1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
16 ;;; This file is part of GNU Guix.
18 ;;; GNU Guix is free software; you can redistribute it and/or modify it
19 ;;; under the terms of the GNU General Public License as published by
20 ;;; the Free Software Foundation; either version 3 of the License, or (at
21 ;;; your option) any later version.
23 ;;; GNU Guix is distributed in the hope that it will be useful, but
24 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
25 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
26 ;;; GNU General Public License for more details.
28 ;;; You should have received a copy of the GNU General Public License
29 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
31 (define-module (gnu packages bioinformatics)
32 #:use-module ((guix licenses) #:prefix license:)
33 #:use-module (guix packages)
34 #:use-module (guix utils)
35 #:use-module (guix download)
36 #:use-module (guix git-download)
37 #:use-module (guix hg-download)
38 #:use-module (guix build-system ant)
39 #:use-module (guix build-system gnu)
40 #:use-module (guix build-system cmake)
41 #:use-module (guix build-system haskell)
42 #:use-module (guix build-system ocaml)
43 #:use-module (guix build-system perl)
44 #:use-module (guix build-system python)
45 #:use-module (guix build-system r)
46 #:use-module (guix build-system ruby)
47 #:use-module (guix build-system scons)
48 #:use-module (guix build-system trivial)
49 #:use-module (gnu packages)
50 #:use-module (gnu packages autotools)
51 #:use-module (gnu packages algebra)
52 #:use-module (gnu packages base)
53 #:use-module (gnu packages bash)
54 #:use-module (gnu packages bison)
55 #:use-module (gnu packages bioconductor)
56 #:use-module (gnu packages boost)
57 #:use-module (gnu packages check)
58 #:use-module (gnu packages compression)
59 #:use-module (gnu packages cpio)
60 #:use-module (gnu packages cran)
61 #:use-module (gnu packages curl)
62 #:use-module (gnu packages documentation)
63 #:use-module (gnu packages databases)
64 #:use-module (gnu packages datastructures)
65 #:use-module (gnu packages file)
66 #:use-module (gnu packages flex)
67 #:use-module (gnu packages gawk)
68 #:use-module (gnu packages gcc)
69 #:use-module (gnu packages gd)
70 #:use-module (gnu packages gtk)
71 #:use-module (gnu packages glib)
72 #:use-module (gnu packages graph)
73 #:use-module (gnu packages groff)
74 #:use-module (gnu packages guile)
75 #:use-module (gnu packages haskell)
76 #:use-module (gnu packages haskell-check)
77 #:use-module (gnu packages haskell-web)
78 #:use-module (gnu packages image)
79 #:use-module (gnu packages imagemagick)
80 #:use-module (gnu packages java)
81 #:use-module (gnu packages java-compression)
82 #:use-module (gnu packages jemalloc)
83 #:use-module (gnu packages dlang)
84 #:use-module (gnu packages linux)
85 #:use-module (gnu packages logging)
86 #:use-module (gnu packages machine-learning)
87 #:use-module (gnu packages man)
88 #:use-module (gnu packages maths)
89 #:use-module (gnu packages mpi)
90 #:use-module (gnu packages ncurses)
91 #:use-module (gnu packages ocaml)
92 #:use-module (gnu packages pcre)
93 #:use-module (gnu packages parallel)
94 #:use-module (gnu packages pdf)
95 #:use-module (gnu packages perl)
96 #:use-module (gnu packages perl-check)
97 #:use-module (gnu packages pkg-config)
98 #:use-module (gnu packages popt)
99 #:use-module (gnu packages protobuf)
100 #:use-module (gnu packages python)
101 #:use-module (gnu packages python-web)
102 #:use-module (gnu packages readline)
103 #:use-module (gnu packages ruby)
104 #:use-module (gnu packages serialization)
105 #:use-module (gnu packages shells)
106 #:use-module (gnu packages statistics)
107 #:use-module (gnu packages swig)
108 #:use-module (gnu packages tbb)
109 #:use-module (gnu packages tex)
110 #:use-module (gnu packages texinfo)
111 #:use-module (gnu packages textutils)
112 #:use-module (gnu packages time)
113 #:use-module (gnu packages tls)
114 #:use-module (gnu packages vim)
115 #:use-module (gnu packages web)
116 #:use-module (gnu packages xml)
117 #:use-module (gnu packages xorg)
118 #:use-module (srfi srfi-1)
119 #:use-module (ice-9 match))
121 (define-public aragorn
128 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
132 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
133 (build-system gnu-build-system)
135 `(#:tests? #f ; there are no tests
137 (modify-phases %standard-phases
147 (string-append "aragorn" ,version ".c"))
150 (lambda* (#:key outputs #:allow-other-keys)
151 (let* ((out (assoc-ref outputs "out"))
152 (bin (string-append out "/bin"))
153 (man (string-append out "/share/man/man1")))
154 (install-file "aragorn" bin)
155 (install-file "aragorn.1" man))
157 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
158 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
160 "Aragorn identifies transfer RNA, mitochondrial RNA and
161 transfer-messenger RNA from nucleotide sequences, based on homology to known
162 tRNA consensus sequences and RNA structure. It also outputs the secondary
163 structure of the predicted RNA.")
164 (license license:gpl2)))
172 ;; BamM is not available on pypi.
174 (url "https://github.com/Ecogenomics/BamM.git")
177 (file-name (git-file-name name version))
180 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
181 (modules '((guix build utils)))
184 ;; Delete bundled htslib.
185 (delete-file-recursively "c/htslib-1.3.1")
187 (build-system python-build-system)
189 `(#:python ,python-2 ; BamM is Python 2 only.
190 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
191 ;; been modified from its original form.
193 (let ((htslib (assoc-ref %build-inputs "htslib")))
194 (list "--with-libhts-lib" (string-append htslib "/lib")
195 "--with-libhts-inc" (string-append htslib "/include/htslib")))
197 (modify-phases %standard-phases
198 (add-after 'unpack 'autogen
200 (with-directory-excursion "c"
201 (let ((sh (which "sh")))
202 (for-each make-file-writable (find-files "." ".*"))
203 ;; Use autogen so that 'configure' works.
204 (substitute* "autogen.sh" (("/bin/sh") sh))
205 (setenv "CONFIG_SHELL" sh)
206 (invoke "./autogen.sh")))
209 ;; Run tests after installation so compilation only happens once.
211 (add-after 'install 'wrap-executable
212 (lambda* (#:key outputs #:allow-other-keys)
213 (let* ((out (assoc-ref outputs "out"))
214 (path (getenv "PATH")))
215 (wrap-program (string-append out "/bin/bamm")
216 `("PATH" ":" prefix (,path))))
218 (add-after 'wrap-executable 'post-install-check
219 (lambda* (#:key inputs outputs #:allow-other-keys)
221 (string-append (assoc-ref outputs "out")
226 (assoc-ref outputs "out")
228 (string-take (string-take-right
229 (assoc-ref inputs "python") 5) 3)
231 (getenv "PYTHONPATH")))
232 ;; There are 2 errors printed, but they are safe to ignore:
233 ;; 1) [E::hts_open_format] fail to open file ...
234 ;; 2) samtools view: failed to open ...
238 `(("autoconf" ,autoconf)
239 ("automake" ,automake)
242 ("python-nose" ,python2-nose)
243 ("python-pysam" ,python2-pysam)))
245 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
246 ("samtools" ,samtools)
250 ("coreutils" ,coreutils)))
252 `(("python-numpy" ,python2-numpy)))
253 (home-page "http://ecogenomics.github.io/BamM/")
254 (synopsis "Metagenomics-focused BAM file manipulator")
256 "BamM is a C library, wrapped in python, to efficiently generate and
257 parse BAM files, specifically for the analysis of metagenomic data. For
258 instance, it implements several methods to assess contig-wise read coverage.")
259 (license license:lgpl3+)))
261 (define-public bamtools
268 (url "https://github.com/pezmaster31/bamtools.git")
269 (commit (string-append "v" version))))
270 (file-name (git-file-name name version))
273 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
274 (build-system cmake-build-system)
276 `(#:tests? #f ;no "check" target
278 (modify-phases %standard-phases
280 'configure 'set-ldflags
281 (lambda* (#:key outputs #:allow-other-keys)
285 (assoc-ref outputs "out") "/lib/bamtools"))
287 (inputs `(("zlib" ,zlib)))
288 (home-page "https://github.com/pezmaster31/bamtools")
289 (synopsis "C++ API and command-line toolkit for working with BAM data")
291 "BamTools provides both a C++ API and a command-line toolkit for handling
293 (license license:expat)))
295 (define-public bcftools
301 (uri (string-append "https://github.com/samtools/bcftools/"
303 version "/bcftools-" version ".tar.bz2"))
306 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
307 (modules '((guix build utils)))
309 ;; Delete bundled htslib.
310 (delete-file-recursively "htslib-1.9")
312 (build-system gnu-build-system)
315 (list "--enable-libgsl")
318 (modify-phases %standard-phases
319 (add-before 'check 'patch-tests
321 (substitute* "test/test.pl"
322 (("/bin/bash") (which "bash")))
330 (home-page "https://samtools.github.io/bcftools/")
331 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
333 "BCFtools is a set of utilities that manipulate variant calls in the
334 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
335 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
336 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
337 (license (list license:gpl3+ license:expat))))
339 (define-public bedops
346 (url "https://github.com/bedops/bedops.git")
347 (commit (string-append "v" version))))
348 (file-name (git-file-name name version))
351 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
352 (build-system gnu-build-system)
355 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
357 (modify-phases %standard-phases
358 (add-after 'unpack 'unpack-tarballs
360 ;; FIXME: Bedops includes tarballs of minimally patched upstream
361 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
362 ;; libraries because at least one of the libraries (zlib) is
363 ;; patched to add a C++ function definition (deflateInit2cpp).
364 ;; Until the Bedops developers offer a way to link against system
365 ;; libraries we have to build the in-tree copies of these three
368 ;; See upstream discussion:
369 ;; https://github.com/bedops/bedops/issues/124
371 ;; Unpack the tarballs to benefit from shebang patching.
372 (with-directory-excursion "third-party"
373 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
374 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
375 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
376 ;; Disable unpacking of tarballs in Makefile.
377 (substitute* "system.mk/Makefile.linux"
378 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
379 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
380 (substitute* "third-party/zlib-1.2.7/Makefile.in"
381 (("^SHELL=.*$") "SHELL=bash\n"))
383 (delete 'configure))))
384 (home-page "https://github.com/bedops/bedops")
385 (synopsis "Tools for high-performance genomic feature operations")
387 "BEDOPS is a suite of tools to address common questions raised in genomic
388 studies---mostly with regard to overlap and proximity relationships between
389 data sets. It aims to be scalable and flexible, facilitating the efficient
390 and accurate analysis and management of large-scale genomic data.
392 BEDOPS provides tools that perform highly efficient and scalable Boolean and
393 other set operations, statistical calculations, archiving, conversion and
394 other management of genomic data of arbitrary scale. Tasks can be easily
395 split by chromosome for distributing whole-genome analyses across a
396 computational cluster.")
397 (license license:gpl2+)))
399 (define-public bedtools
405 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
406 "download/v" version "/"
407 "bedtools-" version ".tar.gz"))
410 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
411 (build-system gnu-build-system)
413 '(#:test-target "test"
415 (list (string-append "prefix=" (assoc-ref %outputs "out")))
417 (modify-phases %standard-phases
418 (delete 'configure))))
419 (native-inputs `(("python" ,python-2)))
421 `(("samtools" ,samtools)
423 (home-page "https://github.com/arq5x/bedtools2")
424 (synopsis "Tools for genome analysis and arithmetic")
426 "Collectively, the bedtools utilities are a swiss-army knife of tools for
427 a wide-range of genomics analysis tasks. The most widely-used tools enable
428 genome arithmetic: that is, set theory on the genome. For example, bedtools
429 allows one to intersect, merge, count, complement, and shuffle genomic
430 intervals from multiple files in widely-used genomic file formats such as BAM,
432 (license license:gpl2)))
434 ;; Later releases of bedtools produce files with more columns than
435 ;; what Ribotaper expects.
436 (define-public bedtools-2.18
437 (package (inherit bedtools)
442 (uri (string-append "https://github.com/arq5x/bedtools2/"
443 "releases/download/v" version
444 "/bedtools-" version ".tar.gz"))
447 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
449 '(#:test-target "test"
451 (modify-phases %standard-phases
454 (lambda* (#:key outputs #:allow-other-keys)
455 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
456 (for-each (lambda (file)
457 (install-file file bin))
458 (find-files "bin" ".*")))
461 ;; Needed for pybedtools.
462 (define-public bedtools-2.26
463 (package (inherit bedtools)
468 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
469 "download/v" version "/"
470 "bedtools-" version ".tar.gz"))
473 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
475 (define-public ribotaper
481 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
482 "files/RiboTaper/RiboTaper_Version_"
486 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
487 (build-system gnu-build-system)
490 (modify-phases %standard-phases
491 (add-after 'install 'wrap-executables
492 (lambda* (#:key inputs outputs #:allow-other-keys)
493 (let* ((out (assoc-ref outputs "out")))
496 (wrap-program (string-append out "/bin/" script)
497 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
498 '("create_annotations_files.bash"
499 "create_metaplots.bash"
500 "Ribotaper_ORF_find.sh"
504 `(("bedtools" ,bedtools-2.18)
505 ("samtools" ,samtools-0.1)
506 ("r-minimal" ,r-minimal)
507 ("r-foreach" ,r-foreach)
508 ("r-xnomial" ,r-xnomial)
510 ("r-multitaper" ,r-multitaper)
511 ("r-seqinr" ,r-seqinr)))
512 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
513 (synopsis "Define translated ORFs using ribosome profiling data")
515 "Ribotaper is a method for defining translated @dfn{open reading
516 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
517 provides the Ribotaper pipeline.")
518 (license license:gpl3+)))
520 (define-public ribodiff
528 (url "https://github.com/ratschlab/RiboDiff.git")
529 (commit (string-append "v" version))))
530 (file-name (git-file-name name version))
533 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
534 (build-system python-build-system)
538 (modify-phases %standard-phases
539 ;; Generate an installable executable script wrapper.
540 (add-after 'unpack 'patch-setup.py
542 (substitute* "setup.py"
543 (("^(.*)packages=.*" line prefix)
544 (string-append line "\n"
545 prefix "scripts=['scripts/TE.py'],\n")))
548 `(("python-numpy" ,python2-numpy)
549 ("python-matplotlib" ,python2-matplotlib)
550 ("python-scipy" ,python2-scipy)
551 ("python-statsmodels" ,python2-statsmodels)))
553 `(("python-mock" ,python2-mock)
554 ("python-nose" ,python2-nose)))
555 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
556 (synopsis "Detect translation efficiency changes from ribosome footprints")
557 (description "RiboDiff is a statistical tool that detects the protein
558 translational efficiency change from Ribo-Seq (ribosome footprinting) and
559 RNA-Seq data. It uses a generalized linear model to detect genes showing
560 difference in translational profile taking mRNA abundance into account. It
561 facilitates us to decipher the translational regulation that behave
562 independently with transcriptional regulation.")
563 (license license:gpl3+)))
565 (define-public bioawk
572 (url "https://github.com/lh3/bioawk.git")
573 (commit (string-append "v" version))))
574 (file-name (git-file-name name version))
577 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
578 (build-system gnu-build-system)
584 `(#:tests? #f ; There are no tests to run.
585 ;; Bison must generate files, before other targets can build.
588 (modify-phases %standard-phases
589 (delete 'configure) ; There is no configure phase.
591 (lambda* (#:key outputs #:allow-other-keys)
592 (let* ((out (assoc-ref outputs "out"))
593 (bin (string-append out "/bin"))
594 (man (string-append out "/share/man/man1")))
596 (copy-file "awk.1" (string-append man "/bioawk.1"))
597 (install-file "bioawk" bin))
599 (home-page "https://github.com/lh3/bioawk")
600 (synopsis "AWK with bioinformatics extensions")
601 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
602 support of several common biological data formats, including optionally gzip'ed
603 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
604 also adds a few built-in functions and a command line option to use TAB as the
605 input/output delimiter. When the new functionality is not used, bioawk is
606 intended to behave exactly the same as the original BWK awk.")
607 (license license:x11)))
609 (define-public python-pybedtools
611 (name "python-pybedtools")
615 (uri (pypi-uri "pybedtools" version))
618 "0l2b2wrnj85azfqgr0zwr60f7j58vlla1hcgxvr9rwikpl8j72ji"))))
619 (build-system python-build-system)
622 (modify-phases %standard-phases
623 ;; See https://github.com/daler/pybedtools/issues/261
624 (add-after 'unpack 'disable-broken-tests
626 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
627 ;; graphical environment.
628 (substitute* "pybedtools/test/test_scripts.py"
629 (("def test_venn_mpl")
630 "def _do_not_test_venn_mpl"))
631 ;; Requires internet access.
632 (substitute* "pybedtools/test/test_helpers.py"
633 (("def test_chromsizes")
634 "def _do_not_test_chromsizes"))
635 ;; FIXME: these two fail for no good reason.
636 (substitute* "pybedtools/test/test1.py"
637 (("def test_issue_157")
638 "def _do_not_test_issue_157")
639 (("def test_to_dataframe")
640 "def _do_not_test_to_dataframe"))
643 ;; Tests don't pass with Bedtools 2.27.1.
644 ;; See https://github.com/daler/pybedtools/issues/260
645 `(("bedtools" ,bedtools-2.26)
646 ("samtools" ,samtools)
647 ("python-matplotlib" ,python-matplotlib)
648 ("python-pysam" ,python-pysam)
649 ("python-pyyaml" ,python-pyyaml)))
651 `(("python-numpy" ,python-numpy)
652 ("python-pandas" ,python-pandas)
653 ("python-cython" ,python-cython)
654 ("python-nose" ,python-nose)
655 ("kentutils" ,kentutils) ; for bedGraphToBigWig
656 ("python-six" ,python-six)))
657 (home-page "https://pythonhosted.org/pybedtools/")
658 (synopsis "Python wrapper for BEDtools programs")
660 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
661 which are widely used for genomic interval manipulation or \"genome algebra\".
662 pybedtools extends BEDTools by offering feature-level manipulations from with
664 (license license:gpl2+)))
666 (define-public python2-pybedtools
667 (let ((pkg (package-with-python2 python-pybedtools)))
668 (package (inherit pkg)
670 `(#:modules ((ice-9 ftw)
674 (guix build python-build-system))
675 ;; See https://github.com/daler/pybedtools/issues/192
676 ,@(substitute-keyword-arguments (package-arguments pkg)
678 `(modify-phases ,phases
681 (let ((cwd (getcwd)))
683 (string-append cwd "/build/"
684 (find (cut string-prefix? "lib" <>)
685 (scandir (string-append cwd "/build")))
686 ":" (getenv "PYTHONPATH"))))
687 ;; The tests need to be run from elsewhere...
688 (mkdir-p "/tmp/test")
689 (copy-recursively "pybedtools/test" "/tmp/test")
690 (with-directory-excursion "/tmp/test"
692 ;; This test fails for unknown reasons
693 "--exclude=.*test_getting_example_beds"))
696 (define-public python-biom-format
698 (name "python-biom-format")
703 ;; Use GitHub as source because PyPI distribution does not contain
704 ;; test data: https://github.com/biocore/biom-format/issues/693
706 (url "https://github.com/biocore/biom-format.git")
708 (file-name (git-file-name name version))
711 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
712 (build-system python-build-system)
715 (modify-phases %standard-phases
716 (add-after 'unpack 'use-cython
717 (lambda _ (setenv "USE_CYTHON" "1") #t))
718 (add-after 'unpack 'disable-broken-test
720 (substitute* "biom/tests/test_cli/test_validate_table.py"
721 (("^(.+)def test_invalid_hdf5" m indent)
722 (string-append indent
723 "@npt.dec.skipif(True, msg='Guix')\n"
726 (add-before 'reset-gzip-timestamps 'make-files-writable
727 (lambda* (#:key outputs #:allow-other-keys)
728 (let ((out (assoc-ref outputs "out")))
729 (for-each (lambda (file) (chmod file #o644))
730 (find-files out "\\.gz"))
733 `(("python-numpy" ,python-numpy)
734 ("python-scipy" ,python-scipy)
735 ("python-flake8" ,python-flake8)
736 ("python-future" ,python-future)
737 ("python-click" ,python-click)
738 ("python-h5py" ,python-h5py)
739 ("python-pandas" ,python-pandas)))
741 `(("python-cython" ,python-cython)
742 ("python-pytest" ,python-pytest)
743 ("python-pytest-cov" ,python-pytest-cov)
744 ("python-nose" ,python-nose)))
745 (home-page "http://www.biom-format.org")
746 (synopsis "Biological Observation Matrix (BIOM) format utilities")
748 "The BIOM file format is designed to be a general-use format for
749 representing counts of observations e.g. operational taxonomic units, KEGG
750 orthology groups or lipid types, in one or more biological samples
751 e.g. microbiome samples, genomes, metagenomes.")
752 (license license:bsd-3)
753 (properties `((python2-variant . ,(delay python2-biom-format))))))
755 (define-public python2-biom-format
756 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
760 (substitute-keyword-arguments (package-arguments base)
762 `(modify-phases ,phases
763 ;; Do not require the unmaintained pyqi library.
764 (add-after 'unpack 'remove-pyqi
766 (substitute* "setup.py"
767 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
770 (define-public bioperl-minimal
771 (let* ((inputs `(("perl-module-build" ,perl-module-build)
772 ("perl-data-stag" ,perl-data-stag)
773 ("perl-libwww" ,perl-libwww)
774 ("perl-uri" ,perl-uri)))
776 (map (compose package-name cadr)
779 (map (compose package-transitive-target-inputs cadr) inputs))))))
781 (name "bioperl-minimal")
786 (uri (string-append "https://github.com/bioperl/bioperl-live/"
788 (string-map (lambda (c)
794 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
795 (build-system perl-build-system)
798 (modify-phases %standard-phases
800 'install 'wrap-programs
801 (lambda* (#:key outputs #:allow-other-keys)
802 ;; Make sure all executables in "bin" find the required Perl
803 ;; modules at runtime. As the PERL5LIB variable contains also
804 ;; the paths of native inputs, we pick the transitive target
805 ;; inputs from %build-inputs.
806 (let* ((out (assoc-ref outputs "out"))
807 (bin (string-append out "/bin/"))
809 (cons (string-append out "/lib/perl5/site_perl")
811 (assoc-ref %build-inputs name))
812 ',transitive-inputs))
814 (for-each (lambda (file)
816 `("PERL5LIB" ":" prefix (,path))))
817 (find-files bin "\\.pl$"))
821 `(("perl-test-most" ,perl-test-most)))
822 (home-page "https://metacpan.org/release/BioPerl")
823 (synopsis "Bioinformatics toolkit")
825 "BioPerl is the product of a community effort to produce Perl code which
826 is useful in biology. Examples include Sequence objects, Alignment objects
827 and database searching objects. These objects not only do what they are
828 advertised to do in the documentation, but they also interact - Alignment
829 objects are made from the Sequence objects, Sequence objects have access to
830 Annotation and SeqFeature objects and databases, Blast objects can be
831 converted to Alignment objects, and so on. This means that the objects
832 provide a coordinated and extensible framework to do computational biology.")
833 (license license:perl-license))))
835 (define-public python-biopython
837 (name "python-biopython")
841 ;; use PyPi rather than biopython.org to ease updating
842 (uri (pypi-uri "biopython" version))
845 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
846 (build-system python-build-system)
849 (modify-phases %standard-phases
850 (add-before 'check 'set-home
851 ;; Some tests require a home directory to be set.
852 (lambda _ (setenv "HOME" "/tmp") #t)))))
854 `(("python-numpy" ,python-numpy)))
855 (home-page "http://biopython.org/")
856 (synopsis "Tools for biological computation in Python")
858 "Biopython is a set of tools for biological computation including parsers
859 for bioinformatics files into Python data structures; interfaces to common
860 bioinformatics programs; a standard sequence class and tools for performing
861 common operations on them; code to perform data classification; code for
862 dealing with alignments; code making it easy to split up parallelizable tasks
863 into separate processes; and more.")
864 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
866 (define-public python2-biopython
867 (package-with-python2 python-biopython))
869 (define-public python-fastalite
871 (name "python-fastalite")
876 (uri (pypi-uri "fastalite" version))
879 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
880 (build-system python-build-system)
882 `(#:tests? #f)) ; Test data is not distributed.
883 (home-page "https://github.com/nhoffman/fastalite")
884 (synopsis "Simplest possible FASTA parser")
885 (description "This library implements a FASTA and a FASTQ parser without
886 relying on a complex dependency tree.")
887 (license license:expat)))
889 (define-public python2-fastalite
890 (package-with-python2 python-fastalite))
892 (define-public bpp-core
893 ;; The last release was in 2014 and the recommended way to install from source
894 ;; is to clone the git repository, so we do this.
895 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
896 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
899 (version (string-append "2.2.0-1." (string-take commit 7)))
903 (url "http://biopp.univ-montp2.fr/git/bpp-core")
905 (file-name (string-append name "-" version "-checkout"))
908 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
909 (build-system cmake-build-system)
911 `(#:parallel-build? #f))
913 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
914 ; compile all of the bpp packages with GCC 5.
915 (home-page "http://biopp.univ-montp2.fr")
916 (synopsis "C++ libraries for Bioinformatics")
918 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
919 analysis, phylogenetics, molecular evolution and population genetics. It is
920 Object Oriented and is designed to be both easy to use and computer efficient.
921 Bio++ intends to help programmers to write computer expensive programs, by
922 providing them a set of re-usable tools.")
923 (license license:cecill-c))))
925 (define-public bpp-phyl
926 ;; The last release was in 2014 and the recommended way to install from source
927 ;; is to clone the git repository, so we do this.
928 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
929 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
932 (version (string-append "2.2.0-1." (string-take commit 7)))
936 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
938 (file-name (string-append name "-" version "-checkout"))
941 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
942 (build-system cmake-build-system)
944 `(#:parallel-build? #f
945 ;; If out-of-source, test data is not copied into the build directory
946 ;; so the tests fail.
947 #:out-of-source? #f))
949 `(("bpp-core" ,bpp-core)
951 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
954 (home-page "http://biopp.univ-montp2.fr")
955 (synopsis "Bio++ phylogenetic Library")
957 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
958 analysis, phylogenetics, molecular evolution and population genetics. This
959 library provides phylogenetics-related modules.")
960 (license license:cecill-c))))
962 (define-public bpp-popgen
963 ;; The last release was in 2014 and the recommended way to install from source
964 ;; is to clone the git repository, so we do this.
965 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
966 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
969 (version (string-append "2.2.0-1." (string-take commit 7)))
973 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
975 (file-name (string-append name "-" version "-checkout"))
978 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
979 (build-system cmake-build-system)
981 `(#:parallel-build? #f
982 #:tests? #f)) ; There are no tests.
984 `(("bpp-core" ,bpp-core)
987 (home-page "http://biopp.univ-montp2.fr")
988 (synopsis "Bio++ population genetics library")
990 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
991 analysis, phylogenetics, molecular evolution and population genetics. This
992 library provides population genetics-related modules.")
993 (license license:cecill-c))))
995 (define-public bpp-seq
996 ;; The last release was in 2014 and the recommended way to install from source
997 ;; is to clone the git repository, so we do this.
998 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
999 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1002 (version (string-append "2.2.0-1." (string-take commit 7)))
1006 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1008 (file-name (string-append name "-" version "-checkout"))
1011 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1012 (build-system cmake-build-system)
1014 `(#:parallel-build? #f
1015 ;; If out-of-source, test data is not copied into the build directory
1016 ;; so the tests fail.
1017 #:out-of-source? #f))
1019 `(("bpp-core" ,bpp-core)
1020 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1021 (home-page "http://biopp.univ-montp2.fr")
1022 (synopsis "Bio++ sequence library")
1024 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1025 analysis, phylogenetics, molecular evolution and population genetics. This
1026 library provides sequence-related modules.")
1027 (license license:cecill-c))))
1029 (define-public bppsuite
1030 ;; The last release was in 2014 and the recommended way to install from source
1031 ;; is to clone the git repository, so we do this.
1032 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1033 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1036 (version (string-append "2.2.0-1." (string-take commit 7)))
1040 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1042 (file-name (string-append name "-" version "-checkout"))
1045 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1046 (build-system cmake-build-system)
1048 `(#:parallel-build? #f
1049 #:tests? #f)) ; There are no tests.
1053 ("texinfo" ,texinfo)))
1055 `(("bpp-core" ,bpp-core)
1056 ("bpp-seq" ,bpp-seq)
1057 ("bpp-phyl" ,bpp-phyl)
1058 ("bpp-phyl" ,bpp-popgen)
1060 (home-page "http://biopp.univ-montp2.fr")
1061 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1063 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1064 analysis, phylogenetics, molecular evolution and population genetics. This
1065 package provides command line tools using the Bio++ library.")
1066 (license license:cecill-c))))
1068 (define-public blast+
1075 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1076 version "/ncbi-blast-" version "+-src.tar.gz"))
1079 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1080 (patches (search-patches "blast+-fix-makefile.patch"))
1081 (modules '((guix build utils)))
1084 ;; Remove bundled bzip2, zlib and pcre.
1085 (delete-file-recursively "c++/src/util/compress/bzip2")
1086 (delete-file-recursively "c++/src/util/compress/zlib")
1087 (delete-file-recursively "c++/src/util/regexp")
1088 (substitute* "c++/src/util/compress/Makefile.in"
1089 (("bzip2 zlib api") "api"))
1090 ;; Remove useless msbuild directory
1091 (delete-file-recursively
1092 "c++/src/build-system/project_tree_builder/msbuild")
1094 (build-system gnu-build-system)
1096 `(;; There are two(!) tests for this massive library, and both fail with
1097 ;; "unparsable timing stats".
1098 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1099 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1102 #:parallel-build? #f ; not supported
1104 (modify-phases %standard-phases
1105 (add-before 'configure 'set-HOME
1106 ;; $HOME needs to be set at some point during the configure phase
1107 (lambda _ (setenv "HOME" "/tmp") #t))
1108 (add-after 'unpack 'enter-dir
1109 (lambda _ (chdir "c++") #t))
1110 (add-after 'enter-dir 'fix-build-system
1112 (define (which* cmd)
1113 (cond ((string=? cmd "date")
1114 ;; make call to "date" deterministic
1119 (format (current-error-port)
1120 "WARNING: Unable to find absolute path for ~s~%"
1124 ;; Rewrite hardcoded paths to various tools
1125 (substitute* (append '("src/build-system/configure.ac"
1126 "src/build-system/configure"
1127 "src/build-system/helpers/run_with_lock.c"
1128 "scripts/common/impl/if_diff.sh"
1129 "scripts/common/impl/run_with_lock.sh"
1130 "src/build-system/Makefile.configurables.real"
1131 "src/build-system/Makefile.in.top"
1132 "src/build-system/Makefile.meta.gmake=no"
1133 "src/build-system/Makefile.meta.in"
1134 "src/build-system/Makefile.meta_l"
1135 "src/build-system/Makefile.meta_p"
1136 "src/build-system/Makefile.meta_r"
1137 "src/build-system/Makefile.mk.in"
1138 "src/build-system/Makefile.requirements"
1139 "src/build-system/Makefile.rules_with_autodep.in")
1140 (find-files "scripts/common/check" "\\.sh$"))
1141 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1142 (or (which* cmd) all)))
1144 (substitute* (find-files "src/build-system" "^config.*")
1145 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1148 ;; rewrite "/var/tmp" in check script
1149 (substitute* "scripts/common/check/check_make_unix.sh"
1150 (("/var/tmp") "/tmp"))
1152 ;; do not reset PATH
1153 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1155 (("action=/bin/") "action=")
1156 (("export PATH") ":"))
1159 (lambda* (#:key inputs outputs #:allow-other-keys)
1160 (let ((out (assoc-ref outputs "out"))
1161 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1162 (include (string-append (assoc-ref outputs "include")
1163 "/include/ncbi-tools++")))
1164 ;; The 'configure' script doesn't recognize things like
1165 ;; '--enable-fast-install'.
1166 (invoke "./configure.orig"
1167 (string-append "--with-build-root=" (getcwd) "/build")
1168 (string-append "--prefix=" out)
1169 (string-append "--libdir=" lib)
1170 (string-append "--includedir=" include)
1171 (string-append "--with-bz2="
1172 (assoc-ref inputs "bzip2"))
1173 (string-append "--with-z="
1174 (assoc-ref inputs "zlib"))
1175 (string-append "--with-pcre="
1176 (assoc-ref inputs "pcre"))
1177 ;; Each library is built twice by default, once
1178 ;; with "-static" in its name, and again
1183 (outputs '("out" ; 21 MB
1191 ("python" ,python-wrapper)))
1194 (home-page "http://blast.ncbi.nlm.nih.gov")
1195 (synopsis "Basic local alignment search tool")
1197 "BLAST is a popular method of performing a DNA or protein sequence
1198 similarity search, using heuristics to produce results quickly. It also
1199 calculates an “expect value” that estimates how many matches would have
1200 occurred at a given score by chance, which can aid a user in judging how much
1201 confidence to have in an alignment.")
1202 ;; Most of the sources are in the public domain, with the following
1205 ;; * ./c++/include/util/bitset/
1206 ;; * ./c++/src/html/ncbi_menu*.js
1208 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1210 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1212 ;; * ./c++/src/corelib/teamcity_*
1213 (license (list license:public-domain
1219 (define-public bless
1225 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1229 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1230 (modules '((guix build utils)))
1233 ;; Remove bundled boost, pigz, zlib, and .git directory
1234 ;; FIXME: also remove bundled sources for murmurhash3 and
1235 ;; kmc once packaged.
1236 (delete-file-recursively "boost")
1237 (delete-file-recursively "pigz")
1238 (delete-file-recursively "google-sparsehash")
1239 (delete-file-recursively "zlib")
1240 (delete-file-recursively ".git")
1242 (build-system gnu-build-system)
1244 '(#:tests? #f ;no "check" target
1246 (list (string-append "ZLIB="
1247 (assoc-ref %build-inputs "zlib:static")
1249 (string-append "LDFLAGS="
1250 (string-join '("-lboost_filesystem"
1257 (modify-phases %standard-phases
1258 (add-after 'unpack 'do-not-build-bundled-pigz
1259 (lambda* (#:key inputs outputs #:allow-other-keys)
1260 (substitute* "Makefile"
1261 (("cd pigz/pigz-2.3.3; make") ""))
1263 (add-after 'unpack 'patch-paths-to-executables
1264 (lambda* (#:key inputs outputs #:allow-other-keys)
1265 (substitute* "parse_args.cpp"
1266 (("kmc_binary = .*")
1267 (string-append "kmc_binary = \""
1268 (assoc-ref outputs "out")
1270 (("pigz_binary = .*")
1271 (string-append "pigz_binary = \""
1272 (assoc-ref inputs "pigz")
1276 (lambda* (#:key outputs #:allow-other-keys)
1277 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1278 (for-each (lambda (file)
1279 (install-file file bin))
1280 '("bless" "kmc/bin/kmc"))
1282 (delete 'configure))))
1286 `(("openmpi" ,openmpi)
1288 ("sparsehash" ,sparsehash)
1290 ("zlib:static" ,zlib "static")
1292 (supported-systems '("x86_64-linux"))
1293 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1294 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1296 "@dfn{Bloom-filter-based error correction solution for high-throughput
1297 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1298 correction tool for genomic reads produced by @dfn{Next-generation
1299 sequencing} (NGS). BLESS produces accurate correction results with much less
1300 memory compared with previous solutions and is also able to tolerate a higher
1301 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1302 errors at the end of reads.")
1303 (license license:gpl3+)))
1305 (define-public bowtie
1312 (url "https://github.com/BenLangmead/bowtie2.git")
1313 (commit (string-append "v" version))))
1314 (file-name (git-file-name name version))
1317 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1318 (modules '((guix build utils)))
1321 (substitute* "Makefile"
1322 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1323 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1324 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1326 (build-system gnu-build-system)
1331 (string-append "prefix=" (assoc-ref %outputs "out")))
1333 (modify-phases %standard-phases
1338 "scripts/test/simple_tests.pl"
1339 "--bowtie2=./bowtie2"
1340 "--bowtie2-build=./bowtie2-build")
1345 ("python" ,python-wrapper)))
1348 ("perl-clone" ,perl-clone)
1349 ("perl-test-deep" ,perl-test-deep)
1350 ("perl-test-simple" ,perl-test-simple)))
1351 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1352 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1354 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1355 reads to long reference sequences. It is particularly good at aligning reads
1356 of about 50 up to 100s or 1,000s of characters, and particularly good at
1357 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1358 genome with an FM Index to keep its memory footprint small: for the human
1359 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1360 gapped, local, and paired-end alignment modes.")
1361 (supported-systems '("x86_64-linux"))
1362 (license license:gpl3+)))
1364 (define-public tophat
1371 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1375 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1376 (modules '((guix build utils)))
1379 ;; Remove bundled SeqAn and samtools
1380 (delete-file-recursively "src/SeqAn-1.4.2")
1381 (delete-file-recursively "src/samtools-0.1.18")
1383 (build-system gnu-build-system)
1385 '(#:parallel-build? #f ; not supported
1387 (modify-phases %standard-phases
1388 (add-after 'unpack 'use-system-samtools
1389 (lambda* (#:key inputs #:allow-other-keys)
1390 (substitute* "src/Makefile.in"
1391 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1392 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1393 (("SAMPROG = samtools_0\\.1\\.18") "")
1394 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1395 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1396 (substitute* '("src/common.cpp"
1398 (("samtools_0.1.18") (which "samtools")))
1399 (substitute* '("src/common.h"
1400 "src/bam2fastx.cpp")
1401 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1402 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1403 (substitute* '("src/bwt_map.h"
1405 "src/align_status.h")
1406 (("#include <bam.h>") "#include <samtools/bam.h>")
1407 (("#include <sam.h>") "#include <samtools/sam.h>"))
1412 ("samtools" ,samtools-0.1)
1413 ("ncurses" ,ncurses)
1414 ("python" ,python-2)
1417 ("seqan" ,seqan-1)))
1418 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1419 (synopsis "Spliced read mapper for RNA-Seq data")
1421 "TopHat is a fast splice junction mapper for nucleotide sequence
1422 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1423 mammalian-sized genomes using the ultra high-throughput short read
1424 aligner Bowtie, and then analyzes the mapping results to identify
1425 splice junctions between exons.")
1426 ;; TopHat is released under the Boost Software License, Version 1.0
1427 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1428 (license license:boost1.0)))
1437 "https://github.com/lh3/bwa/releases/download/v"
1438 version "/bwa-" version ".tar.bz2"))
1441 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1442 (build-system gnu-build-system)
1444 '(#:tests? #f ;no "check" target
1446 (modify-phases %standard-phases
1448 (lambda* (#:key outputs #:allow-other-keys)
1449 (let ((bin (string-append
1450 (assoc-ref outputs "out") "/bin"))
1452 (assoc-ref outputs "out") "/share/doc/bwa"))
1454 (assoc-ref outputs "out") "/share/man/man1")))
1455 (install-file "bwa" bin)
1456 (install-file "README.md" doc)
1457 (install-file "bwa.1" man))
1459 ;; no "configure" script
1460 (delete 'configure))))
1461 (inputs `(("zlib" ,zlib)))
1462 ;; Non-portable SSE instructions are used so building fails on platforms
1463 ;; other than x86_64.
1464 (supported-systems '("x86_64-linux"))
1465 (home-page "http://bio-bwa.sourceforge.net/")
1466 (synopsis "Burrows-Wheeler sequence aligner")
1468 "BWA is a software package for mapping low-divergent sequences against a
1469 large reference genome, such as the human genome. It consists of three
1470 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1471 designed for Illumina sequence reads up to 100bp, while the rest two for
1472 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1473 features such as long-read support and split alignment, but BWA-MEM, which is
1474 the latest, is generally recommended for high-quality queries as it is faster
1475 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1476 70-100bp Illumina reads.")
1477 (license license:gpl3+)))
1479 (define-public bwa-pssm
1480 (package (inherit bwa)
1486 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1488 (file-name (git-file-name name version))
1491 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1492 (build-system gnu-build-system)
1497 (home-page "http://bwa-pssm.binf.ku.dk/")
1498 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1500 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1501 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1502 existing aligners it is fast and sensitive. Unlike most other aligners,
1503 however, it is also adaptible in the sense that one can direct the alignment
1504 based on known biases within the data set. It is coded as a modification of
1505 the original BWA alignment program and shares the genome index structure as
1506 well as many of the command line options.")
1507 (license license:gpl3+)))
1509 (define-public python-bx-python
1511 (name "python-bx-python")
1515 (uri (pypi-uri "bx-python" version))
1518 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1519 (build-system python-build-system)
1520 ;; Tests fail because test data are not included
1521 (arguments '(#:tests? #f))
1523 `(("python-numpy" ,python-numpy)
1524 ("python-six" ,python-six)))
1528 `(("python-lzo" ,python-lzo)
1529 ("python-nose" ,python-nose)
1530 ("python-cython" ,python-cython)))
1531 (home-page "https://github.com/bxlab/bx-python")
1532 (synopsis "Tools for manipulating biological data")
1534 "bx-python provides tools for manipulating biological data, particularly
1535 multiple sequence alignments.")
1536 (license license:expat)))
1538 (define-public python2-bx-python
1539 (package-with-python2 python-bx-python))
1541 (define-public python-pysam
1543 (name "python-pysam")
1547 ;; Test data is missing on PyPi.
1549 (url "https://github.com/pysam-developers/pysam.git")
1550 (commit (string-append "v" version))))
1551 (file-name (git-file-name name version))
1554 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1555 (modules '((guix build utils)))
1557 ;; Drop bundled htslib. TODO: Also remove samtools
1559 (delete-file-recursively "htslib")
1561 (build-system python-build-system)
1563 `(#:modules ((ice-9 ftw)
1565 (guix build python-build-system)
1568 (modify-phases %standard-phases
1569 (add-before 'build 'set-flags
1570 (lambda* (#:key inputs #:allow-other-keys)
1571 (setenv "HTSLIB_MODE" "external")
1572 (setenv "HTSLIB_LIBRARY_DIR"
1573 (string-append (assoc-ref inputs "htslib") "/lib"))
1574 (setenv "HTSLIB_INCLUDE_DIR"
1575 (string-append (assoc-ref inputs "htslib") "/include"))
1576 (setenv "LDFLAGS" "-lncurses")
1577 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1580 (lambda* (#:key inputs outputs #:allow-other-keys)
1581 ;; This file contains tests that require a connection to the
1583 (delete-file "tests/tabix_test.py")
1584 ;; FIXME: This test fails
1585 (delete-file "tests/AlignmentFile_test.py")
1586 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1587 (setenv "PYTHONPATH"
1589 (getenv "PYTHONPATH")
1590 ":" (getcwd) "/build/"
1591 (car (scandir "build"
1592 (negate (cut string-prefix? "." <>))))))
1593 ;; Step out of source dir so python does not import from CWD.
1594 (with-directory-excursion "tests"
1595 (setenv "HOME" "/tmp")
1596 (invoke "make" "-C" "pysam_data")
1597 (invoke "make" "-C" "cbcf_data")
1598 ;; Running nosetests without explicitly asking for a single
1599 ;; process leads to a crash. Running with multiple processes
1600 ;; fails because the tests are not designed to run in parallel.
1602 ;; FIXME: tests keep timing out on some systems.
1603 (invoke "nosetests" "-v" "--processes" "1")))))))
1605 `(("htslib" ,htslib))) ; Included from installed header files.
1607 `(("ncurses" ,ncurses)
1611 `(("python-cython" ,python-cython)
1612 ;; Dependencies below are are for tests only.
1613 ("samtools" ,samtools)
1614 ("bcftools" ,bcftools)
1615 ("python-nose" ,python-nose)))
1616 (home-page "https://github.com/pysam-developers/pysam")
1617 (synopsis "Python bindings to the SAMtools C API")
1619 "Pysam is a Python module for reading and manipulating files in the
1620 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1621 also includes an interface for tabix.")
1622 (license license:expat)))
1624 (define-public python2-pysam
1625 (package-with-python2 python-pysam))
1627 (define-public python-twobitreader
1629 (name "python-twobitreader")
1634 (url "https://github.com/benjschiller/twobitreader")
1636 (file-name (git-file-name name version))
1639 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1640 (build-system python-build-system)
1641 ;; Tests are not included
1642 (arguments '(#:tests? #f))
1644 `(("python-sphinx" ,python-sphinx)))
1645 (home-page "https://github.com/benjschiller/twobitreader")
1646 (synopsis "Python library for reading .2bit files")
1648 "twobitreader is a Python library for reading .2bit files as used by the
1649 UCSC genome browser.")
1650 (license license:artistic2.0)))
1652 (define-public python2-twobitreader
1653 (package-with-python2 python-twobitreader))
1655 (define-public python-plastid
1657 (name "python-plastid")
1661 (uri (pypi-uri "plastid" version))
1664 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1665 (build-system python-build-system)
1667 ;; Some test files are not included.
1670 `(("python-numpy" ,python-numpy)
1671 ("python-scipy" ,python-scipy)
1672 ("python-pandas" ,python-pandas)
1673 ("python-pysam" ,python-pysam)
1674 ("python-matplotlib" ,python-matplotlib)
1675 ("python-biopython" ,python-biopython)
1676 ("python-twobitreader" ,python-twobitreader)
1677 ("python-termcolor" ,python-termcolor)))
1679 `(("python-cython" ,python-cython)
1680 ("python-nose" ,python-nose)))
1681 (home-page "https://github.com/joshuagryphon/plastid")
1682 (synopsis "Python library for genomic analysis")
1684 "plastid is a Python library for genomic analysis – in particular,
1685 high-throughput sequencing data – with an emphasis on simplicity.")
1686 (license license:bsd-3)))
1688 (define-public python2-plastid
1689 (package-with-python2 python-plastid))
1691 (define-public cd-hit
1697 (uri (string-append "https://github.com/weizhongli/cdhit"
1698 "/releases/download/V" version
1700 "-2017-0621-source.tar.gz"))
1703 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1704 (build-system gnu-build-system)
1706 `(#:tests? #f ; there are no tests
1708 ;; Executables are copied directly to the PREFIX.
1709 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1711 (modify-phases %standard-phases
1712 ;; No "configure" script
1714 ;; Remove sources of non-determinism
1715 (add-after 'unpack 'be-timeless
1717 (substitute* "cdhit-utility.c++"
1718 ((" \\(built on \" __DATE__ \"\\)") ""))
1719 (substitute* "cdhit-common.c++"
1720 (("__DATE__") "\"0\"")
1721 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1723 ;; The "install" target does not create the target directory.
1724 (add-before 'install 'create-target-dir
1725 (lambda* (#:key outputs #:allow-other-keys)
1726 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1730 (home-page "http://weizhongli-lab.org/cd-hit/")
1731 (synopsis "Cluster and compare protein or nucleotide sequences")
1733 "CD-HIT is a program for clustering and comparing protein or nucleotide
1734 sequences. CD-HIT is designed to be fast and handle extremely large
1736 ;; The manual says: "It can be copied under the GNU General Public License
1737 ;; version 2 (GPLv2)."
1738 (license license:gpl2)))
1740 (define-public clipper
1747 (url "https://github.com/YeoLab/clipper.git")
1749 (file-name (git-file-name name version))
1752 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1753 (modules '((guix build utils)))
1756 ;; remove unnecessary setup dependency
1757 (substitute* "setup.py"
1758 (("setup_requires = .*") ""))
1760 (build-system python-build-system)
1762 `(#:python ,python-2 ; only Python 2 is supported
1764 (modify-phases %standard-phases
1765 ;; This is fixed in upstream commit
1766 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1767 (add-after 'unpack 'fix-typo
1769 (substitute* "clipper/src/readsToWiggle.pyx"
1773 `(("htseq" ,python2-htseq)
1774 ("python-pybedtools" ,python2-pybedtools)
1775 ("python-cython" ,python2-cython)
1776 ("python-scikit-learn" ,python2-scikit-learn)
1777 ("python-matplotlib" ,python2-matplotlib)
1778 ("python-pandas" ,python2-pandas)
1779 ("python-pysam" ,python2-pysam)
1780 ("python-numpy" ,python2-numpy)
1781 ("python-scipy" ,python2-scipy)))
1783 `(("python-mock" ,python2-mock) ; for tests
1784 ("python-nose" ,python2-nose) ; for tests
1785 ("python-pytz" ,python2-pytz))) ; for tests
1786 (home-page "https://github.com/YeoLab/clipper")
1787 (synopsis "CLIP peak enrichment recognition")
1789 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1790 (license license:gpl2)))
1792 (define-public codingquarry
1794 (name "codingquarry")
1799 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1803 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1804 (build-system gnu-build-system)
1806 '(#:tests? #f ; no "check" target
1808 (modify-phases %standard-phases
1811 (lambda* (#:key outputs #:allow-other-keys)
1812 (let* ((out (assoc-ref outputs "out"))
1813 (bin (string-append out "/bin"))
1814 (doc (string-append out "/share/doc/codingquarry")))
1815 (install-file "INSTRUCTIONS.pdf" doc)
1816 (copy-recursively "QuarryFiles"
1817 (string-append out "/QuarryFiles"))
1818 (install-file "CodingQuarry" bin)
1819 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1821 (inputs `(("openmpi" ,openmpi)))
1822 (native-search-paths
1823 (list (search-path-specification
1824 (variable "QUARRY_PATH")
1825 (files '("QuarryFiles")))))
1826 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1827 (synopsis "Fungal gene predictor")
1828 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1829 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1830 (home-page "https://sourceforge.net/projects/codingquarry/")
1831 (license license:gpl3+)))
1833 (define-public couger
1840 "http://couger.oit.duke.edu/static/assets/COUGER"
1844 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1845 (build-system gnu-build-system)
1849 (modify-phases %standard-phases
1854 (lambda* (#:key outputs #:allow-other-keys)
1855 (let* ((out (assoc-ref outputs "out"))
1856 (bin (string-append out "/bin")))
1857 (copy-recursively "src" (string-append out "/src"))
1859 ;; Add "src" directory to module lookup path.
1860 (substitute* "couger"
1862 (string-append "import sys\nsys.path.append(\""
1863 out "\")\nfrom argparse")))
1864 (install-file "couger" bin))
1867 'install 'wrap-program
1868 (lambda* (#:key inputs outputs #:allow-other-keys)
1869 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1870 (let* ((out (assoc-ref outputs "out"))
1871 (path (getenv "PYTHONPATH")))
1872 (wrap-program (string-append out "/bin/couger")
1873 `("PYTHONPATH" ":" prefix (,path))))
1876 `(("python" ,python-2)
1877 ("python2-pillow" ,python2-pillow)
1878 ("python2-numpy" ,python2-numpy)
1879 ("python2-scipy" ,python2-scipy)
1880 ("python2-matplotlib" ,python2-matplotlib)))
1882 `(("r-minimal" ,r-minimal)
1884 ("randomjungle" ,randomjungle)))
1886 `(("unzip" ,unzip)))
1887 (home-page "http://couger.oit.duke.edu")
1888 (synopsis "Identify co-factors in sets of genomic regions")
1890 "COUGER can be applied to any two sets of genomic regions bound by
1891 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1892 putative co-factors that provide specificity to each TF. The framework
1893 determines the genomic targets uniquely-bound by each TF, and identifies a
1894 small set of co-factors that best explain the in vivo binding differences
1895 between the two TFs.
1897 COUGER uses classification algorithms (support vector machines and random
1898 forests) with features that reflect the DNA binding specificities of putative
1899 co-factors. The features are generated either from high-throughput TF-DNA
1900 binding data (from protein binding microarray experiments), or from large
1901 collections of DNA motifs.")
