitr)
7148 ("r-rmarkdown" ,r-rmarkdown)
7149 ("r-tinytex" ,r-tinytex)
7151 ("r-xfun" ,r-xfun)))
7152 (home-page "https://github.com/rstudio/bookdown")
7153 (synopsis "Authoring books and technical documents with R markdown")
7154 (description "This package provides output formats and utilities for
7155 authoring books and technical documents with R Markdown.")
7156 (license license:gpl3)))
7158 (define-public r-biocstyle
7160 (name "r-biocstyle")
7164 (uri (bioconductor-uri "BiocStyle" version))
7167 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7169 `((upstream-name . "BiocStyle")))
7170 (build-system r-build-system)
7172 `(("r-biocmanager" ,r-biocmanager)
7173 ("r-bookdown" ,r-bookdown)
7174 ("r-knitr" ,r-knitr)
7175 ("r-rmarkdown" ,r-rmarkdown)
7176 ("r-yaml" ,r-yaml)))
7177 (home-page "https://bioconductor.org/packages/BiocStyle")
7178 (synopsis "Bioconductor formatting styles")
7179 (description "This package provides standard formatting styles for
7180 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7182 (license license:artistic2.0)))
7184 (define-public r-bioccheck
7186 (name "r-bioccheck")
7190 (uri (bioconductor-uri "BiocCheck" version))
7193 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7195 `((upstream-name . "BiocCheck")))
7196 (build-system r-build-system)
7199 (modify-phases %standard-phases
7200 ;; This package can be used by calling BiocCheck(<package>) from
7201 ;; within R, or by running R CMD BiocCheck <package>. This phase
7202 ;; makes sure the latter works. For this to work, the BiocCheck
7203 ;; script must be somewhere on the PATH (not the R bin directory).
7204 (add-after 'install 'install-bioccheck-subcommand
7205 (lambda* (#:key outputs #:allow-other-keys)
7206 (let* ((out (assoc-ref outputs "out"))
7207 (dest-dir (string-append out "/bin"))
7209 (string-append out "/site-library/BiocCheck/script/")))
7211 (symlink (string-append script-dir "/checkBadDeps.R")
7212 (string-append dest-dir "/checkBadDeps.R"))
7213 (symlink (string-append script-dir "/BiocCheck")
7214 (string-append dest-dir "/BiocCheck")))
7217 `(("r-codetools" ,r-codetools)
7218 ("r-graph" ,r-graph)
7220 ("r-knitr" ,r-knitr)
7221 ("r-optparse" ,r-optparse)
7222 ("r-biocmanager" ,r-biocmanager)
7223 ("r-biocviews" ,r-biocviews)
7224 ("r-stringdist" ,r-stringdist)))
7225 (home-page "https://bioconductor.org/packages/BiocCheck")
7226 (synopsis "Executes Bioconductor-specific package checks")
7227 (description "This package contains tools to perform additional quality
7228 checks on R packages that are to be submitted to the Bioconductor repository.")
7229 (license license:artistic2.0)))
7231 (define-public r-optparse
7238 (uri (cran-uri "optparse" version))
7241 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7242 (build-system r-build-system)
7244 `(("r-getopt" ,r-getopt)))
7246 "https://github.com/trevorld/optparse")
7247 (synopsis "Command line option parser")
7249 "This package provides a command line parser inspired by Python's
7250 @code{optparse} library to be used with Rscript to write shebang scripts
7251 that accept short and long options.")
7252 (license license:gpl2+)))
7254 (define-public r-dnacopy
7260 (uri (bioconductor-uri "DNAcopy" version))
7263 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7265 `((upstream-name . "DNAcopy")))
7266 (build-system r-build-system)
7268 `(("gfortran" ,gfortran)))
7269 (home-page "https://bioconductor.org/packages/DNAcopy")
7270 (synopsis "Implementation of a circular binary segmentation algorithm")
7271 (description "This package implements the circular binary segmentation (CBS)
7272 algorithm to segment DNA copy number data and identify genomic regions with
7273 abnormal copy number.")
7274 (license license:gpl2+)))
7276 (define-public r-s4vectors
7278 (name "r-s4vectors")
7282 (uri (bioconductor-uri "S4Vectors" version))
7285 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7287 `((upstream-name . "S4Vectors")))
7288 (build-system r-build-system)
7290 `(("r-biocgenerics" ,r-biocgenerics)))
7291 (home-page "https://bioconductor.org/packages/S4Vectors")
7292 (synopsis "S4 implementation of vectors and lists")
7294 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7295 classes and a set of generic functions that extend the semantic of ordinary
7296 vectors and lists in R. Package developers can easily implement vector-like
7297 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7298 In addition, a few low-level concrete subclasses of general interest (e.g.
7299 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7300 S4Vectors package itself.")
7301 (license license:artistic2.0)))
7303 (define-public r-seqinr
7310 (uri (cran-uri "seqinr" version))
7313 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7314 (build-system r-build-system)
7316 `(("r-ade4" ,r-ade4)
7317 ("r-segmented" ,r-segmented)))
7320 (home-page "http://seqinr.r-forge.r-project.org/")
7321 (synopsis "Biological sequences retrieval and analysis")
7323 "This package provides tools for exploratory data analysis and data
7324 visualization of biological sequence (DNA and protein) data. It also includes
7325 utilities for sequence data management under the ACNUC system.")
7326 (license license:gpl2+)))
7328 (define-public r-iranges
7334 (uri (bioconductor-uri "IRanges" version))
7337 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7339 `((upstream-name . "IRanges")))
7340 (build-system r-build-system)
7342 `(("r-biocgenerics" ,r-biocgenerics)
7343 ("r-s4vectors" ,r-s4vectors)))
7344 (home-page "https://bioconductor.org/packages/IRanges")
7345 (synopsis "Infrastructure for manipulating intervals on sequences")
7347 "This package provides efficient low-level and highly reusable S4 classes
7348 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7349 generally, data that can be organized sequentially (formally defined as
7350 @code{Vector} objects), as well as views on these @code{Vector} objects.
7351 Efficient list-like classes are also provided for storing big collections of
7352 instances of the basic classes. All classes in the package use consistent
7353 naming and share the same rich and consistent \"Vector API\" as much as
7355 (license license:artistic2.0)))
7357 (define-public r-genomeinfodbdata
7359 (name "r-genomeinfodbdata")
7363 ;; We cannot use bioconductor-uri here because this tarball is
7364 ;; located under "data/annotation/" instead of "bioc/".
7365 (uri (string-append "https://bioconductor.org/packages/release/"
7366 "data/annotation/src/contrib/GenomeInfoDbData_"
7370 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7372 `((upstream-name . "GenomeInfoDbData")))
7373 (build-system r-build-system)
7374 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7375 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7376 (description "This package contains data for mapping between NCBI taxonomy
7377 ID and species. It is used by functions in the GenomeInfoDb package.")
7378 (license license:artistic2.0)))
7380 (define-public r-genomeinfodb
7382 (name "r-genomeinfodb")
7386 (uri (bioconductor-uri "GenomeInfoDb" version))
7389 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7391 `((upstream-name . "GenomeInfoDb")))
7392 (build-system r-build-system)
7394 `(("r-biocgenerics" ,r-biocgenerics)
7395 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7396 ("r-iranges" ,r-iranges)
7397 ("r-rcurl" ,r-rcurl)
7398 ("r-s4vectors" ,r-s4vectors)))
7399 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7400 (synopsis "Utilities for manipulating chromosome identifiers")
7402 "This package contains data and functions that define and allow
7403 translation between different chromosome sequence naming conventions (e.g.,
7404 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7405 names in their natural, rather than lexicographic, order.")
7406 (license license:artistic2.0)))
7408 (define-public r-edger
7414 (uri (bioconductor-uri "edgeR" version))
7417 "0ihihgzrgb4q3xc8xkzp1v76ndgihrj4gas00fa25vggfs1v6hvg"))))
7418 (properties `((upstream-name . "edgeR")))
7419 (build-system r-build-system)
7421 `(("r-limma" ,r-limma)
7422 ("r-locfit" ,r-locfit)
7424 ("r-statmod" ,r-statmod))) ;for estimateDisp
7425 (home-page "http://bioinf.wehi.edu.au/edgeR")
7426 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7427 (description "This package can do differential expression analysis of
7428 RNA-seq expression profiles with biological replication. It implements a range
7429 of statistical methodology based on the negative binomial distributions,
7430 including empirical Bayes estimation, exact tests, generalized linear models
7431 and quasi-likelihood tests. It be applied to differential signal analysis of
7432 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7434 (license license:gpl2+)))
7436 (define-public r-variantannotation
7438 (name "r-variantannotation")
7442 (uri (bioconductor-uri "VariantAnnotation" version))
7445 "0gvah258mkaafhbna81zwknx8qr3lidbcx5qvwk39q3yswr9mi49"))))
7447 `((upstream-name . "VariantAnnotation")))
7451 `(("r-annotationdbi" ,r-annotationdbi)
7452 ("r-biobase" ,r-biobase)
7453 ("r-biocgenerics" ,r-biocgenerics)
7454 ("r-biostrings" ,r-biostrings)
7455 ("r-bsgenome" ,r-bsgenome)
7457 ("r-genomeinfodb" ,r-genomeinfodb)
7458 ("r-genomicfeatures" ,r-genomicfeatures)
7459 ("r-genomicranges" ,r-genomicranges)
7460 ("r-iranges" ,r-iranges)
7461 ("r-summarizedexperiment" ,r-summarizedexperiment)
7462 ("r-rsamtools" ,r-rsamtools)
7463 ("r-rtracklayer" ,r-rtracklayer)
7464 ("r-s4vectors" ,r-s4vectors)
7465 ("r-xvector" ,r-xvector)
7466 ("r-zlibbioc" ,r-zlibbioc)))
7467 (build-system r-build-system)
7468 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7469 (synopsis "Package for annotation of genetic variants")
7470 (description "This R package can annotate variants, compute amino acid
7471 coding changes and predict coding outcomes.")
7472 (license license:artistic2.0)))
7474 (define-public r-limma
7480 (uri (bioconductor-uri "limma" version))
7483 "1wkh362rmn24q7bkinb6nx62a31wl3r3myg5l326gx65wpwdnx97"))))
7484 (build-system r-build-system)
7485 (home-page "http://bioinf.wehi.edu.au/limma")
7486 (synopsis "Package for linear models for microarray and RNA-seq data")
7487 (description "This package can be used for the analysis of gene expression
7488 studies, especially the use of linear models for analysing designed experiments
7489 and the assessment of differential expression. The analysis methods apply to
7490 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7491 (license license:gpl2+)))
7493 (define-public r-xvector
7499 (uri (bioconductor-uri "XVector" version))
7502 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7504 `((upstream-name . "XVector")))
7505 (build-system r-build-system)
7508 (modify-phases %standard-phases
7509 (add-after 'unpack 'use-system-zlib
7511 (substitute* "DESCRIPTION"
7512 (("zlibbioc, ") ""))
7513 (substitute* "NAMESPACE"
7514 (("import\\(zlibbioc\\)") ""))
7519 `(("r-biocgenerics" ,r-biocgenerics)
7520 ("r-iranges" ,r-iranges)
7521 ("r-s4vectors" ,r-s4vectors)))
7522 (home-page "https://bioconductor.org/packages/XVector")
7523 (synopsis "Representation and manpulation of external sequences")
7525 "This package provides memory efficient S4 classes for storing sequences
7526 \"externally\" (behind an R external pointer, or on disk).")
7527 (license license:artistic2.0)))
7529 (define-public r-genomicranges
7531 (name "r-genomicranges")
7535 (uri (bioconductor-uri "GenomicRanges" version))
7538 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7540 `((upstream-name . "GenomicRanges")))
7541 (build-system r-build-system)
7543 `(("r-biocgenerics" ,r-biocgenerics)
7544 ("r-genomeinfodb" ,r-genomeinfodb)
7545 ("r-iranges" ,r-iranges)
7546 ("r-s4vectors" ,r-s4vectors)
7547 ("r-xvector" ,r-xvector)))
7548 (home-page "https://bioconductor.org/packages/GenomicRanges")
7549 (synopsis "Representation and manipulation of genomic intervals")
7551 "This package provides tools to efficiently represent and manipulate
7552 genomic annotations and alignments is playing a central role when it comes to
7553 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7554 GenomicRanges package defines general purpose containers for storing and
7555 manipulating genomic intervals and variables defined along a genome.")
7556 (license license:artistic2.0)))
7558 (define-public r-biobase
7564 (uri (bioconductor-uri "Biobase" version))
7567 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7569 `((upstream-name . "Biobase")))
7570 (build-system r-build-system)
7572 `(("r-biocgenerics" ,r-biocgenerics)))
7573 (home-page "https://bioconductor.org/packages/Biobase")
7574 (synopsis "Base functions for Bioconductor")
7576 "This package provides functions that are needed by many other packages
7577 on Bioconductor or which replace R functions.")
7578 (license license:artistic2.0)))
7580 (define-public r-annotationdbi
7582 (name "r-annotationdbi")
7586 (uri (bioconductor-uri "AnnotationDbi" version))
7589 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7591 `((upstream-name . "AnnotationDbi")))
7592 (build-system r-build-system)
7594 `(("r-biobase" ,r-biobase)
7595 ("r-biocgenerics" ,r-biocgenerics)
7597 ("r-iranges" ,r-iranges)
7598 ("r-rsqlite" ,r-rsqlite)
7599 ("r-s4vectors" ,r-s4vectors)))
7600 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7601 (synopsis "Annotation database interface")
7603 "This package provides user interface and database connection code for
7604 annotation data packages using SQLite data storage.")
7605 (license license:artistic2.0)))
7607 (define-public r-biomart
7613 (uri (bioconductor-uri "biomaRt" version))
7616 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7618 `((upstream-name . "biomaRt")))
7619 (build-system r-build-system)
7621 `(("r-annotationdbi" ,r-annotationdbi)
7623 ("r-progress" ,r-progress)
7624 ("r-rcurl" ,r-rcurl)
7625 ("r-stringr" ,r-stringr)
7627 (home-page "https://bioconductor.org/packages/biomaRt")
7628 (synopsis "Interface to BioMart databases")
7630 "biomaRt provides an interface to a growing collection of databases
7631 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7632 package enables retrieval of large amounts of data in a uniform way without
7633 the need to know the underlying database schemas or write complex SQL queries.
7634 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7635 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7636 users direct access to a diverse set of data and enable a wide range of
7637 powerful online queries from gene annotation to database mining.")
7638 (license license:artistic2.0)))
7640 (define-public r-biocparallel
7642 (name "r-biocparallel")
7646 (uri (bioconductor-uri "BiocParallel" version))
7649 "0g16cy0vjapqkb188z63r1b6y96m9g8vx0a3v2qavzxc177k0cja"))))
7651 `((upstream-name . "BiocParallel")))
7652 (build-system r-build-system)
7654 `(("r-futile-logger" ,r-futile-logger)
7657 (home-page "https://bioconductor.org/packages/BiocParallel")
7658 (synopsis "Bioconductor facilities for parallel evaluation")
7660 "This package provides modified versions and novel implementation of
7661 functions for parallel evaluation, tailored to use with Bioconductor
7663 (license (list license:gpl2+ license:gpl3+))))
7665 (define-public r-biostrings
7667 (name "r-biostrings")
7671 (uri (bioconductor-uri "Biostrings" version))
7674 "1qyv1ps7vy6gy78pm2rcikg0bgf1mv7falahjp3pkwqq1272hrl8"))))
7676 `((upstream-name . "Biostrings")))
7677 (build-system r-build-system)
7679 `(("r-biocgenerics" ,r-biocgenerics)
7680 ("r-iranges" ,r-iranges)
7681 ("r-s4vectors" ,r-s4vectors)
7682 ("r-xvector" ,r-xvector)))
7683 (home-page "https://bioconductor.org/packages/Biostrings")
7684 (synopsis "String objects and algorithms for biological sequences")
7686 "This package provides memory efficient string containers, string
7687 matching algorithms, and other utilities, for fast manipulation of large
7688 biological sequences or sets of sequences.")
7689 (license license:artistic2.0)))
7691 (define-public r-rsamtools
7693 (name "r-rsamtools")
7697 (uri (bioconductor-uri "Rsamtools" version))
7700 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7702 `((upstream-name . "Rsamtools")))
7703 (build-system r-build-system)
7706 (modify-phases %standard-phases
7707 (add-after 'unpack 'use-system-zlib
7709 (substitute* "DESCRIPTION"
7710 (("zlibbioc, ") ""))
7711 (substitute* "NAMESPACE"
7712 (("import\\(zlibbioc\\)") ""))
7717 `(("r-biocgenerics" ,r-biocgenerics)
7718 ("r-biocparallel" ,r-biocparallel)
7719 ("r-biostrings" ,r-biostrings)
7720 ("r-bitops" ,r-bitops)
7721 ("r-genomeinfodb" ,r-genomeinfodb)
7722 ("r-genomicranges" ,r-genomicranges)
7723 ("r-iranges" ,r-iranges)
7724 ("r-s4vectors" ,r-s4vectors)
7725 ("r-xvector" ,r-xvector)))
7726 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7727 (synopsis "Interface to samtools, bcftools, and tabix")
7729 "This package provides an interface to the 'samtools', 'bcftools', and
7730 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7731 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7733 (license license:expat)))
7735 (define-public r-delayedarray
7737 (name "r-delayedarray")
7741 (uri (bioconductor-uri "DelayedArray" version))
7744 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7746 `((upstream-name . "DelayedArray")))
7747 (build-system r-build-system)
7749 `(("r-biocgenerics" ,r-biocgenerics)
7750 ("r-biocparallel" ,r-biocparallel)
7751 ("r-s4vectors" ,r-s4vectors)
7752 ("r-iranges" ,r-iranges)
7753 ("r-matrixstats" ,r-matrixstats)))
7754 (home-page "https://bioconductor.org/packages/DelayedArray")
7755 (synopsis "Delayed operations on array-like objects")
7757 "Wrapping an array-like object (typically an on-disk object) in a
7758 @code{DelayedArray} object allows one to perform common array operations on it
7759 without loading the object in memory. In order to reduce memory usage and
7760 optimize performance, operations on the object are either delayed or executed
7761 using a block processing mechanism. Note that this also works on in-memory
7762 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7763 @code{Matrix} objects, and ordinary arrays and data frames.")
7764 (license license:artistic2.0)))
7766 (define-public r-summarizedexperiment
7768 (name "r-summarizedexperiment")
7772 (uri (bioconductor-uri "SummarizedExperiment" version))
7775 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7777 `((upstream-name . "SummarizedExperiment")))
7778 (build-system r-build-system)
7780 `(("r-biobase" ,r-biobase)
7781 ("r-biocgenerics" ,r-biocgenerics)
7782 ("r-delayedarray" ,r-delayedarray)
7783 ("r-genomeinfodb" ,r-genomeinfodb)
7784 ("r-genomicranges" ,r-genomicranges)
7785 ("r-iranges" ,r-iranges)
7786 ("r-matrix" ,r-matrix)
7787 ("r-s4vectors" ,r-s4vectors)))
7788 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7789 (synopsis "Container for representing genomic ranges by sample")
7791 "The SummarizedExperiment container contains one or more assays, each
7792 represented by a matrix-like object of numeric or other mode. The rows
7793 typically represent genomic ranges of interest and the columns represent
7795 (license license:artistic2.0)))
7797 (define-public r-genomicalignments
7799 (name "r-genomicalignments")
7803 (uri (bioconductor-uri "GenomicAlignments" version))
7806 "0a3zhwripfw2508fvgx3wzqa8nq8vnslg97a911znpwvxh53jl24"))))
7808 `((upstream-name . "GenomicAlignments")))
7809 (build-system r-build-system)
7811 `(("r-biocgenerics" ,r-biocgenerics)
7812 ("r-biocparallel" ,r-biocparallel)
7813 ("r-biostrings" ,r-biostrings)
7814 ("r-genomeinfodb" ,r-genomeinfodb)
7815 ("r-genomicranges" ,r-genomicranges)
7816 ("r-iranges" ,r-iranges)
7817 ("r-rsamtools" ,r-rsamtools)
7818 ("r-s4vectors" ,r-s4vectors)
7819 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7820 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7821 (synopsis "Representation and manipulation of short genomic alignments")
7823 "This package provides efficient containers for storing and manipulating
7824 short genomic alignments (typically obtained by aligning short reads to a
7825 reference genome). This includes read counting, computing the coverage,
7826 junction detection, and working with the nucleotide content of the
7828 (license license:artistic2.0)))
7830 (define-public r-rtracklayer
7832 (name "r-rtracklayer")
7836 (uri (bioconductor-uri "rtracklayer" version))
7839 "0a4mhd926w9slkfil5xgngjsfdj024a4w57w2bm3d4r0pj8y5da7"))))
7840 (build-system r-build-system)
7843 (modify-phases %standard-phases
7844 (add-after 'unpack 'use-system-zlib
7846 (substitute* "DESCRIPTION"
7847 ((" zlibbioc,") ""))
7848 (substitute* "NAMESPACE"
7849 (("import\\(zlibbioc\\)") ""))
7852 `(("pkg-config" ,pkg-config)))
7856 `(("r-biocgenerics" ,r-biocgenerics)
7857 ("r-biostrings" ,r-biostrings)
7858 ("r-genomeinfodb" ,r-genomeinfodb)
7859 ("r-genomicalignments" ,r-genomicalignments)
7860 ("r-genomicranges" ,r-genomicranges)
7861 ("r-iranges" ,r-iranges)
7862 ("r-rcurl" ,r-rcurl)
7863 ("r-rsamtools" ,r-rsamtools)
7864 ("r-s4vectors" ,r-s4vectors)
7866 ("r-xvector" ,r-xvector)))
7867 (home-page "https://bioconductor.org/packages/rtracklayer")
7868 (synopsis "R interface to genome browsers and their annotation tracks")
7870 "rtracklayer is an extensible framework for interacting with multiple
7871 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7872 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7873 built-in). The user may export/import tracks to/from the supported browsers,
7874 as well as query and modify the browser state, such as the current viewport.")
7875 (license license:artistic2.0)))
7877 (define-public r-genomicfeatures
7879 (name "r-genomicfeatures")
7883 (uri (bioconductor-uri "GenomicFeatures" version))
7886 "0slq6hv5bmc3bgrl824jzmr6db3fvaj6b7ihwmdn76pgqqbq2fq6"))))
7888 `((upstream-name . "GenomicFeatures")))
7889 (build-system r-build-system)
7891 `(("r-annotationdbi" ,r-annotationdbi)
7892 ("r-biobase" ,r-biobase)
7893 ("r-biocgenerics" ,r-biocgenerics)
7894 ("r-biomart" ,r-biomart)
7895 ("r-biostrings" ,r-biostrings)
7897 ("r-genomeinfodb" ,r-genomeinfodb)
7898 ("r-genomicranges" ,r-genomicranges)
7899 ("r-iranges" ,r-iranges)
7900 ("r-rcurl" ,r-rcurl)
7901 ("r-rsqlite" ,r-rsqlite)
7902 ("r-rtracklayer" ,r-rtracklayer)
7903 ("r-s4vectors" ,r-s4vectors)
7904 ("r-xvector" ,r-xvector)))
7905 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7906 (synopsis "Tools for working with transcript centric annotations")
7908 "This package provides a set of tools and methods for making and
7909 manipulating transcript centric annotations. With these tools the user can
7910 easily download the genomic locations of the transcripts, exons and cds of a
7911 given organism, from either the UCSC Genome Browser or a BioMart
7912 database (more sources will be supported in the future). This information is
7913 then stored in a local database that keeps track of the relationship between
7914 transcripts, exons, cds and genes. Flexible methods are provided for
7915 extracting the desired features in a convenient format.")
7916 (license license:artistic2.0)))
7918 (define-public r-go-db
7924 (uri (string-append "https://www.bioconductor.org/packages/"
7925 "release/data/annotation/src/contrib/GO.db_"
7929 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7931 `((upstream-name . "GO.db")))
7932 (build-system r-build-system)
7934 `(("r-annotationdbi" ,r-annotationdbi)))
7935 (home-page "https://bioconductor.org/packages/GO.db")
7936 (synopsis "Annotation maps describing the entire Gene Ontology")
7938 "The purpose of this GO.db annotation package is to provide detailed
7939 information about the latest version of the Gene Ontologies.")
7940 (license license:artistic2.0)))
7942 (define-public r-topgo
7948 (uri (bioconductor-uri "topGO" version))
7951 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7953 `((upstream-name . "topGO")))
7954 (build-system r-build-system)
7956 `(("r-annotationdbi" ,r-annotationdbi)
7958 ("r-biobase" ,r-biobase)
7959 ("r-biocgenerics" ,r-biocgenerics)
7960 ("r-go-db" ,r-go-db)
7961 ("r-graph" ,r-graph)
7962 ("r-lattice" ,r-lattice)
7963 ("r-matrixstats" ,r-matrixstats)
7964 ("r-sparsem" ,r-sparsem)))
7965 (home-page "https://bioconductor.org/packages/topGO")
7966 (synopsis "Enrichment analysis for gene ontology")
7968 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7969 terms while accounting for the topology of the GO graph. Different test
7970 statistics and different methods for eliminating local similarities and
7971 dependencies between GO terms can be implemented and applied.")
7972 ;; Any version of the LGPL applies.
7973 (license license:lgpl2.1+)))
7975 (define-public r-bsgenome
7981 (uri (bioconductor-uri "BSgenome" version))
7984 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7986 `((upstream-name . "BSgenome")))
7987 (build-system r-build-system)
7989 `(("r-biocgenerics" ,r-biocgenerics)
7990 ("r-biostrings" ,r-biostrings)
7991 ("r-genomeinfodb" ,r-genomeinfodb)
7992 ("r-genomicranges" ,r-genomicranges)
7993 ("r-iranges" ,r-iranges)
7994 ("r-rsamtools" ,r-rsamtools)
7995 ("r-rtracklayer" ,r-rtracklayer)
7996 ("r-s4vectors" ,r-s4vectors)
7997 ("r-xvector" ,r-xvector)))
7998 (home-page "https://bioconductor.org/packages/BSgenome")
7999 (synopsis "Infrastructure for Biostrings-based genome data packages")
8001 "This package provides infrastructure shared by all Biostrings-based
8002 genome data packages and support for efficient SNP representation.")
8003 (license license:artistic2.0)))
8005 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
8007 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
8011 ;; We cannot use bioconductor-uri here because this tarball is
8012 ;; located under "data/annotation/" instead of "bioc/".
8013 (uri (string-append "https://www.bioconductor.org/packages/"
8014 "release/data/annotation/src/contrib/"
8015 "BSgenome.Hsapiens.1000genomes.hs37d5_"
8019 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
8021 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
8022 (build-system r-build-system)
8023 ;; As this package provides little more than a very large data file it
8024 ;; doesn't make sense to build substitutes.
8025 (arguments `(#:substitutable? #f))
8027 `(("r-bsgenome" ,r-bsgenome)))
8029 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
8030 (synopsis "Full genome sequences for Homo sapiens")
8032 "This package provides full genome sequences for Homo sapiens from
8033 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
8034 (license license:artistic2.0)))
8036 (define-public r-impute
8042 (uri (bioconductor-uri "impute" version))
8045 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8047 `(("gfortran" ,gfortran)))
8048 (build-system r-build-system)
8049 (home-page "https://bioconductor.org/packages/impute")
8050 (synopsis "Imputation for microarray data")
8052 "This package provides a function to impute missing gene expression
8053 microarray data, using nearest neighbor averaging.")
