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 guile-xyz)
76 #:use-module (gnu packages haskell)
77 #:use-module (gnu packages haskell-check)
78 #:use-module (gnu packages haskell-web)
79 #:use-module (gnu packages image)
80 #:use-module (gnu packages imagemagick)
81 #:use-module (gnu packages java)
82 #:use-module (gnu packages java-compression)
83 #:use-module (gnu packages jemalloc)
84 #:use-module (gnu packages dlang)
85 #:use-module (gnu packages linux)
86 #:use-module (gnu packages logging)
87 #:use-module (gnu packages machine-learning)
88 #:use-module (gnu packages man)
89 #:use-module (gnu packages maths)
90 #:use-module (gnu packages mpi)
91 #:use-module (gnu packages ncurses)
92 #:use-module (gnu packages ocaml)
93 #:use-module (gnu packages pcre)
94 #:use-module (gnu packages parallel)
95 #:use-module (gnu packages pdf)
96 #:use-module (gnu packages perl)
97 #:use-module (gnu packages perl-check)
98 #:use-module (gnu packages pkg-config)
99 #:use-module (gnu packages popt)
100 #:use-module (gnu packages protobuf)
101 #:use-module (gnu packages python)
102 #:use-module (gnu packages python-compression)
103 #:use-module (gnu packages python-web)
104 #:use-module (gnu packages python-xyz)
105 #:use-module (gnu packages readline)
106 #:use-module (gnu packages ruby)
107 #:use-module (gnu packages serialization)
108 #:use-module (gnu packages shells)
109 #:use-module (gnu packages statistics)
110 #:use-module (gnu packages swig)
111 #:use-module (gnu packages tbb)
112 #:use-module (gnu packages tex)
113 #:use-module (gnu packages texinfo)
114 #:use-module (gnu packages textutils)
115 #:use-module (gnu packages time)
116 #:use-module (gnu packages tls)
117 #:use-module (gnu packages vim)
118 #:use-module (gnu packages web)
119 #:use-module (gnu packages xml)
120 #:use-module (gnu packages xorg)
121 #:use-module (srfi srfi-1)
122 #:use-module (ice-9 match))
124 (define-public aragorn
131 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
135 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
136 (build-system gnu-build-system)
138 `(#:tests? #f ; there are no tests
140 (modify-phases %standard-phases
150 (string-append "aragorn" ,version ".c"))
153 (lambda* (#:key outputs #:allow-other-keys)
154 (let* ((out (assoc-ref outputs "out"))
155 (bin (string-append out "/bin"))
156 (man (string-append out "/share/man/man1")))
157 (install-file "aragorn" bin)
158 (install-file "aragorn.1" man))
160 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
161 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
163 "Aragorn identifies transfer RNA, mitochondrial RNA and
164 transfer-messenger RNA from nucleotide sequences, based on homology to known
165 tRNA consensus sequences and RNA structure. It also outputs the secondary
166 structure of the predicted RNA.")
167 (license license:gpl2)))
175 ;; BamM is not available on pypi.
177 (url "https://github.com/Ecogenomics/BamM.git")
180 (file-name (git-file-name name version))
183 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
184 (modules '((guix build utils)))
187 ;; Delete bundled htslib.
188 (delete-file-recursively "c/htslib-1.3.1")
190 (build-system python-build-system)
192 `(#:python ,python-2 ; BamM is Python 2 only.
193 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
194 ;; been modified from its original form.
196 (let ((htslib (assoc-ref %build-inputs "htslib")))
197 (list "--with-libhts-lib" (string-append htslib "/lib")
198 "--with-libhts-inc" (string-append htslib "/include/htslib")))
200 (modify-phases %standard-phases
201 (add-after 'unpack 'autogen
203 (with-directory-excursion "c"
204 (let ((sh (which "sh")))
205 (for-each make-file-writable (find-files "." ".*"))
206 ;; Use autogen so that 'configure' works.
207 (substitute* "autogen.sh" (("/bin/sh") sh))
208 (setenv "CONFIG_SHELL" sh)
209 (invoke "./autogen.sh")))
212 ;; Run tests after installation so compilation only happens once.
214 (add-after 'install 'wrap-executable
215 (lambda* (#:key outputs #:allow-other-keys)
216 (let* ((out (assoc-ref outputs "out"))
217 (path (getenv "PATH")))
218 (wrap-program (string-append out "/bin/bamm")
219 `("PATH" ":" prefix (,path))))
221 (add-after 'wrap-executable 'post-install-check
222 (lambda* (#:key inputs outputs #:allow-other-keys)
224 (string-append (assoc-ref outputs "out")
229 (assoc-ref outputs "out")
231 (string-take (string-take-right
232 (assoc-ref inputs "python") 5) 3)
234 (getenv "PYTHONPATH")))
235 ;; There are 2 errors printed, but they are safe to ignore:
236 ;; 1) [E::hts_open_format] fail to open file ...
237 ;; 2) samtools view: failed to open ...
241 `(("autoconf" ,autoconf)
242 ("automake" ,automake)
245 ("python-nose" ,python2-nose)
246 ("python-pysam" ,python2-pysam)))
248 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
249 ("samtools" ,samtools)
253 ("coreutils" ,coreutils)))
255 `(("python-numpy" ,python2-numpy)))
256 (home-page "http://ecogenomics.github.io/BamM/")
257 (synopsis "Metagenomics-focused BAM file manipulator")
259 "BamM is a C library, wrapped in python, to efficiently generate and
260 parse BAM files, specifically for the analysis of metagenomic data. For
261 instance, it implements several methods to assess contig-wise read coverage.")
262 (license license:lgpl3+)))
264 (define-public bamtools
271 (url "https://github.com/pezmaster31/bamtools.git")
272 (commit (string-append "v" version))))
273 (file-name (git-file-name name version))
276 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
277 (build-system cmake-build-system)
279 `(#:tests? #f ;no "check" target
281 (modify-phases %standard-phases
283 'configure 'set-ldflags
284 (lambda* (#:key outputs #:allow-other-keys)
288 (assoc-ref outputs "out") "/lib/bamtools"))
290 (inputs `(("zlib" ,zlib)))
291 (home-page "https://github.com/pezmaster31/bamtools")
292 (synopsis "C++ API and command-line toolkit for working with BAM data")
294 "BamTools provides both a C++ API and a command-line toolkit for handling
296 (license license:expat)))
298 (define-public bcftools
304 (uri (string-append "https://github.com/samtools/bcftools/"
306 version "/bcftools-" version ".tar.bz2"))
309 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
310 (modules '((guix build utils)))
312 ;; Delete bundled htslib.
313 (delete-file-recursively "htslib-1.9")
315 (build-system gnu-build-system)
318 (list "--enable-libgsl")
321 (modify-phases %standard-phases
322 (add-before 'check 'patch-tests
324 (substitute* "test/test.pl"
325 (("/bin/bash") (which "bash")))
333 (home-page "https://samtools.github.io/bcftools/")
334 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
336 "BCFtools is a set of utilities that manipulate variant calls in the
337 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
338 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
339 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
340 (license (list license:gpl3+ license:expat))))
342 (define-public bedops
349 (url "https://github.com/bedops/bedops.git")
350 (commit (string-append "v" version))))
351 (file-name (git-file-name name version))
354 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
355 (build-system gnu-build-system)
358 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
360 (modify-phases %standard-phases
361 (add-after 'unpack 'unpack-tarballs
363 ;; FIXME: Bedops includes tarballs of minimally patched upstream
364 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
365 ;; libraries because at least one of the libraries (zlib) is
366 ;; patched to add a C++ function definition (deflateInit2cpp).
367 ;; Until the Bedops developers offer a way to link against system
368 ;; libraries we have to build the in-tree copies of these three
371 ;; See upstream discussion:
372 ;; https://github.com/bedops/bedops/issues/124
374 ;; Unpack the tarballs to benefit from shebang patching.
375 (with-directory-excursion "third-party"
376 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
377 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
378 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
379 ;; Disable unpacking of tarballs in Makefile.
380 (substitute* "system.mk/Makefile.linux"
381 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
382 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
383 (substitute* "third-party/zlib-1.2.7/Makefile.in"
384 (("^SHELL=.*$") "SHELL=bash\n"))
386 (delete 'configure))))
387 (home-page "https://github.com/bedops/bedops")
388 (synopsis "Tools for high-performance genomic feature operations")
390 "BEDOPS is a suite of tools to address common questions raised in genomic
391 studies---mostly with regard to overlap and proximity relationships between
392 data sets. It aims to be scalable and flexible, facilitating the efficient
393 and accurate analysis and management of large-scale genomic data.
395 BEDOPS provides tools that perform highly efficient and scalable Boolean and
396 other set operations, statistical calculations, archiving, conversion and
397 other management of genomic data of arbitrary scale. Tasks can be easily
398 split by chromosome for distributing whole-genome analyses across a
399 computational cluster.")
400 (license license:gpl2+)))
402 (define-public bedtools
408 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
409 "download/v" version "/"
410 "bedtools-" version ".tar.gz"))
413 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
414 (build-system gnu-build-system)
416 '(#:test-target "test"
418 (list (string-append "prefix=" (assoc-ref %outputs "out")))
420 (modify-phases %standard-phases
421 (delete 'configure))))
422 (native-inputs `(("python" ,python-2)))
424 `(("samtools" ,samtools)
426 (home-page "https://github.com/arq5x/bedtools2")
427 (synopsis "Tools for genome analysis and arithmetic")
429 "Collectively, the bedtools utilities are a swiss-army knife of tools for
430 a wide-range of genomics analysis tasks. The most widely-used tools enable
431 genome arithmetic: that is, set theory on the genome. For example, bedtools
432 allows one to intersect, merge, count, complement, and shuffle genomic
433 intervals from multiple files in widely-used genomic file formats such as BAM,
435 (license license:gpl2)))
437 ;; Later releases of bedtools produce files with more columns than
438 ;; what Ribotaper expects.
439 (define-public bedtools-2.18
440 (package (inherit bedtools)
445 (uri (string-append "https://github.com/arq5x/bedtools2/"
446 "releases/download/v" version
447 "/bedtools-" version ".tar.gz"))
450 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
452 '(#:test-target "test"
454 (modify-phases %standard-phases
457 (lambda* (#:key outputs #:allow-other-keys)
458 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
459 (for-each (lambda (file)
460 (install-file file bin))
461 (find-files "bin" ".*")))
464 ;; Needed for pybedtools.
465 (define-public bedtools-2.26
466 (package (inherit bedtools)
471 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
472 "download/v" version "/"
473 "bedtools-" version ".tar.gz"))
476 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
478 (define-public ribotaper
484 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
485 "files/RiboTaper/RiboTaper_Version_"
489 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
490 (build-system gnu-build-system)
493 (modify-phases %standard-phases
494 (add-after 'install 'wrap-executables
495 (lambda* (#:key inputs outputs #:allow-other-keys)
496 (let* ((out (assoc-ref outputs "out")))
499 (wrap-program (string-append out "/bin/" script)
500 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
501 '("create_annotations_files.bash"
502 "create_metaplots.bash"
503 "Ribotaper_ORF_find.sh"
507 `(("bedtools" ,bedtools-2.18)
508 ("samtools" ,samtools-0.1)
509 ("r-minimal" ,r-minimal)
510 ("r-foreach" ,r-foreach)
511 ("r-xnomial" ,r-xnomial)
513 ("r-multitaper" ,r-multitaper)
514 ("r-seqinr" ,r-seqinr)))
515 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
516 (synopsis "Define translated ORFs using ribosome profiling data")
518 "Ribotaper is a method for defining translated @dfn{open reading
519 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
520 provides the Ribotaper pipeline.")
521 (license license:gpl3+)))
523 (define-public ribodiff
531 (url "https://github.com/ratschlab/RiboDiff.git")
532 (commit (string-append "v" version))))
533 (file-name (git-file-name name version))
536 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
537 (build-system python-build-system)
541 (modify-phases %standard-phases
542 ;; Generate an installable executable script wrapper.
543 (add-after 'unpack 'patch-setup.py
545 (substitute* "setup.py"
546 (("^(.*)packages=.*" line prefix)
547 (string-append line "\n"
548 prefix "scripts=['scripts/TE.py'],\n")))
551 `(("python-numpy" ,python2-numpy)
552 ("python-matplotlib" ,python2-matplotlib)
553 ("python-scipy" ,python2-scipy)
554 ("python-statsmodels" ,python2-statsmodels)))
556 `(("python-mock" ,python2-mock)
557 ("python-nose" ,python2-nose)))
558 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
559 (synopsis "Detect translation efficiency changes from ribosome footprints")
560 (description "RiboDiff is a statistical tool that detects the protein
561 translational efficiency change from Ribo-Seq (ribosome footprinting) and
562 RNA-Seq data. It uses a generalized linear model to detect genes showing
563 difference in translational profile taking mRNA abundance into account. It
564 facilitates us to decipher the translational regulation that behave
565 independently with transcriptional regulation.")
566 (license license:gpl3+)))
568 (define-public bioawk
575 (url "https://github.com/lh3/bioawk.git")
576 (commit (string-append "v" version))))
577 (file-name (git-file-name name version))
580 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
581 (build-system gnu-build-system)
587 `(#:tests? #f ; There are no tests to run.
588 ;; Bison must generate files, before other targets can build.
591 (modify-phases %standard-phases
592 (delete 'configure) ; There is no configure phase.
594 (lambda* (#:key outputs #:allow-other-keys)
595 (let* ((out (assoc-ref outputs "out"))
596 (bin (string-append out "/bin"))
597 (man (string-append out "/share/man/man1")))
599 (copy-file "awk.1" (string-append man "/bioawk.1"))
600 (install-file "bioawk" bin))
602 (home-page "https://github.com/lh3/bioawk")
603 (synopsis "AWK with bioinformatics extensions")
604 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
605 support of several common biological data formats, including optionally gzip'ed
606 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
607 also adds a few built-in functions and a command line option to use TAB as the
608 input/output delimiter. When the new functionality is not used, bioawk is
609 intended to behave exactly the same as the original BWK awk.")
610 (license license:x11)))
612 (define-public python-pybedtools
614 (name "python-pybedtools")
618 (uri (pypi-uri "pybedtools" version))
621 "0l2b2wrnj85azfqgr0zwr60f7j58vlla1hcgxvr9rwikpl8j72ji"))))
622 (build-system python-build-system)
625 (modify-phases %standard-phases
626 ;; See https://github.com/daler/pybedtools/issues/261
627 (add-after 'unpack 'disable-broken-tests
629 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
630 ;; graphical environment.
631 (substitute* "pybedtools/test/test_scripts.py"
632 (("def test_venn_mpl")
633 "def _do_not_test_venn_mpl"))
634 ;; Requires internet access.
635 (substitute* "pybedtools/test/test_helpers.py"
636 (("def test_chromsizes")
637 "def _do_not_test_chromsizes"))
638 ;; FIXME: these two fail for no good reason.
639 (substitute* "pybedtools/test/test1.py"
640 (("def test_issue_157")
641 "def _do_not_test_issue_157")
642 (("def test_to_dataframe")
643 "def _do_not_test_to_dataframe"))
646 ;; Tests don't pass with Bedtools 2.27.1.
647 ;; See https://github.com/daler/pybedtools/issues/260
648 `(("bedtools" ,bedtools-2.26)
649 ("samtools" ,samtools)
650 ("python-matplotlib" ,python-matplotlib)
651 ("python-pysam" ,python-pysam)
652 ("python-pyyaml" ,python-pyyaml)))
654 `(("python-numpy" ,python-numpy)
655 ("python-pandas" ,python-pandas)
656 ("python-cython" ,python-cython)
657 ("python-nose" ,python-nose)
658 ("kentutils" ,kentutils) ; for bedGraphToBigWig
659 ("python-six" ,python-six)))
660 (home-page "https://pythonhosted.org/pybedtools/")
661 (synopsis "Python wrapper for BEDtools programs")
663 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
664 which are widely used for genomic interval manipulation or \"genome algebra\".
665 pybedtools extends BEDTools by offering feature-level manipulations from with
667 (license license:gpl2+)))
669 (define-public python2-pybedtools
670 (let ((pkg (package-with-python2 python-pybedtools)))
671 (package (inherit pkg)
673 `(#:modules ((ice-9 ftw)
677 (guix build python-build-system))
678 ;; See https://github.com/daler/pybedtools/issues/192
679 ,@(substitute-keyword-arguments (package-arguments pkg)
681 `(modify-phases ,phases
684 (let ((cwd (getcwd)))
686 (string-append cwd "/build/"
687 (find (cut string-prefix? "lib" <>)
688 (scandir (string-append cwd "/build")))
689 ":" (getenv "PYTHONPATH"))))
690 ;; The tests need to be run from elsewhere...
691 (mkdir-p "/tmp/test")
692 (copy-recursively "pybedtools/test" "/tmp/test")
693 (with-directory-excursion "/tmp/test"
695 ;; This test fails for unknown reasons
696 "--exclude=.*test_getting_example_beds"))
699 (define-public python-biom-format
701 (name "python-biom-format")
706 ;; Use GitHub as source because PyPI distribution does not contain
707 ;; test data: https://github.com/biocore/biom-format/issues/693
709 (url "https://github.com/biocore/biom-format.git")
711 (file-name (git-file-name name version))
714 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
715 (build-system python-build-system)
718 (modify-phases %standard-phases
719 (add-after 'unpack 'use-cython
720 (lambda _ (setenv "USE_CYTHON" "1") #t))
721 (add-after 'unpack 'disable-broken-test
723 (substitute* "biom/tests/test_cli/test_validate_table.py"
724 (("^(.+)def test_invalid_hdf5" m indent)
725 (string-append indent
726 "@npt.dec.skipif(True, msg='Guix')\n"
729 (add-before 'reset-gzip-timestamps 'make-files-writable
730 (lambda* (#:key outputs #:allow-other-keys)
731 (let ((out (assoc-ref outputs "out")))
732 (for-each (lambda (file) (chmod file #o644))
733 (find-files out "\\.gz"))
736 `(("python-numpy" ,python-numpy)
737 ("python-scipy" ,python-scipy)
738 ("python-flake8" ,python-flake8)
739 ("python-future" ,python-future)
740 ("python-click" ,python-click)
741 ("python-h5py" ,python-h5py)
742 ("python-pandas" ,python-pandas)))
744 `(("python-cython" ,python-cython)
745 ("python-pytest" ,python-pytest)
746 ("python-pytest-cov" ,python-pytest-cov)
747 ("python-nose" ,python-nose)))
748 (home-page "http://www.biom-format.org")
749 (synopsis "Biological Observation Matrix (BIOM) format utilities")
751 "The BIOM file format is designed to be a general-use format for
752 representing counts of observations e.g. operational taxonomic units, KEGG
753 orthology groups or lipid types, in one or more biological samples
754 e.g. microbiome samples, genomes, metagenomes.")
755 (license license:bsd-3)
756 (properties `((python2-variant . ,(delay python2-biom-format))))))
758 (define-public python2-biom-format
759 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
763 (substitute-keyword-arguments (package-arguments base)
765 `(modify-phases ,phases
766 ;; Do not require the unmaintained pyqi library.
767 (add-after 'unpack 'remove-pyqi
769 (substitute* "setup.py"
770 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
773 (define-public bioperl-minimal
774 (let* ((inputs `(("perl-module-build" ,perl-module-build)
775 ("perl-data-stag" ,perl-data-stag)
776 ("perl-libwww" ,perl-libwww)
777 ("perl-uri" ,perl-uri)))
779 (map (compose package-name cadr)
782 (map (compose package-transitive-target-inputs cadr) inputs))))))
784 (name "bioperl-minimal")
789 (uri (string-append "https://github.com/bioperl/bioperl-live/"
791 (string-map (lambda (c)
797 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
798 (build-system perl-build-system)
801 (modify-phases %standard-phases
803 'install 'wrap-programs
804 (lambda* (#:key outputs #:allow-other-keys)
805 ;; Make sure all executables in "bin" find the required Perl
806 ;; modules at runtime. As the PERL5LIB variable contains also
807 ;; the paths of native inputs, we pick the transitive target
808 ;; inputs from %build-inputs.
809 (let* ((out (assoc-ref outputs "out"))
810 (bin (string-append out "/bin/"))
812 (cons (string-append out "/lib/perl5/site_perl")
814 (assoc-ref %build-inputs name))
815 ',transitive-inputs))
817 (for-each (lambda (file)
819 `("PERL5LIB" ":" prefix (,path))))
820 (find-files bin "\\.pl$"))
824 `(("perl-test-most" ,perl-test-most)))
825 (home-page "https://metacpan.org/release/BioPerl")
826 (synopsis "Bioinformatics toolkit")
828 "BioPerl is the product of a community effort to produce Perl code which
829 is useful in biology. Examples include Sequence objects, Alignment objects
830 and database searching objects. These objects not only do what they are
831 advertised to do in the documentation, but they also interact - Alignment
832 objects are made from the Sequence objects, Sequence objects have access to
833 Annotation and SeqFeature objects and databases, Blast objects can be
834 converted to Alignment objects, and so on. This means that the objects
835 provide a coordinated and extensible framework to do computational biology.")
836 (license license:perl-license))))
838 (define-public python-biopython
840 (name "python-biopython")
844 ;; use PyPi rather than biopython.org to ease updating
845 (uri (pypi-uri "biopython" version))
848 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
849 (build-system python-build-system)
852 (modify-phases %standard-phases
853 (add-before 'check 'set-home
854 ;; Some tests require a home directory to be set.
855 (lambda _ (setenv "HOME" "/tmp") #t)))))
857 `(("python-numpy" ,python-numpy)))
858 (home-page "http://biopython.org/")
859 (synopsis "Tools for biological computation in Python")
861 "Biopython is a set of tools for biological computation including parsers
862 for bioinformatics files into Python data structures; interfaces to common
863 bioinformatics programs; a standard sequence class and tools for performing
864 common operations on them; code to perform data classification; code for
865 dealing with alignments; code making it easy to split up parallelizable tasks
866 into separate processes; and more.")
867 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
869 (define-public python2-biopython
870 (package-with-python2 python-biopython))
872 (define-public python-fastalite
874 (name "python-fastalite")
879 (uri (pypi-uri "fastalite" version))
882 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
883 (build-system python-build-system)
885 `(#:tests? #f)) ; Test data is not distributed.
886 (home-page "https://github.com/nhoffman/fastalite")
887 (synopsis "Simplest possible FASTA parser")
888 (description "This library implements a FASTA and a FASTQ parser without
889 relying on a complex dependency tree.")
890 (license license:expat)))
892 (define-public python2-fastalite
893 (package-with-python2 python-fastalite))
895 (define-public bpp-core
896 ;; The last release was in 2014 and the recommended way to install from source
897 ;; is to clone the git repository, so we do this.
898 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
899 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
902 (version (string-append "2.2.0-1." (string-take commit 7)))
906 (url "http://biopp.univ-montp2.fr/git/bpp-core")
908 (file-name (string-append name "-" version "-checkout"))
911 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
912 (build-system cmake-build-system)
914 `(#:parallel-build? #f))
916 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
917 ; compile all of the bpp packages with GCC 5.
918 (home-page "http://biopp.univ-montp2.fr")
919 (synopsis "C++ libraries for Bioinformatics")
921 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
922 analysis, phylogenetics, molecular evolution and population genetics. It is
923 Object Oriented and is designed to be both easy to use and computer efficient.
924 Bio++ intends to help programmers to write computer expensive programs, by
925 providing them a set of re-usable tools.")
926 (license license:cecill-c))))
928 (define-public bpp-phyl
929 ;; The last release was in 2014 and the recommended way to install from source
930 ;; is to clone the git repository, so we do this.
931 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
932 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
935 (version (string-append "2.2.0-1." (string-take commit 7)))
939 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
941 (file-name (string-append name "-" version "-checkout"))
944 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
945 (build-system cmake-build-system)
947 `(#:parallel-build? #f
948 ;; If out-of-source, test data is not copied into the build directory
949 ;; so the tests fail.
950 #:out-of-source? #f))
952 `(("bpp-core" ,bpp-core)
954 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
957 (home-page "http://biopp.univ-montp2.fr")
958 (synopsis "Bio++ phylogenetic Library")
960 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
961 analysis, phylogenetics, molecular evolution and population genetics. This
962 library provides phylogenetics-related modules.")
963 (license license:cecill-c))))
965 (define-public bpp-popgen
966 ;; The last release was in 2014 and the recommended way to install from source
967 ;; is to clone the git repository, so we do this.
968 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
969 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
972 (version (string-append "2.2.0-1." (string-take commit 7)))
976 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
978 (file-name (string-append name "-" version "-checkout"))
981 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
982 (build-system cmake-build-system)
984 `(#:parallel-build? #f
985 #:tests? #f)) ; There are no tests.
987 `(("bpp-core" ,bpp-core)
990 (home-page "http://biopp.univ-montp2.fr")
991 (synopsis "Bio++ population genetics library")
993 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
994 analysis, phylogenetics, molecular evolution and population genetics. This
995 library provides population genetics-related modules.")
996 (license license:cecill-c))))
998 (define-public bpp-seq
999 ;; The last release was in 2014 and the recommended way to install from source
1000 ;; is to clone the git repository, so we do this.
1001 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1002 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1005 (version (string-append "2.2.0-1." (string-take commit 7)))
1009 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1011 (file-name (string-append name "-" version "-checkout"))
1014 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1015 (build-system cmake-build-system)
1017 `(#:parallel-build? #f
1018 ;; If out-of-source, test data is not copied into the build directory
1019 ;; so the tests fail.
1020 #:out-of-source? #f))
1022 `(("bpp-core" ,bpp-core)
1023 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1024 (home-page "http://biopp.univ-montp2.fr")
1025 (synopsis "Bio++ sequence library")
1027 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1028 analysis, phylogenetics, molecular evolution and population genetics. This
1029 library provides sequence-related modules.")
1030 (license license:cecill-c))))
1032 (define-public bppsuite
1033 ;; The last release was in 2014 and the recommended way to install from source
1034 ;; is to clone the git repository, so we do this.
1035 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1036 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1039 (version (string-append "2.2.0-1." (string-take commit 7)))
1043 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1045 (file-name (string-append name "-" version "-checkout"))
1048 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1049 (build-system cmake-build-system)
1051 `(#:parallel-build? #f
1052 #:tests? #f)) ; There are no tests.
1056 ("texinfo" ,texinfo)))
1058 `(("bpp-core" ,bpp-core)
1059 ("bpp-seq" ,bpp-seq)
1060 ("bpp-phyl" ,bpp-phyl)
1061 ("bpp-phyl" ,bpp-popgen)
1063 (home-page "http://biopp.univ-montp2.fr")
1064 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1066 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1067 analysis, phylogenetics, molecular evolution and population genetics. This
1068 package provides command line tools using the Bio++ library.")
1069 (license license:cecill-c))))
1071 (define-public blast+
1078 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1079 version "/ncbi-blast-" version "+-src.tar.gz"))
1082 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1083 (patches (search-patches "blast+-fix-makefile.patch"))
1084 (modules '((guix build utils)))
1087 ;; Remove bundled bzip2, zlib and pcre.
1088 (delete-file-recursively "c++/src/util/compress/bzip2")
1089 (delete-file-recursively "c++/src/util/compress/zlib")
1090 (delete-file-recursively "c++/src/util/regexp")
1091 (substitute* "c++/src/util/compress/Makefile.in"
1092 (("bzip2 zlib api") "api"))
1093 ;; Remove useless msbuild directory
1094 (delete-file-recursively
1095 "c++/src/build-system/project_tree_builder/msbuild")
1097 (build-system gnu-build-system)
1099 `(;; There are two(!) tests for this massive library, and both fail with
1100 ;; "unparsable timing stats".
1101 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1102 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1105 #:parallel-build? #f ; not supported
1107 (modify-phases %standard-phases
1108 (add-before 'configure 'set-HOME
1109 ;; $HOME needs to be set at some point during the configure phase
1110 (lambda _ (setenv "HOME" "/tmp") #t))
1111 (add-after 'unpack 'enter-dir
1112 (lambda _ (chdir "c++") #t))
1113 (add-after 'enter-dir 'fix-build-system
1115 (define (which* cmd)
1116 (cond ((string=? cmd "date")
1117 ;; make call to "date" deterministic
1122 (format (current-error-port)
1123 "WARNING: Unable to find absolute path for ~s~%"
1127 ;; Rewrite hardcoded paths to various tools
1128 (substitute* (append '("src/build-system/configure.ac"
1129 "src/build-system/configure"
1130 "src/build-system/helpers/run_with_lock.c"
1131 "scripts/common/impl/if_diff.sh"
1132 "scripts/common/impl/run_with_lock.sh"
1133 "src/build-system/Makefile.configurables.real"
1134 "src/build-system/Makefile.in.top"
1135 "src/build-system/Makefile.meta.gmake=no"
1136 "src/build-system/Makefile.meta.in"
1137 "src/build-system/Makefile.meta_l"
1138 "src/build-system/Makefile.meta_p"
1139 "src/build-system/Makefile.meta_r"
1140 "src/build-system/Makefile.mk.in"
1141 "src/build-system/Makefile.requirements"
1142 "src/build-system/Makefile.rules_with_autodep.in")
1143 (find-files "scripts/common/check" "\\.sh$"))
1144 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1145 (or (which* cmd) all)))
1147 (substitute* (find-files "src/build-system" "^config.*")
1148 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1151 ;; rewrite "/var/tmp" in check script
1152 (substitute* "scripts/common/check/check_make_unix.sh"
1153 (("/var/tmp") "/tmp"))
1155 ;; do not reset PATH
1156 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1158 (("action=/bin/") "action=")
1159 (("export PATH") ":"))
1162 (lambda* (#:key inputs outputs #:allow-other-keys)
1163 (let ((out (assoc-ref outputs "out"))
1164 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1165 (include (string-append (assoc-ref outputs "include")
1166 "/include/ncbi-tools++")))
1167 ;; The 'configure' script doesn't recognize things like
1168 ;; '--enable-fast-install'.
1169 (invoke "./configure.orig"
1170 (string-append "--with-build-root=" (getcwd) "/build")
1171 (string-append "--prefix=" out)
1172 (string-append "--libdir=" lib)
1173 (string-append "--includedir=" include)
1174 (string-append "--with-bz2="
1175 (assoc-ref inputs "bzip2"))
1176 (string-append "--with-z="
1177 (assoc-ref inputs "zlib"))
1178 (string-append "--with-pcre="
1179 (assoc-ref inputs "pcre"))
1180 ;; Each library is built twice by default, once
1181 ;; with "-static" in its name, and again
1186 (outputs '("out" ; 21 MB
1194 ("python" ,python-wrapper)))
1197 (home-page "http://blast.ncbi.nlm.nih.gov")
1198 (synopsis "Basic local alignment search tool")
1200 "BLAST is a popular method of performing a DNA or protein sequence
1201 similarity search, using heuristics to produce results quickly. It also
1202 calculates an “expect value” that estimates how many matches would have
1203 occurred at a given score by chance, which can aid a user in judging how much
1204 confidence to have in an alignment.")
1205 ;; Most of the sources are in the public domain, with the following
1208 ;; * ./c++/include/util/bitset/
1209 ;; * ./c++/src/html/ncbi_menu*.js
1211 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1213 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1215 ;; * ./c++/src/corelib/teamcity_*
1216 (license (list license:public-domain
1222 (define-public bless
1228 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1232 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1233 (modules '((guix build utils)))
1236 ;; Remove bundled boost, pigz, zlib, and .git directory
1237 ;; FIXME: also remove bundled sources for murmurhash3 and
1238 ;; kmc once packaged.
1239 (delete-file-recursively "boost")
1240 (delete-file-recursively "pigz")
1241 (delete-file-recursively "google-sparsehash")
1242 (delete-file-recursively "zlib")
1243 (delete-file-recursively ".git")
1245 (build-system gnu-build-system)
1247 '(#:tests? #f ;no "check" target
1249 (list (string-append "ZLIB="
1250 (assoc-ref %build-inputs "zlib:static")
1252 (string-append "LDFLAGS="
1253 (string-join '("-lboost_filesystem"
1260 (modify-phases %standard-phases
1261 (add-after 'unpack 'do-not-build-bundled-pigz
1262 (lambda* (#:key inputs outputs #:allow-other-keys)
1263 (substitute* "Makefile"
1264 (("cd pigz/pigz-2.3.3; make") ""))
1266 (add-after 'unpack 'patch-paths-to-executables
1267 (lambda* (#:key inputs outputs #:allow-other-keys)
1268 (substitute* "parse_args.cpp"
1269 (("kmc_binary = .*")
1270 (string-append "kmc_binary = \""
1271 (assoc-ref outputs "out")
1273 (("pigz_binary = .*")
1274 (string-append "pigz_binary = \""
1275 (assoc-ref inputs "pigz")
1279 (lambda* (#:key outputs #:allow-other-keys)
1280 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1281 (for-each (lambda (file)
1282 (install-file file bin))
1283 '("bless" "kmc/bin/kmc"))
1285 (delete 'configure))))
1289 `(("openmpi" ,openmpi)
1291 ("sparsehash" ,sparsehash)
1293 ("zlib:static" ,zlib "static")
1295 (supported-systems '("x86_64-linux"))
1296 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1297 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1299 "@dfn{Bloom-filter-based error correction solution for high-throughput
1300 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1301 correction tool for genomic reads produced by @dfn{Next-generation
1302 sequencing} (NGS). BLESS produces accurate correction results with much less
1303 memory compared with previous solutions and is also able to tolerate a higher
1304 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1305 errors at the end of reads.")
1306 (license license:gpl3+)))
1308 (define-public bowtie
1315 (url "https://github.com/BenLangmead/bowtie2.git")
1316 (commit (string-append "v" version))))
1317 (file-name (git-file-name name version))
1320 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1321 (modules '((guix build utils)))
1324 (substitute* "Makefile"
1325 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1326 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1327 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1329 (build-system gnu-build-system)
1334 (string-append "prefix=" (assoc-ref %outputs "out")))
1336 (modify-phases %standard-phases
1341 "scripts/test/simple_tests.pl"
1342 "--bowtie2=./bowtie2"
1343 "--bowtie2-build=./bowtie2-build")
1348 ("python" ,python-wrapper)))
1351 ("perl-clone" ,perl-clone)
1352 ("perl-test-deep" ,perl-test-deep)
1353 ("perl-test-simple" ,perl-test-simple)))
1354 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1355 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1357 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1358 reads to long reference sequences. It is particularly good at aligning reads
1359 of about 50 up to 100s or 1,000s of characters, and particularly good at
1360 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1361 genome with an FM Index to keep its memory footprint small: for the human
1362 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1363 gapped, local, and paired-end alignment modes.")
1364 (supported-systems '("x86_64-linux"))
1365 (license license:gpl3+)))
1367 (define-public tophat
1374 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1378 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1379 (modules '((guix build utils)))
1382 ;; Remove bundled SeqAn and samtools
1383 (delete-file-recursively "src/SeqAn-1.4.2")
1384 (delete-file-recursively "src/samtools-0.1.18")
1386 (build-system gnu-build-system)
1388 '(#:parallel-build? #f ; not supported
1390 (modify-phases %standard-phases
1391 (add-after 'unpack 'use-system-samtools
1392 (lambda* (#:key inputs #:allow-other-keys)
1393 (substitute* "src/Makefile.in"
1394 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1395 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1396 (("SAMPROG = samtools_0\\.1\\.18") "")
1397 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1398 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1399 (substitute* '("src/common.cpp"
1401 (("samtools_0.1.18") (which "samtools")))
1402 (substitute* '("src/common.h"
1403 "src/bam2fastx.cpp")
1404 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1405 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1406 (substitute* '("src/bwt_map.h"
1408 "src/align_status.h")
1409 (("#include <bam.h>") "#include <samtools/bam.h>")
1410 (("#include <sam.h>") "#include <samtools/sam.h>"))
1415 ("samtools" ,samtools-0.1)
1416 ("ncurses" ,ncurses)
1417 ("python" ,python-2)
1420 ("seqan" ,seqan-1)))
1421 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1422 (synopsis "Spliced read mapper for RNA-Seq data")
1424 "TopHat is a fast splice junction mapper for nucleotide sequence
1425 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1426 mammalian-sized genomes using the ultra high-throughput short read
1427 aligner Bowtie, and then analyzes the mapping results to identify
1428 splice junctions between exons.")
1429 ;; TopHat is released under the Boost Software License, Version 1.0
1430 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1431 (license license:boost1.0)))
1440 "https://github.com/lh3/bwa/releases/download/v"
1441 version "/bwa-" version ".tar.bz2"))
1444 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1445 (build-system gnu-build-system)
1447 '(#:tests? #f ;no "check" target
1449 (modify-phases %standard-phases
1451 (lambda* (#:key outputs #:allow-other-keys)
1452 (let ((bin (string-append
1453 (assoc-ref outputs "out") "/bin"))
1455 (assoc-ref outputs "out") "/share/doc/bwa"))
1457 (assoc-ref outputs "out") "/share/man/man1")))
1458 (install-file "bwa" bin)
1459 (install-file "README.md" doc)
1460 (install-file "bwa.1" man))
1462 ;; no "configure" script
1463 (delete 'configure))))
1464 (inputs `(("zlib" ,zlib)))
1465 ;; Non-portable SSE instructions are used so building fails on platforms
1466 ;; other than x86_64.
1467 (supported-systems '("x86_64-linux"))
1468 (home-page "http://bio-bwa.sourceforge.net/")
1469 (synopsis "Burrows-Wheeler sequence aligner")
1471 "BWA is a software package for mapping low-divergent sequences against a
1472 large reference genome, such as the human genome. It consists of three
1473 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1474 designed for Illumina sequence reads up to 100bp, while the rest two for
1475 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1476 features such as long-read support and split alignment, but BWA-MEM, which is
1477 the latest, is generally recommended for high-quality queries as it is faster
1478 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1479 70-100bp Illumina reads.")
1480 (license license:gpl3+)))
1482 (define-public bwa-pssm
1483 (package (inherit bwa)
1489 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1491 (file-name (git-file-name name version))
1494 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1495 (build-system gnu-build-system)
1500 (home-page "http://bwa-pssm.binf.ku.dk/")
1501 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1503 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1504 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1505 existing aligners it is fast and sensitive. Unlike most other aligners,
1506 however, it is also adaptible in the sense that one can direct the alignment
1507 based on known biases within the data set. It is coded as a modification of
1508 the original BWA alignment program and shares the genome index structure as
1509 well as many of the command line options.")
1510 (license license:gpl3+)))
1512 (define-public python-bx-python
1514 (name "python-bx-python")
1518 (uri (pypi-uri "bx-python" version))
1521 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1522 (build-system python-build-system)
1523 ;; Tests fail because test data are not included
1524 (arguments '(#:tests? #f))
1526 `(("python-numpy" ,python-numpy)
1527 ("python-six" ,python-six)))
1531 `(("python-lzo" ,python-lzo)
1532 ("python-nose" ,python-nose)
1533 ("python-cython" ,python-cython)))
1534 (home-page "https://github.com/bxlab/bx-python")
1535 (synopsis "Tools for manipulating biological data")
1537 "bx-python provides tools for manipulating biological data, particularly
1538 multiple sequence alignments.")
1539 (license license:expat)))
1541 (define-public python2-bx-python
1542 (package-with-python2 python-bx-python))
1544 (define-public python-pysam
1546 (name "python-pysam")
1550 ;; Test data is missing on PyPi.
1552 (url "https://github.com/pysam-developers/pysam.git")
1553 (commit (string-append "v" version))))
1554 (file-name (git-file-name name version))
1557 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1558 (modules '((guix build utils)))
1560 ;; Drop bundled htslib. TODO: Also remove samtools
1562 (delete-file-recursively "htslib")
1564 (build-system python-build-system)
1566 `(#:modules ((ice-9 ftw)
1568 (guix build python-build-system)
1571 (modify-phases %standard-phases
1572 (add-before 'build 'set-flags
1573 (lambda* (#:key inputs #:allow-other-keys)
1574 (setenv "HTSLIB_MODE" "external")
1575 (setenv "HTSLIB_LIBRARY_DIR"
1576 (string-append (assoc-ref inputs "htslib") "/lib"))
1577 (setenv "HTSLIB_INCLUDE_DIR"
1578 (string-append (assoc-ref inputs "htslib") "/include"))
1579 (setenv "LDFLAGS" "-lncurses")
1580 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1583 (lambda* (#:key inputs outputs #:allow-other-keys)
1584 ;; This file contains tests that require a connection to the
1586 (delete-file "tests/tabix_test.py")
1587 ;; FIXME: This test fails
1588 (delete-file "tests/AlignmentFile_test.py")
1589 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1590 (setenv "PYTHONPATH"
1592 (getenv "PYTHONPATH")
1593 ":" (getcwd) "/build/"
1594 (car (scandir "build"
1595 (negate (cut string-prefix? "." <>))))))
1596 ;; Step out of source dir so python does not import from CWD.
1597 (with-directory-excursion "tests"
1598 (setenv "HOME" "/tmp")
1599 (invoke "make" "-C" "pysam_data")
1600 (invoke "make" "-C" "cbcf_data")
1601 ;; Running nosetests without explicitly asking for a single
1602 ;; process leads to a crash. Running with multiple processes
1603 ;; fails because the tests are not designed to run in parallel.
1605 ;; FIXME: tests keep timing out on some systems.
1606 (invoke "nosetests" "-v" "--processes" "1")))))))
1608 `(("htslib" ,htslib))) ; Included from installed header files.
1610 `(("ncurses" ,ncurses)
1614 `(("python-cython" ,python-cython)
1615 ;; Dependencies below are are for tests only.
1616 ("samtools" ,samtools)
1617 ("bcftools" ,bcftools)
1618 ("python-nose" ,python-nose)))
1619 (home-page "https://github.com/pysam-developers/pysam")
1620 (synopsis "Python bindings to the SAMtools C API")
1622 "Pysam is a Python module for reading and manipulating files in the
1623 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1624 also includes an interface for tabix.")
1625 (license license:expat)))
1627 (define-public python2-pysam
1628 (package-with-python2 python-pysam))
1630 (define-public python-twobitreader
1632 (name "python-twobitreader")
1637 (url "https://github.com/benjschiller/twobitreader")
1639 (file-name (git-file-name name version))
1642 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1643 (build-system python-build-system)
1644 ;; Tests are not included
1645 (arguments '(#:tests? #f))
1647 `(("python-sphinx" ,python-sphinx)))
1648 (home-page "https://github.com/benjschiller/twobitreader")
1649 (synopsis "Python library for reading .2bit files")
1651 "twobitreader is a Python library for reading .2bit files as used by the
1652 UCSC genome browser.")
1653 (license license:artistic2.0)))
1655 (define-public python2-twobitreader
1656 (package-with-python2 python-twobitreader))
1658 (define-public python-plastid
1660 (name "python-plastid")
1664 (uri (pypi-uri "plastid" version))
1667 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1668 (build-system python-build-system)
1670 ;; Some test files are not included.
1673 `(("python-numpy" ,python-numpy)
1674 ("python-scipy" ,python-scipy)
1675 ("python-pandas" ,python-pandas)
1676 ("python-pysam" ,python-pysam)
1677 ("python-matplotlib" ,python-matplotlib)
1678 ("python-biopython" ,python-biopython)
1679 ("python-twobitreader" ,python-twobitreader)
1680 ("python-termcolor" ,python-termcolor)))
1682 `(("python-cython" ,python-cython)
1683 ("python-nose" ,python-nose)))
1684 (home-page "https://github.com/joshuagryphon/plastid")
1685 (synopsis "Python library for genomic analysis")
1687 "plastid is a Python library for genomic analysis – in particular,
1688 high-throughput sequencing data – with an emphasis on simplicity.")
1689 (license license:bsd-3)))
1691 (define-public python2-plastid
1692 (package-with-python2 python-plastid))
1694 (define-public cd-hit
1700 (uri (string-append "https://github.com/weizhongli/cdhit"
1701 "/releases/download/V" version
1703 "-2017-0621-source.tar.gz"))
1706 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1707 (build-system gnu-build-system)
1709 `(#:tests? #f ; there are no tests
1711 ;; Executables are copied directly to the PREFIX.
1712 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1714 (modify-phases %standard-phases
1715 ;; No "configure" script
1717 ;; Remove sources of non-determinism
1718 (add-after 'unpack 'be-timeless
1720 (substitute* "cdhit-utility.c++"
1721 ((" \\(built on \" __DATE__ \"\\)") ""))
1722 (substitute* "cdhit-common.c++"
1723 (("__DATE__") "\"0\"")
1724 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1726 ;; The "install" target does not create the target directory.
1727 (add-before 'install 'create-target-dir
1728 (lambda* (#:key outputs #:allow-other-keys)
1729 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1733 (home-page "http://weizhongli-lab.org/cd-hit/")
1734 (synopsis "Cluster and compare protein or nucleotide sequences")
1736 "CD-HIT is a program for clustering and comparing protein or nucleotide
1737 sequences. CD-HIT is designed to be fast and handle extremely large
1739 ;; The manual says: "It can be copied under the GNU General Public License
1740 ;; version 2 (GPLv2)."
1741 (license license:gpl2)))
1743 (define-public clipper
1750 (url "https://github.com/YeoLab/clipper.git")
1752 (file-name (git-file-name name version))
1755 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1756 (modules '((guix build utils)))
1759 ;; remove unnecessary setup dependency
1760 (substitute* "setup.py"
1761 (("setup_requires = .*") ""))
1763 (build-system python-build-system)
1765 `(#:python ,python-2 ; only Python 2 is supported
1767 (modify-phases %standard-phases
1768 ;; This is fixed in upstream commit
1769 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1770 (add-after 'unpack 'fix-typo
1772 (substitute* "clipper/src/readsToWiggle.pyx"
1776 `(("htseq" ,python2-htseq)
1777 ("python-pybedtools" ,python2-pybedtools)
1778 ("python-cython" ,python2-cython)
1779 ("python-scikit-learn" ,python2-scikit-learn)
1780 ("python-matplotlib" ,python2-matplotlib)
1781 ("python-pandas" ,python2-pandas)
1782 ("python-pysam" ,python2-pysam)
1783 ("python-numpy" ,python2-numpy)
1784 ("python-scipy" ,python2-scipy)))
1786 `(("python-mock" ,python2-mock) ; for tests
1787 ("python-nose" ,python2-nose) ; for tests
1788 ("python-pytz" ,python2-pytz))) ; for tests
1789 (home-page "https://github.com/YeoLab/clipper")
1790 (synopsis "CLIP peak enrichment recognition")
1792 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1793 (license license:gpl2)))
1795 (define-public codingquarry
1797 (name "codingquarry")
1802 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1806 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1807 (build-system gnu-build-system)
1809 '(#:tests? #f ; no "check" target
1811 (modify-phases %standard-phases
1814 (lambda* (#:key outputs #:allow-other-keys)
1815 (let* ((out (assoc-ref outputs "out"))
1816 (bin (string-append out "/bin"))
1817 (doc (string-append out "/share/doc/codingquarry")))
1818 (install-file "INSTRUCTIONS.pdf" doc)
1819 (copy-recursively "QuarryFiles"
1820 (string-append out "/QuarryFiles"))
1821 (install-file "CodingQuarry" bin)
1822 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1824 (inputs `(("openmpi" ,openmpi)))
1825 (native-search-paths
1826 (list (search-path-specification
1827 (variable "QUARRY_PATH")
1828 (files '("QuarryFiles")))))
1829 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1830 (synopsis "Fungal gene predictor")
1831 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1832 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1833 (home-page "https://sourceforge.net/projects/codingquarry/")
1834 (license license:gpl3+)))
1836 (define-public couger
1843 "http://couger.oit.duke.edu/static/assets/COUGER"
1847 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1848 (build-system gnu-build-system)
1852 (modify-phases %standard-phases
1857 (lambda* (#:key outputs #:allow-other-keys)
1858 (let* ((out (assoc-ref outputs "out"))
1859 (bin (string-append out "/bin")))
1860 (copy-recursively "src" (string-append out "/src"))
1862 ;; Add "src" directory to module lookup path.
1863 (substitute* "couger"
1865 (string-append "import sys\nsys.path.append(\""
1866 out "\")\nfrom argparse")))
1867 (install-file "couger" bin))
1870 'install 'wrap-program
1871 (lambda* (#:key inputs outputs #:allow-other-keys)
1872 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1873 (let* ((out (assoc-ref outputs "out"))
1874 (path (getenv "PYTHONPATH")))
1875 (wrap-program (string-append out "/bin/couger")
1876 `("PYTHONPATH" ":" prefix (,path))))
1879 `(("python" ,python-2)
1880 ("python2-pillow" ,python2-pillow)
1881 ("python2-numpy" ,python2-numpy)
1882 ("python2-scipy" ,python2-scipy)
1883 ("python2-matplotlib" ,python2-matplotlib)))
1885 `(("r-minimal" ,r-minimal)
1887 ("randomjungle" ,randomjungle)))
1889 `(("unzip" ,unzip)))
1890 (home-page "http://couger.oit.duke.edu")
1891 (synopsis "Identify co-factors in sets of genomic regions")
1893 "COUGER can be applied to any two sets of genomic regions bound by
1894 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1895 putative co-factors that provide specificity to each TF. The framework
1896 determines the genomic targets uniquely-bound by each TF, and identifies a
1897 small set of co-factors that best explain the in vivo binding differences
1898 between the two TFs.
1900 COUGER uses classification algorithms (support vector machines and random
1901 forests) with features that reflect the DNA binding specificities of putative
1902 co-factors. The features are generated either from high-throughput TF-DNA
1903 binding data (from protein binding microarray experiments), or from large
1904 collections of DNA motifs.")
1905 (license license:gpl3+)))
1907 (define-public clustal-omega
1909 (name "clustal-omega")
1913 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1917 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1918 (build-system gnu-build-system)
1920 `(("argtable" ,argtable)))
1921 (home-page "http://www.clustal.org/omega/")
1922 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1924 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1925 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1926 of handling data-sets of hundreds of thousands of sequences in reasonable
1928 (license license:gpl2+)))
1930 (define-public crossmap
1936 (uri (pypi-uri "CrossMap" version))
1939 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1940 (build-system python-build-system)
1941 (arguments `(#:python ,python-2))
1943 `(("python-bx-python" ,python2-bx-python)
1944 ("python-numpy" ,python2-numpy)
1945 ("python-pysam" ,python2-pysam)
1948 `(("python-cython" ,python2-cython)
1949 ("python-nose" ,python2-nose)))
1950 (home-page "http://crossmap.sourceforge.net/")
1951 (synopsis "Convert genome coordinates between assemblies")
1953 "CrossMap is a program for conversion of genome coordinates or annotation
1954 files between different genome assemblies. It supports most commonly used
1955 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1956 (license license:gpl2+)))
1958 (define-public python-dnaio
1960 (name "python-dnaio")
1965 (uri (pypi-uri "dnaio" version))
1968 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1969 (build-system python-build-system)
1971 `(("python-cython" ,python-cython)
1972 ("python-pytest" ,python-pytest)
1973 ("python-xopen" ,python-xopen)))
1974 (home-page "https://github.com/marcelm/dnaio/")
1975 (synopsis "Read FASTA and FASTQ files efficiently")
1977 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1978 files. The code was previously part of the cutadapt tool.")