1902 (license license:gpl3+)))
1904 (define-public clustal-omega
1906 (name "clustal-omega")
1910 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1914 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1915 (build-system gnu-build-system)
1917 `(("argtable" ,argtable)))
1918 (home-page "http://www.clustal.org/omega/")
1919 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1921 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1922 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1923 of handling data-sets of hundreds of thousands of sequences in reasonable
1925 (license license:gpl2+)))
1927 (define-public crossmap
1933 (uri (pypi-uri "CrossMap" version))
1936 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1937 (build-system python-build-system)
1938 (arguments `(#:python ,python-2))
1940 `(("python-bx-python" ,python2-bx-python)
1941 ("python-numpy" ,python2-numpy)
1942 ("python-pysam" ,python2-pysam)
1945 `(("python-cython" ,python2-cython)
1946 ("python-nose" ,python2-nose)))
1947 (home-page "http://crossmap.sourceforge.net/")
1948 (synopsis "Convert genome coordinates between assemblies")
1950 "CrossMap is a program for conversion of genome coordinates or annotation
1951 files between different genome assemblies. It supports most commonly used
1952 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1953 (license license:gpl2+)))
1955 (define-public python-dnaio
1957 (name "python-dnaio")
1962 (uri (pypi-uri "dnaio" version))
1965 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1966 (build-system python-build-system)
1968 `(("python-cython" ,python-cython)
1969 ("python-pytest" ,python-pytest)
1970 ("python-xopen" ,python-xopen)))
1971 (home-page "https://github.com/marcelm/dnaio/")
1972 (synopsis "Read FASTA and FASTQ files efficiently")
1974 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1975 files. The code was previously part of the cutadapt tool.")
1976 (license license:expat)))
1978 (define-public cutadapt
1985 (url "https://github.com/marcelm/cutadapt.git")
1986 (commit (string-append "v" version))))
1987 (file-name (git-file-name name version))
1990 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1991 (build-system python-build-system)
1993 `(("python-dnaio" ,python-dnaio)
1994 ("python-xopen" ,python-xopen)))
1996 `(("python-cython" ,python-cython)
1997 ("python-pytest" ,python-pytest)))
1998 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1999 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2001 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2002 other types of unwanted sequence from high-throughput sequencing reads.")
2003 (license license:expat)))
2005 (define-public libbigwig
2012 (url "https://github.com/dpryan79/libBigWig.git")
2014 (file-name (string-append name "-" version "-checkout"))
2017 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2018 (build-system gnu-build-system)
2020 `(#:test-target "test"
2021 #:tests? #f ; tests require access to the web
2024 (string-append "prefix=" (assoc-ref %outputs "out")))
2026 (modify-phases %standard-phases
2027 (delete 'configure))))
2032 `(("doxygen" ,doxygen)
2034 ("python" ,python-2)))
2035 (home-page "https://github.com/dpryan79/libBigWig")
2036 (synopsis "C library for handling bigWig files")
2038 "This package provides a C library for parsing local and remote BigWig
2040 (license license:expat)))
2042 (define-public python-pybigwig
2044 (name "python-pybigwig")
2048 (uri (pypi-uri "pyBigWig" version))
2051 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2052 (modules '((guix build utils)))
2055 ;; Delete bundled libBigWig sources
2056 (delete-file-recursively "libBigWig")
2058 (build-system python-build-system)
2061 (modify-phases %standard-phases
2062 (add-after 'unpack 'link-with-libBigWig
2063 (lambda* (#:key inputs #:allow-other-keys)
2064 (substitute* "setup.py"
2065 (("libs=\\[") "libs=[\"BigWig\", "))
2068 `(("python-numpy" ,python-numpy)))
2070 `(("libbigwig" ,libbigwig)
2073 (home-page "https://github.com/dpryan79/pyBigWig")
2074 (synopsis "Access bigWig files in Python using libBigWig")
2076 "This package provides Python bindings to the libBigWig library for
2077 accessing bigWig files.")
2078 (license license:expat)))
2080 (define-public python2-pybigwig
2081 (package-with-python2 python-pybigwig))
2083 (define-public python-dendropy
2085 (name "python-dendropy")
2090 ;; Source from GitHub so that tests are included.
2092 (url "https://github.com/jeetsukumaran/DendroPy.git")
2093 (commit (string-append "v" version))))
2094 (file-name (git-file-name name version))
2097 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2098 (build-system python-build-system)
2099 (home-page "http://packages.python.org/DendroPy/")
2100 (synopsis "Library for phylogenetics and phylogenetic computing")
2102 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2103 writing, simulation, processing and manipulation of phylogenetic
2104 trees (phylogenies) and characters.")
2105 (license license:bsd-3)))
2107 (define-public python2-dendropy
2108 (let ((base (package-with-python2 python-dendropy)))
2113 (modify-phases %standard-phases
2114 (add-after 'unpack 'remove-failing-test
2116 ;; This test fails when the full test suite is run, as documented
2117 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2118 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2119 (("test_collection_comments_and_annotations")
2120 "do_not_test_collection_comments_and_annotations"))
2122 ,@(package-arguments base))))))
2124 (define-public python-py2bit
2126 (name "python-py2bit")
2131 (uri (pypi-uri "py2bit" version))
2134 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2135 (build-system python-build-system)
2136 (home-page "https://github.com/dpryan79/py2bit")
2137 (synopsis "Access 2bit files using lib2bit")
2139 "This package provides Python bindings for lib2bit to access 2bit files
2141 (license license:expat)))
2143 (define-public deeptools
2150 (url "https://github.com/deeptools/deepTools.git")
2152 (file-name (git-file-name name version))
2155 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2156 (build-system python-build-system)
2159 (modify-phases %standard-phases
2160 ;; This phase fails, but it's not needed.
2161 (delete 'reset-gzip-timestamps))))
2163 `(("python-plotly" ,python-plotly)
2164 ("python-scipy" ,python-scipy)
2165 ("python-numpy" ,python-numpy)
2166 ("python-numpydoc" ,python-numpydoc)
2167 ("python-matplotlib" ,python-matplotlib)
2168 ("python-pysam" ,python-pysam)
2169 ("python-py2bit" ,python-py2bit)
2170 ("python-pybigwig" ,python-pybigwig)))
2172 `(("python-mock" ,python-mock) ;for tests
2173 ("python-nose" ,python-nose) ;for tests
2174 ("python-pytz" ,python-pytz))) ;for tests
2175 (home-page "https://github.com/deeptools/deepTools")
2176 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2178 "DeepTools addresses the challenge of handling the large amounts of data
2179 that are now routinely generated from DNA sequencing centers. To do so,
2180 deepTools contains useful modules to process the mapped reads data to create
2181 coverage files in standard bedGraph and bigWig file formats. By doing so,
2182 deepTools allows the creation of normalized coverage files or the comparison
2183 between two files (for example, treatment and control). Finally, using such
2184 normalized and standardized files, multiple visualizations can be created to
2185 identify enrichments with functional annotations of the genome.")
2186 (license license:gpl3+)))
2188 (define-public delly
2195 (url "https://github.com/dellytools/delly.git")
2196 (commit (string-append "v" version))))
2197 (file-name (git-file-name name version))
2199 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2200 (modules '((guix build utils)))
2203 (delete-file-recursively "src/htslib")
2205 (build-system gnu-build-system)
2207 `(#:tests? #f ; There are no tests to run.
2209 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2210 (string-append "prefix=" (assoc-ref %outputs "out")))
2212 (modify-phases %standard-phases
2213 (delete 'configure) ; There is no configure phase.
2214 (add-after 'install 'install-templates
2215 (lambda* (#:key outputs #:allow-other-keys)
2216 (let ((templates (string-append (assoc-ref outputs "out")
2217 "/share/delly/templates")))
2219 (copy-recursively "excludeTemplates" templates)
2226 (home-page "https://github.com/dellytools/delly")
2227 (synopsis "Integrated structural variant prediction method")
2228 (description "Delly is an integrated structural variant prediction method
2229 that can discover and genotype deletions, tandem duplications, inversions and
2230 translocations at single-nucleotide resolution in short-read massively parallel
2231 sequencing data. It uses paired-ends and split-reads to sensitively and
2232 accurately delineate genomic rearrangements throughout the genome.")
2233 (license license:gpl3+)))
2235 (define-public diamond
2242 (url "https://github.com/bbuchfink/diamond.git")
2243 (commit (string-append "v" version))))
2244 (file-name (git-file-name name version))
2247 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2248 (build-system cmake-build-system)
2250 '(#:tests? #f ; no "check" target
2252 (modify-phases %standard-phases
2253 (add-after 'unpack 'remove-native-compilation
2255 (substitute* "CMakeLists.txt" (("-march=native") ""))
2259 (home-page "https://github.com/bbuchfink/diamond")
2260 (synopsis "Accelerated BLAST compatible local sequence aligner")
2262 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2263 translated DNA query sequences against a protein reference database (BLASTP
2264 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2265 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2266 data and settings.")
2267 (license license:agpl3+)))
2269 (define-public discrover
2277 (url "https://github.com/maaskola/discrover.git")
2279 (file-name (git-file-name name version))
2282 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2283 (build-system cmake-build-system)
2285 `(#:tests? #f ; there are no tests
2287 (modify-phases %standard-phases
2288 (add-after 'unpack 'add-missing-includes
2290 (substitute* "src/executioninformation.hpp"
2291 (("#define EXECUTIONINFORMATION_HPP" line)
2292 (string-append line "\n#include <random>")))
2293 (substitute* "src/plasma/fasta.hpp"
2294 (("#define FASTA_HPP" line)
2295 (string-append line "\n#include <random>")))
2301 `(("texlive" ,texlive)
2302 ;; TODO: Replace texlive with minimal texlive-union.
2303 ;; ("texlive" ,(texlive-union (list texlive-latex-doi
2304 ;; texlive-latex-hyperref
2305 ;; texlive-latex-oberdiek
2306 ;; texlive-generic-ifxetex
2307 ;; texlive-latex-url
2308 ;; texlive-latex-pgf
2309 ;; texlive-latex-examplep
2310 ;; texlive-latex-natbib
2311 ;; texlive-latex-verbatimbox
2313 ;; texlive-latex-xcolor
2314 ;; texlive-fonts-amsfonts
2315 ;; texlive-latex-amsfonts
2318 ("imagemagick" ,imagemagick)))
2319 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2320 (synopsis "Discover discriminative nucleotide sequence motifs")
2321 (description "Discrover is a motif discovery method to find binding sites
2322 of nucleic acid binding proteins.")
2323 (license license:gpl3+)))
2325 (define-public eigensoft
2333 (url "https://github.com/DReichLab/EIG.git")
2334 (commit (string-append "v" version))))
2335 (file-name (git-file-name name version))
2338 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2339 (modules '((guix build utils)))
2340 ;; Remove pre-built binaries.
2342 (delete-file-recursively "bin")
2345 (build-system gnu-build-system)
2347 `(#:tests? #f ; There are no tests.
2348 #:make-flags '("CC=gcc")
2350 (modify-phases %standard-phases
2351 ;; There is no configure phase, but the Makefile is in a
2354 (lambda _ (chdir "src") #t))
2355 ;; The provided install target only copies executables to
2356 ;; the "bin" directory in the build root.
2357 (add-after 'install 'actually-install
2358 (lambda* (#:key outputs #:allow-other-keys)
2359 (let* ((out (assoc-ref outputs "out"))
2360 (bin (string-append out "/bin")))
2361 (for-each (lambda (file)
2362 (install-file file bin))
2363 (find-files "../bin" ".*"))
2368 ("openblas" ,openblas)
2370 ("gfortran" ,gfortran "lib")))
2371 (home-page "https://github.com/DReichLab/EIG")
2372 (synopsis "Tools for population genetics")
2373 (description "The EIGENSOFT package provides tools for population
2374 genetics and stratification correction. EIGENSOFT implements methods commonly
2375 used in population genetics analyses such as PCA, computation of Tracy-Widom
2376 statistics, and finding related individuals in structured populations. It
2377 comes with a built-in plotting script and supports multiple file formats and
2378 quantitative phenotypes.")
2379 ;; The license of the eigensoft tools is Expat, but since it's
2380 ;; linking with the GNU Scientific Library (GSL) the effective
2381 ;; license is the GPL.
2382 (license license:gpl3+)))
2384 (define-public edirect
2387 (version "10.2.20181018")
2390 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2391 "/versions/" version
2392 "/edirect-" version ".tar.gz"))
2395 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2396 (build-system perl-build-system)
2399 (modify-phases %standard-phases
2402 (delete 'check) ; simple check after install
2404 (lambda* (#:key outputs #:allow-other-keys)
2405 (install-file "edirect.pl"
2406 (string-append (assoc-ref outputs "out") "/bin"))
2408 (add-after 'install 'wrap-program
2409 (lambda* (#:key outputs #:allow-other-keys)
2410 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2411 (let* ((out (assoc-ref outputs "out"))
2412 (path (getenv "PERL5LIB")))
2413 (wrap-program (string-append out "/bin/edirect.pl")
2414 `("PERL5LIB" ":" prefix (,path))))
2416 (add-after 'wrap-program 'check
2417 (lambda* (#:key outputs #:allow-other-keys)
2418 (invoke (string-append (assoc-ref outputs "out")
2423 `(("perl-html-parser" ,perl-html-parser)
2424 ("perl-encode-locale" ,perl-encode-locale)
2425 ("perl-file-listing" ,perl-file-listing)
2426 ("perl-html-tagset" ,perl-html-tagset)
2427 ("perl-html-tree" ,perl-html-tree)
2428 ("perl-http-cookies" ,perl-http-cookies)
2429 ("perl-http-date" ,perl-http-date)
2430 ("perl-http-message" ,perl-http-message)
2431 ("perl-http-negotiate" ,perl-http-negotiate)
2432 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2433 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2434 ("perl-net-http" ,perl-net-http)
2435 ("perl-uri" ,perl-uri)
2436 ("perl-www-robotrules" ,perl-www-robotrules)
2437 ("perl-xml-simple" ,perl-xml-simple)
2439 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2440 (synopsis "Tools for accessing the NCBI's set of databases")
2442 "Entrez Direct (EDirect) is a method for accessing the National Center
2443 for Biotechnology Information's (NCBI) set of interconnected
2444 databases (publication, sequence, structure, gene, variation, expression,
2445 etc.) from a terminal. Functions take search terms from command-line
2446 arguments. Individual operations are combined to build multi-step queries.
2447 Record retrieval and formatting normally complete the process.
2449 EDirect also provides an argument-driven function that simplifies the
2450 extraction of data from document summaries or other results that are returned
2451 in structured XML format. This can eliminate the need for writing custom
2452 software to answer ad hoc questions.")
2453 (license license:public-domain)))
2455 (define-public exonerate
2464 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2465 "exonerate-" version ".tar.gz"))
2468 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2469 (build-system gnu-build-system)
2471 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2473 `(("pkg-config" ,pkg-config)))
2477 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2478 (synopsis "Generic tool for biological sequence alignment")
2480 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2481 the alignment of sequences using a many alignment models, either exhaustive
2482 dynamic programming or a variety of heuristics.")
2483 (license license:gpl3)))
2485 (define-public express
2493 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2494 version "/express-" version "-src.tgz"))
2497 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2498 (build-system cmake-build-system)
2500 `(#:tests? #f ;no "check" target
2502 (modify-phases %standard-phases
2503 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2504 (lambda* (#:key inputs #:allow-other-keys)
2505 (substitute* "CMakeLists.txt"
2506 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2507 "set(Boost_USE_STATIC_LIBS OFF)")
2508 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2509 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2510 (substitute* "src/CMakeLists.txt"
2511 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2512 (string-append (assoc-ref inputs "bamtools") "/lib"))
2513 (("libprotobuf.a") "libprotobuf.so"))
2517 ("bamtools" ,bamtools)
2518 ("protobuf" ,protobuf)
2520 (home-page "http://bio.math.berkeley.edu/eXpress")
2521 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2523 "eXpress is a streaming tool for quantifying the abundances of a set of
2524 target sequences from sampled subsequences. Example applications include
2525 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2526 analysis (from RNA-Seq), transcription factor binding quantification in
2527 ChIP-Seq, and analysis of metagenomic data.")
2528 (license license:artistic2.0)))
2530 (define-public express-beta-diversity
2532 (name "express-beta-diversity")
2537 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2538 (commit (string-append "v" version))))
2539 (file-name (git-file-name name version))
2542 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2543 (build-system gnu-build-system)
2546 (modify-phases %standard-phases
2548 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2550 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2552 (lambda* (#:key outputs #:allow-other-keys)
2553 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2554 (install-file "../scripts/convertToEBD.py" bin)
2555 (install-file "../bin/ExpressBetaDiversity" bin)
2558 `(("python" ,python-2)))
2559 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2560 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2562 "Express Beta Diversity (EBD) calculates ecological beta diversity
2563 (dissimilarity) measures between biological communities. EBD implements a
2564 variety of diversity measures including those that make use of phylogenetic
2565 similarity of community members.")
2566 (license license:gpl3+)))
2568 (define-public fasttree
2575 "http://www.microbesonline.org/fasttree/FastTree-"
2579 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2580 (build-system gnu-build-system)
2582 `(#:tests? #f ; no "check" target
2584 (modify-phases %standard-phases
2588 (lambda* (#:key source #:allow-other-keys)
2591 "-finline-functions"
2602 "-finline-functions"
2611 (lambda* (#:key outputs #:allow-other-keys)
2612 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2613 (install-file "FastTree" bin)
2614 (install-file "FastTreeMP" bin)
2616 (home-page "http://www.microbesonline.org/fasttree")
2617 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2619 "FastTree can handle alignments with up to a million of sequences in a
2620 reasonable amount of time and memory. For large alignments, FastTree is
2621 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2622 (license license:gpl2+)))
2624 (define-public fastx-toolkit
2626 (name "fastx-toolkit")
2632 "https://github.com/agordon/fastx_toolkit/releases/download/"
2633 version "/fastx_toolkit-" version ".tar.bz2"))
2636 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2637 (build-system gnu-build-system)
2639 `(("libgtextutils" ,libgtextutils)))
2641 `(("pkg-config" ,pkg-config)))
2642 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2643 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2645 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2646 FASTA/FASTQ files preprocessing.
2648 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2649 containing multiple short-reads sequences. The main processing of such
2650 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2651 is sometimes more productive to preprocess the files before mapping the
2652 sequences to the genome---manipulating the sequences to produce better mapping
2653 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2654 (license license:agpl3+)))
2656 (define-public flexbar
2663 (url "https://github.com/seqan/flexbar.git")
2664 (commit (string-append "v" version))))
2665 (file-name (git-file-name name version))
2668 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2669 (build-system cmake-build-system)
2672 (modify-phases %standard-phases
2674 (lambda* (#:key outputs #:allow-other-keys)
2675 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2676 (with-directory-excursion "../source/test"
2677 (invoke "bash" "flexbar_test.sh"))
2680 (lambda* (#:key outputs #:allow-other-keys)
2681 (let* ((out (string-append (assoc-ref outputs "out")))
2682 (bin (string-append out "/bin/")))
2683 (install-file "flexbar" bin))
2689 `(("pkg-config" ,pkg-config)
2691 (home-page "https://github.com/seqan/flexbar")
2692 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2694 "Flexbar preprocesses high-throughput nucleotide sequencing data
2695 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2696 Moreover, trimming and filtering features are provided. Flexbar increases
2697 read mapping rates and improves genome and transcriptome assemblies. It
2698 supports next-generation sequencing data in fasta/q and csfasta/q format from
2699 Illumina, Roche 454, and the SOLiD platform.")
2700 (license license:bsd-3)))
2702 (define-public fraggenescan
2704 (name "fraggenescan")
2710 (string-append "mirror://sourceforge/fraggenescan/"
2711 "FragGeneScan" version ".tar.gz"))
2713 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2714 (build-system gnu-build-system)
2717 (modify-phases %standard-phases
2719 (add-before 'build 'patch-paths
2720 (lambda* (#:key outputs #:allow-other-keys)
2721 (let* ((out (string-append (assoc-ref outputs "out")))
2722 (share (string-append out "/share/fraggenescan/")))
2723 (substitute* "run_FragGeneScan.pl"
2725 (string-append "system(\"" (which "rm")))
2727 (string-append "system(\"" (which "mv")))
2728 (("\\\"awk") (string-append "\"" (which "awk")))
2729 ;; This script and other programs expect the training files
2730 ;; to be in the non-standard location bin/train/XXX. Change
2731 ;; this to be share/fraggenescan/train/XXX instead.
2732 (("^\\$train.file = \\$dir.*")
2733 (string-append "$train_file = \""
2735 "train/\".$FGS_train_file;")))
2736 (substitute* "run_hmm.c"
2737 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2738 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2742 (invoke "make" "clean")
2743 (invoke "make" "fgs")
2746 (lambda* (#:key outputs #:allow-other-keys)
2747 (let* ((out (string-append (assoc-ref outputs "out")))
2748 (bin (string-append out "/bin/"))
2749 (share (string-append out "/share/fraggenescan/train")))
2750 (install-file "run_FragGeneScan.pl" bin)
2751 (install-file "FragGeneScan" bin)
2752 (copy-recursively "train" share))
2755 (add-after 'install 'post-install-check
2756 ;; In lieu of 'make check', run one of the examples and check the
2757 ;; output files gets created.
2758 (lambda* (#:key outputs #:allow-other-keys)
2759 (let* ((out (string-append (assoc-ref outputs "out")))
2760 (bin (string-append out "/bin/"))
2761 (frag (string-append bin "run_FragGeneScan.pl")))
2762 ;; Test complete genome.
2764 "-genome=./example/NC_000913.fna"
2768 (unless (and (file-exists? "test2.faa")
2769 (file-exists? "test2.ffn")
2770 (file-exists? "test2.gff")
2771 (file-exists? "test2.out"))
2772 (error "Expected files do not exist."))
2773 ;; Test incomplete sequences.
2775 "-genome=./example/NC_000913-fgs.ffn"
2782 ("python" ,python-2))) ;not compatible with python 3.
2783 (home-page "https://sourceforge.net/projects/fraggenescan/")
2784 (synopsis "Finds potentially fragmented genes in short reads")
2786 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2787 short and error-prone DNA sequencing reads. It can also be applied to predict
2788 genes in incomplete assemblies or complete genomes.")
2789 ;; GPL3+ according to private correspondense with the authors.
2790 (license license:gpl3+)))
2792 (define-public fxtract
2793 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2801 (url "https://github.com/ctSkennerton/fxtract.git")
2803 (file-name (git-file-name name version))
2806 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2807 (build-system gnu-build-system)
2809 `(#:make-flags (list
2810 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2812 #:test-target "fxtract_test"
2814 (modify-phases %standard-phases
2816 (add-before 'build 'copy-util
2817 (lambda* (#:key inputs #:allow-other-keys)
2819 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2821 ;; Do not use make install as this requires additional dependencies.
2823 (lambda* (#:key outputs #:allow-other-keys)
2824 (let* ((out (assoc-ref outputs "out"))
2825 (bin (string-append out"/bin")))
2826 (install-file "fxtract" bin)
2832 ;; ctskennerton-util is licensed under GPL2.
2833 `(("ctskennerton-util"
2837 (url "https://github.com/ctSkennerton/util.git")
2838 (commit util-commit)))
2839 (file-name (string-append
2840 "ctstennerton-util-" util-commit "-checkout"))
2843 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2844 (home-page "https://github.com/ctSkennerton/fxtract")
2845 (synopsis "Extract sequences from FASTA and FASTQ files")
2847 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2848 or FASTQ) file given a subsequence. It uses a simple substring search for
2849 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2850 lookups or multi-pattern searching as required. By default fxtract looks in
2851 the sequence of each record but can also be told to look in the header,
2852 comment or quality sections.")
2853 ;; 'util' requires SSE instructions.
2854 (supported-systems '("x86_64-linux"))
2855 (license license:expat))))
2857 (define-public gemma
2864 (url "https://github.com/xiangzhou/GEMMA.git")
2865 (commit (string-append "v" version))))
2866 (file-name (git-file-name name version))
2869 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2872 ("gfortran" ,gfortran "lib")
2875 ("openblas" ,openblas)
2877 (build-system gnu-build-system)
2880 '(,@(match (%current-system)
2882 '("FORCE_DYNAMIC=1"))
2884 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2886 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2888 (modify-phases %standard-phases
2890 (add-after 'unpack 'find-eigen
2891 (lambda* (#:key inputs #:allow-other-keys)
2892 ;; Ensure that Eigen headers can be found
2893 (setenv "CPLUS_INCLUDE_PATH"
2894 (string-append (getenv "CPLUS_INCLUDE_PATH")
2896 (assoc-ref inputs "eigen")
2899 (add-before 'build 'bin-mkdir
2904 (lambda* (#:key outputs #:allow-other-keys)
2905 (let ((out (assoc-ref outputs "out")))
2906 (install-file "bin/gemma"
2910 #:tests? #f)) ; no tests included yet
2911 (home-page "https://github.com/xiangzhou/GEMMA")
2912 (synopsis "Tool for genome-wide efficient mixed model association")
2914 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2915 standard linear mixed model resolver with application in genome-wide
2916 association studies (GWAS).")
2917 (license license:gpl3)))
2926 (url "https://github.com/nboley/grit.git")
2928 (file-name (git-file-name name version))
2931 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
2932 (build-system python-build-system)
2934 `(#:python ,python-2
2936 (modify-phases %standard-phases
2937 (add-after 'unpack 'generate-from-cython-sources
2938 (lambda* (#:key inputs outputs #:allow-other-keys)
2939 ;; Delete these C files to force fresh generation from pyx sources.
2940 (delete-file "grit/sparsify_support_fns.c")
2941 (delete-file "grit/call_peaks_support_fns.c")
2942 (substitute* "setup.py"
2943 (("Cython.Setup") "Cython.Build"))
2946 `(("python-scipy" ,python2-scipy)
2947 ("python-numpy" ,python2-numpy)
2948 ("python-pysam" ,python2-pysam)
2949 ("python-networkx" ,python2-networkx)))
2951 `(("python-cython" ,python2-cython)))
2952 (home-page "http://grit-bio.org")
2953 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2955 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2956 full length transcript models. When none of these data sources are available,
2957 GRIT can be run by providing a candidate set of TES or TSS sites. In
2958 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2959 also be run in quantification mode, where it uses a provided GTF file and just
2960 estimates transcript expression.")
2961 (license license:gpl3+)))
2963 (define-public hisat
2970 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2971 version "-beta-source.zip"))
2974 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2975 (build-system gnu-build-system)
2977 `(#:tests? #f ;no check target
2978 #:make-flags '("allall"
2979 ;; Disable unsupported `popcnt' instructions on
2980 ;; architectures other than x86_64
2981 ,@(if (string-prefix? "x86_64"
2982 (or (%current-target-system)
2985 '("POPCNT_CAPABILITY=0")))
2987 (modify-phases %standard-phases
2988 (add-after 'unpack 'patch-sources
2990 ;; XXX Cannot use snippet because zip files are not supported
2991 (substitute* "Makefile"
2992 (("^CC = .*$") "CC = gcc")
2993 (("^CPP = .*$") "CPP = g++")
2994 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2995 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2996 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2997 (substitute* '("hisat-build" "hisat-inspect")
2998 (("/usr/bin/env") (which "env")))
3001 (lambda* (#:key outputs #:allow-other-keys)
3002 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3003 (for-each (lambda (file)
3004 (install-file file bin))
3007 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3009 (delete 'configure))))
3011 `(("unzip" ,unzip)))
3016 ;; Non-portable SSE instructions are used so building fails on platforms
3017 ;; other than x86_64.
3018 (supported-systems '("x86_64-linux"))
3019 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3020 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3022 "HISAT is a fast and sensitive spliced alignment program for mapping
3023 RNA-seq reads. In addition to one global FM index that represents a whole
3024 genome, HISAT uses a large set of small FM indexes that collectively cover the
3025 whole genome. These small indexes (called local indexes) combined with
3026 several alignment strategies enable effective alignment of RNA-seq reads, in
3027 particular, reads spanning multiple exons.")
3028 (license license:gpl3+)))
3030 (define-public hisat2
3037 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3038 "/downloads/hisat2-" version "-source.zip"))
3041 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3042 (build-system gnu-build-system)
3044 `(#:tests? #f ; no check target
3045 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3046 #:modules ((guix build gnu-build-system)
3050 (modify-phases %standard-phases
3051 (add-after 'unpack 'make-deterministic
3053 (substitute* "Makefile"
3058 (lambda* (#:key outputs #:allow-other-keys)
3059 (let* ((out (assoc-ref outputs "out"))
3060 (bin (string-append out "/bin/"))
3061 (doc (string-append out "/share/doc/hisat2/")))
3063 (cut install-file <> bin)
3065 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3067 (install-file "doc/manual.inc.html" doc))
3070 `(("unzip" ,unzip) ; needed for archive from ftp
3072 ("pandoc" ,ghc-pandoc))) ; for documentation
3073 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3074 (synopsis "Graph-based alignment of genomic sequencing reads")
3075 (description "HISAT2 is a fast and sensitive alignment program for mapping
3076 next-generation sequencing reads (both DNA and RNA) to a population of human
3077 genomes (as well as to a single reference genome). In addition to using one
3078 global @dfn{graph FM} (GFM) index that represents a population of human
3079 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3080 the whole genome. These small indexes, combined with several alignment
3081 strategies, enable rapid and accurate alignment of sequencing reads. This new
3082 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3083 ;; HISAT2 contains files from Bowtie2, which is released under
3084 ;; GPLv2 or later. The HISAT2 source files are released under
3086 (license license:gpl3+)))
3088 (define-public hmmer
3096 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3099 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3100 (build-system gnu-build-system)
3101 (native-inputs `(("perl" ,perl)))
3102 (home-page "http://hmmer.org/")
3103 (synopsis "Biosequence analysis using profile hidden Markov models")
3105 "HMMER is used for searching sequence databases for homologs of protein
3106 sequences, and for making protein sequence alignments. It implements methods
3107 using probabilistic models called profile hidden Markov models (profile
3109 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3111 (supported-systems '("x86_64-linux" "i686-linux"))
3112 (license license:bsd-3)))
3114 (define-public htseq
3120 (uri (pypi-uri "HTSeq" version))
3123 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3124 (build-system python-build-system)
3126 `(("python-cython" ,python-cython)))
3127 ;; Numpy needs to be propagated when htseq is used as a Python library.
3129 `(("python-numpy" ,python-numpy)))
3131 `(("python-pysam" ,python-pysam)
3132 ("python-matplotlib" ,python-matplotlib)))
3133 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3134 (synopsis "Analysing high-throughput sequencing data with Python")
3136 "HTSeq is a Python package that provides infrastructure to process data
3137 from high-throughput sequencing assays.")
3138 (license license:gpl3+)))
3140 (define-public python2-htseq
3141 (package-with-python2 htseq))
3143 (define-public java-htsjdk
3145 (name "java-htsjdk")
3146 (version "2.3.0") ; last version without build dependency on gradle
3150 (url "https://github.com/samtools/htsjdk.git")
3152 (file-name (git-file-name name version))
3155 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3156 (modules '((guix build utils)))
3158 ;; Delete pre-built binaries
3160 (delete-file-recursively "lib")
3163 (build-system ant-build-system)
3165 `(#:tests? #f ; test require Internet access
3168 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3169 "/share/java/htsjdk/"))
3170 #:build-target "all"
3172 (modify-phases %standard-phases
3173 ;; The build phase also installs the jars
3174 (delete 'install))))
3176 `(("java-ngs" ,java-ngs)
3177 ("java-snappy-1" ,java-snappy-1)
3178 ("java-commons-compress" ,java-commons-compress)
3179 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3180 ("java-commons-jexl-2" ,java-commons-jexl-2)
3181 ("java-xz" ,java-xz)))
3183 `(("java-testng" ,java-testng)))
3184 (home-page "http://samtools.github.io/htsjdk/")
3185 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3187 "HTSJDK is an implementation of a unified Java library for accessing
3188 common file formats, such as SAM and VCF, used for high-throughput
3189 sequencing (HTS) data. There are also an number of useful utilities for
3190 manipulating HTS data.")
3191 (license license:expat)))
3193 (define-public java-htsjdk-latest
3195 (name "java-htsjdk")
3200 (url "https://github.com/samtools/htsjdk.git")
3202 (file-name (string-append name "-" version "-checkout"))
3205 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3206 (build-system ant-build-system)
3208 `(#:tests? #f ; test require Scala
3210 #:jar-name "htsjdk.jar"
3212 (modify-phases %standard-phases
3213 (add-after 'unpack 'remove-useless-build.xml
3214 (lambda _ (delete-file "build.xml") #t))
3215 ;; The tests require the scalatest package.
3216 (add-after 'unpack 'remove-tests
3217 (lambda _ (delete-file-recursively "src/test") #t)))))
3219 `(("java-ngs" ,java-ngs)
3220 ("java-snappy-1" ,java-snappy-1)
3221 ("java-commons-compress" ,java-commons-compress)
3222 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3223 ("java-commons-jexl-2" ,java-commons-jexl-2)
3224 ("java-xz" ,java-xz)))
3226 `(("java-junit" ,java-junit)))
3227 (home-page "http://samtools.github.io/htsjdk/")
3228 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3230 "HTSJDK is an implementation of a unified Java library for accessing
3231 common file formats, such as SAM and VCF, used for high-throughput
3232 sequencing (HTS) data. There are also an number of useful utilities for
3233 manipulating HTS data.")
3234 (license license:expat)))
3236 ;; This is needed for picard 2.10.3
3237 (define-public java-htsjdk-2.10.1
3238 (package (inherit java-htsjdk-latest)
3239 (name "java-htsjdk")
3244 (url "https://github.com/samtools/htsjdk.git")
3246 (file-name (string-append name "-" version "-checkout"))
3249 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3250 (build-system ant-build-system)
3252 `(#:tests? #f ; tests require Scala
3254 #:jar-name "htsjdk.jar"
3256 (modify-phases %standard-phases
3257 (add-after 'unpack 'remove-useless-build.xml
3258 (lambda _ (delete-file "build.xml") #t))
3259 ;; The tests require the scalatest package.
3260 (add-after 'unpack 'remove-tests
3261 (lambda _ (delete-file-recursively "src/test") #t)))))))
3263 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3264 ;; recent version of java-htsjdk, which depends on gradle.
3265 (define-public java-picard
3267 (name "java-picard")
3272 (url "https://github.com/broadinstitute/picard.git")
3274 (file-name (string-append "java-picard-" version "-checkout"))
3277 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3278 (modules '((guix build utils)))
3281 ;; Delete pre-built binaries.
3282 (delete-file-recursively "lib")
3284 (substitute* "build.xml"
3285 ;; Remove build-time dependency on git.
3286 (("failifexecutionfails=\"true\"")
3287 "failifexecutionfails=\"false\"")
3289 (("depends=\"compile-htsjdk, ")
3291 (("depends=\"compile-htsjdk-tests, ")
3293 ;; Build picard-lib.jar before building picard.jar
3294 (("name=\"picard-jar\" depends=\"" line)
3295 (string-append line "picard-lib-jar, ")))
3297 (build-system ant-build-system)
3299 `(#:build-target "picard-jar"
3300 #:test-target "test"
3301 ;; Tests require jacoco:coverage.
3304 (list (string-append "-Dhtsjdk_lib_dir="
3305 (assoc-ref %build-inputs "java-htsjdk")
3306 "/share/java/htsjdk/")
3307 "-Dhtsjdk-classes=dist/tmp"
3308 (string-append "-Dhtsjdk-version="
3309 ,(package-version java-htsjdk)))
3312 (modify-phases %standard-phases
3313 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3314 (delete 'generate-jar-indices)
3315 (add-after 'unpack 'use-our-htsjdk
3316 (lambda* (#:key inputs #:allow-other-keys)
3317 (substitute* "build.xml"
3318 (("\\$\\{htsjdk\\}/lib")
3319 (string-append (assoc-ref inputs "java-htsjdk")
3320 "/share/java/htsjdk/")))
3322 (add-after 'unpack 'make-test-target-independent
3323 (lambda* (#:key inputs #:allow-other-keys)
3324 (substitute* "build.xml"
3325 (("name=\"test\" depends=\"compile, ")
3326 "name=\"test\" depends=\""))
3328 (replace 'install (install-jars "dist")))))
3330 `(("java-htsjdk" ,java-htsjdk)
3331 ("java-guava" ,java-guava)))
3333 `(("java-testng" ,java-testng)))
3334 (home-page "http://broadinstitute.github.io/picard/")
3335 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3336 (description "Picard is a set of Java command line tools for manipulating
3337 high-throughput sequencing (HTS) data and formats. Picard is implemented
3338 using the HTSJDK Java library to support accessing file formats that are
3339 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3341 (license license:expat)))
3343 ;; This is needed for dropseq-tools
3344 (define-public java-picard-2.10.3
3346 (name "java-picard")
3351 (url "https://github.com/broadinstitute/picard.git")
3353 (file-name (string-append "java-picard-" version "-checkout"))
3356 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3357 (build-system ant-build-system)
3359 `(#:jar-name "picard.jar"
3360 ;; Tests require jacoco:coverage.
3363 #:main-class "picard.cmdline.PicardCommandLine"
3364 #:modules ((guix build ant-build-system)
3366 (guix build java-utils)
3371 (modify-phases %standard-phases
3372 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3373 (delete 'generate-jar-indices)
3374 (add-after 'unpack 'remove-useless-build.xml
3375 (lambda _ (delete-file "build.xml") #t))
3376 ;; This is necessary to ensure that htsjdk is found when using
3377 ;; picard.jar as an executable.
3378 (add-before 'build 'edit-classpath-in-manifest
3379 (lambda* (#:key inputs #:allow-other-keys)
3380 (chmod "build.xml" #o664)
3381 (call-with-output-file "build.xml.new"
3385 (with-input-from-file "build.xml"
3386 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3387 `((target . ,(lambda (tag . kids)
3388 (let ((name ((sxpath '(name *text*))
3390 ;; FIXME: We're breaking the line
3391 ;; early with a dummy path to
3392 ;; ensure that the store reference
3393 ;; isn't broken apart and can still
3394 ;; be found by the reference
3399 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3400 ;; maximum line length is 70
3401 (string-tabulate (const #\b) 57)
3402 (assoc-ref inputs "java-htsjdk"))))
3403 (if (member "manifest" name)
3406 (@ (file "${manifest.file}")
3407 (match "\\r\\n\\r\\n")
3408 (replace "${line.separator}")))
3411 (file "${manifest.file}")
3414 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3415 (*text* . ,(lambda (_ txt) txt))))
3417 (rename-file "build.xml.new" "build.xml")
3420 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3422 `(("java-testng" ,java-testng)
3423 ("java-guava" ,java-guava)))
3424 (home-page "http://broadinstitute.github.io/picard/")
3425 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3426 (description "Picard is a set of Java command line tools for manipulating
3427 high-throughput sequencing (HTS) data and formats. Picard is implemented
3428 using the HTSJDK Java library to support accessing file formats that are
3429 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3431 (license license:expat)))
3433 ;; This is the last version of Picard to provide net.sf.samtools
3434 (define-public java-picard-1.113
3435 (package (inherit java-picard)
3436 (name "java-picard")
3441 (url "https://github.com/broadinstitute/picard.git")
3443 (file-name (string-append "java-picard-" version "-checkout"))
3446 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3447 (modules '((guix build utils)))
3450 ;; Delete pre-built binaries.
3451 (delete-file-recursively "lib")
3454 (build-system ant-build-system)
3456 `(#:build-target "picard-jar"
3457 #:test-target "test"
3458 ;; FIXME: the class path at test time is wrong.
3459 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3460 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3463 ;; This is only used for tests.
3465 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3467 (modify-phases %standard-phases
3468 ;; FIXME: This phase fails.
3469 (delete 'generate-jar-indices)
3470 ;; Do not use bundled ant bzip2.
3471 (add-after 'unpack 'use-ant-bzip
3472 (lambda* (#:key inputs #:allow-other-keys)
3473 (substitute* "build.xml"
3474 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3475 (string-append (assoc-ref inputs "ant")
3478 (add-after 'unpack 'make-test-target-independent
3479 (lambda* (#:key inputs #:allow-other-keys)
3480 (substitute* "build.xml"
3481 (("name=\"test\" depends=\"compile, ")
3482 "name=\"test\" depends=\"compile-tests, ")
3483 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3484 "name=\"compile\" depends=\"compile-src\""))
3486 (add-after 'unpack 'fix-deflater-path
3487 (lambda* (#:key outputs #:allow-other-keys)
3488 (substitute* "src/java/net/sf/samtools/Defaults.java"
3489 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3490 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3491 (assoc-ref outputs "out")
3492 "/lib/jni/libIntelDeflater.so"
3495 ;; Build the deflater library, because we've previously deleted the
3496 ;; pre-built one. This can only be built with access to the JDK
3498 (add-after 'build 'build-jni
3499 (lambda* (#:key inputs #:allow-other-keys)
3502 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3503 "-xf" (assoc-ref inputs "jdk-src"))
3504 (invoke "javah" "-jni"
3505 "-classpath" "classes"
3507 "net.sf.samtools.util.zip.IntelDeflater")
3508 (with-directory-excursion "src/c/inteldeflater"
3509 (invoke "gcc" "-I../../../lib" "-I."
3510 (string-append "-I" (assoc-ref inputs "jdk")
3512 "-I../../../jdk-src/src/share/native/common/"
3513 "-I../../../jdk-src/src/solaris/native/common/"
3514 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3515 (invoke "gcc" "-shared"
3516 "-o" "../../../lib/jni/libIntelDeflater.so"
3517 "IntelDeflater.o" "-lz" "-lstdc++"))
3519 ;; We can only build everything else after building the JNI library.
3520 (add-after 'build-jni 'build-rest
3521 (lambda* (#:key make-flags #:allow-other-keys)
3522 (apply invoke `("ant" "all" ,@make-flags))
3524 (add-before 'build 'set-JAVA6_HOME
3526 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3528 (replace 'install (install-jars "dist"))
3529 (add-after 'install 'install-jni-lib
3530 (lambda* (#:key outputs #:allow-other-keys)
3531 (let ((jni (string-append (assoc-ref outputs "out")
3534 (install-file "lib/jni/libIntelDeflater.so" jni)
3537 `(("java-snappy-1" ,java-snappy-1)
3538 ("java-commons-jexl-2" ,java-commons-jexl-2)
3539 ("java-cofoja" ,java-cofoja)
3540 ("ant" ,ant) ; for bzip2 support at runtime
3543 `(("ant-apache-bcel" ,ant-apache-bcel)
3544 ("ant-junit" ,ant-junit)
3545 ("java-testng" ,java-testng)
3546 ("java-commons-bcel" ,java-commons-bcel)
3547 ("java-jcommander" ,java-jcommander)
3548 ("jdk" ,icedtea-8 "jdk")
3549 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3551 (define-public fastqc
3558 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3559 "projects/fastqc/fastqc_v"
3560 version "_source.zip"))
3563 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3564 (build-system ant-build-system)
3566 `(#:tests? #f ; there are no tests
3567 #:build-target "build"
3569 (modify-phases %standard-phases
3570 (add-after 'unpack 'fix-dependencies
3571 (lambda* (#:key inputs #:allow-other-keys)
3572 (substitute* "build.xml"
3574 (string-append (assoc-ref inputs "java-jbzip2")
3575 "/share/java/jbzip2.jar"))
3577 (string-append (assoc-ref inputs "java-picard-1.113")
3578 "/share/java/sam-1.112.jar"))
3580 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3581 "/share/java/sis-jhdf5.jar")))
3583 ;; There is no installation target
3585 (lambda* (#:key inputs outputs #:allow-other-keys)
3586 (let* ((out (assoc-ref outputs "out"))
3587 (bin (string-append out "/bin"))
3588 (share (string-append out "/share/fastqc/"))
3589 (exe (string-append share "/fastqc")))
3590 (for-each mkdir-p (list bin share))
3591 (copy-recursively "bin" share)
3593 (("my \\$java_bin = 'java';")
3594 (string-append "my $java_bin = '"
3595 (assoc-ref inputs "java")
3598 (symlink exe (string-append bin "/fastqc"))
3602 ("perl" ,perl) ; needed for the wrapper script
3603 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3604 ("java-picard-1.113" ,java-picard-1.113)
3605 ("java-jbzip2" ,java-jbzip2)))
3607 `(("unzip" ,unzip)))
3608 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3609 (synopsis "Quality control tool for high throughput sequence data")
3611 "FastQC aims to provide a simple way to do some quality control
3612 checks on raw sequence data coming from high throughput sequencing
3613 pipelines. It provides a modular set of analyses which you can use to
3614 give a quick impression of whether your data has any problems of which
3615 you should be aware before doing any further analysis.
3617 The main functions of FastQC are:
3620 @item Import of data from BAM, SAM or FastQ files (any variant);
3621 @item Providing a quick overview to tell you in which areas there may
3623 @item Summary graphs and tables to quickly assess your data;
3624 @item Export of results to an HTML based permanent report;
3625 @item Offline operation to allow automated generation of reports
3626 without running the interactive application.
3628 (license license:gpl3+)))
3630 (define-public fastp
3638 (url "https://github.com/OpenGene/fastp.git")
3639 (commit (string-append "v" version))))
3640 (file-name (git-file-name name version))
3643 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3644 (build-system gnu-build-system)
3646 `(#:tests? #f ; there are none
3648 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3650 (modify-phases %standard-phases
3652 (add-before 'install 'create-target-dir
3653 (lambda* (#:key outputs #:allow-other-keys)
3654 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3658 (home-page "https://github.com/OpenGene/fastp/")
3659 (synopsis "All-in-one FastQ preprocessor")
3661 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3662 FastQ files. This tool has multi-threading support to afford high
3664 (license license:expat)))
3666 (define-public htslib
3673 "https://github.com/samtools/htslib/releases/download/"
3674 version "/htslib-" version ".tar.bz2"))
3677 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3678 (build-system gnu-build-system)
3680 `(("openssl" ,openssl)
3685 (home-page "http://www.htslib.org")
3686 (synopsis "C library for reading/writing high-throughput sequencing data")
3688 "HTSlib is a C library for reading/writing high-throughput sequencing
3689 data. It also provides the @command{bgzip}, @command{htsfile}, and
3690 @command{tabix} utilities.")
3691 ;; Files under cram/ are released under the modified BSD license;
3692 ;; the rest is released under the Expat license
3693 (license (list license:expat license:bsd-3))))
3695 ;; This package should be removed once no packages rely upon it.
3703 "https://github.com/samtools/htslib/releases/download/"
3704 version "/htslib-" version ".tar.bz2"))
3707 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3716 (url "https://github.com/nboley/idr.git")
3718 (file-name (git-file-name name version))
3721 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3722 ;; Delete generated C code.
3724 '(begin (delete-file "idr/inv_cdf.c") #t))))
3725 (build-system python-build-system)
3726 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3727 ;; are no longer part of this package. It also asserts False, which
3728 ;; causes the tests to always fail.
3729 (arguments `(#:tests? #f))
3731 `(("python-scipy" ,python-scipy)
3732 ("python-sympy" ,python-sympy)
3733 ("python-numpy" ,python-numpy)
3734 ("python-matplotlib" ,python-matplotlib)))
3736 `(("python-cython" ,python-cython)))
3737 (home-page "https://github.com/nboley/idr")
3738 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3740 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3741 to measure the reproducibility of findings identified from replicate
3742 experiments and provide highly stable thresholds based on reproducibility.")
3743 (license license:gpl2+)))
3745 (define-public jellyfish
3751 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3752 "releases/download/v" version
3753 "/jellyfish-" version ".tar.gz"))
3756 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3757 (build-system gnu-build-system)
3758 (outputs '("out" ;for library
3759 "ruby" ;for Ruby bindings
3760 "python")) ;for Python bindings
3763 (list (string-append "--enable-ruby-binding="
3764 (assoc-ref %outputs "ruby"))
3765 (string-append "--enable-python-binding="
3766 (assoc-ref %outputs "python")))
3768 (modify-phases %standard-phases
3769 (add-before 'check 'set-SHELL-variable
3771 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3773 (setenv "SHELL" (which "bash"))
3779 ("python" ,python-2)
3780 ("pkg-config" ,pkg-config)))
3782 `(("htslib" ,htslib)))
3783 (synopsis "Tool for fast counting of k-mers in DNA")
3785 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3786 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3787 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3788 is a command-line program that reads FASTA and multi-FASTA files containing
3789 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3790 translated into a human-readable text format using the @code{jellyfish dump}
3791 command, or queried for specific k-mers with @code{jellyfish query}.")
3792 (home-page "http://www.genome.umd.edu/jellyfish.html")
3793 ;; JELLYFISH seems to be 64-bit only.
3794 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3795 ;; The combined work is published under the GPLv3 or later. Individual
3796 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3797 (license (list license:gpl3+ license:expat))))
3799 (define-public khmer
3807 (url "https://github.com/dib-lab/khmer.git")
3808 (commit (string-append "v" version))))
3809 (file-name (git-file-name name version))
3812 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3813 (patches (search-patches "khmer-use-libraries.patch"))
3814 (modules '((guix build utils)))
3817 ;; Delete bundled libraries. We do not replace the bundled seqan
3818 ;; as it is a modified subset of the old version 1.4.1.
3820 ;; We do not replace the bundled MurmurHash as the canonical
3821 ;; repository for this code 'SMHasher' is unsuitable for providing
3823 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3824 (delete-file-recursively "third-party/zlib")
3825 (delete-file-recursively "third-party/bzip2")
3827 (build-system python-build-system)
3830 (modify-phases %standard-phases
3831 (add-after 'unpack 'set-cc
3832 (lambda _ (setenv "CC" "gcc") #t))
3833 ;; FIXME: This fails with "permission denied".
3834 (delete 'reset-gzip-timestamps))))
3836 `(("python-cython" ,python-cython)
3837 ("python-pytest" ,python-pytest)
3838 ("python-pytest-runner" ,python-pytest-runner)))
3842 ("python-screed" ,python-screed)
3843 ("python-bz2file" ,python-bz2file)))
3844 (home-page "https://khmer.readthedocs.org/")
3845 (synopsis "K-mer counting, filtering and graph traversal library")
3846 (description "The khmer software is a set of command-line tools for
3847 working with DNA shotgun sequencing data from genomes, transcriptomes,
3848 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3849 sometimes better. Khmer can also identify and fix problems with shotgun
3851 ;; When building on i686, armhf and mips64el, we get the following error:
3852 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3853 (supported-systems '("x86_64-linux" "aarch64-linux"))
3854 (license license:bsd-3)))
3856 (define-public kaiju
3863 (url "https://github.com/bioinformatics-centre/kaiju")
3864 (commit (string-append "v" version))))
3865 (file-name (git-file-name name version))
3868 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3869 (build-system gnu-build-system)
3871 `(#:tests? #f ; There are no tests.
3873 (modify-phases %standard-phases
3875 (add-before 'build 'move-to-src-dir
3876 (lambda _ (chdir "src") #t))
3878 (lambda* (#:key inputs outputs #:allow-other-keys)
3879 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3882 (copy-recursively "bin" bin))
3887 (home-page "http://kaiju.binf.ku.dk/")
3888 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3889 (description "Kaiju is a program for sensitive taxonomic classification
3890 of high-throughput sequencing reads from metagenomic whole genome sequencing
3892 (license license:gpl3+)))
3897 (version "2.1.1.20160309")
3900 (uri (pypi-uri "MACS2" version))
3903 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3904 (build-system python-build-system)
3906 `(#:python ,python-2 ; only compatible with Python 2.7
3907 #:tests? #f)) ; no test target
3909 `(("python-numpy" ,python2-numpy)))
3910 (home-page "https://github.com/taoliu/MACS/")
3911 (synopsis "Model based analysis for ChIP-Seq data")
3913 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3914 identifying transcript factor binding sites named Model-based Analysis of
3915 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3916 the significance of enriched ChIP regions and it improves the spatial
3917 resolution of binding sites through combining the information of both
3918 sequencing tag position and orientation.")