8054 (license license:gpl2+)))
8056 (define-public r-seqpattern
8058 (name "r-seqpattern")
8062 (uri (bioconductor-uri "seqPattern" version))
8065 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8067 `((upstream-name . "seqPattern")))
8068 (build-system r-build-system)
8070 `(("r-biostrings" ,r-biostrings)
8071 ("r-genomicranges" ,r-genomicranges)
8072 ("r-iranges" ,r-iranges)
8073 ("r-kernsmooth" ,r-kernsmooth)
8074 ("r-plotrix" ,r-plotrix)))
8075 (home-page "https://bioconductor.org/packages/seqPattern")
8076 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8078 "This package provides tools to visualize oligonucleotide patterns and
8079 sequence motif occurrences across a large set of sequences centred at a common
8080 reference point and sorted by a user defined feature.")
8081 (license license:gpl3+)))
8083 (define-public r-genomation
8085 (name "r-genomation")
8089 (uri (bioconductor-uri "genomation" version))
8092 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8093 (build-system r-build-system)
8095 `(("r-biostrings" ,r-biostrings)
8096 ("r-bsgenome" ,r-bsgenome)
8097 ("r-data-table" ,r-data-table)
8098 ("r-genomeinfodb" ,r-genomeinfodb)
8099 ("r-genomicalignments" ,r-genomicalignments)
8100 ("r-genomicranges" ,r-genomicranges)
8101 ("r-ggplot2" ,r-ggplot2)
8102 ("r-gridbase" ,r-gridbase)
8103 ("r-impute" ,r-impute)
8104 ("r-iranges" ,r-iranges)
8105 ("r-matrixstats" ,r-matrixstats)
8106 ("r-plotrix" ,r-plotrix)
8109 ("r-readr" ,r-readr)
8110 ("r-reshape2" ,r-reshape2)
8111 ("r-rsamtools" ,r-rsamtools)
8112 ("r-rtracklayer" ,r-rtracklayer)
8113 ("r-runit" ,r-runit)
8114 ("r-s4vectors" ,r-s4vectors)
8115 ("r-seqpattern" ,r-seqpattern)))
8116 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8117 (synopsis "Summary, annotation and visualization of genomic data")
8119 "This package provides a package for summary and annotation of genomic
8120 intervals. Users can visualize and quantify genomic intervals over
8121 pre-defined functional regions, such as promoters, exons, introns, etc. The
8122 genomic intervals represent regions with a defined chromosome position, which
8123 may be associated with a score, such as aligned reads from HT-seq experiments,
8124 TF binding sites, methylation scores, etc. The package can use any tabular
8125 genomic feature data as long as it has minimal information on the locations of
8126 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8127 (license license:artistic2.0)))
8129 (define-public r-genomationdata
8131 (name "r-genomationdata")
8135 ;; We cannot use bioconductor-uri here because this tarball is
8136 ;; located under "data/annotation/" instead of "bioc/".
8137 (uri (string-append "https://bioconductor.org/packages/"
8138 "release/data/experiment/src/contrib/"
8139 "genomationData_" version ".tar.gz"))
8142 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8143 (build-system r-build-system)
8144 ;; As this package provides little more than large data files, it doesn't
8145 ;; make sense to build substitutes.
8146 (arguments `(#:substitutable? #f))
8148 `(("r-knitr" ,r-knitr)))
8149 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8150 (synopsis "Experimental data for use with the genomation package")
8152 "This package contains experimental genetic data for use with the
8153 genomation package. Included are Chip Seq, Methylation and Cage data,
8154 downloaded from Encode.")
8155 (license license:gpl3+)))
8157 (define-public r-org-hs-eg-db
8159 (name "r-org-hs-eg-db")
8163 ;; We cannot use bioconductor-uri here because this tarball is
8164 ;; located under "data/annotation/" instead of "bioc/".
8165 (uri (string-append "https://www.bioconductor.org/packages/"
8166 "release/data/annotation/src/contrib/"
8167 "org.Hs.eg.db_" version ".tar.gz"))
8170 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
8172 `((upstream-name . "org.Hs.eg.db")))
8173 (build-system r-build-system)
8175 `(("r-annotationdbi" ,r-annotationdbi)))
8176 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8177 (synopsis "Genome wide annotation for Human")
8179 "This package contains genome-wide annotations for Human, primarily based
8180 on mapping using Entrez Gene identifiers.")
8181 (license license:artistic2.0)))
8183 (define-public r-org-ce-eg-db
8185 (name "r-org-ce-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.Ce.eg.db_" version ".tar.gz"))
8196 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8198 `((upstream-name . "org.Ce.eg.db")))
8199 (build-system r-build-system)
8201 `(("r-annotationdbi" ,r-annotationdbi)))
8202 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8203 (synopsis "Genome wide annotation for Worm")
8205 "This package provides mappings from Entrez gene identifiers to various
8206 annotations for the genome of the model worm Caenorhabditis elegans.")
8207 (license license:artistic2.0)))
8209 (define-public r-org-dm-eg-db
8211 (name "r-org-dm-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.Dm.eg.db_" version ".tar.gz"))
8222 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8224 `((upstream-name . "org.Dm.eg.db")))
8225 (build-system r-build-system)
8227 `(("r-annotationdbi" ,r-annotationdbi)))
8228 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8229 (synopsis "Genome wide annotation for Fly")
8231 "This package provides mappings from Entrez gene identifiers to various
8232 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8233 (license license:artistic2.0)))
8235 (define-public r-org-mm-eg-db
8237 (name "r-org-mm-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.Mm.eg.db_" version ".tar.gz"))
8248 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8250 `((upstream-name . "org.Mm.eg.db")))
8251 (build-system r-build-system)
8253 `(("r-annotationdbi" ,r-annotationdbi)))
8254 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8255 (synopsis "Genome wide annotation for Mouse")
8257 "This package provides mappings from Entrez gene identifiers to various
8258 annotations for the genome of the model mouse Mus musculus.")
8259 (license license:artistic2.0)))
8261 (define-public r-seqlogo
8268 (uri (bioconductor-uri "seqLogo" version))
8271 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8272 (properties `((upstream-name . "seqLogo")))
8273 (build-system r-build-system)
8274 (home-page "https://bioconductor.org/packages/seqLogo")
8275 (synopsis "Sequence logos for DNA sequence alignments")
8277 "seqLogo takes the position weight matrix of a DNA sequence motif and
8278 plots the corresponding sequence logo as introduced by Schneider and
8280 (license license:lgpl2.0+)))
8282 (define-public r-bsgenome-hsapiens-ucsc-hg19
8284 (name "r-bsgenome-hsapiens-ucsc-hg19")
8288 ;; We cannot use bioconductor-uri here because this tarball is
8289 ;; located under "data/annotation/" instead of "bioc/".
8290 (uri (string-append "https://www.bioconductor.org/packages/"
8291 "release/data/annotation/src/contrib/"
8292 "BSgenome.Hsapiens.UCSC.hg19_"
8296 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8298 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8299 (build-system r-build-system)
8300 ;; As this package provides little more than a very large data file it
8301 ;; doesn't make sense to build substitutes.
8302 (arguments `(#:substitutable? #f))
8304 `(("r-bsgenome" ,r-bsgenome)))
8306 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8307 (synopsis "Full genome sequences for Homo sapiens")
8309 "This package provides full genome sequences for Homo sapiens as provided
8310 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8311 (license license:artistic2.0)))
8313 (define-public r-bsgenome-mmusculus-ucsc-mm9
8315 (name "r-bsgenome-mmusculus-ucsc-mm9")
8319 ;; We cannot use bioconductor-uri here because this tarball is
8320 ;; located under "data/annotation/" instead of "bioc/".
8321 (uri (string-append "https://www.bioconductor.org/packages/"
8322 "release/data/annotation/src/contrib/"
8323 "BSgenome.Mmusculus.UCSC.mm9_"
8327 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8329 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8330 (build-system r-build-system)
8331 ;; As this package provides little more than a very large data file it
8332 ;; doesn't make sense to build substitutes.
8333 (arguments `(#:substitutable? #f))
8335 `(("r-bsgenome" ,r-bsgenome)))
8337 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8338 (synopsis "Full genome sequences for Mouse")
8340 "This package provides full genome sequences for Mus musculus (Mouse) as
8341 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8342 (license license:artistic2.0)))
8344 (define-public r-bsgenome-mmusculus-ucsc-mm10
8346 (name "r-bsgenome-mmusculus-ucsc-mm10")
8350 ;; We cannot use bioconductor-uri here because this tarball is
8351 ;; located under "data/annotation/" instead of "bioc/".
8352 (uri (string-append "https://www.bioconductor.org/packages/"
8353 "release/data/annotation/src/contrib/"
8354 "BSgenome.Mmusculus.UCSC.mm10_"
8358 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8360 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8361 (build-system r-build-system)
8362 ;; As this package provides little more than a very large data file it
8363 ;; doesn't make sense to build substitutes.
8364 (arguments `(#:substitutable? #f))
8366 `(("r-bsgenome" ,r-bsgenome)))
8368 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8369 (synopsis "Full genome sequences for Mouse")
8371 "This package provides full genome sequences for Mus
8372 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8373 in Biostrings objects.")
8374 (license license:artistic2.0)))
8376 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8378 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8382 ;; We cannot use bioconductor-uri here because this tarball is
8383 ;; located under "data/annotation/" instead of "bioc/".
8384 (uri (string-append "https://www.bioconductor.org/packages/"
8385 "release/data/annotation/src/contrib/"
8386 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8390 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8392 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8393 (build-system r-build-system)
8394 ;; As this package provides little more than a very large data file it
8395 ;; doesn't make sense to build substitutes.
8396 (arguments `(#:substitutable? #f))
8398 `(("r-bsgenome" ,r-bsgenome)
8399 ("r-genomicfeatures" ,r-genomicfeatures)
8400 ("r-annotationdbi" ,r-annotationdbi)))
8402 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8403 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8405 "This package loads a TxDb object, which is an R interface to
8406 prefabricated databases contained in this package. This package provides
8407 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8408 based on the knownGene track.")
8409 (license license:artistic2.0)))
8411 (define-public r-bsgenome-celegans-ucsc-ce6
8413 (name "r-bsgenome-celegans-ucsc-ce6")
8417 ;; We cannot use bioconductor-uri here because this tarball is
8418 ;; located under "data/annotation/" instead of "bioc/".
8419 (uri (string-append "https://www.bioconductor.org/packages/"
8420 "release/data/annotation/src/contrib/"
8421 "BSgenome.Celegans.UCSC.ce6_"
8425 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8427 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8428 (build-system r-build-system)
8429 ;; As this package provides little more than a very large data file it
8430 ;; doesn't make sense to build substitutes.
8431 (arguments `(#:substitutable? #f))
8433 `(("r-bsgenome" ,r-bsgenome)))
8435 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8436 (synopsis "Full genome sequences for Worm")
8438 "This package provides full genome sequences for Caenorhabditis
8439 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8441 (license license:artistic2.0)))
8443 (define-public r-bsgenome-celegans-ucsc-ce10
8445 (name "r-bsgenome-celegans-ucsc-ce10")
8449 ;; We cannot use bioconductor-uri here because this tarball is
8450 ;; located under "data/annotation/" instead of "bioc/".
8451 (uri (string-append "https://www.bioconductor.org/packages/"
8452 "release/data/annotation/src/contrib/"
8453 "BSgenome.Celegans.UCSC.ce10_"
8457 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8459 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8460 (build-system r-build-system)
8461 ;; As this package provides little more than a very large data file it
8462 ;; doesn't make sense to build substitutes.
8463 (arguments `(#:substitutable? #f))
8465 `(("r-bsgenome" ,r-bsgenome)))
8467 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8468 (synopsis "Full genome sequences for Worm")
8470 "This package provides full genome sequences for Caenorhabditis
8471 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8473 (license license:artistic2.0)))
8475 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8477 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8481 ;; We cannot use bioconductor-uri here because this tarball is
8482 ;; located under "data/annotation/" instead of "bioc/".
8483 (uri (string-append "https://www.bioconductor.org/packages/"
8484 "release/data/annotation/src/contrib/"
8485 "BSgenome.Dmelanogaster.UCSC.dm3_"
8489 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8491 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8492 (build-system r-build-system)
8493 ;; As this package provides little more than a very large data file it
8494 ;; doesn't make sense to build substitutes.
8495 (arguments `(#:substitutable? #f))
8497 `(("r-bsgenome" ,r-bsgenome)))
8499 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8500 (synopsis "Full genome sequences for Fly")
8502 "This package provides full genome sequences for Drosophila
8503 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8504 Biostrings objects.")
8505 (license license:artistic2.0)))
8507 (define-public r-motifrg
8514 (uri (bioconductor-uri "motifRG" version))
8517 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8518 (properties `((upstream-name . "motifRG")))
8519 (build-system r-build-system)
8521 `(("r-biostrings" ,r-biostrings)
8522 ("r-bsgenome" ,r-bsgenome)
8523 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8524 ("r-iranges" ,r-iranges)
8525 ("r-seqlogo" ,r-seqlogo)
8526 ("r-xvector" ,r-xvector)))
8527 (home-page "https://bioconductor.org/packages/motifRG")
8528 (synopsis "Discover motifs in high throughput sequencing data")
8530 "This package provides tools for discriminative motif discovery in high
8531 throughput genetic sequencing data sets using regression methods.")
8532 (license license:artistic2.0)))
8534 (define-public r-qtl
8541 (uri (string-append "mirror://cran/src/contrib/qtl_"
8545 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8546 (build-system r-build-system)
8547 (home-page "http://rqtl.org/")
8548 (synopsis "R package for analyzing QTL experiments in genetics")
8549 (description "R/qtl is an extension library for the R statistics
8550 system. It is used to analyze experimental crosses for identifying
8551 genes contributing to variation in quantitative traits (so-called
8552 quantitative trait loci, QTLs).
8554 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8555 identify genotyping errors, and to perform single-QTL and two-QTL,
8556 two-dimensional genome scans.")
8557 (license license:gpl3)))
8559 (define-public r-zlibbioc
8565 (uri (bioconductor-uri "zlibbioc" version))
8568 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8570 `((upstream-name . "zlibbioc")))
8571 (build-system r-build-system)
8572 (home-page "https://bioconductor.org/packages/zlibbioc")
8573 (synopsis "Provider for zlib-1.2.5 to R packages")
8574 (description "This package uses the source code of zlib-1.2.5 to create
8575 libraries for systems that do not have these available via other means.")
8576 (license license:artistic2.0)))
8578 (define-public r-r4rna
8585 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8589 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8590 (build-system r-build-system)
8592 `(("r-optparse" ,r-optparse)
8593 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8594 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8595 (synopsis "Analysis framework for RNA secondary structure")
8597 "The R4RNA package aims to be a general framework for the analysis of RNA
8598 secondary structure and comparative analysis in R.")
8599 (license license:gpl3+)))
8601 (define-public r-rhtslib
8608 (uri (bioconductor-uri "Rhtslib" version))
8611 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8612 (properties `((upstream-name . "Rhtslib")))
8613 (build-system r-build-system)
8615 `(("r-zlibbioc" ,r-zlibbioc)))
8619 `(("pkg-config" ,pkg-config)))
8620 (home-page "https://github.com/nhayden/Rhtslib")
8621 (synopsis "High-throughput sequencing library as an R package")
8623 "This package provides the HTSlib C library for high-throughput
8624 nucleotide sequence analysis. The package is primarily useful to developers
8625 of other R packages who wish to make use of HTSlib.")
8626 (license license:lgpl2.0+)))
8628 (define-public r-bamsignals
8630 (name "r-bamsignals")
8635 (uri (bioconductor-uri "bamsignals" version))
8638 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8639 (build-system r-build-system)
8641 `(("r-biocgenerics" ,r-biocgenerics)
8642 ("r-genomicranges" ,r-genomicranges)
8643 ("r-iranges" ,r-iranges)
8645 ("r-rhtslib" ,r-rhtslib)
8646 ("r-zlibbioc" ,r-zlibbioc)))
8649 (home-page "https://bioconductor.org/packages/bamsignals")
8650 (synopsis "Extract read count signals from bam files")
8652 "This package allows to efficiently obtain count vectors from indexed bam
8653 files. It counts the number of nucleotide sequence reads in given genomic
8654 ranges and it computes reads profiles and coverage profiles. It also handles
8656 (license license:gpl2+)))
8658 (define-public r-rcas
8664 (uri (bioconductor-uri "RCAS" version))
8667 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8668 (build-system r-build-system)
8670 `(("r-annotationdbi" ,r-annotationdbi)
8671 ("r-biocgenerics" ,r-biocgenerics)
8672 ("r-biomart" ,r-biomart)
8673 ("r-biostrings" ,r-biostrings)
8674 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8675 ("r-cowplot" ,r-cowplot)
8676 ("r-data-table" ,r-data-table)
8679 ("r-genomation" ,r-genomation)
8680 ("r-genomeinfodb" ,r-genomeinfodb)
8681 ("r-genomicfeatures" ,r-genomicfeatures)
8682 ("r-genomicranges" ,r-genomicranges)
8683 ("r-ggplot2" ,r-ggplot2)
8684 ("r-ggseqlogo" ,r-ggseqlogo)
8685 ("r-knitr" ,r-knitr)
8686 ("r-motifrg" ,r-motifrg)
8687 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8688 ("r-pbapply" ,r-pbapply)
8689 ("r-pheatmap" ,r-pheatmap)
8690 ("r-plotly" ,r-plotly)
8691 ("r-plotrix" ,r-plotrix)
8692 ("r-proxy" ,r-proxy)
8693 ("r-rsqlite" ,r-rsqlite)
8694 ("r-rtracklayer" ,r-rtracklayer)
8695 ("r-rmarkdown" ,r-rmarkdown)
8696 ("r-s4vectors" ,r-s4vectors)
8697 ("r-topgo" ,r-topgo)))
8698 (synopsis "RNA-centric annotation system")
8700 "RCAS aims to be a standalone RNA-centric annotation system that provides
8701 intuitive reports and publication-ready graphics. This package provides the R
8702 library implementing most of the pipeline's features.")
8703 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8704 (license license:artistic2.0)))
8706 (define-public rcas-web
8713 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8714 "releases/download/v" version
8715 "/rcas-web-" version ".tar.gz"))
8718 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8719 (build-system gnu-build-system)
8722 (modify-phases %standard-phases
8723 (add-after 'install 'wrap-executable
8724 (lambda* (#:key inputs outputs #:allow-other-keys)
8725 (let* ((out (assoc-ref outputs "out"))
8726 (json (assoc-ref inputs "guile-json"))
8727 (redis (assoc-ref inputs "guile-redis"))
8728 (path (string-append
8729 json "/share/guile/site/2.2:"
8730 redis "/share/guile/site/2.2")))
8731 (wrap-program (string-append out "/bin/rcas-web")
8732 `("GUILE_LOAD_PATH" ":" = (,path))
8733 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8734 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8737 `(("r-minimal" ,r-minimal)
8739 ("guile-next" ,guile-2.2)
8740 ("guile-json" ,guile-json)
8741 ("guile-redis" ,guile2.2-redis)))
8743 `(("pkg-config" ,pkg-config)))
8744 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8745 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8746 (description "This package provides a simple web interface for the
8747 @dfn{RNA-centric annotation system} (RCAS).")
8748 (license license:agpl3+)))
8750 (define-public r-mutationalpatterns
8752 (name "r-mutationalpatterns")
8757 (uri (bioconductor-uri "MutationalPatterns" version))
8760 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8761 (build-system r-build-system)
8763 `(("r-biocgenerics" ,r-biocgenerics)
8764 ("r-biostrings" ,r-biostrings)
8765 ;; These two packages are suggested packages
8766 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8767 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8768 ("r-genomicranges" ,r-genomicranges)
8769 ("r-genomeinfodb" ,r-genomeinfodb)
8770 ("r-ggplot2" ,r-ggplot2)
8771 ("r-iranges" ,r-iranges)
8774 ("r-pracma" ,r-pracma)
8775 ("r-reshape2" ,r-reshape2)
8776 ("r-cowplot" ,r-cowplot)
8777 ("r-ggdendro" ,r-ggdendro)
8778 ("r-s4vectors" ,r-s4vectors)
8779 ("r-summarizedexperiment" ,r-summarizedexperiment)
8780 ("r-variantannotation" ,r-variantannotation)))
8781 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8782 (synopsis "Extract and visualize mutational patterns in genomic data")
8783 (description "This package provides an extensive toolset for the
8784 characterization and visualization of a wide range of mutational patterns
8785 in SNV base substitution data.")
8786 (license license:expat)))
8788 (define-public r-wgcna
8795 (uri (cran-uri "WGCNA" version))
8798 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8799 (properties `((upstream-name . "WGCNA")))
8800 (build-system r-build-system)
8802 `(("r-annotationdbi" ,r-annotationdbi)
8803 ("r-doparallel" ,r-doparallel)
8804 ("r-dynamictreecut" ,r-dynamictreecut)
8805 ("r-fastcluster" ,r-fastcluster)
8806 ("r-foreach" ,r-foreach)
8807 ("r-go-db" ,r-go-db)
8808 ("r-hmisc" ,r-hmisc)
8809 ("r-impute" ,r-impute)
8811 ("r-robust" ,r-robust)
8812 ("r-survival" ,r-survival)
8813 ("r-matrixstats" ,r-matrixstats)
8814 ("r-preprocesscore" ,r-preprocesscore)))
8816 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8817 (synopsis "Weighted correlation network analysis")
8819 "This package provides functions necessary to perform Weighted
8820 Correlation Network Analysis on high-dimensional data. It includes functions
8821 for rudimentary data cleaning, construction and summarization of correlation
8822 networks, module identification and functions for relating both variables and
8823 modules to sample traits. It also includes a number of utility functions for
8824 data manipulation and visualization.")
8825 (license license:gpl2+)))
8827 (define-public r-chipkernels
8828 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8831 (name "r-chipkernels")
8832 (version (string-append "1.1-" revision "." (string-take commit 9)))
8837 (url "https://github.com/ManuSetty/ChIPKernels.git")
8839 (file-name (string-append name "-" version))
8842 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8843 (build-system r-build-system)
8845 `(("r-iranges" ,r-iranges)
8846 ("r-xvector" ,r-xvector)
8847 ("r-biostrings" ,r-biostrings)
8848 ("r-bsgenome" ,r-bsgenome)
8849 ("r-gtools" ,r-gtools)
8850 ("r-genomicranges" ,r-genomicranges)
8851 ("r-sfsmisc" ,r-sfsmisc)
8852 ("r-kernlab" ,r-kernlab)
8853 ("r-s4vectors" ,r-s4vectors)
8854 ("r-biocgenerics" ,r-biocgenerics)))
8855 (home-page "https://github.com/ManuSetty/ChIPKernels")
8856 (synopsis "Build string kernels for DNA Sequence analysis")
8857 (description "ChIPKernels is an R package for building different string
8858 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8859 must be built and this dictionary can be used for determining kernels for DNA
8861 (license license:gpl2+))))
8863 (define-public r-seqgl
8871 (url "https://github.com/ManuSetty/SeqGL.git")
8873 (file-name (git-file-name name version))
8876 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8877 (build-system r-build-system)
8879 `(("r-biostrings" ,r-biostrings)
8880 ("r-chipkernels" ,r-chipkernels)
8881 ("r-genomicranges" ,r-genomicranges)
8882 ("r-spams" ,r-spams)
8883 ("r-wgcna" ,r-wgcna)
8884 ("r-fastcluster" ,r-fastcluster)))
8885 (home-page "https://github.com/ManuSetty/SeqGL")
8886 (synopsis "Group lasso for Dnase/ChIP-seq data")
8887 (description "SeqGL is a group lasso based algorithm to extract
8888 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8889 This package presents a method which uses group lasso to discriminate between
8890 bound and non bound genomic regions to accurately identify transcription
8891 factors bound at the specific regions.")
8892 (license license:gpl2+)))
8894 (define-public r-gkmsvm
8901 (uri (cran-uri "gkmSVM" version))
8904 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8905 (properties `((upstream-name . "gkmSVM")))
8906 (build-system r-build-system)
8908 `(("r-biocgenerics" ,r-biocgenerics)
8909 ("r-biostrings" ,r-biostrings)
8910 ("r-genomeinfodb" ,r-genomeinfodb)
8911 ("r-genomicranges" ,r-genomicranges)
8912 ("r-iranges" ,r-iranges)
8913 ("r-kernlab" ,r-kernlab)
8916 ("r-rtracklayer" ,r-rtracklayer)
8917 ("r-s4vectors" ,r-s4vectors)
8918 ("r-seqinr" ,r-seqinr)))
8919 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8920 (synopsis "Gapped-kmer support vector machine")
8922 "This R package provides tools for training gapped-kmer SVM classifiers
8923 for DNA and protein sequences. This package supports several sequence
8924 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8925 (license license:gpl2+)))
8927 (define-public r-tximport
8933 (uri (bioconductor-uri "tximport" version))
8936 "0za2js8hqjgz8ria09cglynffj4w9vrzg85nmn1xgpvmc1xk813h"))))
8937 (build-system r-build-system)
8938 (home-page "https://bioconductor.org/packages/tximport")
8939 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8941 "This package provides tools to import transcript-level abundance,
8942 estimated counts and transcript lengths, and to summarize them into matrices
8943 for use with downstream gene-level analysis packages. Average transcript
8944 length, weighted by sample-specific transcript abundance estimates, is
8945 provided as a matrix which can be used as an offset for different expression
8946 of gene-level counts.")
8947 (license license:gpl2+)))
8949 (define-public r-rhdf5
8955 (uri (bioconductor-uri "rhdf5" version))
8958 "0xmpkfdsmgl79ffffj7cf9fx3zxki2rk0xn25k778kr3s0sbmhis"))))
8959 (build-system r-build-system)
8961 `(("r-rhdf5lib" ,r-rhdf5lib)))
8964 (home-page "https://bioconductor.org/packages/rhdf5")
8965 (synopsis "HDF5 interface to R")
8967 "This R/Bioconductor package provides an interface between HDF5 and R.
8968 HDF5's main features are the ability to store and access very large and/or
8969 complex datasets and a wide variety of metadata on mass storage (disk) through
8970 a completely portable file format. The rhdf5 package is thus suited for the
8971 exchange of large and/or complex datasets between R and other software
8972 package, and for letting R applications work on datasets that are larger than
8973 the available RAM.")
8974 (license license:artistic2.0)))
8976 (define-public r-annotationfilter
8978 (name "r-annotationfilter")
8982 (uri (bioconductor-uri "AnnotationFilter" version))
8985 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8987 `((upstream-name . "AnnotationFilter")))
8988 (build-system r-build-system)
8990 `(("r-genomicranges" ,r-genomicranges)
8991 ("r-lazyeval" ,r-lazyeval)))
8992 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8993 (synopsis "Facilities for filtering Bioconductor annotation resources")
8995 "This package provides classes and other infrastructure to implement
8996 filters for manipulating Bioconductor annotation resources. The filters are
8997 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8998 (license license:artistic2.0)))
9000 (define-public emboss
9006 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
9007 (version-major+minor version) ".0/"
9008 "EMBOSS-" version ".tar.gz"))
9011 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
9012 (build-system gnu-build-system)
9015 (list (string-append "--with-hpdf="
9016 (assoc-ref %build-inputs "libharu")))
9018 (modify-phases %standard-phases
9019 (add-after 'unpack 'fix-checks
9021 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9022 ;; and zlib, but assume that they are all found at the same
9024 (substitute* "configure.in"
9025 (("CHECK_PNGDRIVER")
9026 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9027 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9028 AM_CONDITIONAL(AMPNG, true)"))
9030 (add-after 'fix-checks 'disable-update-check
9032 ;; At build time there is no connection to the Internet, so
9033 ;; looking for updates will not work.