1979 (license license:expat)))
1981 (define-public cutadapt
1988 (url "https://github.com/marcelm/cutadapt.git")
1989 (commit (string-append "v" version))))
1990 (file-name (git-file-name name version))
1993 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1994 (build-system python-build-system)
1996 `(("python-dnaio" ,python-dnaio)
1997 ("python-xopen" ,python-xopen)))
1999 `(("python-cython" ,python-cython)
2000 ("python-pytest" ,python-pytest)))
2001 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2002 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2004 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2005 other types of unwanted sequence from high-throughput sequencing reads.")
2006 (license license:expat)))
2008 (define-public libbigwig
2015 (url "https://github.com/dpryan79/libBigWig.git")
2017 (file-name (string-append name "-" version "-checkout"))
2020 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2021 (build-system gnu-build-system)
2023 `(#:test-target "test"
2024 #:tests? #f ; tests require access to the web
2027 (string-append "prefix=" (assoc-ref %outputs "out")))
2029 (modify-phases %standard-phases
2030 (delete 'configure))))
2035 `(("doxygen" ,doxygen)
2037 ("python" ,python-2)))
2038 (home-page "https://github.com/dpryan79/libBigWig")
2039 (synopsis "C library for handling bigWig files")
2041 "This package provides a C library for parsing local and remote BigWig
2043 (license license:expat)))
2045 (define-public python-pybigwig
2047 (name "python-pybigwig")
2051 (uri (pypi-uri "pyBigWig" version))
2054 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2055 (modules '((guix build utils)))
2058 ;; Delete bundled libBigWig sources
2059 (delete-file-recursively "libBigWig")
2061 (build-system python-build-system)
2064 (modify-phases %standard-phases
2065 (add-after 'unpack 'link-with-libBigWig
2066 (lambda* (#:key inputs #:allow-other-keys)
2067 (substitute* "setup.py"
2068 (("libs=\\[") "libs=[\"BigWig\", "))
2071 `(("python-numpy" ,python-numpy)))
2073 `(("libbigwig" ,libbigwig)
2076 (home-page "https://github.com/dpryan79/pyBigWig")
2077 (synopsis "Access bigWig files in Python using libBigWig")
2079 "This package provides Python bindings to the libBigWig library for
2080 accessing bigWig files.")
2081 (license license:expat)))
2083 (define-public python2-pybigwig
2084 (package-with-python2 python-pybigwig))
2086 (define-public python-dendropy
2088 (name "python-dendropy")
2093 ;; Source from GitHub so that tests are included.
2095 (url "https://github.com/jeetsukumaran/DendroPy.git")
2096 (commit (string-append "v" version))))
2097 (file-name (git-file-name name version))
2100 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2101 (build-system python-build-system)
2102 (home-page "http://packages.python.org/DendroPy/")
2103 (synopsis "Library for phylogenetics and phylogenetic computing")
2105 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2106 writing, simulation, processing and manipulation of phylogenetic
2107 trees (phylogenies) and characters.")
2108 (license license:bsd-3)))
2110 (define-public python2-dendropy
2111 (let ((base (package-with-python2 python-dendropy)))
2116 (modify-phases %standard-phases
2117 (add-after 'unpack 'remove-failing-test
2119 ;; This test fails when the full test suite is run, as documented
2120 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2121 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2122 (("test_collection_comments_and_annotations")
2123 "do_not_test_collection_comments_and_annotations"))
2125 ,@(package-arguments base))))))
2127 (define-public python-py2bit
2129 (name "python-py2bit")
2134 (uri (pypi-uri "py2bit" version))
2137 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2138 (build-system python-build-system)
2139 (home-page "https://github.com/dpryan79/py2bit")
2140 (synopsis "Access 2bit files using lib2bit")
2142 "This package provides Python bindings for lib2bit to access 2bit files
2144 (license license:expat)))
2146 (define-public deeptools
2153 (url "https://github.com/deeptools/deepTools.git")
2155 (file-name (git-file-name name version))
2158 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2159 (build-system python-build-system)
2162 (modify-phases %standard-phases
2163 ;; This phase fails, but it's not needed.
2164 (delete 'reset-gzip-timestamps))))
2166 `(("python-plotly" ,python-plotly)
2167 ("python-scipy" ,python-scipy)
2168 ("python-numpy" ,python-numpy)
2169 ("python-numpydoc" ,python-numpydoc)
2170 ("python-matplotlib" ,python-matplotlib)
2171 ("python-pysam" ,python-pysam)
2172 ("python-py2bit" ,python-py2bit)
2173 ("python-pybigwig" ,python-pybigwig)))
2175 `(("python-mock" ,python-mock) ;for tests
2176 ("python-nose" ,python-nose) ;for tests
2177 ("python-pytz" ,python-pytz))) ;for tests
2178 (home-page "https://github.com/deeptools/deepTools")
2179 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2181 "DeepTools addresses the challenge of handling the large amounts of data
2182 that are now routinely generated from DNA sequencing centers. To do so,
2183 deepTools contains useful modules to process the mapped reads data to create
2184 coverage files in standard bedGraph and bigWig file formats. By doing so,
2185 deepTools allows the creation of normalized coverage files or the comparison
2186 between two files (for example, treatment and control). Finally, using such
2187 normalized and standardized files, multiple visualizations can be created to
2188 identify enrichments with functional annotations of the genome.")
2189 (license license:gpl3+)))
2191 (define-public delly
2198 (url "https://github.com/dellytools/delly.git")
2199 (commit (string-append "v" version))))
2200 (file-name (git-file-name name version))
2202 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2203 (modules '((guix build utils)))
2206 (delete-file-recursively "src/htslib")
2208 (build-system gnu-build-system)
2210 `(#:tests? #f ; There are no tests to run.
2212 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2213 (string-append "prefix=" (assoc-ref %outputs "out")))
2215 (modify-phases %standard-phases
2216 (delete 'configure) ; There is no configure phase.
2217 (add-after 'install 'install-templates
2218 (lambda* (#:key outputs #:allow-other-keys)
2219 (let ((templates (string-append (assoc-ref outputs "out")
2220 "/share/delly/templates")))
2222 (copy-recursively "excludeTemplates" templates)
2229 (home-page "https://github.com/dellytools/delly")
2230 (synopsis "Integrated structural variant prediction method")
2231 (description "Delly is an integrated structural variant prediction method
2232 that can discover and genotype deletions, tandem duplications, inversions and
2233 translocations at single-nucleotide resolution in short-read massively parallel
2234 sequencing data. It uses paired-ends and split-reads to sensitively and
2235 accurately delineate genomic rearrangements throughout the genome.")
2236 (license license:gpl3+)))
2238 (define-public diamond
2245 (url "https://github.com/bbuchfink/diamond.git")
2246 (commit (string-append "v" version))))
2247 (file-name (git-file-name name version))
2250 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2251 (build-system cmake-build-system)
2253 '(#:tests? #f ; no "check" target
2255 (modify-phases %standard-phases
2256 (add-after 'unpack 'remove-native-compilation
2258 (substitute* "CMakeLists.txt" (("-march=native") ""))
2262 (home-page "https://github.com/bbuchfink/diamond")
2263 (synopsis "Accelerated BLAST compatible local sequence aligner")
2265 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2266 translated DNA query sequences against a protein reference database (BLASTP
2267 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2268 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2269 data and settings.")
2270 (license license:agpl3+)))
2272 (define-public discrover
2280 (url "https://github.com/maaskola/discrover.git")
2282 (file-name (git-file-name name version))
2285 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2286 (build-system cmake-build-system)
2288 `(#:tests? #f ; there are no tests
2290 (modify-phases %standard-phases
2291 (add-after 'unpack 'add-missing-includes
2293 (substitute* "src/executioninformation.hpp"
2294 (("#define EXECUTIONINFORMATION_HPP" line)
2295 (string-append line "\n#include <random>")))
2296 (substitute* "src/plasma/fasta.hpp"
2297 (("#define FASTA_HPP" line)
2298 (string-append line "\n#include <random>")))
2304 `(("texlive" ,texlive)
2305 ;; TODO: Replace texlive with minimal texlive-union.
2306 ;; ("texlive" ,(texlive-union (list texlive-latex-doi
2307 ;; texlive-latex-hyperref
2308 ;; texlive-latex-oberdiek
2309 ;; texlive-generic-ifxetex
2310 ;; texlive-latex-url
2311 ;; texlive-latex-pgf
2312 ;; texlive-latex-examplep
2313 ;; texlive-latex-natbib
2314 ;; texlive-latex-verbatimbox
2316 ;; texlive-latex-xcolor
2317 ;; texlive-fonts-amsfonts
2318 ;; texlive-latex-amsfonts
2321 ("imagemagick" ,imagemagick)))
2322 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2323 (synopsis "Discover discriminative nucleotide sequence motifs")
2324 (description "Discrover is a motif discovery method to find binding sites
2325 of nucleic acid binding proteins.")
2326 (license license:gpl3+)))
2328 (define-public eigensoft
2336 (url "https://github.com/DReichLab/EIG.git")
2337 (commit (string-append "v" version))))
2338 (file-name (git-file-name name version))
2341 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2342 (modules '((guix build utils)))
2343 ;; Remove pre-built binaries.
2345 (delete-file-recursively "bin")
2348 (build-system gnu-build-system)
2350 `(#:tests? #f ; There are no tests.
2351 #:make-flags '("CC=gcc")
2353 (modify-phases %standard-phases
2354 ;; There is no configure phase, but the Makefile is in a
2357 (lambda _ (chdir "src") #t))
2358 ;; The provided install target only copies executables to
2359 ;; the "bin" directory in the build root.
2360 (add-after 'install 'actually-install
2361 (lambda* (#:key outputs #:allow-other-keys)
2362 (let* ((out (assoc-ref outputs "out"))
2363 (bin (string-append out "/bin")))
2364 (for-each (lambda (file)
2365 (install-file file bin))
2366 (find-files "../bin" ".*"))
2371 ("openblas" ,openblas)
2373 ("gfortran" ,gfortran "lib")))
2374 (home-page "https://github.com/DReichLab/EIG")
2375 (synopsis "Tools for population genetics")
2376 (description "The EIGENSOFT package provides tools for population
2377 genetics and stratification correction. EIGENSOFT implements methods commonly
2378 used in population genetics analyses such as PCA, computation of Tracy-Widom
2379 statistics, and finding related individuals in structured populations. It
2380 comes with a built-in plotting script and supports multiple file formats and
2381 quantitative phenotypes.")
2382 ;; The license of the eigensoft tools is Expat, but since it's
2383 ;; linking with the GNU Scientific Library (GSL) the effective
2384 ;; license is the GPL.
2385 (license license:gpl3+)))
2387 (define-public edirect
2390 (version "10.2.20181018")
2393 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2394 "/versions/" version
2395 "/edirect-" version ".tar.gz"))
2398 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2399 (build-system perl-build-system)
2402 (modify-phases %standard-phases
2405 (delete 'check) ; simple check after install
2407 (lambda* (#:key outputs #:allow-other-keys)
2408 (install-file "edirect.pl"
2409 (string-append (assoc-ref outputs "out") "/bin"))
2411 (add-after 'install 'wrap-program
2412 (lambda* (#:key outputs #:allow-other-keys)
2413 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2414 (let* ((out (assoc-ref outputs "out"))
2415 (path (getenv "PERL5LIB")))
2416 (wrap-program (string-append out "/bin/edirect.pl")
2417 `("PERL5LIB" ":" prefix (,path))))
2419 (add-after 'wrap-program 'check
2420 (lambda* (#:key outputs #:allow-other-keys)
2421 (invoke (string-append (assoc-ref outputs "out")
2426 `(("perl-html-parser" ,perl-html-parser)
2427 ("perl-encode-locale" ,perl-encode-locale)
2428 ("perl-file-listing" ,perl-file-listing)
2429 ("perl-html-tagset" ,perl-html-tagset)
2430 ("perl-html-tree" ,perl-html-tree)
2431 ("perl-http-cookies" ,perl-http-cookies)
2432 ("perl-http-date" ,perl-http-date)
2433 ("perl-http-message" ,perl-http-message)
2434 ("perl-http-negotiate" ,perl-http-negotiate)
2435 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2436 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2437 ("perl-net-http" ,perl-net-http)
2438 ("perl-uri" ,perl-uri)
2439 ("perl-www-robotrules" ,perl-www-robotrules)
2440 ("perl-xml-simple" ,perl-xml-simple)
2442 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2443 (synopsis "Tools for accessing the NCBI's set of databases")
2445 "Entrez Direct (EDirect) is a method for accessing the National Center
2446 for Biotechnology Information's (NCBI) set of interconnected
2447 databases (publication, sequence, structure, gene, variation, expression,
2448 etc.) from a terminal. Functions take search terms from command-line
2449 arguments. Individual operations are combined to build multi-step queries.
2450 Record retrieval and formatting normally complete the process.
2452 EDirect also provides an argument-driven function that simplifies the
2453 extraction of data from document summaries or other results that are returned
2454 in structured XML format. This can eliminate the need for writing custom
2455 software to answer ad hoc questions.")
2456 (license license:public-domain)))
2458 (define-public exonerate
2467 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2468 "exonerate-" version ".tar.gz"))
2471 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2472 (build-system gnu-build-system)
2474 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2476 `(("pkg-config" ,pkg-config)))
2480 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2481 (synopsis "Generic tool for biological sequence alignment")
2483 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2484 the alignment of sequences using a many alignment models, either exhaustive
2485 dynamic programming or a variety of heuristics.")
2486 (license license:gpl3)))
2488 (define-public express
2496 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2497 version "/express-" version "-src.tgz"))
2500 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2501 (build-system cmake-build-system)
2503 `(#:tests? #f ;no "check" target
2505 (modify-phases %standard-phases
2506 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2507 (lambda* (#:key inputs #:allow-other-keys)
2508 (substitute* "CMakeLists.txt"
2509 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2510 "set(Boost_USE_STATIC_LIBS OFF)")
2511 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2512 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2513 (substitute* "src/CMakeLists.txt"
2514 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2515 (string-append (assoc-ref inputs "bamtools") "/lib"))
2516 (("libprotobuf.a") "libprotobuf.so"))
2520 ("bamtools" ,bamtools)
2521 ("protobuf" ,protobuf)
2523 (home-page "http://bio.math.berkeley.edu/eXpress")
2524 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2526 "eXpress is a streaming tool for quantifying the abundances of a set of
2527 target sequences from sampled subsequences. Example applications include
2528 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2529 analysis (from RNA-Seq), transcription factor binding quantification in
2530 ChIP-Seq, and analysis of metagenomic data.")
2531 (license license:artistic2.0)))
2533 (define-public express-beta-diversity
2535 (name "express-beta-diversity")
2540 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2541 (commit (string-append "v" version))))
2542 (file-name (git-file-name name version))
2545 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2546 (build-system gnu-build-system)
2549 (modify-phases %standard-phases
2551 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2553 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2555 (lambda* (#:key outputs #:allow-other-keys)
2556 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2557 (install-file "../scripts/convertToEBD.py" bin)
2558 (install-file "../bin/ExpressBetaDiversity" bin)
2561 `(("python" ,python-2)))
2562 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2563 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2565 "Express Beta Diversity (EBD) calculates ecological beta diversity
2566 (dissimilarity) measures between biological communities. EBD implements a
2567 variety of diversity measures including those that make use of phylogenetic
2568 similarity of community members.")
2569 (license license:gpl3+)))
2571 (define-public fasttree
2578 "http://www.microbesonline.org/fasttree/FastTree-"
2582 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2583 (build-system gnu-build-system)
2585 `(#:tests? #f ; no "check" target
2587 (modify-phases %standard-phases
2591 (lambda* (#:key source #:allow-other-keys)
2594 "-finline-functions"
2605 "-finline-functions"
2614 (lambda* (#:key outputs #:allow-other-keys)
2615 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2616 (install-file "FastTree" bin)
2617 (install-file "FastTreeMP" bin)
2619 (home-page "http://www.microbesonline.org/fasttree")
2620 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2622 "FastTree can handle alignments with up to a million of sequences in a
2623 reasonable amount of time and memory. For large alignments, FastTree is
2624 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2625 (license license:gpl2+)))
2627 (define-public fastx-toolkit
2629 (name "fastx-toolkit")
2635 "https://github.com/agordon/fastx_toolkit/releases/download/"
2636 version "/fastx_toolkit-" version ".tar.bz2"))
2639 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2640 (build-system gnu-build-system)
2642 `(("libgtextutils" ,libgtextutils)))
2644 `(("pkg-config" ,pkg-config)))
2645 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2646 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2648 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2649 FASTA/FASTQ files preprocessing.
2651 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2652 containing multiple short-reads sequences. The main processing of such
2653 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2654 is sometimes more productive to preprocess the files before mapping the
2655 sequences to the genome---manipulating the sequences to produce better mapping
2656 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2657 (license license:agpl3+)))
2659 (define-public flexbar
2666 (url "https://github.com/seqan/flexbar.git")
2667 (commit (string-append "v" version))))
2668 (file-name (git-file-name name version))
2671 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2672 (build-system cmake-build-system)
2675 (modify-phases %standard-phases
2677 (lambda* (#:key outputs #:allow-other-keys)
2678 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2679 (with-directory-excursion "../source/test"
2680 (invoke "bash" "flexbar_test.sh"))
2683 (lambda* (#:key outputs #:allow-other-keys)
2684 (let* ((out (string-append (assoc-ref outputs "out")))
2685 (bin (string-append out "/bin/")))
2686 (install-file "flexbar" bin))
2692 `(("pkg-config" ,pkg-config)
2694 (home-page "https://github.com/seqan/flexbar")
2695 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2697 "Flexbar preprocesses high-throughput nucleotide sequencing data
2698 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2699 Moreover, trimming and filtering features are provided. Flexbar increases
2700 read mapping rates and improves genome and transcriptome assemblies. It
2701 supports next-generation sequencing data in fasta/q and csfasta/q format from
2702 Illumina, Roche 454, and the SOLiD platform.")
2703 (license license:bsd-3)))
2705 (define-public fraggenescan
2707 (name "fraggenescan")
2713 (string-append "mirror://sourceforge/fraggenescan/"
2714 "FragGeneScan" version ".tar.gz"))
2716 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2717 (build-system gnu-build-system)
2720 (modify-phases %standard-phases
2722 (add-before 'build 'patch-paths
2723 (lambda* (#:key outputs #:allow-other-keys)
2724 (let* ((out (string-append (assoc-ref outputs "out")))
2725 (share (string-append out "/share/fraggenescan/")))
2726 (substitute* "run_FragGeneScan.pl"
2728 (string-append "system(\"" (which "rm")))
2730 (string-append "system(\"" (which "mv")))
2731 (("\\\"awk") (string-append "\"" (which "awk")))
2732 ;; This script and other programs expect the training files
2733 ;; to be in the non-standard location bin/train/XXX. Change
2734 ;; this to be share/fraggenescan/train/XXX instead.
2735 (("^\\$train.file = \\$dir.*")
2736 (string-append "$train_file = \""
2738 "train/\".$FGS_train_file;")))
2739 (substitute* "run_hmm.c"
2740 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2741 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2745 (invoke "make" "clean")
2746 (invoke "make" "fgs")
2749 (lambda* (#:key outputs #:allow-other-keys)
2750 (let* ((out (string-append (assoc-ref outputs "out")))
2751 (bin (string-append out "/bin/"))
2752 (share (string-append out "/share/fraggenescan/train")))
2753 (install-file "run_FragGeneScan.pl" bin)
2754 (install-file "FragGeneScan" bin)
2755 (copy-recursively "train" share))
2758 (add-after 'install 'post-install-check
2759 ;; In lieu of 'make check', run one of the examples and check the
2760 ;; output files gets created.
2761 (lambda* (#:key outputs #:allow-other-keys)
2762 (let* ((out (string-append (assoc-ref outputs "out")))
2763 (bin (string-append out "/bin/"))
2764 (frag (string-append bin "run_FragGeneScan.pl")))
2765 ;; Test complete genome.
2767 "-genome=./example/NC_000913.fna"
2771 (unless (and (file-exists? "test2.faa")
2772 (file-exists? "test2.ffn")
2773 (file-exists? "test2.gff")
2774 (file-exists? "test2.out"))
2775 (error "Expected files do not exist."))
2776 ;; Test incomplete sequences.
2778 "-genome=./example/NC_000913-fgs.ffn"
2785 ("python" ,python-2))) ;not compatible with python 3.
2786 (home-page "https://sourceforge.net/projects/fraggenescan/")
2787 (synopsis "Finds potentially fragmented genes in short reads")
2789 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2790 short and error-prone DNA sequencing reads. It can also be applied to predict
2791 genes in incomplete assemblies or complete genomes.")
2792 ;; GPL3+ according to private correspondense with the authors.
2793 (license license:gpl3+)))
2795 (define-public fxtract
2796 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2804 (url "https://github.com/ctSkennerton/fxtract.git")
2806 (file-name (git-file-name name version))
2809 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2810 (build-system gnu-build-system)
2812 `(#:make-flags (list
2813 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2815 #:test-target "fxtract_test"
2817 (modify-phases %standard-phases
2819 (add-before 'build 'copy-util
2820 (lambda* (#:key inputs #:allow-other-keys)
2822 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2824 ;; Do not use make install as this requires additional dependencies.
2826 (lambda* (#:key outputs #:allow-other-keys)
2827 (let* ((out (assoc-ref outputs "out"))
2828 (bin (string-append out"/bin")))
2829 (install-file "fxtract" bin)
2835 ;; ctskennerton-util is licensed under GPL2.
2836 `(("ctskennerton-util"
2840 (url "https://github.com/ctSkennerton/util.git")
2841 (commit util-commit)))
2842 (file-name (string-append
2843 "ctstennerton-util-" util-commit "-checkout"))
2846 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2847 (home-page "https://github.com/ctSkennerton/fxtract")
2848 (synopsis "Extract sequences from FASTA and FASTQ files")
2850 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2851 or FASTQ) file given a subsequence. It uses a simple substring search for
2852 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2853 lookups or multi-pattern searching as required. By default fxtract looks in
2854 the sequence of each record but can also be told to look in the header,
2855 comment or quality sections.")
2856 ;; 'util' requires SSE instructions.
2857 (supported-systems '("x86_64-linux"))
2858 (license license:expat))))
2860 (define-public gemma
2867 (url "https://github.com/xiangzhou/GEMMA.git")
2868 (commit (string-append "v" version))))
2869 (file-name (git-file-name name version))
2872 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2875 ("gfortran" ,gfortran "lib")
2878 ("openblas" ,openblas)
2880 (build-system gnu-build-system)
2883 '(,@(match (%current-system)
2885 '("FORCE_DYNAMIC=1"))
2887 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2889 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2891 (modify-phases %standard-phases
2893 (add-after 'unpack 'find-eigen
2894 (lambda* (#:key inputs #:allow-other-keys)
2895 ;; Ensure that Eigen headers can be found
2896 (setenv "CPLUS_INCLUDE_PATH"
2897 (string-append (getenv "CPLUS_INCLUDE_PATH")
2899 (assoc-ref inputs "eigen")
2902 (add-before 'build 'bin-mkdir
2907 (lambda* (#:key outputs #:allow-other-keys)
2908 (let ((out (assoc-ref outputs "out")))
2909 (install-file "bin/gemma"
2913 #:tests? #f)) ; no tests included yet
2914 (home-page "https://github.com/xiangzhou/GEMMA")
2915 (synopsis "Tool for genome-wide efficient mixed model association")
2917 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2918 standard linear mixed model resolver with application in genome-wide
2919 association studies (GWAS).")
2920 (license license:gpl3)))
2929 (url "https://github.com/nboley/grit.git")
2931 (file-name (git-file-name name version))
2934 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
2935 (build-system python-build-system)
2937 `(#:python ,python-2
2939 (modify-phases %standard-phases
2940 (add-after 'unpack 'generate-from-cython-sources
2941 (lambda* (#:key inputs outputs #:allow-other-keys)
2942 ;; Delete these C files to force fresh generation from pyx sources.
2943 (delete-file "grit/sparsify_support_fns.c")
2944 (delete-file "grit/call_peaks_support_fns.c")
2945 (substitute* "setup.py"
2946 (("Cython.Setup") "Cython.Build"))
2949 `(("python-scipy" ,python2-scipy)
2950 ("python-numpy" ,python2-numpy)
2951 ("python-pysam" ,python2-pysam)
2952 ("python-networkx" ,python2-networkx)))
2954 `(("python-cython" ,python2-cython)))
2955 (home-page "http://grit-bio.org")
2956 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2958 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2959 full length transcript models. When none of these data sources are available,
2960 GRIT can be run by providing a candidate set of TES or TSS sites. In
2961 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2962 also be run in quantification mode, where it uses a provided GTF file and just
2963 estimates transcript expression.")
2964 (license license:gpl3+)))
2966 (define-public hisat
2973 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2974 version "-beta-source.zip"))
2977 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2978 (build-system gnu-build-system)
2980 `(#:tests? #f ;no check target
2981 #:make-flags '("allall"
2982 ;; Disable unsupported `popcnt' instructions on
2983 ;; architectures other than x86_64
2984 ,@(if (string-prefix? "x86_64"
2985 (or (%current-target-system)
2988 '("POPCNT_CAPABILITY=0")))
2990 (modify-phases %standard-phases
2991 (add-after 'unpack 'patch-sources
2993 ;; XXX Cannot use snippet because zip files are not supported
2994 (substitute* "Makefile"
2995 (("^CC = .*$") "CC = gcc")
2996 (("^CPP = .*$") "CPP = g++")
2997 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2998 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2999 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3000 (substitute* '("hisat-build" "hisat-inspect")
3001 (("/usr/bin/env") (which "env")))
3004 (lambda* (#:key outputs #:allow-other-keys)
3005 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3006 (for-each (lambda (file)
3007 (install-file file bin))
3010 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3012 (delete 'configure))))
3014 `(("unzip" ,unzip)))
3019 ;; Non-portable SSE instructions are used so building fails on platforms
3020 ;; other than x86_64.
3021 (supported-systems '("x86_64-linux"))
3022 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3023 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3025 "HISAT is a fast and sensitive spliced alignment program for mapping
3026 RNA-seq reads. In addition to one global FM index that represents a whole
3027 genome, HISAT uses a large set of small FM indexes that collectively cover the
3028 whole genome. These small indexes (called local indexes) combined with
3029 several alignment strategies enable effective alignment of RNA-seq reads, in
3030 particular, reads spanning multiple exons.")
3031 (license license:gpl3+)))
3033 (define-public hisat2
3040 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3041 "/downloads/hisat2-" version "-source.zip"))
3044 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3045 (build-system gnu-build-system)
3047 `(#:tests? #f ; no check target
3048 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3049 #:modules ((guix build gnu-build-system)
3053 (modify-phases %standard-phases
3054 (add-after 'unpack 'make-deterministic
3056 (substitute* "Makefile"
3061 (lambda* (#:key outputs #:allow-other-keys)
3062 (let* ((out (assoc-ref outputs "out"))
3063 (bin (string-append out "/bin/"))
3064 (doc (string-append out "/share/doc/hisat2/")))
3066 (cut install-file <> bin)
3068 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3070 (install-file "doc/manual.inc.html" doc))
3073 `(("unzip" ,unzip) ; needed for archive from ftp
3075 ("pandoc" ,ghc-pandoc))) ; for documentation
3076 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3077 (synopsis "Graph-based alignment of genomic sequencing reads")
3078 (description "HISAT2 is a fast and sensitive alignment program for mapping
3079 next-generation sequencing reads (both DNA and RNA) to a population of human
3080 genomes (as well as to a single reference genome). In addition to using one
3081 global @dfn{graph FM} (GFM) index that represents a population of human
3082 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3083 the whole genome. These small indexes, combined with several alignment
3084 strategies, enable rapid and accurate alignment of sequencing reads. This new
3085 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3086 ;; HISAT2 contains files from Bowtie2, which is released under
3087 ;; GPLv2 or later. The HISAT2 source files are released under
3089 (license license:gpl3+)))
3091 (define-public hmmer
3099 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3102 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3103 (build-system gnu-build-system)
3104 (native-inputs `(("perl" ,perl)))
3105 (home-page "http://hmmer.org/")
3106 (synopsis "Biosequence analysis using profile hidden Markov models")
3108 "HMMER is used for searching sequence databases for homologs of protein
3109 sequences, and for making protein sequence alignments. It implements methods
3110 using probabilistic models called profile hidden Markov models (profile
3112 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3114 (supported-systems '("x86_64-linux" "i686-linux"))
3115 (license license:bsd-3)))
3117 (define-public htseq
3123 (uri (pypi-uri "HTSeq" version))
3126 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3127 (build-system python-build-system)
3129 `(("python-cython" ,python-cython)))
3130 ;; Numpy needs to be propagated when htseq is used as a Python library.
3132 `(("python-numpy" ,python-numpy)))
3134 `(("python-pysam" ,python-pysam)
3135 ("python-matplotlib" ,python-matplotlib)))
3136 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3137 (synopsis "Analysing high-throughput sequencing data with Python")
3139 "HTSeq is a Python package that provides infrastructure to process data
3140 from high-throughput sequencing assays.")
3141 (license license:gpl3+)))
3143 (define-public python2-htseq
3144 (package-with-python2 htseq))
3146 (define-public java-htsjdk
3148 (name "java-htsjdk")
3149 (version "2.3.0") ; last version without build dependency on gradle
3153 (url "https://github.com/samtools/htsjdk.git")
3155 (file-name (git-file-name name version))
3158 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3159 (modules '((guix build utils)))
3161 ;; Delete pre-built binaries
3163 (delete-file-recursively "lib")
3166 (build-system ant-build-system)
3168 `(#:tests? #f ; test require Internet access
3171 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3172 "/share/java/htsjdk/"))
3173 #:build-target "all"
3175 (modify-phases %standard-phases
3176 ;; The build phase also installs the jars
3177 (delete 'install))))
3179 `(("java-ngs" ,java-ngs)
3180 ("java-snappy-1" ,java-snappy-1)
3181 ("java-commons-compress" ,java-commons-compress)
3182 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3183 ("java-commons-jexl-2" ,java-commons-jexl-2)
3184 ("java-xz" ,java-xz)))
3186 `(("java-testng" ,java-testng)))
3187 (home-page "http://samtools.github.io/htsjdk/")
3188 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3190 "HTSJDK is an implementation of a unified Java library for accessing
3191 common file formats, such as SAM and VCF, used for high-throughput
3192 sequencing (HTS) data. There are also an number of useful utilities for
3193 manipulating HTS data.")
3194 (license license:expat)))
3196 (define-public java-htsjdk-latest
3198 (name "java-htsjdk")
3203 (url "https://github.com/samtools/htsjdk.git")
3205 (file-name (string-append name "-" version "-checkout"))
3208 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3209 (build-system ant-build-system)
3211 `(#:tests? #f ; test require Scala
3213 #:jar-name "htsjdk.jar"
3215 (modify-phases %standard-phases
3216 (add-after 'unpack 'remove-useless-build.xml
3217 (lambda _ (delete-file "build.xml") #t))
3218 ;; The tests require the scalatest package.
3219 (add-after 'unpack 'remove-tests
3220 (lambda _ (delete-file-recursively "src/test") #t)))))
3222 `(("java-ngs" ,java-ngs)
3223 ("java-snappy-1" ,java-snappy-1)
3224 ("java-commons-compress" ,java-commons-compress)
3225 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3226 ("java-commons-jexl-2" ,java-commons-jexl-2)
3227 ("java-xz" ,java-xz)))
3229 `(("java-junit" ,java-junit)))
3230 (home-page "http://samtools.github.io/htsjdk/")
3231 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3233 "HTSJDK is an implementation of a unified Java library for accessing
3234 common file formats, such as SAM and VCF, used for high-throughput
3235 sequencing (HTS) data. There are also an number of useful utilities for
3236 manipulating HTS data.")
3237 (license license:expat)))
3239 ;; This is needed for picard 2.10.3
3240 (define-public java-htsjdk-2.10.1
3241 (package (inherit java-htsjdk-latest)
3242 (name "java-htsjdk")
3247 (url "https://github.com/samtools/htsjdk.git")
3249 (file-name (string-append name "-" version "-checkout"))
3252 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3253 (build-system ant-build-system)
3255 `(#:tests? #f ; tests require Scala
3257 #:jar-name "htsjdk.jar"
3259 (modify-phases %standard-phases
3260 (add-after 'unpack 'remove-useless-build.xml
3261 (lambda _ (delete-file "build.xml") #t))
3262 ;; The tests require the scalatest package.
3263 (add-after 'unpack 'remove-tests
3264 (lambda _ (delete-file-recursively "src/test") #t)))))))
3266 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3267 ;; recent version of java-htsjdk, which depends on gradle.
3268 (define-public java-picard
3270 (name "java-picard")
3275 (url "https://github.com/broadinstitute/picard.git")
3277 (file-name (string-append "java-picard-" version "-checkout"))
3280 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3281 (modules '((guix build utils)))
3284 ;; Delete pre-built binaries.
3285 (delete-file-recursively "lib")
3287 (substitute* "build.xml"
3288 ;; Remove build-time dependency on git.
3289 (("failifexecutionfails=\"true\"")
3290 "failifexecutionfails=\"false\"")
3292 (("depends=\"compile-htsjdk, ")
3294 (("depends=\"compile-htsjdk-tests, ")
3296 ;; Build picard-lib.jar before building picard.jar
3297 (("name=\"picard-jar\" depends=\"" line)
3298 (string-append line "picard-lib-jar, ")))
3300 (build-system ant-build-system)
3302 `(#:build-target "picard-jar"
3303 #:test-target "test"
3304 ;; Tests require jacoco:coverage.
3307 (list (string-append "-Dhtsjdk_lib_dir="
3308 (assoc-ref %build-inputs "java-htsjdk")
3309 "/share/java/htsjdk/")
3310 "-Dhtsjdk-classes=dist/tmp"
3311 (string-append "-Dhtsjdk-version="
3312 ,(package-version java-htsjdk)))
3315 (modify-phases %standard-phases
3316 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3317 (delete 'generate-jar-indices)
3318 (add-after 'unpack 'use-our-htsjdk
3319 (lambda* (#:key inputs #:allow-other-keys)
3320 (substitute* "build.xml"
3321 (("\\$\\{htsjdk\\}/lib")
3322 (string-append (assoc-ref inputs "java-htsjdk")
3323 "/share/java/htsjdk/")))
3325 (add-after 'unpack 'make-test-target-independent
3326 (lambda* (#:key inputs #:allow-other-keys)
3327 (substitute* "build.xml"
3328 (("name=\"test\" depends=\"compile, ")
3329 "name=\"test\" depends=\""))
3331 (replace 'install (install-jars "dist")))))
3333 `(("java-htsjdk" ,java-htsjdk)
3334 ("java-guava" ,java-guava)))
3336 `(("java-testng" ,java-testng)))
3337 (home-page "http://broadinstitute.github.io/picard/")
3338 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3339 (description "Picard is a set of Java command line tools for manipulating
3340 high-throughput sequencing (HTS) data and formats. Picard is implemented
3341 using the HTSJDK Java library to support accessing file formats that are
3342 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3344 (license license:expat)))
3346 ;; This is needed for dropseq-tools
3347 (define-public java-picard-2.10.3
3349 (name "java-picard")
3354 (url "https://github.com/broadinstitute/picard.git")
3356 (file-name (string-append "java-picard-" version "-checkout"))
3359 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3360 (build-system ant-build-system)
3362 `(#:jar-name "picard.jar"
3363 ;; Tests require jacoco:coverage.
3366 #:main-class "picard.cmdline.PicardCommandLine"
3367 #:modules ((guix build ant-build-system)
3369 (guix build java-utils)
3374 (modify-phases %standard-phases
3375 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3376 (delete 'generate-jar-indices)
3377 (add-after 'unpack 'remove-useless-build.xml
3378 (lambda _ (delete-file "build.xml") #t))
3379 ;; This is necessary to ensure that htsjdk is found when using
3380 ;; picard.jar as an executable.
3381 (add-before 'build 'edit-classpath-in-manifest
3382 (lambda* (#:key inputs #:allow-other-keys)
3383 (chmod "build.xml" #o664)
3384 (call-with-output-file "build.xml.new"
3388 (with-input-from-file "build.xml"
3389 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3390 `((target . ,(lambda (tag . kids)
3391 (let ((name ((sxpath '(name *text*))
3393 ;; FIXME: We're breaking the line
3394 ;; early with a dummy path to
3395 ;; ensure that the store reference
3396 ;; isn't broken apart and can still
3397 ;; be found by the reference
3402 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3403 ;; maximum line length is 70
3404 (string-tabulate (const #\b) 57)
3405 (assoc-ref inputs "java-htsjdk"))))
3406 (if (member "manifest" name)
3409 (@ (file "${manifest.file}")
3410 (match "\\r\\n\\r\\n")
3411 (replace "${line.separator}")))
3414 (file "${manifest.file}")
3417 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3418 (*text* . ,(lambda (_ txt) txt))))
3420 (rename-file "build.xml.new" "build.xml")
3423 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3425 `(("java-testng" ,java-testng)
3426 ("java-guava" ,java-guava)))
3427 (home-page "http://broadinstitute.github.io/picard/")
3428 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3429 (description "Picard is a set of Java command line tools for manipulating
3430 high-throughput sequencing (HTS) data and formats. Picard is implemented
3431 using the HTSJDK Java library to support accessing file formats that are
3432 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3434 (license license:expat)))
3436 ;; This is the last version of Picard to provide net.sf.samtools
3437 (define-public java-picard-1.113
3438 (package (inherit java-picard)
3439 (name "java-picard")
3444 (url "https://github.com/broadinstitute/picard.git")
3446 (file-name (string-append "java-picard-" version "-checkout"))
3449 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3450 (modules '((guix build utils)))
3453 ;; Delete pre-built binaries.
3454 (delete-file-recursively "lib")
3457 (build-system ant-build-system)
3459 `(#:build-target "picard-jar"
3460 #:test-target "test"
3461 ;; FIXME: the class path at test time is wrong.
3462 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3463 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3466 ;; This is only used for tests.
3468 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3470 (modify-phases %standard-phases
3471 ;; FIXME: This phase fails.
3472 (delete 'generate-jar-indices)
3473 ;; Do not use bundled ant bzip2.
3474 (add-after 'unpack 'use-ant-bzip
3475 (lambda* (#:key inputs #:allow-other-keys)
3476 (substitute* "build.xml"
3477 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3478 (string-append (assoc-ref inputs "ant")
3481 (add-after 'unpack 'make-test-target-independent
3482 (lambda* (#:key inputs #:allow-other-keys)
3483 (substitute* "build.xml"
3484 (("name=\"test\" depends=\"compile, ")
3485 "name=\"test\" depends=\"compile-tests, ")
3486 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3487 "name=\"compile\" depends=\"compile-src\""))
3489 (add-after 'unpack 'fix-deflater-path
3490 (lambda* (#:key outputs #:allow-other-keys)
3491 (substitute* "src/java/net/sf/samtools/Defaults.java"
3492 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3493 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3494 (assoc-ref outputs "out")
3495 "/lib/jni/libIntelDeflater.so"
3498 ;; Build the deflater library, because we've previously deleted the
3499 ;; pre-built one. This can only be built with access to the JDK
3501 (add-after 'build 'build-jni
3502 (lambda* (#:key inputs #:allow-other-keys)
3505 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3506 "-xf" (assoc-ref inputs "jdk-src"))
3507 (invoke "javah" "-jni"
3508 "-classpath" "classes"
3510 "net.sf.samtools.util.zip.IntelDeflater")
3511 (with-directory-excursion "src/c/inteldeflater"
3512 (invoke "gcc" "-I../../../lib" "-I."
3513 (string-append "-I" (assoc-ref inputs "jdk")
3515 "-I../../../jdk-src/src/share/native/common/"
3516 "-I../../../jdk-src/src/solaris/native/common/"
3517 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3518 (invoke "gcc" "-shared"
3519 "-o" "../../../lib/jni/libIntelDeflater.so"
3520 "IntelDeflater.o" "-lz" "-lstdc++"))
3522 ;; We can only build everything else after building the JNI library.
3523 (add-after 'build-jni 'build-rest
3524 (lambda* (#:key make-flags #:allow-other-keys)
3525 (apply invoke `("ant" "all" ,@make-flags))
3527 (add-before 'build 'set-JAVA6_HOME
3529 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3531 (replace 'install (install-jars "dist"))
3532 (add-after 'install 'install-jni-lib
3533 (lambda* (#:key outputs #:allow-other-keys)
3534 (let ((jni (string-append (assoc-ref outputs "out")
3537 (install-file "lib/jni/libIntelDeflater.so" jni)
3540 `(("java-snappy-1" ,java-snappy-1)
3541 ("java-commons-jexl-2" ,java-commons-jexl-2)
3542 ("java-cofoja" ,java-cofoja)
3543 ("ant" ,ant) ; for bzip2 support at runtime
3546 `(("ant-apache-bcel" ,ant-apache-bcel)
3547 ("ant-junit" ,ant-junit)
3548 ("java-testng" ,java-testng)
3549 ("java-commons-bcel" ,java-commons-bcel)
3550 ("java-jcommander" ,java-jcommander)
3551 ("jdk" ,icedtea-8 "jdk")
3552 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3554 (define-public fastqc
3561 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3562 "projects/fastqc/fastqc_v"
3563 version "_source.zip"))
3566 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3567 (build-system ant-build-system)
3569 `(#:tests? #f ; there are no tests
3570 #:build-target "build"
3572 (modify-phases %standard-phases
3573 (add-after 'unpack 'fix-dependencies
3574 (lambda* (#:key inputs #:allow-other-keys)
3575 (substitute* "build.xml"
3577 (string-append (assoc-ref inputs "java-jbzip2")
3578 "/share/java/jbzip2.jar"))
3580 (string-append (assoc-ref inputs "java-picard-1.113")
3581 "/share/java/sam-1.112.jar"))
3583 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3584 "/share/java/sis-jhdf5.jar")))
3586 ;; There is no installation target
3588 (lambda* (#:key inputs outputs #:allow-other-keys)
3589 (let* ((out (assoc-ref outputs "out"))
3590 (bin (string-append out "/bin"))
3591 (share (string-append out "/share/fastqc/"))
3592 (exe (string-append share "/fastqc")))
3593 (for-each mkdir-p (list bin share))
3594 (copy-recursively "bin" share)
3596 (("my \\$java_bin = 'java';")
3597 (string-append "my $java_bin = '"
3598 (assoc-ref inputs "java")
3601 (symlink exe (string-append bin "/fastqc"))
3605 ("perl" ,perl) ; needed for the wrapper script
3606 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3607 ("java-picard-1.113" ,java-picard-1.113)
3608 ("java-jbzip2" ,java-jbzip2)))
3610 `(("unzip" ,unzip)))
3611 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3612 (synopsis "Quality control tool for high throughput sequence data")
3614 "FastQC aims to provide a simple way to do some quality control
3615 checks on raw sequence data coming from high throughput sequencing
3616 pipelines. It provides a modular set of analyses which you can use to
3617 give a quick impression of whether your data has any problems of which
3618 you should be aware before doing any further analysis.
3620 The main functions of FastQC are:
3623 @item Import of data from BAM, SAM or FastQ files (any variant);
3624 @item Providing a quick overview to tell you in which areas there may
3626 @item Summary graphs and tables to quickly assess your data;
3627 @item Export of results to an HTML based permanent report;
3628 @item Offline operation to allow automated generation of reports
3629 without running the interactive application.
3631 (license license:gpl3+)))
3633 (define-public fastp
3641 (url "https://github.com/OpenGene/fastp.git")
3642 (commit (string-append "v" version))))
3643 (file-name (git-file-name name version))
3646 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3647 (build-system gnu-build-system)
3649 `(#:tests? #f ; there are none
3651 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3653 (modify-phases %standard-phases
3655 (add-before 'install 'create-target-dir
3656 (lambda* (#:key outputs #:allow-other-keys)
3657 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3661 (home-page "https://github.com/OpenGene/fastp/")
3662 (synopsis "All-in-one FastQ preprocessor")
3664 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3665 FastQ files. This tool has multi-threading support to afford high
3667 (license license:expat)))
3669 (define-public htslib
3676 "https://github.com/samtools/htslib/releases/download/"
3677 version "/htslib-" version ".tar.bz2"))
3680 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3681 (build-system gnu-build-system)
3683 `(("openssl" ,openssl)
3688 (home-page "http://www.htslib.org")
3689 (synopsis "C library for reading/writing high-throughput sequencing data")
3691 "HTSlib is a C library for reading/writing high-throughput sequencing
3692 data. It also provides the @command{bgzip}, @command{htsfile}, and
3693 @command{tabix} utilities.")
3694 ;; Files under cram/ are released under the modified BSD license;
3695 ;; the rest is released under the Expat license
3696 (license (list license:expat license:bsd-3))))
3698 ;; This package should be removed once no packages rely upon it.
3706 "https://github.com/samtools/htslib/releases/download/"
3707 version "/htslib-" version ".tar.bz2"))
3710 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3719 (url "https://github.com/nboley/idr.git")
3721 (file-name (git-file-name name version))
3724 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3725 ;; Delete generated C code.
3727 '(begin (delete-file "idr/inv_cdf.c") #t))))
3728 (build-system python-build-system)
3729 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3730 ;; are no longer part of this package. It also asserts False, which
3731 ;; causes the tests to always fail.
3732 (arguments `(#:tests? #f))
3734 `(("python-scipy" ,python-scipy)
3735 ("python-sympy" ,python-sympy)
3736 ("python-numpy" ,python-numpy)
3737 ("python-matplotlib" ,python-matplotlib)))
3739 `(("python-cython" ,python-cython)))
3740 (home-page "https://github.com/nboley/idr")
3741 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3743 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3744 to measure the reproducibility of findings identified from replicate
3745 experiments and provide highly stable thresholds based on reproducibility.")
3746 (license license:gpl2+)))
3748 (define-public jellyfish
3754 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3755 "releases/download/v" version
3756 "/jellyfish-" version ".tar.gz"))
3759 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3760 (build-system gnu-build-system)
3761 (outputs '("out" ;for library
3762 "ruby" ;for Ruby bindings
3763 "python")) ;for Python bindings
3766 (list (string-append "--enable-ruby-binding="
3767 (assoc-ref %outputs "ruby"))
3768 (string-append "--enable-python-binding="
3769 (assoc-ref %outputs "python")))
3771 (modify-phases %standard-phases
3772 (add-before 'check 'set-SHELL-variable
3774 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3776 (setenv "SHELL" (which "bash"))
3782 ("python" ,python-2)
3783 ("pkg-config" ,pkg-config)))
3785 `(("htslib" ,htslib)))
3786 (synopsis "Tool for fast counting of k-mers in DNA")
3788 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3789 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3790 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3791 is a command-line program that reads FASTA and multi-FASTA files containing
3792 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3793 translated into a human-readable text format using the @code{jellyfish dump}
3794 command, or queried for specific k-mers with @code{jellyfish query}.")
3795 (home-page "http://www.genome.umd.edu/jellyfish.html")
3796 ;; JELLYFISH seems to be 64-bit only.
3797 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3798 ;; The combined work is published under the GPLv3 or later. Individual
3799 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3800 (license (list license:gpl3+ license:expat))))
3802 (define-public khmer
3810 (url "https://github.com/dib-lab/khmer.git")
3811 (commit (string-append "v" version))))
3812 (file-name (git-file-name name version))
3815 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3816 (patches (search-patches "khmer-use-libraries.patch"))
3817 (modules '((guix build utils)))
3820 ;; Delete bundled libraries. We do not replace the bundled seqan
3821 ;; as it is a modified subset of the old version 1.4.1.
3823 ;; We do not replace the bundled MurmurHash as the canonical
3824 ;; repository for this code 'SMHasher' is unsuitable for providing
3826 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3827 (delete-file-recursively "third-party/zlib")
3828 (delete-file-recursively "third-party/bzip2")
3830 (build-system python-build-system)
3833 (modify-phases %standard-phases
3834 (add-after 'unpack 'set-cc
3835 (lambda _ (setenv "CC" "gcc") #t))
3836 ;; FIXME: This fails with "permission denied".
3837 (delete 'reset-gzip-timestamps))))
3839 `(("python-cython" ,python-cython)
3840 ("python-pytest" ,python-pytest)
3841 ("python-pytest-runner" ,python-pytest-runner)))
3845 ("python-screed" ,python-screed)
3846 ("python-bz2file" ,python-bz2file)))
3847 (home-page "https://khmer.readthedocs.org/")
3848 (synopsis "K-mer counting, filtering and graph traversal library")
3849 (description "The khmer software is a set of command-line tools for
3850 working with DNA shotgun sequencing data from genomes, transcriptomes,
3851 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3852 sometimes better. Khmer can also identify and fix problems with shotgun
3854 ;; When building on i686, armhf and mips64el, we get the following error:
3855 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3856 (supported-systems '("x86_64-linux" "aarch64-linux"))
3857 (license license:bsd-3)))
3859 (define-public kaiju
3866 (url "https://github.com/bioinformatics-centre/kaiju")
3867 (commit (string-append "v" version))))
3868 (file-name (git-file-name name version))
3871 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3872 (build-system gnu-build-system)
3874 `(#:tests? #f ; There are no tests.
3876 (modify-phases %standard-phases
3878 (add-before 'build 'move-to-src-dir
3879 (lambda _ (chdir "src") #t))
3881 (lambda* (#:key inputs outputs #:allow-other-keys)
3882 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3885 (copy-recursively "bin" bin))
3890 (home-page "http://kaiju.binf.ku.dk/")
3891 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3892 (description "Kaiju is a program for sensitive taxonomic classification
3893 of high-throughput sequencing reads from metagenomic whole genome sequencing
3895 (license license:gpl3+)))
3900 (version "2.1.1.20160309")
3903 (uri (pypi-uri "MACS2" version))
3906 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3907 (build-system python-build-system)
3909 `(#:python ,python-2 ; only compatible with Python 2.7
3910 #:tests? #f)) ; no test target
3912 `(("python-numpy" ,python2-numpy)))
3913 (home-page "https://github.com/taoliu/MACS/")
3914 (synopsis "Model based analysis for ChIP-Seq data")
3916 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3917 identifying transcript factor binding sites named Model-based Analysis of
3918 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3919 the significance of enriched ChIP regions and it improves the spatial
3920 resolution of binding sites through combining the information of both
3921 sequencing tag position and orientation.")
3922 (license license:bsd-3)))
3924 (define-public mafft
3931 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3932 "-without-extensions-src.tgz"))
3933 (file-name (string-append name "-" version ".tgz"))
3936 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3937 (build-system gnu-build-system)
3939 `(#:tests? #f ; no automated tests, though there are tests in the read me
3940 #:make-flags (let ((out (assoc-ref %outputs "out")))
3941 (list (string-append "PREFIX=" out)
3942 (string-append "BINDIR="
3943 (string-append out "/bin"))))
3945 (modify-phases %standard-phases
3946 (add-after 'unpack 'enter-dir
3947 (lambda _ (chdir "core") #t))
3948 (add-after 'enter-dir 'patch-makefile
3950 ;; on advice from the MAFFT authors, there is no need to
3951 ;; distribute mafft-profile, mafft-distance, or
3952 ;; mafft-homologs.rb as they are too "specialised".