3919 (license license:bsd-3)))
3921 (define-public mafft
3928 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3929 "-without-extensions-src.tgz"))
3930 (file-name (string-append name "-" version ".tgz"))
3933 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3934 (build-system gnu-build-system)
3936 `(#:tests? #f ; no automated tests, though there are tests in the read me
3937 #:make-flags (let ((out (assoc-ref %outputs "out")))
3938 (list (string-append "PREFIX=" out)
3939 (string-append "BINDIR="
3940 (string-append out "/bin"))))
3942 (modify-phases %standard-phases
3943 (add-after 'unpack 'enter-dir
3944 (lambda _ (chdir "core") #t))
3945 (add-after 'enter-dir 'patch-makefile
3947 ;; on advice from the MAFFT authors, there is no need to
3948 ;; distribute mafft-profile, mafft-distance, or
3949 ;; mafft-homologs.rb as they are too "specialised".
3950 (substitute* "Makefile"
3951 ;; remove mafft-homologs.rb from SCRIPTS
3952 (("^SCRIPTS = mafft mafft-homologs.rb")
3954 ;; remove mafft-homologs from MANPAGES
3955 (("^MANPAGES = mafft.1 mafft-homologs.1")
3956 "MANPAGES = mafft.1")
3957 ;; remove mafft-distance from PROGS
3958 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3959 "PROGS = dvtditr dndfast7 dndblast sextet5")
3960 ;; remove mafft-profile from PROGS
3961 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3962 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3963 (("^rm -f mafft-profile mafft-profile.exe") "#")
3964 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3965 ;; do not install MAN pages in libexec folder
3966 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3967 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3969 (add-after 'enter-dir 'patch-paths
3970 (lambda* (#:key inputs #:allow-other-keys)
3971 (substitute* '("pairash.c"
3973 (("perl") (which "perl"))
3974 (("([\"`| ])awk" _ prefix)
3975 (string-append prefix (which "awk")))
3976 (("grep") (which "grep")))
3979 (add-after 'install 'wrap-programs
3980 (lambda* (#:key outputs #:allow-other-keys)
3981 (let* ((out (assoc-ref outputs "out"))
3982 (bin (string-append out "/bin"))
3983 (path (string-append
3984 (assoc-ref %build-inputs "coreutils") "/bin:")))
3985 (for-each (lambda (file)
3987 `("PATH" ":" prefix (,path))))
3995 ("coreutils" ,coreutils)))
3996 (home-page "http://mafft.cbrc.jp/alignment/software/")
3997 (synopsis "Multiple sequence alignment program")
3999 "MAFFT offers a range of multiple alignment methods for nucleotide and
4000 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4001 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4003 (license (license:non-copyleft
4004 "http://mafft.cbrc.jp/alignment/software/license.txt"
4005 "BSD-3 with different formatting"))))
4014 (url "https://github.com/marbl/mash.git")
4015 (commit (string-append "v" version))))
4016 (file-name (git-file-name name version))
4019 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4020 (modules '((guix build utils)))
4023 ;; Delete bundled kseq.
4024 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4025 (delete-file "src/mash/kseq.h")
4027 (build-system gnu-build-system)
4029 `(#:tests? #f ; No tests.
4032 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4033 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4034 #:make-flags (list "CC=gcc")
4036 (modify-phases %standard-phases
4037 (add-after 'unpack 'fix-includes
4039 (substitute* '("src/mash/Sketch.cpp"
4040 "src/mash/CommandFind.cpp"
4041 "src/mash/CommandScreen.cpp")
4042 (("^#include \"kseq\\.h\"")
4043 "#include \"htslib/kseq.h\""))
4045 (add-after 'fix-includes 'use-c++14
4047 ;; capnproto 0.7 requires c++14 to build
4048 (substitute* "configure.ac"
4049 (("c\\+\\+11") "c++14"))
4050 (substitute* "Makefile.in"
4051 (("c\\+\\+11") "c++14"))
4054 `(("autoconf" ,autoconf)
4055 ;; Capnproto and htslib are statically embedded in the final
4056 ;; application. Therefore we also list their licenses, below.
4057 ("capnproto" ,capnproto)
4058 ("htslib" ,htslib)))
4062 (supported-systems '("x86_64-linux"))
4063 (home-page "https://mash.readthedocs.io")
4064 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4065 (description "Mash is a fast sequence distance estimator that uses the
4066 MinHash algorithm and is designed to work with genomes and metagenomes in the
4067 form of assemblies or reads.")
4068 (license (list license:bsd-3 ; Mash
4069 license:expat ; HTSlib and capnproto
4070 license:public-domain ; MurmurHash 3
4071 license:cpl1.0)))) ; Open Bloom Filter
4073 (define-public metabat
4081 (url "https://bitbucket.org/berkeleylab/metabat.git")
4082 (commit (string-append "v" version))))
4083 (file-name (git-file-name name version))
4086 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4087 (patches (search-patches "metabat-fix-compilation.patch"))))
4088 (build-system scons-build-system)
4090 `(#:scons ,scons-python2
4092 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4093 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4094 #:tests? #f ;; Tests are run during the build phase.
4096 (modify-phases %standard-phases
4097 (add-after 'unpack 'fix-includes
4099 (substitute* "src/BamUtils.h"
4100 (("^#include \"bam/bam\\.h\"")
4101 "#include \"samtools/bam.h\"")
4102 (("^#include \"bam/sam\\.h\"")
4103 "#include \"samtools/sam.h\""))
4104 (substitute* "src/KseqReader.h"
4105 (("^#include \"bam/kseq\\.h\"")
4106 "#include \"htslib/kseq.h\""))
4108 (add-after 'unpack 'fix-scons
4109 (lambda* (#:key inputs #:allow-other-keys)
4110 (substitute* "SConstruct"
4111 (("^htslib_dir += 'samtools'")
4112 (string-append "htslib_dir = '"
4113 (assoc-ref inputs "htslib")
4115 (("^samtools_dir = 'samtools'")
4116 (string-append "samtools_dir = '"
4117 (assoc-ref inputs "samtools")
4119 (("^findStaticOrShared\\('bam', hts_lib")
4120 (string-append "findStaticOrShared('bam', '"
4121 (assoc-ref inputs "samtools")
4123 ;; Do not distribute README.
4124 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4129 ("samtools" ,samtools)
4132 (home-page "https://bitbucket.org/berkeleylab/metabat")
4134 "Reconstruction of single genomes from complex microbial communities")
4136 "Grouping large genomic fragments assembled from shotgun metagenomic
4137 sequences to deconvolute complex microbial communities, or metagenome binning,
4138 enables the study of individual organisms and their interactions. MetaBAT is
4139 an automated metagenome binning software, which integrates empirical
4140 probabilistic distances of genome abundance and tetranucleotide frequency.")
4141 ;; The source code contains inline assembly.
4142 (supported-systems '("x86_64-linux" "i686-linux"))
4143 (license (license:non-copyleft "file://license.txt"
4144 "See license.txt in the distribution."))))
4146 (define-public minced
4153 (url "https://github.com/ctSkennerton/minced.git")
4155 (file-name (git-file-name name version))
4158 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4159 (build-system gnu-build-system)
4161 `(#:test-target "test"
4163 (modify-phases %standard-phases
4165 (add-before 'check 'fix-test
4167 ;; Fix test for latest version.
4168 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4169 (("minced:0.1.6") "minced:0.2.0"))
4171 (replace 'install ; No install target.
4172 (lambda* (#:key inputs outputs #:allow-other-keys)
4173 (let* ((out (assoc-ref outputs "out"))
4174 (bin (string-append out "/bin"))
4175 (wrapper (string-append bin "/minced")))
4176 ;; Minced comes with a wrapper script that tries to figure out where
4177 ;; it is located before running the JAR. Since these paths are known
4178 ;; to us, we build our own wrapper to avoid coreutils dependency.
4179 (install-file "minced.jar" bin)
4180 (with-output-to-file wrapper
4184 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4185 (assoc-ref inputs "jre") "/bin/java -jar "
4186 bin "/minced.jar \"$@\"\n"))))
4187 (chmod wrapper #o555))
4190 `(("jdk" ,icedtea "jdk")))
4193 ("jre" ,icedtea "out")))
4194 (home-page "https://github.com/ctSkennerton/minced")
4195 (synopsis "Mining CRISPRs in Environmental Datasets")
4197 "MinCED is a program to find Clustered Regularly Interspaced Short
4198 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4199 unassembled metagenomic reads, but is mainly designed for full genomes and
4200 assembled metagenomic sequence.")
4201 (license license:gpl3+)))
4209 (uri (pypi-uri "misopy" version))
4212 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4213 (modules '((guix build utils)))
4215 (substitute* "setup.py"
4216 ;; Use setuptools, or else the executables are not
4218 (("distutils.core") "setuptools")
4219 ;; use "gcc" instead of "cc" for compilation
4221 "cc.set_executables(
4225 linker_so='gcc -shared'); defines"))
4227 (build-system python-build-system)
4229 `(#:python ,python-2 ; only Python 2 is supported
4230 #:tests? #f)) ; no "test" target
4232 `(("samtools" ,samtools)
4233 ("python-numpy" ,python2-numpy)
4234 ("python-pysam" ,python2-pysam)
4235 ("python-scipy" ,python2-scipy)
4236 ("python-matplotlib" ,python2-matplotlib)))
4238 `(("python-mock" ,python2-mock) ;for tests
4239 ("python-pytz" ,python2-pytz))) ;for tests
4240 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4241 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4243 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4244 the expression level of alternatively spliced genes from RNA-Seq data, and
4245 identifies differentially regulated isoforms or exons across samples. By
4246 modeling the generative process by which reads are produced from isoforms in
4247 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4248 that a read originated from a particular isoform.")
4249 (license license:gpl2)))
4251 (define-public muscle
4254 (version "3.8.1551")
4256 (method url-fetch/tarbomb)
4258 "http://www.drive5.com/muscle/muscle_src_"
4262 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4263 (build-system gnu-build-system)
4265 `(#:make-flags (list "LDLIBS = -lm")
4267 (modify-phases %standard-phases
4270 ;; There are no tests, so just test if it runs.
4271 (lambda _ (invoke "./muscle" "-version") #t))
4273 (lambda* (#:key outputs #:allow-other-keys)
4274 (let* ((out (assoc-ref outputs "out"))
4275 (bin (string-append out "/bin")))
4276 (install-file "muscle" bin)
4278 (home-page "http://www.drive5.com/muscle")
4279 (synopsis "Multiple sequence alignment program")
4281 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4282 program for nucleotide and protein sequences.")
4283 ;; License information found in 'muscle -h' and usage.cpp.
4284 (license license:public-domain)))
4286 (define-public newick-utils
4287 ;; There are no recent releases so we package from git.
4288 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4290 (name "newick-utils")
4291 (version (string-append "1.6-1." (string-take commit 8)))
4295 (url "https://github.com/tjunier/newick_utils.git")
4297 (file-name (string-append name "-" version "-checkout"))
4300 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4301 (build-system gnu-build-system)
4303 ;; XXX: TODO: Enable Lua and Guile bindings.
4304 ;; https://github.com/tjunier/newick_utils/issues/13
4305 `(("libxml2" ,libxml2)
4309 `(("autoconf" ,autoconf)
4310 ("automake" ,automake)
4311 ("libtool" ,libtool)))
4312 (synopsis "Programs for working with newick format phylogenetic trees")
4314 "Newick-utils is a suite of utilities for processing phylogenetic trees
4315 in Newick format. Functions include re-rooting, extracting subtrees,
4316 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4317 (home-page "https://github.com/tjunier/newick_utils")
4318 (license license:bsd-3))))
4327 "https://github.com/wwood/OrfM/releases/download/v"
4328 version "/orfm-" version ".tar.gz"))
4331 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4332 (build-system gnu-build-system)
4333 (inputs `(("zlib" ,zlib)))
4335 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4336 ("ruby-rspec" ,ruby-rspec)
4338 (synopsis "Simple and not slow open reading frame (ORF) caller")
4340 "An ORF caller finds stretches of DNA that, when translated, are not
4341 interrupted by stop codons. OrfM finds and prints these ORFs.")
4342 (home-page "https://github.com/wwood/OrfM")
4343 (license license:lgpl3+)))
4345 (define-public pplacer
4346 (let ((commit "807f6f3"))
4349 ;; The commit should be updated with each version change.
4350 (version "1.1.alpha19")
4355 (url "https://github.com/matsen/pplacer.git")
4356 (commit (string-append "v" version))))
4357 (file-name (git-file-name name version))
4359 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
4360 (build-system ocaml-build-system)
4362 `(#:ocaml ,ocaml-4.01
4363 #:findlib ,ocaml4.01-findlib
4364 #:modules ((guix build ocaml-build-system)
4368 (modify-phases %standard-phases
4370 (add-after 'unpack 'replace-bundled-cddlib
4371 (lambda* (#:key inputs #:allow-other-keys)
4372 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4373 (local-dir "cddlib_guix"))
4375 (with-directory-excursion local-dir
4376 (invoke "tar" "xvf" cddlib-src))
4377 (let ((cddlib-src-folder
4378 (string-append local-dir "/"
4379 (list-ref (scandir local-dir) 2)
4381 (for-each make-file-writable (find-files "cdd_src" ".*"))
4385 (string-append "cdd_src/" (basename file))))
4386 (find-files cddlib-src-folder ".*[ch]$")))
4388 (add-after 'unpack 'fix-makefile
4390 ;; Remove system calls to 'git'.
4391 (substitute* "Makefile"
4392 (("^DESCRIPT:=pplacer-.*")
4394 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4395 (substitute* "myocamlbuild.ml"
4396 (("git describe --tags --long .*\\\" with")
4398 "echo -n v" ,version "-" ,commit "\" with")))
4401 (lambda* (#:key outputs #:allow-other-keys)
4402 (let* ((out (assoc-ref outputs "out"))
4403 (bin (string-append out "/bin")))
4404 (copy-recursively "bin" bin))
4409 ("ocaml-ounit" ,ocaml4.01-ounit)
4410 ("ocaml-batteries" ,ocaml4.01-batteries)
4411 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4412 ("ocaml-csv" ,ocaml4.01-csv)
4413 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4414 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4415 ("ocaml-mcl" ,ocaml4.01-mcl)
4416 ("ocaml-gsl" ,ocaml4.01-gsl)
4417 ("cddlib-src" ,(package-source cddlib))))
4419 `(("pplacer-scripts" ,pplacer-scripts)))
4420 (synopsis "Phylogenetic placement of biological sequences")
4422 "Pplacer places query sequences on a fixed reference phylogenetic tree
4423 to maximize phylogenetic likelihood or posterior probability according to a
4424 reference alignment. Pplacer is designed to be fast, to give useful
4425 information about uncertainty, and to offer advanced visualization and
4426 downstream analysis.")
4427 (home-page "http://matsen.fhcrc.org/pplacer")
4428 (license license:gpl3))))
4430 ;; This package is installed alongside 'pplacer'. It is a separate package so
4431 ;; that it can use the python-build-system for the scripts that are
4432 ;; distributed alongside the main OCaml binaries.
4433 (define pplacer-scripts
4436 (name "pplacer-scripts")
4437 (build-system python-build-system)
4439 `(#:python ,python-2
4441 (modify-phases %standard-phases
4442 (add-after 'unpack 'enter-scripts-dir
4443 (lambda _ (chdir "scripts") #t))
4445 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
4446 (add-after 'install 'wrap-executables
4447 (lambda* (#:key inputs outputs #:allow-other-keys)
4448 (let* ((out (assoc-ref outputs "out"))
4449 (bin (string-append out "/bin")))
4450 (let ((path (string-append
4451 (assoc-ref inputs "hmmer") "/bin:"
4452 (assoc-ref inputs "infernal") "/bin")))
4454 (wrap-program (string-append bin "/refpkg_align.py")
4455 `("PATH" ":" prefix (,path))))
4456 (let ((path (string-append
4457 (assoc-ref inputs "hmmer") "/bin")))
4458 (wrap-program (string-append bin "/hrefpkg_query.py")
4459 `("PATH" ":" prefix (,path)))))
4462 `(("infernal" ,infernal)
4465 `(("python-biopython" ,python2-biopython)
4466 ("taxtastic" ,taxtastic)))
4467 (synopsis "Pplacer Python scripts")))
4469 (define-public python2-pbcore
4471 (name "python2-pbcore")
4475 (uri (pypi-uri "pbcore" version))
4478 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4479 (build-system python-build-system)
4480 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4482 `(("python-cython" ,python2-cython)
4483 ("python-numpy" ,python2-numpy)
4484 ("python-pysam" ,python2-pysam)
4485 ("python-h5py" ,python2-h5py)))
4487 `(("python-nose" ,python2-nose)
4488 ("python-sphinx" ,python2-sphinx)
4489 ("python-pyxb" ,python2-pyxb)))
4490 (home-page "http://pacificbiosciences.github.io/pbcore/")
4491 (synopsis "Library for reading and writing PacBio data files")
4493 "The pbcore package provides Python APIs for interacting with PacBio data
4494 files and writing bioinformatics applications.")
4495 (license license:bsd-3)))
4497 (define-public python2-warpedlmm
4499 (name "python2-warpedlmm")
4505 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4509 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4510 (build-system python-build-system)
4512 `(#:python ,python-2)) ; requires Python 2.7
4514 `(("python-scipy" ,python2-scipy)
4515 ("python-numpy" ,python2-numpy)
4516 ("python-matplotlib" ,python2-matplotlib)
4517 ("python-fastlmm" ,python2-fastlmm)
4518 ("python-pandas" ,python2-pandas)
4519 ("python-pysnptools" ,python2-pysnptools)))
4521 `(("python-mock" ,python2-mock)
4522 ("python-nose" ,python2-nose)
4524 (home-page "https://github.com/PMBio/warpedLMM")
4525 (synopsis "Implementation of warped linear mixed models")
4527 "WarpedLMM is a Python implementation of the warped linear mixed model,
4528 which automatically learns an optimal warping function (or transformation) for
4529 the phenotype as it models the data.")
4530 (license license:asl2.0)))
4532 (define-public pbtranscript-tofu
4533 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4535 (name "pbtranscript-tofu")
4536 (version (string-append "2.2.3." (string-take commit 7)))
4540 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4542 (file-name (string-append name "-" version "-checkout"))
4545 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4546 (modules '((guix build utils)))
4549 ;; remove bundled Cython sources
4550 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4552 (build-system python-build-system)
4554 `(#:python ,python-2
4555 ;; FIXME: Tests fail with "No such file or directory:
4556 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4559 (modify-phases %standard-phases
4560 (add-after 'unpack 'enter-directory
4562 (chdir "pbtranscript-tofu/pbtranscript/")
4564 ;; With setuptools version 18.0 and later this setup.py hack causes
4565 ;; a build error, so we disable it.
4566 (add-after 'enter-directory 'patch-setuppy
4568 (substitute* "setup.py"
4569 (("if 'setuptools.extension' in sys.modules:")
4573 `(("python-numpy" ,python2-numpy)
4574 ("python-bx-python" ,python2-bx-python)
4575 ("python-networkx" ,python2-networkx)
4576 ("python-scipy" ,python2-scipy)
4577 ("python-pbcore" ,python2-pbcore)
4578 ("python-h5py" ,python2-h5py)))
4580 `(("python-cython" ,python2-cython)
4581 ("python-nose" ,python2-nose)))
4582 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4583 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4585 "pbtranscript-tofu contains scripts to analyze transcriptome data
4586 generated using the PacBio Iso-Seq protocol.")
4587 (license license:bsd-3))))
4589 (define-public prank
4596 "http://wasabiapp.org/download/prank/prank.source."
4600 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4601 (build-system gnu-build-system)
4604 (modify-phases %standard-phases
4605 (add-after 'unpack 'enter-src-dir
4609 (add-after 'unpack 'remove-m64-flag
4610 ;; Prank will build with the correct 'bit-ness' without this flag
4611 ;; and this allows building on 32-bit machines.
4612 (lambda _ (substitute* "src/Makefile"
4617 (lambda* (#:key outputs #:allow-other-keys)
4618 (let* ((out (assoc-ref outputs "out"))
4619 (bin (string-append out "/bin"))
4620 (man (string-append out "/share/man/man1"))
4621 (path (string-append
4622 (assoc-ref %build-inputs "mafft") "/bin:"
4623 (assoc-ref %build-inputs "exonerate") "/bin:"
4624 (assoc-ref %build-inputs "bppsuite") "/bin")))
4625 (install-file "prank" bin)
4626 (wrap-program (string-append bin "/prank")
4627 `("PATH" ":" prefix (,path)))
4628 (install-file "prank.1" man))
4632 ("exonerate" ,exonerate)
4633 ("bppsuite" ,bppsuite)))
4634 (home-page "http://wasabiapp.org/software/prank/")
4635 (synopsis "Probabilistic multiple sequence alignment program")
4637 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4638 codon and amino-acid sequences. It is based on a novel algorithm that treats
4639 insertions correctly and avoids over-estimation of the number of deletion
4640 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4641 in phylogenetics and correctly takes into account the evolutionary distances
4642 between sequences. Lastly, PRANK allows for defining a potential structure
4643 for sequences to be aligned and then, simultaneously with the alignment,
4644 predicts the locations of structural units in the sequences.")
4645 (license license:gpl2+)))
4647 (define-public proteinortho
4649 (name "proteinortho")
4656 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4657 version "_src.tar.gz"))
4660 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4661 (build-system gnu-build-system)
4663 `(#:test-target "test"
4665 (modify-phases %standard-phases
4667 ;; There is no configure script, so we modify the Makefile directly.
4668 (lambda* (#:key outputs #:allow-other-keys)
4669 (substitute* "Makefile"
4672 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4674 (add-before 'install 'make-install-directory
4675 ;; The install directory is not created during 'make install'.
4676 (lambda* (#:key outputs #:allow-other-keys)
4677 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4679 (add-after 'install 'wrap-programs
4680 (lambda* (#:key inputs outputs #:allow-other-keys)
4681 (let* ((path (getenv "PATH"))
4682 (out (assoc-ref outputs "out"))
4683 (binary (string-append out "/bin/proteinortho5.pl")))
4684 (wrap-program binary `("PATH" ":" prefix (,path))))
4688 ("python" ,python-2)
4689 ("blast+" ,blast+)))
4690 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4691 (synopsis "Detect orthologous genes across species")
4693 "Proteinortho is a tool to detect orthologous genes across different
4694 species. For doing so, it compares similarities of given gene sequences and
4695 clusters them to find significant groups. The algorithm was designed to handle
4696 large-scale data and can be applied to hundreds of species at once.")
4697 (license license:gpl2+)))
4699 (define-public pyicoteo
4707 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4708 (commit (string-append "v" version))))
4709 (file-name (git-file-name name version))
4712 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4713 (build-system python-build-system)
4715 `(#:python ,python-2 ; does not work with Python 3
4716 #:tests? #f)) ; there are no tests
4718 `(("python2-matplotlib" ,python2-matplotlib)))
4719 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4720 (synopsis "Analyze high-throughput genetic sequencing data")
4722 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4723 sequencing data. It works with genomic coordinates. There are currently six
4724 different command-line tools:
4727 @item pyicoregion: for generating exploratory regions automatically;
4728 @item pyicoenrich: for differential enrichment between two conditions;
4729 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4730 @item pyicos: for genomic coordinates manipulation;
4731 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4732 @item pyicount: to count how many reads from N experiment files overlap in a
4734 @item pyicotrocol: to combine operations from pyicoteo.
4736 (license license:gpl3+)))
4738 (define-public prodigal
4745 (url "https://github.com/hyattpd/Prodigal.git")
4746 (commit (string-append "v" version))))
4747 (file-name (git-file-name name version))
4750 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4751 (build-system gnu-build-system)
4753 `(#:tests? #f ;no check target
4754 #:make-flags (list (string-append "INSTALLDIR="
4755 (assoc-ref %outputs "out")
4758 (modify-phases %standard-phases
4759 (delete 'configure))))
4760 (home-page "http://prodigal.ornl.gov")
4761 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4763 "Prodigal runs smoothly on finished genomes, draft genomes, and
4764 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4765 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4766 partial genes, and identifies translation initiation sites.")
4767 (license license:gpl3+)))
4769 (define-public roary
4777 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4781 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4782 (build-system perl-build-system)
4785 (modify-phases %standard-phases
4790 ;; The tests are not run by default, so we run each test file
4792 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4794 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4795 (getenv "PERL5LIB")))
4796 (for-each (lambda (file)
4797 (display file)(display "\n")
4798 (invoke "perl" file))
4799 (find-files "t" ".*\\.t$"))
4802 ;; There is no 'install' target in the Makefile.
4803 (lambda* (#:key outputs #:allow-other-keys)
4804 (let* ((out (assoc-ref outputs "out"))
4805 (bin (string-append out "/bin"))
4806 (perl (string-append out "/lib/perl5/site_perl"))
4807 (roary-plots "contrib/roary_plots"))
4810 (copy-recursively "bin" bin)
4811 (copy-recursively "lib" perl)
4813 (add-after 'install 'wrap-programs
4814 (lambda* (#:key inputs outputs #:allow-other-keys)
4815 (let* ((out (assoc-ref outputs "out"))
4816 (perl5lib (getenv "PERL5LIB"))
4817 (path (getenv "PATH")))
4818 (for-each (lambda (prog)
4819 (let ((binary (string-append out "/" prog)))
4820 (wrap-program binary
4821 `("PERL5LIB" ":" prefix
4822 (,(string-append perl5lib ":" out
4823 "/lib/perl5/site_perl"))))
4824 (wrap-program binary
4826 (,(string-append path ":" out "/bin"))))))
4827 (find-files "bin" ".*[^R]$"))
4829 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4830 (r-site-lib (getenv "R_LIBS_SITE"))
4832 (string-append (assoc-ref inputs "coreutils") "/bin")))
4834 `("R_LIBS_SITE" ":" prefix
4835 (,(string-append r-site-lib ":" out "/site-library/"))))
4838 (,(string-append coreutils-path ":" out "/bin"))))))
4841 `(("perl-env-path" ,perl-env-path)
4842 ("perl-test-files" ,perl-test-files)
4843 ("perl-test-most" ,perl-test-most)
4844 ("perl-test-output" ,perl-test-output)))
4846 `(("perl-array-utils" ,perl-array-utils)
4847 ("bioperl" ,bioperl-minimal)
4848 ("perl-digest-md5-file" ,perl-digest-md5-file)
4849 ("perl-exception-class" ,perl-exception-class)
4850 ("perl-file-find-rule" ,perl-file-find-rule)
4851 ("perl-file-grep" ,perl-file-grep)
4852 ("perl-file-slurper" ,perl-file-slurper)
4853 ("perl-file-which" ,perl-file-which)
4854 ("perl-graph" ,perl-graph)
4855 ("perl-graph-readwrite" ,perl-graph-readwrite)
4856 ("perl-log-log4perl" ,perl-log-log4perl)
4857 ("perl-moose" ,perl-moose)
4858 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4859 ("perl-text-csv" ,perl-text-csv)
4860 ("bedtools" ,bedtools)
4864 ("parallel" ,parallel)
4867 ("fasttree" ,fasttree)
4871 ("r-minimal" ,r-minimal)
4872 ("r-ggplot2" ,r-ggplot2)
4873 ("coreutils" ,coreutils)))
4874 (home-page "http://sanger-pathogens.github.io/Roary")
4875 (synopsis "High speed stand-alone pan genome pipeline")
4877 "Roary is a high speed stand alone pan genome pipeline, which takes
4878 annotated assemblies in GFF3 format (produced by the Prokka program) and
4879 calculates the pan genome. Using a standard desktop PC, it can analyse
4880 datasets with thousands of samples, without compromising the quality of the
4881 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4882 single processor. Roary is not intended for metagenomics or for comparing
4883 extremely diverse sets of genomes.")
4884 (license license:gpl3)))
4886 (define-public raxml
4894 (url "https://github.com/stamatak/standard-RAxML.git")
4895 (commit (string-append "v" version))))
4896 (file-name (git-file-name name version))
4899 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4900 (build-system gnu-build-system)
4902 `(#:tests? #f ; There are no tests.
4903 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4904 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4906 (modify-phases %standard-phases
4909 (lambda* (#:key outputs #:allow-other-keys)
4910 (let* ((out (assoc-ref outputs "out"))
4911 (bin (string-append out "/bin"))
4912 (executable "raxmlHPC-HYBRID"))
4913 (install-file executable bin)
4914 (symlink (string-append bin "/" executable) "raxml"))
4917 `(("openmpi" ,openmpi)))
4918 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4919 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4921 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4923 ;; The source includes x86 specific code
4924 (supported-systems '("x86_64-linux" "i686-linux"))
4925 (license license:gpl2+)))
4935 (url "https://github.com/deweylab/RSEM.git")
4936 (commit (string-append "v" version))))
4938 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4939 (file-name (git-file-name name version))
4940 (modules '((guix build utils)))
4943 ;; remove bundled copy of boost and samtools
4944 (delete-file-recursively "boost")
4945 (delete-file-recursively "samtools-1.3")
4947 (build-system gnu-build-system)
4949 `(#:tests? #f ;no "check" target
4951 (list (string-append "BOOST="
4952 (assoc-ref %build-inputs "boost")
4954 (string-append "SAMHEADERS="
4955 (assoc-ref %build-inputs "htslib")
4956 "/include/htslib/sam.h")
4957 (string-append "SAMLIBS="
4958 (assoc-ref %build-inputs "htslib")
4961 (modify-phases %standard-phases
4962 ;; No "configure" script.
4963 ;; Do not build bundled samtools library.
4966 (substitute* "Makefile"
4967 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4968 (("^\\$\\(SAMLIBS\\).*") ""))
4971 (lambda* (#:key outputs #:allow-other-keys)
4972 (let* ((out (string-append (assoc-ref outputs "out")))
4973 (bin (string-append out "/bin/"))
4974 (perl (string-append out "/lib/perl5/site_perl")))
4977 (for-each (lambda (file)
4978 (install-file file bin))
4979 (find-files "." "rsem-.*"))
4980 (install-file "rsem_perl_utils.pm" perl))
4982 (add-after 'install 'wrap-program
4983 (lambda* (#:key outputs #:allow-other-keys)
4984 (let ((out (assoc-ref outputs "out")))
4985 (for-each (lambda (prog)
4986 (wrap-program (string-append out "/bin/" prog)
4987 `("PERL5LIB" ":" prefix
4988 (,(string-append out "/lib/perl5/site_perl")))))
4989 '("rsem-calculate-expression"
4991 "rsem-generate-data-matrix"
4992 "rsem-generate-ngvector"
4993 "rsem-plot-transcript-wiggles"
4994 "rsem-prepare-reference"
4996 "rsem-run-prsem-testing-procedure")))
5000 ("r-minimal" ,r-minimal)
5002 ("htslib" ,htslib-1.3)
5004 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5005 (synopsis "Estimate gene expression levels from RNA-Seq data")
5007 "RSEM is a software package for estimating gene and isoform expression
5008 levels from RNA-Seq data. The RSEM package provides a user-friendly
5009 interface, supports threads for parallel computation of the EM algorithm,
5010 single-end and paired-end read data, quality scores, variable-length reads and
5011 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5012 interval estimates for expression levels. For visualization, it can generate
5013 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5014 (license license:gpl3+)))
5016 (define-public rseqc
5024 (string-append "mirror://sourceforge/rseqc/"
5025 "RSeQC-" version ".tar.gz"))
5027 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5028 (modules '((guix build utils)))
5031 ;; remove bundled copy of pysam
5032 (delete-file-recursively "lib/pysam")
5033 (substitute* "setup.py"
5034 ;; remove dependency on outdated "distribute" module
5035 (("^from distribute_setup import use_setuptools") "")
5036 (("^use_setuptools\\(\\)") "")
5037 ;; do not use bundled copy of pysam
5038 (("^have_pysam = False") "have_pysam = True"))
5040 (build-system python-build-system)
5041 (arguments `(#:python ,python-2))
5043 `(("python-cython" ,python2-cython)
5044 ("python-pysam" ,python2-pysam)
5045 ("python-numpy" ,python2-numpy)
5048 `(("python-nose" ,python2-nose)))
5049 (home-page "http://rseqc.sourceforge.net/")
5050 (synopsis "RNA-seq quality control package")
5052 "RSeQC provides a number of modules that can comprehensively evaluate
5053 high throughput sequence data, especially RNA-seq data. Some basic modules
5054 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5055 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5056 distribution, coverage uniformity, strand specificity, etc.")
5057 (license license:gpl3+)))
5060 ;; There are no release tarballs. According to the installation
5061 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5062 ;; stable release is identified by this changeset ID.
5063 (let ((changeset "2329130")
5067 (version (string-append "0-" revision "." changeset))
5071 (url "https://bitbucket.org/libsleipnir/sleipnir")
5072 (changeset changeset)))
5073 (file-name (string-append name "-" version "-checkout"))
5076 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5077 (build-system gnu-build-system)
5079 `(#:modules ((srfi srfi-1)
5080 (guix build gnu-build-system)
5083 (let ((dirs '("SeekMiner"
5089 (modify-phases %standard-phases
5092 (substitute* "gen_tools_am"
5093 (("/usr/bin/env.*") (which "perl")))
5094 (invoke "bash" "gen_auto")
5096 (add-after 'build 'build-additional-tools
5097 (lambda* (#:key make-flags #:allow-other-keys)
5098 (for-each (lambda (dir)
5099 (with-directory-excursion (string-append "tools/" dir)
5100 (apply invoke "make" make-flags)))
5103 (add-after 'install 'install-additional-tools
5104 (lambda* (#:key make-flags #:allow-other-keys)
5105 (for-each (lambda (dir)
5106 (with-directory-excursion (string-append "tools/" dir)
5107 (apply invoke `("make" ,@make-flags "install"))))
5114 ("readline" ,readline)
5115 ("gengetopt" ,gengetopt)
5116 ("log4cpp" ,log4cpp)))
5118 `(("autoconf" ,autoconf)
5119 ("automake" ,automake)
5121 (home-page "http://seek.princeton.edu")
5122 (synopsis "Gene co-expression search engine")
5124 "SEEK is a computational gene co-expression search engine. SEEK provides
5125 biologists with a way to navigate the massive human expression compendium that
5126 now contains thousands of expression datasets. SEEK returns a robust ranking
5127 of co-expressed genes in the biological area of interest defined by the user's
5128 query genes. It also prioritizes thousands of expression datasets according
5129 to the user's query of interest.")
5130 (license license:cc-by3.0))))
5132 (define-public samtools
5140 (string-append "mirror://sourceforge/samtools/samtools/"
5141 version "/samtools-" version ".tar.bz2"))
5144 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5145 (modules '((guix build utils)))
5147 ;; Delete bundled htslib.
5148 (delete-file-recursively "htslib-1.9")
5150 (build-system gnu-build-system)
5152 `(#:modules ((ice-9 ftw)
5154 (guix build gnu-build-system)
5156 #:configure-flags (list "--with-ncurses")
5158 (modify-phases %standard-phases
5159 (add-after 'unpack 'patch-tests
5161 (substitute* "test/test.pl"
5162 ;; The test script calls out to /bin/bash
5163 (("/bin/bash") (which "bash")))
5165 (add-after 'install 'install-library
5166 (lambda* (#:key outputs #:allow-other-keys)
5167 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5168 (install-file "libbam.a" lib)
5170 (add-after 'install 'install-headers
5171 (lambda* (#:key outputs #:allow-other-keys)
5172 (let ((include (string-append (assoc-ref outputs "out")
5173 "/include/samtools/")))
5174 (for-each (lambda (file)
5175 (install-file file include))
5176 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5178 (native-inputs `(("pkg-config" ,pkg-config)))
5180 `(("htslib" ,htslib)
5181 ("ncurses" ,ncurses)
5185 (home-page "http://samtools.sourceforge.net")
5186 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5188 "Samtools implements various utilities for post-processing nucleotide
5189 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5190 variant calling (in conjunction with bcftools), and a simple alignment
5192 (license license:expat)))
5194 (define-public samtools-0.1
5195 ;; This is the most recent version of the 0.1 line of samtools. The input
5196 ;; and output formats differ greatly from that used and produced by samtools
5197 ;; 1.x and is still used in many bioinformatics pipelines.
5198 (package (inherit samtools)
5204 (string-append "mirror://sourceforge/samtools/samtools/"
5205 version "/samtools-" version ".tar.bz2"))
5207 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5209 `(#:tests? #f ;no "check" target
5211 (list "LIBCURSES=-lncurses")
5212 ,@(substitute-keyword-arguments (package-arguments samtools)
5214 `(modify-phases ,phases
5216 (lambda* (#:key outputs #:allow-other-keys)
5217 (let ((bin (string-append
5218 (assoc-ref outputs "out") "/bin")))
5220 (install-file "samtools" bin)
5222 (delete 'patch-tests)
5223 (delete 'configure))))))))
5225 (define-public mosaik
5226 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5231 ;; There are no release tarballs nor tags.
5234 (url "https://github.com/wanpinglee/MOSAIK.git")
5236 (file-name (string-append name "-" version))
5239 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5240 (build-system gnu-build-system)
5242 `(#:tests? #f ; no tests
5243 #:make-flags (list "CC=gcc")
5245 (modify-phases %standard-phases
5247 (lambda _ (chdir "src") #t))
5249 (lambda* (#:key outputs #:allow-other-keys)
5250 (let ((bin (string-append (assoc-ref outputs "out")
5253 (copy-recursively "../bin" bin)
5257 ("zlib:static" ,zlib "static")
5259 (supported-systems '("x86_64-linux"))
5260 (home-page "https://github.com/wanpinglee/MOSAIK")
5261 (synopsis "Map nucleotide sequence reads to reference genomes")
5263 "MOSAIK is a program for mapping second and third-generation sequencing
5264 reads to a reference genome. MOSAIK can align reads generated by all the
5265 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5266 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5267 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5268 ;; code released into the public domain:
5269 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5270 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5271 (license (list license:gpl2+ license:public-domain)))))
5273 (define-public ngs-sdk
5280 (url "https://github.com/ncbi/ngs.git")
5282 (file-name (git-file-name name version))
5285 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5286 (build-system gnu-build-system)
5288 `(#:parallel-build? #f ; not supported
5289 #:tests? #f ; no "check" target
5291 (modify-phases %standard-phases
5293 (lambda* (#:key outputs #:allow-other-keys)
5294 (let ((out (assoc-ref outputs "out")))
5295 ;; Allow 'konfigure.perl' to find 'package.prl'.
5297 (string-append ".:" (getenv "PERL5LIB")))
5299 ;; The 'configure' script doesn't recognize things like
5300 ;; '--enable-fast-install'.
5301 (invoke "./configure"
5302 (string-append "--build-prefix=" (getcwd) "/build")
5303 (string-append "--prefix=" out))
5305 (add-after 'unpack 'enter-dir
5306 (lambda _ (chdir "ngs-sdk") #t)))))
5307 (native-inputs `(("perl" ,perl)))
5308 ;; According to the test
5309 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5310 ;; in ngs-sdk/setup/konfigure.perl
5311 (supported-systems '("i686-linux" "x86_64-linux"))
5312 (home-page "https://github.com/ncbi/ngs")
5313 (synopsis "API for accessing Next Generation Sequencing data")
5315 "NGS is a domain-specific API for accessing reads, alignments and pileups
5316 produced from Next Generation Sequencing. The API itself is independent from
5317 any particular back-end implementation, and supports use of multiple back-ends
5319 (license license:public-domain)))
5321 (define-public java-ngs
5322 (package (inherit ngs-sdk)
5325 `(,@(substitute-keyword-arguments
5326 `(#:modules ((guix build gnu-build-system)
5330 ,@(package-arguments ngs-sdk))
5332 `(modify-phases ,phases
5333 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5335 `(("jdk" ,icedtea "jdk")
5336 ("ngs-sdk" ,ngs-sdk)))
5337 (synopsis "Java bindings for NGS SDK")))
5339 (define-public ncbi-vdb
5346 (url "https://github.com/ncbi/ncbi-vdb.git")
5348 (file-name (git-file-name name version))
5351 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5352 (build-system gnu-build-system)
5354 `(#:parallel-build? #f ; not supported
5355 #:tests? #f ; no "check" target
5357 (modify-phases %standard-phases
5358 (add-after 'unpack 'make-files-writable
5359 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5360 (add-before 'configure 'set-perl-search-path
5362 ;; Work around "dotless @INC" build failure.
5364 (string-append (getcwd) "/setup:"
5365 (getenv "PERL5LIB")))
5368 (lambda* (#:key inputs outputs #:allow-other-keys)
5369 (let ((out (assoc-ref outputs "out")))
5370 ;; Override include path for libmagic
5371 (substitute* "setup/package.prl"
5372 (("name => 'magic', Include => '/usr/include'")
5373 (string-append "name=> 'magic', Include => '"
5374 (assoc-ref inputs "libmagic")
5377 ;; Install kdf5 library (needed by sra-tools)
5378 (substitute* "build/Makefile.install"
5379 (("LIBRARIES_TO_INSTALL =")
5380 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5382 (substitute* "build/Makefile.env"
5383 (("CFLAGS =" prefix)
5384 (string-append prefix "-msse2 ")))
5386 ;; Override search path for ngs-java
5387 (substitute* "setup/package.prl"
5388 (("/usr/local/ngs/ngs-java")
5389 (assoc-ref inputs "java-ngs")))
5391 ;; The 'configure' script doesn't recognize things like
5392 ;; '--enable-fast-install'.
5393 (invoke "./configure"
5394 (string-append "--build-prefix=" (getcwd) "/build")
5395 (string-append "--prefix=" (assoc-ref outputs "out"))
5396 (string-append "--debug")
5397 (string-append "--with-xml2-prefix="
5398 (assoc-ref inputs "libxml2"))
5399 (string-append "--with-ngs-sdk-prefix="
5400 (assoc-ref inputs "ngs-sdk"))
5401 (string-append "--with-hdf5-prefix="
5402 (assoc-ref inputs "hdf5")))
5404 (add-after 'install 'install-interfaces
5405 (lambda* (#:key outputs #:allow-other-keys)
5406 ;; Install interface libraries. On i686 the interface libraries
5407 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5408 ;; architecture name ("i386") instead of the target system prefix
5410 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5411 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5412 ,(system->linux-architecture
5413 (or (%current-target-system)
5416 (string-append (assoc-ref outputs "out")
5418 ;; Install interface headers
5419 (copy-recursively "interfaces"
5420 (string-append (assoc-ref outputs "out")
5423 ;; These files are needed by sra-tools.
5424 (add-after 'install 'install-configuration-files
5425 (lambda* (#:key outputs #:allow-other-keys)
5426 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5428 (install-file "libs/kfg/default.kfg" target)
5429 (install-file "libs/kfg/certs.kfg" target))
5432 `(("libxml2" ,libxml2)
5433 ("ngs-sdk" ,ngs-sdk)
5434 ("java-ngs" ,java-ngs)
5437 (native-inputs `(("perl" ,perl)))
5438 ;; NCBI-VDB requires SSE capability.
5439 (supported-systems '("i686-linux" "x86_64-linux"))
5440 (home-page "https://github.com/ncbi/ncbi-vdb")
5441 (synopsis "Database engine for genetic information")
5443 "The NCBI-VDB library implements a highly compressed columnar data
5444 warehousing engine that is most often used to store genetic information.
5445 Databases are stored in a portable image within the file system, and can be
5446 accessed/downloaded on demand across HTTP.")
5447 (license license:public-domain)))
5449 (define-public plink
5457 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5458 version "-src.zip"))
5460 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5461 (patches (search-patches "plink-1.07-unclobber-i.patch"
5462 "plink-endian-detection.patch"))))
5463 (build-system gnu-build-system)
5465 '(#:tests? #f ;no "check" target
5466 #:make-flags (list (string-append "LIB_LAPACK="
5467 (assoc-ref %build-inputs "lapack")
5468 "/lib/liblapack.so")
5471 ;; disable phoning home
5474 (modify-phases %standard-phases
5475 ;; no "configure" script
5478 (lambda* (#:key outputs #:allow-other-keys)
5479 (let ((bin (string-append (assoc-ref outputs "out")
5481 (install-file "plink" bin)
5485 ("lapack" ,lapack)))
5487 `(("unzip" ,unzip)))
5488 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5489 (synopsis "Whole genome association analysis toolset")
5491 "PLINK is a whole genome association analysis toolset, designed to
5492 perform a range of basic, large-scale analyses in a computationally efficient
5493 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5494 so there is no support for steps prior to this (e.g. study design and
5495 planning, generating genotype or CNV calls from raw data). Through
5496 integration with gPLINK and Haploview, there is some support for the
5497 subsequent visualization, annotation and storage of results.")
5498 ;; Code is released under GPLv2, except for fisher.h, which is under
5500 (license (list license:gpl2 license:lgpl2.1+))))
5502 (define-public plink-ng
5503 (package (inherit plink)
5510 (url "https://github.com/chrchang/plink-ng.git")
5511 (commit (string-append "v" version))))
5512 (file-name (git-file-name name version))
5514 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5515 (build-system gnu-build-system)
5517 '(#:tests? #f ;no "check" target
5518 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5519 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5521 "-f" "Makefile.std")
5523 (modify-phases %standard-phases
5524 (add-after 'unpack 'chdir
5525 (lambda _ (chdir "1.9") #t))
5526 (delete 'configure) ; no "configure" script
5528 (lambda* (#:key outputs #:allow-other-keys)
5529 (let ((bin (string-append (assoc-ref outputs "out")
5531 (install-file "plink" bin)
5536 ("openblas" ,openblas)))
5537 (home-page "https://www.cog-genomics.org/plink/")
5538 (license license:gpl3+)))
5540 (define-public smithlab-cpp
5541 (let ((revision "1")
5542 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5544 (name "smithlab-cpp")
5545 (version (string-append "0." revision "." (string-take commit 7)))
5549 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5551 (file-name (string-append name "-" version "-checkout"))
5554 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5555 (build-system gnu-build-system)
5557 `(#:modules ((guix build gnu-build-system)
5560 #:tests? #f ;no "check" target
5562 (modify-phases %standard-phases
5563 (add-after 'unpack 'use-samtools-headers
5565 (substitute* '("SAM.cpp"
5567 (("sam.h") "samtools/sam.h"))
5570 (lambda* (#:key outputs #:allow-other-keys)
5571 (let* ((out (assoc-ref outputs "out"))
5572 (lib (string-append out "/lib"))
5573 (include (string-append out "/include/smithlab-cpp")))
5576 (for-each (cut install-file <> lib)
5577 (find-files "." "\\.o$"))
5578 (for-each (cut install-file <> include)
5579 (find-files "." "\\.hpp$")))
5581 (delete 'configure))))
5583 `(("samtools" ,samtools-0.1)
5585 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5586 (synopsis "C++ helper library for functions used in Smith lab projects")
5588 "Smithlab CPP is a C++ library that includes functions used in many of
5589 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5590 structures, classes for genomic regions, mapped sequencing reads, etc.")
5591 (license license:gpl3+))))
5593 (define-public preseq
5599 (uri (string-append "https://github.com/smithlabcode/preseq/"
5600 "releases/download/v" version
5601 "/preseq_v" version ".tar.bz2"))
5603 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5604 (modules '((guix build utils)))
5606 ;; Remove bundled samtools.
5607 (delete-file-recursively "samtools")
5609 (build-system gnu-build-system)
5611 `(#:tests? #f ;no "check" target
5613 (modify-phases %standard-phases
5614 (delete 'configure))
5616 (list (string-append "PREFIX="
5617 (assoc-ref %outputs "out"))
5618 (string-append "LIBBAM="
5619 (assoc-ref %build-inputs "samtools")
5621 (string-append "SMITHLAB_CPP="
5622 (assoc-ref %build-inputs "smithlab-cpp")
5625 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5628 ("samtools" ,samtools-0.1)
5629 ("smithlab-cpp" ,smithlab-cpp)
5631 (home-page "http://smithlabresearch.org/software/preseq/")
5632 (synopsis "Program for analyzing library complexity")
5634 "The preseq package is aimed at predicting and estimating the complexity
5635 of a genomic sequencing library, equivalent to predicting and estimating the
5636 number of redundant reads from a given sequencing depth and how many will be
5637 expected from additional sequencing using an initial sequencing experiment.
5638 The estimates can then be used to examine the utility of further sequencing,
5639 optimize the sequencing depth, or to screen multiple libraries to avoid low
5640 complexity samples.")
5641 (license license:gpl3+)))
5643 (define-public python-screed
5645 (name "python-screed")
5650 (uri (pypi-uri "screed" version))
5653 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5654 (build-system python-build-system)
5657 (modify-phases %standard-phases
5658 ;; Tests must be run after installation, as the "screed" command does
5659 ;; not exist right after building.
5661 (add-after 'install 'check
5662 (lambda* (#:key inputs outputs #:allow-other-keys)
5663 (let ((out (assoc-ref outputs "out")))
5664 (setenv "PYTHONPATH"
5665 (string-append out "/lib/python"
5666 (string-take (string-take-right
5667 (assoc-ref inputs "python")
5670 (getenv "PYTHONPATH")))
5671 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5672 (invoke "python" "setup.py" "test")
5675 `(("python-pytest" ,python-pytest)
5676 ("python-pytest-cov" ,python-pytest-cov)
5677 ("python-pytest-runner" ,python-pytest-runner)))
5679 `(("python-bz2file" ,python-bz2file)))
5680 (home-page "https://github.com/dib-lab/screed/")
5681 (synopsis "Short read sequence database utilities")
5682 (description "Screed parses FASTA and FASTQ files and generates databases.
5683 Values such as sequence name, sequence description, sequence quality and the
5684 sequence itself can be retrieved from these databases.")
5685 (license license:bsd-3)))
5687 (define-public python2-screed
5688 (package-with-python2 python-screed))
5690 (define-public sra-tools
5698 (url "https://github.com/ncbi/sra-tools.git")
5700 (file-name (git-file-name name version))
5703 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5704 (build-system gnu-build-system)
5706 `(#:parallel-build? #f ; not supported
5707 #:tests? #f ; no "check" target
5709 (list (string-append "DEFAULT_CRT="
5710 (assoc-ref %build-inputs "ncbi-vdb")
5712 (string-append "DEFAULT_KFG="
5713 (assoc-ref %build-inputs "ncbi-vdb")
5715 (string-append "VDB_LIBDIR="
5716 (assoc-ref %build-inputs "ncbi-vdb")
5717 ,(if (string-prefix? "x86_64"
5718 (or (%current-target-system)
5723 (modify-phases %standard-phases
5724 (add-before 'configure 'set-perl-search-path
5726 ;; Work around "dotless @INC" build failure.
5728 (string-append (getcwd) "/setup:"
5729 (getenv "PERL5LIB")))
5732 (lambda* (#:key inputs outputs #:allow-other-keys)
5733 ;; The build system expects a directory containing the sources and
5734 ;; raw build output of ncbi-vdb, including files that are not
5735 ;; installed. Since we are building against an installed version of
5736 ;; ncbi-vdb, the following modifications are needed.
5737 (substitute* "setup/konfigure.perl"
5738 ;; Make the configure script look for the "ilib" directory of
5739 ;; "ncbi-vdb" without first checking for the existence of a
5740 ;; matching library in its "lib" directory.
5741 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5742 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5743 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5744 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5745 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5748 (substitute* "tools/copycat/Makefile"
5749 (("smagic-static") "lmagic"))
5751 ;; The 'configure' script doesn't recognize things like
5752 ;; '--enable-fast-install'.