9034 (substitute* "Makefile.am"
9035 (("\\$\\(bindir\\)/embossupdate") ""))
9037 (add-after 'disable-update-check 'autogen
9038 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9044 ("libharu" ,libharu)
9047 `(("autoconf" ,autoconf)
9048 ("automake" ,automake)
9049 ("libtool" ,libtool)
9050 ("pkg-config" ,pkg-config)))
9051 (home-page "http://emboss.sourceforge.net")
9052 (synopsis "Molecular biology analysis suite")
9053 (description "EMBOSS is the \"European Molecular Biology Open Software
9054 Suite\". EMBOSS is an analysis package specially developed for the needs of
9055 the molecular biology (e.g. EMBnet) user community. The software
9056 automatically copes with data in a variety of formats and even allows
9057 transparent retrieval of sequence data from the web. It also provides a
9058 number of libraries for the development of software in the field of molecular
9059 biology. EMBOSS also integrates a range of currently available packages and
9060 tools for sequence analysis into a seamless whole.")
9061 (license license:gpl2+)))
9064 (let ((revision "1")
9065 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9068 ;; The version is 2.13.0 even though no release archives have been
9069 ;; published as yet.
9070 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9074 (url "https://github.com/arq5x/bits.git")
9076 (file-name (string-append name "-" version "-checkout"))
9079 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9080 (build-system gnu-build-system)
9082 `(#:tests? #f ;no tests included
9084 (modify-phases %standard-phases
9086 (add-after 'unpack 'remove-cuda
9088 (substitute* "Makefile"
9090 (("(bits_test_intersections) \\\\" _ match) match))
9093 (lambda* (#:key outputs #:allow-other-keys)
9095 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9100 (home-page "https://github.com/arq5x/bits")
9101 (synopsis "Implementation of binary interval search algorithm")
9102 (description "This package provides an implementation of the
9103 BITS (Binary Interval Search) algorithm, an approach to interval set
9104 intersection. It is especially suited for the comparison of diverse genomic
9105 datasets and the exploration of large datasets of genome
9106 intervals (e.g. genes, sequence alignments).")
9107 (license license:gpl2))))
9109 (define-public piranha
9110 ;; There is no release tarball for the latest version. The latest commit is
9111 ;; older than one year at the time of this writing.
9112 (let ((revision "1")
9113 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9116 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9120 (url "https://github.com/smithlabcode/piranha.git")
9122 (file-name (git-file-name name version))
9125 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9126 (build-system gnu-build-system)
9128 `(#:test-target "test"
9130 (modify-phases %standard-phases
9131 (add-after 'unpack 'copy-smithlab-cpp
9132 (lambda* (#:key inputs #:allow-other-keys)
9133 (for-each (lambda (file)
9134 (install-file file "./src/smithlab_cpp/"))
9135 (find-files (assoc-ref inputs "smithlab-cpp")))
9137 (add-after 'install 'install-to-store
9138 (lambda* (#:key outputs #:allow-other-keys)
9139 (let* ((out (assoc-ref outputs "out"))
9140 (bin (string-append out "/bin")))
9141 (for-each (lambda (file)
9142 (install-file file bin))
9143 (find-files "bin" ".*")))
9146 (list (string-append "--with-bam_tools_headers="
9147 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9148 (string-append "--with-bam_tools_library="
9149 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9151 `(("bamtools" ,bamtools)
9152 ("samtools" ,samtools-0.1)
9155 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9159 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9161 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9164 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9166 `(("python" ,python-2)))
9167 (home-page "https://github.com/smithlabcode/piranha")
9168 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9170 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9171 RIP-seq experiments. It takes input in BED or BAM format and identifies
9172 regions of statistically significant read enrichment. Additional covariates
9173 may optionally be provided to further inform the peak-calling process.")
9174 (license license:gpl3+))))
9182 (uri (string-append "https://pypi.python.org/packages/source/P"
9183 "/PePr/PePr-" version ".tar.gz"))
9186 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9187 (build-system python-build-system)
9189 `(#:python ,python-2 ; python2 only
9190 #:tests? #f)) ; no tests included
9192 `(("python2-numpy" ,python2-numpy)
9193 ("python2-scipy" ,python2-scipy)
9194 ("python2-pysam" ,python2-pysam)))
9195 (home-page "https://github.com/shawnzhangyx/PePr")
9196 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9198 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9199 that is primarily designed for data with biological replicates. It uses a
9200 negative binomial distribution to model the read counts among the samples in
9201 the same group, and look for consistent differences between ChIP and control
9202 group or two ChIP groups run under different conditions.")
9203 (license license:gpl3+)))
9205 (define-public filevercmp
9206 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9209 (version (string-append "0-1." (string-take commit 7)))
9213 (url "https://github.com/ekg/filevercmp.git")
9215 (file-name (git-file-name name commit))
9218 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9219 (build-system gnu-build-system)
9221 `(#:tests? #f ; There are no tests to run.
9223 (modify-phases %standard-phases
9224 (delete 'configure) ; There is no configure phase.
9226 (lambda* (#:key outputs #:allow-other-keys)
9227 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9228 (install-file "filevercmp" bin)
9230 (home-page "https://github.com/ekg/filevercmp")
9231 (synopsis "This program compares version strings")
9232 (description "This program compares version strings. It intends to be a
9233 replacement for strverscmp.")
9234 (license license:gpl3+))))
9236 (define-public multiqc
9243 (uri (pypi-uri "multiqc" version))
9246 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9247 (build-system python-build-system)
9249 `(("python-jinja2" ,python-jinja2)
9250 ("python-simplejson" ,python-simplejson)
9251 ("python-pyyaml" ,python-pyyaml)
9252 ("python-click" ,python-click)
9253 ("python-spectra" ,python-spectra)
9254 ("python-requests" ,python-requests)
9255 ("python-markdown" ,python-markdown)
9256 ("python-lzstring" ,python-lzstring)
9257 ("python-matplotlib" ,python-matplotlib)
9258 ("python-numpy" ,python-numpy)
9259 ;; MultQC checks for the presence of nose at runtime.
9260 ("python-nose" ,python-nose)))
9263 (modify-phases %standard-phases
9264 (add-after 'unpack 'relax-requirements
9266 (substitute* "setup.py"
9267 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9268 ;; than the one in Guix, but should work fine with 2.2.2.
9269 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9270 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9271 (("['\"]matplotlib.*?['\"]")
9274 (home-page "http://multiqc.info")
9275 (synopsis "Aggregate bioinformatics analysis reports")
9277 "MultiQC is a tool to aggregate bioinformatics results across many
9278 samples into a single report. It contains modules for a large number of
9279 common bioinformatics tools.")
9280 (license license:gpl3+)))
9282 (define-public r-chipseq
9289 (uri (bioconductor-uri "chipseq" version))
9292 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9293 (build-system r-build-system)
9295 `(("r-biocgenerics" ,r-biocgenerics)
9296 ("r-genomicranges" ,r-genomicranges)
9297 ("r-iranges" ,r-iranges)
9298 ("r-lattice" ,r-lattice)
9299 ("r-s4vectors" ,r-s4vectors)
9300 ("r-shortread" ,r-shortread)))
9301 (home-page "https://bioconductor.org/packages/chipseq")
9302 (synopsis "Package for analyzing ChIPseq data")
9304 "This package provides tools for processing short read data from ChIPseq
9306 (license license:artistic2.0)))
9308 (define-public r-copyhelper
9310 (name "r-copyhelper")
9315 (uri (string-append "https://bioconductor.org/packages/release/"
9316 "data/experiment/src/contrib/CopyhelpeR_"
9320 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9321 (properties `((upstream-name . "CopyhelpeR")))
9322 (build-system r-build-system)
9323 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9324 (synopsis "Helper files for CopywriteR")
9326 "This package contains the helper files that are required to run the
9327 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9328 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9329 mm10. In addition, it contains a blacklist filter to remove regions that
9330 display copy number variation. Files are stored as GRanges objects from the
9331 GenomicRanges Bioconductor package.")
9332 (license license:gpl2)))
9334 (define-public r-copywriter
9336 (name "r-copywriter")
9341 (uri (bioconductor-uri "CopywriteR" version))
9344 "0aamxafdk98n7s92jyqs65d6ljpnc2463vanvsw80p44qn6l6awn"))))
9345 (properties `((upstream-name . "CopywriteR")))
9346 (build-system r-build-system)
9348 `(("r-biocparallel" ,r-biocparallel)
9349 ("r-chipseq" ,r-chipseq)
9350 ("r-copyhelper" ,r-copyhelper)
9351 ("r-data-table" ,r-data-table)
9352 ("r-dnacopy" ,r-dnacopy)
9353 ("r-futile-logger" ,r-futile-logger)
9354 ("r-genomeinfodb" ,r-genomeinfodb)
9355 ("r-genomicalignments" ,r-genomicalignments)
9356 ("r-genomicranges" ,r-genomicranges)
9357 ("r-gtools" ,r-gtools)
9358 ("r-iranges" ,r-iranges)
9359 ("r-matrixstats" ,r-matrixstats)
9360 ("r-rsamtools" ,r-rsamtools)
9361 ("r-s4vectors" ,r-s4vectors)))
9362 (home-page "https://github.com/PeeperLab/CopywriteR")
9363 (synopsis "Copy number information from targeted sequencing")
9365 "CopywriteR extracts DNA copy number information from targeted sequencing
9366 by utilizing off-target reads. It allows for extracting uniformly distributed
9367 copy number information, can be used without reference, and can be applied to
9368 sequencing data obtained from various techniques including chromatin
9369 immunoprecipitation and target enrichment on small gene panels. Thereby,
9370 CopywriteR constitutes a widely applicable alternative to available copy
9371 number detection tools.")
9372 (license license:gpl2)))
9374 (define-public r-methylkit
9376 (name "r-methylkit")
9380 (uri (bioconductor-uri "methylKit" version))
9383 "0mz6lil1wax931incnw5byx0v9i8ryhwq9mv0nv8s48ai33ch3x6"))))
9384 (properties `((upstream-name . "methylKit")))
9385 (build-system r-build-system)
9387 `(("r-data-table" ,r-data-table)
9388 ("r-emdbook" ,r-emdbook)
9389 ("r-fastseg" ,r-fastseg)
9390 ("r-genomeinfodb" ,r-genomeinfodb)
9391 ("r-genomicranges" ,r-genomicranges)
9392 ("r-gtools" ,r-gtools)
9393 ("r-iranges" ,r-iranges)
9394 ("r-kernsmooth" ,r-kernsmooth)
9395 ("r-limma" ,r-limma)
9396 ("r-mclust" ,r-mclust)
9397 ("r-qvalue" ,r-qvalue)
9398 ("r-r-utils" ,r-r-utils)
9400 ("r-rhtslib" ,r-rhtslib)
9401 ("r-rsamtools" ,r-rsamtools)
9402 ("r-rtracklayer" ,r-rtracklayer)
9403 ("r-s4vectors" ,r-s4vectors)
9404 ("r-zlibbioc" ,r-zlibbioc)))
9407 (home-page "https://github.com/al2na/methylKit")
9409 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9411 "MethylKit is an R package for DNA methylation analysis and annotation
9412 from high-throughput bisulfite sequencing. The package is designed to deal
9413 with sequencing data from @dfn{Reduced representation bisulfite
9414 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9415 genome bisulfite sequencing. It also has functions to analyze base-pair
9416 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9418 (license license:artistic2.0)))
9420 (define-public r-sva
9427 (uri (bioconductor-uri "sva" version))
9430 "1xf0hlrqjxl0y3x13mrkxghiv39fd9v2g8gq3qzbf1wj7il6bph3"))))
9431 (build-system r-build-system)
9433 `(("r-genefilter" ,r-genefilter)
9435 ("r-biocparallel" ,r-biocparallel)
9436 ("r-matrixstats" ,r-matrixstats)
9437 ("r-limma" ,r-limma)))
9438 (home-page "https://bioconductor.org/packages/sva")
9439 (synopsis "Surrogate variable analysis")
9441 "This package contains functions for removing batch effects and other
9442 unwanted variation in high-throughput experiment. It also contains functions
9443 for identifying and building surrogate variables for high-dimensional data
9444 sets. Surrogate variables are covariates constructed directly from
9445 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9446 imaging data that can be used in subsequent analyses to adjust for unknown,
9447 unmodeled, or latent sources of noise.")
9448 (license license:artistic2.0)))
9450 (define-public r-seqminer
9457 (uri (cran-uri "seqminer" version))
9460 "15yhg4vfc7jg1jnqb3371j00pgbmbyc9l1xx63hq1l3p34lazq2l"))))
9461 (build-system r-build-system)
9464 (home-page "http://seqminer.genomic.codes")
9465 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9467 "This package provides tools to integrate nucleotide sequencing
9468 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9469 ;; Any version of the GPL is acceptable
9470 (license (list license:gpl2+ license:gpl3+))))
9472 (define-public r-raremetals2
9474 (name "r-raremetals2")
9479 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9480 "b/b7/RareMETALS2_" version ".tar.gz"))
9483 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9484 (properties `((upstream-name . "RareMETALS2")))
9485 (build-system r-build-system)
9487 `(("r-seqminer" ,r-seqminer)
9488 ("r-mvtnorm" ,r-mvtnorm)
9490 ("r-compquadform" ,r-compquadform)
9491 ("r-getopt" ,r-getopt)))
9492 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9493 (synopsis "Analyze gene-level association tests for binary trait")
9495 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9496 It was designed to meta-analyze gene-level association tests for binary trait.
9497 While rareMETALS offers a near-complete solution for meta-analysis of
9498 gene-level tests for quantitative trait, it does not offer the optimal
9499 solution for binary trait. The package rareMETALS2 offers improved features
9500 for analyzing gene-level association tests in meta-analyses for binary
9502 (license license:gpl3)))
9504 (define-public r-maldiquant
9506 (name "r-maldiquant")
9511 (uri (cran-uri "MALDIquant" version))
9514 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9515 (properties `((upstream-name . "MALDIquant")))
9516 (build-system r-build-system)
9517 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9518 (synopsis "Quantitative analysis of mass spectrometry data")
9520 "This package provides a complete analysis pipeline for matrix-assisted
9521 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9522 two-dimensional mass spectrometry data. In addition to commonly used plotting
9523 and processing methods it includes distinctive features, namely baseline
9524 subtraction methods such as morphological filters (TopHat) or the
9525 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9526 alignment using warping functions, handling of replicated measurements as well
9527 as allowing spectra with different resolutions.")
9528 (license license:gpl3+)))
9530 (define-public r-protgenerics
9532 (name "r-protgenerics")
9537 (uri (bioconductor-uri "ProtGenerics" version))
9540 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9541 (properties `((upstream-name . "ProtGenerics")))
9542 (build-system r-build-system)
9543 (home-page "https://github.com/lgatto/ProtGenerics")
9544 (synopsis "S4 generic functions for proteomics infrastructure")
9546 "This package provides S4 generic functions needed by Bioconductor
9547 proteomics packages.")
9548 (license license:artistic2.0)))
9550 (define-public r-mzr
9557 (uri (bioconductor-uri "mzR" version))
9560 "0li1y6p95ljiva4lvfmql9sipn4dq42sknbh60b36ycjppnf8lj5"))
9561 (modules '((guix build utils)))
9564 (delete-file-recursively "src/boost")
9566 (properties `((upstream-name . "mzR")))
9567 (build-system r-build-system)
9570 (modify-phases %standard-phases
9571 (add-after 'unpack 'use-system-boost
9573 (substitute* "src/Makevars"
9574 (("\\./boost/libs.*") "")
9575 (("ARCH_OBJS=" line)
9577 "\nARCH_LIBS=-lboost_system -lboost_regex \
9578 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9581 `(("boost" ,boost) ; use this instead of the bundled boost sources
9584 `(("r-biobase" ,r-biobase)
9585 ("r-biocgenerics" ,r-biocgenerics)
9586 ("r-ncdf4" ,r-ncdf4)
9587 ("r-protgenerics" ,r-protgenerics)
9589 ("r-rhdf5lib" ,r-rhdf5lib)
9590 ("r-zlibbioc" ,r-zlibbioc)))
9591 (home-page "https://github.com/sneumann/mzR/")
9592 (synopsis "Parser for mass spectrometry data files")
9594 "The mzR package provides a unified API to the common file formats and
9595 parsers available for mass spectrometry data. It comes with a wrapper for the
9596 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9597 The package contains the original code written by the ISB, and a subset of the
9598 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9599 previously been used in XCMS.")
9600 (license license:artistic2.0)))
9602 (define-public r-affyio
9609 (uri (bioconductor-uri "affyio" version))
9612 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9613 (build-system r-build-system)
9615 `(("r-zlibbioc" ,r-zlibbioc)))
9618 (home-page "https://github.com/bmbolstad/affyio")
9619 (synopsis "Tools for parsing Affymetrix data files")
9621 "This package provides routines for parsing Affymetrix data files based
9622 upon file format information. The primary focus is on accessing the CEL and
9624 (license license:lgpl2.0+)))
9626 (define-public r-affy
9633 (uri (bioconductor-uri "affy" version))
9636 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9637 (build-system r-build-system)
9639 `(("r-affyio" ,r-affyio)
9640 ("r-biobase" ,r-biobase)
9641 ("r-biocgenerics" ,r-biocgenerics)
9642 ("r-biocmanager" ,r-biocmanager)
9643 ("r-preprocesscore" ,r-preprocesscore)
9644 ("r-zlibbioc" ,r-zlibbioc)))
9647 (home-page "https://bioconductor.org/packages/affy")
9648 (synopsis "Methods for affymetrix oligonucleotide arrays")
9650 "This package contains functions for exploratory oligonucleotide array
9652 (license license:lgpl2.0+)))
9654 (define-public r-vsn
9661 (uri (bioconductor-uri "vsn" version))
9664 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9665 (build-system r-build-system)
9667 `(("r-affy" ,r-affy)
9668 ("r-biobase" ,r-biobase)
9669 ("r-ggplot2" ,r-ggplot2)
9670 ("r-lattice" ,r-lattice)
9671 ("r-limma" ,r-limma)))
9672 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9673 (synopsis "Variance stabilization and calibration for microarray data")
9675 "The package implements a method for normalising microarray intensities,
9676 and works for single- and multiple-color arrays. It can also be used for data
9677 from other technologies, as long as they have similar format. The method uses
9678 a robust variant of the maximum-likelihood estimator for an
9679 additive-multiplicative error model and affine calibration. The model
9680 incorporates data calibration step (a.k.a. normalization), a model for the
9681 dependence of the variance on the mean intensity and a variance stabilizing
9682 data transformation. Differences between transformed intensities are
9683 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9684 their variance is independent of the mean, and they are usually more sensitive
9685 and specific in detecting differential transcription.")
9686 (license license:artistic2.0)))
9688 (define-public r-mzid
9695 (uri (bioconductor-uri "mzID" version))
9698 "08jbq223viwknsmsi30hyxyxslvmb0l4wx3vmqlkl6qk4vfmxzjz"))))
9699 (properties `((upstream-name . "mzID")))
9700 (build-system r-build-system)
9702 `(("r-doparallel" ,r-doparallel)
9703 ("r-foreach" ,r-foreach)
9704 ("r-iterators" ,r-iterators)
9706 ("r-protgenerics" ,r-protgenerics)
9709 (home-page "https://bioconductor.org/packages/mzID")
9710 (synopsis "Parser for mzIdentML files")
9712 "This package provides a parser for mzIdentML files implemented using the
9713 XML package. The parser tries to be general and able to handle all types of
9714 mzIdentML files with the drawback of having less pretty output than a vendor
9716 (license license:gpl2+)))
9718 (define-public r-pcamethods
9720 (name "r-pcamethods")
9725 (uri (bioconductor-uri "pcaMethods" version))
9728 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9729 (properties `((upstream-name . "pcaMethods")))
9730 (build-system r-build-system)
9732 `(("r-biobase" ,r-biobase)
9733 ("r-biocgenerics" ,r-biocgenerics)
9735 ("r-rcpp" ,r-rcpp)))
9736 (home-page "https://github.com/hredestig/pcamethods")
9737 (synopsis "Collection of PCA methods")
9739 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9740 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9741 for missing value estimation is included for comparison. BPCA, PPCA and
9742 NipalsPCA may be used to perform PCA on incomplete data as well as for
9743 accurate missing value estimation. A set of methods for printing and plotting
9744 the results is also provided. All PCA methods make use of the same data
9745 structure (pcaRes) to provide a common interface to the PCA results.")
9746 (license license:gpl3+)))
9748 (define-public r-msnbase
9755 (uri (bioconductor-uri "MSnbase" version))
9758 "0y658anh06vnvbkfs7r8q40gqgyqr2r8kj7jlpnp33fy1lvp1nv7"))))
9759 (properties `((upstream-name . "MSnbase")))
9760 (build-system r-build-system)
9762 `(("r-affy" ,r-affy)
9763 ("r-biobase" ,r-biobase)
9764 ("r-biocgenerics" ,r-biocgenerics)
9765 ("r-biocparallel" ,r-biocparallel)
9766 ("r-digest" ,r-digest)
9767 ("r-ggplot2" ,r-ggplot2)
9768 ("r-impute" ,r-impute)
9769 ("r-iranges" ,r-iranges)
9770 ("r-lattice" ,r-lattice)
9771 ("r-maldiquant" ,r-maldiquant)
9775 ("r-pcamethods" ,r-pcamethods)
9777 ("r-preprocesscore" ,r-preprocesscore)
9778 ("r-protgenerics" ,r-protgenerics)
9780 ("r-s4vectors" ,r-s4vectors)
9781 ("r-scales" ,r-scales)
9784 (home-page "https://github.com/lgatto/MSnbase")
9785 (synopsis "Base functions and classes for MS-based proteomics")
9787 "This package provides basic plotting, data manipulation and processing
9788 of mass spectrometry based proteomics data.")
9789 (license license:artistic2.0)))
9791 (define-public r-msnid
9798 (uri (bioconductor-uri "MSnID" version))
9801 "0hgq4argllhh5hvxqi8vkf1blc3nibsslhx4zsv2mcv4yj75bv4n"))))
9802 (properties `((upstream-name . "MSnID")))
9803 (build-system r-build-system)
9805 `(("r-biobase" ,r-biobase)
9806 ("r-data-table" ,r-data-table)
9807 ("r-doparallel" ,r-doparallel)
9808 ("r-dplyr" ,r-dplyr)
9809 ("r-foreach" ,r-foreach)
9810 ("r-iterators" ,r-iterators)
9811 ("r-msnbase" ,r-msnbase)
9814 ("r-protgenerics" ,r-protgenerics)
9815 ("r-r-cache" ,r-r-cache)
9817 ("r-reshape2" ,r-reshape2)))
9818 (home-page "https://bioconductor.org/packages/MSnID")
9819 (synopsis "Utilities for LC-MSn proteomics identifications")
9821 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9822 from mzIdentML (leveraging the mzID package) or text files. After collating
9823 the search results from multiple datasets it assesses their identification
9824 quality and optimize filtering criteria to achieve the maximum number of
9825 identifications while not exceeding a specified false discovery rate. It also
9826 contains a number of utilities to explore the MS/MS results and assess missed
9827 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9828 (license license:artistic2.0)))
9830 (define-public r-seurat
9836 (uri (cran-uri "Seurat" version))
9839 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9840 (properties `((upstream-name . "Seurat")))
9841 (build-system r-build-system)
9844 ("r-cluster" ,r-cluster)
9845 ("r-cowplot" ,r-cowplot)
9846 ("r-dosnow" ,r-dosnow)
9847 ("r-dplyr" ,r-dplyr)
9849 ("r-fitdistrplus" ,r-fitdistrplus)
9850 ("r-foreach" ,r-foreach)
9852 ("r-ggplot2" ,r-ggplot2)
9853 ("r-ggridges" ,r-ggridges)
9854 ("r-gplots" ,r-gplots)
9855 ("r-hdf5r" ,r-hdf5r)
9856 ("r-hmisc" ,r-hmisc)
9859 ("r-igraph" ,r-igraph)
9860 ("r-irlba" ,r-irlba)
9862 ("r-lmtest" ,r-lmtest)
9864 ("r-matrix" ,r-matrix)
9865 ("r-metap" ,r-metap)
9866 ("r-mixtools" ,r-mixtools)
9867 ("r-pbapply" ,r-pbapply)
9868 ("r-plotly" ,r-plotly)
9871 ("r-rcolorbrewer" ,r-rcolorbrewer)
9873 ("r-rcppeigen" ,r-rcppeigen)
9874 ("r-rcppprogress" ,r-rcppprogress)
9875 ("r-reshape2" ,r-reshape2)
9876 ("r-reticulate" ,r-reticulate)
9878 ("r-rtsne" ,r-rtsne)
9879 ("r-sdmtools" ,r-sdmtools)
9880 ("r-tidyr" ,r-tidyr)
9881 ("r-tsne" ,r-tsne)))
9882 (home-page "http://www.satijalab.org/seurat")
9883 (synopsis "Seurat is an R toolkit for single cell genomics")
9885 "This package is an R package designed for QC, analysis, and
9886 exploration of single cell RNA-seq data. It easily enables widely-used
9887 analytical techniques, including the identification of highly variable genes,
9888 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9889 algorithms; density clustering, hierarchical clustering, k-means, and the
9890 discovery of differentially expressed genes and markers.")
9891 (license license:gpl3)))
9893 (define-public r-aroma-light
9895 (name "r-aroma-light")
9900 (uri (bioconductor-uri "aroma.light" version))
9903 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9904 (properties `((upstream-name . "aroma.light")))
9905 (build-system r-build-system)
9907 `(("r-matrixstats" ,r-matrixstats)
9908 ("r-r-methodss3" ,r-r-methodss3)
9910 ("r-r-utils" ,r-r-utils)))
9911 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9912 (synopsis "Methods for normalization and visualization of microarray data")
9914 "This package provides methods for microarray analysis that take basic
9915 data types such as matrices and lists of vectors. These methods can be used
9916 standalone, be utilized in other packages, or be wrapped up in higher-level
9918 (license license:gpl2+)))
9920 (define-public r-deseq
9927 (uri (bioconductor-uri "DESeq" version))
9930 "1klv1xrh3173srywr6dnq6i7m9djn4gc9aflr1p3a6yjlqcq6fya"))))
9931 (properties `((upstream-name . "DESeq")))
9932 (build-system r-build-system)
9934 `(("r-biobase" ,r-biobase)
9935 ("r-biocgenerics" ,r-biocgenerics)
9936 ("r-genefilter" ,r-genefilter)
9937 ("r-geneplotter" ,r-geneplotter)
9938 ("r-lattice" ,r-lattice)
9939 ("r-locfit" ,r-locfit)
9941 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9942 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9943 (synopsis "Differential gene expression analysis")
9945 "This package provides tools for estimating variance-mean dependence in
9946 count data from high-throughput genetic sequencing assays and for testing for
9947 differential expression based on a model using the negative binomial
9949 (license license:gpl3+)))
9951 (define-public r-edaseq
9958 (uri (bioconductor-uri "EDASeq" version))
9961 "1gjqzn1kg9qwyz2gwjyy9xzzr1lnc7xd5zwdyvzkadz97gckzxwf"))))
9962 (properties `((upstream-name . "EDASeq")))
9963 (build-system r-build-system)
9965 `(("r-annotationdbi" ,r-annotationdbi)
9966 ("r-aroma-light" ,r-aroma-light)
9967 ("r-biobase" ,r-biobase)
9968 ("r-biocgenerics" ,r-biocgenerics)
9969 ("r-biomart" ,r-biomart)
9970 ("r-biostrings" ,r-biostrings)
9971 ("r-deseq" ,r-deseq)
9972 ("r-genomicfeatures" ,r-genomicfeatures)
9973 ("r-genomicranges" ,r-genomicranges)
9974 ("r-iranges" ,r-iranges)
9975 ("r-rsamtools" ,r-rsamtools)
9976 ("r-shortread" ,r-shortread)))
9977 (home-page "https://github.com/drisso/EDASeq")
9978 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9980 "This package provides support for numerical and graphical summaries of
9981 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9982 adjust for GC-content effect (or other gene-level effects) on read counts:
9983 loess robust local regression, global-scaling, and full-quantile
9984 normalization. Between-lane normalization procedures to adjust for
9985 distributional differences between lanes (e.g., sequencing depth):
9986 global-scaling and full-quantile normalization.")