3953 (substitute* "Makefile"
3954 ;; remove mafft-homologs.rb from SCRIPTS
3955 (("^SCRIPTS = mafft mafft-homologs.rb")
3957 ;; remove mafft-homologs from MANPAGES
3958 (("^MANPAGES = mafft.1 mafft-homologs.1")
3959 "MANPAGES = mafft.1")
3960 ;; remove mafft-distance from PROGS
3961 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3962 "PROGS = dvtditr dndfast7 dndblast sextet5")
3963 ;; remove mafft-profile from PROGS
3964 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3965 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3966 (("^rm -f mafft-profile mafft-profile.exe") "#")
3967 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3968 ;; do not install MAN pages in libexec folder
3969 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3970 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3972 (add-after 'enter-dir 'patch-paths
3973 (lambda* (#:key inputs #:allow-other-keys)
3974 (substitute* '("pairash.c"
3976 (("perl") (which "perl"))
3977 (("([\"`| ])awk" _ prefix)
3978 (string-append prefix (which "awk")))
3979 (("grep") (which "grep")))
3982 (add-after 'install 'wrap-programs
3983 (lambda* (#:key outputs #:allow-other-keys)
3984 (let* ((out (assoc-ref outputs "out"))
3985 (bin (string-append out "/bin"))
3986 (path (string-append
3987 (assoc-ref %build-inputs "coreutils") "/bin:")))
3988 (for-each (lambda (file)
3990 `("PATH" ":" prefix (,path))))
3998 ("coreutils" ,coreutils)))
3999 (home-page "http://mafft.cbrc.jp/alignment/software/")
4000 (synopsis "Multiple sequence alignment program")
4002 "MAFFT offers a range of multiple alignment methods for nucleotide and
4003 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4004 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4006 (license (license:non-copyleft
4007 "http://mafft.cbrc.jp/alignment/software/license.txt"
4008 "BSD-3 with different formatting"))))
4017 (url "https://github.com/marbl/mash.git")
4018 (commit (string-append "v" version))))
4019 (file-name (git-file-name name version))
4022 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4023 (modules '((guix build utils)))
4026 ;; Delete bundled kseq.
4027 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4028 (delete-file "src/mash/kseq.h")
4030 (build-system gnu-build-system)
4032 `(#:tests? #f ; No tests.
4035 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4036 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4037 #:make-flags (list "CC=gcc")
4039 (modify-phases %standard-phases
4040 (add-after 'unpack 'fix-includes
4042 (substitute* '("src/mash/Sketch.cpp"
4043 "src/mash/CommandFind.cpp"
4044 "src/mash/CommandScreen.cpp")
4045 (("^#include \"kseq\\.h\"")
4046 "#include \"htslib/kseq.h\""))
4048 (add-after 'fix-includes 'use-c++14
4050 ;; capnproto 0.7 requires c++14 to build
4051 (substitute* "configure.ac"
4052 (("c\\+\\+11") "c++14"))
4053 (substitute* "Makefile.in"
4054 (("c\\+\\+11") "c++14"))
4057 `(("autoconf" ,autoconf)
4058 ;; Capnproto and htslib are statically embedded in the final
4059 ;; application. Therefore we also list their licenses, below.
4060 ("capnproto" ,capnproto)
4061 ("htslib" ,htslib)))
4065 (supported-systems '("x86_64-linux"))
4066 (home-page "https://mash.readthedocs.io")
4067 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4068 (description "Mash is a fast sequence distance estimator that uses the
4069 MinHash algorithm and is designed to work with genomes and metagenomes in the
4070 form of assemblies or reads.")
4071 (license (list license:bsd-3 ; Mash
4072 license:expat ; HTSlib and capnproto
4073 license:public-domain ; MurmurHash 3
4074 license:cpl1.0)))) ; Open Bloom Filter
4076 (define-public metabat
4084 (url "https://bitbucket.org/berkeleylab/metabat.git")
4085 (commit (string-append "v" version))))
4086 (file-name (git-file-name name version))
4089 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4090 (patches (search-patches "metabat-fix-compilation.patch"))))
4091 (build-system scons-build-system)
4093 `(#:scons ,scons-python2
4095 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4096 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4097 #:tests? #f ;; Tests are run during the build phase.
4099 (modify-phases %standard-phases
4100 (add-after 'unpack 'fix-includes
4102 (substitute* "src/BamUtils.h"
4103 (("^#include \"bam/bam\\.h\"")
4104 "#include \"samtools/bam.h\"")
4105 (("^#include \"bam/sam\\.h\"")
4106 "#include \"samtools/sam.h\""))
4107 (substitute* "src/KseqReader.h"
4108 (("^#include \"bam/kseq\\.h\"")
4109 "#include \"htslib/kseq.h\""))
4111 (add-after 'unpack 'fix-scons
4112 (lambda* (#:key inputs #:allow-other-keys)
4113 (substitute* "SConstruct"
4114 (("^htslib_dir += 'samtools'")
4115 (string-append "htslib_dir = '"
4116 (assoc-ref inputs "htslib")
4118 (("^samtools_dir = 'samtools'")
4119 (string-append "samtools_dir = '"
4120 (assoc-ref inputs "samtools")
4122 (("^findStaticOrShared\\('bam', hts_lib")
4123 (string-append "findStaticOrShared('bam', '"
4124 (assoc-ref inputs "samtools")
4126 ;; Do not distribute README.
4127 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4132 ("samtools" ,samtools)
4135 (home-page "https://bitbucket.org/berkeleylab/metabat")
4137 "Reconstruction of single genomes from complex microbial communities")
4139 "Grouping large genomic fragments assembled from shotgun metagenomic
4140 sequences to deconvolute complex microbial communities, or metagenome binning,
4141 enables the study of individual organisms and their interactions. MetaBAT is
4142 an automated metagenome binning software, which integrates empirical
4143 probabilistic distances of genome abundance and tetranucleotide frequency.")
4144 ;; The source code contains inline assembly.
4145 (supported-systems '("x86_64-linux" "i686-linux"))
4146 (license (license:non-copyleft "file://license.txt"
4147 "See license.txt in the distribution."))))
4149 (define-public minced
4156 (url "https://github.com/ctSkennerton/minced.git")
4158 (file-name (git-file-name name version))
4161 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4162 (build-system gnu-build-system)
4164 `(#:test-target "test"
4166 (modify-phases %standard-phases
4168 (add-before 'check 'fix-test
4170 ;; Fix test for latest version.
4171 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4172 (("minced:0.1.6") "minced:0.2.0"))
4174 (replace 'install ; No install target.
4175 (lambda* (#:key inputs outputs #:allow-other-keys)
4176 (let* ((out (assoc-ref outputs "out"))
4177 (bin (string-append out "/bin"))
4178 (wrapper (string-append bin "/minced")))
4179 ;; Minced comes with a wrapper script that tries to figure out where
4180 ;; it is located before running the JAR. Since these paths are known
4181 ;; to us, we build our own wrapper to avoid coreutils dependency.
4182 (install-file "minced.jar" bin)
4183 (with-output-to-file wrapper
4187 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4188 (assoc-ref inputs "jre") "/bin/java -jar "
4189 bin "/minced.jar \"$@\"\n"))))
4190 (chmod wrapper #o555))
4193 `(("jdk" ,icedtea "jdk")))
4196 ("jre" ,icedtea "out")))
4197 (home-page "https://github.com/ctSkennerton/minced")
4198 (synopsis "Mining CRISPRs in Environmental Datasets")
4200 "MinCED is a program to find Clustered Regularly Interspaced Short
4201 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4202 unassembled metagenomic reads, but is mainly designed for full genomes and
4203 assembled metagenomic sequence.")
4204 (license license:gpl3+)))
4212 (uri (pypi-uri "misopy" version))
4215 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4216 (modules '((guix build utils)))
4218 (substitute* "setup.py"
4219 ;; Use setuptools, or else the executables are not
4221 (("distutils.core") "setuptools")
4222 ;; use "gcc" instead of "cc" for compilation
4224 "cc.set_executables(
4228 linker_so='gcc -shared'); defines"))
4230 (build-system python-build-system)
4232 `(#:python ,python-2 ; only Python 2 is supported
4233 #:tests? #f)) ; no "test" target
4235 `(("samtools" ,samtools)
4236 ("python-numpy" ,python2-numpy)
4237 ("python-pysam" ,python2-pysam)
4238 ("python-scipy" ,python2-scipy)
4239 ("python-matplotlib" ,python2-matplotlib)))
4241 `(("python-mock" ,python2-mock) ;for tests
4242 ("python-pytz" ,python2-pytz))) ;for tests
4243 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4244 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4246 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4247 the expression level of alternatively spliced genes from RNA-Seq data, and
4248 identifies differentially regulated isoforms or exons across samples. By
4249 modeling the generative process by which reads are produced from isoforms in
4250 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4251 that a read originated from a particular isoform.")
4252 (license license:gpl2)))
4254 (define-public muscle
4257 (version "3.8.1551")
4259 (method url-fetch/tarbomb)
4261 "http://www.drive5.com/muscle/muscle_src_"
4265 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4266 (build-system gnu-build-system)
4268 `(#:make-flags (list "LDLIBS = -lm")
4270 (modify-phases %standard-phases
4273 ;; There are no tests, so just test if it runs.
4274 (lambda _ (invoke "./muscle" "-version") #t))
4276 (lambda* (#:key outputs #:allow-other-keys)
4277 (let* ((out (assoc-ref outputs "out"))
4278 (bin (string-append out "/bin")))
4279 (install-file "muscle" bin)
4281 (home-page "http://www.drive5.com/muscle")
4282 (synopsis "Multiple sequence alignment program")
4284 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4285 program for nucleotide and protein sequences.")
4286 ;; License information found in 'muscle -h' and usage.cpp.
4287 (license license:public-domain)))
4289 (define-public newick-utils
4290 ;; There are no recent releases so we package from git.
4291 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4293 (name "newick-utils")
4294 (version (string-append "1.6-1." (string-take commit 8)))
4298 (url "https://github.com/tjunier/newick_utils.git")
4300 (file-name (string-append name "-" version "-checkout"))
4303 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4304 (build-system gnu-build-system)
4306 ;; XXX: TODO: Enable Lua and Guile bindings.
4307 ;; https://github.com/tjunier/newick_utils/issues/13
4308 `(("libxml2" ,libxml2)
4312 `(("autoconf" ,autoconf)
4313 ("automake" ,automake)
4314 ("libtool" ,libtool)))
4315 (synopsis "Programs for working with newick format phylogenetic trees")
4317 "Newick-utils is a suite of utilities for processing phylogenetic trees
4318 in Newick format. Functions include re-rooting, extracting subtrees,
4319 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4320 (home-page "https://github.com/tjunier/newick_utils")
4321 (license license:bsd-3))))
4330 "https://github.com/wwood/OrfM/releases/download/v"
4331 version "/orfm-" version ".tar.gz"))
4334 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4335 (build-system gnu-build-system)
4336 (inputs `(("zlib" ,zlib)))
4338 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4339 ("ruby-rspec" ,ruby-rspec)
4341 (synopsis "Simple and not slow open reading frame (ORF) caller")
4343 "An ORF caller finds stretches of DNA that, when translated, are not
4344 interrupted by stop codons. OrfM finds and prints these ORFs.")
4345 (home-page "https://github.com/wwood/OrfM")
4346 (license license:lgpl3+)))
4348 (define-public pplacer
4349 (let ((commit "807f6f3"))
4352 ;; The commit should be updated with each version change.
4353 (version "1.1.alpha19")
4358 (url "https://github.com/matsen/pplacer.git")
4359 (commit (string-append "v" version))))
4360 (file-name (git-file-name name version))
4362 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
4363 (build-system ocaml-build-system)
4365 `(#:ocaml ,ocaml-4.01
4366 #:findlib ,ocaml4.01-findlib
4367 #:modules ((guix build ocaml-build-system)
4371 (modify-phases %standard-phases
4373 (add-after 'unpack 'replace-bundled-cddlib
4374 (lambda* (#:key inputs #:allow-other-keys)
4375 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4376 (local-dir "cddlib_guix"))
4378 (with-directory-excursion local-dir
4379 (invoke "tar" "xvf" cddlib-src))
4380 (let ((cddlib-src-folder
4381 (string-append local-dir "/"
4382 (list-ref (scandir local-dir) 2)
4384 (for-each make-file-writable (find-files "cdd_src" ".*"))
4388 (string-append "cdd_src/" (basename file))))
4389 (find-files cddlib-src-folder ".*[ch]$")))
4391 (add-after 'unpack 'fix-makefile
4393 ;; Remove system calls to 'git'.
4394 (substitute* "Makefile"
4395 (("^DESCRIPT:=pplacer-.*")
4397 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4398 (substitute* "myocamlbuild.ml"
4399 (("git describe --tags --long .*\\\" with")
4401 "echo -n v" ,version "-" ,commit "\" with")))
4404 (lambda* (#:key outputs #:allow-other-keys)
4405 (let* ((out (assoc-ref outputs "out"))
4406 (bin (string-append out "/bin")))
4407 (copy-recursively "bin" bin))
4412 ("ocaml-ounit" ,ocaml4.01-ounit)
4413 ("ocaml-batteries" ,ocaml4.01-batteries)
4414 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4415 ("ocaml-csv" ,ocaml4.01-csv)
4416 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4417 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4418 ("ocaml-mcl" ,ocaml4.01-mcl)
4419 ("ocaml-gsl" ,ocaml4.01-gsl)
4420 ("cddlib-src" ,(package-source cddlib))))
4422 `(("pplacer-scripts" ,pplacer-scripts)))
4423 (synopsis "Phylogenetic placement of biological sequences")
4425 "Pplacer places query sequences on a fixed reference phylogenetic tree
4426 to maximize phylogenetic likelihood or posterior probability according to a
4427 reference alignment. Pplacer is designed to be fast, to give useful
4428 information about uncertainty, and to offer advanced visualization and
4429 downstream analysis.")
4430 (home-page "http://matsen.fhcrc.org/pplacer")
4431 (license license:gpl3))))
4433 ;; This package is installed alongside 'pplacer'. It is a separate package so
4434 ;; that it can use the python-build-system for the scripts that are
4435 ;; distributed alongside the main OCaml binaries.
4436 (define pplacer-scripts
4439 (name "pplacer-scripts")
4440 (build-system python-build-system)
4442 `(#:python ,python-2
4444 (modify-phases %standard-phases
4445 (add-after 'unpack 'enter-scripts-dir
4446 (lambda _ (chdir "scripts") #t))
4448 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
4449 (add-after 'install 'wrap-executables
4450 (lambda* (#:key inputs outputs #:allow-other-keys)
4451 (let* ((out (assoc-ref outputs "out"))
4452 (bin (string-append out "/bin")))
4453 (let ((path (string-append
4454 (assoc-ref inputs "hmmer") "/bin:"
4455 (assoc-ref inputs "infernal") "/bin")))
4457 (wrap-program (string-append bin "/refpkg_align.py")
4458 `("PATH" ":" prefix (,path))))
4459 (let ((path (string-append
4460 (assoc-ref inputs "hmmer") "/bin")))
4461 (wrap-program (string-append bin "/hrefpkg_query.py")
4462 `("PATH" ":" prefix (,path)))))
4465 `(("infernal" ,infernal)
4468 `(("python-biopython" ,python2-biopython)
4469 ("taxtastic" ,taxtastic)))
4470 (synopsis "Pplacer Python scripts")))
4472 (define-public python2-pbcore
4474 (name "python2-pbcore")
4478 (uri (pypi-uri "pbcore" version))
4481 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4482 (build-system python-build-system)
4483 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4485 `(("python-cython" ,python2-cython)
4486 ("python-numpy" ,python2-numpy)
4487 ("python-pysam" ,python2-pysam)
4488 ("python-h5py" ,python2-h5py)))
4490 `(("python-nose" ,python2-nose)
4491 ("python-sphinx" ,python2-sphinx)
4492 ("python-pyxb" ,python2-pyxb)))
4493 (home-page "http://pacificbiosciences.github.io/pbcore/")
4494 (synopsis "Library for reading and writing PacBio data files")
4496 "The pbcore package provides Python APIs for interacting with PacBio data
4497 files and writing bioinformatics applications.")
4498 (license license:bsd-3)))
4500 (define-public python2-warpedlmm
4502 (name "python2-warpedlmm")
4507 (uri (pypi-uri "WarpedLMM" version ".zip"))
4510 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4511 (build-system python-build-system)
4513 `(#:python ,python-2)) ; requires Python 2.7
4515 `(("python-scipy" ,python2-scipy)
4516 ("python-numpy" ,python2-numpy)
4517 ("python-matplotlib" ,python2-matplotlib)
4518 ("python-fastlmm" ,python2-fastlmm)
4519 ("python-pandas" ,python2-pandas)
4520 ("python-pysnptools" ,python2-pysnptools)))
4522 `(("python-mock" ,python2-mock)
4523 ("python-nose" ,python2-nose)
4525 (home-page "https://github.com/PMBio/warpedLMM")
4526 (synopsis "Implementation of warped linear mixed models")
4528 "WarpedLMM is a Python implementation of the warped linear mixed model,
4529 which automatically learns an optimal warping function (or transformation) for
4530 the phenotype as it models the data.")
4531 (license license:asl2.0)))
4533 (define-public pbtranscript-tofu
4534 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4536 (name "pbtranscript-tofu")
4537 (version (string-append "2.2.3." (string-take commit 7)))
4541 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4543 (file-name (string-append name "-" version "-checkout"))
4546 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4547 (modules '((guix build utils)))
4550 ;; remove bundled Cython sources
4551 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4553 (build-system python-build-system)
4555 `(#:python ,python-2
4556 ;; FIXME: Tests fail with "No such file or directory:
4557 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4560 (modify-phases %standard-phases
4561 (add-after 'unpack 'enter-directory
4563 (chdir "pbtranscript-tofu/pbtranscript/")
4565 ;; With setuptools version 18.0 and later this setup.py hack causes
4566 ;; a build error, so we disable it.
4567 (add-after 'enter-directory 'patch-setuppy
4569 (substitute* "setup.py"
4570 (("if 'setuptools.extension' in sys.modules:")
4574 `(("python-numpy" ,python2-numpy)
4575 ("python-bx-python" ,python2-bx-python)
4576 ("python-networkx" ,python2-networkx)
4577 ("python-scipy" ,python2-scipy)
4578 ("python-pbcore" ,python2-pbcore)
4579 ("python-h5py" ,python2-h5py)))
4581 `(("python-cython" ,python2-cython)
4582 ("python-nose" ,python2-nose)))
4583 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4584 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4586 "pbtranscript-tofu contains scripts to analyze transcriptome data
4587 generated using the PacBio Iso-Seq protocol.")
4588 (license license:bsd-3))))
4590 (define-public prank
4597 "http://wasabiapp.org/download/prank/prank.source."
4601 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4602 (build-system gnu-build-system)
4605 (modify-phases %standard-phases
4606 (add-after 'unpack 'enter-src-dir
4610 (add-after 'unpack 'remove-m64-flag
4611 ;; Prank will build with the correct 'bit-ness' without this flag
4612 ;; and this allows building on 32-bit machines.
4613 (lambda _ (substitute* "src/Makefile"
4618 (lambda* (#:key outputs #:allow-other-keys)
4619 (let* ((out (assoc-ref outputs "out"))
4620 (bin (string-append out "/bin"))
4621 (man (string-append out "/share/man/man1"))
4622 (path (string-append
4623 (assoc-ref %build-inputs "mafft") "/bin:"
4624 (assoc-ref %build-inputs "exonerate") "/bin:"
4625 (assoc-ref %build-inputs "bppsuite") "/bin")))
4626 (install-file "prank" bin)
4627 (wrap-program (string-append bin "/prank")
4628 `("PATH" ":" prefix (,path)))
4629 (install-file "prank.1" man))
4633 ("exonerate" ,exonerate)
4634 ("bppsuite" ,bppsuite)))
4635 (home-page "http://wasabiapp.org/software/prank/")
4636 (synopsis "Probabilistic multiple sequence alignment program")
4638 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4639 codon and amino-acid sequences. It is based on a novel algorithm that treats
4640 insertions correctly and avoids over-estimation of the number of deletion
4641 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4642 in phylogenetics and correctly takes into account the evolutionary distances
4643 between sequences. Lastly, PRANK allows for defining a potential structure
4644 for sequences to be aligned and then, simultaneously with the alignment,
4645 predicts the locations of structural units in the sequences.")
4646 (license license:gpl2+)))
4648 (define-public proteinortho
4650 (name "proteinortho")
4657 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4658 version "_src.tar.gz"))
4661 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4662 (build-system gnu-build-system)
4664 `(#:test-target "test"
4666 (modify-phases %standard-phases
4668 ;; There is no configure script, so we modify the Makefile directly.
4669 (lambda* (#:key outputs #:allow-other-keys)
4670 (substitute* "Makefile"
4673 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4675 (add-before 'install 'make-install-directory
4676 ;; The install directory is not created during 'make install'.
4677 (lambda* (#:key outputs #:allow-other-keys)
4678 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4680 (add-after 'install 'wrap-programs
4681 (lambda* (#:key inputs outputs #:allow-other-keys)
4682 (let* ((path (getenv "PATH"))
4683 (out (assoc-ref outputs "out"))
4684 (binary (string-append out "/bin/proteinortho5.pl")))
4685 (wrap-program binary `("PATH" ":" prefix (,path))))
4689 ("python" ,python-2)
4690 ("blast+" ,blast+)))
4691 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4692 (synopsis "Detect orthologous genes across species")
4694 "Proteinortho is a tool to detect orthologous genes across different
4695 species. For doing so, it compares similarities of given gene sequences and
4696 clusters them to find significant groups. The algorithm was designed to handle
4697 large-scale data and can be applied to hundreds of species at once.")
4698 (license license:gpl2+)))
4700 (define-public pyicoteo
4708 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4709 (commit (string-append "v" version))))
4710 (file-name (git-file-name name version))
4713 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4714 (build-system python-build-system)
4716 `(#:python ,python-2 ; does not work with Python 3
4717 #:tests? #f)) ; there are no tests
4719 `(("python2-matplotlib" ,python2-matplotlib)))
4720 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4721 (synopsis "Analyze high-throughput genetic sequencing data")
4723 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4724 sequencing data. It works with genomic coordinates. There are currently six
4725 different command-line tools:
4728 @item pyicoregion: for generating exploratory regions automatically;
4729 @item pyicoenrich: for differential enrichment between two conditions;
4730 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4731 @item pyicos: for genomic coordinates manipulation;
4732 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4733 @item pyicount: to count how many reads from N experiment files overlap in a
4735 @item pyicotrocol: to combine operations from pyicoteo.
4737 (license license:gpl3+)))
4739 (define-public prodigal
4746 (url "https://github.com/hyattpd/Prodigal.git")
4747 (commit (string-append "v" version))))
4748 (file-name (git-file-name name version))
4751 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4752 (build-system gnu-build-system)
4754 `(#:tests? #f ;no check target
4755 #:make-flags (list (string-append "INSTALLDIR="
4756 (assoc-ref %outputs "out")
4759 (modify-phases %standard-phases
4760 (delete 'configure))))
4761 (home-page "http://prodigal.ornl.gov")
4762 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4764 "Prodigal runs smoothly on finished genomes, draft genomes, and
4765 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4766 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4767 partial genes, and identifies translation initiation sites.")
4768 (license license:gpl3+)))
4770 (define-public roary
4778 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4782 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4783 (build-system perl-build-system)
4786 (modify-phases %standard-phases
4791 ;; The tests are not run by default, so we run each test file
4793 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4795 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4796 (getenv "PERL5LIB")))
4797 (for-each (lambda (file)
4798 (display file)(display "\n")
4799 (invoke "perl" file))
4800 (find-files "t" ".*\\.t$"))
4803 ;; There is no 'install' target in the Makefile.
4804 (lambda* (#:key outputs #:allow-other-keys)
4805 (let* ((out (assoc-ref outputs "out"))
4806 (bin (string-append out "/bin"))
4807 (perl (string-append out "/lib/perl5/site_perl"))
4808 (roary-plots "contrib/roary_plots"))
4811 (copy-recursively "bin" bin)
4812 (copy-recursively "lib" perl)
4814 (add-after 'install 'wrap-programs
4815 (lambda* (#:key inputs outputs #:allow-other-keys)
4816 (let* ((out (assoc-ref outputs "out"))
4817 (perl5lib (getenv "PERL5LIB"))
4818 (path (getenv "PATH")))
4819 (for-each (lambda (prog)
4820 (let ((binary (string-append out "/" prog)))
4821 (wrap-program binary
4822 `("PERL5LIB" ":" prefix
4823 (,(string-append perl5lib ":" out
4824 "/lib/perl5/site_perl"))))
4825 (wrap-program binary
4827 (,(string-append path ":" out "/bin"))))))
4828 (find-files "bin" ".*[^R]$"))
4830 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4831 (r-site-lib (getenv "R_LIBS_SITE"))
4833 (string-append (assoc-ref inputs "coreutils") "/bin")))
4835 `("R_LIBS_SITE" ":" prefix
4836 (,(string-append r-site-lib ":" out "/site-library/"))))
4839 (,(string-append coreutils-path ":" out "/bin"))))))
4842 `(("perl-env-path" ,perl-env-path)
4843 ("perl-test-files" ,perl-test-files)
4844 ("perl-test-most" ,perl-test-most)
4845 ("perl-test-output" ,perl-test-output)))
4847 `(("perl-array-utils" ,perl-array-utils)
4848 ("bioperl" ,bioperl-minimal)
4849 ("perl-digest-md5-file" ,perl-digest-md5-file)
4850 ("perl-exception-class" ,perl-exception-class)
4851 ("perl-file-find-rule" ,perl-file-find-rule)
4852 ("perl-file-grep" ,perl-file-grep)
4853 ("perl-file-slurper" ,perl-file-slurper)
4854 ("perl-file-which" ,perl-file-which)
4855 ("perl-graph" ,perl-graph)
4856 ("perl-graph-readwrite" ,perl-graph-readwrite)
4857 ("perl-log-log4perl" ,perl-log-log4perl)
4858 ("perl-moose" ,perl-moose)
4859 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4860 ("perl-text-csv" ,perl-text-csv)
4861 ("bedtools" ,bedtools)
4865 ("parallel" ,parallel)
4868 ("fasttree" ,fasttree)
4872 ("r-minimal" ,r-minimal)
4873 ("r-ggplot2" ,r-ggplot2)
4874 ("coreutils" ,coreutils)))
4875 (home-page "http://sanger-pathogens.github.io/Roary")
4876 (synopsis "High speed stand-alone pan genome pipeline")
4878 "Roary is a high speed stand alone pan genome pipeline, which takes
4879 annotated assemblies in GFF3 format (produced by the Prokka program) and
4880 calculates the pan genome. Using a standard desktop PC, it can analyse
4881 datasets with thousands of samples, without compromising the quality of the
4882 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4883 single processor. Roary is not intended for metagenomics or for comparing
4884 extremely diverse sets of genomes.")
4885 (license license:gpl3)))
4887 (define-public raxml
4895 (url "https://github.com/stamatak/standard-RAxML.git")
4896 (commit (string-append "v" version))))
4897 (file-name (git-file-name name version))
4900 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4901 (build-system gnu-build-system)
4903 `(#:tests? #f ; There are no tests.
4904 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4905 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4907 (modify-phases %standard-phases
4910 (lambda* (#:key outputs #:allow-other-keys)
4911 (let* ((out (assoc-ref outputs "out"))
4912 (bin (string-append out "/bin"))
4913 (executable "raxmlHPC-HYBRID"))
4914 (install-file executable bin)
4915 (symlink (string-append bin "/" executable) "raxml"))
4918 `(("openmpi" ,openmpi)))
4919 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4920 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4922 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4924 ;; The source includes x86 specific code
4925 (supported-systems '("x86_64-linux" "i686-linux"))
4926 (license license:gpl2+)))
4936 (url "https://github.com/deweylab/RSEM.git")
4937 (commit (string-append "v" version))))
4939 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4940 (file-name (git-file-name name version))
4941 (modules '((guix build utils)))
4944 ;; remove bundled copy of boost and samtools
4945 (delete-file-recursively "boost")
4946 (delete-file-recursively "samtools-1.3")
4948 (build-system gnu-build-system)
4950 `(#:tests? #f ;no "check" target
4952 (list (string-append "BOOST="
4953 (assoc-ref %build-inputs "boost")
4955 (string-append "SAMHEADERS="
4956 (assoc-ref %build-inputs "htslib")
4957 "/include/htslib/sam.h")
4958 (string-append "SAMLIBS="
4959 (assoc-ref %build-inputs "htslib")
4962 (modify-phases %standard-phases
4963 ;; No "configure" script.
4964 ;; Do not build bundled samtools library.
4967 (substitute* "Makefile"
4968 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4969 (("^\\$\\(SAMLIBS\\).*") ""))
4972 (lambda* (#:key outputs #:allow-other-keys)
4973 (let* ((out (string-append (assoc-ref outputs "out")))
4974 (bin (string-append out "/bin/"))
4975 (perl (string-append out "/lib/perl5/site_perl")))
4978 (for-each (lambda (file)
4979 (install-file file bin))
4980 (find-files "." "rsem-.*"))
4981 (install-file "rsem_perl_utils.pm" perl))
4983 (add-after 'install 'wrap-program
4984 (lambda* (#:key outputs #:allow-other-keys)
4985 (let ((out (assoc-ref outputs "out")))
4986 (for-each (lambda (prog)
4987 (wrap-program (string-append out "/bin/" prog)
4988 `("PERL5LIB" ":" prefix
4989 (,(string-append out "/lib/perl5/site_perl")))))
4990 '("rsem-calculate-expression"
4992 "rsem-generate-data-matrix"
4993 "rsem-generate-ngvector"
4994 "rsem-plot-transcript-wiggles"
4995 "rsem-prepare-reference"
4997 "rsem-run-prsem-testing-procedure")))
5001 ("r-minimal" ,r-minimal)
5003 ("htslib" ,htslib-1.3)
5005 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5006 (synopsis "Estimate gene expression levels from RNA-Seq data")
5008 "RSEM is a software package for estimating gene and isoform expression
5009 levels from RNA-Seq data. The RSEM package provides a user-friendly
5010 interface, supports threads for parallel computation of the EM algorithm,
5011 single-end and paired-end read data, quality scores, variable-length reads and
5012 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5013 interval estimates for expression levels. For visualization, it can generate
5014 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5015 (license license:gpl3+)))
5017 (define-public rseqc
5025 (string-append "mirror://sourceforge/rseqc/"
5026 "RSeQC-" version ".tar.gz"))
5028 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5029 (modules '((guix build utils)))
5032 ;; remove bundled copy of pysam
5033 (delete-file-recursively "lib/pysam")
5034 (substitute* "setup.py"
5035 ;; remove dependency on outdated "distribute" module
5036 (("^from distribute_setup import use_setuptools") "")
5037 (("^use_setuptools\\(\\)") "")
5038 ;; do not use bundled copy of pysam
5039 (("^have_pysam = False") "have_pysam = True"))
5041 (build-system python-build-system)
5042 (arguments `(#:python ,python-2))
5044 `(("python-cython" ,python2-cython)
5045 ("python-pysam" ,python2-pysam)
5046 ("python-numpy" ,python2-numpy)
5049 `(("python-nose" ,python2-nose)))
5050 (home-page "http://rseqc.sourceforge.net/")
5051 (synopsis "RNA-seq quality control package")
5053 "RSeQC provides a number of modules that can comprehensively evaluate
5054 high throughput sequence data, especially RNA-seq data. Some basic modules
5055 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5056 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5057 distribution, coverage uniformity, strand specificity, etc.")
5058 (license license:gpl3+)))
5061 ;; There are no release tarballs. According to the installation
5062 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5063 ;; stable release is identified by this changeset ID.
5064 (let ((changeset "2329130")
5068 (version (string-append "0-" revision "." changeset))
5072 (url "https://bitbucket.org/libsleipnir/sleipnir")
5073 (changeset changeset)))
5074 (file-name (string-append name "-" version "-checkout"))
5077 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5078 (build-system gnu-build-system)
5080 `(#:modules ((srfi srfi-1)
5081 (guix build gnu-build-system)
5084 (let ((dirs '("SeekMiner"
5090 (modify-phases %standard-phases
5093 (substitute* "gen_tools_am"
5094 (("/usr/bin/env.*") (which "perl")))
5095 (invoke "bash" "gen_auto")
5097 (add-after 'build 'build-additional-tools
5098 (lambda* (#:key make-flags #:allow-other-keys)
5099 (for-each (lambda (dir)
5100 (with-directory-excursion (string-append "tools/" dir)
5101 (apply invoke "make" make-flags)))
5104 (add-after 'install 'install-additional-tools
5105 (lambda* (#:key make-flags #:allow-other-keys)
5106 (for-each (lambda (dir)
5107 (with-directory-excursion (string-append "tools/" dir)
5108 (apply invoke `("make" ,@make-flags "install"))))
5115 ("readline" ,readline)
5116 ("gengetopt" ,gengetopt)
5117 ("log4cpp" ,log4cpp)))
5119 `(("autoconf" ,autoconf)
5120 ("automake" ,automake)
5122 (home-page "http://seek.princeton.edu")
5123 (synopsis "Gene co-expression search engine")
5125 "SEEK is a computational gene co-expression search engine. SEEK provides
5126 biologists with a way to navigate the massive human expression compendium that
5127 now contains thousands of expression datasets. SEEK returns a robust ranking
5128 of co-expressed genes in the biological area of interest defined by the user's
5129 query genes. It also prioritizes thousands of expression datasets according
5130 to the user's query of interest.")
5131 (license license:cc-by3.0))))
5133 (define-public samtools
5141 (string-append "mirror://sourceforge/samtools/samtools/"
5142 version "/samtools-" version ".tar.bz2"))
5145 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5146 (modules '((guix build utils)))
5148 ;; Delete bundled htslib.
5149 (delete-file-recursively "htslib-1.9")
5151 (build-system gnu-build-system)
5153 `(#:modules ((ice-9 ftw)
5155 (guix build gnu-build-system)
5157 #:configure-flags (list "--with-ncurses")
5159 (modify-phases %standard-phases
5160 (add-after 'unpack 'patch-tests
5162 (substitute* "test/test.pl"
5163 ;; The test script calls out to /bin/bash
5164 (("/bin/bash") (which "bash")))
5166 (add-after 'install 'install-library
5167 (lambda* (#:key outputs #:allow-other-keys)
5168 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5169 (install-file "libbam.a" lib)
5171 (add-after 'install 'install-headers
5172 (lambda* (#:key outputs #:allow-other-keys)
5173 (let ((include (string-append (assoc-ref outputs "out")
5174 "/include/samtools/")))
5175 (for-each (lambda (file)
5176 (install-file file include))
5177 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5179 (native-inputs `(("pkg-config" ,pkg-config)))
5181 `(("htslib" ,htslib)
5182 ("ncurses" ,ncurses)
5186 (home-page "http://samtools.sourceforge.net")
5187 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5189 "Samtools implements various utilities for post-processing nucleotide
5190 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5191 variant calling (in conjunction with bcftools), and a simple alignment
5193 (license license:expat)))
5195 (define-public samtools-0.1
5196 ;; This is the most recent version of the 0.1 line of samtools. The input
5197 ;; and output formats differ greatly from that used and produced by samtools
5198 ;; 1.x and is still used in many bioinformatics pipelines.
5199 (package (inherit samtools)
5205 (string-append "mirror://sourceforge/samtools/samtools/"
5206 version "/samtools-" version ".tar.bz2"))
5208 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5210 `(#:tests? #f ;no "check" target
5212 (list "LIBCURSES=-lncurses")
5213 ,@(substitute-keyword-arguments (package-arguments samtools)
5215 `(modify-phases ,phases
5217 (lambda* (#:key outputs #:allow-other-keys)
5218 (let ((bin (string-append
5219 (assoc-ref outputs "out") "/bin")))
5221 (install-file "samtools" bin)
5223 (delete 'patch-tests)
5224 (delete 'configure))))))))
5226 (define-public mosaik
5227 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5232 ;; There are no release tarballs nor tags.
5235 (url "https://github.com/wanpinglee/MOSAIK.git")
5237 (file-name (string-append name "-" version))
5240 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5241 (build-system gnu-build-system)
5243 `(#:tests? #f ; no tests
5244 #:make-flags (list "CC=gcc")
5246 (modify-phases %standard-phases
5248 (lambda _ (chdir "src") #t))
5250 (lambda* (#:key outputs #:allow-other-keys)
5251 (let ((bin (string-append (assoc-ref outputs "out")
5254 (copy-recursively "../bin" bin)
5258 ("zlib:static" ,zlib "static")
5260 (supported-systems '("x86_64-linux"))
5261 (home-page "https://github.com/wanpinglee/MOSAIK")
5262 (synopsis "Map nucleotide sequence reads to reference genomes")
5264 "MOSAIK is a program for mapping second and third-generation sequencing
5265 reads to a reference genome. MOSAIK can align reads generated by all the
5266 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5267 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5268 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5269 ;; code released into the public domain:
5270 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5271 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5272 (license (list license:gpl2+ license:public-domain)))))
5274 (define-public ngs-sdk
5281 (url "https://github.com/ncbi/ngs.git")
5283 (file-name (git-file-name name version))
5286 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5287 (build-system gnu-build-system)
5289 `(#:parallel-build? #f ; not supported
5290 #:tests? #f ; no "check" target
5292 (modify-phases %standard-phases
5294 (lambda* (#:key outputs #:allow-other-keys)
5295 (let ((out (assoc-ref outputs "out")))
5296 ;; Allow 'konfigure.perl' to find 'package.prl'.
5298 (string-append ".:" (getenv "PERL5LIB")))
5300 ;; The 'configure' script doesn't recognize things like
5301 ;; '--enable-fast-install'.
5302 (invoke "./configure"
5303 (string-append "--build-prefix=" (getcwd) "/build")
5304 (string-append "--prefix=" out))
5306 (add-after 'unpack 'enter-dir
5307 (lambda _ (chdir "ngs-sdk") #t)))))
5308 (native-inputs `(("perl" ,perl)))
5309 ;; According to the test
5310 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5311 ;; in ngs-sdk/setup/konfigure.perl
5312 (supported-systems '("i686-linux" "x86_64-linux"))
5313 (home-page "https://github.com/ncbi/ngs")
5314 (synopsis "API for accessing Next Generation Sequencing data")
5316 "NGS is a domain-specific API for accessing reads, alignments and pileups
5317 produced from Next Generation Sequencing. The API itself is independent from
5318 any particular back-end implementation, and supports use of multiple back-ends
5320 (license license:public-domain)))
5322 (define-public java-ngs
5323 (package (inherit ngs-sdk)
5326 `(,@(substitute-keyword-arguments
5327 `(#:modules ((guix build gnu-build-system)
5331 ,@(package-arguments ngs-sdk))
5333 `(modify-phases ,phases
5334 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5336 `(("jdk" ,icedtea "jdk")
5337 ("ngs-sdk" ,ngs-sdk)))
5338 (synopsis "Java bindings for NGS SDK")))
5340 (define-public ncbi-vdb
5347 (url "https://github.com/ncbi/ncbi-vdb.git")
5349 (file-name (git-file-name name version))
5352 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5353 (build-system gnu-build-system)
5355 `(#:parallel-build? #f ; not supported
5356 #:tests? #f ; no "check" target
5358 (modify-phases %standard-phases
5359 (add-after 'unpack 'make-files-writable
5360 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5361 (add-before 'configure 'set-perl-search-path
5363 ;; Work around "dotless @INC" build failure.
5365 (string-append (getcwd) "/setup:"
5366 (getenv "PERL5LIB")))
5369 (lambda* (#:key inputs outputs #:allow-other-keys)
5370 (let ((out (assoc-ref outputs "out")))
5371 ;; Override include path for libmagic
5372 (substitute* "setup/package.prl"
5373 (("name => 'magic', Include => '/usr/include'")
5374 (string-append "name=> 'magic', Include => '"
5375 (assoc-ref inputs "libmagic")
5378 ;; Install kdf5 library (needed by sra-tools)
5379 (substitute* "build/Makefile.install"
5380 (("LIBRARIES_TO_INSTALL =")
5381 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5383 (substitute* "build/Makefile.env"
5384 (("CFLAGS =" prefix)
5385 (string-append prefix "-msse2 ")))
5387 ;; Override search path for ngs-java
5388 (substitute* "setup/package.prl"
5389 (("/usr/local/ngs/ngs-java")
5390 (assoc-ref inputs "java-ngs")))
5392 ;; The 'configure' script doesn't recognize things like
5393 ;; '--enable-fast-install'.
5394 (invoke "./configure"
5395 (string-append "--build-prefix=" (getcwd) "/build")
5396 (string-append "--prefix=" (assoc-ref outputs "out"))
5397 (string-append "--debug")
5398 (string-append "--with-xml2-prefix="
5399 (assoc-ref inputs "libxml2"))
5400 (string-append "--with-ngs-sdk-prefix="
5401 (assoc-ref inputs "ngs-sdk"))
5402 (string-append "--with-hdf5-prefix="
5403 (assoc-ref inputs "hdf5")))
5405 (add-after 'install 'install-interfaces
5406 (lambda* (#:key outputs #:allow-other-keys)
5407 ;; Install interface libraries. On i686 the interface libraries
5408 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5409 ;; architecture name ("i386") instead of the target system prefix
5411 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5412 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5413 ,(system->linux-architecture
5414 (or (%current-target-system)
5417 (string-append (assoc-ref outputs "out")
5419 ;; Install interface headers
5420 (copy-recursively "interfaces"
5421 (string-append (assoc-ref outputs "out")
5424 ;; These files are needed by sra-tools.
5425 (add-after 'install 'install-configuration-files
5426 (lambda* (#:key outputs #:allow-other-keys)
5427 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5429 (install-file "libs/kfg/default.kfg" target)
5430 (install-file "libs/kfg/certs.kfg" target))
5433 `(("libxml2" ,libxml2)
5434 ("ngs-sdk" ,ngs-sdk)
5435 ("java-ngs" ,java-ngs)
5438 (native-inputs `(("perl" ,perl)))
5439 ;; NCBI-VDB requires SSE capability.
5440 (supported-systems '("i686-linux" "x86_64-linux"))
5441 (home-page "https://github.com/ncbi/ncbi-vdb")
5442 (synopsis "Database engine for genetic information")
5444 "The NCBI-VDB library implements a highly compressed columnar data
5445 warehousing engine that is most often used to store genetic information.
5446 Databases are stored in a portable image within the file system, and can be
5447 accessed/downloaded on demand across HTTP.")
5448 (license license:public-domain)))
5450 (define-public plink
5458 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5459 version "-src.zip"))
5461 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5462 (patches (search-patches "plink-1.07-unclobber-i.patch"
5463 "plink-endian-detection.patch"))))
5464 (build-system gnu-build-system)
5466 '(#:tests? #f ;no "check" target
5467 #:make-flags (list (string-append "LIB_LAPACK="
5468 (assoc-ref %build-inputs "lapack")
5469 "/lib/liblapack.so")
5472 ;; disable phoning home
5475 (modify-phases %standard-phases
5476 ;; no "configure" script
5479 (lambda* (#:key outputs #:allow-other-keys)
5480 (let ((bin (string-append (assoc-ref outputs "out")
5482 (install-file "plink" bin)
5486 ("lapack" ,lapack)))
5488 `(("unzip" ,unzip)))
5489 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5490 (synopsis "Whole genome association analysis toolset")
5492 "PLINK is a whole genome association analysis toolset, designed to
5493 perform a range of basic, large-scale analyses in a computationally efficient
5494 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5495 so there is no support for steps prior to this (e.g. study design and
5496 planning, generating genotype or CNV calls from raw data). Through
5497 integration with gPLINK and Haploview, there is some support for the
5498 subsequent visualization, annotation and storage of results.")
5499 ;; Code is released under GPLv2, except for fisher.h, which is under
5501 (license (list license:gpl2 license:lgpl2.1+))))
5503 (define-public plink-ng
5504 (package (inherit plink)
5511 (url "https://github.com/chrchang/plink-ng.git")
5512 (commit (string-append "v" version))))
5513 (file-name (git-file-name name version))
5515 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5516 (build-system gnu-build-system)
5518 '(#:tests? #f ;no "check" target
5519 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5520 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5522 "-f" "Makefile.std")
5524 (modify-phases %standard-phases
5525 (add-after 'unpack 'chdir
5526 (lambda _ (chdir "1.9") #t))
5527 (delete 'configure) ; no "configure" script
5529 (lambda* (#:key outputs #:allow-other-keys)
5530 (let ((bin (string-append (assoc-ref outputs "out")
5532 (install-file "plink" bin)
5537 ("openblas" ,openblas)))
5538 (home-page "https://www.cog-genomics.org/plink/")
5539 (license license:gpl3+)))
5541 (define-public smithlab-cpp
5542 (let ((revision "1")
5543 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5545 (name "smithlab-cpp")
5546 (version (string-append "0." revision "." (string-take commit 7)))
5550 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5552 (file-name (string-append name "-" version "-checkout"))
5555 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5556 (build-system gnu-build-system)
5558 `(#:modules ((guix build gnu-build-system)
5561 #:tests? #f ;no "check" target
5563 (modify-phases %standard-phases
5564 (add-after 'unpack 'use-samtools-headers
5566 (substitute* '("SAM.cpp"
5568 (("sam.h") "samtools/sam.h"))
5571 (lambda* (#:key outputs #:allow-other-keys)
5572 (let* ((out (assoc-ref outputs "out"))
5573 (lib (string-append out "/lib"))
5574 (include (string-append out "/include/smithlab-cpp")))
5577 (for-each (cut install-file <> lib)
5578 (find-files "." "\\.o$"))
5579 (for-each (cut install-file <> include)
5580 (find-files "." "\\.hpp$")))
5582 (delete 'configure))))
5584 `(("samtools" ,samtools-0.1)
5586 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5587 (synopsis "C++ helper library for functions used in Smith lab projects")
5589 "Smithlab CPP is a C++ library that includes functions used in many of
5590 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5591 structures, classes for genomic regions, mapped sequencing reads, etc.")
5592 (license license:gpl3+))))
5594 (define-public preseq
5600 (uri (string-append "https://github.com/smithlabcode/preseq/"
5601 "releases/download/v" version
5602 "/preseq_v" version ".tar.bz2"))
5604 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5605 (modules '((guix build utils)))
5607 ;; Remove bundled samtools.
5608 (delete-file-recursively "samtools")
5610 (build-system gnu-build-system)
5612 `(#:tests? #f ;no "check" target
5614 (modify-phases %standard-phases
5615 (delete 'configure))
5617 (list (string-append "PREFIX="
5618 (assoc-ref %outputs "out"))
5619 (string-append "LIBBAM="
5620 (assoc-ref %build-inputs "samtools")
5622 (string-append "SMITHLAB_CPP="
5623 (assoc-ref %build-inputs "smithlab-cpp")
5626 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5629 ("samtools" ,samtools-0.1)
5630 ("smithlab-cpp" ,smithlab-cpp)
5632 (home-page "http://smithlabresearch.org/software/preseq/")
5633 (synopsis "Program for analyzing library complexity")
5635 "The preseq package is aimed at predicting and estimating the complexity
5636 of a genomic sequencing library, equivalent to predicting and estimating the
5637 number of redundant reads from a given sequencing depth and how many will be
5638 expected from additional sequencing using an initial sequencing experiment.
5639 The estimates can then be used to examine the utility of further sequencing,
5640 optimize the sequencing depth, or to screen multiple libraries to avoid low
5641 complexity samples.")
5642 (license license:gpl3+)))
5644 (define-public python-screed
5646 (name "python-screed")
5651 (uri (pypi-uri "screed" version))
5654 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5655 (build-system python-build-system)
5658 (modify-phases %standard-phases
5659 ;; Tests must be run after installation, as the "screed" command does
5660 ;; not exist right after building.
5662 (add-after 'install 'check
5663 (lambda* (#:key inputs outputs #:allow-other-keys)
5664 (let ((out (assoc-ref outputs "out")))
5665 (setenv "PYTHONPATH"
5666 (string-append out "/lib/python"
5667 (string-take (string-take-right
5668 (assoc-ref inputs "python")
5671 (getenv "PYTHONPATH")))
5672 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5673 (invoke "python" "setup.py" "test")
5676 `(("python-pytest" ,python-pytest)
5677 ("python-pytest-cov" ,python-pytest-cov)
5678 ("python-pytest-runner" ,python-pytest-runner)))
5680 `(("python-bz2file" ,python-bz2file)))
5681 (home-page "https://github.com/dib-lab/screed/")
5682 (synopsis "Short read sequence database utilities")
5683 (description "Screed parses FASTA and FASTQ files and generates databases.
5684 Values such as sequence name, sequence description, sequence quality and the
5685 sequence itself can be retrieved from these databases.")
5686 (license license:bsd-3)))
5688 (define-public python2-screed
5689 (package-with-python2 python-screed))
5691 (define-public sra-tools
5699 (url "https://github.com/ncbi/sra-tools.git")
5701 (file-name (git-file-name name version))
5704 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5705 (build-system gnu-build-system)
5707 `(#:parallel-build? #f ; not supported
5708 #:tests? #f ; no "check" target
5710 (list (string-append "DEFAULT_CRT="
5711 (assoc-ref %build-inputs "ncbi-vdb")
5713 (string-append "DEFAULT_KFG="
5714 (assoc-ref %build-inputs "ncbi-vdb")
5716 (string-append "VDB_LIBDIR="
5717 (assoc-ref %build-inputs "ncbi-vdb")
5718 ,(if (string-prefix? "x86_64"
5719 (or (%current-target-system)
5724 (modify-phases %standard-phases
5725 (add-before 'configure 'set-perl-search-path
5727 ;; Work around "dotless @INC" build failure.
5729 (string-append (getcwd) "/setup:"
5730 (getenv "PERL5LIB")))
5733 (lambda* (#:key inputs outputs #:allow-other-keys)
5734 ;; The build system expects a directory containing the sources and
5735 ;; raw build output of ncbi-vdb, including files that are not
5736 ;; installed. Since we are building against an installed version of
5737 ;; ncbi-vdb, the following modifications are needed.
5738 (substitute* "setup/konfigure.perl"
5739 ;; Make the configure script look for the "ilib" directory of
5740 ;; "ncbi-vdb" without first checking for the existence of a
5741 ;; matching library in its "lib" directory.
5742 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5743 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5744 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5745 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5746 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5749 (substitute* "tools/copycat/Makefile"
5750 (("smagic-static") "lmagic"))
5752 ;; The 'configure' script doesn't recognize things like
5753 ;; '--enable-fast-install'.