5753 (invoke "./configure"
5754 (string-append "--build-prefix=" (getcwd) "/build")
5755 (string-append "--prefix=" (assoc-ref outputs "out"))
5756 (string-append "--debug")
5757 (string-append "--with-fuse-prefix="
5758 (assoc-ref inputs "fuse"))
5759 (string-append "--with-magic-prefix="
5760 (assoc-ref inputs "libmagic"))
5761 ;; TODO: building with libxml2 fails with linker errors
5762 ;; (string-append "--with-xml2-prefix="
5763 ;; (assoc-ref inputs "libxml2"))
5764 (string-append "--with-ncbi-vdb-sources="
5765 (assoc-ref inputs "ncbi-vdb"))
5766 (string-append "--with-ncbi-vdb-build="
5767 (assoc-ref inputs "ncbi-vdb"))
5768 (string-append "--with-ngs-sdk-prefix="
5769 (assoc-ref inputs "ngs-sdk"))
5770 (string-append "--with-hdf5-prefix="
5771 (assoc-ref inputs "hdf5")))
5773 (native-inputs `(("perl" ,perl)))
5775 `(("ngs-sdk" ,ngs-sdk)
5776 ("ncbi-vdb" ,ncbi-vdb)
5781 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5782 (synopsis "Tools and libraries for reading and writing sequencing data")
5784 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5785 reading of sequencing files from the Sequence Read Archive (SRA) database and
5786 writing files into the .sra format.")
5787 (license license:public-domain)))
5789 (define-public seqan
5795 (uri (string-append "https://github.com/seqan/seqan/releases/"
5796 "download/seqan-v" version
5797 "/seqan-library-" version ".tar.xz"))
5800 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5801 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5802 ;; makes sense to split the outputs.
5803 (outputs '("out" "doc"))
5804 (build-system trivial-build-system)
5806 `(#:modules ((guix build utils))
5809 (use-modules (guix build utils))
5810 (let ((tar (assoc-ref %build-inputs "tar"))
5811 (xz (assoc-ref %build-inputs "xz"))
5812 (out (assoc-ref %outputs "out"))
5813 (doc (assoc-ref %outputs "doc")))
5814 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5815 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5816 (chdir (string-append "seqan-library-" ,version))
5817 (copy-recursively "include" (string-append out "/include"))
5818 (copy-recursively "share" (string-append doc "/share"))
5821 `(("source" ,source)
5824 (home-page "http://www.seqan.de")
5825 (synopsis "Library for nucleotide sequence analysis")
5827 "SeqAn is a C++ library of efficient algorithms and data structures for
5828 the analysis of sequences with the focus on biological data. It contains
5829 algorithms and data structures for string representation and their
5830 manipulation, online and indexed string search, efficient I/O of
5831 bioinformatics file formats, sequence alignment, and more.")
5832 (license license:bsd-3)))
5834 (define-public seqan-1
5835 (package (inherit seqan)
5840 (uri (string-append "http://packages.seqan.de/seqan-library/"
5841 "seqan-library-" version ".tar.bz2"))
5844 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5845 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5846 ;; makes sense to split the outputs.
5847 (outputs '("out" "doc"))
5848 (build-system trivial-build-system)
5850 `(#:modules ((guix build utils))
5853 (use-modules (guix build utils))
5854 (let ((tar (assoc-ref %build-inputs "tar"))
5855 (bzip (assoc-ref %build-inputs "bzip2"))
5856 (out (assoc-ref %outputs "out"))
5857 (doc (assoc-ref %outputs "doc")))
5858 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5859 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5860 (chdir (string-append "seqan-library-" ,version))
5861 (copy-recursively "include" (string-append out "/include"))
5862 (copy-recursively "share" (string-append doc "/share"))
5865 `(("source" ,source)
5867 ("bzip2" ,bzip2)))))
5869 (define-public seqmagick
5876 (uri (pypi-uri "seqmagick" version))
5879 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5880 (build-system python-build-system)
5882 `(("python-biopython" ,python-biopython)))
5884 `(("python-nose" ,python-nose)))
5885 (home-page "https://github.com/fhcrc/seqmagick")
5886 (synopsis "Tools for converting and modifying sequence files")
5888 "Bioinformaticians often have to convert sequence files between formats
5889 and do little manipulations on them, and it's not worth writing scripts for
5890 that. Seqmagick is a utility to expose the file format conversion in
5891 BioPython in a convenient way. Instead of having a big mess of scripts, there
5892 is one that takes arguments.")
5893 (license license:gpl3)))
5895 (define-public seqtk
5902 (url "https://github.com/lh3/seqtk.git")
5903 (commit (string-append "v" version))))
5904 (file-name (git-file-name name version))
5907 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5908 (build-system gnu-build-system)
5911 (modify-phases %standard-phases
5914 ;; There are no tests, so we just run a sanity check.
5915 (lambda _ (invoke "./seqtk" "seq") #t))
5917 (lambda* (#:key outputs #:allow-other-keys)
5918 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5919 (install-file "seqtk" bin)
5923 (home-page "https://github.com/lh3/seqtk")
5924 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5926 "Seqtk is a fast and lightweight tool for processing sequences in the
5927 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5928 optionally compressed by gzip.")
5929 (license license:expat)))
5931 (define-public snap-aligner
5933 (name "snap-aligner")
5934 (version "1.0beta.18")
5938 (url "https://github.com/amplab/snap.git")
5939 (commit (string-append "v" version))))
5940 (file-name (git-file-name name version))
5943 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5944 (build-system gnu-build-system)
5947 (modify-phases %standard-phases
5949 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5951 (lambda* (#:key outputs #:allow-other-keys)
5952 (let* ((out (assoc-ref outputs "out"))
5953 (bin (string-append out "/bin")))
5954 (install-file "snap-aligner" bin)
5955 (install-file "SNAPCommand" bin)
5959 (home-page "http://snap.cs.berkeley.edu/")
5960 (synopsis "Short read DNA sequence aligner")
5962 "SNAP is a fast and accurate aligner for short DNA reads. It is
5963 optimized for modern read lengths of 100 bases or higher, and takes advantage
5964 of these reads to align data quickly through a hash-based indexing scheme.")
5965 ;; 32-bit systems are not supported by the unpatched code.
5966 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5967 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5968 ;; systems without a lot of memory cannot make good use of this program.
5969 (supported-systems '("x86_64-linux"))
5970 (license license:asl2.0)))
5972 (define-public sortmerna
5980 (url "https://github.com/biocore/sortmerna.git")
5982 (file-name (git-file-name name version))
5985 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5986 (build-system gnu-build-system)
5987 (outputs '("out" ;for binaries
5988 "db")) ;for sequence databases
5991 (modify-phases %standard-phases
5993 (lambda* (#:key outputs #:allow-other-keys)
5994 (let* ((out (assoc-ref outputs "out"))
5995 (bin (string-append out "/bin"))
5996 (db (assoc-ref outputs "db"))
5998 (string-append db "/share/sortmerna/rRNA_databases")))
5999 (install-file "sortmerna" bin)
6000 (install-file "indexdb_rna" bin)
6001 (for-each (lambda (file)
6002 (install-file file share))
6003 (find-files "rRNA_databases" ".*fasta"))
6007 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6008 (synopsis "Biological sequence analysis tool for NGS reads")
6010 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6011 and operational taxonomic unit (OTU) picking of next generation
6012 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6013 allows for fast and sensitive analyses of nucleotide sequences. The main
6014 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6015 ;; The source includes x86 specific code
6016 (supported-systems '("x86_64-linux" "i686-linux"))
6017 (license license:lgpl3)))
6026 (url "https://github.com/alexdobin/STAR.git")
6028 (file-name (string-append name "-" version "-checkout"))
6031 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
6032 (modules '((guix build utils)))
6035 (substitute* "source/Makefile"
6037 ;; Remove pre-built binaries and bundled htslib sources.
6038 (delete-file-recursively "bin/MacOSX_x86_64")
6039 (delete-file-recursively "bin/Linux_x86_64")
6040 (delete-file-recursively "bin/Linux_x86_64_static")
6041 (delete-file-recursively "source/htslib")
6043 (build-system gnu-build-system)
6045 '(#:tests? #f ;no check target
6046 #:make-flags '("STAR")
6048 (modify-phases %standard-phases
6049 (add-after 'unpack 'enter-source-dir
6050 (lambda _ (chdir "source") #t))
6051 (add-after 'enter-source-dir 'make-reproducible
6053 (substitute* "Makefile"
6054 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6055 (string-append pre "Built with Guix" post)))
6057 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6059 (substitute* "Makefile"
6060 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6062 (substitute* '("BAMfunctions.cpp"
6067 "bamRemoveDuplicates.cpp")
6068 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6069 (string-append "#include <" header ">")))
6070 (substitute* "IncludeDefine.h"
6071 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6072 (string-append "<" header ">")))
6075 (lambda* (#:key outputs #:allow-other-keys)
6076 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6077 (install-file "STAR" bin))
6079 (delete 'configure))))
6083 `(("htslib" ,htslib)
6085 (home-page "https://github.com/alexdobin/STAR")
6086 (synopsis "Universal RNA-seq aligner")
6088 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6089 based on a previously undescribed RNA-seq alignment algorithm that uses
6090 sequential maximum mappable seed search in uncompressed suffix arrays followed
6091 by seed clustering and stitching procedure. In addition to unbiased de novo
6092 detection of canonical junctions, STAR can discover non-canonical splices and
6093 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6095 ;; Only 64-bit systems are supported according to the README.
6096 (supported-systems '("x86_64-linux" "mips64el-linux"))
6097 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6098 (license license:gpl3+)))
6100 (define-public subread
6106 (uri (string-append "mirror://sourceforge/subread/subread-"
6107 version "/subread-" version "-source.tar.gz"))
6110 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6111 (build-system gnu-build-system)
6113 `(#:tests? #f ;no "check" target
6114 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6115 ;; optimizations by default, so we override these flags such that x86_64
6116 ;; flags are only added when the build target is an x86_64 system.
6118 (list (let ((system ,(or (%current-target-system)
6120 (flags '("-ggdb" "-fomit-frame-pointer"
6121 "-ffast-math" "-funroll-loops"
6122 "-fmessage-length=0"
6123 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6125 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6126 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6127 (if (string-prefix? "x86_64" system)
6128 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6129 (string-append "CCFLAGS=" (string-join flags))))
6130 "-f" "Makefile.Linux"
6131 "CC=gcc ${CCFLAGS}")
6133 (modify-phases %standard-phases
6134 (add-after 'unpack 'enter-dir
6135 (lambda _ (chdir "src") #t))
6137 (lambda* (#:key outputs #:allow-other-keys)
6138 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6140 (copy-recursively "../bin" bin))
6142 ;; no "configure" script
6143 (delete 'configure))))
6144 (inputs `(("zlib" ,zlib)))
6145 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6146 (synopsis "Tool kit for processing next-gen sequencing data")
6148 "The subread package contains the following tools: subread aligner, a
6149 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6150 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6151 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6152 against local background noises.")
6153 (license license:gpl3+)))
6155 (define-public stringtie
6161 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6162 "stringtie-" version ".tar.gz"))
6165 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6166 (modules '((guix build utils)))
6169 (delete-file-recursively "samtools-0.1.18")
6171 (build-system gnu-build-system)
6173 `(#:tests? #f ;no test suite
6175 (modify-phases %standard-phases
6176 ;; no configure script
6178 (add-before 'build 'use-system-samtools
6180 (substitute* "Makefile"
6181 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6183 (substitute* '("gclib/GBam.h"
6185 (("#include \"(bam|sam|kstring).h\"" _ header)
6186 (string-append "#include <samtools/" header ".h>")))
6188 (add-after 'unpack 'remove-duplicate-typedef
6190 ;; This typedef conflicts with the typedef in
6191 ;; glibc-2.25/include/bits/types.h
6192 (substitute* "gclib/GThreads.h"
6193 (("typedef long long __intmax_t;") ""))
6196 (lambda* (#:key outputs #:allow-other-keys)
6197 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6198 (install-file "stringtie" bin)
6201 `(("samtools" ,samtools-0.1)
6203 (home-page "http://ccb.jhu.edu/software/stringtie/")
6204 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6206 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6207 alignments into potential transcripts. It uses a novel network flow algorithm
6208 as well as an optional de novo assembly step to assemble and quantitate
6209 full-length transcripts representing multiple splice variants for each gene
6210 locus. Its input can include not only the alignments of raw reads used by
6211 other transcript assemblers, but also alignments of longer sequences that have
6212 been assembled from those reads. To identify differentially expressed genes
6213 between experiments, StringTie's output can be processed either by the
6214 Cuffdiff or Ballgown programs.")
6215 (license license:artistic2.0)))
6217 (define-public taxtastic
6223 (uri (pypi-uri "taxtastic" version))
6226 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6227 (build-system python-build-system)
6229 `(#:python ,python-2
6231 (modify-phases %standard-phases
6233 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6235 `(("python-sqlalchemy" ,python2-sqlalchemy)
6236 ("python-decorator" ,python2-decorator)
6237 ("python-biopython" ,python2-biopython)
6238 ("python-pandas" ,python2-pandas)
6239 ("python-psycopg2" ,python2-psycopg2)
6240 ("python-fastalite" ,python2-fastalite)
6241 ("python-pyyaml" ,python2-pyyaml)
6242 ("python-six" ,python2-six)
6243 ("python-jinja2" ,python2-jinja2)
6244 ("python-dendropy" ,python2-dendropy)))
6245 (home-page "https://github.com/fhcrc/taxtastic")
6246 (synopsis "Tools for taxonomic naming and annotation")
6248 "Taxtastic is software written in python used to build and maintain
6249 reference packages i.e. collections of reference trees, reference alignments,
6250 profiles, and associated taxonomic information.")
6251 (license license:gpl3+)))
6253 (define-public vcftools
6260 "https://github.com/vcftools/vcftools/releases/download/v"
6261 version "/vcftools-" version ".tar.gz"))
6264 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6265 (build-system gnu-build-system)
6267 `(#:tests? #f ; no "check" target
6269 "CFLAGS=-O2" ; override "-m64" flag
6270 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6271 (string-append "MANDIR=" (assoc-ref %outputs "out")
6272 "/share/man/man1"))))
6274 `(("pkg-config" ,pkg-config)))
6278 (home-page "https://vcftools.github.io/")
6279 (synopsis "Tools for working with VCF files")
6281 "VCFtools is a program package designed for working with VCF files, such
6282 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6283 provide easily accessible methods for working with complex genetic variation
6284 data in the form of VCF files.")
6285 ;; The license is declared as LGPLv3 in the README and
6286 ;; at https://vcftools.github.io/license.html
6287 (license license:lgpl3)))
6289 (define-public infernal
6295 (uri (string-append "http://eddylab.org/software/infernal/"
6296 "infernal-" version ".tar.gz"))
6299 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6300 (build-system gnu-build-system)
6302 `(("perl" ,perl))) ; for tests
6303 (home-page "http://eddylab.org/infernal/")
6304 (synopsis "Inference of RNA alignments")
6305 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6306 searching DNA sequence databases for RNA structure and sequence similarities.
6307 It is an implementation of a special case of profile stochastic context-free
6308 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6309 profile, but it scores a combination of sequence consensus and RNA secondary
6310 structure consensus, so in many cases, it is more capable of identifying RNA
6311 homologs that conserve their secondary structure more than their primary
6313 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6314 (supported-systems '("i686-linux" "x86_64-linux"))
6315 (license license:bsd-3)))
6317 (define-public r-centipede
6319 (name "r-centipede")
6323 (uri (string-append "http://download.r-forge.r-project.org/"
6324 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6327 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6328 (build-system r-build-system)
6329 (home-page "http://centipede.uchicago.edu/")
6330 (synopsis "Predict transcription factor binding sites")
6332 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6333 of the genome that are bound by particular transcription factors. It starts
6334 by identifying a set of candidate binding sites, and then aims to classify the
6335 sites according to whether each site is bound or not bound by a transcription
6336 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6337 between two different types of motif instances using as much relevant
6338 information as possible.")
6339 (license (list license:gpl2+ license:gpl3+))))
6341 (define-public r-vegan
6348 (uri (cran-uri "vegan" version))
6351 "023xznh0iy0496icpchadmp7a3rk3nj9s48fvwlvp3dssw58yp3c"))))
6352 (build-system r-build-system)
6354 `(("gfortran" ,gfortran)))
6356 `(("r-cluster" ,r-cluster)
6357 ("r-knitr" ,r-knitr) ; needed for vignettes
6358 ("r-lattice" ,r-lattice)
6361 ("r-permute" ,r-permute)))
6362 (home-page "https://cran.r-project.org/web/packages/vegan")
6363 (synopsis "Functions for community ecology")
6365 "The vegan package provides tools for descriptive community ecology. It
6366 has most basic functions of diversity analysis, community ordination and
6367 dissimilarity analysis. Most of its multivariate tools can be used for other
6368 data types as well.")
6369 (license license:gpl2+)))
6371 (define-public r-annotate
6378 (uri (bioconductor-uri "annotate" version))
6381 "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
6382 (build-system r-build-system)
6384 `(("r-annotationdbi" ,r-annotationdbi)
6385 ("r-biobase" ,r-biobase)
6386 ("r-biocgenerics" ,r-biocgenerics)
6388 ("r-rcurl" ,r-rcurl)
6390 ("r-xtable" ,r-xtable)))
6392 "https://bioconductor.org/packages/annotate")
6393 (synopsis "Annotation for microarrays")
6394 (description "This package provides R environments for the annotation of
6396 (license license:artistic2.0)))
6398 (define-public r-copynumber
6400 (name "r-copynumber")
6404 (uri (bioconductor-uri "copynumber" version))
6407 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6408 (build-system r-build-system)
6410 `(("r-s4vectors" ,r-s4vectors)
6411 ("r-iranges" ,r-iranges)
6412 ("r-genomicranges" ,r-genomicranges)
6413 ("r-biocgenerics" ,r-biocgenerics)))
6414 (home-page "https://bioconductor.org/packages/copynumber")
6415 (synopsis "Segmentation of single- and multi-track copy number data")
6417 "This package segments single- and multi-track copy number data by a
6418 penalized least squares regression method.")
6419 (license license:artistic2.0)))
6421 (define-public r-geneplotter
6423 (name "r-geneplotter")
6428 (uri (bioconductor-uri "geneplotter" version))
6431 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6432 (build-system r-build-system)
6434 `(("r-annotate" ,r-annotate)
6435 ("r-annotationdbi" ,r-annotationdbi)
6436 ("r-biobase" ,r-biobase)
6437 ("r-biocgenerics" ,r-biocgenerics)
6438 ("r-lattice" ,r-lattice)
6439 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6440 (home-page "https://bioconductor.org/packages/geneplotter")
6441 (synopsis "Graphics functions for genomic data")
6443 "This package provides functions for plotting genomic data.")
6444 (license license:artistic2.0)))
6446 (define-public r-genefilter
6448 (name "r-genefilter")
6453 (uri (bioconductor-uri "genefilter" version))
6456 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6457 (build-system r-build-system)
6459 `(("gfortran" ,gfortran)))
6461 `(("r-annotate" ,r-annotate)
6462 ("r-annotationdbi" ,r-annotationdbi)
6463 ("r-biobase" ,r-biobase)
6464 ("r-s4vectors" ,r-s4vectors)
6465 ("r-survival" ,r-survival)))
6466 (home-page "https://bioconductor.org/packages/genefilter")
6467 (synopsis "Filter genes from high-throughput experiments")
6469 "This package provides basic functions for filtering genes from
6470 high-throughput sequencing experiments.")
6471 (license license:artistic2.0)))
6473 (define-public r-deseq2
6480 (uri (bioconductor-uri "DESeq2" version))
6483 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6484 (properties `((upstream-name . "DESeq2")))
6485 (build-system r-build-system)
6487 `(("r-biobase" ,r-biobase)
6488 ("r-biocgenerics" ,r-biocgenerics)
6489 ("r-biocparallel" ,r-biocparallel)
6490 ("r-genefilter" ,r-genefilter)
6491 ("r-geneplotter" ,r-geneplotter)
6492 ("r-genomicranges" ,r-genomicranges)
6493 ("r-ggplot2" ,r-ggplot2)
6494 ("r-hmisc" ,r-hmisc)
6495 ("r-iranges" ,r-iranges)
6496 ("r-locfit" ,r-locfit)
6498 ("r-rcpparmadillo" ,r-rcpparmadillo)
6499 ("r-s4vectors" ,r-s4vectors)
6500 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6501 (home-page "https://bioconductor.org/packages/DESeq2")
6502 (synopsis "Differential gene expression analysis")
6504 "This package provides functions to estimate variance-mean dependence in
6505 count data from high-throughput nucleotide sequencing assays and test for
6506 differential expression based on a model using the negative binomial
6508 (license license:lgpl3+)))
6510 (define-public r-dexseq
6517 (uri (bioconductor-uri "DEXSeq" version))
6520 "0g5w9bn2nb3m670hkcsnhfvvkza2318z9irlhhwhb3n8rdzlsdym"))))
6521 (properties `((upstream-name . "DEXSeq")))
6522 (build-system r-build-system)
6524 `(("r-annotationdbi" ,r-annotationdbi)
6525 ("r-biobase" ,r-biobase)
6526 ("r-biocgenerics" ,r-biocgenerics)
6527 ("r-biocparallel" ,r-biocparallel)
6528 ("r-biomart" ,r-biomart)
6529 ("r-deseq2" ,r-deseq2)
6530 ("r-genefilter" ,r-genefilter)
6531 ("r-geneplotter" ,r-geneplotter)
6532 ("r-genomicranges" ,r-genomicranges)
6533 ("r-hwriter" ,r-hwriter)
6534 ("r-iranges" ,r-iranges)
6535 ("r-rcolorbrewer" ,r-rcolorbrewer)
6536 ("r-rsamtools" ,r-rsamtools)
6537 ("r-s4vectors" ,r-s4vectors)
6538 ("r-statmod" ,r-statmod)
6539 ("r-stringr" ,r-stringr)
6540 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6541 (home-page "https://bioconductor.org/packages/DEXSeq")
6542 (synopsis "Inference of differential exon usage in RNA-Seq")
6544 "This package is focused on finding differential exon usage using RNA-seq
6545 exon counts between samples with different experimental designs. It provides
6546 functions that allows the user to make the necessary statistical tests based
6547 on a model that uses the negative binomial distribution to estimate the
6548 variance between biological replicates and generalized linear models for
6549 testing. The package also provides functions for the visualization and
6550 exploration of the results.")
6551 (license license:gpl3+)))
6553 (define-public r-annotationforge
6555 (name "r-annotationforge")
6560 (uri (bioconductor-uri "AnnotationForge" version))
6563 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6565 `((upstream-name . "AnnotationForge")))
6566 (build-system r-build-system)
6568 `(("r-annotationdbi" ,r-annotationdbi)
6569 ("r-biobase" ,r-biobase)
6570 ("r-biocgenerics" ,r-biocgenerics)
6572 ("r-rcurl" ,r-rcurl)
6573 ("r-rsqlite" ,r-rsqlite)
6574 ("r-s4vectors" ,r-s4vectors)
6576 (home-page "https://bioconductor.org/packages/AnnotationForge")
6577 (synopsis "Code for building annotation database packages")
6579 "This package provides code for generating Annotation packages and their
6580 databases. Packages produced are intended to be used with AnnotationDbi.")
6581 (license license:artistic2.0)))
6583 (define-public r-rbgl
6590 (uri (bioconductor-uri "RBGL" version))
6593 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6594 (properties `((upstream-name . "RBGL")))
6595 (build-system r-build-system)
6596 (propagated-inputs `(("r-graph" ,r-graph)))
6597 (home-page "https://www.bioconductor.org/packages/RBGL")
6598 (synopsis "Interface to the Boost graph library")
6600 "This package provides a fairly extensive and comprehensive interface to
6601 the graph algorithms contained in the Boost library.")
6602 (license license:artistic2.0)))
6604 (define-public r-gseabase
6611 (uri (bioconductor-uri "GSEABase" version))
6614 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6615 (properties `((upstream-name . "GSEABase")))
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-graph" ,r-graph)
6624 (home-page "https://bioconductor.org/packages/GSEABase")
6625 (synopsis "Gene set enrichment data structures and methods")
6627 "This package provides classes and methods to support @dfn{Gene Set
6628 Enrichment Analysis} (GSEA).")
6629 (license license:artistic2.0)))
6631 (define-public r-category
6638 (uri (bioconductor-uri "Category" version))
6641 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6642 (properties `((upstream-name . "Category")))
6643 (build-system r-build-system)
6645 `(("r-annotate" ,r-annotate)
6646 ("r-annotationdbi" ,r-annotationdbi)
6647 ("r-biobase" ,r-biobase)
6648 ("r-biocgenerics" ,r-biocgenerics)
6649 ("r-genefilter" ,r-genefilter)
6650 ("r-graph" ,r-graph)
6651 ("r-gseabase" ,r-gseabase)
6652 ("r-matrix" ,r-matrix)
6655 (home-page "https://bioconductor.org/packages/Category")
6656 (synopsis "Category analysis")
6658 "This package provides a collection of tools for performing category
6660 (license license:artistic2.0)))
6662 (define-public r-gostats
6669 (uri (bioconductor-uri "GOstats" version))
6672 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6673 (properties `((upstream-name . "GOstats")))
6674 (build-system r-build-system)
6676 `(("r-annotate" ,r-annotate)
6677 ("r-annotationdbi" ,r-annotationdbi)
6678 ("r-annotationforge" ,r-annotationforge)
6679 ("r-biobase" ,r-biobase)
6680 ("r-category" ,r-category)
6681 ("r-go-db" ,r-go-db)
6682 ("r-graph" ,r-graph)
6683 ("r-rgraphviz" ,r-rgraphviz)
6684 ("r-rbgl" ,r-rbgl)))
6685 (home-page "https://bioconductor.org/packages/GOstats")
6686 (synopsis "Tools for manipulating GO and microarrays")
6688 "This package provides a set of tools for interacting with GO and
6689 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6690 testing and other simple calculations.")
6691 (license license:artistic2.0)))
6693 (define-public r-shortread
6695 (name "r-shortread")
6700 (uri (bioconductor-uri "ShortRead" version))
6703 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6704 (properties `((upstream-name . "ShortRead")))
6705 (build-system r-build-system)
6709 `(("r-biobase" ,r-biobase)
6710 ("r-biocgenerics" ,r-biocgenerics)
6711 ("r-biocparallel" ,r-biocparallel)
6712 ("r-biostrings" ,r-biostrings)
6713 ("r-genomeinfodb" ,r-genomeinfodb)
6714 ("r-genomicalignments" ,r-genomicalignments)
6715 ("r-genomicranges" ,r-genomicranges)
6716 ("r-hwriter" ,r-hwriter)
6717 ("r-iranges" ,r-iranges)
6718 ("r-lattice" ,r-lattice)
6719 ("r-latticeextra" ,r-latticeextra)
6720 ("r-rsamtools" ,r-rsamtools)
6721 ("r-s4vectors" ,r-s4vectors)
6722 ("r-xvector" ,r-xvector)
6723 ("r-zlibbioc" ,r-zlibbioc)))
6724 (home-page "https://bioconductor.org/packages/ShortRead")
6725 (synopsis "FASTQ input and manipulation tools")
6727 "This package implements sampling, iteration, and input of FASTQ files.
6728 It includes functions for filtering and trimming reads, and for generating a
6729 quality assessment report. Data are represented as
6730 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6731 purposes. The package also contains legacy support for early single-end,
6732 ungapped alignment formats.")
6733 (license license:artistic2.0)))
6735 (define-public r-systempiper
6737 (name "r-systempiper")
6742 (uri (bioconductor-uri "systemPipeR" version))
6745 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6746 (properties `((upstream-name . "systemPipeR")))
6747 (build-system r-build-system)
6749 `(("r-annotate" ,r-annotate)
6750 ("r-batchjobs" ,r-batchjobs)
6751 ("r-biocgenerics" ,r-biocgenerics)
6752 ("r-biostrings" ,r-biostrings)
6753 ("r-deseq2" ,r-deseq2)
6754 ("r-edger" ,r-edger)
6755 ("r-genomicfeatures" ,r-genomicfeatures)
6756 ("r-genomicranges" ,r-genomicranges)
6757 ("r-ggplot2" ,r-ggplot2)
6758 ("r-go-db" ,r-go-db)
6759 ("r-gostats" ,r-gostats)
6760 ("r-limma" ,r-limma)
6761 ("r-pheatmap" ,r-pheatmap)
6762 ("r-rjson" ,r-rjson)
6763 ("r-rsamtools" ,r-rsamtools)
6764 ("r-shortread" ,r-shortread)
6765 ("r-summarizedexperiment" ,r-summarizedexperiment)
6766 ("r-variantannotation" ,r-variantannotation)))
6767 (home-page "https://github.com/tgirke/systemPipeR")
6768 (synopsis "Next generation sequencing workflow and reporting environment")
6770 "This R package provides tools for building and running automated
6771 end-to-end analysis workflows for a wide range of @dfn{next generation
6772 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6773 Important features include a uniform workflow interface across different NGS
6774 applications, automated report generation, and support for running both R and
6775 command-line software, such as NGS aligners or peak/variant callers, on local
6776 computers or compute clusters. Efficient handling of complex sample sets and
6777 experimental designs is facilitated by a consistently implemented sample
6778 annotation infrastructure.")
6779 (license license:artistic2.0)))
6781 (define-public r-grohmm
6788 (uri (bioconductor-uri "groHMM" version))
6791 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6792 (properties `((upstream-name . "groHMM")))
6793 (build-system r-build-system)
6795 `(("r-genomeinfodb" ,r-genomeinfodb)
6796 ("r-genomicalignments" ,r-genomicalignments)
6797 ("r-genomicranges" ,r-genomicranges)
6798 ("r-iranges" ,r-iranges)
6800 ("r-rtracklayer" ,r-rtracklayer)
6801 ("r-s4vectors" ,r-s4vectors)))
6802 (home-page "https://github.com/Kraus-Lab/groHMM")
6803 (synopsis "GRO-seq analysis pipeline")
6805 "This package provides a pipeline for the analysis of GRO-seq data.")
6806 (license license:gpl3+)))
6808 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6810 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6814 ;; We cannot use bioconductor-uri here because this tarball is
6815 ;; located under "data/annotation/" instead of "bioc/".
6816 (uri (string-append "https://bioconductor.org/packages/"
6817 "release/data/annotation/src/contrib"
6818 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6822 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6824 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6825 (build-system r-build-system)
6826 ;; As this package provides little more than a very large data file it
6827 ;; doesn't make sense to build substitutes.
6828 (arguments `(#:substitutable? #f))
6830 `(("r-genomicfeatures" ,r-genomicfeatures)))
6832 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6833 (synopsis "Annotation package for human genome in TxDb format")
6835 "This package provides an annotation database of Homo sapiens genome
6836 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6837 track. The database is exposed as a @code{TxDb} object.")
6838 (license license:artistic2.0)))
6840 (define-public r-sparql
6846 (uri (cran-uri "SPARQL" version))
6849 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6850 (properties `((upstream-name . "SPARQL")))
6851 (build-system r-build-system)
6853 `(("r-rcurl" ,r-rcurl)
6855 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6856 (synopsis "SPARQL client for R")
6857 (description "This package provides an interface to use SPARQL to pose
6858 SELECT or UPDATE queries to an end-point.")
6859 ;; The only license indication is found in the DESCRIPTION file,
6860 ;; which states GPL-3. So we cannot assume GPLv3+.
6861 (license license:gpl3)))
6863 (define-public vsearch
6871 (url "https://github.com/torognes/vsearch.git")
6872 (commit (string-append "v" version))))
6873 (file-name (git-file-name name version))
6876 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6877 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6880 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6881 ;; for this in the patch.
6882 (delete-file "src/city.h")
6883 (delete-file "src/citycrc.h")
6884 (delete-file "src/city.cc")
6886 (build-system gnu-build-system)
6890 ("cityhash" ,cityhash)))
6892 `(("autoconf" ,autoconf)
6893 ("automake" ,automake)))
6894 (synopsis "Sequence search tools for metagenomics")
6896 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6897 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6898 masking. The tool takes advantage of parallelism in the form of SIMD
6899 vectorization as well as multiple threads to perform accurate alignments at
6900 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6901 Needleman-Wunsch).")
6902 (home-page "https://github.com/torognes/vsearch")
6903 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6905 (supported-systems '("x86_64-linux"))
6906 ;; Dual licensed; also includes public domain source.
6907 (license (list license:gpl3 license:bsd-2))))
6909 (define-public pardre
6912 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6917 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6921 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6922 (build-system gnu-build-system)
6924 `(#:tests? #f ; no tests included
6926 (modify-phases %standard-phases
6929 (lambda* (#:key outputs #:allow-other-keys)
6930 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6931 (install-file "ParDRe" bin)
6934 `(("openmpi" ,openmpi)
6936 (synopsis "Parallel tool to remove duplicate DNA reads")
6938 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6939 Duplicate reads can be seen as identical or nearly identical sequences with
6940 some mismatches. This tool lets users avoid the analysis of unnecessary
6941 reads, reducing the time of subsequent procedures with the
6942 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6943 in order to exploit the parallel capabilities of multicore clusters. It is
6944 faster than multithreaded counterparts (end of 2015) for the same number of
6945 cores and, thanks to the message-passing technology, it can be executed on
6947 (home-page "https://sourceforge.net/projects/pardre/")
6948 (license license:gpl3+)))
6950 (define-public ruby-bio-kseq
6952 (name "ruby-bio-kseq")
6957 (uri (rubygems-uri "bio-kseq" version))
6960 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6961 (build-system ruby-build-system)
6963 `(#:test-target "spec"))
6965 `(("bundler" ,bundler)
6966 ("ruby-rspec" ,ruby-rspec)
6967 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6970 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6972 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6973 FASTQ parsing code. It provides a fast iterator over sequences and their
6975 (home-page "https://github.com/gusevfe/bio-kseq")
6976 (license license:expat)))
6978 (define-public bio-locus
6985 (uri (rubygems-uri "bio-locus" version))
6988 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6989 (build-system ruby-build-system)
6991 `(("ruby-rspec" ,ruby-rspec)))
6992 (synopsis "Tool for fast querying of genome locations")
6994 "Bio-locus is a tabix-like tool for fast querying of genome
6995 locations. Many file formats in bioinformatics contain records that
6996 start with a chromosome name and a position for a SNP, or a start-end
6997 position for indels. Bio-locus allows users to store this chr+pos or
6998 chr+pos+alt information in a database.")
6999 (home-page "https://github.com/pjotrp/bio-locus")
7000 (license license:expat)))
7002 (define-public bio-blastxmlparser
7004 (name "bio-blastxmlparser")
7008 (uri (rubygems-uri "bio-blastxmlparser" version))
7011 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7012 (build-system ruby-build-system)
7014 `(("ruby-bio-logger" ,ruby-bio-logger)
7015 ("ruby-nokogiri" ,ruby-nokogiri)))
7017 `(("ruby-rspec" ,ruby-rspec)))
7018 (synopsis "Fast big data BLAST XML parser and library")
7020 "Very fast parallel big-data BLAST XML file parser which can be used as
7021 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7022 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7023 (home-page "https://github.com/pjotrp/blastxmlparser")
7024 (license license:expat)))
7026 (define-public bioruby
7033 (uri (rubygems-uri "bio" version))
7036 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7037 (build-system ruby-build-system)
7039 `(("ruby-libxml" ,ruby-libxml)))
7041 `(("which" ,which))) ; required for test phase
7044 (modify-phases %standard-phases
7045 (add-before 'build 'patch-test-command
7047 (substitute* '("test/functional/bio/test_command.rb")
7048 (("/bin/sh") (which "sh")))
7049 (substitute* '("test/functional/bio/test_command.rb")
7050 (("/bin/ls") (which "ls")))
7051 (substitute* '("test/functional/bio/test_command.rb")
7052 (("which") (which "which")))
7053 (substitute* '("test/functional/bio/test_command.rb",
7054 "test/data/command/echoarg2.sh")
7055 (("/bin/echo") (which "echo")))
7057 (synopsis "Ruby library, shell and utilities for bioinformatics")
7058 (description "BioRuby comes with a comprehensive set of Ruby development
7059 tools and libraries for bioinformatics and molecular biology. BioRuby has
7060 components for sequence analysis, pathway analysis, protein modelling and
7061 phylogenetic analysis; it supports many widely used data formats and provides
7062 easy access to databases, external programs and public web services, including
7063 BLAST, KEGG, GenBank, MEDLINE and GO.")
7064 (home-page "http://bioruby.org/")
7065 ;; Code is released under Ruby license, except for setup
7066 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7067 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7069 (define-public r-acsnminer
7071 (name "r-acsnminer")
7072 (version "0.16.8.25")
7075 (uri (cran-uri "ACSNMineR" version))
7078 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7079 (properties `((upstream-name . "ACSNMineR")))
7080 (build-system r-build-system)
7082 `(("r-ggplot2" ,r-ggplot2)
7083 ("r-gridextra" ,r-gridextra)))
7084 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7085 (synopsis "Gene enrichment analysis")
7087 "This package provides tools to compute and represent gene set enrichment
7088 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7089 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7090 enrichment can be run with hypergeometric test or Fisher exact test, and can
7091 use multiple corrections. Visualization of data can be done either by
7092 barplots or heatmaps.")
7093 (license license:gpl2+)))
7095 (define-public r-biocgenerics
7097 (name "r-biocgenerics")
7101 (uri (bioconductor-uri "BiocGenerics" version))
7104 "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
7106 `((upstream-name . "BiocGenerics")))
7107 (build-system r-build-system)
7108 (home-page "https://bioconductor.org/packages/BiocGenerics")
7109 (synopsis "S4 generic functions for Bioconductor")
7111 "This package provides S4 generic functions needed by many Bioconductor
7113 (license license:artistic2.0)))
7115 (define-public r-biocinstaller
7117 (name "r-biocinstaller")
7121 (uri (bioconductor-uri "BiocInstaller" version))
7124 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7126 `((upstream-name . "BiocInstaller")))
7127 (build-system r-build-system)
7128 (home-page "https://bioconductor.org/packages/BiocInstaller")
7129 (synopsis "Install Bioconductor packages")
7130 (description "This package is used to install and update R packages from
7131 Bioconductor, CRAN, and Github.")
7132 (license license:artistic2.0)))
7134 (define-public r-biocviews
7136 (name "r-biocviews")
7140 (uri (bioconductor-uri "biocViews" version))
7143 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
7145 `((upstream-name . "biocViews")))
7146 (build-system r-build-system)
7148 `(("r-biobase" ,r-biobase)
7149 ("r-graph" ,r-graph)
7151 ("r-rcurl" ,r-rcurl)
7153 ("r-runit" ,r-runit)))
7154 (home-page "https://bioconductor.org/packages/biocViews")
7155 (synopsis "Bioconductor package categorization helper")
7156 (description "The purpose of biocViews is to create HTML pages that
7157 categorize packages in a Bioconductor package repository according to keywords,
7158 also known as views, in a controlled vocabulary.")
7159 (license license:artistic2.0)))
7161 (define-public r-bookdown
7167 (uri (cran-uri "bookdown" version))
7170 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7171 (build-system r-build-system)
7173 `(("r-htmltools" ,r-htmltools)
7174 ("r-knitr" ,r-knitr)
7175 ("r-rmarkdown" ,r-rmarkdown)
7176 ("r-tinytex" ,r-tinytex)
7178 ("r-xfun" ,r-xfun)))
7179 (home-page "https://github.com/rstudio/bookdown")
7180 (synopsis "Authoring books and technical documents with R markdown")
7181 (description "This package provides output formats and utilities for
7182 authoring books and technical documents with R Markdown.")
7183 (license license:gpl3)))
7185 (define-public r-biocstyle
7187 (name "r-biocstyle")
7191 (uri (bioconductor-uri "BiocStyle" version))
7194 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7196 `((upstream-name . "BiocStyle")))
7197 (build-system r-build-system)
7199 `(("r-biocmanager" ,r-biocmanager)
7200 ("r-bookdown" ,r-bookdown)
7201 ("r-knitr" ,r-knitr)
7202 ("r-rmarkdown" ,r-rmarkdown)
7203 ("r-yaml" ,r-yaml)))
7204 (home-page "https://bioconductor.org/packages/BiocStyle")
7205 (synopsis "Bioconductor formatting styles")
7206 (description "This package provides standard formatting styles for
7207 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7209 (license license:artistic2.0)))
7211 (define-public r-bioccheck
7213 (name "r-bioccheck")
7217 (uri (bioconductor-uri "BiocCheck" version))
7220 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7222 `((upstream-name . "BiocCheck")))
7223 (build-system r-build-system)
7226 (modify-phases %standard-phases
7227 ;; This package can be used by calling BiocCheck(<package>) from
7228 ;; within R, or by running R CMD BiocCheck <package>. This phase
7229 ;; makes sure the latter works. For this to work, the BiocCheck
7230 ;; script must be somewhere on the PATH (not the R bin directory).
7231 (add-after 'install 'install-bioccheck-subcommand
7232 (lambda* (#:key outputs #:allow-other-keys)
7233 (let* ((out (assoc-ref outputs "out"))
7234 (dest-dir (string-append out "/bin"))
7236 (string-append out "/site-library/BiocCheck/script/")))
7238 (symlink (string-append script-dir "/checkBadDeps.R")
7239 (string-append dest-dir "/checkBadDeps.R"))
7240 (symlink (string-append script-dir "/BiocCheck")
7241 (string-append dest-dir "/BiocCheck")))
7244 `(("r-codetools" ,r-codetools)
7245 ("r-graph" ,r-graph)
7247 ("r-knitr" ,r-knitr)
7248 ("r-optparse" ,r-optparse)
7249 ("r-biocmanager" ,r-biocmanager)
7250 ("r-biocviews" ,r-biocviews)
7251 ("r-stringdist" ,r-stringdist)))
7252 (home-page "https://bioconductor.org/packages/BiocCheck")
7253 (synopsis "Executes Bioconductor-specific package checks")
7254 (description "This package contains tools to perform additional quality
7255 checks on R packages that are to be submitted to the Bioconductor repository.")
7256 (license license:artistic2.0)))
7258 (define-public r-optparse
7265 (uri (cran-uri "optparse" version))
7268 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7269 (build-system r-build-system)
7271 `(("r-getopt" ,r-getopt)))
7273 "https://github.com/trevorld/optparse")
7274 (synopsis "Command line option parser")
7276 "This package provides a command line parser inspired by Python's
7277 @code{optparse} library to be used with Rscript to write shebang scripts
7278 that accept short and long options.")
7279 (license license:gpl2+)))
7281 (define-public r-dnacopy
7287 (uri (bioconductor-uri "DNAcopy" version))
7290 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7292 `((upstream-name . "DNAcopy")))
7293 (build-system r-build-system)
7295 `(("gfortran" ,gfortran)))
7296 (home-page "https://bioconductor.org/packages/DNAcopy")
7297 (synopsis "Implementation of a circular binary segmentation algorithm")
7298 (description "This package implements the circular binary segmentation (CBS)
7299 algorithm to segment DNA copy number data and identify genomic regions with
7300 abnormal copy number.")
7301 (license license:gpl2+)))
7303 (define-public r-s4vectors
7305 (name "r-s4vectors")
7309 (uri (bioconductor-uri "S4Vectors" version))
7312 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7314 `((upstream-name . "S4Vectors")))
7315 (build-system r-build-system)
7317 `(("r-biocgenerics" ,r-biocgenerics)))
7318 (home-page "https://bioconductor.org/packages/S4Vectors")
7319 (synopsis "S4 implementation of vectors and lists")
7321 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7322 classes and a set of generic functions that extend the semantic of ordinary
7323 vectors and lists in R. Package developers can easily implement vector-like
7324 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7325 In addition, a few low-level concrete subclasses of general interest (e.g.
7326 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7327 S4Vectors package itself.")
7328 (license license:artistic2.0)))
7330 (define-public r-seqinr
7337 (uri (cran-uri "seqinr" version))
7340 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7341 (build-system r-build-system)
7343 `(("r-ade4" ,r-ade4)
7344 ("r-segmented" ,r-segmented)))
7347 (home-page "http://seqinr.r-forge.r-project.org/")
7348 (synopsis "Biological sequences retrieval and analysis")
7350 "This package provides tools for exploratory data analysis and data
7351 visualization of biological sequence (DNA and protein) data. It also includes
7352 utilities for sequence data management under the ACNUC system.")
7353 (license license:gpl2+)))
7355 (define-public r-iranges
7361 (uri (bioconductor-uri "IRanges" version))
7364 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7366 `((upstream-name . "IRanges")))
7367 (build-system r-build-system)
7369 `(("r-biocgenerics" ,r-biocgenerics)
7370 ("r-s4vectors" ,r-s4vectors)))
7371 (home-page "https://bioconductor.org/packages/IRanges")
7372 (synopsis "Infrastructure for manipulating intervals on sequences")
7374 "This package provides efficient low-level and highly reusable S4 classes
7375 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7376 generally, data that can be organized sequentially (formally defined as
7377 @code{Vector} objects), as well as views on these @code{Vector} objects.
7378 Efficient list-like classes are also provided for storing big collections of
7379 instances of the basic classes. All classes in the package use consistent
7380 naming and share the same rich and consistent \"Vector API\" as much as
7382 (license license:artistic2.0)))
7384 (define-public r-genomeinfodbdata
7386 (name "r-genomeinfodbdata")
7390 ;; We cannot use bioconductor-uri here because this tarball is
7391 ;; located under "data/annotation/" instead of "bioc/".
7392 (uri (string-append "https://bioconductor.org/packages/release/"
7393 "data/annotation/src/contrib/GenomeInfoDbData_"
7397 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7399 `((upstream-name . "GenomeInfoDbData")))
7400 (build-system r-build-system)
7401 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7402 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7403 (description "This package contains data for mapping between NCBI taxonomy
7404 ID and species. It is used by functions in the GenomeInfoDb package.")
7405 (license license:artistic2.0)))
7407 (define-public r-genomeinfodb
7409 (name "r-genomeinfodb")
7413 (uri (bioconductor-uri "GenomeInfoDb" version))
7416 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7418 `((upstream-name . "GenomeInfoDb")))
7419 (build-system r-build-system)
7421 `(("r-biocgenerics" ,r-biocgenerics)
7422 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7423 ("r-iranges" ,r-iranges)
7424 ("r-rcurl" ,r-rcurl)
7425 ("r-s4vectors" ,r-s4vectors)))
7426 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7427 (synopsis "Utilities for manipulating chromosome identifiers")
7429 "This package contains data and functions that define and allow
7430 translation between different chromosome sequence naming conventions (e.g.,
7431 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7432 names in their natural, rather than lexicographic, order.")
7433 (license license:artistic2.0)))
7435 (define-public r-edger
7441 (uri (bioconductor-uri "edgeR" version))
7444 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7445 (properties `((upstream-name . "edgeR")))
7446 (build-system r-build-system)
7448 `(("r-limma" ,r-limma)
7449 ("r-locfit" ,r-locfit)
7451 ("r-statmod" ,r-statmod))) ;for estimateDisp
7452 (home-page "http://bioinf.wehi.edu.au/edgeR")
7453 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7454 (description "This package can do differential expression analysis of
7455 RNA-seq expression profiles with biological replication. It implements a range
7456 of statistical methodology based on the negative binomial distributions,
7457 including empirical Bayes estimation, exact tests, generalized linear models
7458 and quasi-likelihood tests. It be applied to differential signal analysis of
7459 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7461 (license license:gpl2+)))
7463 (define-public r-variantannotation
7465 (name "r-variantannotation")
7469 (uri (bioconductor-uri "VariantAnnotation" version))
7472 "0gf36lr9xy3zmcc4rxs5bi2ccrrc7b6wqp6p3cvnclgif4i0l66k"))))
7474 `((upstream-name . "VariantAnnotation")))
7478 `(("r-annotationdbi" ,r-annotationdbi)
7479 ("r-biobase" ,r-biobase)
7480 ("r-biocgenerics" ,r-biocgenerics)
7481 ("r-biostrings" ,r-biostrings)
7482 ("r-bsgenome" ,r-bsgenome)
7484 ("r-genomeinfodb" ,r-genomeinfodb)
7485 ("r-genomicfeatures" ,r-genomicfeatures)
7486 ("r-genomicranges" ,r-genomicranges)
7487 ("r-iranges" ,r-iranges)
7488 ("r-summarizedexperiment" ,r-summarizedexperiment)
7489 ("r-rsamtools" ,r-rsamtools)
7490 ("r-rtracklayer" ,r-rtracklayer)
7491 ("r-s4vectors" ,r-s4vectors)
7492 ("r-xvector" ,r-xvector)
7493 ("r-zlibbioc" ,r-zlibbioc)))
7494 (build-system r-build-system)
7495 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7496 (synopsis "Package for annotation of genetic variants")
7497 (description "This R package can annotate variants, compute amino acid
7498 coding changes and predict coding outcomes.")
7499 (license license:artistic2.0)))
7501 (define-public r-limma
7507 (uri (bioconductor-uri "limma" version))
7510 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7511 (build-system r-build-system)
7512 (home-page "http://bioinf.wehi.edu.au/limma")
7513 (synopsis "Package for linear models for microarray and RNA-seq data")
7514 (description "This package can be used for the analysis of gene expression
7515 studies, especially the use of linear models for analysing designed experiments
7516 and the assessment of differential expression. The analysis methods apply to
7517 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7518 (license license:gpl2+)))
7520 (define-public r-xvector
7526 (uri (bioconductor-uri "XVector" version))
7529 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7531 `((upstream-name . "XVector")))
7532 (build-system r-build-system)
7535 (modify-phases %standard-phases
7536 (add-after 'unpack 'use-system-zlib
7538 (substitute* "DESCRIPTION"
7539 (("zlibbioc, ") ""))
7540 (substitute* "NAMESPACE"
7541 (("import\\(zlibbioc\\)") ""))
7546 `(("r-biocgenerics" ,r-biocgenerics)
7547 ("r-iranges" ,r-iranges)
7548 ("r-s4vectors" ,r-s4vectors)))
7549 (home-page "https://bioconductor.org/packages/XVector")
7550 (synopsis "Representation and manpulation of external sequences")
7552 "This package provides memory efficient S4 classes for storing sequences
7553 \"externally\" (behind an R external pointer, or on disk).")
7554 (license license:artistic2.0)))
7556 (define-public r-genomicranges
7558 (name "r-genomicranges")
7562 (uri (bioconductor-uri "GenomicRanges" version))
7565 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7567 `((upstream-name . "GenomicRanges")))
7568 (build-system r-build-system)
7570 `(("r-biocgenerics" ,r-biocgenerics)
7571 ("r-genomeinfodb" ,r-genomeinfodb)
7572 ("r-iranges" ,r-iranges)
7573 ("r-s4vectors" ,r-s4vectors)
7574 ("r-xvector" ,r-xvector)))
7575 (home-page "https://bioconductor.org/packages/GenomicRanges")
7576 (synopsis "Representation and manipulation of genomic intervals")
7578 "This package provides tools to efficiently represent and manipulate
7579 genomic annotations and alignments is playing a central role when it comes to
7580 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7581 GenomicRanges package defines general purpose containers for storing and
7582 manipulating genomic intervals and variables defined along a genome.")
7583 (license license:artistic2.0)))
7585 (define-public r-biobase
7591 (uri (bioconductor-uri "Biobase" version))
7594 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7596 `((upstream-name . "Biobase")))
7597 (build-system r-build-system)
7599 `(("r-biocgenerics" ,r-biocgenerics)))
7600 (home-page "https://bioconductor.org/packages/Biobase")
7601 (synopsis "Base functions for Bioconductor")
7603 "This package provides functions that are needed by many other packages
7604 on Bioconductor or which replace R functions.")