9987 (license license:artistic2.0)))
9989 (define-public r-interactivedisplaybase
9991 (name "r-interactivedisplaybase")
9996 (uri (bioconductor-uri "interactiveDisplayBase" version))
9999 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
10001 `((upstream-name . "interactiveDisplayBase")))
10002 (build-system r-build-system)
10004 `(("r-biocgenerics" ,r-biocgenerics)
10005 ("r-shiny" ,r-shiny)))
10006 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10007 (synopsis "Base package for web displays of Bioconductor objects")
10009 "This package contains the basic methods needed to generate interactive
10010 Shiny-based display methods for Bioconductor objects.")
10011 (license license:artistic2.0)))
10013 (define-public r-annotationhub
10015 (name "r-annotationhub")
10020 (uri (bioconductor-uri "AnnotationHub" version))
10023 "00288x3na0izpmbcvsqac1br1qwry86vwc2slj1l47crdfb7za6c"))))
10024 (properties `((upstream-name . "AnnotationHub")))
10025 (build-system r-build-system)
10027 `(("r-annotationdbi" ,r-annotationdbi)
10028 ("r-biocgenerics" ,r-biocgenerics)
10029 ("r-biocmanager" ,r-biocmanager)
10032 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10033 ("r-rsqlite" ,r-rsqlite)
10034 ("r-s4vectors" ,r-s4vectors)
10035 ("r-yaml" ,r-yaml)))
10036 (home-page "https://bioconductor.org/packages/AnnotationHub")
10037 (synopsis "Client to access AnnotationHub resources")
10039 "This package provides a client for the Bioconductor AnnotationHub web
10040 resource. The AnnotationHub web resource provides a central location where
10041 genomic files (e.g. VCF, bed, wig) and other resources from standard
10042 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10043 metadata about each resource, e.g., a textual description, tags, and date of
10044 modification. The client creates and manages a local cache of files retrieved
10045 by the user, helping with quick and reproducible access.")
10046 (license license:artistic2.0)))
10048 (define-public r-fastseg
10055 (uri (bioconductor-uri "fastseg" version))
10058 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10059 (build-system r-build-system)
10061 `(("r-biobase" ,r-biobase)
10062 ("r-biocgenerics" ,r-biocgenerics)
10063 ("r-genomicranges" ,r-genomicranges)
10064 ("r-iranges" ,r-iranges)
10065 ("r-s4vectors" ,r-s4vectors)))
10066 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10067 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10069 "Fastseg implements a very fast and efficient segmentation algorithm.
10070 It can segment data from DNA microarrays and data from next generation
10071 sequencing for example to detect copy number segments. Further it can segment
10072 data from RNA microarrays like tiling arrays to identify transcripts. Most
10073 generally, it can segment data given as a matrix or as a vector. Various data
10074 formats can be used as input to fastseg like expression set objects for
10075 microarrays or GRanges for sequencing data.")
10076 (license license:lgpl2.0+)))
10078 (define-public r-keggrest
10080 (name "r-keggrest")
10085 (uri (bioconductor-uri "KEGGREST" version))
10088 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10089 (properties `((upstream-name . "KEGGREST")))
10090 (build-system r-build-system)
10092 `(("r-biostrings" ,r-biostrings)
10095 (home-page "https://bioconductor.org/packages/KEGGREST")
10096 (synopsis "Client-side REST access to KEGG")
10098 "This package provides a package that provides a client interface to the
10099 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10100 (license license:artistic2.0)))
10102 (define-public r-gage
10109 (uri (bioconductor-uri "gage" version))
10112 "07b098wvryxf0zd423nk6h52s3gyngwjcx2vplqybpbpgl8h2931"))))
10113 (build-system r-build-system)
10115 `(("r-annotationdbi" ,r-annotationdbi)
10116 ("r-graph" ,r-graph)
10117 ("r-keggrest" ,r-keggrest)))
10118 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10119 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10121 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10122 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10123 data attributes including sample sizes, experimental designs, assay platforms,
10124 and other types of heterogeneity. The gage package provides functions for
10125 basic GAGE analysis, result processing and presentation. In addition, it
10126 provides demo microarray data and commonly used gene set data based on KEGG
10127 pathways and GO terms. These funtions and data are also useful for gene set
10128 analysis using other methods.")
10129 (license license:gpl2+)))
10131 (define-public r-genomicfiles
10133 (name "r-genomicfiles")
10138 (uri (bioconductor-uri "GenomicFiles" version))
10141 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10142 (properties `((upstream-name . "GenomicFiles")))
10143 (build-system r-build-system)
10145 `(("r-biocgenerics" ,r-biocgenerics)
10146 ("r-biocparallel" ,r-biocparallel)
10147 ("r-genomeinfodb" ,r-genomeinfodb)
10148 ("r-genomicalignments" ,r-genomicalignments)
10149 ("r-genomicranges" ,r-genomicranges)
10150 ("r-iranges" ,r-iranges)
10151 ("r-rsamtools" ,r-rsamtools)
10152 ("r-rtracklayer" ,r-rtracklayer)
10153 ("r-s4vectors" ,r-s4vectors)
10154 ("r-summarizedexperiment" ,r-summarizedexperiment)
10155 ("r-variantannotation" ,r-variantannotation)))
10156 (home-page "https://bioconductor.org/packages/GenomicFiles")
10157 (synopsis "Distributed computing by file or by range")
10159 "This package provides infrastructure for parallel computations
10160 distributed by file or by range. User defined mapper and reducer functions
10161 provide added flexibility for data combination and manipulation.")
10162 (license license:artistic2.0)))
10164 (define-public r-complexheatmap
10166 (name "r-complexheatmap")
10171 (uri (bioconductor-uri "ComplexHeatmap" version))
10174 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10176 `((upstream-name . "ComplexHeatmap")))
10177 (build-system r-build-system)
10179 `(("r-circlize" ,r-circlize)
10180 ("r-colorspace" ,r-colorspace)
10181 ("r-getoptlong" ,r-getoptlong)
10182 ("r-globaloptions" ,r-globaloptions)
10183 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10185 "https://github.com/jokergoo/ComplexHeatmap")
10186 (synopsis "Making Complex Heatmaps")
10188 "Complex heatmaps are efficient to visualize associations between
10189 different sources of data sets and reveal potential structures. This package
10190 provides a highly flexible way to arrange multiple heatmaps and supports
10191 self-defined annotation graphics.")
10192 (license license:gpl2+)))
10194 (define-public r-dirichletmultinomial
10196 (name "r-dirichletmultinomial")
10201 (uri (bioconductor-uri "DirichletMultinomial" version))
10204 "19bzn0a5jal1xv0ad6wikxc7wrk582hczqamlln0vb2ffwkj1z3f"))))
10206 `((upstream-name . "DirichletMultinomial")))
10207 (build-system r-build-system)
10211 `(("r-biocgenerics" ,r-biocgenerics)
10212 ("r-iranges" ,r-iranges)
10213 ("r-s4vectors" ,r-s4vectors)))
10214 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10215 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10217 "Dirichlet-multinomial mixture models can be used to describe variability
10218 in microbial metagenomic data. This package is an interface to code
10219 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10221 (license license:lgpl3)))
10223 (define-public r-ensembldb
10225 (name "r-ensembldb")
10230 (uri (bioconductor-uri "ensembldb" version))
10233 "0hdz1f34v7sas2v4225icwl3wd4sf17ykpd5dkbx1hc7wcy4w3np"))))
10234 (build-system r-build-system)
10236 `(("r-annotationdbi" ,r-annotationdbi)
10237 ("r-annotationfilter" ,r-annotationfilter)
10238 ("r-biobase" ,r-biobase)
10239 ("r-biocgenerics" ,r-biocgenerics)
10240 ("r-biostrings" ,r-biostrings)
10243 ("r-genomeinfodb" ,r-genomeinfodb)
10244 ("r-genomicfeatures" ,r-genomicfeatures)
10245 ("r-genomicranges" ,r-genomicranges)
10246 ("r-iranges" ,r-iranges)
10247 ("r-protgenerics" ,r-protgenerics)
10248 ("r-rsamtools" ,r-rsamtools)
10249 ("r-rsqlite" ,r-rsqlite)
10250 ("r-rtracklayer" ,r-rtracklayer)
10251 ("r-s4vectors" ,r-s4vectors)))
10252 (home-page "https://github.com/jotsetung/ensembldb")
10253 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10255 "The package provides functions to create and use transcript-centric
10256 annotation databases/packages. The annotation for the databases are directly
10257 fetched from Ensembl using their Perl API. The functionality and data is
10258 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10259 but, in addition to retrieve all gene/transcript models and annotations from
10260 the database, the @code{ensembldb} package also provides a filter framework
10261 allowing to retrieve annotations for specific entries like genes encoded on a
10262 chromosome region or transcript models of lincRNA genes.")
10263 ;; No version specified
10264 (license license:lgpl3+)))
10266 (define-public r-organismdbi
10268 (name "r-organismdbi")
10273 (uri (bioconductor-uri "OrganismDbi" version))
10276 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10277 (properties `((upstream-name . "OrganismDbi")))
10278 (build-system r-build-system)
10280 `(("r-annotationdbi" ,r-annotationdbi)
10281 ("r-biobase" ,r-biobase)
10282 ("r-biocgenerics" ,r-biocgenerics)
10283 ("r-biocmanager" ,r-biocmanager)
10285 ("r-genomicfeatures" ,r-genomicfeatures)
10286 ("r-genomicranges" ,r-genomicranges)
10287 ("r-graph" ,r-graph)
10288 ("r-iranges" ,r-iranges)
10290 ("r-s4vectors" ,r-s4vectors)))
10291 (home-page "https://bioconductor.org/packages/OrganismDbi")
10292 (synopsis "Software to enable the smooth interfacing of database packages")
10293 (description "The package enables a simple unified interface to several
10294 annotation packages each of which has its own schema by taking advantage of
10295 the fact that each of these packages implements a select methods.")
10296 (license license:artistic2.0)))
10298 (define-public r-biovizbase
10300 (name "r-biovizbase")
10305 (uri (bioconductor-uri "biovizBase" version))
10308 "0v54mcn3rnnfx8dmcrms5z3rgq19n3hp4r23azlgzwq6hjw7cccx"))))
10309 (properties `((upstream-name . "biovizBase")))
10310 (build-system r-build-system)
10312 `(("r-annotationdbi" ,r-annotationdbi)
10313 ("r-annotationfilter" ,r-annotationfilter)
10314 ("r-biocgenerics" ,r-biocgenerics)
10315 ("r-biostrings" ,r-biostrings)
10316 ("r-dichromat" ,r-dichromat)
10317 ("r-ensembldb" ,r-ensembldb)
10318 ("r-genomeinfodb" ,r-genomeinfodb)
10319 ("r-genomicalignments" ,r-genomicalignments)
10320 ("r-genomicfeatures" ,r-genomicfeatures)
10321 ("r-genomicranges" ,r-genomicranges)
10322 ("r-hmisc" ,r-hmisc)
10323 ("r-iranges" ,r-iranges)
10324 ("r-rcolorbrewer" ,r-rcolorbrewer)
10325 ("r-rlang" ,r-rlang)
10326 ("r-rsamtools" ,r-rsamtools)
10327 ("r-s4vectors" ,r-s4vectors)
10328 ("r-scales" ,r-scales)
10329 ("r-summarizedexperiment" ,r-summarizedexperiment)
10330 ("r-variantannotation" ,r-variantannotation)))
10331 (home-page "https://bioconductor.org/packages/biovizBase")
10332 (synopsis "Basic graphic utilities for visualization of genomic data")
10334 "The biovizBase package is designed to provide a set of utilities, color
10335 schemes and conventions for genomic data. It serves as the base for various
10336 high-level packages for biological data visualization. This saves development
10337 effort and encourages consistency.")
10338 (license license:artistic2.0)))
10340 (define-public r-ggbio
10347 (uri (bioconductor-uri "ggbio" version))
10350 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10351 (build-system r-build-system)
10353 `(("r-annotationdbi" ,r-annotationdbi)
10354 ("r-annotationfilter" ,r-annotationfilter)
10355 ("r-biobase" ,r-biobase)
10356 ("r-biocgenerics" ,r-biocgenerics)
10357 ("r-biostrings" ,r-biostrings)
10358 ("r-biovizbase" ,r-biovizbase)
10359 ("r-bsgenome" ,r-bsgenome)
10360 ("r-ensembldb" ,r-ensembldb)
10361 ("r-genomeinfodb" ,r-genomeinfodb)
10362 ("r-genomicalignments" ,r-genomicalignments)
10363 ("r-genomicfeatures" ,r-genomicfeatures)
10364 ("r-genomicranges" ,r-genomicranges)
10365 ("r-ggally" ,r-ggally)
10366 ("r-ggplot2" ,r-ggplot2)
10367 ("r-gridextra" ,r-gridextra)
10368 ("r-gtable" ,r-gtable)
10369 ("r-hmisc" ,r-hmisc)
10370 ("r-iranges" ,r-iranges)
10371 ("r-organismdbi" ,r-organismdbi)
10372 ("r-reshape2" ,r-reshape2)
10373 ("r-rlang" ,r-rlang)
10374 ("r-rsamtools" ,r-rsamtools)
10375 ("r-rtracklayer" ,r-rtracklayer)
10376 ("r-s4vectors" ,r-s4vectors)
10377 ("r-scales" ,r-scales)
10378 ("r-summarizedexperiment" ,r-summarizedexperiment)
10379 ("r-variantannotation" ,r-variantannotation)))
10380 (home-page "http://www.tengfei.name/ggbio/")
10381 (synopsis "Visualization tools for genomic data")
10383 "The ggbio package extends and specializes the grammar of graphics for
10384 biological data. The graphics are designed to answer common scientific
10385 questions, in particular those often asked of high throughput genomics data.
10386 All core Bioconductor data structures are supported, where appropriate. The
10387 package supports detailed views of particular genomic regions, as well as
10388 genome-wide overviews. Supported overviews include ideograms and grand linear
10389 views. High-level plots include sequence fragment length, edge-linked
10390 interval to data view, mismatch pileup, and several splicing summaries.")
10391 (license license:artistic2.0)))
10393 (define-public r-gprofiler
10395 (name "r-gprofiler")
10400 (uri (cran-uri "gProfileR" version))
10403 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10404 (properties `((upstream-name . "gProfileR")))
10405 (build-system r-build-system)
10407 `(("r-plyr" ,r-plyr)
10408 ("r-rcurl" ,r-rcurl)))
10409 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10410 (synopsis "Interface to the g:Profiler toolkit")
10412 "This package provides tools for functional enrichment analysis,
10413 gene identifier conversion and mapping homologous genes across related
10414 organisms via the @code{g:Profiler} toolkit.")
10415 (license license:gpl2+)))
10417 (define-public r-gqtlbase
10419 (name "r-gqtlbase")
10424 (uri (bioconductor-uri "gQTLBase" version))
10427 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10428 (properties `((upstream-name . "gQTLBase")))
10429 (build-system r-build-system)
10431 `(("r-batchjobs" ,r-batchjobs)
10432 ("r-bbmisc" ,r-bbmisc)
10433 ("r-biocgenerics" ,r-biocgenerics)
10435 ("r-doparallel" ,r-doparallel)
10437 ("r-ffbase" ,r-ffbase)
10438 ("r-foreach" ,r-foreach)
10439 ("r-genomicfiles" ,r-genomicfiles)
10440 ("r-genomicranges" ,r-genomicranges)
10441 ("r-rtracklayer" ,r-rtracklayer)
10442 ("r-s4vectors" ,r-s4vectors)
10443 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10444 (home-page "https://bioconductor.org/packages/gQTLBase")
10445 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10447 "The purpose of this package is to simplify the storage and interrogation
10448 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10450 (license license:artistic2.0)))
10452 (define-public r-snpstats
10454 (name "r-snpstats")
10459 (uri (bioconductor-uri "snpStats" version))
10462 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10463 (properties `((upstream-name . "snpStats")))
10464 (build-system r-build-system)
10465 (inputs `(("zlib" ,zlib)))
10467 `(("r-biocgenerics" ,r-biocgenerics)
10468 ("r-matrix" ,r-matrix)
10469 ("r-survival" ,r-survival)
10470 ("r-zlibbioc" ,r-zlibbioc)))
10471 (home-page "https://bioconductor.org/packages/snpStats")
10472 (synopsis "Methods for SNP association studies")
10474 "This package provides classes and statistical methods for large
10475 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10476 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10477 (license license:gpl3)))
10479 (define-public r-homo-sapiens
10481 (name "r-homo-sapiens")
10485 ;; We cannot use bioconductor-uri here because this tarball is
10486 ;; located under "data/annotation/" instead of "bioc/".
10487 (uri (string-append "http://www.bioconductor.org/packages/"
10488 "release/data/annotation/src/contrib/"
10490 version ".tar.gz"))
10493 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10495 `((upstream-name . "Homo.sapiens")))
10496 (build-system r-build-system)
10498 `(("r-genomicfeatures" ,r-genomicfeatures)
10499 ("r-go-db" ,r-go-db)
10500 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10501 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10502 ("r-organismdbi" ,r-organismdbi)
10503 ("r-annotationdbi" ,r-annotationdbi)))
10504 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10505 (synopsis "Annotation package for the Homo.sapiens object")
10507 "This package contains the Homo.sapiens object to access data from
10508 several related annotation packages.")
10509 (license license:artistic2.0)))
10511 (define-public r-erma
10518 (uri (bioconductor-uri "erma" version))
10521 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10522 (build-system r-build-system)
10524 `(("r-annotationdbi" ,r-annotationdbi)
10525 ("r-biobase" ,r-biobase)
10526 ("r-biocgenerics" ,r-biocgenerics)
10527 ("r-biocparallel" ,r-biocparallel)
10528 ("r-genomeinfodb" ,r-genomeinfodb)
10529 ("r-genomicfiles" ,r-genomicfiles)
10530 ("r-genomicranges" ,r-genomicranges)
10531 ("r-ggplot2" ,r-ggplot2)
10532 ("r-homo-sapiens" ,r-homo-sapiens)
10533 ("r-iranges" ,r-iranges)
10534 ("r-rtracklayer" ,r-rtracklayer)
10535 ("r-s4vectors" ,r-s4vectors)
10536 ("r-shiny" ,r-shiny)
10537 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10538 (home-page "https://bioconductor.org/packages/erma")
10539 (synopsis "Epigenomic road map adventures")
10541 "The epigenomics road map describes locations of epigenetic marks in DNA
10542 from a variety of cell types. Of interest are locations of histone
10543 modifications, sites of DNA methylation, and regions of accessible chromatin.
10544 This package presents a selection of elements of the road map including
10545 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10546 by Ernst and Kellis.")
10547 (license license:artistic2.0)))
10549 (define-public r-ldblock
10556 (uri (bioconductor-uri "ldblock" version))
10559 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10560 (build-system r-build-system)
10562 `(("r-biocgenerics" ,r-biocgenerics)
10564 ("r-genomeinfodb" ,r-genomeinfodb)
10565 ("r-genomicfiles" ,r-genomicfiles)
10566 ("r-go-db" ,r-go-db)
10567 ("r-homo-sapiens" ,r-homo-sapiens)
10568 ("r-matrix" ,r-matrix)
10569 ("r-rsamtools" ,r-rsamtools)
10570 ("r-snpstats" ,r-snpstats)
10571 ("r-variantannotation" ,r-variantannotation)))
10572 (home-page "https://bioconductor.org/packages/ldblock")
10573 (synopsis "Data structures for linkage disequilibrium measures in populations")
10575 "This package defines data structures for @dfn{linkage
10576 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10577 handling of existing population-level data for the purpose of flexibly
10578 defining LD blocks.")
10579 (license license:artistic2.0)))
10581 (define-public r-gqtlstats
10583 (name "r-gqtlstats")
10588 (uri (bioconductor-uri "gQTLstats" version))
10591 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10592 (properties `((upstream-name . "gQTLstats")))
10593 (build-system r-build-system)
10595 `(("r-annotationdbi" ,r-annotationdbi)
10596 ("r-batchjobs" ,r-batchjobs)
10597 ("r-bbmisc" ,r-bbmisc)
10598 ("r-beeswarm" ,r-beeswarm)
10599 ("r-biobase" ,r-biobase)
10600 ("r-biocgenerics" ,r-biocgenerics)
10601 ("r-doparallel" ,r-doparallel)
10602 ("r-dplyr" ,r-dplyr)
10604 ("r-ffbase" ,r-ffbase)
10605 ("r-foreach" ,r-foreach)
10606 ("r-genomeinfodb" ,r-genomeinfodb)
10607 ("r-genomicfeatures" ,r-genomicfeatures)
10608 ("r-genomicfiles" ,r-genomicfiles)
10609 ("r-genomicranges" ,r-genomicranges)
10610 ("r-ggbeeswarm" ,r-ggbeeswarm)
10611 ("r-ggplot2" ,r-ggplot2)
10612 ("r-gqtlbase" ,r-gqtlbase)
10613 ("r-hardyweinberg" ,r-hardyweinberg)
10614 ("r-homo-sapiens" ,r-homo-sapiens)
10615 ("r-iranges" ,r-iranges)
10616 ("r-limma" ,r-limma)
10618 ("r-plotly" ,r-plotly)
10619 ("r-reshape2" ,r-reshape2)
10620 ("r-s4vectors" ,r-s4vectors)
10621 ("r-shiny" ,r-shiny)
10622 ("r-snpstats" ,r-snpstats)
10623 ("r-summarizedexperiment" ,r-summarizedexperiment)
10624 ("r-variantannotation" ,r-variantannotation)))
10625 (home-page "https://bioconductor.org/packages/gQTLstats")
10626 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10628 "This package provides tools for the computationally efficient analysis
10629 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10630 The software in this package aims to support refinements and functional
10631 interpretation of members of a collection of association statistics on a
10632 family of feature/genome hypotheses.")
10633 (license license:artistic2.0)))
10635 (define-public r-gviz
10642 (uri (bioconductor-uri "Gviz" version))
10645 "05zk9hf30afg6rjg97lzn5v8xij90v8zm09y9vcz0asmc3c8xs0a"))))
10646 (properties `((upstream-name . "Gviz")))
10647 (build-system r-build-system)
10649 `(("r-annotationdbi" ,r-annotationdbi)
10650 ("r-biobase" ,r-biobase)
10651 ("r-biocgenerics" ,r-biocgenerics)
10652 ("r-biomart" ,r-biomart)
10653 ("r-biostrings" ,r-biostrings)
10654 ("r-biovizbase" ,r-biovizbase)
10655 ("r-bsgenome" ,r-bsgenome)
10656 ("r-digest" ,r-digest)
10657 ("r-genomeinfodb" ,r-genomeinfodb)
10658 ("r-genomicalignments" ,r-genomicalignments)
10659 ("r-genomicfeatures" ,r-genomicfeatures)
10660 ("r-genomicranges" ,r-genomicranges)
10661 ("r-iranges" ,r-iranges)
10662 ("r-lattice" ,r-lattice)
10663 ("r-latticeextra" ,r-latticeextra)
10664 ("r-matrixstats" ,r-matrixstats)
10665 ("r-rcolorbrewer" ,r-rcolorbrewer)
10666 ("r-rsamtools" ,r-rsamtools)
10667 ("r-rtracklayer" ,r-rtracklayer)
10668 ("r-s4vectors" ,r-s4vectors)
10669 ("r-xvector" ,r-xvector)))
10670 (home-page "https://bioconductor.org/packages/Gviz")
10671 (synopsis "Plotting data and annotation information along genomic coordinates")
10673 "Genomic data analyses requires integrated visualization of known genomic
10674 information and new experimental data. Gviz uses the biomaRt and the
10675 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10676 and translates this to e.g. gene/transcript structures in viewports of the
10677 grid graphics package. This results in genomic information plotted together
10679 (license license:artistic2.0)))
10681 (define-public r-gwascat
10688 (uri (bioconductor-uri "gwascat" version))
10691 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10692 (build-system r-build-system)
10694 `(("r-annotationdbi" ,r-annotationdbi)
10695 ("r-annotationhub" ,r-annotationhub)
10696 ("r-biocgenerics" ,r-biocgenerics)
10697 ("r-biostrings" ,r-biostrings)
10698 ("r-genomeinfodb" ,r-genomeinfodb)
10699 ("r-genomicfeatures" ,r-genomicfeatures)
10700 ("r-genomicranges" ,r-genomicranges)
10701 ("r-ggbio" ,r-ggbio)
10702 ("r-ggplot2" ,r-ggplot2)
10703 ("r-gqtlstats" ,r-gqtlstats)
10704 ("r-graph" ,r-graph)
10706 ("r-homo-sapiens" ,r-homo-sapiens)
10707 ("r-iranges" ,r-iranges)
10708 ("r-rsamtools" ,r-rsamtools)
10709 ("r-rtracklayer" ,r-rtracklayer)
10710 ("r-s4vectors" ,r-s4vectors)
10711 ("r-snpstats" ,r-snpstats)
10712 ("r-summarizedexperiment" ,r-summarizedexperiment)
10713 ("r-variantannotation" ,r-variantannotation)))
10714 (home-page "https://bioconductor.org/packages/gwascat")
10715 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10717 "This package provides tools for representing and modeling data in the
10718 EMBL-EBI GWAS catalog.")
10719 (license license:artistic2.0)))
10721 (define-public r-sushi
10727 (uri (bioconductor-uri "Sushi" version))
10730 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10731 (properties `((upstream-name . "Sushi")))
10732 (build-system r-build-system)
10734 `(("r-biomart" ,r-biomart)
10736 (home-page "https://bioconductor.org/packages/Sushi")
10737 (synopsis "Tools for visualizing genomics data")
10739 "This package provides flexible, quantitative, and integrative genomic
10740 visualizations for publication-quality multi-panel figures.")
10741 (license license:gpl2+)))
10743 (define-public r-fithic
10749 (uri (bioconductor-uri "FitHiC" version))
10752 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10753 (properties `((upstream-name . "FitHiC")))
10754 (build-system r-build-system)
10756 `(("r-data-table" ,r-data-table)
10757 ("r-fdrtool" ,r-fdrtool)
10758 ("r-rcpp" ,r-rcpp)))
10759 (home-page "https://bioconductor.org/packages/FitHiC")
10760 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10762 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10763 intra-chromosomal contact maps produced by genome-wide genome architecture
10764 assays such as Hi-C.")