5754 (invoke "./configure"
5755 (string-append "--build-prefix=" (getcwd) "/build")
5756 (string-append "--prefix=" (assoc-ref outputs "out"))
5757 (string-append "--debug")
5758 (string-append "--with-fuse-prefix="
5759 (assoc-ref inputs "fuse"))
5760 (string-append "--with-magic-prefix="
5761 (assoc-ref inputs "libmagic"))
5762 ;; TODO: building with libxml2 fails with linker errors
5763 ;; (string-append "--with-xml2-prefix="
5764 ;; (assoc-ref inputs "libxml2"))
5765 (string-append "--with-ncbi-vdb-sources="
5766 (assoc-ref inputs "ncbi-vdb"))
5767 (string-append "--with-ncbi-vdb-build="
5768 (assoc-ref inputs "ncbi-vdb"))
5769 (string-append "--with-ngs-sdk-prefix="
5770 (assoc-ref inputs "ngs-sdk"))
5771 (string-append "--with-hdf5-prefix="
5772 (assoc-ref inputs "hdf5")))
5774 (native-inputs `(("perl" ,perl)))
5776 `(("ngs-sdk" ,ngs-sdk)
5777 ("ncbi-vdb" ,ncbi-vdb)
5782 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5783 (synopsis "Tools and libraries for reading and writing sequencing data")
5785 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5786 reading of sequencing files from the Sequence Read Archive (SRA) database and
5787 writing files into the .sra format.")
5788 (license license:public-domain)))
5790 (define-public seqan
5796 (uri (string-append "https://github.com/seqan/seqan/releases/"
5797 "download/seqan-v" version
5798 "/seqan-library-" version ".tar.xz"))
5801 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5802 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5803 ;; makes sense to split the outputs.
5804 (outputs '("out" "doc"))
5805 (build-system trivial-build-system)
5807 `(#:modules ((guix build utils))
5810 (use-modules (guix build utils))
5811 (let ((tar (assoc-ref %build-inputs "tar"))
5812 (xz (assoc-ref %build-inputs "xz"))
5813 (out (assoc-ref %outputs "out"))
5814 (doc (assoc-ref %outputs "doc")))
5815 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5816 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5817 (chdir (string-append "seqan-library-" ,version))
5818 (copy-recursively "include" (string-append out "/include"))
5819 (copy-recursively "share" (string-append doc "/share"))
5822 `(("source" ,source)
5825 (home-page "http://www.seqan.de")
5826 (synopsis "Library for nucleotide sequence analysis")
5828 "SeqAn is a C++ library of efficient algorithms and data structures for
5829 the analysis of sequences with the focus on biological data. It contains
5830 algorithms and data structures for string representation and their
5831 manipulation, online and indexed string search, efficient I/O of
5832 bioinformatics file formats, sequence alignment, and more.")
5833 (license license:bsd-3)))
5835 (define-public seqan-1
5836 (package (inherit seqan)
5841 (uri (string-append "http://packages.seqan.de/seqan-library/"
5842 "seqan-library-" version ".tar.bz2"))
5845 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5846 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5847 ;; makes sense to split the outputs.
5848 (outputs '("out" "doc"))
5849 (build-system trivial-build-system)
5851 `(#:modules ((guix build utils))
5854 (use-modules (guix build utils))
5855 (let ((tar (assoc-ref %build-inputs "tar"))
5856 (bzip (assoc-ref %build-inputs "bzip2"))
5857 (out (assoc-ref %outputs "out"))
5858 (doc (assoc-ref %outputs "doc")))
5859 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5860 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5861 (chdir (string-append "seqan-library-" ,version))
5862 (copy-recursively "include" (string-append out "/include"))
5863 (copy-recursively "share" (string-append doc "/share"))
5866 `(("source" ,source)
5868 ("bzip2" ,bzip2)))))
5870 (define-public seqmagick
5877 (uri (pypi-uri "seqmagick" version))
5880 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5881 (build-system python-build-system)
5883 `(("python-biopython" ,python-biopython)))
5885 `(("python-nose" ,python-nose)))
5886 (home-page "https://github.com/fhcrc/seqmagick")
5887 (synopsis "Tools for converting and modifying sequence files")
5889 "Bioinformaticians often have to convert sequence files between formats
5890 and do little manipulations on them, and it's not worth writing scripts for
5891 that. Seqmagick is a utility to expose the file format conversion in
5892 BioPython in a convenient way. Instead of having a big mess of scripts, there
5893 is one that takes arguments.")
5894 (license license:gpl3)))
5896 (define-public seqtk
5903 (url "https://github.com/lh3/seqtk.git")
5904 (commit (string-append "v" version))))
5905 (file-name (git-file-name name version))
5908 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5909 (build-system gnu-build-system)
5912 (modify-phases %standard-phases
5915 ;; There are no tests, so we just run a sanity check.
5916 (lambda _ (invoke "./seqtk" "seq") #t))
5918 (lambda* (#:key outputs #:allow-other-keys)
5919 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5920 (install-file "seqtk" bin)
5924 (home-page "https://github.com/lh3/seqtk")
5925 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5927 "Seqtk is a fast and lightweight tool for processing sequences in the
5928 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5929 optionally compressed by gzip.")
5930 (license license:expat)))
5932 (define-public snap-aligner
5934 (name "snap-aligner")
5935 (version "1.0beta.18")
5939 (url "https://github.com/amplab/snap.git")
5940 (commit (string-append "v" version))))
5941 (file-name (git-file-name name version))
5944 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5945 (build-system gnu-build-system)
5948 (modify-phases %standard-phases
5950 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5952 (lambda* (#:key outputs #:allow-other-keys)
5953 (let* ((out (assoc-ref outputs "out"))
5954 (bin (string-append out "/bin")))
5955 (install-file "snap-aligner" bin)
5956 (install-file "SNAPCommand" bin)
5960 (home-page "http://snap.cs.berkeley.edu/")
5961 (synopsis "Short read DNA sequence aligner")
5963 "SNAP is a fast and accurate aligner for short DNA reads. It is
5964 optimized for modern read lengths of 100 bases or higher, and takes advantage
5965 of these reads to align data quickly through a hash-based indexing scheme.")
5966 ;; 32-bit systems are not supported by the unpatched code.
5967 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5968 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5969 ;; systems without a lot of memory cannot make good use of this program.
5970 (supported-systems '("x86_64-linux"))
5971 (license license:asl2.0)))
5973 (define-public sortmerna
5981 (url "https://github.com/biocore/sortmerna.git")
5983 (file-name (git-file-name name version))
5986 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5987 (build-system gnu-build-system)
5988 (outputs '("out" ;for binaries
5989 "db")) ;for sequence databases
5992 (modify-phases %standard-phases
5994 (lambda* (#:key outputs #:allow-other-keys)
5995 (let* ((out (assoc-ref outputs "out"))
5996 (bin (string-append out "/bin"))
5997 (db (assoc-ref outputs "db"))
5999 (string-append db "/share/sortmerna/rRNA_databases")))
6000 (install-file "sortmerna" bin)
6001 (install-file "indexdb_rna" bin)
6002 (for-each (lambda (file)
6003 (install-file file share))
6004 (find-files "rRNA_databases" ".*fasta"))
6008 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6009 (synopsis "Biological sequence analysis tool for NGS reads")
6011 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6012 and operational taxonomic unit (OTU) picking of next generation
6013 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6014 allows for fast and sensitive analyses of nucleotide sequences. The main
6015 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6016 ;; The source includes x86 specific code
6017 (supported-systems '("x86_64-linux" "i686-linux"))
6018 (license license:lgpl3)))
6027 (url "https://github.com/alexdobin/STAR.git")
6029 (file-name (string-append name "-" version "-checkout"))
6032 "1lih6cbpvnvhyvvswdhy06mwyzvwax96m723378v4z6psqzsh11d"))
6033 (modules '((guix build utils)))
6036 (substitute* "source/Makefile"
6038 ;; Remove pre-built binaries and bundled htslib sources.
6039 (delete-file-recursively "bin/MacOSX_x86_64")
6040 (delete-file-recursively "bin/Linux_x86_64")
6041 (delete-file-recursively "bin/Linux_x86_64_static")
6042 (delete-file-recursively "source/htslib")
6044 (build-system gnu-build-system)
6046 '(#:tests? #f ;no check target
6047 #:make-flags '("STAR")
6049 (modify-phases %standard-phases
6050 (add-after 'unpack 'enter-source-dir
6051 (lambda _ (chdir "source") #t))
6052 (add-after 'enter-source-dir 'make-reproducible
6054 (substitute* "Makefile"
6055 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6056 (string-append pre "Built with Guix" post)))
6058 ;; See https://github.com/alexdobin/STAR/pull/562
6059 (add-after 'enter-source-dir 'add-missing-header
6061 (substitute* "SoloReadFeature_inputRecords.cpp"
6062 (("#include \"binarySearch2.h\"" h)
6063 (string-append h "\n#include <math.h>")))
6065 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6067 (substitute* "Makefile"
6068 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6070 (substitute* '("BAMfunctions.cpp"
6075 "bamRemoveDuplicates.cpp")
6076 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6077 (string-append "#include <" header ">")))
6078 (substitute* "IncludeDefine.h"
6079 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6080 (string-append "<" header ">")))
6083 (lambda* (#:key outputs #:allow-other-keys)
6084 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6085 (install-file "STAR" bin))
6087 (delete 'configure))))
6091 `(("htslib" ,htslib)
6093 (home-page "https://github.com/alexdobin/STAR")
6094 (synopsis "Universal RNA-seq aligner")
6096 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6097 based on a previously undescribed RNA-seq alignment algorithm that uses
6098 sequential maximum mappable seed search in uncompressed suffix arrays followed
6099 by seed clustering and stitching procedure. In addition to unbiased de novo
6100 detection of canonical junctions, STAR can discover non-canonical splices and
6101 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6103 ;; Only 64-bit systems are supported according to the README.
6104 (supported-systems '("x86_64-linux" "mips64el-linux"))
6105 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6106 (license license:gpl3+)))
6108 (define-public subread
6114 (uri (string-append "mirror://sourceforge/subread/subread-"
6115 version "/subread-" version "-source.tar.gz"))
6118 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6119 (build-system gnu-build-system)
6121 `(#:tests? #f ;no "check" target
6122 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6123 ;; optimizations by default, so we override these flags such that x86_64
6124 ;; flags are only added when the build target is an x86_64 system.
6126 (list (let ((system ,(or (%current-target-system)
6128 (flags '("-ggdb" "-fomit-frame-pointer"
6129 "-ffast-math" "-funroll-loops"
6130 "-fmessage-length=0"
6131 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6133 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6134 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6135 (if (string-prefix? "x86_64" system)
6136 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6137 (string-append "CCFLAGS=" (string-join flags))))
6138 "-f" "Makefile.Linux"
6139 "CC=gcc ${CCFLAGS}")
6141 (modify-phases %standard-phases
6142 (add-after 'unpack 'enter-dir
6143 (lambda _ (chdir "src") #t))
6145 (lambda* (#:key outputs #:allow-other-keys)
6146 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6148 (copy-recursively "../bin" bin))
6150 ;; no "configure" script
6151 (delete 'configure))))
6152 (inputs `(("zlib" ,zlib)))
6153 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6154 (synopsis "Tool kit for processing next-gen sequencing data")
6156 "The subread package contains the following tools: subread aligner, a
6157 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6158 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6159 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6160 against local background noises.")
6161 (license license:gpl3+)))
6163 (define-public stringtie
6169 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6170 "stringtie-" version ".tar.gz"))
6173 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6174 (modules '((guix build utils)))
6177 (delete-file-recursively "samtools-0.1.18")
6179 (build-system gnu-build-system)
6181 `(#:tests? #f ;no test suite
6183 (modify-phases %standard-phases
6184 ;; no configure script
6186 (add-before 'build 'use-system-samtools
6188 (substitute* "Makefile"
6189 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6191 (substitute* '("gclib/GBam.h"
6193 (("#include \"(bam|sam|kstring).h\"" _ header)
6194 (string-append "#include <samtools/" header ".h>")))
6196 (add-after 'unpack 'remove-duplicate-typedef
6198 ;; This typedef conflicts with the typedef in
6199 ;; glibc-2.25/include/bits/types.h
6200 (substitute* "gclib/GThreads.h"
6201 (("typedef long long __intmax_t;") ""))
6204 (lambda* (#:key outputs #:allow-other-keys)
6205 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6206 (install-file "stringtie" bin)
6209 `(("samtools" ,samtools-0.1)
6211 (home-page "http://ccb.jhu.edu/software/stringtie/")
6212 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6214 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6215 alignments into potential transcripts. It uses a novel network flow algorithm
6216 as well as an optional de novo assembly step to assemble and quantitate
6217 full-length transcripts representing multiple splice variants for each gene
6218 locus. Its input can include not only the alignments of raw reads used by
6219 other transcript assemblers, but also alignments of longer sequences that have
6220 been assembled from those reads. To identify differentially expressed genes
6221 between experiments, StringTie's output can be processed either by the
6222 Cuffdiff or Ballgown programs.")
6223 (license license:artistic2.0)))
6225 (define-public taxtastic
6231 (uri (pypi-uri "taxtastic" version))
6234 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6235 (build-system python-build-system)
6237 `(#:python ,python-2
6239 (modify-phases %standard-phases
6241 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6243 `(("python-sqlalchemy" ,python2-sqlalchemy)
6244 ("python-decorator" ,python2-decorator)
6245 ("python-biopython" ,python2-biopython)
6246 ("python-pandas" ,python2-pandas)
6247 ("python-psycopg2" ,python2-psycopg2)
6248 ("python-fastalite" ,python2-fastalite)
6249 ("python-pyyaml" ,python2-pyyaml)
6250 ("python-six" ,python2-six)
6251 ("python-jinja2" ,python2-jinja2)
6252 ("python-dendropy" ,python2-dendropy)))
6253 (home-page "https://github.com/fhcrc/taxtastic")
6254 (synopsis "Tools for taxonomic naming and annotation")
6256 "Taxtastic is software written in python used to build and maintain
6257 reference packages i.e. collections of reference trees, reference alignments,
6258 profiles, and associated taxonomic information.")
6259 (license license:gpl3+)))
6261 (define-public vcftools
6268 "https://github.com/vcftools/vcftools/releases/download/v"
6269 version "/vcftools-" version ".tar.gz"))
6272 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6273 (build-system gnu-build-system)
6275 `(#:tests? #f ; no "check" target
6277 "CFLAGS=-O2" ; override "-m64" flag
6278 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6279 (string-append "MANDIR=" (assoc-ref %outputs "out")
6280 "/share/man/man1"))))
6282 `(("pkg-config" ,pkg-config)))
6286 (home-page "https://vcftools.github.io/")
6287 (synopsis "Tools for working with VCF files")
6289 "VCFtools is a program package designed for working with VCF files, such
6290 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6291 provide easily accessible methods for working with complex genetic variation
6292 data in the form of VCF files.")
6293 ;; The license is declared as LGPLv3 in the README and
6294 ;; at https://vcftools.github.io/license.html
6295 (license license:lgpl3)))
6297 (define-public infernal
6303 (uri (string-append "http://eddylab.org/software/infernal/"
6304 "infernal-" version ".tar.gz"))
6307 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6308 (build-system gnu-build-system)
6310 `(("perl" ,perl))) ; for tests
6311 (home-page "http://eddylab.org/infernal/")
6312 (synopsis "Inference of RNA alignments")
6313 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6314 searching DNA sequence databases for RNA structure and sequence similarities.
6315 It is an implementation of a special case of profile stochastic context-free
6316 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6317 profile, but it scores a combination of sequence consensus and RNA secondary
6318 structure consensus, so in many cases, it is more capable of identifying RNA
6319 homologs that conserve their secondary structure more than their primary
6321 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6322 (supported-systems '("i686-linux" "x86_64-linux"))
6323 (license license:bsd-3)))
6325 (define-public r-centipede
6327 (name "r-centipede")
6331 (uri (string-append "http://download.r-forge.r-project.org/"
6332 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6335 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6336 (build-system r-build-system)
6337 (home-page "http://centipede.uchicago.edu/")
6338 (synopsis "Predict transcription factor binding sites")
6340 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6341 of the genome that are bound by particular transcription factors. It starts
6342 by identifying a set of candidate binding sites, and then aims to classify the
6343 sites according to whether each site is bound or not bound by a transcription
6344 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6345 between two different types of motif instances using as much relevant
6346 information as possible.")
6347 (license (list license:gpl2+ license:gpl3+))))
6349 (define-public r-copynumber
6351 (name "r-copynumber")
6355 (uri (bioconductor-uri "copynumber" version))
6358 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6359 (build-system r-build-system)
6361 `(("r-s4vectors" ,r-s4vectors)
6362 ("r-iranges" ,r-iranges)
6363 ("r-genomicranges" ,r-genomicranges)
6364 ("r-biocgenerics" ,r-biocgenerics)))
6365 (home-page "https://bioconductor.org/packages/copynumber")
6366 (synopsis "Segmentation of single- and multi-track copy number data")
6368 "This package segments single- and multi-track copy number data by a
6369 penalized least squares regression method.")
6370 (license license:artistic2.0)))
6372 (define-public r-geneplotter
6374 (name "r-geneplotter")
6379 (uri (bioconductor-uri "geneplotter" version))
6382 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6383 (build-system r-build-system)
6385 `(("r-annotate" ,r-annotate)
6386 ("r-annotationdbi" ,r-annotationdbi)
6387 ("r-biobase" ,r-biobase)
6388 ("r-biocgenerics" ,r-biocgenerics)
6389 ("r-lattice" ,r-lattice)
6390 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6391 (home-page "https://bioconductor.org/packages/geneplotter")
6392 (synopsis "Graphics functions for genomic data")
6394 "This package provides functions for plotting genomic data.")
6395 (license license:artistic2.0)))
6397 (define-public r-genefilter
6399 (name "r-genefilter")
6404 (uri (bioconductor-uri "genefilter" version))
6407 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6408 (build-system r-build-system)
6410 `(("gfortran" ,gfortran)))
6412 `(("r-annotate" ,r-annotate)
6413 ("r-annotationdbi" ,r-annotationdbi)
6414 ("r-biobase" ,r-biobase)
6415 ("r-s4vectors" ,r-s4vectors)
6416 ("r-survival" ,r-survival)))
6417 (home-page "https://bioconductor.org/packages/genefilter")
6418 (synopsis "Filter genes from high-throughput experiments")
6420 "This package provides basic functions for filtering genes from
6421 high-throughput sequencing experiments.")
6422 (license license:artistic2.0)))
6424 (define-public r-deseq2
6431 (uri (bioconductor-uri "DESeq2" version))
6434 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6435 (properties `((upstream-name . "DESeq2")))
6436 (build-system r-build-system)
6438 `(("r-biobase" ,r-biobase)
6439 ("r-biocgenerics" ,r-biocgenerics)
6440 ("r-biocparallel" ,r-biocparallel)
6441 ("r-genefilter" ,r-genefilter)
6442 ("r-geneplotter" ,r-geneplotter)
6443 ("r-genomicranges" ,r-genomicranges)
6444 ("r-ggplot2" ,r-ggplot2)
6445 ("r-hmisc" ,r-hmisc)
6446 ("r-iranges" ,r-iranges)
6447 ("r-locfit" ,r-locfit)
6449 ("r-rcpparmadillo" ,r-rcpparmadillo)
6450 ("r-s4vectors" ,r-s4vectors)
6451 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6452 (home-page "https://bioconductor.org/packages/DESeq2")
6453 (synopsis "Differential gene expression analysis")
6455 "This package provides functions to estimate variance-mean dependence in
6456 count data from high-throughput nucleotide sequencing assays and test for
6457 differential expression based on a model using the negative binomial
6459 (license license:lgpl3+)))
6461 (define-public r-dexseq
6468 (uri (bioconductor-uri "DEXSeq" version))
6471 "0g5w9bn2nb3m670hkcsnhfvvkza2318z9irlhhwhb3n8rdzlsdym"))))
6472 (properties `((upstream-name . "DEXSeq")))
6473 (build-system r-build-system)
6475 `(("r-annotationdbi" ,r-annotationdbi)
6476 ("r-biobase" ,r-biobase)
6477 ("r-biocgenerics" ,r-biocgenerics)
6478 ("r-biocparallel" ,r-biocparallel)
6479 ("r-biomart" ,r-biomart)
6480 ("r-deseq2" ,r-deseq2)
6481 ("r-genefilter" ,r-genefilter)
6482 ("r-geneplotter" ,r-geneplotter)
6483 ("r-genomicranges" ,r-genomicranges)
6484 ("r-hwriter" ,r-hwriter)
6485 ("r-iranges" ,r-iranges)
6486 ("r-rcolorbrewer" ,r-rcolorbrewer)
6487 ("r-rsamtools" ,r-rsamtools)
6488 ("r-s4vectors" ,r-s4vectors)
6489 ("r-statmod" ,r-statmod)
6490 ("r-stringr" ,r-stringr)
6491 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6492 (home-page "https://bioconductor.org/packages/DEXSeq")
6493 (synopsis "Inference of differential exon usage in RNA-Seq")
6495 "This package is focused on finding differential exon usage using RNA-seq
6496 exon counts between samples with different experimental designs. It provides
6497 functions that allows the user to make the necessary statistical tests based
6498 on a model that uses the negative binomial distribution to estimate the
6499 variance between biological replicates and generalized linear models for
6500 testing. The package also provides functions for the visualization and
6501 exploration of the results.")
6502 (license license:gpl3+)))
6504 (define-public r-annotationforge
6506 (name "r-annotationforge")
6511 (uri (bioconductor-uri "AnnotationForge" version))
6514 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6516 `((upstream-name . "AnnotationForge")))
6517 (build-system r-build-system)
6519 `(("r-annotationdbi" ,r-annotationdbi)
6520 ("r-biobase" ,r-biobase)
6521 ("r-biocgenerics" ,r-biocgenerics)
6523 ("r-rcurl" ,r-rcurl)
6524 ("r-rsqlite" ,r-rsqlite)
6525 ("r-s4vectors" ,r-s4vectors)
6527 (home-page "https://bioconductor.org/packages/AnnotationForge")
6528 (synopsis "Code for building annotation database packages")
6530 "This package provides code for generating Annotation packages and their
6531 databases. Packages produced are intended to be used with AnnotationDbi.")
6532 (license license:artistic2.0)))
6534 (define-public r-rbgl
6541 (uri (bioconductor-uri "RBGL" version))
6544 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6545 (properties `((upstream-name . "RBGL")))
6546 (build-system r-build-system)
6547 (propagated-inputs `(("r-graph" ,r-graph)))
6548 (home-page "https://www.bioconductor.org/packages/RBGL")
6549 (synopsis "Interface to the Boost graph library")
6551 "This package provides a fairly extensive and comprehensive interface to
6552 the graph algorithms contained in the Boost library.")
6553 (license license:artistic2.0)))
6555 (define-public r-gseabase
6562 (uri (bioconductor-uri "GSEABase" version))
6565 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6566 (properties `((upstream-name . "GSEABase")))
6567 (build-system r-build-system)
6569 `(("r-annotate" ,r-annotate)
6570 ("r-annotationdbi" ,r-annotationdbi)
6571 ("r-biobase" ,r-biobase)
6572 ("r-biocgenerics" ,r-biocgenerics)
6573 ("r-graph" ,r-graph)
6575 (home-page "https://bioconductor.org/packages/GSEABase")
6576 (synopsis "Gene set enrichment data structures and methods")
6578 "This package provides classes and methods to support @dfn{Gene Set
6579 Enrichment Analysis} (GSEA).")
6580 (license license:artistic2.0)))
6582 (define-public r-category
6589 (uri (bioconductor-uri "Category" version))
6592 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6593 (properties `((upstream-name . "Category")))
6594 (build-system r-build-system)
6596 `(("r-annotate" ,r-annotate)
6597 ("r-annotationdbi" ,r-annotationdbi)
6598 ("r-biobase" ,r-biobase)
6599 ("r-biocgenerics" ,r-biocgenerics)
6600 ("r-genefilter" ,r-genefilter)
6601 ("r-graph" ,r-graph)
6602 ("r-gseabase" ,r-gseabase)
6603 ("r-matrix" ,r-matrix)
6606 (home-page "https://bioconductor.org/packages/Category")
6607 (synopsis "Category analysis")
6609 "This package provides a collection of tools for performing category
6611 (license license:artistic2.0)))
6613 (define-public r-gostats
6620 (uri (bioconductor-uri "GOstats" version))
6623 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6624 (properties `((upstream-name . "GOstats")))
6625 (build-system r-build-system)
6627 `(("r-annotate" ,r-annotate)
6628 ("r-annotationdbi" ,r-annotationdbi)
6629 ("r-annotationforge" ,r-annotationforge)
6630 ("r-biobase" ,r-biobase)
6631 ("r-category" ,r-category)
6632 ("r-go-db" ,r-go-db)
6633 ("r-graph" ,r-graph)
6634 ("r-rgraphviz" ,r-rgraphviz)
6635 ("r-rbgl" ,r-rbgl)))
6636 (home-page "https://bioconductor.org/packages/GOstats")
6637 (synopsis "Tools for manipulating GO and microarrays")
6639 "This package provides a set of tools for interacting with GO and
6640 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6641 testing and other simple calculations.")
6642 (license license:artistic2.0)))
6644 (define-public r-shortread
6646 (name "r-shortread")
6651 (uri (bioconductor-uri "ShortRead" version))
6654 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6655 (properties `((upstream-name . "ShortRead")))
6656 (build-system r-build-system)
6660 `(("r-biobase" ,r-biobase)
6661 ("r-biocgenerics" ,r-biocgenerics)
6662 ("r-biocparallel" ,r-biocparallel)
6663 ("r-biostrings" ,r-biostrings)
6664 ("r-genomeinfodb" ,r-genomeinfodb)
6665 ("r-genomicalignments" ,r-genomicalignments)
6666 ("r-genomicranges" ,r-genomicranges)
6667 ("r-hwriter" ,r-hwriter)
6668 ("r-iranges" ,r-iranges)
6669 ("r-lattice" ,r-lattice)
6670 ("r-latticeextra" ,r-latticeextra)
6671 ("r-rsamtools" ,r-rsamtools)
6672 ("r-s4vectors" ,r-s4vectors)
6673 ("r-xvector" ,r-xvector)
6674 ("r-zlibbioc" ,r-zlibbioc)))
6675 (home-page "https://bioconductor.org/packages/ShortRead")
6676 (synopsis "FASTQ input and manipulation tools")
6678 "This package implements sampling, iteration, and input of FASTQ files.
6679 It includes functions for filtering and trimming reads, and for generating a
6680 quality assessment report. Data are represented as
6681 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6682 purposes. The package also contains legacy support for early single-end,
6683 ungapped alignment formats.")
6684 (license license:artistic2.0)))
6686 (define-public r-systempiper
6688 (name "r-systempiper")
6693 (uri (bioconductor-uri "systemPipeR" version))
6696 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6697 (properties `((upstream-name . "systemPipeR")))
6698 (build-system r-build-system)
6700 `(("r-annotate" ,r-annotate)
6701 ("r-batchjobs" ,r-batchjobs)
6702 ("r-biocgenerics" ,r-biocgenerics)
6703 ("r-biostrings" ,r-biostrings)
6704 ("r-deseq2" ,r-deseq2)
6705 ("r-edger" ,r-edger)
6706 ("r-genomicfeatures" ,r-genomicfeatures)
6707 ("r-genomicranges" ,r-genomicranges)
6708 ("r-ggplot2" ,r-ggplot2)
6709 ("r-go-db" ,r-go-db)
6710 ("r-gostats" ,r-gostats)
6711 ("r-limma" ,r-limma)
6712 ("r-pheatmap" ,r-pheatmap)
6713 ("r-rjson" ,r-rjson)
6714 ("r-rsamtools" ,r-rsamtools)
6715 ("r-shortread" ,r-shortread)
6716 ("r-summarizedexperiment" ,r-summarizedexperiment)
6717 ("r-variantannotation" ,r-variantannotation)))
6718 (home-page "https://github.com/tgirke/systemPipeR")
6719 (synopsis "Next generation sequencing workflow and reporting environment")
6721 "This R package provides tools for building and running automated
6722 end-to-end analysis workflows for a wide range of @dfn{next generation
6723 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6724 Important features include a uniform workflow interface across different NGS
6725 applications, automated report generation, and support for running both R and
6726 command-line software, such as NGS aligners or peak/variant callers, on local
6727 computers or compute clusters. Efficient handling of complex sample sets and
6728 experimental designs is facilitated by a consistently implemented sample
6729 annotation infrastructure.")
6730 (license license:artistic2.0)))
6732 (define-public r-grohmm
6739 (uri (bioconductor-uri "groHMM" version))
6742 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6743 (properties `((upstream-name . "groHMM")))
6744 (build-system r-build-system)
6746 `(("r-genomeinfodb" ,r-genomeinfodb)
6747 ("r-genomicalignments" ,r-genomicalignments)
6748 ("r-genomicranges" ,r-genomicranges)
6749 ("r-iranges" ,r-iranges)
6751 ("r-rtracklayer" ,r-rtracklayer)
6752 ("r-s4vectors" ,r-s4vectors)))
6753 (home-page "https://github.com/Kraus-Lab/groHMM")
6754 (synopsis "GRO-seq analysis pipeline")
6756 "This package provides a pipeline for the analysis of GRO-seq data.")
6757 (license license:gpl3+)))
6759 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6761 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6765 ;; We cannot use bioconductor-uri here because this tarball is
6766 ;; located under "data/annotation/" instead of "bioc/".
6767 (uri (string-append "https://bioconductor.org/packages/"
6768 "release/data/annotation/src/contrib"
6769 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6773 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6775 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6776 (build-system r-build-system)
6777 ;; As this package provides little more than a very large data file it
6778 ;; doesn't make sense to build substitutes.
6779 (arguments `(#:substitutable? #f))
6781 `(("r-genomicfeatures" ,r-genomicfeatures)))
6783 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6784 (synopsis "Annotation package for human genome in TxDb format")
6786 "This package provides an annotation database of Homo sapiens genome
6787 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6788 track. The database is exposed as a @code{TxDb} object.")
6789 (license license:artistic2.0)))
6791 (define-public r-sparql
6797 (uri (cran-uri "SPARQL" version))
6800 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6801 (properties `((upstream-name . "SPARQL")))
6802 (build-system r-build-system)
6804 `(("r-rcurl" ,r-rcurl)
6806 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6807 (synopsis "SPARQL client for R")
6808 (description "This package provides an interface to use SPARQL to pose
6809 SELECT or UPDATE queries to an end-point.")
6810 ;; The only license indication is found in the DESCRIPTION file,
6811 ;; which states GPL-3. So we cannot assume GPLv3+.
6812 (license license:gpl3)))
6814 (define-public vsearch
6822 (url "https://github.com/torognes/vsearch.git")
6823 (commit (string-append "v" version))))
6824 (file-name (git-file-name name version))
6827 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6828 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6831 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6832 ;; for this in the patch.
6833 (delete-file "src/city.h")
6834 (delete-file "src/citycrc.h")
6835 (delete-file "src/city.cc")
6837 (build-system gnu-build-system)
6841 ("cityhash" ,cityhash)))
6843 `(("autoconf" ,autoconf)
6844 ("automake" ,automake)))
6845 (synopsis "Sequence search tools for metagenomics")
6847 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6848 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6849 masking. The tool takes advantage of parallelism in the form of SIMD
6850 vectorization as well as multiple threads to perform accurate alignments at
6851 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6852 Needleman-Wunsch).")
6853 (home-page "https://github.com/torognes/vsearch")
6854 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6856 (supported-systems '("x86_64-linux"))
6857 ;; Dual licensed; also includes public domain source.
6858 (license (list license:gpl3 license:bsd-2))))
6860 (define-public pardre
6863 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6868 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6872 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6873 (build-system gnu-build-system)
6875 `(#:tests? #f ; no tests included
6877 (modify-phases %standard-phases
6880 (lambda* (#:key outputs #:allow-other-keys)
6881 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6882 (install-file "ParDRe" bin)
6885 `(("openmpi" ,openmpi)
6887 (synopsis "Parallel tool to remove duplicate DNA reads")
6889 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6890 Duplicate reads can be seen as identical or nearly identical sequences with
6891 some mismatches. This tool lets users avoid the analysis of unnecessary
6892 reads, reducing the time of subsequent procedures with the
6893 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6894 in order to exploit the parallel capabilities of multicore clusters. It is
6895 faster than multithreaded counterparts (end of 2015) for the same number of
6896 cores and, thanks to the message-passing technology, it can be executed on
6898 (home-page "https://sourceforge.net/projects/pardre/")
6899 (license license:gpl3+)))
6901 (define-public ruby-bio-kseq
6903 (name "ruby-bio-kseq")
6908 (uri (rubygems-uri "bio-kseq" version))
6911 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6912 (build-system ruby-build-system)
6914 `(#:test-target "spec"))
6916 `(("bundler" ,bundler)
6917 ("ruby-rspec" ,ruby-rspec)
6918 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6921 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6923 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6924 FASTQ parsing code. It provides a fast iterator over sequences and their
6926 (home-page "https://github.com/gusevfe/bio-kseq")
6927 (license license:expat)))
6929 (define-public bio-locus
6936 (uri (rubygems-uri "bio-locus" version))
6939 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6940 (build-system ruby-build-system)
6942 `(("ruby-rspec" ,ruby-rspec)))
6943 (synopsis "Tool for fast querying of genome locations")
6945 "Bio-locus is a tabix-like tool for fast querying of genome
6946 locations. Many file formats in bioinformatics contain records that
6947 start with a chromosome name and a position for a SNP, or a start-end
6948 position for indels. Bio-locus allows users to store this chr+pos or
6949 chr+pos+alt information in a database.")
6950 (home-page "https://github.com/pjotrp/bio-locus")
6951 (license license:expat)))
6953 (define-public bio-blastxmlparser
6955 (name "bio-blastxmlparser")
6959 (uri (rubygems-uri "bio-blastxmlparser" version))
6962 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6963 (build-system ruby-build-system)
6965 `(("ruby-bio-logger" ,ruby-bio-logger)
6966 ("ruby-nokogiri" ,ruby-nokogiri)))
6968 `(("ruby-rspec" ,ruby-rspec)))
6969 (synopsis "Fast big data BLAST XML parser and library")
6971 "Very fast parallel big-data BLAST XML file parser which can be used as
6972 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6973 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6974 (home-page "https://github.com/pjotrp/blastxmlparser")
6975 (license license:expat)))
6977 (define-public bioruby
6984 (uri (rubygems-uri "bio" version))
6987 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
6988 (build-system ruby-build-system)
6990 `(("ruby-libxml" ,ruby-libxml)))
6992 `(("which" ,which))) ; required for test phase
6995 (modify-phases %standard-phases
6996 (add-before 'build 'patch-test-command
6998 (substitute* '("test/functional/bio/test_command.rb")
6999 (("/bin/sh") (which "sh")))
7000 (substitute* '("test/functional/bio/test_command.rb")
7001 (("/bin/ls") (which "ls")))
7002 (substitute* '("test/functional/bio/test_command.rb")
7003 (("which") (which "which")))
7004 (substitute* '("test/functional/bio/test_command.rb",
7005 "test/data/command/echoarg2.sh")
7006 (("/bin/echo") (which "echo")))
7008 (synopsis "Ruby library, shell and utilities for bioinformatics")
7009 (description "BioRuby comes with a comprehensive set of Ruby development
7010 tools and libraries for bioinformatics and molecular biology. BioRuby has
7011 components for sequence analysis, pathway analysis, protein modelling and
7012 phylogenetic analysis; it supports many widely used data formats and provides
7013 easy access to databases, external programs and public web services, including
7014 BLAST, KEGG, GenBank, MEDLINE and GO.")
7015 (home-page "http://bioruby.org/")
7016 ;; Code is released under Ruby license, except for setup
7017 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7018 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7020 (define-public r-acsnminer
7022 (name "r-acsnminer")
7023 (version "0.16.8.25")
7026 (uri (cran-uri "ACSNMineR" version))
7029 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7030 (properties `((upstream-name . "ACSNMineR")))
7031 (build-system r-build-system)
7033 `(("r-ggplot2" ,r-ggplot2)
7034 ("r-gridextra" ,r-gridextra)))
7035 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7036 (synopsis "Gene enrichment analysis")
7038 "This package provides tools to compute and represent gene set enrichment
7039 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7040 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7041 enrichment can be run with hypergeometric test or Fisher exact test, and can
7042 use multiple corrections. Visualization of data can be done either by
7043 barplots or heatmaps.")
7044 (license license:gpl2+)))
7046 (define-public r-biocinstaller
7048 (name "r-biocinstaller")
7052 (uri (bioconductor-uri "BiocInstaller" version))
7055 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7057 `((upstream-name . "BiocInstaller")))
7058 (build-system r-build-system)
7059 (home-page "https://bioconductor.org/packages/BiocInstaller")
7060 (synopsis "Install Bioconductor packages")
7061 (description "This package is used to install and update R packages from
7062 Bioconductor, CRAN, and Github.")
7063 (license license:artistic2.0)))
7065 (define-public r-biocviews
7067 (name "r-biocviews")
7071 (uri (bioconductor-uri "biocViews" version))
7074 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
7076 `((upstream-name . "biocViews")))
7077 (build-system r-build-system)
7079 `(("r-biobase" ,r-biobase)
7080 ("r-graph" ,r-graph)
7082 ("r-rcurl" ,r-rcurl)
7084 ("r-runit" ,r-runit)))
7085 (home-page "https://bioconductor.org/packages/biocViews")
7086 (synopsis "Bioconductor package categorization helper")
7087 (description "The purpose of biocViews is to create HTML pages that
7088 categorize packages in a Bioconductor package repository according to keywords,
7089 also known as views, in a controlled vocabulary.")
7090 (license license:artistic2.0)))
7092 (define-public r-bookdown
7098 (uri (cran-uri "bookdown" version))
7101 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7102 (build-system r-build-system)
7104 `(("r-htmltools" ,r-htmltools)
7105 ("r-knitr" ,r-knitr)
7106 ("r-rmarkdown" ,r-rmarkdown)
7107 ("r-tinytex" ,r-tinytex)
7109 ("r-xfun" ,r-xfun)))
7110 (home-page "https://github.com/rstudio/bookdown")
7111 (synopsis "Authoring books and technical documents with R markdown")
7112 (description "This package provides output formats and utilities for
7113 authoring books and technical documents with R Markdown.")
7114 (license license:gpl3)))
7116 (define-public r-biocstyle
7118 (name "r-biocstyle")
7122 (uri (bioconductor-uri "BiocStyle" version))
7125 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7127 `((upstream-name . "BiocStyle")))
7128 (build-system r-build-system)
7130 `(("r-biocmanager" ,r-biocmanager)
7131 ("r-bookdown" ,r-bookdown)
7132 ("r-knitr" ,r-knitr)
7133 ("r-rmarkdown" ,r-rmarkdown)
7134 ("r-yaml" ,r-yaml)))
7135 (home-page "https://bioconductor.org/packages/BiocStyle")
7136 (synopsis "Bioconductor formatting styles")
7137 (description "This package provides standard formatting styles for
7138 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7140 (license license:artistic2.0)))
7142 (define-public r-bioccheck
7144 (name "r-bioccheck")
7148 (uri (bioconductor-uri "BiocCheck" version))
7151 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7153 `((upstream-name . "BiocCheck")))
7154 (build-system r-build-system)
7157 (modify-phases %standard-phases
7158 ;; This package can be used by calling BiocCheck(<package>) from
7159 ;; within R, or by running R CMD BiocCheck <package>. This phase
7160 ;; makes sure the latter works. For this to work, the BiocCheck
7161 ;; script must be somewhere on the PATH (not the R bin directory).
7162 (add-after 'install 'install-bioccheck-subcommand
7163 (lambda* (#:key outputs #:allow-other-keys)
7164 (let* ((out (assoc-ref outputs "out"))
7165 (dest-dir (string-append out "/bin"))
7167 (string-append out "/site-library/BiocCheck/script/")))
7169 (symlink (string-append script-dir "/checkBadDeps.R")
7170 (string-append dest-dir "/checkBadDeps.R"))
7171 (symlink (string-append script-dir "/BiocCheck")
7172 (string-append dest-dir "/BiocCheck")))
7175 `(("r-codetools" ,r-codetools)
7176 ("r-graph" ,r-graph)
7178 ("r-knitr" ,r-knitr)
7179 ("r-optparse" ,r-optparse)
7180 ("r-biocmanager" ,r-biocmanager)
7181 ("r-biocviews" ,r-biocviews)
7182 ("r-stringdist" ,r-stringdist)))
7183 (home-page "https://bioconductor.org/packages/BiocCheck")
7184 (synopsis "Executes Bioconductor-specific package checks")
7185 (description "This package contains tools to perform additional quality
7186 checks on R packages that are to be submitted to the Bioconductor repository.")
7187 (license license:artistic2.0)))
7189 (define-public r-optparse
7196 (uri (cran-uri "optparse" version))
7199 "04vyb6dhcga30mvghsg1p052jmf69xqxkvh3hzqz7dscyppy76w1"))))
7200 (build-system r-build-system)
7202 `(("r-getopt" ,r-getopt)))
7204 "https://github.com/trevorld/optparse")
7205 (synopsis "Command line option parser")
7207 "This package provides a command line parser inspired by Python's
7208 @code{optparse} library to be used with Rscript to write shebang scripts
7209 that accept short and long options.")
7210 (license license:gpl2+)))
7212 (define-public r-dnacopy
7218 (uri (bioconductor-uri "DNAcopy" version))
7221 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7223 `((upstream-name . "DNAcopy")))
7224 (build-system r-build-system)
7226 `(("gfortran" ,gfortran)))
7227 (home-page "https://bioconductor.org/packages/DNAcopy")
7228 (synopsis "Implementation of a circular binary segmentation algorithm")
7229 (description "This package implements the circular binary segmentation (CBS)
7230 algorithm to segment DNA copy number data and identify genomic regions with
7231 abnormal copy number.")
7232 (license license:gpl2+)))
7234 (define-public r-s4vectors
7236 (name "r-s4vectors")
7240 (uri (bioconductor-uri "S4Vectors" version))
7243 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7245 `((upstream-name . "S4Vectors")))
7246 (build-system r-build-system)
7248 `(("r-biocgenerics" ,r-biocgenerics)))
7249 (home-page "https://bioconductor.org/packages/S4Vectors")
7250 (synopsis "S4 implementation of vectors and lists")
7252 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7253 classes and a set of generic functions that extend the semantic of ordinary
7254 vectors and lists in R. Package developers can easily implement vector-like
7255 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7256 In addition, a few low-level concrete subclasses of general interest (e.g.
7257 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7258 S4Vectors package itself.")
7259 (license license:artistic2.0)))
7261 (define-public r-seqinr
7268 (uri (cran-uri "seqinr" version))
7271 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7272 (build-system r-build-system)
7274 `(("r-ade4" ,r-ade4)
7275 ("r-segmented" ,r-segmented)))
7278 (home-page "http://seqinr.r-forge.r-project.org/")
7279 (synopsis "Biological sequences retrieval and analysis")
7281 "This package provides tools for exploratory data analysis and data
7282 visualization of biological sequence (DNA and protein) data. It also includes
7283 utilities for sequence data management under the ACNUC system.")
7284 (license license:gpl2+)))
7286 (define-public r-iranges
7292 (uri (bioconductor-uri "IRanges" version))
7295 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7297 `((upstream-name . "IRanges")))
7298 (build-system r-build-system)
7300 `(("r-biocgenerics" ,r-biocgenerics)
7301 ("r-s4vectors" ,r-s4vectors)))
7302 (home-page "https://bioconductor.org/packages/IRanges")
7303 (synopsis "Infrastructure for manipulating intervals on sequences")
7305 "This package provides efficient low-level and highly reusable S4 classes
7306 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7307 generally, data that can be organized sequentially (formally defined as
7308 @code{Vector} objects), as well as views on these @code{Vector} objects.
7309 Efficient list-like classes are also provided for storing big collections of
7310 instances of the basic classes. All classes in the package use consistent
7311 naming and share the same rich and consistent \"Vector API\" as much as
7313 (license license:artistic2.0)))
7315 (define-public r-genomeinfodbdata
7317 (name "r-genomeinfodbdata")
7321 ;; We cannot use bioconductor-uri here because this tarball is
7322 ;; located under "data/annotation/" instead of "bioc/".
7323 (uri (string-append "https://bioconductor.org/packages/release/"
7324 "data/annotation/src/contrib/GenomeInfoDbData_"
7328 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7330 `((upstream-name . "GenomeInfoDbData")))
7331 (build-system r-build-system)
7332 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7333 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7334 (description "This package contains data for mapping between NCBI taxonomy
7335 ID and species. It is used by functions in the GenomeInfoDb package.")
7336 (license license:artistic2.0)))
7338 (define-public r-genomeinfodb
7340 (name "r-genomeinfodb")
7344 (uri (bioconductor-uri "GenomeInfoDb" version))
7347 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7349 `((upstream-name . "GenomeInfoDb")))
7350 (build-system r-build-system)
7352 `(("r-biocgenerics" ,r-biocgenerics)
7353 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7354 ("r-iranges" ,r-iranges)
7355 ("r-rcurl" ,r-rcurl)
7356 ("r-s4vectors" ,r-s4vectors)))
7357 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7358 (synopsis "Utilities for manipulating chromosome identifiers")
7360 "This package contains data and functions that define and allow
7361 translation between different chromosome sequence naming conventions (e.g.,
7362 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7363 names in their natural, rather than lexicographic, order.")
7364 (license license:artistic2.0)))
7366 (define-public r-edger
7372 (uri (bioconductor-uri "edgeR" version))
7375 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7376 (properties `((upstream-name . "edgeR")))
7377 (build-system r-build-system)
7379 `(("r-limma" ,r-limma)
7380 ("r-locfit" ,r-locfit)
7382 ("r-statmod" ,r-statmod))) ;for estimateDisp
7383 (home-page "http://bioinf.wehi.edu.au/edgeR")
7384 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7385 (description "This package can do differential expression analysis of
7386 RNA-seq expression profiles with biological replication. It implements a range
7387 of statistical methodology based on the negative binomial distributions,
7388 including empirical Bayes estimation, exact tests, generalized linear models
7389 and quasi-likelihood tests. It be applied to differential signal analysis of
7390 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7392 (license license:gpl2+)))
7394 (define-public r-variantannotation
7396 (name "r-variantannotation")
7400 (uri (bioconductor-uri "VariantAnnotation" version))
7403 "0kxf583cgkdz1shi85r0mpnfxmzi7s5f6srd1czbdl2iibvrm8jn"))))
7405 `((upstream-name . "VariantAnnotation")))
7409 `(("r-annotationdbi" ,r-annotationdbi)
7410 ("r-biobase" ,r-biobase)
7411 ("r-biocgenerics" ,r-biocgenerics)
7412 ("r-biostrings" ,r-biostrings)
7413 ("r-bsgenome" ,r-bsgenome)
7415 ("r-genomeinfodb" ,r-genomeinfodb)
7416 ("r-genomicfeatures" ,r-genomicfeatures)
7417 ("r-genomicranges" ,r-genomicranges)
7418 ("r-iranges" ,r-iranges)
7419 ("r-summarizedexperiment" ,r-summarizedexperiment)
7420 ("r-rsamtools" ,r-rsamtools)
7421 ("r-rtracklayer" ,r-rtracklayer)
7422 ("r-s4vectors" ,r-s4vectors)
7423 ("r-xvector" ,r-xvector)
7424 ("r-zlibbioc" ,r-zlibbioc)))
7425 (build-system r-build-system)
7426 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7427 (synopsis "Package for annotation of genetic variants")
7428 (description "This R package can annotate variants, compute amino acid
7429 coding changes and predict coding outcomes.")
7430 (license license:artistic2.0)))
7432 (define-public r-limma
7438 (uri (bioconductor-uri "limma" version))
7441 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7442 (build-system r-build-system)
7443 (home-page "http://bioinf.wehi.edu.au/limma")
7444 (synopsis "Package for linear models for microarray and RNA-seq data")
7445 (description "This package can be used for the analysis of gene expression
7446 studies, especially the use of linear models for analysing designed experiments
7447 and the assessment of differential expression. The analysis methods apply to
7448 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7449 (license license:gpl2+)))
7451 (define-public r-xvector
7457 (uri (bioconductor-uri "XVector" version))
7460 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7462 `((upstream-name . "XVector")))
7463 (build-system r-build-system)
7466 (modify-phases %standard-phases
7467 (add-after 'unpack 'use-system-zlib
7469 (substitute* "DESCRIPTION"
7470 (("zlibbioc, ") ""))
7471 (substitute* "NAMESPACE"
7472 (("import\\(zlibbioc\\)") ""))
7477 `(("r-biocgenerics" ,r-biocgenerics)
7478 ("r-iranges" ,r-iranges)
7479 ("r-s4vectors" ,r-s4vectors)))
7480 (home-page "https://bioconductor.org/packages/XVector")
7481 (synopsis "Representation and manpulation of external sequences")
7483 "This package provides memory efficient S4 classes for storing sequences
7484 \"externally\" (behind an R external pointer, or on disk).")
7485 (license license:artistic2.0)))
7487 (define-public r-genomicranges
7489 (name "r-genomicranges")
7493 (uri (bioconductor-uri "GenomicRanges" version))
7496 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7498 `((upstream-name . "GenomicRanges")))
7499 (build-system r-build-system)
7501 `(("r-biocgenerics" ,r-biocgenerics)
7502 ("r-genomeinfodb" ,r-genomeinfodb)
7503 ("r-iranges" ,r-iranges)
7504 ("r-s4vectors" ,r-s4vectors)
7505 ("r-xvector" ,r-xvector)))
7506 (home-page "https://bioconductor.org/packages/GenomicRanges")
7507 (synopsis "Representation and manipulation of genomic intervals")
7509 "This package provides tools to efficiently represent and manipulate
7510 genomic annotations and alignments is playing a central role when it comes to
7511 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7512 GenomicRanges package defines general purpose containers for storing and
7513 manipulating genomic intervals and variables defined along a genome.")
7514 (license license:artistic2.0)))
7516 (define-public r-biobase
7522 (uri (bioconductor-uri "Biobase" version))
7525 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7527 `((upstream-name . "Biobase")))
7528 (build-system r-build-system)
7530 `(("r-biocgenerics" ,r-biocgenerics)))
7531 (home-page "https://bioconductor.org/packages/Biobase")
7532 (synopsis "Base functions for Bioconductor")
7534 "This package provides functions that are needed by many other packages
7535 on Bioconductor or which replace R functions.")
7536 (license license:artistic2.0)))
7538 (define-public r-annotationdbi
7540 (name "r-annotationdbi")
7544 (uri (bioconductor-uri "AnnotationDbi" version))
7547 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7549 `((upstream-name . "AnnotationDbi")))
7550 (build-system r-build-system)
7552 `(("r-biobase" ,r-biobase)
7553 ("r-biocgenerics" ,r-biocgenerics)
7555 ("r-iranges" ,r-iranges)
7556 ("r-rsqlite" ,r-rsqlite)
7557 ("r-s4vectors" ,r-s4vectors)))
7558 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7559 (synopsis "Annotation database interface")
7561 "This package provides user interface and database connection code for
7562 annotation data packages using SQLite data storage.")
7563 (license license:artistic2.0)))
7565 (define-public r-biomart
7571 (uri (bioconductor-uri "biomaRt" version))
7574 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7576 `((upstream-name . "biomaRt")))
7577 (build-system r-build-system)
7579 `(("r-annotationdbi" ,r-annotationdbi)
7581 ("r-progress" ,r-progress)
7582 ("r-rcurl" ,r-rcurl)
7583 ("r-stringr" ,r-stringr)
7585 (home-page "https://bioconductor.org/packages/biomaRt")
7586 (synopsis "Interface to BioMart databases")
7588 "biomaRt provides an interface to a growing collection of databases
7589 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7590 package enables retrieval of large amounts of data in a uniform way without
7591 the need to know the underlying database schemas or write complex SQL queries.