7605 (license license:artistic2.0)))
7607 (define-public r-annotationdbi
7609 (name "r-annotationdbi")
7613 (uri (bioconductor-uri "AnnotationDbi" version))
7616 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7618 `((upstream-name . "AnnotationDbi")))
7619 (build-system r-build-system)
7621 `(("r-biobase" ,r-biobase)
7622 ("r-biocgenerics" ,r-biocgenerics)
7624 ("r-iranges" ,r-iranges)
7625 ("r-rsqlite" ,r-rsqlite)
7626 ("r-s4vectors" ,r-s4vectors)))
7627 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7628 (synopsis "Annotation database interface")
7630 "This package provides user interface and database connection code for
7631 annotation data packages using SQLite data storage.")
7632 (license license:artistic2.0)))
7634 (define-public r-biomart
7640 (uri (bioconductor-uri "biomaRt" version))
7643 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7645 `((upstream-name . "biomaRt")))
7646 (build-system r-build-system)
7648 `(("r-annotationdbi" ,r-annotationdbi)
7650 ("r-progress" ,r-progress)
7651 ("r-rcurl" ,r-rcurl)
7652 ("r-stringr" ,r-stringr)
7654 (home-page "https://bioconductor.org/packages/biomaRt")
7655 (synopsis "Interface to BioMart databases")
7657 "biomaRt provides an interface to a growing collection of databases
7658 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7659 package enables retrieval of large amounts of data in a uniform way without
7660 the need to know the underlying database schemas or write complex SQL queries.
7661 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7662 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7663 users direct access to a diverse set of data and enable a wide range of
7664 powerful online queries from gene annotation to database mining.")
7665 (license license:artistic2.0)))
7667 (define-public r-biocparallel
7669 (name "r-biocparallel")
7673 (uri (bioconductor-uri "BiocParallel" version))
7676 "1164dk0fajb2vrkfpcjs11055qf1cs4vvbnq0aqdaaf2p4lyx41l"))))
7678 `((upstream-name . "BiocParallel")))
7679 (build-system r-build-system)
7681 `(("r-futile-logger" ,r-futile-logger)
7684 (home-page "https://bioconductor.org/packages/BiocParallel")
7685 (synopsis "Bioconductor facilities for parallel evaluation")
7687 "This package provides modified versions and novel implementation of
7688 functions for parallel evaluation, tailored to use with Bioconductor
7690 (license (list license:gpl2+ license:gpl3+))))
7692 (define-public r-biostrings
7694 (name "r-biostrings")
7698 (uri (bioconductor-uri "Biostrings" version))
7701 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7703 `((upstream-name . "Biostrings")))
7704 (build-system r-build-system)
7706 `(("r-biocgenerics" ,r-biocgenerics)
7707 ("r-iranges" ,r-iranges)
7708 ("r-s4vectors" ,r-s4vectors)
7709 ("r-xvector" ,r-xvector)))
7710 (home-page "https://bioconductor.org/packages/Biostrings")
7711 (synopsis "String objects and algorithms for biological sequences")
7713 "This package provides memory efficient string containers, string
7714 matching algorithms, and other utilities, for fast manipulation of large
7715 biological sequences or sets of sequences.")
7716 (license license:artistic2.0)))
7718 (define-public r-rsamtools
7720 (name "r-rsamtools")
7724 (uri (bioconductor-uri "Rsamtools" version))
7727 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7729 `((upstream-name . "Rsamtools")))
7730 (build-system r-build-system)
7733 (modify-phases %standard-phases
7734 (add-after 'unpack 'use-system-zlib
7736 (substitute* "DESCRIPTION"
7737 (("zlibbioc, ") ""))
7738 (substitute* "NAMESPACE"
7739 (("import\\(zlibbioc\\)") ""))
7744 `(("r-biocgenerics" ,r-biocgenerics)
7745 ("r-biocparallel" ,r-biocparallel)
7746 ("r-biostrings" ,r-biostrings)
7747 ("r-bitops" ,r-bitops)
7748 ("r-genomeinfodb" ,r-genomeinfodb)
7749 ("r-genomicranges" ,r-genomicranges)
7750 ("r-iranges" ,r-iranges)
7751 ("r-s4vectors" ,r-s4vectors)
7752 ("r-xvector" ,r-xvector)))
7753 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7754 (synopsis "Interface to samtools, bcftools, and tabix")
7756 "This package provides an interface to the 'samtools', 'bcftools', and
7757 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7758 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7760 (license license:expat)))
7762 (define-public r-delayedarray
7764 (name "r-delayedarray")
7768 (uri (bioconductor-uri "DelayedArray" version))
7771 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7773 `((upstream-name . "DelayedArray")))
7774 (build-system r-build-system)
7776 `(("r-biocgenerics" ,r-biocgenerics)
7777 ("r-biocparallel" ,r-biocparallel)
7778 ("r-s4vectors" ,r-s4vectors)
7779 ("r-iranges" ,r-iranges)
7780 ("r-matrixstats" ,r-matrixstats)))
7781 (home-page "https://bioconductor.org/packages/DelayedArray")
7782 (synopsis "Delayed operations on array-like objects")
7784 "Wrapping an array-like object (typically an on-disk object) in a
7785 @code{DelayedArray} object allows one to perform common array operations on it
7786 without loading the object in memory. In order to reduce memory usage and
7787 optimize performance, operations on the object are either delayed or executed
7788 using a block processing mechanism. Note that this also works on in-memory
7789 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7790 @code{Matrix} objects, and ordinary arrays and data frames.")
7791 (license license:artistic2.0)))
7793 (define-public r-summarizedexperiment
7795 (name "r-summarizedexperiment")
7799 (uri (bioconductor-uri "SummarizedExperiment" version))
7802 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7804 `((upstream-name . "SummarizedExperiment")))
7805 (build-system r-build-system)
7807 `(("r-biobase" ,r-biobase)
7808 ("r-biocgenerics" ,r-biocgenerics)
7809 ("r-delayedarray" ,r-delayedarray)
7810 ("r-genomeinfodb" ,r-genomeinfodb)
7811 ("r-genomicranges" ,r-genomicranges)
7812 ("r-iranges" ,r-iranges)
7813 ("r-matrix" ,r-matrix)
7814 ("r-s4vectors" ,r-s4vectors)))
7815 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7816 (synopsis "Container for representing genomic ranges by sample")
7818 "The SummarizedExperiment container contains one or more assays, each
7819 represented by a matrix-like object of numeric or other mode. The rows
7820 typically represent genomic ranges of interest and the columns represent
7822 (license license:artistic2.0)))
7824 (define-public r-genomicalignments
7826 (name "r-genomicalignments")
7830 (uri (bioconductor-uri "GenomicAlignments" version))
7833 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7835 `((upstream-name . "GenomicAlignments")))
7836 (build-system r-build-system)
7838 `(("r-biocgenerics" ,r-biocgenerics)
7839 ("r-biocparallel" ,r-biocparallel)
7840 ("r-biostrings" ,r-biostrings)
7841 ("r-genomeinfodb" ,r-genomeinfodb)
7842 ("r-genomicranges" ,r-genomicranges)
7843 ("r-iranges" ,r-iranges)
7844 ("r-rsamtools" ,r-rsamtools)
7845 ("r-s4vectors" ,r-s4vectors)
7846 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7847 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7848 (synopsis "Representation and manipulation of short genomic alignments")
7850 "This package provides efficient containers for storing and manipulating
7851 short genomic alignments (typically obtained by aligning short reads to a
7852 reference genome). This includes read counting, computing the coverage,
7853 junction detection, and working with the nucleotide content of the
7855 (license license:artistic2.0)))
7857 (define-public r-rtracklayer
7859 (name "r-rtracklayer")
7863 (uri (bioconductor-uri "rtracklayer" version))
7866 "0a4mhd926w9slkfil5xgngjsfdj024a4w57w2bm3d4r0pj8y5da7"))))
7867 (build-system r-build-system)
7870 (modify-phases %standard-phases
7871 (add-after 'unpack 'use-system-zlib
7873 (substitute* "DESCRIPTION"
7874 ((" zlibbioc,") ""))
7875 (substitute* "NAMESPACE"
7876 (("import\\(zlibbioc\\)") ""))
7879 `(("pkg-config" ,pkg-config)))
7883 `(("r-biocgenerics" ,r-biocgenerics)
7884 ("r-biostrings" ,r-biostrings)
7885 ("r-genomeinfodb" ,r-genomeinfodb)
7886 ("r-genomicalignments" ,r-genomicalignments)
7887 ("r-genomicranges" ,r-genomicranges)
7888 ("r-iranges" ,r-iranges)
7889 ("r-rcurl" ,r-rcurl)
7890 ("r-rsamtools" ,r-rsamtools)
7891 ("r-s4vectors" ,r-s4vectors)
7893 ("r-xvector" ,r-xvector)))
7894 (home-page "https://bioconductor.org/packages/rtracklayer")
7895 (synopsis "R interface to genome browsers and their annotation tracks")
7897 "rtracklayer is an extensible framework for interacting with multiple
7898 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7899 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7900 built-in). The user may export/import tracks to/from the supported browsers,
7901 as well as query and modify the browser state, such as the current viewport.")
7902 (license license:artistic2.0)))
7904 (define-public r-genomicfeatures
7906 (name "r-genomicfeatures")
7910 (uri (bioconductor-uri "GenomicFeatures" version))
7913 "0slq6hv5bmc3bgrl824jzmr6db3fvaj6b7ihwmdn76pgqqbq2fq6"))))
7915 `((upstream-name . "GenomicFeatures")))
7916 (build-system r-build-system)
7918 `(("r-annotationdbi" ,r-annotationdbi)
7919 ("r-biobase" ,r-biobase)
7920 ("r-biocgenerics" ,r-biocgenerics)
7921 ("r-biomart" ,r-biomart)
7922 ("r-biostrings" ,r-biostrings)
7924 ("r-genomeinfodb" ,r-genomeinfodb)
7925 ("r-genomicranges" ,r-genomicranges)
7926 ("r-iranges" ,r-iranges)
7927 ("r-rcurl" ,r-rcurl)
7928 ("r-rsqlite" ,r-rsqlite)
7929 ("r-rtracklayer" ,r-rtracklayer)
7930 ("r-s4vectors" ,r-s4vectors)
7931 ("r-xvector" ,r-xvector)))
7932 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7933 (synopsis "Tools for working with transcript centric annotations")
7935 "This package provides a set of tools and methods for making and
7936 manipulating transcript centric annotations. With these tools the user can
7937 easily download the genomic locations of the transcripts, exons and cds of a
7938 given organism, from either the UCSC Genome Browser or a BioMart
7939 database (more sources will be supported in the future). This information is
7940 then stored in a local database that keeps track of the relationship between
7941 transcripts, exons, cds and genes. Flexible methods are provided for
7942 extracting the desired features in a convenient format.")
7943 (license license:artistic2.0)))
7945 (define-public r-go-db
7951 (uri (string-append "https://www.bioconductor.org/packages/"
7952 "release/data/annotation/src/contrib/GO.db_"
7956 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7958 `((upstream-name . "GO.db")))
7959 (build-system r-build-system)
7961 `(("r-annotationdbi" ,r-annotationdbi)))
7962 (home-page "https://bioconductor.org/packages/GO.db")
7963 (synopsis "Annotation maps describing the entire Gene Ontology")
7965 "The purpose of this GO.db annotation package is to provide detailed
7966 information about the latest version of the Gene Ontologies.")
7967 (license license:artistic2.0)))
7969 (define-public r-topgo
7975 (uri (bioconductor-uri "topGO" version))
7978 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7980 `((upstream-name . "topGO")))
7981 (build-system r-build-system)
7983 `(("r-annotationdbi" ,r-annotationdbi)
7985 ("r-biobase" ,r-biobase)
7986 ("r-biocgenerics" ,r-biocgenerics)
7987 ("r-go-db" ,r-go-db)
7988 ("r-graph" ,r-graph)
7989 ("r-lattice" ,r-lattice)
7990 ("r-matrixstats" ,r-matrixstats)
7991 ("r-sparsem" ,r-sparsem)))
7992 (home-page "https://bioconductor.org/packages/topGO")
7993 (synopsis "Enrichment analysis for gene ontology")
7995 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7996 terms while accounting for the topology of the GO graph. Different test
7997 statistics and different methods for eliminating local similarities and
7998 dependencies between GO terms can be implemented and applied.")
7999 ;; Any version of the LGPL applies.
8000 (license license:lgpl2.1+)))
8002 (define-public r-bsgenome
8008 (uri (bioconductor-uri "BSgenome" version))
8011 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
8013 `((upstream-name . "BSgenome")))
8014 (build-system r-build-system)
8016 `(("r-biocgenerics" ,r-biocgenerics)
8017 ("r-biostrings" ,r-biostrings)
8018 ("r-genomeinfodb" ,r-genomeinfodb)
8019 ("r-genomicranges" ,r-genomicranges)
8020 ("r-iranges" ,r-iranges)
8021 ("r-rsamtools" ,r-rsamtools)
8022 ("r-rtracklayer" ,r-rtracklayer)
8023 ("r-s4vectors" ,r-s4vectors)
8024 ("r-xvector" ,r-xvector)))
8025 (home-page "https://bioconductor.org/packages/BSgenome")
8026 (synopsis "Infrastructure for Biostrings-based genome data packages")
8028 "This package provides infrastructure shared by all Biostrings-based
8029 genome data packages and support for efficient SNP representation.")
8030 (license license:artistic2.0)))
8032 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
8034 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
8038 ;; We cannot use bioconductor-uri here because this tarball is
8039 ;; located under "data/annotation/" instead of "bioc/".
8040 (uri (string-append "https://www.bioconductor.org/packages/"
8041 "release/data/annotation/src/contrib/"
8042 "BSgenome.Hsapiens.1000genomes.hs37d5_"
8046 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
8048 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
8049 (build-system r-build-system)
8050 ;; As this package provides little more than a very large data file it
8051 ;; doesn't make sense to build substitutes.
8052 (arguments `(#:substitutable? #f))
8054 `(("r-bsgenome" ,r-bsgenome)))
8056 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
8057 (synopsis "Full genome sequences for Homo sapiens")
8059 "This package provides full genome sequences for Homo sapiens from
8060 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
8061 (license license:artistic2.0)))
8063 (define-public r-impute
8069 (uri (bioconductor-uri "impute" version))
8072 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8074 `(("gfortran" ,gfortran)))
8075 (build-system r-build-system)
8076 (home-page "https://bioconductor.org/packages/impute")
8077 (synopsis "Imputation for microarray data")
8079 "This package provides a function to impute missing gene expression
8080 microarray data, using nearest neighbor averaging.")
8081 (license license:gpl2+)))
8083 (define-public r-seqpattern
8085 (name "r-seqpattern")
8089 (uri (bioconductor-uri "seqPattern" version))
8092 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8094 `((upstream-name . "seqPattern")))
8095 (build-system r-build-system)
8097 `(("r-biostrings" ,r-biostrings)
8098 ("r-genomicranges" ,r-genomicranges)
8099 ("r-iranges" ,r-iranges)
8100 ("r-kernsmooth" ,r-kernsmooth)
8101 ("r-plotrix" ,r-plotrix)))
8102 (home-page "https://bioconductor.org/packages/seqPattern")
8103 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8105 "This package provides tools to visualize oligonucleotide patterns and
8106 sequence motif occurrences across a large set of sequences centred at a common
8107 reference point and sorted by a user defined feature.")
8108 (license license:gpl3+)))
8110 (define-public r-genomation
8112 (name "r-genomation")
8116 (uri (bioconductor-uri "genomation" version))
8119 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8120 (build-system r-build-system)
8122 `(("r-biostrings" ,r-biostrings)
8123 ("r-bsgenome" ,r-bsgenome)
8124 ("r-data-table" ,r-data-table)
8125 ("r-genomeinfodb" ,r-genomeinfodb)
8126 ("r-genomicalignments" ,r-genomicalignments)
8127 ("r-genomicranges" ,r-genomicranges)
8128 ("r-ggplot2" ,r-ggplot2)
8129 ("r-gridbase" ,r-gridbase)
8130 ("r-impute" ,r-impute)
8131 ("r-iranges" ,r-iranges)
8132 ("r-matrixstats" ,r-matrixstats)
8133 ("r-plotrix" ,r-plotrix)
8136 ("r-readr" ,r-readr)
8137 ("r-reshape2" ,r-reshape2)
8138 ("r-rsamtools" ,r-rsamtools)
8139 ("r-rtracklayer" ,r-rtracklayer)
8140 ("r-runit" ,r-runit)
8141 ("r-s4vectors" ,r-s4vectors)
8142 ("r-seqpattern" ,r-seqpattern)))
8143 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8144 (synopsis "Summary, annotation and visualization of genomic data")
8146 "This package provides a package for summary and annotation of genomic
8147 intervals. Users can visualize and quantify genomic intervals over
8148 pre-defined functional regions, such as promoters, exons, introns, etc. The
8149 genomic intervals represent regions with a defined chromosome position, which
8150 may be associated with a score, such as aligned reads from HT-seq experiments,
8151 TF binding sites, methylation scores, etc. The package can use any tabular
8152 genomic feature data as long as it has minimal information on the locations of
8153 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8154 (license license:artistic2.0)))
8156 (define-public r-genomationdata
8158 (name "r-genomationdata")
8162 ;; We cannot use bioconductor-uri here because this tarball is
8163 ;; located under "data/annotation/" instead of "bioc/".
8164 (uri (string-append "https://bioconductor.org/packages/"
8165 "release/data/experiment/src/contrib/"
8166 "genomationData_" version ".tar.gz"))
8169 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8170 (build-system r-build-system)
8171 ;; As this package provides little more than large data files, it doesn't
8172 ;; make sense to build substitutes.
8173 (arguments `(#:substitutable? #f))
8175 `(("r-knitr" ,r-knitr)))
8176 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8177 (synopsis "Experimental data for use with the genomation package")
8179 "This package contains experimental genetic data for use with the
8180 genomation package. Included are Chip Seq, Methylation and Cage data,
8181 downloaded from Encode.")
8182 (license license:gpl3+)))
8184 (define-public r-org-hs-eg-db
8186 (name "r-org-hs-eg-db")
8190 ;; We cannot use bioconductor-uri here because this tarball is
8191 ;; located under "data/annotation/" instead of "bioc/".
8192 (uri (string-append "https://www.bioconductor.org/packages/"
8193 "release/data/annotation/src/contrib/"
8194 "org.Hs.eg.db_" version ".tar.gz"))
8197 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
8199 `((upstream-name . "org.Hs.eg.db")))
8200 (build-system r-build-system)
8202 `(("r-annotationdbi" ,r-annotationdbi)))
8203 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8204 (synopsis "Genome wide annotation for Human")
8206 "This package contains genome-wide annotations for Human, primarily based
8207 on mapping using Entrez Gene identifiers.")
8208 (license license:artistic2.0)))
8210 (define-public r-org-ce-eg-db
8212 (name "r-org-ce-eg-db")
8216 ;; We cannot use bioconductor-uri here because this tarball is
8217 ;; located under "data/annotation/" instead of "bioc/".
8218 (uri (string-append "https://www.bioconductor.org/packages/"
8219 "release/data/annotation/src/contrib/"
8220 "org.Ce.eg.db_" version ".tar.gz"))
8223 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8225 `((upstream-name . "org.Ce.eg.db")))
8226 (build-system r-build-system)
8228 `(("r-annotationdbi" ,r-annotationdbi)))
8229 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8230 (synopsis "Genome wide annotation for Worm")
8232 "This package provides mappings from Entrez gene identifiers to various
8233 annotations for the genome of the model worm Caenorhabditis elegans.")
8234 (license license:artistic2.0)))
8236 (define-public r-org-dm-eg-db
8238 (name "r-org-dm-eg-db")
8242 ;; We cannot use bioconductor-uri here because this tarball is
8243 ;; located under "data/annotation/" instead of "bioc/".
8244 (uri (string-append "https://www.bioconductor.org/packages/"
8245 "release/data/annotation/src/contrib/"
8246 "org.Dm.eg.db_" version ".tar.gz"))
8249 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8251 `((upstream-name . "org.Dm.eg.db")))
8252 (build-system r-build-system)
8254 `(("r-annotationdbi" ,r-annotationdbi)))
8255 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8256 (synopsis "Genome wide annotation for Fly")
8258 "This package provides mappings from Entrez gene identifiers to various
8259 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8260 (license license:artistic2.0)))
8262 (define-public r-org-mm-eg-db
8264 (name "r-org-mm-eg-db")
8268 ;; We cannot use bioconductor-uri here because this tarball is
8269 ;; located under "data/annotation/" instead of "bioc/".
8270 (uri (string-append "https://www.bioconductor.org/packages/"
8271 "release/data/annotation/src/contrib/"
8272 "org.Mm.eg.db_" version ".tar.gz"))
8275 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8277 `((upstream-name . "org.Mm.eg.db")))
8278 (build-system r-build-system)
8280 `(("r-annotationdbi" ,r-annotationdbi)))
8281 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8282 (synopsis "Genome wide annotation for Mouse")
8284 "This package provides mappings from Entrez gene identifiers to various
8285 annotations for the genome of the model mouse Mus musculus.")
8286 (license license:artistic2.0)))
8288 (define-public r-seqlogo
8295 (uri (bioconductor-uri "seqLogo" version))
8298 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8299 (properties `((upstream-name . "seqLogo")))
8300 (build-system r-build-system)
8301 (home-page "https://bioconductor.org/packages/seqLogo")
8302 (synopsis "Sequence logos for DNA sequence alignments")
8304 "seqLogo takes the position weight matrix of a DNA sequence motif and
8305 plots the corresponding sequence logo as introduced by Schneider and
8307 (license license:lgpl2.0+)))
8309 (define-public r-bsgenome-hsapiens-ucsc-hg19
8311 (name "r-bsgenome-hsapiens-ucsc-hg19")
8315 ;; We cannot use bioconductor-uri here because this tarball is
8316 ;; located under "data/annotation/" instead of "bioc/".
8317 (uri (string-append "https://www.bioconductor.org/packages/"
8318 "release/data/annotation/src/contrib/"
8319 "BSgenome.Hsapiens.UCSC.hg19_"
8323 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8325 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8326 (build-system r-build-system)
8327 ;; As this package provides little more than a very large data file it
8328 ;; doesn't make sense to build substitutes.
8329 (arguments `(#:substitutable? #f))
8331 `(("r-bsgenome" ,r-bsgenome)))
8333 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8334 (synopsis "Full genome sequences for Homo sapiens")
8336 "This package provides full genome sequences for Homo sapiens as provided
8337 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8338 (license license:artistic2.0)))
8340 (define-public r-bsgenome-mmusculus-ucsc-mm9
8342 (name "r-bsgenome-mmusculus-ucsc-mm9")
8346 ;; We cannot use bioconductor-uri here because this tarball is
8347 ;; located under "data/annotation/" instead of "bioc/".
8348 (uri (string-append "https://www.bioconductor.org/packages/"
8349 "release/data/annotation/src/contrib/"
8350 "BSgenome.Mmusculus.UCSC.mm9_"
8354 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8356 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8357 (build-system r-build-system)
8358 ;; As this package provides little more than a very large data file it
8359 ;; doesn't make sense to build substitutes.
8360 (arguments `(#:substitutable? #f))
8362 `(("r-bsgenome" ,r-bsgenome)))
8364 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8365 (synopsis "Full genome sequences for Mouse")
8367 "This package provides full genome sequences for Mus musculus (Mouse) as
8368 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8369 (license license:artistic2.0)))
8371 (define-public r-bsgenome-mmusculus-ucsc-mm10
8373 (name "r-bsgenome-mmusculus-ucsc-mm10")
8377 ;; We cannot use bioconductor-uri here because this tarball is
8378 ;; located under "data/annotation/" instead of "bioc/".
8379 (uri (string-append "https://www.bioconductor.org/packages/"
8380 "release/data/annotation/src/contrib/"
8381 "BSgenome.Mmusculus.UCSC.mm10_"
8385 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8387 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8388 (build-system r-build-system)
8389 ;; As this package provides little more than a very large data file it
8390 ;; doesn't make sense to build substitutes.
8391 (arguments `(#:substitutable? #f))
8393 `(("r-bsgenome" ,r-bsgenome)))
8395 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8396 (synopsis "Full genome sequences for Mouse")
8398 "This package provides full genome sequences for Mus
8399 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8400 in Biostrings objects.")
8401 (license license:artistic2.0)))
8403 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8405 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8409 ;; We cannot use bioconductor-uri here because this tarball is
8410 ;; located under "data/annotation/" instead of "bioc/".
8411 (uri (string-append "https://www.bioconductor.org/packages/"
8412 "release/data/annotation/src/contrib/"
8413 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8417 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8419 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8420 (build-system r-build-system)
8421 ;; As this package provides little more than a very large data file it
8422 ;; doesn't make sense to build substitutes.
8423 (arguments `(#:substitutable? #f))
8425 `(("r-bsgenome" ,r-bsgenome)
8426 ("r-genomicfeatures" ,r-genomicfeatures)
8427 ("r-annotationdbi" ,r-annotationdbi)))
8429 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8430 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8432 "This package loads a TxDb object, which is an R interface to
8433 prefabricated databases contained in this package. This package provides
8434 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8435 based on the knownGene track.")
8436 (license license:artistic2.0)))
8438 (define-public r-bsgenome-celegans-ucsc-ce6
8440 (name "r-bsgenome-celegans-ucsc-ce6")
8444 ;; We cannot use bioconductor-uri here because this tarball is
8445 ;; located under "data/annotation/" instead of "bioc/".
8446 (uri (string-append "https://www.bioconductor.org/packages/"
8447 "release/data/annotation/src/contrib/"
8448 "BSgenome.Celegans.UCSC.ce6_"
8452 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8454 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8455 (build-system r-build-system)
8456 ;; As this package provides little more than a very large data file it
8457 ;; doesn't make sense to build substitutes.
8458 (arguments `(#:substitutable? #f))
8460 `(("r-bsgenome" ,r-bsgenome)))
8462 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8463 (synopsis "Full genome sequences for Worm")
8465 "This package provides full genome sequences for Caenorhabditis
8466 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8468 (license license:artistic2.0)))
8470 (define-public r-bsgenome-celegans-ucsc-ce10
8472 (name "r-bsgenome-celegans-ucsc-ce10")
8476 ;; We cannot use bioconductor-uri here because this tarball is
8477 ;; located under "data/annotation/" instead of "bioc/".
8478 (uri (string-append "https://www.bioconductor.org/packages/"
8479 "release/data/annotation/src/contrib/"
8480 "BSgenome.Celegans.UCSC.ce10_"
8484 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8486 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8487 (build-system r-build-system)
8488 ;; As this package provides little more than a very large data file it
8489 ;; doesn't make sense to build substitutes.
8490 (arguments `(#:substitutable? #f))
8492 `(("r-bsgenome" ,r-bsgenome)))
8494 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8495 (synopsis "Full genome sequences for Worm")
8497 "This package provides full genome sequences for Caenorhabditis
8498 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8500 (license license:artistic2.0)))
8502 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8504 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8508 ;; We cannot use bioconductor-uri here because this tarball is
8509 ;; located under "data/annotation/" instead of "bioc/".
8510 (uri (string-append "https://www.bioconductor.org/packages/"
8511 "release/data/annotation/src/contrib/"
8512 "BSgenome.Dmelanogaster.UCSC.dm3_"
8516 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8518 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8519 (build-system r-build-system)
8520 ;; As this package provides little more than a very large data file it
8521 ;; doesn't make sense to build substitutes.
8522 (arguments `(#:substitutable? #f))
8524 `(("r-bsgenome" ,r-bsgenome)))
8526 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8527 (synopsis "Full genome sequences for Fly")
8529 "This package provides full genome sequences for Drosophila
8530 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8531 Biostrings objects.")
8532 (license license:artistic2.0)))
8534 (define-public r-motifrg
8541 (uri (bioconductor-uri "motifRG" version))
8544 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8545 (properties `((upstream-name . "motifRG")))
8546 (build-system r-build-system)
8548 `(("r-biostrings" ,r-biostrings)
8549 ("r-bsgenome" ,r-bsgenome)
8550 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8551 ("r-iranges" ,r-iranges)
8552 ("r-seqlogo" ,r-seqlogo)
8553 ("r-xvector" ,r-xvector)))
8554 (home-page "https://bioconductor.org/packages/motifRG")
8555 (synopsis "Discover motifs in high throughput sequencing data")
8557 "This package provides tools for discriminative motif discovery in high
8558 throughput genetic sequencing data sets using regression methods.")
8559 (license license:artistic2.0)))
8561 (define-public r-qtl
8568 (uri (string-append "mirror://cran/src/contrib/qtl_"
8572 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8573 (build-system r-build-system)
8574 (home-page "http://rqtl.org/")
8575 (synopsis "R package for analyzing QTL experiments in genetics")
8576 (description "R/qtl is an extension library for the R statistics
8577 system. It is used to analyze experimental crosses for identifying
8578 genes contributing to variation in quantitative traits (so-called
8579 quantitative trait loci, QTLs).
8581 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8582 identify genotyping errors, and to perform single-QTL and two-QTL,
8583 two-dimensional genome scans.")
8584 (license license:gpl3)))
8586 (define-public r-zlibbioc
8592 (uri (bioconductor-uri "zlibbioc" version))
8595 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8597 `((upstream-name . "zlibbioc")))
8598 (build-system r-build-system)
8599 (home-page "https://bioconductor.org/packages/zlibbioc")
8600 (synopsis "Provider for zlib-1.2.5 to R packages")
8601 (description "This package uses the source code of zlib-1.2.5 to create
8602 libraries for systems that do not have these available via other means.")
8603 (license license:artistic2.0)))
8605 (define-public r-r4rna
8612 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8616 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8617 (build-system r-build-system)
8619 `(("r-optparse" ,r-optparse)
8620 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8621 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8622 (synopsis "Analysis framework for RNA secondary structure")
8624 "The R4RNA package aims to be a general framework for the analysis of RNA
8625 secondary structure and comparative analysis in R.")
8626 (license license:gpl3+)))
8628 (define-public r-rhtslib
8635 (uri (bioconductor-uri "Rhtslib" version))
8638 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8639 (properties `((upstream-name . "Rhtslib")))
8640 (build-system r-build-system)
8642 `(("r-zlibbioc" ,r-zlibbioc)))
8646 `(("pkg-config" ,pkg-config)))
8647 (home-page "https://github.com/nhayden/Rhtslib")
8648 (synopsis "High-throughput sequencing library as an R package")
8650 "This package provides the HTSlib C library for high-throughput
8651 nucleotide sequence analysis. The package is primarily useful to developers
8652 of other R packages who wish to make use of HTSlib.")
8653 (license license:lgpl2.0+)))
8655 (define-public r-bamsignals
8657 (name "r-bamsignals")
8662 (uri (bioconductor-uri "bamsignals" version))
8665 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8666 (build-system r-build-system)
8668 `(("r-biocgenerics" ,r-biocgenerics)
8669 ("r-genomicranges" ,r-genomicranges)
8670 ("r-iranges" ,r-iranges)
8672 ("r-rhtslib" ,r-rhtslib)
8673 ("r-zlibbioc" ,r-zlibbioc)))
8676 (home-page "https://bioconductor.org/packages/bamsignals")
8677 (synopsis "Extract read count signals from bam files")
8679 "This package allows to efficiently obtain count vectors from indexed bam
8680 files. It counts the number of nucleotide sequence reads in given genomic
8681 ranges and it computes reads profiles and coverage profiles. It also handles
8683 (license license:gpl2+)))
8685 (define-public r-rcas
8691 (uri (bioconductor-uri "RCAS" version))
8694 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8695 (build-system r-build-system)
8697 `(("r-annotationdbi" ,r-annotationdbi)
8698 ("r-biocgenerics" ,r-biocgenerics)
8699 ("r-biomart" ,r-biomart)
8700 ("r-biostrings" ,r-biostrings)
8701 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8702 ("r-cowplot" ,r-cowplot)
8703 ("r-data-table" ,r-data-table)
8706 ("r-genomation" ,r-genomation)
8707 ("r-genomeinfodb" ,r-genomeinfodb)
8708 ("r-genomicfeatures" ,r-genomicfeatures)
8709 ("r-genomicranges" ,r-genomicranges)
8710 ("r-ggplot2" ,r-ggplot2)
8711 ("r-ggseqlogo" ,r-ggseqlogo)
8712 ("r-knitr" ,r-knitr)
8713 ("r-motifrg" ,r-motifrg)
8714 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8715 ("r-pbapply" ,r-pbapply)
8716 ("r-pheatmap" ,r-pheatmap)
8717 ("r-plotly" ,r-plotly)
8718 ("r-plotrix" ,r-plotrix)
8719 ("r-proxy" ,r-proxy)
8720 ("r-rsqlite" ,r-rsqlite)
8721 ("r-rtracklayer" ,r-rtracklayer)
8722 ("r-rmarkdown" ,r-rmarkdown)
8723 ("r-s4vectors" ,r-s4vectors)
8724 ("r-topgo" ,r-topgo)))
8725 (synopsis "RNA-centric annotation system")
8727 "RCAS aims to be a standalone RNA-centric annotation system that provides
8728 intuitive reports and publication-ready graphics. This package provides the R
8729 library implementing most of the pipeline's features.")
8730 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8731 (license license:artistic2.0)))
8733 (define-public rcas-web
8740 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8741 "releases/download/v" version
8742 "/rcas-web-" version ".tar.gz"))
8745 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8746 (build-system gnu-build-system)
8749 (modify-phases %standard-phases
8750 (add-after 'install 'wrap-executable
8751 (lambda* (#:key inputs outputs #:allow-other-keys)
8752 (let* ((out (assoc-ref outputs "out"))
8753 (json (assoc-ref inputs "guile-json"))
8754 (redis (assoc-ref inputs "guile-redis"))
8755 (path (string-append
8756 json "/share/guile/site/2.2:"
8757 redis "/share/guile/site/2.2")))
8758 (wrap-program (string-append out "/bin/rcas-web")
8759 `("GUILE_LOAD_PATH" ":" = (,path))
8760 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8761 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8764 `(("r-minimal" ,r-minimal)
8766 ("guile-next" ,guile-2.2)
8767 ("guile-json" ,guile-json)
8768 ("guile-redis" ,guile2.2-redis)))
8770 `(("pkg-config" ,pkg-config)))
8771 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8772 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8773 (description "This package provides a simple web interface for the
8774 @dfn{RNA-centric annotation system} (RCAS).")
8775 (license license:agpl3+)))
8777 (define-public r-mutationalpatterns
8779 (name "r-mutationalpatterns")
8784 (uri (bioconductor-uri "MutationalPatterns" version))
8787 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8788 (build-system r-build-system)
8790 `(("r-biocgenerics" ,r-biocgenerics)
8791 ("r-biostrings" ,r-biostrings)
8792 ;; These two packages are suggested packages
8793 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8794 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8795 ("r-genomicranges" ,r-genomicranges)
8796 ("r-genomeinfodb" ,r-genomeinfodb)
8797 ("r-ggplot2" ,r-ggplot2)
8798 ("r-iranges" ,r-iranges)
8801 ("r-pracma" ,r-pracma)
8802 ("r-reshape2" ,r-reshape2)
8803 ("r-cowplot" ,r-cowplot)
8804 ("r-ggdendro" ,r-ggdendro)
8805 ("r-s4vectors" ,r-s4vectors)
8806 ("r-summarizedexperiment" ,r-summarizedexperiment)
8807 ("r-variantannotation" ,r-variantannotation)))
8808 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8809 (synopsis "Extract and visualize mutational patterns in genomic data")
8810 (description "This package provides an extensive toolset for the
8811 characterization and visualization of a wide range of mutational patterns
8812 in SNV base substitution data.")
8813 (license license:expat)))
8815 (define-public r-wgcna
8822 (uri (cran-uri "WGCNA" version))
8825 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8826 (properties `((upstream-name . "WGCNA")))
8827 (build-system r-build-system)
8829 `(("r-annotationdbi" ,r-annotationdbi)
8830 ("r-doparallel" ,r-doparallel)
8831 ("r-dynamictreecut" ,r-dynamictreecut)
8832 ("r-fastcluster" ,r-fastcluster)
8833 ("r-foreach" ,r-foreach)
8834 ("r-go-db" ,r-go-db)
8835 ("r-hmisc" ,r-hmisc)
8836 ("r-impute" ,r-impute)
8838 ("r-robust" ,r-robust)
8839 ("r-survival" ,r-survival)
8840 ("r-matrixstats" ,r-matrixstats)
8841 ("r-preprocesscore" ,r-preprocesscore)))
8843 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8844 (synopsis "Weighted correlation network analysis")
8846 "This package provides functions necessary to perform Weighted
8847 Correlation Network Analysis on high-dimensional data. It includes functions
8848 for rudimentary data cleaning, construction and summarization of correlation
8849 networks, module identification and functions for relating both variables and
8850 modules to sample traits. It also includes a number of utility functions for
8851 data manipulation and visualization.")
8852 (license license:gpl2+)))
8854 (define-public r-chipkernels
8855 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8858 (name "r-chipkernels")
8859 (version (string-append "1.1-" revision "." (string-take commit 9)))
8864 (url "https://github.com/ManuSetty/ChIPKernels.git")
8866 (file-name (string-append name "-" version))
8869 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8870 (build-system r-build-system)
8872 `(("r-iranges" ,r-iranges)
8873 ("r-xvector" ,r-xvector)
8874 ("r-biostrings" ,r-biostrings)
8875 ("r-bsgenome" ,r-bsgenome)
8876 ("r-gtools" ,r-gtools)
8877 ("r-genomicranges" ,r-genomicranges)
8878 ("r-sfsmisc" ,r-sfsmisc)
8879 ("r-kernlab" ,r-kernlab)
8880 ("r-s4vectors" ,r-s4vectors)
8881 ("r-biocgenerics" ,r-biocgenerics)))
8882 (home-page "https://github.com/ManuSetty/ChIPKernels")
8883 (synopsis "Build string kernels for DNA Sequence analysis")
8884 (description "ChIPKernels is an R package for building different string
8885 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8886 must be built and this dictionary can be used for determining kernels for DNA
8888 (license license:gpl2+))))
8890 (define-public r-seqgl
8898 (url "https://github.com/ManuSetty/SeqGL.git")
8900 (file-name (git-file-name name version))
8903 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8904 (build-system r-build-system)
8906 `(("r-biostrings" ,r-biostrings)
8907 ("r-chipkernels" ,r-chipkernels)
8908 ("r-genomicranges" ,r-genomicranges)
8909 ("r-spams" ,r-spams)
8910 ("r-wgcna" ,r-wgcna)
8911 ("r-fastcluster" ,r-fastcluster)))
8912 (home-page "https://github.com/ManuSetty/SeqGL")
8913 (synopsis "Group lasso for Dnase/ChIP-seq data")
8914 (description "SeqGL is a group lasso based algorithm to extract
8915 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8916 This package presents a method which uses group lasso to discriminate between
8917 bound and non bound genomic regions to accurately identify transcription
8918 factors bound at the specific regions.")
8919 (license license:gpl2+)))
8921 (define-public r-gkmsvm
8928 (uri (cran-uri "gkmSVM" version))
8931 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8932 (properties `((upstream-name . "gkmSVM")))
8933 (build-system r-build-system)
8935 `(("r-biocgenerics" ,r-biocgenerics)
8936 ("r-biostrings" ,r-biostrings)
8937 ("r-genomeinfodb" ,r-genomeinfodb)
8938 ("r-genomicranges" ,r-genomicranges)
8939 ("r-iranges" ,r-iranges)
8940 ("r-kernlab" ,r-kernlab)
8943 ("r-rtracklayer" ,r-rtracklayer)
8944 ("r-s4vectors" ,r-s4vectors)
8945 ("r-seqinr" ,r-seqinr)))
8946 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8947 (synopsis "Gapped-kmer support vector machine")
8949 "This R package provides tools for training gapped-kmer SVM classifiers
8950 for DNA and protein sequences. This package supports several sequence
8951 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8952 (license license:gpl2+)))
8954 (define-public r-tximport
8960 (uri (bioconductor-uri "tximport" version))
8963 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8964 (build-system r-build-system)
8965 (home-page "https://bioconductor.org/packages/tximport")
8966 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8968 "This package provides tools to import transcript-level abundance,
8969 estimated counts and transcript lengths, and to summarize them into matrices
8970 for use with downstream gene-level analysis packages. Average transcript
8971 length, weighted by sample-specific transcript abundance estimates, is
8972 provided as a matrix which can be used as an offset for different expression
8973 of gene-level counts.")
8974 (license license:gpl2+)))
8976 (define-public r-rhdf5
8982 (uri (bioconductor-uri "rhdf5" version))
8985 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8986 (build-system r-build-system)
8988 `(("r-rhdf5lib" ,r-rhdf5lib)))
8991 (home-page "https://bioconductor.org/packages/rhdf5")
8992 (synopsis "HDF5 interface to R")
8994 "This R/Bioconductor package provides an interface between HDF5 and R.
8995 HDF5's main features are the ability to store and access very large and/or
8996 complex datasets and a wide variety of metadata on mass storage (disk) through
8997 a completely portable file format. The rhdf5 package is thus suited for the
8998 exchange of large and/or complex datasets between R and other software
8999 package, and for letting R applications work on datasets that are larger than
9000 the available RAM.")
9001 (license license:artistic2.0)))
9003 (define-public r-annotationfilter
9005 (name "r-annotationfilter")
9009 (uri (bioconductor-uri "AnnotationFilter" version))
9012 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
9014 `((upstream-name . "AnnotationFilter")))
9015 (build-system r-build-system)
9017 `(("r-genomicranges" ,r-genomicranges)
9018 ("r-lazyeval" ,r-lazyeval)))
9019 (home-page "https://github.com/Bioconductor/AnnotationFilter")
9020 (synopsis "Facilities for filtering Bioconductor annotation resources")
9022 "This package provides classes and other infrastructure to implement
9023 filters for manipulating Bioconductor annotation resources. The filters are
9024 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
9025 (license license:artistic2.0)))
9027 (define-public emboss
9033 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
9034 (version-major+minor version) ".0/"
9035 "EMBOSS-" version ".tar.gz"))
9038 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
9039 (build-system gnu-build-system)
9042 (list (string-append "--with-hpdf="
9043 (assoc-ref %build-inputs "libharu")))
9045 (modify-phases %standard-phases
9046 (add-after 'unpack 'fix-checks
9048 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9049 ;; and zlib, but assume that they are all found at the same
9051 (substitute* "configure.in"
9052 (("CHECK_PNGDRIVER")
9053 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9054 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9055 AM_CONDITIONAL(AMPNG, true)"))
9057 (add-after 'fix-checks 'disable-update-check
9059 ;; At build time there is no connection to the Internet, so
9060 ;; looking for updates will not work.
9061 (substitute* "Makefile.am"
9062 (("\\$\\(bindir\\)/embossupdate") ""))
9064 (add-after 'disable-update-check 'autogen
9065 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9071 ("libharu" ,libharu)
9074 `(("autoconf" ,autoconf)
9075 ("automake" ,automake)
9076 ("libtool" ,libtool)
9077 ("pkg-config" ,pkg-config)))
9078 (home-page "http://emboss.sourceforge.net")
9079 (synopsis "Molecular biology analysis suite")
9080 (description "EMBOSS is the \"European Molecular Biology Open Software
9081 Suite\". EMBOSS is an analysis package specially developed for the needs of
9082 the molecular biology (e.g. EMBnet) user community. The software
9083 automatically copes with data in a variety of formats and even allows
9084 transparent retrieval of sequence data from the web. It also provides a
9085 number of libraries for the development of software in the field of molecular
9086 biology. EMBOSS also integrates a range of currently available packages and
9087 tools for sequence analysis into a seamless whole.")
9088 (license license:gpl2+)))
9091 (let ((revision "1")
9092 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9095 ;; The version is 2.13.0 even though no release archives have been
9096 ;; published as yet.
9097 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9101 (url "https://github.com/arq5x/bits.git")
9103 (file-name (string-append name "-" version "-checkout"))
9106 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9107 (build-system gnu-build-system)
9109 `(#:tests? #f ;no tests included
9111 (modify-phases %standard-phases
9113 (add-after 'unpack 'remove-cuda
9115 (substitute* "Makefile"
9117 (("(bits_test_intersections) \\\\" _ match) match))
9120 (lambda* (#:key outputs #:allow-other-keys)
9122 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9127 (home-page "https://github.com/arq5x/bits")
9128 (synopsis "Implementation of binary interval search algorithm")
9129 (description "This package provides an implementation of the
9130 BITS (Binary Interval Search) algorithm, an approach to interval set
9131 intersection. It is especially suited for the comparison of diverse genomic
9132 datasets and the exploration of large datasets of genome
9133 intervals (e.g. genes, sequence alignments).")
9134 (license license:gpl2))))
9136 (define-public piranha
9137 ;; There is no release tarball for the latest version. The latest commit is
9138 ;; older than one year at the time of this writing.
9139 (let ((revision "1")
9140 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9143 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9147 (url "https://github.com/smithlabcode/piranha.git")
9149 (file-name (git-file-name name version))
9152 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9153 (build-system gnu-build-system)
9155 `(#:test-target "test"
9157 (modify-phases %standard-phases
9158 (add-after 'unpack 'copy-smithlab-cpp
9159 (lambda* (#:key inputs #:allow-other-keys)
9160 (for-each (lambda (file)
9161 (install-file file "./src/smithlab_cpp/"))
9162 (find-files (assoc-ref inputs "smithlab-cpp")))
9164 (add-after 'install 'install-to-store
9165 (lambda* (#:key outputs #:allow-other-keys)
9166 (let* ((out (assoc-ref outputs "out"))
9167 (bin (string-append out "/bin")))
9168 (for-each (lambda (file)
9169 (install-file file bin))
9170 (find-files "bin" ".*")))
9173 (list (string-append "--with-bam_tools_headers="
9174 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9175 (string-append "--with-bam_tools_library="
9176 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9178 `(("bamtools" ,bamtools)
9179 ("samtools" ,samtools-0.1)
9182 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9186 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9188 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9191 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9193 `(("python" ,python-2)))
9194 (home-page "https://github.com/smithlabcode/piranha")
9195 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9197 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9198 RIP-seq experiments. It takes input in BED or BAM format and identifies
9199 regions of statistically significant read enrichment. Additional covariates
9200 may optionally be provided to further inform the peak-calling process.")
9201 (license license:gpl3+))))
9209 (uri (string-append "https://pypi.python.org/packages/source/P"
9210 "/PePr/PePr-" version ".tar.gz"))
9213 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9214 (build-system python-build-system)
9216 `(#:python ,python-2 ; python2 only
9217 #:tests? #f)) ; no tests included
9219 `(("python2-numpy" ,python2-numpy)
9220 ("python2-scipy" ,python2-scipy)
9221 ("python2-pysam" ,python2-pysam)))
9222 (home-page "https://github.com/shawnzhangyx/PePr")
9223 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9225 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9226 that is primarily designed for data with biological replicates. It uses a
9227 negative binomial distribution to model the read counts among the samples in
9228 the same group, and look for consistent differences between ChIP and control
9229 group or two ChIP groups run under different conditions.")
9230 (license license:gpl3+)))
9232 (define-public filevercmp
9233 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9236 (version (string-append "0-1." (string-take commit 7)))
9240 (url "https://github.com/ekg/filevercmp.git")
9242 (file-name (git-file-name name commit))
9245 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9246 (build-system gnu-build-system)
9248 `(#:tests? #f ; There are no tests to run.
9250 (modify-phases %standard-phases
9251 (delete 'configure) ; There is no configure phase.
9253 (lambda* (#:key outputs #:allow-other-keys)
9254 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9255 (install-file "filevercmp" bin)
9257 (home-page "https://github.com/ekg/filevercmp")
9258 (synopsis "This program compares version strings")
9259 (description "This program compares version strings. It intends to be a
9260 replacement for strverscmp.")
9261 (license license:gpl3+))))
9263 (define-public multiqc
9270 (uri (pypi-uri "multiqc" version))
9273 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9274 (build-system python-build-system)
9276 `(("python-jinja2" ,python-jinja2)
9277 ("python-simplejson" ,python-simplejson)
9278 ("python-pyyaml" ,python-pyyaml)
9279 ("python-click" ,python-click)
9280 ("python-spectra" ,python-spectra)
9281 ("python-requests" ,python-requests)
9282 ("python-markdown" ,python-markdown)
9283 ("python-lzstring" ,python-lzstring)
9284 ("python-matplotlib" ,python-matplotlib)
9285 ("python-numpy" ,python-numpy)
9286 ;; MultQC checks for the presence of nose at runtime.
9287 ("python-nose" ,python-nose)))
9290 (modify-phases %standard-phases
9291 (add-after 'unpack 'relax-requirements
9293 (substitute* "setup.py"
9294 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9295 ;; than the one in Guix, but should work fine with 2.2.2.
9296 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9297 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9298 (("['\"]matplotlib.*?['\"]")
9301 (home-page "http://multiqc.info")
9302 (synopsis "Aggregate bioinformatics analysis reports")
9304 "MultiQC is a tool to aggregate bioinformatics results across many
9305 samples into a single report. It contains modules for a large number of
9306 common bioinformatics tools.")
9307 (license license:gpl3+)))
9309 (define-public r-chipseq
9316 (uri (bioconductor-uri "chipseq" version))
9319 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9320 (build-system r-build-system)
9322 `(("r-biocgenerics" ,r-biocgenerics)
9323 ("r-genomicranges" ,r-genomicranges)
9324 ("r-iranges" ,r-iranges)
9325 ("r-lattice" ,r-lattice)
9326 ("r-s4vectors" ,r-s4vectors)
9327 ("r-shortread" ,r-shortread)))
9328 (home-page "https://bioconductor.org/packages/chipseq")
9329 (synopsis "Package for analyzing ChIPseq data")
9331 "This package provides tools for processing short read data from ChIPseq
9333 (license license:artistic2.0)))
9335 (define-public r-copyhelper
9337 (name "r-copyhelper")
9342 (uri (string-append "https://bioconductor.org/packages/release/"
9343 "data/experiment/src/contrib/CopyhelpeR_"
9347 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9348 (properties `((upstream-name . "CopyhelpeR")))
9349 (build-system r-build-system)
9350 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9351 (synopsis "Helper files for CopywriteR")
9353 "This package contains the helper files that are required to run the
9354 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9355 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9356 mm10. In addition, it contains a blacklist filter to remove regions that
9357 display copy number variation. Files are stored as GRanges objects from the
9358 GenomicRanges Bioconductor package.")
9359 (license license:gpl2)))
9361 (define-public r-copywriter
9363 (name "r-copywriter")
9368 (uri (bioconductor-uri "CopywriteR" version))
9371 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
9372 (properties `((upstream-name . "CopywriteR")))
9373 (build-system r-build-system)
9375 `(("r-biocparallel" ,r-biocparallel)
9376 ("r-chipseq" ,r-chipseq)
9377 ("r-copyhelper" ,r-copyhelper)
9378 ("r-data-table" ,r-data-table)
9379 ("r-dnacopy" ,r-dnacopy)
9380 ("r-futile-logger" ,r-futile-logger)
9381 ("r-genomeinfodb" ,r-genomeinfodb)
9382 ("r-genomicalignments" ,r-genomicalignments)
9383 ("r-genomicranges" ,r-genomicranges)
9384 ("r-gtools" ,r-gtools)
9385 ("r-iranges" ,r-iranges)
9386 ("r-matrixstats" ,r-matrixstats)
9387 ("r-rsamtools" ,r-rsamtools)
9388 ("r-s4vectors" ,r-s4vectors)))
9389 (home-page "https://github.com/PeeperLab/CopywriteR")
9390 (synopsis "Copy number information from targeted sequencing")
9392 "CopywriteR extracts DNA copy number information from targeted sequencing
9393 by utilizing off-target reads. It allows for extracting uniformly distributed
9394 copy number information, can be used without reference, and can be applied to
9395 sequencing data obtained from various techniques including chromatin
9396 immunoprecipitation and target enrichment on small gene panels. Thereby,
9397 CopywriteR constitutes a widely applicable alternative to available copy
9398 number detection tools.")