10765 (license license:gpl2+)))
10767 (define-public r-hitc
10773 (uri (bioconductor-uri "HiTC" version))
10776 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10777 (properties `((upstream-name . "HiTC")))
10778 (build-system r-build-system)
10780 `(("r-biostrings" ,r-biostrings)
10781 ("r-genomeinfodb" ,r-genomeinfodb)
10782 ("r-genomicranges" ,r-genomicranges)
10783 ("r-iranges" ,r-iranges)
10784 ("r-matrix" ,r-matrix)
10785 ("r-rcolorbrewer" ,r-rcolorbrewer)
10786 ("r-rtracklayer" ,r-rtracklayer)))
10787 (home-page "https://bioconductor.org/packages/HiTC")
10788 (synopsis "High throughput chromosome conformation capture analysis")
10790 "The HiTC package was developed to explore high-throughput \"C\" data
10791 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10792 quality controls, normalization, visualization, and further analysis are also
10794 (license license:artistic2.0)))
10796 (define-public r-qvalue
10803 (uri (bioconductor-uri "qvalue" version))
10806 "03qxshqwwq1rj23p6pjrz08jm3ziikvy9badi4mz2rcwy2nz783a"))))
10807 (build-system r-build-system)
10809 `(("r-ggplot2" ,r-ggplot2)
10810 ("r-reshape2" ,r-reshape2)))
10811 (home-page "http://github.com/jdstorey/qvalue")
10812 (synopsis "Q-value estimation for false discovery rate control")
10814 "This package takes a list of p-values resulting from the simultaneous
10815 testing of many hypotheses and estimates their q-values and local @dfn{false
10816 discovery rate} (FDR) values. The q-value of a test measures the proportion
10817 of false positives incurred when that particular test is called significant.
10818 The local FDR measures the posterior probability the null hypothesis is true
10819 given the test's p-value. Various plots are automatically generated, allowing
10820 one to make sensible significance cut-offs. The software can be applied to
10821 problems in genomics, brain imaging, astrophysics, and data mining.")
10822 ;; Any version of the LGPL.
10823 (license license:lgpl3+)))
10825 (define-public r-hdf5array
10827 (name "r-hdf5array")
10832 (uri (bioconductor-uri "HDF5Array" version))
10835 "1w7ad8cfsbh5xx82m3l4lc0vbmj9lcsqxxpiy3ana2ycgn1bqv3g"))))
10836 (properties `((upstream-name . "HDF5Array")))
10837 (build-system r-build-system)
10839 `(("r-biocgenerics" ,r-biocgenerics)
10840 ("r-delayedarray" ,r-delayedarray)
10841 ("r-iranges" ,r-iranges)
10842 ("r-rhdf5" ,r-rhdf5)
10843 ("r-s4vectors" ,r-s4vectors)))
10844 (home-page "https://bioconductor.org/packages/HDF5Array")
10845 (synopsis "HDF5 back end for DelayedArray objects")
10846 (description "This package provides an array-like container for convenient
10847 access and manipulation of HDF5 datasets. It supports delayed operations and
10848 block processing.")
10849 (license license:artistic2.0)))
10851 (define-public r-rhdf5lib
10853 (name "r-rhdf5lib")
10858 (uri (bioconductor-uri "Rhdf5lib" version))
10861 "01gpz780g850ql20b2ql6pvr678ydk4nq4sn5iiih94a4crb9lz1"))
10862 (modules '((guix build utils)))
10865 ;; Delete bundled binaries
10866 (delete-file-recursively "src/winlib/")
10868 (properties `((upstream-name . "Rhdf5lib")))
10869 (build-system r-build-system)
10872 (modify-phases %standard-phases
10873 (add-after 'unpack 'do-not-use-bundled-hdf5
10874 (lambda* (#:key inputs #:allow-other-keys)
10875 (for-each delete-file '("configure" "configure.ac"))
10876 ;; Do not make other packages link with the proprietary libsz.
10877 (substitute* "R/zzz.R"
10878 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10879 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10880 (("'%s/libhdf5.a %s/libsz.a -lz'")
10881 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10882 (with-directory-excursion "src"
10883 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10884 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10886 ;; Remove timestamp and host system information to make
10887 ;; the build reproducible.
10888 (substitute* "hdf5/src/libhdf5.settings.in"
10889 (("Configured on: @CONFIG_DATE@")
10890 "Configured on: Guix")
10891 (("Uname information:.*")
10892 "Uname information: Linux\n")
10893 ;; Remove unnecessary store reference.
10895 "C Compiler: GCC\n"))
10896 (rename-file "Makevars.in" "Makevars")
10897 (substitute* "Makevars"
10898 (("HDF5_CXX_LIB=.*")
10899 (string-append "HDF5_CXX_LIB="
10900 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10902 (string-append "HDF5_LIB="
10903 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10904 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10905 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10906 ;; szip is non-free software
10907 (("cp \\$\\{SZIP_LIB\\}.*") "")
10908 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10913 `(("hdf5" ,hdf5-1.10)))
10915 `(("hdf5-source" ,(package-source hdf5-1.10))))
10916 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10917 (synopsis "HDF5 library as an R package")
10918 (description "This package provides C and C++ HDF5 libraries for use in R
10920 (license license:artistic2.0)))
10922 (define-public r-beachmat
10924 (name "r-beachmat")
10929 (uri (bioconductor-uri "beachmat" version))
10932 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10933 (build-system r-build-system)
10938 `(("r-biocgenerics" ,r-biocgenerics)
10939 ("r-delayedarray" ,r-delayedarray)
10940 ("r-hdf5array" ,r-hdf5array)
10942 ("r-rhdf5" ,r-rhdf5)
10943 ("r-rhdf5lib" ,r-rhdf5lib)))
10944 (home-page "https://bioconductor.org/packages/beachmat")
10945 (synopsis "Compiling Bioconductor to handle each matrix type")
10946 (description "This package provides a consistent C++ class interface for a
10947 variety of commonly used matrix types, including sparse and HDF5-backed
10949 (license license:gpl3)))
10951 (define-public r-singlecellexperiment
10953 (name "r-singlecellexperiment")
10958 (uri (bioconductor-uri "SingleCellExperiment" version))
10961 "19r4r7djrn46qlijkj1g926vcklxzcrxjlxv6cg43m9j9jgfs3dj"))))
10963 `((upstream-name . "SingleCellExperiment")))
10964 (build-system r-build-system)
10966 `(("r-biocgenerics" ,r-biocgenerics)
10967 ("r-s4vectors" ,r-s4vectors)
10968 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10969 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10970 (synopsis "S4 classes for single cell data")
10971 (description "This package defines an S4 class for storing data from
10972 single-cell experiments. This includes specialized methods to store and
10973 retrieve spike-in information, dimensionality reduction coordinates and size
10974 factors for each cell, along with the usual metadata for genes and
10976 (license license:gpl3)))
10978 (define-public r-scater
10984 (uri (bioconductor-uri "scater" version))
10987 "1kwa9n70c5j0xcj6nkmlkzjr63cnj78mp8nhg58n07fq1ijm4ns3"))))
10988 (build-system r-build-system)
10990 `(("r-beachmat" ,r-beachmat)
10991 ("r-biocgenerics" ,r-biocgenerics)
10992 ("r-biocparallel" ,r-biocparallel)
10993 ("r-delayedarray" ,r-delayedarray)
10994 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10995 ("r-dplyr" ,r-dplyr)
10996 ("r-ggbeeswarm" ,r-ggbeeswarm)
10997 ("r-ggplot2" ,r-ggplot2)
10998 ("r-matrix" ,r-matrix)
11001 ("r-reshape2" ,r-reshape2)
11002 ("r-rhdf5lib" ,r-rhdf5lib)
11003 ("r-s4vectors" ,r-s4vectors)
11004 ("r-singlecellexperiment" ,r-singlecellexperiment)
11005 ("r-summarizedexperiment" ,r-summarizedexperiment)
11006 ("r-viridis" ,r-viridis)))
11007 (home-page "https://github.com/davismcc/scater")
11008 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11009 (description "This package provides a collection of tools for doing
11010 various analyses of single-cell RNA-seq gene expression data, with a focus on
11012 (license license:gpl2+)))
11014 (define-public r-scran
11021 (uri (bioconductor-uri "scran" version))
11024 "1viyzrwfm9vccsf54c6g7k1dn7skkfx4ml1jy12q67wa20sx8l03"))))
11025 (build-system r-build-system)
11027 `(("r-beachmat" ,r-beachmat)
11028 ("r-biocgenerics" ,r-biocgenerics)
11029 ("r-biocneighbors" ,r-biocneighbors)
11030 ("r-biocparallel" ,r-biocparallel)
11031 ("r-delayedarray" ,r-delayedarray)
11032 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11033 ("r-dynamictreecut" ,r-dynamictreecut)
11034 ("r-edger" ,r-edger)
11035 ("r-igraph" ,r-igraph)
11036 ("r-limma" ,r-limma)
11037 ("r-matrix" ,r-matrix)
11039 ("r-rhdf5lib" ,r-rhdf5lib)
11040 ("r-s4vectors" ,r-s4vectors)
11041 ("r-scater" ,r-scater)
11042 ("r-singlecellexperiment" ,r-singlecellexperiment)
11043 ("r-statmod" ,r-statmod)
11044 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11045 (home-page "https://bioconductor.org/packages/scran")
11046 (synopsis "Methods for single-cell RNA-Seq data analysis")
11047 (description "This package implements a variety of low-level analyses of
11048 single-cell RNA-seq data. Methods are provided for normalization of
11049 cell-specific biases, assignment of cell cycle phase, and detection of highly
11050 variable and significantly correlated genes.")
11051 (license license:gpl3)))
11053 (define-public r-delayedmatrixstats
11055 (name "r-delayedmatrixstats")
11060 (uri (bioconductor-uri "DelayedMatrixStats" version))
11063 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11065 `((upstream-name . "DelayedMatrixStats")))
11066 (build-system r-build-system)
11068 `(("r-biocparallel" ,r-biocparallel)
11069 ("r-delayedarray" ,r-delayedarray)
11070 ("r-hdf5array" ,r-hdf5array)
11071 ("r-iranges" ,r-iranges)
11072 ("r-matrix" ,r-matrix)
11073 ("r-matrixstats" ,r-matrixstats)
11074 ("r-s4vectors" ,r-s4vectors)))
11075 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11076 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11078 "This package provides a port of the @code{matrixStats} API for use with
11079 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11080 contains high-performing functions operating on rows and columns of
11081 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11082 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11083 are optimized per data type and for subsetted calculations such that both
11084 memory usage and processing time is minimized.")
11085 (license license:expat)))
11087 (define-public r-phangorn
11089 (name "r-phangorn")
11094 (uri (cran-uri "phangorn" version))
11097 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11098 (build-system r-build-system)
11101 ("r-fastmatch" ,r-fastmatch)
11102 ("r-igraph" ,r-igraph)
11103 ("r-magrittr" ,r-magrittr)
11104 ("r-matrix" ,r-matrix)
11105 ("r-quadprog" ,r-quadprog)
11106 ("r-rcpp" ,r-rcpp)))
11107 (home-page "https://github.com/KlausVigo/phangorn")
11108 (synopsis "Phylogenetic analysis in R")
11110 "Phangorn is a package for phylogenetic analysis in R. It supports
11111 estimation of phylogenetic trees and networks using Maximum Likelihood,
11112 Maximum Parsimony, distance methods and Hadamard conjugation.")
11113 (license license:gpl2+)))
11115 (define-public r-dropbead
11116 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11119 (name "r-dropbead")
11120 (version (string-append "0-" revision "." (string-take commit 7)))
11124 (uri (git-reference
11125 (url "https://github.com/rajewsky-lab/dropbead.git")
11127 (file-name (git-file-name name version))
11130 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11131 (build-system r-build-system)
11133 `(("r-ggplot2" ,r-ggplot2)
11134 ("r-rcolorbrewer" ,r-rcolorbrewer)
11135 ("r-gridextra" ,r-gridextra)
11136 ("r-gplots" ,r-gplots)
11137 ("r-plyr" ,r-plyr)))
11138 (home-page "https://github.com/rajewsky-lab/dropbead")
11139 (synopsis "Basic exploration and analysis of Drop-seq data")
11140 (description "This package offers a quick and straight-forward way to
11141 explore and perform basic analysis of single cell sequencing data coming from
11142 droplet sequencing. It has been particularly tailored for Drop-seq.")
11143 (license license:gpl3))))
11145 (define htslib-for-sambamba
11146 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11149 (name "htslib-for-sambamba")
11150 (version (string-append "1.3.1-1." (string-take commit 9)))
11154 (uri (git-reference
11155 (url "https://github.com/lomereiter/htslib.git")
11157 (file-name (string-append "htslib-" version "-checkout"))
11160 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11162 `(("autoconf" ,autoconf)
11163 ("automake" ,automake)
11164 ,@(package-native-inputs htslib))))))
11166 (define-public sambamba
11173 (uri (git-reference
11174 (url "https://github.com/lomereiter/sambamba.git")
11175 (commit (string-append "v" version))))
11176 (file-name (string-append name "-" version "-checkout"))
11179 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
11180 (build-system gnu-build-system)
11182 `(#:tests? #f ; there is no test target
11183 #:parallel-build? #f ; not supported
11185 (modify-phases %standard-phases
11186 (delete 'configure)
11187 (add-after 'unpack 'fix-ldc-version
11189 (substitute* "gen_ldc_version_info.py"
11190 (("/usr/bin/env.*") (which "python3")))
11191 (substitute* "Makefile"
11192 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11193 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11195 (add-after 'unpack 'place-biod-and-undead
11196 (lambda* (#:key inputs #:allow-other-keys)
11197 (copy-recursively (assoc-ref inputs "biod") "BioD")
11198 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11200 (add-after 'unpack 'unbundle-prerequisites
11202 (substitute* "Makefile"
11203 (("htslib/libhts.a lz4/lib/liblz4.a")
11205 ((" lz4-static htslib-static") ""))
11208 (lambda* (#:key outputs #:allow-other-keys)
11209 (let* ((out (assoc-ref outputs "out"))
11210 (bin (string-append out "/bin")))
11212 (install-file "bin/sambamba" bin)
11217 ("python" ,python-minimal)
11219 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
11222 (uri (git-reference
11223 (url "https://github.com/biod/BioD.git")
11225 (file-name (string-append "biod-"
11226 (string-take commit 9)
11230 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
11232 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
11235 (uri (git-reference
11236 (url "https://github.com/biod/undeaD.git")
11238 (file-name (string-append "undead-"
11239 (string-take commit 9)
11243 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11246 ("htslib" ,htslib-for-sambamba)))
11247 (home-page "http://lomereiter.github.io/sambamba")
11248 (synopsis "Tools for working with SAM/BAM data")
11249 (description "Sambamba is a high performance modern robust and
11250 fast tool (and library), written in the D programming language, for
11251 working with SAM and BAM files. Current parallelised functionality is
11252 an important subset of samtools functionality, including view, index,
11253 sort, markdup, and depth.")
11254 (license license:gpl2+)))
11256 (define-public ritornello
11258 (name "ritornello")
11262 (uri (git-reference
11263 (url "https://github.com/KlugerLab/Ritornello.git")
11264 (commit (string-append "v" version))))
11265 (file-name (git-file-name name version))
11268 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11269 (build-system gnu-build-system)
11271 `(#:tests? #f ; there are no tests
11273 (modify-phases %standard-phases
11274 (add-after 'unpack 'patch-samtools-references
11275 (lambda* (#:key inputs #:allow-other-keys)
11276 (substitute* '("src/SamStream.h"
11278 (("<sam.h>") "<samtools/sam.h>"))
11280 (delete 'configure)
11282 (lambda* (#:key inputs outputs #:allow-other-keys)
11283 (let* ((out (assoc-ref outputs "out"))
11284 (bin (string-append out "/bin/")))
11286 (install-file "bin/Ritornello" bin)
11289 `(("samtools" ,samtools-0.1)
11293 (home-page "https://github.com/KlugerLab/Ritornello")
11294 (synopsis "Control-free peak caller for ChIP-seq data")
11295 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11296 signal processing that can accurately call binding events without the need to
11297 do a pair total DNA input or IgG control sample. It has been tested for use
11298 with narrow binding events such as transcription factor ChIP-seq.")
11299 (license license:gpl3+)))
11301 (define-public trim-galore
11303 (name "trim-galore")
11308 (uri (git-reference
11309 (url "https://github.com/FelixKrueger/TrimGalore.git")
11311 (file-name (string-append name "-" version "-checkout"))
11314 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11315 (build-system gnu-build-system)
11317 `(#:tests? #f ; no tests
11319 (modify-phases %standard-phases
11320 (delete 'configure)
11322 (add-after 'unpack 'hardcode-tool-references
11323 (lambda* (#:key inputs #:allow-other-keys)
11324 (substitute* "trim_galore"
11325 (("\\$path_to_cutadapt = 'cutadapt'")
11326 (string-append "$path_to_cutadapt = '"
11327 (assoc-ref inputs "cutadapt")
11330 (string-append "| "
11331 (assoc-ref inputs "gzip")
11334 (string-append "\""
11335 (assoc-ref inputs "gzip")
11339 (lambda* (#:key outputs #:allow-other-keys)
11340 (let ((bin (string-append (assoc-ref outputs "out")
11343 (install-file "trim_galore" bin)
11348 ("cutadapt" ,cutadapt)))
11350 `(("unzip" ,unzip)))
11351 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11352 (synopsis "Wrapper around Cutadapt and FastQC")
11353 (description "Trim Galore! is a wrapper script to automate quality and
11354 adapter trimming as well as quality control, with some added functionality to
11355 remove biased methylation positions for RRBS sequence files.")
11356 (license license:gpl3+)))
11358 (define-public gess
11364 (uri (string-append "http://compbio.uthscsa.edu/"
11366 "gess-" version ".src.tar.gz"))
11369 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11370 (build-system gnu-build-system)
11372 `(#:tests? #f ; no tests
11374 (modify-phases %standard-phases
11375 (delete 'configure)
11378 (lambda* (#:key inputs outputs #:allow-other-keys)
11379 (let* ((python (assoc-ref inputs "python"))
11380 (out (assoc-ref outputs "out"))
11381 (bin (string-append out "/bin/"))
11382 (target (string-append
11383 out "/lib/python2.7/site-packages/gess/")))
11385 (copy-recursively "." target)
11386 ;; Make GESS.py executable
11387 (chmod (string-append target "GESS.py") #o555)
11388 ;; Add Python shebang to the top and make Matplotlib
11390 (substitute* (string-append target "GESS.py")
11391 (("\"\"\"Description:" line)
11392 (string-append "#!" (which "python") "
11394 matplotlib.use('Agg')
11396 ;; Make sure GESS has all modules in its path
11397 (wrap-program (string-append target "GESS.py")
11398 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11400 (symlink (string-append target "GESS.py")
11401 (string-append bin "GESS.py"))
11404 `(("python" ,python-2)
11405 ("python2-pysam" ,python2-pysam)
11406 ("python2-scipy" ,python2-scipy)
11407 ("python2-numpy" ,python2-numpy)
11408 ("python2-networkx" ,python2-networkx)
11409 ("python2-biopython" ,python2-biopython)))
11410 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11411 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11413 "GESS is an implementation of a novel computational method to detect de
11414 novo exon-skipping events directly from raw RNA-seq data without the prior
11415 knowledge of gene annotation information. GESS stands for the graph-based
11416 exon-skipping scanner detection scheme.")
11417 (license license:bsd-3)))
11419 (define-public phylip
11426 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11427 "download/phylip-" version ".tar.gz"))
11430 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11431 (build-system gnu-build-system)
11433 `(#:tests? #f ; no check target
11434 #:make-flags (list "-f" "Makefile.unx" "install")
11435 #:parallel-build? #f ; not supported
11437 (modify-phases %standard-phases
11438 (add-after 'unpack 'enter-dir
11439 (lambda _ (chdir "src") #t))
11440 (delete 'configure)
11442 (lambda* (#:key inputs outputs #:allow-other-keys)
11443 (let ((target (string-append (assoc-ref outputs "out")
11446 (for-each (lambda (file)
11447 (install-file file target))
11448 (find-files "../exe" ".*")))
11450 (home-page "http://evolution.genetics.washington.edu/phylip/")
11451 (synopsis "Tools for inferring phylogenies")
11452 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11453 programs for inferring phylogenies (evolutionary trees).")
11454 (license license:bsd-2)))
11463 (uri (string-append "https://integrativemodeling.org/"
11464 version "/download/imp-" version ".tar.gz"))
11467 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11468 (build-system cmake-build-system)
11470 `(;; FIXME: Some tests fail because they produce warnings, others fail
11471 ;; because the PYTHONPATH does not include the modeller's directory.
11479 ("python" ,python-2)))
11481 `(("python2-numpy" ,python2-numpy)
11482 ("python2-scipy" ,python2-scipy)
11483 ("python2-pandas" ,python2-pandas)
11484 ("python2-scikit-learn" ,python2-scikit-learn)
11485 ("python2-networkx" ,python2-networkx)))
11486 (home-page "https://integrativemodeling.org")
11487 (synopsis "Integrative modeling platform")
11488 (description "IMP's broad goal is to contribute to a comprehensive
11489 structural characterization of biomolecules ranging in size and complexity
11490 from small peptides to large macromolecular assemblies, by integrating data
11491 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11492 Python toolbox for solving complex modeling problems, and a number of
11493 applications for tackling some common problems in a user-friendly way.")
11494 ;; IMP is largely available under the GNU Lesser GPL; see the file
11495 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11496 ;; available under the GNU GPL (see the file COPYING.GPL).
11497 (license (list license:lgpl2.1+
11500 (define-public tadbit
11506 (uri (git-reference
11507 (url "https://github.com/3DGenomes/TADbit.git")
11508 (commit (string-append "v" version))))
11509 (file-name (git-file-name name version))
11512 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11513 (build-system python-build-system)
11515 `(;; Tests are included and must be run after installation, but
11516 ;; they are incomplete and thus cannot be run.
11520 (modify-phases %standard-phases
11521 (add-after 'unpack 'fix-problems-with-setup.py
11522 (lambda* (#:key outputs #:allow-other-keys)
11523 ;; setup.py opens these files for writing
11524 (chmod "_pytadbit/_version.py" #o664)
11525 (chmod "README.rst" #o664)
11527 ;; Don't attempt to install the bash completions to
11528 ;; the home directory.
11529 (rename-file "extras/.bash_completion"
11531 (substitute* "setup.py"
11532 (("\\(path.expanduser\\('~'\\)")
11533 (string-append "(\""
11534 (assoc-ref outputs "out")
11535 "/etc/bash_completion.d\""))
11536 (("extras/\\.bash_completion")
11540 ;; TODO: add Chimera for visualization
11543 ("python2-scipy" ,python2-scipy)
11544 ("python2-numpy" ,python2-numpy)
11545 ("python2-matplotlib" ,python2-matplotlib)
11546 ("python2-pysam" ,python2-pysam)))
11547 (home-page "https://3dgenomes.github.io/TADbit/")
11548 (synopsis "Analyze, model, and explore 3C-based data")
11550 "TADbit is a complete Python library to deal with all steps to analyze,
11551 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11552 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11553 correct interaction matrices, identify and compare the so-called
11554 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11555 interaction matrices, and finally, extract structural properties from the
11556 models. TADbit is complemented by TADkit for visualizing 3D models.")
11557 (license license:gpl3+)))
11559 (define-public kentutils
11562 ;; 302.1.0 is out, but the only difference is the inclusion of
11563 ;; pre-built binaries.
11564 (version "302.0.0")
11568 (uri (git-reference
11569 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11570 (commit (string-append "v" version))))
11571 (file-name (git-file-name name version))
11574 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11575 (modules '((guix build utils)
11580 ;; Only the contents of the specified directories are free
11581 ;; for all uses, so we remove the rest. "hg/autoSql" and
11582 ;; "hg/autoXml" are nominally free, but they depend on a
11583 ;; library that is built from the sources in "hg/lib",
11584 ;; which is nonfree.
11585 (let ((free (list "." ".."
11586 "utils" "lib" "inc" "tagStorm"
11587 "parasol" "htslib"))
11588 (directory? (lambda (file)
11589 (eq? 'directory (stat:type (stat file))))))
11590 (for-each (lambda (file)
11591 (and (directory? file)
11592 (delete-file-recursively file)))
11593 (map (cut string-append "src/" <>)
11596 (not (member file free)))))))
11597 ;; Only make the utils target, not the userApps target,
11598 ;; because that requires libraries we won't build.
11599 (substitute* "Makefile"
11600 ((" userApps") " utils"))
11601 ;; Only build libraries that are free.
11602 (substitute* "src/makefile"
11603 (("DIRS =.*") "DIRS =\n")
11604 (("cd jkOwnLib.*") "")
11607 (substitute* "src/utils/makefile"
11608 ;; These tools depend on "jkhgap.a", which is part of the
11609 ;; nonfree "src/hg/lib" directory.
11610 (("raSqlQuery") "")
11611 (("pslLiftSubrangeBlat") "")
11613 ;; Do not build UCSC tools, which may require nonfree
11615 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11617 (build-system gnu-build-system)
11619 `( ;; There is no global test target and the test target for
11620 ;; individual tools depends on input files that are not
11624 (modify-phases %standard-phases
11625 (add-after 'unpack 'fix-permissions
11626 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11627 (add-after 'unpack 'fix-paths
11629 (substitute* "Makefile"
11630 (("/bin/echo") (which "echo")))
11632 (add-after 'unpack 'prepare-samtabix
11633 (lambda* (#:key inputs #:allow-other-keys)
11634 (copy-recursively (assoc-ref inputs "samtabix")
11637 (delete 'configure)
11639 (lambda* (#:key outputs #:allow-other-keys)
11640 (let ((bin (string-append (assoc-ref outputs "out")
11642 (copy-recursively "bin" bin))
11648 (uri (git-reference
11649 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11650 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11653 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11659 ("mariadb" ,mariadb)
11660 ("openssl" ,openssl)))
11661 (home-page "http://genome.cse.ucsc.edu/index.html")
11662 (synopsis "Assorted bioinformatics utilities")
11663 (description "This package provides the kentUtils, a selection of
11664 bioinformatics utilities used in combination with the UCSC genome
11666 ;; Only a subset of the sources are released under a non-copyleft
11667 ;; free software license. All other sources are removed in a
11668 ;; snippet. See this bug report for an explanation of how the
11669 ;; license statements apply:
11670 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11671 (license (license:non-copyleft
11672 "http://genome.ucsc.edu/license/"
11673 "The contents of this package are free for all uses."))))
11675 (define-public f-seq
11676 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11680 (version (string-append "1.1-" revision "." (string-take commit 7)))
11683 (uri (git-reference
11684 (url "https://github.com/aboyle/F-seq.git")
11686 (file-name (string-append name "-" version))
11689 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11690 (modules '((guix build utils)))
11691 ;; Remove bundled Java library archives.
11694 (for-each delete-file (find-files "lib" ".*"))
11696 (build-system ant-build-system)
11698 `(#:tests? #f ; no tests included
11700 (modify-phases %standard-phases
11702 (lambda* (#:key inputs outputs #:allow-other-keys)
11703 (let* ((target (assoc-ref outputs "out"))
11704 (bin (string-append target "/bin"))
11705 (doc (string-append target "/share/doc/f-seq"))
11706 (lib (string-append target "/lib")))
11709 (substitute* "bin/linux/fseq"
11710 (("java") (which "java"))
11711 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11712 (string-append (assoc-ref inputs "java-commons-cli")
11713 "/share/java/commons-cli.jar"))
11715 (string-append "REALDIR=" bin "\n")))
11716 (install-file "README.txt" doc)
11717 (install-file "bin/linux/fseq" bin)
11718 (install-file "build~/fseq.jar" lib)
11719 (copy-recursively "lib" lib)
11723 ("java-commons-cli" ,java-commons-cli)))
11724 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11725 (synopsis "Feature density estimator for high-throughput sequence tags")
11727 "F-Seq is a software package that generates a continuous tag sequence
11728 density estimation allowing identification of biologically meaningful sites
11729 such as transcription factor binding sites (ChIP-seq) or regions of open
11730 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11732 (license license:gpl3+))))
11734 (define-public bismark
11741 (uri (git-reference
11742 (url "https://github.com/FelixKrueger/Bismark.git")
11744 (file-name (string-append name "-" version "-checkout"))
11747 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11750 ;; highcharts.js is non-free software. The code is available under
11751 ;; CC-BY-NC or proprietary licenses only.