7592 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7593 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7594 users direct access to a diverse set of data and enable a wide range of
7595 powerful online queries from gene annotation to database mining.")
7596 (license license:artistic2.0)))
7598 (define-public r-biocparallel
7600 (name "r-biocparallel")
7604 (uri (bioconductor-uri "BiocParallel" version))
7607 "1164dk0fajb2vrkfpcjs11055qf1cs4vvbnq0aqdaaf2p4lyx41l"))))
7609 `((upstream-name . "BiocParallel")))
7610 (build-system r-build-system)
7612 `(("r-futile-logger" ,r-futile-logger)
7615 (home-page "https://bioconductor.org/packages/BiocParallel")
7616 (synopsis "Bioconductor facilities for parallel evaluation")
7618 "This package provides modified versions and novel implementation of
7619 functions for parallel evaluation, tailored to use with Bioconductor
7621 (license (list license:gpl2+ license:gpl3+))))
7623 (define-public r-biostrings
7625 (name "r-biostrings")
7629 (uri (bioconductor-uri "Biostrings" version))
7632 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7634 `((upstream-name . "Biostrings")))
7635 (build-system r-build-system)
7637 `(("r-biocgenerics" ,r-biocgenerics)
7638 ("r-iranges" ,r-iranges)
7639 ("r-s4vectors" ,r-s4vectors)
7640 ("r-xvector" ,r-xvector)))
7641 (home-page "https://bioconductor.org/packages/Biostrings")
7642 (synopsis "String objects and algorithms for biological sequences")
7644 "This package provides memory efficient string containers, string
7645 matching algorithms, and other utilities, for fast manipulation of large
7646 biological sequences or sets of sequences.")
7647 (license license:artistic2.0)))
7649 (define-public r-rsamtools
7651 (name "r-rsamtools")
7655 (uri (bioconductor-uri "Rsamtools" version))
7658 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7660 `((upstream-name . "Rsamtools")))
7661 (build-system r-build-system)
7664 (modify-phases %standard-phases
7665 (add-after 'unpack 'use-system-zlib
7667 (substitute* "DESCRIPTION"
7668 (("zlibbioc, ") ""))
7669 (substitute* "NAMESPACE"
7670 (("import\\(zlibbioc\\)") ""))
7675 `(("r-biocgenerics" ,r-biocgenerics)
7676 ("r-biocparallel" ,r-biocparallel)
7677 ("r-biostrings" ,r-biostrings)
7678 ("r-bitops" ,r-bitops)
7679 ("r-genomeinfodb" ,r-genomeinfodb)
7680 ("r-genomicranges" ,r-genomicranges)
7681 ("r-iranges" ,r-iranges)
7682 ("r-s4vectors" ,r-s4vectors)
7683 ("r-xvector" ,r-xvector)))
7684 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7685 (synopsis "Interface to samtools, bcftools, and tabix")
7687 "This package provides an interface to the 'samtools', 'bcftools', and
7688 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7689 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7691 (license license:expat)))
7693 (define-public r-delayedarray
7695 (name "r-delayedarray")
7699 (uri (bioconductor-uri "DelayedArray" version))
7702 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7704 `((upstream-name . "DelayedArray")))
7705 (build-system r-build-system)
7707 `(("r-biocgenerics" ,r-biocgenerics)
7708 ("r-biocparallel" ,r-biocparallel)
7709 ("r-s4vectors" ,r-s4vectors)
7710 ("r-iranges" ,r-iranges)
7711 ("r-matrixstats" ,r-matrixstats)))
7712 (home-page "https://bioconductor.org/packages/DelayedArray")
7713 (synopsis "Delayed operations on array-like objects")
7715 "Wrapping an array-like object (typically an on-disk object) in a
7716 @code{DelayedArray} object allows one to perform common array operations on it
7717 without loading the object in memory. In order to reduce memory usage and
7718 optimize performance, operations on the object are either delayed or executed
7719 using a block processing mechanism. Note that this also works on in-memory
7720 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7721 @code{Matrix} objects, and ordinary arrays and data frames.")
7722 (license license:artistic2.0)))
7724 (define-public r-summarizedexperiment
7726 (name "r-summarizedexperiment")
7730 (uri (bioconductor-uri "SummarizedExperiment" version))
7733 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7735 `((upstream-name . "SummarizedExperiment")))
7736 (build-system r-build-system)
7738 `(("r-biobase" ,r-biobase)
7739 ("r-biocgenerics" ,r-biocgenerics)
7740 ("r-delayedarray" ,r-delayedarray)
7741 ("r-genomeinfodb" ,r-genomeinfodb)
7742 ("r-genomicranges" ,r-genomicranges)
7743 ("r-iranges" ,r-iranges)
7744 ("r-matrix" ,r-matrix)
7745 ("r-s4vectors" ,r-s4vectors)))
7746 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7747 (synopsis "Container for representing genomic ranges by sample")
7749 "The SummarizedExperiment container contains one or more assays, each
7750 represented by a matrix-like object of numeric or other mode. The rows
7751 typically represent genomic ranges of interest and the columns represent
7753 (license license:artistic2.0)))
7755 (define-public r-genomicalignments
7757 (name "r-genomicalignments")
7761 (uri (bioconductor-uri "GenomicAlignments" version))
7764 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7766 `((upstream-name . "GenomicAlignments")))
7767 (build-system r-build-system)
7769 `(("r-biocgenerics" ,r-biocgenerics)
7770 ("r-biocparallel" ,r-biocparallel)
7771 ("r-biostrings" ,r-biostrings)
7772 ("r-genomeinfodb" ,r-genomeinfodb)
7773 ("r-genomicranges" ,r-genomicranges)
7774 ("r-iranges" ,r-iranges)
7775 ("r-rsamtools" ,r-rsamtools)
7776 ("r-s4vectors" ,r-s4vectors)
7777 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7778 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7779 (synopsis "Representation and manipulation of short genomic alignments")
7781 "This package provides efficient containers for storing and manipulating
7782 short genomic alignments (typically obtained by aligning short reads to a
7783 reference genome). This includes read counting, computing the coverage,
7784 junction detection, and working with the nucleotide content of the
7786 (license license:artistic2.0)))
7788 (define-public r-rtracklayer
7790 (name "r-rtracklayer")
7794 (uri (bioconductor-uri "rtracklayer" version))
7797 "1ycmcxvgvszvjv75hlmg0i6pq8i7r8720vgmfayb905s9l6j82x6"))))
7798 (build-system r-build-system)
7801 (modify-phases %standard-phases
7802 (add-after 'unpack 'use-system-zlib
7804 (substitute* "DESCRIPTION"
7805 ((" zlibbioc,") ""))
7806 (substitute* "NAMESPACE"
7807 (("import\\(zlibbioc\\)") ""))
7810 `(("pkg-config" ,pkg-config)))
7814 `(("r-biocgenerics" ,r-biocgenerics)
7815 ("r-biostrings" ,r-biostrings)
7816 ("r-genomeinfodb" ,r-genomeinfodb)
7817 ("r-genomicalignments" ,r-genomicalignments)
7818 ("r-genomicranges" ,r-genomicranges)
7819 ("r-iranges" ,r-iranges)
7820 ("r-rcurl" ,r-rcurl)
7821 ("r-rsamtools" ,r-rsamtools)
7822 ("r-s4vectors" ,r-s4vectors)
7824 ("r-xvector" ,r-xvector)))
7825 (home-page "https://bioconductor.org/packages/rtracklayer")
7826 (synopsis "R interface to genome browsers and their annotation tracks")
7828 "rtracklayer is an extensible framework for interacting with multiple
7829 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7830 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7831 built-in). The user may export/import tracks to/from the supported browsers,
7832 as well as query and modify the browser state, such as the current viewport.")
7833 (license license:artistic2.0)))
7835 (define-public r-genomicfeatures
7837 (name "r-genomicfeatures")
7841 (uri (bioconductor-uri "GenomicFeatures" version))
7844 "0qs94b0ywrjyc9m1jykrbch3lb07576m508dikvx18vwn304mban"))))
7846 `((upstream-name . "GenomicFeatures")))
7847 (build-system r-build-system)
7849 `(("r-annotationdbi" ,r-annotationdbi)
7850 ("r-biobase" ,r-biobase)
7851 ("r-biocgenerics" ,r-biocgenerics)
7852 ("r-biomart" ,r-biomart)
7853 ("r-biostrings" ,r-biostrings)
7855 ("r-genomeinfodb" ,r-genomeinfodb)
7856 ("r-genomicranges" ,r-genomicranges)
7857 ("r-iranges" ,r-iranges)
7858 ("r-rcurl" ,r-rcurl)
7859 ("r-rsqlite" ,r-rsqlite)
7860 ("r-rtracklayer" ,r-rtracklayer)
7861 ("r-s4vectors" ,r-s4vectors)
7862 ("r-xvector" ,r-xvector)))
7863 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7864 (synopsis "Tools for working with transcript centric annotations")
7866 "This package provides a set of tools and methods for making and
7867 manipulating transcript centric annotations. With these tools the user can
7868 easily download the genomic locations of the transcripts, exons and cds of a
7869 given organism, from either the UCSC Genome Browser or a BioMart
7870 database (more sources will be supported in the future). This information is
7871 then stored in a local database that keeps track of the relationship between
7872 transcripts, exons, cds and genes. Flexible methods are provided for
7873 extracting the desired features in a convenient format.")
7874 (license license:artistic2.0)))
7876 (define-public r-go-db
7882 (uri (string-append "https://www.bioconductor.org/packages/"
7883 "release/data/annotation/src/contrib/GO.db_"
7887 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7889 `((upstream-name . "GO.db")))
7890 (build-system r-build-system)
7892 `(("r-annotationdbi" ,r-annotationdbi)))
7893 (home-page "https://bioconductor.org/packages/GO.db")
7894 (synopsis "Annotation maps describing the entire Gene Ontology")
7896 "The purpose of this GO.db annotation package is to provide detailed
7897 information about the latest version of the Gene Ontologies.")
7898 (license license:artistic2.0)))
7900 (define-public r-topgo
7906 (uri (bioconductor-uri "topGO" version))
7909 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7911 `((upstream-name . "topGO")))
7912 (build-system r-build-system)
7914 `(("r-annotationdbi" ,r-annotationdbi)
7916 ("r-biobase" ,r-biobase)
7917 ("r-biocgenerics" ,r-biocgenerics)
7918 ("r-go-db" ,r-go-db)
7919 ("r-graph" ,r-graph)
7920 ("r-lattice" ,r-lattice)
7921 ("r-matrixstats" ,r-matrixstats)
7922 ("r-sparsem" ,r-sparsem)))
7923 (home-page "https://bioconductor.org/packages/topGO")
7924 (synopsis "Enrichment analysis for gene ontology")
7926 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7927 terms while accounting for the topology of the GO graph. Different test
7928 statistics and different methods for eliminating local similarities and
7929 dependencies between GO terms can be implemented and applied.")
7930 ;; Any version of the LGPL applies.
7931 (license license:lgpl2.1+)))
7933 (define-public r-bsgenome
7939 (uri (bioconductor-uri "BSgenome" version))
7942 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7944 `((upstream-name . "BSgenome")))
7945 (build-system r-build-system)
7947 `(("r-biocgenerics" ,r-biocgenerics)
7948 ("r-biostrings" ,r-biostrings)
7949 ("r-genomeinfodb" ,r-genomeinfodb)
7950 ("r-genomicranges" ,r-genomicranges)
7951 ("r-iranges" ,r-iranges)
7952 ("r-rsamtools" ,r-rsamtools)
7953 ("r-rtracklayer" ,r-rtracklayer)
7954 ("r-s4vectors" ,r-s4vectors)
7955 ("r-xvector" ,r-xvector)))
7956 (home-page "https://bioconductor.org/packages/BSgenome")
7957 (synopsis "Infrastructure for Biostrings-based genome data packages")
7959 "This package provides infrastructure shared by all Biostrings-based
7960 genome data packages and support for efficient SNP representation.")
7961 (license license:artistic2.0)))
7963 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7965 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7969 ;; We cannot use bioconductor-uri here because this tarball is
7970 ;; located under "data/annotation/" instead of "bioc/".
7971 (uri (string-append "https://www.bioconductor.org/packages/"
7972 "release/data/annotation/src/contrib/"
7973 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7977 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7979 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7980 (build-system r-build-system)
7981 ;; As this package provides little more than a very large data file it
7982 ;; doesn't make sense to build substitutes.
7983 (arguments `(#:substitutable? #f))
7985 `(("r-bsgenome" ,r-bsgenome)))
7987 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7988 (synopsis "Full genome sequences for Homo sapiens")
7990 "This package provides full genome sequences for Homo sapiens from
7991 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7992 (license license:artistic2.0)))
7994 (define-public r-impute
8000 (uri (bioconductor-uri "impute" version))
8003 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8005 `(("gfortran" ,gfortran)))
8006 (build-system r-build-system)
8007 (home-page "https://bioconductor.org/packages/impute")
8008 (synopsis "Imputation for microarray data")
8010 "This package provides a function to impute missing gene expression
8011 microarray data, using nearest neighbor averaging.")
8012 (license license:gpl2+)))
8014 (define-public r-seqpattern
8016 (name "r-seqpattern")
8020 (uri (bioconductor-uri "seqPattern" version))
8023 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8025 `((upstream-name . "seqPattern")))
8026 (build-system r-build-system)
8028 `(("r-biostrings" ,r-biostrings)
8029 ("r-genomicranges" ,r-genomicranges)
8030 ("r-iranges" ,r-iranges)
8031 ("r-kernsmooth" ,r-kernsmooth)
8032 ("r-plotrix" ,r-plotrix)))
8033 (home-page "https://bioconductor.org/packages/seqPattern")
8034 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8036 "This package provides tools to visualize oligonucleotide patterns and
8037 sequence motif occurrences across a large set of sequences centred at a common
8038 reference point and sorted by a user defined feature.")
8039 (license license:gpl3+)))
8041 (define-public r-genomation
8043 (name "r-genomation")
8047 (uri (bioconductor-uri "genomation" version))
8050 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8051 (build-system r-build-system)
8053 `(("r-biostrings" ,r-biostrings)
8054 ("r-bsgenome" ,r-bsgenome)
8055 ("r-data-table" ,r-data-table)
8056 ("r-genomeinfodb" ,r-genomeinfodb)
8057 ("r-genomicalignments" ,r-genomicalignments)
8058 ("r-genomicranges" ,r-genomicranges)
8059 ("r-ggplot2" ,r-ggplot2)
8060 ("r-gridbase" ,r-gridbase)
8061 ("r-impute" ,r-impute)
8062 ("r-iranges" ,r-iranges)
8063 ("r-matrixstats" ,r-matrixstats)
8064 ("r-plotrix" ,r-plotrix)
8067 ("r-readr" ,r-readr)
8068 ("r-reshape2" ,r-reshape2)
8069 ("r-rsamtools" ,r-rsamtools)
8070 ("r-rtracklayer" ,r-rtracklayer)
8071 ("r-runit" ,r-runit)
8072 ("r-s4vectors" ,r-s4vectors)
8073 ("r-seqpattern" ,r-seqpattern)))
8074 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8075 (synopsis "Summary, annotation and visualization of genomic data")
8077 "This package provides a package for summary and annotation of genomic
8078 intervals. Users can visualize and quantify genomic intervals over
8079 pre-defined functional regions, such as promoters, exons, introns, etc. The
8080 genomic intervals represent regions with a defined chromosome position, which
8081 may be associated with a score, such as aligned reads from HT-seq experiments,
8082 TF binding sites, methylation scores, etc. The package can use any tabular
8083 genomic feature data as long as it has minimal information on the locations of
8084 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8085 (license license:artistic2.0)))
8087 (define-public r-genomationdata
8089 (name "r-genomationdata")
8093 ;; We cannot use bioconductor-uri here because this tarball is
8094 ;; located under "data/annotation/" instead of "bioc/".
8095 (uri (string-append "https://bioconductor.org/packages/"
8096 "release/data/experiment/src/contrib/"
8097 "genomationData_" version ".tar.gz"))
8100 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8101 (build-system r-build-system)
8102 ;; As this package provides little more than large data files, it doesn't
8103 ;; make sense to build substitutes.
8104 (arguments `(#:substitutable? #f))
8106 `(("r-knitr" ,r-knitr)))
8107 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8108 (synopsis "Experimental data for use with the genomation package")
8110 "This package contains experimental genetic data for use with the
8111 genomation package. Included are Chip Seq, Methylation and Cage data,
8112 downloaded from Encode.")
8113 (license license:gpl3+)))
8115 (define-public r-org-hs-eg-db
8117 (name "r-org-hs-eg-db")
8121 ;; We cannot use bioconductor-uri here because this tarball is
8122 ;; located under "data/annotation/" instead of "bioc/".
8123 (uri (string-append "https://www.bioconductor.org/packages/"
8124 "release/data/annotation/src/contrib/"
8125 "org.Hs.eg.db_" version ".tar.gz"))
8128 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
8130 `((upstream-name . "org.Hs.eg.db")))
8131 (build-system r-build-system)
8133 `(("r-annotationdbi" ,r-annotationdbi)))
8134 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8135 (synopsis "Genome wide annotation for Human")
8137 "This package contains genome-wide annotations for Human, primarily based
8138 on mapping using Entrez Gene identifiers.")
8139 (license license:artistic2.0)))
8141 (define-public r-org-ce-eg-db
8143 (name "r-org-ce-eg-db")
8147 ;; We cannot use bioconductor-uri here because this tarball is
8148 ;; located under "data/annotation/" instead of "bioc/".
8149 (uri (string-append "https://www.bioconductor.org/packages/"
8150 "release/data/annotation/src/contrib/"
8151 "org.Ce.eg.db_" version ".tar.gz"))
8154 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8156 `((upstream-name . "org.Ce.eg.db")))
8157 (build-system r-build-system)
8159 `(("r-annotationdbi" ,r-annotationdbi)))
8160 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8161 (synopsis "Genome wide annotation for Worm")
8163 "This package provides mappings from Entrez gene identifiers to various
8164 annotations for the genome of the model worm Caenorhabditis elegans.")
8165 (license license:artistic2.0)))
8167 (define-public r-org-dm-eg-db
8169 (name "r-org-dm-eg-db")
8173 ;; We cannot use bioconductor-uri here because this tarball is
8174 ;; located under "data/annotation/" instead of "bioc/".
8175 (uri (string-append "https://www.bioconductor.org/packages/"
8176 "release/data/annotation/src/contrib/"
8177 "org.Dm.eg.db_" version ".tar.gz"))
8180 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8182 `((upstream-name . "org.Dm.eg.db")))
8183 (build-system r-build-system)
8185 `(("r-annotationdbi" ,r-annotationdbi)))
8186 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8187 (synopsis "Genome wide annotation for Fly")
8189 "This package provides mappings from Entrez gene identifiers to various
8190 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8191 (license license:artistic2.0)))
8193 (define-public r-org-mm-eg-db
8195 (name "r-org-mm-eg-db")
8199 ;; We cannot use bioconductor-uri here because this tarball is
8200 ;; located under "data/annotation/" instead of "bioc/".
8201 (uri (string-append "https://www.bioconductor.org/packages/"
8202 "release/data/annotation/src/contrib/"
8203 "org.Mm.eg.db_" version ".tar.gz"))
8206 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8208 `((upstream-name . "org.Mm.eg.db")))
8209 (build-system r-build-system)
8211 `(("r-annotationdbi" ,r-annotationdbi)))
8212 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8213 (synopsis "Genome wide annotation for Mouse")
8215 "This package provides mappings from Entrez gene identifiers to various
8216 annotations for the genome of the model mouse Mus musculus.")
8217 (license license:artistic2.0)))
8219 (define-public r-seqlogo
8226 (uri (bioconductor-uri "seqLogo" version))
8229 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8230 (properties `((upstream-name . "seqLogo")))
8231 (build-system r-build-system)
8232 (home-page "https://bioconductor.org/packages/seqLogo")
8233 (synopsis "Sequence logos for DNA sequence alignments")
8235 "seqLogo takes the position weight matrix of a DNA sequence motif and
8236 plots the corresponding sequence logo as introduced by Schneider and
8238 (license license:lgpl2.0+)))
8240 (define-public r-bsgenome-hsapiens-ucsc-hg19
8242 (name "r-bsgenome-hsapiens-ucsc-hg19")
8246 ;; We cannot use bioconductor-uri here because this tarball is
8247 ;; located under "data/annotation/" instead of "bioc/".
8248 (uri (string-append "https://www.bioconductor.org/packages/"
8249 "release/data/annotation/src/contrib/"
8250 "BSgenome.Hsapiens.UCSC.hg19_"
8254 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8256 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8257 (build-system r-build-system)
8258 ;; As this package provides little more than a very large data file it
8259 ;; doesn't make sense to build substitutes.
8260 (arguments `(#:substitutable? #f))
8262 `(("r-bsgenome" ,r-bsgenome)))
8264 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8265 (synopsis "Full genome sequences for Homo sapiens")
8267 "This package provides full genome sequences for Homo sapiens as provided
8268 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8269 (license license:artistic2.0)))
8271 (define-public r-bsgenome-mmusculus-ucsc-mm9
8273 (name "r-bsgenome-mmusculus-ucsc-mm9")
8277 ;; We cannot use bioconductor-uri here because this tarball is
8278 ;; located under "data/annotation/" instead of "bioc/".
8279 (uri (string-append "https://www.bioconductor.org/packages/"
8280 "release/data/annotation/src/contrib/"
8281 "BSgenome.Mmusculus.UCSC.mm9_"
8285 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8287 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8288 (build-system r-build-system)
8289 ;; As this package provides little more than a very large data file it
8290 ;; doesn't make sense to build substitutes.
8291 (arguments `(#:substitutable? #f))
8293 `(("r-bsgenome" ,r-bsgenome)))
8295 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8296 (synopsis "Full genome sequences for Mouse")
8298 "This package provides full genome sequences for Mus musculus (Mouse) as
8299 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8300 (license license:artistic2.0)))
8302 (define-public r-bsgenome-mmusculus-ucsc-mm10
8304 (name "r-bsgenome-mmusculus-ucsc-mm10")
8308 ;; We cannot use bioconductor-uri here because this tarball is
8309 ;; located under "data/annotation/" instead of "bioc/".
8310 (uri (string-append "https://www.bioconductor.org/packages/"
8311 "release/data/annotation/src/contrib/"
8312 "BSgenome.Mmusculus.UCSC.mm10_"
8316 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8318 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8319 (build-system r-build-system)
8320 ;; As this package provides little more than a very large data file it
8321 ;; doesn't make sense to build substitutes.
8322 (arguments `(#:substitutable? #f))
8324 `(("r-bsgenome" ,r-bsgenome)))
8326 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8327 (synopsis "Full genome sequences for Mouse")
8329 "This package provides full genome sequences for Mus
8330 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8331 in Biostrings objects.")
8332 (license license:artistic2.0)))
8334 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8336 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8340 ;; We cannot use bioconductor-uri here because this tarball is
8341 ;; located under "data/annotation/" instead of "bioc/".
8342 (uri (string-append "https://www.bioconductor.org/packages/"
8343 "release/data/annotation/src/contrib/"
8344 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8348 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8350 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8351 (build-system r-build-system)
8352 ;; As this package provides little more than a very large data file it
8353 ;; doesn't make sense to build substitutes.
8354 (arguments `(#:substitutable? #f))
8356 `(("r-bsgenome" ,r-bsgenome)
8357 ("r-genomicfeatures" ,r-genomicfeatures)
8358 ("r-annotationdbi" ,r-annotationdbi)))
8360 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8361 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8363 "This package loads a TxDb object, which is an R interface to
8364 prefabricated databases contained in this package. This package provides
8365 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8366 based on the knownGene track.")
8367 (license license:artistic2.0)))
8369 (define-public r-bsgenome-celegans-ucsc-ce6
8371 (name "r-bsgenome-celegans-ucsc-ce6")
8375 ;; We cannot use bioconductor-uri here because this tarball is
8376 ;; located under "data/annotation/" instead of "bioc/".
8377 (uri (string-append "https://www.bioconductor.org/packages/"
8378 "release/data/annotation/src/contrib/"
8379 "BSgenome.Celegans.UCSC.ce6_"
8383 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8385 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8386 (build-system r-build-system)
8387 ;; As this package provides little more than a very large data file it
8388 ;; doesn't make sense to build substitutes.
8389 (arguments `(#:substitutable? #f))
8391 `(("r-bsgenome" ,r-bsgenome)))
8393 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8394 (synopsis "Full genome sequences for Worm")
8396 "This package provides full genome sequences for Caenorhabditis
8397 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8399 (license license:artistic2.0)))
8401 (define-public r-bsgenome-celegans-ucsc-ce10
8403 (name "r-bsgenome-celegans-ucsc-ce10")
8407 ;; We cannot use bioconductor-uri here because this tarball is
8408 ;; located under "data/annotation/" instead of "bioc/".
8409 (uri (string-append "https://www.bioconductor.org/packages/"
8410 "release/data/annotation/src/contrib/"
8411 "BSgenome.Celegans.UCSC.ce10_"
8415 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8417 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8418 (build-system r-build-system)
8419 ;; As this package provides little more than a very large data file it
8420 ;; doesn't make sense to build substitutes.
8421 (arguments `(#:substitutable? #f))
8423 `(("r-bsgenome" ,r-bsgenome)))
8425 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8426 (synopsis "Full genome sequences for Worm")
8428 "This package provides full genome sequences for Caenorhabditis
8429 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8431 (license license:artistic2.0)))
8433 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8435 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8439 ;; We cannot use bioconductor-uri here because this tarball is
8440 ;; located under "data/annotation/" instead of "bioc/".
8441 (uri (string-append "https://www.bioconductor.org/packages/"
8442 "release/data/annotation/src/contrib/"
8443 "BSgenome.Dmelanogaster.UCSC.dm3_"
8447 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8449 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8450 (build-system r-build-system)
8451 ;; As this package provides little more than a very large data file it
8452 ;; doesn't make sense to build substitutes.
8453 (arguments `(#:substitutable? #f))
8455 `(("r-bsgenome" ,r-bsgenome)))
8457 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8458 (synopsis "Full genome sequences for Fly")
8460 "This package provides full genome sequences for Drosophila
8461 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8462 Biostrings objects.")
8463 (license license:artistic2.0)))
8465 (define-public r-motifrg
8472 (uri (bioconductor-uri "motifRG" version))
8475 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8476 (properties `((upstream-name . "motifRG")))
8477 (build-system r-build-system)
8479 `(("r-biostrings" ,r-biostrings)
8480 ("r-bsgenome" ,r-bsgenome)
8481 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8482 ("r-iranges" ,r-iranges)
8483 ("r-seqlogo" ,r-seqlogo)
8484 ("r-xvector" ,r-xvector)))
8485 (home-page "https://bioconductor.org/packages/motifRG")
8486 (synopsis "Discover motifs in high throughput sequencing data")
8488 "This package provides tools for discriminative motif discovery in high
8489 throughput genetic sequencing data sets using regression methods.")
8490 (license license:artistic2.0)))
8492 (define-public r-qtl
8499 (uri (string-append "mirror://cran/src/contrib/qtl_"
8503 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8504 (build-system r-build-system)
8505 (home-page "http://rqtl.org/")
8506 (synopsis "R package for analyzing QTL experiments in genetics")
8507 (description "R/qtl is an extension library for the R statistics
8508 system. It is used to analyze experimental crosses for identifying
8509 genes contributing to variation in quantitative traits (so-called
8510 quantitative trait loci, QTLs).
8512 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8513 identify genotyping errors, and to perform single-QTL and two-QTL,
8514 two-dimensional genome scans.")
8515 (license license:gpl3)))
8517 (define-public r-zlibbioc
8523 (uri (bioconductor-uri "zlibbioc" version))
8526 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8528 `((upstream-name . "zlibbioc")))
8529 (build-system r-build-system)
8530 (home-page "https://bioconductor.org/packages/zlibbioc")
8531 (synopsis "Provider for zlib-1.2.5 to R packages")
8532 (description "This package uses the source code of zlib-1.2.5 to create
8533 libraries for systems that do not have these available via other means.")
8534 (license license:artistic2.0)))
8536 (define-public r-r4rna
8543 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8547 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8548 (build-system r-build-system)
8550 `(("r-optparse" ,r-optparse)
8551 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8552 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8553 (synopsis "Analysis framework for RNA secondary structure")
8555 "The R4RNA package aims to be a general framework for the analysis of RNA
8556 secondary structure and comparative analysis in R.")
8557 (license license:gpl3+)))
8559 (define-public r-rhtslib
8566 (uri (bioconductor-uri "Rhtslib" version))
8569 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8570 (properties `((upstream-name . "Rhtslib")))
8571 (build-system r-build-system)
8573 `(("r-zlibbioc" ,r-zlibbioc)))
8577 `(("pkg-config" ,pkg-config)))
8578 (home-page "https://github.com/nhayden/Rhtslib")
8579 (synopsis "High-throughput sequencing library as an R package")
8581 "This package provides the HTSlib C library for high-throughput
8582 nucleotide sequence analysis. The package is primarily useful to developers
8583 of other R packages who wish to make use of HTSlib.")
8584 (license license:lgpl2.0+)))
8586 (define-public r-bamsignals
8588 (name "r-bamsignals")
8593 (uri (bioconductor-uri "bamsignals" version))
8596 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8597 (build-system r-build-system)
8599 `(("r-biocgenerics" ,r-biocgenerics)
8600 ("r-genomicranges" ,r-genomicranges)
8601 ("r-iranges" ,r-iranges)
8603 ("r-rhtslib" ,r-rhtslib)
8604 ("r-zlibbioc" ,r-zlibbioc)))
8607 (home-page "https://bioconductor.org/packages/bamsignals")
8608 (synopsis "Extract read count signals from bam files")
8610 "This package allows to efficiently obtain count vectors from indexed bam
8611 files. It counts the number of nucleotide sequence reads in given genomic
8612 ranges and it computes reads profiles and coverage profiles. It also handles
8614 (license license:gpl2+)))
8616 (define-public r-rcas
8622 (uri (bioconductor-uri "RCAS" version))
8625 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8626 (build-system r-build-system)
8628 `(("r-annotationdbi" ,r-annotationdbi)
8629 ("r-biocgenerics" ,r-biocgenerics)
8630 ("r-biomart" ,r-biomart)
8631 ("r-biostrings" ,r-biostrings)
8632 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8633 ("r-cowplot" ,r-cowplot)
8634 ("r-data-table" ,r-data-table)
8637 ("r-genomation" ,r-genomation)
8638 ("r-genomeinfodb" ,r-genomeinfodb)
8639 ("r-genomicfeatures" ,r-genomicfeatures)
8640 ("r-genomicranges" ,r-genomicranges)
8641 ("r-ggplot2" ,r-ggplot2)
8642 ("r-ggseqlogo" ,r-ggseqlogo)
8643 ("r-knitr" ,r-knitr)
8644 ("r-motifrg" ,r-motifrg)
8645 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8646 ("r-pbapply" ,r-pbapply)
8647 ("r-pheatmap" ,r-pheatmap)
8648 ("r-plotly" ,r-plotly)
8649 ("r-plotrix" ,r-plotrix)
8650 ("r-proxy" ,r-proxy)
8651 ("r-rsqlite" ,r-rsqlite)
8652 ("r-rtracklayer" ,r-rtracklayer)
8653 ("r-rmarkdown" ,r-rmarkdown)
8654 ("r-s4vectors" ,r-s4vectors)
8655 ("r-topgo" ,r-topgo)))
8656 (synopsis "RNA-centric annotation system")
8658 "RCAS aims to be a standalone RNA-centric annotation system that provides
8659 intuitive reports and publication-ready graphics. This package provides the R
8660 library implementing most of the pipeline's features.")
8661 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8662 (license license:artistic2.0)))
8664 (define-public rcas-web
8671 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8672 "releases/download/v" version
8673 "/rcas-web-" version ".tar.gz"))
8676 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8677 (build-system gnu-build-system)
8680 (modify-phases %standard-phases
8681 (add-after 'install 'wrap-executable
8682 (lambda* (#:key inputs outputs #:allow-other-keys)
8683 (let* ((out (assoc-ref outputs "out"))
8684 (json (assoc-ref inputs "guile-json"))
8685 (redis (assoc-ref inputs "guile-redis"))
8686 (path (string-append
8687 json "/share/guile/site/2.2:"
8688 redis "/share/guile/site/2.2")))
8689 (wrap-program (string-append out "/bin/rcas-web")
8690 `("GUILE_LOAD_PATH" ":" = (,path))
8691 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8692 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8695 `(("r-minimal" ,r-minimal)
8697 ("guile-next" ,guile-2.2)
8698 ("guile-json" ,guile-json)
8699 ("guile-redis" ,guile-redis)))
8701 `(("pkg-config" ,pkg-config)))
8702 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8703 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8704 (description "This package provides a simple web interface for the
8705 @dfn{RNA-centric annotation system} (RCAS).")
8706 (license license:agpl3+)))
8708 (define-public r-mutationalpatterns
8710 (name "r-mutationalpatterns")
8715 (uri (bioconductor-uri "MutationalPatterns" version))
8718 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8719 (build-system r-build-system)
8721 `(("r-biocgenerics" ,r-biocgenerics)
8722 ("r-biostrings" ,r-biostrings)
8723 ;; These two packages are suggested packages
8724 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8725 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8726 ("r-genomicranges" ,r-genomicranges)
8727 ("r-genomeinfodb" ,r-genomeinfodb)
8728 ("r-ggplot2" ,r-ggplot2)
8729 ("r-iranges" ,r-iranges)
8732 ("r-pracma" ,r-pracma)
8733 ("r-reshape2" ,r-reshape2)
8734 ("r-cowplot" ,r-cowplot)
8735 ("r-ggdendro" ,r-ggdendro)
8736 ("r-s4vectors" ,r-s4vectors)
8737 ("r-summarizedexperiment" ,r-summarizedexperiment)
8738 ("r-variantannotation" ,r-variantannotation)))
8739 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8740 (synopsis "Extract and visualize mutational patterns in genomic data")
8741 (description "This package provides an extensive toolset for the
8742 characterization and visualization of a wide range of mutational patterns
8743 in SNV base substitution data.")
8744 (license license:expat)))
8746 (define-public r-wgcna
8753 (uri (cran-uri "WGCNA" version))
8756 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8757 (properties `((upstream-name . "WGCNA")))
8758 (build-system r-build-system)
8760 `(("r-annotationdbi" ,r-annotationdbi)
8761 ("r-doparallel" ,r-doparallel)
8762 ("r-dynamictreecut" ,r-dynamictreecut)
8763 ("r-fastcluster" ,r-fastcluster)
8764 ("r-foreach" ,r-foreach)
8765 ("r-go-db" ,r-go-db)
8766 ("r-hmisc" ,r-hmisc)
8767 ("r-impute" ,r-impute)
8769 ("r-robust" ,r-robust)
8770 ("r-survival" ,r-survival)
8771 ("r-matrixstats" ,r-matrixstats)
8772 ("r-preprocesscore" ,r-preprocesscore)))
8774 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8775 (synopsis "Weighted correlation network analysis")
8777 "This package provides functions necessary to perform Weighted
8778 Correlation Network Analysis on high-dimensional data. It includes functions
8779 for rudimentary data cleaning, construction and summarization of correlation
8780 networks, module identification and functions for relating both variables and
8781 modules to sample traits. It also includes a number of utility functions for
8782 data manipulation and visualization.")
8783 (license license:gpl2+)))
8785 (define-public r-chipkernels
8786 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8789 (name "r-chipkernels")
8790 (version (string-append "1.1-" revision "." (string-take commit 9)))
8795 (url "https://github.com/ManuSetty/ChIPKernels.git")
8797 (file-name (string-append name "-" version))
8800 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8801 (build-system r-build-system)
8803 `(("r-iranges" ,r-iranges)
8804 ("r-xvector" ,r-xvector)
8805 ("r-biostrings" ,r-biostrings)
8806 ("r-bsgenome" ,r-bsgenome)
8807 ("r-gtools" ,r-gtools)
8808 ("r-genomicranges" ,r-genomicranges)
8809 ("r-sfsmisc" ,r-sfsmisc)
8810 ("r-kernlab" ,r-kernlab)
8811 ("r-s4vectors" ,r-s4vectors)
8812 ("r-biocgenerics" ,r-biocgenerics)))
8813 (home-page "https://github.com/ManuSetty/ChIPKernels")
8814 (synopsis "Build string kernels for DNA Sequence analysis")
8815 (description "ChIPKernels is an R package for building different string
8816 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8817 must be built and this dictionary can be used for determining kernels for DNA
8819 (license license:gpl2+))))
8821 (define-public r-seqgl
8829 (url "https://github.com/ManuSetty/SeqGL.git")
8831 (file-name (git-file-name name version))
8834 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8835 (build-system r-build-system)
8837 `(("r-biostrings" ,r-biostrings)
8838 ("r-chipkernels" ,r-chipkernels)
8839 ("r-genomicranges" ,r-genomicranges)
8840 ("r-spams" ,r-spams)
8841 ("r-wgcna" ,r-wgcna)
8842 ("r-fastcluster" ,r-fastcluster)))
8843 (home-page "https://github.com/ManuSetty/SeqGL")
8844 (synopsis "Group lasso for Dnase/ChIP-seq data")
8845 (description "SeqGL is a group lasso based algorithm to extract
8846 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8847 This package presents a method which uses group lasso to discriminate between
8848 bound and non bound genomic regions to accurately identify transcription
8849 factors bound at the specific regions.")
8850 (license license:gpl2+)))
8852 (define-public r-gkmsvm
8859 (uri (cran-uri "gkmSVM" version))
8862 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8863 (properties `((upstream-name . "gkmSVM")))
8864 (build-system r-build-system)
8866 `(("r-biocgenerics" ,r-biocgenerics)
8867 ("r-biostrings" ,r-biostrings)
8868 ("r-genomeinfodb" ,r-genomeinfodb)
8869 ("r-genomicranges" ,r-genomicranges)
8870 ("r-iranges" ,r-iranges)
8871 ("r-kernlab" ,r-kernlab)
8874 ("r-rtracklayer" ,r-rtracklayer)
8875 ("r-s4vectors" ,r-s4vectors)
8876 ("r-seqinr" ,r-seqinr)))
8877 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8878 (synopsis "Gapped-kmer support vector machine")
8880 "This R package provides tools for training gapped-kmer SVM classifiers
8881 for DNA and protein sequences. This package supports several sequence
8882 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8883 (license license:gpl2+)))
8885 (define-public r-tximport
8891 (uri (bioconductor-uri "tximport" version))
8894 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8895 (build-system r-build-system)
8896 (home-page "https://bioconductor.org/packages/tximport")
8897 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8899 "This package provides tools to import transcript-level abundance,
8900 estimated counts and transcript lengths, and to summarize them into matrices
8901 for use with downstream gene-level analysis packages. Average transcript
8902 length, weighted by sample-specific transcript abundance estimates, is
8903 provided as a matrix which can be used as an offset for different expression
8904 of gene-level counts.")
8905 (license license:gpl2+)))
8907 (define-public r-rhdf5
8913 (uri (bioconductor-uri "rhdf5" version))
8916 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8917 (build-system r-build-system)
8919 `(("r-rhdf5lib" ,r-rhdf5lib)))
8922 (home-page "https://bioconductor.org/packages/rhdf5")
8923 (synopsis "HDF5 interface to R")
8925 "This R/Bioconductor package provides an interface between HDF5 and R.
8926 HDF5's main features are the ability to store and access very large and/or
8927 complex datasets and a wide variety of metadata on mass storage (disk) through
8928 a completely portable file format. The rhdf5 package is thus suited for the
8929 exchange of large and/or complex datasets between R and other software
8930 package, and for letting R applications work on datasets that are larger than
8931 the available RAM.")
8932 (license license:artistic2.0)))
8934 (define-public r-annotationfilter
8936 (name "r-annotationfilter")
8940 (uri (bioconductor-uri "AnnotationFilter" version))
8943 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8945 `((upstream-name . "AnnotationFilter")))
8946 (build-system r-build-system)
8948 `(("r-genomicranges" ,r-genomicranges)
8949 ("r-lazyeval" ,r-lazyeval)))
8950 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8951 (synopsis "Facilities for filtering Bioconductor annotation resources")
8953 "This package provides classes and other infrastructure to implement
8954 filters for manipulating Bioconductor annotation resources. The filters are
8955 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8956 (license license:artistic2.0)))
8958 (define-public emboss
8964 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8965 (version-major+minor version) ".0/"
8966 "EMBOSS-" version ".tar.gz"))
8969 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8970 (build-system gnu-build-system)
8973 (list (string-append "--with-hpdf="
8974 (assoc-ref %build-inputs "libharu")))
8976 (modify-phases %standard-phases
8977 (add-after 'unpack 'fix-checks
8979 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8980 ;; and zlib, but assume that they are all found at the same
8982 (substitute* "configure.in"
8983 (("CHECK_PNGDRIVER")
8984 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8985 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8986 AM_CONDITIONAL(AMPNG, true)"))
8988 (add-after 'fix-checks 'disable-update-check
8990 ;; At build time there is no connection to the Internet, so
8991 ;; looking for updates will not work.
8992 (substitute* "Makefile.am"
8993 (("\\$\\(bindir\\)/embossupdate") ""))
8995 (add-after 'disable-update-check 'autogen
8996 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9002 ("libharu" ,libharu)
9005 `(("autoconf" ,autoconf)
9006 ("automake" ,automake)
9007 ("libtool" ,libtool)
9008 ("pkg-config" ,pkg-config)))
9009 (home-page "http://emboss.sourceforge.net")
9010 (synopsis "Molecular biology analysis suite")
9011 (description "EMBOSS is the \"European Molecular Biology Open Software
9012 Suite\". EMBOSS is an analysis package specially developed for the needs of
9013 the molecular biology (e.g. EMBnet) user community. The software
9014 automatically copes with data in a variety of formats and even allows
9015 transparent retrieval of sequence data from the web. It also provides a
9016 number of libraries for the development of software in the field of molecular
9017 biology. EMBOSS also integrates a range of currently available packages and
9018 tools for sequence analysis into a seamless whole.")
9019 (license license:gpl2+)))
9022 (let ((revision "1")
9023 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9026 ;; The version is 2.13.0 even though no release archives have been
9027 ;; published as yet.
9028 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9032 (url "https://github.com/arq5x/bits.git")
9034 (file-name (string-append name "-" version "-checkout"))
9037 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9038 (build-system gnu-build-system)
9040 `(#:tests? #f ;no tests included
9042 (modify-phases %standard-phases
9044 (add-after 'unpack 'remove-cuda
9046 (substitute* "Makefile"
9048 (("(bits_test_intersections) \\\\" _ match) match))
9051 (lambda* (#:key outputs #:allow-other-keys)
9053 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9058 (home-page "https://github.com/arq5x/bits")
9059 (synopsis "Implementation of binary interval search algorithm")
9060 (description "This package provides an implementation of the
9061 BITS (Binary Interval Search) algorithm, an approach to interval set
9062 intersection. It is especially suited for the comparison of diverse genomic
9063 datasets and the exploration of large datasets of genome
9064 intervals (e.g. genes, sequence alignments).")
9065 (license license:gpl2))))
9067 (define-public piranha
9068 ;; There is no release tarball for the latest version. The latest commit is
9069 ;; older than one year at the time of this writing.
9070 (let ((revision "1")
9071 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9074 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9078 (url "https://github.com/smithlabcode/piranha.git")
9080 (file-name (git-file-name name version))
9083 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9084 (build-system gnu-build-system)
9086 `(#:test-target "test"
9088 (modify-phases %standard-phases
9089 (add-after 'unpack 'copy-smithlab-cpp
9090 (lambda* (#:key inputs #:allow-other-keys)
9091 (for-each (lambda (file)
9092 (install-file file "./src/smithlab_cpp/"))
9093 (find-files (assoc-ref inputs "smithlab-cpp")))
9095 (add-after 'install 'install-to-store
9096 (lambda* (#:key outputs #:allow-other-keys)
9097 (let* ((out (assoc-ref outputs "out"))
9098 (bin (string-append out "/bin")))
9099 (for-each (lambda (file)
9100 (install-file file bin))
9101 (find-files "bin" ".*")))
9104 (list (string-append "--with-bam_tools_headers="
9105 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9106 (string-append "--with-bam_tools_library="
9107 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9109 `(("bamtools" ,bamtools)
9110 ("samtools" ,samtools-0.1)
9113 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9117 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9119 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9122 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9124 `(("python" ,python-2)))
9125 (home-page "https://github.com/smithlabcode/piranha")
9126 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9128 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9129 RIP-seq experiments. It takes input in BED or BAM format and identifies
9130 regions of statistically significant read enrichment. Additional covariates
9131 may optionally be provided to further inform the peak-calling process.")
9132 (license license:gpl3+))))
9140 (uri (pypi-uri "PePr" version))
9143 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9144 (build-system python-build-system)
9146 `(#:python ,python-2 ; python2 only
9147 #:tests? #f)) ; no tests included
9149 `(("python2-numpy" ,python2-numpy)
9150 ("python2-scipy" ,python2-scipy)
9151 ("python2-pysam" ,python2-pysam)))
9152 (home-page "https://github.com/shawnzhangyx/PePr")
9153 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9155 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9156 that is primarily designed for data with biological replicates. It uses a
9157 negative binomial distribution to model the read counts among the samples in
9158 the same group, and look for consistent differences between ChIP and control
9159 group or two ChIP groups run under different conditions.")
9160 (license license:gpl3+)))
9162 (define-public filevercmp
9163 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9166 (version (string-append "0-1." (string-take commit 7)))
9170 (url "https://github.com/ekg/filevercmp.git")
9172 (file-name (git-file-name name commit))
9175 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9176 (build-system gnu-build-system)
9178 `(#:tests? #f ; There are no tests to run.
9180 (modify-phases %standard-phases
9181 (delete 'configure) ; There is no configure phase.
9183 (lambda* (#:key outputs #:allow-other-keys)
9184 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9185 (install-file "filevercmp" bin)
9187 (home-page "https://github.com/ekg/filevercmp")
9188 (synopsis "This program compares version strings")
9189 (description "This program compares version strings. It intends to be a
9190 replacement for strverscmp.")
9191 (license license:gpl3+))))
9193 (define-public multiqc
9200 (uri (pypi-uri "multiqc" version))
9203 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9204 (build-system python-build-system)
9206 `(("python-jinja2" ,python-jinja2)
9207 ("python-simplejson" ,python-simplejson)
9208 ("python-pyyaml" ,python-pyyaml)
9209 ("python-click" ,python-click)
9210 ("python-spectra" ,python-spectra)
9211 ("python-requests" ,python-requests)
9212 ("python-markdown" ,python-markdown)
9213 ("python-lzstring" ,python-lzstring)
9214 ("python-matplotlib" ,python-matplotlib)
9215 ("python-numpy" ,python-numpy)
9216 ;; MultQC checks for the presence of nose at runtime.
9217 ("python-nose" ,python-nose)))
9220 (modify-phases %standard-phases
9221 (add-after 'unpack 'relax-requirements
9223 (substitute* "setup.py"
9224 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9225 ;; than the one in Guix, but should work fine with 2.2.2.
9226 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9227 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9228 (("['\"]matplotlib.*?['\"]")
9231 (home-page "http://multiqc.info")
9232 (synopsis "Aggregate bioinformatics analysis reports")
9234 "MultiQC is a tool to aggregate bioinformatics results across many
9235 samples into a single report. It contains modules for a large number of
9236 common bioinformatics tools.")
9237 (license license:gpl3+)))
9239 (define-public r-chipseq
9246 (uri (bioconductor-uri "chipseq" version))
9249 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9250 (build-system r-build-system)
9252 `(("r-biocgenerics" ,r-biocgenerics)
9253 ("r-genomicranges" ,r-genomicranges)
9254 ("r-iranges" ,r-iranges)
9255 ("r-lattice" ,r-lattice)
9256 ("r-s4vectors" ,r-s4vectors)
9257 ("r-shortread" ,r-shortread)))
9258 (home-page "https://bioconductor.org/packages/chipseq")
9259 (synopsis "Package for analyzing ChIPseq data")
9261 "This package provides tools for processing short read data from ChIPseq
9263 (license license:artistic2.0)))
9265 (define-public r-copyhelper
9267 (name "r-copyhelper")
9272 (uri (string-append "https://bioconductor.org/packages/release/"
9273 "data/experiment/src/contrib/CopyhelpeR_"
9277 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9278 (properties `((upstream-name . "CopyhelpeR")))
9279 (build-system r-build-system)
9280 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9281 (synopsis "Helper files for CopywriteR")
9283 "This package contains the helper files that are required to run the
9284 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9285 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9286 mm10. In addition, it contains a blacklist filter to remove regions that
9287 display copy number variation. Files are stored as GRanges objects from the
9288 GenomicRanges Bioconductor package.")
9289 (license license:gpl2)))
9291 (define-public r-copywriter
9293 (name "r-copywriter")
9298 (uri (bioconductor-uri "CopywriteR" version))
9301 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
9302 (properties `((upstream-name . "CopywriteR")))
9303 (build-system r-build-system)
9305 `(("r-biocparallel" ,r-biocparallel)
9306 ("r-chipseq" ,r-chipseq)
9307 ("r-copyhelper" ,r-copyhelper)
9308 ("r-data-table" ,r-data-table)
9309 ("r-dnacopy" ,r-dnacopy)
9310 ("r-futile-logger" ,r-futile-logger)
9311 ("r-genomeinfodb" ,r-genomeinfodb)
9312 ("r-genomicalignments" ,r-genomicalignments)
9313 ("r-genomicranges" ,r-genomicranges)
9314 ("r-gtools" ,r-gtools)
9315 ("r-iranges" ,r-iranges)
9316 ("r-matrixstats" ,r-matrixstats)
9317 ("r-rsamtools" ,r-rsamtools)
9318 ("r-s4vectors" ,r-s4vectors)))
9319 (home-page "https://github.com/PeeperLab/CopywriteR")
9320 (synopsis "Copy number information from targeted sequencing")
9322 "CopywriteR extracts DNA copy number information from targeted sequencing
9323 by utilizing off-target reads. It allows for extracting uniformly distributed
9324 copy number information, can be used without reference, and can be applied to
9325 sequencing data obtained from various techniques including chromatin
9326 immunoprecipitation and target enrichment on small gene panels. Thereby,
9327 CopywriteR constitutes a widely applicable alternative to available copy
9328 number detection tools.")