9399 (license license:gpl2)))
9401 (define-public r-methylkit
9403 (name "r-methylkit")
9407 (uri (bioconductor-uri "methylKit" version))
9410 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
9411 (properties `((upstream-name . "methylKit")))
9412 (build-system r-build-system)
9414 `(("r-data-table" ,r-data-table)
9415 ("r-emdbook" ,r-emdbook)
9416 ("r-fastseg" ,r-fastseg)
9417 ("r-genomeinfodb" ,r-genomeinfodb)
9418 ("r-genomicranges" ,r-genomicranges)
9419 ("r-gtools" ,r-gtools)
9420 ("r-iranges" ,r-iranges)
9421 ("r-kernsmooth" ,r-kernsmooth)
9422 ("r-limma" ,r-limma)
9423 ("r-mclust" ,r-mclust)
9424 ("r-qvalue" ,r-qvalue)
9425 ("r-r-utils" ,r-r-utils)
9427 ("r-rhtslib" ,r-rhtslib)
9428 ("r-rsamtools" ,r-rsamtools)
9429 ("r-rtracklayer" ,r-rtracklayer)
9430 ("r-s4vectors" ,r-s4vectors)
9431 ("r-zlibbioc" ,r-zlibbioc)))
9434 (home-page "https://github.com/al2na/methylKit")
9436 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9438 "MethylKit is an R package for DNA methylation analysis and annotation
9439 from high-throughput bisulfite sequencing. The package is designed to deal
9440 with sequencing data from @dfn{Reduced representation bisulfite
9441 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9442 genome bisulfite sequencing. It also has functions to analyze base-pair
9443 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9445 (license license:artistic2.0)))
9447 (define-public r-sva
9454 (uri (bioconductor-uri "sva" version))
9457 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
9458 (build-system r-build-system)
9460 `(("r-genefilter" ,r-genefilter)
9462 ("r-biocparallel" ,r-biocparallel)
9463 ("r-matrixstats" ,r-matrixstats)
9464 ("r-limma" ,r-limma)))
9465 (home-page "https://bioconductor.org/packages/sva")
9466 (synopsis "Surrogate variable analysis")
9468 "This package contains functions for removing batch effects and other
9469 unwanted variation in high-throughput experiment. It also contains functions
9470 for identifying and building surrogate variables for high-dimensional data
9471 sets. Surrogate variables are covariates constructed directly from
9472 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9473 imaging data that can be used in subsequent analyses to adjust for unknown,
9474 unmodeled, or latent sources of noise.")
9475 (license license:artistic2.0)))
9477 (define-public r-seqminer
9484 (uri (cran-uri "seqminer" version))
9487 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9488 (build-system r-build-system)
9491 (home-page "http://seqminer.genomic.codes")
9492 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9494 "This package provides tools to integrate nucleotide sequencing
9495 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9496 ;; Any version of the GPL is acceptable
9497 (license (list license:gpl2+ license:gpl3+))))
9499 (define-public r-raremetals2
9501 (name "r-raremetals2")
9506 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9507 "b/b7/RareMETALS2_" version ".tar.gz"))
9510 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9511 (properties `((upstream-name . "RareMETALS2")))
9512 (build-system r-build-system)
9514 `(("r-seqminer" ,r-seqminer)
9515 ("r-mvtnorm" ,r-mvtnorm)
9517 ("r-compquadform" ,r-compquadform)
9518 ("r-getopt" ,r-getopt)))
9519 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9520 (synopsis "Analyze gene-level association tests for binary trait")
9522 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9523 It was designed to meta-analyze gene-level association tests for binary trait.
9524 While rareMETALS offers a near-complete solution for meta-analysis of
9525 gene-level tests for quantitative trait, it does not offer the optimal
9526 solution for binary trait. The package rareMETALS2 offers improved features
9527 for analyzing gene-level association tests in meta-analyses for binary
9529 (license license:gpl3)))
9531 (define-public r-maldiquant
9533 (name "r-maldiquant")
9538 (uri (cran-uri "MALDIquant" version))
9541 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9542 (properties `((upstream-name . "MALDIquant")))
9543 (build-system r-build-system)
9544 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9545 (synopsis "Quantitative analysis of mass spectrometry data")
9547 "This package provides a complete analysis pipeline for matrix-assisted
9548 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9549 two-dimensional mass spectrometry data. In addition to commonly used plotting
9550 and processing methods it includes distinctive features, namely baseline
9551 subtraction methods such as morphological filters (TopHat) or the
9552 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9553 alignment using warping functions, handling of replicated measurements as well
9554 as allowing spectra with different resolutions.")
9555 (license license:gpl3+)))
9557 (define-public r-protgenerics
9559 (name "r-protgenerics")
9564 (uri (bioconductor-uri "ProtGenerics" version))
9567 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9568 (properties `((upstream-name . "ProtGenerics")))
9569 (build-system r-build-system)
9570 (home-page "https://github.com/lgatto/ProtGenerics")
9571 (synopsis "S4 generic functions for proteomics infrastructure")
9573 "This package provides S4 generic functions needed by Bioconductor
9574 proteomics packages.")
9575 (license license:artistic2.0)))
9577 (define-public r-mzr
9584 (uri (bioconductor-uri "mzR" version))
9587 "0mlwg646k49klxrznckzfv54a9mz6irj42fqpaaa0xjm6cw2lwaa"))
9588 (modules '((guix build utils)))
9591 (delete-file-recursively "src/boost")
9593 (properties `((upstream-name . "mzR")))
9594 (build-system r-build-system)
9597 (modify-phases %standard-phases
9598 (add-after 'unpack 'use-system-boost
9600 (substitute* "src/Makevars"
9601 (("\\./boost/libs.*") "")
9602 (("ARCH_OBJS=" line)
9604 "\nARCH_LIBS=-lboost_system -lboost_regex \
9605 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9608 `(("boost" ,boost) ; use this instead of the bundled boost sources
9611 `(("r-biobase" ,r-biobase)
9612 ("r-biocgenerics" ,r-biocgenerics)
9613 ("r-ncdf4" ,r-ncdf4)
9614 ("r-protgenerics" ,r-protgenerics)
9616 ("r-rhdf5lib" ,r-rhdf5lib)
9617 ("r-zlibbioc" ,r-zlibbioc)))
9618 (home-page "https://github.com/sneumann/mzR/")
9619 (synopsis "Parser for mass spectrometry data files")
9621 "The mzR package provides a unified API to the common file formats and
9622 parsers available for mass spectrometry data. It comes with a wrapper for the
9623 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9624 The package contains the original code written by the ISB, and a subset of the
9625 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9626 previously been used in XCMS.")
9627 (license license:artistic2.0)))
9629 (define-public r-affyio
9636 (uri (bioconductor-uri "affyio" version))
9639 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9640 (build-system r-build-system)
9642 `(("r-zlibbioc" ,r-zlibbioc)))
9645 (home-page "https://github.com/bmbolstad/affyio")
9646 (synopsis "Tools for parsing Affymetrix data files")
9648 "This package provides routines for parsing Affymetrix data files based
9649 upon file format information. The primary focus is on accessing the CEL and
9651 (license license:lgpl2.0+)))
9653 (define-public r-affy
9660 (uri (bioconductor-uri "affy" version))
9663 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9664 (build-system r-build-system)
9666 `(("r-affyio" ,r-affyio)
9667 ("r-biobase" ,r-biobase)
9668 ("r-biocgenerics" ,r-biocgenerics)
9669 ("r-biocmanager" ,r-biocmanager)
9670 ("r-preprocesscore" ,r-preprocesscore)
9671 ("r-zlibbioc" ,r-zlibbioc)))
9674 (home-page "https://bioconductor.org/packages/affy")
9675 (synopsis "Methods for affymetrix oligonucleotide arrays")
9677 "This package contains functions for exploratory oligonucleotide array
9679 (license license:lgpl2.0+)))
9681 (define-public r-vsn
9688 (uri (bioconductor-uri "vsn" version))
9691 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9692 (build-system r-build-system)
9694 `(("r-affy" ,r-affy)
9695 ("r-biobase" ,r-biobase)
9696 ("r-ggplot2" ,r-ggplot2)
9697 ("r-lattice" ,r-lattice)
9698 ("r-limma" ,r-limma)))
9699 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9700 (synopsis "Variance stabilization and calibration for microarray data")
9702 "The package implements a method for normalising microarray intensities,
9703 and works for single- and multiple-color arrays. It can also be used for data
9704 from other technologies, as long as they have similar format. The method uses
9705 a robust variant of the maximum-likelihood estimator for an
9706 additive-multiplicative error model and affine calibration. The model
9707 incorporates data calibration step (a.k.a. normalization), a model for the
9708 dependence of the variance on the mean intensity and a variance stabilizing
9709 data transformation. Differences between transformed intensities are
9710 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9711 their variance is independent of the mean, and they are usually more sensitive
9712 and specific in detecting differential transcription.")
9713 (license license:artistic2.0)))
9715 (define-public r-mzid
9722 (uri (bioconductor-uri "mzID" version))
9725 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9726 (properties `((upstream-name . "mzID")))
9727 (build-system r-build-system)
9729 `(("r-doparallel" ,r-doparallel)
9730 ("r-foreach" ,r-foreach)
9731 ("r-iterators" ,r-iterators)
9733 ("r-protgenerics" ,r-protgenerics)
9736 (home-page "https://bioconductor.org/packages/mzID")
9737 (synopsis "Parser for mzIdentML files")
9739 "This package provides a parser for mzIdentML files implemented using the
9740 XML package. The parser tries to be general and able to handle all types of
9741 mzIdentML files with the drawback of having less pretty output than a vendor
9743 (license license:gpl2+)))
9745 (define-public r-pcamethods
9747 (name "r-pcamethods")
9752 (uri (bioconductor-uri "pcaMethods" version))
9755 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9756 (properties `((upstream-name . "pcaMethods")))
9757 (build-system r-build-system)
9759 `(("r-biobase" ,r-biobase)
9760 ("r-biocgenerics" ,r-biocgenerics)
9762 ("r-rcpp" ,r-rcpp)))
9763 (home-page "https://github.com/hredestig/pcamethods")
9764 (synopsis "Collection of PCA methods")
9766 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9767 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9768 for missing value estimation is included for comparison. BPCA, PPCA and
9769 NipalsPCA may be used to perform PCA on incomplete data as well as for
9770 accurate missing value estimation. A set of methods for printing and plotting
9771 the results is also provided. All PCA methods make use of the same data
9772 structure (pcaRes) to provide a common interface to the PCA results.")
9773 (license license:gpl3+)))
9775 (define-public r-msnbase
9782 (uri (bioconductor-uri "MSnbase" version))
9785 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9786 (properties `((upstream-name . "MSnbase")))
9787 (build-system r-build-system)
9789 `(("r-affy" ,r-affy)
9790 ("r-biobase" ,r-biobase)
9791 ("r-biocgenerics" ,r-biocgenerics)
9792 ("r-biocparallel" ,r-biocparallel)
9793 ("r-digest" ,r-digest)
9794 ("r-ggplot2" ,r-ggplot2)
9795 ("r-impute" ,r-impute)
9796 ("r-iranges" ,r-iranges)
9797 ("r-lattice" ,r-lattice)
9798 ("r-maldiquant" ,r-maldiquant)
9802 ("r-pcamethods" ,r-pcamethods)
9804 ("r-preprocesscore" ,r-preprocesscore)
9805 ("r-protgenerics" ,r-protgenerics)
9807 ("r-s4vectors" ,r-s4vectors)
9808 ("r-scales" ,r-scales)
9811 (home-page "https://github.com/lgatto/MSnbase")
9812 (synopsis "Base functions and classes for MS-based proteomics")
9814 "This package provides basic plotting, data manipulation and processing
9815 of mass spectrometry based proteomics data.")
9816 (license license:artistic2.0)))
9818 (define-public r-msnid
9825 (uri (bioconductor-uri "MSnID" version))
9828 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9829 (properties `((upstream-name . "MSnID")))
9830 (build-system r-build-system)
9832 `(("r-biobase" ,r-biobase)
9833 ("r-data-table" ,r-data-table)
9834 ("r-doparallel" ,r-doparallel)
9835 ("r-dplyr" ,r-dplyr)
9836 ("r-foreach" ,r-foreach)
9837 ("r-iterators" ,r-iterators)
9838 ("r-msnbase" ,r-msnbase)
9841 ("r-protgenerics" ,r-protgenerics)
9842 ("r-r-cache" ,r-r-cache)
9844 ("r-reshape2" ,r-reshape2)))
9845 (home-page "https://bioconductor.org/packages/MSnID")
9846 (synopsis "Utilities for LC-MSn proteomics identifications")
9848 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9849 from mzIdentML (leveraging the mzID package) or text files. After collating
9850 the search results from multiple datasets it assesses their identification
9851 quality and optimize filtering criteria to achieve the maximum number of
9852 identifications while not exceeding a specified false discovery rate. It also
9853 contains a number of utilities to explore the MS/MS results and assess missed
9854 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9855 (license license:artistic2.0)))
9857 (define-public r-seurat
9863 (uri (cran-uri "Seurat" version))
9866 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9867 (properties `((upstream-name . "Seurat")))
9868 (build-system r-build-system)
9871 ("r-cluster" ,r-cluster)
9872 ("r-cowplot" ,r-cowplot)
9873 ("r-dosnow" ,r-dosnow)
9874 ("r-dplyr" ,r-dplyr)
9876 ("r-fitdistrplus" ,r-fitdistrplus)
9877 ("r-foreach" ,r-foreach)
9879 ("r-ggplot2" ,r-ggplot2)
9880 ("r-ggridges" ,r-ggridges)
9881 ("r-gplots" ,r-gplots)
9882 ("r-hdf5r" ,r-hdf5r)
9883 ("r-hmisc" ,r-hmisc)
9886 ("r-igraph" ,r-igraph)
9887 ("r-irlba" ,r-irlba)
9889 ("r-lmtest" ,r-lmtest)
9891 ("r-matrix" ,r-matrix)
9892 ("r-metap" ,r-metap)
9893 ("r-mixtools" ,r-mixtools)
9894 ("r-pbapply" ,r-pbapply)
9895 ("r-plotly" ,r-plotly)
9898 ("r-rcolorbrewer" ,r-rcolorbrewer)
9900 ("r-rcppeigen" ,r-rcppeigen)
9901 ("r-rcppprogress" ,r-rcppprogress)
9902 ("r-reshape2" ,r-reshape2)
9903 ("r-reticulate" ,r-reticulate)
9905 ("r-rtsne" ,r-rtsne)
9906 ("r-sdmtools" ,r-sdmtools)
9907 ("r-tidyr" ,r-tidyr)
9908 ("r-tsne" ,r-tsne)))
9909 (home-page "http://www.satijalab.org/seurat")
9910 (synopsis "Seurat is an R toolkit for single cell genomics")
9912 "This package is an R package designed for QC, analysis, and
9913 exploration of single cell RNA-seq data. It easily enables widely-used
9914 analytical techniques, including the identification of highly variable genes,
9915 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9916 algorithms; density clustering, hierarchical clustering, k-means, and the
9917 discovery of differentially expressed genes and markers.")
9918 (license license:gpl3)))
9920 (define-public r-aroma-light
9922 (name "r-aroma-light")
9927 (uri (bioconductor-uri "aroma.light" version))
9930 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9931 (properties `((upstream-name . "aroma.light")))
9932 (build-system r-build-system)
9934 `(("r-matrixstats" ,r-matrixstats)
9935 ("r-r-methodss3" ,r-r-methodss3)
9937 ("r-r-utils" ,r-r-utils)))
9938 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9939 (synopsis "Methods for normalization and visualization of microarray data")
9941 "This package provides methods for microarray analysis that take basic
9942 data types such as matrices and lists of vectors. These methods can be used
9943 standalone, be utilized in other packages, or be wrapped up in higher-level
9945 (license license:gpl2+)))
9947 (define-public r-deseq
9954 (uri (bioconductor-uri "DESeq" version))
9957 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9958 (properties `((upstream-name . "DESeq")))
9959 (build-system r-build-system)
9961 `(("r-biobase" ,r-biobase)
9962 ("r-biocgenerics" ,r-biocgenerics)
9963 ("r-genefilter" ,r-genefilter)
9964 ("r-geneplotter" ,r-geneplotter)
9965 ("r-lattice" ,r-lattice)
9966 ("r-locfit" ,r-locfit)
9968 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9969 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9970 (synopsis "Differential gene expression analysis")
9972 "This package provides tools for estimating variance-mean dependence in
9973 count data from high-throughput genetic sequencing assays and for testing for
9974 differential expression based on a model using the negative binomial
9976 (license license:gpl3+)))
9978 (define-public r-edaseq
9985 (uri (bioconductor-uri "EDASeq" version))
9988 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9989 (properties `((upstream-name . "EDASeq")))
9990 (build-system r-build-system)
9992 `(("r-annotationdbi" ,r-annotationdbi)
9993 ("r-aroma-light" ,r-aroma-light)
9994 ("r-biobase" ,r-biobase)
9995 ("r-biocgenerics" ,r-biocgenerics)
9996 ("r-biocmanager" ,r-biocmanager)
9997 ("r-biomart" ,r-biomart)
9998 ("r-biostrings" ,r-biostrings)
9999 ("r-deseq" ,r-deseq)
10000 ("r-genomicfeatures" ,r-genomicfeatures)
10001 ("r-genomicranges" ,r-genomicranges)
10002 ("r-iranges" ,r-iranges)
10003 ("r-rsamtools" ,r-rsamtools)
10004 ("r-shortread" ,r-shortread)))
10005 (home-page "https://github.com/drisso/EDASeq")
10006 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
10008 "This package provides support for numerical and graphical summaries of
10009 RNA-Seq genomic read data. Provided within-lane normalization procedures to
10010 adjust for GC-content effect (or other gene-level effects) on read counts:
10011 loess robust local regression, global-scaling, and full-quantile
10012 normalization. Between-lane normalization procedures to adjust for
10013 distributional differences between lanes (e.g., sequencing depth):
10014 global-scaling and full-quantile normalization.")
10015 (license license:artistic2.0)))
10017 (define-public r-interactivedisplaybase
10019 (name "r-interactivedisplaybase")
10024 (uri (bioconductor-uri "interactiveDisplayBase" version))
10027 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
10029 `((upstream-name . "interactiveDisplayBase")))
10030 (build-system r-build-system)
10032 `(("r-biocgenerics" ,r-biocgenerics)
10033 ("r-shiny" ,r-shiny)))
10034 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10035 (synopsis "Base package for web displays of Bioconductor objects")
10037 "This package contains the basic methods needed to generate interactive
10038 Shiny-based display methods for Bioconductor objects.")
10039 (license license:artistic2.0)))
10041 (define-public r-annotationhub
10043 (name "r-annotationhub")
10048 (uri (bioconductor-uri "AnnotationHub" version))
10051 "17fgrvcnbii9siv5rq5j09bxhqffx47f6jf10418qvr7hh61ic1g"))))
10052 (properties `((upstream-name . "AnnotationHub")))
10053 (build-system r-build-system)
10055 `(("r-annotationdbi" ,r-annotationdbi)
10056 ("r-biocgenerics" ,r-biocgenerics)
10057 ("r-biocmanager" ,r-biocmanager)
10060 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10061 ("r-rsqlite" ,r-rsqlite)
10062 ("r-s4vectors" ,r-s4vectors)
10063 ("r-yaml" ,r-yaml)))
10064 (home-page "https://bioconductor.org/packages/AnnotationHub")
10065 (synopsis "Client to access AnnotationHub resources")
10067 "This package provides a client for the Bioconductor AnnotationHub web
10068 resource. The AnnotationHub web resource provides a central location where
10069 genomic files (e.g. VCF, bed, wig) and other resources from standard
10070 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10071 metadata about each resource, e.g., a textual description, tags, and date of
10072 modification. The client creates and manages a local cache of files retrieved
10073 by the user, helping with quick and reproducible access.")
10074 (license license:artistic2.0)))
10076 (define-public r-fastseg
10083 (uri (bioconductor-uri "fastseg" version))
10086 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10087 (build-system r-build-system)
10089 `(("r-biobase" ,r-biobase)
10090 ("r-biocgenerics" ,r-biocgenerics)
10091 ("r-genomicranges" ,r-genomicranges)
10092 ("r-iranges" ,r-iranges)
10093 ("r-s4vectors" ,r-s4vectors)))
10094 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10095 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10097 "Fastseg implements a very fast and efficient segmentation algorithm.
10098 It can segment data from DNA microarrays and data from next generation
10099 sequencing for example to detect copy number segments. Further it can segment
10100 data from RNA microarrays like tiling arrays to identify transcripts. Most
10101 generally, it can segment data given as a matrix or as a vector. Various data
10102 formats can be used as input to fastseg like expression set objects for
10103 microarrays or GRanges for sequencing data.")
10104 (license license:lgpl2.0+)))
10106 (define-public r-keggrest
10108 (name "r-keggrest")
10113 (uri (bioconductor-uri "KEGGREST" version))
10116 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10117 (properties `((upstream-name . "KEGGREST")))
10118 (build-system r-build-system)
10120 `(("r-biostrings" ,r-biostrings)
10123 (home-page "https://bioconductor.org/packages/KEGGREST")
10124 (synopsis "Client-side REST access to KEGG")
10126 "This package provides a package that provides a client interface to the
10127 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10128 (license license:artistic2.0)))
10130 (define-public r-gage
10137 (uri (bioconductor-uri "gage" version))
10140 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
10141 (build-system r-build-system)
10143 `(("r-annotationdbi" ,r-annotationdbi)
10144 ("r-graph" ,r-graph)
10145 ("r-keggrest" ,r-keggrest)))
10146 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10147 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10149 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10150 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10151 data attributes including sample sizes, experimental designs, assay platforms,
10152 and other types of heterogeneity. The gage package provides functions for
10153 basic GAGE analysis, result processing and presentation. In addition, it
10154 provides demo microarray data and commonly used gene set data based on KEGG
10155 pathways and GO terms. These funtions and data are also useful for gene set
10156 analysis using other methods.")
10157 (license license:gpl2+)))
10159 (define-public r-genomicfiles
10161 (name "r-genomicfiles")
10166 (uri (bioconductor-uri "GenomicFiles" version))
10169 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10170 (properties `((upstream-name . "GenomicFiles")))
10171 (build-system r-build-system)
10173 `(("r-biocgenerics" ,r-biocgenerics)
10174 ("r-biocparallel" ,r-biocparallel)
10175 ("r-genomeinfodb" ,r-genomeinfodb)
10176 ("r-genomicalignments" ,r-genomicalignments)
10177 ("r-genomicranges" ,r-genomicranges)
10178 ("r-iranges" ,r-iranges)
10179 ("r-rsamtools" ,r-rsamtools)
10180 ("r-rtracklayer" ,r-rtracklayer)
10181 ("r-s4vectors" ,r-s4vectors)
10182 ("r-summarizedexperiment" ,r-summarizedexperiment)
10183 ("r-variantannotation" ,r-variantannotation)))
10184 (home-page "https://bioconductor.org/packages/GenomicFiles")
10185 (synopsis "Distributed computing by file or by range")
10187 "This package provides infrastructure for parallel computations
10188 distributed by file or by range. User defined mapper and reducer functions
10189 provide added flexibility for data combination and manipulation.")
10190 (license license:artistic2.0)))
10192 (define-public r-complexheatmap
10194 (name "r-complexheatmap")
10199 (uri (bioconductor-uri "ComplexHeatmap" version))
10202 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10204 `((upstream-name . "ComplexHeatmap")))
10205 (build-system r-build-system)
10207 `(("r-circlize" ,r-circlize)
10208 ("r-colorspace" ,r-colorspace)
10209 ("r-getoptlong" ,r-getoptlong)
10210 ("r-globaloptions" ,r-globaloptions)
10211 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10213 "https://github.com/jokergoo/ComplexHeatmap")
10214 (synopsis "Making Complex Heatmaps")
10216 "Complex heatmaps are efficient to visualize associations between
10217 different sources of data sets and reveal potential structures. This package
10218 provides a highly flexible way to arrange multiple heatmaps and supports
10219 self-defined annotation graphics.")
10220 (license license:gpl2+)))
10222 (define-public r-dirichletmultinomial
10224 (name "r-dirichletmultinomial")
10229 (uri (bioconductor-uri "DirichletMultinomial" version))
10232 "19bzn0a5jal1xv0ad6wikxc7wrk582hczqamlln0vb2ffwkj1z3f"))))
10234 `((upstream-name . "DirichletMultinomial")))
10235 (build-system r-build-system)
10239 `(("r-biocgenerics" ,r-biocgenerics)
10240 ("r-iranges" ,r-iranges)
10241 ("r-s4vectors" ,r-s4vectors)))
10242 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10243 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10245 "Dirichlet-multinomial mixture models can be used to describe variability
10246 in microbial metagenomic data. This package is an interface to code
10247 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10249 (license license:lgpl3)))
10251 (define-public r-ensembldb
10253 (name "r-ensembldb")
10258 (uri (bioconductor-uri "ensembldb" version))
10261 "0hdz1f34v7sas2v4225icwl3wd4sf17ykpd5dkbx1hc7wcy4w3np"))))
10262 (build-system r-build-system)
10264 `(("r-annotationdbi" ,r-annotationdbi)
10265 ("r-annotationfilter" ,r-annotationfilter)
10266 ("r-biobase" ,r-biobase)
10267 ("r-biocgenerics" ,r-biocgenerics)
10268 ("r-biostrings" ,r-biostrings)
10271 ("r-genomeinfodb" ,r-genomeinfodb)
10272 ("r-genomicfeatures" ,r-genomicfeatures)
10273 ("r-genomicranges" ,r-genomicranges)
10274 ("r-iranges" ,r-iranges)
10275 ("r-protgenerics" ,r-protgenerics)
10276 ("r-rsamtools" ,r-rsamtools)
10277 ("r-rsqlite" ,r-rsqlite)
10278 ("r-rtracklayer" ,r-rtracklayer)
10279 ("r-s4vectors" ,r-s4vectors)))
10280 (home-page "https://github.com/jotsetung/ensembldb")
10281 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10283 "The package provides functions to create and use transcript-centric
10284 annotation databases/packages. The annotation for the databases are directly
10285 fetched from Ensembl using their Perl API. The functionality and data is
10286 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10287 but, in addition to retrieve all gene/transcript models and annotations from
10288 the database, the @code{ensembldb} package also provides a filter framework
10289 allowing to retrieve annotations for specific entries like genes encoded on a
10290 chromosome region or transcript models of lincRNA genes.")
10291 ;; No version specified
10292 (license license:lgpl3+)))
10294 (define-public r-organismdbi
10296 (name "r-organismdbi")
10301 (uri (bioconductor-uri "OrganismDbi" version))
10304 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10305 (properties `((upstream-name . "OrganismDbi")))
10306 (build-system r-build-system)
10308 `(("r-annotationdbi" ,r-annotationdbi)
10309 ("r-biobase" ,r-biobase)
10310 ("r-biocgenerics" ,r-biocgenerics)
10311 ("r-biocmanager" ,r-biocmanager)
10313 ("r-genomicfeatures" ,r-genomicfeatures)
10314 ("r-genomicranges" ,r-genomicranges)
10315 ("r-graph" ,r-graph)
10316 ("r-iranges" ,r-iranges)
10318 ("r-s4vectors" ,r-s4vectors)))
10319 (home-page "https://bioconductor.org/packages/OrganismDbi")
10320 (synopsis "Software to enable the smooth interfacing of database packages")
10321 (description "The package enables a simple unified interface to several
10322 annotation packages each of which has its own schema by taking advantage of
10323 the fact that each of these packages implements a select methods.")
10324 (license license:artistic2.0)))
10326 (define-public r-biovizbase
10328 (name "r-biovizbase")
10333 (uri (bioconductor-uri "biovizBase" version))
10336 "0v54mcn3rnnfx8dmcrms5z3rgq19n3hp4r23azlgzwq6hjw7cccx"))))
10337 (properties `((upstream-name . "biovizBase")))
10338 (build-system r-build-system)
10340 `(("r-annotationdbi" ,r-annotationdbi)
10341 ("r-annotationfilter" ,r-annotationfilter)
10342 ("r-biocgenerics" ,r-biocgenerics)
10343 ("r-biostrings" ,r-biostrings)
10344 ("r-dichromat" ,r-dichromat)
10345 ("r-ensembldb" ,r-ensembldb)
10346 ("r-genomeinfodb" ,r-genomeinfodb)
10347 ("r-genomicalignments" ,r-genomicalignments)
10348 ("r-genomicfeatures" ,r-genomicfeatures)
10349 ("r-genomicranges" ,r-genomicranges)
10350 ("r-hmisc" ,r-hmisc)
10351 ("r-iranges" ,r-iranges)
10352 ("r-rcolorbrewer" ,r-rcolorbrewer)
10353 ("r-rlang" ,r-rlang)
10354 ("r-rsamtools" ,r-rsamtools)
10355 ("r-s4vectors" ,r-s4vectors)
10356 ("r-scales" ,r-scales)
10357 ("r-summarizedexperiment" ,r-summarizedexperiment)
10358 ("r-variantannotation" ,r-variantannotation)))
10359 (home-page "https://bioconductor.org/packages/biovizBase")
10360 (synopsis "Basic graphic utilities for visualization of genomic data")
10362 "The biovizBase package is designed to provide a set of utilities, color
10363 schemes and conventions for genomic data. It serves as the base for various
10364 high-level packages for biological data visualization. This saves development
10365 effort and encourages consistency.")
10366 (license license:artistic2.0)))
10368 (define-public r-ggbio
10375 (uri (bioconductor-uri "ggbio" version))
10378 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10379 (build-system r-build-system)
10381 `(("r-annotationdbi" ,r-annotationdbi)
10382 ("r-annotationfilter" ,r-annotationfilter)
10383 ("r-biobase" ,r-biobase)
10384 ("r-biocgenerics" ,r-biocgenerics)
10385 ("r-biostrings" ,r-biostrings)
10386 ("r-biovizbase" ,r-biovizbase)
10387 ("r-bsgenome" ,r-bsgenome)
10388 ("r-ensembldb" ,r-ensembldb)
10389 ("r-genomeinfodb" ,r-genomeinfodb)
10390 ("r-genomicalignments" ,r-genomicalignments)
10391 ("r-genomicfeatures" ,r-genomicfeatures)
10392 ("r-genomicranges" ,r-genomicranges)
10393 ("r-ggally" ,r-ggally)
10394 ("r-ggplot2" ,r-ggplot2)
10395 ("r-gridextra" ,r-gridextra)
10396 ("r-gtable" ,r-gtable)
10397 ("r-hmisc" ,r-hmisc)
10398 ("r-iranges" ,r-iranges)
10399 ("r-organismdbi" ,r-organismdbi)
10400 ("r-reshape2" ,r-reshape2)
10401 ("r-rlang" ,r-rlang)
10402 ("r-rsamtools" ,r-rsamtools)
10403 ("r-rtracklayer" ,r-rtracklayer)
10404 ("r-s4vectors" ,r-s4vectors)
10405 ("r-scales" ,r-scales)
10406 ("r-summarizedexperiment" ,r-summarizedexperiment)
10407 ("r-variantannotation" ,r-variantannotation)))
10408 (home-page "http://www.tengfei.name/ggbio/")
10409 (synopsis "Visualization tools for genomic data")
10411 "The ggbio package extends and specializes the grammar of graphics for
10412 biological data. The graphics are designed to answer common scientific
10413 questions, in particular those often asked of high throughput genomics data.
10414 All core Bioconductor data structures are supported, where appropriate. The
10415 package supports detailed views of particular genomic regions, as well as
10416 genome-wide overviews. Supported overviews include ideograms and grand linear
10417 views. High-level plots include sequence fragment length, edge-linked
10418 interval to data view, mismatch pileup, and several splicing summaries.")
10419 (license license:artistic2.0)))
10421 (define-public r-gprofiler
10423 (name "r-gprofiler")
10428 (uri (cran-uri "gProfileR" version))
10431 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10432 (properties `((upstream-name . "gProfileR")))
10433 (build-system r-build-system)
10435 `(("r-plyr" ,r-plyr)
10436 ("r-rcurl" ,r-rcurl)))
10437 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10438 (synopsis "Interface to the g:Profiler toolkit")
10440 "This package provides tools for functional enrichment analysis,
10441 gene identifier conversion and mapping homologous genes across related
10442 organisms via the @code{g:Profiler} toolkit.")
10443 (license license:gpl2+)))
10445 (define-public r-gqtlbase
10447 (name "r-gqtlbase")
10452 (uri (bioconductor-uri "gQTLBase" version))
10455 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10456 (properties `((upstream-name . "gQTLBase")))
10457 (build-system r-build-system)
10459 `(("r-batchjobs" ,r-batchjobs)
10460 ("r-bbmisc" ,r-bbmisc)
10461 ("r-biocgenerics" ,r-biocgenerics)
10463 ("r-doparallel" ,r-doparallel)
10465 ("r-ffbase" ,r-ffbase)
10466 ("r-foreach" ,r-foreach)
10467 ("r-genomicfiles" ,r-genomicfiles)
10468 ("r-genomicranges" ,r-genomicranges)
10469 ("r-rtracklayer" ,r-rtracklayer)
10470 ("r-s4vectors" ,r-s4vectors)
10471 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10472 (home-page "https://bioconductor.org/packages/gQTLBase")
10473 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10475 "The purpose of this package is to simplify the storage and interrogation
10476 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10478 (license license:artistic2.0)))
10480 (define-public r-snpstats
10482 (name "r-snpstats")
10487 (uri (bioconductor-uri "snpStats" version))
10490 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10491 (properties `((upstream-name . "snpStats")))
10492 (build-system r-build-system)
10493 (inputs `(("zlib" ,zlib)))
10495 `(("r-biocgenerics" ,r-biocgenerics)
10496 ("r-matrix" ,r-matrix)
10497 ("r-survival" ,r-survival)
10498 ("r-zlibbioc" ,r-zlibbioc)))
10499 (home-page "https://bioconductor.org/packages/snpStats")
10500 (synopsis "Methods for SNP association studies")
10502 "This package provides classes and statistical methods for large
10503 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10504 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10505 (license license:gpl3)))
10507 (define-public r-homo-sapiens
10509 (name "r-homo-sapiens")
10513 ;; We cannot use bioconductor-uri here because this tarball is
10514 ;; located under "data/annotation/" instead of "bioc/".
10515 (uri (string-append "http://www.bioconductor.org/packages/"
10516 "release/data/annotation/src/contrib/"
10518 version ".tar.gz"))
10521 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10523 `((upstream-name . "Homo.sapiens")))
10524 (build-system r-build-system)
10526 `(("r-genomicfeatures" ,r-genomicfeatures)
10527 ("r-go-db" ,r-go-db)
10528 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10529 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10530 ("r-organismdbi" ,r-organismdbi)
10531 ("r-annotationdbi" ,r-annotationdbi)))
10532 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10533 (synopsis "Annotation package for the Homo.sapiens object")
10535 "This package contains the Homo.sapiens object to access data from
10536 several related annotation packages.")
10537 (license license:artistic2.0)))
10539 (define-public r-erma
10546 (uri (bioconductor-uri "erma" version))
10549 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10550 (build-system r-build-system)
10552 `(("r-annotationdbi" ,r-annotationdbi)
10553 ("r-biobase" ,r-biobase)
10554 ("r-biocgenerics" ,r-biocgenerics)
10555 ("r-biocparallel" ,r-biocparallel)
10556 ("r-genomeinfodb" ,r-genomeinfodb)
10557 ("r-genomicfiles" ,r-genomicfiles)
10558 ("r-genomicranges" ,r-genomicranges)
10559 ("r-ggplot2" ,r-ggplot2)
10560 ("r-homo-sapiens" ,r-homo-sapiens)
10561 ("r-iranges" ,r-iranges)
10562 ("r-rtracklayer" ,r-rtracklayer)
10563 ("r-s4vectors" ,r-s4vectors)
10564 ("r-shiny" ,r-shiny)
10565 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10566 (home-page "https://bioconductor.org/packages/erma")
10567 (synopsis "Epigenomic road map adventures")
10569 "The epigenomics road map describes locations of epigenetic marks in DNA
10570 from a variety of cell types. Of interest are locations of histone
10571 modifications, sites of DNA methylation, and regions of accessible chromatin.
10572 This package presents a selection of elements of the road map including
10573 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10574 by Ernst and Kellis.")
10575 (license license:artistic2.0)))
10577 (define-public r-ldblock
10584 (uri (bioconductor-uri "ldblock" version))
10587 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10588 (build-system r-build-system)
10590 `(("r-biocgenerics" ,r-biocgenerics)
10592 ("r-genomeinfodb" ,r-genomeinfodb)
10593 ("r-genomicfiles" ,r-genomicfiles)
10594 ("r-go-db" ,r-go-db)
10595 ("r-homo-sapiens" ,r-homo-sapiens)
10596 ("r-matrix" ,r-matrix)
10597 ("r-rsamtools" ,r-rsamtools)
10598 ("r-snpstats" ,r-snpstats)
10599 ("r-variantannotation" ,r-variantannotation)))
10600 (home-page "https://bioconductor.org/packages/ldblock")
10601 (synopsis "Data structures for linkage disequilibrium measures in populations")
10603 "This package defines data structures for @dfn{linkage
10604 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10605 handling of existing population-level data for the purpose of flexibly
10606 defining LD blocks.")
10607 (license license:artistic2.0)))
10609 (define-public r-gqtlstats
10611 (name "r-gqtlstats")
10616 (uri (bioconductor-uri "gQTLstats" version))
10619 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10620 (properties `((upstream-name . "gQTLstats")))
10621 (build-system r-build-system)
10623 `(("r-annotationdbi" ,r-annotationdbi)
10624 ("r-batchjobs" ,r-batchjobs)
10625 ("r-bbmisc" ,r-bbmisc)
10626 ("r-beeswarm" ,r-beeswarm)
10627 ("r-biobase" ,r-biobase)
10628 ("r-biocgenerics" ,r-biocgenerics)
10629 ("r-doparallel" ,r-doparallel)
10630 ("r-dplyr" ,r-dplyr)
10632 ("r-ffbase" ,r-ffbase)
10633 ("r-foreach" ,r-foreach)
10634 ("r-genomeinfodb" ,r-genomeinfodb)
10635 ("r-genomicfeatures" ,r-genomicfeatures)
10636 ("r-genomicfiles" ,r-genomicfiles)
10637 ("r-genomicranges" ,r-genomicranges)
10638 ("r-ggbeeswarm" ,r-ggbeeswarm)
10639 ("r-ggplot2" ,r-ggplot2)
10640 ("r-gqtlbase" ,r-gqtlbase)
10641 ("r-hardyweinberg" ,r-hardyweinberg)
10642 ("r-homo-sapiens" ,r-homo-sapiens)
10643 ("r-iranges" ,r-iranges)
10644 ("r-limma" ,r-limma)
10646 ("r-plotly" ,r-plotly)
10647 ("r-reshape2" ,r-reshape2)
10648 ("r-s4vectors" ,r-s4vectors)
10649 ("r-shiny" ,r-shiny)
10650 ("r-snpstats" ,r-snpstats)
10651 ("r-summarizedexperiment" ,r-summarizedexperiment)
10652 ("r-variantannotation" ,r-variantannotation)))
10653 (home-page "https://bioconductor.org/packages/gQTLstats")
10654 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10656 "This package provides tools for the computationally efficient analysis
10657 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10658 The software in this package aims to support refinements and functional
10659 interpretation of members of a collection of association statistics on a
10660 family of feature/genome hypotheses.")
10661 (license license:artistic2.0)))
10663 (define-public r-gviz
10670 (uri (bioconductor-uri "Gviz" version))
10673 "05zk9hf30afg6rjg97lzn5v8xij90v8zm09y9vcz0asmc3c8xs0a"))))
10674 (properties `((upstream-name . "Gviz")))
10675 (build-system r-build-system)
10677 `(("r-annotationdbi" ,r-annotationdbi)
10678 ("r-biobase" ,r-biobase)
10679 ("r-biocgenerics" ,r-biocgenerics)
10680 ("r-biomart" ,r-biomart)
10681 ("r-biostrings" ,r-biostrings)
10682 ("r-biovizbase" ,r-biovizbase)
10683 ("r-bsgenome" ,r-bsgenome)
10684 ("r-digest" ,r-digest)
10685 ("r-genomeinfodb" ,r-genomeinfodb)
10686 ("r-genomicalignments" ,r-genomicalignments)
10687 ("r-genomicfeatures" ,r-genomicfeatures)
10688 ("r-genomicranges" ,r-genomicranges)
10689 ("r-iranges" ,r-iranges)
10690 ("r-lattice" ,r-lattice)
10691 ("r-latticeextra" ,r-latticeextra)
10692 ("r-matrixstats" ,r-matrixstats)
10693 ("r-rcolorbrewer" ,r-rcolorbrewer)
10694 ("r-rsamtools" ,r-rsamtools)
10695 ("r-rtracklayer" ,r-rtracklayer)
10696 ("r-s4vectors" ,r-s4vectors)
10697 ("r-xvector" ,r-xvector)))
10698 (home-page "https://bioconductor.org/packages/Gviz")
10699 (synopsis "Plotting data and annotation information along genomic coordinates")
10701 "Genomic data analyses requires integrated visualization of known genomic
10702 information and new experimental data. Gviz uses the biomaRt and the
10703 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10704 and translates this to e.g. gene/transcript structures in viewports of the
10705 grid graphics package. This results in genomic information plotted together
10707 (license license:artistic2.0)))
10709 (define-public r-gwascat
10716 (uri (bioconductor-uri "gwascat" version))
10719 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10720 (build-system r-build-system)
10722 `(("r-annotationdbi" ,r-annotationdbi)
10723 ("r-annotationhub" ,r-annotationhub)
10724 ("r-biocgenerics" ,r-biocgenerics)
10725 ("r-biostrings" ,r-biostrings)
10726 ("r-genomeinfodb" ,r-genomeinfodb)
10727 ("r-genomicfeatures" ,r-genomicfeatures)
10728 ("r-genomicranges" ,r-genomicranges)
10729 ("r-ggbio" ,r-ggbio)
10730 ("r-ggplot2" ,r-ggplot2)
10731 ("r-gqtlstats" ,r-gqtlstats)
10732 ("r-graph" ,r-graph)
10734 ("r-homo-sapiens" ,r-homo-sapiens)
10735 ("r-iranges" ,r-iranges)
10736 ("r-rsamtools" ,r-rsamtools)
10737 ("r-rtracklayer" ,r-rtracklayer)
10738 ("r-s4vectors" ,r-s4vectors)
10739 ("r-snpstats" ,r-snpstats)
10740 ("r-summarizedexperiment" ,r-summarizedexperiment)
10741 ("r-variantannotation" ,r-variantannotation)))
10742 (home-page "https://bioconductor.org/packages/gwascat")
10743 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10745 "This package provides tools for representing and modeling data in the
10746 EMBL-EBI GWAS catalog.")
10747 (license license:artistic2.0)))
10749 (define-public r-sushi
10755 (uri (bioconductor-uri "Sushi" version))
10758 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10759 (properties `((upstream-name . "Sushi")))
10760 (build-system r-build-system)
10762 `(("r-biomart" ,r-biomart)
10764 (home-page "https://bioconductor.org/packages/Sushi")
10765 (synopsis "Tools for visualizing genomics data")
10767 "This package provides flexible, quantitative, and integrative genomic
10768 visualizations for publication-quality multi-panel figures.")
10769 (license license:gpl2+)))
10771 (define-public r-fithic
10777 (uri (bioconductor-uri "FitHiC" version))
10780 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10781 (properties `((upstream-name . "FitHiC")))
10782 (build-system r-build-system)
10784 `(("r-data-table" ,r-data-table)
10785 ("r-fdrtool" ,r-fdrtool)
10786 ("r-rcpp" ,r-rcpp)))
10787 (home-page "https://bioconductor.org/packages/FitHiC")
10788 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10790 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10791 intra-chromosomal contact maps produced by genome-wide genome architecture
10792 assays such as Hi-C.")
10793 (license license:gpl2+)))
10795 (define-public r-hitc
10801 (uri (bioconductor-uri "HiTC" version))
10804 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10805 (properties `((upstream-name . "HiTC")))
10806 (build-system r-build-system)
10808 `(("r-biostrings" ,r-biostrings)
10809 ("r-genomeinfodb" ,r-genomeinfodb)
10810 ("r-genomicranges" ,r-genomicranges)
10811 ("r-iranges" ,r-iranges)
10812 ("r-matrix" ,r-matrix)
10813 ("r-rcolorbrewer" ,r-rcolorbrewer)
10814 ("r-rtracklayer" ,r-rtracklayer)))
10815 (home-page "https://bioconductor.org/packages/HiTC")
10816 (synopsis "High throughput chromosome conformation capture analysis")
10818 "The HiTC package was developed to explore high-throughput \"C\" data
10819 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10820 quality controls, normalization, visualization, and further analysis are also
10822 (license license:artistic2.0)))
10824 (define-public r-qvalue
10831 (uri (bioconductor-uri "qvalue" version))
10834 "03qxshqwwq1rj23p6pjrz08jm3ziikvy9badi4mz2rcwy2nz783a"))))
10835 (build-system r-build-system)
10837 `(("r-ggplot2" ,r-ggplot2)
10838 ("r-reshape2" ,r-reshape2)))
10839 (home-page "http://github.com/jdstorey/qvalue")
10840 (synopsis "Q-value estimation for false discovery rate control")
10842 "This package takes a list of p-values resulting from the simultaneous
10843 testing of many hypotheses and estimates their q-values and local @dfn{false
10844 discovery rate} (FDR) values. The q-value of a test measures the proportion
10845 of false positives incurred when that particular test is called significant.
10846 The local FDR measures the posterior probability the null hypothesis is true
10847 given the test's p-value. Various plots are automatically generated, allowing
10848 one to make sensible significance cut-offs. The software can be applied to
10849 problems in genomics, brain imaging, astrophysics, and data mining.")
10850 ;; Any version of the LGPL.
10851 (license license:lgpl3+)))
10853 (define-public r-hdf5array
10855 (name "r-hdf5array")
10860 (uri (bioconductor-uri "HDF5Array" version))
10863 "1w7ad8cfsbh5xx82m3l4lc0vbmj9lcsqxxpiy3ana2ycgn1bqv3g"))))
10864 (properties `((upstream-name . "HDF5Array")))
10865 (build-system r-build-system)
10867 `(("r-biocgenerics" ,r-biocgenerics)
10868 ("r-delayedarray" ,r-delayedarray)
10869 ("r-iranges" ,r-iranges)
10870 ("r-rhdf5" ,r-rhdf5)
10871 ("r-s4vectors" ,r-s4vectors)))
10872 (home-page "https://bioconductor.org/packages/HDF5Array")
10873 (synopsis "HDF5 back end for DelayedArray objects")
10874 (description "This package provides an array-like container for convenient
10875 access and manipulation of HDF5 datasets. It supports delayed operations and
10876 block processing.")
10877 (license license:artistic2.0)))
10879 (define-public r-rhdf5lib
10881 (name "r-rhdf5lib")
10886 (uri (bioconductor-uri "Rhdf5lib" version))
10889 "01gpz780g850ql20b2ql6pvr678ydk4nq4sn5iiih94a4crb9lz1"))
10890 (modules '((guix build utils)))
10893 ;; Delete bundled binaries
10894 (delete-file-recursively "src/winlib/")
10896 (properties `((upstream-name . "Rhdf5lib")))
10897 (build-system r-build-system)
10900 (modify-phases %standard-phases
10901 (add-after 'unpack 'do-not-use-bundled-hdf5
10902 (lambda* (#:key inputs #:allow-other-keys)
10903 (for-each delete-file '("configure" "configure.ac"))
10904 ;; Do not make other packages link with the proprietary libsz.
10905 (substitute* "R/zzz.R"
10906 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10907 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10908 (("'%s/libhdf5.a %s/libsz.a -lz'")
10909 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10910 (with-directory-excursion "src"
10911 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10912 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10914 ;; Remove timestamp and host system information to make
10915 ;; the build reproducible.
10916 (substitute* "hdf5/src/libhdf5.settings.in"
10917 (("Configured on: @CONFIG_DATE@")
10918 "Configured on: Guix")
10919 (("Uname information:.*")
10920 "Uname information: Linux\n")
10921 ;; Remove unnecessary store reference.
10923 "C Compiler: GCC\n"))
10924 (rename-file "Makevars.in" "Makevars")
10925 (substitute* "Makevars"
10926 (("HDF5_CXX_LIB=.*")
10927 (string-append "HDF5_CXX_LIB="
10928 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10930 (string-append "HDF5_LIB="
10931 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10932 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10933 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10934 ;; szip is non-free software
10935 (("cp \\$\\{SZIP_LIB\\}.*") "")
10936 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10941 `(("hdf5" ,hdf5-1.10)))
10943 `(("hdf5-source" ,(package-source hdf5-1.10))))
10944 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10945 (synopsis "HDF5 library as an R package")
10946 (description "This package provides C and C++ HDF5 libraries for use in R
10948 (license license:artistic2.0)))
10950 (define-public r-beachmat
10952 (name "r-beachmat")
10957 (uri (bioconductor-uri "beachmat" version))
10960 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10961 (build-system r-build-system)
10966 `(("r-biocgenerics" ,r-biocgenerics)
10967 ("r-delayedarray" ,r-delayedarray)
10968 ("r-hdf5array" ,r-hdf5array)
10970 ("r-rhdf5" ,r-rhdf5)
10971 ("r-rhdf5lib" ,r-rhdf5lib)))
10972 (home-page "https://bioconductor.org/packages/beachmat")
10973 (synopsis "Compiling Bioconductor to handle each matrix type")
10974 (description "This package provides a consistent C++ class interface for a
10975 variety of commonly used matrix types, including sparse and HDF5-backed
10977 (license license:gpl3)))
10979 (define-public r-singlecellexperiment
10981 (name "r-singlecellexperiment")
10986 (uri (bioconductor-uri "SingleCellExperiment" version))
10989 "19r4r7djrn46qlijkj1g926vcklxzcrxjlxv6cg43m9j9jgfs3dj"))))
10991 `((upstream-name . "SingleCellExperiment")))
10992 (build-system r-build-system)
10994 `(("r-biocgenerics" ,r-biocgenerics)
10995 ("r-s4vectors" ,r-s4vectors)
10996 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10997 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10998 (synopsis "S4 classes for single cell data")
10999 (description "This package defines an S4 class for storing data from
11000 single-cell experiments. This includes specialized methods to store and
11001 retrieve spike-in information, dimensionality reduction coordinates and size
11002 factors for each cell, along with the usual metadata for genes and
11004 (license license:gpl3)))
11006 (define-public r-scater
11012 (uri (bioconductor-uri "scater" version))
11015 "1kwa9n70c5j0xcj6nkmlkzjr63cnj78mp8nhg58n07fq1ijm4ns3"))))
11016 (build-system r-build-system)
11018 `(("r-beachmat" ,r-beachmat)
11019 ("r-biocgenerics" ,r-biocgenerics)
11020 ("r-biocparallel" ,r-biocparallel)
11021 ("r-delayedarray" ,r-delayedarray)
11022 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11023 ("r-dplyr" ,r-dplyr)
11024 ("r-ggbeeswarm" ,r-ggbeeswarm)
11025 ("r-ggplot2" ,r-ggplot2)
11026 ("r-matrix" ,r-matrix)
11029 ("r-reshape2" ,r-reshape2)
11030 ("r-rhdf5lib" ,r-rhdf5lib)
11031 ("r-s4vectors" ,r-s4vectors)
11032 ("r-singlecellexperiment" ,r-singlecellexperiment)
11033 ("r-summarizedexperiment" ,r-summarizedexperiment)
11034 ("r-viridis" ,r-viridis)))
11035 (home-page "https://github.com/davismcc/scater")
11036 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11037 (description "This package provides a collection of tools for doing
11038 various analyses of single-cell RNA-seq gene expression data, with a focus on
11040 (license license:gpl2+)))
11042 (define-public r-scran
11049 (uri (bioconductor-uri "scran" version))
11052 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
11053 (build-system r-build-system)
11055 `(("r-beachmat" ,r-beachmat)
11056 ("r-biocgenerics" ,r-biocgenerics)
11057 ("r-biocneighbors" ,r-biocneighbors)
11058 ("r-biocparallel" ,r-biocparallel)
11059 ("r-delayedarray" ,r-delayedarray)
11060 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11061 ("r-dynamictreecut" ,r-dynamictreecut)
11062 ("r-edger" ,r-edger)
11063 ("r-igraph" ,r-igraph)
11064 ("r-limma" ,r-limma)
11065 ("r-matrix" ,r-matrix)
11067 ("r-rhdf5lib" ,r-rhdf5lib)
11068 ("r-s4vectors" ,r-s4vectors)
11069 ("r-scater" ,r-scater)
11070 ("r-singlecellexperiment" ,r-singlecellexperiment)
11071 ("r-statmod" ,r-statmod)
11072 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11073 (home-page "https://bioconductor.org/packages/scran")
11074 (synopsis "Methods for single-cell RNA-Seq data analysis")
11075 (description "This package implements a variety of low-level analyses of
11076 single-cell RNA-seq data. Methods are provided for normalization of
11077 cell-specific biases, assignment of cell cycle phase, and detection of highly
11078 variable and significantly correlated genes.")