11752 (delete-file "bismark_sitrep/highcharts.js")
11754 (build-system perl-build-system)
11756 `(#:tests? #f ; there are no tests
11758 (modify-phases %standard-phases
11759 (delete 'configure)
11762 (lambda* (#:key inputs outputs #:allow-other-keys)
11763 (let* ((out (assoc-ref outputs "out"))
11764 (bin (string-append out "/bin"))
11765 (share (string-append out "/share/bismark"))
11766 (docdir (string-append out "/share/doc/bismark"))
11767 (docs '("Docs/Bismark_User_Guide.html"))
11768 (scripts '("bismark"
11769 "bismark_genome_preparation"
11770 "bismark_methylation_extractor"
11773 "coverage2cytosine"
11774 "deduplicate_bismark"
11775 "filter_non_conversion"
11777 "bismark2summary")))
11778 (substitute* "bismark2report"
11779 (("\\$RealBin/bismark_sitrep")
11780 (string-append share "/bismark_sitrep")))
11784 (for-each (lambda (file) (install-file file bin))
11786 (for-each (lambda (file) (install-file file docdir))
11788 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11789 (copy-recursively "bismark_sitrep"
11790 (string-append share "/bismark_sitrep"))
11792 ;; Fix references to gunzip
11793 (substitute* (map (lambda (file)
11794 (string-append bin "/" file))
11797 (string-append "\"" (assoc-ref inputs "gzip")
11798 "/bin/gunzip -c")))
11802 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11803 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11804 (description "Bismark is a program to map bisulfite treated sequencing
11805 reads to a genome of interest and perform methylation calls in a single step.
11806 The output can be easily imported into a genome viewer, such as SeqMonk, and
11807 enables a researcher to analyse the methylation levels of their samples
11808 straight away. Its main features are:
11811 @item Bisulfite mapping and methylation calling in one single step
11812 @item Supports single-end and paired-end read alignments
11813 @item Supports ungapped and gapped alignments
11814 @item Alignment seed length, number of mismatches etc are adjustable
11815 @item Output discriminates between cytosine methylation in CpG, CHG
11818 (license license:gpl3+)))
11820 (define-public paml
11826 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11827 "paml" version ".tgz"))
11830 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11831 (modules '((guix build utils)))
11832 ;; Remove Windows binaries
11835 (for-each delete-file (find-files "." "\\.exe$"))
11837 (build-system gnu-build-system)
11839 `(#:tests? #f ; there are no tests
11840 #:make-flags '("CC=gcc")
11842 (modify-phases %standard-phases
11843 (replace 'configure
11845 (substitute* "src/BFdriver.c"
11846 (("/bin/bash") (which "bash")))
11850 (lambda* (#:key outputs #:allow-other-keys)
11851 (let ((tools '("baseml" "basemlg" "codeml"
11852 "pamp" "evolver" "yn00" "chi2"))
11853 (bin (string-append (assoc-ref outputs "out") "/bin"))
11854 (docdir (string-append (assoc-ref outputs "out")
11855 "/share/doc/paml")))
11857 (for-each (lambda (file) (install-file file bin)) tools)
11858 (copy-recursively "../doc" docdir)
11860 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11861 (synopsis "Phylogentic analysis by maximum likelihood")
11862 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11863 contains a few programs for model fitting and phylogenetic tree reconstruction
11864 using nucleotide or amino-acid sequence data.")
11866 (license license:gpl3)))
11868 (define-public kallisto
11874 (uri (git-reference
11875 (url "https://github.com/pachterlab/kallisto.git")
11876 (commit (string-append "v" version))))
11877 (file-name (git-file-name name version))
11880 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11881 (build-system cmake-build-system)
11883 `(#:tests? #f ; no "check" target
11885 (modify-phases %standard-phases
11886 (add-after 'unpack 'do-not-use-bundled-htslib
11888 (substitute* "CMakeLists.txt"
11889 (("^ExternalProject_Add" m)
11890 (string-append "if (NEVER)\n" m))
11892 (string-append ")\nendif(NEVER)"))
11893 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11894 (string-append "# " m)))
11895 (substitute* "src/CMakeLists.txt"
11896 (("target_link_libraries\\(kallisto kallisto_core pthread \
11897 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11898 "target_link_libraries(kallisto kallisto_core pthread hts)")
11899 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11905 (home-page "http://pachterlab.github.io/kallisto/")
11906 (synopsis "Near-optimal RNA-Seq quantification")
11908 "Kallisto is a program for quantifying abundances of transcripts from
11909 RNA-Seq data, or more generally of target sequences using high-throughput
11910 sequencing reads. It is based on the novel idea of pseudoalignment for
11911 rapidly determining the compatibility of reads with targets, without the need
11912 for alignment. Pseudoalignment of reads preserves the key information needed
11913 for quantification, and kallisto is therefore not only fast, but also as
11914 accurate as existing quantification tools.")
11915 (license license:bsd-2)))
11917 (define-public libgff
11923 (uri (git-reference
11924 (url "https://github.com/Kingsford-Group/libgff.git")
11925 (commit (string-append "v" version))))
11926 (file-name (git-file-name name version))
11929 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11930 (build-system cmake-build-system)
11931 (arguments `(#:tests? #f)) ; no tests included
11932 (home-page "https://github.com/Kingsford-Group/libgff")
11933 (synopsis "Parser library for reading/writing GFF files")
11934 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11935 code that is used in the Cufflinks codebase. The goal of this library is to
11936 provide this functionality without the necessity of drawing in a heavy-weight
11937 dependency like SeqAn.")
11938 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11940 (define-public libdivsufsort
11942 (name "libdivsufsort")
11946 (uri (git-reference
11947 (url "https://github.com/y-256/libdivsufsort.git")
11949 (file-name (git-file-name name version))
11952 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11953 (build-system cmake-build-system)
11955 '(#:tests? #f ; there are no tests
11957 ;; Needed for rapmap and sailfish.
11958 '("-DBUILD_DIVSUFSORT64=ON")))
11959 (home-page "https://github.com/y-256/libdivsufsort")
11960 (synopsis "Lightweight suffix-sorting library")
11961 (description "libdivsufsort is a software library that implements a
11962 lightweight suffix array construction algorithm. This library provides a
11963 simple and an efficient C API to construct a suffix array and a
11964 Burrows-Wheeler transformed string from a given string over a constant-size
11965 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11966 bytes of memory space, where n is the length of the string.")
11967 (license license:expat)))
11969 (define-public sailfish
11975 (uri (git-reference
11976 (url "https://github.com/kingsfordgroup/sailfish.git")
11977 (commit (string-append "v" version))))
11978 (file-name (git-file-name name version))
11981 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11982 (modules '((guix build utils)))
11985 ;; Delete bundled headers for eigen3.
11986 (delete-file-recursively "include/eigen3/")
11988 (build-system cmake-build-system)
11990 `(#:configure-flags
11991 (list (string-append "-DBOOST_INCLUDEDIR="
11992 (assoc-ref %build-inputs "boost")
11994 (string-append "-DBOOST_LIBRARYDIR="
11995 (assoc-ref %build-inputs "boost")
11997 (string-append "-DBoost_LIBRARIES="
11998 "-lboost_iostreams "
11999 "-lboost_filesystem "
12004 "-lboost_program_options")
12005 "-DBoost_FOUND=TRUE"
12006 ;; Don't download RapMap---we already have it!
12007 "-DFETCHED_RAPMAP=1")
12008 ;; Tests must be run after installation and the location of the test
12009 ;; data file must be overridden. But the tests fail. It looks like
12010 ;; they are not really meant to be run.
12013 (modify-phases %standard-phases
12014 ;; Boost cannot be found, even though it's right there.
12015 (add-after 'unpack 'do-not-look-for-boost
12016 (lambda* (#:key inputs #:allow-other-keys)
12017 (substitute* "CMakeLists.txt"
12018 (("find_package\\(Boost 1\\.53\\.0") "#"))
12020 (add-after 'unpack 'do-not-assign-to-macro
12022 (substitute* "include/spdlog/details/format.cc"
12023 (("const unsigned CHAR_WIDTH = 1;") ""))
12025 (add-after 'unpack 'prepare-rapmap
12026 (lambda* (#:key inputs #:allow-other-keys)
12027 (let ((src "external/install/src/rapmap/")
12028 (include "external/install/include/rapmap/")
12029 (rapmap (assoc-ref inputs "rapmap")))
12030 (mkdir-p "/tmp/rapmap")
12032 (assoc-ref inputs "rapmap")
12034 "--strip-components=1")
12037 (for-each (lambda (file)
12038 (install-file file src))
12039 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12040 (copy-recursively "/tmp/rapmap/include" include))
12042 (add-after 'unpack 'use-system-libraries
12043 (lambda* (#:key inputs #:allow-other-keys)
12044 (substitute* '("src/SailfishIndexer.cpp"
12045 "src/SailfishUtils.cpp"
12046 "src/SailfishQuantify.cpp"
12047 "src/FASTAParser.cpp"
12049 "include/SailfishUtils.hpp"
12050 "include/SailfishIndex.hpp"
12051 "include/CollapsedEMOptimizer.hpp"
12052 "src/CollapsedEMOptimizer.cpp")
12053 (("#include \"jellyfish/config.h\"") ""))
12054 (substitute* "src/CMakeLists.txt"
12055 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12056 (string-append (assoc-ref inputs "jellyfish")
12057 "/include/jellyfish-" ,(package-version jellyfish)))
12058 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12059 (string-append (assoc-ref inputs "jellyfish")
12060 "/lib/libjellyfish-2.0.a"))
12061 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12062 (string-append (assoc-ref inputs "libdivsufsort")
12063 "/lib/libdivsufsort.so"))
12064 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12065 (string-append (assoc-ref inputs "libdivsufsort")
12066 "/lib/libdivsufsort64.so")))
12067 (substitute* "CMakeLists.txt"
12068 ;; Don't prefer static libs
12069 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12070 (("find_package\\(Jellyfish.*") "")
12071 (("ExternalProject_Add\\(libjellyfish") "message(")
12072 (("ExternalProject_Add\\(libgff") "message(")
12073 (("ExternalProject_Add\\(libsparsehash") "message(")
12074 (("ExternalProject_Add\\(libdivsufsort") "message("))
12076 ;; Ensure that Eigen headers can be found
12077 (setenv "CPLUS_INCLUDE_PATH"
12078 (string-append (getenv "CPLUS_INCLUDE_PATH")
12080 (assoc-ref inputs "eigen")
12081 "/include/eigen3"))
12086 ("jemalloc" ,jemalloc)
12087 ("jellyfish" ,jellyfish)
12088 ("sparsehash" ,sparsehash)
12091 (uri (git-reference
12092 (url "https://github.com/COMBINE-lab/RapMap.git")
12093 (commit (string-append "sf-v" version))))
12094 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12097 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12098 (modules '((guix build utils)))
12099 ;; These files are expected to be excluded.
12101 '(begin (delete-file-recursively "include/spdlog")
12102 (for-each delete-file '("include/xxhash.h"
12105 ("libdivsufsort" ,libdivsufsort)
12110 `(("pkg-config" ,pkg-config)))
12111 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12112 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12113 (description "Sailfish is a tool for genomic transcript quantification
12114 from RNA-seq data. It requires a set of target transcripts (either from a
12115 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12116 fasta file containing your reference transcripts and a (set of) fasta/fastq
12117 file(s) containing your reads.")
12118 (license license:gpl3+)))
12120 (define libstadenio-for-salmon
12122 (name "libstadenio")
12126 (uri (git-reference
12127 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12128 (commit (string-append "v" version))))
12129 (file-name (string-append name "-" version "-checkout"))
12132 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12133 (build-system gnu-build-system)
12134 (arguments '(#:parallel-tests? #f)) ; not supported
12138 `(("perl" ,perl))) ; for tests
12139 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12140 (synopsis "General purpose trace and experiment file library")
12141 (description "This package provides a library of file reading and writing
12142 code to provide a general purpose Trace file (and Experiment File) reading
12145 The following file formats are supported:
12148 @item SCF trace files
12149 @item ABI trace files
12150 @item ALF trace files
12151 @item ZTR trace files
12152 @item SFF trace archives
12153 @item SRF trace archives
12154 @item Experiment files
12155 @item Plain text files
12156 @item SAM/BAM sequence files
12157 @item CRAM sequence files
12159 (license license:bsd-3)))
12161 (define spdlog-for-salmon
12167 (uri (git-reference
12168 (url "https://github.com/COMBINE-lab/spdlog.git")
12169 (commit (string-append "v" version))))
12170 (file-name (string-append name "-" version "-checkout"))
12173 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12174 (build-system cmake-build-system)
12175 (home-page "https://github.com/COMBINE-lab/spdlog")
12176 (synopsis "Very fast C++ logging library")
12177 (description "Spdlog is a very fast header-only C++ logging library with
12178 performance as its primary goal.")
12179 (license license:expat)))
12181 ;; This is a modified variant of bwa for use with Salmon. It installs a
12182 ;; library to avoid having to build this as part of Salmon.
12183 (define bwa-for-salmon
12184 (package (inherit bwa)
12186 (version "0.7.12.5")
12189 (uri (git-reference
12190 (url "https://github.com/COMBINE-lab/bwa.git")
12191 (commit (string-append "v" version))))
12192 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12195 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12196 (build-system gnu-build-system)
12198 '(#:tests? #f ;no "check" target
12200 (modify-phases %standard-phases
12202 (lambda* (#:key outputs #:allow-other-keys)
12203 (let* ((out (assoc-ref outputs "out"))
12204 (bin (string-append out "/bin"))
12205 (lib (string-append out "/lib"))
12206 (doc (string-append out "/share/doc/bwa"))
12207 (man (string-append out "/share/man/man1"))
12208 (inc (string-append out "/include/bwa")))
12209 (install-file "bwa" bin)
12210 (install-file "README.md" doc)
12211 (install-file "bwa.1" man)
12212 (install-file "libbwa.a" lib)
12215 (for-each (lambda (file)
12216 (install-file file inc))
12217 (find-files "." "\\.h$")))
12219 ;; no "configure" script
12220 (delete 'configure))))))
12222 (define-public salmon
12228 (uri (git-reference
12229 (url "https://github.com/COMBINE-lab/salmon.git")
12230 (commit (string-append "v" version))))
12231 (file-name (string-append name "-" version "-checkout"))
12234 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12235 (modules '((guix build utils)))
12238 ;; Delete bundled headers for eigen3.
12239 (delete-file-recursively "include/eigen3/")
12241 (build-system cmake-build-system)
12243 `(#:configure-flags
12244 (list (string-append "-DBOOST_INCLUDEDIR="
12245 (assoc-ref %build-inputs "boost")
12247 (string-append "-DBOOST_LIBRARYDIR="
12248 (assoc-ref %build-inputs "boost")
12250 (string-append "-DBoost_LIBRARIES="
12251 "-lboost_iostreams "
12252 "-lboost_filesystem "
12257 "-lboost_program_options")
12258 "-DBoost_FOUND=TRUE"
12259 "-DTBB_LIBRARIES=tbb tbbmalloc"
12260 ;; Don't download RapMap---we already have it!
12261 "-DFETCHED_RAPMAP=1")
12263 (modify-phases %standard-phases
12264 ;; Boost cannot be found, even though it's right there.
12265 (add-after 'unpack 'do-not-look-for-boost
12266 (lambda* (#:key inputs #:allow-other-keys)
12267 (substitute* "CMakeLists.txt"
12268 (("find_package\\(Boost 1\\.53\\.0") "#"))
12270 (add-after 'unpack 'do-not-phone-home
12272 (substitute* "src/Salmon.cpp"
12273 (("getVersionMessage\\(\\)") "\"\""))
12275 (add-after 'unpack 'prepare-rapmap
12276 (lambda* (#:key inputs #:allow-other-keys)
12277 (let ((src "external/install/src/rapmap/")
12278 (include "external/install/include/rapmap/")
12279 (rapmap (assoc-ref inputs "rapmap")))
12282 (for-each (lambda (file)
12283 (install-file file src))
12284 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12285 (copy-recursively (string-append rapmap "/include") include)
12286 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12287 "external/install/include/rapmap/FastxParser.hpp"
12288 "external/install/include/rapmap/concurrentqueue.h"
12289 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12290 "external/install/src/rapmap/FastxParser.cpp"
12291 "external/install/src/rapmap/xxhash.c")))
12293 (add-after 'unpack 'use-system-libraries
12294 (lambda* (#:key inputs #:allow-other-keys)
12295 (substitute* "src/CMakeLists.txt"
12296 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12297 (string-append (assoc-ref inputs "jellyfish")
12298 "/include/jellyfish-" ,(package-version jellyfish)))
12299 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12300 (string-append (assoc-ref inputs "jellyfish")
12301 "/lib/libjellyfish-2.0.a"))
12302 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12303 (string-append (assoc-ref inputs "libdivsufsort")
12304 "/lib/libdivsufsort.so"))
12305 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12306 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12307 "/lib/libstaden-read.a"))
12308 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12309 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12310 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12311 (string-append (assoc-ref inputs "libdivsufsort")
12312 "/lib/libdivsufsort64.so")))
12313 (substitute* "CMakeLists.txt"
12314 ;; Don't prefer static libs
12315 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12316 (("set\\(TBB_LIBRARIES") "message(")
12317 (("find_package\\(Jellyfish.*") "")
12318 (("ExternalProject_Add\\(libcereal") "message(")
12319 (("ExternalProject_Add\\(libbwa") "message(")
12320 (("ExternalProject_Add\\(libjellyfish") "message(")
12321 (("ExternalProject_Add\\(libgff") "message(")
12322 (("ExternalProject_Add\\(libtbb") "message(")
12323 (("ExternalProject_Add\\(libspdlog") "message(")
12324 (("ExternalProject_Add\\(libdivsufsort") "message(")
12325 (("ExternalProject_Add\\(libstadenio") "message(")
12326 (("ExternalProject_Add_Step\\(") "message("))
12328 ;; Ensure that all headers can be found
12329 (setenv "CPLUS_INCLUDE_PATH"
12330 (string-append (getenv "CPLUS_INCLUDE_PATH")
12332 (assoc-ref inputs "bwa")
12335 (assoc-ref inputs "eigen")
12336 "/include/eigen3"))
12338 (string-append (assoc-ref inputs "bwa")
12341 (assoc-ref inputs "eigen")
12342 "/include/eigen3"))
12344 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12345 ;; run. It only exists after the install phase.
12346 (add-after 'unpack 'fix-tests
12348 (substitute* "src/CMakeLists.txt"
12349 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12350 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12354 ("bwa" ,bwa-for-salmon)
12360 (uri (git-reference
12361 (url "https://github.com/COMBINE-lab/RapMap.git")
12362 (commit (string-append "salmon-v" version))))
12363 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12366 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12367 ("jemalloc" ,jemalloc)
12368 ("jellyfish" ,jellyfish)
12371 ("libdivsufsort" ,libdivsufsort)
12372 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12373 ("spdlog-for-salmon" ,spdlog-for-salmon)
12376 (home-page "https://github.com/COMBINE-lab/salmon")
12377 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12378 (description "Salmon is a program to produce highly-accurate,
12379 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12380 its accuracy and speed via a number of different innovations, including the
12381 use of lightweight alignments (accurate but fast-to-compute proxies for
12382 traditional read alignments) and massively-parallel stochastic collapsed
12383 variational inference.")
12384 (license license:gpl3+)))
12386 (define-public python-loompy
12388 (name "python-loompy")
12393 (uri (pypi-uri "loompy" version))
12396 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12397 (build-system python-build-system)
12398 ;; There are no tests
12399 (arguments '(#:tests? #f))
12401 `(("python-h5py" ,python-h5py)
12402 ("python-numpy" ,python-numpy)
12403 ("python-scipy" ,python-scipy)))
12404 (home-page "https://github.com/linnarsson-lab/loompy")
12405 (synopsis "Work with .loom files for single-cell RNA-seq data")
12406 (description "The loom file format is an efficient format for very large
12407 omics datasets, consisting of a main matrix, optional additional layers, a
12408 variable number of row and column annotations. Loom also supports sparse
12409 graphs. This library makes it easy to work with @file{.loom} files for
12410 single-cell RNA-seq data.")
12411 (license license:bsd-3)))
12413 ;; We cannot use the latest commit because it requires Java 9.
12414 (define-public java-forester
12415 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12418 (name "java-forester")
12419 (version (string-append "0-" revision "." (string-take commit 7)))
12422 (uri (git-reference
12423 (url "https://github.com/cmzmasek/forester.git")
12425 (file-name (string-append name "-" version "-checkout"))
12428 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12429 (modules '((guix build utils)))
12432 ;; Delete bundled jars and pre-built classes
12433 (delete-file-recursively "forester/java/resources")
12434 (delete-file-recursively "forester/java/classes")
12435 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12436 ;; Delete bundled applications
12437 (delete-file-recursively "forester_applications")
12439 (build-system ant-build-system)
12441 `(#:tests? #f ; there are none
12443 #:modules ((guix build ant-build-system)
12445 (guix build java-utils)
12449 (modify-phases %standard-phases
12450 (add-after 'unpack 'chdir
12451 (lambda _ (chdir "forester/java") #t))
12452 (add-after 'chdir 'fix-dependencies
12454 (chmod "build.xml" #o664)
12455 (call-with-output-file "build.xml.new"
12459 (with-input-from-file "build.xml"
12460 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12461 `(;; Remove all unjar tags to avoid repacking classes.
12462 (unjar . ,(lambda _ '()))
12463 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12464 (*text* . ,(lambda (_ txt) txt))))
12466 (rename-file "build.xml.new" "build.xml")
12468 ;; FIXME: itext is difficult to package as it depends on a few
12469 ;; unpackaged libraries.
12470 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12472 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12473 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12474 (("pdf_written_to = PdfExporter.*")
12475 "throw new IOException(\"PDF export is not available.\");"))
12477 ;; There is no install target
12478 (replace 'install (install-jars ".")))))
12480 `(("java-commons-codec" ,java-commons-codec)
12481 ("java-openchart2" ,java-openchart2)))
12482 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12483 (synopsis "Phylogenomics libraries for Java")
12484 (description "Forester is a collection of Java libraries for
12485 phylogenomics and evolutionary biology research. It includes support for
12486 reading, writing, and exporting phylogenetic trees.")
12487 (license license:lgpl2.1+))))
12489 (define-public java-forester-1.005
12491 (name "java-forester")
12495 (uri (string-append "http://search.maven.org/remotecontent?"
12496 "filepath=org/biojava/thirdparty/forester/"
12497 version "/forester-" version "-sources.jar"))
12498 (file-name (string-append name "-" version ".jar"))
12501 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12502 (build-system ant-build-system)
12504 `(#:tests? #f ; there are none
12506 #:modules ((guix build ant-build-system)
12508 (guix build java-utils)
12512 (modify-phases %standard-phases
12513 (add-after 'unpack 'fix-dependencies
12514 (lambda* (#:key inputs #:allow-other-keys)
12515 (call-with-output-file "build.xml"
12519 (with-input-from-file "src/build.xml"
12520 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12521 `(;; Remove all unjar tags to avoid repacking classes.
12522 (unjar . ,(lambda _ '()))
12523 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12524 (*text* . ,(lambda (_ txt) txt))))
12526 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12527 "synth_look_and_feel_1.xml")
12528 (copy-file (assoc-ref inputs "phyloxml.xsd")
12530 (substitute* "build.xml"
12531 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12532 "synth_look_and_feel_1.xml")
12533 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12536 ;; FIXME: itext is difficult to package as it depends on a few
12537 ;; unpackaged libraries.
12538 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12540 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12541 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12542 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12543 (("pdf_written_to = PdfExporter.*")
12544 "throw new IOException(\"PDF export is not available.\"); /*")
12545 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12546 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12548 (add-after 'unpack 'delete-pre-built-classes
12549 (lambda _ (delete-file-recursively "src/classes") #t))
12550 ;; There is no install target
12551 (replace 'install (install-jars ".")))))
12553 `(("java-commons-codec" ,java-commons-codec)
12554 ("java-openchart2" ,java-openchart2)))
12555 ;; The source archive does not contain the resources.
12560 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12561 "b61cc2dcede0bede317db362472333115756b8c6/"
12562 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12563 (file-name (string-append name "-phyloxml-" version ".xsd"))
12566 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12567 ("synth_look_and_feel_1.xml"
12570 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12571 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12572 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12573 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12576 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12577 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12578 (synopsis "Phylogenomics libraries for Java")
12579 (description "Forester is a collection of Java libraries for
12580 phylogenomics and evolutionary biology research. It includes support for
12581 reading, writing, and exporting phylogenetic trees.")
12582 (license license:lgpl2.1+)))
12584 (define-public java-biojava-core
12586 (name "java-biojava-core")
12590 (uri (git-reference
12591 (url "https://github.com/biojava/biojava")
12592 (commit (string-append "biojava-" version))))
12593 (file-name (string-append name "-" version "-checkout"))
12596 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12597 (build-system ant-build-system)
12600 #:jar-name "biojava-core.jar"
12601 #:source-dir "biojava-core/src/main/java/"
12602 #:test-dir "biojava-core/src/test"
12603 ;; These tests seem to require internet access.
12604 #:test-exclude (list "**/SearchIOTest.java"
12605 "**/BlastXMLParserTest.java"
12606 "**/GenbankCookbookTest.java"
12607 "**/GenbankProxySequenceReaderTest.java")
12609 (modify-phases %standard-phases
12610 (add-before 'build 'copy-resources
12612 (copy-recursively "biojava-core/src/main/resources"
12615 (add-before 'check 'copy-test-resources
12617 (copy-recursively "biojava-core/src/test/resources"
12618 "build/test-classes")
12621 `(("java-log4j-api" ,java-log4j-api)
12622 ("java-log4j-core" ,java-log4j-core)
12623 ("java-slf4j-api" ,java-slf4j-api)
12624 ("java-slf4j-simple" ,java-slf4j-simple)))
12626 `(("java-junit" ,java-junit)
12627 ("java-hamcrest-core" ,java-hamcrest-core)))
12628 (home-page "http://biojava.org")
12629 (synopsis "Core libraries of Java framework for processing biological data")
12630 (description "BioJava is a project dedicated to providing a Java framework
12631 for processing biological data. It provides analytical and statistical
12632 routines, parsers for common file formats, reference implementations of
12633 popular algorithms, and allows the manipulation of sequences and 3D
12634 structures. The goal of the biojava project is to facilitate rapid
12635 application development for bioinformatics.