9329 (license license:gpl2)))
9331 (define-public r-methylkit
9333 (name "r-methylkit")
9337 (uri (bioconductor-uri "methylKit" version))
9340 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
9341 (properties `((upstream-name . "methylKit")))
9342 (build-system r-build-system)
9344 `(("r-data-table" ,r-data-table)
9345 ("r-emdbook" ,r-emdbook)
9346 ("r-fastseg" ,r-fastseg)
9347 ("r-genomeinfodb" ,r-genomeinfodb)
9348 ("r-genomicranges" ,r-genomicranges)
9349 ("r-gtools" ,r-gtools)
9350 ("r-iranges" ,r-iranges)
9351 ("r-kernsmooth" ,r-kernsmooth)
9352 ("r-limma" ,r-limma)
9353 ("r-mclust" ,r-mclust)
9354 ("r-qvalue" ,r-qvalue)
9355 ("r-r-utils" ,r-r-utils)
9357 ("r-rhtslib" ,r-rhtslib)
9358 ("r-rsamtools" ,r-rsamtools)
9359 ("r-rtracklayer" ,r-rtracklayer)
9360 ("r-s4vectors" ,r-s4vectors)
9361 ("r-zlibbioc" ,r-zlibbioc)))
9364 (home-page "https://github.com/al2na/methylKit")
9366 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9368 "MethylKit is an R package for DNA methylation analysis and annotation
9369 from high-throughput bisulfite sequencing. The package is designed to deal
9370 with sequencing data from @dfn{Reduced representation bisulfite
9371 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9372 genome bisulfite sequencing. It also has functions to analyze base-pair
9373 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9375 (license license:artistic2.0)))
9377 (define-public r-sva
9384 (uri (bioconductor-uri "sva" version))
9387 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
9388 (build-system r-build-system)
9390 `(("r-genefilter" ,r-genefilter)
9392 ("r-biocparallel" ,r-biocparallel)
9393 ("r-matrixstats" ,r-matrixstats)
9394 ("r-limma" ,r-limma)))
9395 (home-page "https://bioconductor.org/packages/sva")
9396 (synopsis "Surrogate variable analysis")
9398 "This package contains functions for removing batch effects and other
9399 unwanted variation in high-throughput experiment. It also contains functions
9400 for identifying and building surrogate variables for high-dimensional data
9401 sets. Surrogate variables are covariates constructed directly from
9402 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9403 imaging data that can be used in subsequent analyses to adjust for unknown,
9404 unmodeled, or latent sources of noise.")
9405 (license license:artistic2.0)))
9407 (define-public r-seqminer
9414 (uri (cran-uri "seqminer" version))
9417 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9418 (build-system r-build-system)
9421 (home-page "http://seqminer.genomic.codes")
9422 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9424 "This package provides tools to integrate nucleotide sequencing
9425 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9426 ;; Any version of the GPL is acceptable
9427 (license (list license:gpl2+ license:gpl3+))))
9429 (define-public r-raremetals2
9431 (name "r-raremetals2")
9436 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9437 "b/b7/RareMETALS2_" version ".tar.gz"))
9440 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9441 (properties `((upstream-name . "RareMETALS2")))
9442 (build-system r-build-system)
9444 `(("r-seqminer" ,r-seqminer)
9445 ("r-mvtnorm" ,r-mvtnorm)
9447 ("r-compquadform" ,r-compquadform)
9448 ("r-getopt" ,r-getopt)))
9449 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9450 (synopsis "Analyze gene-level association tests for binary trait")
9452 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9453 It was designed to meta-analyze gene-level association tests for binary trait.
9454 While rareMETALS offers a near-complete solution for meta-analysis of
9455 gene-level tests for quantitative trait, it does not offer the optimal
9456 solution for binary trait. The package rareMETALS2 offers improved features
9457 for analyzing gene-level association tests in meta-analyses for binary
9459 (license license:gpl3)))
9461 (define-public r-maldiquant
9463 (name "r-maldiquant")
9468 (uri (cran-uri "MALDIquant" version))
9471 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9472 (properties `((upstream-name . "MALDIquant")))
9473 (build-system r-build-system)
9474 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9475 (synopsis "Quantitative analysis of mass spectrometry data")
9477 "This package provides a complete analysis pipeline for matrix-assisted
9478 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9479 two-dimensional mass spectrometry data. In addition to commonly used plotting
9480 and processing methods it includes distinctive features, namely baseline
9481 subtraction methods such as morphological filters (TopHat) or the
9482 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9483 alignment using warping functions, handling of replicated measurements as well
9484 as allowing spectra with different resolutions.")
9485 (license license:gpl3+)))
9487 (define-public r-protgenerics
9489 (name "r-protgenerics")
9494 (uri (bioconductor-uri "ProtGenerics" version))
9497 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9498 (properties `((upstream-name . "ProtGenerics")))
9499 (build-system r-build-system)
9500 (home-page "https://github.com/lgatto/ProtGenerics")
9501 (synopsis "S4 generic functions for proteomics infrastructure")
9503 "This package provides S4 generic functions needed by Bioconductor
9504 proteomics packages.")
9505 (license license:artistic2.0)))
9507 (define-public r-mzr
9514 (uri (bioconductor-uri "mzR" version))
9517 "0mlwg646k49klxrznckzfv54a9mz6irj42fqpaaa0xjm6cw2lwaa"))
9518 (modules '((guix build utils)))
9521 (delete-file-recursively "src/boost")
9523 (properties `((upstream-name . "mzR")))
9524 (build-system r-build-system)
9527 (modify-phases %standard-phases
9528 (add-after 'unpack 'use-system-boost
9530 (substitute* "src/Makevars"
9531 (("\\./boost/libs.*") "")
9532 (("ARCH_OBJS=" line)
9534 "\nARCH_LIBS=-lboost_system -lboost_regex \
9535 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9538 `(("boost" ,boost) ; use this instead of the bundled boost sources
9541 `(("r-biobase" ,r-biobase)
9542 ("r-biocgenerics" ,r-biocgenerics)
9543 ("r-ncdf4" ,r-ncdf4)
9544 ("r-protgenerics" ,r-protgenerics)
9546 ("r-rhdf5lib" ,r-rhdf5lib)
9547 ("r-zlibbioc" ,r-zlibbioc)))
9548 (home-page "https://github.com/sneumann/mzR/")
9549 (synopsis "Parser for mass spectrometry data files")
9551 "The mzR package provides a unified API to the common file formats and
9552 parsers available for mass spectrometry data. It comes with a wrapper for the
9553 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9554 The package contains the original code written by the ISB, and a subset of the
9555 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9556 previously been used in XCMS.")
9557 (license license:artistic2.0)))
9559 (define-public r-affyio
9566 (uri (bioconductor-uri "affyio" version))
9569 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9570 (build-system r-build-system)
9572 `(("r-zlibbioc" ,r-zlibbioc)))
9575 (home-page "https://github.com/bmbolstad/affyio")
9576 (synopsis "Tools for parsing Affymetrix data files")
9578 "This package provides routines for parsing Affymetrix data files based
9579 upon file format information. The primary focus is on accessing the CEL and
9581 (license license:lgpl2.0+)))
9583 (define-public r-affy
9590 (uri (bioconductor-uri "affy" version))
9593 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9594 (build-system r-build-system)
9596 `(("r-affyio" ,r-affyio)
9597 ("r-biobase" ,r-biobase)
9598 ("r-biocgenerics" ,r-biocgenerics)
9599 ("r-biocmanager" ,r-biocmanager)
9600 ("r-preprocesscore" ,r-preprocesscore)
9601 ("r-zlibbioc" ,r-zlibbioc)))
9604 (home-page "https://bioconductor.org/packages/affy")
9605 (synopsis "Methods for affymetrix oligonucleotide arrays")
9607 "This package contains functions for exploratory oligonucleotide array
9609 (license license:lgpl2.0+)))
9611 (define-public r-vsn
9618 (uri (bioconductor-uri "vsn" version))
9621 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9622 (build-system r-build-system)
9624 `(("r-affy" ,r-affy)
9625 ("r-biobase" ,r-biobase)
9626 ("r-ggplot2" ,r-ggplot2)
9627 ("r-lattice" ,r-lattice)
9628 ("r-limma" ,r-limma)))
9629 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9630 (synopsis "Variance stabilization and calibration for microarray data")
9632 "The package implements a method for normalising microarray intensities,
9633 and works for single- and multiple-color arrays. It can also be used for data
9634 from other technologies, as long as they have similar format. The method uses
9635 a robust variant of the maximum-likelihood estimator for an
9636 additive-multiplicative error model and affine calibration. The model
9637 incorporates data calibration step (a.k.a. normalization), a model for the
9638 dependence of the variance on the mean intensity and a variance stabilizing
9639 data transformation. Differences between transformed intensities are
9640 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9641 their variance is independent of the mean, and they are usually more sensitive
9642 and specific in detecting differential transcription.")
9643 (license license:artistic2.0)))
9645 (define-public r-mzid
9652 (uri (bioconductor-uri "mzID" version))
9655 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9656 (properties `((upstream-name . "mzID")))
9657 (build-system r-build-system)
9659 `(("r-doparallel" ,r-doparallel)
9660 ("r-foreach" ,r-foreach)
9661 ("r-iterators" ,r-iterators)
9663 ("r-protgenerics" ,r-protgenerics)
9666 (home-page "https://bioconductor.org/packages/mzID")
9667 (synopsis "Parser for mzIdentML files")
9669 "This package provides a parser for mzIdentML files implemented using the
9670 XML package. The parser tries to be general and able to handle all types of
9671 mzIdentML files with the drawback of having less pretty output than a vendor
9673 (license license:gpl2+)))
9675 (define-public r-pcamethods
9677 (name "r-pcamethods")
9682 (uri (bioconductor-uri "pcaMethods" version))
9685 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9686 (properties `((upstream-name . "pcaMethods")))
9687 (build-system r-build-system)
9689 `(("r-biobase" ,r-biobase)
9690 ("r-biocgenerics" ,r-biocgenerics)
9692 ("r-rcpp" ,r-rcpp)))
9693 (home-page "https://github.com/hredestig/pcamethods")
9694 (synopsis "Collection of PCA methods")
9696 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9697 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9698 for missing value estimation is included for comparison. BPCA, PPCA and
9699 NipalsPCA may be used to perform PCA on incomplete data as well as for
9700 accurate missing value estimation. A set of methods for printing and plotting
9701 the results is also provided. All PCA methods make use of the same data
9702 structure (pcaRes) to provide a common interface to the PCA results.")
9703 (license license:gpl3+)))
9705 (define-public r-msnbase
9712 (uri (bioconductor-uri "MSnbase" version))
9715 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9716 (properties `((upstream-name . "MSnbase")))
9717 (build-system r-build-system)
9719 `(("r-affy" ,r-affy)
9720 ("r-biobase" ,r-biobase)
9721 ("r-biocgenerics" ,r-biocgenerics)
9722 ("r-biocparallel" ,r-biocparallel)
9723 ("r-digest" ,r-digest)
9724 ("r-ggplot2" ,r-ggplot2)
9725 ("r-impute" ,r-impute)
9726 ("r-iranges" ,r-iranges)
9727 ("r-lattice" ,r-lattice)
9728 ("r-maldiquant" ,r-maldiquant)
9732 ("r-pcamethods" ,r-pcamethods)
9734 ("r-preprocesscore" ,r-preprocesscore)
9735 ("r-protgenerics" ,r-protgenerics)
9737 ("r-s4vectors" ,r-s4vectors)
9738 ("r-scales" ,r-scales)
9741 (home-page "https://github.com/lgatto/MSnbase")
9742 (synopsis "Base functions and classes for MS-based proteomics")
9744 "This package provides basic plotting, data manipulation and processing
9745 of mass spectrometry based proteomics data.")
9746 (license license:artistic2.0)))
9748 (define-public r-msnid
9755 (uri (bioconductor-uri "MSnID" version))
9758 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9759 (properties `((upstream-name . "MSnID")))
9760 (build-system r-build-system)
9762 `(("r-biobase" ,r-biobase)
9763 ("r-data-table" ,r-data-table)
9764 ("r-doparallel" ,r-doparallel)
9765 ("r-dplyr" ,r-dplyr)
9766 ("r-foreach" ,r-foreach)
9767 ("r-iterators" ,r-iterators)
9768 ("r-msnbase" ,r-msnbase)
9771 ("r-protgenerics" ,r-protgenerics)
9772 ("r-r-cache" ,r-r-cache)
9774 ("r-reshape2" ,r-reshape2)))
9775 (home-page "https://bioconductor.org/packages/MSnID")
9776 (synopsis "Utilities for LC-MSn proteomics identifications")
9778 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9779 from mzIdentML (leveraging the mzID package) or text files. After collating
9780 the search results from multiple datasets it assesses their identification
9781 quality and optimize filtering criteria to achieve the maximum number of
9782 identifications while not exceeding a specified false discovery rate. It also
9783 contains a number of utilities to explore the MS/MS results and assess missed
9784 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9785 (license license:artistic2.0)))
9787 (define-public r-seurat
9793 (uri (cran-uri "Seurat" version))
9796 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9797 (properties `((upstream-name . "Seurat")))
9798 (build-system r-build-system)
9801 ("r-cluster" ,r-cluster)
9802 ("r-cowplot" ,r-cowplot)
9803 ("r-dosnow" ,r-dosnow)
9804 ("r-dplyr" ,r-dplyr)
9806 ("r-fitdistrplus" ,r-fitdistrplus)
9807 ("r-foreach" ,r-foreach)
9809 ("r-ggplot2" ,r-ggplot2)
9810 ("r-ggridges" ,r-ggridges)
9811 ("r-gplots" ,r-gplots)
9812 ("r-hdf5r" ,r-hdf5r)
9813 ("r-hmisc" ,r-hmisc)
9816 ("r-igraph" ,r-igraph)
9817 ("r-irlba" ,r-irlba)
9819 ("r-lmtest" ,r-lmtest)
9821 ("r-matrix" ,r-matrix)
9822 ("r-metap" ,r-metap)
9823 ("r-mixtools" ,r-mixtools)
9824 ("r-pbapply" ,r-pbapply)
9825 ("r-plotly" ,r-plotly)
9828 ("r-rcolorbrewer" ,r-rcolorbrewer)
9830 ("r-rcppeigen" ,r-rcppeigen)
9831 ("r-rcppprogress" ,r-rcppprogress)
9832 ("r-reshape2" ,r-reshape2)
9833 ("r-reticulate" ,r-reticulate)
9835 ("r-rtsne" ,r-rtsne)
9836 ("r-sdmtools" ,r-sdmtools)
9837 ("r-tidyr" ,r-tidyr)
9838 ("r-tsne" ,r-tsne)))
9839 (home-page "http://www.satijalab.org/seurat")
9840 (synopsis "Seurat is an R toolkit for single cell genomics")
9842 "This package is an R package designed for QC, analysis, and
9843 exploration of single cell RNA-seq data. It easily enables widely-used
9844 analytical techniques, including the identification of highly variable genes,
9845 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9846 algorithms; density clustering, hierarchical clustering, k-means, and the
9847 discovery of differentially expressed genes and markers.")
9848 (license license:gpl3)))
9850 (define-public r-aroma-light
9852 (name "r-aroma-light")
9857 (uri (bioconductor-uri "aroma.light" version))
9860 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9861 (properties `((upstream-name . "aroma.light")))
9862 (build-system r-build-system)
9864 `(("r-matrixstats" ,r-matrixstats)
9865 ("r-r-methodss3" ,r-r-methodss3)
9867 ("r-r-utils" ,r-r-utils)))
9868 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9869 (synopsis "Methods for normalization and visualization of microarray data")
9871 "This package provides methods for microarray analysis that take basic
9872 data types such as matrices and lists of vectors. These methods can be used
9873 standalone, be utilized in other packages, or be wrapped up in higher-level
9875 (license license:gpl2+)))
9877 (define-public r-deseq
9884 (uri (bioconductor-uri "DESeq" version))
9887 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9888 (properties `((upstream-name . "DESeq")))
9889 (build-system r-build-system)
9891 `(("r-biobase" ,r-biobase)
9892 ("r-biocgenerics" ,r-biocgenerics)
9893 ("r-genefilter" ,r-genefilter)
9894 ("r-geneplotter" ,r-geneplotter)
9895 ("r-lattice" ,r-lattice)
9896 ("r-locfit" ,r-locfit)
9898 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9899 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9900 (synopsis "Differential gene expression analysis")
9902 "This package provides tools for estimating variance-mean dependence in
9903 count data from high-throughput genetic sequencing assays and for testing for
9904 differential expression based on a model using the negative binomial
9906 (license license:gpl3+)))
9908 (define-public r-edaseq
9915 (uri (bioconductor-uri "EDASeq" version))
9918 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9919 (properties `((upstream-name . "EDASeq")))
9920 (build-system r-build-system)
9922 `(("r-annotationdbi" ,r-annotationdbi)
9923 ("r-aroma-light" ,r-aroma-light)
9924 ("r-biobase" ,r-biobase)
9925 ("r-biocgenerics" ,r-biocgenerics)
9926 ("r-biocmanager" ,r-biocmanager)
9927 ("r-biomart" ,r-biomart)
9928 ("r-biostrings" ,r-biostrings)
9929 ("r-deseq" ,r-deseq)
9930 ("r-genomicfeatures" ,r-genomicfeatures)
9931 ("r-genomicranges" ,r-genomicranges)
9932 ("r-iranges" ,r-iranges)
9933 ("r-rsamtools" ,r-rsamtools)
9934 ("r-shortread" ,r-shortread)))
9935 (home-page "https://github.com/drisso/EDASeq")
9936 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9938 "This package provides support for numerical and graphical summaries of
9939 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9940 adjust for GC-content effect (or other gene-level effects) on read counts:
9941 loess robust local regression, global-scaling, and full-quantile
9942 normalization. Between-lane normalization procedures to adjust for
9943 distributional differences between lanes (e.g., sequencing depth):
9944 global-scaling and full-quantile normalization.")
9945 (license license:artistic2.0)))
9947 (define-public r-interactivedisplaybase
9949 (name "r-interactivedisplaybase")
9954 (uri (bioconductor-uri "interactiveDisplayBase" version))
9957 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9959 `((upstream-name . "interactiveDisplayBase")))
9960 (build-system r-build-system)
9962 `(("r-biocgenerics" ,r-biocgenerics)
9963 ("r-shiny" ,r-shiny)))
9964 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9965 (synopsis "Base package for web displays of Bioconductor objects")
9967 "This package contains the basic methods needed to generate interactive
9968 Shiny-based display methods for Bioconductor objects.")
9969 (license license:artistic2.0)))
9971 (define-public r-annotationhub
9973 (name "r-annotationhub")
9978 (uri (bioconductor-uri "AnnotationHub" version))
9981 "17fgrvcnbii9siv5rq5j09bxhqffx47f6jf10418qvr7hh61ic1g"))))
9982 (properties `((upstream-name . "AnnotationHub")))
9983 (build-system r-build-system)
9985 `(("r-annotationdbi" ,r-annotationdbi)
9986 ("r-biocgenerics" ,r-biocgenerics)
9987 ("r-biocmanager" ,r-biocmanager)
9990 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9991 ("r-rsqlite" ,r-rsqlite)
9992 ("r-s4vectors" ,r-s4vectors)
9993 ("r-yaml" ,r-yaml)))
9994 (home-page "https://bioconductor.org/packages/AnnotationHub")
9995 (synopsis "Client to access AnnotationHub resources")
9997 "This package provides a client for the Bioconductor AnnotationHub web
9998 resource. The AnnotationHub web resource provides a central location where
9999 genomic files (e.g. VCF, bed, wig) and other resources from standard
10000 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10001 metadata about each resource, e.g., a textual description, tags, and date of
10002 modification. The client creates and manages a local cache of files retrieved
10003 by the user, helping with quick and reproducible access.")
10004 (license license:artistic2.0)))
10006 (define-public r-fastseg
10013 (uri (bioconductor-uri "fastseg" version))
10016 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10017 (build-system r-build-system)
10019 `(("r-biobase" ,r-biobase)
10020 ("r-biocgenerics" ,r-biocgenerics)
10021 ("r-genomicranges" ,r-genomicranges)
10022 ("r-iranges" ,r-iranges)
10023 ("r-s4vectors" ,r-s4vectors)))
10024 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10025 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10027 "Fastseg implements a very fast and efficient segmentation algorithm.
10028 It can segment data from DNA microarrays and data from next generation
10029 sequencing for example to detect copy number segments. Further it can segment
10030 data from RNA microarrays like tiling arrays to identify transcripts. Most
10031 generally, it can segment data given as a matrix or as a vector. Various data
10032 formats can be used as input to fastseg like expression set objects for
10033 microarrays or GRanges for sequencing data.")
10034 (license license:lgpl2.0+)))
10036 (define-public r-keggrest
10038 (name "r-keggrest")
10043 (uri (bioconductor-uri "KEGGREST" version))
10046 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10047 (properties `((upstream-name . "KEGGREST")))
10048 (build-system r-build-system)
10050 `(("r-biostrings" ,r-biostrings)
10053 (home-page "https://bioconductor.org/packages/KEGGREST")
10054 (synopsis "Client-side REST access to KEGG")
10056 "This package provides a package that provides a client interface to the
10057 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10058 (license license:artistic2.0)))
10060 (define-public r-gage
10067 (uri (bioconductor-uri "gage" version))
10070 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
10071 (build-system r-build-system)
10073 `(("r-annotationdbi" ,r-annotationdbi)
10074 ("r-graph" ,r-graph)
10075 ("r-keggrest" ,r-keggrest)))
10076 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10077 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10079 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10080 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10081 data attributes including sample sizes, experimental designs, assay platforms,
10082 and other types of heterogeneity. The gage package provides functions for
10083 basic GAGE analysis, result processing and presentation. In addition, it
10084 provides demo microarray data and commonly used gene set data based on KEGG
10085 pathways and GO terms. These funtions and data are also useful for gene set
10086 analysis using other methods.")
10087 (license license:gpl2+)))
10089 (define-public r-genomicfiles
10091 (name "r-genomicfiles")
10096 (uri (bioconductor-uri "GenomicFiles" version))
10099 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10100 (properties `((upstream-name . "GenomicFiles")))
10101 (build-system r-build-system)
10103 `(("r-biocgenerics" ,r-biocgenerics)
10104 ("r-biocparallel" ,r-biocparallel)
10105 ("r-genomeinfodb" ,r-genomeinfodb)
10106 ("r-genomicalignments" ,r-genomicalignments)
10107 ("r-genomicranges" ,r-genomicranges)
10108 ("r-iranges" ,r-iranges)
10109 ("r-rsamtools" ,r-rsamtools)
10110 ("r-rtracklayer" ,r-rtracklayer)
10111 ("r-s4vectors" ,r-s4vectors)
10112 ("r-summarizedexperiment" ,r-summarizedexperiment)
10113 ("r-variantannotation" ,r-variantannotation)))
10114 (home-page "https://bioconductor.org/packages/GenomicFiles")
10115 (synopsis "Distributed computing by file or by range")
10117 "This package provides infrastructure for parallel computations
10118 distributed by file or by range. User defined mapper and reducer functions
10119 provide added flexibility for data combination and manipulation.")
10120 (license license:artistic2.0)))
10122 (define-public r-complexheatmap
10124 (name "r-complexheatmap")
10129 (uri (bioconductor-uri "ComplexHeatmap" version))
10132 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10134 `((upstream-name . "ComplexHeatmap")))
10135 (build-system r-build-system)
10137 `(("r-circlize" ,r-circlize)
10138 ("r-colorspace" ,r-colorspace)
10139 ("r-getoptlong" ,r-getoptlong)
10140 ("r-globaloptions" ,r-globaloptions)
10141 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10143 "https://github.com/jokergoo/ComplexHeatmap")
10144 (synopsis "Making Complex Heatmaps")
10146 "Complex heatmaps are efficient to visualize associations between
10147 different sources of data sets and reveal potential structures. This package
10148 provides a highly flexible way to arrange multiple heatmaps and supports
10149 self-defined annotation graphics.")
10150 (license license:gpl2+)))
10152 (define-public r-dirichletmultinomial
10154 (name "r-dirichletmultinomial")
10159 (uri (bioconductor-uri "DirichletMultinomial" version))
10162 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
10164 `((upstream-name . "DirichletMultinomial")))
10165 (build-system r-build-system)
10169 `(("r-biocgenerics" ,r-biocgenerics)
10170 ("r-iranges" ,r-iranges)
10171 ("r-s4vectors" ,r-s4vectors)))
10172 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10173 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10175 "Dirichlet-multinomial mixture models can be used to describe variability
10176 in microbial metagenomic data. This package is an interface to code
10177 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10179 (license license:lgpl3)))
10181 (define-public r-ensembldb
10183 (name "r-ensembldb")
10188 (uri (bioconductor-uri "ensembldb" version))
10191 "0kzdsfk6mdwlp57sw4j2cf7lx5nc67v5j0xr3iag9kzmgikaq1lb"))))
10192 (build-system r-build-system)
10194 `(("r-annotationdbi" ,r-annotationdbi)
10195 ("r-annotationfilter" ,r-annotationfilter)
10196 ("r-biobase" ,r-biobase)
10197 ("r-biocgenerics" ,r-biocgenerics)
10198 ("r-biostrings" ,r-biostrings)
10201 ("r-genomeinfodb" ,r-genomeinfodb)
10202 ("r-genomicfeatures" ,r-genomicfeatures)
10203 ("r-genomicranges" ,r-genomicranges)
10204 ("r-iranges" ,r-iranges)
10205 ("r-protgenerics" ,r-protgenerics)
10206 ("r-rsamtools" ,r-rsamtools)
10207 ("r-rsqlite" ,r-rsqlite)
10208 ("r-rtracklayer" ,r-rtracklayer)
10209 ("r-s4vectors" ,r-s4vectors)))
10210 (home-page "https://github.com/jotsetung/ensembldb")
10211 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10213 "The package provides functions to create and use transcript-centric
10214 annotation databases/packages. The annotation for the databases are directly
10215 fetched from Ensembl using their Perl API. The functionality and data is
10216 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10217 but, in addition to retrieve all gene/transcript models and annotations from
10218 the database, the @code{ensembldb} package also provides a filter framework
10219 allowing to retrieve annotations for specific entries like genes encoded on a
10220 chromosome region or transcript models of lincRNA genes.")
10221 ;; No version specified
10222 (license license:lgpl3+)))
10224 (define-public r-organismdbi
10226 (name "r-organismdbi")
10231 (uri (bioconductor-uri "OrganismDbi" version))
10234 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10235 (properties `((upstream-name . "OrganismDbi")))
10236 (build-system r-build-system)
10238 `(("r-annotationdbi" ,r-annotationdbi)
10239 ("r-biobase" ,r-biobase)
10240 ("r-biocgenerics" ,r-biocgenerics)
10241 ("r-biocmanager" ,r-biocmanager)
10243 ("r-genomicfeatures" ,r-genomicfeatures)
10244 ("r-genomicranges" ,r-genomicranges)
10245 ("r-graph" ,r-graph)
10246 ("r-iranges" ,r-iranges)
10248 ("r-s4vectors" ,r-s4vectors)))
10249 (home-page "https://bioconductor.org/packages/OrganismDbi")
10250 (synopsis "Software to enable the smooth interfacing of database packages")
10251 (description "The package enables a simple unified interface to several
10252 annotation packages each of which has its own schema by taking advantage of
10253 the fact that each of these packages implements a select methods.")
10254 (license license:artistic2.0)))
10256 (define-public r-biovizbase
10258 (name "r-biovizbase")
10263 (uri (bioconductor-uri "biovizBase" version))
10266 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
10267 (properties `((upstream-name . "biovizBase")))
10268 (build-system r-build-system)
10270 `(("r-annotationdbi" ,r-annotationdbi)
10271 ("r-annotationfilter" ,r-annotationfilter)
10272 ("r-biocgenerics" ,r-biocgenerics)
10273 ("r-biostrings" ,r-biostrings)
10274 ("r-dichromat" ,r-dichromat)
10275 ("r-ensembldb" ,r-ensembldb)
10276 ("r-genomeinfodb" ,r-genomeinfodb)
10277 ("r-genomicalignments" ,r-genomicalignments)
10278 ("r-genomicfeatures" ,r-genomicfeatures)
10279 ("r-genomicranges" ,r-genomicranges)
10280 ("r-hmisc" ,r-hmisc)
10281 ("r-iranges" ,r-iranges)
10282 ("r-rcolorbrewer" ,r-rcolorbrewer)
10283 ("r-rlang" ,r-rlang)
10284 ("r-rsamtools" ,r-rsamtools)
10285 ("r-s4vectors" ,r-s4vectors)
10286 ("r-scales" ,r-scales)
10287 ("r-summarizedexperiment" ,r-summarizedexperiment)
10288 ("r-variantannotation" ,r-variantannotation)))
10289 (home-page "https://bioconductor.org/packages/biovizBase")
10290 (synopsis "Basic graphic utilities for visualization of genomic data")
10292 "The biovizBase package is designed to provide a set of utilities, color
10293 schemes and conventions for genomic data. It serves as the base for various
10294 high-level packages for biological data visualization. This saves development
10295 effort and encourages consistency.")
10296 (license license:artistic2.0)))
10298 (define-public r-ggbio
10305 (uri (bioconductor-uri "ggbio" version))
10308 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10309 (build-system r-build-system)
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-annotationfilter" ,r-annotationfilter)
10313 ("r-biobase" ,r-biobase)
10314 ("r-biocgenerics" ,r-biocgenerics)
10315 ("r-biostrings" ,r-biostrings)
10316 ("r-biovizbase" ,r-biovizbase)
10317 ("r-bsgenome" ,r-bsgenome)
10318 ("r-ensembldb" ,r-ensembldb)
10319 ("r-genomeinfodb" ,r-genomeinfodb)
10320 ("r-genomicalignments" ,r-genomicalignments)
10321 ("r-genomicfeatures" ,r-genomicfeatures)
10322 ("r-genomicranges" ,r-genomicranges)
10323 ("r-ggally" ,r-ggally)
10324 ("r-ggplot2" ,r-ggplot2)
10325 ("r-gridextra" ,r-gridextra)
10326 ("r-gtable" ,r-gtable)
10327 ("r-hmisc" ,r-hmisc)
10328 ("r-iranges" ,r-iranges)
10329 ("r-organismdbi" ,r-organismdbi)
10330 ("r-reshape2" ,r-reshape2)
10331 ("r-rlang" ,r-rlang)
10332 ("r-rsamtools" ,r-rsamtools)
10333 ("r-rtracklayer" ,r-rtracklayer)
10334 ("r-s4vectors" ,r-s4vectors)
10335 ("r-scales" ,r-scales)
10336 ("r-summarizedexperiment" ,r-summarizedexperiment)
10337 ("r-variantannotation" ,r-variantannotation)))
10338 (home-page "http://www.tengfei.name/ggbio/")
10339 (synopsis "Visualization tools for genomic data")
10341 "The ggbio package extends and specializes the grammar of graphics for
10342 biological data. The graphics are designed to answer common scientific
10343 questions, in particular those often asked of high throughput genomics data.
10344 All core Bioconductor data structures are supported, where appropriate. The
10345 package supports detailed views of particular genomic regions, as well as
10346 genome-wide overviews. Supported overviews include ideograms and grand linear
10347 views. High-level plots include sequence fragment length, edge-linked
10348 interval to data view, mismatch pileup, and several splicing summaries.")
10349 (license license:artistic2.0)))
10351 (define-public r-gprofiler
10353 (name "r-gprofiler")
10358 (uri (cran-uri "gProfileR" version))
10361 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10362 (properties `((upstream-name . "gProfileR")))
10363 (build-system r-build-system)
10365 `(("r-plyr" ,r-plyr)
10366 ("r-rcurl" ,r-rcurl)))
10367 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10368 (synopsis "Interface to the g:Profiler toolkit")
10370 "This package provides tools for functional enrichment analysis,
10371 gene identifier conversion and mapping homologous genes across related
10372 organisms via the @code{g:Profiler} toolkit.")
10373 (license license:gpl2+)))
10375 (define-public r-gqtlbase
10377 (name "r-gqtlbase")
10382 (uri (bioconductor-uri "gQTLBase" version))
10385 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10386 (properties `((upstream-name . "gQTLBase")))
10387 (build-system r-build-system)
10389 `(("r-batchjobs" ,r-batchjobs)
10390 ("r-bbmisc" ,r-bbmisc)
10391 ("r-biocgenerics" ,r-biocgenerics)
10393 ("r-doparallel" ,r-doparallel)
10395 ("r-ffbase" ,r-ffbase)
10396 ("r-foreach" ,r-foreach)
10397 ("r-genomicfiles" ,r-genomicfiles)
10398 ("r-genomicranges" ,r-genomicranges)
10399 ("r-rtracklayer" ,r-rtracklayer)
10400 ("r-s4vectors" ,r-s4vectors)
10401 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10402 (home-page "https://bioconductor.org/packages/gQTLBase")
10403 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10405 "The purpose of this package is to simplify the storage and interrogation
10406 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10408 (license license:artistic2.0)))
10410 (define-public r-snpstats
10412 (name "r-snpstats")
10417 (uri (bioconductor-uri "snpStats" version))
10420 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10421 (properties `((upstream-name . "snpStats")))
10422 (build-system r-build-system)
10423 (inputs `(("zlib" ,zlib)))
10425 `(("r-biocgenerics" ,r-biocgenerics)
10426 ("r-matrix" ,r-matrix)
10427 ("r-survival" ,r-survival)
10428 ("r-zlibbioc" ,r-zlibbioc)))
10429 (home-page "https://bioconductor.org/packages/snpStats")
10430 (synopsis "Methods for SNP association studies")
10432 "This package provides classes and statistical methods for large
10433 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10434 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10435 (license license:gpl3)))
10437 (define-public r-homo-sapiens
10439 (name "r-homo-sapiens")
10443 ;; We cannot use bioconductor-uri here because this tarball is
10444 ;; located under "data/annotation/" instead of "bioc/".
10445 (uri (string-append "http://www.bioconductor.org/packages/"
10446 "release/data/annotation/src/contrib/"
10448 version ".tar.gz"))
10451 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10453 `((upstream-name . "Homo.sapiens")))
10454 (build-system r-build-system)
10456 `(("r-genomicfeatures" ,r-genomicfeatures)
10457 ("r-go-db" ,r-go-db)
10458 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10459 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10460 ("r-organismdbi" ,r-organismdbi)
10461 ("r-annotationdbi" ,r-annotationdbi)))
10462 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10463 (synopsis "Annotation package for the Homo.sapiens object")
10465 "This package contains the Homo.sapiens object to access data from
10466 several related annotation packages.")
10467 (license license:artistic2.0)))
10469 (define-public r-erma
10476 (uri (bioconductor-uri "erma" version))
10479 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10480 (build-system r-build-system)
10482 `(("r-annotationdbi" ,r-annotationdbi)
10483 ("r-biobase" ,r-biobase)
10484 ("r-biocgenerics" ,r-biocgenerics)
10485 ("r-biocparallel" ,r-biocparallel)
10486 ("r-genomeinfodb" ,r-genomeinfodb)
10487 ("r-genomicfiles" ,r-genomicfiles)
10488 ("r-genomicranges" ,r-genomicranges)
10489 ("r-ggplot2" ,r-ggplot2)
10490 ("r-homo-sapiens" ,r-homo-sapiens)
10491 ("r-iranges" ,r-iranges)
10492 ("r-rtracklayer" ,r-rtracklayer)
10493 ("r-s4vectors" ,r-s4vectors)
10494 ("r-shiny" ,r-shiny)
10495 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10496 (home-page "https://bioconductor.org/packages/erma")
10497 (synopsis "Epigenomic road map adventures")
10499 "The epigenomics road map describes locations of epigenetic marks in DNA
10500 from a variety of cell types. Of interest are locations of histone
10501 modifications, sites of DNA methylation, and regions of accessible chromatin.
10502 This package presents a selection of elements of the road map including
10503 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10504 by Ernst and Kellis.")
10505 (license license:artistic2.0)))
10507 (define-public r-ldblock
10514 (uri (bioconductor-uri "ldblock" version))
10517 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10518 (build-system r-build-system)
10520 `(("r-biocgenerics" ,r-biocgenerics)
10522 ("r-genomeinfodb" ,r-genomeinfodb)
10523 ("r-genomicfiles" ,r-genomicfiles)
10524 ("r-go-db" ,r-go-db)
10525 ("r-homo-sapiens" ,r-homo-sapiens)
10526 ("r-matrix" ,r-matrix)
10527 ("r-rsamtools" ,r-rsamtools)
10528 ("r-snpstats" ,r-snpstats)
10529 ("r-variantannotation" ,r-variantannotation)))
10530 (home-page "https://bioconductor.org/packages/ldblock")
10531 (synopsis "Data structures for linkage disequilibrium measures in populations")
10533 "This package defines data structures for @dfn{linkage
10534 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10535 handling of existing population-level data for the purpose of flexibly
10536 defining LD blocks.")
10537 (license license:artistic2.0)))
10539 (define-public r-gqtlstats
10541 (name "r-gqtlstats")
10546 (uri (bioconductor-uri "gQTLstats" version))
10549 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10550 (properties `((upstream-name . "gQTLstats")))
10551 (build-system r-build-system)
10553 `(("r-annotationdbi" ,r-annotationdbi)
10554 ("r-batchjobs" ,r-batchjobs)
10555 ("r-bbmisc" ,r-bbmisc)
10556 ("r-beeswarm" ,r-beeswarm)
10557 ("r-biobase" ,r-biobase)
10558 ("r-biocgenerics" ,r-biocgenerics)
10559 ("r-doparallel" ,r-doparallel)
10560 ("r-dplyr" ,r-dplyr)
10562 ("r-ffbase" ,r-ffbase)
10563 ("r-foreach" ,r-foreach)
10564 ("r-genomeinfodb" ,r-genomeinfodb)
10565 ("r-genomicfeatures" ,r-genomicfeatures)
10566 ("r-genomicfiles" ,r-genomicfiles)
10567 ("r-genomicranges" ,r-genomicranges)
10568 ("r-ggbeeswarm" ,r-ggbeeswarm)
10569 ("r-ggplot2" ,r-ggplot2)
10570 ("r-gqtlbase" ,r-gqtlbase)
10571 ("r-hardyweinberg" ,r-hardyweinberg)
10572 ("r-homo-sapiens" ,r-homo-sapiens)
10573 ("r-iranges" ,r-iranges)
10574 ("r-limma" ,r-limma)
10576 ("r-plotly" ,r-plotly)
10577 ("r-reshape2" ,r-reshape2)
10578 ("r-s4vectors" ,r-s4vectors)
10579 ("r-shiny" ,r-shiny)
10580 ("r-snpstats" ,r-snpstats)
10581 ("r-summarizedexperiment" ,r-summarizedexperiment)
10582 ("r-variantannotation" ,r-variantannotation)))
10583 (home-page "https://bioconductor.org/packages/gQTLstats")
10584 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10586 "This package provides tools for the computationally efficient analysis
10587 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10588 The software in this package aims to support refinements and functional
10589 interpretation of members of a collection of association statistics on a
10590 family of feature/genome hypotheses.")
10591 (license license:artistic2.0)))
10593 (define-public r-gviz
10600 (uri (bioconductor-uri "Gviz" version))
10603 "0jvcivgw0ahv2rjadxmrww76xambhf7silczmh38nn4yn4qw6w9y"))))
10604 (properties `((upstream-name . "Gviz")))
10605 (build-system r-build-system)
10607 `(("r-annotationdbi" ,r-annotationdbi)
10608 ("r-biobase" ,r-biobase)
10609 ("r-biocgenerics" ,r-biocgenerics)
10610 ("r-biomart" ,r-biomart)
10611 ("r-biostrings" ,r-biostrings)
10612 ("r-biovizbase" ,r-biovizbase)
10613 ("r-bsgenome" ,r-bsgenome)
10614 ("r-digest" ,r-digest)
10615 ("r-genomeinfodb" ,r-genomeinfodb)
10616 ("r-genomicalignments" ,r-genomicalignments)
10617 ("r-genomicfeatures" ,r-genomicfeatures)
10618 ("r-genomicranges" ,r-genomicranges)
10619 ("r-iranges" ,r-iranges)
10620 ("r-lattice" ,r-lattice)
10621 ("r-latticeextra" ,r-latticeextra)
10622 ("r-matrixstats" ,r-matrixstats)
10623 ("r-rcolorbrewer" ,r-rcolorbrewer)
10624 ("r-rsamtools" ,r-rsamtools)
10625 ("r-rtracklayer" ,r-rtracklayer)
10626 ("r-s4vectors" ,r-s4vectors)
10627 ("r-xvector" ,r-xvector)))
10628 (home-page "https://bioconductor.org/packages/Gviz")
10629 (synopsis "Plotting data and annotation information along genomic coordinates")
10631 "Genomic data analyses requires integrated visualization of known genomic
10632 information and new experimental data. Gviz uses the biomaRt and the
10633 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10634 and translates this to e.g. gene/transcript structures in viewports of the
10635 grid graphics package. This results in genomic information plotted together
10637 (license license:artistic2.0)))
10639 (define-public r-gwascat
10646 (uri (bioconductor-uri "gwascat" version))
10649 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10650 (build-system r-build-system)
10652 `(("r-annotationdbi" ,r-annotationdbi)
10653 ("r-annotationhub" ,r-annotationhub)
10654 ("r-biocgenerics" ,r-biocgenerics)
10655 ("r-biostrings" ,r-biostrings)
10656 ("r-genomeinfodb" ,r-genomeinfodb)
10657 ("r-genomicfeatures" ,r-genomicfeatures)
10658 ("r-genomicranges" ,r-genomicranges)
10659 ("r-ggbio" ,r-ggbio)
10660 ("r-ggplot2" ,r-ggplot2)
10661 ("r-gqtlstats" ,r-gqtlstats)
10662 ("r-graph" ,r-graph)
10664 ("r-homo-sapiens" ,r-homo-sapiens)
10665 ("r-iranges" ,r-iranges)
10666 ("r-rsamtools" ,r-rsamtools)
10667 ("r-rtracklayer" ,r-rtracklayer)
10668 ("r-s4vectors" ,r-s4vectors)
10669 ("r-snpstats" ,r-snpstats)
10670 ("r-summarizedexperiment" ,r-summarizedexperiment)
10671 ("r-variantannotation" ,r-variantannotation)))
10672 (home-page "https://bioconductor.org/packages/gwascat")
10673 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10675 "This package provides tools for representing and modeling data in the
10676 EMBL-EBI GWAS catalog.")
10677 (license license:artistic2.0)))
10679 (define-public r-sushi
10685 (uri (bioconductor-uri "Sushi" version))
10688 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10689 (properties `((upstream-name . "Sushi")))
10690 (build-system r-build-system)
10692 `(("r-biomart" ,r-biomart)
10694 (home-page "https://bioconductor.org/packages/Sushi")
10695 (synopsis "Tools for visualizing genomics data")
10697 "This package provides flexible, quantitative, and integrative genomic
10698 visualizations for publication-quality multi-panel figures.")
10699 (license license:gpl2+)))
10701 (define-public r-fithic
10707 (uri (bioconductor-uri "FitHiC" version))
10710 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10711 (properties `((upstream-name . "FitHiC")))
10712 (build-system r-build-system)
10714 `(("r-data-table" ,r-data-table)
10715 ("r-fdrtool" ,r-fdrtool)
10716 ("r-rcpp" ,r-rcpp)))
10717 (home-page "https://bioconductor.org/packages/FitHiC")
10718 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10720 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10721 intra-chromosomal contact maps produced by genome-wide genome architecture
10722 assays such as Hi-C.")
10723 (license license:gpl2+)))
10725 (define-public r-hitc
10731 (uri (bioconductor-uri "HiTC" version))
10734 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10735 (properties `((upstream-name . "HiTC")))
10736 (build-system r-build-system)
10738 `(("r-biostrings" ,r-biostrings)
10739 ("r-genomeinfodb" ,r-genomeinfodb)
10740 ("r-genomicranges" ,r-genomicranges)
10741 ("r-iranges" ,r-iranges)
10742 ("r-matrix" ,r-matrix)
10743 ("r-rcolorbrewer" ,r-rcolorbrewer)
10744 ("r-rtracklayer" ,r-rtracklayer)))
10745 (home-page "https://bioconductor.org/packages/HiTC")
10746 (synopsis "High throughput chromosome conformation capture analysis")
10748 "The HiTC package was developed to explore high-throughput \"C\" data
10749 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10750 quality controls, normalization, visualization, and further analysis are also
10752 (license license:artistic2.0)))
10754 (define-public r-qvalue
10761 (uri (bioconductor-uri "qvalue" version))
10764 "0kxavzm1j2mk26qicmjm90nxx4w5h3dxighzks7wzihay3k8cysc"))))
10765 (build-system r-build-system)
10767 `(("r-ggplot2" ,r-ggplot2)
10768 ("r-reshape2" ,r-reshape2)))
10769 (home-page "http://github.com/jdstorey/qvalue")
10770 (synopsis "Q-value estimation for false discovery rate control")
10772 "This package takes a list of p-values resulting from the simultaneous
10773 testing of many hypotheses and estimates their q-values and local @dfn{false
10774 discovery rate} (FDR) values. The q-value of a test measures the proportion
10775 of false positives incurred when that particular test is called significant.
10776 The local FDR measures the posterior probability the null hypothesis is true
10777 given the test's p-value. Various plots are automatically generated, allowing
10778 one to make sensible significance cut-offs. The software can be applied to
10779 problems in genomics, brain imaging, astrophysics, and data mining.")
10780 ;; Any version of the LGPL.
10781 (license license:lgpl3+)))
10783 (define-public r-hdf5array
10785 (name "r-hdf5array")
10790 (uri (bioconductor-uri "HDF5Array" version))
10793 "1qwdsygcadl58qj598hfyvs8hp0hqcl9ghnhknahrlhmb7k2bd2d"))))
10794 (properties `((upstream-name . "HDF5Array")))
10795 (build-system r-build-system)
10797 `(("r-biocgenerics" ,r-biocgenerics)
10798 ("r-delayedarray" ,r-delayedarray)
10799 ("r-iranges" ,r-iranges)
10800 ("r-rhdf5" ,r-rhdf5)
10801 ("r-s4vectors" ,r-s4vectors)))
10802 (home-page "https://bioconductor.org/packages/HDF5Array")
10803 (synopsis "HDF5 back end for DelayedArray objects")
10804 (description "This package provides an array-like container for convenient
10805 access and manipulation of HDF5 datasets. It supports delayed operations and
10806 block processing.")
10807 (license license:artistic2.0)))
10809 (define-public r-rhdf5lib
10811 (name "r-rhdf5lib")
10816 (uri (bioconductor-uri "Rhdf5lib" version))
10819 "06bxd3wz8lrvh2hzvmjpdv4lvzj5lz9353bw5b3zb98cb8w9r2j5"))
10820 (modules '((guix build utils)))
10823 ;; Delete bundled binaries
10824 (delete-file-recursively "src/winlib/")
10826 (properties `((upstream-name . "Rhdf5lib")))
10827 (build-system r-build-system)
10830 (modify-phases %standard-phases
10831 (add-after 'unpack 'do-not-use-bundled-hdf5
10832 (lambda* (#:key inputs #:allow-other-keys)
10833 (for-each delete-file '("configure" "configure.ac"))
10834 ;; Do not make other packages link with the proprietary libsz.
10835 (substitute* "R/zzz.R"
10836 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10837 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10838 (("'%s/libhdf5.a %s/libsz.a -lz'")
10839 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10840 (with-directory-excursion "src"
10841 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10842 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10844 ;; Remove timestamp and host system information to make
10845 ;; the build reproducible.
10846 (substitute* "hdf5/src/libhdf5.settings.in"
10847 (("Configured on: @CONFIG_DATE@")
10848 "Configured on: Guix")
10849 (("Uname information:.*")
10850 "Uname information: Linux\n")
10851 ;; Remove unnecessary store reference.
10853 "C Compiler: GCC\n"))
10854 (rename-file "Makevars.in" "Makevars")
10855 (substitute* "Makevars"
10856 (("HDF5_CXX_LIB=.*")
10857 (string-append "HDF5_CXX_LIB="
10858 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10860 (string-append "HDF5_LIB="
10861 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10862 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10863 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10864 ;; szip is non-free software
10865 (("cp \\$\\{SZIP_LIB\\}.*") "")
10866 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10871 `(("hdf5" ,hdf5-1.10)))
10873 `(("hdf5-source" ,(package-source hdf5-1.10))))
10874 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10875 (synopsis "HDF5 library as an R package")
10876 (description "This package provides C and C++ HDF5 libraries for use in R
10878 (license license:artistic2.0)))
10880 (define-public r-beachmat
10882 (name "r-beachmat")
10887 (uri (bioconductor-uri "beachmat" version))
10890 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10891 (build-system r-build-system)
10896 `(("r-biocgenerics" ,r-biocgenerics)
10897 ("r-delayedarray" ,r-delayedarray)
10898 ("r-hdf5array" ,r-hdf5array)
10900 ("r-rhdf5" ,r-rhdf5)
10901 ("r-rhdf5lib" ,r-rhdf5lib)))
10902 (home-page "https://bioconductor.org/packages/beachmat")
10903 (synopsis "Compiling Bioconductor to handle each matrix type")
10904 (description "This package provides a consistent C++ class interface for a
10905 variety of commonly used matrix types, including sparse and HDF5-backed
10907 (license license:gpl3)))
10909 (define-public r-singlecellexperiment
10911 (name "r-singlecellexperiment")
10916 (uri (bioconductor-uri "SingleCellExperiment" version))
10919 "12139kk9cqgzpm6f3cwdsq31gj5lxamz2q939dy9fa0fa54gdaq4"))))
10921 `((upstream-name . "SingleCellExperiment")))
10922 (build-system r-build-system)
10924 `(("r-biocgenerics" ,r-biocgenerics)
10925 ("r-s4vectors" ,r-s4vectors)
10926 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10927 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10928 (synopsis "S4 classes for single cell data")
10929 (description "This package defines an S4 class for storing data from
10930 single-cell experiments. This includes specialized methods to store and
10931 retrieve spike-in information, dimensionality reduction coordinates and size
10932 factors for each cell, along with the usual metadata for genes and
10934 (license license:gpl3)))
10936 (define-public r-scater
10942 (uri (bioconductor-uri "scater" version))
10945 "0rijhy7g5qmcn927y1wyd63la1fhyar9fv1hccsqd23jd98yc55a"))))
10946 (build-system r-build-system)
10948 `(("r-beachmat" ,r-beachmat)
10949 ("r-biocgenerics" ,r-biocgenerics)
10950 ("r-biocparallel" ,r-biocparallel)
10951 ("r-delayedarray" ,r-delayedarray)
10952 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10953 ("r-dplyr" ,r-dplyr)
10954 ("r-ggbeeswarm" ,r-ggbeeswarm)
10955 ("r-ggplot2" ,r-ggplot2)
10956 ("r-matrix" ,r-matrix)
10959 ("r-reshape2" ,r-reshape2)
10960 ("r-rhdf5lib" ,r-rhdf5lib)
10961 ("r-s4vectors" ,r-s4vectors)
10962 ("r-singlecellexperiment" ,r-singlecellexperiment)
10963 ("r-summarizedexperiment" ,r-summarizedexperiment)
10964 ("r-viridis" ,r-viridis)))
10965 (home-page "https://github.com/davismcc/scater")
10966 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10967 (description "This package provides a collection of tools for doing
10968 various analyses of single-cell RNA-seq gene expression data, with a focus on
10970 (license license:gpl2+)))
10972 (define-public r-scran
10979 (uri (bioconductor-uri "scran" version))
10982 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
10983 (build-system r-build-system)
10985 `(("r-beachmat" ,r-beachmat)
10986 ("r-biocgenerics" ,r-biocgenerics)
10987 ("r-biocneighbors" ,r-biocneighbors)
10988 ("r-biocparallel" ,r-biocparallel)
10989 ("r-delayedarray" ,r-delayedarray)
10990 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10991 ("r-dynamictreecut" ,r-dynamictreecut)
10992 ("r-edger" ,r-edger)
10993 ("r-igraph" ,r-igraph)
10994 ("r-limma" ,r-limma)
10995 ("r-matrix" ,r-matrix)
10997 ("r-rhdf5lib" ,r-rhdf5lib)
10998 ("r-s4vectors" ,r-s4vectors)
10999 ("r-scater" ,r-scater)
11000 ("r-singlecellexperiment" ,r-singlecellexperiment)
11001 ("r-statmod" ,r-statmod)
11002 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11003 (home-page "https://bioconductor.org/packages/scran")
11004 (synopsis "Methods for single-cell RNA-Seq data analysis")
11005 (description "This package implements a variety of low-level analyses of
11006 single-cell RNA-seq data. Methods are provided for normalization of
11007 cell-specific biases, assignment of cell cycle phase, and detection of highly
11008 variable and significantly correlated genes.")