11079 (license license:gpl3)))
11081 (define-public r-delayedmatrixstats
11083 (name "r-delayedmatrixstats")
11088 (uri (bioconductor-uri "DelayedMatrixStats" version))
11091 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11093 `((upstream-name . "DelayedMatrixStats")))
11094 (build-system r-build-system)
11096 `(("r-biocparallel" ,r-biocparallel)
11097 ("r-delayedarray" ,r-delayedarray)
11098 ("r-hdf5array" ,r-hdf5array)
11099 ("r-iranges" ,r-iranges)
11100 ("r-matrix" ,r-matrix)
11101 ("r-matrixstats" ,r-matrixstats)
11102 ("r-s4vectors" ,r-s4vectors)))
11103 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11104 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11106 "This package provides a port of the @code{matrixStats} API for use with
11107 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11108 contains high-performing functions operating on rows and columns of
11109 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11110 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11111 are optimized per data type and for subsetted calculations such that both
11112 memory usage and processing time is minimized.")
11113 (license license:expat)))
11115 (define-public r-phangorn
11117 (name "r-phangorn")
11122 (uri (cran-uri "phangorn" version))
11125 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11126 (build-system r-build-system)
11129 ("r-fastmatch" ,r-fastmatch)
11130 ("r-igraph" ,r-igraph)
11131 ("r-magrittr" ,r-magrittr)
11132 ("r-matrix" ,r-matrix)
11133 ("r-quadprog" ,r-quadprog)
11134 ("r-rcpp" ,r-rcpp)))
11135 (home-page "https://github.com/KlausVigo/phangorn")
11136 (synopsis "Phylogenetic analysis in R")
11138 "Phangorn is a package for phylogenetic analysis in R. It supports
11139 estimation of phylogenetic trees and networks using Maximum Likelihood,
11140 Maximum Parsimony, distance methods and Hadamard conjugation.")
11141 (license license:gpl2+)))
11143 (define-public r-dropbead
11144 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11147 (name "r-dropbead")
11148 (version (string-append "0-" revision "." (string-take commit 7)))
11152 (uri (git-reference
11153 (url "https://github.com/rajewsky-lab/dropbead.git")
11155 (file-name (git-file-name name version))
11158 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11159 (build-system r-build-system)
11161 `(("r-ggplot2" ,r-ggplot2)
11162 ("r-rcolorbrewer" ,r-rcolorbrewer)
11163 ("r-gridextra" ,r-gridextra)
11164 ("r-gplots" ,r-gplots)
11165 ("r-plyr" ,r-plyr)))
11166 (home-page "https://github.com/rajewsky-lab/dropbead")
11167 (synopsis "Basic exploration and analysis of Drop-seq data")
11168 (description "This package offers a quick and straight-forward way to
11169 explore and perform basic analysis of single cell sequencing data coming from
11170 droplet sequencing. It has been particularly tailored for Drop-seq.")
11171 (license license:gpl3))))
11173 (define htslib-for-sambamba
11174 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11177 (name "htslib-for-sambamba")
11178 (version (string-append "1.3.1-1." (string-take commit 9)))
11182 (uri (git-reference
11183 (url "https://github.com/lomereiter/htslib.git")
11185 (file-name (string-append "htslib-" version "-checkout"))
11188 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11190 `(("autoconf" ,autoconf)
11191 ("automake" ,automake)
11192 ,@(package-native-inputs htslib))))))
11194 (define-public sambamba
11201 (uri (git-reference
11202 (url "https://github.com/lomereiter/sambamba.git")
11203 (commit (string-append "v" version))))
11204 (file-name (string-append name "-" version "-checkout"))
11207 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
11208 (build-system gnu-build-system)
11210 `(#:tests? #f ; there is no test target
11211 #:parallel-build? #f ; not supported
11213 (modify-phases %standard-phases
11214 (delete 'configure)
11215 (add-after 'unpack 'fix-ldc-version
11217 (substitute* "gen_ldc_version_info.py"
11218 (("/usr/bin/env.*") (which "python3")))
11219 (substitute* "Makefile"
11220 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11221 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11223 (add-after 'unpack 'place-biod-and-undead
11224 (lambda* (#:key inputs #:allow-other-keys)
11225 (copy-recursively (assoc-ref inputs "biod") "BioD")
11226 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11228 (add-after 'unpack 'unbundle-prerequisites
11230 (substitute* "Makefile"
11231 (("htslib/libhts.a lz4/lib/liblz4.a")
11233 ((" lz4-static htslib-static") ""))
11236 (lambda* (#:key outputs #:allow-other-keys)
11237 (let* ((out (assoc-ref outputs "out"))
11238 (bin (string-append out "/bin")))
11240 (install-file "bin/sambamba" bin)
11245 ("python" ,python-minimal)
11247 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
11250 (uri (git-reference
11251 (url "https://github.com/biod/BioD.git")
11253 (file-name (string-append "biod-"
11254 (string-take commit 9)
11258 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
11260 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
11263 (uri (git-reference
11264 (url "https://github.com/biod/undeaD.git")
11266 (file-name (string-append "undead-"
11267 (string-take commit 9)
11271 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11274 ("htslib" ,htslib-for-sambamba)))
11275 (home-page "http://lomereiter.github.io/sambamba")
11276 (synopsis "Tools for working with SAM/BAM data")
11277 (description "Sambamba is a high performance modern robust and
11278 fast tool (and library), written in the D programming language, for
11279 working with SAM and BAM files. Current parallelised functionality is
11280 an important subset of samtools functionality, including view, index,
11281 sort, markdup, and depth.")
11282 (license license:gpl2+)))
11284 (define-public ritornello
11286 (name "ritornello")
11290 (uri (git-reference
11291 (url "https://github.com/KlugerLab/Ritornello.git")
11292 (commit (string-append "v" version))))
11293 (file-name (git-file-name name version))
11296 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11297 (build-system gnu-build-system)
11299 `(#:tests? #f ; there are no tests
11301 (modify-phases %standard-phases
11302 (add-after 'unpack 'patch-samtools-references
11303 (lambda* (#:key inputs #:allow-other-keys)
11304 (substitute* '("src/SamStream.h"
11306 (("<sam.h>") "<samtools/sam.h>"))
11308 (delete 'configure)
11310 (lambda* (#:key inputs outputs #:allow-other-keys)
11311 (let* ((out (assoc-ref outputs "out"))
11312 (bin (string-append out "/bin/")))
11314 (install-file "bin/Ritornello" bin)
11317 `(("samtools" ,samtools-0.1)
11321 (home-page "https://github.com/KlugerLab/Ritornello")
11322 (synopsis "Control-free peak caller for ChIP-seq data")
11323 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11324 signal processing that can accurately call binding events without the need to
11325 do a pair total DNA input or IgG control sample. It has been tested for use
11326 with narrow binding events such as transcription factor ChIP-seq.")
11327 (license license:gpl3+)))
11329 (define-public trim-galore
11331 (name "trim-galore")
11336 (uri (git-reference
11337 (url "https://github.com/FelixKrueger/TrimGalore.git")
11339 (file-name (string-append name "-" version "-checkout"))
11342 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11343 (build-system gnu-build-system)
11345 `(#:tests? #f ; no tests
11347 (modify-phases %standard-phases
11348 (delete 'configure)
11350 (add-after 'unpack 'hardcode-tool-references
11351 (lambda* (#:key inputs #:allow-other-keys)
11352 (substitute* "trim_galore"
11353 (("\\$path_to_cutadapt = 'cutadapt'")
11354 (string-append "$path_to_cutadapt = '"
11355 (assoc-ref inputs "cutadapt")
11358 (string-append "| "
11359 (assoc-ref inputs "gzip")
11362 (string-append "\""
11363 (assoc-ref inputs "gzip")
11367 (lambda* (#:key outputs #:allow-other-keys)
11368 (let ((bin (string-append (assoc-ref outputs "out")
11371 (install-file "trim_galore" bin)
11376 ("cutadapt" ,cutadapt)))
11378 `(("unzip" ,unzip)))
11379 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11380 (synopsis "Wrapper around Cutadapt and FastQC")
11381 (description "Trim Galore! is a wrapper script to automate quality and
11382 adapter trimming as well as quality control, with some added functionality to
11383 remove biased methylation positions for RRBS sequence files.")
11384 (license license:gpl3+)))
11386 (define-public gess
11392 (uri (string-append "http://compbio.uthscsa.edu/"
11394 "gess-" version ".src.tar.gz"))
11397 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11398 (build-system gnu-build-system)
11400 `(#:tests? #f ; no tests
11402 (modify-phases %standard-phases
11403 (delete 'configure)
11406 (lambda* (#:key inputs outputs #:allow-other-keys)
11407 (let* ((python (assoc-ref inputs "python"))
11408 (out (assoc-ref outputs "out"))
11409 (bin (string-append out "/bin/"))
11410 (target (string-append
11412 ,(version-major+minor
11413 (package-version python))
11414 "/site-packages/gess/")))
11416 (copy-recursively "." target)
11417 ;; Make GESS.py executable
11418 (chmod (string-append target "GESS.py") #o555)
11419 ;; Add Python shebang to the top and make Matplotlib
11421 (substitute* (string-append target "GESS.py")
11422 (("\"\"\"Description:" line)
11423 (string-append "#!" (which "python") "
11425 matplotlib.use('Agg')
11427 ;; Make sure GESS has all modules in its path
11428 (wrap-program (string-append target "GESS.py")
11429 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11431 (symlink (string-append target "GESS.py")
11432 (string-append bin "GESS.py"))
11435 `(("python" ,python-2)
11436 ("python2-pysam" ,python2-pysam)
11437 ("python2-scipy" ,python2-scipy)
11438 ("python2-numpy" ,python2-numpy)
11439 ("python2-networkx" ,python2-networkx)
11440 ("python2-biopython" ,python2-biopython)))
11441 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11442 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11444 "GESS is an implementation of a novel computational method to detect de
11445 novo exon-skipping events directly from raw RNA-seq data without the prior
11446 knowledge of gene annotation information. GESS stands for the graph-based
11447 exon-skipping scanner detection scheme.")
11448 (license license:bsd-3)))
11450 (define-public phylip
11457 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11458 "download/phylip-" version ".tar.gz"))
11461 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11462 (build-system gnu-build-system)
11464 `(#:tests? #f ; no check target
11465 #:make-flags (list "-f" "Makefile.unx" "install")
11466 #:parallel-build? #f ; not supported
11468 (modify-phases %standard-phases
11469 (add-after 'unpack 'enter-dir
11470 (lambda _ (chdir "src") #t))
11471 (delete 'configure)
11473 (lambda* (#:key inputs outputs #:allow-other-keys)
11474 (let ((target (string-append (assoc-ref outputs "out")
11477 (for-each (lambda (file)
11478 (install-file file target))
11479 (find-files "../exe" ".*")))
11481 (home-page "http://evolution.genetics.washington.edu/phylip/")
11482 (synopsis "Tools for inferring phylogenies")
11483 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11484 programs for inferring phylogenies (evolutionary trees).")
11485 (license license:bsd-2)))
11494 (uri (string-append "https://integrativemodeling.org/"
11495 version "/download/imp-" version ".tar.gz"))
11498 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11499 (build-system cmake-build-system)
11501 `(;; FIXME: Some tests fail because they produce warnings, others fail
11502 ;; because the PYTHONPATH does not include the modeller's directory.
11510 ("python" ,python-2)))
11512 `(("python2-numpy" ,python2-numpy)
11513 ("python2-scipy" ,python2-scipy)
11514 ("python2-pandas" ,python2-pandas)
11515 ("python2-scikit-learn" ,python2-scikit-learn)
11516 ("python2-networkx" ,python2-networkx)))
11517 (home-page "https://integrativemodeling.org")
11518 (synopsis "Integrative modeling platform")
11519 (description "IMP's broad goal is to contribute to a comprehensive
11520 structural characterization of biomolecules ranging in size and complexity
11521 from small peptides to large macromolecular assemblies, by integrating data
11522 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11523 Python toolbox for solving complex modeling problems, and a number of
11524 applications for tackling some common problems in a user-friendly way.")
11525 ;; IMP is largely available under the GNU Lesser GPL; see the file
11526 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11527 ;; available under the GNU GPL (see the file COPYING.GPL).
11528 (license (list license:lgpl2.1+
11531 (define-public tadbit
11537 (uri (git-reference
11538 (url "https://github.com/3DGenomes/TADbit.git")
11539 (commit (string-append "v" version))))
11540 (file-name (git-file-name name version))
11543 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11544 (build-system python-build-system)
11546 `(;; Tests are included and must be run after installation, but
11547 ;; they are incomplete and thus cannot be run.
11551 (modify-phases %standard-phases
11552 (add-after 'unpack 'fix-problems-with-setup.py
11553 (lambda* (#:key outputs #:allow-other-keys)
11554 ;; setup.py opens these files for writing
11555 (chmod "_pytadbit/_version.py" #o664)
11556 (chmod "README.rst" #o664)
11558 ;; Don't attempt to install the bash completions to
11559 ;; the home directory.
11560 (rename-file "extras/.bash_completion"
11562 (substitute* "setup.py"
11563 (("\\(path.expanduser\\('~'\\)")
11564 (string-append "(\""
11565 (assoc-ref outputs "out")
11566 "/etc/bash_completion.d\""))
11567 (("extras/\\.bash_completion")
11571 ;; TODO: add Chimera for visualization
11574 ("python2-scipy" ,python2-scipy)
11575 ("python2-numpy" ,python2-numpy)
11576 ("python2-matplotlib" ,python2-matplotlib)
11577 ("python2-pysam" ,python2-pysam)))
11578 (home-page "https://3dgenomes.github.io/TADbit/")
11579 (synopsis "Analyze, model, and explore 3C-based data")
11581 "TADbit is a complete Python library to deal with all steps to analyze,
11582 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11583 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11584 correct interaction matrices, identify and compare the so-called
11585 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11586 interaction matrices, and finally, extract structural properties from the
11587 models. TADbit is complemented by TADkit for visualizing 3D models.")
11588 (license license:gpl3+)))
11590 (define-public kentutils
11593 ;; 302.1.0 is out, but the only difference is the inclusion of
11594 ;; pre-built binaries.
11595 (version "302.0.0")
11599 (uri (git-reference
11600 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11601 (commit (string-append "v" version))))
11602 (file-name (git-file-name name version))
11605 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11606 (modules '((guix build utils)
11611 ;; Only the contents of the specified directories are free
11612 ;; for all uses, so we remove the rest. "hg/autoSql" and
11613 ;; "hg/autoXml" are nominally free, but they depend on a
11614 ;; library that is built from the sources in "hg/lib",
11615 ;; which is nonfree.
11616 (let ((free (list "." ".."
11617 "utils" "lib" "inc" "tagStorm"
11618 "parasol" "htslib"))
11619 (directory? (lambda (file)
11620 (eq? 'directory (stat:type (stat file))))))
11621 (for-each (lambda (file)
11622 (and (directory? file)
11623 (delete-file-recursively file)))
11624 (map (cut string-append "src/" <>)
11627 (not (member file free)))))))
11628 ;; Only make the utils target, not the userApps target,
11629 ;; because that requires libraries we won't build.
11630 (substitute* "Makefile"
11631 ((" userApps") " utils"))
11632 ;; Only build libraries that are free.
11633 (substitute* "src/makefile"
11634 (("DIRS =.*") "DIRS =\n")
11635 (("cd jkOwnLib.*") "")
11638 (substitute* "src/utils/makefile"
11639 ;; These tools depend on "jkhgap.a", which is part of the
11640 ;; nonfree "src/hg/lib" directory.
11641 (("raSqlQuery") "")
11642 (("pslLiftSubrangeBlat") "")
11644 ;; Do not build UCSC tools, which may require nonfree
11646 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11648 (build-system gnu-build-system)
11650 `( ;; There is no global test target and the test target for
11651 ;; individual tools depends on input files that are not
11655 (modify-phases %standard-phases
11656 (add-after 'unpack 'fix-permissions
11657 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11658 (add-after 'unpack 'fix-paths
11660 (substitute* "Makefile"
11661 (("/bin/echo") (which "echo")))
11663 (add-after 'unpack 'prepare-samtabix
11664 (lambda* (#:key inputs #:allow-other-keys)
11665 (copy-recursively (assoc-ref inputs "samtabix")
11668 (delete 'configure)
11670 (lambda* (#:key outputs #:allow-other-keys)
11671 (let ((bin (string-append (assoc-ref outputs "out")
11673 (copy-recursively "bin" bin))
11679 (uri (git-reference
11680 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11681 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11684 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11690 ("mariadb" ,mariadb)
11691 ("openssl" ,openssl)))
11692 (home-page "http://genome.cse.ucsc.edu/index.html")
11693 (synopsis "Assorted bioinformatics utilities")
11694 (description "This package provides the kentUtils, a selection of
11695 bioinformatics utilities used in combination with the UCSC genome
11697 ;; Only a subset of the sources are released under a non-copyleft
11698 ;; free software license. All other sources are removed in a
11699 ;; snippet. See this bug report for an explanation of how the
11700 ;; license statements apply:
11701 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11702 (license (license:non-copyleft
11703 "http://genome.ucsc.edu/license/"
11704 "The contents of this package are free for all uses."))))
11706 (define-public f-seq
11707 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11711 (version (string-append "1.1-" revision "." (string-take commit 7)))
11714 (uri (git-reference
11715 (url "https://github.com/aboyle/F-seq.git")
11717 (file-name (string-append name "-" version))
11720 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11721 (modules '((guix build utils)))
11722 ;; Remove bundled Java library archives.
11725 (for-each delete-file (find-files "lib" ".*"))
11727 (build-system ant-build-system)
11729 `(#:tests? #f ; no tests included
11731 (modify-phases %standard-phases
11733 (lambda* (#:key inputs outputs #:allow-other-keys)
11734 (let* ((target (assoc-ref outputs "out"))
11735 (bin (string-append target "/bin"))
11736 (doc (string-append target "/share/doc/f-seq"))
11737 (lib (string-append target "/lib")))
11740 (substitute* "bin/linux/fseq"
11741 (("java") (which "java"))
11742 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11743 (string-append (assoc-ref inputs "java-commons-cli")
11744 "/share/java/commons-cli.jar"))
11746 (string-append "REALDIR=" bin "\n")))
11747 (install-file "README.txt" doc)
11748 (install-file "bin/linux/fseq" bin)
11749 (install-file "build~/fseq.jar" lib)
11750 (copy-recursively "lib" lib)
11754 ("java-commons-cli" ,java-commons-cli)))
11755 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11756 (synopsis "Feature density estimator for high-throughput sequence tags")
11758 "F-Seq is a software package that generates a continuous tag sequence
11759 density estimation allowing identification of biologically meaningful sites
11760 such as transcription factor binding sites (ChIP-seq) or regions of open
11761 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11763 (license license:gpl3+))))
11765 (define-public bismark
11772 (uri (git-reference
11773 (url "https://github.com/FelixKrueger/Bismark.git")
11775 (file-name (string-append name "-" version "-checkout"))
11778 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11781 ;; highcharts.js is non-free software. The code is available under
11782 ;; CC-BY-NC or proprietary licenses only.
11783 (delete-file "bismark_sitrep/highcharts.js")
11785 (build-system perl-build-system)
11787 `(#:tests? #f ; there are no tests
11789 (modify-phases %standard-phases
11790 (delete 'configure)
11793 (lambda* (#:key inputs outputs #:allow-other-keys)
11794 (let* ((out (assoc-ref outputs "out"))
11795 (bin (string-append out "/bin"))
11796 (share (string-append out "/share/bismark"))
11797 (docdir (string-append out "/share/doc/bismark"))
11798 (docs '("Docs/Bismark_User_Guide.html"))
11799 (scripts '("bismark"
11800 "bismark_genome_preparation"
11801 "bismark_methylation_extractor"
11804 "coverage2cytosine"
11805 "deduplicate_bismark"
11806 "filter_non_conversion"
11808 "bismark2summary")))
11809 (substitute* "bismark2report"
11810 (("\\$RealBin/bismark_sitrep")
11811 (string-append share "/bismark_sitrep")))
11815 (for-each (lambda (file) (install-file file bin))
11817 (for-each (lambda (file) (install-file file docdir))
11819 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11820 (copy-recursively "bismark_sitrep"
11821 (string-append share "/bismark_sitrep"))
11823 ;; Fix references to gunzip
11824 (substitute* (map (lambda (file)
11825 (string-append bin "/" file))
11828 (string-append "\"" (assoc-ref inputs "gzip")
11829 "/bin/gunzip -c")))
11833 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11834 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11835 (description "Bismark is a program to map bisulfite treated sequencing
11836 reads to a genome of interest and perform methylation calls in a single step.
11837 The output can be easily imported into a genome viewer, such as SeqMonk, and
11838 enables a researcher to analyse the methylation levels of their samples
11839 straight away. Its main features are:
11842 @item Bisulfite mapping and methylation calling in one single step
11843 @item Supports single-end and paired-end read alignments
11844 @item Supports ungapped and gapped alignments
11845 @item Alignment seed length, number of mismatches etc are adjustable
11846 @item Output discriminates between cytosine methylation in CpG, CHG
11849 (license license:gpl3+)))
11851 (define-public paml
11857 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11858 "paml" version ".tgz"))
11861 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11862 (modules '((guix build utils)))
11863 ;; Remove Windows binaries
11866 (for-each delete-file (find-files "." "\\.exe$"))
11868 (build-system gnu-build-system)
11870 `(#:tests? #f ; there are no tests
11871 #:make-flags '("CC=gcc")
11873 (modify-phases %standard-phases
11874 (replace 'configure
11876 (substitute* "src/BFdriver.c"
11877 (("/bin/bash") (which "bash")))
11881 (lambda* (#:key outputs #:allow-other-keys)
11882 (let ((tools '("baseml" "basemlg" "codeml"
11883 "pamp" "evolver" "yn00" "chi2"))
11884 (bin (string-append (assoc-ref outputs "out") "/bin"))
11885 (docdir (string-append (assoc-ref outputs "out")
11886 "/share/doc/paml")))
11888 (for-each (lambda (file) (install-file file bin)) tools)
11889 (copy-recursively "../doc" docdir)
11891 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11892 (synopsis "Phylogentic analysis by maximum likelihood")
11893 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11894 contains a few programs for model fitting and phylogenetic tree reconstruction
11895 using nucleotide or amino-acid sequence data.")
11897 (license license:gpl3)))
11899 (define-public kallisto
11905 (uri (git-reference
11906 (url "https://github.com/pachterlab/kallisto.git")
11907 (commit (string-append "v" version))))
11908 (file-name (git-file-name name version))
11911 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11912 (build-system cmake-build-system)
11914 `(#:tests? #f ; no "check" target
11916 (modify-phases %standard-phases
11917 (add-after 'unpack 'do-not-use-bundled-htslib
11919 (substitute* "CMakeLists.txt"
11920 (("^ExternalProject_Add" m)
11921 (string-append "if (NEVER)\n" m))
11923 (string-append ")\nendif(NEVER)"))
11924 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11925 (string-append "# " m)))
11926 (substitute* "src/CMakeLists.txt"
11927 (("target_link_libraries\\(kallisto kallisto_core pthread \
11928 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11929 "target_link_libraries(kallisto kallisto_core pthread hts)")
11930 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11936 (home-page "http://pachterlab.github.io/kallisto/")
11937 (synopsis "Near-optimal RNA-Seq quantification")
11939 "Kallisto is a program for quantifying abundances of transcripts from
11940 RNA-Seq data, or more generally of target sequences using high-throughput
11941 sequencing reads. It is based on the novel idea of pseudoalignment for
11942 rapidly determining the compatibility of reads with targets, without the need
11943 for alignment. Pseudoalignment of reads preserves the key information needed
11944 for quantification, and kallisto is therefore not only fast, but also as
11945 accurate as existing quantification tools.")
11946 (license license:bsd-2)))
11948 (define-public libgff
11954 (uri (git-reference
11955 (url "https://github.com/Kingsford-Group/libgff.git")
11956 (commit (string-append "v" version))))
11957 (file-name (git-file-name name version))
11960 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11961 (build-system cmake-build-system)
11962 (arguments `(#:tests? #f)) ; no tests included
11963 (home-page "https://github.com/Kingsford-Group/libgff")
11964 (synopsis "Parser library for reading/writing GFF files")
11965 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11966 code that is used in the Cufflinks codebase. The goal of this library is to
11967 provide this functionality without the necessity of drawing in a heavy-weight
11968 dependency like SeqAn.")
11969 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11971 (define-public libdivsufsort
11973 (name "libdivsufsort")
11977 (uri (git-reference
11978 (url "https://github.com/y-256/libdivsufsort.git")
11980 (file-name (git-file-name name version))
11983 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11984 (build-system cmake-build-system)
11986 '(#:tests? #f ; there are no tests
11988 ;; Needed for rapmap and sailfish.
11989 '("-DBUILD_DIVSUFSORT64=ON")))
11990 (home-page "https://github.com/y-256/libdivsufsort")
11991 (synopsis "Lightweight suffix-sorting library")
11992 (description "libdivsufsort is a software library that implements a
11993 lightweight suffix array construction algorithm. This library provides a
11994 simple and an efficient C API to construct a suffix array and a
11995 Burrows-Wheeler transformed string from a given string over a constant-size
11996 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11997 bytes of memory space, where n is the length of the string.")
11998 (license license:expat)))
12000 (define-public sailfish
12006 (uri (git-reference
12007 (url "https://github.com/kingsfordgroup/sailfish.git")
12008 (commit (string-append "v" version))))
12009 (file-name (git-file-name name version))
12012 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
12013 (modules '((guix build utils)))
12016 ;; Delete bundled headers for eigen3.
12017 (delete-file-recursively "include/eigen3/")
12019 (build-system cmake-build-system)
12021 `(#:configure-flags
12022 (list (string-append "-DBOOST_INCLUDEDIR="
12023 (assoc-ref %build-inputs "boost")
12025 (string-append "-DBOOST_LIBRARYDIR="
12026 (assoc-ref %build-inputs "boost")
12028 (string-append "-DBoost_LIBRARIES="
12029 "-lboost_iostreams "
12030 "-lboost_filesystem "
12035 "-lboost_program_options")
12036 "-DBoost_FOUND=TRUE"
12037 ;; Don't download RapMap---we already have it!
12038 "-DFETCHED_RAPMAP=1")
12039 ;; Tests must be run after installation and the location of the test
12040 ;; data file must be overridden. But the tests fail. It looks like
12041 ;; they are not really meant to be run.
12044 (modify-phases %standard-phases
12045 ;; Boost cannot be found, even though it's right there.
12046 (add-after 'unpack 'do-not-look-for-boost
12047 (lambda* (#:key inputs #:allow-other-keys)
12048 (substitute* "CMakeLists.txt"
12049 (("find_package\\(Boost 1\\.53\\.0") "#"))
12051 (add-after 'unpack 'do-not-assign-to-macro
12053 (substitute* "include/spdlog/details/format.cc"
12054 (("const unsigned CHAR_WIDTH = 1;") ""))
12056 (add-after 'unpack 'prepare-rapmap
12057 (lambda* (#:key inputs #:allow-other-keys)
12058 (let ((src "external/install/src/rapmap/")
12059 (include "external/install/include/rapmap/")
12060 (rapmap (assoc-ref inputs "rapmap")))
12061 (mkdir-p "/tmp/rapmap")
12063 (assoc-ref inputs "rapmap")
12065 "--strip-components=1")
12068 (for-each (lambda (file)
12069 (install-file file src))
12070 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12071 (copy-recursively "/tmp/rapmap/include" include))
12073 (add-after 'unpack 'use-system-libraries
12074 (lambda* (#:key inputs #:allow-other-keys)
12075 (substitute* '("src/SailfishIndexer.cpp"
12076 "src/SailfishUtils.cpp"
12077 "src/SailfishQuantify.cpp"
12078 "src/FASTAParser.cpp"
12080 "include/SailfishUtils.hpp"
12081 "include/SailfishIndex.hpp"
12082 "include/CollapsedEMOptimizer.hpp"
12083 "src/CollapsedEMOptimizer.cpp")
12084 (("#include \"jellyfish/config.h\"") ""))
12085 (substitute* "src/CMakeLists.txt"
12086 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12087 (string-append (assoc-ref inputs "jellyfish")
12088 "/include/jellyfish-" ,(package-version jellyfish)))
12089 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12090 (string-append (assoc-ref inputs "jellyfish")
12091 "/lib/libjellyfish-2.0.a"))
12092 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12093 (string-append (assoc-ref inputs "libdivsufsort")
12094 "/lib/libdivsufsort.so"))
12095 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12096 (string-append (assoc-ref inputs "libdivsufsort")
12097 "/lib/libdivsufsort64.so")))
12098 (substitute* "CMakeLists.txt"
12099 ;; Don't prefer static libs
12100 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12101 (("find_package\\(Jellyfish.*") "")
12102 (("ExternalProject_Add\\(libjellyfish") "message(")
12103 (("ExternalProject_Add\\(libgff") "message(")
12104 (("ExternalProject_Add\\(libsparsehash") "message(")
12105 (("ExternalProject_Add\\(libdivsufsort") "message("))
12107 ;; Ensure that Eigen headers can be found
12108 (setenv "CPLUS_INCLUDE_PATH"
12109 (string-append (getenv "CPLUS_INCLUDE_PATH")
12111 (assoc-ref inputs "eigen")
12112 "/include/eigen3"))
12117 ("jemalloc" ,jemalloc)
12118 ("jellyfish" ,jellyfish)
12119 ("sparsehash" ,sparsehash)
12122 (uri (git-reference
12123 (url "https://github.com/COMBINE-lab/RapMap.git")
12124 (commit (string-append "sf-v" version))))
12125 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12128 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12129 (modules '((guix build utils)))
12130 ;; These files are expected to be excluded.
12132 '(begin (delete-file-recursively "include/spdlog")
12133 (for-each delete-file '("include/xxhash.h"
12136 ("libdivsufsort" ,libdivsufsort)
12141 `(("pkg-config" ,pkg-config)))
12142 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12143 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12144 (description "Sailfish is a tool for genomic transcript quantification
12145 from RNA-seq data. It requires a set of target transcripts (either from a
12146 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12147 fasta file containing your reference transcripts and a (set of) fasta/fastq
12148 file(s) containing your reads.")
12149 (license license:gpl3+)))
12151 (define libstadenio-for-salmon
12153 (name "libstadenio")
12157 (uri (git-reference
12158 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12159 (commit (string-append "v" version))))
12160 (file-name (string-append name "-" version "-checkout"))
12163 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12164 (build-system gnu-build-system)
12165 (arguments '(#:parallel-tests? #f)) ; not supported
12169 `(("perl" ,perl))) ; for tests
12170 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12171 (synopsis "General purpose trace and experiment file library")
12172 (description "This package provides a library of file reading and writing
12173 code to provide a general purpose Trace file (and Experiment File) reading
12176 The following file formats are supported:
12179 @item SCF trace files
12180 @item ABI trace files
12181 @item ALF trace files
12182 @item ZTR trace files
12183 @item SFF trace archives
12184 @item SRF trace archives
12185 @item Experiment files
12186 @item Plain text files
12187 @item SAM/BAM sequence files
12188 @item CRAM sequence files
12190 (license license:bsd-3)))
12192 (define spdlog-for-salmon
12198 (uri (git-reference
12199 (url "https://github.com/COMBINE-lab/spdlog.git")
12200 (commit (string-append "v" version))))
12201 (file-name (string-append name "-" version "-checkout"))
12204 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12205 (build-system cmake-build-system)
12206 (home-page "https://github.com/COMBINE-lab/spdlog")
12207 (synopsis "Very fast C++ logging library")
12208 (description "Spdlog is a very fast header-only C++ logging library with
12209 performance as its primary goal.")
12210 (license license:expat)))
12212 ;; This is a modified variant of bwa for use with Salmon. It installs a
12213 ;; library to avoid having to build this as part of Salmon.
12214 (define bwa-for-salmon
12215 (package (inherit bwa)
12217 (version "0.7.12.5")
12220 (uri (git-reference
12221 (url "https://github.com/COMBINE-lab/bwa.git")
12222 (commit (string-append "v" version))))
12223 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12226 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12227 (build-system gnu-build-system)
12229 '(#:tests? #f ;no "check" target
12231 (modify-phases %standard-phases
12233 (lambda* (#:key outputs #:allow-other-keys)
12234 (let* ((out (assoc-ref outputs "out"))
12235 (bin (string-append out "/bin"))
12236 (lib (string-append out "/lib"))
12237 (doc (string-append out "/share/doc/bwa"))
12238 (man (string-append out "/share/man/man1"))
12239 (inc (string-append out "/include/bwa")))
12240 (install-file "bwa" bin)
12241 (install-file "README.md" doc)
12242 (install-file "bwa.1" man)
12243 (install-file "libbwa.a" lib)
12246 (for-each (lambda (file)
12247 (install-file file inc))
12248 (find-files "." "\\.h$")))
12250 ;; no "configure" script
12251 (delete 'configure))))))
12253 (define-public salmon
12259 (uri (git-reference
12260 (url "https://github.com/COMBINE-lab/salmon.git")
12261 (commit (string-append "v" version))))
12262 (file-name (string-append name "-" version "-checkout"))
12265 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12266 (modules '((guix build utils)))
12269 ;; Delete bundled headers for eigen3.
12270 (delete-file-recursively "include/eigen3/")
12272 (build-system cmake-build-system)
12274 `(#:configure-flags
12275 (list (string-append "-DBOOST_INCLUDEDIR="
12276 (assoc-ref %build-inputs "boost")
12278 (string-append "-DBOOST_LIBRARYDIR="
12279 (assoc-ref %build-inputs "boost")
12281 (string-append "-DBoost_LIBRARIES="
12282 "-lboost_iostreams "
12283 "-lboost_filesystem "
12288 "-lboost_program_options")
12289 "-DBoost_FOUND=TRUE"
12290 "-DTBB_LIBRARIES=tbb tbbmalloc"
12291 ;; Don't download RapMap---we already have it!
12292 "-DFETCHED_RAPMAP=1")
12294 (modify-phases %standard-phases
12295 ;; Boost cannot be found, even though it's right there.
12296 (add-after 'unpack 'do-not-look-for-boost
12297 (lambda* (#:key inputs #:allow-other-keys)
12298 (substitute* "CMakeLists.txt"
12299 (("find_package\\(Boost 1\\.53\\.0") "#"))
12301 (add-after 'unpack 'do-not-phone-home
12303 (substitute* "src/Salmon.cpp"
12304 (("getVersionMessage\\(\\)") "\"\""))
12306 (add-after 'unpack 'prepare-rapmap
12307 (lambda* (#:key inputs #:allow-other-keys)
12308 (let ((src "external/install/src/rapmap/")
12309 (include "external/install/include/rapmap/")
12310 (rapmap (assoc-ref inputs "rapmap")))
12313 (for-each (lambda (file)
12314 (install-file file src))
12315 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12316 (copy-recursively (string-append rapmap "/include") include)
12317 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12318 "external/install/include/rapmap/FastxParser.hpp"
12319 "external/install/include/rapmap/concurrentqueue.h"
12320 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12321 "external/install/src/rapmap/FastxParser.cpp"
12322 "external/install/src/rapmap/xxhash.c")))
12324 (add-after 'unpack 'use-system-libraries
12325 (lambda* (#:key inputs #:allow-other-keys)
12326 (substitute* "src/CMakeLists.txt"
12327 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12328 (string-append (assoc-ref inputs "jellyfish")
12329 "/include/jellyfish-" ,(package-version jellyfish)))
12330 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12331 (string-append (assoc-ref inputs "jellyfish")
12332 "/lib/libjellyfish-2.0.a"))
12333 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12334 (string-append (assoc-ref inputs "libdivsufsort")
12335 "/lib/libdivsufsort.so"))
12336 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12337 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12338 "/lib/libstaden-read.a"))
12339 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12340 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12341 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12342 (string-append (assoc-ref inputs "libdivsufsort")
12343 "/lib/libdivsufsort64.so")))
12344 (substitute* "CMakeLists.txt"
12345 ;; Don't prefer static libs
12346 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12347 (("set\\(TBB_LIBRARIES") "message(")
12348 (("find_package\\(Jellyfish.*") "")
12349 (("ExternalProject_Add\\(libcereal") "message(")
12350 (("ExternalProject_Add\\(libbwa") "message(")
12351 (("ExternalProject_Add\\(libjellyfish") "message(")
12352 (("ExternalProject_Add\\(libgff") "message(")
12353 (("ExternalProject_Add\\(libtbb") "message(")
12354 (("ExternalProject_Add\\(libspdlog") "message(")
12355 (("ExternalProject_Add\\(libdivsufsort") "message(")
12356 (("ExternalProject_Add\\(libstadenio") "message(")
12357 (("ExternalProject_Add_Step\\(") "message("))
12359 ;; Ensure that all headers can be found
12360 (setenv "CPLUS_INCLUDE_PATH"
12361 (string-append (getenv "CPLUS_INCLUDE_PATH")
12363 (assoc-ref inputs "bwa")
12366 (assoc-ref inputs "eigen")
12367 "/include/eigen3"))
12369 (string-append (assoc-ref inputs "bwa")
12372 (assoc-ref inputs "eigen")
12373 "/include/eigen3"))
12375 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12376 ;; run. It only exists after the install phase.
12377 (add-after 'unpack 'fix-tests
12379 (substitute* "src/CMakeLists.txt"
12380 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12381 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12385 ("bwa" ,bwa-for-salmon)
12391 (uri (git-reference
12392 (url "https://github.com/COMBINE-lab/RapMap.git")
12393 (commit (string-append "salmon-v" version))))
12394 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12397 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12398 ("jemalloc" ,jemalloc)
12399 ("jellyfish" ,jellyfish)
12402 ("libdivsufsort" ,libdivsufsort)
12403 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12404 ("spdlog-for-salmon" ,spdlog-for-salmon)
12407 (home-page "https://github.com/COMBINE-lab/salmon")
12408 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12409 (description "Salmon is a program to produce highly-accurate,
12410 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12411 its accuracy and speed via a number of different innovations, including the
12412 use of lightweight alignments (accurate but fast-to-compute proxies for
12413 traditional read alignments) and massively-parallel stochastic collapsed
12414 variational inference.")
12415 (license license:gpl3+)))
12417 (define-public python-loompy
12419 (name "python-loompy")
12424 (uri (pypi-uri "loompy" version))
12427 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12428 (build-system python-build-system)
12429 ;; There are no tests
12430 (arguments '(#:tests? #f))
12432 `(("python-h5py" ,python-h5py)
12433 ("python-numpy" ,python-numpy)
12434 ("python-scipy" ,python-scipy)))
12435 (home-page "https://github.com/linnarsson-lab/loompy")
12436 (synopsis "Work with .loom files for single-cell RNA-seq data")
12437 (description "The loom file format is an efficient format for very large
12438 omics datasets, consisting of a main matrix, optional additional layers, a
12439 variable number of row and column annotations. Loom also supports sparse
12440 graphs. This library makes it easy to work with @file{.loom} files for
12441 single-cell RNA-seq data.")
12442 (license license:bsd-3)))
12444 ;; We cannot use the latest commit because it requires Java 9.
12445 (define-public java-forester
12446 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12449 (name "java-forester")
12450 (version (string-append "0-" revision "." (string-take commit 7)))
12453 (uri (git-reference
12454 (url "https://github.com/cmzmasek/forester.git")
12456 (file-name (string-append name "-" version "-checkout"))
12459 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12460 (modules '((guix build utils)))
12463 ;; Delete bundled jars and pre-built classes
12464 (delete-file-recursively "forester/java/resources")
12465 (delete-file-recursively "forester/java/classes")
12466 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12467 ;; Delete bundled applications
12468 (delete-file-recursively "forester_applications")
12470 (build-system ant-build-system)
12472 `(#:tests? #f ; there are none
12474 #:modules ((guix build ant-build-system)
12476 (guix build java-utils)
12480 (modify-phases %standard-phases
12481 (add-after 'unpack 'chdir
12482 (lambda _ (chdir "forester/java") #t))
12483 (add-after 'chdir 'fix-dependencies
12485 (chmod "build.xml" #o664)
12486 (call-with-output-file "build.xml.new"
12490 (with-input-from-file "build.xml"
12491 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12492 `(;; Remove all unjar tags to avoid repacking classes.
12493 (unjar . ,(lambda _ '()))
12494 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12495 (*text* . ,(lambda (_ txt) txt))))
12497 (rename-file "build.xml.new" "build.xml")
12499 ;; FIXME: itext is difficult to package as it depends on a few
12500 ;; unpackaged libraries.
12501 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12503 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12504 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12505 (("pdf_written_to = PdfExporter.*")
12506 "throw new IOException(\"PDF export is not available.\");"))
12508 ;; There is no install target
12509 (replace 'install (install-jars ".")))))
12511 `(("java-commons-codec" ,java-commons-codec)
12512 ("java-openchart2" ,java-openchart2)))
12513 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12514 (synopsis "Phylogenomics libraries for Java")
12515 (description "Forester is a collection of Java libraries for
12516 phylogenomics and evolutionary biology research. It includes support for
12517 reading, writing, and exporting phylogenetic trees.")
12518 (license license:lgpl2.1+))))
12520 (define-public java-forester-1.005
12522 (name "java-forester")
12526 (uri (string-append "http://search.maven.org/remotecontent?"
12527 "filepath=org/biojava/thirdparty/forester/"
12528 version "/forester-" version "-sources.jar"))
12529 (file-name (string-append name "-" version ".jar"))
12532 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12533 (build-system ant-build-system)
12535 `(#:tests? #f ; there are none
12537 #:modules ((guix build ant-build-system)
12539 (guix build java-utils)
12543 (modify-phases %standard-phases
12544 (add-after 'unpack 'fix-dependencies
12545 (lambda* (#:key inputs #:allow-other-keys)
12546 (call-with-output-file "build.xml"
12550 (with-input-from-file "src/build.xml"
12551 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12552 `(;; Remove all unjar tags to avoid repacking classes.
12553 (unjar . ,(lambda _ '()))
12554 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12555 (*text* . ,(lambda (_ txt) txt))))
12557 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12558 "synth_look_and_feel_1.xml")
12559 (copy-file (assoc-ref inputs "phyloxml.xsd")
12561 (substitute* "build.xml"
12562 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12563 "synth_look_and_feel_1.xml")
12564 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12567 ;; FIXME: itext is difficult to package as it depends on a few
12568 ;; unpackaged libraries.
12569 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12571 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12572 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12573 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12574 (("pdf_written_to = PdfExporter.*")
12575 "throw new IOException(\"PDF export is not available.\"); /*")
12576 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12577 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12579 (add-after 'unpack 'delete-pre-built-classes
12580 (lambda _ (delete-file-recursively "src/classes") #t))
12581 ;; There is no install target
12582 (replace 'install (install-jars ".")))))
12584 `(("java-commons-codec" ,java-commons-codec)
12585 ("java-openchart2" ,java-openchart2)))
12586 ;; The source archive does not contain the resources.
12591 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12592 "b61cc2dcede0bede317db362472333115756b8c6/"
12593 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12594 (file-name (string-append name "-phyloxml-" version ".xsd"))
12597 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12598 ("synth_look_and_feel_1.xml"
12601 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12602 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12603 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12604 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12607 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12608 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12609 (synopsis "Phylogenomics libraries for Java")
12610 (description "Forester is a collection of Java libraries for
12611 phylogenomics and evolutionary biology research. It includes support for
12612 reading, writing, and exporting phylogenetic trees.")
12613 (license license:lgpl2.1+)))
12615 (define-public java-biojava-core
12617 (name "java-biojava-core")
12621 (uri (git-reference
12622 (url "https://github.com/biojava/biojava")
12623 (commit (string-append "biojava-" version))))
12624 (file-name (string-append name "-" version "-checkout"))
12627 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12628 (build-system ant-build-system)
12631 #:jar-name "biojava-core.jar"
12632 #:source-dir "biojava-core/src/main/java/"
12633 #:test-dir "biojava-core/src/test"
12634 ;; These tests seem to require internet access.
12635 #:test-exclude (list "**/SearchIOTest.java"
12636 "**/BlastXMLParserTest.java"
12637 "**/GenbankCookbookTest.java"
12638 "**/GenbankProxySequenceReaderTest.java")
12640 (modify-phases %standard-phases
12641 (add-before 'build 'copy-resources
12643 (copy-recursively "biojava-core/src/main/resources"
12646 (add-before 'check 'copy-test-resources
12648 (copy-recursively "biojava-core/src/test/resources"
12649 "build/test-classes")
12652 `(("java-log4j-api" ,java-log4j-api)
12653 ("java-log4j-core" ,java-log4j-core)
12654 ("java-slf4j-api" ,java-slf4j-api)
12655 ("java-slf4j-simple" ,java-slf4j-simple)))
12657 `(("java-junit" ,java-junit)
12658 ("java-hamcrest-core" ,java-hamcrest-core)))
12659 (home-page "http://biojava.org")
12660 (synopsis "Core libraries of Java framework for processing biological data")
12661 (description "BioJava is a project dedicated to providing a Java framework
12662 for processing biological data. It provides analytical and statistical
12663 routines, parsers for common file formats, reference implementations of
12664 popular algorithms, and allows the manipulation of sequences and 3D
12665 structures. The goal of the biojava project is to facilitate rapid
12666 application development for bioinformatics.
12668 This package provides the core libraries.")
12669 (license license:lgpl2.1+)))
12671 (define-public java-biojava-phylo
12672 (package (inherit java-biojava-core)
12673 (name "java-biojava-phylo")
12674 (build-system ant-build-system)
12677 #:jar-name "biojava-phylo.jar"
12678 #:source-dir "biojava-phylo/src/main/java/"
12679 #:test-dir "biojava-phylo/src/test"
12681 (modify-phases %standard-phases
12682 (add-before 'build 'copy-resources
12684 (copy-recursively "biojava-phylo/src/main/resources"
12687 (add-before 'check 'copy-test-resources
12689 (copy-recursively "biojava-phylo/src/test/resources"
12690 "build/test-classes")
12693 `(("java-log4j-api" ,java-log4j-api)
12694 ("java-log4j-core" ,java-log4j-core)
12695 ("java-slf4j-api" ,java-slf4j-api)
12696 ("java-slf4j-simple" ,java-slf4j-simple)
12697 ("java-biojava-core" ,java-biojava-core)
12698 ("java-forester" ,java-forester)))
12700 `(("java-junit" ,java-junit)
12701 ("java-hamcrest-core" ,java-hamcrest-core)))
12702 (home-page "http://biojava.org")
12703 (synopsis "Biojava interface to the forester phylogenomics library")
12704 (description "The phylo module provides a biojava interface layer to the
12705 forester phylogenomics library for constructing phylogenetic trees.")))
12707 (define-public java-biojava-alignment
12708 (package (inherit java-biojava-core)
12709 (name "java-biojava-alignment")
12710 (build-system ant-build-system)
12713 #:jar-name "biojava-alignment.jar"
12714 #:source-dir "biojava-alignment/src/main/java/"
12715 #:test-dir "biojava-alignment/src/test"
12717 (modify-phases %standard-phases
12718 (add-before 'build 'copy-resources
12720 (copy-recursively "biojava-alignment/src/main/resources"
12723 (add-before 'check 'copy-test-resources
12725 (copy-recursively "biojava-alignment/src/test/resources"
12726 "build/test-classes")
12729 `(("java-log4j-api" ,java-log4j-api)
12730 ("java-log4j-core" ,java-log4j-core)
12731 ("java-slf4j-api" ,java-slf4j-api)
12732 ("java-slf4j-simple" ,java-slf4j-simple)
12733 ("java-biojava-core" ,java-biojava-core)
12734 ("java-biojava-phylo" ,java-biojava-phylo)
12735 ("java-forester" ,java-forester)))
12737 `(("java-junit" ,java-junit)
12738 ("java-hamcrest-core" ,java-hamcrest-core)))
12739 (home-page "http://biojava.org")
12740 (synopsis "Biojava API for genetic sequence alignment")
12741 (description "The alignment module of BioJava provides an API that
12745 @item implementations of dynamic programming algorithms for sequence
12747 @item reading and writing of popular alignment file formats;
12748 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12751 (define-public java-biojava-core-4.0
12752 (package (inherit java-biojava-core)
12753 (name "java-biojava-core")
12757 (uri (git-reference
12758 (url "https://github.com/biojava/biojava")
12759 (commit (string-append "biojava-" version))))
12760 (file-name (string-append name "-" version "-checkout"))
12763 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12765 (define-public java-biojava-phylo-4.0
12766 (package (inherit java-biojava-core-4.0)
12767 (name "java-biojava-phylo")
12768 (build-system ant-build-system)
12771 #:jar-name "biojava-phylo.jar"
12772 #:source-dir "biojava-phylo/src/main/java/"
12773 #:test-dir "biojava-phylo/src/test"
12775 (modify-phases %standard-phases
12776 (add-before 'build 'copy-resources
12778 (copy-recursively "biojava-phylo/src/main/resources"
12781 (add-before 'check 'copy-test-resources
12783 (copy-recursively "biojava-phylo/src/test/resources"
12784 "build/test-classes")
12787 `(("java-log4j-api" ,java-log4j-api)
12788 ("java-log4j-core" ,java-log4j-core)
12789 ("java-slf4j-api" ,java-slf4j-api)
12790 ("java-slf4j-simple" ,java-slf4j-simple)
12791 ("java-biojava-core" ,java-biojava-core-4.0)
12792 ("java-forester" ,java-forester-1.005)))
12794 `(("java-junit" ,java-junit)
12795 ("java-hamcrest-core" ,java-hamcrest-core)))
12796 (home-page "http://biojava.org")
12797 (synopsis "Biojava interface to the forester phylogenomics library")
12798 (description "The phylo module provides a biojava interface layer to the
12799 forester phylogenomics library for constructing phylogenetic trees.")))