12637 This package provides the core libraries.")
12638 (license license:lgpl2.1+)))
12640 (define-public java-biojava-phylo
12641 (package (inherit java-biojava-core)
12642 (name "java-biojava-phylo")
12643 (build-system ant-build-system)
12646 #:jar-name "biojava-phylo.jar"
12647 #:source-dir "biojava-phylo/src/main/java/"
12648 #:test-dir "biojava-phylo/src/test"
12650 (modify-phases %standard-phases
12651 (add-before 'build 'copy-resources
12653 (copy-recursively "biojava-phylo/src/main/resources"
12656 (add-before 'check 'copy-test-resources
12658 (copy-recursively "biojava-phylo/src/test/resources"
12659 "build/test-classes")
12662 `(("java-log4j-api" ,java-log4j-api)
12663 ("java-log4j-core" ,java-log4j-core)
12664 ("java-slf4j-api" ,java-slf4j-api)
12665 ("java-slf4j-simple" ,java-slf4j-simple)
12666 ("java-biojava-core" ,java-biojava-core)
12667 ("java-forester" ,java-forester)))
12669 `(("java-junit" ,java-junit)
12670 ("java-hamcrest-core" ,java-hamcrest-core)))
12671 (home-page "http://biojava.org")
12672 (synopsis "Biojava interface to the forester phylogenomics library")
12673 (description "The phylo module provides a biojava interface layer to the
12674 forester phylogenomics library for constructing phylogenetic trees.")))
12676 (define-public java-biojava-alignment
12677 (package (inherit java-biojava-core)
12678 (name "java-biojava-alignment")
12679 (build-system ant-build-system)
12682 #:jar-name "biojava-alignment.jar"
12683 #:source-dir "biojava-alignment/src/main/java/"
12684 #:test-dir "biojava-alignment/src/test"
12686 (modify-phases %standard-phases
12687 (add-before 'build 'copy-resources
12689 (copy-recursively "biojava-alignment/src/main/resources"
12692 (add-before 'check 'copy-test-resources
12694 (copy-recursively "biojava-alignment/src/test/resources"
12695 "build/test-classes")
12698 `(("java-log4j-api" ,java-log4j-api)
12699 ("java-log4j-core" ,java-log4j-core)
12700 ("java-slf4j-api" ,java-slf4j-api)
12701 ("java-slf4j-simple" ,java-slf4j-simple)
12702 ("java-biojava-core" ,java-biojava-core)
12703 ("java-biojava-phylo" ,java-biojava-phylo)
12704 ("java-forester" ,java-forester)))
12706 `(("java-junit" ,java-junit)
12707 ("java-hamcrest-core" ,java-hamcrest-core)))
12708 (home-page "http://biojava.org")
12709 (synopsis "Biojava API for genetic sequence alignment")
12710 (description "The alignment module of BioJava provides an API that
12714 @item implementations of dynamic programming algorithms for sequence
12716 @item reading and writing of popular alignment file formats;
12717 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12720 (define-public java-biojava-core-4.0
12721 (package (inherit java-biojava-core)
12722 (name "java-biojava-core")
12726 (uri (git-reference
12727 (url "https://github.com/biojava/biojava")
12728 (commit (string-append "biojava-" version))))
12729 (file-name (string-append name "-" version "-checkout"))
12732 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12734 (define-public java-biojava-phylo-4.0
12735 (package (inherit java-biojava-core-4.0)
12736 (name "java-biojava-phylo")
12737 (build-system ant-build-system)
12740 #:jar-name "biojava-phylo.jar"
12741 #:source-dir "biojava-phylo/src/main/java/"
12742 #:test-dir "biojava-phylo/src/test"
12744 (modify-phases %standard-phases
12745 (add-before 'build 'copy-resources
12747 (copy-recursively "biojava-phylo/src/main/resources"
12750 (add-before 'check 'copy-test-resources
12752 (copy-recursively "biojava-phylo/src/test/resources"
12753 "build/test-classes")
12756 `(("java-log4j-api" ,java-log4j-api)
12757 ("java-log4j-core" ,java-log4j-core)
12758 ("java-slf4j-api" ,java-slf4j-api)
12759 ("java-slf4j-simple" ,java-slf4j-simple)
12760 ("java-biojava-core" ,java-biojava-core-4.0)
12761 ("java-forester" ,java-forester-1.005)))
12763 `(("java-junit" ,java-junit)
12764 ("java-hamcrest-core" ,java-hamcrest-core)))
12765 (home-page "http://biojava.org")
12766 (synopsis "Biojava interface to the forester phylogenomics library")
12767 (description "The phylo module provides a biojava interface layer to the
12768 forester phylogenomics library for constructing phylogenetic trees.")))
12770 (define-public java-biojava-alignment-4.0
12771 (package (inherit java-biojava-core-4.0)
12772 (name "java-biojava-alignment")
12773 (build-system ant-build-system)
12776 #:jar-name "biojava-alignment.jar"
12777 #:source-dir "biojava-alignment/src/main/java/"
12778 #:test-dir "biojava-alignment/src/test"
12780 (modify-phases %standard-phases
12781 (add-before 'build 'copy-resources
12783 (copy-recursively "biojava-alignment/src/main/resources"
12786 (add-before 'check 'copy-test-resources
12788 (copy-recursively "biojava-alignment/src/test/resources"
12789 "build/test-classes")
12792 `(("java-log4j-api" ,java-log4j-api)
12793 ("java-log4j-core" ,java-log4j-core)
12794 ("java-slf4j-api" ,java-slf4j-api)
12795 ("java-slf4j-simple" ,java-slf4j-simple)
12796 ("java-biojava-core" ,java-biojava-core-4.0)
12797 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12798 ("java-forester" ,java-forester-1.005)))
12800 `(("java-junit" ,java-junit)
12801 ("java-hamcrest-core" ,java-hamcrest-core)))
12802 (home-page "http://biojava.org")
12803 (synopsis "Biojava API for genetic sequence alignment")
12804 (description "The alignment module of BioJava provides an API that
12808 @item implementations of dynamic programming algorithms for sequence
12810 @item reading and writing of popular alignment file formats;
12811 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12814 (define-public dropseq-tools
12816 (name "dropseq-tools")
12821 (uri "http://mccarrolllab.com/download/1276/")
12822 (file-name (string-append "dropseq-tools-" version ".zip"))
12825 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12826 ;; Delete bundled libraries
12827 (modules '((guix build utils)))
12830 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12831 (delete-file-recursively "3rdParty")
12833 (build-system ant-build-system)
12835 `(#:tests? #f ; test data are not included
12836 #:test-target "test"
12837 #:build-target "all"
12838 #:source-dir "public/src/"
12841 (list (string-append "-Dpicard.executable.dir="
12842 (assoc-ref %build-inputs "java-picard")
12844 #:modules ((ice-9 match)
12847 (guix build java-utils)
12848 (guix build ant-build-system))
12850 (modify-phases %standard-phases
12851 ;; FIXME: fails with "java.io.FileNotFoundException:
12852 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12853 (delete 'generate-jar-indices)
12854 ;; All dependencies must be linked to "lib", because that's where
12855 ;; they will be searched for when the Class-Path property of the
12856 ;; manifest is computed.
12857 (add-after 'unpack 'record-references
12858 (lambda* (#:key inputs #:allow-other-keys)
12859 (mkdir-p "jar/lib")
12860 (let ((dirs (filter-map (match-lambda
12862 (if (and (string-prefix? "java-" name)
12863 (not (string=? name "java-testng")))
12866 (for-each (lambda (jar)
12867 (symlink jar (string-append "jar/lib/" (basename jar))))
12868 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12871 ;; There is no installation target
12873 (lambda* (#:key inputs outputs #:allow-other-keys)
12874 (let* ((out (assoc-ref outputs "out"))
12875 (bin (string-append out "/bin"))
12876 (share (string-append out "/share/java/"))
12877 (lib (string-append share "/lib/"))
12878 (scripts (list "BAMTagHistogram"
12879 "BAMTagofTagCounts"
12880 "BaseDistributionAtReadPosition"
12881 "CollapseBarcodesInPlace"
12882 "CollapseTagWithContext"
12884 "CreateIntervalsFiles"
12885 "DetectBeadSynthesisErrors"
12886 "DigitalExpression"
12887 "Drop-seq_alignment.sh"
12890 "GatherGeneGCLength"
12891 "GatherMolecularBarcodeDistributionByGene"
12892 "GatherReadQualityMetrics"
12895 "SelectCellsByNumTranscripts"
12896 "SingleCellRnaSeqMetricsCollector"
12897 "TagBamWithReadSequenceExtended"
12898 "TagReadWithGeneExon"
12899 "TagReadWithInterval"
12900 "TrimStartingSequence"
12901 "ValidateReference")))
12902 (for-each mkdir-p (list bin share lib))
12903 (install-file "dist/dropseq.jar" share)
12904 (for-each (lambda (script)
12905 (chmod script #o555)
12906 (install-file script bin))
12908 (substitute* (map (lambda (script)
12909 (string-append bin "/" script))
12911 (("^java") (which "java"))
12912 (("jar_deploy_dir=.*")
12913 (string-append "jar_deploy_dir=" share "\n"))))
12915 ;; FIXME: We do this after stripping jars because we don't want it to
12916 ;; copy all these jars and strip them. We only want to install
12917 ;; links. Arguably, this is a problem with the ant-build-system.
12918 (add-after 'strip-jar-timestamps 'install-links
12919 (lambda* (#:key outputs #:allow-other-keys)
12920 (let* ((out (assoc-ref outputs "out"))
12921 (share (string-append out "/share/java/"))
12922 (lib (string-append share "/lib/")))
12923 (for-each (lambda (jar)
12924 (symlink (readlink jar)
12925 (string-append lib (basename jar))))
12926 (find-files "jar/lib" "\\.jar$")))
12929 `(("jdk" ,icedtea-8)
12930 ("java-picard" ,java-picard-2.10.3)
12931 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12932 ("java-commons-math3" ,java-commons-math3)
12933 ("java-commons-jexl2" ,java-commons-jexl-2)
12934 ("java-commons-collections4" ,java-commons-collections4)
12935 ("java-commons-lang2" ,java-commons-lang)
12936 ("java-commons-io" ,java-commons-io)
12937 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12938 ("java-guava" ,java-guava)
12939 ("java-la4j" ,java-la4j)
12940 ("java-biojava-core" ,java-biojava-core-4.0)
12941 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12942 ("java-jdistlib" ,java-jdistlib)
12943 ("java-simple-xml" ,java-simple-xml)
12944 ("java-snakeyaml" ,java-snakeyaml)))
12947 ("java-testng" ,java-testng)))
12948 (home-page "http://mccarrolllab.com/dropseq/")
12949 (synopsis "Tools for Drop-seq analyses")
12950 (description "Drop-seq is a technology to enable biologists to
12951 analyze RNA expression genome-wide in thousands of individual cells at
12952 once. This package provides tools to perform Drop-seq analyses.")
12953 (license license:expat)))
12955 (define-public pigx-rnaseq
12957 (name "pigx-rnaseq")
12961 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12962 "releases/download/v" version
12963 "/pigx_rnaseq-" version ".tar.gz"))
12966 "16gla23rmziimqan7w494q0nr7vfbp42zzkrl9fracmr4k7b1kzr"))))
12967 (build-system gnu-build-system)
12969 `(#:parallel-tests? #f ; not supported
12971 (modify-phases %standard-phases
12972 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12973 (add-after 'unpack 'disable-resource-intensive-test
12975 (substitute* "Makefile.in"
12976 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12977 (("^ tests/test_multiqc/test.sh") "")
12978 (("^ test.sh") ""))
12982 ("snakemake" ,snakemake-4)
12984 ("multiqc" ,multiqc)
12986 ("trim-galore" ,trim-galore)
12988 ("samtools" ,samtools)
12989 ("bedtools" ,bedtools)
12990 ("r-minimal" ,r-minimal)
12991 ("r-rmarkdown" ,r-rmarkdown)
12992 ("r-ggplot2" ,r-ggplot2)
12993 ("r-ggrepel" ,r-ggrepel)
12994 ("r-gprofiler" ,r-gprofiler)
12995 ("r-deseq2" ,r-deseq2)
12997 ("r-knitr" ,r-knitr)
12998 ("r-pheatmap" ,r-pheatmap)
12999 ("r-corrplot" ,r-corrplot)
13000 ("r-reshape2" ,r-reshape2)
13001 ("r-plotly" ,r-plotly)
13002 ("r-scales" ,r-scales)
13003 ("r-summarizedexperiment" ,r-summarizedexperiment)
13004 ("r-crosstalk" ,r-crosstalk)
13005 ("r-tximport" ,r-tximport)
13006 ("r-rtracklayer" ,r-rtracklayer)
13007 ("r-rjson" ,r-rjson)
13009 ("ghc-pandoc" ,ghc-pandoc)
13010 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13011 ("python-wrapper" ,python-wrapper)
13012 ("python-pyyaml" ,python-pyyaml)))
13013 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13014 (synopsis "Analysis pipeline for RNA sequencing experiments")
13015 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
13016 reporting for RNA sequencing experiments. It is easy to use and produces high
13017 quality reports. The inputs are reads files from the sequencing experiment,
13018 and a configuration file which describes the experiment. In addition to
13019 quality control of the experiment, the pipeline produces a differential
13020 expression report comparing samples in an easily configurable manner.")
13021 (license license:gpl3+)))
13023 (define-public pigx-chipseq
13025 (name "pigx-chipseq")
13029 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
13030 "releases/download/v" version
13031 "/pigx_chipseq-" version ".tar.gz"))
13034 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
13035 (build-system gnu-build-system)
13036 ;; parts of the tests rely on access to the network
13037 (arguments '(#:tests? #f))
13040 ("coreutils" ,coreutils)
13041 ("r-minimal" ,r-minimal)
13042 ("r-argparser" ,r-argparser)
13043 ("r-biocparallel" ,r-biocparallel)
13044 ("r-biostrings" ,r-biostrings)
13045 ("r-chipseq" ,r-chipseq)
13046 ("r-data-table" ,r-data-table)
13047 ("r-dplyr" ,r-dplyr)
13048 ("r-genomation" ,r-genomation)
13049 ("r-genomicalignments" ,r-genomicalignments)
13050 ("r-genomicranges" ,r-genomicranges)
13051 ("r-rsamtools" ,r-rsamtools)
13052 ("r-rtracklayer" ,r-rtracklayer)
13053 ("r-s4vectors" ,r-s4vectors)
13054 ("r-stringr" ,r-stringr)
13055 ("r-tibble" ,r-tibble)
13056 ("r-tidyr" ,r-tidyr)
13057 ("r-jsonlite" ,r-jsonlite)
13058 ("r-heatmaply" ,r-heatmaply)
13059 ("r-htmlwidgets" ,r-htmlwidgets)
13060 ("r-ggplot2" ,r-ggplot2)
13061 ("r-plotly" ,r-plotly)
13062 ("r-rmarkdown" ,r-rmarkdown)
13063 ("python-wrapper" ,python-wrapper)
13064 ("python-pyyaml" ,python-pyyaml)
13065 ("python-magic" ,python-magic)
13066 ("python-xlrd" ,python-xlrd)
13067 ("trim-galore" ,trim-galore)
13069 ("multiqc" ,multiqc)
13071 ("ghc-pandoc" ,ghc-pandoc)
13072 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13076 ("snakemake" ,snakemake)
13077 ("samtools" ,samtools)
13078 ("bedtools" ,bedtools)
13079 ("kentutils" ,kentutils)))
13081 `(("python-pytest" ,python-pytest)))
13082 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13083 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13084 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13085 calling and reporting for ChIP sequencing experiments. It is easy to use and
13086 produces high quality reports. The inputs are reads files from the sequencing
13087 experiment, and a configuration file which describes the experiment. In
13088 addition to quality control of the experiment, the pipeline enables to set up
13089 multiple peak calling analysis and allows the generation of a UCSC track hub
13090 in an easily configurable manner.")
13091 (license license:gpl3+)))
13093 (define-public pigx-bsseq
13095 (name "pigx-bsseq")
13099 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13100 "releases/download/v" version
13101 "/pigx_bsseq-" version ".tar.gz"))
13104 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13105 (build-system gnu-build-system)
13108 (modify-phases %standard-phases
13109 (add-before 'check 'set-timezone
13110 ;; The readr package is picky about timezones.
13111 (lambda* (#:key inputs #:allow-other-keys)
13112 (setenv "TZ" "UTC+1")
13114 (string-append (assoc-ref inputs "tzdata")
13115 "/share/zoneinfo"))
13118 `(("tzdata" ,tzdata)))
13120 `(("coreutils" ,coreutils)
13123 ("r-minimal" ,r-minimal)
13124 ("r-annotationhub" ,r-annotationhub)
13126 ("r-genomation" ,r-genomation)
13127 ("r-methylkit" ,r-methylkit)
13128 ("r-rtracklayer" ,r-rtracklayer)
13129 ("r-rmarkdown" ,r-rmarkdown)
13130 ("r-bookdown" ,r-bookdown)
13131 ("r-ggplot2" ,r-ggplot2)
13132 ("r-ggbio" ,r-ggbio)
13133 ("ghc-pandoc" ,ghc-pandoc)
13134 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13135 ("python-wrapper" ,python-wrapper)
13136 ("python-pyyaml" ,python-pyyaml)
13137 ("snakemake" ,snakemake)
13138 ("bismark" ,bismark)
13141 ("trim-galore" ,trim-galore)
13142 ("cutadapt" ,cutadapt)
13143 ("samtools" ,samtools)))
13144 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13145 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13146 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13147 data of bisulfite experiments; it produces reports on aggregate methylation
13148 and coverage and can be used to produce information on differential
13149 methylation and segmentation.")
13150 (license license:gpl3+)))
13152 (define-public pigx-scrnaseq
13154 (name "pigx-scrnaseq")
13158 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13159 "releases/download/v" version
13160 "/pigx_scrnaseq-" version ".tar.gz"))
13163 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13164 (build-system gnu-build-system)
13166 `(#:configure-flags
13167 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13168 "/share/java/picard.jar")
13169 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13170 "/share/java/dropseq.jar"))))
13172 `(("coreutils" ,coreutils)
13174 ("dropseq-tools" ,dropseq-tools)
13176 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13177 ("java" ,icedtea-8)
13178 ("python-wrapper" ,python-wrapper)
13179 ("python-pyyaml" ,python-pyyaml)
13180 ("python-pandas" ,python-pandas)
13181 ("python-magic" ,python-magic)
13182 ("python-numpy" ,python-numpy)
13183 ("python-loompy" ,python-loompy)
13184 ("ghc-pandoc" ,ghc-pandoc)
13185 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13186 ("samtools" ,samtools)
13187 ("snakemake" ,snakemake)
13189 ("r-minimal" ,r-minimal)
13190 ("r-argparser" ,r-argparser)
13191 ("r-cowplot" ,r-cowplot)
13192 ("r-data-table" ,r-data-table)
13193 ("r-delayedarray" ,r-delayedarray)
13194 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13195 ("r-dplyr" ,r-dplyr)
13196 ("r-dropbead" ,r-dropbead)
13198 ("r-genomicalignments" ,r-genomicalignments)
13199 ("r-genomicfiles" ,r-genomicfiles)
13200 ("r-genomicranges" ,r-genomicranges)
13201 ("r-ggplot2" ,r-ggplot2)
13202 ("r-hdf5array" ,r-hdf5array)
13203 ("r-pheatmap" ,r-pheatmap)
13204 ("r-rmarkdown" ,r-rmarkdown)
13205 ("r-rsamtools" ,r-rsamtools)
13206 ("r-rtracklayer" ,r-rtracklayer)
13207 ("r-rtsne" ,r-rtsne)
13208 ("r-scater" ,r-scater)
13209 ("r-scran" ,r-scran)
13210 ("r-singlecellexperiment" ,r-singlecellexperiment)
13211 ("r-stringr" ,r-stringr)
13212 ("r-yaml" ,r-yaml)))
13213 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13214 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13215 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13216 quality control for single cell RNA sequencing experiments. The inputs are
13217 read files from the sequencing experiment, and a configuration file which
13218 describes the experiment. It produces processed files for downstream analysis
13219 and interactive quality reports. The pipeline is designed to work with UMI
13221 (license license:gpl3+)))
13223 (define-public pigx
13229 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13230 "releases/download/v" version
13231 "/pigx-" version ".tar.gz"))
13234 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13235 (build-system gnu-build-system)
13237 `(("python" ,python)
13238 ("pigx-bsseq" ,pigx-bsseq)
13239 ("pigx-chipseq" ,pigx-chipseq)
13240 ("pigx-rnaseq" ,pigx-rnaseq)
13241 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13242 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13243 (synopsis "Analysis pipelines for genomics")
13244 (description "PiGx is a collection of genomics pipelines. It includes the
13245 following pipelines:
13248 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13249 @item PiGx RNAseq for RNAseq samples
13250 @item PiGx scRNAseq for single cell dropseq analysis
13251 @item PiGx ChIPseq for reads from ChIPseq experiments
13254 All pipelines are easily configured with a simple sample sheet and a
13255 descriptive settings file. The result is a set of comprehensive, interactive
13256 HTML reports with interesting findings about your samples.")
13257 (license license:gpl3+)))
13259 (define-public r-diversitree
13261 (name "r-diversitree")
13266 (uri (cran-uri "diversitree" version))
13269 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13270 (build-system r-build-system)
13272 `(("gfortran" ,gfortran)))
13273 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13276 ("r-desolve" ,r-desolve)
13278 ("r-suplex" ,r-subplex)))
13279 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13280 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13281 (description "This package contains a number of comparative \"phylogenetic\"
13282 methods, mostly focusing on analysing diversification and character evolution.
13283 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13284 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13285 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13286 include Markov models of discrete and continuous trait evolution and constant
13287 rate speciation and extinction.")
13288 (license license:gpl2+)))
13290 (define-public sjcount
13291 ;; There is no tag for version 3.2, nor is there a release archive.
13292 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13296 (version (git-version "3.2" revision commit))
13299 (uri (git-reference
13300 (url "https://github.com/pervouchine/sjcount-full.git")
13302 (file-name (string-append name "-" version "-checkout"))
13305 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13306 (build-system gnu-build-system)
13308 `(#:tests? #f ; requires a 1.4G test file
13310 (list (string-append "SAMTOOLS_DIR="
13311 (assoc-ref %build-inputs "samtools")
13314 (modify-phases %standard-phases
13315 (replace 'configure
13316 (lambda* (#:key inputs #:allow-other-keys)
13317 (substitute* "makefile"
13318 (("-I \\$\\{SAMTOOLS_DIR\\}")
13319 (string-append "-I" (assoc-ref inputs "samtools")
13320 "/include/samtools"))
13321 (("-lz ") "-lz -lpthread "))
13324 (lambda* (#:key outputs #:allow-other-keys)
13325 (for-each (lambda (tool)
13327 (string-append (assoc-ref outputs "out")
13329 '("j_count" "b_count" "sjcount"))
13332 `(("samtools" ,samtools-0.1)
13334 (home-page "https://github.com/pervouchine/sjcount-full/")
13335 (synopsis "Annotation-agnostic splice junction counting pipeline")
13336 (description "Sjcount is a utility for fast quantification of splice
13337 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13338 version does count multisplits.")
13339 (license license:gpl3+))))
13341 (define-public minimap2
13348 (uri (string-append "https://github.com/lh3/minimap2/"
13349 "releases/download/v" version "/"
13350 "minimap2-" version ".tar.bz2"))
13353 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13354 (build-system gnu-build-system)
13356 `(#:tests? #f ; there are none
13359 (let ((system ,(or (%current-target-system)
13360 (%current-system))))
13362 ((string-prefix? "x86_64" system)
13364 ((or (string-prefix? "armhf" system)
13365 (string-prefix? "aarch64" system))
13367 (_ "sse2only=1"))))
13369 (modify-phases %standard-phases
13370 (delete 'configure)
13372 (lambda* (#:key outputs #:allow-other-keys)
13373 (let* ((out (assoc-ref outputs "out"))
13374 (bin (string-append out "/bin"))
13375 (man (string-append out "/share/man/man1")))
13376 (install-file "minimap2" bin)
13378 (install-file "minimap2.1" man))
13382 (home-page "https://lh3.github.io/minimap2/")
13383 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13384 (description "Minimap2 is a versatile sequence alignment program that
13385 aligns DNA or mRNA sequences against a large reference database. Typical use
13389 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13390 @item finding overlaps between long reads with error rate up to ~15%;
13391 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13392 reads against a reference genome;
13393 @item aligning Illumina single- or paired-end reads;
13394 @item assembly-to-assembly alignment;
13395 @item full-genome alignment between two closely related species with
13396 divergence below ~15%.
13398 (license license:expat)))
13400 (define-public r-circus
13407 (uri (git-reference
13408 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13409 (commit (string-append "v" version))))
13410 (file-name (git-file-name name version))
13413 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13414 (build-system r-build-system)
13416 `(("r-annotationdbi" ,r-annotationdbi)
13417 ("r-annotationhub" ,r-annotationhub)
13418 ("r-biomart" ,r-biomart)
13419 ("r-data-table" ,r-data-table)
13421 ("r-genomicfeatures" ,r-genomicfeatures)
13422 ("r-genomicranges" ,r-genomicranges)
13423 ("r-ggplot2" ,r-ggplot2)
13425 ("r-iranges" ,r-iranges)
13426 ("r-rcolorbrewer" ,r-rcolorbrewer)
13427 ("r-rmysql" ,r-rmysql)
13428 ("r-s4vectors" ,r-s4vectors)
13429 ("r-stringr" ,r-stringr)
13430 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13432 `(("r-knitr" ,r-knitr)))
13433 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13434 (synopsis "Annotation, analysis and visualization of circRNA data")
13435 (description "Circus is an R package for annotation, analysis and
13436 visualization of circRNA data. Users can annotate their circRNA candidates
13437 with host genes, gene featrues they are spliced from, and discriminate between
13438 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13439 can be calculated, and a number of descriptive plots easily generated.")
13440 (license license:artistic2.0)))
13442 (define-public r-loomr
13443 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13447 (version (git-version "0.2.0" revision commit))
13451 (uri (git-reference
13452 (url "https://github.com/mojaveazure/loomR.git")
13454 (file-name (git-file-name name version))
13457 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13458 (build-system r-build-system)
13461 ("r-hdf5r" ,r-hdf5r)
13462 ("r-iterators" ,r-iterators)
13463 ("r-itertools" ,r-itertools)
13464 ("r-matrix" ,r-matrix)))
13465 (home-page "https://github.com/mojaveazure/loomR")
13466 (synopsis "R interface for loom files")
13467 (description "This package provides an R interface to access, create,
13468 and modify loom files. loomR aims to be completely compatible with loompy.")
13469 (license license:gpl3))))
13471 (define-public gffread
13472 ;; We cannot use the tagged release because it is not in sync with gclib.
13473 ;; See https://github.com/gpertea/gffread/issues/26
13474 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13478 (version (git-version "0.9.12" revision commit))
13482 (uri (git-reference
13483 (url "https://github.com/gpertea/gffread.git")
13485 (file-name (git-file-name name version))
13488 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13489 (build-system gnu-build-system)
13491 `(#:tests? #f ; no check target
13493 (list "GCLDIR=gclib")
13495 (modify-phases %standard-phases
13496 (delete 'configure)
13497 (add-after 'unpack 'copy-gclib-source
13498 (lambda* (#:key inputs #:allow-other-keys)
13500 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13502 ;; There is no install target
13504 (lambda* (#:key outputs #:allow-other-keys)
13505 (let* ((out (assoc-ref outputs "out"))
13506 (bin (string-append out "/bin")))
13507 (install-file "gffread" bin))
13511 ,(let ((version "0.10.3")
13512 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13516 (uri (git-reference
13517 (url "https://github.com/gpertea/gclib.git")
13519 (file-name (git-file-name "gclib" version))
13522 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13523 (home-page "https://github.com/gpertea/gffread/")
13524 (synopsis "Parse and convert GFF/GTF files")
13526 "This package provides a GFF/GTF file parsing utility providing format
13527 conversions, region filtering, FASTA sequence extraction and more.")