11009 (license license:gpl3)))
11011 (define-public r-delayedmatrixstats
11013 (name "r-delayedmatrixstats")
11018 (uri (bioconductor-uri "DelayedMatrixStats" version))
11021 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11023 `((upstream-name . "DelayedMatrixStats")))
11024 (build-system r-build-system)
11026 `(("r-biocparallel" ,r-biocparallel)
11027 ("r-delayedarray" ,r-delayedarray)
11028 ("r-hdf5array" ,r-hdf5array)
11029 ("r-iranges" ,r-iranges)
11030 ("r-matrix" ,r-matrix)
11031 ("r-matrixstats" ,r-matrixstats)
11032 ("r-s4vectors" ,r-s4vectors)))
11033 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11034 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11036 "This package provides a port of the @code{matrixStats} API for use with
11037 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11038 contains high-performing functions operating on rows and columns of
11039 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11040 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11041 are optimized per data type and for subsetted calculations such that both
11042 memory usage and processing time is minimized.")
11043 (license license:expat)))
11045 (define-public r-phangorn
11047 (name "r-phangorn")
11052 (uri (cran-uri "phangorn" version))
11055 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11056 (build-system r-build-system)
11059 ("r-fastmatch" ,r-fastmatch)
11060 ("r-igraph" ,r-igraph)
11061 ("r-magrittr" ,r-magrittr)
11062 ("r-matrix" ,r-matrix)
11063 ("r-quadprog" ,r-quadprog)
11064 ("r-rcpp" ,r-rcpp)))
11065 (home-page "https://github.com/KlausVigo/phangorn")
11066 (synopsis "Phylogenetic analysis in R")
11068 "Phangorn is a package for phylogenetic analysis in R. It supports
11069 estimation of phylogenetic trees and networks using Maximum Likelihood,
11070 Maximum Parsimony, distance methods and Hadamard conjugation.")
11071 (license license:gpl2+)))
11073 (define-public r-dropbead
11074 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11077 (name "r-dropbead")
11078 (version (string-append "0-" revision "." (string-take commit 7)))
11082 (uri (git-reference
11083 (url "https://github.com/rajewsky-lab/dropbead.git")
11085 (file-name (git-file-name name version))
11088 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11089 (build-system r-build-system)
11091 `(("r-ggplot2" ,r-ggplot2)
11092 ("r-rcolorbrewer" ,r-rcolorbrewer)
11093 ("r-gridextra" ,r-gridextra)
11094 ("r-gplots" ,r-gplots)
11095 ("r-plyr" ,r-plyr)))
11096 (home-page "https://github.com/rajewsky-lab/dropbead")
11097 (synopsis "Basic exploration and analysis of Drop-seq data")
11098 (description "This package offers a quick and straight-forward way to
11099 explore and perform basic analysis of single cell sequencing data coming from
11100 droplet sequencing. It has been particularly tailored for Drop-seq.")
11101 (license license:gpl3))))
11103 (define htslib-for-sambamba
11104 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11107 (name "htslib-for-sambamba")
11108 (version (string-append "1.3.1-1." (string-take commit 9)))
11112 (uri (git-reference
11113 (url "https://github.com/lomereiter/htslib.git")
11115 (file-name (string-append "htslib-" version "-checkout"))
11118 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11120 `(("autoconf" ,autoconf)
11121 ("automake" ,automake)
11122 ,@(package-native-inputs htslib))))))
11124 (define-public sambamba
11131 (uri (git-reference
11132 (url "https://github.com/lomereiter/sambamba.git")
11133 (commit (string-append "v" version))))
11134 (file-name (string-append name "-" version "-checkout"))
11137 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
11138 (build-system gnu-build-system)
11140 `(#:tests? #f ; there is no test target
11141 #:parallel-build? #f ; not supported
11143 (modify-phases %standard-phases
11144 (delete 'configure)
11145 (add-after 'unpack 'fix-ldc-version
11147 (substitute* "gen_ldc_version_info.py"
11148 (("/usr/bin/env.*") (which "python3")))
11149 (substitute* "Makefile"
11150 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11151 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11153 (add-after 'unpack 'place-biod-and-undead
11154 (lambda* (#:key inputs #:allow-other-keys)
11155 (copy-recursively (assoc-ref inputs "biod") "BioD")
11156 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11158 (add-after 'unpack 'unbundle-prerequisites
11160 (substitute* "Makefile"
11161 (("htslib/libhts.a lz4/lib/liblz4.a")
11163 ((" lz4-static htslib-static") ""))
11166 (lambda* (#:key outputs #:allow-other-keys)
11167 (let* ((out (assoc-ref outputs "out"))
11168 (bin (string-append out "/bin")))
11170 (install-file "bin/sambamba" bin)
11175 ("python" ,python-minimal)
11177 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
11180 (uri (git-reference
11181 (url "https://github.com/biod/BioD.git")
11183 (file-name (string-append "biod-"
11184 (string-take commit 9)
11188 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
11190 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
11193 (uri (git-reference
11194 (url "https://github.com/biod/undeaD.git")
11196 (file-name (string-append "undead-"
11197 (string-take commit 9)
11201 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11204 ("htslib" ,htslib-for-sambamba)))
11205 (home-page "http://lomereiter.github.io/sambamba")
11206 (synopsis "Tools for working with SAM/BAM data")
11207 (description "Sambamba is a high performance modern robust and
11208 fast tool (and library), written in the D programming language, for
11209 working with SAM and BAM files. Current parallelised functionality is
11210 an important subset of samtools functionality, including view, index,
11211 sort, markdup, and depth.")
11212 (license license:gpl2+)))
11214 (define-public ritornello
11216 (name "ritornello")
11220 (uri (git-reference
11221 (url "https://github.com/KlugerLab/Ritornello.git")
11222 (commit (string-append "v" version))))
11223 (file-name (git-file-name name version))
11226 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11227 (build-system gnu-build-system)
11229 `(#:tests? #f ; there are no tests
11231 (modify-phases %standard-phases
11232 (add-after 'unpack 'patch-samtools-references
11233 (lambda* (#:key inputs #:allow-other-keys)
11234 (substitute* '("src/SamStream.h"
11236 (("<sam.h>") "<samtools/sam.h>"))
11238 (delete 'configure)
11240 (lambda* (#:key inputs outputs #:allow-other-keys)
11241 (let* ((out (assoc-ref outputs "out"))
11242 (bin (string-append out "/bin/")))
11244 (install-file "bin/Ritornello" bin)
11247 `(("samtools" ,samtools-0.1)
11251 (home-page "https://github.com/KlugerLab/Ritornello")
11252 (synopsis "Control-free peak caller for ChIP-seq data")
11253 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11254 signal processing that can accurately call binding events without the need to
11255 do a pair total DNA input or IgG control sample. It has been tested for use
11256 with narrow binding events such as transcription factor ChIP-seq.")
11257 (license license:gpl3+)))
11259 (define-public trim-galore
11261 (name "trim-galore")
11266 (uri (git-reference
11267 (url "https://github.com/FelixKrueger/TrimGalore.git")
11269 (file-name (string-append name "-" version "-checkout"))
11272 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11273 (build-system gnu-build-system)
11275 `(#:tests? #f ; no tests
11277 (modify-phases %standard-phases
11278 (delete 'configure)
11280 (add-after 'unpack 'hardcode-tool-references
11281 (lambda* (#:key inputs #:allow-other-keys)
11282 (substitute* "trim_galore"
11283 (("\\$path_to_cutadapt = 'cutadapt'")
11284 (string-append "$path_to_cutadapt = '"
11285 (assoc-ref inputs "cutadapt")
11288 (string-append "| "
11289 (assoc-ref inputs "gzip")
11292 (string-append "\""
11293 (assoc-ref inputs "gzip")
11297 (lambda* (#:key outputs #:allow-other-keys)
11298 (let ((bin (string-append (assoc-ref outputs "out")
11301 (install-file "trim_galore" bin)
11306 ("cutadapt" ,cutadapt)))
11308 `(("unzip" ,unzip)))
11309 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11310 (synopsis "Wrapper around Cutadapt and FastQC")
11311 (description "Trim Galore! is a wrapper script to automate quality and
11312 adapter trimming as well as quality control, with some added functionality to
11313 remove biased methylation positions for RRBS sequence files.")
11314 (license license:gpl3+)))
11316 (define-public gess
11322 (uri (string-append "http://compbio.uthscsa.edu/"
11324 "gess-" version ".src.tar.gz"))
11327 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11328 (build-system gnu-build-system)
11330 `(#:tests? #f ; no tests
11332 (modify-phases %standard-phases
11333 (delete 'configure)
11336 (lambda* (#:key inputs outputs #:allow-other-keys)
11337 (let* ((python (assoc-ref inputs "python"))
11338 (out (assoc-ref outputs "out"))
11339 (bin (string-append out "/bin/"))
11340 (target (string-append
11342 ,(version-major+minor
11343 (package-version python))
11344 "/site-packages/gess/")))
11346 (copy-recursively "." target)
11347 ;; Make GESS.py executable
11348 (chmod (string-append target "GESS.py") #o555)
11349 ;; Add Python shebang to the top and make Matplotlib
11351 (substitute* (string-append target "GESS.py")
11352 (("\"\"\"Description:" line)
11353 (string-append "#!" (which "python") "
11355 matplotlib.use('Agg')
11357 ;; Make sure GESS has all modules in its path
11358 (wrap-program (string-append target "GESS.py")
11359 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11361 (symlink (string-append target "GESS.py")
11362 (string-append bin "GESS.py"))
11365 `(("python" ,python-2)
11366 ("python2-pysam" ,python2-pysam)
11367 ("python2-scipy" ,python2-scipy)
11368 ("python2-numpy" ,python2-numpy)
11369 ("python2-networkx" ,python2-networkx)
11370 ("python2-biopython" ,python2-biopython)))
11371 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11372 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11374 "GESS is an implementation of a novel computational method to detect de
11375 novo exon-skipping events directly from raw RNA-seq data without the prior
11376 knowledge of gene annotation information. GESS stands for the graph-based
11377 exon-skipping scanner detection scheme.")
11378 (license license:bsd-3)))
11380 (define-public phylip
11387 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11388 "download/phylip-" version ".tar.gz"))
11391 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11392 (build-system gnu-build-system)
11394 `(#:tests? #f ; no check target
11395 #:make-flags (list "-f" "Makefile.unx" "install")
11396 #:parallel-build? #f ; not supported
11398 (modify-phases %standard-phases
11399 (add-after 'unpack 'enter-dir
11400 (lambda _ (chdir "src") #t))
11401 (delete 'configure)
11403 (lambda* (#:key inputs outputs #:allow-other-keys)
11404 (let ((target (string-append (assoc-ref outputs "out")
11407 (for-each (lambda (file)
11408 (install-file file target))
11409 (find-files "../exe" ".*")))
11411 (home-page "http://evolution.genetics.washington.edu/phylip/")
11412 (synopsis "Tools for inferring phylogenies")
11413 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11414 programs for inferring phylogenies (evolutionary trees).")
11415 (license license:bsd-2)))
11424 (uri (string-append "https://integrativemodeling.org/"
11425 version "/download/imp-" version ".tar.gz"))
11428 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11429 (build-system cmake-build-system)
11431 `(;; FIXME: Some tests fail because they produce warnings, others fail
11432 ;; because the PYTHONPATH does not include the modeller's directory.
11440 ("python" ,python-2)))
11442 `(("python2-numpy" ,python2-numpy)
11443 ("python2-scipy" ,python2-scipy)
11444 ("python2-pandas" ,python2-pandas)
11445 ("python2-scikit-learn" ,python2-scikit-learn)
11446 ("python2-networkx" ,python2-networkx)))
11447 (home-page "https://integrativemodeling.org")
11448 (synopsis "Integrative modeling platform")
11449 (description "IMP's broad goal is to contribute to a comprehensive
11450 structural characterization of biomolecules ranging in size and complexity
11451 from small peptides to large macromolecular assemblies, by integrating data
11452 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11453 Python toolbox for solving complex modeling problems, and a number of
11454 applications for tackling some common problems in a user-friendly way.")
11455 ;; IMP is largely available under the GNU Lesser GPL; see the file
11456 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11457 ;; available under the GNU GPL (see the file COPYING.GPL).
11458 (license (list license:lgpl2.1+
11461 (define-public tadbit
11467 (uri (git-reference
11468 (url "https://github.com/3DGenomes/TADbit.git")
11469 (commit (string-append "v" version))))
11470 (file-name (git-file-name name version))
11473 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11474 (build-system python-build-system)
11476 `(;; Tests are included and must be run after installation, but
11477 ;; they are incomplete and thus cannot be run.
11481 (modify-phases %standard-phases
11482 (add-after 'unpack 'fix-problems-with-setup.py
11483 (lambda* (#:key outputs #:allow-other-keys)
11484 ;; setup.py opens these files for writing
11485 (chmod "_pytadbit/_version.py" #o664)
11486 (chmod "README.rst" #o664)
11488 ;; Don't attempt to install the bash completions to
11489 ;; the home directory.
11490 (rename-file "extras/.bash_completion"
11492 (substitute* "setup.py"
11493 (("\\(path.expanduser\\('~'\\)")
11494 (string-append "(\""
11495 (assoc-ref outputs "out")
11496 "/etc/bash_completion.d\""))
11497 (("extras/\\.bash_completion")
11501 ;; TODO: add Chimera for visualization
11504 ("python2-scipy" ,python2-scipy)
11505 ("python2-numpy" ,python2-numpy)
11506 ("python2-matplotlib" ,python2-matplotlib)
11507 ("python2-pysam" ,python2-pysam)))
11508 (home-page "https://3dgenomes.github.io/TADbit/")
11509 (synopsis "Analyze, model, and explore 3C-based data")
11511 "TADbit is a complete Python library to deal with all steps to analyze,
11512 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11513 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11514 correct interaction matrices, identify and compare the so-called
11515 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11516 interaction matrices, and finally, extract structural properties from the
11517 models. TADbit is complemented by TADkit for visualizing 3D models.")
11518 (license license:gpl3+)))
11520 (define-public kentutils
11523 ;; 302.1.0 is out, but the only difference is the inclusion of
11524 ;; pre-built binaries.
11525 (version "302.0.0")
11529 (uri (git-reference
11530 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11531 (commit (string-append "v" version))))
11532 (file-name (git-file-name name version))
11535 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11536 (modules '((guix build utils)
11541 ;; Only the contents of the specified directories are free
11542 ;; for all uses, so we remove the rest. "hg/autoSql" and
11543 ;; "hg/autoXml" are nominally free, but they depend on a
11544 ;; library that is built from the sources in "hg/lib",
11545 ;; which is nonfree.
11546 (let ((free (list "." ".."
11547 "utils" "lib" "inc" "tagStorm"
11548 "parasol" "htslib"))
11549 (directory? (lambda (file)
11550 (eq? 'directory (stat:type (stat file))))))
11551 (for-each (lambda (file)
11552 (and (directory? file)
11553 (delete-file-recursively file)))
11554 (map (cut string-append "src/" <>)
11557 (not (member file free)))))))
11558 ;; Only make the utils target, not the userApps target,
11559 ;; because that requires libraries we won't build.
11560 (substitute* "Makefile"
11561 ((" userApps") " utils"))
11562 ;; Only build libraries that are free.
11563 (substitute* "src/makefile"
11564 (("DIRS =.*") "DIRS =\n")
11565 (("cd jkOwnLib.*") "")
11568 (substitute* "src/utils/makefile"
11569 ;; These tools depend on "jkhgap.a", which is part of the
11570 ;; nonfree "src/hg/lib" directory.
11571 (("raSqlQuery") "")
11572 (("pslLiftSubrangeBlat") "")
11574 ;; Do not build UCSC tools, which may require nonfree
11576 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11578 (build-system gnu-build-system)
11580 `( ;; There is no global test target and the test target for
11581 ;; individual tools depends on input files that are not
11585 (modify-phases %standard-phases
11586 (add-after 'unpack 'fix-permissions
11587 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11588 (add-after 'unpack 'fix-paths
11590 (substitute* "Makefile"
11591 (("/bin/echo") (which "echo")))
11593 (add-after 'unpack 'prepare-samtabix
11594 (lambda* (#:key inputs #:allow-other-keys)
11595 (copy-recursively (assoc-ref inputs "samtabix")
11598 (delete 'configure)
11600 (lambda* (#:key outputs #:allow-other-keys)
11601 (let ((bin (string-append (assoc-ref outputs "out")
11603 (copy-recursively "bin" bin))
11609 (uri (git-reference
11610 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11611 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11614 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11620 ("mariadb" ,mariadb)
11621 ("openssl" ,openssl)))
11622 (home-page "http://genome.cse.ucsc.edu/index.html")
11623 (synopsis "Assorted bioinformatics utilities")
11624 (description "This package provides the kentUtils, a selection of
11625 bioinformatics utilities used in combination with the UCSC genome
11627 ;; Only a subset of the sources are released under a non-copyleft
11628 ;; free software license. All other sources are removed in a
11629 ;; snippet. See this bug report for an explanation of how the
11630 ;; license statements apply:
11631 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11632 (license (license:non-copyleft
11633 "http://genome.ucsc.edu/license/"
11634 "The contents of this package are free for all uses."))))
11636 (define-public f-seq
11637 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11641 (version (string-append "1.1-" revision "." (string-take commit 7)))
11644 (uri (git-reference
11645 (url "https://github.com/aboyle/F-seq.git")
11647 (file-name (string-append name "-" version))
11650 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11651 (modules '((guix build utils)))
11652 ;; Remove bundled Java library archives.
11655 (for-each delete-file (find-files "lib" ".*"))
11657 (build-system ant-build-system)
11659 `(#:tests? #f ; no tests included
11661 (modify-phases %standard-phases
11663 (lambda* (#:key inputs outputs #:allow-other-keys)
11664 (let* ((target (assoc-ref outputs "out"))
11665 (bin (string-append target "/bin"))
11666 (doc (string-append target "/share/doc/f-seq"))
11667 (lib (string-append target "/lib")))
11670 (substitute* "bin/linux/fseq"
11671 (("java") (which "java"))
11672 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11673 (string-append (assoc-ref inputs "java-commons-cli")
11674 "/share/java/commons-cli.jar"))
11676 (string-append "REALDIR=" bin "\n")))
11677 (install-file "README.txt" doc)
11678 (install-file "bin/linux/fseq" bin)
11679 (install-file "build~/fseq.jar" lib)
11680 (copy-recursively "lib" lib)
11684 ("java-commons-cli" ,java-commons-cli)))
11685 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11686 (synopsis "Feature density estimator for high-throughput sequence tags")
11688 "F-Seq is a software package that generates a continuous tag sequence
11689 density estimation allowing identification of biologically meaningful sites
11690 such as transcription factor binding sites (ChIP-seq) or regions of open
11691 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11693 (license license:gpl3+))))
11695 (define-public bismark
11702 (uri (git-reference
11703 (url "https://github.com/FelixKrueger/Bismark.git")
11705 (file-name (string-append name "-" version "-checkout"))
11708 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11711 ;; highcharts.js is non-free software. The code is available under
11712 ;; CC-BY-NC or proprietary licenses only.
11713 (delete-file "bismark_sitrep/highcharts.js")
11715 (build-system perl-build-system)
11717 `(#:tests? #f ; there are no tests
11719 (modify-phases %standard-phases
11720 (delete 'configure)
11723 (lambda* (#:key inputs outputs #:allow-other-keys)
11724 (let* ((out (assoc-ref outputs "out"))
11725 (bin (string-append out "/bin"))
11726 (share (string-append out "/share/bismark"))
11727 (docdir (string-append out "/share/doc/bismark"))
11728 (docs '("Docs/Bismark_User_Guide.html"))
11729 (scripts '("bismark"
11730 "bismark_genome_preparation"
11731 "bismark_methylation_extractor"
11734 "coverage2cytosine"
11735 "deduplicate_bismark"
11736 "filter_non_conversion"
11738 "bismark2summary")))
11739 (substitute* "bismark2report"
11740 (("\\$RealBin/bismark_sitrep")
11741 (string-append share "/bismark_sitrep")))
11745 (for-each (lambda (file) (install-file file bin))
11747 (for-each (lambda (file) (install-file file docdir))
11749 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11750 (copy-recursively "bismark_sitrep"
11751 (string-append share "/bismark_sitrep"))
11753 ;; Fix references to gunzip
11754 (substitute* (map (lambda (file)
11755 (string-append bin "/" file))
11758 (string-append "\"" (assoc-ref inputs "gzip")
11759 "/bin/gunzip -c")))
11763 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11764 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11765 (description "Bismark is a program to map bisulfite treated sequencing
11766 reads to a genome of interest and perform methylation calls in a single step.
11767 The output can be easily imported into a genome viewer, such as SeqMonk, and
11768 enables a researcher to analyse the methylation levels of their samples
11769 straight away. Its main features are:
11772 @item Bisulfite mapping and methylation calling in one single step
11773 @item Supports single-end and paired-end read alignments
11774 @item Supports ungapped and gapped alignments
11775 @item Alignment seed length, number of mismatches etc are adjustable
11776 @item Output discriminates between cytosine methylation in CpG, CHG
11779 (license license:gpl3+)))
11781 (define-public paml
11787 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11788 "paml" version ".tgz"))
11791 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11792 (modules '((guix build utils)))
11793 ;; Remove Windows binaries
11796 (for-each delete-file (find-files "." "\\.exe$"))
11798 (build-system gnu-build-system)
11800 `(#:tests? #f ; there are no tests
11801 #:make-flags '("CC=gcc")
11803 (modify-phases %standard-phases
11804 (replace 'configure
11806 (substitute* "src/BFdriver.c"
11807 (("/bin/bash") (which "bash")))
11811 (lambda* (#:key outputs #:allow-other-keys)
11812 (let ((tools '("baseml" "basemlg" "codeml"
11813 "pamp" "evolver" "yn00" "chi2"))
11814 (bin (string-append (assoc-ref outputs "out") "/bin"))
11815 (docdir (string-append (assoc-ref outputs "out")
11816 "/share/doc/paml")))
11818 (for-each (lambda (file) (install-file file bin)) tools)
11819 (copy-recursively "../doc" docdir)
11821 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11822 (synopsis "Phylogentic analysis by maximum likelihood")
11823 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11824 contains a few programs for model fitting and phylogenetic tree reconstruction
11825 using nucleotide or amino-acid sequence data.")
11827 (license license:gpl3)))
11829 (define-public kallisto
11835 (uri (git-reference
11836 (url "https://github.com/pachterlab/kallisto.git")
11837 (commit (string-append "v" version))))
11838 (file-name (git-file-name name version))
11841 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11842 (build-system cmake-build-system)
11844 `(#:tests? #f ; no "check" target
11846 (modify-phases %standard-phases
11847 (add-after 'unpack 'do-not-use-bundled-htslib
11849 (substitute* "CMakeLists.txt"
11850 (("^ExternalProject_Add" m)
11851 (string-append "if (NEVER)\n" m))
11853 (string-append ")\nendif(NEVER)"))
11854 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11855 (string-append "# " m)))
11856 (substitute* "src/CMakeLists.txt"
11857 (("target_link_libraries\\(kallisto kallisto_core pthread \
11858 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11859 "target_link_libraries(kallisto kallisto_core pthread hts)")
11860 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11866 (home-page "http://pachterlab.github.io/kallisto/")
11867 (synopsis "Near-optimal RNA-Seq quantification")
11869 "Kallisto is a program for quantifying abundances of transcripts from
11870 RNA-Seq data, or more generally of target sequences using high-throughput
11871 sequencing reads. It is based on the novel idea of pseudoalignment for
11872 rapidly determining the compatibility of reads with targets, without the need
11873 for alignment. Pseudoalignment of reads preserves the key information needed
11874 for quantification, and kallisto is therefore not only fast, but also as
11875 accurate as existing quantification tools.")
11876 (license license:bsd-2)))
11878 (define-public libgff
11884 (uri (git-reference
11885 (url "https://github.com/Kingsford-Group/libgff.git")
11886 (commit (string-append "v" version))))
11887 (file-name (git-file-name name version))
11890 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11891 (build-system cmake-build-system)
11892 (arguments `(#:tests? #f)) ; no tests included
11893 (home-page "https://github.com/Kingsford-Group/libgff")
11894 (synopsis "Parser library for reading/writing GFF files")
11895 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11896 code that is used in the Cufflinks codebase. The goal of this library is to
11897 provide this functionality without the necessity of drawing in a heavy-weight
11898 dependency like SeqAn.")
11899 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11901 (define-public libdivsufsort
11903 (name "libdivsufsort")
11907 (uri (git-reference
11908 (url "https://github.com/y-256/libdivsufsort.git")
11910 (file-name (git-file-name name version))
11913 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11914 (build-system cmake-build-system)
11916 '(#:tests? #f ; there are no tests
11918 ;; Needed for rapmap and sailfish.
11919 '("-DBUILD_DIVSUFSORT64=ON")))
11920 (home-page "https://github.com/y-256/libdivsufsort")
11921 (synopsis "Lightweight suffix-sorting library")
11922 (description "libdivsufsort is a software library that implements a
11923 lightweight suffix array construction algorithm. This library provides a
11924 simple and an efficient C API to construct a suffix array and a
11925 Burrows-Wheeler transformed string from a given string over a constant-size
11926 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11927 bytes of memory space, where n is the length of the string.")
11928 (license license:expat)))
11930 (define-public sailfish
11936 (uri (git-reference
11937 (url "https://github.com/kingsfordgroup/sailfish.git")
11938 (commit (string-append "v" version))))
11939 (file-name (git-file-name name version))
11942 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11943 (modules '((guix build utils)))
11946 ;; Delete bundled headers for eigen3.
11947 (delete-file-recursively "include/eigen3/")
11949 (build-system cmake-build-system)
11951 `(#:configure-flags
11952 (list (string-append "-DBOOST_INCLUDEDIR="
11953 (assoc-ref %build-inputs "boost")
11955 (string-append "-DBOOST_LIBRARYDIR="
11956 (assoc-ref %build-inputs "boost")
11958 (string-append "-DBoost_LIBRARIES="
11959 "-lboost_iostreams "
11960 "-lboost_filesystem "
11965 "-lboost_program_options")
11966 "-DBoost_FOUND=TRUE"
11967 ;; Don't download RapMap---we already have it!
11968 "-DFETCHED_RAPMAP=1")
11969 ;; Tests must be run after installation and the location of the test
11970 ;; data file must be overridden. But the tests fail. It looks like
11971 ;; they are not really meant to be run.
11974 (modify-phases %standard-phases
11975 ;; Boost cannot be found, even though it's right there.
11976 (add-after 'unpack 'do-not-look-for-boost
11977 (lambda* (#:key inputs #:allow-other-keys)
11978 (substitute* "CMakeLists.txt"
11979 (("find_package\\(Boost 1\\.53\\.0") "#"))
11981 (add-after 'unpack 'do-not-assign-to-macro
11983 (substitute* "include/spdlog/details/format.cc"
11984 (("const unsigned CHAR_WIDTH = 1;") ""))
11986 (add-after 'unpack 'prepare-rapmap
11987 (lambda* (#:key inputs #:allow-other-keys)
11988 (let ((src "external/install/src/rapmap/")
11989 (include "external/install/include/rapmap/")
11990 (rapmap (assoc-ref inputs "rapmap")))
11991 (mkdir-p "/tmp/rapmap")
11993 (assoc-ref inputs "rapmap")
11995 "--strip-components=1")
11998 (for-each (lambda (file)
11999 (install-file file src))
12000 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12001 (copy-recursively "/tmp/rapmap/include" include))
12003 (add-after 'unpack 'use-system-libraries
12004 (lambda* (#:key inputs #:allow-other-keys)
12005 (substitute* '("src/SailfishIndexer.cpp"
12006 "src/SailfishUtils.cpp"
12007 "src/SailfishQuantify.cpp"
12008 "src/FASTAParser.cpp"
12010 "include/SailfishUtils.hpp"
12011 "include/SailfishIndex.hpp"
12012 "include/CollapsedEMOptimizer.hpp"
12013 "src/CollapsedEMOptimizer.cpp")
12014 (("#include \"jellyfish/config.h\"") ""))
12015 (substitute* "src/CMakeLists.txt"
12016 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12017 (string-append (assoc-ref inputs "jellyfish")
12018 "/include/jellyfish-" ,(package-version jellyfish)))
12019 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12020 (string-append (assoc-ref inputs "jellyfish")
12021 "/lib/libjellyfish-2.0.a"))
12022 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12023 (string-append (assoc-ref inputs "libdivsufsort")
12024 "/lib/libdivsufsort.so"))
12025 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12026 (string-append (assoc-ref inputs "libdivsufsort")
12027 "/lib/libdivsufsort64.so")))
12028 (substitute* "CMakeLists.txt"
12029 ;; Don't prefer static libs
12030 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12031 (("find_package\\(Jellyfish.*") "")
12032 (("ExternalProject_Add\\(libjellyfish") "message(")
12033 (("ExternalProject_Add\\(libgff") "message(")
12034 (("ExternalProject_Add\\(libsparsehash") "message(")
12035 (("ExternalProject_Add\\(libdivsufsort") "message("))
12037 ;; Ensure that Eigen headers can be found
12038 (setenv "CPLUS_INCLUDE_PATH"
12039 (string-append (getenv "CPLUS_INCLUDE_PATH")
12041 (assoc-ref inputs "eigen")
12042 "/include/eigen3"))
12047 ("jemalloc" ,jemalloc)
12048 ("jellyfish" ,jellyfish)
12049 ("sparsehash" ,sparsehash)
12052 (uri (git-reference
12053 (url "https://github.com/COMBINE-lab/RapMap.git")
12054 (commit (string-append "sf-v" version))))
12055 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12058 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12059 (modules '((guix build utils)))
12060 ;; These files are expected to be excluded.
12062 '(begin (delete-file-recursively "include/spdlog")
12063 (for-each delete-file '("include/xxhash.h"
12066 ("libdivsufsort" ,libdivsufsort)
12071 `(("pkg-config" ,pkg-config)))
12072 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12073 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12074 (description "Sailfish is a tool for genomic transcript quantification
12075 from RNA-seq data. It requires a set of target transcripts (either from a
12076 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12077 fasta file containing your reference transcripts and a (set of) fasta/fastq
12078 file(s) containing your reads.")
12079 (license license:gpl3+)))
12081 (define libstadenio-for-salmon
12083 (name "libstadenio")
12087 (uri (git-reference
12088 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12089 (commit (string-append "v" version))))
12090 (file-name (string-append name "-" version "-checkout"))
12093 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12094 (build-system gnu-build-system)
12095 (arguments '(#:parallel-tests? #f)) ; not supported
12099 `(("perl" ,perl))) ; for tests
12100 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12101 (synopsis "General purpose trace and experiment file library")
12102 (description "This package provides a library of file reading and writing
12103 code to provide a general purpose Trace file (and Experiment File) reading
12106 The following file formats are supported:
12109 @item SCF trace files
12110 @item ABI trace files
12111 @item ALF trace files
12112 @item ZTR trace files
12113 @item SFF trace archives
12114 @item SRF trace archives
12115 @item Experiment files
12116 @item Plain text files
12117 @item SAM/BAM sequence files
12118 @item CRAM sequence files
12120 (license license:bsd-3)))
12122 (define spdlog-for-salmon
12128 (uri (git-reference
12129 (url "https://github.com/COMBINE-lab/spdlog.git")
12130 (commit (string-append "v" version))))
12131 (file-name (string-append name "-" version "-checkout"))
12134 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12135 (build-system cmake-build-system)
12136 (home-page "https://github.com/COMBINE-lab/spdlog")
12137 (synopsis "Very fast C++ logging library")
12138 (description "Spdlog is a very fast header-only C++ logging library with
12139 performance as its primary goal.")
12140 (license license:expat)))
12142 ;; This is a modified variant of bwa for use with Salmon. It installs a
12143 ;; library to avoid having to build this as part of Salmon.
12144 (define bwa-for-salmon
12145 (package (inherit bwa)
12147 (version "0.7.12.5")
12150 (uri (git-reference
12151 (url "https://github.com/COMBINE-lab/bwa.git")
12152 (commit (string-append "v" version))))
12153 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12156 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12157 (build-system gnu-build-system)
12159 '(#:tests? #f ;no "check" target
12161 (modify-phases %standard-phases
12163 (lambda* (#:key outputs #:allow-other-keys)
12164 (let* ((out (assoc-ref outputs "out"))
12165 (bin (string-append out "/bin"))
12166 (lib (string-append out "/lib"))
12167 (doc (string-append out "/share/doc/bwa"))
12168 (man (string-append out "/share/man/man1"))
12169 (inc (string-append out "/include/bwa")))
12170 (install-file "bwa" bin)
12171 (install-file "README.md" doc)
12172 (install-file "bwa.1" man)
12173 (install-file "libbwa.a" lib)
12176 (for-each (lambda (file)
12177 (install-file file inc))
12178 (find-files "." "\\.h$")))
12180 ;; no "configure" script
12181 (delete 'configure))))))
12183 (define-public salmon
12189 (uri (git-reference
12190 (url "https://github.com/COMBINE-lab/salmon.git")
12191 (commit (string-append "v" version))))
12192 (file-name (string-append name "-" version "-checkout"))
12195 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12196 (modules '((guix build utils)))
12199 ;; Delete bundled headers for eigen3.
12200 (delete-file-recursively "include/eigen3/")
12202 (build-system cmake-build-system)
12204 `(#:configure-flags
12205 (list (string-append "-DBOOST_INCLUDEDIR="
12206 (assoc-ref %build-inputs "boost")
12208 (string-append "-DBOOST_LIBRARYDIR="
12209 (assoc-ref %build-inputs "boost")
12211 (string-append "-DBoost_LIBRARIES="
12212 "-lboost_iostreams "
12213 "-lboost_filesystem "
12218 "-lboost_program_options")
12219 "-DBoost_FOUND=TRUE"
12220 "-DTBB_LIBRARIES=tbb tbbmalloc"
12221 ;; Don't download RapMap---we already have it!
12222 "-DFETCHED_RAPMAP=1")
12224 (modify-phases %standard-phases
12225 ;; Boost cannot be found, even though it's right there.
12226 (add-after 'unpack 'do-not-look-for-boost
12227 (lambda* (#:key inputs #:allow-other-keys)
12228 (substitute* "CMakeLists.txt"
12229 (("find_package\\(Boost 1\\.53\\.0") "#"))
12231 (add-after 'unpack 'do-not-phone-home
12233 (substitute* "src/Salmon.cpp"
12234 (("getVersionMessage\\(\\)") "\"\""))
12236 (add-after 'unpack 'prepare-rapmap
12237 (lambda* (#:key inputs #:allow-other-keys)
12238 (let ((src "external/install/src/rapmap/")
12239 (include "external/install/include/rapmap/")
12240 (rapmap (assoc-ref inputs "rapmap")))
12243 (for-each (lambda (file)
12244 (install-file file src))
12245 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12246 (copy-recursively (string-append rapmap "/include") include)
12247 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12248 "external/install/include/rapmap/FastxParser.hpp"
12249 "external/install/include/rapmap/concurrentqueue.h"
12250 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12251 "external/install/src/rapmap/FastxParser.cpp"
12252 "external/install/src/rapmap/xxhash.c")))
12254 (add-after 'unpack 'use-system-libraries
12255 (lambda* (#:key inputs #:allow-other-keys)
12256 (substitute* "src/CMakeLists.txt"
12257 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12258 (string-append (assoc-ref inputs "jellyfish")
12259 "/include/jellyfish-" ,(package-version jellyfish)))
12260 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12261 (string-append (assoc-ref inputs "jellyfish")
12262 "/lib/libjellyfish-2.0.a"))
12263 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12264 (string-append (assoc-ref inputs "libdivsufsort")
12265 "/lib/libdivsufsort.so"))
12266 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12267 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12268 "/lib/libstaden-read.a"))
12269 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12270 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12271 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12272 (string-append (assoc-ref inputs "libdivsufsort")
12273 "/lib/libdivsufsort64.so")))
12274 (substitute* "CMakeLists.txt"
12275 ;; Don't prefer static libs
12276 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12277 (("set\\(TBB_LIBRARIES") "message(")
12278 (("find_package\\(Jellyfish.*") "")
12279 (("ExternalProject_Add\\(libcereal") "message(")
12280 (("ExternalProject_Add\\(libbwa") "message(")
12281 (("ExternalProject_Add\\(libjellyfish") "message(")
12282 (("ExternalProject_Add\\(libgff") "message(")
12283 (("ExternalProject_Add\\(libtbb") "message(")
12284 (("ExternalProject_Add\\(libspdlog") "message(")
12285 (("ExternalProject_Add\\(libdivsufsort") "message(")
12286 (("ExternalProject_Add\\(libstadenio") "message(")
12287 (("ExternalProject_Add_Step\\(") "message("))
12289 ;; Ensure that all headers can be found
12290 (setenv "CPLUS_INCLUDE_PATH"
12291 (string-append (getenv "CPLUS_INCLUDE_PATH")
12293 (assoc-ref inputs "bwa")
12296 (assoc-ref inputs "eigen")
12297 "/include/eigen3"))
12299 (string-append (assoc-ref inputs "bwa")
12302 (assoc-ref inputs "eigen")
12303 "/include/eigen3"))
12305 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12306 ;; run. It only exists after the install phase.
12307 (add-after 'unpack 'fix-tests
12309 (substitute* "src/CMakeLists.txt"
12310 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12311 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12315 ("bwa" ,bwa-for-salmon)
12321 (uri (git-reference
12322 (url "https://github.com/COMBINE-lab/RapMap.git")
12323 (commit (string-append "salmon-v" version))))
12324 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12327 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12328 ("jemalloc" ,jemalloc)
12329 ("jellyfish" ,jellyfish)
12332 ("libdivsufsort" ,libdivsufsort)
12333 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12334 ("spdlog-for-salmon" ,spdlog-for-salmon)
12337 (home-page "https://github.com/COMBINE-lab/salmon")
12338 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12339 (description "Salmon is a program to produce highly-accurate,
12340 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12341 its accuracy and speed via a number of different innovations, including the
12342 use of lightweight alignments (accurate but fast-to-compute proxies for
12343 traditional read alignments) and massively-parallel stochastic collapsed
12344 variational inference.")
12345 (license license:gpl3+)))
12347 (define-public python-loompy
12349 (name "python-loompy")
12354 (uri (pypi-uri "loompy" version))
12357 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12358 (build-system python-build-system)
12359 ;; There are no tests
12360 (arguments '(#:tests? #f))
12362 `(("python-h5py" ,python-h5py)
12363 ("python-numpy" ,python-numpy)
12364 ("python-scipy" ,python-scipy)))
12365 (home-page "https://github.com/linnarsson-lab/loompy")
12366 (synopsis "Work with .loom files for single-cell RNA-seq data")
12367 (description "The loom file format is an efficient format for very large
12368 omics datasets, consisting of a main matrix, optional additional layers, a
12369 variable number of row and column annotations. Loom also supports sparse
12370 graphs. This library makes it easy to work with @file{.loom} files for
12371 single-cell RNA-seq data.")
12372 (license license:bsd-3)))
12374 ;; We cannot use the latest commit because it requires Java 9.
12375 (define-public java-forester
12376 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12379 (name "java-forester")
12380 (version (string-append "0-" revision "." (string-take commit 7)))
12383 (uri (git-reference
12384 (url "https://github.com/cmzmasek/forester.git")
12386 (file-name (string-append name "-" version "-checkout"))
12389 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12390 (modules '((guix build utils)))
12393 ;; Delete bundled jars and pre-built classes
12394 (delete-file-recursively "forester/java/resources")
12395 (delete-file-recursively "forester/java/classes")
12396 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12397 ;; Delete bundled applications
12398 (delete-file-recursively "forester_applications")
12400 (build-system ant-build-system)
12402 `(#:tests? #f ; there are none
12404 #:modules ((guix build ant-build-system)
12406 (guix build java-utils)
12410 (modify-phases %standard-phases
12411 (add-after 'unpack 'chdir
12412 (lambda _ (chdir "forester/java") #t))
12413 (add-after 'chdir 'fix-dependencies
12415 (chmod "build.xml" #o664)
12416 (call-with-output-file "build.xml.new"
12420 (with-input-from-file "build.xml"
12421 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12422 `(;; Remove all unjar tags to avoid repacking classes.
12423 (unjar . ,(lambda _ '()))
12424 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12425 (*text* . ,(lambda (_ txt) txt))))
12427 (rename-file "build.xml.new" "build.xml")
12429 ;; FIXME: itext is difficult to package as it depends on a few
12430 ;; unpackaged libraries.
12431 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12433 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12434 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12435 (("pdf_written_to = PdfExporter.*")
12436 "throw new IOException(\"PDF export is not available.\");"))
12438 ;; There is no install target
12439 (replace 'install (install-jars ".")))))
12441 `(("java-commons-codec" ,java-commons-codec)
12442 ("java-openchart2" ,java-openchart2)))
12443 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12444 (synopsis "Phylogenomics libraries for Java")
12445 (description "Forester is a collection of Java libraries for
12446 phylogenomics and evolutionary biology research. It includes support for
12447 reading, writing, and exporting phylogenetic trees.")
12448 (license license:lgpl2.1+))))
12450 (define-public java-forester-1.005
12452 (name "java-forester")
12456 (uri (string-append "http://search.maven.org/remotecontent?"
12457 "filepath=org/biojava/thirdparty/forester/"
12458 version "/forester-" version "-sources.jar"))
12459 (file-name (string-append name "-" version ".jar"))
12462 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12463 (build-system ant-build-system)
12465 `(#:tests? #f ; there are none
12467 #:modules ((guix build ant-build-system)
12469 (guix build java-utils)
12473 (modify-phases %standard-phases
12474 (add-after 'unpack 'fix-dependencies
12475 (lambda* (#:key inputs #:allow-other-keys)
12476 (call-with-output-file "build.xml"
12480 (with-input-from-file "src/build.xml"
12481 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12482 `(;; Remove all unjar tags to avoid repacking classes.
12483 (unjar . ,(lambda _ '()))
12484 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12485 (*text* . ,(lambda (_ txt) txt))))
12487 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12488 "synth_look_and_feel_1.xml")
12489 (copy-file (assoc-ref inputs "phyloxml.xsd")
12491 (substitute* "build.xml"
12492 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12493 "synth_look_and_feel_1.xml")
12494 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12497 ;; FIXME: itext is difficult to package as it depends on a few
12498 ;; unpackaged libraries.
12499 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12501 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12502 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12503 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12504 (("pdf_written_to = PdfExporter.*")
12505 "throw new IOException(\"PDF export is not available.\"); /*")
12506 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12507 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12509 (add-after 'unpack 'delete-pre-built-classes
12510 (lambda _ (delete-file-recursively "src/classes") #t))
12511 ;; There is no install target
12512 (replace 'install (install-jars ".")))))
12514 `(("java-commons-codec" ,java-commons-codec)
12515 ("java-openchart2" ,java-openchart2)))
12516 ;; The source archive does not contain the resources.
12521 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12522 "b61cc2dcede0bede317db362472333115756b8c6/"
12523 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12524 (file-name (string-append name "-phyloxml-" version ".xsd"))
12527 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12528 ("synth_look_and_feel_1.xml"
12531 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12532 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12533 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12534 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12537 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12538 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12539 (synopsis "Phylogenomics libraries for Java")
12540 (description "Forester is a collection of Java libraries for
12541 phylogenomics and evolutionary biology research. It includes support for
12542 reading, writing, and exporting phylogenetic trees.")
12543 (license license:lgpl2.1+)))
12545 (define-public java-biojava-core
12547 (name "java-biojava-core")
12551 (uri (git-reference
12552 (url "https://github.com/biojava/biojava")
12553 (commit (string-append "biojava-" version))))
12554 (file-name (string-append name "-" version "-checkout"))
12557 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12558 (build-system ant-build-system)
12561 #:jar-name "biojava-core.jar"
12562 #:source-dir "biojava-core/src/main/java/"
12563 #:test-dir "biojava-core/src/test"
12564 ;; These tests seem to require internet access.
12565 #:test-exclude (list "**/SearchIOTest.java"
12566 "**/BlastXMLParserTest.java"
12567 "**/GenbankCookbookTest.java"
12568 "**/GenbankProxySequenceReaderTest.java")
12570 (modify-phases %standard-phases
12571 (add-before 'build 'copy-resources
12573 (copy-recursively "biojava-core/src/main/resources"
12576 (add-before 'check 'copy-test-resources
12578 (copy-recursively "biojava-core/src/test/resources"
12579 "build/test-classes")
12582 `(("java-log4j-api" ,java-log4j-api)
12583 ("java-log4j-core" ,java-log4j-core)
12584 ("java-slf4j-api" ,java-slf4j-api)
12585 ("java-slf4j-simple" ,java-slf4j-simple)))
12587 `(("java-junit" ,java-junit)
12588 ("java-hamcrest-core" ,java-hamcrest-core)))
12589 (home-page "http://biojava.org")
12590 (synopsis "Core libraries of Java framework for processing biological data")
12591 (description "BioJava is a project dedicated to providing a Java framework
12592 for processing biological data. It provides analytical and statistical
12593 routines, parsers for common file formats, reference implementations of
12594 popular algorithms, and allows the manipulation of sequences and 3D
12595 structures. The goal of the biojava project is to facilitate rapid
12596 application development for bioinformatics.
12598 This package provides the core libraries.")
12599 (license license:lgpl2.1+)))
12601 (define-public java-biojava-phylo
12602 (package (inherit java-biojava-core)
12603 (name "java-biojava-phylo")
12604 (build-system ant-build-system)
12607 #:jar-name "biojava-phylo.jar"
12608 #:source-dir "biojava-phylo/src/main/java/"
12609 #:test-dir "biojava-phylo/src/test"
12611 (modify-phases %standard-phases
12612 (add-before 'build 'copy-resources
12614 (copy-recursively "biojava-phylo/src/main/resources"
12617 (add-before 'check 'copy-test-resources
12619 (copy-recursively "biojava-phylo/src/test/resources"
12620 "build/test-classes")
12623 `(("java-log4j-api" ,java-log4j-api)
12624 ("java-log4j-core" ,java-log4j-core)
12625 ("java-slf4j-api" ,java-slf4j-api)
12626 ("java-slf4j-simple" ,java-slf4j-simple)
12627 ("java-biojava-core" ,java-biojava-core)
12628 ("java-forester" ,java-forester)))
12630 `(("java-junit" ,java-junit)
12631 ("java-hamcrest-core" ,java-hamcrest-core)))
12632 (home-page "http://biojava.org")
12633 (synopsis "Biojava interface to the forester phylogenomics library")
12634 (description "The phylo module provides a biojava interface layer to the
12635 forester phylogenomics library for constructing phylogenetic trees.")))
12637 (define-public java-biojava-alignment
12638 (package (inherit java-biojava-core)
12639 (name "java-biojava-alignment")
12640 (build-system ant-build-system)
12643 #:jar-name "biojava-alignment.jar"
12644 #:source-dir "biojava-alignment/src/main/java/"
12645 #:test-dir "biojava-alignment/src/test"
12647 (modify-phases %standard-phases
12648 (add-before 'build 'copy-resources
12650 (copy-recursively "biojava-alignment/src/main/resources"
12653 (add-before 'check 'copy-test-resources
12655 (copy-recursively "biojava-alignment/src/test/resources"
12656 "build/test-classes")
12659 `(("java-log4j-api" ,java-log4j-api)
12660 ("java-log4j-core" ,java-log4j-core)
12661 ("java-slf4j-api" ,java-slf4j-api)
12662 ("java-slf4j-simple" ,java-slf4j-simple)
12663 ("java-biojava-core" ,java-biojava-core)
12664 ("java-biojava-phylo" ,java-biojava-phylo)
12665 ("java-forester" ,java-forester)))
12667 `(("java-junit" ,java-junit)
12668 ("java-hamcrest-core" ,java-hamcrest-core)))
12669 (home-page "http://biojava.org")
12670 (synopsis "Biojava API for genetic sequence alignment")
12671 (description "The alignment module of BioJava provides an API that
12675 @item implementations of dynamic programming algorithms for sequence
12677 @item reading and writing of popular alignment file formats;
12678 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12681 (define-public java-biojava-core-4.0
12682 (package (inherit java-biojava-core)
12683 (name "java-biojava-core")
12687 (uri (git-reference
12688 (url "https://github.com/biojava/biojava")
12689 (commit (string-append "biojava-" version))))
12690 (file-name (string-append name "-" version "-checkout"))
12693 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12695 (define-public java-biojava-phylo-4.0
12696 (package (inherit java-biojava-core-4.0)
12697 (name "java-biojava-phylo")
12698 (build-system ant-build-system)
12701 #:jar-name "biojava-phylo.jar"
12702 #:source-dir "biojava-phylo/src/main/java/"
12703 #:test-dir "biojava-phylo/src/test"
12705 (modify-phases %standard-phases
12706 (add-before 'build 'copy-resources
12708 (copy-recursively "biojava-phylo/src/main/resources"
12711 (add-before 'check 'copy-test-resources
12713 (copy-recursively "biojava-phylo/src/test/resources"
12714 "build/test-classes")
12717 `(("java-log4j-api" ,java-log4j-api)
12718 ("java-log4j-core" ,java-log4j-core)
12719 ("java-slf4j-api" ,java-slf4j-api)
12720 ("java-slf4j-simple" ,java-slf4j-simple)
12721 ("java-biojava-core" ,java-biojava-core-4.0)
12722 ("java-forester" ,java-forester-1.005)))
12724 `(("java-junit" ,java-junit)
12725 ("java-hamcrest-core" ,java-hamcrest-core)))
12726 (home-page "http://biojava.org")
12727 (synopsis "Biojava interface to the forester phylogenomics library")
12728 (description "The phylo module provides a biojava interface layer to the
12729 forester phylogenomics library for constructing phylogenetic trees.")))