12801 (define-public java-biojava-alignment-4.0
12802 (package (inherit java-biojava-core-4.0)
12803 (name "java-biojava-alignment")
12804 (build-system ant-build-system)
12807 #:jar-name "biojava-alignment.jar"
12808 #:source-dir "biojava-alignment/src/main/java/"
12809 #:test-dir "biojava-alignment/src/test"
12811 (modify-phases %standard-phases
12812 (add-before 'build 'copy-resources
12814 (copy-recursively "biojava-alignment/src/main/resources"
12817 (add-before 'check 'copy-test-resources
12819 (copy-recursively "biojava-alignment/src/test/resources"
12820 "build/test-classes")
12823 `(("java-log4j-api" ,java-log4j-api)
12824 ("java-log4j-core" ,java-log4j-core)
12825 ("java-slf4j-api" ,java-slf4j-api)
12826 ("java-slf4j-simple" ,java-slf4j-simple)
12827 ("java-biojava-core" ,java-biojava-core-4.0)
12828 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12829 ("java-forester" ,java-forester-1.005)))
12831 `(("java-junit" ,java-junit)
12832 ("java-hamcrest-core" ,java-hamcrest-core)))
12833 (home-page "http://biojava.org")
12834 (synopsis "Biojava API for genetic sequence alignment")
12835 (description "The alignment module of BioJava provides an API that
12839 @item implementations of dynamic programming algorithms for sequence
12841 @item reading and writing of popular alignment file formats;
12842 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12845 (define-public dropseq-tools
12847 (name "dropseq-tools")
12852 (uri "http://mccarrolllab.com/download/1276/")
12853 (file-name (string-append "dropseq-tools-" version ".zip"))
12856 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12857 ;; Delete bundled libraries
12858 (modules '((guix build utils)))
12861 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12862 (delete-file-recursively "3rdParty")
12864 (build-system ant-build-system)
12866 `(#:tests? #f ; test data are not included
12867 #:test-target "test"
12868 #:build-target "all"
12869 #:source-dir "public/src/"
12872 (list (string-append "-Dpicard.executable.dir="
12873 (assoc-ref %build-inputs "java-picard")
12875 #:modules ((ice-9 match)
12878 (guix build java-utils)
12879 (guix build ant-build-system))
12881 (modify-phases %standard-phases
12882 ;; FIXME: fails with "java.io.FileNotFoundException:
12883 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12884 (delete 'generate-jar-indices)
12885 ;; All dependencies must be linked to "lib", because that's where
12886 ;; they will be searched for when the Class-Path property of the
12887 ;; manifest is computed.
12888 (add-after 'unpack 'record-references
12889 (lambda* (#:key inputs #:allow-other-keys)
12890 (mkdir-p "jar/lib")
12891 (let ((dirs (filter-map (match-lambda
12893 (if (and (string-prefix? "java-" name)
12894 (not (string=? name "java-testng")))
12897 (for-each (lambda (jar)
12898 (symlink jar (string-append "jar/lib/" (basename jar))))
12899 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12902 ;; There is no installation target
12904 (lambda* (#:key inputs outputs #:allow-other-keys)
12905 (let* ((out (assoc-ref outputs "out"))
12906 (bin (string-append out "/bin"))
12907 (share (string-append out "/share/java/"))
12908 (lib (string-append share "/lib/"))
12909 (scripts (list "BAMTagHistogram"
12910 "BAMTagofTagCounts"
12911 "BaseDistributionAtReadPosition"
12912 "CollapseBarcodesInPlace"
12913 "CollapseTagWithContext"
12915 "CreateIntervalsFiles"
12916 "DetectBeadSynthesisErrors"
12917 "DigitalExpression"
12918 "Drop-seq_alignment.sh"
12921 "GatherGeneGCLength"
12922 "GatherMolecularBarcodeDistributionByGene"
12923 "GatherReadQualityMetrics"
12926 "SelectCellsByNumTranscripts"
12927 "SingleCellRnaSeqMetricsCollector"
12928 "TagBamWithReadSequenceExtended"
12929 "TagReadWithGeneExon"
12930 "TagReadWithInterval"
12931 "TrimStartingSequence"
12932 "ValidateReference")))
12933 (for-each mkdir-p (list bin share lib))
12934 (install-file "dist/dropseq.jar" share)
12935 (for-each (lambda (script)
12936 (chmod script #o555)
12937 (install-file script bin))
12939 (substitute* (map (lambda (script)
12940 (string-append bin "/" script))
12942 (("^java") (which "java"))
12943 (("jar_deploy_dir=.*")
12944 (string-append "jar_deploy_dir=" share "\n"))))
12946 ;; FIXME: We do this after stripping jars because we don't want it to
12947 ;; copy all these jars and strip them. We only want to install
12948 ;; links. Arguably, this is a problem with the ant-build-system.
12949 (add-after 'strip-jar-timestamps 'install-links
12950 (lambda* (#:key outputs #:allow-other-keys)
12951 (let* ((out (assoc-ref outputs "out"))
12952 (share (string-append out "/share/java/"))
12953 (lib (string-append share "/lib/")))
12954 (for-each (lambda (jar)
12955 (symlink (readlink jar)
12956 (string-append lib (basename jar))))
12957 (find-files "jar/lib" "\\.jar$")))
12960 `(("jdk" ,icedtea-8)
12961 ("java-picard" ,java-picard-2.10.3)
12962 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12963 ("java-commons-math3" ,java-commons-math3)
12964 ("java-commons-jexl2" ,java-commons-jexl-2)
12965 ("java-commons-collections4" ,java-commons-collections4)
12966 ("java-commons-lang2" ,java-commons-lang)
12967 ("java-commons-io" ,java-commons-io)
12968 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12969 ("java-guava" ,java-guava)
12970 ("java-la4j" ,java-la4j)
12971 ("java-biojava-core" ,java-biojava-core-4.0)
12972 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12973 ("java-jdistlib" ,java-jdistlib)
12974 ("java-simple-xml" ,java-simple-xml)
12975 ("java-snakeyaml" ,java-snakeyaml)))
12978 ("java-testng" ,java-testng)))
12979 (home-page "http://mccarrolllab.com/dropseq/")
12980 (synopsis "Tools for Drop-seq analyses")
12981 (description "Drop-seq is a technology to enable biologists to
12982 analyze RNA expression genome-wide in thousands of individual cells at
12983 once. This package provides tools to perform Drop-seq analyses.")
12984 (license license:expat)))
12986 (define-public pigx-rnaseq
12988 (name "pigx-rnaseq")
12992 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12993 "releases/download/v" version
12994 "/pigx_rnaseq-" version ".tar.gz"))
12997 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12998 (build-system gnu-build-system)
13000 `(#:parallel-tests? #f ; not supported
13002 (modify-phases %standard-phases
13003 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
13004 (add-after 'unpack 'disable-resource-intensive-test
13006 (substitute* "Makefile.in"
13007 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
13008 (("^ tests/test_multiqc/test.sh") "")
13009 (("^ test.sh") ""))
13013 ("snakemake" ,snakemake)
13015 ("multiqc" ,multiqc)
13017 ("trim-galore" ,trim-galore)
13019 ("samtools" ,samtools)
13020 ("bedtools" ,bedtools)
13021 ("r-minimal" ,r-minimal)
13022 ("r-rmarkdown" ,r-rmarkdown)
13023 ("r-ggplot2" ,r-ggplot2)
13024 ("r-ggrepel" ,r-ggrepel)
13025 ("r-gprofiler" ,r-gprofiler)
13026 ("r-deseq2" ,r-deseq2)
13028 ("r-knitr" ,r-knitr)
13029 ("r-pheatmap" ,r-pheatmap)
13030 ("r-corrplot" ,r-corrplot)
13031 ("r-reshape2" ,r-reshape2)
13032 ("r-plotly" ,r-plotly)
13033 ("r-scales" ,r-scales)
13034 ("r-summarizedexperiment" ,r-summarizedexperiment)
13035 ("r-crosstalk" ,r-crosstalk)
13036 ("r-tximport" ,r-tximport)
13037 ("r-rtracklayer" ,r-rtracklayer)
13038 ("r-rjson" ,r-rjson)
13040 ("ghc-pandoc" ,ghc-pandoc)
13041 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13042 ("python-wrapper" ,python-wrapper)
13043 ("python-pyyaml" ,python-pyyaml)))
13044 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13045 (synopsis "Analysis pipeline for RNA sequencing experiments")
13046 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
13047 reporting for RNA sequencing experiments. It is easy to use and produces high
13048 quality reports. The inputs are reads files from the sequencing experiment,
13049 and a configuration file which describes the experiment. In addition to
13050 quality control of the experiment, the pipeline produces a differential
13051 expression report comparing samples in an easily configurable manner.")
13052 (license license:gpl3+)))
13054 (define-public pigx-chipseq
13056 (name "pigx-chipseq")
13060 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
13061 "releases/download/v" version
13062 "/pigx_chipseq-" version ".tar.gz"))
13065 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
13066 (build-system gnu-build-system)
13067 ;; parts of the tests rely on access to the network
13068 (arguments '(#:tests? #f))
13071 ("coreutils" ,coreutils)
13072 ("r-minimal" ,r-minimal)
13073 ("r-argparser" ,r-argparser)
13074 ("r-biocparallel" ,r-biocparallel)
13075 ("r-biostrings" ,r-biostrings)
13076 ("r-chipseq" ,r-chipseq)
13077 ("r-data-table" ,r-data-table)
13078 ("r-dplyr" ,r-dplyr)
13079 ("r-genomation" ,r-genomation)
13080 ("r-genomicalignments" ,r-genomicalignments)
13081 ("r-genomicranges" ,r-genomicranges)
13082 ("r-rsamtools" ,r-rsamtools)
13083 ("r-rtracklayer" ,r-rtracklayer)
13084 ("r-s4vectors" ,r-s4vectors)
13085 ("r-stringr" ,r-stringr)
13086 ("r-tibble" ,r-tibble)
13087 ("r-tidyr" ,r-tidyr)
13088 ("r-jsonlite" ,r-jsonlite)
13089 ("r-heatmaply" ,r-heatmaply)
13090 ("r-htmlwidgets" ,r-htmlwidgets)
13091 ("r-ggplot2" ,r-ggplot2)
13092 ("r-plotly" ,r-plotly)
13093 ("r-rmarkdown" ,r-rmarkdown)
13094 ("python-wrapper" ,python-wrapper)
13095 ("python-pyyaml" ,python-pyyaml)
13096 ("python-magic" ,python-magic)
13097 ("python-xlrd" ,python-xlrd)
13098 ("trim-galore" ,trim-galore)
13100 ("multiqc" ,multiqc)
13102 ("ghc-pandoc" ,ghc-pandoc)
13103 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13107 ("snakemake" ,snakemake)
13108 ("samtools" ,samtools)
13109 ("bedtools" ,bedtools)
13110 ("kentutils" ,kentutils)))
13112 `(("python-pytest" ,python-pytest)))
13113 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13114 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13115 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13116 calling and reporting for ChIP sequencing experiments. It is easy to use and
13117 produces high quality reports. The inputs are reads files from the sequencing
13118 experiment, and a configuration file which describes the experiment. In
13119 addition to quality control of the experiment, the pipeline enables to set up
13120 multiple peak calling analysis and allows the generation of a UCSC track hub
13121 in an easily configurable manner.")
13122 (license license:gpl3+)))
13124 (define-public pigx-bsseq
13126 (name "pigx-bsseq")
13130 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13131 "releases/download/v" version
13132 "/pigx_bsseq-" version ".tar.gz"))
13135 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13136 (build-system gnu-build-system)
13139 (modify-phases %standard-phases
13140 (add-before 'check 'set-timezone
13141 ;; The readr package is picky about timezones.
13142 (lambda* (#:key inputs #:allow-other-keys)
13143 (setenv "TZ" "UTC+1")
13145 (string-append (assoc-ref inputs "tzdata")
13146 "/share/zoneinfo"))
13149 `(("tzdata" ,tzdata)))
13151 `(("coreutils" ,coreutils)
13154 ("r-minimal" ,r-minimal)
13155 ("r-annotationhub" ,r-annotationhub)
13157 ("r-genomation" ,r-genomation)
13158 ("r-methylkit" ,r-methylkit)
13159 ("r-rtracklayer" ,r-rtracklayer)
13160 ("r-rmarkdown" ,r-rmarkdown)
13161 ("r-bookdown" ,r-bookdown)
13162 ("r-ggplot2" ,r-ggplot2)
13163 ("r-ggbio" ,r-ggbio)
13164 ("ghc-pandoc" ,ghc-pandoc)
13165 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13166 ("python-wrapper" ,python-wrapper)
13167 ("python-pyyaml" ,python-pyyaml)
13168 ("snakemake" ,snakemake)
13169 ("bismark" ,bismark)
13172 ("trim-galore" ,trim-galore)
13173 ("cutadapt" ,cutadapt)
13174 ("samtools" ,samtools)))
13175 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13176 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13177 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13178 data of bisulfite experiments; it produces reports on aggregate methylation
13179 and coverage and can be used to produce information on differential
13180 methylation and segmentation.")
13181 (license license:gpl3+)))
13183 (define-public pigx-scrnaseq
13185 (name "pigx-scrnaseq")
13189 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13190 "releases/download/v" version
13191 "/pigx_scrnaseq-" version ".tar.gz"))
13194 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13195 (build-system gnu-build-system)
13197 `(#:configure-flags
13198 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13199 "/share/java/picard.jar")
13200 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13201 "/share/java/dropseq.jar"))))
13203 `(("coreutils" ,coreutils)
13205 ("dropseq-tools" ,dropseq-tools)
13207 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13208 ("java" ,icedtea-8)
13209 ("python-wrapper" ,python-wrapper)
13210 ("python-pyyaml" ,python-pyyaml)
13211 ("python-pandas" ,python-pandas)
13212 ("python-magic" ,python-magic)
13213 ("python-numpy" ,python-numpy)
13214 ("python-loompy" ,python-loompy)
13215 ("ghc-pandoc" ,ghc-pandoc)
13216 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13217 ("samtools" ,samtools)
13218 ("snakemake" ,snakemake)
13220 ("r-minimal" ,r-minimal)
13221 ("r-argparser" ,r-argparser)
13222 ("r-cowplot" ,r-cowplot)
13223 ("r-data-table" ,r-data-table)
13224 ("r-delayedarray" ,r-delayedarray)
13225 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13226 ("r-dplyr" ,r-dplyr)
13227 ("r-dropbead" ,r-dropbead)
13229 ("r-genomicalignments" ,r-genomicalignments)
13230 ("r-genomicfiles" ,r-genomicfiles)
13231 ("r-genomicranges" ,r-genomicranges)
13232 ("r-ggplot2" ,r-ggplot2)
13233 ("r-hdf5array" ,r-hdf5array)
13234 ("r-pheatmap" ,r-pheatmap)
13235 ("r-rmarkdown" ,r-rmarkdown)
13236 ("r-rsamtools" ,r-rsamtools)
13237 ("r-rtracklayer" ,r-rtracklayer)
13238 ("r-rtsne" ,r-rtsne)
13239 ("r-scater" ,r-scater)
13240 ("r-scran" ,r-scran)
13241 ("r-singlecellexperiment" ,r-singlecellexperiment)
13242 ("r-stringr" ,r-stringr)
13243 ("r-yaml" ,r-yaml)))
13244 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13245 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13246 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13247 quality control for single cell RNA sequencing experiments. The inputs are
13248 read files from the sequencing experiment, and a configuration file which
13249 describes the experiment. It produces processed files for downstream analysis
13250 and interactive quality reports. The pipeline is designed to work with UMI
13252 (license license:gpl3+)))
13254 (define-public pigx
13260 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13261 "releases/download/v" version
13262 "/pigx-" version ".tar.gz"))
13265 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13266 (build-system gnu-build-system)
13268 `(("python" ,python)
13269 ("pigx-bsseq" ,pigx-bsseq)
13270 ("pigx-chipseq" ,pigx-chipseq)
13271 ("pigx-rnaseq" ,pigx-rnaseq)
13272 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13273 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13274 (synopsis "Analysis pipelines for genomics")
13275 (description "PiGx is a collection of genomics pipelines. It includes the
13276 following pipelines:
13279 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13280 @item PiGx RNAseq for RNAseq samples
13281 @item PiGx scRNAseq for single cell dropseq analysis
13282 @item PiGx ChIPseq for reads from ChIPseq experiments
13285 All pipelines are easily configured with a simple sample sheet and a
13286 descriptive settings file. The result is a set of comprehensive, interactive
13287 HTML reports with interesting findings about your samples.")
13288 (license license:gpl3+)))
13290 (define-public mantis
13291 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13295 (version (git-version "0" revision commit))
13298 (uri (git-reference
13299 (url "https://github.com/splatlab/mantis.git")
13301 (file-name (git-file-name name version))
13304 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13305 (build-system cmake-build-system)
13306 (arguments '(#:tests? #f)) ; there are none
13308 `(("sdsl-lite" ,sdsl-lite)
13309 ("openssl" ,openssl)
13311 (home-page "https://github.com/splatlab/mantis")
13312 (synopsis "Large-scale sequence-search index data structure")
13313 (description "Mantis is a space-efficient data structure that can be
13314 used to index thousands of raw-read genomics experiments and facilitate
13315 large-scale sequence searches on those experiments. Mantis uses counting
13316 quotient filters instead of Bloom filters, enabling rapid index builds and
13317 queries, small indexes, and exact results, i.e., no false positives or
13318 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13319 representation, so it supports fast graph traversal and other topological
13320 analyses in addition to large-scale sequence-level searches.")
13321 ;; uses __uint128_t and inline assembly
13322 (supported-systems '("x86_64-linux"))
13323 (license license:bsd-3))))
13325 (define-public r-diversitree
13327 (name "r-diversitree")
13332 (uri (cran-uri "diversitree" version))
13335 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13336 (build-system r-build-system)
13338 `(("gfortran" ,gfortran)))
13339 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13342 ("r-desolve" ,r-desolve)
13344 ("r-suplex" ,r-subplex)))
13345 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13346 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13347 (description "This package contains a number of comparative \"phylogenetic\"
13348 methods, mostly focusing on analysing diversification and character evolution.
13349 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13350 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13351 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13352 include Markov models of discrete and continuous trait evolution and constant
13353 rate speciation and extinction.")
13354 (license license:gpl2+)))
13356 (define-public sjcount
13357 ;; There is no tag for version 3.2, nor is there a release archive.
13358 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13362 (version (git-version "3.2" revision commit))
13365 (uri (git-reference
13366 (url "https://github.com/pervouchine/sjcount-full.git")
13368 (file-name (string-append name "-" version "-checkout"))
13371 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13372 (build-system gnu-build-system)
13374 `(#:tests? #f ; requires a 1.4G test file
13376 (list (string-append "SAMTOOLS_DIR="
13377 (assoc-ref %build-inputs "samtools")
13380 (modify-phases %standard-phases
13381 (replace 'configure
13382 (lambda* (#:key inputs #:allow-other-keys)
13383 (substitute* "makefile"
13384 (("-I \\$\\{SAMTOOLS_DIR\\}")
13385 (string-append "-I" (assoc-ref inputs "samtools")
13386 "/include/samtools"))
13387 (("-lz ") "-lz -lpthread "))
13390 (lambda* (#:key outputs #:allow-other-keys)
13391 (for-each (lambda (tool)
13393 (string-append (assoc-ref outputs "out")
13395 '("j_count" "b_count" "sjcount"))
13398 `(("samtools" ,samtools-0.1)
13400 (home-page "https://github.com/pervouchine/sjcount-full/")
13401 (synopsis "Annotation-agnostic splice junction counting pipeline")
13402 (description "Sjcount is a utility for fast quantification of splice
13403 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13404 version does count multisplits.")
13405 (license license:gpl3+))))
13407 (define-public minimap2
13414 (uri (string-append "https://github.com/lh3/minimap2/"
13415 "releases/download/v" version "/"
13416 "minimap2-" version ".tar.bz2"))
13419 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13420 (build-system gnu-build-system)
13422 `(#:tests? #f ; there are none
13425 (let ((system ,(or (%current-target-system)
13426 (%current-system))))
13428 ((string-prefix? "x86_64" system)
13430 ((or (string-prefix? "armhf" system)
13431 (string-prefix? "aarch64" system))
13433 (_ "sse2only=1"))))
13435 (modify-phases %standard-phases
13436 (delete 'configure)
13438 (lambda* (#:key outputs #:allow-other-keys)
13439 (let* ((out (assoc-ref outputs "out"))
13440 (bin (string-append out "/bin"))
13441 (man (string-append out "/share/man/man1")))
13442 (install-file "minimap2" bin)
13444 (install-file "minimap2.1" man))
13448 (home-page "https://lh3.github.io/minimap2/")
13449 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13450 (description "Minimap2 is a versatile sequence alignment program that
13451 aligns DNA or mRNA sequences against a large reference database. Typical use
13455 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13456 @item finding overlaps between long reads with error rate up to ~15%;
13457 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13458 reads against a reference genome;
13459 @item aligning Illumina single- or paired-end reads;
13460 @item assembly-to-assembly alignment;
13461 @item full-genome alignment between two closely related species with
13462 divergence below ~15%.
13464 (license license:expat)))
13466 (define-public r-circus
13473 (uri (git-reference
13474 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13475 (commit (string-append "v" version))))
13476 (file-name (git-file-name name version))
13479 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13480 (build-system r-build-system)
13482 `(("r-annotationdbi" ,r-annotationdbi)
13483 ("r-annotationhub" ,r-annotationhub)
13484 ("r-biomart" ,r-biomart)
13485 ("r-data-table" ,r-data-table)
13487 ("r-genomicfeatures" ,r-genomicfeatures)
13488 ("r-genomicranges" ,r-genomicranges)
13489 ("r-ggplot2" ,r-ggplot2)
13491 ("r-iranges" ,r-iranges)
13492 ("r-rcolorbrewer" ,r-rcolorbrewer)
13493 ("r-rmysql" ,r-rmysql)
13494 ("r-s4vectors" ,r-s4vectors)
13495 ("r-stringr" ,r-stringr)
13496 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13498 `(("r-knitr" ,r-knitr)))
13499 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13500 (synopsis "Annotation, analysis and visualization of circRNA data")
13501 (description "Circus is an R package for annotation, analysis and
13502 visualization of circRNA data. Users can annotate their circRNA candidates
13503 with host genes, gene featrues they are spliced from, and discriminate between
13504 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13505 can be calculated, and a number of descriptive plots easily generated.")
13506 (license license:artistic2.0)))
13508 (define-public r-loomr
13509 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13513 (version (git-version "0.2.0" revision commit))
13517 (uri (git-reference
13518 (url "https://github.com/mojaveazure/loomR.git")
13520 (file-name (git-file-name name version))
13523 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13524 (build-system r-build-system)
13527 ("r-hdf5r" ,r-hdf5r)
13528 ("r-iterators" ,r-iterators)
13529 ("r-itertools" ,r-itertools)
13530 ("r-matrix" ,r-matrix)))
13531 (home-page "https://github.com/mojaveazure/loomR")
13532 (synopsis "R interface for loom files")
13533 (description "This package provides an R interface to access, create,
13534 and modify loom files. loomR aims to be completely compatible with loompy.")
13535 (license license:gpl3))))
13537 (define-public gffread
13538 ;; We cannot use the tagged release because it is not in sync with gclib.
13539 ;; See https://github.com/gpertea/gffread/issues/26
13540 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13544 (version (git-version "0.9.12" revision commit))
13548 (uri (git-reference
13549 (url "https://github.com/gpertea/gffread.git")
13551 (file-name (git-file-name name version))
13554 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13555 (build-system gnu-build-system)
13557 `(#:tests? #f ; no check target
13559 (list "GCLDIR=gclib")
13561 (modify-phases %standard-phases
13562 (delete 'configure)
13563 (add-after 'unpack 'copy-gclib-source
13564 (lambda* (#:key inputs #:allow-other-keys)
13566 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13568 ;; There is no install target
13570 (lambda* (#:key outputs #:allow-other-keys)
13571 (let* ((out (assoc-ref outputs "out"))
13572 (bin (string-append out "/bin")))
13573 (install-file "gffread" bin))
13577 ,(let ((version "0.10.3")
13578 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13582 (uri (git-reference
13583 (url "https://github.com/gpertea/gclib.git")
13585 (file-name (git-file-name "gclib" version))
13588 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13589 (home-page "https://github.com/gpertea/gffread/")
13590 (synopsis "Parse and convert GFF/GTF files")
13592 "This package provides a GFF/GTF file parsing utility providing format
13593 conversions, region filtering, FASTA sequence extraction and more.")
13594 ;; gffread is under Expat, but gclib is under Artistic 2.0
13595 (license (list license:expat
13596 license:artistic2.0)))))
13598 (define-public find-circ
13599 ;; The last release was in 2015. The license was clarified in 2017, so we
13600 ;; take the latest commit.
13601 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13605 (version (git-version "1.2" revision commit))
13609 (uri (git-reference
13610 (url "https://github.com/marvin-jens/find_circ.git")
13612 (file-name (git-file-name name version))
13615 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13616 (build-system gnu-build-system)
13618 `(#:tests? #f ; there are none
13620 ;; There is no actual build system.
13621 (modify-phases %standard-phases
13622 (delete 'configure)
13625 (lambda* (#:key outputs #:allow-other-keys)
13626 (let* ((out (assoc-ref outputs "out"))
13627 (bin (string-append out "/bin"))
13628 (path (getenv "PYTHONPATH")))
13629 (for-each (lambda (script)
13630 (install-file script bin)
13631 (wrap-program (string-append bin "/" script)
13632 `("PYTHONPATH" ":" prefix (,path))))
13637 "unmapped2anchors.py")))
13640 `(("python2" ,python-2)
13641 ("python2-pysam" ,python2-pysam)
13642 ("python2-numpy" ,python2-numpy)))
13643 (home-page "https://github.com/marvin-jens/find_circ")
13644 (synopsis "circRNA detection from RNA-seq reads")
13645 (description "This package provides tools to detect head-to-tail
13646 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13648 (license license:gpl3))))
13650 (define-public python-scanpy
13652 (name "python-scanpy")
13657 (uri (pypi-uri "scanpy" version))
13660 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13661 (build-system python-build-system)
13663 `(("python-anndata" ,python-anndata)
13664 ("python-igraph" ,python-igraph)
13665 ("python-numba" ,python-numba)
13666 ("python-joblib" ,python-joblib)
13667 ("python-natsort" ,python-natsort)
13668 ("python-networkx" ,python-networkx)
13669 ("python-statsmodels" ,python-statsmodels)
13670 ("python-scikit-learn" ,python-scikit-learn)
13671 ("python-matplotlib" ,python-matplotlib)
13672 ("python-pandas" ,python-pandas)
13673 ("python-scipy" ,python-scipy)
13674 ("python-seaborn" ,python-seaborn)
13675 ("python-h5py" ,python-h5py)
13676 ("python-tables" ,python-tables)))
13677 (home-page "http://github.com/theislab/scanpy")
13678 (synopsis "Single-Cell Analysis in Python.")
13679 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13680 expression data. It includes preprocessing, visualization, clustering,
13681 pseudotime and trajectory inference and differential expression testing. The
13682 Python-based implementation efficiently deals with datasets of more than one
13684 (license license:bsd-3)))
13686 (define-public gffcompare
13687 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13690 (name "gffcompare")
13691 (version (git-version "0.10.15" revision commit))
13695 (uri (git-reference
13696 (url "https://github.com/gpertea/gffcompare/")
13698 (file-name (git-file-name name version))
13700 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13701 (build-system gnu-build-system)
13703 `(#:tests? #f ; no check target
13705 (modify-phases %standard-phases
13706 (delete 'configure)
13707 (add-before 'build 'copy-gclib-source
13708 (lambda* (#:key inputs #:allow-other-keys)
13711 (assoc-ref inputs "gclib-source") "../gclib")
13714 (lambda* (#:key outputs #:allow-other-keys)
13715 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13716 (install-file "gffcompare" bin)
13719 `(("gclib-source" ; see 'README.md' of gffcompare
13720 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13723 (version (git-version "0.10.3" revision commit)))
13726 (uri (git-reference
13727 (url "https://github.com/gpertea/gclib/")
13729 (file-name (git-file-name name version))
13731 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13732 (home-page "https://github.com/gpertea/gffcompare/")
13733 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13735 "@code{gffcompare} is a tool that can:
13737 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13738 (Cufflinks, Stringtie);
13739 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13740 resulted from assembly of different samples);
13741 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13742 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13746 license:expat ;license for gffcompare
13747 license:artistic2.0))))) ;license for gclib
13749 (define-public python-intervaltree
13751 (name "python-intervaltree")
13756 (uri (pypi-uri "intervaltree" version))
13759 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13760 (build-system python-build-system)
13761 ;; FIXME: error when collecting tests
13762 (arguments '(#:tests? #f))
13764 `(("python-sortedcontainers" ,python-sortedcontainers)))
13766 `(("python-pytest" ,python-pytest)))
13767 (home-page "https://github.com/chaimleib/intervaltree")
13768 (synopsis "Editable interval tree data structure")
13770 "This package provides a mutable, self-balancing interval tree
13771 implementation for Python. Queries may be by point, by range overlap, or by
13772 range envelopment. This library was designed to allow tagging text and time
13773 intervals, where the intervals include the lower bound but not the upper
13775 (license license:asl2.0)))
13777 (define-public python-pypairix
13779 (name "python-pypairix")
13784 (uri (pypi-uri "pypairix" version))
13787 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13788 (build-system python-build-system)
13789 ;; FIXME: the tests fail because test.support cannot be loaded:
13790 ;; ImportError: cannot import name 'support'
13791 (arguments '(#:tests? #f))
13794 (home-page "https://github.com/4dn-dcic/pairix")
13795 (synopsis "Support for querying pairix-indexed bgzipped text files")
13797 "Pypairix is a Python module for fast querying on a pairix-indexed
13798 bgzipped text file that contains a pair of genomic coordinates per line.")
13799 (license license:expat)))
13801 (define-public python-pyfaidx
13803 (name "python-pyfaidx")
13804 (version "0.5.4.2")
13808 (uri (pypi-uri "pyfaidx" version))
13811 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13812 (build-system python-build-system)
13814 `(("python-setuptools" ,python-setuptools)
13815 ("python-six" ,python-six)))
13816 (home-page "http://mattshirley.com")
13817 (synopsis "Random access to fasta subsequences")
13819 "This package provides procedures for efficient pythonic random access to
13820 fasta subsequences.")
13821 (license license:bsd-3)))
13823 (define-public python-cooler
13825 (name "python-cooler")
13830 (uri (pypi-uri "cooler" version))
13833 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13834 (build-system python-build-system)
13836 `(("python-biopython" ,python-biopython)
13837 ("python-click" ,python-click)
13838 ("python-cytoolz" ,python-cytoolz)
13839 ("python-dask" ,python-dask)
13840 ("python-h5py" ,python-h5py)
13841 ("python-multiprocess" ,python-multiprocess)
13842 ("python-pandas" ,python-pandas)
13843 ("python-pyfaidx" ,python-pyfaidx)
13844 ("python-pypairix" ,python-pypairix)
13845 ("python-pysam" ,python-pysam)
13846 ("python-scipy" ,python-scipy)))
13848 `(("python-mock" ,python-mock)
13849 ("python-nose" ,python-nose)
13850 ("python-numpydoc" ,python-numpydoc)
13851 ("python-sphinx" ,python-sphinx)))
13852 (home-page "https://github.com/mirnylab/cooler")
13853 (synopsis "Sparse binary format for genomic interaction matrices")
13855 "Cooler is a support library for a sparse, compressed, binary persistent
13856 storage format, called @code{cool}, used to store genomic interaction data,
13857 such as Hi-C contact matrices.")
13858 (license license:bsd-3)))
13860 (define-public python-hicexplorer
13862 (name "python-hicexplorer")
13866 ;; The latest version is not available on Pypi.
13868 (uri (git-reference
13869 (url "https://github.com/deeptools/HiCExplorer.git")
13871 (file-name (git-file-name name version))
13874 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13875 (build-system python-build-system)
13878 (modify-phases %standard-phases
13879 (add-after 'unpack 'loosen-up-requirements
13881 (substitute* "setup.py"
13885 `(("python-biopython" ,python-biopython)
13886 ("python-configparser" ,python-configparser)
13887 ("python-cooler" ,python-cooler)
13888 ("python-future" ,python-future)
13889 ("python-intervaltree" ,python-intervaltree)
13890 ("python-jinja2" ,python-jinja2)
13891 ("python-matplotlib" ,python-matplotlib)
13892 ("python-numpy" ,python-numpy)
13893 ("python-pandas" ,python-pandas)
13894 ("python-pybigwig" ,python-pybigwig)
13895 ("python-pysam" ,python-pysam)
13896 ("python-scipy" ,python-scipy)
13897 ("python-six" ,python-six)
13898 ("python-tables" ,python-tables)
13899 ("python-unidecode" ,python-unidecode)))
13900 (home-page "http://hicexplorer.readthedocs.io")
13901 (synopsis "Process, analyze and visualize Hi-C data")
13903 "HiCExplorer is a powerful and easy to use set of tools to process,
13904 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13905 contact matrices, correction of contacts, TAD detection, A/B compartments,
13906 merging, reordering or chromosomes, conversion from different formats
13907 including cooler and detection of long-range contacts. Moreover, it allows
13908 the visualization of multiple contact matrices along with other types of data
13909 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13910 genomic scores), long range contacts and the visualization of viewpoints.")
13911 (license license:gpl3)))
13913 (define-public python-pygenometracks
13915 (name "python-pygenometracks")
13920 (uri (pypi-uri "pyGenomeTracks" version))
13923 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13924 (build-system python-build-system)
13926 `(("python-configparser" ,python-configparser)
13927 ("python-future" ,python-future)
13928 ("python-hicexplorer" ,python-hicexplorer)
13929 ("python-intervaltree" ,python-intervaltree)
13930 ("python-matplotlib" ,python-matplotlib)
13931 ("python-numpy" ,python-numpy)
13932 ("python-pybigwig" ,python-pybigwig)))
13934 `(("python-pytest" ,python-pytest)))
13935 (home-page "https://pygenometracks.readthedocs.io")
13936 (synopsis "Program and library to plot beautiful genome browser tracks")
13938 "This package aims to produce high-quality genome browser tracks that
13939 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13940 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13941 pyGenomeTracks can make plots with or without Hi-C data.")
13942 (license license:gpl3+)))
13944 (define-public python-hic2cool
13946 (name "python-hic2cool")
13951 (uri (pypi-uri "hic2cool" version))
13954 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13955 (build-system python-build-system)
13956 (arguments '(#:tests? #f)) ; no tests included
13958 `(("python-cooler" ,python-cooler)))
13959 (home-page "https://github.com/4dn-dcic/hic2cool")
13960 (synopsis "Converter for .hic and .cool files")
13962 "This package provides a converter between @code{.hic} files (from
13963 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13964 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13966 (license license:expat)))
13968 (define-public r-pore
13976 (string-append "mirror://sourceforge/rpore/" version
13977 "/poRe_" version ".tar.gz"))
13979 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13980 (properties `((upstream-name . "poRe")))
13981 (build-system r-build-system)
13983 `(("r-bit64" ,r-bit64)
13984 ("r-data-table" ,r-data-table)
13985 ("r-rhdf5" ,r-rhdf5)
13986 ("r-shiny" ,r-shiny)
13987 ("r-svdialogs" ,r-svdialogs)))
13988 (home-page "https://sourceforge.net/projects/rpore/")
13989 (synopsis "Visualize Nanopore sequencing data")
13991 "This package provides graphical user interfaces to organize and visualize Nanopore
13993 ;; This is free software but the license variant is unclear:
13994 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13995 (license license:bsd-3)))
13997 (define-public r-xbioc
13998 (let ((revision "1")
13999 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
14002 (version (git-version "0.1.15" revision commit))
14005 (uri (git-reference
14006 (url "https://github.com/renozao/xbioc.git")
14008 (file-name (git-file-name name version))
14011 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
14012 (build-system r-build-system)
14014 `(("r-annotationdbi" ,r-annotationdbi)
14015 ("r-assertthat" ,r-assertthat)
14016 ("r-biobase" ,r-biobase)
14017 ("r-biocinstaller" ,r-biocinstaller)
14018 ("r-digest" ,r-digest)
14019 ("r-pkgmaker" ,r-pkgmaker)
14021 ("r-reshape2" ,r-reshape2)
14022 ("r-stringr" ,r-stringr)))
14023 (home-page "https://github.com/renozao/xbioc/")
14024 (synopsis "Extra base functions for Bioconductor")
14025 (description "This package provides extra utility functions to perform
14026 common tasks in the analysis of omics data, leveraging and enhancing features
14027 provided by Bioconductor packages.")
14028 (license license:gpl3+))))
14030 (define-public r-cssam
14031 (let ((revision "1")
14032 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14035 (version (git-version "1.4" revision commit))
14038 (uri (git-reference
14039 (url "https://github.com/shenorrLab/csSAM.git")
14041 (file-name (git-file-name name version))
14044 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14045 (build-system r-build-system)
14047 `(("r-formula" ,r-formula)
14048 ("r-ggplot2" ,r-ggplot2)
14049 ("r-pkgmaker" ,r-pkgmaker)
14051 ("r-rngtools" ,r-rngtools)
14052 ("r-scales" ,r-scales)))
14053 (home-page "https://github.com/shenorrLab/csSAM/")
14054 (synopsis "Cell type-specific statistical analysis of microarray")
14055 (description "This package implements the method csSAM that computes
14056 cell-specific differential expression from measured cell proportions using
14059 (license license:lgpl2.1+))))
14061 (define-public r-bseqsc
14062 (let ((revision "1")
14063 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14066 (version (git-version "1.0" revision commit))
14069 (uri (git-reference
14070 (url "https://github.com/shenorrLab/bseqsc.git")
14072 (file-name (git-file-name name version))
14075 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14076 (build-system r-build-system)
14078 `(("r-abind" ,r-abind)
14079 ("r-annotationdbi" ,r-annotationdbi)
14080 ("r-biobase" ,r-biobase)
14081 ("r-cssam" ,r-cssam)
14082 ("r-dplyr" ,r-dplyr)
14083 ("r-e1071" ,r-e1071)
14084 ("r-edger" ,r-edger)
14085 ("r-ggplot2" ,r-ggplot2)
14087 ("r-openxlsx" ,r-openxlsx)
14088 ("r-pkgmaker" ,r-pkgmaker)
14090 ("r-preprocesscore" ,r-preprocesscore)
14091 ("r-rngtools" ,r-rngtools)
14092 ("r-scales" ,r-scales)
14093 ("r-stringr" ,r-stringr)
14094 ("r-xbioc" ,r-xbioc)))
14095 (home-page "https://github.com/shenorrLab/bseqsc")
14096 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14097 (description "BSeq-sc is a bioinformatics analysis pipeline that
14098 leverages single-cell sequencing data to estimate cell type proportion and
14099 cell type-specific gene expression differences from RNA-seq data from bulk
14100 tissue samples. This is a companion package to the publication \"A
14101 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14102 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14103 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14104 (license license:gpl2+))))
14106 (define-public porechop
14107 ;; The recommended way to install is to clone the git repository
14108 ;; https://github.com/rrwick/Porechop#installation
14109 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14113 (version (git-version "0.2.3" revision commit))
14117 (uri (git-reference
14118 (url "https://github.com/rrwick/Porechop.git")
14120 (file-name (git-file-name name version))
14122 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14123 (build-system python-build-system)
14124 (home-page "https://github.com/rrwick/porechop")
14125 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14127 "The porechop package is a tool for finding and removing adapters from Oxford
14128 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14129 has an adapter in its middle, it is treated as chimeric and chopped into
14130 separate reads. Porechop performs thorough alignments to effectively find
14131 adapters, even at low sequence identity. Porechop also supports demultiplexing
14132 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14133 Barcoding Kit or Rapid Barcoding Kit.")
14134 (license license:gpl3+))))
14136 (define-public poretools
14137 ;; The latest release was in 2016 and the latest commit is from 2017
14138 ;; the recommended way to install is to clone the git repository
14139 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14140 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14144 (version (git-version "0.6.0" revision commit))
14148 (uri (git-reference
14149 (url "https://github.com/arq5x/poretools.git")
14151 (file-name (git-file-name name version))
14153 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14154 (build-system python-build-system)
14155 ;; requires python >=2.7, <3.0, and the same for python dependencies
14156 (arguments `(#:python ,python-2))
14160 `(("python-dateutil" ,python2-dateutil)
14161 ("python-h5py" ,python2-h5py)
14162 ("python-matplotlib" ,python2-matplotlib)
14163 ("python-pandas" ,python2-pandas)
14164 ("python-seaborn" ,python2-seaborn)))
14165 (home-page "https://poretools.readthedocs.io")
14166 (synopsis "Toolkit for working with nanopore sequencing data")
14168 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14169 This @code{poretools} package is a flexible toolkit for exploring datasets
14170 generated by nanopore sequencing devices for the purposes of quality control and
14171 downstream analysis. Poretools operates directly on the native FAST5, a variant
14172 of the Hierarchical Data Format (HDF5) standard.")
14173 (license license:expat))))
14175 (define-public r-absfiltergsea
14177 (name "r-absfiltergsea")
14182 (uri (cran-uri "AbsFilterGSEA" version))
14184 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14185 (properties `((upstream-name . "AbsFilterGSEA")))
14186 (build-system r-build-system)
14188 `(("r-biobase" ,r-biobase)
14189 ("r-deseq" ,r-deseq)
14190 ("r-limma" ,r-limma)
14192 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14193 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14194 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14196 "This package provides a function that performs gene-permuting of a gene-set
14197 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14198 Without filtering, users can perform (original) two-tailed or one-tailed
14200 (license license:gpl2)))
14202 (define-public jamm
14205 (version "1.0.7.5")
14209 (uri (git-reference
14210 (url "https://github.com/mahmoudibrahim/JAMM.git")
14211 (commit (string-append "JAMMv" version))))
14212 (file-name (git-file-name name version))
14215 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14216 (build-system gnu-build-system)
14218 `(#:tests? #f ; there are none
14220 (modify-phases %standard-phases
14221 (delete 'configure)
14224 (lambda* (#:key inputs outputs #:allow-other-keys)
14225 (let* ((out (assoc-ref outputs "out"))
14226 (libexec (string-append out "/libexec/jamm"))
14227 (bin (string-append out "/bin")))
14228 (substitute* '("JAMM.sh"
14229 "SignalGenerator.sh")
14231 (string-append "sPath=\"" libexec "\"\n")))
14232 (for-each (lambda (file)
14233 (install-file file libexec))
14234 (list "bincalculator.r"
14246 (chmod script #o555)
14247 (install-file script bin)
14248 (wrap-program (string-append bin "/" script)
14249 `("PATH" ":" prefix
14250 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14251 ,(string-append (assoc-ref inputs "gawk") "/bin")
14252 ,(string-append (assoc-ref inputs "perl") "/bin")
14253 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14254 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14255 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14256 (list "JAMM.sh" "SignalGenerator.sh")))
14260 ("coreutils" ,coreutils)
14263 ("r-minimal" ,r-minimal)
14264 ;;("r-parallel" ,r-parallel)
14265 ("r-signal" ,r-signal)
14266 ("r-mclust" ,r-mclust)))
14267 (home-page "https://github.com/mahmoudibrahim/JAMM")
14268 (synopsis "Peak finder for NGS datasets")
14270 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14271 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14272 boundaries accurately. JAMM is applicable to both broad and narrow
14274 (license license:gpl3+)))
14276 (define-public ngless
14283 (uri (git-reference
14284 (url "https://gitlab.com/ngless/ngless.git")
14285 (commit (string-append "v" version))))
14286 (file-name (git-file-name name version))
14289 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14290 (build-system haskell-build-system)
14292 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14293 ; error: parse error on input import
14294 ; import Options.Applicative
14296 (modify-phases %standard-phases
14297 (add-after 'unpack 'create-cabal-file
14298 (lambda _ (invoke "hpack") #t))
14299 ;; These tools are expected to be installed alongside ngless.
14300 (add-after 'install 'link-tools
14301 (lambda* (#:key inputs outputs #:allow-other-keys)
14302 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14303 (symlink (string-append (assoc-ref inputs "prodigal")
14305 (string-append bin "ngless-" ,version "-prodigal"))
14306 (symlink (string-append (assoc-ref inputs "minimap2")
14308 (string-append bin "ngless-" ,version "-minimap2"))
14309 (symlink (string-append (assoc-ref inputs "samtools")
14311 (string-append bin "ngless-" ,version "-samtools"))
14312 (symlink (string-append (assoc-ref inputs "bwa")
14314 (string-append bin "ngless-" ,version "-bwa"))
14317 `(("prodigal" ,prodigal)
14319 ("samtools" ,samtools)
14320 ("minimap2" ,minimap2)
14321 ("ghc-aeson" ,ghc-aeson)
14322 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14323 ("ghc-async" ,ghc-async)
14324 ("ghc-atomic-write" ,ghc-atomic-write)
14325 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14326 ("ghc-chart" ,ghc-chart)
14327 ("ghc-chart-cairo" ,ghc-chart-cairo)
14328 ("ghc-conduit" ,ghc-conduit)
14329 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14330 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14331 ("ghc-conduit-extra" ,ghc-conduit-extra)
14332 ("ghc-configurator" ,ghc-configurator)
14333 ("ghc-convertible" ,ghc-convertible)
14334 ("ghc-data-default" ,ghc-data-default)
14335 ("ghc-double-conversion" ,ghc-double-conversion)
14336 ("ghc-edit-distance" ,ghc-edit-distance)
14337 ("ghc-either" ,ghc-either)
14338 ("ghc-errors" ,ghc-errors)
14339 ("ghc-extra" ,ghc-extra)
14340 ("ghc-filemanip" ,ghc-filemanip)
14341 ("ghc-file-embed" ,ghc-file-embed)
14342 ("ghc-gitrev" ,ghc-gitrev)
14343 ("ghc-hashtables" ,ghc-hashtables)
14344 ("ghc-http-conduit" ,ghc-http-conduit)
14345 ("ghc-inline-c" ,ghc-inline-c)
14346 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14347 ("ghc-intervalmap" ,ghc-intervalmap)
14348 ("ghc-missingh" ,ghc-missingh)
14349 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14350 ("ghc-parsec" ,ghc-parsec)
14351 ("ghc-regex" ,ghc-regex)
14352 ("ghc-safe" ,ghc-safe)
14353 ("ghc-safeio" ,ghc-safeio)
14354 ("ghc-strict" ,ghc-strict)
14355 ("ghc-tar" ,ghc-tar)
14356 ("ghc-text" ,ghc-text)
14357 ("ghc-unliftio" ,ghc-unliftio)
14358 ("ghc-unliftio-core" ,ghc-unliftio-core)
14359 ("ghc-vector" ,ghc-vector)
14360 ("ghc-yaml" ,ghc-yaml)
14361 ("ghc-zlib" ,ghc-zlib)))
14364 ("r-hdf5r" ,r-hdf5r)
14365 ("r-iterators" ,r-iterators)
14366 ("r-itertools" ,r-itertools)
14367 ("r-matrix" ,r-matrix)))
14369 `(("ghc-hpack" ,ghc-hpack)
14370 ("ghc-quickcheck" ,ghc-quickcheck)
14371 ("ghc-test-framework" ,ghc-test-framework)
14372 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14373 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14374 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14375 (home-page "https://gitlab.com/ngless/ngless")
14376 (synopsis "DSL for processing next-generation sequencing data")
14377 (description "Ngless is a domain-specific language for
14378 @dfn{next-generation sequencing} (NGS) data processing.")
14379 (license license:expat)))
14381 (define-public filtlong
14382 ;; The recommended way to install is to clone the git repository
14383 ;; https://github.com/rrwick/Filtlong#installation
14384 ;; and the lastest release is more than nine months old
14385 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14389 (version (git-version "0.2.0" revision commit))
14393 (uri (git-reference
14394 (url "https://github.com/rrwick/Filtlong.git")
14396 (file-name (git-file-name name version))
14398 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14399 (build-system gnu-build-system)
14401 `(#:tests? #f ; no check target
14403 (modify-phases %standard-phases
14404 (delete 'configure)
14406 (lambda* (#:key outputs #:allow-other-keys)
14407 (let* ((out (assoc-ref outputs "out"))
14408 (bin (string-append out "/bin"))
14409 (scripts (string-append out "/share/filtlong/scripts")))
14410 (install-file "bin/filtlong" bin)
14411 (install-file "scripts/histogram.py" scripts)
14412 (install-file "scripts/read_info_histograms.sh" scripts))
14414 (add-after 'install 'wrap-program
14415 (lambda* (#:key inputs outputs #:allow-other-keys)
14416 (let* ((out (assoc-ref outputs "out"))
14417 (path (getenv "PYTHONPATH")))
14418 (wrap-program (string-append out
14419 "/share/filtlong/scripts/histogram.py")
14420 `("PYTHONPATH" ":" prefix (,path))))
14422 (add-before 'check 'patch-tests
14424 (substitute* "scripts/read_info_histograms.sh"
14425 (("awk") (which "gawk")))
14428 `(("gawk" ,gawk) ;for read_info_histograms.sh
14429 ("python" ,python-2) ;required for histogram.py
14431 (home-page "https://github.com/rrwick/Filtlong/")
14432 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14434 "The Filtlong package is a tool for filtering long reads by quality.
14435 It can take a set of long reads and produce a smaller, better subset. It uses
14436 both read length (longer is better) and read identity (higher is better) when
14437 choosing which reads pass the filter.")
14438 (license (list license:gpl3 ;filtlong
14439 license:asl2.0))))) ;histogram.py
14441 (define-public nanopolish
14442 ;; The recommended way to install is to clone the git repository
14443 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14444 ;; Also, the differences between release and current version seem to be
14446 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14449 (name "nanopolish")
14450 (version (git-version "0.10.2" revision commit))
14454 (uri (git-reference
14455 (url "https://github.com/jts/nanopolish.git")
14458 (file-name (git-file-name name version))
14460 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14461 (build-system gnu-build-system)
14464 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14465 #:tests? #f ; no check target
14467 (modify-phases %standard-phases
14468 (add-after 'unpack 'find-eigen
14469 (lambda* (#:key inputs #:allow-other-keys)
14471 (string-append (assoc-ref inputs "eigen")
14472 "/include/eigen3"))
14474 (delete 'configure)
14476 (lambda* (#:key outputs #:allow-other-keys)
14477 (let* ((out (assoc-ref outputs "out"))
14478 (bin (string-append out "/bin"))
14479 (scripts (string-append out "/share/nanopolish/scripts")))
14481 (install-file "nanopolish" bin)
14482 (for-each (lambda (file) (install-file file scripts))
14483 (find-files "scripts" ".*"))
14485 (add-after 'install 'wrap-programs
14486 (lambda* (#:key outputs #:allow-other-keys)
14487 (for-each (lambda (file)
14488 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14489 (find-files "/share/nanopolish/scripts" "\\.py"))
14490 (for-each (lambda (file)
14491 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14492 (find-files "/share/nanopolish/scripts" "\\.pl"))
14500 ("python-biopython" ,python-biopython)
14501 ("python-numpy" ,python-numpy)
14502 ("python-pysam" ,python-pysam)
14503 ("python-scikit-learn" , python-scikit-learn)
14504 ("python-scipy" ,python-scipy)
14506 (home-page "https://github.com/jts/nanopolish")
14507 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14509 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14510 Nanopolish can calculate an improved consensus sequence for a draft genome
14511 assembly, detect base modifications, call SNPs (Single nucleotide
14512 polymorphisms) and indels with respect to a reference genome and more.")
14513 (license license:expat))))