13528 ;; gffread is under Expat, but gclib is under Artistic 2.0
13529 (license (list license:expat
13530 license:artistic2.0)))))
13532 (define-public find-circ
13533 ;; The last release was in 2015. The license was clarified in 2017, so we
13534 ;; take the latest commit.
13535 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13539 (version (git-version "1.2" revision commit))
13543 (uri (git-reference
13544 (url "https://github.com/marvin-jens/find_circ.git")
13546 (file-name (git-file-name name version))
13549 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13550 (build-system gnu-build-system)
13552 `(#:tests? #f ; there are none
13554 ;; There is no actual build system.
13555 (modify-phases %standard-phases
13556 (delete 'configure)
13559 (lambda* (#:key outputs #:allow-other-keys)
13560 (let* ((out (assoc-ref outputs "out"))
13561 (bin (string-append out "/bin"))
13562 (path (getenv "PYTHONPATH")))
13563 (for-each (lambda (script)
13564 (install-file script bin)
13565 (wrap-program (string-append bin "/" script)
13566 `("PYTHONPATH" ":" prefix (,path))))
13571 "unmapped2anchors.py")))
13574 `(("python2" ,python-2)
13575 ("python2-pysam" ,python2-pysam)
13576 ("python2-numpy" ,python2-numpy)))
13577 (home-page "https://github.com/marvin-jens/find_circ")
13578 (synopsis "circRNA detection from RNA-seq reads")
13579 (description "This package provides tools to detect head-to-tail
13580 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13582 (license license:gpl3))))
13584 (define-public python-scanpy
13586 (name "python-scanpy")
13591 (uri (pypi-uri "scanpy" version))
13594 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13595 (build-system python-build-system)
13597 `(("python-anndata" ,python-anndata)
13598 ("python-igraph" ,python-igraph)
13599 ("python-numba" ,python-numba)
13600 ("python-joblib" ,python-joblib)
13601 ("python-natsort" ,python-natsort)
13602 ("python-networkx" ,python-networkx)
13603 ("python-statsmodels" ,python-statsmodels)
13604 ("python-scikit-learn" ,python-scikit-learn)
13605 ("python-matplotlib" ,python-matplotlib)
13606 ("python-pandas" ,python-pandas)
13607 ("python-scipy" ,python-scipy)
13608 ("python-seaborn" ,python-seaborn)
13609 ("python-h5py" ,python-h5py)
13610 ("python-tables" ,python-tables)))
13611 (home-page "http://github.com/theislab/scanpy")
13612 (synopsis "Single-Cell Analysis in Python.")
13613 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13614 expression data. It includes preprocessing, visualization, clustering,
13615 pseudotime and trajectory inference and differential expression testing. The
13616 Python-based implementation efficiently deals with datasets of more than one
13618 (license license:bsd-3)))
13620 (define-public gffcompare
13621 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13624 (name "gffcompare")
13625 (version (git-version "0.10.15" revision commit))
13629 (uri (git-reference
13630 (url "https://github.com/gpertea/gffcompare/")
13632 (file-name (git-file-name name version))
13634 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13635 (build-system gnu-build-system)
13637 `(#:tests? #f ; no check target
13639 (modify-phases %standard-phases
13640 (delete 'configure)
13641 (add-before 'build 'copy-gclib-source
13642 (lambda* (#:key inputs #:allow-other-keys)
13645 (assoc-ref inputs "gclib-source") "../gclib")
13648 (lambda* (#:key outputs #:allow-other-keys)
13649 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13650 (install-file "gffcompare" bin)
13653 `(("gclib-source" ; see 'README.md' of gffcompare
13654 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13657 (version (git-version "0.10.3" revision commit)))
13660 (uri (git-reference
13661 (url "https://github.com/gpertea/gclib/")
13663 (file-name (git-file-name name version))
13665 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13666 (home-page "https://github.com/gpertea/gffcompare/")
13667 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13669 "@code{gffcompare} is a tool that can:
13671 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13672 (Cufflinks, Stringtie);
13673 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13674 resulted from assembly of different samples);
13675 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13676 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13680 license:expat ;license for gffcompare
13681 license:artistic2.0))))) ;license for gclib
13683 (define-public python-intervaltree
13685 (name "python-intervaltree")
13690 (uri (pypi-uri "intervaltree" version))
13693 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13694 (build-system python-build-system)
13695 ;; FIXME: error when collecting tests
13696 (arguments '(#:tests? #f))
13698 `(("python-sortedcontainers" ,python-sortedcontainers)))
13700 `(("python-pytest" ,python-pytest)))
13701 (home-page "https://github.com/chaimleib/intervaltree")
13702 (synopsis "Editable interval tree data structure")
13704 "This package provides a mutable, self-balancing interval tree
13705 implementation for Python. Queries may be by point, by range overlap, or by
13706 range envelopment. This library was designed to allow tagging text and time
13707 intervals, where the intervals include the lower bound but not the upper
13709 (license license:asl2.0)))
13711 (define-public python-pypairix
13713 (name "python-pypairix")
13718 (uri (pypi-uri "pypairix" version))
13721 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13722 (build-system python-build-system)
13723 ;; FIXME: the tests fail because test.support cannot be loaded:
13724 ;; ImportError: cannot import name 'support'
13725 (arguments '(#:tests? #f))
13728 (home-page "https://github.com/4dn-dcic/pairix")
13729 (synopsis "Support for querying pairix-indexed bgzipped text files")
13731 "Pypairix is a Python module for fast querying on a pairix-indexed
13732 bgzipped text file that contains a pair of genomic coordinates per line.")
13733 (license license:expat)))
13735 (define-public python-pyfaidx
13737 (name "python-pyfaidx")
13738 (version "0.5.4.2")
13742 (uri (pypi-uri "pyfaidx" version))
13745 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13746 (build-system python-build-system)
13748 `(("python-setuptools" ,python-setuptools)
13749 ("python-six" ,python-six)))
13750 (home-page "http://mattshirley.com")
13751 (synopsis "Random access to fasta subsequences")
13753 "This package provides procedures for efficient pythonic random access to
13754 fasta subsequences.")
13755 (license license:bsd-3)))
13757 (define-public python-cooler
13759 (name "python-cooler")
13764 (uri (pypi-uri "cooler" version))
13767 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13768 (build-system python-build-system)
13770 `(("python-biopython" ,python-biopython)
13771 ("python-click" ,python-click)
13772 ("python-cytoolz" ,python-cytoolz)
13773 ("python-dask" ,python-dask)
13774 ("python-h5py" ,python-h5py)
13775 ("python-multiprocess" ,python-multiprocess)
13776 ("python-pandas" ,python-pandas)
13777 ("python-pyfaidx" ,python-pyfaidx)
13778 ("python-pypairix" ,python-pypairix)
13779 ("python-pysam" ,python-pysam)
13780 ("python-scipy" ,python-scipy)))
13782 `(("python-mock" ,python-mock)
13783 ("python-nose" ,python-nose)
13784 ("python-numpydoc" ,python-numpydoc)
13785 ("python-sphinx" ,python-sphinx)))
13786 (home-page "https://github.com/mirnylab/cooler")
13787 (synopsis "Sparse binary format for genomic interaction matrices")
13789 "Cooler is a support library for a sparse, compressed, binary persistent
13790 storage format, called @code{cool}, used to store genomic interaction data,
13791 such as Hi-C contact matrices.")
13792 (license license:bsd-3)))
13794 (define-public python-hicexplorer
13796 (name "python-hicexplorer")
13800 ;; The latest version is not available on Pypi.
13802 (uri (git-reference
13803 (url "https://github.com/deeptools/HiCExplorer.git")
13805 (file-name (git-file-name name version))
13808 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13809 (build-system python-build-system)
13812 (modify-phases %standard-phases
13813 (add-after 'unpack 'loosen-up-requirements
13815 (substitute* "setup.py"
13819 `(("python-biopython" ,python-biopython)
13820 ("python-configparser" ,python-configparser)
13821 ("python-cooler" ,python-cooler)
13822 ("python-future" ,python-future)
13823 ("python-intervaltree" ,python-intervaltree)
13824 ("python-jinja2" ,python-jinja2)
13825 ("python-matplotlib" ,python-matplotlib)
13826 ("python-numpy" ,python-numpy)
13827 ("python-pandas" ,python-pandas)
13828 ("python-pybigwig" ,python-pybigwig)
13829 ("python-pysam" ,python-pysam)
13830 ("python-scipy" ,python-scipy)
13831 ("python-six" ,python-six)
13832 ("python-tables" ,python-tables)
13833 ("python-unidecode" ,python-unidecode)))
13834 (home-page "http://hicexplorer.readthedocs.io")
13835 (synopsis "Process, analyze and visualize Hi-C data")
13837 "HiCExplorer is a powerful and easy to use set of tools to process,
13838 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13839 contact matrices, correction of contacts, TAD detection, A/B compartments,
13840 merging, reordering or chromosomes, conversion from different formats
13841 including cooler and detection of long-range contacts. Moreover, it allows
13842 the visualization of multiple contact matrices along with other types of data
13843 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13844 genomic scores), long range contacts and the visualization of viewpoints.")
13845 (license license:gpl3)))
13847 (define-public python-pygenometracks
13849 (name "python-pygenometracks")
13854 (uri (pypi-uri "pyGenomeTracks" version))
13857 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13858 (build-system python-build-system)
13860 `(("python-configparser" ,python-configparser)
13861 ("python-future" ,python-future)
13862 ("python-hicexplorer" ,python-hicexplorer)
13863 ("python-intervaltree" ,python-intervaltree)
13864 ("python-matplotlib" ,python-matplotlib)
13865 ("python-numpy" ,python-numpy)
13866 ("python-pybigwig" ,python-pybigwig)))
13868 `(("python-pytest" ,python-pytest)))
13869 (home-page "https://pygenometracks.readthedocs.io")
13870 (synopsis "Program and library to plot beautiful genome browser tracks")
13872 "This package aims to produce high-quality genome browser tracks that
13873 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13874 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13875 pyGenomeTracks can make plots with or without Hi-C data.")
13876 (license license:gpl3+)))
13878 (define-public python-hic2cool
13880 (name "python-hic2cool")
13885 (uri (pypi-uri "hic2cool" version))
13888 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13889 (build-system python-build-system)
13890 (arguments '(#:tests? #f)) ; no tests included
13892 `(("python-cooler" ,python-cooler)))
13893 (home-page "https://github.com/4dn-dcic/hic2cool")
13894 (synopsis "Converter for .hic and .cool files")
13896 "This package provides a converter between @code{.hic} files (from
13897 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13898 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13900 (license license:expat)))
13902 (define-public r-pore
13910 (string-append "mirror://sourceforge/rpore/" version
13911 "/poRe_" version ".tar.gz"))
13913 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13914 (properties `((upstream-name . "poRe")))
13915 (build-system r-build-system)
13917 `(("r-bit64" ,r-bit64)
13918 ("r-data-table" ,r-data-table)
13919 ("r-rhdf5" ,r-rhdf5)
13920 ("r-shiny" ,r-shiny)
13921 ("r-svdialogs" ,r-svdialogs)))
13922 (home-page "https://sourceforge.net/projects/rpore/")
13923 (synopsis "Visualize Nanopore sequencing data")
13925 "This package provides graphical user interfaces to organize and visualize Nanopore
13927 ;; This is free software but the license variant is unclear:
13928 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13929 (license license:bsd-3)))
13931 (define-public r-xbioc
13932 (let ((revision "1")
13933 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13936 (version (git-version "0.1.15" revision commit))
13939 (uri (git-reference
13940 (url "https://github.com/renozao/xbioc.git")
13942 (file-name (git-file-name name version))
13945 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13946 (build-system r-build-system)
13948 `(("r-annotationdbi" ,r-annotationdbi)
13949 ("r-assertthat" ,r-assertthat)
13950 ("r-biobase" ,r-biobase)
13951 ("r-biocinstaller" ,r-biocinstaller)
13952 ("r-digest" ,r-digest)
13953 ("r-pkgmaker" ,r-pkgmaker)
13955 ("r-reshape2" ,r-reshape2)
13956 ("r-stringr" ,r-stringr)))
13957 (home-page "https://github.com/renozao/xbioc/")
13958 (synopsis "Extra base functions for Bioconductor")
13959 (description "This package provides extra utility functions to perform
13960 common tasks in the analysis of omics data, leveraging and enhancing features
13961 provided by Bioconductor packages.")
13962 (license license:gpl3+))))
13964 (define-public r-cssam
13965 (let ((revision "1")
13966 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13969 (version (git-version "1.4" revision commit))
13972 (uri (git-reference
13973 (url "https://github.com/shenorrLab/csSAM.git")
13975 (file-name (git-file-name name version))
13978 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13979 (build-system r-build-system)
13981 `(("r-formula" ,r-formula)
13982 ("r-ggplot2" ,r-ggplot2)
13983 ("r-pkgmaker" ,r-pkgmaker)
13985 ("r-rngtools" ,r-rngtools)
13986 ("r-scales" ,r-scales)))
13987 (home-page "https://github.com/shenorrLab/csSAM/")
13988 (synopsis "Cell type-specific statistical analysis of microarray")
13989 (description "This package implements the method csSAM that computes
13990 cell-specific differential expression from measured cell proportions using
13993 (license license:lgpl2.1+))))
13995 (define-public r-bseqsc
13996 (let ((revision "1")
13997 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14000 (version (git-version "1.0" revision commit))
14003 (uri (git-reference
14004 (url "https://github.com/shenorrLab/bseqsc.git")
14006 (file-name (git-file-name name version))
14009 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14010 (build-system r-build-system)
14012 `(("r-abind" ,r-abind)
14013 ("r-annotationdbi" ,r-annotationdbi)
14014 ("r-biobase" ,r-biobase)
14015 ("r-cssam" ,r-cssam)
14016 ("r-dplyr" ,r-dplyr)
14017 ("r-e1071" ,r-e1071)
14018 ("r-edger" ,r-edger)
14019 ("r-ggplot2" ,r-ggplot2)
14021 ("r-openxlsx" ,r-openxlsx)
14022 ("r-pkgmaker" ,r-pkgmaker)
14024 ("r-preprocesscore" ,r-preprocesscore)
14025 ("r-rngtools" ,r-rngtools)
14026 ("r-scales" ,r-scales)
14027 ("r-stringr" ,r-stringr)
14028 ("r-xbioc" ,r-xbioc)))
14029 (home-page "https://github.com/shenorrLab/bseqsc")
14030 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14031 (description "BSeq-sc is a bioinformatics analysis pipeline that
14032 leverages single-cell sequencing data to estimate cell type proportion and
14033 cell type-specific gene expression differences from RNA-seq data from bulk
14034 tissue samples. This is a companion package to the publication \"A
14035 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14036 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14037 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14038 (license license:gpl2+))))
14040 (define-public porechop
14041 ;; The recommended way to install is to clone the git repository
14042 ;; https://github.com/rrwick/Porechop#installation
14043 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14047 (version (git-version "0.2.3" revision commit))
14051 (uri (git-reference
14052 (url "https://github.com/rrwick/Porechop.git")
14054 (file-name (git-file-name name version))
14056 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14057 (build-system python-build-system)
14058 (home-page "https://github.com/rrwick/porechop")
14059 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14061 "The porechop package is a tool for finding and removing adapters from Oxford
14062 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14063 has an adapter in its middle, it is treated as chimeric and chopped into
14064 separate reads. Porechop performs thorough alignments to effectively find
14065 adapters, even at low sequence identity. Porechop also supports demultiplexing
14066 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14067 Barcoding Kit or Rapid Barcoding Kit.")
14068 (license license:gpl3+))))
14070 (define-public poretools
14071 ;; The latest release was in 2016 and the latest commit is from 2017
14072 ;; the recommended way to install is to clone the git repository
14073 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14074 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14078 (version (git-version "0.6.0" revision commit))
14082 (uri (git-reference
14083 (url "https://github.com/arq5x/poretools.git")
14085 (file-name (git-file-name name version))
14087 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14088 (build-system python-build-system)
14089 ;; requires python >=2.7, <3.0, and the same for python dependencies
14090 (arguments `(#:python ,python-2))
14094 `(("python-dateutil" ,python2-dateutil)
14095 ("python-h5py" ,python2-h5py)
14096 ("python-matplotlib" ,python2-matplotlib)
14097 ("python-pandas" ,python2-pandas)
14098 ("python-seaborn" ,python2-seaborn)))
14099 (home-page "https://poretools.readthedocs.io")
14100 (synopsis "Toolkit for working with nanopore sequencing data")
14102 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14103 This @code{poretools} package is a flexible toolkit for exploring datasets
14104 generated by nanopore sequencing devices for the purposes of quality control and
14105 downstream analysis. Poretools operates directly on the native FAST5, a variant
14106 of the Hierarchical Data Format (HDF5) standard.")
14107 (license license:expat))))
14109 (define-public r-absfiltergsea
14111 (name "r-absfiltergsea")
14116 (uri (cran-uri "AbsFilterGSEA" version))
14118 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14119 (properties `((upstream-name . "AbsFilterGSEA")))
14120 (build-system r-build-system)
14122 `(("r-biobase" ,r-biobase)
14123 ("r-deseq" ,r-deseq)
14124 ("r-limma" ,r-limma)
14126 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14127 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14128 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14130 "This package provides a function that performs gene-permuting of a gene-set
14131 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14132 Without filtering, users can perform (original) two-tailed or one-tailed
14134 (license license:gpl2)))
14136 (define-public jamm
14139 (version "1.0.7.5")
14143 (uri (git-reference
14144 (url "https://github.com/mahmoudibrahim/JAMM.git")
14145 (commit (string-append "JAMMv" version))))
14146 (file-name (git-file-name name version))
14149 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14150 (build-system gnu-build-system)
14152 `(#:tests? #f ; there are none
14154 (modify-phases %standard-phases
14155 (delete 'configure)
14157 (lambda* (#:key inputs outputs #:allow-other-keys)
14158 (substitute* "JAMM.sh"
14160 (string-append "")))
14163 (lambda* (#:key inputs outputs #:allow-other-keys)
14164 (let* ((out (assoc-ref outputs "out"))
14165 (libexec (string-append out "/libexec/jamm"))
14166 (bin (string-append out "/bin")))
14167 (substitute* '("JAMM.sh"
14168 "SignalGenerator.sh")
14170 (string-append "sPath=\"" libexec "\"\n")))
14171 (for-each (lambda (file)
14172 (install-file file libexec))
14173 (list "bincalculator.r"
14185 (chmod script #o555)
14186 (install-file script bin)
14187 (wrap-program (string-append bin "/" script)
14188 `("PATH" ":" prefix
14189 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14190 ,(string-append (assoc-ref inputs "gawk") "/bin")
14191 ,(string-append (assoc-ref inputs "perl") "/bin")
14192 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14193 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14194 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14195 (list "JAMM.sh" "SignalGenerator.sh")))
14199 ("coreutils" ,coreutils)
14202 ("r-minimal" ,r-minimal)
14203 ;;("r-parallel" ,r-parallel)
14204 ("r-signal" ,r-signal)
14205 ("r-mclust" ,r-mclust)))
14206 (home-page "https://github.com/mahmoudibrahim/JAMM")
14207 (synopsis "Peak finder for NGS datasets")
14209 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14210 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14211 boundaries accurately. JAMM is applicable to both broad and narrow
14213 (license license:gpl3+)))
14215 (define-public ngless
14222 (uri (git-reference
14223 (url "https://gitlab.com/ngless/ngless.git")
14224 (commit (string-append "v" version))))
14225 (file-name (git-file-name name version))
14228 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14229 (build-system haskell-build-system)
14231 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14232 ; error: parse error on input import
14233 ; import Options.Applicative
14235 (modify-phases %standard-phases
14236 (add-after 'unpack 'create-cabal-file
14237 (lambda _ (invoke "hpack") #t))
14238 ;; These tools are expected to be installed alongside ngless.
14239 (add-after 'install 'link-tools
14240 (lambda* (#:key inputs outputs #:allow-other-keys)
14241 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14242 (symlink (string-append (assoc-ref inputs "prodigal")
14244 (string-append bin "ngless-" ,version "-prodigal"))
14245 (symlink (string-append (assoc-ref inputs "minimap2")
14247 (string-append bin "ngless-" ,version "-minimap2"))
14248 (symlink (string-append (assoc-ref inputs "samtools")
14250 (string-append bin "ngless-" ,version "-samtools"))
14251 (symlink (string-append (assoc-ref inputs "bwa")
14253 (string-append bin "ngless-" ,version "-bwa"))
14256 `(("prodigal" ,prodigal)
14258 ("samtools" ,samtools)
14259 ("minimap2" ,minimap2)
14260 ("ghc-aeson" ,ghc-aeson)
14261 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14262 ("ghc-async" ,ghc-async)
14263 ("ghc-atomic-write" ,ghc-atomic-write)
14264 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14265 ("ghc-chart" ,ghc-chart)
14266 ("ghc-chart-cairo" ,ghc-chart-cairo)
14267 ("ghc-conduit" ,ghc-conduit)
14268 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14269 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14270 ("ghc-conduit-extra" ,ghc-conduit-extra)
14271 ("ghc-configurator" ,ghc-configurator)
14272 ("ghc-convertible" ,ghc-convertible)
14273 ("ghc-data-default" ,ghc-data-default)
14274 ("ghc-double-conversion" ,ghc-double-conversion)
14275 ("ghc-edit-distance" ,ghc-edit-distance)
14276 ("ghc-either" ,ghc-either)
14277 ("ghc-errors" ,ghc-errors)
14278 ("ghc-extra" ,ghc-extra)
14279 ("ghc-filemanip" ,ghc-filemanip)
14280 ("ghc-file-embed" ,ghc-file-embed)
14281 ("ghc-gitrev" ,ghc-gitrev)
14282 ("ghc-hashtables" ,ghc-hashtables)
14283 ("ghc-http-conduit" ,ghc-http-conduit)
14284 ("ghc-inline-c" ,ghc-inline-c)
14285 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14286 ("ghc-intervalmap" ,ghc-intervalmap)
14287 ("ghc-missingh" ,ghc-missingh)
14288 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14289 ("ghc-parsec" ,ghc-parsec)
14290 ("ghc-regex" ,ghc-regex)
14291 ("ghc-safe" ,ghc-safe)
14292 ("ghc-safeio" ,ghc-safeio)
14293 ("ghc-strict" ,ghc-strict)
14294 ("ghc-tar" ,ghc-tar)
14295 ("ghc-text" ,ghc-text)
14296 ("ghc-unliftio" ,ghc-unliftio)
14297 ("ghc-unliftio-core" ,ghc-unliftio-core)
14298 ("ghc-vector" ,ghc-vector)
14299 ("ghc-yaml" ,ghc-yaml)
14300 ("ghc-zlib" ,ghc-zlib)))
14303 ("r-hdf5r" ,r-hdf5r)
14304 ("r-iterators" ,r-iterators)
14305 ("r-itertools" ,r-itertools)
14306 ("r-matrix" ,r-matrix)))
14308 `(("ghc-hpack" ,ghc-hpack)
14309 ("ghc-quickcheck" ,ghc-quickcheck)
14310 ("ghc-test-framework" ,ghc-test-framework)
14311 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14312 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14313 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14314 (home-page "https://gitlab.com/ngless/ngless")
14315 (synopsis "DSL for processing next-generation sequencing data")
14316 (description "Ngless is a domain-specific language for
14317 @dfn{next-generation sequencing} (NGS) data processing.")
14318 (license license:expat)))
14320 (define-public filtlong
14321 ;; The recommended way to install is to clone the git repository
14322 ;; https://github.com/rrwick/Filtlong#installation
14323 ;; and the lastest release is more than nine months old
14324 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14328 (version (git-version "0.2.0" revision commit))
14332 (uri (git-reference
14333 (url "https://github.com/rrwick/Filtlong.git")
14335 (file-name (git-file-name name version))
14337 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14338 (build-system gnu-build-system)
14340 `(#:tests? #f ; no check target
14342 (modify-phases %standard-phases
14343 (delete 'configure)
14345 (lambda* (#:key outputs #:allow-other-keys)
14346 (let* ((out (assoc-ref outputs "out"))
14347 (bin (string-append out "/bin"))
14348 (scripts (string-append out "/share/filtlong/scripts")))
14349 (install-file "bin/filtlong" bin)
14350 (install-file "scripts/histogram.py" scripts)
14351 (install-file "scripts/read_info_histograms.sh" scripts))
14353 (add-after 'install 'wrap-program
14354 (lambda* (#:key inputs outputs #:allow-other-keys)
14355 (let* ((out (assoc-ref outputs "out"))
14356 (path (getenv "PYTHONPATH")))
14357 (wrap-program (string-append out
14358 "/share/filtlong/scripts/histogram.py")
14359 `("PYTHONPATH" ":" prefix (,path))))
14361 (add-before 'check 'patch-tests
14363 (substitute* "scripts/read_info_histograms.sh"
14364 (("awk") (which "gawk")))
14367 `(("gawk" ,gawk) ;for read_info_histograms.sh
14368 ("python" ,python-2) ;required for histogram.py
14370 (home-page "https://github.com/rrwick/Filtlong/")
14371 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14373 "The Filtlong package is a tool for filtering long reads by quality.
14374 It can take a set of long reads and produce a smaller, better subset. It uses
14375 both read length (longer is better) and read identity (higher is better) when
14376 choosing which reads pass the filter.")
14377 (license (list license:gpl3 ;filtlong
14378 license:asl2.0))))) ;histogram.py
14380 (define-public nanopolish
14381 ;; The recommended way to install is to clone the git repository
14382 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14383 ;; Also, the differences between release and current version seem to be
14385 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14388 (name "nanopolish")
14389 (version (git-version "0.10.2" revision commit))
14393 (uri (git-reference
14394 (url "https://github.com/jts/nanopolish.git")
14397 (file-name (git-file-name name version))
14399 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14400 (build-system gnu-build-system)
14403 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14404 #:tests? #f ; no check target
14406 (modify-phases %standard-phases
14407 (add-after 'unpack 'find-eigen
14408 (lambda* (#:key inputs #:allow-other-keys)
14410 (string-append (assoc-ref inputs "eigen")
14411 "/include/eigen3"))
14413 (delete 'configure)
14415 (lambda* (#:key outputs #:allow-other-keys)
14416 (let* ((out (assoc-ref outputs "out"))
14417 (bin (string-append out "/bin"))
14418 (scripts (string-append out "/share/nanopolish/scripts")))
14420 (install-file "nanopolish" bin)
14421 (for-each (lambda (file) (install-file file scripts))
14422 (find-files "scripts" ".*"))
14424 (add-after 'install 'wrap-programs
14425 (lambda* (#:key outputs #:allow-other-keys)
14426 (for-each (lambda (file)
14427 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14428 (find-files "/share/nanopolish/scripts" "\\.py"))
14429 (for-each (lambda (file)
14430 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14431 (find-files "/share/nanopolish/scripts" "\\.pl"))
14439 ("python-biopython" ,python-biopython)
14440 ("python-numpy" ,python-numpy)
14441 ("python-pysam" ,python-pysam)
14442 ("python-scikit-learn" , python-scikit-learn)
14443 ("python-scipy" ,python-scipy)
14445 (home-page "https://github.com/jts/nanopolish")
14446 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14448 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14449 Nanopolish can calculate an improved consensus sequence for a draft genome
14450 assembly, detect base modifications, call SNPs (Single nucleotide
14451 polymorphisms) and indels with respect to a reference genome and more.")
14452 (license license:expat))))