12731 (define-public java-biojava-alignment-4.0
12732 (package (inherit java-biojava-core-4.0)
12733 (name "java-biojava-alignment")
12734 (build-system ant-build-system)
12737 #:jar-name "biojava-alignment.jar"
12738 #:source-dir "biojava-alignment/src/main/java/"
12739 #:test-dir "biojava-alignment/src/test"
12741 (modify-phases %standard-phases
12742 (add-before 'build 'copy-resources
12744 (copy-recursively "biojava-alignment/src/main/resources"
12747 (add-before 'check 'copy-test-resources
12749 (copy-recursively "biojava-alignment/src/test/resources"
12750 "build/test-classes")
12753 `(("java-log4j-api" ,java-log4j-api)
12754 ("java-log4j-core" ,java-log4j-core)
12755 ("java-slf4j-api" ,java-slf4j-api)
12756 ("java-slf4j-simple" ,java-slf4j-simple)
12757 ("java-biojava-core" ,java-biojava-core-4.0)
12758 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12759 ("java-forester" ,java-forester-1.005)))
12761 `(("java-junit" ,java-junit)
12762 ("java-hamcrest-core" ,java-hamcrest-core)))
12763 (home-page "http://biojava.org")
12764 (synopsis "Biojava API for genetic sequence alignment")
12765 (description "The alignment module of BioJava provides an API that
12769 @item implementations of dynamic programming algorithms for sequence
12771 @item reading and writing of popular alignment file formats;
12772 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12775 (define-public dropseq-tools
12777 (name "dropseq-tools")
12782 (uri "http://mccarrolllab.com/download/1276/")
12783 (file-name (string-append "dropseq-tools-" version ".zip"))
12786 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12787 ;; Delete bundled libraries
12788 (modules '((guix build utils)))
12791 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12792 (delete-file-recursively "3rdParty")
12794 (build-system ant-build-system)
12796 `(#:tests? #f ; test data are not included
12797 #:test-target "test"
12798 #:build-target "all"
12799 #:source-dir "public/src/"
12802 (list (string-append "-Dpicard.executable.dir="
12803 (assoc-ref %build-inputs "java-picard")
12805 #:modules ((ice-9 match)
12808 (guix build java-utils)
12809 (guix build ant-build-system))
12811 (modify-phases %standard-phases
12812 ;; FIXME: fails with "java.io.FileNotFoundException:
12813 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12814 (delete 'generate-jar-indices)
12815 ;; All dependencies must be linked to "lib", because that's where
12816 ;; they will be searched for when the Class-Path property of the
12817 ;; manifest is computed.
12818 (add-after 'unpack 'record-references
12819 (lambda* (#:key inputs #:allow-other-keys)
12820 (mkdir-p "jar/lib")
12821 (let ((dirs (filter-map (match-lambda
12823 (if (and (string-prefix? "java-" name)
12824 (not (string=? name "java-testng")))
12827 (for-each (lambda (jar)
12828 (symlink jar (string-append "jar/lib/" (basename jar))))
12829 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12832 ;; There is no installation target
12834 (lambda* (#:key inputs outputs #:allow-other-keys)
12835 (let* ((out (assoc-ref outputs "out"))
12836 (bin (string-append out "/bin"))
12837 (share (string-append out "/share/java/"))
12838 (lib (string-append share "/lib/"))
12839 (scripts (list "BAMTagHistogram"
12840 "BAMTagofTagCounts"
12841 "BaseDistributionAtReadPosition"
12842 "CollapseBarcodesInPlace"
12843 "CollapseTagWithContext"
12845 "CreateIntervalsFiles"
12846 "DetectBeadSynthesisErrors"
12847 "DigitalExpression"
12848 "Drop-seq_alignment.sh"
12851 "GatherGeneGCLength"
12852 "GatherMolecularBarcodeDistributionByGene"
12853 "GatherReadQualityMetrics"
12856 "SelectCellsByNumTranscripts"
12857 "SingleCellRnaSeqMetricsCollector"
12858 "TagBamWithReadSequenceExtended"
12859 "TagReadWithGeneExon"
12860 "TagReadWithInterval"
12861 "TrimStartingSequence"
12862 "ValidateReference")))
12863 (for-each mkdir-p (list bin share lib))
12864 (install-file "dist/dropseq.jar" share)
12865 (for-each (lambda (script)
12866 (chmod script #o555)
12867 (install-file script bin))
12869 (substitute* (map (lambda (script)
12870 (string-append bin "/" script))
12872 (("^java") (which "java"))
12873 (("jar_deploy_dir=.*")
12874 (string-append "jar_deploy_dir=" share "\n"))))
12876 ;; FIXME: We do this after stripping jars because we don't want it to
12877 ;; copy all these jars and strip them. We only want to install
12878 ;; links. Arguably, this is a problem with the ant-build-system.
12879 (add-after 'strip-jar-timestamps 'install-links
12880 (lambda* (#:key outputs #:allow-other-keys)
12881 (let* ((out (assoc-ref outputs "out"))
12882 (share (string-append out "/share/java/"))
12883 (lib (string-append share "/lib/")))
12884 (for-each (lambda (jar)
12885 (symlink (readlink jar)
12886 (string-append lib (basename jar))))
12887 (find-files "jar/lib" "\\.jar$")))
12890 `(("jdk" ,icedtea-8)
12891 ("java-picard" ,java-picard-2.10.3)
12892 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12893 ("java-commons-math3" ,java-commons-math3)
12894 ("java-commons-jexl2" ,java-commons-jexl-2)
12895 ("java-commons-collections4" ,java-commons-collections4)
12896 ("java-commons-lang2" ,java-commons-lang)
12897 ("java-commons-io" ,java-commons-io)
12898 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12899 ("java-guava" ,java-guava)
12900 ("java-la4j" ,java-la4j)
12901 ("java-biojava-core" ,java-biojava-core-4.0)
12902 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12903 ("java-jdistlib" ,java-jdistlib)
12904 ("java-simple-xml" ,java-simple-xml)
12905 ("java-snakeyaml" ,java-snakeyaml)))
12908 ("java-testng" ,java-testng)))
12909 (home-page "http://mccarrolllab.com/dropseq/")
12910 (synopsis "Tools for Drop-seq analyses")
12911 (description "Drop-seq is a technology to enable biologists to
12912 analyze RNA expression genome-wide in thousands of individual cells at
12913 once. This package provides tools to perform Drop-seq analyses.")
12914 (license license:expat)))
12916 (define-public pigx-rnaseq
12918 (name "pigx-rnaseq")
12922 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12923 "releases/download/v" version
12924 "/pigx_rnaseq-" version ".tar.gz"))
12927 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12928 (build-system gnu-build-system)
12930 `(#:parallel-tests? #f ; not supported
12932 (modify-phases %standard-phases
12933 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12934 (add-after 'unpack 'disable-resource-intensive-test
12936 (substitute* "Makefile.in"
12937 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12938 (("^ tests/test_multiqc/test.sh") "")
12939 (("^ test.sh") ""))
12943 ("snakemake" ,snakemake)
12945 ("multiqc" ,multiqc)
12947 ("trim-galore" ,trim-galore)
12949 ("samtools" ,samtools)
12950 ("bedtools" ,bedtools)
12951 ("r-minimal" ,r-minimal)
12952 ("r-rmarkdown" ,r-rmarkdown)
12953 ("r-ggplot2" ,r-ggplot2)
12954 ("r-ggrepel" ,r-ggrepel)
12955 ("r-gprofiler" ,r-gprofiler)
12956 ("r-deseq2" ,r-deseq2)
12958 ("r-knitr" ,r-knitr)
12959 ("r-pheatmap" ,r-pheatmap)
12960 ("r-corrplot" ,r-corrplot)
12961 ("r-reshape2" ,r-reshape2)
12962 ("r-plotly" ,r-plotly)
12963 ("r-scales" ,r-scales)
12964 ("r-summarizedexperiment" ,r-summarizedexperiment)
12965 ("r-crosstalk" ,r-crosstalk)
12966 ("r-tximport" ,r-tximport)
12967 ("r-rtracklayer" ,r-rtracklayer)
12968 ("r-rjson" ,r-rjson)
12970 ("ghc-pandoc" ,ghc-pandoc)
12971 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12972 ("python-wrapper" ,python-wrapper)
12973 ("python-pyyaml" ,python-pyyaml)))
12974 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12975 (synopsis "Analysis pipeline for RNA sequencing experiments")
12976 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12977 reporting for RNA sequencing experiments. It is easy to use and produces high
12978 quality reports. The inputs are reads files from the sequencing experiment,
12979 and a configuration file which describes the experiment. In addition to
12980 quality control of the experiment, the pipeline produces a differential
12981 expression report comparing samples in an easily configurable manner.")
12982 (license license:gpl3+)))
12984 (define-public pigx-chipseq
12986 (name "pigx-chipseq")
12990 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12991 "releases/download/v" version
12992 "/pigx_chipseq-" version ".tar.gz"))
12995 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
12996 (build-system gnu-build-system)
12997 ;; parts of the tests rely on access to the network
12998 (arguments '(#:tests? #f))
13001 ("coreutils" ,coreutils)
13002 ("r-minimal" ,r-minimal)
13003 ("r-argparser" ,r-argparser)
13004 ("r-biocparallel" ,r-biocparallel)
13005 ("r-biostrings" ,r-biostrings)
13006 ("r-chipseq" ,r-chipseq)
13007 ("r-data-table" ,r-data-table)
13008 ("r-dplyr" ,r-dplyr)
13009 ("r-genomation" ,r-genomation)
13010 ("r-genomicalignments" ,r-genomicalignments)
13011 ("r-genomicranges" ,r-genomicranges)
13012 ("r-rsamtools" ,r-rsamtools)
13013 ("r-rtracklayer" ,r-rtracklayer)
13014 ("r-s4vectors" ,r-s4vectors)
13015 ("r-stringr" ,r-stringr)
13016 ("r-tibble" ,r-tibble)
13017 ("r-tidyr" ,r-tidyr)
13018 ("r-jsonlite" ,r-jsonlite)
13019 ("r-heatmaply" ,r-heatmaply)
13020 ("r-htmlwidgets" ,r-htmlwidgets)
13021 ("r-ggplot2" ,r-ggplot2)
13022 ("r-plotly" ,r-plotly)
13023 ("r-rmarkdown" ,r-rmarkdown)
13024 ("python-wrapper" ,python-wrapper)
13025 ("python-pyyaml" ,python-pyyaml)
13026 ("python-magic" ,python-magic)
13027 ("python-xlrd" ,python-xlrd)
13028 ("trim-galore" ,trim-galore)
13030 ("multiqc" ,multiqc)
13032 ("ghc-pandoc" ,ghc-pandoc)
13033 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13037 ("snakemake" ,snakemake)
13038 ("samtools" ,samtools)
13039 ("bedtools" ,bedtools)
13040 ("kentutils" ,kentutils)))
13042 `(("python-pytest" ,python-pytest)))
13043 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13044 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13045 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13046 calling and reporting for ChIP sequencing experiments. It is easy to use and
13047 produces high quality reports. The inputs are reads files from the sequencing
13048 experiment, and a configuration file which describes the experiment. In
13049 addition to quality control of the experiment, the pipeline enables to set up
13050 multiple peak calling analysis and allows the generation of a UCSC track hub
13051 in an easily configurable manner.")
13052 (license license:gpl3+)))
13054 (define-public pigx-bsseq
13056 (name "pigx-bsseq")
13060 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13061 "releases/download/v" version
13062 "/pigx_bsseq-" version ".tar.gz"))
13065 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13066 (build-system gnu-build-system)
13069 (modify-phases %standard-phases
13070 (add-before 'check 'set-timezone
13071 ;; The readr package is picky about timezones.
13072 (lambda* (#:key inputs #:allow-other-keys)
13073 (setenv "TZ" "UTC+1")
13075 (string-append (assoc-ref inputs "tzdata")
13076 "/share/zoneinfo"))
13079 `(("tzdata" ,tzdata)))
13081 `(("coreutils" ,coreutils)
13084 ("r-minimal" ,r-minimal)
13085 ("r-annotationhub" ,r-annotationhub)
13087 ("r-genomation" ,r-genomation)
13088 ("r-methylkit" ,r-methylkit)
13089 ("r-rtracklayer" ,r-rtracklayer)
13090 ("r-rmarkdown" ,r-rmarkdown)
13091 ("r-bookdown" ,r-bookdown)
13092 ("r-ggplot2" ,r-ggplot2)
13093 ("r-ggbio" ,r-ggbio)
13094 ("ghc-pandoc" ,ghc-pandoc)
13095 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13096 ("python-wrapper" ,python-wrapper)
13097 ("python-pyyaml" ,python-pyyaml)
13098 ("snakemake" ,snakemake)
13099 ("bismark" ,bismark)
13102 ("trim-galore" ,trim-galore)
13103 ("cutadapt" ,cutadapt)
13104 ("samtools" ,samtools)))
13105 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13106 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13107 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13108 data of bisulfite experiments; it produces reports on aggregate methylation
13109 and coverage and can be used to produce information on differential
13110 methylation and segmentation.")
13111 (license license:gpl3+)))
13113 (define-public pigx-scrnaseq
13115 (name "pigx-scrnaseq")
13119 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13120 "releases/download/v" version
13121 "/pigx_scrnaseq-" version ".tar.gz"))
13124 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13125 (build-system gnu-build-system)
13127 `(#:configure-flags
13128 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13129 "/share/java/picard.jar")
13130 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13131 "/share/java/dropseq.jar"))))
13133 `(("coreutils" ,coreutils)
13135 ("dropseq-tools" ,dropseq-tools)
13137 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13138 ("java" ,icedtea-8)
13139 ("python-wrapper" ,python-wrapper)
13140 ("python-pyyaml" ,python-pyyaml)
13141 ("python-pandas" ,python-pandas)
13142 ("python-magic" ,python-magic)
13143 ("python-numpy" ,python-numpy)
13144 ("python-loompy" ,python-loompy)
13145 ("ghc-pandoc" ,ghc-pandoc)
13146 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13147 ("samtools" ,samtools)
13148 ("snakemake" ,snakemake)
13150 ("r-minimal" ,r-minimal)
13151 ("r-argparser" ,r-argparser)
13152 ("r-cowplot" ,r-cowplot)
13153 ("r-data-table" ,r-data-table)
13154 ("r-delayedarray" ,r-delayedarray)
13155 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13156 ("r-dplyr" ,r-dplyr)
13157 ("r-dropbead" ,r-dropbead)
13159 ("r-genomicalignments" ,r-genomicalignments)
13160 ("r-genomicfiles" ,r-genomicfiles)
13161 ("r-genomicranges" ,r-genomicranges)
13162 ("r-ggplot2" ,r-ggplot2)
13163 ("r-hdf5array" ,r-hdf5array)
13164 ("r-pheatmap" ,r-pheatmap)
13165 ("r-rmarkdown" ,r-rmarkdown)
13166 ("r-rsamtools" ,r-rsamtools)
13167 ("r-rtracklayer" ,r-rtracklayer)
13168 ("r-rtsne" ,r-rtsne)
13169 ("r-scater" ,r-scater)
13170 ("r-scran" ,r-scran)
13171 ("r-singlecellexperiment" ,r-singlecellexperiment)
13172 ("r-stringr" ,r-stringr)
13173 ("r-yaml" ,r-yaml)))
13174 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13175 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13176 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13177 quality control for single cell RNA sequencing experiments. The inputs are
13178 read files from the sequencing experiment, and a configuration file which
13179 describes the experiment. It produces processed files for downstream analysis
13180 and interactive quality reports. The pipeline is designed to work with UMI
13182 (license license:gpl3+)))
13184 (define-public pigx
13190 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13191 "releases/download/v" version
13192 "/pigx-" version ".tar.gz"))
13195 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13196 (build-system gnu-build-system)
13198 `(("python" ,python)
13199 ("pigx-bsseq" ,pigx-bsseq)
13200 ("pigx-chipseq" ,pigx-chipseq)
13201 ("pigx-rnaseq" ,pigx-rnaseq)
13202 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13203 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13204 (synopsis "Analysis pipelines for genomics")
13205 (description "PiGx is a collection of genomics pipelines. It includes the
13206 following pipelines:
13209 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13210 @item PiGx RNAseq for RNAseq samples
13211 @item PiGx scRNAseq for single cell dropseq analysis
13212 @item PiGx ChIPseq for reads from ChIPseq experiments
13215 All pipelines are easily configured with a simple sample sheet and a
13216 descriptive settings file. The result is a set of comprehensive, interactive
13217 HTML reports with interesting findings about your samples.")
13218 (license license:gpl3+)))
13220 (define-public mantis
13221 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13225 (version (git-version "0" revision commit))
13228 (uri (git-reference
13229 (url "https://github.com/splatlab/mantis.git")
13231 (file-name (git-file-name name version))
13234 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13235 (build-system cmake-build-system)
13236 (arguments '(#:tests? #f)) ; there are none
13238 `(("sdsl-lite" ,sdsl-lite)
13239 ("openssl" ,openssl)
13241 (home-page "https://github.com/splatlab/mantis")
13242 (synopsis "Large-scale sequence-search index data structure")
13243 (description "Mantis is a space-efficient data structure that can be
13244 used to index thousands of raw-read genomics experiments and facilitate
13245 large-scale sequence searches on those experiments. Mantis uses counting
13246 quotient filters instead of Bloom filters, enabling rapid index builds and
13247 queries, small indexes, and exact results, i.e., no false positives or
13248 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13249 representation, so it supports fast graph traversal and other topological
13250 analyses in addition to large-scale sequence-level searches.")
13251 ;; uses __uint128_t and inline assembly
13252 (supported-systems '("x86_64-linux"))
13253 (license license:bsd-3))))
13255 (define-public r-diversitree
13257 (name "r-diversitree")
13262 (uri (cran-uri "diversitree" version))
13265 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13266 (build-system r-build-system)
13268 `(("gfortran" ,gfortran)))
13269 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13272 ("r-desolve" ,r-desolve)
13274 ("r-suplex" ,r-subplex)))
13275 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13276 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13277 (description "This package contains a number of comparative \"phylogenetic\"
13278 methods, mostly focusing on analysing diversification and character evolution.
13279 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13280 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13281 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13282 include Markov models of discrete and continuous trait evolution and constant
13283 rate speciation and extinction.")
13284 (license license:gpl2+)))
13286 (define-public sjcount
13287 ;; There is no tag for version 3.2, nor is there a release archive.
13288 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13292 (version (git-version "3.2" revision commit))
13295 (uri (git-reference
13296 (url "https://github.com/pervouchine/sjcount-full.git")
13298 (file-name (string-append name "-" version "-checkout"))
13301 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13302 (build-system gnu-build-system)
13304 `(#:tests? #f ; requires a 1.4G test file
13306 (list (string-append "SAMTOOLS_DIR="
13307 (assoc-ref %build-inputs "samtools")
13310 (modify-phases %standard-phases
13311 (replace 'configure
13312 (lambda* (#:key inputs #:allow-other-keys)
13313 (substitute* "makefile"
13314 (("-I \\$\\{SAMTOOLS_DIR\\}")
13315 (string-append "-I" (assoc-ref inputs "samtools")
13316 "/include/samtools"))
13317 (("-lz ") "-lz -lpthread "))
13320 (lambda* (#:key outputs #:allow-other-keys)
13321 (for-each (lambda (tool)
13323 (string-append (assoc-ref outputs "out")
13325 '("j_count" "b_count" "sjcount"))
13328 `(("samtools" ,samtools-0.1)
13330 (home-page "https://github.com/pervouchine/sjcount-full/")
13331 (synopsis "Annotation-agnostic splice junction counting pipeline")
13332 (description "Sjcount is a utility for fast quantification of splice
13333 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13334 version does count multisplits.")
13335 (license license:gpl3+))))
13337 (define-public minimap2
13344 (uri (string-append "https://github.com/lh3/minimap2/"
13345 "releases/download/v" version "/"
13346 "minimap2-" version ".tar.bz2"))
13349 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13350 (build-system gnu-build-system)
13352 `(#:tests? #f ; there are none
13355 (let ((system ,(or (%current-target-system)
13356 (%current-system))))
13358 ((string-prefix? "x86_64" system)
13360 ((or (string-prefix? "armhf" system)
13361 (string-prefix? "aarch64" system))
13363 (_ "sse2only=1"))))
13365 (modify-phases %standard-phases
13366 (delete 'configure)
13368 (lambda* (#:key outputs #:allow-other-keys)
13369 (let* ((out (assoc-ref outputs "out"))
13370 (bin (string-append out "/bin"))
13371 (man (string-append out "/share/man/man1")))
13372 (install-file "minimap2" bin)
13374 (install-file "minimap2.1" man))
13378 (home-page "https://lh3.github.io/minimap2/")
13379 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13380 (description "Minimap2 is a versatile sequence alignment program that
13381 aligns DNA or mRNA sequences against a large reference database. Typical use
13385 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13386 @item finding overlaps between long reads with error rate up to ~15%;
13387 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13388 reads against a reference genome;
13389 @item aligning Illumina single- or paired-end reads;
13390 @item assembly-to-assembly alignment;
13391 @item full-genome alignment between two closely related species with
13392 divergence below ~15%.
13394 (license license:expat)))
13396 (define-public r-circus
13403 (uri (git-reference
13404 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13405 (commit (string-append "v" version))))
13406 (file-name (git-file-name name version))
13409 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13410 (build-system r-build-system)
13412 `(("r-annotationdbi" ,r-annotationdbi)
13413 ("r-annotationhub" ,r-annotationhub)
13414 ("r-biomart" ,r-biomart)
13415 ("r-data-table" ,r-data-table)
13417 ("r-genomicfeatures" ,r-genomicfeatures)
13418 ("r-genomicranges" ,r-genomicranges)
13419 ("r-ggplot2" ,r-ggplot2)
13421 ("r-iranges" ,r-iranges)
13422 ("r-rcolorbrewer" ,r-rcolorbrewer)
13423 ("r-rmysql" ,r-rmysql)
13424 ("r-s4vectors" ,r-s4vectors)
13425 ("r-stringr" ,r-stringr)
13426 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13428 `(("r-knitr" ,r-knitr)))
13429 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13430 (synopsis "Annotation, analysis and visualization of circRNA data")
13431 (description "Circus is an R package for annotation, analysis and
13432 visualization of circRNA data. Users can annotate their circRNA candidates
13433 with host genes, gene featrues they are spliced from, and discriminate between
13434 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13435 can be calculated, and a number of descriptive plots easily generated.")
13436 (license license:artistic2.0)))
13438 (define-public r-loomr
13439 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13443 (version (git-version "0.2.0" revision commit))
13447 (uri (git-reference
13448 (url "https://github.com/mojaveazure/loomR.git")
13450 (file-name (git-file-name name version))
13453 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13454 (build-system r-build-system)
13457 ("r-hdf5r" ,r-hdf5r)
13458 ("r-iterators" ,r-iterators)
13459 ("r-itertools" ,r-itertools)
13460 ("r-matrix" ,r-matrix)))
13461 (home-page "https://github.com/mojaveazure/loomR")
13462 (synopsis "R interface for loom files")
13463 (description "This package provides an R interface to access, create,
13464 and modify loom files. loomR aims to be completely compatible with loompy.")
13465 (license license:gpl3))))
13467 (define-public gffread
13468 ;; We cannot use the tagged release because it is not in sync with gclib.
13469 ;; See https://github.com/gpertea/gffread/issues/26
13470 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13474 (version (git-version "0.9.12" revision commit))
13478 (uri (git-reference
13479 (url "https://github.com/gpertea/gffread.git")
13481 (file-name (git-file-name name version))
13484 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13485 (build-system gnu-build-system)
13487 `(#:tests? #f ; no check target
13489 (list "GCLDIR=gclib")
13491 (modify-phases %standard-phases
13492 (delete 'configure)
13493 (add-after 'unpack 'copy-gclib-source
13494 (lambda* (#:key inputs #:allow-other-keys)
13496 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13498 ;; There is no install target
13500 (lambda* (#:key outputs #:allow-other-keys)
13501 (let* ((out (assoc-ref outputs "out"))
13502 (bin (string-append out "/bin")))
13503 (install-file "gffread" bin))
13507 ,(let ((version "0.10.3")
13508 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13512 (uri (git-reference
13513 (url "https://github.com/gpertea/gclib.git")
13515 (file-name (git-file-name "gclib" version))
13518 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13519 (home-page "https://github.com/gpertea/gffread/")
13520 (synopsis "Parse and convert GFF/GTF files")
13522 "This package provides a GFF/GTF file parsing utility providing format
13523 conversions, region filtering, FASTA sequence extraction and more.")
13524 ;; gffread is under Expat, but gclib is under Artistic 2.0
13525 (license (list license:expat
13526 license:artistic2.0)))))
13528 (define-public find-circ
13529 ;; The last release was in 2015. The license was clarified in 2017, so we
13530 ;; take the latest commit.
13531 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13535 (version (git-version "1.2" revision commit))
13539 (uri (git-reference
13540 (url "https://github.com/marvin-jens/find_circ.git")
13542 (file-name (git-file-name name version))
13545 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13546 (build-system gnu-build-system)
13548 `(#:tests? #f ; there are none
13550 ;; There is no actual build system.
13551 (modify-phases %standard-phases
13552 (delete 'configure)
13555 (lambda* (#:key outputs #:allow-other-keys)
13556 (let* ((out (assoc-ref outputs "out"))
13557 (bin (string-append out "/bin"))
13558 (path (getenv "PYTHONPATH")))
13559 (for-each (lambda (script)
13560 (install-file script bin)
13561 (wrap-program (string-append bin "/" script)
13562 `("PYTHONPATH" ":" prefix (,path))))
13567 "unmapped2anchors.py")))
13570 `(("python2" ,python-2)
13571 ("python2-pysam" ,python2-pysam)
13572 ("python2-numpy" ,python2-numpy)))
13573 (home-page "https://github.com/marvin-jens/find_circ")
13574 (synopsis "circRNA detection from RNA-seq reads")
13575 (description "This package provides tools to detect head-to-tail
13576 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13578 (license license:gpl3))))
13580 (define-public python-scanpy
13582 (name "python-scanpy")
13587 (uri (pypi-uri "scanpy" version))
13590 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13591 (build-system python-build-system)
13593 `(("python-anndata" ,python-anndata)
13594 ("python-igraph" ,python-igraph)
13595 ("python-numba" ,python-numba)
13596 ("python-joblib" ,python-joblib)
13597 ("python-natsort" ,python-natsort)
13598 ("python-networkx" ,python-networkx)
13599 ("python-statsmodels" ,python-statsmodels)
13600 ("python-scikit-learn" ,python-scikit-learn)
13601 ("python-matplotlib" ,python-matplotlib)
13602 ("python-pandas" ,python-pandas)
13603 ("python-scipy" ,python-scipy)
13604 ("python-seaborn" ,python-seaborn)
13605 ("python-h5py" ,python-h5py)
13606 ("python-tables" ,python-tables)))
13607 (home-page "http://github.com/theislab/scanpy")
13608 (synopsis "Single-Cell Analysis in Python.")
13609 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13610 expression data. It includes preprocessing, visualization, clustering,
13611 pseudotime and trajectory inference and differential expression testing. The
13612 Python-based implementation efficiently deals with datasets of more than one
13614 (license license:bsd-3)))
13616 (define-public gffcompare
13617 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13620 (name "gffcompare")
13621 (version (git-version "0.10.15" revision commit))
13625 (uri (git-reference
13626 (url "https://github.com/gpertea/gffcompare/")
13628 (file-name (git-file-name name version))
13630 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13631 (build-system gnu-build-system)
13633 `(#:tests? #f ; no check target
13635 (modify-phases %standard-phases
13636 (delete 'configure)
13637 (add-before 'build 'copy-gclib-source
13638 (lambda* (#:key inputs #:allow-other-keys)
13641 (assoc-ref inputs "gclib-source") "../gclib")
13644 (lambda* (#:key outputs #:allow-other-keys)
13645 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13646 (install-file "gffcompare" bin)
13649 `(("gclib-source" ; see 'README.md' of gffcompare
13650 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13653 (version (git-version "0.10.3" revision commit)))
13656 (uri (git-reference
13657 (url "https://github.com/gpertea/gclib/")
13659 (file-name (git-file-name name version))
13661 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13662 (home-page "https://github.com/gpertea/gffcompare/")
13663 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13665 "@code{gffcompare} is a tool that can:
13667 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13668 (Cufflinks, Stringtie);
13669 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13670 resulted from assembly of different samples);
13671 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13672 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13676 license:expat ;license for gffcompare
13677 license:artistic2.0))))) ;license for gclib
13679 (define-public python-intervaltree
13681 (name "python-intervaltree")
13686 (uri (pypi-uri "intervaltree" version))
13689 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13690 (build-system python-build-system)
13691 ;; FIXME: error when collecting tests
13692 (arguments '(#:tests? #f))
13694 `(("python-sortedcontainers" ,python-sortedcontainers)))
13696 `(("python-pytest" ,python-pytest)))
13697 (home-page "https://github.com/chaimleib/intervaltree")
13698 (synopsis "Editable interval tree data structure")
13700 "This package provides a mutable, self-balancing interval tree
13701 implementation for Python. Queries may be by point, by range overlap, or by
13702 range envelopment. This library was designed to allow tagging text and time
13703 intervals, where the intervals include the lower bound but not the upper
13705 (license license:asl2.0)))
13707 (define-public python-pypairix
13709 (name "python-pypairix")
13714 (uri (pypi-uri "pypairix" version))
13717 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13718 (build-system python-build-system)
13719 ;; FIXME: the tests fail because test.support cannot be loaded:
13720 ;; ImportError: cannot import name 'support'
13721 (arguments '(#:tests? #f))
13724 (home-page "https://github.com/4dn-dcic/pairix")
13725 (synopsis "Support for querying pairix-indexed bgzipped text files")
13727 "Pypairix is a Python module for fast querying on a pairix-indexed
13728 bgzipped text file that contains a pair of genomic coordinates per line.")
13729 (license license:expat)))
13731 (define-public python-pyfaidx
13733 (name "python-pyfaidx")
13734 (version "0.5.4.2")
13738 (uri (pypi-uri "pyfaidx" version))
13741 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13742 (build-system python-build-system)
13744 `(("python-setuptools" ,python-setuptools)
13745 ("python-six" ,python-six)))
13746 (home-page "http://mattshirley.com")
13747 (synopsis "Random access to fasta subsequences")
13749 "This package provides procedures for efficient pythonic random access to
13750 fasta subsequences.")
13751 (license license:bsd-3)))
13753 (define-public python-cooler
13755 (name "python-cooler")
13760 (uri (pypi-uri "cooler" version))
13763 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13764 (build-system python-build-system)
13766 `(("python-biopython" ,python-biopython)
13767 ("python-click" ,python-click)
13768 ("python-cytoolz" ,python-cytoolz)
13769 ("python-dask" ,python-dask)
13770 ("python-h5py" ,python-h5py)
13771 ("python-multiprocess" ,python-multiprocess)
13772 ("python-pandas" ,python-pandas)
13773 ("python-pyfaidx" ,python-pyfaidx)
13774 ("python-pypairix" ,python-pypairix)
13775 ("python-pysam" ,python-pysam)
13776 ("python-scipy" ,python-scipy)))
13778 `(("python-mock" ,python-mock)
13779 ("python-nose" ,python-nose)
13780 ("python-numpydoc" ,python-numpydoc)
13781 ("python-sphinx" ,python-sphinx)))
13782 (home-page "https://github.com/mirnylab/cooler")
13783 (synopsis "Sparse binary format for genomic interaction matrices")
13785 "Cooler is a support library for a sparse, compressed, binary persistent
13786 storage format, called @code{cool}, used to store genomic interaction data,
13787 such as Hi-C contact matrices.")
13788 (license license:bsd-3)))
13790 (define-public python-hicexplorer
13792 (name "python-hicexplorer")
13796 ;; The latest version is not available on Pypi.
13798 (uri (git-reference
13799 (url "https://github.com/deeptools/HiCExplorer.git")
13801 (file-name (git-file-name name version))
13804 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13805 (build-system python-build-system)
13808 (modify-phases %standard-phases
13809 (add-after 'unpack 'loosen-up-requirements
13811 (substitute* "setup.py"
13815 `(("python-biopython" ,python-biopython)
13816 ("python-configparser" ,python-configparser)
13817 ("python-cooler" ,python-cooler)
13818 ("python-future" ,python-future)
13819 ("python-intervaltree" ,python-intervaltree)
13820 ("python-jinja2" ,python-jinja2)
13821 ("python-matplotlib" ,python-matplotlib)
13822 ("python-numpy" ,python-numpy)
13823 ("python-pandas" ,python-pandas)
13824 ("python-pybigwig" ,python-pybigwig)
13825 ("python-pysam" ,python-pysam)
13826 ("python-scipy" ,python-scipy)
13827 ("python-six" ,python-six)
13828 ("python-tables" ,python-tables)
13829 ("python-unidecode" ,python-unidecode)))
13830 (home-page "http://hicexplorer.readthedocs.io")
13831 (synopsis "Process, analyze and visualize Hi-C data")
13833 "HiCExplorer is a powerful and easy to use set of tools to process,
13834 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13835 contact matrices, correction of contacts, TAD detection, A/B compartments,
13836 merging, reordering or chromosomes, conversion from different formats
13837 including cooler and detection of long-range contacts. Moreover, it allows
13838 the visualization of multiple contact matrices along with other types of data
13839 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13840 genomic scores), long range contacts and the visualization of viewpoints.")
13841 (license license:gpl3)))
13843 (define-public python-pygenometracks
13845 (name "python-pygenometracks")
13850 (uri (pypi-uri "pyGenomeTracks" version))
13853 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13854 (build-system python-build-system)
13856 `(("python-configparser" ,python-configparser)
13857 ("python-future" ,python-future)
13858 ("python-hicexplorer" ,python-hicexplorer)
13859 ("python-intervaltree" ,python-intervaltree)
13860 ("python-matplotlib" ,python-matplotlib)
13861 ("python-numpy" ,python-numpy)
13862 ("python-pybigwig" ,python-pybigwig)))
13864 `(("python-pytest" ,python-pytest)))
13865 (home-page "https://pygenometracks.readthedocs.io")
13866 (synopsis "Program and library to plot beautiful genome browser tracks")
13868 "This package aims to produce high-quality genome browser tracks that
13869 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13870 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13871 pyGenomeTracks can make plots with or without Hi-C data.")
13872 (license license:gpl3+)))
13874 (define-public python-hic2cool
13876 (name "python-hic2cool")
13881 (uri (pypi-uri "hic2cool" version))
13884 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13885 (build-system python-build-system)
13886 (arguments '(#:tests? #f)) ; no tests included
13888 `(("python-cooler" ,python-cooler)))
13889 (home-page "https://github.com/4dn-dcic/hic2cool")
13890 (synopsis "Converter for .hic and .cool files")
13892 "This package provides a converter between @code{.hic} files (from
13893 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13894 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13896 (license license:expat)))
13898 (define-public r-pore
13906 (string-append "mirror://sourceforge/rpore/" version
13907 "/poRe_" version ".tar.gz"))
13909 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13910 (properties `((upstream-name . "poRe")))
13911 (build-system r-build-system)
13913 `(("r-bit64" ,r-bit64)
13914 ("r-data-table" ,r-data-table)
13915 ("r-rhdf5" ,r-rhdf5)
13916 ("r-shiny" ,r-shiny)
13917 ("r-svdialogs" ,r-svdialogs)))
13918 (home-page "https://sourceforge.net/projects/rpore/")
13919 (synopsis "Visualize Nanopore sequencing data")
13921 "This package provides graphical user interfaces to organize and visualize Nanopore
13923 ;; This is free software but the license variant is unclear:
13924 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13925 (license license:bsd-3)))
13927 (define-public r-xbioc
13928 (let ((revision "1")
13929 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13932 (version (git-version "0.1.15" revision commit))
13935 (uri (git-reference
13936 (url "https://github.com/renozao/xbioc.git")
13938 (file-name (git-file-name name version))
13941 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13942 (build-system r-build-system)
13944 `(("r-annotationdbi" ,r-annotationdbi)
13945 ("r-assertthat" ,r-assertthat)
13946 ("r-biobase" ,r-biobase)
13947 ("r-biocinstaller" ,r-biocinstaller)
13948 ("r-digest" ,r-digest)
13949 ("r-pkgmaker" ,r-pkgmaker)
13951 ("r-reshape2" ,r-reshape2)
13952 ("r-stringr" ,r-stringr)))
13953 (home-page "https://github.com/renozao/xbioc/")
13954 (synopsis "Extra base functions for Bioconductor")
13955 (description "This package provides extra utility functions to perform
13956 common tasks in the analysis of omics data, leveraging and enhancing features
13957 provided by Bioconductor packages.")
13958 (license license:gpl3+))))
13960 (define-public r-cssam
13961 (let ((revision "1")
13962 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13965 (version (git-version "1.4" revision commit))
13968 (uri (git-reference
13969 (url "https://github.com/shenorrLab/csSAM.git")
13971 (file-name (git-file-name name version))
13974 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13975 (build-system r-build-system)
13977 `(("r-formula" ,r-formula)
13978 ("r-ggplot2" ,r-ggplot2)
13979 ("r-pkgmaker" ,r-pkgmaker)
13981 ("r-rngtools" ,r-rngtools)
13982 ("r-scales" ,r-scales)))
13983 (home-page "https://github.com/shenorrLab/csSAM/")
13984 (synopsis "Cell type-specific statistical analysis of microarray")
13985 (description "This package implements the method csSAM that computes
13986 cell-specific differential expression from measured cell proportions using
13989 (license license:lgpl2.1+))))
13991 (define-public r-bseqsc
13992 (let ((revision "1")
13993 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13996 (version (git-version "1.0" revision commit))
13999 (uri (git-reference
14000 (url "https://github.com/shenorrLab/bseqsc.git")
14002 (file-name (git-file-name name version))
14005 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14006 (build-system r-build-system)
14008 `(("r-abind" ,r-abind)
14009 ("r-annotationdbi" ,r-annotationdbi)
14010 ("r-biobase" ,r-biobase)
14011 ("r-cssam" ,r-cssam)
14012 ("r-dplyr" ,r-dplyr)
14013 ("r-e1071" ,r-e1071)
14014 ("r-edger" ,r-edger)
14015 ("r-ggplot2" ,r-ggplot2)
14017 ("r-openxlsx" ,r-openxlsx)
14018 ("r-pkgmaker" ,r-pkgmaker)
14020 ("r-preprocesscore" ,r-preprocesscore)
14021 ("r-rngtools" ,r-rngtools)
14022 ("r-scales" ,r-scales)
14023 ("r-stringr" ,r-stringr)
14024 ("r-xbioc" ,r-xbioc)))
14025 (home-page "https://github.com/shenorrLab/bseqsc")
14026 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14027 (description "BSeq-sc is a bioinformatics analysis pipeline that
14028 leverages single-cell sequencing data to estimate cell type proportion and
14029 cell type-specific gene expression differences from RNA-seq data from bulk
14030 tissue samples. This is a companion package to the publication \"A
14031 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14032 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14033 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14034 (license license:gpl2+))))
14036 (define-public porechop
14037 ;; The recommended way to install is to clone the git repository
14038 ;; https://github.com/rrwick/Porechop#installation
14039 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14043 (version (git-version "0.2.3" revision commit))
14047 (uri (git-reference
14048 (url "https://github.com/rrwick/Porechop.git")
14050 (file-name (git-file-name name version))
14052 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14053 (build-system python-build-system)
14054 (home-page "https://github.com/rrwick/porechop")
14055 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14057 "The porechop package is a tool for finding and removing adapters from Oxford
14058 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14059 has an adapter in its middle, it is treated as chimeric and chopped into
14060 separate reads. Porechop performs thorough alignments to effectively find
14061 adapters, even at low sequence identity. Porechop also supports demultiplexing
14062 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14063 Barcoding Kit or Rapid Barcoding Kit.")
14064 (license license:gpl3+))))
14066 (define-public poretools
14067 ;; The latest release was in 2016 and the latest commit is from 2017
14068 ;; the recommended way to install is to clone the git repository
14069 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14070 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14074 (version (git-version "0.6.0" revision commit))
14078 (uri (git-reference
14079 (url "https://github.com/arq5x/poretools.git")
14081 (file-name (git-file-name name version))
14083 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14084 (build-system python-build-system)
14085 ;; requires python >=2.7, <3.0, and the same for python dependencies
14086 (arguments `(#:python ,python-2))
14090 `(("python-dateutil" ,python2-dateutil)
14091 ("python-h5py" ,python2-h5py)
14092 ("python-matplotlib" ,python2-matplotlib)
14093 ("python-pandas" ,python2-pandas)
14094 ("python-seaborn" ,python2-seaborn)))
14095 (home-page "https://poretools.readthedocs.io")
14096 (synopsis "Toolkit for working with nanopore sequencing data")
14098 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14099 This @code{poretools} package is a flexible toolkit for exploring datasets
14100 generated by nanopore sequencing devices for the purposes of quality control and
14101 downstream analysis. Poretools operates directly on the native FAST5, a variant
14102 of the Hierarchical Data Format (HDF5) standard.")
14103 (license license:expat))))
14105 (define-public r-absfiltergsea
14107 (name "r-absfiltergsea")
14112 (uri (cran-uri "AbsFilterGSEA" version))
14114 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14115 (properties `((upstream-name . "AbsFilterGSEA")))
14116 (build-system r-build-system)
14118 `(("r-biobase" ,r-biobase)
14119 ("r-deseq" ,r-deseq)
14120 ("r-limma" ,r-limma)
14122 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14123 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14124 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14126 "This package provides a function that performs gene-permuting of a gene-set
14127 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14128 Without filtering, users can perform (original) two-tailed or one-tailed
14130 (license license:gpl2)))
14132 (define-public jamm
14135 (version "1.0.7.5")
14139 (uri (git-reference
14140 (url "https://github.com/mahmoudibrahim/JAMM.git")
14141 (commit (string-append "JAMMv" version))))
14142 (file-name (git-file-name name version))
14145 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14146 (build-system gnu-build-system)
14148 `(#:tests? #f ; there are none
14150 (modify-phases %standard-phases
14151 (delete 'configure)
14154 (lambda* (#:key inputs outputs #:allow-other-keys)
14155 (let* ((out (assoc-ref outputs "out"))
14156 (libexec (string-append out "/libexec/jamm"))
14157 (bin (string-append out "/bin")))
14158 (substitute* '("JAMM.sh"
14159 "SignalGenerator.sh")
14161 (string-append "sPath=\"" libexec "\"\n")))
14162 (for-each (lambda (file)
14163 (install-file file libexec))
14164 (list "bincalculator.r"
14176 (chmod script #o555)
14177 (install-file script bin)
14178 (wrap-program (string-append bin "/" script)
14179 `("PATH" ":" prefix
14180 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14181 ,(string-append (assoc-ref inputs "gawk") "/bin")
14182 ,(string-append (assoc-ref inputs "perl") "/bin")
14183 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14184 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14185 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14186 (list "JAMM.sh" "SignalGenerator.sh")))
14190 ("coreutils" ,coreutils)
14193 ("r-minimal" ,r-minimal)
14194 ;;("r-parallel" ,r-parallel)
14195 ("r-signal" ,r-signal)
14196 ("r-mclust" ,r-mclust)))
14197 (home-page "https://github.com/mahmoudibrahim/JAMM")
14198 (synopsis "Peak finder for NGS datasets")
14200 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14201 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14202 boundaries accurately. JAMM is applicable to both broad and narrow
14204 (license license:gpl3+)))
14206 (define-public ngless
14213 (uri (git-reference
14214 (url "https://gitlab.com/ngless/ngless.git")
14215 (commit (string-append "v" version))))
14216 (file-name (git-file-name name version))
14219 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14220 (build-system haskell-build-system)
14222 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14223 ; error: parse error on input import
14224 ; import Options.Applicative
14226 (modify-phases %standard-phases
14227 (add-after 'unpack 'create-cabal-file
14228 (lambda _ (invoke "hpack") #t))
14229 ;; These tools are expected to be installed alongside ngless.
14230 (add-after 'install 'link-tools
14231 (lambda* (#:key inputs outputs #:allow-other-keys)
14232 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14233 (symlink (string-append (assoc-ref inputs "prodigal")
14235 (string-append bin "ngless-" ,version "-prodigal"))
14236 (symlink (string-append (assoc-ref inputs "minimap2")
14238 (string-append bin "ngless-" ,version "-minimap2"))
14239 (symlink (string-append (assoc-ref inputs "samtools")
14241 (string-append bin "ngless-" ,version "-samtools"))
14242 (symlink (string-append (assoc-ref inputs "bwa")
14244 (string-append bin "ngless-" ,version "-bwa"))
14247 `(("prodigal" ,prodigal)
14249 ("samtools" ,samtools)
14250 ("minimap2" ,minimap2)
14251 ("ghc-aeson" ,ghc-aeson)
14252 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14253 ("ghc-async" ,ghc-async)
14254 ("ghc-atomic-write" ,ghc-atomic-write)
14255 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14256 ("ghc-chart" ,ghc-chart)
14257 ("ghc-chart-cairo" ,ghc-chart-cairo)
14258 ("ghc-conduit" ,ghc-conduit)
14259 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14260 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14261 ("ghc-conduit-extra" ,ghc-conduit-extra)
14262 ("ghc-configurator" ,ghc-configurator)
14263 ("ghc-convertible" ,ghc-convertible)
14264 ("ghc-data-default" ,ghc-data-default)
14265 ("ghc-double-conversion" ,ghc-double-conversion)
14266 ("ghc-edit-distance" ,ghc-edit-distance)
14267 ("ghc-either" ,ghc-either)
14268 ("ghc-errors" ,ghc-errors)
14269 ("ghc-extra" ,ghc-extra)
14270 ("ghc-filemanip" ,ghc-filemanip)
14271 ("ghc-file-embed" ,ghc-file-embed)
14272 ("ghc-gitrev" ,ghc-gitrev)
14273 ("ghc-hashtables" ,ghc-hashtables)
14274 ("ghc-http-conduit" ,ghc-http-conduit)
14275 ("ghc-inline-c" ,ghc-inline-c)
14276 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14277 ("ghc-intervalmap" ,ghc-intervalmap)
14278 ("ghc-missingh" ,ghc-missingh)
14279 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14280 ("ghc-parsec" ,ghc-parsec)
14281 ("ghc-regex" ,ghc-regex)
14282 ("ghc-safe" ,ghc-safe)
14283 ("ghc-safeio" ,ghc-safeio)
14284 ("ghc-strict" ,ghc-strict)
14285 ("ghc-tar" ,ghc-tar)
14286 ("ghc-text" ,ghc-text)
14287 ("ghc-unliftio" ,ghc-unliftio)
14288 ("ghc-unliftio-core" ,ghc-unliftio-core)
14289 ("ghc-vector" ,ghc-vector)
14290 ("ghc-yaml" ,ghc-yaml)
14291 ("ghc-zlib" ,ghc-zlib)))
14294 ("r-hdf5r" ,r-hdf5r)
14295 ("r-iterators" ,r-iterators)
14296 ("r-itertools" ,r-itertools)
14297 ("r-matrix" ,r-matrix)))
14299 `(("ghc-hpack" ,ghc-hpack)
14300 ("ghc-quickcheck" ,ghc-quickcheck)
14301 ("ghc-test-framework" ,ghc-test-framework)
14302 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14303 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14304 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14305 (home-page "https://gitlab.com/ngless/ngless")
14306 (synopsis "DSL for processing next-generation sequencing data")
14307 (description "Ngless is a domain-specific language for
14308 @dfn{next-generation sequencing} (NGS) data processing.")
14309 (license license:expat)))
14311 (define-public filtlong
14312 ;; The recommended way to install is to clone the git repository
14313 ;; https://github.com/rrwick/Filtlong#installation
14314 ;; and the lastest release is more than nine months old
14315 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14319 (version (git-version "0.2.0" revision commit))
14323 (uri (git-reference
14324 (url "https://github.com/rrwick/Filtlong.git")
14326 (file-name (git-file-name name version))
14328 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14329 (build-system gnu-build-system)
14331 `(#:tests? #f ; no check target
14333 (modify-phases %standard-phases
14334 (delete 'configure)
14336 (lambda* (#:key outputs #:allow-other-keys)
14337 (let* ((out (assoc-ref outputs "out"))
14338 (bin (string-append out "/bin"))
14339 (scripts (string-append out "/share/filtlong/scripts")))
14340 (install-file "bin/filtlong" bin)
14341 (install-file "scripts/histogram.py" scripts)
14342 (install-file "scripts/read_info_histograms.sh" scripts))
14344 (add-after 'install 'wrap-program
14345 (lambda* (#:key inputs outputs #:allow-other-keys)
14346 (let* ((out (assoc-ref outputs "out"))
14347 (path (getenv "PYTHONPATH")))
14348 (wrap-program (string-append out
14349 "/share/filtlong/scripts/histogram.py")
14350 `("PYTHONPATH" ":" prefix (,path))))
14352 (add-before 'check 'patch-tests
14354 (substitute* "scripts/read_info_histograms.sh"
14355 (("awk") (which "gawk")))
14358 `(("gawk" ,gawk) ;for read_info_histograms.sh
14359 ("python" ,python-2) ;required for histogram.py
14361 (home-page "https://github.com/rrwick/Filtlong/")
14362 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14364 "The Filtlong package is a tool for filtering long reads by quality.
14365 It can take a set of long reads and produce a smaller, better subset. It uses
14366 both read length (longer is better) and read identity (higher is better) when
14367 choosing which reads pass the filter.")
14368 (license (list license:gpl3 ;filtlong
14369 license:asl2.0))))) ;histogram.py
14371 (define-public nanopolish
14372 ;; The recommended way to install is to clone the git repository
14373 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14374 ;; Also, the differences between release and current version seem to be
14376 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14379 (name "nanopolish")
14380 (version (git-version "0.10.2" revision commit))
14384 (uri (git-reference
14385 (url "https://github.com/jts/nanopolish.git")
14388 (file-name (git-file-name name version))
14390 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14391 (build-system gnu-build-system)
14394 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14395 #:tests? #f ; no check target
14397 (modify-phases %standard-phases
14398 (add-after 'unpack 'find-eigen
14399 (lambda* (#:key inputs #:allow-other-keys)
14401 (string-append (assoc-ref inputs "eigen")
14402 "/include/eigen3"))
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/nanopolish/scripts")))
14411 (install-file "nanopolish" bin)
14412 (for-each (lambda (file) (install-file file scripts))
14413 (find-files "scripts" ".*"))
14415 (add-after 'install 'wrap-programs
14416 (lambda* (#:key outputs #:allow-other-keys)
14417 (for-each (lambda (file)
14418 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14419 (find-files "/share/nanopolish/scripts" "\\.py"))
14420 (for-each (lambda (file)
14421 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14422 (find-files "/share/nanopolish/scripts" "\\.pl"))
14430 ("python-biopython" ,python-biopython)
14431 ("python-numpy" ,python-numpy)
14432 ("python-pysam" ,python-pysam)
14433 ("python-scikit-learn" , python-scikit-learn)
14434 ("python-scipy" ,python-scipy)
14436 (home-page "https://github.com/jts/nanopolish")
14437 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14439 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14440 Nanopolish can calculate an improved consensus sequence for a draft genome
14441 assembly, detect base modifications, call SNPs (Single nucleotide
14442 polymorphisms) and indels with respect to a reference genome and more.")
14443 (license license:expat))))